diff options
Diffstat (limited to 'net/core/dev.c')
| -rw-r--r-- | net/core/dev.c | 4435 |
1 files changed, 2666 insertions, 1769 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index c6c985fe7b1b..3be256051e99 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -79,6 +79,7 @@ #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mutex.h> +#include <linux/rwsem.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> @@ -90,6 +91,7 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/skbuff.h> +#include <linux/kthread.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <net/net_namespace.h> @@ -97,8 +99,10 @@ #include <net/busy_poll.h> #include <linux/rtnetlink.h> #include <linux/stat.h> +#include <net/dsa.h> #include <net/dst.h> #include <net/dst_metadata.h> +#include <net/gro.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/checksum.h> @@ -127,6 +131,7 @@ #include <trace/events/napi.h> #include <trace/events/net.h> #include <trace/events/skb.h> +#include <trace/events/qdisc.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> #include <linux/static_key.h> @@ -135,26 +140,24 @@ #include <linux/if_macvlan.h> #include <linux/errqueue.h> #include <linux/hrtimer.h> -#include <linux/netfilter_ingress.h> +#include <linux/netfilter_netdev.h> #include <linux/crash_dump.h> #include <linux/sctp.h> #include <net/udp_tunnel.h> #include <linux/net_namespace.h> #include <linux/indirect_call_wrapper.h> #include <net/devlink.h> +#include <linux/pm_runtime.h> +#include <linux/prandom.h> +#include <linux/once_lite.h> +#include "dev.h" #include "net-sysfs.h" -#define MAX_GRO_SKBS 8 - -/* This should be increased if a protocol with a bigger head is added. */ -#define GRO_MAX_HEAD (MAX_HEADER + 128) static DEFINE_SPINLOCK(ptype_lock); -static DEFINE_SPINLOCK(offload_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; struct list_head ptype_all __read_mostly; /* Taps */ -static struct list_head offload_base __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_info(unsigned long val, @@ -194,7 +197,7 @@ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); -static seqcount_t devnet_rename_seq; +static DECLARE_RWSEM(devnet_rename_sem); static inline void dev_base_seq_inc(struct net *net) { @@ -214,18 +217,38 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } -static inline void rps_lock(struct softnet_data *sd) +static inline void rps_lock_irqsave(struct softnet_data *sd, + unsigned long *flags) { -#ifdef CONFIG_RPS - spin_lock(&sd->input_pkt_queue.lock); -#endif + if (IS_ENABLED(CONFIG_RPS)) + spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_save(*flags); } -static inline void rps_unlock(struct softnet_data *sd) +static inline void rps_lock_irq_disable(struct softnet_data *sd) { -#ifdef CONFIG_RPS - spin_unlock(&sd->input_pkt_queue.lock); -#endif + if (IS_ENABLED(CONFIG_RPS)) + spin_lock_irq(&sd->input_pkt_queue.lock); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_disable(); +} + +static inline void rps_unlock_irq_restore(struct softnet_data *sd, + unsigned long *flags) +{ + if (IS_ENABLED(CONFIG_RPS)) + spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_restore(*flags); +} + +static inline void rps_unlock_irq_enable(struct softnet_data *sd) +{ + if (IS_ENABLED(CONFIG_RPS)) + spin_unlock_irq(&sd->input_pkt_queue.lock); + else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_irq_enable(); } static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, @@ -295,6 +318,12 @@ static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, return NULL; } +bool netdev_name_in_use(struct net *net, const char *name) +{ + return netdev_name_node_lookup(net, name); +} +EXPORT_SYMBOL(netdev_name_in_use); + int netdev_name_node_alt_create(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; @@ -312,7 +341,6 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name) return 0; } -EXPORT_SYMBOL(netdev_name_node_alt_create); static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { @@ -340,7 +368,6 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) return 0; } -EXPORT_SYMBOL(netdev_name_node_alt_destroy); static void netdev_name_node_alt_flush(struct net_device *dev) { @@ -357,12 +384,12 @@ static void list_netdevice(struct net_device *dev) ASSERT_RTNL(); - write_lock_bh(&dev_base_lock); + write_lock(&dev_base_lock); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); - write_unlock_bh(&dev_base_lock); + write_unlock(&dev_base_lock); dev_base_seq_inc(net); } @@ -370,16 +397,18 @@ static void list_netdevice(struct net_device *dev) /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */ -static void unlist_netdevice(struct net_device *dev) +static void unlist_netdevice(struct net_device *dev, bool lock) { ASSERT_RTNL(); /* Unlink dev from the device chain */ - write_lock_bh(&dev_base_lock); + if (lock) + write_lock(&dev_base_lock); list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); - write_unlock_bh(&dev_base_lock); + if (lock) + write_unlock(&dev_base_lock); dev_base_seq_inc(dev_net(dev)); } @@ -398,6 +427,89 @@ static RAW_NOTIFIER_HEAD(netdev_chain); DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); EXPORT_PER_CPU_SYMBOL(softnet_data); +#ifdef CONFIG_LOCKDEP +/* + * 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, + ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, + ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, + ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, + ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, + ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, + ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, + ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, + ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, + ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, + ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, + ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, + ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, + 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 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)]; + +static inline unsigned short netdev_lock_pos(unsigned short dev_type) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) + if (netdev_lock_type[i] == dev_type) + return i; + /* the last key is used by default */ + return ARRAY_SIZE(netdev_lock_type) - 1; +} + +static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, + unsigned short dev_type) +{ + int i; + + i = netdev_lock_pos(dev_type); + lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], + netdev_lock_name[i]); +} + +static inline void netdev_set_addr_lockdep_class(struct net_device *dev) +{ + int i; + + i = netdev_lock_pos(dev->type); + lockdep_set_class_and_name(&dev->addr_list_lock, + &netdev_addr_lock_key[i], + netdev_lock_name[i]); +} +#else +static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, + unsigned short dev_type) +{ +} + +static inline void netdev_set_addr_lockdep_class(struct net_device *dev) +{ +} +#endif + /******************************************************************************* * * Protocol management and registration routines @@ -507,209 +619,6 @@ void dev_remove_pack(struct packet_type *pt) EXPORT_SYMBOL(dev_remove_pack); -/** - * dev_add_offload - register offload handlers - * @po: protocol offload declaration - * - * Add protocol offload handlers to the networking stack. The passed - * &proto_offload is linked into kernel lists and may not be freed until - * it has been removed from the kernel lists. - * - * This call does not sleep therefore it can not - * guarantee all CPU's that are in middle of receiving packets - * will see the new offload handlers (until the next received packet). - */ -void dev_add_offload(struct packet_offload *po) -{ - struct packet_offload *elem; - - spin_lock(&offload_lock); - list_for_each_entry(elem, &offload_base, list) { - if (po->priority < elem->priority) - break; - } - list_add_rcu(&po->list, elem->list.prev); - spin_unlock(&offload_lock); -} -EXPORT_SYMBOL(dev_add_offload); - -/** - * __dev_remove_offload - remove offload handler - * @po: packet offload declaration - * - * Remove a protocol offload handler that was previously added to the - * kernel offload handlers by dev_add_offload(). The passed &offload_type - * is removed from the kernel lists and can be freed or reused once this - * function returns. - * - * The packet type might still be in use by receivers - * and must not be freed until after all the CPU's have gone - * through a quiescent state. - */ -static void __dev_remove_offload(struct packet_offload *po) -{ - struct list_head *head = &offload_base; - struct packet_offload *po1; - - spin_lock(&offload_lock); - - list_for_each_entry(po1, head, list) { - if (po == po1) { - list_del_rcu(&po->list); - goto out; - } - } - - pr_warn("dev_remove_offload: %p not found\n", po); -out: - spin_unlock(&offload_lock); -} - -/** - * dev_remove_offload - remove packet offload handler - * @po: packet offload declaration - * - * Remove a packet offload handler that was previously added to the kernel - * offload handlers by dev_add_offload(). The passed &offload_type is - * removed from the kernel lists and can be freed or reused once this - * function returns. - * - * This call sleeps to guarantee that no CPU is looking at the packet - * type after return. - */ -void dev_remove_offload(struct packet_offload *po) -{ - __dev_remove_offload(po); - - synchronize_net(); -} -EXPORT_SYMBOL(dev_remove_offload); - -/****************************************************************************** - * - * Device Boot-time Settings Routines - * - ******************************************************************************/ - -/* Boot time configuration table */ -static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX]; - -/** - * netdev_boot_setup_add - add new setup entry - * @name: name of the device - * @map: configured settings for the device - * - * Adds new setup entry to the dev_boot_setup list. The function - * returns 0 on error and 1 on success. This is a generic routine to - * all netdevices. - */ -static int netdev_boot_setup_add(char *name, struct ifmap *map) -{ - struct netdev_boot_setup *s; - int i; - - s = dev_boot_setup; - for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { - if (s[i].name[0] == '\0' || s[i].name[0] == ' ') { - memset(s[i].name, 0, sizeof(s[i].name)); - strlcpy(s[i].name, name, IFNAMSIZ); - memcpy(&s[i].map, map, sizeof(s[i].map)); - break; - } - } - - return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1; -} - -/** - * 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. - */ -int netdev_boot_setup_check(struct net_device *dev) -{ - struct netdev_boot_setup *s = dev_boot_setup; - int i; - - 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; - return 1; - } - } - return 0; -} -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 - * - * 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) -{ - const struct netdev_boot_setup *s = dev_boot_setup; - char name[IFNAMSIZ]; - int i; - - sprintf(name, "%s%d", prefix, unit); - - /* - * If device already registered then return base of 1 - * to indicate not to probe for this interface - */ - if (__dev_get_by_name(&init_net, name)) - return 1; - - for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) - if (!strcmp(name, s[i].name)) - return s[i].map.base_addr; - return 0; -} - -/* - * Saves at boot time configured settings for any netdevice. - */ -int __init netdev_boot_setup(char *str) -{ - int ints[5]; - struct ifmap map; - - str = get_options(str, ARRAY_SIZE(ints), ints); - if (!str || !*str) - return 0; - - /* Save settings */ - memset(&map, 0, sizeof(map)); - if (ints[0] > 0) - map.irq = ints[1]; - if (ints[0] > 1) - map.base_addr = ints[2]; - if (ints[0] > 2) - map.mem_start = ints[3]; - if (ints[0] > 3) - map.mem_end = ints[4]; - - /* Add new entry to the list */ - return netdev_boot_setup_add(str, &map); -} - -__setup("netdev=", netdev_boot_setup); - /******************************************************************************* * * Device Interface Subroutines @@ -759,6 +668,56 @@ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); +static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack) +{ + int k = stack->num_paths++; + + if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX)) + return NULL; + + return &stack->path[k]; +} + +int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, + struct net_device_path_stack *stack) +{ + const struct net_device *last_dev; + struct net_device_path_ctx ctx = { + .dev = dev, + }; + struct net_device_path *path; + int ret = 0; + + memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); + stack->num_paths = 0; + while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { + last_dev = ctx.dev; + path = dev_fwd_path(stack); + if (!path) + return -1; + + memset(path, 0, sizeof(struct net_device_path)); + ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path); + if (ret < 0) + return -1; + + if (WARN_ON_ONCE(last_dev == ctx.dev)) + return -1; + } + + if (!ctx.dev) + return ret; + + path = dev_fwd_path(stack); + if (!path) + return -1; + path->type = DEV_PATH_ETHERNET; + path->dev = ctx.dev; + + return ret; +} +EXPORT_SYMBOL_GPL(dev_fill_forward_path); + /** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace @@ -819,8 +778,7 @@ struct net_device *dev_get_by_name(struct net *net, const char *name) rcu_read_lock(); dev = dev_get_by_name_rcu(net, name); - if (dev) - dev_hold(dev); + dev_hold(dev); rcu_read_unlock(); return dev; } @@ -893,8 +851,7 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); - if (dev) - dev_hold(dev); + dev_hold(dev); rcu_read_unlock(); return dev; } @@ -930,33 +887,28 @@ EXPORT_SYMBOL(dev_get_by_napi_id); * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @ifindex: the ifindex of the interface to get the name from. - * - * The use of raw_seqcount_begin() and cond_resched() before - * retrying is required as we want to give the writers a chance - * to complete when CONFIG_PREEMPTION is not set. */ int netdev_get_name(struct net *net, char *name, int ifindex) { struct net_device *dev; - unsigned int seq; + int ret; -retry: - seq = raw_seqcount_begin(&devnet_rename_seq); + down_read(&devnet_rename_sem); rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); if (!dev) { - rcu_read_unlock(); - return -ENODEV; + ret = -ENODEV; + goto out; } strcpy(name, dev->name); - rcu_read_unlock(); - if (read_seqcount_retry(&devnet_rename_seq, seq)) { - cond_resched(); - goto retry; - } - return 0; + ret = 0; +out: + rcu_read_unlock(); + up_read(&devnet_rename_sem); + return ret; } /** @@ -987,19 +939,6 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); -struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type) -{ - struct net_device *dev; - - ASSERT_RTNL(); - for_each_netdev(net, dev) - if (dev->type == type) - return dev; - - return NULL; -} -EXPORT_SYMBOL(__dev_getfirstbyhwtype); - struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; @@ -1050,7 +989,7 @@ EXPORT_SYMBOL(__dev_get_by_flags); * @name: name string * * Network device names need to be valid file names to - * to allow sysfs to work. We also disallow any kind of + * allow sysfs to work. We also disallow any kind of * whitespace. */ bool dev_valid_name(const char *name) @@ -1113,6 +1052,18 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) return -ENOMEM; for_each_netdev(net, d) { + struct netdev_name_node *name_node; + list_for_each_entry(name_node, &d->name_node->list, list) { + if (!sscanf(name_node->name, name, &i)) + continue; + if (i < 0 || i >= max_netdevices) + continue; + + /* avoid cases where sscanf is not exact inverse of printf */ + snprintf(buf, IFNAMSIZ, name, i); + if (!strncmp(buf, name_node->name, IFNAMSIZ)) + __set_bit(i, inuse); + } if (!sscanf(d->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) @@ -1121,7 +1072,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, d->name, IFNAMSIZ)) - set_bit(i, inuse); + __set_bit(i, inuse); } i = find_first_zero_bit(inuse, max_netdevices); @@ -1129,7 +1080,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) } snprintf(buf, IFNAMSIZ, name, i); - if (!__dev_get_by_name(net, buf)) + if (!netdev_name_in_use(net, buf)) return i; /* It is possible to run out of possible slots @@ -1149,7 +1100,7 @@ static int dev_alloc_name_ns(struct net *net, BUG_ON(!net); ret = __dev_alloc_name(net, name, buf); if (ret >= 0) - strlcpy(dev->name, buf, IFNAMSIZ); + strscpy(dev->name, buf, IFNAMSIZ); return ret; } @@ -1183,10 +1134,10 @@ static int dev_get_valid_name(struct net *net, struct net_device *dev, if (strchr(name, '%')) return dev_alloc_name_ns(net, dev, name); - else if (__dev_get_by_name(net, name)) + else if (netdev_name_in_use(net, name)) return -EEXIST; else if (dev->name != name) - strlcpy(dev->name, name, IFNAMSIZ); + strscpy(dev->name, name, IFNAMSIZ); return 0; } @@ -1228,10 +1179,10 @@ int dev_change_name(struct net_device *dev, const char *newname) likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) return -EBUSY; - write_seqcount_begin(&devnet_rename_seq); + down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return 0; } @@ -1239,7 +1190,7 @@ int dev_change_name(struct net_device *dev, const char *newname) err = dev_get_valid_name(net, dev, newname); if (err < 0) { - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return err; } @@ -1254,23 +1205,23 @@ rollback: if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); dev->name_assign_type = old_assign_type; - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return ret; } - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); netdev_adjacent_rename_links(dev, oldname); - write_lock_bh(&dev_base_lock); + write_lock(&dev_base_lock); netdev_name_node_del(dev->name_node); - write_unlock_bh(&dev_base_lock); + write_unlock(&dev_base_lock); synchronize_rcu(); - write_lock_bh(&dev_base_lock); + write_lock(&dev_base_lock); netdev_name_node_add(net, dev->name_node); - write_unlock_bh(&dev_base_lock); + write_unlock(&dev_base_lock); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); ret = notifier_to_errno(ret); @@ -1279,15 +1230,15 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - write_seqcount_begin(&devnet_rename_seq); + down_write(&devnet_rename_sem); memcpy(dev->name, oldname, IFNAMSIZ); memcpy(oldname, newname, IFNAMSIZ); dev->name_assign_type = old_assign_type; old_assign_type = NET_NAME_RENAMED; goto rollback; } else { - pr_err("%s: name change rollback failed: %d\n", - dev->name, ret); + netdev_err(dev, "name change rollback failed: %d\n", + ret); } } @@ -1388,6 +1339,25 @@ void netdev_state_change(struct net_device *dev) EXPORT_SYMBOL(netdev_state_change); /** + * __netdev_notify_peers - notify network peers about existence of @dev, + * to be called when rtnl lock is already held. + * @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 + * a device wants to inform the rest of the network about some sort of + * reconfiguration such as a failover event or virtual machine + * migration. + */ +void __netdev_notify_peers(struct net_device *dev) +{ + ASSERT_RTNL(); + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); + call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev); +} +EXPORT_SYMBOL(__netdev_notify_peers); + +/** * netdev_notify_peers - notify network peers about existence of @dev * @dev: network device * @@ -1400,21 +1370,47 @@ EXPORT_SYMBOL(netdev_state_change); void netdev_notify_peers(struct net_device *dev) { rtnl_lock(); - call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); - call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev); + __netdev_notify_peers(dev); rtnl_unlock(); } EXPORT_SYMBOL(netdev_notify_peers); +static int napi_threaded_poll(void *data); + +static int napi_kthread_create(struct napi_struct *n) +{ + int err = 0; + + /* Create and wake up the kthread once to put it in + * TASK_INTERRUPTIBLE mode to avoid the blocked task + * warning and work with loadavg. + */ + n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d", + n->dev->name, n->napi_id); + if (IS_ERR(n->thread)) { + err = PTR_ERR(n->thread); + pr_err("kthread_run failed with err %d\n", err); + n->thread = NULL; + } + + return err; +} + static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int ret; ASSERT_RTNL(); + dev_addr_check(dev); - if (!netif_device_present(dev)) - return -ENODEV; + if (!netif_device_present(dev)) { + /* may be detached because parent is runtime-suspended */ + if (dev->dev.parent) + pm_runtime_resume(dev->dev.parent); + if (!netif_device_present(dev)) + return -ENODEV; + } /* Block netpoll from trying to do any rx path servicing. * If we don't do this there is a chance ndo_poll_controller @@ -1631,7 +1627,8 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) - N(PRE_CHANGEADDR) + N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) + N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) } #undef N return "UNKNOWN_NETDEV_EVENT"; @@ -1948,6 +1945,32 @@ static int call_netdevice_notifiers_info(unsigned long val, return raw_notifier_call_chain(&netdev_chain, val, info); } +/** + * call_netdevice_notifiers_info_robust - call per-netns notifier blocks + * for and rollback on error + * @val_up: value passed unmodified to notifier function + * @val_down: value passed unmodified to the notifier function when + * recovering from an error on @val_up + * @info: notifier information data + * + * Call all per-netns network notifier blocks, but not notifier blocks on + * the global notifier chain. Parameters and return value are as for + * raw_notifier_call_chain_robust(). + */ + +static int +call_netdevice_notifiers_info_robust(unsigned long val_up, + unsigned long val_down, + struct netdev_notifier_info *info) +{ + struct net *net = dev_net(info->dev); + + ASSERT_RTNL(); + + return raw_notifier_call_chain_robust(&net->netdev_chain, + val_up, val_down, info); +} + static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack) @@ -2029,7 +2052,8 @@ void net_dec_egress_queue(void) EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif -static DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); +DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); +EXPORT_SYMBOL(netstamp_needed_key); #ifdef CONFIG_JUMP_LABEL static atomic_t netstamp_needed_deferred; static atomic_t netstamp_wanted; @@ -2090,40 +2114,27 @@ EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; + skb->mono_delivery_time = 0; if (static_branch_unlikely(&netstamp_needed_key)) - __net_timestamp(skb); + skb->tstamp = ktime_get_real(); } #define net_timestamp_check(COND, SKB) \ if (static_branch_unlikely(&netstamp_needed_key)) { \ if ((COND) && !(SKB)->tstamp) \ - __net_timestamp(SKB); \ + (SKB)->tstamp = ktime_get_real(); \ } \ bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) { - unsigned int len; - - if (!(dev->flags & IFF_UP)) - return false; - - len = dev->mtu + dev->hard_header_len + VLAN_HLEN; - if (skb->len <= len) - return true; - - /* if TSO is enabled, we don't care about the length as the packet - * could be forwarded without being segmented before - */ - if (skb_is_gso(skb)) - return true; - - return false; + return __is_skb_forwardable(dev, skb, true); } EXPORT_SYMBOL_GPL(is_skb_forwardable); -int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb, + bool check_mtu) { - int ret = ____dev_forward_skb(dev, skb); + int ret = ____dev_forward_skb(dev, skb, check_mtu); if (likely(!ret)) { skb->protocol = eth_type_trans(skb, dev); @@ -2132,6 +2143,11 @@ int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) return ret; } + +int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + return __dev_forward_skb2(dev, skb, true); +} EXPORT_SYMBOL_GPL(__dev_forward_skb); /** @@ -2158,6 +2174,11 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(dev_forward_skb); +int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb) +{ + return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb); +} + static inline int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) @@ -2301,7 +2322,7 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq) /* If TC0 is invalidated disable TC mapping */ if (tc->offset + tc->count > txq) { - pr_warn("Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); + netdev_warn(dev, "Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); dev->num_tc = 0; return; } @@ -2312,8 +2333,8 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq) tc = &dev->tc_to_txq[q]; if (tc->offset + tc->count > txq) { - pr_warn("Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", - i, q); + netdev_warn(dev, "Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", + i, q); netdev_set_prio_tc_map(dev, i, 0); } } @@ -2340,16 +2361,14 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS -struct static_key xps_needed __read_mostly; -EXPORT_SYMBOL(xps_needed); -struct static_key xps_rxqs_needed __read_mostly; -EXPORT_SYMBOL(xps_rxqs_needed); +static struct static_key xps_needed __read_mostly; +static struct static_key xps_rxqs_needed __read_mostly; static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ 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; @@ -2368,6 +2387,8 @@ 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; @@ -2380,7 +2401,7 @@ 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; @@ -2388,7 +2409,7 @@ 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; } @@ -2400,74 +2421,54 @@ 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(); } @@ -2517,16 +2518,35 @@ 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) { @@ -2544,38 +2564,48 @@ 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; @@ -2588,29 +2618,21 @@ 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++; @@ -2618,78 +2640,81 @@ 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); @@ -2697,11 +2722,10 @@ 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) @@ -2722,7 +2746,7 @@ 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; @@ -2874,6 +2898,8 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (dev->num_tc) netif_setup_tc(dev, txq); + dev_qdisc_change_real_num_tx(dev, txq); + dev->real_num_tx_queues = txq; if (disabling) { @@ -2925,15 +2951,117 @@ EXPORT_SYMBOL(netif_set_real_num_rx_queues); #endif /** + * netif_set_real_num_queues - set actual number of RX and TX queues used + * @dev: Network device + * @txq: Actual number of TX queues + * @rxq: Actual number of RX queues + * + * Set the real number of both TX and RX queues. + * Does nothing if the number of queues is already correct. + */ +int netif_set_real_num_queues(struct net_device *dev, + unsigned int txq, unsigned int rxq) +{ + unsigned int old_rxq = dev->real_num_rx_queues; + int err; + + if (txq < 1 || txq > dev->num_tx_queues || + rxq < 1 || rxq > dev->num_rx_queues) + return -EINVAL; + + /* Start from increases, so the error path only does decreases - + * decreases can't fail. + */ + if (rxq > dev->real_num_rx_queues) { + err = netif_set_real_num_rx_queues(dev, rxq); + if (err) + return err; + } + if (txq > dev->real_num_tx_queues) { + err = netif_set_real_num_tx_queues(dev, txq); + if (err) + goto undo_rx; + } + if (rxq < dev->real_num_rx_queues) + WARN_ON(netif_set_real_num_rx_queues(dev, rxq)); + if (txq < dev->real_num_tx_queues) + WARN_ON(netif_set_real_num_tx_queues(dev, txq)); + + return 0; +undo_rx: + WARN_ON(netif_set_real_num_rx_queues(dev, old_rxq)); + return err; +} +EXPORT_SYMBOL(netif_set_real_num_queues); + +/** + * netif_set_tso_max_size() - set the max size of TSO frames supported + * @dev: netdev to update + * @size: max skb->len of a TSO frame + * + * Set the limit on the size of TSO super-frames the device can handle. + * Unless explicitly set the stack will assume the value of + * %GSO_LEGACY_MAX_SIZE. + */ +void netif_set_tso_max_size(struct net_device *dev, unsigned int size) +{ + dev->tso_max_size = min(GSO_MAX_SIZE, size); + if (size < READ_ONCE(dev->gso_max_size)) + netif_set_gso_max_size(dev, size); +} +EXPORT_SYMBOL(netif_set_tso_max_size); + +/** + * netif_set_tso_max_segs() - set the max number of segs supported for TSO + * @dev: netdev to update + * @segs: max number of TCP segments + * + * Set the limit on the number of TCP segments the device can generate from + * a single TSO super-frame. + * Unless explicitly set the stack will assume the value of %GSO_MAX_SEGS. + */ +void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs) +{ + dev->tso_max_segs = segs; + if (segs < READ_ONCE(dev->gso_max_segs)) + netif_set_gso_max_segs(dev, segs); +} +EXPORT_SYMBOL(netif_set_tso_max_segs); + +/** + * netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper + * @to: netdev to update + * @from: netdev from which to copy the limits + */ +void netif_inherit_tso_max(struct net_device *to, const struct net_device *from) +{ + netif_set_tso_max_size(to, from->tso_max_size); + netif_set_tso_max_segs(to, from->tso_max_segs); +} +EXPORT_SYMBOL(netif_inherit_tso_max); + +/** * netif_get_num_default_rss_queues - default number of RSS queues * - * This routine should set an upper limit on the number of RSS queues - * used by default by multiqueue devices. + * Default value is the number of physical cores if there are only 1 or 2, or + * divided by 2 if there are more. */ int netif_get_num_default_rss_queues(void) { - return is_kdump_kernel() ? - 1 : min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus()); + cpumask_var_t cpus; + int cpu, count = 0; + + if (unlikely(is_kdump_kernel() || !zalloc_cpumask_var(&cpus, GFP_KERNEL))) + return 1; + + cpumask_copy(cpus, cpu_online_mask); + for_each_cpu(cpu, cpus) { + ++count; + cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu)); + } + free_cpumask_var(cpus); + + return count > 2 ? DIV_ROUND_UP(count, 2) : count; } EXPORT_SYMBOL(netif_get_num_default_rss_queues); @@ -3016,7 +3144,7 @@ EXPORT_SYMBOL(__dev_kfree_skb_irq); void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { - if (in_irq() || irqs_disabled()) + if (in_hardirq() || irqs_disabled()) __dev_kfree_skb_irq(skb, reason); else dev_kfree_skb(skb); @@ -3072,6 +3200,12 @@ static u16 skb_tx_hash(const struct net_device *dev, qoffset = sb_dev->tc_to_txq[tc].offset; qcount = sb_dev->tc_to_txq[tc].count; + if (unlikely(!qcount)) { + net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n", + sb_dev->name, qoffset, tc); + qoffset = 0; + qcount = dev->real_num_tx_queues; + } } if (skb_rx_queue_recorded(skb)) { @@ -3119,7 +3253,7 @@ int skb_checksum_help(struct sk_buff *skb) if (skb->ip_summed == CHECKSUM_COMPLETE) goto out_set_summed; - if (unlikely(skb_shinfo(skb)->gso_size)) { + if (unlikely(skb_is_gso(skb))) { skb_warn_bad_offload(skb); return -EINVAL; } @@ -3134,12 +3268,18 @@ int skb_checksum_help(struct sk_buff *skb) } offset = skb_checksum_start_offset(skb); - BUG_ON(offset >= skb_headlen(skb)); + ret = -EINVAL; + if (WARN_ON_ONCE(offset >= skb_headlen(skb))) { + DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); + goto out; + } csum = skb_checksum(skb, offset, skb->len - offset, 0); offset += skb->csum_offset; - BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb)); - + if (WARN_ON_ONCE(offset + sizeof(__sum16) > skb_headlen(skb))) { + DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); + goto out; + } ret = skb_ensure_writable(skb, offset + sizeof(__sum16)); if (ret) goto out; @@ -3210,40 +3350,6 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) return __vlan_get_protocol(skb, type, depth); } -/** - * skb_mac_gso_segment - mac layer segmentation handler. - * @skb: buffer to segment - * @features: features for the output path (see dev->features) - */ -struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, - netdev_features_t features) -{ - struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); - struct packet_offload *ptype; - int vlan_depth = skb->mac_len; - __be16 type = skb_network_protocol(skb, &vlan_depth); - - if (unlikely(!type)) - return ERR_PTR(-EINVAL); - - __skb_pull(skb, vlan_depth); - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { - if (ptype->type == type && ptype->callbacks.gso_segment) { - segs = ptype->callbacks.gso_segment(skb, features); - break; - } - } - rcu_read_unlock(); - - __skb_push(skb, skb->data - skb_mac_header(skb)); - - return segs; -} -EXPORT_SYMBOL(skb_mac_gso_segment); - - /* openvswitch calls this on rx path, so we need a different check. */ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) @@ -3266,7 +3372,7 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. * - * Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb. + * Segmentation preserves SKB_GSO_CB_OFFSET bytes of previous skb cb. */ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) @@ -3295,7 +3401,7 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, features &= ~NETIF_F_GSO_PARTIAL; } - BUILD_BUG_ON(SKB_SGO_CB_OFFSET + + BUILD_BUG_ON(SKB_GSO_CB_OFFSET + sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb)); SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); @@ -3315,13 +3421,16 @@ EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG +static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) +{ + netdev_err(dev, "hw csum failure\n"); + skb_dump(KERN_ERR, skb, true); + dump_stack(); +} + void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { - if (net_ratelimit()) { - pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>"); - skb_dump(KERN_ERR, skb, true); - dump_stack(); - } + DO_ONCE_LITE(do_netdev_rx_csum_fault, dev, skb); } EXPORT_SYMBOL(netdev_rx_csum_fault); #endif @@ -3369,10 +3478,9 @@ static netdev_features_t net_mpls_features(struct sk_buff *skb, static netdev_features_t harmonize_features(struct sk_buff *skb, netdev_features_t features) { - int tmp; __be16 type; - type = skb_network_protocol(skb, &tmp); + type = skb_network_protocol(skb, NULL); features = net_mpls_features(skb, features, type); if (skb->ip_summed != CHECKSUM_NONE && @@ -3406,8 +3514,13 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, { u16 gso_segs = skb_shinfo(skb)->gso_segs; - if (gso_segs > dev->gso_max_segs) + if (gso_segs > READ_ONCE(dev->gso_max_segs)) + return features & ~NETIF_F_GSO_MASK; + + if (!skb_shinfo(skb)->gso_type) { + skb_warn_bad_offload(skb); return features & ~NETIF_F_GSO_MASK; + } /* Support for GSO partial features requires software * intervention before we can actually process the packets @@ -3520,11 +3633,22 @@ static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features) { - if (unlikely(skb->csum_not_inet)) + if (unlikely(skb_csum_is_sctp(skb))) return !!(features & NETIF_F_SCTP_CRC) ? 0 : skb_crc32c_csum_help(skb); - return !!(features & NETIF_F_CSUM_MASK) ? 0 : skb_checksum_help(skb); + if (features & NETIF_F_HW_CSUM) + return 0; + + if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { + switch (skb->csum_offset) { + case offsetof(struct tcphdr, check): + case offsetof(struct udphdr, check): + return 0; + } + } + + return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); @@ -3579,7 +3703,7 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device out_kfree_skb: kfree_skb(skb); out_null: - atomic_long_inc(&dev->tx_dropped); + dev_core_stats_tx_dropped_inc(dev); return NULL; } @@ -3652,6 +3776,18 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) } } +static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q, + struct sk_buff **to_free, + struct netdev_queue *txq) +{ + int rc; + + rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK; + if (rc == NET_XMIT_SUCCESS) + trace_qdisc_enqueue(q, txq, skb); + return rc; +} + static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) @@ -3664,11 +3800,35 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) && + qdisc_run_begin(q)) { + /* Retest nolock_qdisc_is_empty() within the protection + * of q->seqlock to protect from racing with requeuing. + */ + if (unlikely(!nolock_qdisc_is_empty(q))) { + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); + __qdisc_run(q); + qdisc_run_end(q); + + goto no_lock_out; + } + + qdisc_bstats_cpu_update(q, skb); + if (sch_direct_xmit(skb, q, dev, txq, NULL, true) && + !nolock_qdisc_is_empty(q)) + __qdisc_run(q); + + qdisc_run_end(q); + return NET_XMIT_SUCCESS; + } + + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); qdisc_run(q); +no_lock_out: if (unlikely(to_free)) - kfree_skb_list(to_free); + kfree_skb_list_reason(to_free, + SKB_DROP_REASON_QDISC_DROP); return rc; } @@ -3677,8 +3837,12 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, * separate lock before trying to get qdisc main lock. * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. + * On PREEMPT_RT it is possible to preempt the qdisc owner during xmit + * and then other tasks will only enqueue packets. The packets will be + * sent after the qdisc owner is scheduled again. To prevent this + * scenario the task always serialize on the lock. */ - contended = qdisc_is_running(q); + contended = qdisc_is_running(q) || IS_ENABLED(CONFIG_PREEMPT_RT); if (unlikely(contended)) spin_lock(&q->busylock); @@ -3707,7 +3871,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -3719,7 +3883,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, } spin_unlock(root_lock); if (unlikely(to_free)) - kfree_skb_list(to_free); + kfree_skb_list_reason(to_free, SKB_DROP_REASON_QDISC_DROP); if (unlikely(contended)) spin_unlock(&q->busylock); return rc; @@ -3761,10 +3925,11 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); skb->pkt_type = PACKET_LOOPBACK; - skb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!skb_dst(skb)); + if (skb->ip_summed == CHECKSUM_NONE) + skb->ip_summed = CHECKSUM_UNNECESSARY; + DEBUG_NET_WARN_ON_ONCE(!skb_dst(skb)); skb_dst_force(skb); - netif_rx_ni(skb); + netif_rx(skb); return 0; } EXPORT_SYMBOL(dev_loopback_xmit); @@ -3773,6 +3938,7 @@ EXPORT_SYMBOL(dev_loopback_xmit); static struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { +#ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress); struct tcf_result cl_res; @@ -3780,9 +3946,11 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) return skb; /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */ + tc_skb_cb(skb)->mru = 0; + tc_skb_cb(skb)->post_ct = false; mini_qdisc_bstats_cpu_update(miniq, skb); - switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { + switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); @@ -3790,7 +3958,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) case TC_ACT_SHOT: mini_qdisc_qstats_cpu_drop(miniq); *ret = NET_XMIT_DROP; - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_TC_EGRESS); return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: @@ -3806,22 +3974,44 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) default: break; } +#endif /* CONFIG_NET_CLS_ACT */ return skb; } + +static struct netdev_queue * +netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) +{ + int qm = skb_get_queue_mapping(skb); + + return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); +} + +static bool netdev_xmit_txqueue_skipped(void) +{ + return __this_cpu_read(softnet_data.xmit.skip_txqueue); +} + +void netdev_xmit_skip_txqueue(bool skip) +{ + __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); +} +EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); #endif /* CONFIG_NET_EGRESS */ #ifdef CONFIG_XPS 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) { @@ -3852,18 +4042,18 @@ 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; @@ -3949,43 +4139,39 @@ struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, } /** - * __dev_queue_xmit - transmit a buffer - * @skb: buffer to transmit - * @sb_dev: suboordinate device used for L2 forwarding offload + * __dev_queue_xmit() - transmit a buffer + * @skb: buffer to transmit + * @sb_dev: suboordinate device used for L2 forwarding offload * - * Queue a buffer for transmission to a network device. The caller must - * have set the device and priority and built the buffer before calling - * this function. The function can be called from an interrupt. + * Queue a buffer for transmission to a network device. The caller must + * have set the device and priority and built the buffer before calling + * this function. The function can be called from an interrupt. * - * A negative errno code is returned on a failure. A success does not - * guarantee the frame will be transmitted as it may be dropped due - * to congestion or traffic shaping. + * When calling this method, interrupts MUST be enabled. This is because + * the BH enable code must have IRQs enabled so that it will not deadlock. * - * ----------------------------------------------------------------------------------- - * I notice this method can also return errors from the queue disciplines, - * including NET_XMIT_DROP, which is a positive value. So, errors can also - * be positive. + * Regardless of the return value, the skb is consumed, so it is currently + * difficult to retry a send to this method. (You can bump the ref count + * before sending to hold a reference for retry if you are careful.) * - * Regardless of the return value, the skb is consumed, so it is currently - * difficult to retry a send to this method. (You can bump the ref count - * before sending to hold a reference for retry if you are careful.) - * - * When calling this method, interrupts MUST be enabled. This is because - * the BH enable code must have IRQs enabled so that it will not deadlock. - * --BLG + * Return: + * * 0 - buffer successfully transmitted + * * positive qdisc return code - NET_XMIT_DROP etc. + * * negative errno - other errors */ -static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) +int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) { struct net_device *dev = skb->dev; - struct netdev_queue *txq; + struct netdev_queue *txq = NULL; struct Qdisc *q; int rc = -ENOMEM; bool again = false; skb_reset_mac_header(skb); + skb_assert_len(skb); if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP)) - __skb_tstamp_tx(skb, NULL, skb->sk, SCM_TSTAMP_SCHED); + __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); /* Disable soft irqs for various locks below. Also * stops preemption for RCU. @@ -3997,13 +4183,26 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT skb->tc_at_ingress = 0; -# ifdef CONFIG_NET_EGRESS +#endif +#ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { + if (nf_hook_egress_active()) { + skb = nf_hook_egress(skb, &rc, dev); + if (!skb) + goto out; + } + + netdev_xmit_skip_txqueue(false); + + nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; + nf_skip_egress(skb, false); + + if (netdev_xmit_txqueue_skipped()) + txq = netdev_tx_queue_mapping(dev, skb); } -# endif #endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. @@ -4013,7 +4212,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) else skb_dst_force(skb); - txq = netdev_core_pick_tx(dev, skb, sb_dev); + if (!txq) + txq = netdev_core_pick_tx(dev, skb, sb_dev); + q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); @@ -4037,7 +4238,10 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ - if (txq->xmit_lock_owner != cpu) { + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + if (READ_ONCE(txq->xmit_lock_owner) != cpu) { if (dev_xmit_recursion()) goto recursion_alert; @@ -4072,27 +4276,16 @@ recursion_alert: rc = -ENETDOWN; rcu_read_unlock_bh(); - atomic_long_inc(&dev->tx_dropped); + dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return rc; out: rcu_read_unlock_bh(); return rc; } +EXPORT_SYMBOL(__dev_queue_xmit); -int dev_queue_xmit(struct sk_buff *skb) -{ - return __dev_queue_xmit(skb, NULL); -} -EXPORT_SYMBOL(dev_queue_xmit); - -int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) -{ - return __dev_queue_xmit(skb, sb_dev); -} -EXPORT_SYMBOL(dev_queue_xmit_accel); - -int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb; @@ -4113,23 +4306,21 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) local_bh_disable(); + dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); + dev_xmit_recursion_dec(); local_bh_enable(); - - if (!dev_xmit_complete(ret)) - kfree_skb(skb); - return ret; drop: - atomic_long_inc(&dev->tx_dropped); + dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return NET_XMIT_DROP; } -EXPORT_SYMBOL(dev_direct_xmit); +EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines @@ -4139,20 +4330,45 @@ int netdev_max_backlog __read_mostly = 1000; EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; +unsigned int sysctl_skb_defer_max __read_mostly = 64; int netdev_budget __read_mostly = 300; -unsigned int __read_mostly netdev_budget_usecs = 2000; +/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ +unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ; 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; -/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ -int gro_normal_batch __read_mostly = 8; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, struct napi_struct *napi) { + struct task_struct *thread; + + lockdep_assert_irqs_disabled(); + + if (test_bit(NAPI_STATE_THREADED, &napi->state)) { + /* Paired with smp_mb__before_atomic() in + * napi_enable()/dev_set_threaded(). + * Use READ_ONCE() to guarantee a complete + * read on napi->thread. Only call + * wake_up_process() when it's not NULL. + */ + thread = READ_ONCE(napi->thread); + if (thread) { + /* Avoid doing set_bit() if the thread is in + * INTERRUPTIBLE state, cause napi_thread_wait() + * makes sure to proceed with napi polling + * if the thread is explicitly woken from here. + */ + if (READ_ONCE(thread->__state) != TASK_INTERRUPTIBLE) + set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); + wake_up_process(thread); + return; + } + } + list_add_tail(&napi->poll_list, &sd->poll_list); __raise_softirq_irqoff(NET_RX_SOFTIRQ); } @@ -4366,16 +4582,25 @@ static void rps_trigger_softirq(void *data) #endif /* CONFIG_RPS */ +/* Called from hardirq (IPI) context */ +static void trigger_rx_softirq(void *data) +{ + struct softnet_data *sd = data; + + __raise_softirq_irqoff(NET_RX_SOFTIRQ); + smp_store_release(&sd->defer_ipi_scheduled, 0); +} + /* * Check if this softnet_data structure is another cpu one * If yes, queue it to our IPI list and return 1 * If no, return 0 */ -static int rps_ipi_queued(struct softnet_data *sd) +static int napi_schedule_rps(struct softnet_data *sd) { -#ifdef CONFIG_RPS struct softnet_data *mysd = this_cpu_ptr(&softnet_data); +#ifdef CONFIG_RPS if (sd != mysd) { sd->rps_ipi_next = mysd->rps_ipi_list; mysd->rps_ipi_list = sd; @@ -4384,6 +4609,7 @@ static int rps_ipi_queued(struct softnet_data *sd) return 1; } #endif /* CONFIG_RPS */ + __napi_schedule_irqoff(&mysd->backlog); return 0; } @@ -4398,7 +4624,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) struct softnet_data *sd; unsigned int old_flow, new_flow; - if (qlen < (netdev_max_backlog >> 1)) + if (qlen < (READ_ONCE(netdev_max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); @@ -4434,46 +4660,42 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) static int enqueue_to_backlog(struct sk_buff *skb, int cpu, unsigned int *qtail) { + enum skb_drop_reason reason; struct softnet_data *sd; unsigned long flags; unsigned int qlen; + reason = SKB_DROP_REASON_NOT_SPECIFIED; sd = &per_cpu(softnet_data, cpu); - local_irq_save(flags); - - rps_lock(sd); + rps_lock_irqsave(sd, &flags); if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) { + if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) { if (qlen) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); input_queue_tail_incr_save(sd, qtail); - rps_unlock(sd); - local_irq_restore(flags); + rps_unlock_irq_restore(sd, &flags); return NET_RX_SUCCESS; } /* Schedule NAPI for backlog device * We can use non atomic operation since we own the queue lock */ - if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) { - if (!rps_ipi_queued(sd)) - ____napi_schedule(sd, &sd->backlog); - } + if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) + napi_schedule_rps(sd); goto enqueue; } + reason = SKB_DROP_REASON_CPU_BACKLOG; drop: sd->dropped++; - rps_unlock(sd); - - local_irq_restore(flags); + rps_unlock_irq_restore(sd, &flags); - atomic_long_inc(&skb->dev->rx_dropped); - kfree_skb(skb); + dev_core_stats_rx_dropped_inc(skb->dev); + kfree_skb_reason(skb, reason); return NET_RX_DROP; } @@ -4500,63 +4722,40 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) return rxqueue; } -static u32 netif_receive_generic_xdp(struct sk_buff *skb, - struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) +u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) { + void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; - void *orig_data, *orig_data_end; - u32 metalen, act = XDP_DROP; + bool orig_bcast, orig_host; + u32 mac_len, frame_sz; __be16 orig_eth_type; struct ethhdr *eth; - bool orig_bcast; - int hlen, off; - u32 mac_len; - - /* Reinjected packets coming from act_mirred or similar should - * not get XDP generic processing. - */ - if (skb_is_tc_redirected(skb)) - return XDP_PASS; - - /* XDP packets must be linear and must have sufficient headroom - * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also - * native XDP provides, thus we need to do it here as well. - */ - if (skb_cloned(skb) || skb_is_nonlinear(skb) || - skb_headroom(skb) < XDP_PACKET_HEADROOM) { - int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); - int troom = skb->tail + skb->data_len - skb->end; - - /* In case we have to go down the path and also linearize, - * then lets do the pskb_expand_head() work just once here. - */ - if (pskb_expand_head(skb, - hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, - troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) - goto do_drop; - if (skb_linearize(skb)) - goto do_drop; - } + u32 metalen, act; + int off; /* The XDP program wants to see the packet starting at the MAC * header. */ mac_len = skb->data - skb_mac_header(skb); - hlen = skb_headlen(skb) + mac_len; - xdp->data = skb->data - mac_len; - xdp->data_meta = xdp->data; - xdp->data_end = xdp->data + hlen; - xdp->data_hard_start = skb->data - skb_headroom(skb); + hard_start = skb->data - skb_headroom(skb); + + /* SKB "head" area always have tailroom for skb_shared_info */ + frame_sz = (void *)skb_end_pointer(skb) - hard_start; + frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + rxqueue = netif_get_rxqueue(skb); + xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); + xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, + skb_headlen(skb) + mac_len, true); + orig_data_end = xdp->data_end; orig_data = xdp->data; eth = (struct ethhdr *)xdp->data; + orig_host = ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr); orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest); orig_eth_type = eth->h_proto; - rxqueue = netif_get_rxqueue(skb); - xdp->rxq = &rxqueue->xdp_rxq; - act = bpf_prog_run_xdp(xdp_prog, xdp); /* check if bpf_xdp_adjust_head was used */ @@ -4571,24 +4770,31 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, skb_reset_network_header(skb); } - /* check if bpf_xdp_adjust_tail was used. it can only "shrink" - * pckt. - */ - off = orig_data_end - xdp->data_end; + /* check if bpf_xdp_adjust_tail was used */ + off = xdp->data_end - orig_data_end; if (off != 0) { skb_set_tail_pointer(skb, xdp->data_end - xdp->data); - skb->len -= off; - + skb->len += off; /* positive on grow, negative on shrink */ } /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; if ((orig_eth_type != eth->h_proto) || + (orig_host != ether_addr_equal_64bits(eth->h_dest, + skb->dev->dev_addr)) || (orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) { __skb_push(skb, ETH_HLEN); + skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); } + /* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull + * before calling us again on redirect path. We do not call do_redirect + * as we leave that up to the caller. + * + * Caller is responsible for managing lifetime of skb (i.e. calling + * kfree_skb in response to actions it cannot handle/XDP_DROP). + */ switch (act) { case XDP_REDIRECT: case XDP_TX: @@ -4599,12 +4805,55 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, if (metalen) skb_metadata_set(skb, metalen); break; + } + + return act; +} + +static u32 netif_receive_generic_xdp(struct sk_buff *skb, + struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) +{ + u32 act = XDP_DROP; + + /* Reinjected packets coming from act_mirred or similar should + * not get XDP generic processing. + */ + if (skb_is_redirected(skb)) + return XDP_PASS; + + /* XDP packets must be linear and must have sufficient headroom + * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also + * native XDP provides, thus we need to do it here as well. + */ + if (skb_cloned(skb) || skb_is_nonlinear(skb) || + skb_headroom(skb) < XDP_PACKET_HEADROOM) { + int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); + int troom = skb->tail + skb->data_len - skb->end; + + /* In case we have to go down the path and also linearize, + * then lets do the pskb_expand_head() work just once here. + */ + if (pskb_expand_head(skb, + hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, + troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) + goto do_drop; + if (skb_linearize(skb)) + goto do_drop; + } + + act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog); + switch (act) { + case XDP_REDIRECT: + case XDP_TX: + case XDP_PASS: + break; default: - bpf_warn_invalid_xdp_action(act); - /* fall through */ + bpf_warn_invalid_xdp_action(skb->dev, xdp_prog, act); + fallthrough; case XDP_ABORTED: trace_xdp_exception(skb->dev, xdp_prog, act); - /* fall through */ + fallthrough; case XDP_DROP: do_drop: kfree_skb(skb); @@ -4615,7 +4864,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, } /* When doing generic XDP we have to bypass the qdisc layer and the - * network taps in order to match in-driver-XDP behavior. + * network taps in order to match in-driver-XDP behavior. This also means + * that XDP packets are able to starve other packets going through a qdisc, + * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX + * queues, so they do not have this starvation issue. */ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) { @@ -4627,7 +4879,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); - if (!netif_xmit_stopped(txq)) { + if (!netif_xmit_frozen_or_drv_stopped(txq)) { rc = netdev_start_xmit(skb, dev, txq, 0); if (dev_xmit_complete(rc)) free_skb = false; @@ -4635,10 +4887,10 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) HARD_TX_UNLOCK(dev, txq); if (free_skb) { trace_xdp_exception(dev, xdp_prog, XDP_TX); + dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); } } -EXPORT_SYMBOL_GPL(generic_xdp_tx); static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); @@ -4667,7 +4919,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb) } return XDP_PASS; out_redir: - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_XDP); return XDP_DROP; } EXPORT_SYMBOL_GPL(do_xdp_generic); @@ -4676,7 +4928,7 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_rx(skb); @@ -4685,7 +4937,6 @@ static int netif_rx_internal(struct sk_buff *skb) struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; - preempt_disable(); rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -4695,63 +4946,72 @@ static int netif_rx_internal(struct sk_buff *skb) ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - preempt_enable(); } else #endif { unsigned int qtail; - ret = enqueue_to_backlog(skb, get_cpu(), &qtail); - put_cpu(); + ret = enqueue_to_backlog(skb, smp_processor_id(), &qtail); } return ret; } /** + * __netif_rx - Slightly optimized version of netif_rx + * @skb: buffer to post + * + * This behaves as netif_rx except that it does not disable bottom halves. + * As a result this function may only be invoked from the interrupt context + * (either hard or soft interrupt). + */ +int __netif_rx(struct sk_buff *skb) +{ + int ret; + + lockdep_assert_once(hardirq_count() | softirq_count()); + + trace_netif_rx_entry(skb); + ret = netif_rx_internal(skb); + trace_netif_rx_exit(ret); + return ret; +} +EXPORT_SYMBOL(__netif_rx); + +/** * netif_rx - post buffer to the network code * @skb: buffer to post * * This function receives a packet from a device driver and queues it for - * the upper (protocol) levels to process. It always succeeds. The buffer - * may be dropped during processing for congestion control or by the - * protocol layers. + * the upper (protocol) levels to process via the backlog NAPI device. It + * always succeeds. The buffer may be dropped during processing for + * congestion control or by the protocol layers. + * The network buffer is passed via the backlog NAPI device. Modern NIC + * driver should use NAPI and GRO. + * This function can used from interrupt and from process context. The + * caller from process context must not disable interrupts before invoking + * this function. * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped) * */ - int netif_rx(struct sk_buff *skb) { + bool need_bh_off = !(hardirq_count() | softirq_count()); int ret; + if (need_bh_off) + local_bh_disable(); trace_netif_rx_entry(skb); - ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); - + if (need_bh_off) + local_bh_enable(); return ret; } EXPORT_SYMBOL(netif_rx); -int netif_rx_ni(struct sk_buff *skb) -{ - int err; - - trace_netif_rx_ni_entry(skb); - - preempt_disable(); - err = netif_rx_internal(skb); - if (local_softirq_pending()) - do_softirq(); - preempt_enable(); - trace_netif_rx_ni_exit(err); - - return err; -} -EXPORT_SYMBOL(netif_rx_ni); - static __latent_entropy void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); @@ -4773,15 +5033,14 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) trace_consume_skb(skb); else - trace_kfree_skb(skb, net_tx_action); + trace_kfree_skb(skb, net_tx_action, + SKB_DROP_REASON_NOT_SPECIFIED); if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); else __kfree_skb_defer(skb); } - - __kfree_skb_flush(); } if (sd->output_queue) { @@ -4793,25 +5052,43 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); + rcu_read_lock(); + while (head) { struct Qdisc *q = head; spinlock_t *root_lock = NULL; head = head->next_sched; - if (!(q->flags & TCQ_F_NOLOCK)) { - root_lock = qdisc_lock(q); - spin_lock(root_lock); - } /* We need to make sure head->next_sched is read * before clearing __QDISC_STATE_SCHED */ smp_mb__before_atomic(); + + if (!(q->flags & TCQ_F_NOLOCK)) { + root_lock = qdisc_lock(q); + spin_lock(root_lock); + } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, + &q->state))) { + /* There is a synchronize_net() between + * STATE_DEACTIVATED flag being set and + * qdisc_reset()/some_qdisc_is_busy() in + * dev_deactivate(), so we can safely bail out + * early here to avoid data race between + * qdisc_deactivate() and some_qdisc_is_busy() + * for lockless qdisc. + */ + clear_bit(__QDISC_STATE_SCHED, &q->state); + continue; + } + clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); if (root_lock) spin_unlock(root_lock); } + + rcu_read_unlock(); } xfrm_dev_backlog(sd); @@ -4826,7 +5103,7 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); static inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, - struct net_device *orig_dev) + struct net_device *orig_dev, bool *another) { #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress); @@ -4846,22 +5123,26 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, } qdisc_skb_cb(skb)->pkt_len = skb->len; + tc_skb_cb(skb)->mru = 0; + tc_skb_cb(skb)->post_ct = false; skb->tc_at_ingress = 1; mini_qdisc_bstats_cpu_update(miniq, skb); - switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { + switch (tcf_classify(skb, miniq->block, miniq->filter_list, &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); break; case TC_ACT_SHOT: mini_qdisc_qstats_cpu_drop(miniq); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS); + *ret = NET_RX_DROP; return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_REDIRECT: /* skb_mac_header check was done by cls/act_bpf, so @@ -4869,9 +5150,15 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, * redirecting to another netdev */ __skb_push(skb, skb->mac_len); - skb_do_redirect(skb); + if (skb_do_redirect(skb) == -EAGAIN) { + __skb_pull(skb, skb->mac_len); + *another = true; + break; + } + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_CONSUMED: + *ret = NET_RX_SUCCESS; return NULL; default: break; @@ -4987,17 +5274,18 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, return 0; } -static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc, +static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, struct packet_type **ppt_prev) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; + struct sk_buff *skb = *pskb; struct net_device *orig_dev; bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; - net_timestamp_check(!netdev_tstamp_prequeue, skb); + net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_receive_skb(skb); @@ -5018,17 +5306,17 @@ another_round: if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret2; - preempt_disable(); + migrate_disable(); ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); - preempt_enable(); + migrate_enable(); - if (ret2 != XDP_PASS) - return NET_RX_DROP; - skb_reset_mac_len(skb); + if (ret2 != XDP_PASS) { + ret = NET_RX_DROP; + goto out; + } } - if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || - skb->protocol == cpu_to_be16(ETH_P_8021AD)) { + if (eth_type_vlan(skb->protocol)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; @@ -5055,15 +5343,22 @@ another_round: skip_taps: #ifdef CONFIG_NET_INGRESS if (static_branch_unlikely(&ingress_needed_key)) { - skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev); + bool another = false; + + nf_skip_egress(skb, true); + skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, + &another); + if (another) + goto another_round; if (!skb) goto out; + nf_skip_egress(skb, false); if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) goto out; } #endif - skb_reset_tc(skb); + skb_reset_redirect(skb); skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; @@ -5093,6 +5388,7 @@ skip_classify: goto another_round; case RX_HANDLER_EXACT: deliver_exact = true; + break; case RX_HANDLER_PASS: break; default: @@ -5100,15 +5396,14 @@ skip_classify: } } - if (unlikely(skb_vlan_tag_present(skb))) { + if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) { check_vlan_id: if (skb_vlan_tag_get_id(skb)) { /* Vlan id is non 0 and vlan_do_receive() above couldn't * find vlan device. */ skb->pkt_type = PACKET_OTHERHOST; - } else if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || - skb->protocol == cpu_to_be16(ETH_P_8021AD)) { + } else if (eth_type_vlan(skb->protocol)) { /* Outer header is 802.1P with vlan 0, inner header is * 802.1Q or 802.1AD and vlan_do_receive() above could * not find vlan dev for vlan id 0. @@ -5162,10 +5457,10 @@ check_vlan_id: } else { drop: if (!deliver_exact) - atomic_long_inc(&skb->dev->rx_dropped); + dev_core_stats_rx_dropped_inc(skb->dev); else - atomic_long_inc(&skb->dev->rx_nohandler); - kfree_skb(skb); + dev_core_stats_rx_nohandler_inc(skb->dev); + kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) */ @@ -5173,6 +5468,13 @@ drop: } out: + /* The invariant here is that if *ppt_prev is not NULL + * then skb should also be non-NULL. + * + * Apparently *ppt_prev assignment above holds this invariant due to + * skb dereferencing near it. + */ + *pskb = skb; return ret; } @@ -5182,7 +5484,7 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) struct packet_type *pt_prev = NULL; int ret; - ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev); + ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (pt_prev) ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb, skb->dev, pt_prev, orig_dev); @@ -5195,7 +5497,7 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) * * More direct receive version of netif_receive_skb(). It should * only be used by callers that have a need to skip RPS and Generic XDP. - * Caller must also take care of handling if (page_is_)pfmemalloc. + * Caller must also take care of handling if ``(page_is_)pfmemalloc``. * * This function may only be called from softirq context and interrupts * should be enabled. @@ -5260,7 +5562,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo struct packet_type *pt_prev = NULL; skb_list_del_init(skb); - __netif_receive_skb_core(skb, pfmemalloc, &pt_prev); + __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (!pt_prev) continue; if (pt_curr != pt_prev || od_curr != orig_dev) { @@ -5354,10 +5656,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) } break; - case XDP_QUERY_PROG: - xdp->prog_id = old ? old->aux->id : 0; - break; - default: ret = -EINVAL; break; @@ -5370,7 +5668,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; @@ -5393,14 +5691,14 @@ static int netif_receive_skb_internal(struct sk_buff *skb) return ret; } -static void netif_receive_skb_list_internal(struct list_head *head) +void netif_receive_skb_list_internal(struct list_head *head) { struct sk_buff *skb, *next; struct list_head sublist; INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); @@ -5479,7 +5777,7 @@ void netif_receive_skb_list(struct list_head *head) } EXPORT_SYMBOL(netif_receive_skb_list); -DEFINE_PER_CPU(struct work_struct, flush_works); +static DEFINE_PER_CPU(struct work_struct, flush_works); /* Network device is going away, flush any packets still pending */ static void flush_backlog(struct work_struct *work) @@ -5490,17 +5788,15 @@ static void flush_backlog(struct work_struct *work) local_bh_disable(); sd = this_cpu_ptr(&softnet_data); - local_irq_disable(); - rps_lock(sd); + rps_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); - kfree_skb(skb); + dev_kfree_skb_irq(skb); input_queue_head_incr(sd); } } - rps_unlock(sd); - local_irq_enable(); + rps_unlock_irq_enable(sd); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { @@ -5512,560 +5808,62 @@ static void flush_backlog(struct work_struct *work) local_bh_enable(); } -static void flush_all_backlogs(void) -{ - unsigned int cpu; - - get_online_cpus(); - - for_each_online_cpu(cpu) - queue_work_on(cpu, system_highpri_wq, - per_cpu_ptr(&flush_works, cpu)); - - for_each_online_cpu(cpu) - flush_work(per_cpu_ptr(&flush_works, cpu)); - - put_online_cpus(); -} - -/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ -static void gro_normal_list(struct napi_struct *napi) -{ - if (!napi->rx_count) - return; - netif_receive_skb_list_internal(&napi->rx_list); - INIT_LIST_HEAD(&napi->rx_list); - napi->rx_count = 0; -} - -/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, - * pass the whole batch up to the stack. - */ -static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) -{ - list_add_tail(&skb->list, &napi->rx_list); - if (++napi->rx_count >= gro_normal_batch) - gro_normal_list(napi); -} - -INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); -INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int)); -static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) -{ - struct packet_offload *ptype; - __be16 type = skb->protocol; - struct list_head *head = &offload_base; - int err = -ENOENT; - - BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); - - if (NAPI_GRO_CB(skb)->count == 1) { - skb_shinfo(skb)->gso_size = 0; - goto out; - } - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->callbacks.gro_complete) - continue; - - err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, - ipv6_gro_complete, inet_gro_complete, - skb, 0); - break; - } - rcu_read_unlock(); - - if (err) { - WARN_ON(&ptype->list == head); - kfree_skb(skb); - return NET_RX_SUCCESS; - } - -out: - gro_normal_one(napi, skb); - return NET_RX_SUCCESS; -} - -static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, - bool flush_old) -{ - struct list_head *head = &napi->gro_hash[index].list; - struct sk_buff *skb, *p; - - list_for_each_entry_safe_reverse(skb, p, head, list) { - if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) - return; - skb_list_del_init(skb); - napi_gro_complete(napi, skb); - napi->gro_hash[index].count--; - } - - if (!napi->gro_hash[index].count) - __clear_bit(index, &napi->gro_bitmask); -} - -/* napi->gro_hash[].list contains packets ordered by age. - * youngest packets at the head of it. - * Complete skbs in reverse order to reduce latencies. - */ -void napi_gro_flush(struct napi_struct *napi, bool flush_old) -{ - unsigned long bitmask = napi->gro_bitmask; - unsigned int i, base = ~0U; - - while ((i = ffs(bitmask)) != 0) { - bitmask >>= i; - base += i; - __napi_gro_flush_chain(napi, base, flush_old); - } -} -EXPORT_SYMBOL(napi_gro_flush); - -static struct list_head *gro_list_prepare(struct napi_struct *napi, - struct sk_buff *skb) -{ - unsigned int maclen = skb->dev->hard_header_len; - u32 hash = skb_get_hash_raw(skb); - struct list_head *head; - struct sk_buff *p; - - head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)].list; - list_for_each_entry(p, head, list) { - unsigned long diffs; - - NAPI_GRO_CB(p)->flush = 0; - - if (hash != skb_get_hash_raw(p)) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - - diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; - diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); - if (skb_vlan_tag_present(p)) - diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); - diffs |= skb_metadata_dst_cmp(p, skb); - diffs |= skb_metadata_differs(p, skb); - if (maclen == ETH_HLEN) - diffs |= compare_ether_header(skb_mac_header(p), - skb_mac_header(skb)); - else if (!diffs) - diffs = memcmp(skb_mac_header(p), - skb_mac_header(skb), - maclen); - NAPI_GRO_CB(p)->same_flow = !diffs; - } - - return head; -} - -static void skb_gro_reset_offset(struct sk_buff *skb) -{ - const struct skb_shared_info *pinfo = skb_shinfo(skb); - const skb_frag_t *frag0 = &pinfo->frags[0]; - - NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; - - if (!skb_headlen(skb) && pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0))) { - NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); - NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, - skb_frag_size(frag0), - skb->end - skb->tail); - } -} - -static void gro_pull_from_frag0(struct sk_buff *skb, int grow) -{ - struct skb_shared_info *pinfo = skb_shinfo(skb); - - BUG_ON(skb->end - skb->tail < grow); - - memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); - - skb->data_len -= grow; - skb->tail += grow; - - skb_frag_off_add(&pinfo->frags[0], grow); - skb_frag_size_sub(&pinfo->frags[0], grow); - - if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { - skb_frag_unref(skb, 0); - memmove(pinfo->frags, pinfo->frags + 1, - --pinfo->nr_frags * sizeof(pinfo->frags[0])); - } -} - -static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) +static bool flush_required(int cpu) { - struct sk_buff *oldest; +#if IS_ENABLED(CONFIG_RPS) + struct softnet_data *sd = &per_cpu(softnet_data, cpu); + bool do_flush; - oldest = list_last_entry(head, struct sk_buff, list); + rps_lock_irq_disable(sd); - /* We are called with head length >= MAX_GRO_SKBS, so this is - * impossible. + /* as insertion into process_queue happens with the rps lock held, + * process_queue access may race only with dequeue */ - if (WARN_ON_ONCE(!oldest)) - return; + do_flush = !skb_queue_empty(&sd->input_pkt_queue) || + !skb_queue_empty_lockless(&sd->process_queue); + rps_unlock_irq_enable(sd); - /* Do not adjust napi->gro_hash[].count, caller is adding a new - * SKB to the chain. + return do_flush; +#endif + /* without RPS we can't safely check input_pkt_queue: during a + * concurrent remote skb_queue_splice() we can detect as empty both + * input_pkt_queue and process_queue even if the latter could end-up + * containing a lot of packets. */ - skb_list_del_init(oldest); - napi_gro_complete(napi, oldest); -} - -INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *, - struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *, - struct sk_buff *)); -static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) -{ - u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); - struct list_head *head = &offload_base; - struct packet_offload *ptype; - __be16 type = skb->protocol; - struct list_head *gro_head; - struct sk_buff *pp = NULL; - enum gro_result ret; - int same_flow; - int grow; - - if (netif_elide_gro(skb->dev)) - goto normal; - - gro_head = gro_list_prepare(napi, skb); - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->callbacks.gro_receive) - continue; - - 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 = 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; - NAPI_GRO_CB(skb)->is_fou = 0; - NAPI_GRO_CB(skb)->is_atomic = 1; - NAPI_GRO_CB(skb)->gro_remcsum_start = 0; - - /* Setup for GRO checksum validation */ - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - NAPI_GRO_CB(skb)->csum = skb->csum; - NAPI_GRO_CB(skb)->csum_valid = 1; - NAPI_GRO_CB(skb)->csum_cnt = 0; - break; - case CHECKSUM_UNNECESSARY: - NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; - NAPI_GRO_CB(skb)->csum_valid = 0; - break; - default: - NAPI_GRO_CB(skb)->csum_cnt = 0; - NAPI_GRO_CB(skb)->csum_valid = 0; - } - - pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, - ipv6_gro_receive, inet_gro_receive, - gro_head, skb); - break; - } - rcu_read_unlock(); - - if (&ptype->list == head) - goto normal; - - if (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; - - if (pp) { - skb_list_del_init(pp); - napi_gro_complete(napi, pp); - napi->gro_hash[hash].count--; - } - - if (same_flow) - goto ok; - - if (NAPI_GRO_CB(skb)->flush) - goto normal; - - if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) { - gro_flush_oldest(napi, gro_head); - } else { - napi->gro_hash[hash].count++; - } - NAPI_GRO_CB(skb)->count = 1; - NAPI_GRO_CB(skb)->age = jiffies; - NAPI_GRO_CB(skb)->last = skb; - skb_shinfo(skb)->gso_size = skb_gro_len(skb); - list_add(&skb->list, gro_head); - ret = GRO_HELD; - -pull: - grow = skb_gro_offset(skb) - skb_headlen(skb); - if (grow > 0) - gro_pull_from_frag0(skb, grow); -ok: - if (napi->gro_hash[hash].count) { - if (!test_bit(hash, &napi->gro_bitmask)) - __set_bit(hash, &napi->gro_bitmask); - } else if (test_bit(hash, &napi->gro_bitmask)) { - __clear_bit(hash, &napi->gro_bitmask); - } - - return ret; - -normal: - ret = GRO_NORMAL; - goto pull; -} - -struct packet_offload *gro_find_receive_by_type(__be16 type) -{ - struct list_head *offload_head = &offload_base; - struct packet_offload *ptype; - - list_for_each_entry_rcu(ptype, offload_head, list) { - if (ptype->type != type || !ptype->callbacks.gro_receive) - continue; - return ptype; - } - return NULL; -} -EXPORT_SYMBOL(gro_find_receive_by_type); - -struct packet_offload *gro_find_complete_by_type(__be16 type) -{ - struct list_head *offload_head = &offload_base; - struct packet_offload *ptype; - - list_for_each_entry_rcu(ptype, offload_head, list) { - if (ptype->type != type || !ptype->callbacks.gro_complete) - continue; - return ptype; - } - return NULL; -} -EXPORT_SYMBOL(gro_find_complete_by_type); - -static void napi_skb_free_stolen_head(struct sk_buff *skb) -{ - skb_dst_drop(skb); - skb_ext_put(skb); - kmem_cache_free(skbuff_head_cache, skb); -} - -static gro_result_t napi_skb_finish(struct napi_struct *napi, - struct sk_buff *skb, - gro_result_t ret) -{ - switch (ret) { - case GRO_NORMAL: - gro_normal_one(napi, skb); - break; - - case GRO_DROP: - kfree_skb(skb); - break; - - case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) - napi_skb_free_stolen_head(skb); - else - __kfree_skb(skb); - break; - - case GRO_HELD: - case GRO_MERGED: - case GRO_CONSUMED: - break; - } - - return ret; -} - -gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) -{ - gro_result_t ret; - - skb_mark_napi_id(skb, napi); - trace_napi_gro_receive_entry(skb); - - skb_gro_reset_offset(skb); - - ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); - trace_napi_gro_receive_exit(ret); - - return ret; -} -EXPORT_SYMBOL(napi_gro_receive); - -static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) -{ - if (unlikely(skb->pfmemalloc)) { - consume_skb(skb); - return; - } - __skb_pull(skb, skb_headlen(skb)); - /* restore the reserve we had after netdev_alloc_skb_ip_align() */ - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb)); - __vlan_hwaccel_clear_tag(skb); - skb->dev = napi->dev; - skb->skb_iif = 0; - - /* eth_type_trans() assumes pkt_type is PACKET_HOST */ - skb->pkt_type = PACKET_HOST; - - skb->encapsulation = 0; - skb_shinfo(skb)->gso_type = 0; - skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); - skb_ext_reset(skb); - - napi->skb = skb; -} - -struct sk_buff *napi_get_frags(struct napi_struct *napi) -{ - struct sk_buff *skb = napi->skb; - - if (!skb) { - skb = napi_alloc_skb(napi, GRO_MAX_HEAD); - if (skb) { - napi->skb = skb; - skb_mark_napi_id(skb, napi); - } - } - return skb; + return true; } -EXPORT_SYMBOL(napi_get_frags); -static gro_result_t napi_frags_finish(struct napi_struct *napi, - struct sk_buff *skb, - gro_result_t ret) +static void flush_all_backlogs(void) { - switch (ret) { - case GRO_NORMAL: - case GRO_HELD: - __skb_push(skb, ETH_HLEN); - skb->protocol = eth_type_trans(skb, skb->dev); - if (ret == GRO_NORMAL) - gro_normal_one(napi, skb); - break; - - case GRO_DROP: - napi_reuse_skb(napi, skb); - break; - - case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) - napi_skb_free_stolen_head(skb); - else - napi_reuse_skb(napi, skb); - break; - - case GRO_MERGED: - case GRO_CONSUMED: - break; - } - - return ret; -} + static cpumask_t flush_cpus; + unsigned int cpu; -/* Upper GRO stack assumes network header starts at gro_offset=0 - * Drivers could call both napi_gro_frags() and napi_gro_receive() - * We copy ethernet header into skb->data to have a common layout. - */ -static struct sk_buff *napi_frags_skb(struct napi_struct *napi) -{ - struct sk_buff *skb = napi->skb; - const struct ethhdr *eth; - unsigned int hlen = sizeof(*eth); + /* since we are under rtnl lock protection we can use static data + * for the cpumask and avoid allocating on stack the possibly + * large mask + */ + ASSERT_RTNL(); - napi->skb = NULL; + cpus_read_lock(); - skb_reset_mac_header(skb); - skb_gro_reset_offset(skb); - - if (unlikely(skb_gro_header_hard(skb, hlen))) { - eth = skb_gro_header_slow(skb, hlen, 0); - if (unlikely(!eth)) { - net_warn_ratelimited("%s: dropping impossible skb from %s\n", - __func__, napi->dev->name); - napi_reuse_skb(napi, skb); - return NULL; + cpumask_clear(&flush_cpus); + for_each_online_cpu(cpu) { + if (flush_required(cpu)) { + queue_work_on(cpu, system_highpri_wq, + per_cpu_ptr(&flush_works, cpu)); + cpumask_set_cpu(cpu, &flush_cpus); } - } else { - eth = (const struct ethhdr *)skb->data; - gro_pull_from_frag0(skb, hlen); - NAPI_GRO_CB(skb)->frag0 += hlen; - NAPI_GRO_CB(skb)->frag0_len -= hlen; } - __skb_pull(skb, hlen); - /* - * This works because the only protocols we care about don't require - * special handling. - * We'll fix it up properly in napi_frags_finish() + /* we can have in flight packet[s] on the cpus we are not flushing, + * synchronize_net() in unregister_netdevice_many() will take care of + * them */ - skb->protocol = eth->h_proto; - - return skb; -} - -gro_result_t napi_gro_frags(struct napi_struct *napi) -{ - gro_result_t ret; - struct sk_buff *skb = napi_frags_skb(napi); - - if (!skb) - return GRO_DROP; - - trace_napi_gro_frags_entry(skb); - - ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); - trace_napi_gro_frags_exit(ret); - - return ret; -} -EXPORT_SYMBOL(napi_gro_frags); - -/* Compute the checksum from gro_offset and return the folded value - * after adding in any pseudo checksum. - */ -__sum16 __skb_gro_checksum_complete(struct sk_buff *skb) -{ - __wsum wsum; - __sum16 sum; - - wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), 0); - - /* NAPI_GRO_CB(skb)->csum holds pseudo checksum */ - sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum)); - /* See comments in __skb_checksum_complete(). */ - if (likely(!sum)) { - if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && - !skb->csum_complete_sw) - netdev_rx_csum_fault(skb->dev, skb); - } - - NAPI_GRO_CB(skb)->csum = wsum; - NAPI_GRO_CB(skb)->csum_valid = 1; + for_each_cpu(cpu, &flush_cpus) + flush_work(per_cpu_ptr(&flush_works, cpu)); - return sum; + cpus_read_unlock(); } -EXPORT_SYMBOL(__skb_gro_checksum_complete); static void net_rps_send_ipi(struct softnet_data *remsd) { @@ -6124,7 +5922,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = dev_rx_weight; + napi->weight = READ_ONCE(dev_rx_weight); while (again) { struct sk_buff *skb; @@ -6138,8 +5936,7 @@ static int process_backlog(struct napi_struct *napi, int quota) } - local_irq_disable(); - rps_lock(sd); + rps_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). @@ -6155,8 +5952,7 @@ static int process_backlog(struct napi_struct *napi, int quota) skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); } - rps_unlock(sd); - local_irq_enable(); + rps_unlock_irq_enable(sd); } return work; @@ -6184,7 +5980,7 @@ EXPORT_SYMBOL(__napi_schedule); * @n: napi context * * Test if NAPI routine is already running, and if not mark - * it as running. This is used as a condition variable + * it as running. This is used as a condition variable to * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ @@ -6216,17 +6012,25 @@ EXPORT_SYMBOL(napi_schedule_prep); * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule * - * Variant of __napi_schedule() assuming hard irqs are masked + * Variant of __napi_schedule() assuming hard irqs are masked. + * + * On PREEMPT_RT enabled kernels this maps to __napi_schedule() + * because the interrupt disabled assumption might not be true + * due to force-threaded interrupts and spinlock substitution. */ void __napi_schedule_irqoff(struct napi_struct *n) { - ____napi_schedule(this_cpu_ptr(&softnet_data), n); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + else + __napi_schedule(n); } EXPORT_SYMBOL(__napi_schedule_irqoff); bool napi_complete_done(struct napi_struct *n, int work_done) { - unsigned long flags, val, new; + unsigned long flags, val, new, timeout = 0; + bool ret = true; /* * 1) Don't let napi dequeue from the cpu poll list @@ -6238,20 +6042,23 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; + if (work_done) { + if (n->gro_bitmask) + timeout = READ_ONCE(n->dev->gro_flush_timeout); + n->defer_hard_irqs_count = READ_ONCE(n->dev->napi_defer_hard_irqs); + } + if (n->defer_hard_irqs_count > 0) { + n->defer_hard_irqs_count--; + timeout = READ_ONCE(n->dev->gro_flush_timeout); + if (timeout) + ret = false; + } if (n->gro_bitmask) { - unsigned long timeout = 0; - - if (work_done) - timeout = n->dev->gro_flush_timeout; - /* When the NAPI instance uses a timeout and keeps postponing * it, we need to bound somehow the time packets are kept in * the GRO layer */ napi_gro_flush(n, !!timeout); - if (timeout) - hrtimer_start(&n->timer, ns_to_ktime(timeout), - HRTIMER_MODE_REL_PINNED); } gro_normal_list(n); @@ -6268,7 +6075,9 @@ bool napi_complete_done(struct napi_struct *n, int work_done) WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); - new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED); + new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | + NAPIF_STATE_SCHED_THREADED | + NAPIF_STATE_PREFER_BUSY_POLL); /* If STATE_MISSED was set, leave STATE_SCHED set, * because we will call napi->poll() one more time. @@ -6283,7 +6092,10 @@ bool napi_complete_done(struct napi_struct *n, int work_done) return false; } - return true; + if (timeout) + hrtimer_start(&n->timer, ns_to_ktime(timeout), + HRTIMER_MODE_REL_PINNED); + return ret; } EXPORT_SYMBOL(napi_complete_done); @@ -6302,10 +6114,30 @@ 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, bool skip_schedule) +{ + if (!skip_schedule) { + gro_normal_list(napi); + __napi_schedule(napi); + return; + } + + if (napi->gro_bitmask) { + /* flush too old packets + * If HZ < 1000, flush all packets. + */ + napi_gro_flush(napi, HZ >= 1000); + } + + gro_normal_list(napi); + clear_bit(NAPI_STATE_SCHED, &napi->state); +} -static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) +static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll, + u16 budget) { + bool skip_schedule = false; + unsigned long timeout; int rc; /* Busy polling means there is a high chance device driver hard irq @@ -6322,29 +6154,33 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) local_bh_disable(); + if (prefer_busy_poll) { + napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs); + timeout = READ_ONCE(napi->dev->gro_flush_timeout); + if (napi->defer_hard_irqs_count && timeout) { + hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); + skip_schedule = true; + } + } + /* 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); + rc = napi->poll(napi, budget); /* We can't gro_normal_list() here, because napi->poll() might have * rearmed the napi (napi_complete_done()) in which case it could * already be running on another CPU. */ - trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); + trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); - if (rc == BUSY_POLL_BUDGET) { - /* As the whole budget was spent, we still own the napi so can - * safely handle the rx_list. - */ - gro_normal_list(napi); - __napi_schedule(napi); - } + if (rc == budget) + __busy_poll_stop(napi, skip_schedule); local_bh_enable(); } void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), - void *loop_end_arg) + void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); @@ -6372,17 +6208,23 @@ restart: * we avoid dirtying napi->state as much as we can. */ if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED | - NAPIF_STATE_IN_BUSY_POLL)) + NAPIF_STATE_IN_BUSY_POLL)) { + if (prefer_busy_poll) + set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; + } if (cmpxchg(&napi->state, val, val | NAPIF_STATE_IN_BUSY_POLL | - NAPIF_STATE_SCHED) != val) + NAPIF_STATE_SCHED) != val) { + if (prefer_busy_poll) + set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; + } have_poll_lock = netpoll_poll_lock(napi); napi_poll = napi->poll; } - work = napi_poll(napi, BUSY_POLL_BUDGET); - trace_napi_poll(napi, work, BUSY_POLL_BUDGET); + work = napi_poll(napi, budget); + trace_napi_poll(napi, work, budget); gro_normal_list(napi); count: if (work > 0) @@ -6395,7 +6237,7 @@ count: if (unlikely(need_resched())) { if (napi_poll) - busy_poll_stop(napi, have_poll_lock); + busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget); preempt_enable(); rcu_read_unlock(); cond_resched(); @@ -6406,7 +6248,7 @@ count: cpu_relax(); } if (napi_poll) - busy_poll_stop(napi, have_poll_lock); + busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget); preempt_enable(); out: rcu_read_unlock(); @@ -6417,8 +6259,7 @@ EXPORT_SYMBOL(napi_busy_loop); 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)) + if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state)) return; spin_lock(&napi_hash_lock); @@ -6439,20 +6280,14 @@ static void napi_hash_add(struct napi_struct *napi) /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi */ -bool napi_hash_del(struct napi_struct *napi) +static void napi_hash_del(struct napi_struct *napi) { - bool rcu_sync_needed = false; - spin_lock(&napi_hash_lock); - if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) { - rcu_sync_needed = true; - hlist_del_rcu(&napi->napi_hash_node); - } + hlist_del_init_rcu(&napi->napi_hash_node); + spin_unlock(&napi_hash_lock); - return rcu_sync_needed; } -EXPORT_SYMBOL_GPL(napi_hash_del); static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) { @@ -6463,9 +6298,11 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ - if (napi->gro_bitmask && !napi_disable_pending(napi) && - !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) + if (!napi_disable_pending(napi) && + !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) { + clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); __napi_schedule_irqoff(napi); + } return HRTIMER_NORESTART; } @@ -6481,10 +6318,58 @@ static void init_gro_hash(struct napi_struct *napi) napi->gro_bitmask = 0; } -void netif_napi_add(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight) +int dev_set_threaded(struct net_device *dev, bool threaded) +{ + struct napi_struct *napi; + int err = 0; + + if (dev->threaded == threaded) + return 0; + + if (threaded) { + list_for_each_entry(napi, &dev->napi_list, dev_list) { + if (!napi->thread) { + err = napi_kthread_create(napi); + if (err) { + threaded = false; + break; + } + } + } + } + + dev->threaded = threaded; + + /* Make sure kthread is created before THREADED bit + * is set. + */ + smp_mb__before_atomic(); + + /* Setting/unsetting threaded mode on a napi might not immediately + * take effect, if the current napi instance is actively being + * polled. In this case, the switch between threaded mode and + * softirq mode will happen in the next round of napi_schedule(). + * This should not cause hiccups/stalls to the live traffic. + */ + list_for_each_entry(napi, &dev->napi_list, dev_list) { + if (threaded) + set_bit(NAPI_STATE_THREADED, &napi->state); + else + clear_bit(NAPI_STATE_THREADED, &napi->state); + } + + return err; +} +EXPORT_SYMBOL(dev_set_threaded); + +void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight) { + if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) + return; + INIT_LIST_HEAD(&napi->poll_list); + INIT_HLIST_NODE(&napi->napi_hash_node); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; init_gro_hash(napi); @@ -6496,25 +6381,44 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, netdev_err_once(dev, "%s() called with weight %d\n", __func__, weight); napi->weight = weight; - list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; #ifdef CONFIG_NETPOLL napi->poll_owner = -1; #endif set_bit(NAPI_STATE_SCHED, &napi->state); + set_bit(NAPI_STATE_NPSVC, &napi->state); + list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); + napi_get_frags_check(napi); + /* Create kthread for this napi if dev->threaded is set. + * Clear dev->threaded if kthread creation failed so that + * threaded mode will not be enabled in napi_enable(). + */ + if (dev->threaded && napi_kthread_create(napi)) + dev->threaded = 0; } -EXPORT_SYMBOL(netif_napi_add); +EXPORT_SYMBOL(netif_napi_add_weight); void napi_disable(struct napi_struct *n) { + unsigned long val, new; + might_sleep(); set_bit(NAPI_STATE_DISABLE, &n->state); - while (test_and_set_bit(NAPI_STATE_SCHED, &n->state)) - msleep(1); - while (test_and_set_bit(NAPI_STATE_NPSVC, &n->state)) - msleep(1); + for ( ; ; ) { + val = READ_ONCE(n->state); + if (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { + usleep_range(20, 200); + continue; + } + + new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; + new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); + + if (cmpxchg(&n->state, val, new) == val) + break; + } hrtimer_cancel(&n->timer); @@ -6522,6 +6426,28 @@ void napi_disable(struct napi_struct *n) } EXPORT_SYMBOL(napi_disable); +/** + * napi_enable - enable NAPI scheduling + * @n: NAPI context + * + * Resume NAPI from being scheduled on this context. + * Must be paired with napi_disable. + */ +void napi_enable(struct napi_struct *n) +{ + unsigned long val, new; + + do { + val = READ_ONCE(n->state); + BUG_ON(!test_bit(NAPI_STATE_SCHED, &val)); + + new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC); + if (n->dev->threaded && n->thread) + new |= NAPIF_STATE_THREADED; + } while (cmpxchg(&n->state, val, new) != val); +} +EXPORT_SYMBOL(napi_enable); + static void flush_gro_hash(struct napi_struct *napi) { int i; @@ -6536,28 +6462,29 @@ static void flush_gro_hash(struct napi_struct *napi) } /* Must be called in process context */ -void netif_napi_del(struct napi_struct *napi) +void __netif_napi_del(struct napi_struct *napi) { - might_sleep(); - if (napi_hash_del(napi)) - synchronize_net(); - list_del_init(&napi->dev_list); + if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) + return; + + napi_hash_del(napi); + list_del_rcu(&napi->dev_list); napi_free_frags(napi); flush_gro_hash(napi); napi->gro_bitmask = 0; + + if (napi->thread) { + kthread_stop(napi->thread); + napi->thread = NULL; + } } -EXPORT_SYMBOL(netif_napi_del); +EXPORT_SYMBOL(__netif_napi_del); -static int napi_poll(struct napi_struct *n, struct list_head *repoll) +static int __napi_poll(struct napi_struct *n, bool *repoll) { - void *have; int work, weight; - list_del_init(&n->poll_list); - - have = netpoll_poll_lock(n); - weight = n->weight; /* This NAPI_STATE_SCHED test is for avoiding a race @@ -6572,10 +6499,12 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) trace_napi_poll(n, work, weight); } - WARN_ON_ONCE(work > weight); + if (unlikely(work > weight)) + netdev_err_once(n->dev, "NAPI poll function %pS returned %d, exceeding its budget of %d.\n", + n->poll, work, weight); if (likely(work < weight)) - goto out_unlock; + return work; /* Drivers must not modify the NAPI state if they * consume the entire weight. In such cases this code @@ -6584,7 +6513,20 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) */ if (unlikely(napi_disable_pending(n))) { napi_complete(n); - goto out_unlock; + return work; + } + + /* The NAPI context has more processing work, but busy-polling + * is preferred. Exit early. + */ + if (napi_prefer_busy_poll(n)) { + if (napi_complete_done(n, work)) { + /* If timeout is not set, we need to make sure + * that the NAPI is re-scheduled. + */ + napi_schedule(n); + } + return work; } if (n->gro_bitmask) { @@ -6602,23 +6544,116 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) if (unlikely(!list_empty(&n->poll_list))) { pr_warn_once("%s: Budget exhausted after napi rescheduled\n", n->dev ? n->dev->name : "backlog"); - goto out_unlock; + return work; } - list_add_tail(&n->poll_list, repoll); + *repoll = true; + + return work; +} + +static int napi_poll(struct napi_struct *n, struct list_head *repoll) +{ + bool do_repoll = false; + void *have; + int work; + + list_del_init(&n->poll_list); + + have = netpoll_poll_lock(n); + + work = __napi_poll(n, &do_repoll); + + if (do_repoll) + list_add_tail(&n->poll_list, repoll); -out_unlock: netpoll_poll_unlock(have); return work; } +static int napi_thread_wait(struct napi_struct *napi) +{ + bool woken = false; + + set_current_state(TASK_INTERRUPTIBLE); + + while (!kthread_should_stop()) { + /* Testing SCHED_THREADED bit here to make sure the current + * kthread owns this napi and could poll on this napi. + * Testing SCHED bit is not enough because SCHED bit might be + * set by some other busy poll thread or by napi_disable(). + */ + if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) { + WARN_ON(!list_empty(&napi->poll_list)); + __set_current_state(TASK_RUNNING); + return 0; + } + + schedule(); + /* woken being true indicates this thread owns this napi. */ + woken = true; + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + + return -1; +} + +static int napi_threaded_poll(void *data) +{ + struct napi_struct *napi = data; + void *have; + + while (!napi_thread_wait(napi)) { + for (;;) { + bool repoll = false; + + local_bh_disable(); + + have = netpoll_poll_lock(napi); + __napi_poll(napi, &repoll); + netpoll_poll_unlock(have); + + local_bh_enable(); + + if (!repoll) + break; + + cond_resched(); + } + } + return 0; +} + +static void skb_defer_free_flush(struct softnet_data *sd) +{ + struct sk_buff *skb, *next; + unsigned long flags; + + /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */ + if (!READ_ONCE(sd->defer_list)) + return; + + spin_lock_irqsave(&sd->defer_lock, flags); + skb = sd->defer_list; + sd->defer_list = NULL; + sd->defer_count = 0; + spin_unlock_irqrestore(&sd->defer_lock, flags); + + while (skb != NULL) { + next = skb->next; + napi_consume_skb(skb, 1); + skb = next; + } +} + static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + - usecs_to_jiffies(netdev_budget_usecs); - int budget = netdev_budget; + usecs_to_jiffies(READ_ONCE(netdev_budget_usecs)); + int budget = READ_ONCE(netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); @@ -6629,9 +6664,11 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) for (;;) { struct napi_struct *n; + skb_defer_free_flush(sd); + if (list_empty(&list)) { if (!sd_has_rps_ipi_waiting(sd) && list_empty(&repoll)) - goto out; + goto end; break; } @@ -6658,12 +6695,12 @@ 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(); +end:; } struct netdev_adjacent { struct net_device *dev; + netdevice_tracker dev_tracker; /* upper master flag, there can only be one master device per list */ bool master; @@ -6693,9 +6730,10 @@ 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) +static int ____netdev_has_upper_dev(struct net_device *upper_dev, + struct netdev_nested_priv *priv) { - struct net_device *dev = data; + struct net_device *dev = (struct net_device *)priv->data; return upper_dev == dev; } @@ -6712,15 +6750,19 @@ static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data) bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { + struct netdev_nested_priv priv = { + .data = (void *)upper_dev, + }; + ASSERT_RTNL(); return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, - upper_dev); + &priv); } EXPORT_SYMBOL(netdev_has_upper_dev); /** - * netdev_has_upper_dev_all - Check if device is linked to an upper device + * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * @@ -6732,8 +6774,12 @@ EXPORT_SYMBOL(netdev_has_upper_dev); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { + struct netdev_nested_priv priv = { + .data = (void *)upper_dev, + }; + return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, - upper_dev); + &priv); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); @@ -6878,8 +6924,8 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, static int __netdev_walk_all_upper_dev(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -6891,7 +6937,7 @@ static int __netdev_walk_all_upper_dev(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -6927,8 +6973,8 @@ static int __netdev_walk_all_upper_dev(struct net_device *dev, int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -6939,7 +6985,7 @@ int netdev_walk_all_upper_dev_rcu(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -6975,10 +7021,15 @@ EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); static bool __netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { + struct netdev_nested_priv priv = { + .flags = 0, + .data = (void *)upper_dev, + }; + ASSERT_RTNL(); return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, - upper_dev); + &priv); } /** @@ -7023,7 +7074,7 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, { struct netdev_adjacent *lower; - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); @@ -7096,8 +7147,8 @@ static struct net_device *__netdev_next_lower_dev(struct net_device *dev, int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7108,7 +7159,7 @@ int netdev_walk_all_lower_dev(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7143,8 +7194,8 @@ EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); static int __netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7156,7 +7207,7 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7245,22 +7296,44 @@ static u8 __netdev_lower_depth(struct net_device *dev) return max_depth; } -static int __netdev_update_upper_level(struct net_device *dev, void *data) +static int __netdev_update_upper_level(struct net_device *dev, + struct netdev_nested_priv *__unused) { dev->upper_level = __netdev_upper_depth(dev) + 1; return 0; } -static int __netdev_update_lower_level(struct net_device *dev, void *data) +#ifdef CONFIG_LOCKDEP +static LIST_HEAD(net_unlink_list); + +static void net_unlink_todo(struct net_device *dev) +{ + if (list_empty(&dev->unlink_list)) + list_add_tail(&dev->unlink_list, &net_unlink_list); +} +#endif + +static int __netdev_update_lower_level(struct net_device *dev, + struct netdev_nested_priv *priv) { dev->lower_level = __netdev_lower_depth(dev) + 1; + +#ifdef CONFIG_LOCKDEP + if (!priv) + return 0; + + if (priv->flags & NESTED_SYNC_IMM) + dev->nested_level = dev->lower_level - 1; + if (priv->flags & NESTED_SYNC_TODO) + net_unlink_todo(dev); +#endif return 0; } int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7271,7 +7344,7 @@ int netdev_walk_all_lower_dev_rcu(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7402,7 +7475,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj->ref_nr = 1; adj->private = private; adj->ignore = false; - dev_hold(adj_dev); + netdev_hold(adj_dev, &adj->dev_tracker, GFP_KERNEL); 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); @@ -7431,8 +7504,8 @@ remove_symlinks: if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: + netdev_put(adj_dev, &adj->dev_tracker); kfree(adj); - dev_put(adj_dev); return ret; } @@ -7473,7 +7546,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, list_del_rcu(&adj->list); 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); + netdev_put(adj_dev, &adj->dev_tracker); kfree_rcu(adj, rcu); } @@ -7531,6 +7604,7 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *upper_priv, void *upper_info, + struct netdev_nested_priv *priv, struct netlink_ext_ack *extack) { struct netdev_notifier_changeupper_info changeupper_info = { @@ -7587,9 +7661,9 @@ static int __netdev_upper_dev_link(struct net_device *dev, __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); - __netdev_update_lower_level(upper_dev, NULL); + __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, - NULL); + priv); return 0; @@ -7614,8 +7688,13 @@ int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack) { + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, + .data = NULL, + }; + return __netdev_upper_dev_link(dev, upper_dev, false, - NULL, NULL, extack); + NULL, NULL, &priv, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); @@ -7638,21 +7717,19 @@ int netdev_master_upper_dev_link(struct net_device *dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack) { + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, + .data = NULL, + }; + return __netdev_upper_dev_link(dev, upper_dev, true, - upper_priv, upper_info, extack); + upper_priv, upper_info, &priv, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); -/** - * netdev_upper_dev_unlink - Removes a link to upper device - * @dev: device - * @upper_dev: new upper device - * - * Removes a link to device which is upper to this one. The caller must hold - * the RTNL lock. - */ -void netdev_upper_dev_unlink(struct net_device *dev, - struct net_device *upper_dev) +static void __netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev, + struct netdev_nested_priv *priv) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { @@ -7677,9 +7754,28 @@ void netdev_upper_dev_unlink(struct net_device *dev, __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); - __netdev_update_lower_level(upper_dev, NULL); + __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, - NULL); + priv); +} + +/** + * netdev_upper_dev_unlink - Removes a link to upper device + * @dev: device + * @upper_dev: new upper device + * + * Removes a link to device which is upper to this one. The caller must hold + * the RTNL lock. + */ +void netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) +{ + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_TODO, + .data = NULL, + }; + + __netdev_upper_dev_unlink(dev, upper_dev, &priv); } EXPORT_SYMBOL(netdev_upper_dev_unlink); @@ -7715,6 +7811,10 @@ int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *dev, struct netlink_ext_ack *extack) { + struct netdev_nested_priv priv = { + .flags = 0, + .data = NULL, + }; int err; if (!new_dev) @@ -7722,8 +7822,8 @@ int netdev_adjacent_change_prepare(struct net_device *old_dev, if (old_dev && new_dev != old_dev) netdev_adjacent_dev_disable(dev, old_dev); - - err = netdev_upper_dev_link(new_dev, dev, extack); + err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv, + extack); if (err) { if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); @@ -7738,6 +7838,11 @@ void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, + .data = NULL, + }; + if (!new_dev || !old_dev) return; @@ -7745,7 +7850,7 @@ void netdev_adjacent_change_commit(struct net_device *old_dev, return; netdev_adjacent_dev_enable(dev, old_dev); - netdev_upper_dev_unlink(old_dev, dev); + __netdev_upper_dev_unlink(old_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_commit); @@ -7753,13 +7858,18 @@ void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { + struct netdev_nested_priv priv = { + .flags = 0, + .data = NULL, + }; + if (!new_dev) return; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); - netdev_upper_dev_unlink(new_dev, dev); + __netdev_upper_dev_unlink(new_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_abort); @@ -7785,6 +7895,298 @@ void netdev_bonding_info_change(struct net_device *dev, } EXPORT_SYMBOL(netdev_bonding_info_change); +static int netdev_offload_xstats_enable_l3(struct net_device *dev, + struct netlink_ext_ack *extack) +{ + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .info.extack = extack, + .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, + }; + int err; + int rc; + + dev->offload_xstats_l3 = kzalloc(sizeof(*dev->offload_xstats_l3), + GFP_KERNEL); + if (!dev->offload_xstats_l3) + return -ENOMEM; + + rc = call_netdevice_notifiers_info_robust(NETDEV_OFFLOAD_XSTATS_ENABLE, + NETDEV_OFFLOAD_XSTATS_DISABLE, + &info.info); + err = notifier_to_errno(rc); + if (err) + goto free_stats; + + return 0; + +free_stats: + kfree(dev->offload_xstats_l3); + dev->offload_xstats_l3 = NULL; + return err; +} + +int netdev_offload_xstats_enable(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct netlink_ext_ack *extack) +{ + ASSERT_RTNL(); + + if (netdev_offload_xstats_enabled(dev, type)) + return -EALREADY; + + switch (type) { + case NETDEV_OFFLOAD_XSTATS_TYPE_L3: + return netdev_offload_xstats_enable_l3(dev, extack); + } + + WARN_ON(1); + return -EINVAL; +} +EXPORT_SYMBOL(netdev_offload_xstats_enable); + +static void netdev_offload_xstats_disable_l3(struct net_device *dev) +{ + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, + }; + + call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_DISABLE, + &info.info); + kfree(dev->offload_xstats_l3); + dev->offload_xstats_l3 = NULL; +} + +int netdev_offload_xstats_disable(struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + ASSERT_RTNL(); + + if (!netdev_offload_xstats_enabled(dev, type)) + return -EALREADY; + + switch (type) { + case NETDEV_OFFLOAD_XSTATS_TYPE_L3: + netdev_offload_xstats_disable_l3(dev); + return 0; + } + + WARN_ON(1); + return -EINVAL; +} +EXPORT_SYMBOL(netdev_offload_xstats_disable); + +static void netdev_offload_xstats_disable_all(struct net_device *dev) +{ + netdev_offload_xstats_disable(dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3); +} + +static struct rtnl_hw_stats64 * +netdev_offload_xstats_get_ptr(const struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + switch (type) { + case NETDEV_OFFLOAD_XSTATS_TYPE_L3: + return dev->offload_xstats_l3; + } + + WARN_ON(1); + return NULL; +} + +bool netdev_offload_xstats_enabled(const struct net_device *dev, + enum netdev_offload_xstats_type type) +{ + ASSERT_RTNL(); + + return netdev_offload_xstats_get_ptr(dev, type); +} +EXPORT_SYMBOL(netdev_offload_xstats_enabled); + +struct netdev_notifier_offload_xstats_ru { + bool used; +}; + +struct netdev_notifier_offload_xstats_rd { + struct rtnl_hw_stats64 stats; + bool used; +}; + +static void netdev_hw_stats64_add(struct rtnl_hw_stats64 *dest, + const struct rtnl_hw_stats64 *src) +{ + dest->rx_packets += src->rx_packets; + dest->tx_packets += src->tx_packets; + dest->rx_bytes += src->rx_bytes; + dest->tx_bytes += src->tx_bytes; + dest->rx_errors += src->rx_errors; + dest->tx_errors += src->tx_errors; + dest->rx_dropped += src->rx_dropped; + dest->tx_dropped += src->tx_dropped; + dest->multicast += src->multicast; +} + +static int netdev_offload_xstats_get_used(struct net_device *dev, + enum netdev_offload_xstats_type type, + bool *p_used, + struct netlink_ext_ack *extack) +{ + struct netdev_notifier_offload_xstats_ru report_used = {}; + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .info.extack = extack, + .type = type, + .report_used = &report_used, + }; + int rc; + + WARN_ON(!netdev_offload_xstats_enabled(dev, type)); + rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_USED, + &info.info); + *p_used = report_used.used; + return notifier_to_errno(rc); +} + +static int netdev_offload_xstats_get_stats(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *p_stats, + bool *p_used, + struct netlink_ext_ack *extack) +{ + struct netdev_notifier_offload_xstats_rd report_delta = {}; + struct netdev_notifier_offload_xstats_info info = { + .info.dev = dev, + .info.extack = extack, + .type = type, + .report_delta = &report_delta, + }; + struct rtnl_hw_stats64 *stats; + int rc; + + stats = netdev_offload_xstats_get_ptr(dev, type); + if (WARN_ON(!stats)) + return -EINVAL; + + rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, + &info.info); + + /* Cache whatever we got, even if there was an error, otherwise the + * successful stats retrievals would get lost. + */ + netdev_hw_stats64_add(stats, &report_delta.stats); + + if (p_stats) + *p_stats = *stats; + *p_used = report_delta.used; + + return notifier_to_errno(rc); +} + +int netdev_offload_xstats_get(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *p_stats, bool *p_used, + struct netlink_ext_ack *extack) +{ + ASSERT_RTNL(); + + if (p_stats) + return netdev_offload_xstats_get_stats(dev, type, p_stats, + p_used, extack); + else + return netdev_offload_xstats_get_used(dev, type, p_used, + extack); +} +EXPORT_SYMBOL(netdev_offload_xstats_get); + +void +netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *report_delta, + const struct rtnl_hw_stats64 *stats) +{ + report_delta->used = true; + netdev_hw_stats64_add(&report_delta->stats, stats); +} +EXPORT_SYMBOL(netdev_offload_xstats_report_delta); + +void +netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *report_used) +{ + report_used->used = true; +} +EXPORT_SYMBOL(netdev_offload_xstats_report_used); + +void netdev_offload_xstats_push_delta(struct net_device *dev, + enum netdev_offload_xstats_type type, + const struct rtnl_hw_stats64 *p_stats) +{ + struct rtnl_hw_stats64 *stats; + + ASSERT_RTNL(); + + stats = netdev_offload_xstats_get_ptr(dev, type); + if (WARN_ON(!stats)) + return; + + netdev_hw_stats64_add(stats, p_stats); +} +EXPORT_SYMBOL(netdev_offload_xstats_push_delta); + +/** + * netdev_get_xmit_slave - Get the xmit slave of master device + * @dev: device + * @skb: The packet + * @all_slaves: assume all the slaves are active + * + * The reference counters are not incremented so the caller must be + * careful with locks. The caller must hold RCU lock. + * %NULL is returned if no slave is found. + */ + +struct net_device *netdev_get_xmit_slave(struct net_device *dev, + struct sk_buff *skb, + bool all_slaves) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_get_xmit_slave) + return NULL; + return ops->ndo_get_xmit_slave(dev, skb, all_slaves); +} +EXPORT_SYMBOL(netdev_get_xmit_slave); + +static struct net_device *netdev_sk_get_lower_dev(struct net_device *dev, + struct sock *sk) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_sk_get_lower_dev) + return NULL; + return ops->ndo_sk_get_lower_dev(dev, sk); +} + +/** + * netdev_sk_get_lowest_dev - Get the lowest device in chain given device and socket + * @dev: device + * @sk: the socket + * + * %NULL is returned if no lower device is found. + */ + +struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, + struct sock *sk) +{ + struct net_device *lower; + + lower = netdev_sk_get_lower_dev(dev, sk); + while (lower) { + dev = lower; + lower = netdev_sk_get_lower_dev(dev, sk); + } + + return dev; +} +EXPORT_SYMBOL(netdev_sk_get_lowest_dev); + static void netdev_adjacent_add_links(struct net_device *dev) { struct netdev_adjacent *iter; @@ -7877,7 +8279,7 @@ EXPORT_SYMBOL(netdev_lower_dev_get_private); /** - * netdev_lower_change - Dispatch event about lower device state change + * netdev_lower_state_changed - Dispatch event about lower device state change * @lower_dev: device * @lower_state_info: state to dispatch * @@ -7925,8 +8327,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) dev->flags &= ~IFF_PROMISC; else { dev->promiscuity -= inc; - pr_warn("%s: promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n", - dev->name); + netdev_warn(dev, "promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n"); return -EOVERFLOW; } } @@ -7996,8 +8397,7 @@ static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) dev->flags &= ~IFF_ALLMULTI; else { dev->allmulti -= inc; - pr_warn("%s: allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n", - dev->name); + netdev_warn(dev, "allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n"); return -EOVERFLOW; } } @@ -8351,7 +8751,6 @@ void dev_set_group(struct net_device *dev, int new_group) { dev->group = new_group; } -EXPORT_SYMBOL(dev_set_group); /** * dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR. @@ -8407,6 +8806,48 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, } EXPORT_SYMBOL(dev_set_mac_address); +static DECLARE_RWSEM(dev_addr_sem); + +int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, + struct netlink_ext_ack *extack) +{ + int ret; + + down_write(&dev_addr_sem); + ret = dev_set_mac_address(dev, sa, extack); + up_write(&dev_addr_sem); + return ret; +} +EXPORT_SYMBOL(dev_set_mac_address_user); + +int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) +{ + size_t size = sizeof(sa->sa_data); + struct net_device *dev; + int ret = 0; + + down_read(&dev_addr_sem); + rcu_read_lock(); + + dev = dev_get_by_name_rcu(net, dev_name); + if (!dev) { + ret = -ENODEV; + goto unlock; + } + if (!dev->addr_len) + memset(sa->sa_data, 0, size); + else + memcpy(sa->sa_data, dev->dev_addr, + min_t(size_t, size, dev->addr_len)); + sa->sa_family = dev->type; + +unlock: + rcu_read_unlock(); + up_read(&dev_addr_sem); + return ret; +} +EXPORT_SYMBOL(dev_get_mac_address); + /** * dev_change_carrier - Change device carrier * @dev: device @@ -8424,7 +8865,6 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier) return -ENODEV; return ops->ndo_change_carrier(dev, new_carrier); } -EXPORT_SYMBOL(dev_change_carrier); /** * dev_get_phys_port_id - Get device physical port ID @@ -8442,7 +8882,6 @@ int dev_get_phys_port_id(struct net_device *dev, return -EOPNOTSUPP; return ops->ndo_get_phys_port_id(dev, ppid); } -EXPORT_SYMBOL(dev_get_phys_port_id); /** * dev_get_phys_port_name - Get device physical port name @@ -8465,7 +8904,6 @@ int dev_get_phys_port_name(struct net_device *dev, } return devlink_compat_phys_port_name_get(dev, name, len); } -EXPORT_SYMBOL(dev_get_phys_port_name); /** * dev_get_port_parent_id - Get the device's port parent identifier @@ -8492,20 +8930,17 @@ int dev_get_port_parent_id(struct net_device *dev, } err = devlink_compat_switch_id_get(dev, ppid); - if (!err || err != -EOPNOTSUPP) + if (!recurse || err != -EOPNOTSUPP) return err; - if (!recurse) - return -EOPNOTSUPP; - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = dev_get_port_parent_id(lower_dev, ppid, recurse); + err = dev_get_port_parent_id(lower_dev, ppid, true); if (err) break; if (!first.id_len) first = *ppid; else if (memcmp(&first, ppid, sizeof(*ppid))) - return -ENODATA; + return -EOPNOTSUPP; } return err; @@ -8532,328 +8967,581 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) EXPORT_SYMBOL(netdev_port_same_parent_id); /** - * dev_change_proto_down - update protocol port state information + * dev_change_proto_down - set carrier according to proto_down. + * * @dev: device * @proto_down: new value - * - * This info can be used by switch drivers to set the phys state of the - * port. */ int dev_change_proto_down(struct net_device *dev, bool proto_down) { - const struct net_device_ops *ops = dev->netdev_ops; - - if (!ops->ndo_change_proto_down) + if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; - return ops->ndo_change_proto_down(dev, proto_down); + if (proto_down) + netif_carrier_off(dev); + else + netif_carrier_on(dev); + dev->proto_down = proto_down; + return 0; } -EXPORT_SYMBOL(dev_change_proto_down); /** - * dev_change_proto_down_generic - generic implementation for - * ndo_change_proto_down that sets carrier according to - * proto_down. + * dev_change_proto_down_reason - proto down reason * * @dev: device - * @proto_down: new value + * @mask: proto down mask + * @value: proto down value */ -int dev_change_proto_down_generic(struct net_device *dev, bool proto_down) +void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, + u32 value) { - if (proto_down) - netif_carrier_off(dev); - else - netif_carrier_on(dev); - dev->proto_down = proto_down; - return 0; + int b; + + if (!mask) { + dev->proto_down_reason = value; + } else { + for_each_set_bit(b, &mask, 32) { + if (value & (1 << b)) + dev->proto_down_reason |= BIT(b); + else + dev->proto_down_reason &= ~BIT(b); + } + } } -EXPORT_SYMBOL(dev_change_proto_down_generic); -u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op, - enum bpf_netdev_command cmd) +struct bpf_xdp_link { + struct bpf_link link; + struct net_device *dev; /* protected by rtnl_lock, no refcnt held */ + int flags; +}; + +static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags) { - struct netdev_bpf xdp; + if (flags & XDP_FLAGS_HW_MODE) + return XDP_MODE_HW; + if (flags & XDP_FLAGS_DRV_MODE) + return XDP_MODE_DRV; + if (flags & XDP_FLAGS_SKB_MODE) + return XDP_MODE_SKB; + return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB; +} + +static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) +{ + switch (mode) { + case XDP_MODE_SKB: + return generic_xdp_install; + case XDP_MODE_DRV: + case XDP_MODE_HW: + return dev->netdev_ops->ndo_bpf; + default: + return NULL; + } +} - if (!bpf_op) - return 0; +static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev, + enum bpf_xdp_mode mode) +{ + return dev->xdp_state[mode].link; +} - memset(&xdp, 0, sizeof(xdp)); - xdp.command = cmd; +static struct bpf_prog *dev_xdp_prog(struct net_device *dev, + enum bpf_xdp_mode mode) +{ + struct bpf_xdp_link *link = dev_xdp_link(dev, mode); - /* Query must always succeed. */ - WARN_ON(bpf_op(dev, &xdp) < 0 && cmd == XDP_QUERY_PROG); + if (link) + return link->link.prog; + return dev->xdp_state[mode].prog; +} - return xdp.prog_id; +u8 dev_xdp_prog_count(struct net_device *dev) +{ + u8 count = 0; + int i; + + for (i = 0; i < __MAX_XDP_MODE; i++) + if (dev->xdp_state[i].prog || dev->xdp_state[i].link) + count++; + return count; +} +EXPORT_SYMBOL_GPL(dev_xdp_prog_count); + +u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) +{ + struct bpf_prog *prog = dev_xdp_prog(dev, mode); + + return prog ? prog->aux->id : 0; +} + +static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode, + struct bpf_xdp_link *link) +{ + dev->xdp_state[mode].link = link; + dev->xdp_state[mode].prog = NULL; +} + +static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode, + struct bpf_prog *prog) +{ + dev->xdp_state[mode].link = NULL; + dev->xdp_state[mode].prog = prog; } -static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op, - struct netlink_ext_ack *extack, u32 flags, - struct bpf_prog *prog) +static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, + bpf_op_t bpf_op, struct netlink_ext_ack *extack, + u32 flags, struct bpf_prog *prog) { - bool non_hw = !(flags & XDP_FLAGS_HW_MODE); - struct bpf_prog *prev_prog = NULL; struct netdev_bpf xdp; int err; - if (non_hw) { - prev_prog = bpf_prog_by_id(__dev_xdp_query(dev, bpf_op, - XDP_QUERY_PROG)); - if (IS_ERR(prev_prog)) - prev_prog = NULL; - } - memset(&xdp, 0, sizeof(xdp)); - if (flags & XDP_FLAGS_HW_MODE) - xdp.command = XDP_SETUP_PROG_HW; - else - xdp.command = XDP_SETUP_PROG; + xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG; xdp.extack = extack; xdp.flags = flags; xdp.prog = prog; + /* Drivers assume refcnt is already incremented (i.e, prog pointer is + * "moved" into driver), so they don't increment it on their own, but + * they do decrement refcnt when program is detached or replaced. + * Given net_device also owns link/prog, we need to bump refcnt here + * to prevent drivers from underflowing it. + */ + if (prog) + bpf_prog_inc(prog); err = bpf_op(dev, &xdp); - if (!err && non_hw) - bpf_prog_change_xdp(prev_prog, prog); + if (err) { + if (prog) + bpf_prog_put(prog); + return err; + } - if (prev_prog) - bpf_prog_put(prev_prog); + if (mode != XDP_MODE_HW) + bpf_prog_change_xdp(dev_xdp_prog(dev, mode), prog); - return err; + return 0; } static void dev_xdp_uninstall(struct net_device *dev) { - struct netdev_bpf xdp; - bpf_op_t ndo_bpf; + struct bpf_xdp_link *link; + struct bpf_prog *prog; + enum bpf_xdp_mode mode; + bpf_op_t bpf_op; - /* Remove generic XDP */ - WARN_ON(dev_xdp_install(dev, generic_xdp_install, NULL, 0, NULL)); + ASSERT_RTNL(); - /* Remove from the driver */ - ndo_bpf = dev->netdev_ops->ndo_bpf; - if (!ndo_bpf) - return; + for (mode = XDP_MODE_SKB; mode < __MAX_XDP_MODE; mode++) { + prog = dev_xdp_prog(dev, mode); + if (!prog) + continue; - memset(&xdp, 0, sizeof(xdp)); - xdp.command = XDP_QUERY_PROG; - WARN_ON(ndo_bpf(dev, &xdp)); - if (xdp.prog_id) - WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, - NULL)); + bpf_op = dev_xdp_bpf_op(dev, mode); + if (!bpf_op) + continue; - /* Remove HW offload */ - memset(&xdp, 0, sizeof(xdp)); - xdp.command = XDP_QUERY_PROG_HW; - if (!ndo_bpf(dev, &xdp) && xdp.prog_id) - WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, - NULL)); + WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); + + /* auto-detach link from net device */ + link = dev_xdp_link(dev, mode); + if (link) + link->dev = NULL; + else + bpf_prog_put(prog); + + dev_xdp_set_link(dev, mode, NULL); + } } -/** - * dev_change_xdp_fd - set or clear a bpf program for a device rx path - * @dev: device - * @extack: netlink extended ack - * @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, struct netlink_ext_ack *extack, - int fd, u32 flags) +static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack, + struct bpf_xdp_link *link, struct bpf_prog *new_prog, + struct bpf_prog *old_prog, u32 flags) { - const struct net_device_ops *ops = dev->netdev_ops; - enum bpf_netdev_command query; - struct bpf_prog *prog = NULL; - bpf_op_t bpf_op, bpf_chk; - bool offload; + unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); + struct bpf_prog *cur_prog; + struct net_device *upper; + struct list_head *iter; + enum bpf_xdp_mode mode; + bpf_op_t bpf_op; int err; ASSERT_RTNL(); - offload = flags & XDP_FLAGS_HW_MODE; - query = offload ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG; - - bpf_op = bpf_chk = ops->ndo_bpf; - if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) { - NL_SET_ERR_MSG(extack, "underlying driver does not support XDP in native mode"); - return -EOPNOTSUPP; + /* either link or prog attachment, never both */ + if (link && (new_prog || old_prog)) + return -EINVAL; + /* link supports only XDP mode flags */ + if (link && (flags & ~XDP_FLAGS_MODES)) { + NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); + return -EINVAL; + } + /* just one XDP mode bit should be set, zero defaults to drv/skb mode */ + if (num_modes > 1) { + NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); + return -EINVAL; + } + /* avoid ambiguity if offload + drv/skb mode progs are both loaded */ + if (!num_modes && dev_xdp_prog_count(dev) > 1) { + NL_SET_ERR_MSG(extack, + "More than one program loaded, unset mode is ambiguous"); + return -EINVAL; + } + /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ + if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { + NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); + return -EINVAL; } - if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE)) - bpf_op = generic_xdp_install; - if (bpf_op == bpf_chk) - bpf_chk = generic_xdp_install; - if (fd >= 0) { - u32 prog_id; + mode = dev_xdp_mode(dev, flags); + /* can't replace attached link */ + if (dev_xdp_link(dev, mode)) { + NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link"); + return -EBUSY; + } - if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) { - NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time"); + /* don't allow if an upper device already has a program */ + netdev_for_each_upper_dev_rcu(dev, upper, iter) { + if (dev_xdp_prog_count(upper) > 0) { + NL_SET_ERR_MSG(extack, "Cannot attach when an upper device already has a program"); return -EEXIST; } + } + + cur_prog = dev_xdp_prog(dev, mode); + /* can't replace attached prog with link */ + if (link && cur_prog) { + NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link"); + return -EBUSY; + } + if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) { + NL_SET_ERR_MSG(extack, "Active program does not match expected"); + return -EEXIST; + } + + /* put effective new program into new_prog */ + if (link) + new_prog = link->link.prog; - prog_id = __dev_xdp_query(dev, bpf_op, query); - if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && prog_id) { + if (new_prog) { + bool offload = mode == XDP_MODE_HW; + enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB + ? XDP_MODE_DRV : XDP_MODE_SKB; + + if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; } - - prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, - bpf_op == ops->ndo_bpf); - if (IS_ERR(prog)) - return PTR_ERR(prog); - - if (!offload && bpf_prog_is_dev_bound(prog->aux)) { - NL_SET_ERR_MSG(extack, "using device-bound program without HW_MODE flag is not supported"); - bpf_prog_put(prog); + if (!offload && dev_xdp_prog(dev, other_mode)) { + NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time"); + return -EEXIST; + } + if (!offload && bpf_prog_is_dev_bound(new_prog->aux)) { + NL_SET_ERR_MSG(extack, "Using device-bound program without HW_MODE flag is not supported"); + return -EINVAL; + } + if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) { + NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); + return -EINVAL; + } + if (new_prog->expected_attach_type == BPF_XDP_CPUMAP) { + NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device"); return -EINVAL; } + } - /* prog->aux->id may be 0 for orphaned device-bound progs */ - if (prog->aux->id && prog->aux->id == prog_id) { - bpf_prog_put(prog); - return 0; + /* don't call drivers if the effective program didn't change */ + if (new_prog != cur_prog) { + bpf_op = dev_xdp_bpf_op(dev, mode); + if (!bpf_op) { + NL_SET_ERR_MSG(extack, "Underlying driver does not support XDP in native mode"); + return -EOPNOTSUPP; } - } else { - if (!__dev_xdp_query(dev, bpf_op, query)) - return 0; + + err = dev_xdp_install(dev, mode, bpf_op, extack, flags, new_prog); + if (err) + return err; } - err = dev_xdp_install(dev, bpf_op, extack, flags, prog); - if (err < 0 && prog) - bpf_prog_put(prog); + if (link) + dev_xdp_set_link(dev, mode, link); + else + dev_xdp_set_prog(dev, mode, new_prog); + if (cur_prog) + bpf_prog_put(cur_prog); - return err; + return 0; } -/** - * dev_new_index - allocate an ifindex - * @net: the applicable net namespace - * - * Returns a suitable unique value for a new device interface - * number. The caller must hold the rtnl semaphore or the - * dev_base_lock to be sure it remains unique. - */ -static int dev_new_index(struct net *net) +static int dev_xdp_attach_link(struct net_device *dev, + struct netlink_ext_ack *extack, + struct bpf_xdp_link *link) { - int ifindex = net->ifindex; + return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags); +} - for (;;) { - if (++ifindex <= 0) - ifindex = 1; - if (!__dev_get_by_index(net, ifindex)) - return net->ifindex = ifindex; +static int dev_xdp_detach_link(struct net_device *dev, + struct netlink_ext_ack *extack, + struct bpf_xdp_link *link) +{ + enum bpf_xdp_mode mode; + bpf_op_t bpf_op; + + ASSERT_RTNL(); + + mode = dev_xdp_mode(dev, link->flags); + if (dev_xdp_link(dev, mode) != link) + return -EINVAL; + + bpf_op = dev_xdp_bpf_op(dev, mode); + WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); + dev_xdp_set_link(dev, mode, NULL); + return 0; +} + +static void bpf_xdp_link_release(struct bpf_link *link) +{ + struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); + + rtnl_lock(); + + /* if racing with net_device's tear down, xdp_link->dev might be + * already NULL, in which case link was already auto-detached + */ + if (xdp_link->dev) { + WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link)); + xdp_link->dev = NULL; } + + rtnl_unlock(); } -/* Delayed registration/unregisteration */ -static LIST_HEAD(net_todo_list); -DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); +static int bpf_xdp_link_detach(struct bpf_link *link) +{ + bpf_xdp_link_release(link); + return 0; +} -static void net_set_todo(struct net_device *dev) +static void bpf_xdp_link_dealloc(struct bpf_link *link) { - list_add_tail(&dev->todo_list, &net_todo_list); - dev_net(dev)->dev_unreg_count++; + struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); + + kfree(xdp_link); } -static void rollback_registered_many(struct list_head *head) +static void bpf_xdp_link_show_fdinfo(const struct bpf_link *link, + struct seq_file *seq) { - struct net_device *dev, *tmp; - LIST_HEAD(close_head); + struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); + u32 ifindex = 0; - BUG_ON(dev_boot_phase); - ASSERT_RTNL(); + rtnl_lock(); + if (xdp_link->dev) + ifindex = xdp_link->dev->ifindex; + rtnl_unlock(); - list_for_each_entry_safe(dev, tmp, head, unreg_list) { - /* Some devices call without registering - * for initialization unwind. Remove those - * devices and proceed with the remaining. - */ - if (dev->reg_state == NETREG_UNINITIALIZED) { - pr_debug("unregister_netdevice: device %s/%p never was registered\n", - dev->name, dev); + seq_printf(seq, "ifindex:\t%u\n", ifindex); +} - WARN_ON(1); - list_del(&dev->unreg_list); - continue; - } - dev->dismantle = true; - BUG_ON(dev->reg_state != NETREG_REGISTERED); - } +static int bpf_xdp_link_fill_link_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); + u32 ifindex = 0; - /* If device is running, close it first. */ - list_for_each_entry(dev, head, unreg_list) - list_add_tail(&dev->close_list, &close_head); - dev_close_many(&close_head, true); + rtnl_lock(); + if (xdp_link->dev) + ifindex = xdp_link->dev->ifindex; + rtnl_unlock(); - list_for_each_entry(dev, head, unreg_list) { - /* And unlink it from device chain. */ - unlist_netdevice(dev); + info->xdp.ifindex = ifindex; + return 0; +} - dev->reg_state = NETREG_UNREGISTERING; +static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, + struct bpf_prog *old_prog) +{ + struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); + enum bpf_xdp_mode mode; + bpf_op_t bpf_op; + int err = 0; + + rtnl_lock(); + + /* link might have been auto-released already, so fail */ + if (!xdp_link->dev) { + err = -ENOLINK; + goto out_unlock; } - flush_all_backlogs(); - synchronize_net(); + if (old_prog && link->prog != old_prog) { + err = -EPERM; + goto out_unlock; + } + old_prog = link->prog; + if (old_prog->type != new_prog->type || + old_prog->expected_attach_type != new_prog->expected_attach_type) { + err = -EINVAL; + goto out_unlock; + } - list_for_each_entry(dev, head, unreg_list) { - struct sk_buff *skb = NULL; + if (old_prog == new_prog) { + /* no-op, don't disturb drivers */ + bpf_prog_put(new_prog); + goto out_unlock; + } - /* Shutdown queueing discipline. */ - dev_shutdown(dev); + mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags); + bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); + err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, + xdp_link->flags, new_prog); + if (err) + goto out_unlock; - dev_xdp_uninstall(dev); + old_prog = xchg(&link->prog, new_prog); + bpf_prog_put(old_prog); - /* Notify protocols, that we are about to destroy - * this device. They should clean all the things. - */ - call_netdevice_notifiers(NETDEV_UNREGISTER, dev); +out_unlock: + rtnl_unlock(); + return err; +} - if (!dev->rtnl_link_ops || - dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL, NULL, 0); +static const struct bpf_link_ops bpf_xdp_link_lops = { + .release = bpf_xdp_link_release, + .dealloc = bpf_xdp_link_dealloc, + .detach = bpf_xdp_link_detach, + .show_fdinfo = bpf_xdp_link_show_fdinfo, + .fill_link_info = bpf_xdp_link_fill_link_info, + .update_prog = bpf_xdp_link_update, +}; - /* - * Flush the unicast and multicast chains - */ - dev_uc_flush(dev); - dev_mc_flush(dev); +int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct net *net = current->nsproxy->net_ns; + struct bpf_link_primer link_primer; + struct bpf_xdp_link *link; + struct net_device *dev; + int err, fd; - netdev_name_node_alt_flush(dev); - netdev_name_node_free(dev->name_node); + rtnl_lock(); + dev = dev_get_by_index(net, attr->link_create.target_ifindex); + if (!dev) { + rtnl_unlock(); + return -EINVAL; + } - if (dev->netdev_ops->ndo_uninit) - dev->netdev_ops->ndo_uninit(dev); + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto unlock; + } - if (skb) - rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); + bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog); + link->dev = dev; + link->flags = attr->link_create.flags; - /* Notifier chain MUST detach us all upper devices. */ - WARN_ON(netdev_has_any_upper_dev(dev)); - WARN_ON(netdev_has_any_lower_dev(dev)); + err = bpf_link_prime(&link->link, &link_primer); + if (err) { + kfree(link); + goto unlock; + } - /* Remove entries from kobject tree */ - netdev_unregister_kobject(dev); -#ifdef CONFIG_XPS - /* Remove XPS queueing entries */ - netif_reset_xps_queues_gt(dev, 0); -#endif + err = dev_xdp_attach_link(dev, NULL, link); + rtnl_unlock(); + + if (err) { + link->dev = NULL; + bpf_link_cleanup(&link_primer); + goto out_put_dev; } - synchronize_net(); + fd = bpf_link_settle(&link_primer); + /* link itself doesn't hold dev's refcnt to not complicate shutdown */ + dev_put(dev); + return fd; - list_for_each_entry(dev, head, unreg_list) - dev_put(dev); +unlock: + rtnl_unlock(); + +out_put_dev: + dev_put(dev); + return err; } -static void rollback_registered(struct net_device *dev) +/** + * dev_change_xdp_fd - set or clear a bpf program for a device rx path + * @dev: device + * @extack: netlink extended ack + * @fd: new program fd or negative value to clear + * @expected_fd: old program fd that userspace expects to replace or clear + * @flags: xdp-related flags + * + * Set or clear a bpf program for a device + */ +int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, + int fd, int expected_fd, u32 flags) { - LIST_HEAD(single); + enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags); + struct bpf_prog *new_prog = NULL, *old_prog = NULL; + int err; - list_add(&dev->unreg_list, &single); - rollback_registered_many(&single); - list_del(&single); + ASSERT_RTNL(); + + if (fd >= 0) { + new_prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, + mode != XDP_MODE_SKB); + if (IS_ERR(new_prog)) + return PTR_ERR(new_prog); + } + + if (expected_fd >= 0) { + old_prog = bpf_prog_get_type_dev(expected_fd, BPF_PROG_TYPE_XDP, + mode != XDP_MODE_SKB); + if (IS_ERR(old_prog)) { + err = PTR_ERR(old_prog); + old_prog = NULL; + goto err_out; + } + } + + err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags); + +err_out: + if (err && new_prog) + bpf_prog_put(new_prog); + if (old_prog) + bpf_prog_put(old_prog); + return err; +} + +/** + * dev_new_index - allocate an ifindex + * @net: the applicable net namespace + * + * Returns a suitable unique value for a new device interface + * number. The caller must hold the rtnl semaphore or the + * dev_base_lock to be sure it remains unique. + */ +static int dev_new_index(struct net *net) +{ + int ifindex = net->ifindex; + + for (;;) { + if (++ifindex <= 0) + ifindex = 1; + if (!__dev_get_by_index(net, ifindex)) + return net->ifindex = ifindex; + } +} + +/* Delayed registration/unregisteration */ +LIST_HEAD(net_todo_list); +DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); + +static void net_set_todo(struct net_device *dev) +{ + list_add_tail(&dev->todo_list, &net_todo_list); + atomic_inc(&dev_net(dev)->dev_unreg_count); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, @@ -8889,11 +9577,13 @@ static void netdev_sync_lower_features(struct net_device *upper, netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); lower->wanted_features &= ~feature; - netdev_update_features(lower); + __netdev_update_features(lower); if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); + else + netdev_features_change(lower); } } } @@ -8974,6 +9664,27 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, } } + if ((features & NETIF_F_GRO_HW) && (features & NETIF_F_LRO)) { + netdev_dbg(dev, "Dropping LRO feature since HW-GRO is requested.\n"); + features &= ~NETIF_F_LRO; + } + + if (features & NETIF_F_HW_TLS_TX) { + bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) == + (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); + bool hw_csum = features & NETIF_F_HW_CSUM; + + if (!ip_csum && !hw_csum) { + netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); + features &= ~NETIF_F_HW_TLS_TX; + } + } + + if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { + netdev_dbg(dev, "Dropping TLS RX HW offload feature since no RXCSUM feature.\n"); + features &= ~NETIF_F_HW_TLS_RX; + } + return features; } @@ -8994,7 +9705,7 @@ int __netdev_update_features(struct net_device *dev) /* driver might be less strict about feature dependencies */ features = netdev_fix_features(dev, features); - /* some features can't be enabled if they're off an an upper device */ + /* some features can't be enabled if they're off on an upper device */ netdev_for_each_upper_dev_rcu(dev, upper, iter) features = netdev_sync_upper_features(dev, upper, features); @@ -9118,6 +9829,11 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, else netif_dormant_off(dev); + if (rootdev->operstate == IF_OPER_TESTING) + netif_testing_on(dev); + else + netif_testing_off(dev); + if (netif_carrier_ok(rootdev)) netif_carrier_on(dev); else @@ -9134,7 +9850,7 @@ static int netif_alloc_rx_queues(struct net_device *dev) BUG_ON(count < 1); - rx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL); + rx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!rx) return -ENOMEM; @@ -9144,7 +9860,7 @@ static int netif_alloc_rx_queues(struct net_device *dev) rx[i].dev = dev; /* XDP RX-queue setup */ - err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i); + err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0); if (err < 0) goto err_rxq_info; } @@ -9178,7 +9894,7 @@ static void netdev_init_one_queue(struct net_device *dev, { /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); - lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key); + netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); queue->xmit_lock_owner = -1; netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; @@ -9201,7 +9917,7 @@ static int netif_alloc_netdev_queues(struct net_device *dev) if (count < 1 || count > 0xffff) return -EINVAL; - tx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL); + tx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!tx) return -ENOMEM; @@ -9225,48 +9941,15 @@ void netif_tx_stop_all_queues(struct net_device *dev) } EXPORT_SYMBOL(netif_tx_stop_all_queues); -static void netdev_register_lockdep_key(struct net_device *dev) -{ - lockdep_register_key(&dev->qdisc_tx_busylock_key); - lockdep_register_key(&dev->qdisc_running_key); - lockdep_register_key(&dev->qdisc_xmit_lock_key); - lockdep_register_key(&dev->addr_list_lock_key); -} - -static void netdev_unregister_lockdep_key(struct net_device *dev) -{ - lockdep_unregister_key(&dev->qdisc_tx_busylock_key); - lockdep_unregister_key(&dev->qdisc_running_key); - lockdep_unregister_key(&dev->qdisc_xmit_lock_key); - lockdep_unregister_key(&dev->addr_list_lock_key); -} - -void netdev_update_lockdep_key(struct net_device *dev) -{ - lockdep_unregister_key(&dev->addr_list_lock_key); - lockdep_register_key(&dev->addr_list_lock_key); - - lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); -} -EXPORT_SYMBOL(netdev_update_lockdep_key); - /** - * register_netdevice - register a network device - * @dev: device to register - * - * Take a completed network device structure and add it to the kernel - * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier - * chain. 0 is returned on success. A negative errno code is returned - * on a failure to set up the device, or if the name is a duplicate. - * - * Callers must hold the rtnl semaphore. You may want - * register_netdev() instead of this. + * register_netdevice() - register a network device + * @dev: device to register * - * BUGS: - * The locking appears insufficient to guarantee two parallel registers - * will not get the same name. + * Take a prepared network device structure and make it externally accessible. + * A %NETDEV_REGISTER message is sent to the netdev notifier chain. + * Callers must hold the rtnl lock - you may want register_netdev() + * instead of this. */ - int register_netdevice(struct net_device *dev) { int ret; @@ -9283,8 +9966,12 @@ int register_netdevice(struct net_device *dev) BUG_ON(dev->reg_state != NETREG_UNINITIALIZED); BUG_ON(!net); + ret = ethtool_check_ops(dev->ethtool_ops); + if (ret) + return ret; + spin_lock_init(&dev->addr_list_lock); - lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); + netdev_set_addr_lockdep_class(dev); ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) @@ -9326,7 +10013,7 @@ int register_netdevice(struct net_device *dev) dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF); dev->features |= NETIF_F_SOFT_FEATURES; - if (dev->netdev_ops->ndo_udp_tunnel_add) { + if (dev->udp_tunnel_nic_info) { dev->features |= NETIF_F_RX_UDP_TUNNEL_PORT; dev->hw_features |= NETIF_F_RX_UDP_TUNNEL_PORT; } @@ -9368,11 +10055,11 @@ int register_netdevice(struct net_device *dev) goto err_uninit; ret = netdev_register_kobject(dev); - if (ret) { - dev->reg_state = NETREG_UNREGISTERED; + write_lock(&dev_base_lock); + dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; + write_unlock(&dev_base_lock); + if (ret) goto err_uninit; - } - dev->reg_state = NETREG_REGISTERED; __netdev_update_features(dev); @@ -9386,8 +10073,10 @@ int register_netdevice(struct net_device *dev) linkwatch_init_dev(dev); dev_init_scheduler(dev); - dev_hold(dev); + + netdev_hold(dev, &dev->dev_registered_tracker, GFP_KERNEL); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); /* If the device has permanent device address, driver should @@ -9401,10 +10090,10 @@ int register_netdevice(struct net_device *dev) ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); ret = notifier_to_errno(ret); if (ret) { - rollback_registered(dev); - rcu_barrier(); - - dev->reg_state = NETREG_UNREGISTERED; + /* Expect explicit free_netdev() on failure */ + dev->needs_free_netdev = false; + unregister_netdevice_queue(dev, NULL); + goto out; } /* * Prevent userspace races by waiting until the network @@ -9499,17 +10188,25 @@ EXPORT_SYMBOL(register_netdev); int netdev_refcnt_read(const struct net_device *dev) { +#ifdef CONFIG_PCPU_DEV_REFCNT int i, refcnt = 0; for_each_possible_cpu(i) refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); return refcnt; +#else + return refcount_read(&dev->dev_refcnt); +#endif } EXPORT_SYMBOL(netdev_refcnt_read); +int netdev_unregister_timeout_secs __read_mostly = 10; + +#define WAIT_REFS_MIN_MSECS 1 +#define WAIT_REFS_MAX_MSECS 250 /** - * netdev_wait_allrefs - wait until all references are gone. - * @dev: target net_device + * netdev_wait_allrefs_any - wait until all references are gone. + * @list: list of net_devices to wait on * * This is called when unregistering network devices. * @@ -9519,50 +10216,68 @@ EXPORT_SYMBOL(netdev_refcnt_read); * We can get stuck here if buggy protocols don't correctly * call dev_put. */ -static void netdev_wait_allrefs(struct net_device *dev) +static struct net_device *netdev_wait_allrefs_any(struct list_head *list) { unsigned long rebroadcast_time, warning_time; - int refcnt; - - linkwatch_forget_dev(dev); + struct net_device *dev; + int wait = 0; rebroadcast_time = warning_time = jiffies; - refcnt = netdev_refcnt_read(dev); - while (refcnt != 0) { + list_for_each_entry(dev, list, todo_list) + if (netdev_refcnt_read(dev) == 1) + return dev; + + while (true) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); /* Rebroadcast unregister notification */ - call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + list_for_each_entry(dev, list, todo_list) + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); __rtnl_unlock(); rcu_barrier(); rtnl_lock(); - if (test_bit(__LINK_STATE_LINKWATCH_PENDING, - &dev->state)) { - /* We must not have linkwatch events - * pending on unregister. If this - * happens, we simply run the queue - * unscheduled, resulting in a noop - * for this device. - */ - linkwatch_run_queue(); - } + list_for_each_entry(dev, list, todo_list) + if (test_bit(__LINK_STATE_LINKWATCH_PENDING, + &dev->state)) { + /* We must not have linkwatch events + * pending on unregister. If this + * happens, we simply run the queue + * unscheduled, resulting in a noop + * for this device. + */ + linkwatch_run_queue(); + break; + } __rtnl_unlock(); rebroadcast_time = jiffies; } - msleep(250); + if (!wait) { + rcu_barrier(); + wait = WAIT_REFS_MIN_MSECS; + } else { + msleep(wait); + wait = min(wait << 1, WAIT_REFS_MAX_MSECS); + } + + list_for_each_entry(dev, list, todo_list) + if (netdev_refcnt_read(dev) == 1) + return dev; - refcnt = netdev_refcnt_read(dev); + if (time_after(jiffies, warning_time + + READ_ONCE(netdev_unregister_timeout_secs) * HZ)) { + list_for_each_entry(dev, list, todo_list) { + pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", + dev->name, netdev_refcnt_read(dev)); + ref_tracker_dir_print(&dev->refcnt_tracker, 10); + } - if (refcnt && time_after(jiffies, warning_time + 10 * HZ)) { - pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", - dev->name, refcnt); warning_time = jiffies; } } @@ -9594,53 +10309,62 @@ static void netdev_wait_allrefs(struct net_device *dev) */ void netdev_run_todo(void) { + struct net_device *dev, *tmp; struct list_head list; +#ifdef CONFIG_LOCKDEP + struct list_head unlink_list; + + list_replace_init(&net_unlink_list, &unlink_list); + + while (!list_empty(&unlink_list)) { + struct net_device *dev = list_first_entry(&unlink_list, + struct net_device, + unlink_list); + list_del_init(&dev->unlink_list); + dev->nested_level = dev->lower_level - 1; + } +#endif /* Snapshot list, allow later requests */ list_replace_init(&net_todo_list, &list); __rtnl_unlock(); - /* Wait for rcu callbacks to finish before next phase */ if (!list_empty(&list)) rcu_barrier(); - while (!list_empty(&list)) { - struct net_device *dev - = list_first_entry(&list, struct net_device, todo_list); - list_del(&dev->todo_list); - + list_for_each_entry_safe(dev, tmp, &list, todo_list) { if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { - pr_err("network todo '%s' but state %d\n", - dev->name, dev->reg_state); - dump_stack(); + netdev_WARN(dev, "run_todo but not unregistering\n"); + list_del(&dev->todo_list); continue; } + write_lock(&dev_base_lock); dev->reg_state = NETREG_UNREGISTERED; + write_unlock(&dev_base_lock); + linkwatch_forget_dev(dev); + } - netdev_wait_allrefs(dev); + while (!list_empty(&list)) { + dev = netdev_wait_allrefs_any(&list); + list_del(&dev->todo_list); /* paranoia */ - BUG_ON(netdev_refcnt_read(dev)); + BUG_ON(netdev_refcnt_read(dev) != 1); BUG_ON(!list_empty(&dev->ptype_all)); BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); -#if IS_ENABLED(CONFIG_DECNET) - WARN_ON(dev->dn_ptr); -#endif + if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) free_netdev(dev); - /* Report a network device has been unregistered */ - rtnl_lock(); - dev_net(dev)->dev_unreg_count--; - __rtnl_unlock(); - wake_up(&netdev_unregistering_wq); + if (atomic_dec_and_test(&dev_net(dev)->dev_unreg_count)) + wake_up(&netdev_unregistering_wq); /* Free network device */ kobject_put(&dev->dev.kobj); @@ -9676,6 +10400,21 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, } EXPORT_SYMBOL(netdev_stats_to_stats64); +struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev) +{ + struct net_device_core_stats __percpu *p; + + p = alloc_percpu_gfp(struct net_device_core_stats, + GFP_ATOMIC | __GFP_NOWARN); + + if (p && cmpxchg(&dev->core_stats, NULL, p)) + free_percpu(p); + + /* This READ_ONCE() pairs with the cmpxchg() above */ + return READ_ONCE(dev->core_stats); +} +EXPORT_SYMBOL(netdev_core_stats_alloc); + /** * dev_get_stats - get network device statistics * @dev: device to get statistics from @@ -9690,6 +10429,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage) { const struct net_device_ops *ops = dev->netdev_ops; + const struct net_device_core_stats __percpu *p; if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); @@ -9699,13 +10439,74 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, } else { netdev_stats_to_stats64(storage, &dev->stats); } - storage->rx_dropped += (unsigned long)atomic_long_read(&dev->rx_dropped); - storage->tx_dropped += (unsigned long)atomic_long_read(&dev->tx_dropped); - storage->rx_nohandler += (unsigned long)atomic_long_read(&dev->rx_nohandler); + + /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ + p = READ_ONCE(dev->core_stats); + if (p) { + const struct net_device_core_stats *core_stats; + int i; + + for_each_possible_cpu(i) { + core_stats = per_cpu_ptr(p, i); + storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); + storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); + storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); + storage->rx_otherhost_dropped += READ_ONCE(core_stats->rx_otherhost_dropped); + } + } return storage; } EXPORT_SYMBOL(dev_get_stats); +/** + * dev_fetch_sw_netstats - get per-cpu network device statistics + * @s: place to store stats + * @netstats: per-cpu network stats to read from + * + * Read per-cpu network statistics and populate the related fields in @s. + */ +void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, + const struct pcpu_sw_netstats __percpu *netstats) +{ + int cpu; + + for_each_possible_cpu(cpu) { + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + const struct pcpu_sw_netstats *stats; + unsigned int start; + + stats = per_cpu_ptr(netstats, cpu); + do { + start = u64_stats_fetch_begin_irq(&stats->syncp); + rx_packets = u64_stats_read(&stats->rx_packets); + rx_bytes = u64_stats_read(&stats->rx_bytes); + tx_packets = u64_stats_read(&stats->tx_packets); + tx_bytes = u64_stats_read(&stats->tx_bytes); + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + + s->rx_packets += rx_packets; + s->rx_bytes += rx_bytes; + s->tx_packets += tx_packets; + s->tx_bytes += tx_bytes; + } +} +EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats); + +/** + * dev_get_tstats64 - ndo_get_stats64 implementation + * @dev: device to get statistics from + * @s: place to store stats + * + * Populate @s from dev->stats and dev->tstats. Can be used as + * ndo_get_stats64() callback. + */ +void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s) +{ + netdev_stats_to_stats64(s, &dev->stats); + dev_fetch_sw_netstats(s, dev->tstats); +} +EXPORT_SYMBOL_GPL(dev_get_tstats64); + struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { struct netdev_queue *queue = dev_ingress_queue(dev); @@ -9784,16 +10585,22 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; - p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); + p = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!p) return NULL; dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; + ref_tracker_dir_init(&dev->refcnt_tracker, 128); +#ifdef CONFIG_PCPU_DEV_REFCNT dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_dev; + __dev_hold(dev); +#else + refcount_set(&dev->dev_refcnt, 1); +#endif if (dev_addr_init(dev)) goto free_pcpu; @@ -9803,12 +10610,17 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); - netdev_register_lockdep_key(dev); - - dev->gso_max_size = GSO_MAX_SIZE; + dev->gso_max_size = GSO_LEGACY_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; + dev->gro_max_size = GRO_LEGACY_MAX_SIZE; + dev->tso_max_size = TSO_LEGACY_MAX_SIZE; + dev->tso_max_segs = TSO_MAX_SEGS; dev->upper_level = 1; dev->lower_level = 1; +#ifdef CONFIG_LOCKDEP + dev->nested_level = 0; + INIT_LIST_HEAD(&dev->unlink_list); +#endif INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); @@ -9846,7 +10658,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; - nf_hook_ingress_init(dev); + nf_hook_netdev_init(dev); return dev; @@ -9855,8 +10667,10 @@ free_all: return NULL; free_pcpu: +#ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); free_dev: +#endif netdev_freemem(dev); return NULL; } @@ -9876,6 +10690,17 @@ void free_netdev(struct net_device *dev) struct napi_struct *p, *n; might_sleep(); + + /* When called immediately after register_netdevice() failed the unwind + * handling may still be dismantling the device. Handle that case by + * deferring the free. + */ + if (dev->reg_state == NETREG_UNREGISTERING) { + ASSERT_RTNL(); + dev->needs_free_netdev = true; + return; + } + netif_free_tx_queues(dev); netif_free_rx_queues(dev); @@ -9887,13 +10712,16 @@ void free_netdev(struct net_device *dev) list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); + ref_tracker_dir_exit(&dev->refcnt_tracker); +#ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; +#endif + free_percpu(dev->core_stats); + dev->core_stats = NULL; free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; - netdev_unregister_lockdep_key(dev); - /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { netdev_freemem(dev); @@ -9944,9 +10772,10 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) if (head) { list_move_tail(&dev->unreg_list, head); } else { - rollback_registered(dev); - /* Finish processing unregister after unlock */ - net_set_todo(dev); + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + unregister_netdevice_many(&single); } } EXPORT_SYMBOL(unregister_netdevice_queue); @@ -9960,14 +10789,103 @@ EXPORT_SYMBOL(unregister_netdevice_queue); */ void unregister_netdevice_many(struct list_head *head) { - struct net_device *dev; + struct net_device *dev, *tmp; + LIST_HEAD(close_head); - if (!list_empty(head)) { - rollback_registered_many(head); - list_for_each_entry(dev, head, unreg_list) - net_set_todo(dev); - list_del(head); + BUG_ON(dev_boot_phase); + ASSERT_RTNL(); + + if (list_empty(head)) + return; + + list_for_each_entry_safe(dev, tmp, head, unreg_list) { + /* Some devices call without registering + * for initialization unwind. Remove those + * devices and proceed with the remaining. + */ + if (dev->reg_state == NETREG_UNINITIALIZED) { + pr_debug("unregister_netdevice: device %s/%p never was registered\n", + dev->name, dev); + + WARN_ON(1); + list_del(&dev->unreg_list); + continue; + } + dev->dismantle = true; + BUG_ON(dev->reg_state != NETREG_REGISTERED); + } + + /* If device is running, close it first. */ + list_for_each_entry(dev, head, unreg_list) + list_add_tail(&dev->close_list, &close_head); + dev_close_many(&close_head, true); + + list_for_each_entry(dev, head, unreg_list) { + /* And unlink it from device chain. */ + write_lock(&dev_base_lock); + unlist_netdevice(dev, false); + dev->reg_state = NETREG_UNREGISTERING; + write_unlock(&dev_base_lock); + } + flush_all_backlogs(); + + synchronize_net(); + + list_for_each_entry(dev, head, unreg_list) { + struct sk_buff *skb = NULL; + + /* Shutdown queueing discipline. */ + dev_shutdown(dev); + + dev_xdp_uninstall(dev); + + netdev_offload_xstats_disable_all(dev); + + /* Notify protocols, that we are about to destroy + * this device. They should clean all the things. + */ + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, + GFP_KERNEL, NULL, 0); + + /* + * Flush the unicast and multicast chains + */ + dev_uc_flush(dev); + dev_mc_flush(dev); + + netdev_name_node_alt_flush(dev); + netdev_name_node_free(dev->name_node); + + if (dev->netdev_ops->ndo_uninit) + dev->netdev_ops->ndo_uninit(dev); + + if (skb) + rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); + + /* 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); +#ifdef CONFIG_XPS + /* Remove XPS queueing entries */ + netif_reset_xps_queues_gt(dev, 0); +#endif + } + + synchronize_net(); + + list_for_each_entry(dev, head, unreg_list) { + netdev_put(dev, &dev->dev_registered_tracker); + net_set_todo(dev); } + + list_del(head); } EXPORT_SYMBOL(unregister_netdevice_many); @@ -9991,11 +10909,13 @@ void unregister_netdev(struct net_device *dev) EXPORT_SYMBOL(unregister_netdev); /** - * dev_change_net_namespace - move device to different nethost namespace + * __dev_change_net_namespace - move device to different nethost namespace * @dev: device * @net: network namespace * @pat: If not NULL name pattern to try if the current device name * is already taken in the destination network namespace. + * @new_ifindex: If not zero, specifies device index in the target + * namespace. * * This function shuts down a device interface and moves it * to a new network namespace. On success 0 is returned, on @@ -10004,9 +10924,11 @@ EXPORT_SYMBOL(unregister_netdev); * Callers must hold the rtnl semaphore. */ -int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) +int __dev_change_net_namespace(struct net_device *dev, struct net *net, + const char *pat, int new_ifindex) { - int err, new_nsid, new_ifindex; + struct net *net_old = dev_net(dev); + int err, new_nsid; ASSERT_RTNL(); @@ -10021,14 +10943,14 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Get out if there is nothing todo */ err = 0; - if (net_eq(dev_net(dev), net)) + if (net_eq(net_old, net)) goto out; /* Pick the destination device name, and ensure * we can use it in the destination network namespace. */ err = -EEXIST; - if (__dev_get_by_name(net, dev->name)) { + if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; @@ -10037,6 +10959,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char goto out; } + /* Check that new_ifindex isn't used yet. */ + err = -EBUSY; + if (new_ifindex && __dev_get_by_index(net, new_ifindex)) + goto out; + /* * And now a mini version of register_netdevice unregister_netdevice. */ @@ -10045,7 +10972,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev_close(dev); /* And unlink it from device chain */ - unlist_netdevice(dev); + unlist_netdevice(dev, true); synchronize_net(); @@ -10064,10 +10991,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); /* If there is an ifindex conflict assign a new one */ - if (__dev_get_by_index(net, dev->ifindex)) - new_ifindex = dev_new_index(net); - else - new_ifindex = dev->ifindex; + if (!new_ifindex) { + if (__dev_get_by_index(net, dev->ifindex)) + new_ifindex = dev_new_index(net); + else + new_ifindex = dev->ifindex; + } rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid, new_ifindex); @@ -10097,6 +11026,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char err = device_rename(&dev->dev, dev->name); WARN_ON(err); + /* Adapt owner in case owning user namespace of target network + * namespace is different from the original one. + */ + err = netdev_change_owner(dev, net_old, net); + WARN_ON(err); + /* Add the device back in the hashes */ list_netdevice(dev); @@ -10114,7 +11049,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char out: return err; } -EXPORT_SYMBOL_GPL(dev_change_net_namespace); +EXPORT_SYMBOL_GPL(__dev_change_net_namespace); static int dev_cpu_dead(unsigned int oldcpu) { @@ -10171,11 +11106,11 @@ static int dev_cpu_dead(unsigned int oldcpu) /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { - netif_rx_ni(skb); + netif_rx(skb); input_queue_head_incr(oldsd); } while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { - netif_rx_ni(skb); + netif_rx(skb); input_queue_head_incr(oldsd); } @@ -10229,8 +11164,7 @@ static int __net_init netdev_init(struct net *net) BUILD_BUG_ON(GRO_HASH_BUCKETS > 8 * sizeof_field(struct napi_struct, gro_bitmask)); - if (net != &init_net) - INIT_LIST_HEAD(&net->dev_base_head); + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) @@ -10346,14 +11280,14 @@ static struct pernet_operations __net_initdata netdev_net_ops = { .exit = netdev_exit, }; -static void __net_exit default_device_exit(struct net *net) +static void __net_exit default_device_exit_net(struct net *net) { struct net_device *dev, *aux; /* * Push all migratable network devices back to the * initial network namespace */ - rtnl_lock(); + ASSERT_RTNL(); for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; @@ -10363,12 +11297,12 @@ static void __net_exit default_device_exit(struct net *net) continue; /* Leave virtual devices for the generic cleanup */ - if (dev->rtnl_link_ops) + if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); - if (__dev_get_by_name(&init_net, fb_name)) + if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { @@ -10377,35 +11311,6 @@ static void __net_exit default_device_exit(struct net *net) BUG(); } } - rtnl_unlock(); -} - -static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) -{ - /* Return with the rtnl_lock held when there are no network - * devices unregistering in any network namespace in net_list. - */ - struct net *net; - bool unregistering; - DEFINE_WAIT_FUNC(wait, woken_wake_function); - - add_wait_queue(&netdev_unregistering_wq, &wait); - for (;;) { - unregistering = false; - rtnl_lock(); - list_for_each_entry(net, net_list, exit_list) { - if (net->dev_unreg_count > 0) { - unregistering = true; - break; - } - } - if (!unregistering) - break; - __rtnl_unlock(); - - wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); - } - remove_wait_queue(&netdev_unregistering_wq, &wait); } static void __net_exit default_device_exit_batch(struct list_head *net_list) @@ -10419,18 +11324,12 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) struct net *net; LIST_HEAD(dev_kill_list); - /* To prevent network device cleanup code from dereferencing - * loopback devices or network devices that have been freed - * wait here for all pending unregistrations to complete, - * before unregistring the loopback device and allowing the - * network namespace be freed. - * - * The netdev todo list containing all network devices - * unregistrations that happen in default_device_exit_batch - * will run in the rtnl_unlock() at the end of - * default_device_exit_batch. - */ - rtnl_lock_unregistering(net_list); + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + default_device_exit_net(net); + cond_resched(); + } + list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) @@ -10444,7 +11343,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) } static struct pernet_operations __net_initdata default_device_ops = { - .exit = default_device_exit, .exit_batch = default_device_exit_batch, }; @@ -10475,8 +11373,6 @@ static int __init net_dev_init(void) for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); - INIT_LIST_HEAD(&offload_base); - if (register_pernet_subsys(&netdev_net_ops)) goto out; @@ -10498,10 +11394,11 @@ static int __init net_dev_init(void) INIT_LIST_HEAD(&sd->poll_list); sd->output_queue_tailp = &sd->output_queue; #ifdef CONFIG_RPS - sd->csd.func = rps_trigger_softirq; - sd->csd.info = sd; + INIT_CSD(&sd->csd, rps_trigger_softirq, sd); sd->cpu = i; #endif + INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd); + spin_lock_init(&sd->defer_lock); init_gro_hash(&sd->backlog); sd->backlog.poll = process_backlog; |