diff options
Diffstat (limited to 'net/core/dev.c')
| -rw-r--r-- | net/core/dev.c | 1340 |
1 files changed, 658 insertions, 682 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 6666b28b6815..304f2deae5f9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1,5 +1,5 @@ /* - * NET3 Protocol independent device support routines. + * NET3 Protocol independent device support routines. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -7,7 +7,7 @@ * 2 of the License, or (at your option) any later version. * * Derived from the non IP parts of dev.c 1.0.19 - * Authors: Ross Biro + * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * @@ -21,9 +21,9 @@ * * Changes: * D.J. Barrow : Fixed bug where dev->refcnt gets set - * to 2 if register_netdev gets called - * before net_dev_init & also removed a - * few lines of code in the process. + * to 2 if register_netdev gets called + * before net_dev_init & also removed a + * few lines of code in the process. * Alan Cox : device private ioctl copies fields back. * Alan Cox : Transmit queue code does relevant * stunts to keep the queue safe. @@ -36,7 +36,7 @@ * Alan Cox : 100 backlog just doesn't cut it when * you start doing multicast video 8) * Alan Cox : Rewrote net_bh and list manager. - * Alan Cox : Fix ETH_P_ALL echoback lengths. + * Alan Cox : Fix ETH_P_ALL echoback lengths. * Alan Cox : Took out transmit every packet pass * Saved a few bytes in the ioctl handler * Alan Cox : Network driver sets packet type before @@ -46,7 +46,7 @@ * Richard Kooijman: Timestamp fixes. * Alan Cox : Wrong field in SIOCGIFDSTADDR * Alan Cox : Device lock protection. - * Alan Cox : Fixed nasty side effect of device close + * Alan Cox : Fixed nasty side effect of device close * changes. * Rudi Cilibrasi : Pass the right thing to * set_mac_address() @@ -67,12 +67,12 @@ * Paul Rusty Russell : SIOCSIFNAME * Pekka Riikonen : Netdev boot-time settings code * Andrew Morton : Make unregister_netdevice wait - * indefinitely on dev->refcnt - * J Hadi Salim : - Backlog queue sampling + * indefinitely on dev->refcnt + * J Hadi Salim : - Backlog queue sampling * - netif_rx() feedback */ -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/cpu.h> @@ -139,7 +139,6 @@ #include <linux/errqueue.h> #include <linux/hrtimer.h> #include <linux/netfilter_ingress.h> -#include <linux/sctp.h> #include <linux/crash_dump.h> #include "net-sysfs.h" @@ -193,7 +192,8 @@ static seqcount_t devnet_rename_seq; static inline void dev_base_seq_inc(struct net *net) { - while (++net->dev_base_seq == 0); + while (++net->dev_base_seq == 0) + ; } static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) @@ -275,8 +275,8 @@ EXPORT_PER_CPU_SYMBOL(softnet_data); * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type */ -static const unsigned short netdev_lock_type[] = - {ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, +static const unsigned short netdev_lock_type[] = { + ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, @@ -292,22 +292,22 @@ static const unsigned short netdev_lock_type[] = ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; -static const char *const netdev_lock_name[] = - {"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", - "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", - "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", - "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", - "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", - "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", - "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", - "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", - "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", - "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", - "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", - "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", - "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", - "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", - "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; +static const char *const netdev_lock_name[] = { + "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", + "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", + "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", + "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", + "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", + "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", + "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", + "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", + "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", + "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", + "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", + "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", + "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", + "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", + "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; @@ -353,10 +353,11 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) #endif /******************************************************************************* + * + * Protocol management and registration routines + * + *******************************************************************************/ - Protocol management and registration routines - -*******************************************************************************/ /* * Add a protocol ID to the list. Now that the input handler is @@ -539,10 +540,10 @@ void dev_remove_offload(struct packet_offload *po) EXPORT_SYMBOL(dev_remove_offload); /****************************************************************************** - - Device Boot-time Settings Routines - -*******************************************************************************/ + * + * Device Boot-time Settings Routines + * + ******************************************************************************/ /* Boot time configuration table */ static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX]; @@ -575,13 +576,13 @@ static int netdev_boot_setup_add(char *name, struct ifmap *map) } /** - * netdev_boot_setup_check - check boot time settings - * @dev: the netdevice + * netdev_boot_setup_check - check boot time settings + * @dev: the netdevice * - * Check boot time settings for the device. - * The found settings are set for the device to be used - * later in the device probing. - * Returns 0 if no settings found, 1 if they are. + * Check boot time settings for the device. + * The found settings are set for the device to be used + * later in the device probing. + * Returns 0 if no settings found, 1 if they are. */ int netdev_boot_setup_check(struct net_device *dev) { @@ -591,10 +592,10 @@ int netdev_boot_setup_check(struct net_device *dev) for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { if (s[i].name[0] != '\0' && s[i].name[0] != ' ' && !strcmp(dev->name, s[i].name)) { - dev->irq = s[i].map.irq; - dev->base_addr = s[i].map.base_addr; - dev->mem_start = s[i].map.mem_start; - dev->mem_end = s[i].map.mem_end; + dev->irq = s[i].map.irq; + dev->base_addr = s[i].map.base_addr; + dev->mem_start = s[i].map.mem_start; + dev->mem_end = s[i].map.mem_end; return 1; } } @@ -604,14 +605,14 @@ EXPORT_SYMBOL(netdev_boot_setup_check); /** - * netdev_boot_base - get address from boot time settings - * @prefix: prefix for network device - * @unit: id for network device + * netdev_boot_base - get address from boot time settings + * @prefix: prefix for network device + * @unit: id for network device * - * Check boot time settings for the base address of device. - * The found settings are set for the device to be used - * later in the device probing. - * Returns 0 if no settings found. + * Check boot time settings for the base address of device. + * The found settings are set for the device to be used + * later in the device probing. + * Returns 0 if no settings found. */ unsigned long netdev_boot_base(const char *prefix, int unit) { @@ -664,10 +665,10 @@ int __init netdev_boot_setup(char *str) __setup("netdev=", netdev_boot_setup); /******************************************************************************* - - Device Interface Subroutines - -*******************************************************************************/ + * + * Device Interface Subroutines + * + *******************************************************************************/ /** * dev_get_iflink - get 'iflink' value of a interface @@ -738,15 +739,15 @@ struct net_device *__dev_get_by_name(struct net *net, const char *name) EXPORT_SYMBOL(__dev_get_by_name); /** - * dev_get_by_name_rcu - find a device by its name - * @net: the applicable net namespace - * @name: name to find + * dev_get_by_name_rcu - find a device by its name + * @net: the applicable net namespace + * @name: name to find * - * Find an interface by name. - * If the name is found a pointer to the device is returned. - * If the name is not found then %NULL is returned. - * The reference counters are not incremented so the caller must be - * careful with locks. The caller must hold RCU lock. + * Find an interface by name. + * If the name is found a pointer to the device is returned. + * If the name is not found then %NULL is returned. + * The reference counters are not incremented so the caller must be + * careful with locks. The caller must hold RCU lock. */ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) @@ -1290,8 +1291,8 @@ void netdev_state_change(struct net_device *dev) EXPORT_SYMBOL(netdev_state_change); /** - * netdev_notify_peers - notify network peers about existence of @dev - * @dev: network device + * netdev_notify_peers - notify network peers about existence of @dev + * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when @@ -1519,17 +1520,17 @@ static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, static int dev_boot_phase = 1; /** - * register_netdevice_notifier - register a network notifier block - * @nb: notifier + * register_netdevice_notifier - register a network notifier block + * @nb: notifier * - * Register a notifier to be called when network device events occur. - * The notifier passed is linked into the kernel structures and must - * not be reused until it has been unregistered. A negative errno code - * is returned on a failure. + * Register a notifier to be called when network device events occur. + * The notifier passed is linked into the kernel structures and must + * not be reused until it has been unregistered. A negative errno code + * is returned on a failure. * - * When registered all registration and up events are replayed - * to the new notifier to allow device to have a race free - * view of the network device list. + * When registered all registration and up events are replayed + * to the new notifier to allow device to have a race free + * view of the network device list. */ int register_netdevice_notifier(struct notifier_block *nb) @@ -1586,17 +1587,17 @@ outroll: EXPORT_SYMBOL(register_netdevice_notifier); /** - * unregister_netdevice_notifier - unregister a network notifier block - * @nb: notifier + * unregister_netdevice_notifier - unregister a network notifier block + * @nb: notifier * - * Unregister a notifier previously registered by - * register_netdevice_notifier(). The notifier is unlinked into the - * kernel structures and may then be reused. A negative errno code - * is returned on a failure. + * Unregister a notifier previously registered by + * register_netdevice_notifier(). The notifier is unlinked into the + * kernel structures and may then be reused. A negative errno code + * is returned on a failure. * - * After unregistering unregister and down device events are synthesized - * for all devices on the device list to the removed notifier to remove - * the need for special case cleanup code. + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) @@ -1696,24 +1697,19 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue); static struct static_key netstamp_needed __read_mostly; #ifdef HAVE_JUMP_LABEL -/* We are not allowed to call static_key_slow_dec() from irq context - * If net_disable_timestamp() is called from irq context, defer the - * static_key_slow_dec() calls. - */ static atomic_t netstamp_needed_deferred; -#endif - -void net_enable_timestamp(void) +static void netstamp_clear(struct work_struct *work) { -#ifdef HAVE_JUMP_LABEL int deferred = atomic_xchg(&netstamp_needed_deferred, 0); - if (deferred) { - while (--deferred) - static_key_slow_dec(&netstamp_needed); - return; - } + while (deferred--) + static_key_slow_dec(&netstamp_needed); +} +static DECLARE_WORK(netstamp_work, netstamp_clear); #endif + +void net_enable_timestamp(void) +{ static_key_slow_inc(&netstamp_needed); } EXPORT_SYMBOL(net_enable_timestamp); @@ -1721,25 +1717,25 @@ EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef HAVE_JUMP_LABEL - if (in_interrupt()) { - atomic_inc(&netstamp_needed_deferred); - return; - } -#endif + /* net_disable_timestamp() can be called from non process context */ + atomic_inc(&netstamp_needed_deferred); + schedule_work(&netstamp_work); +#else static_key_slow_dec(&netstamp_needed); +#endif } EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { - skb->tstamp.tv64 = 0; + skb->tstamp = 0; if (static_key_false(&netstamp_needed)) __net_timestamp(skb); } #define net_timestamp_check(COND, SKB) \ if (static_key_false(&netstamp_needed)) { \ - if ((COND) && !(SKB)->tstamp.tv64) \ + if ((COND) && !(SKB)->tstamp) \ __net_timestamp(SKB); \ } \ @@ -1944,37 +1940,80 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq) } } +int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) +{ + if (dev->num_tc) { + struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; + int i; + + for (i = 0; i < TC_MAX_QUEUE; i++, tc++) { + if ((txq - tc->offset) < tc->count) + return i; + } + + return -1; + } + + return 0; +} + #ifdef CONFIG_XPS static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) -static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps, - int cpu, u16 index) +static bool remove_xps_queue(struct xps_dev_maps *dev_maps, + int tci, u16 index) { struct xps_map *map = NULL; int pos; if (dev_maps) - map = xmap_dereference(dev_maps->cpu_map[cpu]); + map = xmap_dereference(dev_maps->cpu_map[tci]); + if (!map) + return false; - for (pos = 0; map && pos < map->len; pos++) { - if (map->queues[pos] == index) { - if (map->len > 1) { - map->queues[pos] = map->queues[--map->len]; - } else { - RCU_INIT_POINTER(dev_maps->cpu_map[cpu], NULL); - kfree_rcu(map, rcu); - map = NULL; - } + for (pos = map->len; pos--;) { + if (map->queues[pos] != index) + continue; + + if (map->len > 1) { + map->queues[pos] = map->queues[--map->len]; break; } + + RCU_INIT_POINTER(dev_maps->cpu_map[tci], NULL); + kfree_rcu(map, rcu); + return false; } - return map; + return true; } -static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) +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; + bool active = false; + int tci; + + for (tci = cpu * num_tc; num_tc--; tci++) { + int i, j; + + for (i = count, j = offset; i--; j++) { + if (!remove_xps_queue(dev_maps, cpu, j)) + break; + } + + active |= i < 0; + } + + return active; +} + +static void netif_reset_xps_queues(struct net_device *dev, u16 offset, + u16 count) { struct xps_dev_maps *dev_maps; int cpu, i; @@ -1986,21 +2025,16 @@ static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) if (!dev_maps) goto out_no_maps; - for_each_possible_cpu(cpu) { - for (i = index; i < dev->num_tx_queues; i++) { - if (!remove_xps_queue(dev_maps, cpu, i)) - break; - } - if (i == dev->num_tx_queues) - active = true; - } + for_each_possible_cpu(cpu) + active |= remove_xps_queue_cpu(dev, dev_maps, cpu, + offset, count); if (!active) { RCU_INIT_POINTER(dev->xps_maps, NULL); kfree_rcu(dev_maps, rcu); } - for (i = index; i < dev->num_tx_queues; i++) + for (i = offset + (count - 1); count--; i--) netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i), NUMA_NO_NODE); @@ -2008,6 +2042,11 @@ out_no_maps: mutex_unlock(&xps_map_mutex); } +static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) +{ + netif_reset_xps_queues(dev, index, dev->num_tx_queues - index); +} + static struct xps_map *expand_xps_map(struct xps_map *map, int cpu, u16 index) { @@ -2047,20 +2086,28 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index) { struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; + int i, cpu, tci, numa_node_id = -2; + int maps_sz, num_tc = 1, tc = 0; struct xps_map *map, *new_map; - int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES); - int cpu, numa_node_id = -2; bool active = false; + if (dev->num_tc) { + num_tc = dev->num_tc; + tc = netdev_txq_to_tc(dev, index); + if (tc < 0) + return -EINVAL; + } + + maps_sz = XPS_DEV_MAPS_SIZE(num_tc); + if (maps_sz < L1_CACHE_BYTES) + maps_sz = L1_CACHE_BYTES; + mutex_lock(&xps_map_mutex); dev_maps = xmap_dereference(dev->xps_maps); /* allocate memory for queue storage */ - for_each_online_cpu(cpu) { - if (!cpumask_test_cpu(cpu, mask)) - continue; - + for_each_cpu_and(cpu, cpu_online_mask, mask) { if (!new_dev_maps) new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); if (!new_dev_maps) { @@ -2068,25 +2115,38 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, return -ENOMEM; } - map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + tci = cpu * num_tc + tc; + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[tci]) : NULL; map = expand_xps_map(map, cpu, index); if (!map) goto error; - RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); } if (!new_dev_maps) goto out_no_new_maps; for_each_possible_cpu(cpu) { + /* copy maps belonging to foreign traffic classes */ + for (i = tc, tci = cpu * num_tc; dev_maps && i--; tci++) { + /* fill in the new device map from the old device map */ + map = xmap_dereference(dev_maps->cpu_map[tci]); + RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + } + + /* We need to explicitly update tci as prevous loop + * could break out early if dev_maps is NULL. + */ + tci = cpu * num_tc + tc; + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) { /* add queue to CPU maps */ int pos = 0; - map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = xmap_dereference(new_dev_maps->cpu_map[tci]); while ((pos < map->len) && (map->queues[pos] != index)) pos++; @@ -2100,26 +2160,36 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, #endif } else if (dev_maps) { /* fill in the new device map from the old device map */ - map = xmap_dereference(dev_maps->cpu_map[cpu]); - RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + map = xmap_dereference(dev_maps->cpu_map[tci]); + RCU_INIT_POINTER(new_dev_maps->cpu_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->cpu_map[tci]); + RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map); + } } rcu_assign_pointer(dev->xps_maps, new_dev_maps); /* Cleanup old maps */ - if (dev_maps) { - for_each_possible_cpu(cpu) { - new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); - map = xmap_dereference(dev_maps->cpu_map[cpu]); + if (!dev_maps) + goto out_no_old_maps; + + for_each_possible_cpu(cpu) { + for (i = num_tc, tci = cpu * num_tc; i--; tci++) { + new_map = xmap_dereference(new_dev_maps->cpu_map[tci]); + map = xmap_dereference(dev_maps->cpu_map[tci]); if (map && map != new_map) kfree_rcu(map, rcu); } - - kfree_rcu(dev_maps, rcu); } + kfree_rcu(dev_maps, rcu); + +out_no_old_maps: dev_maps = new_dev_maps; active = true; @@ -2134,11 +2204,12 @@ out_no_new_maps: /* removes queue from unused CPUs */ for_each_possible_cpu(cpu) { - if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) - continue; - - if (remove_xps_queue(dev_maps, cpu, index)) - active = true; + for (i = tc, tci = cpu * num_tc; i--; tci++) + active |= remove_xps_queue(dev_maps, tci, index); + if (!cpumask_test_cpu(cpu, mask) || !cpu_online(cpu)) + active |= remove_xps_queue(dev_maps, tci, index); + for (i = num_tc - tc, tci++; --i; tci++) + active |= remove_xps_queue(dev_maps, tci, index); } /* free map if not active */ @@ -2154,11 +2225,14 @@ out_no_maps: error: /* remove any maps that we added */ for_each_possible_cpu(cpu) { - new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); - map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : - NULL; - if (new_map && new_map != map) - kfree(new_map); + for (i = num_tc, tci = cpu * num_tc; i--; tci++) { + new_map = xmap_dereference(new_dev_maps->cpu_map[tci]); + map = dev_maps ? + xmap_dereference(dev_maps->cpu_map[tci]) : + NULL; + if (new_map && new_map != map) + kfree(new_map); + } } mutex_unlock(&xps_map_mutex); @@ -2169,6 +2243,44 @@ error: EXPORT_SYMBOL(netif_set_xps_queue); #endif +void netdev_reset_tc(struct net_device *dev) +{ +#ifdef CONFIG_XPS + netif_reset_xps_queues_gt(dev, 0); +#endif + dev->num_tc = 0; + memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); + memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); +} +EXPORT_SYMBOL(netdev_reset_tc); + +int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) +{ + if (tc >= dev->num_tc) + return -EINVAL; + +#ifdef CONFIG_XPS + netif_reset_xps_queues(dev, offset, count); +#endif + dev->tc_to_txq[tc].count = count; + dev->tc_to_txq[tc].offset = offset; + return 0; +} +EXPORT_SYMBOL(netdev_set_tc_queue); + +int netdev_set_num_tc(struct net_device *dev, u8 num_tc) +{ + if (num_tc > TC_MAX_QUEUE) + return -EINVAL; + +#ifdef CONFIG_XPS + netif_reset_xps_queues_gt(dev, 0); +#endif + dev->num_tc = num_tc; + return 0; +} +EXPORT_SYMBOL(netdev_set_num_tc); + /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. @@ -2293,28 +2405,6 @@ void netif_schedule_queue(struct netdev_queue *txq) } EXPORT_SYMBOL(netif_schedule_queue); -/** - * netif_wake_subqueue - allow sending packets on subqueue - * @dev: network device - * @queue_index: sub queue index - * - * Resume individual transmit queue of a device with multiple transmit queues. - */ -void netif_wake_subqueue(struct net_device *dev, u16 queue_index) -{ - struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); - - if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) { - struct Qdisc *q; - - rcu_read_lock(); - q = rcu_dereference(txq->qdisc); - __netif_schedule(q); - rcu_read_unlock(); - } -} -EXPORT_SYMBOL(netif_wake_subqueue); - void netif_tx_wake_queue(struct netdev_queue *dev_queue) { if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) { @@ -2408,6 +2498,7 @@ u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, if (dev->num_tc) { u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; qcount = dev->tc_to_txq[tc].count; } @@ -2487,141 +2578,6 @@ out: } EXPORT_SYMBOL(skb_checksum_help); -/* skb_csum_offload_check - Driver helper function to determine if a device - * with limited checksum offload capabilities is able to offload the checksum - * for a given packet. - * - * Arguments: - * skb - sk_buff for the packet in question - * spec - contains the description of what device can offload - * csum_encapped - returns true if the checksum being offloaded is - * encpasulated. That is it is checksum for the transport header - * in the inner headers. - * checksum_help - when set indicates that helper function should - * call skb_checksum_help if offload checks fail - * - * Returns: - * true: Packet has passed the checksum checks and should be offloadable to - * the device (a driver may still need to check for additional - * restrictions of its device) - * false: Checksum is not offloadable. If checksum_help was set then - * skb_checksum_help was called to resolve checksum for non-GSO - * packets and when IP protocol is not SCTP - */ -bool __skb_csum_offload_chk(struct sk_buff *skb, - const struct skb_csum_offl_spec *spec, - bool *csum_encapped, - bool csum_help) -{ - struct iphdr *iph; - struct ipv6hdr *ipv6; - void *nhdr; - int protocol; - u8 ip_proto; - - if (skb->protocol == htons(ETH_P_8021Q) || - skb->protocol == htons(ETH_P_8021AD)) { - if (!spec->vlan_okay) - goto need_help; - } - - /* We check whether the checksum refers to a transport layer checksum in - * the outermost header or an encapsulated transport layer checksum that - * corresponds to the inner headers of the skb. If the checksum is for - * something else in the packet we need help. - */ - if (skb_checksum_start_offset(skb) == skb_transport_offset(skb)) { - /* Non-encapsulated checksum */ - protocol = eproto_to_ipproto(vlan_get_protocol(skb)); - nhdr = skb_network_header(skb); - *csum_encapped = false; - if (spec->no_not_encapped) - goto need_help; - } else if (skb->encapsulation && spec->encap_okay && - skb_checksum_start_offset(skb) == - skb_inner_transport_offset(skb)) { - /* Encapsulated checksum */ - *csum_encapped = true; - switch (skb->inner_protocol_type) { - case ENCAP_TYPE_ETHER: - protocol = eproto_to_ipproto(skb->inner_protocol); - break; - case ENCAP_TYPE_IPPROTO: - protocol = skb->inner_protocol; - break; - } - nhdr = skb_inner_network_header(skb); - } else { - goto need_help; - } - - switch (protocol) { - case IPPROTO_IP: - if (!spec->ipv4_okay) - goto need_help; - iph = nhdr; - ip_proto = iph->protocol; - if (iph->ihl != 5 && !spec->ip_options_okay) - goto need_help; - break; - case IPPROTO_IPV6: - if (!spec->ipv6_okay) - goto need_help; - if (spec->no_encapped_ipv6 && *csum_encapped) - goto need_help; - ipv6 = nhdr; - nhdr += sizeof(*ipv6); - ip_proto = ipv6->nexthdr; - break; - default: - goto need_help; - } - -ip_proto_again: - switch (ip_proto) { - case IPPROTO_TCP: - if (!spec->tcp_okay || - skb->csum_offset != offsetof(struct tcphdr, check)) - goto need_help; - break; - case IPPROTO_UDP: - if (!spec->udp_okay || - skb->csum_offset != offsetof(struct udphdr, check)) - goto need_help; - break; - case IPPROTO_SCTP: - if (!spec->sctp_okay || - skb->csum_offset != offsetof(struct sctphdr, checksum)) - goto cant_help; - break; - case NEXTHDR_HOP: - case NEXTHDR_ROUTING: - case NEXTHDR_DEST: { - u8 *opthdr = nhdr; - - if (protocol != IPPROTO_IPV6 || !spec->ext_hdrs_okay) - goto need_help; - - ip_proto = opthdr[0]; - nhdr += (opthdr[1] + 1) << 3; - - goto ip_proto_again; - } - default: - goto need_help; - } - - /* Passed the tests for offloading checksum */ - return true; - -need_help: - if (csum_help && !skb_shinfo(skb)->gso_size) - skb_checksum_help(skb); -cant_help: - return false; -} -EXPORT_SYMBOL(__skb_csum_offload_chk); - __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; @@ -2679,9 +2635,10 @@ EXPORT_SYMBOL(skb_mac_gso_segment); static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) { if (tx_path) - return skb->ip_summed != CHECKSUM_PARTIAL; - else - return skb->ip_summed == CHECKSUM_NONE; + return skb->ip_summed != CHECKSUM_PARTIAL && + skb->ip_summed != CHECKSUM_NONE; + + return skb->ip_summed == CHECKSUM_NONE; } /** @@ -2700,11 +2657,12 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) { + struct sk_buff *segs; + if (unlikely(skb_needs_check(skb, tx_path))) { int err; - skb_warn_bad_offload(skb); - + /* We're going to init ->check field in TCP or UDP header */ err = skb_cow_head(skb, 0); if (err < 0) return ERR_PTR(err); @@ -2732,7 +2690,12 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, skb_reset_mac_header(skb); skb_reset_mac_len(skb); - return skb_mac_gso_segment(skb, features); + segs = skb_mac_gso_segment(skb, features); + + if (unlikely(skb_needs_check(skb, tx_path))) + skb_warn_bad_offload(skb); + + return segs; } EXPORT_SYMBOL(__skb_gso_segment); @@ -2757,9 +2720,11 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; + if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + if (PageHighMem(skb_frag_page(frag))) return 1; } @@ -2773,6 +2738,7 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; dma_addr_t addr = page_to_phys(skb_frag_page(frag)); + if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask) return 1; } @@ -2815,9 +2781,9 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); - } else if (illegal_highdma(skb->dev, skb)) { - features &= ~NETIF_F_SG; } + if (illegal_highdma(skb->dev, skb)) + features &= ~NETIF_F_SG; return features; } @@ -3173,9 +3139,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) if (!cl) return skb; - /* skb->tc_verd and qdisc_skb_cb(skb)->pkt_len were already set - * earlier by the caller. - */ + /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ qdisc_bstats_cpu_update(cl->q, skb); switch (tc_classify(skb, cl, &cl_res, false)) { @@ -3216,8 +3180,14 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_maps); if (dev_maps) { - map = rcu_dereference( - dev_maps->cpu_map[skb->sender_cpu - 1]); + unsigned int tci = skb->sender_cpu - 1; + + if (dev->num_tc) { + tci *= dev->num_tc; + tci += netdev_get_prio_tc_map(dev, skb->priority); + } + + map = rcu_dereference(dev_maps->cpu_map[tci]); if (map) { if (map->len == 1) queue_index = map->queues[0]; @@ -3244,6 +3214,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) if (queue_index < 0 || skb->ooo_okay || queue_index >= dev->real_num_tx_queues) { int new_index = get_xps_queue(dev, skb); + if (new_index < 0) new_index = skb_tx_hash(dev, skb); @@ -3273,6 +3244,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) queue_index = ops->ndo_select_queue(dev, skb, accel_priv, __netdev_pick_tx); @@ -3334,7 +3306,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); + skb->tc_at_ingress = 0; # ifdef CONFIG_NET_EGRESS if (static_key_false(&egress_needed)) { skb = sch_handle_egress(skb, &rc, dev); @@ -3361,16 +3333,16 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) } /* The device has no queue. Common case for software devices: - loopback, all the sorts of tunnels... + * loopback, all the sorts of tunnels... - Really, it is unlikely that netif_tx_lock protection is necessary - here. (f.e. loopback and IP tunnels are clean ignoring statistics - counters.) - However, it is possible, that they rely on protection - made by us here. + * Really, it is unlikely that netif_tx_lock protection is necessary + * here. (f.e. loopback and IP tunnels are clean ignoring statistics + * counters.) + * However, it is possible, that they rely on protection + * made by us here. - Check this and shot the lock. It is not prone from deadlocks. - Either shot noqueue qdisc, it is even simpler 8) + * Check this and shot the lock. It is not prone from deadlocks. + *Either shot noqueue qdisc, it is even simpler 8) */ if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ @@ -3432,16 +3404,20 @@ int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) EXPORT_SYMBOL(dev_queue_xmit_accel); -/*======================================================================= - Receiver routines - =======================================================================*/ +/************************************************************************* + * Receiver routines + *************************************************************************/ int netdev_max_backlog __read_mostly = 1000; EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; -int weight_p __read_mostly = 64; /* old backlog weight */ +int weight_p __read_mostly = 64; /* old backlog weight */ +int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ +int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ +int dev_rx_weight __read_mostly = 64; +int dev_tx_weight __read_mostly = 64; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -3461,6 +3437,8 @@ EXPORT_SYMBOL(rps_cpu_mask); struct static_key rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); +struct static_key rfs_needed __read_mostly; +EXPORT_SYMBOL(rfs_needed); static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, @@ -3796,6 +3774,7 @@ static int netif_rx_internal(struct sk_buff *skb) #endif { unsigned int qtail; + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); put_cpu(); } @@ -3855,6 +3834,7 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) while (clist) { struct sk_buff *skb = clist; + clist = clist->next; WARN_ON(atomic_read(&skb->users)); @@ -3928,7 +3908,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, } qdisc_skb_cb(skb)->pkt_len = skb->len; - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); + skb->tc_at_ingress = 1; qdisc_bstats_cpu_update(cl->q, skb); switch (tc_classify(skb, cl, &cl_res, false)) { @@ -3993,9 +3973,7 @@ int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data) { - ASSERT_RTNL(); - - if (dev->rx_handler) + if (netdev_is_rx_handler_busy(dev)) return -EBUSY; /* Note: rx_handler_data must be set before rx_handler */ @@ -4101,12 +4079,8 @@ another_round: goto out; } -#ifdef CONFIG_NET_CLS_ACT - if (skb->tc_verd & TC_NCLS) { - skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); - goto ncls; - } -#endif + if (skb_skip_tc_classify(skb)) + goto skip_classify; if (pfmemalloc) goto skip_taps; @@ -4134,10 +4108,8 @@ skip_taps: goto out; } #endif -#ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = 0; -ncls: -#endif + skb_reset_tc(skb); +skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; @@ -4453,7 +4425,9 @@ static void skb_gro_reset_offset(struct sk_buff *skb) pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); - NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); + NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, + skb_frag_size(frag0), + skb->end - skb->tail); } } @@ -4491,7 +4465,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (!(skb->dev->features & NETIF_F_GRO)) goto normal; - if (skb_is_gso(skb) || skb_has_frag_list(skb) || skb->csum_bad) + if (skb->csum_bad) goto normal; gro_list_prepare(napi, skb); @@ -4504,7 +4478,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff skb_set_network_header(skb, skb_gro_offset(skb)); skb_reset_mac_len(skb); NAPI_GRO_CB(skb)->same_flow = 0; - NAPI_GRO_CB(skb)->flush = 0; + NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb); NAPI_GRO_CB(skb)->free = 0; NAPI_GRO_CB(skb)->encap_mark = 0; NAPI_GRO_CB(skb)->recursion_counter = 0; @@ -4536,6 +4510,11 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (&ptype->list == head) goto normal; + if (IS_ERR(pp) && PTR_ERR(pp) == -EINPROGRESS) { + ret = GRO_CONSUMED; + goto ok; + } + same_flow = NAPI_GRO_CB(skb)->same_flow; ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; @@ -4631,6 +4610,7 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) case GRO_MERGED_FREE: if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) { skb_dst_drop(skb); + secpath_reset(skb); kmem_cache_free(skbuff_head_cache, skb); } else { __kfree_skb(skb); @@ -4639,6 +4619,7 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) case GRO_HELD: case GRO_MERGED: + case GRO_CONSUMED: break; } @@ -4671,6 +4652,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->encapsulation = 0; skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); + secpath_reset(skb); napi->skb = skb; } @@ -4709,6 +4691,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, break; case GRO_MERGED: + case GRO_CONSUMED: break; } @@ -4845,7 +4828,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = weight_p; + napi->weight = dev_rx_weight; while (again) { struct sk_buff *skb; @@ -4912,26 +4895,19 @@ void __napi_schedule_irqoff(struct napi_struct *n) } EXPORT_SYMBOL(__napi_schedule_irqoff); -void __napi_complete(struct napi_struct *n) -{ - BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); - - list_del_init(&n->poll_list); - smp_mb__before_atomic(); - clear_bit(NAPI_STATE_SCHED, &n->state); -} -EXPORT_SYMBOL(__napi_complete); - -void napi_complete_done(struct napi_struct *n, int work_done) +bool napi_complete_done(struct napi_struct *n, int work_done) { unsigned long flags; /* - * don't let napi dequeue from the cpu poll list - * just in case its running on a different cpu + * 1) Don't let napi dequeue from the cpu poll list + * just in case its running on a different cpu. + * 2) If we are busy polling, do nothing here, we have + * the guarantee we will be called later. */ - if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state))) - return; + if (unlikely(n->state & (NAPIF_STATE_NPSVC | + NAPIF_STATE_IN_BUSY_POLL))) + return false; if (n->gro_list) { unsigned long timeout = 0; @@ -4945,14 +4921,14 @@ void napi_complete_done(struct napi_struct *n, int work_done) else napi_gro_flush(n, false); } - if (likely(list_empty(&n->poll_list))) { - WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state)); - } else { + if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); - __napi_complete(n); + list_del_init(&n->poll_list); local_irq_restore(flags); } + WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state)); + return true; } EXPORT_SYMBOL(napi_complete_done); @@ -4970,13 +4946,40 @@ static struct napi_struct *napi_by_id(unsigned int napi_id) } #if defined(CONFIG_NET_RX_BUSY_POLL) + #define BUSY_POLL_BUDGET 8 + +static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) +{ + int rc; + + clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state); + + local_bh_disable(); + + /* All we really want here is to re-enable device interrupts. + * Ideally, a new ndo_busy_poll_stop() could avoid another round. + */ + rc = napi->poll(napi, BUSY_POLL_BUDGET); + netpoll_poll_unlock(have_poll_lock); + if (rc == BUSY_POLL_BUDGET) + __napi_schedule(napi); + local_bh_enable(); + if (local_softirq_pending()) + do_softirq(); +} + bool sk_busy_loop(struct sock *sk, int nonblock) { unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0; - int (*busy_poll)(struct napi_struct *dev); + int (*napi_poll)(struct napi_struct *napi, int budget); + void *have_poll_lock = NULL; struct napi_struct *napi; - int rc = false; + int rc; + +restart: + rc = false; + napi_poll = NULL; rcu_read_lock(); @@ -4984,39 +4987,54 @@ bool sk_busy_loop(struct sock *sk, int nonblock) if (!napi) goto out; - /* Note: ndo_busy_poll method is optional in linux-4.5 */ - busy_poll = napi->dev->netdev_ops->ndo_busy_poll; - - do { + preempt_disable(); + for (;;) { rc = 0; local_bh_disable(); - if (busy_poll) { - rc = busy_poll(napi); - } else if (napi_schedule_prep(napi)) { - void *have = netpoll_poll_lock(napi); - - if (test_bit(NAPI_STATE_SCHED, &napi->state)) { - rc = napi->poll(napi, BUSY_POLL_BUDGET); - trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); - if (rc == BUSY_POLL_BUDGET) { - napi_complete_done(napi, rc); - napi_schedule(napi); - } - } - netpoll_poll_unlock(have); + if (!napi_poll) { + unsigned long val = READ_ONCE(napi->state); + + /* If multiple threads are competing for this napi, + * we avoid dirtying napi->state as much as we can. + */ + if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED | + NAPIF_STATE_IN_BUSY_POLL)) + goto count; + if (cmpxchg(&napi->state, val, + val | NAPIF_STATE_IN_BUSY_POLL | + NAPIF_STATE_SCHED) != val) + goto count; + have_poll_lock = netpoll_poll_lock(napi); + napi_poll = napi->poll; } + rc = napi_poll(napi, BUSY_POLL_BUDGET); + trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); +count: if (rc > 0) __NET_ADD_STATS(sock_net(sk), LINUX_MIB_BUSYPOLLRXPACKETS, rc); local_bh_enable(); - if (rc == LL_FLUSH_FAILED) - break; /* permanent failure */ + if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) || + busy_loop_timeout(end_time)) + break; + if (unlikely(need_resched())) { + if (napi_poll) + busy_poll_stop(napi, have_poll_lock); + preempt_enable(); + rcu_read_unlock(); + cond_resched(); + rc = !skb_queue_empty(&sk->sk_receive_queue); + if (rc || busy_loop_timeout(end_time)) + return rc; + goto restart; + } cpu_relax(); - } while (!nonblock && skb_queue_empty(&sk->sk_receive_queue) && - !need_resched() && !busy_loop_timeout(end_time)); - + } + if (napi_poll) + busy_poll_stop(napi, have_poll_lock); + preempt_enable(); rc = !skb_queue_empty(&sk->sk_receive_queue); out: rcu_read_unlock(); @@ -5026,7 +5044,7 @@ EXPORT_SYMBOL(sk_busy_loop); #endif /* CONFIG_NET_RX_BUSY_POLL */ -void napi_hash_add(struct napi_struct *napi) +static void napi_hash_add(struct napi_struct *napi) { if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state) || test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) @@ -5046,7 +5064,6 @@ void napi_hash_add(struct napi_struct *napi) spin_unlock(&napi_hash_lock); } -EXPORT_SYMBOL_GPL(napi_hash_add); /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi @@ -5072,7 +5089,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) napi = container_of(timer, struct napi_struct, timer); if (napi->gro_list) - napi_schedule(napi); + napi_schedule_irqoff(napi); return HRTIMER_NORESTART; } @@ -5094,7 +5111,6 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; #ifdef CONFIG_NETPOLL - spin_lock_init(&napi->poll_lock); napi->poll_owner = -1; #endif set_bit(NAPI_STATE_SCHED, &napi->state); @@ -5212,7 +5228,7 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) if (list_empty(&list)) { if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll)) - return; + goto out; break; } @@ -5230,7 +5246,6 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) } } - __kfree_skb_flush(); local_irq_disable(); list_splice_tail_init(&sd->poll_list, &list); @@ -5240,6 +5255,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) __raise_softirq_irqoff(NET_RX_SOFTIRQ); net_rps_action_and_irq_enable(sd); +out: + __kfree_skb_flush(); } struct netdev_adjacent { @@ -5270,6 +5287,13 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, return NULL; } +static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data) +{ + struct net_device *dev = data; + + return upper_dev == dev; +} + /** * netdev_has_upper_dev - Check if device is linked to an upper device * @dev: device @@ -5284,11 +5308,30 @@ bool netdev_has_upper_dev(struct net_device *dev, { ASSERT_RTNL(); - return __netdev_find_adj(upper_dev, &dev->all_adj_list.upper); + return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev, + upper_dev); } EXPORT_SYMBOL(netdev_has_upper_dev); /** + * netdev_has_upper_dev_all - Check if device is linked to an upper device + * @dev: device + * @upper_dev: upper device to check + * + * Find out if a device is linked to specified upper device and return true + * in case it is. Note that this checks the entire upper device chain. + * The caller must hold rcu lock. + */ + +bool netdev_has_upper_dev_all_rcu(struct net_device *dev, + struct net_device *upper_dev) +{ + return !!netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev, + upper_dev); +} +EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); + +/** * netdev_has_any_upper_dev - Check if device is linked to some device * @dev: device * @@ -5299,7 +5342,7 @@ static bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); - return !list_empty(&dev->all_adj_list.upper); + return !list_empty(&dev->adj_list.upper); } /** @@ -5326,6 +5369,20 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) } EXPORT_SYMBOL(netdev_master_upper_dev_get); +/** + * netdev_has_any_lower_dev - Check if device is linked to some device + * @dev: device + * + * Find out if a device is linked to a lower device and return true in case + * it is. The caller must hold the RTNL lock. + */ +static bool netdev_has_any_lower_dev(struct net_device *dev) +{ + ASSERT_RTNL(); + + return !list_empty(&dev->adj_list.lower); +} + void *netdev_adjacent_get_private(struct list_head *adj_list) { struct netdev_adjacent *adj; @@ -5362,16 +5419,8 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); -/** - * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list - * @dev: device - * @iter: list_head ** of the current position - * - * Gets the next device from the dev's upper list, starting from iter - * position. The caller must hold RCU read lock. - */ -struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, - struct list_head **iter) +static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *upper; @@ -5379,14 +5428,41 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); - if (&upper->list == &dev->all_adj_list.upper) + if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } -EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu); + +int netdev_walk_all_upper_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *udev; + struct list_head *iter; + int ret; + + for (iter = &dev->adj_list.upper, + udev = netdev_next_upper_dev_rcu(dev, &iter); + udev; + udev = netdev_next_upper_dev_rcu(dev, &iter)) { + /* first is the upper device itself */ + ret = fn(udev, data); + if (ret) + return ret; + + /* then look at all of its upper devices */ + ret = netdev_walk_all_upper_dev_rcu(udev, fn, data); + if (ret) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); /** * netdev_lower_get_next_private - Get the next ->private from the @@ -5469,55 +5545,90 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) } EXPORT_SYMBOL(netdev_lower_get_next); -/** - * netdev_all_lower_get_next - Get the next device from all lower neighbour list - * @dev: device - * @iter: list_head ** of the current position - * - * Gets the next netdev_adjacent from the dev's all lower neighbour - * list, starting from iter position. The caller must hold RTNL lock or - * its own locking that guarantees that the neighbour all lower - * list will remain unchanged. - */ -struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct list_head **iter) +static struct net_device *netdev_next_lower_dev(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *lower; - lower = list_entry(*iter, struct netdev_adjacent, list); + lower = list_entry((*iter)->next, struct netdev_adjacent, list); - if (&lower->list == &dev->all_adj_list.lower) + if (&lower->list == &dev->adj_list.lower) return NULL; - *iter = lower->list.next; + *iter = &lower->list; return lower->dev; } -EXPORT_SYMBOL(netdev_all_lower_get_next); -/** - * netdev_all_lower_get_next_rcu - Get the next device from all - * lower neighbour list, RCU variant - * @dev: device - * @iter: list_head ** of the current position - * - * Gets the next netdev_adjacent from the dev's all lower neighbour - * list, starting from iter position. The caller must hold RCU read lock. - */ -struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, - struct list_head **iter) +int netdev_walk_all_lower_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev; + struct list_head *iter; + int ret; + + for (iter = &dev->adj_list.lower, + ldev = netdev_next_lower_dev(dev, &iter); + ldev; + ldev = netdev_next_lower_dev(dev, &iter)) { + /* first is the lower device itself */ + ret = fn(ldev, data); + if (ret) + return ret; + + /* then look at all of its lower devices */ + ret = netdev_walk_all_lower_dev(ldev, fn, data); + if (ret) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); + +static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); - - if (&lower->list == &dev->all_adj_list.lower) + if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } -EXPORT_SYMBOL(netdev_all_lower_get_next_rcu); + +int netdev_walk_all_lower_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev; + struct list_head *iter; + int ret; + + for (iter = &dev->adj_list.lower, + ldev = netdev_next_lower_dev_rcu(dev, &iter); + ldev; + ldev = netdev_next_lower_dev_rcu(dev, &iter)) { + /* first is the lower device itself */ + ret = fn(ldev, data); + if (ret) + return ret; + + /* then look at all of its lower devices */ + ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data); + if (ret) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev_rcu); /** * netdev_lower_get_first_private_rcu - Get the first ->private from the @@ -5564,6 +5675,7 @@ static int netdev_adjacent_sysfs_add(struct net_device *dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", adj_dev->name); return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), @@ -5574,6 +5686,7 @@ static void netdev_adjacent_sysfs_del(struct net_device *dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", name); sysfs_remove_link(&(dev->dev.kobj), linkname); @@ -5590,7 +5703,6 @@ static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, - u16 ref_nr, struct list_head *dev_list, void *private, bool master) { @@ -5600,7 +5712,10 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { - adj->ref_nr += ref_nr; + adj->ref_nr += 1; + pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d\n", + dev->name, adj_dev->name, adj->ref_nr); + return 0; } @@ -5610,12 +5725,12 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj->dev = adj_dev; adj->master = master; - adj->ref_nr = ref_nr; + adj->ref_nr = 1; adj->private = private; dev_hold(adj_dev); - pr_debug("dev_hold for %s, because of link added from %s to %s\n", - adj_dev->name, dev->name, adj_dev->name); + pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", + dev->name, adj_dev->name, adj->ref_nr, adj_dev->name); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) { ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); @@ -5654,17 +5769,22 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, { struct netdev_adjacent *adj; + pr_debug("Remove adjacency: dev %s adj_dev %s ref_nr %d\n", + dev->name, adj_dev->name, ref_nr); + adj = __netdev_find_adj(adj_dev, dev_list); if (!adj) { - pr_err("tried to remove device %s from %s\n", + pr_err("Adjacency does not exist for device %s from %s\n", dev->name, adj_dev->name); - BUG(); + WARN_ON(1); + return; } if (adj->ref_nr > ref_nr) { - pr_debug("%s to %s ref_nr-%d = %d\n", dev->name, adj_dev->name, - ref_nr, adj->ref_nr-ref_nr); + pr_debug("adjacency: %s to %s ref_nr - %d = %d\n", + dev->name, adj_dev->name, ref_nr, + adj->ref_nr - ref_nr); adj->ref_nr -= ref_nr; return; } @@ -5676,7 +5796,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); - pr_debug("dev_put for %s, because link removed from %s to %s\n", + pr_debug("adjacency: dev_put for %s, because link removed from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); dev_put(adj_dev); kfree_rcu(adj, rcu); @@ -5684,38 +5804,27 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, static int __netdev_adjacent_dev_link_lists(struct net_device *dev, struct net_device *upper_dev, - u16 ref_nr, struct list_head *up_list, struct list_head *down_list, void *private, bool master) { int ret; - ret = __netdev_adjacent_dev_insert(dev, upper_dev, ref_nr, up_list, + ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, master); if (ret) return ret; - ret = __netdev_adjacent_dev_insert(upper_dev, dev, ref_nr, down_list, + ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, false); if (ret) { - __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list); + __netdev_adjacent_dev_remove(dev, upper_dev, 1, up_list); return ret; } return 0; } -static int __netdev_adjacent_dev_link(struct net_device *dev, - struct net_device *upper_dev, - u16 ref_nr) -{ - return __netdev_adjacent_dev_link_lists(dev, upper_dev, ref_nr, - &dev->all_adj_list.upper, - &upper_dev->all_adj_list.lower, - NULL, false); -} - static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, struct net_device *upper_dev, u16 ref_nr, @@ -5726,40 +5835,19 @@ static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, __netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list); } -static void __netdev_adjacent_dev_unlink(struct net_device *dev, - struct net_device *upper_dev, - u16 ref_nr) -{ - __netdev_adjacent_dev_unlink_lists(dev, upper_dev, ref_nr, - &dev->all_adj_list.upper, - &upper_dev->all_adj_list.lower); -} - static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, struct net_device *upper_dev, void *private, bool master) { - int ret = __netdev_adjacent_dev_link(dev, upper_dev, 1); - - if (ret) - return ret; - - ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, 1, - &dev->adj_list.upper, - &upper_dev->adj_list.lower, - private, master); - if (ret) { - __netdev_adjacent_dev_unlink(dev, upper_dev, 1); - return ret; - } - - return 0; + return __netdev_adjacent_dev_link_lists(dev, upper_dev, + &dev->adj_list.upper, + &upper_dev->adj_list.lower, + private, master); } static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, struct net_device *upper_dev) { - __netdev_adjacent_dev_unlink(dev, upper_dev, 1); __netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1, &dev->adj_list.upper, &upper_dev->adj_list.lower); @@ -5770,7 +5858,6 @@ static int __netdev_upper_dev_link(struct net_device *dev, void *upper_priv, void *upper_info) { struct netdev_notifier_changeupper_info changeupper_info; - struct netdev_adjacent *i, *j, *to_i, *to_j; int ret = 0; ASSERT_RTNL(); @@ -5779,10 +5866,10 @@ static int __netdev_upper_dev_link(struct net_device *dev, return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ - if (__netdev_find_adj(dev, &upper_dev->all_adj_list.upper)) + if (netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; - if (__netdev_find_adj(upper_dev, &dev->adj_list.upper)) + if (netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; if (master && netdev_master_upper_dev_get(dev)) @@ -5804,80 +5891,15 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (ret) return ret; - /* Now that we linked these devs, make all the upper_dev's - * all_adj_list.upper visible to every dev's all_adj_list.lower an - * versa, and don't forget the devices itself. All of these - * links are non-neighbours. - */ - list_for_each_entry(i, &dev->all_adj_list.lower, list) { - list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { - pr_debug("Interlinking %s with %s, non-neighbour\n", - i->dev->name, j->dev->name); - ret = __netdev_adjacent_dev_link(i->dev, j->dev, i->ref_nr); - if (ret) - goto rollback_mesh; - } - } - - /* add dev to every upper_dev's upper device */ - list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { - pr_debug("linking %s's upper device %s with %s\n", - upper_dev->name, i->dev->name, dev->name); - ret = __netdev_adjacent_dev_link(dev, i->dev, i->ref_nr); - if (ret) - goto rollback_upper_mesh; - } - - /* add upper_dev to every dev's lower device */ - list_for_each_entry(i, &dev->all_adj_list.lower, list) { - pr_debug("linking %s's lower device %s with %s\n", dev->name, - i->dev->name, upper_dev->name); - ret = __netdev_adjacent_dev_link(i->dev, upper_dev, i->ref_nr); - if (ret) - goto rollback_lower_mesh; - } - ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) - goto rollback_lower_mesh; + goto rollback; return 0; -rollback_lower_mesh: - to_i = i; - list_for_each_entry(i, &dev->all_adj_list.lower, list) { - if (i == to_i) - break; - __netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr); - } - - i = NULL; - -rollback_upper_mesh: - to_i = i; - list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { - if (i == to_i) - break; - __netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr); - } - - i = j = NULL; - -rollback_mesh: - to_i = i; - to_j = j; - list_for_each_entry(i, &dev->all_adj_list.lower, list) { - list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { - if (i == to_i && j == to_j) - break; - __netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr); - } - if (i == to_i) - break; - } - +rollback: __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); return ret; @@ -5934,7 +5956,7 @@ void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { struct netdev_notifier_changeupper_info changeupper_info; - struct netdev_adjacent *i, *j; + ASSERT_RTNL(); changeupper_info.upper_dev = upper_dev; @@ -5946,23 +5968,6 @@ void netdev_upper_dev_unlink(struct net_device *dev, __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); - /* Here is the tricky part. We must remove all dev's lower - * devices from all upper_dev's upper devices and vice - * versa, to maintain the graph relationship. - */ - list_for_each_entry(i, &dev->all_adj_list.lower, list) - list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) - __netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr); - - /* remove also the devices itself from lower/upper device - * list - */ - list_for_each_entry(i, &dev->all_adj_list.lower, list) - __netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr); - - list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) - __netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr); - call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, &changeupper_info.info); } @@ -6118,50 +6123,6 @@ void netdev_lower_state_changed(struct net_device *lower_dev, } EXPORT_SYMBOL(netdev_lower_state_changed); -int netdev_default_l2upper_neigh_construct(struct net_device *dev, - struct neighbour *n) -{ - struct net_device *lower_dev, *stop_dev; - struct list_head *iter; - int err; - - netdev_for_each_lower_dev(dev, lower_dev, iter) { - if (!lower_dev->netdev_ops->ndo_neigh_construct) - continue; - err = lower_dev->netdev_ops->ndo_neigh_construct(lower_dev, n); - if (err) { - stop_dev = lower_dev; - goto rollback; - } - } - return 0; - -rollback: - netdev_for_each_lower_dev(dev, lower_dev, iter) { - if (lower_dev == stop_dev) - break; - if (!lower_dev->netdev_ops->ndo_neigh_destroy) - continue; - lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n); - } - return err; -} -EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_construct); - -void netdev_default_l2upper_neigh_destroy(struct net_device *dev, - struct neighbour *n) -{ - struct net_device *lower_dev; - struct list_head *iter; - - netdev_for_each_lower_dev(dev, lower_dev, iter) { - if (!lower_dev->netdev_ops->ndo_neigh_destroy) - continue; - lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n); - } -} -EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_destroy); - static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; @@ -6414,8 +6375,8 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags) } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI - is important. Some (broken) drivers set IFF_PROMISC, when - IFF_ALLMULTI is requested not asking us and not reporting. + * is important. Some (broken) drivers set IFF_PROMISC, when + * IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { int inc = (flags & IFF_ALLMULTI) ? 1 : -1; @@ -6500,9 +6461,18 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) if (new_mtu == dev->mtu) return 0; - /* MTU must be positive. */ - if (new_mtu < 0) + /* MTU must be positive, and in range */ + if (new_mtu < 0 || new_mtu < dev->min_mtu) { + net_err_ratelimited("%s: Invalid MTU %d requested, hw min %d\n", + dev->name, new_mtu, dev->min_mtu); return -EINVAL; + } + + if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { + net_err_ratelimited("%s: Invalid MTU %d requested, hw max %d\n", + dev->name, new_mtu, dev->max_mtu); + return -EINVAL; + } if (!netif_device_present(dev)) return -ENODEV; @@ -6649,26 +6619,42 @@ EXPORT_SYMBOL(dev_change_proto_down); * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device * @fd: new program fd or negative value to clear + * @flags: xdp-related flags * * Set or clear a bpf program for a device */ -int dev_change_xdp_fd(struct net_device *dev, int fd) +int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags) { const struct net_device_ops *ops = dev->netdev_ops; struct bpf_prog *prog = NULL; - struct netdev_xdp xdp = {}; + struct netdev_xdp xdp; int err; + ASSERT_RTNL(); + if (!ops->ndo_xdp) return -EOPNOTSUPP; if (fd >= 0) { + if (flags & XDP_FLAGS_UPDATE_IF_NOEXIST) { + memset(&xdp, 0, sizeof(xdp)); + xdp.command = XDP_QUERY_PROG; + + err = ops->ndo_xdp(dev, &xdp); + if (err < 0) + return err; + if (xdp.prog_attached) + return -EBUSY; + } + prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); if (IS_ERR(prog)) return PTR_ERR(prog); } + memset(&xdp, 0, sizeof(xdp)); xdp.command = XDP_SETUP_PROG; xdp.prog = prog; + err = ops->ndo_xdp(dev, &xdp); if (err < 0 && prog) bpf_prog_put(prog); @@ -6688,6 +6674,7 @@ EXPORT_SYMBOL(dev_change_xdp_fd); static int dev_new_index(struct net *net) { int ifindex = net->ifindex; + for (;;) { if (++ifindex <= 0) ifindex = 1; @@ -6754,8 +6741,8 @@ static void rollback_registered_many(struct list_head *head) /* Notify protocols, that we are about to destroy - this device. They should clean all the things. - */ + * this device. They should clean all the things. + */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); if (!dev->rtnl_link_ops || @@ -6777,6 +6764,7 @@ static void rollback_registered_many(struct list_head *head) /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); + WARN_ON(netdev_has_any_lower_dev(dev)); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); @@ -6912,13 +6900,6 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~dev->gso_partial_features; } -#ifdef CONFIG_NET_RX_BUSY_POLL - if (dev->netdev_ops->ndo_busy_poll) - features |= NETIF_F_BUSY_POLL; - else -#endif - features &= ~NETIF_F_BUSY_POLL; - return features; } @@ -7107,6 +7088,7 @@ void netif_tx_stop_all_queues(struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + netif_tx_stop_queue(txq); } } @@ -7581,17 +7563,17 @@ void netdev_freemem(struct net_device *dev) } /** - * alloc_netdev_mqs - allocate network device - * @sizeof_priv: size of private data to allocate space for - * @name: device name format string - * @name_assign_type: origin of device name - * @setup: callback to initialize device - * @txqs: the number of TX subqueues to allocate - * @rxqs: the number of RX subqueues to allocate - * - * Allocates a struct net_device with private data area for driver use - * and performs basic initialization. Also allocates subqueue structs - * for each queue on the device. + * alloc_netdev_mqs - allocate network device + * @sizeof_priv: size of private data to allocate space for + * @name: device name format string + * @name_assign_type: origin of device name + * @setup: callback to initialize device + * @txqs: the number of TX subqueues to allocate + * @rxqs: the number of RX subqueues to allocate + * + * Allocates a struct net_device with private data area for driver use + * and performs basic initialization. Also allocates subqueue structs + * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, @@ -7655,8 +7637,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, INIT_LIST_HEAD(&dev->link_watch_list); INIT_LIST_HEAD(&dev->adj_list.upper); INIT_LIST_HEAD(&dev->adj_list.lower); - INIT_LIST_HEAD(&dev->all_adj_list.upper); - INIT_LIST_HEAD(&dev->all_adj_list.lower); INIT_LIST_HEAD(&dev->ptype_all); INIT_LIST_HEAD(&dev->ptype_specific); #ifdef CONFIG_NET_SCHED @@ -7667,7 +7647,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; - dev->tx_queue_len = 1; + dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; } dev->num_tx_queues = txqs; @@ -7705,13 +7685,13 @@ free_dev: EXPORT_SYMBOL(alloc_netdev_mqs); /** - * free_netdev - free network device - * @dev: device + * free_netdev - free network device + * @dev: device * - * This function does the last stage of destroying an allocated device - * interface. The reference to the device object is released. - * If this is the last reference then it will be freed. - * Must be called in process context. + * This function does the last stage of destroying an allocated device + * interface. The reference to the device object is released. If this + * is the last reference then it will be freed.Must be called in process + * context. */ void free_netdev(struct net_device *dev) { @@ -7893,12 +7873,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev_shutdown(dev); /* Notify protocols, that we are about to destroy - this device. They should clean all the things. - - Note that dev->reg_state stays at NETREG_REGISTERED. - This is wanted because this way 8021q and macvlan know - the device is just moving and can keep their slaves up. - */ + * this device. They should clean all the things. + * + * Note that dev->reg_state stays at NETREG_REGISTERED. + * This is wanted because this way 8021q and macvlan know + * the device is just moving and can keep their slaves up. + */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); @@ -7948,18 +7928,13 @@ out: } EXPORT_SYMBOL_GPL(dev_change_net_namespace); -static int dev_cpu_callback(struct notifier_block *nfb, - unsigned long action, - void *ocpu) +static int dev_cpu_dead(unsigned int oldcpu) { struct sk_buff **list_skb; struct sk_buff *skb; - unsigned int cpu, oldcpu = (unsigned long)ocpu; + unsigned int cpu; struct softnet_data *sd, *oldsd; - if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) - return NOTIFY_OK; - local_irq_disable(); cpu = smp_processor_id(); sd = &per_cpu(softnet_data, cpu); @@ -8009,10 +7984,9 @@ static int dev_cpu_callback(struct notifier_block *nfb, input_queue_head_incr(oldsd); } - return NOTIFY_OK; + return 0; } - /** * netdev_increment_features - increment feature set by one * @all: current feature set @@ -8346,7 +8320,9 @@ static int __init net_dev_init(void) open_softirq(NET_TX_SOFTIRQ, net_tx_action); open_softirq(NET_RX_SOFTIRQ, net_rx_action); - hotcpu_notifier(dev_cpu_callback, 0); + rc = cpuhp_setup_state_nocalls(CPUHP_NET_DEV_DEAD, "net/dev:dead", + NULL, dev_cpu_dead); + WARN_ON(rc < 0); dst_subsys_init(); rc = 0; out: |