diff options
Diffstat (limited to 'net/core')
42 files changed, 14825 insertions, 7103 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 8a04dd22cf7..71093d94ad2 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -3,15 +3,17 @@ # obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ - gen_stats.o gen_estimator.o net_namespace.o + gen_stats.o gen_estimator.o net_namespace.o secure_seq.o flow_dissector.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ - neighbour.o rtnetlink.o utils.o link_watch.o filter.o + neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ + sock_diag.o dev_ioctl.o tso.o obj-$(CONFIG_XFRM) += flow.o obj-y += net-sysfs.o +obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_NET_DMA) += user_dma.o @@ -19,3 +21,6 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o +obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o +obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o +obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o diff --git a/net/core/datagram.c b/net/core/datagram.c index 18ac112ea7a..488dd1a825c 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -37,7 +37,6 @@ #include <linux/types.h> #include <linux/kernel.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/errno.h> @@ -49,6 +48,7 @@ #include <linux/highmem.h> #include <linux/spinlock.h> #include <linux/slab.h> +#include <linux/pagemap.h> #include <net/protocol.h> #include <linux/skbuff.h> @@ -57,6 +57,7 @@ #include <net/sock.h> #include <net/tcp_states.h> #include <trace/events/skb.h> +#include <net/busy_poll.h> /* * Is a socket 'connection oriented' ? @@ -66,7 +67,7 @@ static inline int connection_based(struct sock *sk) return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM; } -static int receiver_wake_function(wait_queue_t *wait, unsigned mode, int sync, +static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int sync, void *key) { unsigned long bits = (unsigned long)key; @@ -79,9 +80,10 @@ static int receiver_wake_function(wait_queue_t *wait, unsigned mode, int sync, return autoremove_wake_function(wait, mode, sync, key); } /* - * Wait for a packet.. + * Wait for the last received packet to be different from skb */ -static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) +static int wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, + const struct sk_buff *skb) { int error; DEFINE_WAIT_FUNC(wait, receiver_wake_function); @@ -93,7 +95,7 @@ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) if (error) goto out_err; - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (sk->sk_receive_queue.prev != skb) goto out; /* Socket shut down? */ @@ -133,6 +135,8 @@ out_noerr: * @sk: socket * @flags: MSG_ flags * @peeked: returns non-zero if this packet has been seen before + * @off: an offset in bytes to peek skb from. Returns an offset + * within an skb where data actually starts * @err: error code returned * * Get a datagram skbuff, understands the peeking, nonblocking wakeups @@ -157,10 +161,10 @@ out_noerr: * quite explicitly by POSIX 1003.1g, don't change them without having * the standard around please. */ -struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, - int *peeked, int *err) +struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, + int *peeked, int *off, int *err) { - struct sk_buff *skb; + struct sk_buff *skb, *last; long timeo; /* * Caller is allowed not to check sk->sk_err before skb_recv_datagram() @@ -180,28 +184,41 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, * However, this function was correct in any case. 8) */ unsigned long cpu_flags; + struct sk_buff_head *queue = &sk->sk_receive_queue; + int _off = *off; - spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags); - skb = skb_peek(&sk->sk_receive_queue); - if (skb) { + last = (struct sk_buff *)queue; + spin_lock_irqsave(&queue->lock, cpu_flags); + skb_queue_walk(queue, skb) { + last = skb; *peeked = skb->peeked; if (flags & MSG_PEEK) { + if (_off >= skb->len && (skb->len || _off || + skb->peeked)) { + _off -= skb->len; + continue; + } skb->peeked = 1; atomic_inc(&skb->users); } else - __skb_unlink(skb, &sk->sk_receive_queue); - } - spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags); + __skb_unlink(skb, queue); - if (skb) + spin_unlock_irqrestore(&queue->lock, cpu_flags); + *off = _off; return skb; + } + spin_unlock_irqrestore(&queue->lock, cpu_flags); + + if (sk_can_busy_loop(sk) && + sk_busy_loop(sk, flags & MSG_DONTWAIT)) + continue; /* User doesn't want to wait */ error = -EAGAIN; if (!timeo) goto no_packet; - } while (!wait_for_packet(sk, err, &timeo)); + } while (!wait_for_more_packets(sk, err, &timeo, last)); return NULL; @@ -211,13 +228,13 @@ no_packet: } EXPORT_SYMBOL(__skb_recv_datagram); -struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, +struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int noblock, int *err) { - int peeked; + int peeked, off = 0; return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - &peeked, err); + &peeked, &off, err); } EXPORT_SYMBOL(skb_recv_datagram); @@ -243,7 +260,6 @@ void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) unlock_sock_fast(sk, slow); /* skb is now orphaned, can be freed outside of locked section */ - trace_kfree_skb(skb, skb_free_datagram_locked); __kfree_skb(skb); } EXPORT_SYMBOL(skb_free_datagram_locked); @@ -324,15 +340,15 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { int err; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; @@ -410,15 +426,15 @@ int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset, /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { int err; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; @@ -500,15 +516,15 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { int err; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; @@ -558,6 +574,77 @@ fault: } EXPORT_SYMBOL(skb_copy_datagram_from_iovec); +/** + * zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec + * @skb: buffer to copy + * @from: io vector to copy from + * @offset: offset in the io vector to start copying from + * @count: amount of vectors to copy to buffer from + * + * The function will first copy up to headlen, and then pin the userspace + * pages and build frags through them. + * + * Returns 0, -EFAULT or -EMSGSIZE. + * Note: the iovec is not modified during the copy + */ +int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from, + int offset, size_t count) +{ + int len = iov_length(from, count) - offset; + int copy = min_t(int, skb_headlen(skb), len); + int size; + int i = 0; + + /* copy up to skb headlen */ + if (skb_copy_datagram_from_iovec(skb, 0, from, offset, copy)) + return -EFAULT; + + if (len == copy) + return 0; + + offset += copy; + while (count--) { + struct page *page[MAX_SKB_FRAGS]; + int num_pages; + unsigned long base; + unsigned long truesize; + + /* Skip over from offset and copied */ + if (offset >= from->iov_len) { + offset -= from->iov_len; + ++from; + continue; + } + len = from->iov_len - offset; + base = (unsigned long)from->iov_base + offset; + size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT; + if (i + size > MAX_SKB_FRAGS) + return -EMSGSIZE; + num_pages = get_user_pages_fast(base, size, 0, &page[i]); + if (num_pages != size) { + release_pages(&page[i], num_pages, 0); + return -EFAULT; + } + truesize = size * PAGE_SIZE; + skb->data_len += len; + skb->len += len; + skb->truesize += truesize; + atomic_add(truesize, &skb->sk->sk_wmem_alloc); + while (len) { + int off = base & ~PAGE_MASK; + int size = min_t(int, len, PAGE_SIZE - off); + skb_fill_page_desc(skb, i, page[i], off, size); + base += size; + len -= size; + i++; + } + offset = 0; + ++from; + } + return 0; +} +EXPORT_SYMBOL(zerocopy_sg_from_iovec); + static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, u8 __user *to, int len, __wsum *csump) @@ -585,16 +672,16 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { __wsum csum2; int err = 0; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; @@ -653,17 +740,37 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) sum = csum_fold(skb_checksum(skb, 0, len, skb->csum)); if (likely(!sum)) { - if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && + !skb->csum_complete_sw) netdev_rx_csum_fault(skb->dev); - skb->ip_summed = CHECKSUM_UNNECESSARY; } + skb->csum_valid = !sum; return sum; } EXPORT_SYMBOL(__skb_checksum_complete_head); __sum16 __skb_checksum_complete(struct sk_buff *skb) { - return __skb_checksum_complete_head(skb, skb->len); + __wsum csum; + __sum16 sum; + + csum = skb_checksum(skb, 0, skb->len, 0); + + /* skb->csum holds pseudo checksum */ + sum = csum_fold(csum_add(skb->csum, csum)); + if (likely(!sum)) { + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && + !skb->csum_complete_sw) + netdev_rx_csum_fault(skb->dev); + } + + /* Save full packet checksum */ + skb->csum = csum; + skb->ip_summed = CHECKSUM_COMPLETE; + skb->csum_complete_sw = 1; + skb->csum_valid = !sum; + + return sum; } EXPORT_SYMBOL(__skb_checksum_complete); @@ -745,7 +852,9 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, /* exceptional events? */ if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR; + mask |= POLLERR | + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); + if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) diff --git a/net/core/dev.c b/net/core/dev.c index d28b3a023bb..367a586d0c8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -73,7 +73,6 @@ */ #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/cpu.h> @@ -98,8 +97,6 @@ #include <net/net_namespace.h> #include <net/sock.h> #include <linux/rtnetlink.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> #include <linux/stat.h> #include <net/dst.h> #include <net/pkt_sched.h> @@ -107,12 +104,10 @@ #include <net/xfrm.h> #include <linux/highmem.h> #include <linux/init.h> -#include <linux/kmod.h> #include <linux/module.h> #include <linux/netpoll.h> #include <linux/rcupdate.h> #include <linux/delay.h> -#include <net/wext.h> #include <net/iw_handler.h> #include <asm/current.h> #include <linux/audit.h> @@ -132,6 +127,11 @@ #include <trace/events/skb.h> #include <linux/pci.h> #include <linux/inetdevice.h> +#include <linux/cpu_rmap.h> +#include <linux/static_key.h> +#include <linux/hashtable.h> +#include <linux/vmalloc.h> +#include <linux/if_macvlan.h> #include "net-sysfs.h" @@ -141,40 +141,16 @@ /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) -/* - * The list of packet types we will receive (as opposed to discard) - * and the routines to invoke. - * - * Why 16. Because with 16 the only overlap we get on a hash of the - * low nibble of the protocol value is RARP/SNAP/X.25. - * - * NOTE: That is no longer true with the addition of VLAN tags. Not - * sure which should go first, but I bet it won't make much - * difference if we are running VLANs. The good news is that - * this protocol won't be in the list unless compiled in, so - * the average user (w/out VLANs) will not be adversely affected. - * --BLG - * - * 0800 IP - * 8100 802.1Q VLAN - * 0001 802.3 - * 0002 AX.25 - * 0004 802.2 - * 8035 RARP - * 0005 SNAP - * 0805 X.25 - * 0806 ARP - * 8137 IPX - * 0009 Localtalk - * 86DD IPv6 - */ - -#define PTYPE_HASH_SIZE (16) -#define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) - static DEFINE_SPINLOCK(ptype_lock); -static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; -static struct list_head ptype_all __read_mostly; /* Taps */ +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, + struct net_device *dev, + struct netdev_notifier_info *info); /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl @@ -198,9 +174,23 @@ static struct list_head ptype_all __read_mostly; /* Taps */ DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); +/* protects napi_hash addition/deletion and napi_gen_id */ +static DEFINE_SPINLOCK(napi_hash_lock); + +static unsigned int napi_gen_id; +static DEFINE_HASHTABLE(napi_hash, 8); + +static seqcount_t devnet_rename_seq; + +static inline void dev_base_seq_inc(struct net *net) +{ + while (++net->dev_base_seq == 0); +} + static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { - unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); + unsigned int hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); + return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } @@ -224,7 +214,7 @@ static inline void rps_unlock(struct softnet_data *sd) } /* Device list insertion */ -static int list_netdevice(struct net_device *dev) +static void list_netdevice(struct net_device *dev) { struct net *net = dev_net(dev); @@ -236,7 +226,8 @@ static int list_netdevice(struct net_device *dev) hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock_bh(&dev_base_lock); - return 0; + + dev_base_seq_inc(net); } /* Device list removal @@ -252,6 +243,8 @@ static void unlist_netdevice(struct net_device *dev) hlist_del_rcu(&dev->name_hlist); hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock); + + dev_base_seq_inc(dev_net(dev)); } /* @@ -286,10 +279,9 @@ static const unsigned short netdev_lock_type[] = 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_IEEE802_TR, ARPHRD_IEEE80211, - ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, - ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, - ARPHRD_VOID, ARPHRD_NONE}; + 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", @@ -304,10 +296,9 @@ static const char *const netdev_lock_name[] = "_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_IEEE802_TR", "_xmit_IEEE80211", - "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", - "_xmit_PHONET_PIPE", "_xmit_IEEE802154", - "_xmit_VOID", "_xmit_NONE"}; + "_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)]; @@ -432,7 +423,7 @@ void __dev_remove_pack(struct packet_type *pt) } } - printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt); + pr_warn("dev_remove_pack: %p not found\n", pt); out: spin_unlock(&ptype_lock); } @@ -458,6 +449,81 @@ 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 list_head *head = &offload_base; + + spin_lock(&offload_lock); + list_add_rcu(&po->list, head); + 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 @@ -603,11 +669,10 @@ __setup("netdev=", netdev_boot_setup); struct net_device *__dev_get_by_name(struct net *net, const char *name) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_name_hash(net, name); - hlist_for_each_entry(dev, p, head, name_hlist) + hlist_for_each_entry(dev, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; @@ -629,11 +694,10 @@ EXPORT_SYMBOL(__dev_get_by_name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_name_hash(net, name); - hlist_for_each_entry_rcu(dev, p, head, name_hlist) + hlist_for_each_entry_rcu(dev, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; @@ -680,11 +744,10 @@ EXPORT_SYMBOL(dev_get_by_name); struct net_device *__dev_get_by_index(struct net *net, int ifindex) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); - hlist_for_each_entry(dev, p, head, index_hlist) + hlist_for_each_entry(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; @@ -705,11 +768,10 @@ EXPORT_SYMBOL(__dev_get_by_index); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); - hlist_for_each_entry_rcu(dev, p, head, index_hlist) + hlist_for_each_entry_rcu(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; @@ -743,13 +805,48 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) EXPORT_SYMBOL(dev_get_by_index); /** + * netdev_get_name - get a netdevice name, knowing its ifindex. + * @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_PREEMPT is not set. + */ +int netdev_get_name(struct net *net, char *name, int ifindex) +{ + struct net_device *dev; + unsigned int seq; + +retry: + seq = raw_seqcount_begin(&devnet_rename_seq); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + + strcpy(name, dev->name); + rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) { + cond_resched(); + goto retry; + } + + return 0; +} + +/** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device - * is not found or a pointer to the device. The caller must hold RCU + * is not found or a pointer to the device. + * The caller must hold RCU or RTNL. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * @@ -833,21 +930,21 @@ EXPORT_SYMBOL(dev_get_by_flags_rcu); * to allow sysfs to work. We also disallow any kind of * whitespace. */ -int dev_valid_name(const char *name) +bool dev_valid_name(const char *name) { if (*name == '\0') - return 0; + return false; if (strlen(name) >= IFNAMSIZ) - return 0; + return false; if (!strcmp(name, ".") || !strcmp(name, "..")) - return 0; + return false; while (*name) { if (*name == '/' || isspace(*name)) - return 0; + return false; name++; } - return 1; + return true; } EXPORT_SYMBOL(dev_valid_name); @@ -946,18 +1043,30 @@ int dev_alloc_name(struct net_device *dev, const char *name) } EXPORT_SYMBOL(dev_alloc_name); -static int dev_get_valid_name(struct net_device *dev, const char *name, bool fmt) +static int dev_alloc_name_ns(struct net *net, + struct net_device *dev, + const char *name) { - struct net *net; + char buf[IFNAMSIZ]; + int ret; - BUG_ON(!dev_net(dev)); - net = dev_net(dev); + ret = __dev_alloc_name(net, name, buf); + if (ret >= 0) + strlcpy(dev->name, buf, IFNAMSIZ); + return ret; +} + +static int dev_get_valid_name(struct net *net, + struct net_device *dev, + const char *name) +{ + BUG_ON(!net); if (!dev_valid_name(name)) return -EINVAL; - if (fmt && strchr(name, '%')) - return dev_alloc_name(dev, name); + if (strchr(name, '%')) + return dev_alloc_name_ns(net, dev, name); else if (__dev_get_by_name(net, name)) return -EEXIST; else if (dev->name != name) @@ -988,24 +1097,35 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) + write_seqcount_begin(&devnet_rename_seq); + + if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { + write_seqcount_end(&devnet_rename_seq); return 0; + } memcpy(oldname, dev->name, IFNAMSIZ); - err = dev_get_valid_name(dev, newname, 1); - if (err < 0) + err = dev_get_valid_name(net, dev, newname); + if (err < 0) { + write_seqcount_end(&devnet_rename_seq); return err; + } rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); + write_seqcount_end(&devnet_rename_seq); return ret; } + write_seqcount_end(&devnet_rename_seq); + + netdev_adjacent_rename_links(dev, oldname); + write_lock_bh(&dev_base_lock); - hlist_del(&dev->name_hlist); + hlist_del_rcu(&dev->name_hlist); write_unlock_bh(&dev_base_lock); synchronize_rcu(); @@ -1021,11 +1141,12 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; + write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); + memcpy(oldname, newname, IFNAMSIZ); goto rollback; } else { - printk(KERN_ERR - "%s: name change rollback failed: %d.\n", + pr_err("%s: name change rollback failed: %d\n", dev->name, ret); } } @@ -1043,22 +1164,23 @@ rollback: */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { + char *new_ifalias; + ASSERT_RTNL(); if (len >= IFALIASZ) return -EINVAL; if (!len) { - if (dev->ifalias) { - kfree(dev->ifalias); - dev->ifalias = NULL; - } + kfree(dev->ifalias); + dev->ifalias = NULL; return 0; } - dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); - if (!dev->ifalias) + new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); + if (!new_ifalias) return -ENOMEM; + dev->ifalias = new_ifalias; strlcpy(dev->ifalias, alias, len+1); return len; @@ -1088,40 +1210,33 @@ EXPORT_SYMBOL(netdev_features_change); void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { - call_netdevice_notifiers(NETDEV_CHANGE, dev); - rtmsg_ifinfo(RTM_NEWLINK, dev, 0); + struct netdev_notifier_change_info change_info; + + change_info.flags_changed = 0; + call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + &change_info.info); + rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); } } EXPORT_SYMBOL(netdev_state_change); -int netdev_bonding_change(struct net_device *dev, unsigned long event) -{ - return call_netdevice_notifiers(event, dev); -} -EXPORT_SYMBOL(netdev_bonding_change); - /** - * dev_load - load a network module - * @net: the applicable net namespace - * @name: name of interface + * netdev_notify_peers - notify network peers about existence of @dev + * @dev: network device * - * If a network interface is not present and the process has suitable - * privileges this function loads the module. If module loading is not - * available in this kernel then it becomes a nop. + * 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 dev_load(struct net *net, const char *name) +void netdev_notify_peers(struct net_device *dev) { - struct net_device *dev; - - rcu_read_lock(); - dev = dev_get_by_name_rcu(net, name); - rcu_read_unlock(); - - if (!dev && capable(CAP_NET_ADMIN)) - request_module("%s", name); + rtnl_lock(); + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); + rtnl_unlock(); } -EXPORT_SYMBOL(dev_load); +EXPORT_SYMBOL(netdev_notify_peers); static int __dev_open(struct net_device *dev) { @@ -1130,20 +1245,20 @@ static int __dev_open(struct net_device *dev) ASSERT_RTNL(); - /* - * Is it even present? - */ 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 + * or ndo_poll may be running while we open the device + */ + netpoll_poll_disable(dev); + ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev); ret = notifier_to_errno(ret); if (ret) return ret; - /* - * Call device private open method - */ set_bit(__LINK_STATE_START, &dev->state); if (ops->ndo_validate_addr) @@ -1152,32 +1267,16 @@ static int __dev_open(struct net_device *dev) if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); - /* - * If it went open OK then: - */ + netpoll_poll_enable(dev); if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { - /* - * Set the flags. - */ dev->flags |= IFF_UP; - - /* - * Enable NET_DMA - */ net_dmaengine_get(); - - /* - * Initialize multicasting status - */ dev_set_rx_mode(dev); - - /* - * Wakeup transmit queue engine - */ dev_activate(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; @@ -1199,74 +1298,95 @@ int dev_open(struct net_device *dev) { int ret; - /* - * Is it already up? - */ if (dev->flags & IFF_UP) return 0; - /* - * Open device - */ ret = __dev_open(dev); if (ret < 0) return ret; - /* - * ... and announce new interface. - */ - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); call_netdevice_notifiers(NETDEV_UP, dev); return ret; } EXPORT_SYMBOL(dev_open); -static int __dev_close(struct net_device *dev) +static int __dev_close_many(struct list_head *head) { - const struct net_device_ops *ops = dev->netdev_ops; + struct net_device *dev; ASSERT_RTNL(); might_sleep(); - /* - * Tell people we are going down, so that they can - * prepare to death, when device is still operating. - */ - call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); + list_for_each_entry(dev, head, close_list) { + /* Temporarily disable netpoll until the interface is down */ + netpoll_poll_disable(dev); - clear_bit(__LINK_STATE_START, &dev->state); + call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); - /* Synchronize to scheduled poll. We cannot touch poll list, - * it can be even on different cpu. So just clear netif_running(). - * - * dev->stop() will invoke napi_disable() on all of it's - * napi_struct instances on this device. - */ - smp_mb__after_clear_bit(); /* Commit netif_running(). */ + clear_bit(__LINK_STATE_START, &dev->state); - dev_deactivate(dev); + /* Synchronize to scheduled poll. We cannot touch poll list, it + * can be even on different cpu. So just clear netif_running(). + * + * dev->stop() will invoke napi_disable() on all of it's + * napi_struct instances on this device. + */ + smp_mb__after_atomic(); /* Commit netif_running(). */ + } - /* - * Call the device specific close. This cannot fail. - * Only if device is UP - * - * We allow it to be called even after a DETACH hot-plug - * event. - */ - if (ops->ndo_stop) - ops->ndo_stop(dev); + dev_deactivate_many(head); - /* - * Device is now down. - */ + list_for_each_entry(dev, head, close_list) { + const struct net_device_ops *ops = dev->netdev_ops; - dev->flags &= ~IFF_UP; + /* + * Call the device specific close. This cannot fail. + * Only if device is UP + * + * We allow it to be called even after a DETACH hot-plug + * event. + */ + if (ops->ndo_stop) + ops->ndo_stop(dev); - /* - * Shutdown NET_DMA - */ - net_dmaengine_put(); + dev->flags &= ~IFF_UP; + net_dmaengine_put(); + netpoll_poll_enable(dev); + } + + return 0; +} + +static int __dev_close(struct net_device *dev) +{ + int retval; + LIST_HEAD(single); + + list_add(&dev->close_list, &single); + retval = __dev_close_many(&single); + list_del(&single); + + return retval; +} + +static int dev_close_many(struct list_head *head) +{ + struct net_device *dev, *tmp; + + /* Remove the devices that don't need to be closed */ + list_for_each_entry_safe(dev, tmp, head, close_list) + if (!(dev->flags & IFF_UP)) + list_del_init(&dev->close_list); + + __dev_close_many(head); + + list_for_each_entry_safe(dev, tmp, head, close_list) { + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + call_netdevice_notifiers(NETDEV_DOWN, dev); + list_del_init(&dev->close_list); + } return 0; } @@ -1282,17 +1402,13 @@ static int __dev_close(struct net_device *dev) */ int dev_close(struct net_device *dev) { - if (!(dev->flags & IFF_UP)) - return 0; - - __dev_close(dev); - - /* - * Tell people we are down - */ - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); - call_netdevice_notifiers(NETDEV_DOWN, dev); + if (dev->flags & IFF_UP) { + LIST_HEAD(single); + list_add(&dev->close_list, &single); + dev_close_many(&single); + list_del(&single); + } return 0; } EXPORT_SYMBOL(dev_close); @@ -1308,25 +1424,35 @@ EXPORT_SYMBOL(dev_close); */ void dev_disable_lro(struct net_device *dev) { - if (dev->ethtool_ops && dev->ethtool_ops->get_flags && - dev->ethtool_ops->set_flags) { - u32 flags = dev->ethtool_ops->get_flags(dev); - if (flags & ETH_FLAG_LRO) { - flags &= ~ETH_FLAG_LRO; - dev->ethtool_ops->set_flags(dev, flags); - } - } - WARN_ON(dev->features & NETIF_F_LRO); + /* + * If we're trying to disable lro on a vlan device + * use the underlying physical device instead + */ + if (is_vlan_dev(dev)) + dev = vlan_dev_real_dev(dev); + + /* the same for macvlan devices */ + if (netif_is_macvlan(dev)) + dev = macvlan_dev_real_dev(dev); + + dev->wanted_features &= ~NETIF_F_LRO; + netdev_update_features(dev); + + if (unlikely(dev->features & NETIF_F_LRO)) + netdev_WARN(dev, "failed to disable LRO!\n"); } EXPORT_SYMBOL(dev_disable_lro); +static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, + struct net_device *dev) +{ + struct netdev_notifier_info info; -static int dev_boot_phase = 1; + netdev_notifier_info_init(&info, dev); + return nb->notifier_call(nb, val, &info); +} -/* - * Device change register/unregister. These are not inline or static - * as we export them to the world. - */ +static int dev_boot_phase = 1; /** * register_netdevice_notifier - register a network notifier block @@ -1357,7 +1483,7 @@ int register_netdevice_notifier(struct notifier_block *nb) goto unlock; for_each_net(net) { for_each_netdev(net, dev) { - err = nb->notifier_call(nb, NETDEV_REGISTER, dev); + err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); err = notifier_to_errno(err); if (err) goto rollback; @@ -1365,7 +1491,7 @@ int register_netdevice_notifier(struct notifier_block *nb) if (!(dev->flags & IFF_UP)) continue; - nb->notifier_call(nb, NETDEV_UP, dev); + call_netdevice_notifier(nb, NETDEV_UP, dev); } } @@ -1378,17 +1504,18 @@ rollback: for_each_net(net) { for_each_netdev(net, dev) { if (dev == last) - break; + goto outroll; if (dev->flags & IFF_UP) { - nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); - nb->notifier_call(nb, NETDEV_DOWN, dev); + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); } - nb->notifier_call(nb, NETDEV_UNREGISTER, dev); - nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } } +outroll: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } @@ -1402,20 +1529,59 @@ EXPORT_SYMBOL(register_netdevice_notifier); * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. + * + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { + struct net_device *dev; + struct net *net; int err; rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_chain, nb); + if (err) + goto unlock; + + for_each_net(net) { + for_each_netdev(net, dev) { + if (dev->flags & IFF_UP) { + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); + } + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); + } + } +unlock: rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier); /** + * call_netdevice_notifiers_info - call all network notifier blocks + * @val: value passed unmodified to notifier function + * @dev: net_device pointer passed unmodified to notifier function + * @info: notifier information data + * + * Call all network notifier blocks. Parameters and return value + * are as for raw_notifier_call_chain(). + */ + +static int call_netdevice_notifiers_info(unsigned long val, + struct net_device *dev, + struct netdev_notifier_info *info) +{ + ASSERT_RTNL(); + netdev_notifier_info_init(info, dev); + return raw_notifier_call_chain(&netdev_chain, val, info); +} + +/** * call_netdevice_notifiers - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function @@ -1426,38 +1592,104 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - ASSERT_RTNL(); - return raw_notifier_call_chain(&netdev_chain, val, dev); + struct netdev_notifier_info info; + + return call_netdevice_notifiers_info(val, dev, &info); } +EXPORT_SYMBOL(call_netdevice_notifiers); -/* When > 0 there are consumers of rx skb time stamps */ -static atomic_t netstamp_needed = ATOMIC_INIT(0); +static struct static_key netstamp_needed __read_mostly; +#ifdef HAVE_JUMP_LABEL +/* We are not allowed to call static_key_slow_dec() from irq context + * If net_disable_timestamp() is called from irq context, defer the + * static_key_slow_dec() calls. + */ +static atomic_t netstamp_needed_deferred; +#endif void net_enable_timestamp(void) { - atomic_inc(&netstamp_needed); +#ifdef HAVE_JUMP_LABEL + int deferred = atomic_xchg(&netstamp_needed_deferred, 0); + + if (deferred) { + while (--deferred) + static_key_slow_dec(&netstamp_needed); + return; + } +#endif + static_key_slow_inc(&netstamp_needed); } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { - atomic_dec(&netstamp_needed); +#ifdef HAVE_JUMP_LABEL + if (in_interrupt()) { + atomic_inc(&netstamp_needed_deferred); + return; + } +#endif + static_key_slow_dec(&netstamp_needed); } EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { - if (atomic_read(&netstamp_needed)) + skb->tstamp.tv64 = 0; + if (static_key_false(&netstamp_needed)) __net_timestamp(skb); - else - skb->tstamp.tv64 = 0; } -static inline void net_timestamp_check(struct sk_buff *skb) +#define net_timestamp_check(COND, SKB) \ + if (static_key_false(&netstamp_needed)) { \ + if ((COND) && !(SKB)->tstamp.tv64) \ + __net_timestamp(SKB); \ + } \ + +bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb) { - if (!skb->tstamp.tv64 && atomic_read(&netstamp_needed)) - __net_timestamp(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; +} +EXPORT_SYMBOL_GPL(is_skb_forwardable); + +int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + if (skb_copy_ubufs(skb, GFP_ATOMIC)) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + } + + if (unlikely(!is_skb_forwardable(dev, skb))) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + + skb_scrub_packet(skb, true); + skb->protocol = eth_type_trans(skb, dev); + + return 0; } +EXPORT_SYMBOL_GPL(__dev_forward_skb); /** * dev_forward_skb - loopback an skb to another netif @@ -1479,23 +1711,33 @@ static inline void net_timestamp_check(struct sk_buff *skb) */ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { - skb_orphan(skb); - nf_reset(skb); - - if (unlikely(!(dev->flags & IFF_UP) || - (skb->len > (dev->mtu + dev->hard_header_len + VLAN_HLEN)))) { - atomic_long_inc(&dev->rx_dropped); - kfree_skb(skb); - return NET_RX_DROP; - } - skb_set_dev(skb, dev); - skb->tstamp.tv64 = 0; - skb->pkt_type = PACKET_HOST; - skb->protocol = eth_type_trans(skb, dev); - return netif_rx(skb); + return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); +static inline int deliver_skb(struct sk_buff *skb, + struct packet_type *pt_prev, + struct net_device *orig_dev) +{ + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + return -ENOMEM; + atomic_inc(&skb->users); + return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); +} + +static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) +{ + if (!ptype->af_packet_priv || !skb->sk) + return false; + + if (ptype->id_match) + return ptype->id_match(ptype, skb->sk); + else if ((struct sock *)ptype->af_packet_priv == skb->sk) + return true; + + return false; +} + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -1504,13 +1746,8 @@ EXPORT_SYMBOL_GPL(dev_forward_skb); static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct packet_type *ptype; - -#ifdef CONFIG_NET_CLS_ACT - if (!(skb->tstamp.tv64 && (G_TC_FROM(skb->tc_verd) & AT_INGRESS))) - net_timestamp_set(skb); -#else - net_timestamp_set(skb); -#endif + struct sk_buff *skb2 = NULL; + struct packet_type *pt_prev = NULL; rcu_read_lock(); list_for_each_entry_rcu(ptype, &ptype_all, list) { @@ -1518,12 +1755,19 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) * they originated from - MvS (miquels@drinkel.ow.org) */ if ((ptype->dev == dev || !ptype->dev) && - (ptype->af_packet_priv == NULL || - (struct sock *)ptype->af_packet_priv != skb->sk)) { - struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + (!skb_loop_sk(ptype, skb))) { + if (pt_prev) { + deliver_skb(skb2, pt_prev, skb->dev); + pt_prev = ptype; + continue; + } + + skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) break; + net_timestamp_set(skb2); + /* skb->nh should be correctly set by sender, so that the second statement is just protection against buggy protocols. @@ -1531,23 +1775,286 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb2); if (skb_network_header(skb2) < skb2->data || - skb2->network_header > skb2->tail) { - if (net_ratelimit()) - printk(KERN_CRIT "protocol %04x is " - "buggy, dev %s\n", - ntohs(skb2->protocol), - dev->name); + skb_network_header(skb2) > skb_tail_pointer(skb2)) { + net_crit_ratelimited("protocol %04x is buggy, dev %s\n", + ntohs(skb2->protocol), + dev->name); skb_reset_network_header(skb2); } skb2->transport_header = skb2->network_header; skb2->pkt_type = PACKET_OUTGOING; - ptype->func(skb2, skb->dev, ptype, skb->dev); + pt_prev = ptype; } } + if (pt_prev) + pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); rcu_read_unlock(); } +/** + * netif_setup_tc - Handle tc mappings on real_num_tx_queues change + * @dev: Network device + * @txq: number of queues available + * + * If real_num_tx_queues is changed the tc mappings may no longer be + * valid. To resolve this verify the tc mapping remains valid and if + * not NULL the mapping. With no priorities mapping to this + * offset/count pair it will no longer be used. In the worst case TC0 + * is invalid nothing can be done so disable priority mappings. If is + * expected that drivers will fix this mapping if they can before + * calling netif_set_real_num_tx_queues. + */ +static void netif_setup_tc(struct net_device *dev, unsigned int txq) +{ + int i; + struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; + + /* 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"); + dev->num_tc = 0; + return; + } + + /* Invalidated prio to tc mappings set to TC0 */ + for (i = 1; i < TC_BITMASK + 1; i++) { + int q = netdev_get_prio_tc_map(dev, i); + + 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_set_prio_tc_map(dev, i, 0); + } + } +} + +#ifdef CONFIG_XPS +static DEFINE_MUTEX(xps_map_mutex); +#define xmap_dereference(P) \ + rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) + +static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps, + int cpu, u16 index) +{ + struct xps_map *map = NULL; + int pos; + + if (dev_maps) + map = xmap_dereference(dev_maps->cpu_map[cpu]); + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] == index) { + if (map->len > 1) { + map->queues[pos] = map->queues[--map->len]; + } else { + RCU_INIT_POINTER(dev_maps->cpu_map[cpu], NULL); + kfree_rcu(map, rcu); + map = NULL; + } + break; + } + } + + return map; +} + +static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) +{ + struct xps_dev_maps *dev_maps; + int cpu, i; + bool active = false; + + mutex_lock(&xps_map_mutex); + dev_maps = xmap_dereference(dev->xps_maps); + + if (!dev_maps) + goto out_no_maps; + + for_each_possible_cpu(cpu) { + for (i = index; i < dev->num_tx_queues; i++) { + if (!remove_xps_queue(dev_maps, cpu, i)) + break; + } + if (i == dev->num_tx_queues) + active = true; + } + + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + + for (i = index; i < dev->num_tx_queues; i++) + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i), + NUMA_NO_NODE); + +out_no_maps: + mutex_unlock(&xps_map_mutex); +} + +static struct xps_map *expand_xps_map(struct xps_map *map, + int cpu, u16 index) +{ + struct xps_map *new_map; + int alloc_len = XPS_MIN_MAP_ALLOC; + int i, pos; + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] != index) + continue; + return map; + } + + /* Need to add queue to this CPU's existing map */ + if (map) { + if (pos < map->alloc_len) + return map; + + alloc_len = map->alloc_len * 2; + } + + /* Need to allocate new map to store queue on this CPU's map */ + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, + cpu_to_node(cpu)); + if (!new_map) + return NULL; + + for (i = 0; i < pos; i++) + new_map->queues[i] = map->queues[i]; + new_map->alloc_len = alloc_len; + new_map->len = pos; + + return new_map; +} + +int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, + u16 index) +{ + struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; + struct xps_map *map, *new_map; + int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES); + int cpu, numa_node_id = -2; + bool active = false; + + mutex_lock(&xps_map_mutex); + + dev_maps = xmap_dereference(dev->xps_maps); + + /* allocate memory for queue storage */ + for_each_online_cpu(cpu) { + if (!cpumask_test_cpu(cpu, mask)) + continue; + + if (!new_dev_maps) + new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); + if (!new_dev_maps) { + mutex_unlock(&xps_map_mutex); + return -ENOMEM; + } + + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + + map = expand_xps_map(map, cpu, index); + if (!map) + goto error; + + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + if (!new_dev_maps) + goto out_no_new_maps; + + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) { + /* add queue to CPU maps */ + int pos = 0; + + map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + while ((pos < map->len) && (map->queues[pos] != index)) + pos++; + + if (pos == map->len) + map->queues[map->len++] = index; +#ifdef CONFIG_NUMA + if (numa_node_id == -2) + numa_node_id = cpu_to_node(cpu); + else if (numa_node_id != cpu_to_node(cpu)) + 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->cpu_map[cpu]); + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + } + + rcu_assign_pointer(dev->xps_maps, new_dev_maps); + + /* Cleanup old maps */ + if (dev_maps) { + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = xmap_dereference(dev_maps->cpu_map[cpu]); + if (map && map != new_map) + kfree_rcu(map, rcu); + } + + kfree_rcu(dev_maps, rcu); + } + + dev_maps = new_dev_maps; + active = true; + +out_no_new_maps: + /* 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 queue from unused CPUs */ + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) + continue; + + if (remove_xps_queue(dev_maps, cpu, index)) + active = true; + } + + /* free map if not active */ + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + +out_no_maps: + mutex_unlock(&xps_map_mutex); + + return 0; +error: + /* remove any maps that we added */ + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + if (new_map && new_map != map) + kfree(new_map); + } + + mutex_unlock(&xps_map_mutex); + + kfree(new_dev_maps); + return -ENOMEM; +} +EXPORT_SYMBOL(netif_set_xps_queue); + +#endif /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. @@ -1559,7 +2066,8 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL; - if (dev->reg_state == NETREG_REGISTERED) { + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, @@ -1567,8 +2075,15 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (rc) return rc; - if (txq < dev->real_num_tx_queues) + if (dev->num_tc) + netif_setup_tc(dev, txq); + + if (txq < dev->real_num_tx_queues) { qdisc_reset_all_tx_gt(dev, txq); +#ifdef CONFIG_XPS + netif_reset_xps_queues_gt(dev, txq); +#endif + } } dev->real_num_tx_queues = txq; @@ -1576,7 +2091,7 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) } EXPORT_SYMBOL(netif_set_real_num_tx_queues); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS /** * netif_set_real_num_rx_queues - set actual number of RX queues used * @dev: Network device @@ -1609,6 +2124,18 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) EXPORT_SYMBOL(netif_set_real_num_rx_queues); #endif +/** + * 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. + */ +int netif_get_num_default_rss_queues(void) +{ + return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus()); +} +EXPORT_SYMBOL(netif_get_num_default_rss_queues); + static inline void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; @@ -1630,30 +2157,42 @@ void __netif_schedule(struct Qdisc *q) } EXPORT_SYMBOL(__netif_schedule); -void dev_kfree_skb_irq(struct sk_buff *skb) +struct dev_kfree_skb_cb { + enum skb_free_reason reason; +}; + +static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) { - if (atomic_dec_and_test(&skb->users)) { - struct softnet_data *sd; - unsigned long flags; + return (struct dev_kfree_skb_cb *)skb->cb; +} + +void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) +{ + unsigned long flags; - local_irq_save(flags); - sd = &__get_cpu_var(softnet_data); - skb->next = sd->completion_queue; - sd->completion_queue = skb; - raise_softirq_irqoff(NET_TX_SOFTIRQ); - local_irq_restore(flags); + if (likely(atomic_read(&skb->users) == 1)) { + smp_rmb(); + atomic_set(&skb->users, 0); + } else if (likely(!atomic_dec_and_test(&skb->users))) { + return; } + get_kfree_skb_cb(skb)->reason = reason; + local_irq_save(flags); + skb->next = __this_cpu_read(softnet_data.completion_queue); + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); } -EXPORT_SYMBOL(dev_kfree_skb_irq); +EXPORT_SYMBOL(__dev_kfree_skb_irq); -void dev_kfree_skb_any(struct sk_buff *skb) +void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { if (in_irq() || irqs_disabled()) - dev_kfree_skb_irq(skb); + __dev_kfree_skb_irq(skb, reason); else dev_kfree_skb(skb); } -EXPORT_SYMBOL(dev_kfree_skb_any); +EXPORT_SYMBOL(__dev_kfree_skb_any); /** @@ -1687,62 +2226,25 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); -static bool can_checksum_protocol(unsigned long features, __be16 protocol) -{ - return ((features & NETIF_F_NO_CSUM) || - ((features & NETIF_F_V4_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_V6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); -} - -static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) +static void skb_warn_bad_offload(const struct sk_buff *skb) { - __be16 protocol = skb->protocol; - int features = dev->features; + static const netdev_features_t null_features = 0; + struct net_device *dev = skb->dev; + const char *driver = ""; - if (vlan_tx_tag_present(skb)) { - features &= dev->vlan_features; - } else if (protocol == htons(ETH_P_8021Q)) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - protocol = veh->h_vlan_encapsulated_proto; - features &= dev->vlan_features; - } + if (!net_ratelimit()) + return; - return can_checksum_protocol(features, protocol); -} + if (dev && dev->dev.parent) + driver = dev_driver_string(dev->dev.parent); -/** - * skb_dev_set -- assign a new device to a buffer - * @skb: buffer for the new device - * @dev: network device - * - * If an skb is owned by a device already, we have to reset - * all data private to the namespace a device belongs to - * before assigning it a new device. - */ -#ifdef CONFIG_NET_NS -void skb_set_dev(struct sk_buff *skb, struct net_device *dev) -{ - skb_dst_drop(skb); - if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) { - secpath_reset(skb); - nf_reset(skb); - skb_init_secmark(skb); - skb->mark = 0; - skb->priority = 0; - skb->nf_trace = 0; - skb->ipvs_property = 0; -#ifdef CONFIG_NET_SCHED - skb->tc_index = 0; -#endif - } - skb->dev = dev; + WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d " + "gso_type=%d ip_summed=%d\n", + driver, dev ? &dev->features : &null_features, + skb->sk ? &skb->sk->sk_route_caps : &null_features, + skb->len, skb->data_len, skb_shinfo(skb)->gso_size, + skb_shinfo(skb)->gso_type, skb->ip_summed); } -EXPORT_SYMBOL(skb_set_dev); -#endif /* CONFIG_NET_NS */ /* * Invalidate hardware checksum when packet is to be mangled, and @@ -1757,11 +2259,20 @@ int skb_checksum_help(struct sk_buff *skb) goto out_set_summed; if (unlikely(skb_shinfo(skb)->gso_size)) { - /* Let GSO fix up the checksum. */ - goto out_set_summed; + skb_warn_bad_offload(skb); + return -EINVAL; } - offset = skb->csum_start - skb_headroom(skb); + /* Before computing a checksum, we should make sure no frag could + * be modified by an external entity : checksum could be wrong. + */ + if (skb_has_shared_frag(skb)) { + ret = __skb_linearize(skb); + if (ret) + goto out; + } + + offset = skb_checksum_start_offset(skb); BUG_ON(offset >= skb_headlen(skb)); csum = skb_checksum(skb, offset, skb->len - offset, 0); @@ -1783,69 +2294,85 @@ out: } EXPORT_SYMBOL(skb_checksum_help); -/** - * skb_gso_segment - Perform segmentation on skb. - * @skb: buffer to segment - * @features: features for the output path (see dev->features) - * - * This function segments the given skb and returns a list of segments. - * - * It may return NULL if the skb requires no segmentation. This is - * only possible when GSO is used for verifying header integrity. - */ -struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) +__be16 skb_network_protocol(struct sk_buff *skb, int *depth) { - struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); - struct packet_type *ptype; + unsigned int vlan_depth = skb->mac_len; __be16 type = skb->protocol; - int vlan_depth = ETH_HLEN; - int err; - while (type == htons(ETH_P_8021Q)) { - struct vlan_hdr *vh; + /* Tunnel gso handlers can set protocol to ethernet. */ + if (type == htons(ETH_P_TEB)) { + struct ethhdr *eth; - if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) - return ERR_PTR(-EINVAL); + if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) + return 0; - vh = (struct vlan_hdr *)(skb->data + vlan_depth); - type = vh->h_vlan_encapsulated_proto; - vlan_depth += VLAN_HLEN; + eth = (struct ethhdr *)skb_mac_header(skb); + type = eth->h_proto; } - skb_reset_mac_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; - __skb_pull(skb, skb->mac_len); + /* if skb->protocol is 802.1Q/AD then the header should already be + * present at mac_len - VLAN_HLEN (if mac_len > 0), or at + * ETH_HLEN otherwise + */ + if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { + if (vlan_depth) { + if (unlikely(WARN_ON(vlan_depth < VLAN_HLEN))) + return 0; + vlan_depth -= VLAN_HLEN; + } else { + vlan_depth = ETH_HLEN; + } + do { + struct vlan_hdr *vh; - if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { - struct net_device *dev = skb->dev; - struct ethtool_drvinfo info = {}; + if (unlikely(!pskb_may_pull(skb, + vlan_depth + VLAN_HLEN))) + return 0; - if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) - dev->ethtool_ops->get_drvinfo(dev, &info); + vh = (struct vlan_hdr *)(skb->data + vlan_depth); + type = vh->h_vlan_encapsulated_proto; + vlan_depth += VLAN_HLEN; + } while (type == htons(ETH_P_8021Q) || + type == htons(ETH_P_8021AD)); + } - WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d ip_summed=%d\n", - info.driver, dev ? dev->features : 0L, - skb->sk ? skb->sk->sk_route_caps : 0L, - skb->len, skb->data_len, skb->ip_summed); + *depth = vlan_depth; - if (skb_header_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) - return ERR_PTR(err); - } + return type; +} + +/** + * 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, - &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { - if (ptype->type == type && !ptype->dev && ptype->gso_segment) { + list_for_each_entry_rcu(ptype, &offload_base, list) { + if (ptype->type == type && ptype->callbacks.gso_segment) { if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { - err = ptype->gso_send_check(skb); + int err; + + err = ptype->callbacks.gso_send_check(skb); segs = ERR_PTR(err); if (err || skb_gso_ok(skb, features)) break; __skb_push(skb, (skb->data - skb_network_header(skb))); } - segs = ptype->gso_segment(skb, features); + segs = ptype->callbacks.gso_segment(skb, features); break; } } @@ -1855,15 +2382,59 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) return segs; } -EXPORT_SYMBOL(skb_gso_segment); +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) +{ + if (tx_path) + return skb->ip_summed != CHECKSUM_PARTIAL; + else + return skb->ip_summed == CHECKSUM_NONE; +} + +/** + * __skb_gso_segment - Perform segmentation on skb. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + * @tx_path: whether it is called in TX path + * + * This function segments the given skb and returns a list of segments. + * + * It may return NULL if the skb requires no segmentation. This is + * only possible when GSO is used for verifying header integrity. + */ +struct sk_buff *__skb_gso_segment(struct sk_buff *skb, + netdev_features_t features, bool tx_path) +{ + if (unlikely(skb_needs_check(skb, tx_path))) { + int err; + + skb_warn_bad_offload(skb); + + if (skb_header_cloned(skb) && + (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + return ERR_PTR(err); + } + + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); + SKB_GSO_CB(skb)->encap_level = 0; + + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + return skb_mac_gso_segment(skb, features); +} +EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev) { if (net_ratelimit()) { - printk(KERN_ERR "%s: hw csum failure.\n", - dev ? dev->name : "<unknown>"); + pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>"); dump_stack(); } } @@ -1880,9 +2451,11 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) #ifdef CONFIG_HIGHMEM int i; if (!(dev->features & NETIF_F_HIGHDMA)) { - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - if (PageHighMem(skb_shinfo(skb)->frags[i].page)) + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + if (PageHighMem(skb_frag_page(frag))) return 1; + } } if (PCI_DMA_BUS_IS_PHYS) { @@ -1891,7 +2464,8 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) if (!pdev) return 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - dma_addr_t addr = page_to_phys(skb_shinfo(skb)->frags[i].page); + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + dma_addr_t addr = page_to_phys(skb_frag_page(frag)); if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask) return 1; } @@ -1910,13 +2484,8 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) { struct dev_gso_cb *cb; - do { - struct sk_buff *nskb = skb->next; - - skb->next = nskb->next; - nskb->next = NULL; - kfree_skb(nskb); - } while (skb->next); + kfree_skb_list(skb->next); + skb->next = NULL; cb = DEV_GSO_CB(skb); if (cb->destructor) @@ -1926,16 +2495,14 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) /** * dev_gso_segment - Perform emulated hardware segmentation on skb. * @skb: buffer to segment + * @features: device features as applicable to this skb * * This function segments the given skb and stores the list of segments * in skb->next. */ -static int dev_gso_segment(struct sk_buff *skb) +static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) { - struct net_device *dev = skb->dev; struct sk_buff *segs; - int features = dev->features & ~(illegal_highdma(dev, skb) ? - NETIF_F_SG : 0); segs = skb_gso_segment(skb, features); @@ -1953,103 +2520,117 @@ static int dev_gso_segment(struct sk_buff *skb) return 0; } -/* - * Try to orphan skb early, right before transmission by the device. - * We cannot orphan skb if tx timestamp is requested or the sk-reference - * is needed on driver level for other reasons, e.g. see net/can/raw.c +/* If MPLS offload request, verify we are testing hardware MPLS features + * instead of standard features for the netdev. */ -static inline void skb_orphan_try(struct sk_buff *skb) +#ifdef CONFIG_NET_MPLS_GSO +static netdev_features_t net_mpls_features(struct sk_buff *skb, + netdev_features_t features, + __be16 type) { - struct sock *sk = skb->sk; + if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC)) + features &= skb->dev->mpls_features; - if (sk && !skb_shinfo(skb)->tx_flags) { - /* skb_tx_hash() wont be able to get sk. - * We copy sk_hash into skb->rxhash - */ - if (!skb->rxhash) - skb->rxhash = sk->sk_hash; - skb_orphan(skb); - } + return features; +} +#else +static netdev_features_t net_mpls_features(struct sk_buff *skb, + netdev_features_t features, + __be16 type) +{ + return features; } +#endif -int netif_get_vlan_features(struct sk_buff *skb, struct net_device *dev) +static netdev_features_t harmonize_features(struct sk_buff *skb, + netdev_features_t features) { - __be16 protocol = skb->protocol; + int tmp; + __be16 type; - if (protocol == htons(ETH_P_8021Q)) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - protocol = veh->h_vlan_encapsulated_proto; - } else if (!skb->vlan_tci) - return dev->features; + type = skb_network_protocol(skb, &tmp); + features = net_mpls_features(skb, features, type); - if (protocol != htons(ETH_P_8021Q)) - return dev->features & dev->vlan_features; - else - return 0; + if (skb->ip_summed != CHECKSUM_NONE && + !can_checksum_protocol(features, type)) { + features &= ~NETIF_F_ALL_CSUM; + } else if (illegal_highdma(skb->dev, skb)) { + features &= ~NETIF_F_SG; + } + + return features; } -EXPORT_SYMBOL(netif_get_vlan_features); -/* - * Returns true if either: - * 1. skb has frag_list and the device doesn't support FRAGLIST, or - * 2. skb is fragmented and the device does not support SG, or if - * at least one of fragments is in highmem and device does not - * support DMA from it. - */ -static inline int skb_needs_linearize(struct sk_buff *skb, - struct net_device *dev) +netdev_features_t netif_skb_features(struct sk_buff *skb) { - if (skb_is_nonlinear(skb)) { - int features = dev->features; + __be16 protocol = skb->protocol; + netdev_features_t features = skb->dev->features; - if (vlan_tx_tag_present(skb)) - features &= dev->vlan_features; + if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + features &= ~NETIF_F_GSO_MASK; - return (skb_has_frag_list(skb) && - !(features & NETIF_F_FRAGLIST)) || - (skb_shinfo(skb)->nr_frags && - (!(features & NETIF_F_SG) || - illegal_highdma(dev, skb))); + if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } else if (!vlan_tx_tag_present(skb)) { + return harmonize_features(skb, features); } - return 0; + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); + + if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) + features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | + NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; + + return harmonize_features(skb, features); } +EXPORT_SYMBOL(netif_skb_features); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { const struct net_device_ops *ops = dev->netdev_ops; int rc = NETDEV_TX_OK; + unsigned int skb_len; if (likely(!skb->next)) { + netdev_features_t features; + /* - * If device doesnt need skb->dst, release it right now while + * If device doesn't need skb->dst, release it right now while * its hot in this cpu cache */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); - if (!list_empty(&ptype_all)) - dev_queue_xmit_nit(skb, dev); - - skb_orphan_try(skb); + features = netif_skb_features(skb); if (vlan_tx_tag_present(skb) && - !(dev->features & NETIF_F_HW_VLAN_TX)) { - skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); + !vlan_hw_offload_capable(features, skb->vlan_proto)) { + skb = __vlan_put_tag(skb, skb->vlan_proto, + vlan_tx_tag_get(skb)); if (unlikely(!skb)) goto out; skb->vlan_tci = 0; } - if (netif_needs_gso(dev, skb)) { - if (unlikely(dev_gso_segment(skb))) + /* If encapsulation offload request, verify we are testing + * hardware encapsulation features instead of standard + * features for the netdev + */ + if (skb->encapsulation) + features &= dev->hw_enc_features; + + if (netif_needs_gso(skb, features)) { + if (unlikely(dev_gso_segment(skb, features))) goto out_kfree_skb; if (skb->next) goto gso; } else { - if (skb_needs_linearize(skb, dev) && + if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto out_kfree_skb; @@ -2058,16 +2639,25 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, * checksumming here. */ if (skb->ip_summed == CHECKSUM_PARTIAL) { - skb_set_transport_header(skb, skb->csum_start - - skb_headroom(skb)); - if (!dev_can_checksum(dev, skb) && + if (skb->encapsulation) + skb_set_inner_transport_header(skb, + skb_checksum_start_offset(skb)); + else + skb_set_transport_header(skb, + skb_checksum_start_offset(skb)); + if (!(features & NETIF_F_ALL_CSUM) && skb_checksum_help(skb)) goto out_kfree_skb; } } + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(skb, dev); + + skb_len = skb->len; + trace_net_dev_start_xmit(skb, dev); rc = ops->ndo_start_xmit(skb, dev); - trace_net_dev_xmit(skb, rc); + trace_net_dev_xmit(skb, rc, dev, skb_len); if (rc == NETDEV_TX_OK) txq_trans_update(txq); return rc; @@ -2080,15 +2670,13 @@ gso: skb->next = nskb->next; nskb->next = NULL; - /* - * If device doesnt need nskb->dst, release it right now while - * its hot in this cpu cache - */ - if (dev->priv_flags & IFF_XMIT_DST_RELEASE) - skb_dst_drop(nskb); + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(nskb, dev); + skb_len = nskb->len; + trace_net_dev_start_xmit(nskb, dev); rc = ops->ndo_start_xmit(nskb, dev); - trace_net_dev_xmit(nskb, rc); + trace_net_dev_xmit(nskb, rc, dev, skb_len); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) goto out_kfree_gso_skb; @@ -2097,128 +2685,51 @@ gso: return rc; } txq_trans_update(txq); - if (unlikely(netif_tx_queue_stopped(txq) && skb->next)) + if (unlikely(netif_xmit_stopped(txq) && skb->next)) return NETDEV_TX_BUSY; } while (skb->next); out_kfree_gso_skb: - if (likely(skb->next == NULL)) + if (likely(skb->next == NULL)) { skb->destructor = DEV_GSO_CB(skb)->destructor; + consume_skb(skb); + return rc; + } out_kfree_skb: kfree_skb(skb); out: return rc; } +EXPORT_SYMBOL_GPL(dev_hard_start_xmit); -static u32 hashrnd __read_mostly; - -u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) +static void qdisc_pkt_len_init(struct sk_buff *skb) { - u32 hash; - - if (skb_rx_queue_recorded(skb)) { - hash = skb_get_rx_queue(skb); - while (unlikely(hash >= dev->real_num_tx_queues)) - hash -= dev->real_num_tx_queues; - return hash; - } + const struct skb_shared_info *shinfo = skb_shinfo(skb); - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = (__force u16) skb->protocol ^ skb->rxhash; - hash = jhash_1word(hash, hashrnd); + qdisc_skb_cb(skb)->pkt_len = skb->len; - return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32); -} -EXPORT_SYMBOL(skb_tx_hash); - -static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) -{ - if (unlikely(queue_index >= dev->real_num_tx_queues)) { - if (net_ratelimit()) { - pr_warning("%s selects TX queue %d, but " - "real number of TX queues is %d\n", - dev->name, queue_index, dev->real_num_tx_queues); - } - return 0; - } - return queue_index; -} - -static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) -{ -#ifdef CONFIG_XPS - struct xps_dev_maps *dev_maps; - struct xps_map *map; - int queue_index = -1; - - rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_maps); - if (dev_maps) { - map = rcu_dereference( - dev_maps->cpu_map[raw_smp_processor_id()]); - if (map) { - if (map->len == 1) - queue_index = map->queues[0]; - else { - u32 hash; - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = (__force u16) skb->protocol ^ - skb->rxhash; - hash = jhash_1word(hash, hashrnd); - queue_index = map->queues[ - ((u64)hash * map->len) >> 32]; - } - if (unlikely(queue_index >= dev->real_num_tx_queues)) - queue_index = -1; - } - } - rcu_read_unlock(); - - return queue_index; -#else - return -1; -#endif -} - -static struct netdev_queue *dev_pick_tx(struct net_device *dev, - struct sk_buff *skb) -{ - int queue_index; - const struct net_device_ops *ops = dev->netdev_ops; - - if (dev->real_num_tx_queues == 1) - queue_index = 0; - else if (ops->ndo_select_queue) { - queue_index = ops->ndo_select_queue(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); - } else { - struct sock *sk = skb->sk; - queue_index = sk_tx_queue_get(sk); + /* To get more precise estimation of bytes sent on wire, + * we add to pkt_len the headers size of all segments + */ + if (shinfo->gso_size) { + unsigned int hdr_len; + u16 gso_segs = shinfo->gso_segs; - if (queue_index < 0 || skb->ooo_okay || - queue_index >= dev->real_num_tx_queues) { - int old_index = queue_index; + /* mac layer + network layer */ + hdr_len = skb_transport_header(skb) - skb_mac_header(skb); - queue_index = get_xps_queue(dev, skb); - if (queue_index < 0) - queue_index = skb_tx_hash(dev, skb); + /* + transport layer */ + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len += tcp_hdrlen(skb); + else + hdr_len += sizeof(struct udphdr); - if (queue_index != old_index && sk) { - struct dst_entry *dst = - rcu_dereference_check(sk->sk_dst_cache, 1); + if (shinfo->gso_type & SKB_GSO_DODGY) + gso_segs = DIV_ROUND_UP(skb->len - hdr_len, + shinfo->gso_size); - if (dst && skb_dst(skb) == dst) - sk_tx_queue_set(sk, queue_index); - } - } + qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } - - skb_set_queue_mapping(skb, queue_index); - return netdev_get_tx_queue(dev, queue_index); } static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, @@ -2226,15 +2737,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct netdev_queue *txq) { spinlock_t *root_lock = qdisc_lock(q); - bool contended = qdisc_is_running(q); + bool contended; int rc; + qdisc_pkt_len_init(skb); + qdisc_calculate_pkt_len(skb, q); /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. * This permits __QDISC_STATE_RUNNING owner to get the lock more often * and dequeue packets faster. */ + contended = qdisc_is_running(q); if (unlikely(contended)) spin_lock(&q->busylock); @@ -2251,7 +2765,9 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, */ if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) skb_dst_force(skb); - __qdisc_update_bstats(q, skb->len); + + qdisc_bstats_update(q, skb); + if (sch_direct_xmit(skb, q, dev, txq, root_lock)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -2264,7 +2780,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, rc = NET_XMIT_SUCCESS; } else { skb_dst_force(skb); - rc = qdisc_enqueue_root(skb, q); + rc = q->enqueue(skb, q) & NET_XMIT_MASK; if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -2279,12 +2795,46 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) +static void skb_update_prio(struct sk_buff *skb) +{ + struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); + + if (!skb->priority && skb->sk && map) { + unsigned int prioidx = skb->sk->sk_cgrp_prioidx; + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; + } +} +#else +#define skb_update_prio(skb) +#endif + static DEFINE_PER_CPU(int, xmit_recursion); #define RECURSION_LIMIT 10 /** - * dev_queue_xmit - transmit a buffer + * dev_loopback_xmit - loop back @skb * @skb: buffer to transmit + */ +int dev_loopback_xmit(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)); + skb_dst_force(skb); + netif_rx_ni(skb); + return 0; +} +EXPORT_SYMBOL(dev_loopback_xmit); + +/** + * __dev_queue_xmit - transmit a buffer + * @skb: buffer to transmit + * @accel_priv: private data 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 @@ -2307,19 +2857,23 @@ static DEFINE_PER_CPU(int, xmit_recursion); * the BH enable code must have IRQs enabled so that it will not deadlock. * --BLG */ -int dev_queue_xmit(struct sk_buff *skb) +static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) { struct net_device *dev = skb->dev; struct netdev_queue *txq; struct Qdisc *q; int rc = -ENOMEM; + skb_reset_mac_header(skb); + /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ rcu_read_lock_bh(); - txq = dev_pick_tx(dev, skb); + skb_update_prio(skb); + + txq = netdev_pick_tx(dev, skb, accel_priv); q = rcu_dereference_bh(txq->qdisc); #ifdef CONFIG_NET_CLS_ACT @@ -2353,7 +2907,7 @@ int dev_queue_xmit(struct sk_buff *skb) HARD_TX_LOCK(dev, txq, cpu); - if (!netif_tx_queue_stopped(txq)) { + if (!netif_xmit_stopped(txq)) { __this_cpu_inc(xmit_recursion); rc = dev_hard_start_xmit(skb, dev, txq); __this_cpu_dec(xmit_recursion); @@ -2363,37 +2917,49 @@ int dev_queue_xmit(struct sk_buff *skb) } } HARD_TX_UNLOCK(dev, txq); - if (net_ratelimit()) - printk(KERN_CRIT "Virtual device %s asks to " - "queue packet!\n", dev->name); + net_crit_ratelimited("Virtual device %s asks to queue packet!\n", + dev->name); } else { /* Recursion is detected! It is possible, * unfortunately */ recursion_alert: - if (net_ratelimit()) - printk(KERN_CRIT "Dead loop on virtual device " - "%s, fix it urgently!\n", dev->name); + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); } } rc = -ENETDOWN; rcu_read_unlock_bh(); + atomic_long_inc(&dev->tx_dropped); kfree_skb(skb); return rc; out: rcu_read_unlock_bh(); return rc; } + +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, void *accel_priv) +{ + return __dev_queue_xmit(skb, accel_priv); +} +EXPORT_SYMBOL(dev_queue_xmit_accel); + /*======================================================================= Receiver routines =======================================================================*/ int netdev_max_backlog __read_mostly = 1000; +EXPORT_SYMBOL(netdev_max_backlog); + int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; int weight_p __read_mostly = 64; /* old backlog weight */ @@ -2406,82 +2972,58 @@ static inline void ____napi_schedule(struct softnet_data *sd, __raise_softirq_irqoff(NET_RX_SOFTIRQ); } -/* - * __skb_get_rxhash: calculate a flow hash based on src/dst addresses - * and src/dst port numbers. Returns a non-zero hash number on success - * and 0 on failure. - */ -__u32 __skb_get_rxhash(struct sk_buff *skb) -{ - int nhoff, hash = 0, poff; - struct ipv6hdr *ip6; - struct iphdr *ip; - u8 ip_proto; - u32 addr1, addr2, ihl; - union { - u32 v32; - u16 v16[2]; - } ports; +#ifdef CONFIG_RPS - nhoff = skb_network_offset(skb); +/* One global table that all flow-based protocols share. */ +struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; +EXPORT_SYMBOL(rps_sock_flow_table); - switch (skb->protocol) { - case __constant_htons(ETH_P_IP): - if (!pskb_may_pull(skb, sizeof(*ip) + nhoff)) - goto done; +struct static_key rps_needed __read_mostly; - ip = (struct iphdr *) (skb->data + nhoff); - if (ip->frag_off & htons(IP_MF | IP_OFFSET)) - ip_proto = 0; - else - ip_proto = ip->protocol; - addr1 = (__force u32) ip->saddr; - addr2 = (__force u32) ip->daddr; - ihl = ip->ihl; - break; - case __constant_htons(ETH_P_IPV6): - if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff)) - goto done; +static struct rps_dev_flow * +set_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow *rflow, u16 next_cpu) +{ + if (next_cpu != RPS_NO_CPU) { +#ifdef CONFIG_RFS_ACCEL + struct netdev_rx_queue *rxqueue; + struct rps_dev_flow_table *flow_table; + struct rps_dev_flow *old_rflow; + u32 flow_id; + u16 rxq_index; + int rc; - ip6 = (struct ipv6hdr *) (skb->data + nhoff); - ip_proto = ip6->nexthdr; - addr1 = (__force u32) ip6->saddr.s6_addr32[3]; - addr2 = (__force u32) ip6->daddr.s6_addr32[3]; - ihl = (40 >> 2); - break; - default: - goto done; - } + /* Should we steer this flow to a different hardware queue? */ + if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap || + !(dev->features & NETIF_F_NTUPLE)) + goto out; + rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu); + if (rxq_index == skb_get_rx_queue(skb)) + goto out; - ports.v32 = 0; - poff = proto_ports_offset(ip_proto); - if (poff >= 0) { - nhoff += ihl * 4 + poff; - if (pskb_may_pull(skb, nhoff + 4)) { - ports.v32 = * (__force u32 *) (skb->data + nhoff); - if (ports.v16[1] < ports.v16[0]) - swap(ports.v16[0], ports.v16[1]); - } + rxqueue = dev->_rx + rxq_index; + flow_table = rcu_dereference(rxqueue->rps_flow_table); + if (!flow_table) + goto out; + flow_id = skb_get_hash(skb) & flow_table->mask; + rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, + rxq_index, flow_id); + if (rc < 0) + goto out; + old_rflow = rflow; + rflow = &flow_table->flows[flow_id]; + rflow->filter = rc; + if (old_rflow->filter == rflow->filter) + old_rflow->filter = RPS_NO_FILTER; + out: +#endif + rflow->last_qtail = + per_cpu(softnet_data, next_cpu).input_queue_head; } - /* get a consistent hash (same value on both flow directions) */ - if (addr2 < addr1) - swap(addr1, addr2); - - hash = jhash_3words(addr1, addr2, ports.v32, hashrnd); - if (!hash) - hash = 1; - -done: - return hash; + rflow->cpu = next_cpu; + return rflow; } -EXPORT_SYMBOL(__skb_get_rxhash); - -#ifdef CONFIG_RPS - -/* One global table that all flow-based protocols share. */ -struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; -EXPORT_SYMBOL(rps_sock_flow_table); /* * get_rps_cpu is called from netif_receive_skb and returns the target @@ -2497,6 +3039,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_sock_flow_table *sock_flow_table; int cpu = -1; u16 tcpu; + u32 hash; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); @@ -2513,18 +3056,20 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, map = rcu_dereference(rxqueue->rps_map); if (map) { - if (map->len == 1) { + if (map->len == 1 && + !rcu_access_pointer(rxqueue->rps_flow_table)) { tcpu = map->cpus[0]; if (cpu_online(tcpu)) cpu = tcpu; goto done; } - } else if (!rcu_dereference_raw(rxqueue->rps_flow_table)) { + } else if (!rcu_access_pointer(rxqueue->rps_flow_table)) { goto done; } skb_reset_network_header(skb); - if (!skb_get_rxhash(skb)) + hash = skb_get_hash(skb); + if (!hash) goto done; flow_table = rcu_dereference(rxqueue->rps_flow_table); @@ -2533,11 +3078,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, u16 next_cpu; struct rps_dev_flow *rflow; - rflow = &flow_table->flows[skb->rxhash & flow_table->mask]; + rflow = &flow_table->flows[hash & flow_table->mask]; tcpu = rflow->cpu; - next_cpu = sock_flow_table->ents[skb->rxhash & - sock_flow_table->mask]; + next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask]; /* * If the desired CPU (where last recvmsg was done) is @@ -2554,11 +3098,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || ((int)(per_cpu(softnet_data, tcpu).input_queue_head - rflow->last_qtail)) >= 0)) { - tcpu = rflow->cpu = next_cpu; - if (tcpu != RPS_NO_CPU) - rflow->last_qtail = per_cpu(softnet_data, - tcpu).input_queue_head; + tcpu = next_cpu; + rflow = set_rps_cpu(dev, skb, rflow, next_cpu); } + if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; @@ -2567,7 +3110,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, } if (map) { - tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; + tcpu = map->cpus[((u64) hash * map->len) >> 32]; if (cpu_online(tcpu)) { cpu = tcpu; @@ -2579,6 +3122,46 @@ done: return cpu; } +#ifdef CONFIG_RFS_ACCEL + +/** + * rps_may_expire_flow - check whether an RFS hardware filter may be removed + * @dev: Device on which the filter was set + * @rxq_index: RX queue index + * @flow_id: Flow ID passed to ndo_rx_flow_steer() + * @filter_id: Filter ID returned by ndo_rx_flow_steer() + * + * Drivers that implement ndo_rx_flow_steer() should periodically call + * this function for each installed filter and remove the filters for + * which it returns %true. + */ +bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, + u32 flow_id, u16 filter_id) +{ + struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index; + struct rps_dev_flow_table *flow_table; + struct rps_dev_flow *rflow; + bool expire = true; + int cpu; + + rcu_read_lock(); + flow_table = rcu_dereference(rxqueue->rps_flow_table); + if (flow_table && flow_id <= flow_table->mask) { + rflow = &flow_table->flows[flow_id]; + cpu = ACCESS_ONCE(rflow->cpu); + if (rflow->filter == filter_id && cpu != RPS_NO_CPU && + ((int)(per_cpu(softnet_data, cpu).input_queue_head - + rflow->last_qtail) < + (int)(10 * flow_table->mask))) + expire = false; + } + rcu_read_unlock(); + return expire; +} +EXPORT_SYMBOL(rps_may_expire_flow); + +#endif /* CONFIG_RFS_ACCEL */ + /* Called from hardirq (IPI) context */ static void rps_trigger_softirq(void *data) { @@ -2611,6 +3194,46 @@ static int rps_ipi_queued(struct softnet_data *sd) return 0; } +#ifdef CONFIG_NET_FLOW_LIMIT +int netdev_flow_limit_table_len __read_mostly = (1 << 12); +#endif + +static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) +{ +#ifdef CONFIG_NET_FLOW_LIMIT + struct sd_flow_limit *fl; + struct softnet_data *sd; + unsigned int old_flow, new_flow; + + if (qlen < (netdev_max_backlog >> 1)) + return false; + + sd = &__get_cpu_var(softnet_data); + + rcu_read_lock(); + fl = rcu_dereference(sd->flow_limit); + if (fl) { + new_flow = skb_get_hash(skb) & (fl->num_buckets - 1); + old_flow = fl->history[fl->history_head]; + fl->history[fl->history_head] = new_flow; + + fl->history_head++; + fl->history_head &= FLOW_LIMIT_HISTORY - 1; + + if (likely(fl->buckets[old_flow])) + fl->buckets[old_flow]--; + + if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) { + fl->count++; + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); +#endif + return false; +} + /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). @@ -2620,13 +3243,15 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, { struct softnet_data *sd; unsigned long flags; + unsigned int qlen; sd = &per_cpu(softnet_data, cpu); local_irq_save(flags); rps_lock(sd); - if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) { + qlen = skb_queue_len(&sd->input_pkt_queue); + if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) { if (skb_queue_len(&sd->input_pkt_queue)) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); @@ -2656,35 +3281,15 @@ enqueue: return NET_RX_DROP; } -/** - * 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. - * - * return values: - * NET_RX_SUCCESS (no congestion) - * NET_RX_DROP (packet was dropped) - * - */ - -int netif_rx(struct sk_buff *skb) +static int netif_rx_internal(struct sk_buff *skb) { int ret; - /* if netpoll wants it, pretend we never saw it */ - if (netpoll_rx(skb)) - return NET_RX_DROP; - - if (netdev_tstamp_prequeue) - net_timestamp_check(skb); + net_timestamp_check(netdev_tstamp_prequeue, skb); trace_netif_rx(skb); #ifdef CONFIG_RPS - { + if (static_key_false(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; @@ -2699,24 +3304,47 @@ int netif_rx(struct sk_buff *skb) rcu_read_unlock(); preempt_enable(); - } -#else + } else +#endif { unsigned int qtail; ret = enqueue_to_backlog(skb, get_cpu(), &qtail); put_cpu(); } -#endif return ret; } + +/** + * 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. + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped) + * + */ + +int netif_rx(struct sk_buff *skb) +{ + trace_netif_rx_entry(skb); + + return netif_rx_internal(skb); +} 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(skb); + err = netif_rx_internal(skb); if (local_softirq_pending()) do_softirq(); preempt_enable(); @@ -2742,7 +3370,10 @@ static void net_tx_action(struct softirq_action *h) clist = clist->next; WARN_ON(atomic_read(&skb->users)); - trace_kfree_skb(skb, net_tx_action); + if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) + trace_consume_skb(skb); + else + trace_kfree_skb(skb, net_tx_action); __kfree_skb(skb); } } @@ -2764,7 +3395,7 @@ static void net_tx_action(struct softirq_action *h) root_lock = qdisc_lock(q); if (spin_trylock(root_lock)) { - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); @@ -2774,7 +3405,7 @@ static void net_tx_action(struct softirq_action *h) &q->state)) { __netif_reschedule(q); } else { - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(__QDISC_STATE_SCHED, &q->state); } @@ -2783,14 +3414,6 @@ static void net_tx_action(struct softirq_action *h) } } -static inline int deliver_skb(struct sk_buff *skb, - struct packet_type *pt_prev, - struct net_device *orig_dev) -{ - atomic_inc(&skb->users); - return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); -} - #if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \ (defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)) /* This hook is defined here for ATM LANE */ @@ -2804,8 +3427,8 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions * a compare and 2 stores extra right now if we dont have it on * but have CONFIG_NET_CLS_ACT - * NOTE: This doesnt stop any functionality; if you dont have - * the ingress scheduler, you just cant add policies on ingress. + * NOTE: This doesn't stop any functionality; if you dont have + * the ingress scheduler, you just can't add policies on ingress. * */ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) @@ -2816,9 +3439,8 @@ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) struct Qdisc *q; if (unlikely(MAX_RED_LOOP < ttl++)) { - if (net_ratelimit()) - pr_warning( "Redir loop detected Dropping packet (%d->%d)\n", - skb->skb_iif, dev->ifindex); + net_warn_ratelimited("Redir loop detected Dropping packet (%d->%d)\n", + skb->skb_iif, dev->ifindex); return TC_ACT_SHOT; } @@ -2869,11 +3491,13 @@ out: * @rx_handler: receive handler to register * @rx_handler_data: data pointer that is used by rx handler * - * Register a receive hander for a device. This handler will then be + * Register a receive handler for a device. This handler will then be * called from __netif_receive_skb. A negative errno code is returned * on a failure. * * The caller must hold the rtnl_mutex. + * + * For a general description of rx_handler, see enum rx_handler_result. */ int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, @@ -2884,6 +3508,7 @@ int netdev_rx_handler_register(struct net_device *dev, if (dev->rx_handler) return -EBUSY; + /* Note: rx_handler_data must be set before rx_handler */ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); rcu_assign_pointer(dev->rx_handler, rx_handler); @@ -2895,7 +3520,7 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_register); * netdev_rx_handler_unregister - unregister receive handler * @dev: device to unregister a handler from * - * Unregister a receive hander from a device. + * Unregister a receive handler from a device. * * The caller must hold the rtnl_mutex. */ @@ -2903,113 +3528,71 @@ void netdev_rx_handler_unregister(struct net_device *dev) { ASSERT_RTNL(); - rcu_assign_pointer(dev->rx_handler, NULL); - rcu_assign_pointer(dev->rx_handler_data, NULL); + RCU_INIT_POINTER(dev->rx_handler, NULL); + /* a reader seeing a non NULL rx_handler in a rcu_read_lock() + * section has a guarantee to see a non NULL rx_handler_data + * as well. + */ + synchronize_net(); + RCU_INIT_POINTER(dev->rx_handler_data, NULL); } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); -static inline void skb_bond_set_mac_by_master(struct sk_buff *skb, - struct net_device *master) -{ - if (skb->pkt_type == PACKET_HOST) { - u16 *dest = (u16 *) eth_hdr(skb)->h_dest; - - memcpy(dest, master->dev_addr, ETH_ALEN); - } -} - -/* On bonding slaves other than the currently active slave, suppress - * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and - * ARP on active-backup slaves with arp_validate enabled. +/* + * Limit the use of PFMEMALLOC reserves to those protocols that implement + * the special handling of PFMEMALLOC skbs. */ -int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master) +static bool skb_pfmemalloc_protocol(struct sk_buff *skb) { - struct net_device *dev = skb->dev; - - if (master->priv_flags & IFF_MASTER_ARPMON) - dev->last_rx = jiffies; - - if ((master->priv_flags & IFF_MASTER_ALB) && - (master->priv_flags & IFF_BRIDGE_PORT)) { - /* Do address unmangle. The local destination address - * will be always the one master has. Provides the right - * functionality in a bridge. - */ - skb_bond_set_mac_by_master(skb, master); - } - - if (dev->priv_flags & IFF_SLAVE_INACTIVE) { - if ((dev->priv_flags & IFF_SLAVE_NEEDARP) && - skb->protocol == __cpu_to_be16(ETH_P_ARP)) - return 0; - - if (master->priv_flags & IFF_MASTER_ALB) { - if (skb->pkt_type != PACKET_BROADCAST && - skb->pkt_type != PACKET_MULTICAST) - return 0; - } - if (master->priv_flags & IFF_MASTER_8023AD && - skb->protocol == __cpu_to_be16(ETH_P_SLOW)) - return 0; - - return 1; + switch (skb->protocol) { + case htons(ETH_P_ARP): + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + case htons(ETH_P_8021Q): + case htons(ETH_P_8021AD): + return true; + default: + return false; } - return 0; } -EXPORT_SYMBOL(__skb_bond_should_drop); -static int __netif_receive_skb(struct sk_buff *skb) +static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; struct net_device *orig_dev; - struct net_device *master; - struct net_device *null_or_orig; - struct net_device *orig_or_bond; + struct net_device *null_or_dev; + bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; - if (!netdev_tstamp_prequeue) - net_timestamp_check(skb); + net_timestamp_check(!netdev_tstamp_prequeue, skb); trace_netif_receive_skb(skb); - /* if we've gotten here through NAPI, check netpoll */ - if (netpoll_receive_skb(skb)) - return NET_RX_DROP; - - if (!skb->skb_iif) - skb->skb_iif = skb->dev->ifindex; - - /* - * bonding note: skbs received on inactive slaves should only - * be delivered to pkt handlers that are exact matches. Also - * the deliver_no_wcard flag will be set. If packet handlers - * are sensitive to duplicate packets these skbs will need to - * be dropped at the handler. - */ - null_or_orig = NULL; orig_dev = skb->dev; - master = ACCESS_ONCE(orig_dev->master); - if (skb->deliver_no_wcard) - null_or_orig = orig_dev; - else if (master) { - if (skb_bond_should_drop(skb, master)) { - skb->deliver_no_wcard = 1; - null_or_orig = orig_dev; /* deliver only exact match */ - } else - skb->dev = master; - } - __this_cpu_inc(softnet_data.processed); skb_reset_network_header(skb); - skb_reset_transport_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; + if (!skb_transport_header_was_set(skb)) + skb_reset_transport_header(skb); + skb_reset_mac_len(skb); pt_prev = NULL; rcu_read_lock(); +another_round: + skb->skb_iif = skb->dev->ifindex; + + __this_cpu_inc(softnet_data.processed); + + if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || + skb->protocol == cpu_to_be16(ETH_P_8021AD)) { + skb = vlan_untag(skb); + if (unlikely(!skb)) + goto unlock; + } + #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); @@ -3017,64 +3600,79 @@ static int __netif_receive_skb(struct sk_buff *skb) } #endif + if (pfmemalloc) + goto skip_taps; + list_for_each_entry_rcu(ptype, &ptype_all, list) { - if (ptype->dev == null_or_orig || ptype->dev == skb->dev || - ptype->dev == orig_dev) { + if (!ptype->dev || ptype->dev == skb->dev) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } } +skip_taps: #ifdef CONFIG_NET_CLS_ACT skb = handle_ing(skb, &pt_prev, &ret, orig_dev); if (!skb) - goto out; + goto unlock; ncls: #endif - /* Handle special case of bridge or macvlan */ - rx_handler = rcu_dereference(skb->dev->rx_handler); - if (rx_handler) { + if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) + goto drop; + + if (vlan_tx_tag_present(skb)) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } - skb = rx_handler(skb); - if (!skb) - goto out; + if (vlan_do_receive(&skb)) + goto another_round; + else if (unlikely(!skb)) + goto unlock; } - if (vlan_tx_tag_present(skb)) { + rx_handler = rcu_dereference(skb->dev->rx_handler); + if (rx_handler) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } - if (vlan_hwaccel_do_receive(&skb)) { - ret = __netif_receive_skb(skb); - goto out; - } else if (unlikely(!skb)) - goto out; + switch (rx_handler(&skb)) { + case RX_HANDLER_CONSUMED: + ret = NET_RX_SUCCESS; + goto unlock; + case RX_HANDLER_ANOTHER: + goto another_round; + case RX_HANDLER_EXACT: + deliver_exact = true; + case RX_HANDLER_PASS: + break; + default: + BUG(); + } } - /* - * Make sure frames received on VLAN interfaces stacked on - * bonding interfaces still make their way to any base bonding - * device that may have registered for a specific ptype. The - * handler may have to adjust skb->dev and orig_dev. - */ - orig_or_bond = orig_dev; - if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) && - (vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) { - orig_or_bond = vlan_dev_real_dev(skb->dev); + if (unlikely(vlan_tx_tag_present(skb))) { + if (vlan_tx_tag_get_id(skb)) + skb->pkt_type = PACKET_OTHERHOST; + /* Note: we might in the future use prio bits + * and set skb->priority like in vlan_do_receive() + * For the time being, just ignore Priority Code Point + */ + skb->vlan_tci = 0; } + /* deliver only exact match when indicated */ + null_or_dev = deliver_exact ? skb->dev : NULL; + type = skb->protocol; list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { - if (ptype->type == type && (ptype->dev == null_or_orig || - ptype->dev == skb->dev || ptype->dev == orig_dev || - ptype->dev == orig_or_bond)) { + if (ptype->type == type && + (ptype->dev == null_or_dev || ptype->dev == skb->dev || + ptype->dev == orig_dev)) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -3082,8 +3680,12 @@ ncls: } if (pt_prev) { - ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + goto drop; + else + ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { +drop: atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); /* Jamal, now you will not able to escape explaining @@ -3092,36 +3694,45 @@ ncls: ret = NET_RX_DROP; } -out: +unlock: rcu_read_unlock(); return ret; } -/** - * netif_receive_skb - process receive buffer from network - * @skb: buffer to process - * - * netif_receive_skb() is the main receive data processing function. - * It always succeeds. The buffer may be dropped during processing - * for congestion control or by the protocol layers. - * - * This function may only be called from softirq context and interrupts - * should be enabled. - * - * Return values (usually ignored): - * NET_RX_SUCCESS: no congestion - * NET_RX_DROP: packet was dropped - */ -int netif_receive_skb(struct sk_buff *skb) +static int __netif_receive_skb(struct sk_buff *skb) { - if (netdev_tstamp_prequeue) - net_timestamp_check(skb); + int ret; + + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { + unsigned long pflags = current->flags; + + /* + * PFMEMALLOC skbs are special, they should + * - be delivered to SOCK_MEMALLOC sockets only + * - stay away from userspace + * - have bounded memory usage + * + * Use PF_MEMALLOC as this saves us from propagating the allocation + * context down to all allocation sites. + */ + current->flags |= PF_MEMALLOC; + ret = __netif_receive_skb_core(skb, true); + tsk_restore_flags(current, pflags, PF_MEMALLOC); + } else + ret = __netif_receive_skb_core(skb, false); + + return ret; +} + +static int netif_receive_skb_internal(struct sk_buff *skb) +{ + net_timestamp_check(netdev_tstamp_prequeue, skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; #ifdef CONFIG_RPS - { + if (static_key_false(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu, ret; @@ -3132,16 +3743,34 @@ int netif_receive_skb(struct sk_buff *skb) if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - } else { - rcu_read_unlock(); - ret = __netif_receive_skb(skb); + return ret; } - - return ret; + rcu_read_unlock(); } -#else - return __netif_receive_skb(skb); #endif + return __netif_receive_skb(skb); +} + +/** + * netif_receive_skb - process receive buffer from network + * @skb: buffer to process + * + * netif_receive_skb() is the main receive data processing function. + * It always succeeds. The buffer may be dropped during processing + * for congestion control or by the protocol layers. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + * + * Return values (usually ignored): + * NET_RX_SUCCESS: no congestion + * NET_RX_DROP: packet was dropped + */ +int netif_receive_skb(struct sk_buff *skb) +{ + trace_netif_receive_skb_entry(skb); + + return netif_receive_skb_internal(skb); } EXPORT_SYMBOL(netif_receive_skb); @@ -3175,11 +3804,13 @@ static void flush_backlog(void *arg) static int napi_gro_complete(struct sk_buff *skb) { - struct packet_type *ptype; + struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; + 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; @@ -3187,10 +3818,10 @@ static int napi_gro_complete(struct sk_buff *skb) rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || ptype->dev || !ptype->gro_complete) + if (ptype->type != type || !ptype->callbacks.gro_complete) continue; - err = ptype->gro_complete(skb); + err = ptype->callbacks.gro_complete(skb, 0); break; } rcu_read_unlock(); @@ -3202,53 +3833,137 @@ static int napi_gro_complete(struct sk_buff *skb) } out: - return netif_receive_skb(skb); + return netif_receive_skb_internal(skb); } -inline void napi_gro_flush(struct napi_struct *napi) +/* napi->gro_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) { - struct sk_buff *skb, *next; + struct sk_buff *skb, *prev = NULL; - for (skb = napi->gro_list; skb; skb = next) { - next = skb->next; + /* scan list and build reverse chain */ + for (skb = napi->gro_list; skb != NULL; skb = skb->next) { + skb->prev = prev; + prev = skb; + } + + for (skb = prev; skb; skb = prev) { skb->next = NULL; + + if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) + return; + + prev = skb->prev; napi_gro_complete(skb); + napi->gro_count--; } - napi->gro_count = 0; napi->gro_list = NULL; } EXPORT_SYMBOL(napi_gro_flush); -enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) +{ + struct sk_buff *p; + unsigned int maclen = skb->dev->hard_header_len; + u32 hash = skb_get_hash_raw(skb); + + for (p = napi->gro_list; p; p = p->next) { + 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 |= p->vlan_tci ^ skb->vlan_tci; + 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; + } +} + +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_mac_header(skb) == skb_tail_pointer(skb) && + pinfo->nr_frags && + !PageHighMem(skb_frag_page(frag0))) { + NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); + NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); + } +} + +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; + + pinfo->frags[0].page_offset += 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 enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; - struct packet_type *ptype; + struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; + struct list_head *head = &offload_base; int same_flow; - int mac_len; enum gro_result ret; + int grow; - if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb)) + if (!(skb->dev->features & NETIF_F_GRO)) goto normal; if (skb_is_gso(skb) || skb_has_frag_list(skb)) goto normal; + gro_list_prepare(napi, skb); + NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */ + rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || ptype->dev || !ptype->gro_receive) + if (ptype->type != type || !ptype->callbacks.gro_receive) continue; skb_set_network_header(skb, skb_gro_offset(skb)); - mac_len = skb->network_header - skb->mac_header; - skb->mac_len = mac_len; + skb_reset_mac_len(skb); NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; + NAPI_GRO_CB(skb)->udp_mark = 0; - pp = ptype->gro_receive(&napi->gro_list, skb); + pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); break; } rcu_read_unlock(); @@ -3271,38 +3986,35 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) if (same_flow) goto ok; - if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS) + if (NAPI_GRO_CB(skb)->flush) goto normal; - napi->gro_count++; + if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { + struct sk_buff *nskb = napi->gro_list; + + /* locate the end of the list to select the 'oldest' flow */ + while (nskb->next) { + pp = &nskb->next; + nskb = *pp; + } + *pp = NULL; + nskb->next = NULL; + napi_gro_complete(nskb); + } else { + napi->gro_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); skb->next = napi->gro_list; napi->gro_list = skb; ret = GRO_HELD; pull: - if (skb_headlen(skb) < skb_gro_offset(skb)) { - int grow = skb_gro_offset(skb) - skb_headlen(skb); - - BUG_ON(skb->end - skb->tail < grow); - - memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); - - skb->tail += grow; - skb->data_len -= grow; - - skb_shinfo(skb)->frags[0].page_offset += grow; - skb_shinfo(skb)->frags[0].size -= grow; - - if (unlikely(!skb_shinfo(skb)->frags[0].size)) { - put_page(skb_shinfo(skb)->frags[0].page); - memmove(skb_shinfo(skb)->frags, - skb_shinfo(skb)->frags + 1, - --skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t)); - } - } - + grow = skb_gro_offset(skb) - skb_headlen(skb); + if (grow > 0) + gro_pull_from_frag0(skb, grow); ok: return ret; @@ -3310,40 +4022,54 @@ normal: ret = GRO_NORMAL; goto pull; } -EXPORT_SYMBOL(dev_gro_receive); -static inline gro_result_t -__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +struct packet_offload *gro_find_receive_by_type(__be16 type) { - struct sk_buff *p; - - for (p = napi->gro_list; p; p = p->next) { - unsigned long diffs; + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; - diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; - diffs |= p->vlan_tci ^ skb->vlan_tci; - diffs |= compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); - NAPI_GRO_CB(p)->same_flow = !diffs; - NAPI_GRO_CB(p)->flush = 0; + 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); - return dev_gro_receive(napi, skb); +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); -gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) +static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { switch (ret) { case GRO_NORMAL: - if (netif_receive_skb(skb)) + if (netif_receive_skb_internal(skb)) ret = GRO_DROP; break; case GRO_DROP: - case GRO_MERGED_FREE: kfree_skb(skb); break; + case GRO_MERGED_FREE: + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + kmem_cache_free(skbuff_head_cache, skb); + else + __kfree_skb(skb); + break; + case GRO_HELD: case GRO_MERGED: break; @@ -3351,37 +4077,28 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) return ret; } -EXPORT_SYMBOL(napi_skb_finish); - -void skb_gro_reset_offset(struct sk_buff *skb) -{ - NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; - - if (skb->mac_header == skb->tail && - !PageHighMem(skb_shinfo(skb)->frags[0].page)) { - NAPI_GRO_CB(skb)->frag0 = - page_address(skb_shinfo(skb)->frags[0].page) + - skb_shinfo(skb)->frags[0].page_offset; - NAPI_GRO_CB(skb)->frag0_len = skb_shinfo(skb)->frags[0].size; - } -} -EXPORT_SYMBOL(skb_gro_reset_offset); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { + trace_napi_gro_receive_entry(skb); + skb_gro_reset_offset(skb); - return napi_skb_finish(__napi_gro_receive(napi, skb), skb); + return napi_skb_finish(dev_gro_receive(napi, skb), skb); } EXPORT_SYMBOL(napi_gro_receive); static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) { __skb_pull(skb, skb_headlen(skb)); - skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb)); + /* restore the reserve we had after netdev_alloc_skb_ip_align() */ + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb)); skb->vlan_tci = 0; + skb->dev = napi->dev; + skb->skb_iif = 0; + skb->encapsulation = 0; + skb_shinfo(skb)->gso_type = 0; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); napi->skb = skb; } @@ -3392,24 +4109,22 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) if (!skb) { skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD); - if (skb) - napi->skb = skb; + napi->skb = skb; } return skb; } EXPORT_SYMBOL(napi_get_frags); -gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, - gro_result_t ret) +static gro_result_t napi_frags_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) { switch (ret) { case GRO_NORMAL: case GRO_HELD: + __skb_push(skb, ETH_HLEN); skb->protocol = eth_type_trans(skb, skb->dev); - - if (ret == GRO_HELD) - skb_gro_pull(skb, -ETH_HLEN); - else if (netif_receive_skb(skb)) + if (ret == GRO_NORMAL && netif_receive_skb_internal(skb)) ret = GRO_DROP; break; @@ -3424,44 +4139,45 @@ gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, return ret; } -EXPORT_SYMBOL(napi_frags_finish); -struct sk_buff *napi_frags_skb(struct napi_struct *napi) +/* 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; - struct ethhdr *eth; - unsigned int hlen; - unsigned int off; + const struct ethhdr *eth; + unsigned int hlen = sizeof(*eth); napi->skb = NULL; skb_reset_mac_header(skb); skb_gro_reset_offset(skb); - off = skb_gro_offset(skb); - hlen = off + sizeof(*eth); - eth = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) { - eth = skb_gro_header_slow(skb, hlen, off); + eth = skb_gro_header_fast(skb, 0); + if (unlikely(skb_gro_header_hard(skb, hlen))) { + eth = skb_gro_header_slow(skb, hlen, 0); if (unlikely(!eth)) { napi_reuse_skb(napi, skb); - skb = NULL; - goto out; + return NULL; } + } else { + gro_pull_from_frag0(skb, hlen); + NAPI_GRO_CB(skb)->frag0 += hlen; + NAPI_GRO_CB(skb)->frag0_len -= hlen; } - - skb_gro_pull(skb, sizeof(*eth)); + __skb_pull(skb, hlen); /* * This works because the only protocols we care about don't require - * special handling. We'll fix it up properly at the end. + * special handling. + * We'll fix it up properly in napi_frags_finish() */ skb->protocol = eth->h_proto; -out: return skb; } -EXPORT_SYMBOL(napi_frags_skb); gro_result_t napi_gro_frags(struct napi_struct *napi) { @@ -3470,12 +4186,14 @@ gro_result_t napi_gro_frags(struct napi_struct *napi) if (!skb) return GRO_DROP; - return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb)); + trace_napi_gro_frags_entry(skb); + + return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); } EXPORT_SYMBOL(napi_gro_frags); /* - * net_rps_action sends any pending IPI's for rps. + * net_rps_action_and_irq_enable sends any pending IPI's for rps. * Note: called with local irq disabled, but exits with local irq enabled. */ static void net_rps_action_and_irq_enable(struct softnet_data *sd) @@ -3493,8 +4211,8 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) struct softnet_data *next = remsd->rps_ipi_next; if (cpu_online(remsd->cpu)) - __smp_call_function_single(remsd->cpu, - &remsd->csd, 0); + smp_call_function_single_async(remsd->cpu, + &remsd->csd); remsd = next; } } else @@ -3518,9 +4236,8 @@ static int process_backlog(struct napi_struct *napi, int quota) #endif napi->weight = weight_p; local_irq_disable(); - while (work < quota) { + while (1) { struct sk_buff *skb; - unsigned int qlen; while ((skb = __skb_dequeue(&sd->process_queue))) { local_irq_enable(); @@ -3534,24 +4251,24 @@ static int process_backlog(struct napi_struct *napi, int quota) } rps_lock(sd); - qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen) - skb_queue_splice_tail_init(&sd->input_pkt_queue, - &sd->process_queue); - - if (qlen < quota - work) { + if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). * only current cpu owns and manipulates this napi, - * and NAPI_STATE_SCHED is the only possible flag set on backlog. - * we can use a plain write instead of clear_bit(), + * and NAPI_STATE_SCHED is the only possible flag set + * on backlog. + * We can use a plain write instead of clear_bit(), * and we dont need an smp_mb() memory barrier. */ list_del(&napi->poll_list); napi->state = 0; + rps_unlock(sd); - quota = work + qlen; + break; } + + skb_queue_splice_tail_init(&sd->input_pkt_queue, + &sd->process_queue); rps_unlock(sd); } local_irq_enable(); @@ -3581,7 +4298,7 @@ void __napi_complete(struct napi_struct *n) BUG_ON(n->gro_list); list_del(&n->poll_list); - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); } EXPORT_SYMBOL(__napi_complete); @@ -3597,13 +4314,65 @@ void napi_complete(struct napi_struct *n) if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state))) return; - napi_gro_flush(n); + napi_gro_flush(n, false); local_irq_save(flags); __napi_complete(n); local_irq_restore(flags); } EXPORT_SYMBOL(napi_complete); +/* must be called under rcu_read_lock(), as we dont take a reference */ +struct napi_struct *napi_by_id(unsigned int napi_id) +{ + unsigned int hash = napi_id % HASH_SIZE(napi_hash); + struct napi_struct *napi; + + hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) + if (napi->napi_id == napi_id) + return napi; + + return NULL; +} +EXPORT_SYMBOL_GPL(napi_by_id); + +void napi_hash_add(struct napi_struct *napi) +{ + if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) { + + spin_lock(&napi_hash_lock); + + /* 0 is not a valid id, we also skip an id that is taken + * we expect both events to be extremely rare + */ + napi->napi_id = 0; + while (!napi->napi_id) { + napi->napi_id = ++napi_gen_id; + if (napi_by_id(napi->napi_id)) + napi->napi_id = 0; + } + + hlist_add_head_rcu(&napi->napi_hash_node, + &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); + + spin_unlock(&napi_hash_lock); + } +} +EXPORT_SYMBOL_GPL(napi_hash_add); + +/* Warning : caller is responsible to make sure rcu grace period + * is respected before freeing memory containing @napi + */ +void napi_hash_del(struct napi_struct *napi) +{ + spin_lock(&napi_hash_lock); + + if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) + hlist_del_rcu(&napi->napi_hash_node); + + spin_unlock(&napi_hash_lock); +} +EXPORT_SYMBOL_GPL(napi_hash_del); + void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { @@ -3612,6 +4381,9 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, napi->gro_list = NULL; napi->skb = NULL; napi->poll = poll; + if (weight > NAPI_POLL_WEIGHT) + pr_err_once("netif_napi_add() called with weight %d on device %s\n", + weight, dev->name); napi->weight = weight; list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; @@ -3625,17 +4397,10 @@ EXPORT_SYMBOL(netif_napi_add); void netif_napi_del(struct napi_struct *napi) { - struct sk_buff *skb, *next; - list_del_init(&napi->dev_list); napi_free_frags(napi); - for (skb = napi->gro_list; skb; skb = next) { - next = skb->next; - skb->next = NULL; - kfree_skb(skb); - } - + kfree_skb_list(napi->gro_list); napi->gro_list = NULL; napi->gro_count = 0; } @@ -3658,7 +4423,7 @@ static void net_rx_action(struct softirq_action *h) * Allow this to run for 2 jiffies since which will allow * an average latency of 1.5/HZ. */ - if (unlikely(budget <= 0 || time_after(jiffies, time_limit))) + if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit))) goto softnet_break; local_irq_enable(); @@ -3678,7 +4443,7 @@ static void net_rx_action(struct softirq_action *h) * with netpoll's poll_napi(). Only the entity which * obtains the lock and sees NAPI_STATE_SCHED set will * actually make the ->poll() call. Therefore we avoid - * accidently calling ->poll() when NAPI is not scheduled. + * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; if (test_bit(NAPI_STATE_SCHED, &n->state)) { @@ -3702,8 +4467,17 @@ static void net_rx_action(struct softirq_action *h) local_irq_enable(); napi_complete(n); local_irq_disable(); - } else + } else { + if (n->gro_list) { + /* flush too old packets + * If HZ < 1000, flush all packets. + */ + local_irq_enable(); + napi_gro_flush(n, HZ >= 1000); + local_irq_disable(); + } list_move_tail(&n->poll_list, &sd->poll_list); + } } netpoll_poll_unlock(have); @@ -3727,488 +4501,721 @@ softnet_break: goto out; } -static gifconf_func_t *gifconf_list[NPROTO]; +struct netdev_adjacent { + struct net_device *dev; + + /* upper master flag, there can only be one master device per list */ + bool master; + + /* counter for the number of times this device was added to us */ + u16 ref_nr; + + /* private field for the users */ + void *private; + + struct list_head list; + struct rcu_head rcu; +}; + +static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *adj_list) +{ + struct netdev_adjacent *adj; + + list_for_each_entry(adj, adj_list, list) { + if (adj->dev == adj_dev) + return adj; + } + return NULL; +} /** - * register_gifconf - register a SIOCGIF handler - * @family: Address family - * @gifconf: Function handler + * netdev_has_upper_dev - Check if device is linked to an upper device + * @dev: device + * @upper_dev: upper device to check * - * Register protocol dependent address dumping routines. The handler - * that is passed must not be freed or reused until it has been replaced - * by another handler. + * Find out if a device is linked to specified upper device and return true + * in case it is. Note that this checks only immediate upper device, + * not through a complete stack of devices. The caller must hold the RTNL lock. */ -int register_gifconf(unsigned int family, gifconf_func_t *gifconf) +bool netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev) { - if (family >= NPROTO) - return -EINVAL; - gifconf_list[family] = gifconf; - return 0; -} -EXPORT_SYMBOL(register_gifconf); + ASSERT_RTNL(); + return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper); +} +EXPORT_SYMBOL(netdev_has_upper_dev); -/* - * Map an interface index to its name (SIOCGIFNAME) +/** + * netdev_has_any_upper_dev - Check if device is linked to some device + * @dev: device + * + * Find out if a device is linked to an upper device and return true in case + * it is. The caller must hold the RTNL lock. */ +static bool netdev_has_any_upper_dev(struct net_device *dev) +{ + ASSERT_RTNL(); -/* - * We need this ioctl for efficient implementation of the - * if_indextoname() function required by the IPv6 API. Without - * it, we would have to search all the interfaces to find a - * match. --pb - */ + return !list_empty(&dev->all_adj_list.upper); +} -static int dev_ifname(struct net *net, struct ifreq __user *arg) +/** + * netdev_master_upper_dev_get - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RTNL lock. + */ +struct net_device *netdev_master_upper_dev_get(struct net_device *dev) { - struct net_device *dev; - struct ifreq ifr; + struct netdev_adjacent *upper; - /* - * Fetch the caller's info block. - */ + ASSERT_RTNL(); - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; + if (list_empty(&dev->adj_list.upper)) + return NULL; - rcu_read_lock(); - dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); - if (!dev) { - rcu_read_unlock(); - return -ENODEV; - } + upper = list_first_entry(&dev->adj_list.upper, + struct netdev_adjacent, list); + if (likely(upper->master)) + return upper->dev; + return NULL; +} +EXPORT_SYMBOL(netdev_master_upper_dev_get); - strcpy(ifr.ifr_name, dev->name); - rcu_read_unlock(); +void *netdev_adjacent_get_private(struct list_head *adj_list) +{ + struct netdev_adjacent *adj; - if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) - return -EFAULT; - return 0; + adj = list_entry(adj_list, struct netdev_adjacent, list); + + return adj->private; } +EXPORT_SYMBOL(netdev_adjacent_get_private); -/* - * Perform a SIOCGIFCONF call. This structure will change - * size eventually, and there is nothing I can do about it. - * Thus we will need a 'compatibility mode'. +/** + * netdev_upper_get_next_dev_rcu - Get the next dev from upper list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next device from the dev's upper list, starting from iter + * position. The caller must hold RCU read lock. */ - -static int dev_ifconf(struct net *net, char __user *arg) +struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter) { - struct ifconf ifc; - struct net_device *dev; - char __user *pos; - int len; - int total; - int i; - - /* - * Fetch the caller's info block. - */ + struct netdev_adjacent *upper; - if (copy_from_user(&ifc, arg, sizeof(struct ifconf))) - return -EFAULT; + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); - pos = ifc.ifc_buf; - len = ifc.ifc_len; + upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); - /* - * Loop over the interfaces, and write an info block for each. - */ - - total = 0; - for_each_netdev(net, dev) { - for (i = 0; i < NPROTO; i++) { - if (gifconf_list[i]) { - int done; - if (!pos) - done = gifconf_list[i](dev, NULL, 0); - else - done = gifconf_list[i](dev, pos + total, - len - total); - if (done < 0) - return -EFAULT; - total += done; - } - } - } + if (&upper->list == &dev->adj_list.upper) + return NULL; - /* - * All done. Write the updated control block back to the caller. - */ - ifc.ifc_len = total; + *iter = &upper->list; - /* - * Both BSD and Solaris return 0 here, so we do too. - */ - return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0; + return upper->dev; } +EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); -#ifdef CONFIG_PROC_FS -/* - * This is invoked by the /proc filesystem handler to display a device - * in detail. +/** + * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next device from the dev's upper list, starting from iter + * position. The caller must hold RCU read lock. */ -void *dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) +struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter) { - struct net *net = seq_file_net(seq); - loff_t off; - struct net_device *dev; + struct netdev_adjacent *upper; - rcu_read_lock(); - if (!*pos) - return SEQ_START_TOKEN; + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); - off = 1; - for_each_netdev_rcu(net, dev) - if (off++ == *pos) - return dev; + upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); - return NULL; -} + if (&upper->list == &dev->all_adj_list.upper) + return NULL; -void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct net_device *dev = (v == SEQ_START_TOKEN) ? - first_net_device(seq_file_net(seq)) : - next_net_device((struct net_device *)v); + *iter = &upper->list; - ++*pos; - return rcu_dereference(dev); + return upper->dev; } +EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu); -void dev_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) +/** + * netdev_lower_get_next_private - Get the next ->private from the + * lower neighbour list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent->private from the dev's lower neighbour + * list, starting from iter position. The caller must hold either hold the + * RTNL lock or its own locking that guarantees that the neighbour lower + * list will remain unchainged. + */ +void *netdev_lower_get_next_private(struct net_device *dev, + struct list_head **iter) { - rcu_read_unlock(); + struct netdev_adjacent *lower; + + lower = list_entry(*iter, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = lower->list.next; + + return lower->private; } +EXPORT_SYMBOL(netdev_lower_get_next_private); -static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) +/** + * netdev_lower_get_next_private_rcu - Get the next ->private from the + * lower neighbour list, RCU + * variant + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent->private from the dev's lower neighbour + * list, starting from iter position. The caller must hold RCU read lock. + */ +void *netdev_lower_get_next_private_rcu(struct net_device *dev, + struct list_head **iter) { - struct rtnl_link_stats64 temp; - const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); + struct netdev_adjacent *lower; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; - seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " - "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", - dev->name, stats->rx_bytes, stats->rx_packets, - stats->rx_errors, - stats->rx_dropped + stats->rx_missed_errors, - stats->rx_fifo_errors, - stats->rx_length_errors + stats->rx_over_errors + - stats->rx_crc_errors + stats->rx_frame_errors, - stats->rx_compressed, stats->multicast, - stats->tx_bytes, stats->tx_packets, - stats->tx_errors, stats->tx_dropped, - stats->tx_fifo_errors, stats->collisions, - stats->tx_carrier_errors + - stats->tx_aborted_errors + - stats->tx_window_errors + - stats->tx_heartbeat_errors, - stats->tx_compressed); + *iter = &lower->list; + + return lower->private; } +EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); -/* - * Called from the PROCfs module. This now uses the new arbitrary sized - * /proc/net interface to create /proc/net/dev +/** + * netdev_lower_get_next - Get the next device from the lower neighbour + * list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent from the dev's lower neighbour + * list, starting from iter position. The caller must hold RTNL lock or + * its own locking that guarantees that the neighbour lower + * list will remain unchainged. */ -static int dev_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Inter-| Receive " - " | Transmit\n" - " face |bytes packets errs drop fifo frame " - "compressed multicast|bytes packets errs " - "drop fifo colls carrier compressed\n"); - else - dev_seq_printf_stats(seq, v); - return 0; +void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) +{ + struct netdev_adjacent *lower; + + lower = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; + + return lower->dev; } +EXPORT_SYMBOL(netdev_lower_get_next); -static struct softnet_data *softnet_get_online(loff_t *pos) +/** + * netdev_lower_get_first_private_rcu - Get the first ->private from the + * lower neighbour list, RCU + * variant + * @dev: device + * + * Gets the first netdev_adjacent->private from the dev's lower neighbour + * list. The caller must hold RCU read lock. + */ +void *netdev_lower_get_first_private_rcu(struct net_device *dev) { - struct softnet_data *sd = NULL; + struct netdev_adjacent *lower; - while (*pos < nr_cpu_ids) - if (cpu_online(*pos)) { - sd = &per_cpu(softnet_data, *pos); - break; - } else - ++*pos; - return sd; + lower = list_first_or_null_rcu(&dev->adj_list.lower, + struct netdev_adjacent, list); + if (lower) + return lower->private; + return NULL; } +EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); -static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) +/** + * netdev_master_upper_dev_get_rcu - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RCU read lock. + */ +struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { - return softnet_get_online(pos); + struct netdev_adjacent *upper; + + upper = list_first_or_null_rcu(&dev->adj_list.upper, + struct netdev_adjacent, list); + if (upper && likely(upper->master)) + return upper->dev; + return NULL; } +EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); -static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static int netdev_adjacent_sysfs_add(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) { - ++*pos; - return softnet_get_online(pos); + char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? + "upper_%s" : "lower_%s", adj_dev->name); + return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), + linkname); } - -static void softnet_seq_stop(struct seq_file *seq, void *v) +static void netdev_adjacent_sysfs_del(struct net_device *dev, + char *name, + struct list_head *dev_list) { + char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? + "upper_%s" : "lower_%s", name); + sysfs_remove_link(&(dev->dev.kobj), linkname); } -static int softnet_seq_show(struct seq_file *seq, void *v) +#define netdev_adjacent_is_neigh_list(dev, dev_list) \ + (dev_list == &dev->adj_list.upper || \ + dev_list == &dev->adj_list.lower) + +static int __netdev_adjacent_dev_insert(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list, + void *private, bool master) { - struct softnet_data *sd = v; + struct netdev_adjacent *adj; + int ret; + + adj = __netdev_find_adj(dev, adj_dev, dev_list); + + if (adj) { + adj->ref_nr++; + return 0; + } + + adj = kmalloc(sizeof(*adj), GFP_KERNEL); + if (!adj) + return -ENOMEM; + + adj->dev = adj_dev; + adj->master = master; + adj->ref_nr = 1; + adj->private = private; + dev_hold(adj_dev); + + pr_debug("dev_hold for %s, because of link added from %s to %s\n", + adj_dev->name, dev->name, adj_dev->name); + + if (netdev_adjacent_is_neigh_list(dev, dev_list)) { + ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); + if (ret) + goto free_adj; + } + + /* Ensure that master link is always the first item in list. */ + if (master) { + ret = sysfs_create_link(&(dev->dev.kobj), + &(adj_dev->dev.kobj), "master"); + if (ret) + goto remove_symlinks; + + list_add_rcu(&adj->list, dev_list); + } else { + list_add_tail_rcu(&adj->list, dev_list); + } - seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", - sd->processed, sd->dropped, sd->time_squeeze, 0, - 0, 0, 0, 0, /* was fastroute */ - sd->cpu_collision, sd->received_rps); return 0; -} -static const struct seq_operations dev_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = dev_seq_show, -}; +remove_symlinks: + if (netdev_adjacent_is_neigh_list(dev, dev_list)) + netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); +free_adj: + kfree(adj); + dev_put(adj_dev); -static int dev_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &dev_seq_ops, - sizeof(struct seq_net_private)); + return ret; } -static const struct file_operations dev_seq_fops = { - .owner = THIS_MODULE, - .open = dev_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; +static void __netdev_adjacent_dev_remove(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) +{ + struct netdev_adjacent *adj; -static const struct seq_operations softnet_seq_ops = { - .start = softnet_seq_start, - .next = softnet_seq_next, - .stop = softnet_seq_stop, - .show = softnet_seq_show, -}; + adj = __netdev_find_adj(dev, adj_dev, dev_list); -static int softnet_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &softnet_seq_ops); -} + if (!adj) { + pr_err("tried to remove device %s from %s\n", + dev->name, adj_dev->name); + BUG(); + } -static const struct file_operations softnet_seq_fops = { - .owner = THIS_MODULE, - .open = softnet_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; + if (adj->ref_nr > 1) { + pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name, + adj->ref_nr-1); + adj->ref_nr--; + return; + } + + if (adj->master) + sysfs_remove_link(&(dev->dev.kobj), "master"); -static void *ptype_get_idx(loff_t pos) + if (netdev_adjacent_is_neigh_list(dev, dev_list)) + netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); + + list_del_rcu(&adj->list); + pr_debug("dev_put for %s, because link removed from %s to %s\n", + adj_dev->name, dev->name, adj_dev->name); + dev_put(adj_dev); + kfree_rcu(adj, rcu); +} + +static int __netdev_adjacent_dev_link_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list, + void *private, bool master) { - struct packet_type *pt = NULL; - loff_t i = 0; - int t; + int ret; - list_for_each_entry_rcu(pt, &ptype_all, list) { - if (i == pos) - return pt; - ++i; - } + ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, + master); + if (ret) + return ret; - for (t = 0; t < PTYPE_HASH_SIZE; t++) { - list_for_each_entry_rcu(pt, &ptype_base[t], list) { - if (i == pos) - return pt; - ++i; - } + ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, + false); + if (ret) { + __netdev_adjacent_dev_remove(dev, upper_dev, up_list); + return ret; } - return NULL; + + return 0; } -static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) +static int __netdev_adjacent_dev_link(struct net_device *dev, + struct net_device *upper_dev) { - rcu_read_lock(); - return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; + return __netdev_adjacent_dev_link_lists(dev, upper_dev, + &dev->all_adj_list.upper, + &upper_dev->all_adj_list.lower, + NULL, false); } -static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list) { - struct packet_type *pt; - struct list_head *nxt; - int hash; + __netdev_adjacent_dev_remove(dev, upper_dev, up_list); + __netdev_adjacent_dev_remove(upper_dev, dev, down_list); +} - ++*pos; - if (v == SEQ_START_TOKEN) - return ptype_get_idx(0); +static void __netdev_adjacent_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) +{ + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + &dev->all_adj_list.upper, + &upper_dev->all_adj_list.lower); +} - pt = v; - nxt = pt->list.next; - if (pt->type == htons(ETH_P_ALL)) { - if (nxt != &ptype_all) - goto found; - hash = 0; - nxt = ptype_base[0].next; - } else - hash = ntohs(pt->type) & PTYPE_HASH_MASK; +static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, + struct net_device *upper_dev, + void *private, bool master) +{ + int ret = __netdev_adjacent_dev_link(dev, upper_dev); - while (nxt == &ptype_base[hash]) { - if (++hash >= PTYPE_HASH_SIZE) - return NULL; - nxt = ptype_base[hash].next; + if (ret) + return ret; + + ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, + &dev->adj_list.upper, + &upper_dev->adj_list.lower, + private, master); + if (ret) { + __netdev_adjacent_dev_unlink(dev, upper_dev); + return ret; } -found: - return list_entry(nxt, struct packet_type, list); + + return 0; } -static void ptype_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) +static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, + struct net_device *upper_dev) { - rcu_read_unlock(); + __netdev_adjacent_dev_unlink(dev, upper_dev); + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + &dev->adj_list.upper, + &upper_dev->adj_list.lower); } -static int ptype_seq_show(struct seq_file *seq, void *v) +static int __netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev, bool master, + void *private) { - struct packet_type *pt = v; + struct netdev_adjacent *i, *j, *to_i, *to_j; + int ret = 0; - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Type Device Function\n"); - else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { - if (pt->type == htons(ETH_P_ALL)) - seq_puts(seq, "ALL "); - else - seq_printf(seq, "%04x", ntohs(pt->type)); + ASSERT_RTNL(); - seq_printf(seq, " %-8s %pF\n", - pt->dev ? pt->dev->name : "", pt->func); + if (dev == upper_dev) + return -EBUSY; + + /* To prevent loops, check if dev is not upper device to upper_dev. */ + if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper)) + return -EBUSY; + + if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper)) + return -EEXIST; + + if (master && netdev_master_upper_dev_get(dev)) + return -EBUSY; + + ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private, + master); + if (ret) + return ret; + + /* Now that we linked these devs, make all the upper_dev's + * all_adj_list.upper visible to every dev's all_adj_list.lower an + * versa, and don't forget the devices itself. All of these + * links are non-neighbours. + */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { + pr_debug("Interlinking %s with %s, non-neighbour\n", + i->dev->name, j->dev->name); + ret = __netdev_adjacent_dev_link(i->dev, j->dev); + if (ret) + goto rollback_mesh; + } + } + + /* add dev to every upper_dev's upper device */ + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { + pr_debug("linking %s's upper device %s with %s\n", + upper_dev->name, i->dev->name, dev->name); + ret = __netdev_adjacent_dev_link(dev, i->dev); + if (ret) + goto rollback_upper_mesh; } + /* add upper_dev to every dev's lower device */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + pr_debug("linking %s's lower device %s with %s\n", dev->name, + i->dev->name, upper_dev->name); + ret = __netdev_adjacent_dev_link(i->dev, upper_dev); + if (ret) + goto rollback_lower_mesh; + } + + call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); return 0; -} -static const struct seq_operations ptype_seq_ops = { - .start = ptype_seq_start, - .next = ptype_seq_next, - .stop = ptype_seq_stop, - .show = ptype_seq_show, -}; +rollback_lower_mesh: + to_i = i; + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + if (i == to_i) + break; + __netdev_adjacent_dev_unlink(i->dev, upper_dev); + } + + i = NULL; -static int ptype_seq_open(struct inode *inode, struct file *file) +rollback_upper_mesh: + to_i = i; + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { + if (i == to_i) + break; + __netdev_adjacent_dev_unlink(dev, i->dev); + } + + i = j = NULL; + +rollback_mesh: + to_i = i; + to_j = j; + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { + if (i == to_i && j == to_j) + break; + __netdev_adjacent_dev_unlink(i->dev, j->dev); + } + if (i == to_i) + break; + } + + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); + + return ret; +} + +/** + * netdev_upper_dev_link - Add a link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. The caller must hold + * the RTNL lock. On a failure a negative errno code is returned. + * On success the reference counts are adjusted and the function + * returns zero. + */ +int netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) { - return seq_open_net(inode, file, &ptype_seq_ops, - sizeof(struct seq_net_private)); + return __netdev_upper_dev_link(dev, upper_dev, false, NULL); } +EXPORT_SYMBOL(netdev_upper_dev_link); -static const struct file_operations ptype_seq_fops = { - .owner = THIS_MODULE, - .open = ptype_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; +/** + * netdev_master_upper_dev_link - Add a master link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. In this case, only + * one master upper device can be linked, although other non-master devices + * might be linked as well. The caller must hold the RTNL lock. + * On a failure a negative errno code is returned. On success the reference + * counts are adjusted and the function returns zero. + */ +int netdev_master_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) +{ + return __netdev_upper_dev_link(dev, upper_dev, true, NULL); +} +EXPORT_SYMBOL(netdev_master_upper_dev_link); +int netdev_master_upper_dev_link_private(struct net_device *dev, + struct net_device *upper_dev, + void *private) +{ + return __netdev_upper_dev_link(dev, upper_dev, true, private); +} +EXPORT_SYMBOL(netdev_master_upper_dev_link_private); -static int __net_init dev_proc_net_init(struct net *net) +/** + * 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) { - int rc = -ENOMEM; + struct netdev_adjacent *i, *j; + ASSERT_RTNL(); - if (!proc_net_fops_create(net, "dev", S_IRUGO, &dev_seq_fops)) - goto out; - if (!proc_net_fops_create(net, "softnet_stat", S_IRUGO, &softnet_seq_fops)) - goto out_dev; - if (!proc_net_fops_create(net, "ptype", S_IRUGO, &ptype_seq_fops)) - goto out_softnet; + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); - if (wext_proc_init(net)) - goto out_ptype; - rc = 0; -out: - return rc; -out_ptype: - proc_net_remove(net, "ptype"); -out_softnet: - proc_net_remove(net, "softnet_stat"); -out_dev: - proc_net_remove(net, "dev"); - goto out; + /* Here is the tricky part. We must remove all dev's lower + * devices from all upper_dev's upper devices and vice + * versa, to maintain the graph relationship. + */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) + __netdev_adjacent_dev_unlink(i->dev, j->dev); + + /* remove also the devices itself from lower/upper device + * list + */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) + __netdev_adjacent_dev_unlink(i->dev, upper_dev); + + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) + __netdev_adjacent_dev_unlink(dev, i->dev); + + call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); } +EXPORT_SYMBOL(netdev_upper_dev_unlink); -static void __net_exit dev_proc_net_exit(struct net *net) +void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { - wext_proc_exit(net); + struct netdev_adjacent *iter; - proc_net_remove(net, "ptype"); - proc_net_remove(net, "softnet_stat"); - proc_net_remove(net, "dev"); -} + list_for_each_entry(iter, &dev->adj_list.upper, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.lower); + } -static struct pernet_operations __net_initdata dev_proc_ops = { - .init = dev_proc_net_init, - .exit = dev_proc_net_exit, -}; + list_for_each_entry(iter, &dev->adj_list.lower, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.upper); + } +} -static int __init dev_proc_init(void) +void *netdev_lower_dev_get_private(struct net_device *dev, + struct net_device *lower_dev) { - return register_pernet_subsys(&dev_proc_ops); + struct netdev_adjacent *lower; + + if (!lower_dev) + return NULL; + lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower); + if (!lower) + return NULL; + + return lower->private; } -#else -#define dev_proc_init() 0 -#endif /* CONFIG_PROC_FS */ +EXPORT_SYMBOL(netdev_lower_dev_get_private); -/** - * netdev_set_master - set up master/slave pair - * @slave: slave device - * @master: new master device - * - * Changes the master device of the slave. Pass %NULL to break the - * bonding. The caller must hold the RTNL semaphore. On a failure - * a negative errno code is returned. On success the reference counts - * are adjusted, %RTM_NEWLINK is sent to the routing socket and the - * function returns zero. - */ -int netdev_set_master(struct net_device *slave, struct net_device *master) +int dev_get_nest_level(struct net_device *dev, + bool (*type_check)(struct net_device *dev)) { - struct net_device *old = slave->master; + struct net_device *lower = NULL; + struct list_head *iter; + int max_nest = -1; + int nest; ASSERT_RTNL(); - if (master) { - if (old) - return -EBUSY; - dev_hold(master); + netdev_for_each_lower_dev(dev, lower, iter) { + nest = dev_get_nest_level(lower, type_check); + if (max_nest < nest) + max_nest = nest; } - slave->master = master; + if (type_check(dev)) + max_nest++; - if (old) { - synchronize_net(); - dev_put(old); - } - if (master) - slave->flags |= IFF_SLAVE; - else - slave->flags &= ~IFF_SLAVE; - - rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); - return 0; + return max_nest; } -EXPORT_SYMBOL(netdev_set_master); +EXPORT_SYMBOL(dev_get_nest_level); static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; - if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags) + if (ops->ndo_change_rx_flags) ops->ndo_change_rx_flags(dev, flags); } -static int __dev_set_promiscuity(struct net_device *dev, int inc) +static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) { - unsigned short old_flags = dev->flags; - uid_t uid; - gid_t gid; + unsigned int old_flags = dev->flags; + kuid_t uid; + kgid_t gid; ASSERT_RTNL(); @@ -4223,16 +5230,15 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc) dev->flags &= ~IFF_PROMISC; else { dev->promiscuity -= inc; - printk(KERN_WARNING "%s: promiscuity touches roof, " - "set promiscuity failed, promiscuity feature " - "of device might be broken.\n", dev->name); + pr_warn("%s: promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n", + dev->name); return -EOVERFLOW; } } if (dev->flags != old_flags) { - printk(KERN_INFO "device %s %s promiscuous mode\n", - dev->name, (dev->flags & IFF_PROMISC) ? "entered" : - "left"); + pr_info("device %s %s promiscuous mode\n", + dev->name, + dev->flags & IFF_PROMISC ? "entered" : "left"); if (audit_enabled) { current_uid_gid(&uid, &gid); audit_log(current->audit_context, GFP_ATOMIC, @@ -4240,13 +5246,16 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc) "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), - audit_get_loginuid(current), - uid, gid, + from_kuid(&init_user_ns, audit_get_loginuid(current)), + from_kuid(&init_user_ns, uid), + from_kgid(&init_user_ns, gid), audit_get_sessionid(current)); } dev_change_rx_flags(dev, IFF_PROMISC); } + if (notify) + __dev_notify_flags(dev, old_flags, IFF_PROMISC); return 0; } @@ -4263,10 +5272,10 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc) */ int dev_set_promiscuity(struct net_device *dev, int inc) { - unsigned short old_flags = dev->flags; + unsigned int old_flags = dev->flags; int err; - err = __dev_set_promiscuity(dev, inc); + err = __dev_set_promiscuity(dev, inc, true); if (err < 0) return err; if (dev->flags != old_flags) @@ -4275,22 +5284,9 @@ int dev_set_promiscuity(struct net_device *dev, int inc) } EXPORT_SYMBOL(dev_set_promiscuity); -/** - * dev_set_allmulti - update allmulti count on a device - * @dev: device - * @inc: modifier - * - * Add or remove reception of all multicast frames to a device. While the - * count in the device remains above zero the interface remains listening - * to all interfaces. Once it hits zero the device reverts back to normal - * filtering operation. A negative @inc value is used to drop the counter - * when releasing a resource needing all multicasts. - * Return 0 if successful or a negative errno code on error. - */ - -int dev_set_allmulti(struct net_device *dev, int inc) +static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) { - unsigned short old_flags = dev->flags; + unsigned int old_flags = dev->flags, old_gflags = dev->gflags; ASSERT_RTNL(); @@ -4305,18 +5301,38 @@ int dev_set_allmulti(struct net_device *dev, int inc) dev->flags &= ~IFF_ALLMULTI; else { dev->allmulti -= inc; - printk(KERN_WARNING "%s: allmulti touches roof, " - "set allmulti failed, allmulti feature of " - "device might be broken.\n", dev->name); + pr_warn("%s: allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n", + dev->name); return -EOVERFLOW; } } if (dev->flags ^ old_flags) { dev_change_rx_flags(dev, IFF_ALLMULTI); dev_set_rx_mode(dev); + if (notify) + __dev_notify_flags(dev, old_flags, + dev->gflags ^ old_gflags); } return 0; } + +/** + * dev_set_allmulti - update allmulti count on a device + * @dev: device + * @inc: modifier + * + * Add or remove reception of all multicast frames to a device. While the + * count in the device remains above zero the interface remains listening + * to all interfaces. Once it hits zero the device reverts back to normal + * filtering operation. A negative @inc value is used to drop the counter + * when releasing a resource needing all multicasts. + * Return 0 if successful or a negative errno code on error. + */ + +int dev_set_allmulti(struct net_device *dev, int inc) +{ + return __dev_set_allmulti(dev, inc, true); +} EXPORT_SYMBOL(dev_set_allmulti); /* @@ -4336,23 +5352,21 @@ void __dev_set_rx_mode(struct net_device *dev) if (!netif_device_present(dev)) return; - if (ops->ndo_set_rx_mode) - ops->ndo_set_rx_mode(dev); - else { + if (!(dev->priv_flags & IFF_UNICAST_FLT)) { /* Unicast addresses changes may only happen under the rtnl, * therefore calling __dev_set_promiscuity here is safe. */ if (!netdev_uc_empty(dev) && !dev->uc_promisc) { - __dev_set_promiscuity(dev, 1); - dev->uc_promisc = 1; + __dev_set_promiscuity(dev, 1, false); + dev->uc_promisc = true; } else if (netdev_uc_empty(dev) && dev->uc_promisc) { - __dev_set_promiscuity(dev, -1); - dev->uc_promisc = 0; + __dev_set_promiscuity(dev, -1, false); + dev->uc_promisc = false; } - - if (ops->ndo_set_multicast_list) - ops->ndo_set_multicast_list(dev); } + + if (ops->ndo_set_rx_mode) + ops->ndo_set_rx_mode(dev); } void dev_set_rx_mode(struct net_device *dev) @@ -4368,9 +5382,9 @@ void dev_set_rx_mode(struct net_device *dev) * * Get the combination of flag bits exported through APIs to userspace. */ -unsigned dev_get_flags(const struct net_device *dev) +unsigned int dev_get_flags(const struct net_device *dev) { - unsigned flags; + unsigned int flags; flags = (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI | @@ -4395,7 +5409,7 @@ EXPORT_SYMBOL(dev_get_flags); int __dev_change_flags(struct net_device *dev, unsigned int flags) { - int old_flags = dev->flags; + unsigned int old_flags = dev->flags; int ret; ASSERT_RTNL(); @@ -4435,9 +5449,13 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags) if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; + unsigned int old_flags = dev->flags; dev->gflags ^= IFF_PROMISC; - dev_set_promiscuity(dev, inc); + + if (__dev_set_promiscuity(dev, inc, false) >= 0) + if (dev->flags != old_flags) + dev_set_rx_mode(dev); } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI @@ -4448,16 +5466,20 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags) int inc = (flags & IFF_ALLMULTI) ? 1 : -1; dev->gflags ^= IFF_ALLMULTI; - dev_set_allmulti(dev, inc); + __dev_set_allmulti(dev, inc, false); } return ret; } -void __dev_notify_flags(struct net_device *dev, unsigned int old_flags) +void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, + unsigned int gchanges) { unsigned int changes = dev->flags ^ old_flags; + if (gchanges) + rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC); + if (changes & IFF_UP) { if (dev->flags & IFF_UP) call_netdevice_notifiers(NETDEV_UP, dev); @@ -4466,8 +5488,13 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags) } if (dev->flags & IFF_UP && - (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) - call_netdevice_notifiers(NETDEV_CHANGE, dev); + (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { + struct netdev_notifier_change_info change_info; + + change_info.flags_changed = changes; + call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + &change_info.info); + } } /** @@ -4478,24 +5505,32 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags) * Change settings on device based state flags. The flags are * in the userspace exported format. */ -int dev_change_flags(struct net_device *dev, unsigned flags) +int dev_change_flags(struct net_device *dev, unsigned int flags) { - int ret, changes; - int old_flags = dev->flags; + int ret; + unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags; ret = __dev_change_flags(dev, flags); if (ret < 0) return ret; - changes = old_flags ^ dev->flags; - if (changes) - rtmsg_ifinfo(RTM_NEWLINK, dev, changes); - - __dev_notify_flags(dev, old_flags); + changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); + __dev_notify_flags(dev, old_flags, changes); return ret; } EXPORT_SYMBOL(dev_change_flags); +static int __dev_set_mtu(struct net_device *dev, int new_mtu) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_change_mtu) + return ops->ndo_change_mtu(dev, new_mtu); + + dev->mtu = new_mtu; + return 0; +} + /** * dev_set_mtu - Change maximum transfer unit * @dev: device @@ -4505,8 +5540,7 @@ EXPORT_SYMBOL(dev_change_flags); */ int dev_set_mtu(struct net_device *dev, int new_mtu) { - const struct net_device_ops *ops = dev->netdev_ops; - int err; + int err, orig_mtu; if (new_mtu == dev->mtu) return 0; @@ -4518,19 +5552,41 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) if (!netif_device_present(dev)) return -ENODEV; - err = 0; - if (ops->ndo_change_mtu) - err = ops->ndo_change_mtu(dev, new_mtu); - else - dev->mtu = new_mtu; + err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) + return err; + + orig_mtu = dev->mtu; + err = __dev_set_mtu(dev, new_mtu); - if (!err && dev->flags & IFF_UP) - call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + if (!err) { + err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) { + /* setting mtu back and notifying everyone again, + * so that they have a chance to revert changes. + */ + __dev_set_mtu(dev, orig_mtu); + call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + } + } return err; } EXPORT_SYMBOL(dev_set_mtu); /** + * dev_set_group - Change group this device belongs to + * @dev: device + * @new_group: group this device should belong to + */ +void dev_set_group(struct net_device *dev, int new_group) +{ + dev->group = new_group; +} +EXPORT_SYMBOL(dev_set_group); + +/** * dev_set_mac_address - Change Media Access Control Address * @dev: device * @sa: new address @@ -4549,365 +5605,51 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) if (!netif_device_present(dev)) return -ENODEV; err = ops->ndo_set_mac_address(dev, sa); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return err; + if (err) + return err; + dev->addr_assign_type = NET_ADDR_SET; + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + add_device_randomness(dev->dev_addr, dev->addr_len); + return 0; } EXPORT_SYMBOL(dev_set_mac_address); -/* - * Perform the SIOCxIFxxx calls, inside rcu_read_lock() - */ -static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) -{ - int err; - struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); - - if (!dev) - return -ENODEV; - - switch (cmd) { - case SIOCGIFFLAGS: /* Get interface flags */ - ifr->ifr_flags = (short) dev_get_flags(dev); - return 0; - - case SIOCGIFMETRIC: /* Get the metric on the interface - (currently unused) */ - ifr->ifr_metric = 0; - return 0; - - case SIOCGIFMTU: /* Get the MTU of a device */ - ifr->ifr_mtu = dev->mtu; - return 0; - - case SIOCGIFHWADDR: - if (!dev->addr_len) - memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); - else - memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - ifr->ifr_hwaddr.sa_family = dev->type; - return 0; - - case SIOCGIFSLAVE: - err = -EINVAL; - break; - - case SIOCGIFMAP: - ifr->ifr_map.mem_start = dev->mem_start; - ifr->ifr_map.mem_end = dev->mem_end; - ifr->ifr_map.base_addr = dev->base_addr; - ifr->ifr_map.irq = dev->irq; - ifr->ifr_map.dma = dev->dma; - ifr->ifr_map.port = dev->if_port; - return 0; - - case SIOCGIFINDEX: - ifr->ifr_ifindex = dev->ifindex; - return 0; - - case SIOCGIFTXQLEN: - ifr->ifr_qlen = dev->tx_queue_len; - return 0; - - default: - /* dev_ioctl() should ensure this case - * is never reached - */ - WARN_ON(1); - err = -EINVAL; - break; - - } - return err; -} - -/* - * Perform the SIOCxIFxxx calls, inside rtnl_lock() +/** + * dev_change_carrier - Change device carrier + * @dev: device + * @new_carrier: new value + * + * Change device carrier */ -static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) +int dev_change_carrier(struct net_device *dev, bool new_carrier) { - int err; - struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); - const struct net_device_ops *ops; - - if (!dev) - return -ENODEV; - - ops = dev->netdev_ops; - - switch (cmd) { - case SIOCSIFFLAGS: /* Set interface flags */ - return dev_change_flags(dev, ifr->ifr_flags); - - case SIOCSIFMETRIC: /* Set the metric on the interface - (currently unused) */ - return -EOPNOTSUPP; - - case SIOCSIFMTU: /* Set the MTU of a device */ - return dev_set_mtu(dev, ifr->ifr_mtu); - - case SIOCSIFHWADDR: - return dev_set_mac_address(dev, &ifr->ifr_hwaddr); - - case SIOCSIFHWBROADCAST: - if (ifr->ifr_hwaddr.sa_family != dev->type) - return -EINVAL; - memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return 0; + const struct net_device_ops *ops = dev->netdev_ops; - case SIOCSIFMAP: - if (ops->ndo_set_config) { - if (!netif_device_present(dev)) - return -ENODEV; - return ops->ndo_set_config(dev, &ifr->ifr_map); - } + if (!ops->ndo_change_carrier) return -EOPNOTSUPP; - - case SIOCADDMULTI: - if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; - if (!netif_device_present(dev)) - return -ENODEV; - return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); - - case SIOCDELMULTI: - if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; - if (!netif_device_present(dev)) - return -ENODEV; - return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); - - case SIOCSIFTXQLEN: - if (ifr->ifr_qlen < 0) - return -EINVAL; - dev->tx_queue_len = ifr->ifr_qlen; - return 0; - - case SIOCSIFNAME: - ifr->ifr_newname[IFNAMSIZ-1] = '\0'; - return dev_change_name(dev, ifr->ifr_newname); - - /* - * Unknown or private ioctl - */ - default: - if ((cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15) || - cmd == SIOCBONDENSLAVE || - cmd == SIOCBONDRELEASE || - cmd == SIOCBONDSETHWADDR || - cmd == SIOCBONDSLAVEINFOQUERY || - cmd == SIOCBONDINFOQUERY || - cmd == SIOCBONDCHANGEACTIVE || - cmd == SIOCGMIIPHY || - cmd == SIOCGMIIREG || - cmd == SIOCSMIIREG || - cmd == SIOCBRADDIF || - cmd == SIOCBRDELIF || - cmd == SIOCSHWTSTAMP || - cmd == SIOCWANDEV) { - err = -EOPNOTSUPP; - if (ops->ndo_do_ioctl) { - if (netif_device_present(dev)) - err = ops->ndo_do_ioctl(dev, ifr, cmd); - else - err = -ENODEV; - } - } else - err = -EINVAL; - - } - return err; + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_change_carrier(dev, new_carrier); } - -/* - * This function handles all "interface"-type I/O control requests. The actual - * 'doing' part of this is dev_ifsioc above. - */ +EXPORT_SYMBOL(dev_change_carrier); /** - * dev_ioctl - network device ioctl - * @net: the applicable net namespace - * @cmd: command to issue - * @arg: pointer to a struct ifreq in user space + * dev_get_phys_port_id - Get device physical port ID + * @dev: device + * @ppid: port ID * - * Issue ioctl functions to devices. This is normally called by the - * user space syscall interfaces but can sometimes be useful for - * other purposes. The return value is the return from the syscall if - * positive or a negative errno code on error. + * Get device physical port ID */ - -int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) +int dev_get_phys_port_id(struct net_device *dev, + struct netdev_phys_port_id *ppid) { - struct ifreq ifr; - int ret; - char *colon; - - /* One special case: SIOCGIFCONF takes ifconf argument - and requires shared lock, because it sleeps writing - to user space. - */ - - if (cmd == SIOCGIFCONF) { - rtnl_lock(); - ret = dev_ifconf(net, (char __user *) arg); - rtnl_unlock(); - return ret; - } - if (cmd == SIOCGIFNAME) - return dev_ifname(net, (struct ifreq __user *)arg); - - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; - - ifr.ifr_name[IFNAMSIZ-1] = 0; - - colon = strchr(ifr.ifr_name, ':'); - if (colon) - *colon = 0; - - /* - * See which interface the caller is talking about. - */ - - switch (cmd) { - /* - * These ioctl calls: - * - can be done by all. - * - atomic and do not require locking. - * - return a value - */ - case SIOCGIFFLAGS: - case SIOCGIFMETRIC: - case SIOCGIFMTU: - case SIOCGIFHWADDR: - case SIOCGIFSLAVE: - case SIOCGIFMAP: - case SIOCGIFINDEX: - case SIOCGIFTXQLEN: - dev_load(net, ifr.ifr_name); - rcu_read_lock(); - ret = dev_ifsioc_locked(net, &ifr, cmd); - rcu_read_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; - - case SIOCETHTOOL: - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ethtool(net, &ifr); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; - - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - return a value - */ - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCSIFNAME: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; - - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - do not return a value - */ - case SIOCSIFFLAGS: - case SIOCSIFMETRIC: - case SIOCSIFMTU: - case SIOCSIFMAP: - case SIOCSIFHWADDR: - case SIOCSIFSLAVE: - case SIOCADDMULTI: - case SIOCDELMULTI: - case SIOCSIFHWBROADCAST: - case SIOCSIFTXQLEN: - case SIOCSMIIREG: - case SIOCBONDENSLAVE: - case SIOCBONDRELEASE: - case SIOCBONDSETHWADDR: - case SIOCBONDCHANGEACTIVE: - case SIOCBRADDIF: - case SIOCBRDELIF: - case SIOCSHWTSTAMP: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - /* fall through */ - case SIOCBONDSLAVEINFOQUERY: - case SIOCBONDINFOQUERY: - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - return ret; - - case SIOCGIFMEM: - /* Get the per device memory space. We can add this but - * currently do not support it */ - case SIOCSIFMEM: - /* Set the per device memory buffer space. - * Not applicable in our case */ - case SIOCSIFLINK: - return -EINVAL; + const struct net_device_ops *ops = dev->netdev_ops; - /* - * Unknown or private ioctl. - */ - default: - if (cmd == SIOCWANDEV || - (cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15)) { - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - if (!ret && copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - return ret; - } - /* Take care of Wireless Extensions */ - if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) - return wext_handle_ioctl(net, &ifr, cmd, arg); - return -EINVAL; - } + if (!ops->ndo_get_phys_port_id) + return -EOPNOTSUPP; + return ops->ndo_get_phys_port_id(dev, ppid); } - +EXPORT_SYMBOL(dev_get_phys_port_id); /** * dev_new_index - allocate an ifindex @@ -4919,26 +5661,29 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) */ static int dev_new_index(struct net *net) { - static int ifindex; + int ifindex = net->ifindex; for (;;) { if (++ifindex <= 0) ifindex = 1; if (!__dev_get_by_index(net, ifindex)) - return ifindex; + return net->ifindex = ifindex; } } /* Delayed registration/unregisteration */ static 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); + dev_net(dev)->dev_unreg_count++; } static void rollback_registered_many(struct list_head *head) { struct net_device *dev, *tmp; + LIST_HEAD(close_head); BUG_ON(dev_boot_phase); ASSERT_RTNL(); @@ -4949,19 +5694,23 @@ static void rollback_registered_many(struct list_head *head) * 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); + 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. */ - dev_close(dev); + /* 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); + list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ unlist_netdevice(dev); @@ -4980,10 +5729,6 @@ static void rollback_registered_many(struct list_head *head) */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - if (!dev->rtnl_link_ops || - dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); - /* * Flush the unicast and multicast chains */ @@ -4993,18 +5738,22 @@ static void rollback_registered_many(struct list_head *head) if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); - /* Notifier chain MUST detach us from master device. */ - WARN_ON(dev->master); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + + /* Notifier chain MUST detach us all upper devices. */ + WARN_ON(netdev_has_any_upper_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 } - /* Process any work delayed until the end of the batch */ - dev = list_first_entry(head, struct net_device, unreg_list); - call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - - rcu_barrier(); + synchronize_net(); list_for_each_entry(dev, head, unreg_list) dev_put(dev); @@ -5016,50 +5765,144 @@ static void rollback_registered(struct net_device *dev) list_add(&dev->unreg_list, &single); rollback_registered_many(&single); + list_del(&single); } -unsigned long netdev_fix_features(unsigned long features, const char *name) +static netdev_features_t netdev_fix_features(struct net_device *dev, + netdev_features_t features) { - /* Fix illegal SG+CSUM combinations. */ - if ((features & NETIF_F_SG) && - !(features & NETIF_F_ALL_CSUM)) { - if (name) - printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no " - "checksum feature.\n", name); - features &= ~NETIF_F_SG; + /* Fix illegal checksum combinations */ + if ((features & NETIF_F_HW_CSUM) && + (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { + netdev_warn(dev, "mixed HW and IP checksum settings.\n"); + features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } /* TSO requires that SG is present as well. */ - if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) { - if (name) - printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no " - "SG feature.\n", name); + if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { + netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); + features &= ~NETIF_F_ALL_TSO; + } + + if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) && + !(features & NETIF_F_IP_CSUM)) { + netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n"); features &= ~NETIF_F_TSO; + features &= ~NETIF_F_TSO_ECN; + } + + if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) && + !(features & NETIF_F_IPV6_CSUM)) { + netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n"); + features &= ~NETIF_F_TSO6; } + /* TSO ECN requires that TSO is present as well. */ + if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) + features &= ~NETIF_F_TSO_ECN; + + /* Software GSO depends on SG. */ + if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { + netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); + features &= ~NETIF_F_GSO; + } + + /* UFO needs SG and checksumming */ if (features & NETIF_F_UFO) { /* maybe split UFO into V4 and V6? */ if (!((features & NETIF_F_GEN_CSUM) || (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - if (name) - printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no checksum offload features.\n", - name); + netdev_dbg(dev, + "Dropping NETIF_F_UFO since no checksum offload features.\n"); features &= ~NETIF_F_UFO; } if (!(features & NETIF_F_SG)) { - if (name) - printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no NETIF_F_SG feature.\n", name); + netdev_dbg(dev, + "Dropping NETIF_F_UFO since no NETIF_F_SG feature.\n"); features &= ~NETIF_F_UFO; } } +#ifdef CONFIG_NET_RX_BUSY_POLL + if (dev->netdev_ops->ndo_busy_poll) + features |= NETIF_F_BUSY_POLL; + else +#endif + features &= ~NETIF_F_BUSY_POLL; + return features; } -EXPORT_SYMBOL(netdev_fix_features); + +int __netdev_update_features(struct net_device *dev) +{ + netdev_features_t features; + int err = 0; + + ASSERT_RTNL(); + + features = netdev_get_wanted_features(dev); + + if (dev->netdev_ops->ndo_fix_features) + features = dev->netdev_ops->ndo_fix_features(dev, features); + + /* driver might be less strict about feature dependencies */ + features = netdev_fix_features(dev, features); + + if (dev->features == features) + return 0; + + netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", + &dev->features, &features); + + if (dev->netdev_ops->ndo_set_features) + err = dev->netdev_ops->ndo_set_features(dev, features); + + if (unlikely(err < 0)) { + netdev_err(dev, + "set_features() failed (%d); wanted %pNF, left %pNF\n", + err, &features, &dev->features); + return -1; + } + + if (!err) + dev->features = features; + + return 1; +} + +/** + * netdev_update_features - recalculate device features + * @dev: the device to check + * + * Recalculate dev->features set and send notifications if it + * has changed. Should be called after driver or hardware dependent + * conditions might have changed that influence the features. + */ +void netdev_update_features(struct net_device *dev) +{ + if (__netdev_update_features(dev)) + netdev_features_change(dev); +} +EXPORT_SYMBOL(netdev_update_features); + +/** + * netdev_change_features - recalculate device features + * @dev: the device to check + * + * Recalculate dev->features set and send notifications even + * if they have not changed. Should be called instead of + * netdev_update_features() if also dev->vlan_features might + * have changed to allow the changes to be propagated to stacked + * VLAN devices. + */ +void netdev_change_features(struct net_device *dev) +{ + __netdev_update_features(dev); + netdev_features_change(dev); +} +EXPORT_SYMBOL(netdev_change_features); /** * netif_stacked_transfer_operstate - transfer operstate @@ -5088,7 +5931,7 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, } EXPORT_SYMBOL(netif_stacked_transfer_operstate); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; @@ -5097,10 +5940,9 @@ static int netif_alloc_rx_queues(struct net_device *dev) BUG_ON(count < 1); rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL); - if (!rx) { - pr_err("netdev: Unable to allocate %u rx queues.\n", count); + if (!rx) return -ENOMEM; - } + dev->_rx = rx; for (i = 0; i < count; i++) @@ -5116,22 +5958,31 @@ static void netdev_init_one_queue(struct net_device *dev, spin_lock_init(&queue->_xmit_lock); netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); queue->xmit_lock_owner = -1; - netdev_queue_numa_node_write(queue, -1); + netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; +#ifdef CONFIG_BQL + dql_init(&queue->dql, HZ); +#endif +} + +static void netif_free_tx_queues(struct net_device *dev) +{ + kvfree(dev->_tx); } static int netif_alloc_netdev_queues(struct net_device *dev) { unsigned int count = dev->num_tx_queues; struct netdev_queue *tx; + size_t sz = count * sizeof(*tx); - BUG_ON(count < 1); + BUG_ON(count < 1 || count > 0xffff); - tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL); + tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); if (!tx) { - pr_err("netdev: Unable to allocate %u tx queues.\n", - count); - return -ENOMEM; + tx = vzalloc(sz); + if (!tx) + return -ENOMEM; } dev->_tx = tx; @@ -5177,6 +6028,10 @@ int register_netdevice(struct net_device *dev) dev->iflink = -1; + ret = dev_get_valid_name(net, dev, dev->name); + if (ret < 0) + goto out; + /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -5187,40 +6042,46 @@ int register_netdevice(struct net_device *dev) } } - ret = dev_get_valid_name(dev, dev->name, 0); - if (ret) + if (((dev->hw_features | dev->features) & + NETIF_F_HW_VLAN_CTAG_FILTER) && + (!dev->netdev_ops->ndo_vlan_rx_add_vid || + !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { + netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); + ret = -EINVAL; + goto err_uninit; + } + + ret = -EBUSY; + if (!dev->ifindex) + dev->ifindex = dev_new_index(net); + else if (__dev_get_by_index(net, dev->ifindex)) goto err_uninit; - dev->ifindex = dev_new_index(net); if (dev->iflink == -1) dev->iflink = dev->ifindex; - /* Fix illegal checksum combinations */ - if ((dev->features & NETIF_F_HW_CSUM) && - (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - printk(KERN_NOTICE "%s: mixed HW and IP checksum settings.\n", - dev->name); - dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); - } + /* Transfer changeable features to wanted_features and enable + * software offloads (GSO and GRO). + */ + dev->hw_features |= NETIF_F_SOFT_FEATURES; + dev->features |= NETIF_F_SOFT_FEATURES; + dev->wanted_features = dev->features & dev->hw_features; - if ((dev->features & NETIF_F_NO_CSUM) && - (dev->features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - printk(KERN_NOTICE "%s: mixed no checksumming and other settings.\n", - dev->name); - dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM); + if (!(dev->flags & IFF_LOOPBACK)) { + dev->hw_features |= NETIF_F_NOCACHE_COPY; } - dev->features = netdev_fix_features(dev->features, dev->name); + /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. + */ + dev->vlan_features |= NETIF_F_HIGHDMA; - /* Enable software GSO if SG is supported. */ - if (dev->features & NETIF_F_SG) - dev->features |= NETIF_F_GSO; + /* Make NETIF_F_SG inheritable to tunnel devices. + */ + dev->hw_enc_features |= NETIF_F_SG; - /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, - * vlan_dev_init() will do the dev->features check, so these features - * are enabled only if supported by underlying device. + /* Make NETIF_F_SG inheritable to MPLS. */ - dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA); + dev->mpls_features |= NETIF_F_SG; ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); @@ -5232,6 +6093,8 @@ int register_netdevice(struct net_device *dev) goto err_uninit; dev->reg_state = NETREG_REGISTERED; + __netdev_update_features(dev); + /* * Default initial state at registry is that the * device is present. @@ -5239,9 +6102,19 @@ int register_netdevice(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); + linkwatch_init_dev(dev); + dev_init_scheduler(dev); dev_hold(dev); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); + + /* If the device has permanent device address, driver should + * set dev_addr and also addr_assign_type should be set to + * NET_ADDR_PERM (default value). + */ + if (dev->addr_assign_type == NET_ADDR_PERM) + memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); @@ -5256,7 +6129,7 @@ int register_netdevice(struct net_device *dev) */ if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); out: return ret; @@ -5327,19 +6200,7 @@ int register_netdev(struct net_device *dev) int err; rtnl_lock(); - - /* - * If the name is a format string the caller wants us to do a - * name allocation. - */ - if (strchr(dev->name, '%')) { - err = dev_alloc_name(dev, dev->name); - if (err < 0) - goto out; - } - err = register_netdevice(dev); -out: rtnl_unlock(); return err; } @@ -5355,8 +6216,9 @@ int netdev_refcnt_read(const struct net_device *dev) } EXPORT_SYMBOL(netdev_refcnt_read); -/* +/** * netdev_wait_allrefs - wait until all references are gone. + * @dev: target net_device * * This is called when unregistering network devices. * @@ -5382,9 +6244,12 @@ static void netdev_wait_allrefs(struct net_device *dev) /* Rebroadcast unregister notification */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - /* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users - * should have already handle it the first time */ + __rtnl_unlock(); + rcu_barrier(); + rtnl_lock(); + + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { /* We must not have linkwatch events @@ -5406,10 +6271,8 @@ static void netdev_wait_allrefs(struct net_device *dev) refcnt = netdev_refcnt_read(dev); if (time_after(jiffies, warning_time + 10 * HZ)) { - printk(KERN_EMERG "unregister_netdevice: " - "waiting for %s to become free. Usage " - "count = %d\n", - dev->name, refcnt); + pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", + dev->name, refcnt); warning_time = jiffies; } } @@ -5448,13 +6311,22 @@ void netdev_run_todo(void) __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); + rtnl_lock(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); + __rtnl_unlock(); + if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { - printk(KERN_ERR "network todo '%s' but state %d\n", + pr_err("network todo '%s' but state %d\n", dev->name, dev->reg_state); dump_stack(); continue; @@ -5468,55 +6340,33 @@ void netdev_run_todo(void) /* paranoia */ BUG_ON(netdev_refcnt_read(dev)); - WARN_ON(rcu_dereference_raw(dev->ip_ptr)); - WARN_ON(rcu_dereference_raw(dev->ip6_ptr)); + WARN_ON(rcu_access_pointer(dev->ip_ptr)); + WARN_ON(rcu_access_pointer(dev->ip6_ptr)); WARN_ON(dev->dn_ptr); if (dev->destructor) dev->destructor(dev); + /* Report a network device has been unregistered */ + rtnl_lock(); + dev_net(dev)->dev_unreg_count--; + __rtnl_unlock(); + wake_up(&netdev_unregistering_wq); + /* Free network device */ kobject_put(&dev->dev.kobj); } } -/** - * dev_txq_stats_fold - fold tx_queues stats - * @dev: device to get statistics from - * @stats: struct rtnl_link_stats64 to hold results - */ -void dev_txq_stats_fold(const struct net_device *dev, - struct rtnl_link_stats64 *stats) -{ - u64 tx_bytes = 0, tx_packets = 0, tx_dropped = 0; - unsigned int i; - struct netdev_queue *txq; - - for (i = 0; i < dev->num_tx_queues; i++) { - txq = netdev_get_tx_queue(dev, i); - spin_lock_bh(&txq->_xmit_lock); - tx_bytes += txq->tx_bytes; - tx_packets += txq->tx_packets; - tx_dropped += txq->tx_dropped; - spin_unlock_bh(&txq->_xmit_lock); - } - if (tx_bytes || tx_packets || tx_dropped) { - stats->tx_bytes = tx_bytes; - stats->tx_packets = tx_packets; - stats->tx_dropped = tx_dropped; - } -} -EXPORT_SYMBOL(dev_txq_stats_fold); - /* Convert net_device_stats to rtnl_link_stats64. They have the same * fields in the same order, with only the type differing. */ -static void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, - const struct net_device_stats *netdev_stats) +void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, + const struct net_device_stats *netdev_stats) { #if BITS_PER_LONG == 64 - BUILD_BUG_ON(sizeof(*stats64) != sizeof(*netdev_stats)); - memcpy(stats64, netdev_stats, sizeof(*stats64)); + BUILD_BUG_ON(sizeof(*stats64) != sizeof(*netdev_stats)); + memcpy(stats64, netdev_stats, sizeof(*stats64)); #else size_t i, n = sizeof(*stats64) / sizeof(u64); const unsigned long *src = (const unsigned long *)netdev_stats; @@ -5528,6 +6378,7 @@ static void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, dst[i] = src[i]; #endif } +EXPORT_SYMBOL(netdev_stats_to_stats64); /** * dev_get_stats - get network device statistics @@ -5551,9 +6402,9 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); } else { netdev_stats_to_stats64(storage, &dev->stats); - dev_txq_stats_fold(dev, storage); } storage->rx_dropped += atomic_long_read(&dev->rx_dropped); + storage->tx_dropped += atomic_long_read(&dev->tx_dropped); return storage; } EXPORT_SYMBOL(dev_get_stats); @@ -5576,19 +6427,38 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) return queue; } +static const struct ethtool_ops default_ethtool_ops; + +void netdev_set_default_ethtool_ops(struct net_device *dev, + const struct ethtool_ops *ops) +{ + if (dev->ethtool_ops == &default_ethtool_ops) + dev->ethtool_ops = ops; +} +EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); + +void netdev_freemem(struct net_device *dev) +{ + char *addr = (char *)dev - dev->padded; + + kvfree(addr); +} + /** - * alloc_netdev_mq - allocate network device + * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @setup: callback to initialize device - * @queue_count: the number of subqueues to allocate + * @txqs: the number of TX subqueues to allocate + * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use - * and performs basic initialization. Also allocates subquue structs - * for each queue on the device at the end of the netdevice. + * and performs basic initialization. Also allocates subqueue structs + * for each queue on the device. */ -struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, - void (*setup)(struct net_device *), unsigned int queue_count) +struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, + void (*setup)(struct net_device *), + unsigned int txqs, unsigned int rxqs) { struct net_device *dev; size_t alloc_size; @@ -5596,12 +6466,18 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, BUG_ON(strlen(name) >= sizeof(dev->name)); - if (queue_count < 1) { - pr_err("alloc_netdev: Unable to allocate device " - "with zero queues.\n"); + if (txqs < 1) { + pr_err("alloc_netdev: Unable to allocate device with zero queues\n"); return NULL; } +#ifdef CONFIG_SYSFS + if (rxqs < 1) { + pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); + return NULL; + } +#endif + alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ @@ -5611,18 +6487,18 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; - p = kzalloc(alloc_size, GFP_KERNEL); - if (!p) { - printk(KERN_ERR "alloc_netdev: Unable to allocate device.\n"); + p = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + if (!p) + p = vzalloc(alloc_size); + if (!p) return NULL; - } dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) - goto free_p; + goto free_dev; if (dev_addr_init(dev)) goto free_pcpu; @@ -5632,42 +6508,49 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); - dev->num_tx_queues = queue_count; - dev->real_num_tx_queues = queue_count; - if (netif_alloc_netdev_queues(dev)) - goto free_pcpu; - -#ifdef CONFIG_RPS - dev->num_rx_queues = queue_count; - dev->real_num_rx_queues = queue_count; - if (netif_alloc_rx_queues(dev)) - goto free_pcpu; -#endif - dev->gso_max_size = GSO_MAX_SIZE; + dev->gso_max_segs = GSO_MAX_SEGS; - INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); - dev->ethtool_ntuple_list.count = 0; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); + INIT_LIST_HEAD(&dev->close_list); INIT_LIST_HEAD(&dev->link_watch_list); + INIT_LIST_HEAD(&dev->adj_list.upper); + INIT_LIST_HEAD(&dev->adj_list.lower); + INIT_LIST_HEAD(&dev->all_adj_list.upper); + INIT_LIST_HEAD(&dev->all_adj_list.lower); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); + + dev->num_tx_queues = txqs; + dev->real_num_tx_queues = txqs; + if (netif_alloc_netdev_queues(dev)) + goto free_all; + +#ifdef CONFIG_SYSFS + dev->num_rx_queues = rxqs; + dev->real_num_rx_queues = rxqs; + if (netif_alloc_rx_queues(dev)) + goto free_all; +#endif + strcpy(dev->name, name); + dev->group = INIT_NETDEV_GROUP; + if (!dev->ethtool_ops) + dev->ethtool_ops = &default_ethtool_ops; return dev; +free_all: + free_netdev(dev); + return NULL; + free_pcpu: free_percpu(dev->pcpu_refcnt); - kfree(dev->_tx); -#ifdef CONFIG_RPS - kfree(dev->_rx); -#endif - -free_p: - kfree(p); +free_dev: + netdev_freemem(dev); return NULL; } -EXPORT_SYMBOL(alloc_netdev_mq); +EXPORT_SYMBOL(alloc_netdev_mqs); /** * free_netdev - free network device @@ -5683,19 +6566,16 @@ void free_netdev(struct net_device *dev) release_net(dev_net(dev)); - kfree(dev->_tx); -#ifdef CONFIG_RPS + netif_free_tx_queues(dev); +#ifdef CONFIG_SYSFS kfree(dev->_rx); #endif - kfree(rcu_dereference_raw(dev->ingress_queue)); + kfree(rcu_dereference_protected(dev->ingress_queue, 1)); /* Flush device addresses */ dev_addr_flush(dev); - /* Clear ethtool n-tuple list */ - ethtool_ntuple_flush(dev); - list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); @@ -5704,7 +6584,7 @@ void free_netdev(struct net_device *dev) /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { - kfree((char *)dev - dev->padded); + netdev_freemem(dev); return; } @@ -5725,7 +6605,10 @@ EXPORT_SYMBOL(free_netdev); void synchronize_net(void) { might_sleep(); - synchronize_rcu(); + if (rtnl_is_locked()) + synchronize_rcu_expedited(); + else + synchronize_rcu(); } EXPORT_SYMBOL(synchronize_net); @@ -5759,6 +6642,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue); /** * unregister_netdevice_many - unregister many devices * @head: list of devices + * + * Note: As most callers use a stack allocated list_head, + * we force a list_del() to make sure stack wont be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { @@ -5768,6 +6654,7 @@ void unregister_netdevice_many(struct list_head *head) rollback_registered_many(head); list_for_each_entry(dev, head, unreg_list) net_set_todo(dev); + list_del(head); } } EXPORT_SYMBOL(unregister_netdevice_many); @@ -5817,7 +6704,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char goto out; /* Ensure the device has been registrered */ - err = -EINVAL; if (dev->reg_state != NETREG_REGISTERED) goto out; @@ -5834,7 +6720,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* We get here if we can't use the current device name */ if (!pat) goto out; - if (dev_get_valid_name(dev, pat, 1)) + if (dev_get_valid_name(net, dev, pat) < 0) goto out; } @@ -5862,7 +6748,9 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); + rcu_barrier(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); /* * Flush the unicast and multicast chains @@ -5870,6 +6758,9 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev_uc_flush(dev); dev_mc_flush(dev); + /* Send a netdev-removed uevent to the old namespace */ + kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); + /* Actually switch the network namespace */ dev_net_set(dev, net); @@ -5881,6 +6772,9 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev->iflink = dev->ifindex; } + /* Send a netdev-add uevent to the new namespace */ + kobject_uevent(&dev->dev.kobj, KOBJ_ADD); + /* Fixup kobjects */ err = device_rename(&dev->dev, dev->name); WARN_ON(err); @@ -5895,7 +6789,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); synchronize_net(); err = 0; @@ -5936,17 +6830,22 @@ static int dev_cpu_callback(struct notifier_block *nfb, oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } + /* Append NAPI poll list from offline CPU. */ + if (!list_empty(&oldsd->poll_list)) { + list_splice_init(&oldsd->poll_list, &sd->poll_list); + raise_softirq_irqoff(NET_RX_SOFTIRQ); + } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { - netif_rx(skb); + netif_rx_internal(skb); input_queue_head_incr(oldsd); } while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { - netif_rx(skb); + netif_rx_internal(skb); input_queue_head_incr(oldsd); } @@ -5964,38 +6863,25 @@ static int dev_cpu_callback(struct notifier_block *nfb, * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ -unsigned long netdev_increment_features(unsigned long all, unsigned long one, - unsigned long mask) -{ - /* If device needs checksumming, downgrade to it. */ - if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM)) - all ^= NETIF_F_NO_CSUM | (one & NETIF_F_ALL_CSUM); - else if (mask & NETIF_F_ALL_CSUM) { - /* If one device supports v4/v6 checksumming, set for all. */ - if (one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM) && - !(all & NETIF_F_GEN_CSUM)) { - all &= ~NETIF_F_ALL_CSUM; - all |= one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - } - - /* If one device supports hw checksumming, set for all. */ - if (one & NETIF_F_GEN_CSUM && !(all & NETIF_F_GEN_CSUM)) { - all &= ~NETIF_F_ALL_CSUM; - all |= NETIF_F_HW_CSUM; - } - } +netdev_features_t netdev_increment_features(netdev_features_t all, + netdev_features_t one, netdev_features_t mask) +{ + if (mask & NETIF_F_GEN_CSUM) + mask |= NETIF_F_ALL_CSUM; + mask |= NETIF_F_VLAN_CHALLENGED; - one |= NETIF_F_ALL_CSUM; + all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask; + all &= one | ~NETIF_F_ALL_FOR_ALL; - one |= all & NETIF_F_ONE_FOR_ALL; - all &= one | NETIF_F_LLTX | NETIF_F_GSO | NETIF_F_UFO; - all |= one & mask & NETIF_F_ONE_FOR_ALL; + /* If one device supports hw checksumming, set for all. */ + if (all & NETIF_F_GEN_CSUM) + all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); return all; } EXPORT_SYMBOL(netdev_increment_features); -static struct hlist_head *netdev_create_hash(void) +static struct hlist_head * __net_init netdev_create_hash(void) { int i; struct hlist_head *hash; @@ -6011,7 +6897,8 @@ static struct hlist_head *netdev_create_hash(void) /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { - INIT_LIST_HEAD(&net->dev_base_head); + if (net != &init_net) + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) @@ -6032,29 +6919,23 @@ err_name: /** * netdev_drivername - network driver for the device * @dev: network device - * @buffer: buffer for resulting name - * @len: size of buffer * * Determine network driver for device. */ -char *netdev_drivername(const struct net_device *dev, char *buffer, int len) +const char *netdev_drivername(const struct net_device *dev) { const struct device_driver *driver; const struct device *parent; - - if (len <= 0 || !buffer) - return buffer; - buffer[0] = 0; + const char *empty = ""; parent = dev->dev.parent; - if (!parent) - return buffer; + return empty; driver = parent->driver; if (driver && driver->name) - strlcpy(buffer, driver->name, len); - return buffer; + return driver->name; + return empty; } static int __netdev_printk(const char *level, const struct net_device *dev, @@ -6062,13 +6943,18 @@ static int __netdev_printk(const char *level, const struct net_device *dev, { int r; - if (dev && dev->dev.parent) - r = dev_printk(level, dev->dev.parent, "%s: %pV", - netdev_name(dev), vaf); - else if (dev) + if (dev && dev->dev.parent) { + r = dev_printk_emit(level[1] - '0', + dev->dev.parent, + "%s %s %s: %pV", + dev_driver_string(dev->dev.parent), + dev_name(dev->dev.parent), + netdev_name(dev), vaf); + } else if (dev) { r = printk("%s%s: %pV", level, netdev_name(dev), vaf); - else + } else { r = printk("%s(NULL net_device): %pV", level, vaf); + } return r; } @@ -6086,6 +6972,7 @@ int netdev_printk(const char *level, const struct net_device *dev, vaf.va = &args; r = __netdev_printk(level, dev, &vaf); + va_end(args); return r; @@ -6105,6 +6992,7 @@ int func(const struct net_device *dev, const char *fmt, ...) \ vaf.va = &args; \ \ r = __netdev_printk(level, dev, &vaf); \ + \ va_end(args); \ \ return r; \ @@ -6150,22 +7038,50 @@ static void __net_exit default_device_exit(struct net *net) if (dev->rtnl_link_ops) continue; - /* Push remaing network devices to init_net */ + /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { - printk(KERN_EMERG "%s: failed to move %s to init_net: %d\n", - __func__, dev->name, err); + pr_emerg("%s: failed to move %s to init_net: %d\n", + __func__, dev->name, err); 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(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + 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(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network - * namespace. Do this in the reverse order of registeration. + * namespace. Do this in the reverse order of registration. * Do this across as many network namespaces as possible to * improve batching efficiency. */ @@ -6173,7 +7089,18 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) struct net *net; LIST_HEAD(dev_kill_list); - rtnl_lock(); + /* 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); list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops) @@ -6218,6 +7145,8 @@ 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; @@ -6228,24 +7157,18 @@ static int __init net_dev_init(void) for_each_possible_cpu(i) { struct softnet_data *sd = &per_cpu(softnet_data, i); - memset(sd, 0, sizeof(*sd)); skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); - sd->completion_queue = NULL; INIT_LIST_HEAD(&sd->poll_list); - sd->output_queue = NULL; sd->output_queue_tailp = &sd->output_queue; #ifdef CONFIG_RPS sd->csd.func = rps_trigger_softirq; sd->csd.info = sd; - sd->csd.flags = 0; sd->cpu = i; #endif sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; - sd->backlog.gro_list = NULL; - sd->backlog.gro_count = 0; } dev_boot_phase = 0; @@ -6270,19 +7193,9 @@ static int __init net_dev_init(void) hotcpu_notifier(dev_cpu_callback, 0); dst_init(); - dev_mcast_init(); rc = 0; out: return rc; } subsys_initcall(net_dev_init); - -static int __init initialize_hashrnd(void) -{ - get_random_bytes(&hashrnd, sizeof(hashrnd)); - return 0; -} - -late_initcall_sync(initialize_hashrnd); - diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 508f9c18992..b6b230600b9 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -13,20 +13,46 @@ #include <linux/netdevice.h> #include <linux/rtnetlink.h> +#include <linux/export.h> #include <linux/list.h> -#include <linux/proc_fs.h> /* * General list handling functions */ -static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, - unsigned char *addr, int addr_len, - unsigned char addr_type, bool global) +static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type, bool global, + bool sync) { struct netdev_hw_addr *ha; int alloc_size; + alloc_size = sizeof(*ha); + if (alloc_size < L1_CACHE_BYTES) + alloc_size = L1_CACHE_BYTES; + ha = kmalloc(alloc_size, GFP_ATOMIC); + if (!ha) + return -ENOMEM; + memcpy(ha->addr, addr, addr_len); + ha->type = addr_type; + ha->refcount = 1; + ha->global_use = global; + ha->synced = sync ? 1 : 0; + ha->sync_cnt = 0; + list_add_tail_rcu(&ha->list, &list->list); + list->count++; + + return 0; +} + +static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type, bool global, bool sync, + int sync_count) +{ + struct netdev_hw_addr *ha; + if (addr_len > MAX_ADDR_LEN) return -EINVAL; @@ -40,115 +66,133 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, else ha->global_use = true; } + if (sync) { + if (ha->synced && sync_count) + return -EEXIST; + else + ha->synced++; + } ha->refcount++; return 0; } } - - alloc_size = sizeof(*ha); - if (alloc_size < L1_CACHE_BYTES) - alloc_size = L1_CACHE_BYTES; - ha = kmalloc(alloc_size, GFP_ATOMIC); - if (!ha) - return -ENOMEM; - memcpy(ha->addr, addr, addr_len); - ha->type = addr_type; - ha->refcount = 1; - ha->global_use = global; - ha->synced = false; - list_add_tail_rcu(&ha->list, &list->list); - list->count++; - return 0; + return __hw_addr_create_ex(list, addr, addr_len, addr_type, global, + sync); } -static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) +static int __hw_addr_add(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) { - return __hw_addr_add_ex(list, addr, addr_len, addr_type, false); + return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, + 0); } -static void ha_rcu_free(struct rcu_head *head) +static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, + struct netdev_hw_addr *ha, bool global, + bool sync) { - struct netdev_hw_addr *ha; + if (global && !ha->global_use) + return -ENOENT; + + if (sync && !ha->synced) + return -ENOENT; - ha = container_of(head, struct netdev_hw_addr, rcu_head); - kfree(ha); + if (global) + ha->global_use = false; + + if (sync) + ha->synced--; + + if (--ha->refcount) + return 0; + list_del_rcu(&ha->list); + kfree_rcu(ha, rcu_head); + list->count--; + return 0; } static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, - unsigned char *addr, int addr_len, - unsigned char addr_type, bool global) + const unsigned char *addr, int addr_len, + unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha; list_for_each_entry(ha, &list->list, list) { if (!memcmp(ha->addr, addr, addr_len) && - (ha->type == addr_type || !addr_type)) { - if (global) { - if (!ha->global_use) - break; - else - ha->global_use = false; - } - if (--ha->refcount) - return 0; - list_del_rcu(&ha->list); - call_rcu(&ha->rcu_head, ha_rcu_free); - list->count--; - return 0; - } + (ha->type == addr_type || !addr_type)) + return __hw_addr_del_entry(list, ha, global, sync); } return -ENOENT; } -static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) +static int __hw_addr_del(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) { - return __hw_addr_del_ex(list, addr, addr_len, addr_type, false); + return __hw_addr_del_ex(list, addr, addr_len, addr_type, false, false); } -int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, unsigned char addr_type) +static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr *ha, + int addr_len) { int err; - struct netdev_hw_addr *ha, *ha2; - unsigned char type; - list_for_each_entry(ha, &from_list->list, list) { - type = addr_type ? addr_type : ha->type; - err = __hw_addr_add(to_list, ha->addr, addr_len, type); - if (err) - goto unroll; + err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, + false, true, ha->sync_cnt); + if (err && err != -EEXIST) + return err; + + if (!err) { + ha->sync_cnt++; + ha->refcount++; } + return 0; +} -unroll: - list_for_each_entry(ha2, &from_list->list, list) { - if (ha2 == ha) - break; - type = addr_type ? addr_type : ha2->type; - __hw_addr_del(to_list, ha2->addr, addr_len, type); - } - return err; +static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + struct netdev_hw_addr *ha, + int addr_len) +{ + int err; + + err = __hw_addr_del_ex(to_list, ha->addr, addr_len, ha->type, + false, true); + if (err) + return; + ha->sync_cnt--; + /* address on from list is not marked synced */ + __hw_addr_del_entry(from_list, ha, false, false); } -EXPORT_SYMBOL(__hw_addr_add_multiple); -void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, unsigned char addr_type) +static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) { - struct netdev_hw_addr *ha; - unsigned char type; + int err = 0; + struct netdev_hw_addr *ha, *tmp; - list_for_each_entry(ha, &from_list->list, list) { - type = addr_type ? addr_type : ha->type; - __hw_addr_del(to_list, ha->addr, addr_len, addr_type); + list_for_each_entry_safe(ha, tmp, &from_list->list, list) { + if (ha->sync_cnt == ha->refcount) { + __hw_addr_unsync_one(to_list, from_list, ha, addr_len); + } else { + err = __hw_addr_sync_one(to_list, ha, addr_len); + if (err) + break; + } } + return err; } -EXPORT_SYMBOL(__hw_addr_del_multiple); +/* This function only works where there is a strict 1-1 relationship + * between source and destionation of they synch. If you ever need to + * sync addresses to more then 1 destination, you need to use + * __hw_addr_sync_multiple(). + */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len) @@ -157,17 +201,12 @@ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { - if (!ha->synced) { - err = __hw_addr_add(to_list, ha->addr, - addr_len, ha->type); + if (!ha->sync_cnt) { + err = __hw_addr_sync_one(to_list, ha, addr_len); if (err) break; - ha->synced = true; - ha->refcount++; - } else if (ha->refcount == 1) { - __hw_addr_del(to_list, ha->addr, addr_len, ha->type); - __hw_addr_del(from_list, ha->addr, addr_len, ha->type); - } + } else if (ha->refcount == 1) + __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } return err; } @@ -180,28 +219,107 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &from_list->list, list) { - if (ha->synced) { - __hw_addr_del(to_list, ha->addr, - addr_len, ha->type); - ha->synced = false; - __hw_addr_del(from_list, ha->addr, - addr_len, ha->type); - } + if (ha->sync_cnt) + __hw_addr_unsync_one(to_list, from_list, ha, addr_len); } } EXPORT_SYMBOL(__hw_addr_unsync); -void __hw_addr_flush(struct netdev_hw_addr_list *list) +/** + * __hw_addr_sync_dev - Synchonize device's multicast list + * @list: address list to syncronize + * @dev: device to sync + * @sync: function to call if address should be added + * @unsync: function to call if address should be removed + * + * This funciton is intended to be called from the ndo_set_rx_mode + * function of devices that require explicit address add/remove + * notifications. The unsync function may be NULL in which case + * the addresses requiring removal will simply be removed without + * any notification to the device. + **/ +int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*sync)(struct net_device *, const unsigned char *), + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + struct netdev_hw_addr *ha, *tmp; + int err; + + /* first go through and flush out any stale entries */ + list_for_each_entry_safe(ha, tmp, &list->list, list) { + if (!ha->sync_cnt || ha->refcount != 1) + continue; + + /* if unsync is defined and fails defer unsyncing address */ + if (unsync && unsync(dev, ha->addr)) + continue; + + ha->sync_cnt--; + __hw_addr_del_entry(list, ha, false, false); + } + + /* go through and sync new entries to the list */ + list_for_each_entry_safe(ha, tmp, &list->list, list) { + if (ha->sync_cnt) + continue; + + err = sync(dev, ha->addr); + if (err) + return err; + + ha->sync_cnt++; + ha->refcount++; + } + + return 0; +} +EXPORT_SYMBOL(__hw_addr_sync_dev); + +/** + * __hw_addr_unsync_dev - Remove synchonized addresses from device + * @list: address list to remove syncronized addresses from + * @dev: device to sync + * @unsync: function to call if address should be removed + * + * Remove all addresses that were added to the device by __hw_addr_sync_dev(). + * This function is intended to be called from the ndo_stop or ndo_open + * functions on devices that require explicit address add/remove + * notifications. If the unsync function pointer is NULL then this function + * can be used to just reset the sync_cnt for the addresses in the list. + **/ +void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, + struct net_device *dev, + int (*unsync)(struct net_device *, + const unsigned char *)) +{ + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &list->list, list) { + if (!ha->sync_cnt) + continue; + + /* if unsync is defined and fails defer unsyncing address */ + if (unsync && unsync(dev, ha->addr)) + continue; + + ha->sync_cnt--; + __hw_addr_del_entry(list, ha, false, false); + } +} +EXPORT_SYMBOL(__hw_addr_unsync_dev); + +static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; list_for_each_entry_safe(ha, tmp, &list->list, list) { list_del_rcu(&ha->list); - call_rcu(&ha->rcu_head, ha_rcu_free); + kfree_rcu(ha, rcu_head); } list->count = 0; } -EXPORT_SYMBOL(__hw_addr_flush); void __hw_addr_init(struct netdev_hw_addr_list *list) { @@ -276,7 +394,7 @@ EXPORT_SYMBOL(dev_addr_init); * * The caller must hold the rtnl_mutex. */ -int dev_addr_add(struct net_device *dev, unsigned char *addr, +int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; @@ -301,7 +419,7 @@ EXPORT_SYMBOL(dev_addr_add); * * The caller must hold the rtnl_mutex. */ -int dev_addr_del(struct net_device *dev, unsigned char *addr, +int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type) { int err; @@ -315,7 +433,8 @@ int dev_addr_del(struct net_device *dev, unsigned char *addr, */ ha = list_first_entry(&dev->dev_addrs.list, struct netdev_hw_addr, list); - if (ha->addr == dev->dev_addr && ha->refcount == 1) + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == addr_type && ha->refcount == 1) return -ENOENT; err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, @@ -326,62 +445,37 @@ int dev_addr_del(struct net_device *dev, unsigned char *addr, } EXPORT_SYMBOL(dev_addr_del); +/* + * Unicast list handling functions + */ + /** - * dev_addr_add_multiple - Add device addresses from another device - * @to_dev: device to which addresses will be added - * @from_dev: device from which addresses will be added - * @addr_type: address type - 0 means type will be used from from_dev - * - * Add device addresses of the one device to another. - ** - * The caller must hold the rtnl_mutex. + * dev_uc_add_excl - Add a global secondary unicast address + * @dev: device + * @addr: address to add */ -int dev_addr_add_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type) +int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { + struct netdev_hw_addr *ha; int err; - ASSERT_RTNL(); - - if (from_dev->addr_len != to_dev->addr_len) - return -EINVAL; - err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, - to_dev->addr_len, addr_type); + netif_addr_lock_bh(dev); + list_for_each_entry(ha, &dev->uc.list, list) { + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == NETDEV_HW_ADDR_T_UNICAST) { + err = -EEXIST; + goto out; + } + } + err = __hw_addr_create_ex(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST, true, false); if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); + __dev_set_rx_mode(dev); +out: + netif_addr_unlock_bh(dev); return err; } -EXPORT_SYMBOL(dev_addr_add_multiple); - -/** - * dev_addr_del_multiple - Delete device addresses by another device - * @to_dev: device where the addresses will be deleted - * @from_dev: device by which addresses the addresses will be deleted - * @addr_type: address type - 0 means type will used from from_dev - * - * Deletes addresses in to device by the list of addresses in from device. - * - * The caller must hold the rtnl_mutex. - */ -int dev_addr_del_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type) -{ - ASSERT_RTNL(); - - if (from_dev->addr_len != to_dev->addr_len) - return -EINVAL; - __hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, - to_dev->addr_len, addr_type); - call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); - return 0; -} -EXPORT_SYMBOL(dev_addr_del_multiple); - -/* - * Unicast list handling functions - */ +EXPORT_SYMBOL(dev_uc_add_excl); /** * dev_uc_add - Add a secondary unicast address @@ -391,7 +485,7 @@ EXPORT_SYMBOL(dev_addr_del_multiple); * Add a secondary unicast address to the device or increase * the reference count if it already exists. */ -int dev_uc_add(struct net_device *dev, unsigned char *addr) +int dev_uc_add(struct net_device *dev, const unsigned char *addr) { int err; @@ -413,7 +507,7 @@ EXPORT_SYMBOL(dev_uc_add); * Release reference to a secondary unicast address and remove it * from the device if the reference count drops to zero. */ -int dev_uc_del(struct net_device *dev, unsigned char *addr) +int dev_uc_del(struct net_device *dev, const unsigned char *addr) { int err; @@ -434,10 +528,11 @@ EXPORT_SYMBOL(dev_uc_del); * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be - * locked by netif_tx_lock_bh. + * locked by netif_addr_lock_bh. * * This function is intended to be called from the dev->set_rx_mode - * function of layered software devices. + * function of layered software devices. This function assumes that + * addresses will only ever be synced to the @to devices and no other. */ int dev_uc_sync(struct net_device *to, struct net_device *from) { @@ -446,16 +541,46 @@ int dev_uc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_bh(to); + netif_addr_lock_nested(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); - netif_addr_unlock_bh(to); + netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_uc_sync); /** + * dev_uc_sync_multiple - Synchronize device's unicast list to another + * device, but allow for multiple calls to sync to multiple devices. + * @to: destination device + * @from: source device + * + * Add newly added addresses to the destination device and release + * addresses that have been deleted from the source. The source device + * must be locked by netif_addr_lock_bh. + * + * This function is intended to be called from the dev->set_rx_mode + * function of layered software devices. It allows for a single source + * device to be synced to multiple destination devices. + */ +int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) +{ + int err = 0; + + if (to->addr_len != from->addr_len) + return -EINVAL; + + netif_addr_lock_nested(to); + err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + netif_addr_unlock(to); + return err; +} +EXPORT_SYMBOL(dev_uc_sync_multiple); + +/** * dev_uc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device @@ -470,7 +595,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock(to); + netif_addr_lock_nested(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); @@ -508,14 +633,42 @@ EXPORT_SYMBOL(dev_uc_init); * Multicast list handling functions */ -static int __dev_mc_add(struct net_device *dev, unsigned char *addr, +/** + * dev_mc_add_excl - Add a global secondary multicast address + * @dev: device + * @addr: address to add + */ +int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) +{ + struct netdev_hw_addr *ha; + int err; + + netif_addr_lock_bh(dev); + list_for_each_entry(ha, &dev->mc.list, list) { + if (!memcmp(ha->addr, addr, dev->addr_len) && + ha->type == NETDEV_HW_ADDR_T_MULTICAST) { + err = -EEXIST; + goto out; + } + } + err = __hw_addr_create_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, true, false); + if (!err) + __dev_set_rx_mode(dev); +out: + netif_addr_unlock_bh(dev); + return err; +} +EXPORT_SYMBOL(dev_mc_add_excl); + +static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_MULTICAST, global); + NETDEV_HW_ADDR_T_MULTICAST, global, false, 0); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); @@ -529,7 +682,7 @@ static int __dev_mc_add(struct net_device *dev, unsigned char *addr, * Add a multicast address to the device or increase * the reference count if it already exists. */ -int dev_mc_add(struct net_device *dev, unsigned char *addr) +int dev_mc_add(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, false); } @@ -542,20 +695,20 @@ EXPORT_SYMBOL(dev_mc_add); * * Add a global multicast address to the device. */ -int dev_mc_add_global(struct net_device *dev, unsigned char *addr) +int dev_mc_add_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_add(dev, addr, true); } EXPORT_SYMBOL(dev_mc_add_global); -static int __dev_mc_del(struct net_device *dev, unsigned char *addr, +static int __dev_mc_del(struct net_device *dev, const unsigned char *addr, bool global) { int err; netif_addr_lock_bh(dev); err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_MULTICAST, global); + NETDEV_HW_ADDR_T_MULTICAST, global, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); @@ -570,7 +723,7 @@ static int __dev_mc_del(struct net_device *dev, unsigned char *addr, * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ -int dev_mc_del(struct net_device *dev, unsigned char *addr) +int dev_mc_del(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, false); } @@ -584,23 +737,23 @@ EXPORT_SYMBOL(dev_mc_del); * Release reference to a multicast address and remove it * from the device if the reference count drops to zero. */ -int dev_mc_del_global(struct net_device *dev, unsigned char *addr) +int dev_mc_del_global(struct net_device *dev, const unsigned char *addr) { return __dev_mc_del(dev, addr, true); } EXPORT_SYMBOL(dev_mc_del_global); /** - * dev_mc_sync - Synchronize device's unicast list to another device + * dev_mc_sync - Synchronize device's multicast list to another device * @to: destination device * @from: source device * * Add newly added addresses to the destination device and release * addresses that have no users left. The source device must be - * locked by netif_tx_lock_bh. + * locked by netif_addr_lock_bh. * - * This function is intended to be called from the dev->set_multicast_list - * or dev->set_rx_mode function of layered software devices. + * This function is intended to be called from the ndo_set_rx_mode + * function of layered software devices. */ int dev_mc_sync(struct net_device *to, struct net_device *from) { @@ -609,16 +762,46 @@ int dev_mc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_bh(to); + netif_addr_lock_nested(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); - netif_addr_unlock_bh(to); + netif_addr_unlock(to); return err; } EXPORT_SYMBOL(dev_mc_sync); /** + * dev_mc_sync_multiple - Synchronize device's multicast list to another + * device, but allow for multiple calls to sync to multiple devices. + * @to: destination device + * @from: source device + * + * Add newly added addresses to the destination device and release + * addresses that have no users left. The source device must be + * locked by netif_addr_lock_bh. + * + * This function is intended to be called from the ndo_set_rx_mode + * function of layered software devices. It allows for a single + * source device to be synced to multiple destination devices. + */ +int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) +{ + int err = 0; + + if (to->addr_len != from->addr_len) + return -EINVAL; + + netif_addr_lock_nested(to); + err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + netif_addr_unlock(to); + return err; +} +EXPORT_SYMBOL(dev_mc_sync_multiple); + +/** * dev_mc_unsync - Remove synchronized addresses from the destination device * @to: destination device * @from: source device @@ -633,7 +816,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock(to); + netif_addr_lock_nested(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); @@ -666,76 +849,3 @@ void dev_mc_init(struct net_device *dev) __hw_addr_init(&dev->mc); } EXPORT_SYMBOL(dev_mc_init); - -#ifdef CONFIG_PROC_FS -#include <linux/seq_file.h> - -static int dev_mc_seq_show(struct seq_file *seq, void *v) -{ - struct netdev_hw_addr *ha; - struct net_device *dev = v; - - if (v == SEQ_START_TOKEN) - return 0; - - netif_addr_lock_bh(dev); - netdev_for_each_mc_addr(ha, dev) { - int i; - - seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, - dev->name, ha->refcount, ha->global_use); - - for (i = 0; i < dev->addr_len; i++) - seq_printf(seq, "%02x", ha->addr[i]); - - seq_putc(seq, '\n'); - } - netif_addr_unlock_bh(dev); - return 0; -} - -static const struct seq_operations dev_mc_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = dev_mc_seq_show, -}; - -static int dev_mc_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &dev_mc_seq_ops, - sizeof(struct seq_net_private)); -} - -static const struct file_operations dev_mc_seq_fops = { - .owner = THIS_MODULE, - .open = dev_mc_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - -#endif - -static int __net_init dev_mc_net_init(struct net *net) -{ - if (!proc_net_fops_create(net, "dev_mcast", 0, &dev_mc_seq_fops)) - return -ENOMEM; - return 0; -} - -static void __net_exit dev_mc_net_exit(struct net *net) -{ - proc_net_remove(net, "dev_mcast"); -} - -static struct pernet_operations __net_initdata dev_mc_net_ops = { - .init = dev_mc_net_init, - .exit = dev_mc_net_exit, -}; - -void __init dev_mcast_init(void) -{ - register_pernet_subsys(&dev_mc_net_ops); -} - diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c new file mode 100644 index 00000000000..cf999e09bcd --- /dev/null +++ b/net/core/dev_ioctl.c @@ -0,0 +1,567 @@ +#include <linux/kmod.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/net_tstamp.h> +#include <linux/wireless.h> +#include <net/wext.h> + +/* + * Map an interface index to its name (SIOCGIFNAME) + */ + +/* + * We need this ioctl for efficient implementation of the + * if_indextoname() function required by the IPv6 API. Without + * it, we would have to search all the interfaces to find a + * match. --pb + */ + +static int dev_ifname(struct net *net, struct ifreq __user *arg) +{ + struct ifreq ifr; + int error; + + /* + * Fetch the caller's info block. + */ + + if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + return -EFAULT; + + error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex); + if (error) + return error; + + if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) + return -EFAULT; + return 0; +} + +static gifconf_func_t *gifconf_list[NPROTO]; + +/** + * register_gifconf - register a SIOCGIF handler + * @family: Address family + * @gifconf: Function handler + * + * Register protocol dependent address dumping routines. The handler + * that is passed must not be freed or reused until it has been replaced + * by another handler. + */ +int register_gifconf(unsigned int family, gifconf_func_t *gifconf) +{ + if (family >= NPROTO) + return -EINVAL; + gifconf_list[family] = gifconf; + return 0; +} +EXPORT_SYMBOL(register_gifconf); + +/* + * Perform a SIOCGIFCONF call. This structure will change + * size eventually, and there is nothing I can do about it. + * Thus we will need a 'compatibility mode'. + */ + +static int dev_ifconf(struct net *net, char __user *arg) +{ + struct ifconf ifc; + struct net_device *dev; + char __user *pos; + int len; + int total; + int i; + + /* + * Fetch the caller's info block. + */ + + if (copy_from_user(&ifc, arg, sizeof(struct ifconf))) + return -EFAULT; + + pos = ifc.ifc_buf; + len = ifc.ifc_len; + + /* + * Loop over the interfaces, and write an info block for each. + */ + + total = 0; + for_each_netdev(net, dev) { + for (i = 0; i < NPROTO; i++) { + if (gifconf_list[i]) { + int done; + if (!pos) + done = gifconf_list[i](dev, NULL, 0); + else + done = gifconf_list[i](dev, pos + total, + len - total); + if (done < 0) + return -EFAULT; + total += done; + } + } + } + + /* + * All done. Write the updated control block back to the caller. + */ + ifc.ifc_len = total; + + /* + * Both BSD and Solaris return 0 here, so we do too. + */ + return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0; +} + +/* + * Perform the SIOCxIFxxx calls, inside rcu_read_lock() + */ +static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) +{ + int err; + struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); + + if (!dev) + return -ENODEV; + + switch (cmd) { + case SIOCGIFFLAGS: /* Get interface flags */ + ifr->ifr_flags = (short) dev_get_flags(dev); + return 0; + + case SIOCGIFMETRIC: /* Get the metric on the interface + (currently unused) */ + ifr->ifr_metric = 0; + return 0; + + case SIOCGIFMTU: /* Get the MTU of a device */ + ifr->ifr_mtu = dev->mtu; + return 0; + + case SIOCGIFHWADDR: + if (!dev->addr_len) + memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); + else + memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + ifr->ifr_hwaddr.sa_family = dev->type; + return 0; + + case SIOCGIFSLAVE: + err = -EINVAL; + break; + + case SIOCGIFMAP: + ifr->ifr_map.mem_start = dev->mem_start; + ifr->ifr_map.mem_end = dev->mem_end; + ifr->ifr_map.base_addr = dev->base_addr; + ifr->ifr_map.irq = dev->irq; + ifr->ifr_map.dma = dev->dma; + ifr->ifr_map.port = dev->if_port; + return 0; + + case SIOCGIFINDEX: + ifr->ifr_ifindex = dev->ifindex; + return 0; + + case SIOCGIFTXQLEN: + ifr->ifr_qlen = dev->tx_queue_len; + return 0; + + default: + /* dev_ioctl() should ensure this case + * is never reached + */ + WARN_ON(1); + err = -ENOTTY; + break; + + } + return err; +} + +static int net_hwtstamp_validate(struct ifreq *ifr) +{ + struct hwtstamp_config cfg; + enum hwtstamp_tx_types tx_type; + enum hwtstamp_rx_filters rx_filter; + int tx_type_valid = 0; + int rx_filter_valid = 0; + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + if (cfg.flags) /* reserved for future extensions */ + return -EINVAL; + + tx_type = cfg.tx_type; + rx_filter = cfg.rx_filter; + + switch (tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + case HWTSTAMP_TX_ONESTEP_SYNC: + tx_type_valid = 1; + break; + } + + switch (rx_filter) { + case HWTSTAMP_FILTER_NONE: + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + rx_filter_valid = 1; + break; + } + + if (!tx_type_valid || !rx_filter_valid) + return -ERANGE; + + return 0; +} + +/* + * Perform the SIOCxIFxxx calls, inside rtnl_lock() + */ +static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) +{ + int err; + struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); + const struct net_device_ops *ops; + + if (!dev) + return -ENODEV; + + ops = dev->netdev_ops; + + switch (cmd) { + case SIOCSIFFLAGS: /* Set interface flags */ + return dev_change_flags(dev, ifr->ifr_flags); + + case SIOCSIFMETRIC: /* Set the metric on the interface + (currently unused) */ + return -EOPNOTSUPP; + + case SIOCSIFMTU: /* Set the MTU of a device */ + return dev_set_mtu(dev, ifr->ifr_mtu); + + case SIOCSIFHWADDR: + return dev_set_mac_address(dev, &ifr->ifr_hwaddr); + + case SIOCSIFHWBROADCAST: + if (ifr->ifr_hwaddr.sa_family != dev->type) + return -EINVAL; + memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return 0; + + case SIOCSIFMAP: + if (ops->ndo_set_config) { + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_set_config(dev, &ifr->ifr_map); + } + return -EOPNOTSUPP; + + case SIOCADDMULTI: + if (!ops->ndo_set_rx_mode || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); + + case SIOCDELMULTI: + if (!ops->ndo_set_rx_mode || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); + + case SIOCSIFTXQLEN: + if (ifr->ifr_qlen < 0) + return -EINVAL; + dev->tx_queue_len = ifr->ifr_qlen; + return 0; + + case SIOCSIFNAME: + ifr->ifr_newname[IFNAMSIZ-1] = '\0'; + return dev_change_name(dev, ifr->ifr_newname); + + case SIOCSHWTSTAMP: + err = net_hwtstamp_validate(ifr); + if (err) + return err; + /* fall through */ + + /* + * Unknown or private ioctl + */ + default: + if ((cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15) || + cmd == SIOCBONDENSLAVE || + cmd == SIOCBONDRELEASE || + cmd == SIOCBONDSETHWADDR || + cmd == SIOCBONDSLAVEINFOQUERY || + cmd == SIOCBONDINFOQUERY || + cmd == SIOCBONDCHANGEACTIVE || + cmd == SIOCGMIIPHY || + cmd == SIOCGMIIREG || + cmd == SIOCSMIIREG || + cmd == SIOCBRADDIF || + cmd == SIOCBRDELIF || + cmd == SIOCSHWTSTAMP || + cmd == SIOCGHWTSTAMP || + cmd == SIOCWANDEV) { + err = -EOPNOTSUPP; + if (ops->ndo_do_ioctl) { + if (netif_device_present(dev)) + err = ops->ndo_do_ioctl(dev, ifr, cmd); + else + err = -ENODEV; + } + } else + err = -EINVAL; + + } + return err; +} + +/** + * dev_load - load a network module + * @net: the applicable net namespace + * @name: name of interface + * + * If a network interface is not present and the process has suitable + * privileges this function loads the module. If module loading is not + * available in this kernel then it becomes a nop. + */ + +void dev_load(struct net *net, const char *name) +{ + struct net_device *dev; + int no_module; + + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); + rcu_read_unlock(); + + no_module = !dev; + if (no_module && capable(CAP_NET_ADMIN)) + no_module = request_module("netdev-%s", name); + if (no_module && capable(CAP_SYS_MODULE)) { + if (!request_module("%s", name)) + pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", + name); + } +} +EXPORT_SYMBOL(dev_load); + +/* + * This function handles all "interface"-type I/O control requests. The actual + * 'doing' part of this is dev_ifsioc above. + */ + +/** + * dev_ioctl - network device ioctl + * @net: the applicable net namespace + * @cmd: command to issue + * @arg: pointer to a struct ifreq in user space + * + * Issue ioctl functions to devices. This is normally called by the + * user space syscall interfaces but can sometimes be useful for + * other purposes. The return value is the return from the syscall if + * positive or a negative errno code on error. + */ + +int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) +{ + struct ifreq ifr; + int ret; + char *colon; + + /* One special case: SIOCGIFCONF takes ifconf argument + and requires shared lock, because it sleeps writing + to user space. + */ + + if (cmd == SIOCGIFCONF) { + rtnl_lock(); + ret = dev_ifconf(net, (char __user *) arg); + rtnl_unlock(); + return ret; + } + if (cmd == SIOCGIFNAME) + return dev_ifname(net, (struct ifreq __user *)arg); + + if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + return -EFAULT; + + ifr.ifr_name[IFNAMSIZ-1] = 0; + + colon = strchr(ifr.ifr_name, ':'); + if (colon) + *colon = 0; + + /* + * See which interface the caller is talking about. + */ + + switch (cmd) { + /* + * These ioctl calls: + * - can be done by all. + * - atomic and do not require locking. + * - return a value + */ + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFHWADDR: + case SIOCGIFSLAVE: + case SIOCGIFMAP: + case SIOCGIFINDEX: + case SIOCGIFTXQLEN: + dev_load(net, ifr.ifr_name); + rcu_read_lock(); + ret = dev_ifsioc_locked(net, &ifr, cmd); + rcu_read_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + case SIOCETHTOOL: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ethtool(net, &ifr); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - return a value + */ + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSIFNAME: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - do not return a value + */ + case SIOCSIFMAP: + case SIOCSIFTXQLEN: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + /* + * These ioctl calls: + * - require local superuser power. + * - require strict serialization. + * - do not return a value + */ + case SIOCSIFFLAGS: + case SIOCSIFMETRIC: + case SIOCSIFMTU: + case SIOCSIFHWADDR: + case SIOCSIFSLAVE: + case SIOCADDMULTI: + case SIOCDELMULTI: + case SIOCSIFHWBROADCAST: + case SIOCSMIIREG: + case SIOCBONDENSLAVE: + case SIOCBONDRELEASE: + case SIOCBONDSETHWADDR: + case SIOCBONDCHANGEACTIVE: + case SIOCBRADDIF: + case SIOCBRDELIF: + case SIOCSHWTSTAMP: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + return ret; + + case SIOCGIFMEM: + /* Get the per device memory space. We can add this but + * currently do not support it */ + case SIOCSIFMEM: + /* Set the per device memory buffer space. + * Not applicable in our case */ + case SIOCSIFLINK: + return -ENOTTY; + + /* + * Unknown or private ioctl. + */ + default: + if (cmd == SIOCWANDEV || + cmd == SIOCGHWTSTAMP || + (cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15)) { + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + if (!ret && copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + return ret; + } + /* Take care of Wireless Extensions */ + if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) + return wext_handle_ioctl(net, &ifr, cmd, arg); + return -ENOTTY; + } +} diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 36e603c78ce..e70301eb7a4 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -4,6 +4,8 @@ * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> @@ -22,6 +24,7 @@ #include <linux/timer.h> #include <linux/bitops.h> #include <linux/slab.h> +#include <linux/module.h> #include <net/genetlink.h> #include <net/netevent.h> @@ -33,22 +36,19 @@ #define TRACE_ON 1 #define TRACE_OFF 0 -static void send_dm_alert(struct work_struct *unused); - - /* * Globals, our netlink socket pointer * and the work handle that will send up * netlink alerts */ static int trace_state = TRACE_OFF; -static DEFINE_SPINLOCK(trace_state_lock); +static DEFINE_MUTEX(trace_state_mutex); struct per_cpu_dm_data { - struct work_struct dm_alert_work; - struct sk_buff *skb; - atomic_t dm_hit_count; - struct timer_list send_timer; + spinlock_t lock; + struct sk_buff *skb; + struct work_struct dm_alert_work; + struct timer_list send_timer; }; struct dm_hw_stat_delta { @@ -64,7 +64,6 @@ static struct genl_family net_drop_monitor_family = { .hdrsize = 0, .name = "NET_DM", .version = 2, - .maxattr = NET_DM_CMD_MAX, }; static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); @@ -74,56 +73,64 @@ static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static LIST_HEAD(hw_stats_list); -static void reset_per_cpu_data(struct per_cpu_dm_data *data) +static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; + struct sk_buff *skb; + unsigned long flags; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); al += sizeof(struct nlattr); - data->skb = genlmsg_new(al, GFP_KERNEL); - genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family, - 0, NET_DM_CMD_ALERT); - nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg)); - msg = nla_data(nla); - memset(msg, 0, al); - atomic_set(&data->dm_hit_count, dm_hit_limit); + skb = genlmsg_new(al, GFP_KERNEL); + + if (skb) { + genlmsg_put(skb, 0, 0, &net_drop_monitor_family, + 0, NET_DM_CMD_ALERT); + nla = nla_reserve(skb, NLA_UNSPEC, + sizeof(struct net_dm_alert_msg)); + msg = nla_data(nla); + memset(msg, 0, al); + } else { + mod_timer(&data->send_timer, jiffies + HZ / 10); + } + + spin_lock_irqsave(&data->lock, flags); + swap(data->skb, skb); + spin_unlock_irqrestore(&data->lock, flags); + + return skb; } -static void send_dm_alert(struct work_struct *unused) +static struct genl_multicast_group dropmon_mcgrps[] = { + { .name = "events", }, +}; + +static void send_dm_alert(struct work_struct *work) { struct sk_buff *skb; - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); - - /* - * Grab the skb we're about to send - */ - skb = data->skb; + struct per_cpu_dm_data *data; - /* - * Replace it with a new one - */ - reset_per_cpu_data(data); + data = container_of(work, struct per_cpu_dm_data, dm_alert_work); - /* - * Ship it! - */ - genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); + skb = reset_per_cpu_data(data); + if (skb) + genlmsg_multicast(&net_drop_monitor_family, skb, 0, + 0, GFP_KERNEL); } /* * This is the timer function to delay the sending of an alert * in the event that more drops will arrive during the - * hysteresis period. Note that it operates under the timer interrupt - * so we don't need to disable preemption here + * hysteresis period. */ -static void sched_send_work(unsigned long unused) +static void sched_send_work(unsigned long _data) { - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data; schedule_work(&data->dm_alert_work); } @@ -134,17 +141,19 @@ static void trace_drop_common(struct sk_buff *skb, void *location) struct nlmsghdr *nlh; struct nlattr *nla; int i; - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct sk_buff *dskb; + struct per_cpu_dm_data *data; + unsigned long flags; + local_irq_save(flags); + data = &__get_cpu_var(dm_cpu_data); + spin_lock(&data->lock); + dskb = data->skb; - if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) { - /* - * we're already at zero, discard this hit - */ + if (!dskb) goto out; - } - nlh = (struct nlmsghdr *)data->skb->data; + nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); for (i = 0; i < msg->entries; i++) { @@ -153,11 +162,12 @@ static void trace_drop_common(struct sk_buff *skb, void *location) goto out; } } - + if (msg->entries == dm_hit_limit) + goto out; /* * We need to create a new entry */ - __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point)); + __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); msg->points[msg->entries].count = 1; @@ -165,11 +175,11 @@ static void trace_drop_common(struct sk_buff *skb, void *location) if (!timer_pending(&data->send_timer)) { data->send_timer.expires = jiffies + dm_delay * HZ; - add_timer_on(&data->send_timer, smp_processor_id()); + add_timer(&data->send_timer); } out: - return; + spin_unlock_irqrestore(&data->lock, flags); } static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location) @@ -207,21 +217,13 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi) rcu_read_unlock(); } - -static void free_dm_hw_stat(struct rcu_head *head) -{ - struct dm_hw_stat_delta *n; - n = container_of(head, struct dm_hw_stat_delta, rcu); - kfree(n); -} - static int set_all_monitor_traces(int state) { int rc = 0; struct dm_hw_stat_delta *new_stat = NULL; struct dm_hw_stat_delta *temp; - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); if (state == trace_state) { rc = -EAGAIN; @@ -230,9 +232,15 @@ static int set_all_monitor_traces(int state) switch (state) { case TRACE_ON: + if (!try_module_get(THIS_MODULE)) { + rc = -ENODEV; + break; + } + rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL); rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL); break; + case TRACE_OFF: rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL); rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL); @@ -245,9 +253,12 @@ static int set_all_monitor_traces(int state) list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) { if (new_stat->dev == NULL) { list_del_rcu(&new_stat->list); - call_rcu(&new_stat->rcu, free_dm_hw_stat); + kfree_rcu(new_stat, rcu); } } + + module_put(THIS_MODULE); + break; default: rc = 1; @@ -260,7 +271,7 @@ static int set_all_monitor_traces(int state) rc = -EINPROGRESS; out_unlock: - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); return rc; } @@ -288,9 +299,9 @@ static int net_dm_cmd_trace(struct sk_buff *skb, } static int dropmon_net_event(struct notifier_block *ev_block, - unsigned long event, void *ptr) + unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dm_hw_stat_delta *new_stat = NULL; struct dm_hw_stat_delta *tmp; @@ -303,30 +314,30 @@ static int dropmon_net_event(struct notifier_block *ev_block, new_stat->dev = dev; new_stat->last_rx = jiffies; - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); list_add_rcu(&new_stat->list, &hw_stats_list); - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); break; case NETDEV_UNREGISTER: - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { if (new_stat->dev == dev) { new_stat->dev = NULL; if (trace_state == TRACE_OFF) { list_del_rcu(&new_stat->list); - call_rcu(&new_stat->rcu, free_dm_hw_stat); + kfree_rcu(new_stat, rcu); break; } } } - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); break; } out: return NOTIFY_DONE; } -static struct genl_ops dropmon_ops[] = { +static const struct genl_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_CONFIG, .doit = net_dm_cmd_config, @@ -350,38 +361,40 @@ static int __init init_net_drop_monitor(void) struct per_cpu_dm_data *data; int cpu, rc; - printk(KERN_INFO "Initalizing network drop monitor service\n"); + pr_info("Initializing network drop monitor service\n"); if (sizeof(void *) > 8) { - printk(KERN_ERR "Unable to store program counters on this arch, Drop monitor failed\n"); + pr_err("Unable to store program counters on this arch, Drop monitor failed\n"); return -ENOSPC; } - rc = genl_register_family_with_ops(&net_drop_monitor_family, - dropmon_ops, - ARRAY_SIZE(dropmon_ops)); + rc = genl_register_family_with_ops_groups(&net_drop_monitor_family, + dropmon_ops, dropmon_mcgrps); if (rc) { - printk(KERN_ERR "Could not create drop monitor netlink family\n"); + pr_err("Could not create drop monitor netlink family\n"); return rc; } + WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { - printk(KERN_CRIT "Failed to register netdevice notifier\n"); + pr_crit("Failed to register netdevice notifier\n"); goto out_unreg; } rc = 0; - for_each_present_cpu(cpu) { + for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); - reset_per_cpu_data(data); INIT_WORK(&data->dm_alert_work, send_dm_alert); init_timer(&data->send_timer); - data->send_timer.data = cpu; + data->send_timer.data = (unsigned long)data; data->send_timer.function = sched_send_work; + spin_lock_init(&data->lock); + reset_per_cpu_data(data); } + goto out; out_unreg: @@ -390,4 +403,37 @@ out: return rc; } -late_initcall(init_net_drop_monitor); +static void exit_net_drop_monitor(void) +{ + struct per_cpu_dm_data *data; + int cpu; + + BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); + + /* + * Because of the module_get/put we do in the trace state change path + * we are guarnateed not to have any current users when we get here + * all we need to do is make sure that we don't have any running timers + * or pending schedule calls + */ + + for_each_possible_cpu(cpu) { + data = &per_cpu(dm_cpu_data, cpu); + del_timer_sync(&data->send_timer); + cancel_work_sync(&data->dm_alert_work); + /* + * At this point, we should have exclusive access + * to this struct and can free the skb inside it + */ + kfree_skb(data->skb); + } + + BUG_ON(genl_unregister_family(&net_drop_monitor_family)); +} + +module_init(init_net_drop_monitor); +module_exit(exit_net_drop_monitor); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); +MODULE_ALIAS_GENL_FAMILY("NET_DM"); diff --git a/net/core/dst.c b/net/core/dst.c index b99c7c7ffce..a028409ee43 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -19,6 +19,7 @@ #include <linux/types.h> #include <net/net_namespace.h> #include <linux/sched.h> +#include <linux/prefetch.h> #include <net/dst.h> @@ -33,9 +34,6 @@ * 3) This list is guarded by a mutex, * so that the gc_task and dst_dev_event() can be synchronized. */ -#if RT_CACHE_DEBUG >= 2 -static atomic_t dst_total = ATOMIC_INIT(0); -#endif /* * We want to keep lock & list close together @@ -69,10 +67,6 @@ static void dst_gc_task(struct work_struct *work) unsigned long expires = ~0L; struct dst_entry *dst, *next, head; struct dst_entry *last = &head; -#if RT_CACHE_DEBUG >= 2 - ktime_t time_start = ktime_get(); - struct timespec elapsed; -#endif mutex_lock(&dst_gc_mutex); next = dst_busy_list; @@ -100,7 +94,7 @@ loop: * But we do not have state "obsoleted, but * referenced by parent", so it is right. */ - if (dst->obsolete > 1) + if (dst->obsolete > 0) continue; ___dst_free(dst); @@ -146,25 +140,27 @@ loop: spin_unlock_bh(&dst_garbage.lock); mutex_unlock(&dst_gc_mutex); -#if RT_CACHE_DEBUG >= 2 - elapsed = ktime_to_timespec(ktime_sub(ktime_get(), time_start)); - printk(KERN_DEBUG "dst_total: %d delayed: %d work_perf: %d" - " expires: %lu elapsed: %lu us\n", - atomic_read(&dst_total), delayed, work_performed, - expires, - elapsed.tv_sec * USEC_PER_SEC + - elapsed.tv_nsec / NSEC_PER_USEC); -#endif } -int dst_discard(struct sk_buff *skb) +int dst_discard_sk(struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } -EXPORT_SYMBOL(dst_discard); +EXPORT_SYMBOL(dst_discard_sk); -void *dst_alloc(struct dst_ops *ops) +const u32 dst_default_metrics[RTAX_MAX + 1] = { + /* This initializer is needed to force linker to place this variable + * into const section. Otherwise it might end into bss section. + * We really want to avoid false sharing on this variable, and catch + * any writes on it. + */ + [RTAX_MAX] = 0xdeadbeef, +}; + + +void *dst_alloc(struct dst_ops *ops, struct net_device *dev, + int initial_ref, int initial_obsolete, unsigned short flags) { struct dst_entry *dst; @@ -172,18 +168,38 @@ void *dst_alloc(struct dst_ops *ops) if (ops->gc(ops)) return NULL; } - dst = kmem_cache_zalloc(ops->kmem_cachep, GFP_ATOMIC); + dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) return NULL; - atomic_set(&dst->__refcnt, 0); + dst->child = NULL; + dst->dev = dev; + if (dev) + dev_hold(dev); dst->ops = ops; - dst->lastuse = jiffies; + dst_init_metrics(dst, dst_default_metrics, true); + dst->expires = 0UL; dst->path = dst; - dst->input = dst->output = dst_discard; -#if RT_CACHE_DEBUG >= 2 - atomic_inc(&dst_total); + dst->from = NULL; +#ifdef CONFIG_XFRM + dst->xfrm = NULL; +#endif + dst->input = dst_discard; + dst->output = dst_discard_sk; + dst->error = 0; + dst->obsolete = initial_obsolete; + dst->header_len = 0; + dst->trailer_len = 0; +#ifdef CONFIG_IP_ROUTE_CLASSID + dst->tclassid = 0; #endif - dst_entries_add(ops, 1); + atomic_set(&dst->__refcnt, initial_ref); + dst->__use = 0; + dst->lastuse = jiffies; + dst->flags = flags; + dst->pending_confirm = 0; + dst->next = NULL; + if (!(flags & DST_NOCOUNT)) + dst_entries_add(ops, 1); return dst; } EXPORT_SYMBOL(dst_alloc); @@ -193,9 +209,11 @@ static void ___dst_free(struct dst_entry *dst) /* The first case (dev==NULL) is required, when protocol module is unloaded. */ - if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) - dst->input = dst->output = dst_discard; - dst->obsolete = 2; + if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { + dst->input = dst_discard; + dst->output = dst_discard_sk; + } + dst->obsolete = DST_OBSOLETE_DEAD; } void __dst_free(struct dst_entry *dst) @@ -207,8 +225,8 @@ void __dst_free(struct dst_entry *dst) if (dst_garbage.timer_inc > DST_GC_INC) { dst_garbage.timer_inc = DST_GC_INC; dst_garbage.timer_expires = DST_GC_MIN; - cancel_delayed_work(&dst_gc_work); - schedule_delayed_work(&dst_gc_work, dst_garbage.timer_expires); + mod_delayed_work(system_wq, &dst_gc_work, + dst_garbage.timer_expires); } spin_unlock_bh(&dst_garbage.lock); } @@ -217,34 +235,19 @@ EXPORT_SYMBOL(__dst_free); struct dst_entry *dst_destroy(struct dst_entry * dst) { struct dst_entry *child; - struct neighbour *neigh; - struct hh_cache *hh; smp_rmb(); again: - neigh = dst->neighbour; - hh = dst->hh; child = dst->child; - dst->hh = NULL; - if (hh) - hh_cache_put(hh); - - if (neigh) { - dst->neighbour = NULL; - neigh_release(neigh); - } - - dst_entries_add(dst->ops, -1); + if (!(dst->flags & DST_NOCOUNT)) + dst_entries_add(dst->ops, -1); if (dst->ops->destroy) dst->ops->destroy(dst); if (dst->dev) dev_put(dst->dev); -#if RT_CACHE_DEBUG >= 2 - atomic_dec(&dst_total); -#endif kmem_cache_free(dst->ops->kmem_cachep, dst); dst = child; @@ -266,6 +269,15 @@ again: } EXPORT_SYMBOL(dst_destroy); +static void dst_destroy_rcu(struct rcu_head *head) +{ + struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); + + dst = dst_destroy(dst); + if (dst) + __dst_free(dst); +} + void dst_release(struct dst_entry *dst) { if (dst) { @@ -273,37 +285,71 @@ void dst_release(struct dst_entry *dst) newrefcnt = atomic_dec_return(&dst->__refcnt); WARN_ON(newrefcnt < 0); - if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) { - dst = dst_destroy(dst); - if (dst) - __dst_free(dst); - } + if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) + call_rcu(&dst->rcu_head, dst_destroy_rcu); } } EXPORT_SYMBOL(dst_release); +u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) +{ + u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC); + + if (p) { + u32 *old_p = __DST_METRICS_PTR(old); + unsigned long prev, new; + + memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + kfree(p); + p = __DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } + } + return p; +} +EXPORT_SYMBOL(dst_cow_metrics_generic); + +/* Caller asserts that dst_metrics_read_only(dst) is false. */ +void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) +{ + unsigned long prev, new; + + new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY; + prev = cmpxchg(&dst->_metrics, old, new); + if (prev == old) + kfree(__DST_METRICS_PTR(old)); +} +EXPORT_SYMBOL(__dst_destroy_metrics_generic); + /** - * skb_dst_set_noref - sets skb dst, without a reference + * __skb_dst_set_noref - sets skb dst, without a reference * @skb: buffer * @dst: dst entry + * @force: if force is set, use noref version even for DST_NOCACHE entries * * Sets skb dst, assuming a reference was not taken on dst * skb_dst_drop() should not dst_release() this dst */ -void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) +void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst, bool force) { WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); /* If dst not in cache, we must take a reference, because * dst_release() will destroy dst as soon as its refcount becomes zero */ - if (unlikely(dst->flags & DST_NOCACHE)) { + if (unlikely((dst->flags & DST_NOCACHE) && !force)) { dst_hold(dst); skb_dst_set(skb, dst); } else { skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } } -EXPORT_SYMBOL(skb_dst_set_noref); +EXPORT_SYMBOL(__skb_dst_set_noref); /* Dirty hack. We did it in 2.2 (in __dst_free), * we have _very_ good reasons not to repeat @@ -323,27 +369,23 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, return; if (!unregister) { - dst->input = dst->output = dst_discard; + dst->input = dst_discard; + dst->output = dst_discard_sk; } else { dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); dev_put(dev); - if (dst->neighbour && dst->neighbour->dev == dev) { - dst->neighbour->dev = dst->dev; - dev_hold(dst->dev); - dev_put(dev); - } } } static int dst_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dst_entry *dst, *last = NULL; switch (event) { - case NETDEV_UNREGISTER: + case NETDEV_UNREGISTER_FINAL: case NETDEV_DOWN: mutex_lock(&dst_gc_mutex); for (dst = dst_busy_list; dst; dst = dst->next) { diff --git a/net/core/ethtool.c b/net/core/ethtool.c index d5bc2881888..17cb912793f 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -17,10 +17,14 @@ #include <linux/errno.h> #include <linux/ethtool.h> #include <linux/netdevice.h> +#include <linux/net_tstamp.h> +#include <linux/phy.h> #include <linux/bitops.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/slab.h> +#include <linux/rtnetlink.h> +#include <linux/sched.h> /* * Some useful ethtool_ops methods that're device independent. @@ -34,152 +38,315 @@ u32 ethtool_op_get_link(struct net_device *dev) } EXPORT_SYMBOL(ethtool_op_get_link); -u32 ethtool_op_get_rx_csum(struct net_device *dev) +int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { - return (dev->features & NETIF_F_ALL_CSUM) != 0; + info->so_timestamping = + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info->phc_index = -1; + return 0; } -EXPORT_SYMBOL(ethtool_op_get_rx_csum); +EXPORT_SYMBOL(ethtool_op_get_ts_info); -u32 ethtool_op_get_tx_csum(struct net_device *dev) -{ - return (dev->features & NETIF_F_ALL_CSUM) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_tx_csum); +/* Handlers for each ethtool command */ -int ethtool_op_set_tx_csum(struct net_device *dev, u32 data) +#define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32) + +static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { + [NETIF_F_SG_BIT] = "tx-scatter-gather", + [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4", + [NETIF_F_HW_CSUM_BIT] = "tx-checksum-ip-generic", + [NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6", + [NETIF_F_HIGHDMA_BIT] = "highdma", + [NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist", + [NETIF_F_HW_VLAN_CTAG_TX_BIT] = "tx-vlan-hw-insert", + + [NETIF_F_HW_VLAN_CTAG_RX_BIT] = "rx-vlan-hw-parse", + [NETIF_F_HW_VLAN_CTAG_FILTER_BIT] = "rx-vlan-filter", + [NETIF_F_HW_VLAN_STAG_TX_BIT] = "tx-vlan-stag-hw-insert", + [NETIF_F_HW_VLAN_STAG_RX_BIT] = "rx-vlan-stag-hw-parse", + [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter", + [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", + [NETIF_F_GSO_BIT] = "tx-generic-segmentation", + [NETIF_F_LLTX_BIT] = "tx-lockless", + [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", + [NETIF_F_GRO_BIT] = "rx-gro", + [NETIF_F_LRO_BIT] = "rx-lro", + + [NETIF_F_TSO_BIT] = "tx-tcp-segmentation", + [NETIF_F_UFO_BIT] = "tx-udp-fragmentation", + [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust", + [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", + [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", + [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", + [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", + [NETIF_F_GSO_IPIP_BIT] = "tx-ipip-segmentation", + [NETIF_F_GSO_SIT_BIT] = "tx-sit-segmentation", + [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", + [NETIF_F_GSO_MPLS_BIT] = "tx-mpls-segmentation", + + [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", + [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp", + [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", + [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", + [NETIF_F_RXHASH_BIT] = "rx-hashing", + [NETIF_F_RXCSUM_BIT] = "rx-checksum", + [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy", + [NETIF_F_LOOPBACK_BIT] = "loopback", + [NETIF_F_RXFCS_BIT] = "rx-fcs", + [NETIF_F_RXALL_BIT] = "rx-all", + [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", + [NETIF_F_BUSY_POLL_BIT] = "busy-poll", +}; + +static int ethtool_get_features(struct net_device *dev, void __user *useraddr) { - if (data) - dev->features |= NETIF_F_IP_CSUM; - else - dev->features &= ~NETIF_F_IP_CSUM; + struct ethtool_gfeatures cmd = { + .cmd = ETHTOOL_GFEATURES, + .size = ETHTOOL_DEV_FEATURE_WORDS, + }; + struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; + u32 __user *sizeaddr; + u32 copy_size; + int i; + + /* in case feature bits run out again */ + BUILD_BUG_ON(ETHTOOL_DEV_FEATURE_WORDS * sizeof(u32) > sizeof(netdev_features_t)); + + for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) { + features[i].available = (u32)(dev->hw_features >> (32 * i)); + features[i].requested = (u32)(dev->wanted_features >> (32 * i)); + features[i].active = (u32)(dev->features >> (32 * i)); + features[i].never_changed = + (u32)(NETIF_F_NEVER_CHANGE >> (32 * i)); + } - return 0; -} + sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size); + if (get_user(copy_size, sizeaddr)) + return -EFAULT; -int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_HW_CSUM; - else - dev->features &= ~NETIF_F_HW_CSUM; + if (copy_size > ETHTOOL_DEV_FEATURE_WORDS) + copy_size = ETHTOOL_DEV_FEATURE_WORDS; + + if (copy_to_user(useraddr, &cmd, sizeof(cmd))) + return -EFAULT; + useraddr += sizeof(cmd); + if (copy_to_user(useraddr, features, copy_size * sizeof(*features))) + return -EFAULT; return 0; } -EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum); -int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data) +static int ethtool_set_features(struct net_device *dev, void __user *useraddr) { - if (data) - dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; - else - dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); + struct ethtool_sfeatures cmd; + struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; + netdev_features_t wanted = 0, valid = 0; + int i, ret = 0; - return 0; + if (copy_from_user(&cmd, useraddr, sizeof(cmd))) + return -EFAULT; + useraddr += sizeof(cmd); + + if (cmd.size != ETHTOOL_DEV_FEATURE_WORDS) + return -EINVAL; + + if (copy_from_user(features, useraddr, sizeof(features))) + return -EFAULT; + + for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) { + valid |= (netdev_features_t)features[i].valid << (32 * i); + wanted |= (netdev_features_t)features[i].requested << (32 * i); + } + + if (valid & ~NETIF_F_ETHTOOL_BITS) + return -EINVAL; + + if (valid & ~dev->hw_features) { + valid &= dev->hw_features; + ret |= ETHTOOL_F_UNSUPPORTED; + } + + dev->wanted_features &= ~valid; + dev->wanted_features |= wanted & valid; + __netdev_update_features(dev); + + if ((dev->wanted_features ^ dev->features) & valid) + ret |= ETHTOOL_F_WISH; + + return ret; } -EXPORT_SYMBOL(ethtool_op_set_tx_ipv6_csum); -u32 ethtool_op_get_sg(struct net_device *dev) +static int __ethtool_get_sset_count(struct net_device *dev, int sset) { - return (dev->features & NETIF_F_SG) != 0; + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (sset == ETH_SS_FEATURES) + return ARRAY_SIZE(netdev_features_strings); + + if (ops->get_sset_count && ops->get_strings) + return ops->get_sset_count(dev, sset); + else + return -EOPNOTSUPP; } -EXPORT_SYMBOL(ethtool_op_get_sg); -int ethtool_op_set_sg(struct net_device *dev, u32 data) +static void __ethtool_get_strings(struct net_device *dev, + u32 stringset, u8 *data) { - if (data) - dev->features |= NETIF_F_SG; - else - dev->features &= ~NETIF_F_SG; + const struct ethtool_ops *ops = dev->ethtool_ops; - return 0; + if (stringset == ETH_SS_FEATURES) + memcpy(data, netdev_features_strings, + sizeof(netdev_features_strings)); + else + /* ops->get_strings is valid because checked earlier */ + ops->get_strings(dev, stringset, data); } -EXPORT_SYMBOL(ethtool_op_set_sg); -u32 ethtool_op_get_tso(struct net_device *dev) +static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd) { - return (dev->features & NETIF_F_TSO) != 0; + /* feature masks of legacy discrete ethtool ops */ + + switch (eth_cmd) { + case ETHTOOL_GTXCSUM: + case ETHTOOL_STXCSUM: + return NETIF_F_ALL_CSUM | NETIF_F_SCTP_CSUM; + case ETHTOOL_GRXCSUM: + case ETHTOOL_SRXCSUM: + return NETIF_F_RXCSUM; + case ETHTOOL_GSG: + case ETHTOOL_SSG: + return NETIF_F_SG; + case ETHTOOL_GTSO: + case ETHTOOL_STSO: + return NETIF_F_ALL_TSO; + case ETHTOOL_GUFO: + case ETHTOOL_SUFO: + return NETIF_F_UFO; + case ETHTOOL_GGSO: + case ETHTOOL_SGSO: + return NETIF_F_GSO; + case ETHTOOL_GGRO: + case ETHTOOL_SGRO: + return NETIF_F_GRO; + default: + BUG(); + } } -EXPORT_SYMBOL(ethtool_op_get_tso); -int ethtool_op_set_tso(struct net_device *dev, u32 data) +static int ethtool_get_one_feature(struct net_device *dev, + char __user *useraddr, u32 ethcmd) { - if (data) - dev->features |= NETIF_F_TSO; - else - dev->features &= ~NETIF_F_TSO; + netdev_features_t mask = ethtool_get_feature_mask(ethcmd); + struct ethtool_value edata = { + .cmd = ethcmd, + .data = !!(dev->features & mask), + }; + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; return 0; } -EXPORT_SYMBOL(ethtool_op_set_tso); -u32 ethtool_op_get_ufo(struct net_device *dev) +static int ethtool_set_one_feature(struct net_device *dev, + void __user *useraddr, u32 ethcmd) { - return (dev->features & NETIF_F_UFO) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_ufo); + struct ethtool_value edata; + netdev_features_t mask; -int ethtool_op_set_ufo(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_UFO; + if (copy_from_user(&edata, useraddr, sizeof(edata))) + return -EFAULT; + + mask = ethtool_get_feature_mask(ethcmd); + mask &= dev->hw_features; + if (!mask) + return -EOPNOTSUPP; + + if (edata.data) + dev->wanted_features |= mask; else - dev->features &= ~NETIF_F_UFO; + dev->wanted_features &= ~mask; + + __netdev_update_features(dev); + return 0; } -EXPORT_SYMBOL(ethtool_op_set_ufo); -/* the following list of flags are the same as their associated - * NETIF_F_xxx values in include/linux/netdevice.h - */ -static const u32 flags_dup_features = - (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | ETH_FLAG_NTUPLE | - ETH_FLAG_RXHASH); +#define ETH_ALL_FLAGS (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | \ + ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH) +#define ETH_ALL_FEATURES (NETIF_F_LRO | NETIF_F_HW_VLAN_CTAG_RX | \ + NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_NTUPLE | \ + NETIF_F_RXHASH) -u32 ethtool_op_get_flags(struct net_device *dev) +static u32 __ethtool_get_flags(struct net_device *dev) { - /* in the future, this function will probably contain additional - * handling for flags which are not so easily handled - * by a simple masking operation - */ - - return dev->features & flags_dup_features; + u32 flags = 0; + + if (dev->features & NETIF_F_LRO) + flags |= ETH_FLAG_LRO; + if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) + flags |= ETH_FLAG_RXVLAN; + if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) + flags |= ETH_FLAG_TXVLAN; + if (dev->features & NETIF_F_NTUPLE) + flags |= ETH_FLAG_NTUPLE; + if (dev->features & NETIF_F_RXHASH) + flags |= ETH_FLAG_RXHASH; + + return flags; } -EXPORT_SYMBOL(ethtool_op_get_flags); -int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported) +static int __ethtool_set_flags(struct net_device *dev, u32 data) { - if (data & ~supported) + netdev_features_t features = 0, changed; + + if (data & ~ETH_ALL_FLAGS) return -EINVAL; - dev->features = ((dev->features & ~flags_dup_features) | - (data & flags_dup_features)); + if (data & ETH_FLAG_LRO) + features |= NETIF_F_LRO; + if (data & ETH_FLAG_RXVLAN) + features |= NETIF_F_HW_VLAN_CTAG_RX; + if (data & ETH_FLAG_TXVLAN) + features |= NETIF_F_HW_VLAN_CTAG_TX; + if (data & ETH_FLAG_NTUPLE) + features |= NETIF_F_NTUPLE; + if (data & ETH_FLAG_RXHASH) + features |= NETIF_F_RXHASH; + + /* allow changing only bits set in hw_features */ + changed = (features ^ dev->features) & ETH_ALL_FEATURES; + if (changed & ~dev->hw_features) + return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP; + + dev->wanted_features = + (dev->wanted_features & ~changed) | (features & changed); + + __netdev_update_features(dev); + return 0; } -EXPORT_SYMBOL(ethtool_op_set_flags); -void ethtool_ntuple_flush(struct net_device *dev) +int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { - struct ethtool_rx_ntuple_flow_spec_container *fsc, *f; + ASSERT_RTNL(); - list_for_each_entry_safe(fsc, f, &dev->ethtool_ntuple_list.list, list) { - list_del(&fsc->list); - kfree(fsc); - } - dev->ethtool_ntuple_list.count = 0; -} -EXPORT_SYMBOL(ethtool_ntuple_flush); + if (!dev->ethtool_ops->get_settings) + return -EOPNOTSUPP; -/* Handlers for each ethtool command */ + memset(cmd, 0, sizeof(struct ethtool_cmd)); + cmd->cmd = ETHTOOL_GSET; + return dev->ethtool_ops->get_settings(dev, cmd); +} +EXPORT_SYMBOL(__ethtool_get_settings); static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { - struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET }; int err; + struct ethtool_cmd cmd; - if (!dev->ethtool_ops->get_settings) - return -EOPNOTSUPP; - - err = dev->ethtool_ops->get_settings(dev, &cmd); + err = __ethtool_get_settings(dev, &cmd); if (err < 0) return err; @@ -209,7 +376,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GDRVINFO; - if (ops && ops->get_drvinfo) { + if (ops->get_drvinfo) { ops->get_drvinfo(dev, &info); } else if (dev->dev.parent && dev->dev.parent->driver) { strlcpy(info.bus_info, dev_name(dev->dev.parent), @@ -224,7 +391,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, * this method of obtaining string set info is deprecated; * Use ETHTOOL_GSSET_INFO instead. */ - if (ops && ops->get_sset_count) { + if (ops->get_sset_count) { int rc; rc = ops->get_sset_count(dev, ETH_SS_TEST); @@ -237,9 +404,9 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (rc >= 0) info.n_priv_flags = rc; } - if (ops && ops->get_regs_len) + if (ops->get_regs_len) info.regdump_len = ops->get_regs_len(dev); - if (ops && ops->get_eeprom_len) + if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); if (copy_to_user(useraddr, &info, sizeof(info))) @@ -251,14 +418,10 @@ static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev, void __user *useraddr) { struct ethtool_sset_info info; - const struct ethtool_ops *ops = dev->ethtool_ops; u64 sset_mask; int i, idx = 0, n_bits = 0, ret, rc; u32 *info_buf = NULL; - if (!ops->get_sset_count) - return -EOPNOTSUPP; - if (copy_from_user(&info, useraddr, sizeof(info))) return -EFAULT; @@ -285,7 +448,7 @@ static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev, if (!(sset_mask & (1ULL << i))) continue; - rc = ops->get_sset_count(dev, i); + rc = __ethtool_get_sset_count(dev, i); if (rc >= 0) { info.sset_mask |= (1ULL << i); info_buf[idx++] = rc; @@ -312,6 +475,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, { struct ethtool_rxnfc info; size_t info_size = sizeof(info); + int rc; if (!dev->ethtool_ops->set_rxnfc) return -EOPNOTSUPP; @@ -327,7 +491,15 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, if (copy_from_user(&info, useraddr, info_size)) return -EFAULT; - return dev->ethtool_ops->set_rxnfc(dev, &info); + rc = dev->ethtool_ops->set_rxnfc(dev, &info); + if (rc) + return rc; + + if (cmd == ETHTOOL_SRXCLSRLINS && + copy_to_user(useraddr, &info, info_size)) + return -EFAULT; + + return 0; } static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, @@ -385,37 +557,64 @@ err_out: return ret; } +static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr, + struct ethtool_rxnfc *rx_rings, + u32 size) +{ + int i; + + if (copy_from_user(indir, useraddr, size * sizeof(indir[0]))) + return -EFAULT; + + /* Validate ring indices */ + for (i = 0; i < size; i++) + if (indir[i] >= rx_rings->data) + return -EINVAL; + + return 0; +} + static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, void __user *useraddr) { - struct ethtool_rxfh_indir *indir; - u32 table_size; - size_t full_size; + u32 user_size, dev_size; + u32 *indir; int ret; - if (!dev->ethtool_ops->get_rxfh_indir) + if (!dev->ethtool_ops->get_rxfh_indir_size || + !dev->ethtool_ops->get_rxfh) + return -EOPNOTSUPP; + dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); + if (dev_size == 0) return -EOPNOTSUPP; - if (copy_from_user(&table_size, + if (copy_from_user(&user_size, useraddr + offsetof(struct ethtool_rxfh_indir, size), - sizeof(table_size))) + sizeof(user_size))) return -EFAULT; - if (table_size > - (KMALLOC_MAX_SIZE - sizeof(*indir)) / sizeof(*indir->ring_index)) - return -ENOMEM; - full_size = sizeof(*indir) + sizeof(*indir->ring_index) * table_size; - indir = kzalloc(full_size, GFP_USER); + if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, size), + &dev_size, sizeof(dev_size))) + return -EFAULT; + + /* If the user buffer size is 0, this is just a query for the + * device table size. Otherwise, if it's smaller than the + * device table size it's an error. + */ + if (user_size < dev_size) + return user_size == 0 ? 0 : -EINVAL; + + indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); if (!indir) return -ENOMEM; - indir->cmd = ETHTOOL_GRXFHINDIR; - indir->size = table_size; - ret = dev->ethtool_ops->get_rxfh_indir(dev, indir); + ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL); if (ret) goto out; - if (copy_to_user(useraddr, indir, full_size)) + if (copy_to_user(useraddr + + offsetof(struct ethtool_rxfh_indir, ring_index[0]), + indir, dev_size * sizeof(indir[0]))) ret = -EFAULT; out: @@ -426,377 +625,220 @@ out: static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, void __user *useraddr) { - struct ethtool_rxfh_indir *indir; - u32 table_size; - size_t full_size; + struct ethtool_rxnfc rx_rings; + u32 user_size, dev_size, i; + u32 *indir; + const struct ethtool_ops *ops = dev->ethtool_ops; int ret; + u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]); + + if (!ops->get_rxfh_indir_size || !ops->set_rxfh || + !ops->get_rxnfc) + return -EOPNOTSUPP; - if (!dev->ethtool_ops->set_rxfh_indir) + dev_size = ops->get_rxfh_indir_size(dev); + if (dev_size == 0) return -EOPNOTSUPP; - if (copy_from_user(&table_size, + if (copy_from_user(&user_size, useraddr + offsetof(struct ethtool_rxfh_indir, size), - sizeof(table_size))) + sizeof(user_size))) return -EFAULT; - if (table_size > - (KMALLOC_MAX_SIZE - sizeof(*indir)) / sizeof(*indir->ring_index)) - return -ENOMEM; - full_size = sizeof(*indir) + sizeof(*indir->ring_index) * table_size; - indir = kmalloc(full_size, GFP_USER); + if (user_size != 0 && user_size != dev_size) + return -EINVAL; + + indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); if (!indir) return -ENOMEM; - if (copy_from_user(indir, useraddr, full_size)) { - ret = -EFAULT; + rx_rings.cmd = ETHTOOL_GRXRINGS; + ret = ops->get_rxnfc(dev, &rx_rings, NULL); + if (ret) goto out; + + if (user_size == 0) { + for (i = 0; i < dev_size; i++) + indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data); + } else { + ret = ethtool_copy_validate_indir(indir, + useraddr + ringidx_offset, + &rx_rings, + dev_size); + if (ret) + goto out; } - ret = dev->ethtool_ops->set_rxfh_indir(dev, indir); + ret = ops->set_rxfh(dev, indir, NULL); out: kfree(indir); return ret; } -static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, - struct ethtool_rx_ntuple_flow_spec *spec, - struct ethtool_rx_ntuple_flow_spec_container *fsc) +static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, + void __user *useraddr) { + int ret; + const struct ethtool_ops *ops = dev->ethtool_ops; + u32 user_indir_size, user_key_size; + u32 dev_indir_size = 0, dev_key_size = 0; + struct ethtool_rxfh rxfh; + u32 total_size; + u32 indir_bytes; + u32 *indir = NULL; + u8 *hkey = NULL; + u8 *rss_config; + + if (!(dev->ethtool_ops->get_rxfh_indir_size || + dev->ethtool_ops->get_rxfh_key_size) || + !dev->ethtool_ops->get_rxfh) + return -EOPNOTSUPP; - /* don't add filters forever */ - if (list->count >= ETHTOOL_MAX_NTUPLE_LIST_ENTRY) { - /* free the container */ - kfree(fsc); - return; - } + if (ops->get_rxfh_indir_size) + dev_indir_size = ops->get_rxfh_indir_size(dev); + if (ops->get_rxfh_key_size) + dev_key_size = ops->get_rxfh_key_size(dev); - /* Copy the whole filter over */ - fsc->fs.flow_type = spec->flow_type; - memcpy(&fsc->fs.h_u, &spec->h_u, sizeof(spec->h_u)); - memcpy(&fsc->fs.m_u, &spec->m_u, sizeof(spec->m_u)); + if ((dev_key_size + dev_indir_size) == 0) + return -EOPNOTSUPP; - fsc->fs.vlan_tag = spec->vlan_tag; - fsc->fs.vlan_tag_mask = spec->vlan_tag_mask; - fsc->fs.data = spec->data; - fsc->fs.data_mask = spec->data_mask; - fsc->fs.action = spec->action; + if (copy_from_user(&rxfh, useraddr, sizeof(rxfh))) + return -EFAULT; + user_indir_size = rxfh.indir_size; + user_key_size = rxfh.key_size; - /* add to the list */ - list_add_tail_rcu(&fsc->list, &list->list); - list->count++; -} + /* Check that reserved fields are 0 for now */ + if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1]) + return -EINVAL; -/* - * ethtool does not (or did not) set masks for flow parameters that are - * not specified, so if both value and mask are 0 then this must be - * treated as equivalent to a mask with all bits set. Implement that - * here rather than in drivers. - */ -static void rx_ntuple_fix_masks(struct ethtool_rx_ntuple_flow_spec *fs) -{ - struct ethtool_tcpip4_spec *entry = &fs->h_u.tcp_ip4_spec; - struct ethtool_tcpip4_spec *mask = &fs->m_u.tcp_ip4_spec; - - if (fs->flow_type != TCP_V4_FLOW && - fs->flow_type != UDP_V4_FLOW && - fs->flow_type != SCTP_V4_FLOW) - return; - - if (!(entry->ip4src | mask->ip4src)) - mask->ip4src = htonl(0xffffffff); - if (!(entry->ip4dst | mask->ip4dst)) - mask->ip4dst = htonl(0xffffffff); - if (!(entry->psrc | mask->psrc)) - mask->psrc = htons(0xffff); - if (!(entry->pdst | mask->pdst)) - mask->pdst = htons(0xffff); - if (!(entry->tos | mask->tos)) - mask->tos = 0xff; - if (!(fs->vlan_tag | fs->vlan_tag_mask)) - fs->vlan_tag_mask = 0xffff; - if (!(fs->data | fs->data_mask)) - fs->data_mask = 0xffffffffffffffffULL; -} + rxfh.indir_size = dev_indir_size; + rxfh.key_size = dev_key_size; + if (copy_to_user(useraddr, &rxfh, sizeof(rxfh))) + return -EFAULT; -static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, - void __user *useraddr) -{ - struct ethtool_rx_ntuple cmd; - const struct ethtool_ops *ops = dev->ethtool_ops; - struct ethtool_rx_ntuple_flow_spec_container *fsc = NULL; - int ret; + /* If the user buffer size is 0, this is just a query for the + * device table size and key size. Otherwise, if the User size is + * not equal to device table size or key size it's an error. + */ + if (!user_indir_size && !user_key_size) + return 0; - if (!(dev->features & NETIF_F_NTUPLE)) + if ((user_indir_size && (user_indir_size != dev_indir_size)) || + (user_key_size && (user_key_size != dev_key_size))) return -EINVAL; - if (copy_from_user(&cmd, useraddr, sizeof(cmd))) - return -EFAULT; + indir_bytes = user_indir_size * sizeof(indir[0]); + total_size = indir_bytes + user_key_size; + rss_config = kzalloc(total_size, GFP_USER); + if (!rss_config) + return -ENOMEM; - rx_ntuple_fix_masks(&cmd.fs); + if (user_indir_size) + indir = (u32 *)rss_config; - /* - * Cache filter in dev struct for GET operation only if - * the underlying driver doesn't have its own GET operation, and - * only if the filter was added successfully. First make sure we - * can allocate the filter, then continue if successful. - */ - if (!ops->get_rx_ntuple) { - fsc = kmalloc(sizeof(*fsc), GFP_ATOMIC); - if (!fsc) - return -ENOMEM; - } + if (user_key_size) + hkey = rss_config + indir_bytes; - ret = ops->set_rx_ntuple(dev, &cmd); - if (ret) { - kfree(fsc); - return ret; + ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey); + if (!ret) { + if (copy_to_user(useraddr + + offsetof(struct ethtool_rxfh, rss_config[0]), + rss_config, total_size)) + ret = -EFAULT; } - if (!ops->get_rx_ntuple) - __rx_ntuple_filter_add(&dev->ethtool_ntuple_list, &cmd.fs, fsc); + kfree(rss_config); return ret; } -static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, + void __user *useraddr) { - struct ethtool_gstrings gstrings; + int ret; const struct ethtool_ops *ops = dev->ethtool_ops; - struct ethtool_rx_ntuple_flow_spec_container *fsc; - u8 *data; - char *p; - int ret, i, num_strings = 0; + struct ethtool_rxnfc rx_rings; + struct ethtool_rxfh rxfh; + u32 dev_indir_size = 0, dev_key_size = 0, i; + u32 *indir = NULL, indir_bytes = 0; + u8 *hkey = NULL; + u8 *rss_config; + u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]); + + if (!(ops->get_rxfh_indir_size || ops->get_rxfh_key_size) || + !ops->get_rxnfc || !ops->set_rxfh) + return -EOPNOTSUPP; - if (!ops->get_sset_count) + if (ops->get_rxfh_indir_size) + dev_indir_size = ops->get_rxfh_indir_size(dev); + if (ops->get_rxfh_key_size) + dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev); + if ((dev_key_size + dev_indir_size) == 0) return -EOPNOTSUPP; - if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) + if (copy_from_user(&rxfh, useraddr, sizeof(rxfh))) return -EFAULT; - ret = ops->get_sset_count(dev, gstrings.string_set); - if (ret < 0) - return ret; + /* Check that reserved fields are 0 for now */ + if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1]) + return -EINVAL; - gstrings.len = ret; + /* If either indir or hash key is valid, proceed further. + * It is not valid to request that both be unchanged. + */ + if ((rxfh.indir_size && + rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE && + rxfh.indir_size != dev_indir_size) || + (rxfh.key_size && (rxfh.key_size != dev_key_size)) || + (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE && + rxfh.key_size == 0)) + return -EINVAL; - data = kzalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); - if (!data) + if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) + indir_bytes = dev_indir_size * sizeof(indir[0]); + + rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER); + if (!rss_config) return -ENOMEM; - if (ops->get_rx_ntuple) { - /* driver-specific filter grab */ - ret = ops->get_rx_ntuple(dev, gstrings.string_set, data); - goto copy; - } + rx_rings.cmd = ETHTOOL_GRXRINGS; + ret = ops->get_rxnfc(dev, &rx_rings, NULL); + if (ret) + goto out; - /* default ethtool filter grab */ - i = 0; - p = (char *)data; - list_for_each_entry(fsc, &dev->ethtool_ntuple_list.list, list) { - sprintf(p, "Filter %d:\n", i); - p += ETH_GSTRING_LEN; - num_strings++; - - switch (fsc->fs.flow_type) { - case TCP_V4_FLOW: - sprintf(p, "\tFlow Type: TCP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case UDP_V4_FLOW: - sprintf(p, "\tFlow Type: UDP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case SCTP_V4_FLOW: - sprintf(p, "\tFlow Type: SCTP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case AH_ESP_V4_FLOW: - sprintf(p, "\tFlow Type: AH ESP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case ESP_V4_FLOW: - sprintf(p, "\tFlow Type: ESP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IP_USER_FLOW: - sprintf(p, "\tFlow Type: Raw IP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IPV4_FLOW: - sprintf(p, "\tFlow Type: IPv4\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - default: - sprintf(p, "\tFlow Type: Unknown\n"); - p += ETH_GSTRING_LEN; - num_strings++; - goto unknown_filter; - } + /* rxfh.indir_size == 0 means reset the indir table to default. + * rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE means leave it unchanged. + */ + if (rxfh.indir_size && + rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) { + indir = (u32 *)rss_config; + ret = ethtool_copy_validate_indir(indir, + useraddr + rss_cfg_offset, + &rx_rings, + rxfh.indir_size); + if (ret) + goto out; + } else if (rxfh.indir_size == 0) { + indir = (u32 *)rss_config; + for (i = 0; i < dev_indir_size; i++) + indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data); + } - /* now the rest of the filters */ - switch (fsc->fs.flow_type) { - case TCP_V4_FLOW: - case UDP_V4_FLOW: - case SCTP_V4_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.tcp_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.tcp_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc Port: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.psrc, - fsc->fs.m_u.tcp_ip4_spec.psrc); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest Port: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.pdst, - fsc->fs.m_u.tcp_ip4_spec.pdst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.tos, - fsc->fs.m_u.tcp_ip4_spec.tos); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case AH_ESP_V4_FLOW: - case ESP_V4_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.ah_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.ah_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSPI: %d, mask: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.spi, - fsc->fs.m_u.ah_ip4_spec.spi); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.tos, - fsc->fs.m_u.ah_ip4_spec.tos); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IP_USER_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IPV4_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tL4 bytes: 0x%x, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.l4_4_bytes, - fsc->fs.m_u.usr_ip4_spec.l4_4_bytes); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.tos, - fsc->fs.m_u.usr_ip4_spec.tos); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tIP Version: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip_ver, - fsc->fs.m_u.usr_ip4_spec.ip_ver); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tProtocol: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.proto, - fsc->fs.m_u.usr_ip4_spec.proto); - p += ETH_GSTRING_LEN; - num_strings++; - break; + if (rxfh.key_size) { + hkey = rss_config + indir_bytes; + if (copy_from_user(hkey, + useraddr + rss_cfg_offset + indir_bytes, + rxfh.key_size)) { + ret = -EFAULT; + goto out; } - sprintf(p, "\tVLAN: %d, mask: 0x%x\n", - fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tUser-defined: 0x%Lx\n", fsc->fs.data); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tUser-defined mask: 0x%Lx\n", fsc->fs.data_mask); - p += ETH_GSTRING_LEN; - num_strings++; - if (fsc->fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP) - sprintf(p, "\tAction: Drop\n"); - else - sprintf(p, "\tAction: Direct to queue %d\n", - fsc->fs.action); - p += ETH_GSTRING_LEN; - num_strings++; -unknown_filter: - i++; } -copy: - /* indicate to userspace how many strings we actually have */ - gstrings.len = num_strings; - ret = -EFAULT; - if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) - goto out; - useraddr += sizeof(gstrings); - if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) - goto out; - ret = 0; + + ret = ops->set_rxfh(dev, indir, hkey); out: - kfree(data); + kfree(rss_config); return ret; } @@ -817,8 +859,8 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = vmalloc(reglen); - if (!regbuf) + regbuf = vzalloc(reglen); + if (reglen && !regbuf) return -ENOMEM; ops->get_regs(dev, ®s, regbuf); @@ -827,7 +869,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (copy_to_user(useraddr, ®s, sizeof(regs))) goto out; useraddr += offsetof(struct ethtool_regs, data); - if (copy_to_user(useraddr, regbuf, regs.len)) + if (regbuf && copy_to_user(useraddr, regbuf, regs.len)) goto out; ret = 0; @@ -883,6 +925,40 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) return dev->ethtool_ops->set_wol(dev, &wol); } +static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_eee edata; + int rc; + + if (!dev->ethtool_ops->get_eee) + return -EOPNOTSUPP; + + memset(&edata, 0, sizeof(struct ethtool_eee)); + edata.cmd = ETHTOOL_GEEE; + rc = dev->ethtool_ops->get_eee(dev, &edata); + + if (rc) + return rc; + + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + + return 0; +} + +static int ethtool_set_eee(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_eee edata; + + if (!dev->ethtool_ops->set_eee) + return -EOPNOTSUPP; + + if (copy_from_user(&edata, useraddr, sizeof(edata))) + return -EFAULT; + + return dev->ethtool_ops->set_eee(dev, &edata); +} + static int ethtool_nway_reset(struct net_device *dev) { if (!dev->ethtool_ops->nway_reset) @@ -891,18 +967,31 @@ static int ethtool_nway_reset(struct net_device *dev) return dev->ethtool_ops->nway_reset(dev); } -static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) +static int ethtool_get_link(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value edata = { .cmd = ETHTOOL_GLINK }; + + if (!dev->ethtool_ops->get_link) + return -EOPNOTSUPP; + + edata.data = netif_running(dev) && dev->ethtool_ops->get_link(dev); + + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + return 0; +} + +static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, + int (*getter)(struct net_device *, + struct ethtool_eeprom *, u8 *), + u32 total_len) { struct ethtool_eeprom eeprom; - const struct ethtool_ops *ops = dev->ethtool_ops; void __user *userbuf = useraddr + sizeof(eeprom); u32 bytes_remaining; u8 *data; int ret = 0; - if (!ops->get_eeprom || !ops->get_eeprom_len) - return -EOPNOTSUPP; - if (copy_from_user(&eeprom, useraddr, sizeof(eeprom))) return -EFAULT; @@ -911,7 +1000,7 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) return -EINVAL; /* Check for exceeding total eeprom len */ - if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) + if (eeprom.offset + eeprom.len > total_len) return -EINVAL; data = kmalloc(PAGE_SIZE, GFP_USER); @@ -922,7 +1011,7 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) while (bytes_remaining > 0) { eeprom.len = min(bytes_remaining, (u32)PAGE_SIZE); - ret = ops->get_eeprom(dev, &eeprom, data); + ret = getter(dev, &eeprom, data); if (ret) break; if (copy_to_user(userbuf, data, eeprom.len)) { @@ -943,6 +1032,17 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) return ret; } +static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_eeprom || !ops->get_eeprom_len) + return -EOPNOTSUPP; + + return ethtool_get_any_eeprom(dev, useraddr, ops->get_eeprom, + ops->get_eeprom_len(dev)); +} + static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) { struct ethtool_eeprom eeprom; @@ -1046,190 +1146,60 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_ringparam(dev, &ringparam); } -static int ethtool_get_pauseparam(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_get_channels(struct net_device *dev, + void __user *useraddr) { - struct ethtool_pauseparam pauseparam = { ETHTOOL_GPAUSEPARAM }; + struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; - if (!dev->ethtool_ops->get_pauseparam) + if (!dev->ethtool_ops->get_channels) return -EOPNOTSUPP; - dev->ethtool_ops->get_pauseparam(dev, &pauseparam); + dev->ethtool_ops->get_channels(dev, &channels); - if (copy_to_user(useraddr, &pauseparam, sizeof(pauseparam))) + if (copy_to_user(useraddr, &channels, sizeof(channels))) return -EFAULT; return 0; } -static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr) -{ - struct ethtool_pauseparam pauseparam; - - if (!dev->ethtool_ops->set_pauseparam) - return -EOPNOTSUPP; - - if (copy_from_user(&pauseparam, useraddr, sizeof(pauseparam))) - return -EFAULT; - - return dev->ethtool_ops->set_pauseparam(dev, &pauseparam); -} - -static int __ethtool_set_sg(struct net_device *dev, u32 data) -{ - int err; - - if (!data && dev->ethtool_ops->set_tso) { - err = dev->ethtool_ops->set_tso(dev, 0); - if (err) - return err; - } - - if (!data && dev->ethtool_ops->set_ufo) { - err = dev->ethtool_ops->set_ufo(dev, 0); - if (err) - return err; - } - return dev->ethtool_ops->set_sg(dev, data); -} - -static int ethtool_set_tx_csum(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata; - int err; - - if (!dev->ethtool_ops->set_tx_csum) - return -EOPNOTSUPP; - - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - - if (!edata.data && dev->ethtool_ops->set_sg) { - err = __ethtool_set_sg(dev, 0); - if (err) - return err; - } - - return dev->ethtool_ops->set_tx_csum(dev, edata.data); -} -EXPORT_SYMBOL(ethtool_op_set_tx_csum); - -static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata; - - if (!dev->ethtool_ops->set_rx_csum) - return -EOPNOTSUPP; - - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - - if (!edata.data && dev->ethtool_ops->set_sg) - dev->features &= ~NETIF_F_GRO; - - return dev->ethtool_ops->set_rx_csum(dev, edata.data); -} - -static int ethtool_set_sg(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata; - - if (!dev->ethtool_ops->set_sg) - return -EOPNOTSUPP; - - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - - if (edata.data && - !(dev->features & NETIF_F_ALL_CSUM)) - return -EINVAL; - - return __ethtool_set_sg(dev, edata.data); -} - -static int ethtool_set_tso(struct net_device *dev, char __user *useraddr) +static noinline_for_stack int ethtool_set_channels(struct net_device *dev, + void __user *useraddr) { - struct ethtool_value edata; + struct ethtool_channels channels; - if (!dev->ethtool_ops->set_tso) + if (!dev->ethtool_ops->set_channels) return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) + if (copy_from_user(&channels, useraddr, sizeof(channels))) return -EFAULT; - if (edata.data && !(dev->features & NETIF_F_SG)) - return -EINVAL; - - return dev->ethtool_ops->set_tso(dev, edata.data); + return dev->ethtool_ops->set_channels(dev, &channels); } -static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr) +static int ethtool_get_pauseparam(struct net_device *dev, void __user *useraddr) { - struct ethtool_value edata; + struct ethtool_pauseparam pauseparam = { ETHTOOL_GPAUSEPARAM }; - if (!dev->ethtool_ops->set_ufo) + if (!dev->ethtool_ops->get_pauseparam) return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) - return -EFAULT; - if (edata.data && !(dev->features & NETIF_F_SG)) - return -EINVAL; - if (edata.data && !((dev->features & NETIF_F_GEN_CSUM) || - (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) - == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) - return -EINVAL; - return dev->ethtool_ops->set_ufo(dev, edata.data); -} -static int ethtool_get_gso(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata = { ETHTOOL_GGSO }; - - edata.data = dev->features & NETIF_F_GSO; - if (copy_to_user(useraddr, &edata, sizeof(edata))) - return -EFAULT; - return 0; -} - -static int ethtool_set_gso(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata; + dev->ethtool_ops->get_pauseparam(dev, &pauseparam); - if (copy_from_user(&edata, useraddr, sizeof(edata))) + if (copy_to_user(useraddr, &pauseparam, sizeof(pauseparam))) return -EFAULT; - if (edata.data) - dev->features |= NETIF_F_GSO; - else - dev->features &= ~NETIF_F_GSO; return 0; } -static int ethtool_get_gro(struct net_device *dev, char __user *useraddr) +static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr) { - struct ethtool_value edata = { ETHTOOL_GGRO }; - - edata.data = dev->features & NETIF_F_GRO; - if (copy_to_user(useraddr, &edata, sizeof(edata))) - return -EFAULT; - return 0; -} + struct ethtool_pauseparam pauseparam; -static int ethtool_set_gro(struct net_device *dev, char __user *useraddr) -{ - struct ethtool_value edata; + if (!dev->ethtool_ops->set_pauseparam) + return -EOPNOTSUPP; - if (copy_from_user(&edata, useraddr, sizeof(edata))) + if (copy_from_user(&pauseparam, useraddr, sizeof(pauseparam))) return -EFAULT; - if (edata.data) { - u32 rxcsum = dev->ethtool_ops->get_rx_csum ? - dev->ethtool_ops->get_rx_csum(dev) : - ethtool_op_get_rx_csum(dev); - - if (!rxcsum) - return -EINVAL; - dev->features |= NETIF_F_GRO; - } else - dev->features &= ~NETIF_F_GRO; - - return 0; + return dev->ethtool_ops->set_pauseparam(dev, &pauseparam); } static int ethtool_self_test(struct net_device *dev, char __user *useraddr) @@ -1273,17 +1243,13 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) { struct ethtool_gstrings gstrings; - const struct ethtool_ops *ops = dev->ethtool_ops; u8 *data; int ret; - if (!ops->get_strings || !ops->get_sset_count) - return -EOPNOTSUPP; - if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) return -EFAULT; - ret = ops->get_sset_count(dev, gstrings.string_set); + ret = __ethtool_get_sset_count(dev, gstrings.string_set); if (ret < 0) return ret; @@ -1293,7 +1259,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) if (!data) return -ENOMEM; - ops->get_strings(dev, gstrings.string_set, data); + __ethtool_get_strings(dev, gstrings.string_set, data); ret = -EFAULT; if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) @@ -1303,7 +1269,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) goto out; ret = 0; - out: +out: kfree(data); return ret; } @@ -1311,14 +1277,61 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) { struct ethtool_value id; + static bool busy; + const struct ethtool_ops *ops = dev->ethtool_ops; + int rc; - if (!dev->ethtool_ops->phys_id) + if (!ops->set_phys_id) return -EOPNOTSUPP; + if (busy) + return -EBUSY; + if (copy_from_user(&id, useraddr, sizeof(id))) return -EFAULT; - return dev->ethtool_ops->phys_id(dev, id.data); + rc = ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); + if (rc < 0) + return rc; + + /* Drop the RTNL lock while waiting, but prevent reentry or + * removal of the device. + */ + busy = true; + dev_hold(dev); + rtnl_unlock(); + + if (rc == 0) { + /* Driver will handle this itself */ + schedule_timeout_interruptible( + id.data ? (id.data * HZ) : MAX_SCHEDULE_TIMEOUT); + } else { + /* Driver expects to be called at twice the frequency in rc */ + int n = rc * 2, i, interval = HZ / n; + + /* Count down seconds */ + do { + /* Count down iterations per second */ + i = n; + do { + rtnl_lock(); + rc = ops->set_phys_id(dev, + (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); + rtnl_unlock(); + if (rc) + break; + schedule_timeout_interruptible(interval); + } while (!signal_pending(current) && --i != 0); + } while (!signal_pending(current) && + (id.data == 0 || --id.data != 0)); + } + + rtnl_lock(); + dev_put(dev); + busy = false; + + (void) ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); + return rc; } static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) @@ -1433,10 +1446,182 @@ static noinline_for_stack int ethtool_flash_device(struct net_device *dev, if (!dev->ethtool_ops->flash_device) return -EOPNOTSUPP; + efl.data[ETHTOOL_FLASH_MAX_FILENAME - 1] = 0; + return dev->ethtool_ops->flash_device(dev, &efl); } -/* The main entry point in this file. Called from net/core/dev.c */ +static int ethtool_set_dump(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_dump dump; + + if (!dev->ethtool_ops->set_dump) + return -EOPNOTSUPP; + + if (copy_from_user(&dump, useraddr, sizeof(dump))) + return -EFAULT; + + return dev->ethtool_ops->set_dump(dev, &dump); +} + +static int ethtool_get_dump_flag(struct net_device *dev, + void __user *useraddr) +{ + int ret; + struct ethtool_dump dump; + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_dump_flag) + return -EOPNOTSUPP; + + if (copy_from_user(&dump, useraddr, sizeof(dump))) + return -EFAULT; + + ret = ops->get_dump_flag(dev, &dump); + if (ret) + return ret; + + if (copy_to_user(useraddr, &dump, sizeof(dump))) + return -EFAULT; + return 0; +} + +static int ethtool_get_dump_data(struct net_device *dev, + void __user *useraddr) +{ + int ret; + __u32 len; + struct ethtool_dump dump, tmp; + const struct ethtool_ops *ops = dev->ethtool_ops; + void *data = NULL; + + if (!ops->get_dump_data || !ops->get_dump_flag) + return -EOPNOTSUPP; + + if (copy_from_user(&dump, useraddr, sizeof(dump))) + return -EFAULT; + + memset(&tmp, 0, sizeof(tmp)); + tmp.cmd = ETHTOOL_GET_DUMP_FLAG; + ret = ops->get_dump_flag(dev, &tmp); + if (ret) + return ret; + + len = min(tmp.len, dump.len); + if (!len) + return -EFAULT; + + /* Don't ever let the driver think there's more space available + * than it requested with .get_dump_flag(). + */ + dump.len = len; + + /* Always allocate enough space to hold the whole thing so that the + * driver does not need to check the length and bother with partial + * dumping. + */ + data = vzalloc(tmp.len); + if (!data) + return -ENOMEM; + ret = ops->get_dump_data(dev, &dump, data); + if (ret) + goto out; + + /* There are two sane possibilities: + * 1. The driver's .get_dump_data() does not touch dump.len. + * 2. Or it may set dump.len to how much it really writes, which + * should be tmp.len (or len if it can do a partial dump). + * In any case respond to userspace with the actual length of data + * it's receiving. + */ + WARN_ON(dump.len != len && dump.len != tmp.len); + dump.len = len; + + if (copy_to_user(useraddr, &dump, sizeof(dump))) { + ret = -EFAULT; + goto out; + } + useraddr += offsetof(struct ethtool_dump, data); + if (copy_to_user(useraddr, data, len)) + ret = -EFAULT; +out: + vfree(data); + return ret; +} + +static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) +{ + int err = 0; + struct ethtool_ts_info info; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct phy_device *phydev = dev->phydev; + + memset(&info, 0, sizeof(info)); + info.cmd = ETHTOOL_GET_TS_INFO; + + if (phydev && phydev->drv && phydev->drv->ts_info) { + err = phydev->drv->ts_info(phydev, &info); + } else if (ops->get_ts_info) { + err = ops->get_ts_info(dev, &info); + } else { + info.so_timestamping = + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info.phc_index = -1; + } + + if (err) + return err; + + if (copy_to_user(useraddr, &info, sizeof(info))) + err = -EFAULT; + + return err; +} + +static int ethtool_get_module_info(struct net_device *dev, + void __user *useraddr) +{ + int ret; + struct ethtool_modinfo modinfo; + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_module_info) + return -EOPNOTSUPP; + + if (copy_from_user(&modinfo, useraddr, sizeof(modinfo))) + return -EFAULT; + + ret = ops->get_module_info(dev, &modinfo); + if (ret) + return ret; + + if (copy_to_user(useraddr, &modinfo, sizeof(modinfo))) + return -EFAULT; + + return 0; +} + +static int ethtool_get_module_eeprom(struct net_device *dev, + void __user *useraddr) +{ + int ret; + struct ethtool_modinfo modinfo; + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_module_info || !ops->get_module_eeprom) + return -EOPNOTSUPP; + + ret = ops->get_module_info(dev, &modinfo); + if (ret) + return ret; + + return ethtool_get_any_eeprom(dev, useraddr, ops->get_module_eeprom, + modinfo.eeprom_len); +} + +/* The main entry point in this file. Called from net/core/dev_ioctl.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) { @@ -1444,7 +1629,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) void __user *useraddr = ifr->ifr_data; u32 ethcmd; int rc; - unsigned long old_features; + netdev_features_t old_features; if (!dev || !netif_device_present(dev)) return -ENODEV; @@ -1452,28 +1637,21 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) return -EFAULT; - if (!dev->ethtool_ops) { - /* ETHTOOL_GDRVINFO does not require any driver support. - * It is also unprivileged and does not change anything, - * so we can take a shortcut to it. */ - if (ethcmd == ETHTOOL_GDRVINFO) - return ethtool_get_drvinfo(dev, useraddr); - else - return -EOPNOTSUPP; - } - /* Allow some commands to be done by anyone */ switch (ethcmd) { case ETHTOOL_GSET: case ETHTOOL_GDRVINFO: case ETHTOOL_GMSGLVL: + case ETHTOOL_GLINK: case ETHTOOL_GCOALESCE: case ETHTOOL_GRINGPARAM: case ETHTOOL_GPAUSEPARAM: case ETHTOOL_GRXCSUM: case ETHTOOL_GTXCSUM: case ETHTOOL_GSG: + case ETHTOOL_GSSET_INFO: case ETHTOOL_GSTRINGS: + case ETHTOOL_GSTATS: case ETHTOOL_GTSO: case ETHTOOL_GPERMADDR: case ETHTOOL_GUFO: @@ -1486,9 +1664,15 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: case ETHTOOL_GRXCLSRLALL: + case ETHTOOL_GRXFHINDIR: + case ETHTOOL_GRSSH: + case ETHTOOL_GFEATURES: + case ETHTOOL_GCHANNELS: + case ETHTOOL_GET_TS_INFO: + case ETHTOOL_GEEE: break; default: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; } @@ -1526,12 +1710,17 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) rc = ethtool_set_value_void(dev, useraddr, dev->ethtool_ops->set_msglevel); break; + case ETHTOOL_GEEE: + rc = ethtool_get_eee(dev, useraddr); + break; + case ETHTOOL_SEEE: + rc = ethtool_set_eee(dev, useraddr); + break; case ETHTOOL_NWAY_RST: rc = ethtool_nway_reset(dev); break; case ETHTOOL_GLINK: - rc = ethtool_get_value(dev, useraddr, ethcmd, - dev->ethtool_ops->get_link); + rc = ethtool_get_link(dev, useraddr); break; case ETHTOOL_GEEPROM: rc = ethtool_get_eeprom(dev, useraddr); @@ -1557,42 +1746,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SPAUSEPARAM: rc = ethtool_set_pauseparam(dev, useraddr); break; - case ETHTOOL_GRXCSUM: - rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_rx_csum ? - dev->ethtool_ops->get_rx_csum : - ethtool_op_get_rx_csum)); - break; - case ETHTOOL_SRXCSUM: - rc = ethtool_set_rx_csum(dev, useraddr); - break; - case ETHTOOL_GTXCSUM: - rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_tx_csum ? - dev->ethtool_ops->get_tx_csum : - ethtool_op_get_tx_csum)); - break; - case ETHTOOL_STXCSUM: - rc = ethtool_set_tx_csum(dev, useraddr); - break; - case ETHTOOL_GSG: - rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_sg ? - dev->ethtool_ops->get_sg : - ethtool_op_get_sg)); - break; - case ETHTOOL_SSG: - rc = ethtool_set_sg(dev, useraddr); - break; - case ETHTOOL_GTSO: - rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_tso ? - dev->ethtool_ops->get_tso : - ethtool_op_get_tso)); - break; - case ETHTOOL_STSO: - rc = ethtool_set_tso(dev, useraddr); - break; case ETHTOOL_TEST: rc = ethtool_self_test(dev, useraddr); break; @@ -1608,30 +1761,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GPERMADDR: rc = ethtool_get_perm_addr(dev, useraddr); break; - case ETHTOOL_GUFO: - rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_ufo ? - dev->ethtool_ops->get_ufo : - ethtool_op_get_ufo)); - break; - case ETHTOOL_SUFO: - rc = ethtool_set_ufo(dev, useraddr); - break; - case ETHTOOL_GGSO: - rc = ethtool_get_gso(dev, useraddr); - break; - case ETHTOOL_SGSO: - rc = ethtool_set_gso(dev, useraddr); - break; case ETHTOOL_GFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_flags ? - dev->ethtool_ops->get_flags : - ethtool_op_get_flags)); + __ethtool_get_flags); break; case ETHTOOL_SFLAGS: - rc = ethtool_set_value(dev, useraddr, - dev->ethtool_ops->set_flags); + rc = ethtool_set_value(dev, useraddr, __ethtool_set_flags); break; case ETHTOOL_GPFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, @@ -1653,24 +1788,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SRXCLSRLINS: rc = ethtool_set_rxnfc(dev, ethcmd, useraddr); break; - case ETHTOOL_GGRO: - rc = ethtool_get_gro(dev, useraddr); - break; - case ETHTOOL_SGRO: - rc = ethtool_set_gro(dev, useraddr); - break; case ETHTOOL_FLASHDEV: rc = ethtool_flash_device(dev, useraddr); break; case ETHTOOL_RESET: rc = ethtool_reset(dev, useraddr); break; - case ETHTOOL_SRXNTUPLE: - rc = ethtool_set_rx_ntuple(dev, useraddr); - break; - case ETHTOOL_GRXNTUPLE: - rc = ethtool_get_rx_ntuple(dev, useraddr); - break; case ETHTOOL_GSSET_INFO: rc = ethtool_get_sset_info(dev, useraddr); break; @@ -1680,6 +1803,60 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SRXFHINDIR: rc = ethtool_set_rxfh_indir(dev, useraddr); break; + case ETHTOOL_GRSSH: + rc = ethtool_get_rxfh(dev, useraddr); + break; + case ETHTOOL_SRSSH: + rc = ethtool_set_rxfh(dev, useraddr); + break; + case ETHTOOL_GFEATURES: + rc = ethtool_get_features(dev, useraddr); + break; + case ETHTOOL_SFEATURES: + rc = ethtool_set_features(dev, useraddr); + break; + case ETHTOOL_GTXCSUM: + case ETHTOOL_GRXCSUM: + case ETHTOOL_GSG: + case ETHTOOL_GTSO: + case ETHTOOL_GUFO: + case ETHTOOL_GGSO: + case ETHTOOL_GGRO: + rc = ethtool_get_one_feature(dev, useraddr, ethcmd); + break; + case ETHTOOL_STXCSUM: + case ETHTOOL_SRXCSUM: + case ETHTOOL_SSG: + case ETHTOOL_STSO: + case ETHTOOL_SUFO: + case ETHTOOL_SGSO: + case ETHTOOL_SGRO: + rc = ethtool_set_one_feature(dev, useraddr, ethcmd); + break; + case ETHTOOL_GCHANNELS: + rc = ethtool_get_channels(dev, useraddr); + break; + case ETHTOOL_SCHANNELS: + rc = ethtool_set_channels(dev, useraddr); + break; + case ETHTOOL_SET_DUMP: + rc = ethtool_set_dump(dev, useraddr); + break; + case ETHTOOL_GET_DUMP_FLAG: + rc = ethtool_get_dump_flag(dev, useraddr); + break; + case ETHTOOL_GET_DUMP_DATA: + rc = ethtool_get_dump_data(dev, useraddr); + break; + case ETHTOOL_GET_TS_INFO: + rc = ethtool_get_ts_info(dev, useraddr); + break; + case ETHTOOL_GMODULEINFO: + rc = ethtool_get_module_info(dev, useraddr); + break; + case ETHTOOL_GMODULEEEPROM: + rc = ethtool_get_module_eeprom(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 82a4369ae15..185c341fafb 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/list.h> +#include <linux/module.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/fib_rules.h> @@ -32,6 +33,9 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->flags = flags; r->fr_net = hold_net(ops->fro_net); + r->suppress_prefixlen = -1; + r->suppress_ifgroup = -1; + /* The lock is not required here, the list in unreacheable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); @@ -150,6 +154,8 @@ static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) { list_del_rcu(&rule->list); + if (ops->delete) + ops->delete(rule); fib_rule_put(rule); } } @@ -181,14 +187,13 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, { int ret = 0; - if (rule->iifindex && (rule->iifindex != fl->iif) && - !(fl->flags & FLOWI_FLAG_MATCH_ANY_IIF)) + if (rule->iifindex && (rule->iifindex != fl->flowi_iif)) goto out; - if (rule->oifindex && (rule->oifindex != fl->oif)) + if (rule->oifindex && (rule->oifindex != fl->flowi_oif)) goto out; - if ((rule->mark ^ fl->mark) & rule->mark_mask) + if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) goto out; ret = ops->match(rule, fl, flags); @@ -224,6 +229,9 @@ jumped: else err = ops->action(rule, fl, flags, arg); + if (!err && ops->suppress && ops->suppress(rule, arg)) + continue; + if (err != -EAGAIN) { if ((arg->flags & FIB_LOOKUP_NOREF) || likely(atomic_inc_not_zero(&rule->refcnt))) { @@ -264,7 +272,7 @@ errout: return err; } -static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); @@ -335,6 +343,15 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) rule->action = frh->action; rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); + if (tb[FRA_SUPPRESS_PREFIXLEN]) + rule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); + else + rule->suppress_prefixlen = -1; + + if (tb[FRA_SUPPRESS_IFGROUP]) + rule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); + else + rule->suppress_ifgroup = -1; if (!tb[FRA_PRIORITY] && ops->default_pref) rule->pref = ops->default_pref(ops); @@ -385,8 +402,8 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) */ list_for_each_entry(r, &ops->rules_list, list) { if (r->action == FR_ACT_GOTO && - r->target == rule->pref) { - BUG_ON(rtnl_dereference(r->ctarget) != NULL); + r->target == rule->pref && + rtnl_dereference(r->ctarget) == NULL) { rcu_assign_pointer(r->ctarget, rule); if (--ops->unresolved_rules == 0) break; @@ -400,7 +417,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (unresolved) ops->unresolved_rules++; - notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).pid); + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); return 0; @@ -413,7 +430,7 @@ errout: return err; } -static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); @@ -443,7 +460,8 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (frh->action && (frh->action != rule->action)) continue; - if (frh->table && (frh_get_table(frh, tb) != rule->table)) + if (frh_get_table(frh, tb) && + (frh_get_table(frh, tb) != rule->table)) continue; if (tb[FRA_PRIORITY] && @@ -476,8 +494,11 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) list_del_rcu(&rule->list); - if (rule->action == FR_ACT_GOTO) + if (rule->action == FR_ACT_GOTO) { ops->nr_goto_rules--; + if (rtnl_dereference(rule->ctarget) == NULL) + ops->unresolved_rules--; + } /* * Check if this rule is a target to any of them. If so, @@ -488,14 +509,16 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (ops->nr_goto_rules > 0) { list_for_each_entry(tmp, &ops->rules_list, list) { if (rtnl_dereference(tmp->ctarget) == rule) { - rcu_assign_pointer(tmp->ctarget, NULL); + RCU_INIT_POINTER(tmp->ctarget, NULL); ops->unresolved_rules++; } } } notify_rule_change(RTM_DELRULE, rule, ops, nlh, - NETLINK_CB(skb).pid); + NETLINK_CB(skb).portid); + if (ops->delete) + ops->delete(rule); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); @@ -516,6 +539,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4); /* FRA_FWMASK */ @@ -539,41 +564,47 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->family = ops->family; frh->table = rule->table; - NLA_PUT_U32(skb, FRA_TABLE, rule->table); + if (nla_put_u32(skb, FRA_TABLE, rule->table)) + goto nla_put_failure; + if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) + goto nla_put_failure; frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; frh->flags = rule->flags; if (rule->action == FR_ACT_GOTO && - rcu_dereference_raw(rule->ctarget) == NULL) + rcu_access_pointer(rule->ctarget) == NULL) frh->flags |= FIB_RULE_UNRESOLVED; if (rule->iifname[0]) { - NLA_PUT_STRING(skb, FRA_IIFNAME, rule->iifname); - + if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) + goto nla_put_failure; if (rule->iifindex == -1) frh->flags |= FIB_RULE_IIF_DETACHED; } if (rule->oifname[0]) { - NLA_PUT_STRING(skb, FRA_OIFNAME, rule->oifname); - + if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) + goto nla_put_failure; if (rule->oifindex == -1) frh->flags |= FIB_RULE_OIF_DETACHED; } - if (rule->pref) - NLA_PUT_U32(skb, FRA_PRIORITY, rule->pref); - - if (rule->mark) - NLA_PUT_U32(skb, FRA_FWMARK, rule->mark); - - if (rule->mark_mask || rule->mark) - NLA_PUT_U32(skb, FRA_FWMASK, rule->mark_mask); + if ((rule->pref && + nla_put_u32(skb, FRA_PRIORITY, rule->pref)) || + (rule->mark && + nla_put_u32(skb, FRA_FWMARK, rule->mark)) || + ((rule->mark_mask || rule->mark) && + nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || + (rule->target && + nla_put_u32(skb, FRA_GOTO, rule->target))) + goto nla_put_failure; - if (rule->target) - NLA_PUT_U32(skb, FRA_GOTO, rule->target); + if (rule->suppress_ifgroup != -1) { + if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup)) + goto nla_put_failure; + } if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; @@ -591,17 +622,19 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, int idx = 0; struct fib_rule *rule; - list_for_each_entry(rule, &ops->rules_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; - if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).pid, + if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWRULE, NLM_F_MULTI, ops) < 0) break; skip: idx++; } + rcu_read_unlock(); cb->args[1] = idx; rules_ops_put(ops); @@ -698,9 +731,9 @@ static void detach_rules(struct list_head *rules, struct net_device *dev) static int fib_rules_event(struct notifier_block *this, unsigned long event, - void *ptr) + void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct fib_rules_ops *ops; @@ -712,6 +745,13 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, attach_rules(&ops->rules_list, dev); break; + case NETDEV_CHANGENAME: + list_for_each_entry(ops, &net->rules_ops, list) { + detach_rules(&ops->rules_list, dev); + attach_rules(&ops->rules_list, dev); + } + break; + case NETDEV_UNREGISTER: list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); @@ -739,9 +779,9 @@ static struct pernet_operations fib_rules_net_ops = { static int __init fib_rules_init(void) { int err; - rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL); - rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL); - rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule); + rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL); err = register_pernet_subsys(&fib_rules_net_ops); if (err < 0) diff --git a/net/core/filter.c b/net/core/filter.c index 25500f16a18..1dbf6462f76 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1,11 +1,16 @@ /* * Linux Socket Filter - Kernel level socket filtering * - * Author: - * Jay Schulist <jschlst@samba.org> + * Based on the design of the Berkeley Packet Filter. The new + * internal format has been designed by PLUMgrid: * - * Based on the design of: - * - The Berkeley Packet Filter + * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com + * + * Authors: + * + * Jay Schulist <jschlst@samba.org> + * Alexei Starovoitov <ast@plumgrid.com> + * Daniel Borkmann <dborkman@redhat.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -33,62 +38,39 @@ #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <asm/unaligned.h> #include <linux/filter.h> -#include <linux/reciprocal_div.h> - -enum { - BPF_S_RET_K = 1, - BPF_S_RET_A, - BPF_S_ALU_ADD_K, - BPF_S_ALU_ADD_X, - BPF_S_ALU_SUB_K, - BPF_S_ALU_SUB_X, - BPF_S_ALU_MUL_K, - BPF_S_ALU_MUL_X, - BPF_S_ALU_DIV_X, - BPF_S_ALU_AND_K, - BPF_S_ALU_AND_X, - BPF_S_ALU_OR_K, - BPF_S_ALU_OR_X, - BPF_S_ALU_LSH_K, - BPF_S_ALU_LSH_X, - BPF_S_ALU_RSH_K, - BPF_S_ALU_RSH_X, - BPF_S_ALU_NEG, - BPF_S_LD_W_ABS, - BPF_S_LD_H_ABS, - BPF_S_LD_B_ABS, - BPF_S_LD_W_LEN, - BPF_S_LD_W_IND, - BPF_S_LD_H_IND, - BPF_S_LD_B_IND, - BPF_S_LD_IMM, - BPF_S_LDX_W_LEN, - BPF_S_LDX_B_MSH, - BPF_S_LDX_IMM, - BPF_S_MISC_TAX, - BPF_S_MISC_TXA, - BPF_S_ALU_DIV_K, - BPF_S_LD_MEM, - BPF_S_LDX_MEM, - BPF_S_ST, - BPF_S_STX, - BPF_S_JMP_JA, - BPF_S_JMP_JEQ_K, - BPF_S_JMP_JEQ_X, - BPF_S_JMP_JGE_K, - BPF_S_JMP_JGE_X, - BPF_S_JMP_JGT_K, - BPF_S_JMP_JGT_X, - BPF_S_JMP_JSET_K, - BPF_S_JMP_JSET_X, -}; - -/* No hurry in this branch */ -static void *__load_pointer(const struct sk_buff *skb, int k) +#include <linux/ratelimit.h> +#include <linux/seccomp.h> +#include <linux/if_vlan.h> + +/* Registers */ +#define BPF_R0 regs[BPF_REG_0] +#define BPF_R1 regs[BPF_REG_1] +#define BPF_R2 regs[BPF_REG_2] +#define BPF_R3 regs[BPF_REG_3] +#define BPF_R4 regs[BPF_REG_4] +#define BPF_R5 regs[BPF_REG_5] +#define BPF_R6 regs[BPF_REG_6] +#define BPF_R7 regs[BPF_REG_7] +#define BPF_R8 regs[BPF_REG_8] +#define BPF_R9 regs[BPF_REG_9] +#define BPF_R10 regs[BPF_REG_10] + +/* Named registers */ +#define DST regs[insn->dst_reg] +#define SRC regs[insn->src_reg] +#define FP regs[BPF_REG_FP] +#define ARG1 regs[BPF_REG_ARG1] +#define CTX regs[BPF_REG_CTX] +#define IMM insn->imm + +/* No hurry in this branch + * + * Exported for the bpf jit load helper. + */ +void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; @@ -96,9 +78,9 @@ static void *__load_pointer(const struct sk_buff *skb, int k) ptr = skb_network_header(skb) + k - SKF_NET_OFF; else if (k >= SKF_LL_OFF) ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - - if (ptr >= skb->head && ptr < skb_tail_pointer(skb)) + if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; + return NULL; } @@ -107,11 +89,8 @@ static inline void *load_pointer(const struct sk_buff *skb, int k, { if (k >= 0) return skb_header_pointer(skb, k, size, buffer); - else { - if (k >= SKF_AD_OFF) - return NULL; - return __load_pointer(skb, k); - } + + return bpf_internal_load_pointer_neg_helper(skb, k, size); } /** @@ -131,344 +110,1032 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) int err; struct sk_filter *filter; + /* + * If the skb was allocated from pfmemalloc reserves, only + * allow SOCK_MEMALLOC sockets to use it as this socket is + * helping free memory + */ + if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) + return -ENOMEM; + err = security_sock_rcv_skb(sk, skb); if (err) return err; - rcu_read_lock_bh(); - filter = rcu_dereference_bh(sk->sk_filter); + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); if (filter) { - unsigned int pkt_len = sk_run_filter(skb, filter->insns); + unsigned int pkt_len = SK_RUN_FILTER(filter, skb); err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } - rcu_read_unlock_bh(); + rcu_read_unlock(); return err; } EXPORT_SYMBOL(sk_filter); +/* Base function for offset calculation. Needs to go into .text section, + * therefore keeping it non-static as well; will also be used by JITs + * anyway later on, so do not let the compiler omit it. + */ +noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return 0; +} + /** - * sk_run_filter - run a filter on a socket - * @skb: buffer to run the filter on - * @filter: filter to apply + * __sk_run_filter - run a filter on a given context + * @ctx: buffer to run the filter on + * @insn: filter to apply * - * Decode and apply filter instructions to the skb->data. - * Return length to keep, 0 for none. @skb is the data we are - * filtering, @filter is the array of filter instructions. - * Because all jumps are guaranteed to be before last instruction, - * and last instruction guaranteed to be a RET, we dont need to check - * flen. (We used to pass to this function the length of filter) + * Decode and apply filter instructions to the skb->data. Return length to + * keep, 0 for none. @ctx is the data we are operating on, @insn is the + * array of filter instructions. */ -unsigned int sk_run_filter(const struct sk_buff *skb, - const struct sock_filter *fentry) +static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) { + u64 stack[MAX_BPF_STACK / sizeof(u64)]; + u64 regs[MAX_BPF_REG], tmp; + static const void *jumptable[256] = { + [0 ... 255] = &&default_label, + /* Now overwrite non-defaults ... */ + /* 32 bit ALU operations */ + [BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X, + [BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K, + [BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X, + [BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K, + [BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X, + [BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K, + [BPF_ALU | BPF_OR | BPF_X] = &&ALU_OR_X, + [BPF_ALU | BPF_OR | BPF_K] = &&ALU_OR_K, + [BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X, + [BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K, + [BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X, + [BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K, + [BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X, + [BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K, + [BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X, + [BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K, + [BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X, + [BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K, + [BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X, + [BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K, + [BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X, + [BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K, + [BPF_ALU | BPF_NEG] = &&ALU_NEG, + [BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE, + [BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE, + /* 64 bit ALU operations */ + [BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X, + [BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K, + [BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X, + [BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K, + [BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X, + [BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K, + [BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X, + [BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K, + [BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X, + [BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K, + [BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X, + [BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K, + [BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X, + [BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K, + [BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X, + [BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K, + [BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X, + [BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K, + [BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X, + [BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K, + [BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X, + [BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K, + [BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X, + [BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K, + [BPF_ALU64 | BPF_NEG] = &&ALU64_NEG, + /* Call instruction */ + [BPF_JMP | BPF_CALL] = &&JMP_CALL, + /* Jumps */ + [BPF_JMP | BPF_JA] = &&JMP_JA, + [BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X, + [BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K, + [BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X, + [BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K, + [BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X, + [BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K, + [BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X, + [BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K, + [BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X, + [BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K, + [BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X, + [BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K, + [BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X, + [BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K, + /* Program return */ + [BPF_JMP | BPF_EXIT] = &&JMP_EXIT, + /* Store instructions */ + [BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B, + [BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H, + [BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W, + [BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW, + [BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W, + [BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW, + [BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B, + [BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H, + [BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W, + [BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW, + /* Load instructions */ + [BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B, + [BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H, + [BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W, + [BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW, + [BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W, + [BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H, + [BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B, + [BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W, + [BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H, + [BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B, + }; void *ptr; - u32 A = 0; /* Accumulator */ - u32 X = 0; /* Index Register */ - u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ - u32 tmp; - int k; + int off; - /* - * Process array of filter instructions. - */ - for (;; fentry++) { -#if defined(CONFIG_X86_32) -#define K (fentry->k) -#else - const u32 K = fentry->k; -#endif +#define CONT ({ insn++; goto select_insn; }) +#define CONT_JMP ({ insn++; goto select_insn; }) - switch (fentry->code) { - case BPF_S_ALU_ADD_X: - A += X; - continue; - case BPF_S_ALU_ADD_K: - A += K; - continue; - case BPF_S_ALU_SUB_X: - A -= X; - continue; - case BPF_S_ALU_SUB_K: - A -= K; - continue; - case BPF_S_ALU_MUL_X: - A *= X; - continue; - case BPF_S_ALU_MUL_K: - A *= K; - continue; - case BPF_S_ALU_DIV_X: - if (X == 0) - return 0; - A /= X; - continue; - case BPF_S_ALU_DIV_K: - A = reciprocal_divide(A, K); - continue; - case BPF_S_ALU_AND_X: - A &= X; - continue; - case BPF_S_ALU_AND_K: - A &= K; - continue; - case BPF_S_ALU_OR_X: - A |= X; - continue; - case BPF_S_ALU_OR_K: - A |= K; - continue; - case BPF_S_ALU_LSH_X: - A <<= X; - continue; - case BPF_S_ALU_LSH_K: - A <<= K; - continue; - case BPF_S_ALU_RSH_X: - A >>= X; - continue; - case BPF_S_ALU_RSH_K: - A >>= K; - continue; - case BPF_S_ALU_NEG: - A = -A; - continue; - case BPF_S_JMP_JA: - fentry += K; - continue; - case BPF_S_JMP_JGT_K: - fentry += (A > K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JGE_K: - fentry += (A >= K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JEQ_K: - fentry += (A == K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JSET_K: - fentry += (A & K) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JGT_X: - fentry += (A > X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JGE_X: - fentry += (A >= X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JEQ_X: - fentry += (A == X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_JMP_JSET_X: - fentry += (A & X) ? fentry->jt : fentry->jf; - continue; - case BPF_S_LD_W_ABS: - k = K; -load_w: - ptr = load_pointer(skb, k, 4, &tmp); - if (ptr != NULL) { - A = get_unaligned_be32(ptr); - continue; - } + FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; + ARG1 = (u64) (unsigned long) ctx; + + /* Registers used in classic BPF programs need to be reset first. */ + regs[BPF_REG_A] = 0; + regs[BPF_REG_X] = 0; + +select_insn: + goto *jumptable[insn->code]; + + /* ALU */ +#define ALU(OPCODE, OP) \ + ALU64_##OPCODE##_X: \ + DST = DST OP SRC; \ + CONT; \ + ALU_##OPCODE##_X: \ + DST = (u32) DST OP (u32) SRC; \ + CONT; \ + ALU64_##OPCODE##_K: \ + DST = DST OP IMM; \ + CONT; \ + ALU_##OPCODE##_K: \ + DST = (u32) DST OP (u32) IMM; \ + CONT; + + ALU(ADD, +) + ALU(SUB, -) + ALU(AND, &) + ALU(OR, |) + ALU(LSH, <<) + ALU(RSH, >>) + ALU(XOR, ^) + ALU(MUL, *) +#undef ALU + ALU_NEG: + DST = (u32) -DST; + CONT; + ALU64_NEG: + DST = -DST; + CONT; + ALU_MOV_X: + DST = (u32) SRC; + CONT; + ALU_MOV_K: + DST = (u32) IMM; + CONT; + ALU64_MOV_X: + DST = SRC; + CONT; + ALU64_MOV_K: + DST = IMM; + CONT; + ALU64_ARSH_X: + (*(s64 *) &DST) >>= SRC; + CONT; + ALU64_ARSH_K: + (*(s64 *) &DST) >>= IMM; + CONT; + ALU64_MOD_X: + if (unlikely(SRC == 0)) + return 0; + tmp = DST; + DST = do_div(tmp, SRC); + CONT; + ALU_MOD_X: + if (unlikely(SRC == 0)) + return 0; + tmp = (u32) DST; + DST = do_div(tmp, (u32) SRC); + CONT; + ALU64_MOD_K: + tmp = DST; + DST = do_div(tmp, IMM); + CONT; + ALU_MOD_K: + tmp = (u32) DST; + DST = do_div(tmp, (u32) IMM); + CONT; + ALU64_DIV_X: + if (unlikely(SRC == 0)) + return 0; + do_div(DST, SRC); + CONT; + ALU_DIV_X: + if (unlikely(SRC == 0)) + return 0; + tmp = (u32) DST; + do_div(tmp, (u32) SRC); + DST = (u32) tmp; + CONT; + ALU64_DIV_K: + do_div(DST, IMM); + CONT; + ALU_DIV_K: + tmp = (u32) DST; + do_div(tmp, (u32) IMM); + DST = (u32) tmp; + CONT; + ALU_END_TO_BE: + switch (IMM) { + case 16: + DST = (__force u16) cpu_to_be16(DST); break; - case BPF_S_LD_H_ABS: - k = K; -load_h: - ptr = load_pointer(skb, k, 2, &tmp); - if (ptr != NULL) { - A = get_unaligned_be16(ptr); - continue; - } + case 32: + DST = (__force u32) cpu_to_be32(DST); break; - case BPF_S_LD_B_ABS: - k = K; -load_b: - ptr = load_pointer(skb, k, 1, &tmp); - if (ptr != NULL) { - A = *(u8 *)ptr; - continue; - } + case 64: + DST = (__force u64) cpu_to_be64(DST); + break; + } + CONT; + ALU_END_TO_LE: + switch (IMM) { + case 16: + DST = (__force u16) cpu_to_le16(DST); + break; + case 32: + DST = (__force u32) cpu_to_le32(DST); + break; + case 64: + DST = (__force u64) cpu_to_le64(DST); break; - case BPF_S_LD_W_LEN: - A = skb->len; - continue; - case BPF_S_LDX_W_LEN: - X = skb->len; - continue; - case BPF_S_LD_W_IND: - k = X + K; - goto load_w; - case BPF_S_LD_H_IND: - k = X + K; - goto load_h; - case BPF_S_LD_B_IND: - k = X + K; - goto load_b; - case BPF_S_LDX_B_MSH: - ptr = load_pointer(skb, K, 1, &tmp); - if (ptr != NULL) { - X = (*(u8 *)ptr & 0xf) << 2; - continue; - } - return 0; - case BPF_S_LD_IMM: - A = K; - continue; - case BPF_S_LDX_IMM: - X = K; - continue; - case BPF_S_LD_MEM: - A = mem[K]; - continue; - case BPF_S_LDX_MEM: - X = mem[K]; - continue; - case BPF_S_MISC_TAX: - X = A; - continue; - case BPF_S_MISC_TXA: - A = X; - continue; - case BPF_S_RET_K: - return K; - case BPF_S_RET_A: - return A; - case BPF_S_ST: - mem[K] = A; - continue; - case BPF_S_STX: - mem[K] = X; - continue; - default: - WARN_ON(1); - return 0; } + CONT; - /* - * Handle ancillary data, which are impossible - * (or very difficult) to get parsing packet contents. + /* CALL */ + JMP_CALL: + /* Function call scratches BPF_R1-BPF_R5 registers, + * preserves BPF_R6-BPF_R9, and stores return value + * into BPF_R0. */ - switch (k-SKF_AD_OFF) { - case SKF_AD_PROTOCOL: - A = ntohs(skb->protocol); - continue; - case SKF_AD_PKTTYPE: - A = skb->pkt_type; - continue; - case SKF_AD_IFINDEX: - if (!skb->dev) - return 0; - A = skb->dev->ifindex; - continue; - case SKF_AD_MARK: - A = skb->mark; - continue; - case SKF_AD_QUEUE: - A = skb->queue_mapping; - continue; - case SKF_AD_HATYPE: - if (!skb->dev) - return 0; - A = skb->dev->type; - continue; - case SKF_AD_RXHASH: - A = skb->rxhash; - continue; - case SKF_AD_CPU: - A = raw_smp_processor_id(); - continue; - case SKF_AD_NLATTR: { - struct nlattr *nla; - - if (skb_is_nonlinear(skb)) - return 0; - if (A > skb->len - sizeof(struct nlattr)) - return 0; - - nla = nla_find((struct nlattr *)&skb->data[A], - skb->len - A, X); - if (nla) - A = (void *)nla - (void *)skb->data; - else - A = 0; - continue; + BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, + BPF_R4, BPF_R5); + CONT; + + /* JMP */ + JMP_JA: + insn += insn->off; + CONT; + JMP_JEQ_X: + if (DST == SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JEQ_K: + if (DST == IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JNE_X: + if (DST != SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JNE_K: + if (DST != IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGT_X: + if (DST > SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGT_K: + if (DST > IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGE_X: + if (DST >= SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JGE_K: + if (DST >= IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGT_X: + if (((s64) DST) > ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGT_K: + if (((s64) DST) > ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGE_X: + if (((s64) DST) >= ((s64) SRC)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSGE_K: + if (((s64) DST) >= ((s64) IMM)) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSET_X: + if (DST & SRC) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_JSET_K: + if (DST & IMM) { + insn += insn->off; + CONT_JMP; + } + CONT; + JMP_EXIT: + return BPF_R0; + + /* STX and ST and LDX*/ +#define LDST(SIZEOP, SIZE) \ + STX_MEM_##SIZEOP: \ + *(SIZE *)(unsigned long) (DST + insn->off) = SRC; \ + CONT; \ + ST_MEM_##SIZEOP: \ + *(SIZE *)(unsigned long) (DST + insn->off) = IMM; \ + CONT; \ + LDX_MEM_##SIZEOP: \ + DST = *(SIZE *)(unsigned long) (SRC + insn->off); \ + CONT; + + LDST(B, u8) + LDST(H, u16) + LDST(W, u32) + LDST(DW, u64) +#undef LDST + STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */ + atomic_add((u32) SRC, (atomic_t *)(unsigned long) + (DST + insn->off)); + CONT; + STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */ + atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) + (DST + insn->off)); + CONT; + LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */ + off = IMM; +load_word: + /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are + * only appearing in the programs where ctx == + * skb. All programs keep 'ctx' in regs[BPF_REG_CTX] + * == BPF_R6, sk_convert_filter() saves it in BPF_R6, + * internal BPF verifier will check that BPF_R6 == + * ctx. + * + * BPF_ABS and BPF_IND are wrappers of function calls, + * so they scratch BPF_R1-BPF_R5 registers, preserve + * BPF_R6-BPF_R9, and store return value into BPF_R0. + * + * Implicit input: + * ctx == skb == BPF_R6 == CTX + * + * Explicit input: + * SRC == any register + * IMM == 32-bit immediate + * + * Output: + * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness + */ + + ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp); + if (likely(ptr != NULL)) { + BPF_R0 = get_unaligned_be32(ptr); + CONT; + } + + return 0; + LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */ + off = IMM; +load_half: + ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp); + if (likely(ptr != NULL)) { + BPF_R0 = get_unaligned_be16(ptr); + CONT; + } + + return 0; + LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */ + off = IMM; +load_byte: + ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp); + if (likely(ptr != NULL)) { + BPF_R0 = *(u8 *)ptr; + CONT; + } + + return 0; + LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */ + off = IMM + SRC; + goto load_word; + LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */ + off = IMM + SRC; + goto load_half; + LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */ + off = IMM + SRC; + goto load_byte; + + default_label: + /* If we ever reach this, we have a bug somewhere. */ + WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); + return 0; +} + +/* Helper to find the offset of pkt_type in sk_buff structure. We want + * to make sure its still a 3bit field starting at a byte boundary; + * taken from arch/x86/net/bpf_jit_comp.c. + */ +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_TYPE_MAX (7 << 5) +#else +#define PKT_TYPE_MAX 7 +#endif +static unsigned int pkt_type_offset(void) +{ + struct sk_buff skb_probe = { .pkt_type = ~0, }; + u8 *ct = (u8 *) &skb_probe; + unsigned int off; + + for (off = 0; off < sizeof(struct sk_buff); off++) { + if (ct[off] == PKT_TYPE_MAX) + return off; + } + + pr_err_once("Please fix %s, as pkt_type couldn't be found!\n", __func__); + return -1; +} + +static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +{ + return __skb_get_poff((struct sk_buff *)(unsigned long) ctx); +} + +static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; + struct nlattr *nla; + + if (skb_is_nonlinear(skb)) + return 0; + + if (skb->len < sizeof(struct nlattr)) + return 0; + + if (a > skb->len - sizeof(struct nlattr)) + return 0; + + nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x); + if (nla) + return (void *) nla - (void *) skb->data; + + return 0; +} + +static u64 __skb_get_nlattr_nest(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; + struct nlattr *nla; + + if (skb_is_nonlinear(skb)) + return 0; + + if (skb->len < sizeof(struct nlattr)) + return 0; + + if (a > skb->len - sizeof(struct nlattr)) + return 0; + + nla = (struct nlattr *) &skb->data[a]; + if (nla->nla_len > skb->len - a) + return 0; + + nla = nla_find_nested(nla, x); + if (nla) + return (void *) nla - (void *) skb->data; + + return 0; +} + +static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +{ + return raw_smp_processor_id(); +} + +/* note that this only generates 32-bit random numbers */ +static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +{ + return prandom_u32(); +} + +static bool convert_bpf_extensions(struct sock_filter *fp, + struct sock_filter_int **insnp) +{ + struct sock_filter_int *insn = *insnp; + + switch (fp->k) { + case SKF_AD_OFF + SKF_AD_PROTOCOL: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + + /* A = *(u16 *) (CTX + offsetof(protocol)) */ + *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, protocol)); + /* A = ntohs(A) [emitting a nop or swap16] */ + *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); + break; + + case SKF_AD_OFF + SKF_AD_PKTTYPE: + *insn = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX, + pkt_type_offset()); + if (insn->off < 0) + return false; + insn++; + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX); +#ifdef __BIG_ENDIAN_BITFIELD + insn++; + *insn = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 5); +#endif + break; + + case SKF_AD_OFF + SKF_AD_IFINDEX: + case SKF_AD_OFF + SKF_AD_HATYPE: + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); + BUILD_BUG_ON(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)) < 0); + + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + BPF_REG_TMP, BPF_REG_CTX, + offsetof(struct sk_buff, dev)); + /* if (tmp != 0) goto pc + 1 */ + *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); + *insn++ = BPF_EXIT_INSN(); + if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP, + offsetof(struct net_device, ifindex)); + else + *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP, + offsetof(struct net_device, type)); + break; + + case SKF_AD_OFF + SKF_AD_MARK: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, mark)); + break; + + case SKF_AD_OFF + SKF_AD_RXHASH: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, hash)); + break; + + case SKF_AD_OFF + SKF_AD_QUEUE: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + + *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, queue_mapping)); + break; + + case SKF_AD_OFF + SKF_AD_VLAN_TAG: + case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); + + /* A = *(u16 *) (CTX + offsetof(vlan_tci)) */ + *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, vlan_tci)); + if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) { + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, + ~VLAN_TAG_PRESENT); + } else { + /* A >>= 12 */ + *insn++ = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12); + /* A &= 1 */ + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 1); } - case SKF_AD_NLATTR_NEST: { - struct nlattr *nla; - - if (skb_is_nonlinear(skb)) - return 0; - if (A > skb->len - sizeof(struct nlattr)) - return 0; - - nla = (struct nlattr *)&skb->data[A]; - if (nla->nla_len > A - skb->len) - return 0; - - nla = nla_find_nested(nla, X); - if (nla) - A = (void *)nla - (void *)skb->data; - else - A = 0; - continue; + break; + + case SKF_AD_OFF + SKF_AD_PAY_OFFSET: + case SKF_AD_OFF + SKF_AD_NLATTR: + case SKF_AD_OFF + SKF_AD_NLATTR_NEST: + case SKF_AD_OFF + SKF_AD_CPU: + case SKF_AD_OFF + SKF_AD_RANDOM: + /* arg1 = CTX */ + *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); + /* arg2 = A */ + *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A); + /* arg3 = X */ + *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X); + /* Emit call(arg1=CTX, arg2=A, arg3=X) */ + switch (fp->k) { + case SKF_AD_OFF + SKF_AD_PAY_OFFSET: + *insn = BPF_EMIT_CALL(__skb_get_pay_offset); + break; + case SKF_AD_OFF + SKF_AD_NLATTR: + *insn = BPF_EMIT_CALL(__skb_get_nlattr); + break; + case SKF_AD_OFF + SKF_AD_NLATTR_NEST: + *insn = BPF_EMIT_CALL(__skb_get_nlattr_nest); + break; + case SKF_AD_OFF + SKF_AD_CPU: + *insn = BPF_EMIT_CALL(__get_raw_cpu_id); + break; + case SKF_AD_OFF + SKF_AD_RANDOM: + *insn = BPF_EMIT_CALL(__get_random_u32); + break; } + break; + + case SKF_AD_OFF + SKF_AD_ALU_XOR_X: + /* A ^= X */ + *insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X); + break; + + default: + /* This is just a dummy call to avoid letting the compiler + * evict __bpf_call_base() as an optimization. Placed here + * where no-one bothers. + */ + BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0); + return false; + } + + *insnp = insn; + return true; +} + +/** + * sk_convert_filter - convert filter program + * @prog: the user passed filter program + * @len: the length of the user passed filter program + * @new_prog: buffer where converted program will be stored + * @new_len: pointer to store length of converted program + * + * Remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style. + * Conversion workflow: + * + * 1) First pass for calculating the new program length: + * sk_convert_filter(old_prog, old_len, NULL, &new_len) + * + * 2) 2nd pass to remap in two passes: 1st pass finds new + * jump offsets, 2nd pass remapping: + * new_prog = kmalloc(sizeof(struct sock_filter_int) * new_len); + * sk_convert_filter(old_prog, old_len, new_prog, &new_len); + * + * User BPF's register A is mapped to our BPF register 6, user BPF + * register X is mapped to BPF register 7; frame pointer is always + * register 10; Context 'void *ctx' is stored in register 1, that is, + * for socket filters: ctx == 'struct sk_buff *', for seccomp: + * ctx == 'struct seccomp_data *'. + */ +int sk_convert_filter(struct sock_filter *prog, int len, + struct sock_filter_int *new_prog, int *new_len) +{ + int new_flen = 0, pass = 0, target, i; + struct sock_filter_int *new_insn; + struct sock_filter *fp; + int *addrs = NULL; + u8 bpf_src; + + BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK); + BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); + + if (len <= 0 || len > BPF_MAXINSNS) + return -EINVAL; + + if (new_prog) { + addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL); + if (!addrs) + return -ENOMEM; + } + +do_pass: + new_insn = new_prog; + fp = prog; + + if (new_insn) + *new_insn = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); + new_insn++; + + for (i = 0; i < len; fp++, i++) { + struct sock_filter_int tmp_insns[6] = { }; + struct sock_filter_int *insn = tmp_insns; + + if (addrs) + addrs[i] = new_insn - new_prog; + + switch (fp->code) { + /* All arithmetic insns and skb loads map as-is. */ + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU | BPF_MOD | BPF_K: + case BPF_ALU | BPF_NEG: + case BPF_LD | BPF_ABS | BPF_W: + case BPF_LD | BPF_ABS | BPF_H: + case BPF_LD | BPF_ABS | BPF_B: + case BPF_LD | BPF_IND | BPF_W: + case BPF_LD | BPF_IND | BPF_H: + case BPF_LD | BPF_IND | BPF_B: + /* Check for overloaded BPF extension and + * directly convert it if found, otherwise + * just move on with mapping. + */ + if (BPF_CLASS(fp->code) == BPF_LD && + BPF_MODE(fp->code) == BPF_ABS && + convert_bpf_extensions(fp, &insn)) + break; + + *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); + break; + + /* Jump transformation cannot use BPF block macros + * everywhere as offset calculation and target updates + * require a bit more work than the rest, i.e. jump + * opcodes map as-is, but offsets need adjustment. + */ + +#define BPF_EMIT_JMP \ + do { \ + if (target >= len || target < 0) \ + goto err; \ + insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0; \ + /* Adjust pc relative offset for 2nd or 3rd insn. */ \ + insn->off -= insn - tmp_insns; \ + } while (0) + + case BPF_JMP | BPF_JA: + target = i + fp->k + 1; + insn->code = fp->code; + BPF_EMIT_JMP; + break; + + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) { + /* BPF immediates are signed, zero extend + * immediate into tmp register and use it + * in compare insn. + */ + *insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k); + + insn->dst_reg = BPF_REG_A; + insn->src_reg = BPF_REG_TMP; + bpf_src = BPF_X; + } else { + insn->dst_reg = BPF_REG_A; + insn->src_reg = BPF_REG_X; + insn->imm = fp->k; + bpf_src = BPF_SRC(fp->code); + } + + /* Common case where 'jump_false' is next insn. */ + if (fp->jf == 0) { + insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; + target = i + fp->jt + 1; + BPF_EMIT_JMP; + break; + } + + /* Convert JEQ into JNE when 'jump_true' is next insn. */ + if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) { + insn->code = BPF_JMP | BPF_JNE | bpf_src; + target = i + fp->jf + 1; + BPF_EMIT_JMP; + break; + } + + /* Other jumps are mapped into two insns: Jxx and JA. */ + target = i + fp->jt + 1; + insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; + BPF_EMIT_JMP; + insn++; + + insn->code = BPF_JMP | BPF_JA; + target = i + fp->jf + 1; + BPF_EMIT_JMP; + break; + + /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ + case BPF_LDX | BPF_MSH | BPF_B: + /* tmp = A */ + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A); + /* A = BPF_R0 = *(u8 *) (skb->data + K) */ + *insn++ = BPF_LD_ABS(BPF_B, fp->k); + /* A &= 0xf */ + *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); + /* A <<= 2 */ + *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); + /* X = A */ + *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); + /* A = tmp */ + *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); + break; + + /* RET_K, RET_A are remaped into 2 insns. */ + case BPF_RET | BPF_A: + case BPF_RET | BPF_K: + *insn++ = BPF_MOV32_RAW(BPF_RVAL(fp->code) == BPF_K ? + BPF_K : BPF_X, BPF_REG_0, + BPF_REG_A, fp->k); + *insn = BPF_EXIT_INSN(); + break; + + /* Store to stack. */ + case BPF_ST: + case BPF_STX: + *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) == + BPF_ST ? BPF_REG_A : BPF_REG_X, + -(BPF_MEMWORDS - fp->k) * 4); + break; + + /* Load from stack. */ + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, BPF_REG_FP, + -(BPF_MEMWORDS - fp->k) * 4); + break; + + /* A = K or X = K */ + case BPF_LD | BPF_IMM: + case BPF_LDX | BPF_IMM: + *insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, fp->k); + break; + + /* X = A */ + case BPF_MISC | BPF_TAX: + *insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); + break; + + /* A = X */ + case BPF_MISC | BPF_TXA: + *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X); + break; + + /* A = skb->len or X = skb->len */ + case BPF_LD | BPF_W | BPF_LEN: + case BPF_LDX | BPF_W | BPF_LEN: + *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? + BPF_REG_A : BPF_REG_X, BPF_REG_CTX, + offsetof(struct sk_buff, len)); + break; + + /* Access seccomp_data fields. */ + case BPF_LDX | BPF_ABS | BPF_W: + /* A = *(u32 *) (ctx + K) */ + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); + break; + + /* Unkown instruction. */ default: - return 0; + goto err; } + + insn++; + if (new_prog) + memcpy(new_insn, tmp_insns, + sizeof(*insn) * (insn - tmp_insns)); + new_insn += insn - tmp_insns; + } + + if (!new_prog) { + /* Only calculating new length. */ + *new_len = new_insn - new_prog; + return 0; + } + + pass++; + if (new_flen != new_insn - new_prog) { + new_flen = new_insn - new_prog; + if (pass > 2) + goto err; + goto do_pass; } + kfree(addrs); + BUG_ON(*new_len != new_flen); return 0; +err: + kfree(addrs); + return -EINVAL; } -EXPORT_SYMBOL(sk_run_filter); -/* - * Security : +/* Security: + * * A BPF program is able to use 16 cells of memory to store intermediate - * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()) + * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()). + * * As we dont want to clear mem[] array for each packet going through * sk_run_filter(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure - * a malicious user doesnt try to abuse us. + * a malicious user doesn't try to abuse us. */ static int check_load_and_stores(struct sock_filter *filter, int flen) { - u16 *masks, memvalid = 0; /* one bit per cell, 16 cells */ + u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ int pc, ret = 0; BUILD_BUG_ON(BPF_MEMWORDS > 16); - masks = kmalloc(flen * sizeof(*masks), GFP_KERNEL); + + masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL); if (!masks) return -ENOMEM; + memset(masks, 0xff, flen * sizeof(*masks)); for (pc = 0; pc < flen; pc++) { memvalid &= masks[pc]; switch (filter[pc].code) { - case BPF_S_ST: - case BPF_S_STX: + case BPF_ST: + case BPF_STX: memvalid |= (1 << filter[pc].k); break; - case BPF_S_LD_MEM: - case BPF_S_LDX_MEM: + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: if (!(memvalid & (1 << filter[pc].k))) { ret = -EINVAL; goto error; } break; - case BPF_S_JMP_JA: - /* a jump must set masks on target */ + case BPF_JMP | BPF_JA: + /* A jump must set masks on target */ masks[pc + 1 + filter[pc].k] &= memvalid; memvalid = ~0; break; - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JEQ_X: - case BPF_S_JMP_JGE_K: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JSET_X: - case BPF_S_JMP_JSET_K: - /* a jump must set masks on targets */ + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + /* A jump must set masks on targets */ masks[pc + 1 + filter[pc].jt] &= memvalid; masks[pc + 1 + filter[pc].jf] &= memvalid; memvalid = ~0; @@ -480,6 +1147,72 @@ error: return ret; } +static bool chk_code_allowed(u16 code_to_probe) +{ + static const bool codes[] = { + /* 32 bit ALU operations */ + [BPF_ALU | BPF_ADD | BPF_K] = true, + [BPF_ALU | BPF_ADD | BPF_X] = true, + [BPF_ALU | BPF_SUB | BPF_K] = true, + [BPF_ALU | BPF_SUB | BPF_X] = true, + [BPF_ALU | BPF_MUL | BPF_K] = true, + [BPF_ALU | BPF_MUL | BPF_X] = true, + [BPF_ALU | BPF_DIV | BPF_K] = true, + [BPF_ALU | BPF_DIV | BPF_X] = true, + [BPF_ALU | BPF_MOD | BPF_K] = true, + [BPF_ALU | BPF_MOD | BPF_X] = true, + [BPF_ALU | BPF_AND | BPF_K] = true, + [BPF_ALU | BPF_AND | BPF_X] = true, + [BPF_ALU | BPF_OR | BPF_K] = true, + [BPF_ALU | BPF_OR | BPF_X] = true, + [BPF_ALU | BPF_XOR | BPF_K] = true, + [BPF_ALU | BPF_XOR | BPF_X] = true, + [BPF_ALU | BPF_LSH | BPF_K] = true, + [BPF_ALU | BPF_LSH | BPF_X] = true, + [BPF_ALU | BPF_RSH | BPF_K] = true, + [BPF_ALU | BPF_RSH | BPF_X] = true, + [BPF_ALU | BPF_NEG] = true, + /* Load instructions */ + [BPF_LD | BPF_W | BPF_ABS] = true, + [BPF_LD | BPF_H | BPF_ABS] = true, + [BPF_LD | BPF_B | BPF_ABS] = true, + [BPF_LD | BPF_W | BPF_LEN] = true, + [BPF_LD | BPF_W | BPF_IND] = true, + [BPF_LD | BPF_H | BPF_IND] = true, + [BPF_LD | BPF_B | BPF_IND] = true, + [BPF_LD | BPF_IMM] = true, + [BPF_LD | BPF_MEM] = true, + [BPF_LDX | BPF_W | BPF_LEN] = true, + [BPF_LDX | BPF_B | BPF_MSH] = true, + [BPF_LDX | BPF_IMM] = true, + [BPF_LDX | BPF_MEM] = true, + /* Store instructions */ + [BPF_ST] = true, + [BPF_STX] = true, + /* Misc instructions */ + [BPF_MISC | BPF_TAX] = true, + [BPF_MISC | BPF_TXA] = true, + /* Return instructions */ + [BPF_RET | BPF_K] = true, + [BPF_RET | BPF_A] = true, + /* Jump instructions */ + [BPF_JMP | BPF_JA] = true, + [BPF_JMP | BPF_JEQ | BPF_K] = true, + [BPF_JMP | BPF_JEQ | BPF_X] = true, + [BPF_JMP | BPF_JGE | BPF_K] = true, + [BPF_JMP | BPF_JGE | BPF_X] = true, + [BPF_JMP | BPF_JGT | BPF_K] = true, + [BPF_JMP | BPF_JGT | BPF_X] = true, + [BPF_JMP | BPF_JSET | BPF_K] = true, + [BPF_JMP | BPF_JSET | BPF_X] = true, + }; + + if (code_to_probe >= ARRAY_SIZE(codes)) + return false; + + return codes[code_to_probe]; +} + /** * sk_chk_filter - verify socket filter code * @filter: filter to verify @@ -494,146 +1227,354 @@ error: * * Returns 0 if the rule set is legal or -EINVAL if not. */ -int sk_chk_filter(struct sock_filter *filter, int flen) +int sk_chk_filter(struct sock_filter *filter, unsigned int flen) { - /* - * Valid instructions are initialized to non-0. - * Invalid instructions are initialized to 0. - */ - static const u8 codes[] = { - [BPF_ALU|BPF_ADD|BPF_K] = BPF_S_ALU_ADD_K, - [BPF_ALU|BPF_ADD|BPF_X] = BPF_S_ALU_ADD_X, - [BPF_ALU|BPF_SUB|BPF_K] = BPF_S_ALU_SUB_K, - [BPF_ALU|BPF_SUB|BPF_X] = BPF_S_ALU_SUB_X, - [BPF_ALU|BPF_MUL|BPF_K] = BPF_S_ALU_MUL_K, - [BPF_ALU|BPF_MUL|BPF_X] = BPF_S_ALU_MUL_X, - [BPF_ALU|BPF_DIV|BPF_X] = BPF_S_ALU_DIV_X, - [BPF_ALU|BPF_AND|BPF_K] = BPF_S_ALU_AND_K, - [BPF_ALU|BPF_AND|BPF_X] = BPF_S_ALU_AND_X, - [BPF_ALU|BPF_OR|BPF_K] = BPF_S_ALU_OR_K, - [BPF_ALU|BPF_OR|BPF_X] = BPF_S_ALU_OR_X, - [BPF_ALU|BPF_LSH|BPF_K] = BPF_S_ALU_LSH_K, - [BPF_ALU|BPF_LSH|BPF_X] = BPF_S_ALU_LSH_X, - [BPF_ALU|BPF_RSH|BPF_K] = BPF_S_ALU_RSH_K, - [BPF_ALU|BPF_RSH|BPF_X] = BPF_S_ALU_RSH_X, - [BPF_ALU|BPF_NEG] = BPF_S_ALU_NEG, - [BPF_LD|BPF_W|BPF_ABS] = BPF_S_LD_W_ABS, - [BPF_LD|BPF_H|BPF_ABS] = BPF_S_LD_H_ABS, - [BPF_LD|BPF_B|BPF_ABS] = BPF_S_LD_B_ABS, - [BPF_LD|BPF_W|BPF_LEN] = BPF_S_LD_W_LEN, - [BPF_LD|BPF_W|BPF_IND] = BPF_S_LD_W_IND, - [BPF_LD|BPF_H|BPF_IND] = BPF_S_LD_H_IND, - [BPF_LD|BPF_B|BPF_IND] = BPF_S_LD_B_IND, - [BPF_LD|BPF_IMM] = BPF_S_LD_IMM, - [BPF_LDX|BPF_W|BPF_LEN] = BPF_S_LDX_W_LEN, - [BPF_LDX|BPF_B|BPF_MSH] = BPF_S_LDX_B_MSH, - [BPF_LDX|BPF_IMM] = BPF_S_LDX_IMM, - [BPF_MISC|BPF_TAX] = BPF_S_MISC_TAX, - [BPF_MISC|BPF_TXA] = BPF_S_MISC_TXA, - [BPF_RET|BPF_K] = BPF_S_RET_K, - [BPF_RET|BPF_A] = BPF_S_RET_A, - [BPF_ALU|BPF_DIV|BPF_K] = BPF_S_ALU_DIV_K, - [BPF_LD|BPF_MEM] = BPF_S_LD_MEM, - [BPF_LDX|BPF_MEM] = BPF_S_LDX_MEM, - [BPF_ST] = BPF_S_ST, - [BPF_STX] = BPF_S_STX, - [BPF_JMP|BPF_JA] = BPF_S_JMP_JA, - [BPF_JMP|BPF_JEQ|BPF_K] = BPF_S_JMP_JEQ_K, - [BPF_JMP|BPF_JEQ|BPF_X] = BPF_S_JMP_JEQ_X, - [BPF_JMP|BPF_JGE|BPF_K] = BPF_S_JMP_JGE_K, - [BPF_JMP|BPF_JGE|BPF_X] = BPF_S_JMP_JGE_X, - [BPF_JMP|BPF_JGT|BPF_K] = BPF_S_JMP_JGT_K, - [BPF_JMP|BPF_JGT|BPF_X] = BPF_S_JMP_JGT_X, - [BPF_JMP|BPF_JSET|BPF_K] = BPF_S_JMP_JSET_K, - [BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X, - }; + bool anc_found; int pc; if (flen == 0 || flen > BPF_MAXINSNS) return -EINVAL; - /* check the filter code now */ + /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { struct sock_filter *ftest = &filter[pc]; - u16 code = ftest->code; - if (code >= ARRAY_SIZE(codes)) - return -EINVAL; - code = codes[code]; - if (!code) + /* May we actually operate on this code? */ + if (!chk_code_allowed(ftest->code)) return -EINVAL; + /* Some instructions need special checks */ - switch (code) { - case BPF_S_ALU_DIV_K: - /* check for division by zero */ + switch (ftest->code) { + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_MOD | BPF_K: + /* Check for division by zero */ if (ftest->k == 0) return -EINVAL; - ftest->k = reciprocal_value(ftest->k); break; - case BPF_S_LD_MEM: - case BPF_S_LDX_MEM: - case BPF_S_ST: - case BPF_S_STX: - /* check for invalid memory addresses */ + case BPF_LD | BPF_MEM: + case BPF_LDX | BPF_MEM: + case BPF_ST: + case BPF_STX: + /* Check for invalid memory addresses */ if (ftest->k >= BPF_MEMWORDS) return -EINVAL; break; - case BPF_S_JMP_JA: - /* - * Note, the large ftest->k might cause loops. + case BPF_JMP | BPF_JA: + /* Note, the large ftest->k might cause loops. * Compare this with conditional jumps below, * where offsets are limited. --ANK (981016) */ - if (ftest->k >= (unsigned)(flen-pc-1)) + if (ftest->k >= (unsigned int)(flen - pc - 1)) return -EINVAL; break; - case BPF_S_JMP_JEQ_K: - case BPF_S_JMP_JEQ_X: - case BPF_S_JMP_JGE_K: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JSET_X: - case BPF_S_JMP_JSET_K: - /* for conditionals both must be safe */ + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP | BPF_JSET | BPF_X: + /* Both conditionals must be safe */ if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; break; + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: + anc_found = false; + if (bpf_anc_helper(ftest) & BPF_ANC) + anc_found = true; + /* Ancillary operation unknown or unsupported */ + if (anc_found == false && ftest->k >= SKF_AD_OFF) + return -EINVAL; } - ftest->code = code; } - /* last instruction must be a RET code */ + /* Last instruction must be a RET code */ switch (filter[flen - 1].code) { - case BPF_S_RET_K: - case BPF_S_RET_A: + case BPF_RET | BPF_K: + case BPF_RET | BPF_A: return check_load_and_stores(filter, flen); } + return -EINVAL; } EXPORT_SYMBOL(sk_chk_filter); +static int sk_store_orig_filter(struct sk_filter *fp, + const struct sock_fprog *fprog) +{ + unsigned int fsize = sk_filter_proglen(fprog); + struct sock_fprog_kern *fkprog; + + fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL); + if (!fp->orig_prog) + return -ENOMEM; + + fkprog = fp->orig_prog; + fkprog->len = fprog->len; + fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL); + if (!fkprog->filter) { + kfree(fp->orig_prog); + return -ENOMEM; + } + + return 0; +} + +static void sk_release_orig_filter(struct sk_filter *fp) +{ + struct sock_fprog_kern *fprog = fp->orig_prog; + + if (fprog) { + kfree(fprog->filter); + kfree(fprog); + } +} + /** - * sk_filter_rcu_release - Release a socket filter by rcu_head + * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free */ -static void sk_filter_rcu_release(struct rcu_head *rcu) +static void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); + sk_release_orig_filter(fp); + sk_filter_free(fp); +} + +/** + * sk_filter_release - release a socket filter + * @fp: filter to remove + * + * Remove a filter from a socket and release its resources. + */ +static void sk_filter_release(struct sk_filter *fp) +{ + if (atomic_dec_and_test(&fp->refcnt)) + call_rcu(&fp->rcu, sk_filter_release_rcu); +} + +void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) +{ + atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc); sk_filter_release(fp); } -static void sk_filter_delayed_uncharge(struct sock *sk, struct sk_filter *fp) +void sk_filter_charge(struct sock *sk, struct sk_filter *fp) +{ + atomic_inc(&fp->refcnt); + atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc); +} + +static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp, + struct sock *sk, + unsigned int len) +{ + struct sk_filter *fp_new; + + if (sk == NULL) + return krealloc(fp, len, GFP_KERNEL); + + fp_new = sock_kmalloc(sk, len, GFP_KERNEL); + if (fp_new) { + *fp_new = *fp; + /* As we're keeping orig_prog in fp_new along, + * we need to make sure we're not evicting it + * from the old fp. + */ + fp->orig_prog = NULL; + sk_filter_uncharge(sk, fp); + } + + return fp_new; +} + +static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, + struct sock *sk) +{ + struct sock_filter *old_prog; + struct sk_filter *old_fp; + int err, new_len, old_len = fp->len; + + /* We are free to overwrite insns et al right here as it + * won't be used at this point in time anymore internally + * after the migration to the internal BPF instruction + * representation. + */ + BUILD_BUG_ON(sizeof(struct sock_filter) != + sizeof(struct sock_filter_int)); + + /* Conversion cannot happen on overlapping memory areas, + * so we need to keep the user BPF around until the 2nd + * pass. At this time, the user BPF is stored in fp->insns. + */ + old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter), + GFP_KERNEL); + if (!old_prog) { + err = -ENOMEM; + goto out_err; + } + + /* 1st pass: calculate the new program length. */ + err = sk_convert_filter(old_prog, old_len, NULL, &new_len); + if (err) + goto out_err_free; + + /* Expand fp for appending the new filter representation. */ + old_fp = fp; + fp = __sk_migrate_realloc(old_fp, sk, sk_filter_size(new_len)); + if (!fp) { + /* The old_fp is still around in case we couldn't + * allocate new memory, so uncharge on that one. + */ + fp = old_fp; + err = -ENOMEM; + goto out_err_free; + } + + fp->len = new_len; + + /* 2nd pass: remap sock_filter insns into sock_filter_int insns. */ + err = sk_convert_filter(old_prog, old_len, fp->insnsi, &new_len); + if (err) + /* 2nd sk_convert_filter() can fail only if it fails + * to allocate memory, remapping must succeed. Note, + * that at this time old_fp has already been released + * by __sk_migrate_realloc(). + */ + goto out_err_free; + + sk_filter_select_runtime(fp); + + kfree(old_prog); + return fp; + +out_err_free: + kfree(old_prog); +out_err: + /* Rollback filter setup. */ + if (sk != NULL) + sk_filter_uncharge(sk, fp); + else + kfree(fp); + return ERR_PTR(err); +} + +void __weak bpf_int_jit_compile(struct sk_filter *prog) +{ +} + +/** + * sk_filter_select_runtime - select execution runtime for BPF program + * @fp: sk_filter populated with internal BPF program + * + * try to JIT internal BPF program, if JIT is not available select interpreter + * BPF program will be executed via SK_RUN_FILTER() macro + */ +void sk_filter_select_runtime(struct sk_filter *fp) +{ + fp->bpf_func = (void *) __sk_run_filter; + + /* Probe if internal BPF can be JITed */ + bpf_int_jit_compile(fp); +} +EXPORT_SYMBOL_GPL(sk_filter_select_runtime); + +/* free internal BPF program */ +void sk_filter_free(struct sk_filter *fp) { - unsigned int size = sk_filter_len(fp); + bpf_jit_free(fp); +} +EXPORT_SYMBOL_GPL(sk_filter_free); + +static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, + struct sock *sk) +{ + int err; + + fp->bpf_func = NULL; + fp->jited = 0; + + err = sk_chk_filter(fp->insns, fp->len); + if (err) { + if (sk != NULL) + sk_filter_uncharge(sk, fp); + else + kfree(fp); + return ERR_PTR(err); + } + + /* Probe if we can JIT compile the filter and if so, do + * the compilation of the filter. + */ + bpf_jit_compile(fp); - atomic_sub(size, &sk->sk_omem_alloc); - call_rcu_bh(&fp->rcu, sk_filter_rcu_release); + /* JIT compiler couldn't process this filter, so do the + * internal BPF translation for the optimized interpreter. + */ + if (!fp->jited) + fp = __sk_migrate_filter(fp, sk); + + return fp; } /** + * sk_unattached_filter_create - create an unattached filter + * @pfp: the unattached filter that is created + * @fprog: the filter program + * + * Create a filter independent of any socket. We first run some + * sanity checks on it to make sure it does not explode on us later. + * If an error occurs or there is insufficient memory for the filter + * a negative errno code is returned. On success the return is zero. + */ +int sk_unattached_filter_create(struct sk_filter **pfp, + struct sock_fprog_kern *fprog) +{ + unsigned int fsize = sk_filter_proglen(fprog); + struct sk_filter *fp; + + /* Make sure new filter is there and in the right amounts. */ + if (fprog->filter == NULL) + return -EINVAL; + + fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL); + if (!fp) + return -ENOMEM; + + memcpy(fp->insns, fprog->filter, fsize); + + atomic_set(&fp->refcnt, 1); + fp->len = fprog->len; + /* Since unattached filters are not copied back to user + * space through sk_get_filter(), we do not need to hold + * a copy here, and can spare us the work. + */ + fp->orig_prog = NULL; + + /* __sk_prepare_filter() already takes care of uncharging + * memory in case something goes wrong. + */ + fp = __sk_prepare_filter(fp, NULL); + if (IS_ERR(fp)) + return PTR_ERR(fp); + + *pfp = fp; + return 0; +} +EXPORT_SYMBOL_GPL(sk_unattached_filter_create); + +void sk_unattached_filter_destroy(struct sk_filter *fp) +{ + sk_filter_release(fp); +} +EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy); + +/** * sk_attach_filter - attach a socket filter * @fprog: the filter program * @sk: the socket to use @@ -646,36 +1587,49 @@ static void sk_filter_delayed_uncharge(struct sock *sk, struct sk_filter *fp) int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct sk_filter *fp, *old_fp; - unsigned int fsize = sizeof(struct sock_filter) * fprog->len; + unsigned int fsize = sk_filter_proglen(fprog); + unsigned int sk_fsize = sk_filter_size(fprog->len); int err; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) return -EINVAL; - fp = sock_kmalloc(sk, fsize+sizeof(*fp), GFP_KERNEL); + fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL); if (!fp) return -ENOMEM; + if (copy_from_user(fp->insns, fprog->filter, fsize)) { - sock_kfree_s(sk, fp, fsize+sizeof(*fp)); + sock_kfree_s(sk, fp, sk_fsize); return -EFAULT; } atomic_set(&fp->refcnt, 1); fp->len = fprog->len; - err = sk_chk_filter(fp->insns, fp->len); + err = sk_store_orig_filter(fp, fprog); if (err) { sk_filter_uncharge(sk, fp); - return err; + return -ENOMEM; } + /* __sk_prepare_filter() already takes care of uncharging + * memory in case something goes wrong. + */ + fp = __sk_prepare_filter(fp, sk); + if (IS_ERR(fp)) + return PTR_ERR(fp); + old_fp = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) - sk_filter_delayed_uncharge(sk, old_fp); + sk_filter_uncharge(sk, old_fp); + return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); @@ -685,13 +1639,57 @@ int sk_detach_filter(struct sock *sk) int ret = -ENOENT; struct sk_filter *filter; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + filter = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); if (filter) { - rcu_assign_pointer(sk->sk_filter, NULL); - sk_filter_delayed_uncharge(sk, filter); + RCU_INIT_POINTER(sk->sk_filter, NULL); + sk_filter_uncharge(sk, filter); ret = 0; } + return ret; } EXPORT_SYMBOL_GPL(sk_detach_filter); + +int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, + unsigned int len) +{ + struct sock_fprog_kern *fprog; + struct sk_filter *filter; + int ret = 0; + + lock_sock(sk); + filter = rcu_dereference_protected(sk->sk_filter, + sock_owned_by_user(sk)); + if (!filter) + goto out; + + /* We're copying the filter that has been originally attached, + * so no conversion/decode needed anymore. + */ + fprog = filter->orig_prog; + + ret = fprog->len; + if (!len) + /* User space only enquires number of filter blocks. */ + goto out; + + ret = -EINVAL; + if (len < fprog->len) + goto out; + + ret = -EFAULT; + if (copy_to_user(ubuf, fprog->filter, sk_filter_proglen(fprog))) + goto out; + + /* Instead of bytes, the API requests to return the number + * of filter blocks. + */ + ret = fprog->len; +out: + release_sock(sk); + return ret; +} diff --git a/net/core/flow.c b/net/core/flow.c index 127c8a7ffd6..a0348fde1fd 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -22,14 +22,16 @@ #include <linux/cpumask.h> #include <linux/mutex.h> #include <net/flow.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/security.h> +#include <net/net_namespace.h> struct flow_cache_entry { union { struct hlist_node hlist; struct list_head gc_list; } u; + struct net *net; u16 family; u8 dir; u32 genid; @@ -37,37 +39,14 @@ struct flow_cache_entry { struct flow_cache_object *object; }; -struct flow_cache_percpu { - struct hlist_head *hash_table; - int hash_count; - u32 hash_rnd; - int hash_rnd_recalc; - struct tasklet_struct flush_tasklet; -}; - struct flow_flush_info { struct flow_cache *cache; atomic_t cpuleft; struct completion completion; }; -struct flow_cache { - u32 hash_shift; - struct flow_cache_percpu __percpu *percpu; - struct notifier_block hotcpu_notifier; - int low_watermark; - int high_watermark; - struct timer_list rnd_timer; -}; - -atomic_t flow_cache_genid = ATOMIC_INIT(0); -EXPORT_SYMBOL(flow_cache_genid); -static struct flow_cache flow_cache_global; static struct kmem_cache *flow_cachep __read_mostly; -static DEFINE_SPINLOCK(flow_cache_gc_lock); -static LIST_HEAD(flow_cache_gc_list); - #define flow_cache_hash_size(cache) (1 << (cache)->hash_shift) #define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) @@ -83,16 +62,18 @@ static void flow_cache_new_hashrnd(unsigned long arg) add_timer(&fc->rnd_timer); } -static int flow_entry_valid(struct flow_cache_entry *fle) +static int flow_entry_valid(struct flow_cache_entry *fle, + struct netns_xfrm *xfrm) { - if (atomic_read(&flow_cache_genid) != fle->genid) + if (atomic_read(&xfrm->flow_cache_genid) != fle->genid) return 0; if (fle->object && !fle->object->ops->check(fle->object)) return 0; return 1; } -static void flow_entry_kill(struct flow_cache_entry *fle) +static void flow_entry_kill(struct flow_cache_entry *fle, + struct netns_xfrm *xfrm) { if (fle->object) fle->object->ops->delete(fle->object); @@ -103,26 +84,28 @@ static void flow_cache_gc_task(struct work_struct *work) { struct list_head gc_list; struct flow_cache_entry *fce, *n; + struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm, + flow_cache_gc_work); INIT_LIST_HEAD(&gc_list); - spin_lock_bh(&flow_cache_gc_lock); - list_splice_tail_init(&flow_cache_gc_list, &gc_list); - spin_unlock_bh(&flow_cache_gc_lock); + spin_lock_bh(&xfrm->flow_cache_gc_lock); + list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list); + spin_unlock_bh(&xfrm->flow_cache_gc_lock); list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) - flow_entry_kill(fce); + flow_entry_kill(fce, xfrm); } -static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task); static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, - int deleted, struct list_head *gc_list) + int deleted, struct list_head *gc_list, + struct netns_xfrm *xfrm) { if (deleted) { fcp->hash_count -= deleted; - spin_lock_bh(&flow_cache_gc_lock); - list_splice_tail(gc_list, &flow_cache_gc_list); - spin_unlock_bh(&flow_cache_gc_lock); - schedule_work(&flow_cache_gc_work); + spin_lock_bh(&xfrm->flow_cache_gc_lock); + list_splice_tail(gc_list, &xfrm->flow_cache_gc_list); + spin_unlock_bh(&xfrm->flow_cache_gc_lock); + schedule_work(&xfrm->flow_cache_gc_work); } } @@ -131,17 +114,19 @@ static void __flow_cache_shrink(struct flow_cache *fc, int shrink_to) { struct flow_cache_entry *fle; - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; + struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm, + flow_cache_global); for (i = 0; i < flow_cache_hash_size(fc); i++) { int saved = 0; - hlist_for_each_entry_safe(fle, entry, tmp, + hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { if (saved < shrink_to && - flow_entry_valid(fle)) { + flow_entry_valid(fle, xfrm)) { saved++; } else { deleted++; @@ -151,7 +136,7 @@ static void __flow_cache_shrink(struct flow_cache *fc, } } - flow_cache_queue_garbage(fcp, deleted, &gc_list); + flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm); } static void flow_cache_shrink(struct flow_cache *fc, @@ -172,31 +157,28 @@ static void flow_new_hash_rnd(struct flow_cache *fc, static u32 flow_hash_code(struct flow_cache *fc, struct flow_cache_percpu *fcp, - struct flowi *key) + const struct flowi *key, + size_t keysize) { - u32 *k = (u32 *) key; + const u32 *k = (const u32 *) key; + const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32); - return jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd) + return jhash2(k, length, fcp->hash_rnd) & (flow_cache_hash_size(fc) - 1); } -typedef unsigned long flow_compare_t; - /* I hear what you're saying, use memcmp. But memcmp cannot make - * important assumptions that we can here, such as alignment and - * constant size. + * important assumptions that we can here, such as alignment. */ -static int flow_key_compare(struct flowi *key1, struct flowi *key2) +static int flow_key_compare(const struct flowi *key1, const struct flowi *key2, + size_t keysize) { - flow_compare_t *k1, *k1_lim, *k2; - const int n_elem = sizeof(struct flowi) / sizeof(flow_compare_t); + const flow_compare_t *k1, *k1_lim, *k2; - BUILD_BUG_ON(sizeof(struct flowi) % sizeof(flow_compare_t)); + k1 = (const flow_compare_t *) key1; + k1_lim = k1 + keysize; - k1 = (flow_compare_t *) key1; - k1_lim = k1 + n_elem; - - k2 = (flow_compare_t *) key2; + k2 = (const flow_compare_t *) key2; do { if (*k1++ != *k2++) @@ -207,14 +189,14 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2) } struct flow_cache_object * -flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, +flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver, void *ctx) { - struct flow_cache *fc = &flow_cache_global; + struct flow_cache *fc = &net->xfrm.flow_cache_global; struct flow_cache_percpu *fcp; struct flow_cache_entry *fle, *tfle; - struct hlist_node *entry; struct flow_cache_object *flo; + size_t keysize; unsigned int hash; local_bh_disable(); @@ -222,6 +204,11 @@ flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, fle = NULL; flo = NULL; + + keysize = flow_key_size(family); + if (!keysize) + goto nocache; + /* Packet really early in init? Making flow_cache_init a * pre-smp initcall would solve this. --RR */ if (!fcp->hash_table) @@ -230,11 +217,12 @@ flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, if (fcp->hash_rnd_recalc) flow_new_hash_rnd(fc, fcp); - hash = flow_hash_code(fc, fcp, key); - hlist_for_each_entry(tfle, entry, &fcp->hash_table[hash], u.hlist) { - if (tfle->family == family && + hash = flow_hash_code(fc, fcp, key, keysize); + hlist_for_each_entry(tfle, &fcp->hash_table[hash], u.hlist) { + if (tfle->net == net && + tfle->family == family && tfle->dir == dir && - flow_key_compare(key, &tfle->key) == 0) { + flow_key_compare(key, &tfle->key, keysize) == 0) { fle = tfle; break; } @@ -246,14 +234,15 @@ flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC); if (fle) { + fle->net = net; fle->family = family; fle->dir = dir; - memcpy(&fle->key, key, sizeof(*key)); + memcpy(&fle->key, key, keysize * sizeof(flow_compare_t)); fle->object = NULL; hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]); fcp->hash_count++; } - } else if (likely(fle->genid == atomic_read(&flow_cache_genid))) { + } else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) { flo = fle->object; if (!flo) goto ret_object; @@ -274,13 +263,13 @@ nocache: } flo = resolver(net, key, family, dir, flo, ctx); if (fle) { - fle->genid = atomic_read(&flow_cache_genid); + fle->genid = atomic_read(&net->xfrm.flow_cache_genid); if (!IS_ERR(flo)) fle->object = flo; else fle->genid--; } else { - if (flo && !IS_ERR(flo)) + if (!IS_ERR_OR_NULL(flo)) flo->ops->delete(flo); } ret_object: @@ -295,15 +284,17 @@ static void flow_cache_flush_tasklet(unsigned long data) struct flow_cache *fc = info->cache; struct flow_cache_percpu *fcp; struct flow_cache_entry *fle; - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; + struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm, + flow_cache_global); fcp = this_cpu_ptr(fc->percpu); for (i = 0; i < flow_cache_hash_size(fc); i++) { - hlist_for_each_entry_safe(fle, entry, tmp, + hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { - if (flow_entry_valid(fle)) + if (flow_entry_valid(fle, xfrm)) continue; deleted++; @@ -312,47 +303,94 @@ static void flow_cache_flush_tasklet(unsigned long data) } } - flow_cache_queue_garbage(fcp, deleted, &gc_list); + flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm); if (atomic_dec_and_test(&info->cpuleft)) complete(&info->completion); } +/* + * Return whether a cpu needs flushing. Conservatively, we assume + * the presence of any entries means the core may require flushing, + * since the flow_cache_ops.check() function may assume it's running + * on the same core as the per-cpu cache component. + */ +static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu) +{ + struct flow_cache_percpu *fcp; + int i; + + fcp = per_cpu_ptr(fc->percpu, cpu); + for (i = 0; i < flow_cache_hash_size(fc); i++) + if (!hlist_empty(&fcp->hash_table[i])) + return 0; + return 1; +} + static void flow_cache_flush_per_cpu(void *data) { struct flow_flush_info *info = data; - int cpu; struct tasklet_struct *tasklet; - cpu = smp_processor_id(); - tasklet = &per_cpu_ptr(info->cache->percpu, cpu)->flush_tasklet; + tasklet = &this_cpu_ptr(info->cache->percpu)->flush_tasklet; tasklet->data = (unsigned long)info; tasklet_schedule(tasklet); } -void flow_cache_flush(void) +void flow_cache_flush(struct net *net) { struct flow_flush_info info; - static DEFINE_MUTEX(flow_flush_sem); + cpumask_var_t mask; + int i, self; + + /* Track which cpus need flushing to avoid disturbing all cores. */ + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return; + cpumask_clear(mask); /* Don't want cpus going down or up during this. */ get_online_cpus(); - mutex_lock(&flow_flush_sem); - info.cache = &flow_cache_global; - atomic_set(&info.cpuleft, num_online_cpus()); + mutex_lock(&net->xfrm.flow_flush_sem); + info.cache = &net->xfrm.flow_cache_global; + for_each_online_cpu(i) + if (!flow_cache_percpu_empty(info.cache, i)) + cpumask_set_cpu(i, mask); + atomic_set(&info.cpuleft, cpumask_weight(mask)); + if (atomic_read(&info.cpuleft) == 0) + goto done; + init_completion(&info.completion); local_bh_disable(); - smp_call_function(flow_cache_flush_per_cpu, &info, 0); - flow_cache_flush_tasklet((unsigned long)&info); + self = cpumask_test_and_clear_cpu(smp_processor_id(), mask); + on_each_cpu_mask(mask, flow_cache_flush_per_cpu, &info, 0); + if (self) + flow_cache_flush_tasklet((unsigned long)&info); local_bh_enable(); wait_for_completion(&info.completion); - mutex_unlock(&flow_flush_sem); + +done: + mutex_unlock(&net->xfrm.flow_flush_sem); put_online_cpus(); + free_cpumask_var(mask); } -static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) +static void flow_cache_flush_task(struct work_struct *work) +{ + struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm, + flow_cache_gc_work); + struct net *net = container_of(xfrm, struct net, xfrm); + + flow_cache_flush(net); +} + +void flow_cache_flush_deferred(struct net *net) +{ + schedule_work(&net->xfrm.flow_cache_flush_work); +} + +static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) { struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc); @@ -370,11 +408,12 @@ static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) return 0; } -static int __cpuinit flow_cache_cpu(struct notifier_block *nfb, +static int flow_cache_cpu(struct notifier_block *nfb, unsigned long action, void *hcpu) { - struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier); + struct flow_cache *fc = container_of(nfb, struct flow_cache, + hotcpu_notifier); int res, cpu = (unsigned long) hcpu; struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); @@ -393,9 +432,20 @@ static int __cpuinit flow_cache_cpu(struct notifier_block *nfb, return NOTIFY_OK; } -static int __init flow_cache_init(struct flow_cache *fc) +int flow_cache_init(struct net *net) { int i; + struct flow_cache *fc = &net->xfrm.flow_cache_global; + + if (!flow_cachep) + flow_cachep = kmem_cache_create("flow_cache", + sizeof(struct flow_cache_entry), + 0, SLAB_PANIC, NULL); + spin_lock_init(&net->xfrm.flow_cache_gc_lock); + INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list); + INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task); + INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task); + mutex_init(&net->xfrm.flow_flush_sem); fc->hash_shift = 10; fc->low_watermark = 2 * flow_cache_hash_size(fc); @@ -405,14 +455,18 @@ static int __init flow_cache_init(struct flow_cache *fc) if (!fc->percpu) return -ENOMEM; + cpu_notifier_register_begin(); + for_each_online_cpu(i) { if (flow_cache_cpu_prepare(fc, i)) - return -ENOMEM; + goto err; } fc->hotcpu_notifier = (struct notifier_block){ .notifier_call = flow_cache_cpu, }; - register_hotcpu_notifier(&fc->hotcpu_notifier); + __register_hotcpu_notifier(&fc->hotcpu_notifier); + + cpu_notifier_register_done(); setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd, (unsigned long) fc); @@ -420,15 +474,38 @@ static int __init flow_cache_init(struct flow_cache *fc) add_timer(&fc->rnd_timer); return 0; + +err: + for_each_possible_cpu(i) { + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i); + kfree(fcp->hash_table); + fcp->hash_table = NULL; + } + + cpu_notifier_register_done(); + + free_percpu(fc->percpu); + fc->percpu = NULL; + + return -ENOMEM; } +EXPORT_SYMBOL(flow_cache_init); -static int __init flow_cache_init_global(void) +void flow_cache_fini(struct net *net) { - flow_cachep = kmem_cache_create("flow_cache", - sizeof(struct flow_cache_entry), - 0, SLAB_PANIC, NULL); + int i; + struct flow_cache *fc = &net->xfrm.flow_cache_global; - return flow_cache_init(&flow_cache_global); -} + del_timer_sync(&fc->rnd_timer); + unregister_hotcpu_notifier(&fc->hotcpu_notifier); -module_init(flow_cache_init_global); + for_each_possible_cpu(i) { + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i); + kfree(fcp->hash_table); + fcp->hash_table = NULL; + } + + free_percpu(fc->percpu); + fc->percpu = NULL; +} +EXPORT_SYMBOL(flow_cache_fini); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c new file mode 100644 index 00000000000..107ed12a532 --- /dev/null +++ b/net/core/flow_dissector.c @@ -0,0 +1,405 @@ +#include <linux/skbuff.h> +#include <linux/export.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/if_vlan.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <linux/igmp.h> +#include <linux/icmp.h> +#include <linux/sctp.h> +#include <linux/dccp.h> +#include <linux/if_tunnel.h> +#include <linux/if_pppox.h> +#include <linux/ppp_defs.h> +#include <net/flow_keys.h> + +/* copy saddr & daddr, possibly using 64bit load/store + * Equivalent to : flow->src = iph->saddr; + * flow->dst = iph->daddr; + */ +static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph) +{ + BUILD_BUG_ON(offsetof(typeof(*flow), dst) != + offsetof(typeof(*flow), src) + sizeof(flow->src)); + memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst)); +} + +/** + * skb_flow_get_ports - extract the upper layer ports and return them + * @skb: buffer to extract the ports from + * @thoff: transport header offset + * @ip_proto: protocol for which to get port offset + * + * The function will try to retrieve the ports at offset thoff + poff where poff + * is the protocol port offset returned from proto_ports_offset + */ +__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto) +{ + int poff = proto_ports_offset(ip_proto); + + if (poff >= 0) { + __be32 *ports, _ports; + + ports = skb_header_pointer(skb, thoff + poff, + sizeof(_ports), &_ports); + if (ports) + return *ports; + } + + return 0; +} +EXPORT_SYMBOL(skb_flow_get_ports); + +bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow) +{ + int nhoff = skb_network_offset(skb); + u8 ip_proto; + __be16 proto = skb->protocol; + + memset(flow, 0, sizeof(*flow)); + +again: + switch (proto) { + case htons(ETH_P_IP): { + const struct iphdr *iph; + struct iphdr _iph; +ip: + iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); + if (!iph || iph->ihl < 5) + return false; + nhoff += iph->ihl * 4; + + ip_proto = iph->protocol; + if (ip_is_fragment(iph)) + ip_proto = 0; + + iph_to_flow_copy_addrs(flow, iph); + break; + } + case htons(ETH_P_IPV6): { + const struct ipv6hdr *iph; + struct ipv6hdr _iph; +ipv6: + iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); + if (!iph) + return false; + + ip_proto = iph->nexthdr; + flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr); + flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr); + nhoff += sizeof(struct ipv6hdr); + break; + } + case htons(ETH_P_8021AD): + case htons(ETH_P_8021Q): { + const struct vlan_hdr *vlan; + struct vlan_hdr _vlan; + + vlan = skb_header_pointer(skb, nhoff, sizeof(_vlan), &_vlan); + if (!vlan) + return false; + + proto = vlan->h_vlan_encapsulated_proto; + nhoff += sizeof(*vlan); + goto again; + } + case htons(ETH_P_PPP_SES): { + struct { + struct pppoe_hdr hdr; + __be16 proto; + } *hdr, _hdr; + hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr); + if (!hdr) + return false; + proto = hdr->proto; + nhoff += PPPOE_SES_HLEN; + switch (proto) { + case htons(PPP_IP): + goto ip; + case htons(PPP_IPV6): + goto ipv6; + default: + return false; + } + } + default: + return false; + } + + switch (ip_proto) { + case IPPROTO_GRE: { + struct gre_hdr { + __be16 flags; + __be16 proto; + } *hdr, _hdr; + + hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr); + if (!hdr) + return false; + /* + * Only look inside GRE if version zero and no + * routing + */ + if (!(hdr->flags & (GRE_VERSION|GRE_ROUTING))) { + proto = hdr->proto; + nhoff += 4; + if (hdr->flags & GRE_CSUM) + nhoff += 4; + if (hdr->flags & GRE_KEY) + nhoff += 4; + if (hdr->flags & GRE_SEQ) + nhoff += 4; + if (proto == htons(ETH_P_TEB)) { + const struct ethhdr *eth; + struct ethhdr _eth; + + eth = skb_header_pointer(skb, nhoff, + sizeof(_eth), &_eth); + if (!eth) + return false; + proto = eth->h_proto; + nhoff += sizeof(*eth); + } + goto again; + } + break; + } + case IPPROTO_IPIP: + proto = htons(ETH_P_IP); + goto ip; + case IPPROTO_IPV6: + proto = htons(ETH_P_IPV6); + goto ipv6; + default: + break; + } + + flow->ip_proto = ip_proto; + flow->ports = skb_flow_get_ports(skb, nhoff, ip_proto); + flow->thoff = (u16) nhoff; + + return true; +} +EXPORT_SYMBOL(skb_flow_dissect); + +static u32 hashrnd __read_mostly; +static __always_inline void __flow_hash_secret_init(void) +{ + net_get_random_once(&hashrnd, sizeof(hashrnd)); +} + +static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c) +{ + __flow_hash_secret_init(); + return jhash_3words(a, b, c, hashrnd); +} + +static __always_inline u32 __flow_hash_1word(u32 a) +{ + __flow_hash_secret_init(); + return jhash_1word(a, hashrnd); +} + +/* + * __skb_get_hash: calculate a flow hash based on src/dst addresses + * and src/dst port numbers. Sets hash in skb to non-zero hash value + * on success, zero indicates no valid hash. Also, sets l4_hash in skb + * if hash is a canonical 4-tuple hash over transport ports. + */ +void __skb_get_hash(struct sk_buff *skb) +{ + struct flow_keys keys; + u32 hash; + + if (!skb_flow_dissect(skb, &keys)) + return; + + if (keys.ports) + skb->l4_hash = 1; + + /* get a consistent hash (same value on both flow directions) */ + if (((__force u32)keys.dst < (__force u32)keys.src) || + (((__force u32)keys.dst == (__force u32)keys.src) && + ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) { + swap(keys.dst, keys.src); + swap(keys.port16[0], keys.port16[1]); + } + + hash = __flow_hash_3words((__force u32)keys.dst, + (__force u32)keys.src, + (__force u32)keys.ports); + if (!hash) + hash = 1; + + skb->hash = hash; +} +EXPORT_SYMBOL(__skb_get_hash); + +/* + * Returns a Tx hash based on the given packet descriptor a Tx queues' number + * to be used as a distribution range. + */ +u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, + unsigned int num_tx_queues) +{ + u32 hash; + u16 qoffset = 0; + u16 qcount = num_tx_queues; + + if (skb_rx_queue_recorded(skb)) { + hash = skb_get_rx_queue(skb); + while (unlikely(hash >= num_tx_queues)) + hash -= num_tx_queues; + return hash; + } + + if (dev->num_tc) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; + qcount = dev->tc_to_txq[tc].count; + } + + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol; + hash = __flow_hash_1word(hash); + + return (u16) (((u64) hash * qcount) >> 32) + qoffset; +} +EXPORT_SYMBOL(__skb_tx_hash); + +/* __skb_get_poff() returns the offset to the payload as far as it could + * be dissected. The main user is currently BPF, so that we can dynamically + * truncate packets without needing to push actual payload to the user + * space and can analyze headers only, instead. + */ +u32 __skb_get_poff(const struct sk_buff *skb) +{ + struct flow_keys keys; + u32 poff = 0; + + if (!skb_flow_dissect(skb, &keys)) + return 0; + + poff += keys.thoff; + switch (keys.ip_proto) { + case IPPROTO_TCP: { + const struct tcphdr *tcph; + struct tcphdr _tcph; + + tcph = skb_header_pointer(skb, poff, sizeof(_tcph), &_tcph); + if (!tcph) + return poff; + + poff += max_t(u32, sizeof(struct tcphdr), tcph->doff * 4); + break; + } + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + poff += sizeof(struct udphdr); + break; + /* For the rest, we do not really care about header + * extensions at this point for now. + */ + case IPPROTO_ICMP: + poff += sizeof(struct icmphdr); + break; + case IPPROTO_ICMPV6: + poff += sizeof(struct icmp6hdr); + break; + case IPPROTO_IGMP: + poff += sizeof(struct igmphdr); + break; + case IPPROTO_DCCP: + poff += sizeof(struct dccp_hdr); + break; + case IPPROTO_SCTP: + poff += sizeof(struct sctphdr); + break; + } + + return poff; +} + +static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +{ +#ifdef CONFIG_XPS + struct xps_dev_maps *dev_maps; + struct xps_map *map; + int queue_index = -1; + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + map = rcu_dereference( + dev_maps->cpu_map[raw_smp_processor_id()]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else { + u32 hash; + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol ^ + skb->hash; + hash = __flow_hash_1word(hash); + queue_index = map->queues[ + ((u64)hash * map->len) >> 32]; + } + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + } + rcu_read_unlock(); + + return queue_index; +#else + return -1; +#endif +} + +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + int queue_index = sk_tx_queue_get(sk); + + if (queue_index < 0 || skb->ooo_okay || + queue_index >= dev->real_num_tx_queues) { + int new_index = get_xps_queue(dev, skb); + if (new_index < 0) + new_index = skb_tx_hash(dev, skb); + + if (queue_index != new_index && sk && + rcu_access_pointer(sk->sk_dst_cache)) + sk_tx_queue_set(sk, new_index); + + queue_index = new_index; + } + + return queue_index; +} + +struct netdev_queue *netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb, + void *accel_priv) +{ + int queue_index = 0; + + if (dev->real_num_tx_queues != 1) { + const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) + queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + __netdev_pick_tx); + else + queue_index = __netdev_pick_tx(dev, skb); + + if (!accel_priv) + queue_index = netdev_cap_txqueue(dev, queue_index); + } + + skb_set_queue_mapping(skb, queue_index); + return netdev_get_tx_queue(dev, queue_index); +} diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 7c2373321b7..6b5b6e7013c 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -14,7 +14,6 @@ */ #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> @@ -83,7 +82,7 @@ struct gen_estimator { struct list_head list; struct gnet_stats_basic_packed *bstats; - struct gnet_stats_rate_est *rate_est; + struct gnet_stats_rate_est64 *rate_est; spinlock_t *stats_lock; int ewma_log; u64 last_bytes; @@ -168,7 +167,7 @@ static void gen_add_node(struct gen_estimator *est) static struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats, - const struct gnet_stats_rate_est *rate_est) + const struct gnet_stats_rate_est64 *rate_est) { struct rb_node *p = est_root.rb_node; @@ -204,7 +203,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats * */ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_rate_est *rate_est, + struct gnet_stats_rate_est64 *rate_est, spinlock_t *stats_lock, struct nlattr *opt) { @@ -249,13 +248,6 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, } EXPORT_SYMBOL(gen_new_estimator); -static void __gen_kill_estimator(struct rcu_head *head) -{ - struct gen_estimator *e = container_of(head, - struct gen_estimator, e_rcu); - kfree(e); -} - /** * gen_kill_estimator - remove a rate estimator * @bstats: basic statistics @@ -266,7 +258,7 @@ static void __gen_kill_estimator(struct rcu_head *head) * Note : Caller should respect an RCU grace period before freeing stats_lock */ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_rate_est *rate_est) + struct gnet_stats_rate_est64 *rate_est) { struct gen_estimator *e; @@ -279,7 +271,7 @@ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, write_unlock(&est_lock); list_del_rcu(&e->list); - call_rcu(&e->e_rcu, __gen_kill_estimator); + kfree_rcu(e, e_rcu); } spin_unlock_bh(&est_tree_lock); } @@ -298,7 +290,7 @@ EXPORT_SYMBOL(gen_kill_estimator); * Returns 0 on success or a negative error code. */ int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, - struct gnet_stats_rate_est *rate_est, + struct gnet_stats_rate_est64 *rate_est, spinlock_t *stats_lock, struct nlattr *opt) { gen_kill_estimator(bstats, rate_est); @@ -314,7 +306,7 @@ EXPORT_SYMBOL(gen_replace_estimator); * Returns true if estimator is active, and false if not. */ bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, - const struct gnet_stats_rate_est *rate_est) + const struct gnet_stats_rate_est64 *rate_est) { bool res; diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 0452eb27a27..9d3d9e78397 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -27,7 +27,8 @@ static inline int gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size) { - NLA_PUT(d->skb, type, size, buf); + if (nla_put(d->skb, type, size, buf)) + goto nla_put_failure; return 0; nla_put_failure: @@ -142,18 +143,30 @@ EXPORT_SYMBOL(gnet_stats_copy_basic); int gnet_stats_copy_rate_est(struct gnet_dump *d, const struct gnet_stats_basic_packed *b, - struct gnet_stats_rate_est *r) + struct gnet_stats_rate_est64 *r) { + struct gnet_stats_rate_est est; + int res; + if (b && !gen_estimator_active(b, r)) return 0; + est.bps = min_t(u64, UINT_MAX, r->bps); + /* we have some time before reaching 2^32 packets per second */ + est.pps = r->pps; + if (d->compat_tc_stats) { - d->tc_stats.bps = r->bps; - d->tc_stats.pps = r->pps; + d->tc_stats.bps = est.bps; + d->tc_stats.pps = est.pps; } - if (d->tail) - return gnet_stats_copy(d, TCA_STATS_RATE_EST, r, sizeof(*r)); + if (d->tail) { + res = gnet_stats_copy(d, TCA_STATS_RATE_EST, &est, sizeof(est)); + if (res < 0 || est.bps == r->bps) + return res; + /* emit 64bit stats only if needed */ + return gnet_stats_copy(d, TCA_STATS_RATE_EST64, r, sizeof(*r)); + } return 0; } diff --git a/net/core/iovec.c b/net/core/iovec.c index c40f27e7d20..e1ec45ab1e6 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -35,11 +35,11 @@ * in any case. */ -int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) +int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode) { int size, ct, err; - if (m->msg_namelen) { + if (m->msg_name && m->msg_namelen) { if (mode == VERIFY_READ) { void __user *namep; namep = (void __user __force *) m->msg_name; @@ -51,6 +51,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, m->msg_name = address; } else { m->msg_name = NULL; + m->msg_namelen = 0; } size = m->msg_iovlen * sizeof(struct iovec); @@ -74,111 +75,6 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, } /* - * Copy kernel to iovec. Returns -EFAULT on error. - * - * Note: this modifies the original iovec. - */ - -int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len) -{ - while (len > 0) { - if (iov->iov_len) { - int copy = min_t(unsigned int, iov->iov_len, len); - if (copy_to_user(iov->iov_base, kdata, copy)) - return -EFAULT; - kdata += copy; - len -= copy; - iov->iov_len -= copy; - iov->iov_base += copy; - } - iov++; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_toiovec); - -/* - * Copy kernel to iovec. Returns -EFAULT on error. - */ - -int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata, - int offset, int len) -{ - int copy; - for (; len > 0; ++iov) { - /* Skip over the finished iovecs */ - if (unlikely(offset >= iov->iov_len)) { - offset -= iov->iov_len; - continue; - } - copy = min_t(unsigned int, iov->iov_len - offset, len); - if (copy_to_user(iov->iov_base + offset, kdata, copy)) - return -EFAULT; - offset = 0; - kdata += copy; - len -= copy; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_toiovecend); - -/* - * Copy iovec to kernel. Returns -EFAULT on error. - * - * Note: this modifies the original iovec. - */ - -int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len) -{ - while (len > 0) { - if (iov->iov_len) { - int copy = min_t(unsigned int, len, iov->iov_len); - if (copy_from_user(kdata, iov->iov_base, copy)) - return -EFAULT; - len -= copy; - kdata += copy; - iov->iov_base += copy; - iov->iov_len -= copy; - } - iov++; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_fromiovec); - -/* - * Copy iovec from kernel. Returns -EFAULT on error. - */ - -int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, - int offset, int len) -{ - /* Skip over the finished iovecs */ - while (offset >= iov->iov_len) { - offset -= iov->iov_len; - iov++; - } - - while (len > 0) { - u8 __user *base = iov->iov_base + offset; - int copy = min_t(unsigned int, len, iov->iov_len - offset); - - offset = 0; - if (copy_from_user(kdata, base, copy)) - return -EFAULT; - len -= copy; - kdata += copy; - iov++; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_fromiovecend); - -/* * And now for the all-in-one: copy and checksum from a user iovec * directly to a datagram * Calls to csum_partial but the last must be in 32 bit chunks @@ -262,3 +158,27 @@ out_fault: goto out; } EXPORT_SYMBOL(csum_partial_copy_fromiovecend); + +unsigned long iov_pages(const struct iovec *iov, int offset, + unsigned long nr_segs) +{ + unsigned long seg, base; + int pages = 0, len, size; + + while (nr_segs && (offset >= iov->iov_len)) { + offset -= iov->iov_len; + ++iov; + --nr_segs; + } + + for (seg = 0; seg < nr_segs; seg++) { + base = (unsigned long)iov[seg].iov_base + offset; + len = iov[seg].iov_len - offset; + size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT; + pages += size; + offset = 0; + } + + return pages; +} +EXPORT_SYMBOL(iov_pages); diff --git a/net/core/kmap_skb.h b/net/core/kmap_skb.h deleted file mode 100644 index 283c2b993fb..00000000000 --- a/net/core/kmap_skb.h +++ /dev/null @@ -1,19 +0,0 @@ -#include <linux/highmem.h> - -static inline void *kmap_skb_frag(const skb_frag_t *frag) -{ -#ifdef CONFIG_HIGHMEM - BUG_ON(in_irq()); - - local_bh_disable(); -#endif - return kmap_atomic(frag->page, KM_SKB_DATA_SOFTIRQ); -} - -static inline void kunmap_skb_frag(void *vaddr) -{ - kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ); -#ifdef CONFIG_HIGHMEM - local_bh_enable(); -#endif -} diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 01a1101b593..bd0767e6b2b 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -76,10 +76,26 @@ static void rfc2863_policy(struct net_device *dev) } +void linkwatch_init_dev(struct net_device *dev) +{ + /* Handle pre-registration link state changes */ + if (!netif_carrier_ok(dev) || netif_dormant(dev)) + rfc2863_policy(dev); +} + + static bool linkwatch_urgent_event(struct net_device *dev) { - return netif_running(dev) && netif_carrier_ok(dev) && - qdisc_tx_changing(dev); + if (!netif_running(dev)) + return false; + + if (dev->ifindex != dev->iflink) + return true; + + if (dev->priv_flags & IFF_TEAM_PORT) + return true; + + return netif_carrier_ok(dev) && qdisc_tx_changing(dev); } @@ -115,22 +131,13 @@ static void linkwatch_schedule_work(int urgent) delay = 0; /* - * This is true if we've scheduled it immeditately or if we don't - * need an immediate execution and it's already pending. + * If urgent, schedule immediate execution; otherwise, don't + * override the existing timer. */ - if (schedule_delayed_work(&linkwatch_work, delay) == !delay) - return; - - /* Don't bother if there is nothing urgent. */ - if (!test_bit(LW_URGENT, &linkwatch_flags)) - return; - - /* It's already running which is good enough. */ - if (!cancel_delayed_work(&linkwatch_work)) - return; - - /* Otherwise we reschedule it again for immediate exection. */ - schedule_delayed_work(&linkwatch_work, 0); + if (test_bit(LW_URGENT, &linkwatch_flags)) + mod_delayed_work(system_wq, &linkwatch_work, 0); + else + schedule_delayed_work(&linkwatch_work, delay); } @@ -140,7 +147,7 @@ static void linkwatch_do_dev(struct net_device *dev) * Make sure the above read is complete since it can be * rewritten as soon as we clear the bit below. */ - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); /* We are about to handle this device, * so new events can be accepted diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8cc8f9a79db..ef31fef25e5 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -15,6 +15,8 @@ * Harald Welte Add neighbour cache statistics like rtstat */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> @@ -36,23 +38,16 @@ #include <linux/random.h> #include <linux/string.h> #include <linux/log2.h> +#include <linux/inetdevice.h> +#include <net/addrconf.h> +#define DEBUG #define NEIGH_DEBUG 1 - -#define NEIGH_PRINTK(x...) printk(x) -#define NEIGH_NOPRINTK(x...) do { ; } while(0) -#define NEIGH_PRINTK0 NEIGH_PRINTK -#define NEIGH_PRINTK1 NEIGH_NOPRINTK -#define NEIGH_PRINTK2 NEIGH_NOPRINTK - -#if NEIGH_DEBUG >= 1 -#undef NEIGH_PRINTK1 -#define NEIGH_PRINTK1 NEIGH_PRINTK -#endif -#if NEIGH_DEBUG >= 2 -#undef NEIGH_PRINTK2 -#define NEIGH_PRINTK2 NEIGH_PRINTK -#endif +#define neigh_dbg(level, fmt, ...) \ +do { \ + if (level <= NEIGH_DEBUG) \ + pr_debug(fmt, ##__VA_ARGS__); \ +} while (0) #define PNEIGH_HASHMASK 0xF @@ -99,7 +94,7 @@ static const struct file_operations neigh_stat_seq_fops; static DEFINE_RWLOCK(neigh_tbl_lock); -static int neigh_blackhole(struct sk_buff *skb) +static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) { kfree_skb(skb); return -ENETDOWN; @@ -122,7 +117,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) unsigned long neigh_rand_reach_time(unsigned long base) { - return base ? (net_random() % base) + (base >> 1) : 0; + return base ? (prandom_u32() % base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); @@ -138,7 +133,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - for (i = 0; i <= nht->hash_mask; i++) { + for (i = 0; i < (1 << nht->hash_shift); i++) { struct neighbour *n; struct neighbour __rcu **np; @@ -211,7 +206,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - for (i = 0; i <= nht->hash_mask; i++) { + for (i = 0; i < (1 << nht->hash_shift); i++) { struct neighbour *n; struct neighbour __rcu **np = &nht->hash_buckets[i]; @@ -238,13 +233,14 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) we must kill timers etc. and move it to safe state. */ - skb_queue_purge(&n->arp_queue); + __skb_queue_purge(&n->arp_queue); + n->arp_queue_len_bytes = 0; n->output = neigh_blackhole; if (n->nud_state & NUD_VALID) n->nud_state = NUD_NOARP; else n->nud_state = NUD_NONE; - NEIGH_PRINTK2("neigh %p is stray.\n", n); + neigh_dbg(2, "neigh %p is stray\n", n); } write_unlock(&n->lock); neigh_cleanup_and_release(n); @@ -273,7 +269,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) } EXPORT_SYMBOL(neigh_ifdown); -static struct neighbour *neigh_alloc(struct neigh_table *tbl) +static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev) { struct neighbour *n = NULL; unsigned long now = jiffies; @@ -288,16 +284,17 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl) goto out_entries; } - n = kmem_cache_zalloc(tbl->kmem_cachep, GFP_ATOMIC); + n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC); if (!n) goto out_entries; - skb_queue_head_init(&n->arp_queue); + __skb_queue_head_init(&n->arp_queue); rwlock_init(&n->lock); seqlock_init(&n->ha_lock); n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; + seqlock_init(&n->hh.hh_lock); n->parms = neigh_parms_clone(&tbl->parms); setup_timer(&n->timer, neigh_timer_handler, (unsigned long)n); @@ -313,11 +310,18 @@ out_entries: goto out; } -static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries) +static void neigh_get_hash_rnd(u32 *x) { - size_t size = entries * sizeof(struct neighbour *); + get_random_bytes(x, sizeof(*x)); + *x |= 1; +} + +static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) +{ + size_t size = (1 << shift) * sizeof(struct neighbour *); struct neigh_hash_table *ret; - struct neighbour **buckets; + struct neighbour __rcu **buckets; + int i; ret = kmalloc(sizeof(*ret), GFP_ATOMIC); if (!ret) @@ -325,16 +329,17 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries) if (size <= PAGE_SIZE) buckets = kzalloc(size, GFP_ATOMIC); else - buckets = (struct neighbour **) + buckets = (struct neighbour __rcu **) __get_free_pages(GFP_ATOMIC | __GFP_ZERO, get_order(size)); if (!buckets) { kfree(ret); return NULL; } - rcu_assign_pointer(ret->hash_buckets, buckets); - ret->hash_mask = entries - 1; - get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd)); + ret->hash_buckets = buckets; + ret->hash_shift = shift; + for (i = 0; i < NEIGH_NUM_HASH_RND; i++) + neigh_get_hash_rnd(&ret->hash_rnd[i]); return ret; } @@ -343,8 +348,8 @@ static void neigh_hash_free_rcu(struct rcu_head *head) struct neigh_hash_table *nht = container_of(head, struct neigh_hash_table, rcu); - size_t size = (nht->hash_mask + 1) * sizeof(struct neighbour *); - struct neighbour **buckets = nht->hash_buckets; + size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *); + struct neighbour __rcu **buckets = nht->hash_buckets; if (size <= PAGE_SIZE) kfree(buckets); @@ -354,21 +359,20 @@ static void neigh_hash_free_rcu(struct rcu_head *head) } static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl, - unsigned long new_entries) + unsigned long new_shift) { unsigned int i, hash; struct neigh_hash_table *new_nht, *old_nht; NEIGH_CACHE_STAT_INC(tbl, hash_grows); - BUG_ON(!is_power_of_2(new_entries)); old_nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - new_nht = neigh_hash_alloc(new_entries); + new_nht = neigh_hash_alloc(new_shift); if (!new_nht) return old_nht; - for (i = 0; i <= old_nht->hash_mask; i++) { + for (i = 0; i < (1 << old_nht->hash_shift); i++) { struct neighbour *n, *next; for (n = rcu_dereference_protected(old_nht->hash_buckets[i], @@ -378,7 +382,7 @@ static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl, hash = tbl->hash(n->primary_key, n->dev, new_nht->hash_rnd); - hash &= new_nht->hash_mask; + hash >>= (32 - new_nht->hash_shift); next = rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock)); @@ -407,7 +411,7 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask; + hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); n != NULL; @@ -437,7 +441,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) & nht->hash_mask; + hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) >> (32 - nht->hash_shift); for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); n != NULL; @@ -456,13 +460,13 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, } EXPORT_SYMBOL(neigh_lookup_nodev); -struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, - struct net_device *dev) +struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, + struct net_device *dev, bool want_ref) { u32 hash_val; int key_len = tbl->key_len; int error; - struct neighbour *n1, *rc, *n = neigh_alloc(tbl); + struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev); struct neigh_hash_table *nht; if (!n) { @@ -480,6 +484,14 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, goto out_neigh_release; } + if (dev->netdev_ops->ndo_neigh_construct) { + error = dev->netdev_ops->ndo_neigh_construct(n); + if (error < 0) { + rc = ERR_PTR(error); + goto out_neigh_release; + } + } + /* Device specific setup. */ if (n->parms->neigh_setup && (error = n->parms->neigh_setup(n)) < 0) { @@ -487,16 +499,16 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, goto out_neigh_release; } - n->confirmed = jiffies - (n->parms->base_reachable_time << 1); + n->confirmed = jiffies - (NEIGH_VAR(n->parms, BASE_REACHABLE_TIME) << 1); write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - if (atomic_read(&tbl->entries) > (nht->hash_mask + 1)) - nht = neigh_hash_grow(tbl, (nht->hash_mask + 1) << 1); + if (atomic_read(&tbl->entries) > (1 << nht->hash_shift)) + nht = neigh_hash_grow(tbl, nht->hash_shift + 1); - hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask; + hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); if (n->parms->dead) { rc = ERR_PTR(-EINVAL); @@ -509,20 +521,22 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, n1 = rcu_dereference_protected(n1->next, lockdep_is_held(&tbl->lock))) { if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) { - neigh_hold(n1); + if (want_ref) + neigh_hold(n1); rc = n1; goto out_tbl_unlock; } } n->dead = 0; - neigh_hold(n); + if (want_ref) + neigh_hold(n); rcu_assign_pointer(n->next, rcu_dereference_protected(nht->hash_buckets[hash_val], lockdep_is_held(&tbl->lock))); rcu_assign_pointer(nht->hash_buckets[hash_val], n); write_unlock_bh(&tbl->lock); - NEIGH_PRINTK2("neigh %p is created.\n", n); + neigh_dbg(2, "neigh %p is created\n", n); rc = n; out: return rc; @@ -532,7 +546,7 @@ out_neigh_release: neigh_release(n); goto out; } -EXPORT_SYMBOL(neigh_create); +EXPORT_SYMBOL(__neigh_create); static u32 pneigh_hash(const void *pkey, int key_len) { @@ -677,51 +691,40 @@ static inline void neigh_parms_put(struct neigh_parms *parms) neigh_parms_destroy(parms); } -static void neigh_destroy_rcu(struct rcu_head *head) -{ - struct neighbour *neigh = container_of(head, struct neighbour, rcu); - - kmem_cache_free(neigh->tbl->kmem_cachep, neigh); -} /* * neighbour must already be out of the table; * */ void neigh_destroy(struct neighbour *neigh) { - struct hh_cache *hh; + struct net_device *dev = neigh->dev; NEIGH_CACHE_STAT_INC(neigh->tbl, destroys); if (!neigh->dead) { - printk(KERN_WARNING - "Destroying alive neighbour %p\n", neigh); + pr_warn("Destroying alive neighbour %p\n", neigh); dump_stack(); return; } if (neigh_del_timer(neigh)) - printk(KERN_WARNING "Impossible event.\n"); + pr_warn("Impossible event\n"); - while ((hh = neigh->hh) != NULL) { - neigh->hh = hh->hh_next; - hh->hh_next = NULL; - - write_seqlock_bh(&hh->hh_lock); - hh->hh_output = neigh_blackhole; - write_sequnlock_bh(&hh->hh_lock); - hh_cache_put(hh); - } + write_lock_bh(&neigh->lock); + __skb_queue_purge(&neigh->arp_queue); + write_unlock_bh(&neigh->lock); + neigh->arp_queue_len_bytes = 0; - skb_queue_purge(&neigh->arp_queue); + if (dev->netdev_ops->ndo_neigh_destroy) + dev->netdev_ops->ndo_neigh_destroy(neigh); - dev_put(neigh->dev); + dev_put(dev); neigh_parms_put(neigh->parms); - NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh); + neigh_dbg(2, "neigh %p is destroyed\n", neigh); atomic_dec(&neigh->tbl->entries); - call_rcu(&neigh->rcu, neigh_destroy_rcu); + kfree_rcu(neigh, rcu); } EXPORT_SYMBOL(neigh_destroy); @@ -732,14 +735,9 @@ EXPORT_SYMBOL(neigh_destroy); */ static void neigh_suspect(struct neighbour *neigh) { - struct hh_cache *hh; - - NEIGH_PRINTK2("neigh %p is suspected.\n", neigh); + neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->output = neigh->ops->output; - - for (hh = neigh->hh; hh; hh = hh->hh_next) - hh->hh_output = neigh->ops->output; } /* Neighbour state is OK; @@ -749,14 +747,9 @@ static void neigh_suspect(struct neighbour *neigh) */ static void neigh_connect(struct neighbour *neigh) { - struct hh_cache *hh; - - NEIGH_PRINTK2("neigh %p is connected.\n", neigh); + neigh_dbg(2, "neigh %p is connected\n", neigh); neigh->output = neigh->ops->connected_output; - - for (hh = neigh->hh; hh; hh = hh->hh_next) - hh->hh_output = neigh->ops->hh_output; } static void neigh_periodic_work(struct work_struct *work) @@ -782,10 +775,13 @@ static void neigh_periodic_work(struct work_struct *work) tbl->last_rand = jiffies; for (p = &tbl->parms; p; p = p->next) p->reachable_time = - neigh_rand_reach_time(p->base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } - for (i = 0 ; i <= nht->hash_mask; i++) { + if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + goto out; + + for (i = 0 ; i < (1 << nht->hash_shift); i++) { np = &nht->hash_buckets[i]; while ((n = rcu_dereference_protected(*np, @@ -805,7 +801,7 @@ static void neigh_periodic_work(struct work_struct *work) if (atomic_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + n->parms->gc_staletime))) { + time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; n->dead = 1; write_unlock(&n->lock); @@ -824,22 +820,26 @@ next_elt: write_unlock_bh(&tbl->lock); cond_resched(); write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); } - /* Cycle through all hash buckets every base_reachable_time/2 ticks. - * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 - * base_reachable_time. +out: + /* Cycle through all hash buckets every BASE_REACHABLE_TIME/2 ticks. + * ARP entry timeouts range from 1/2 BASE_REACHABLE_TIME to 3/2 + * BASE_REACHABLE_TIME. */ - schedule_delayed_work(&tbl->gc_work, - tbl->parms.base_reachable_time >> 1); + queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, + NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1); write_unlock_bh(&tbl->lock); } static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; - return (n->nud_state & NUD_PROBE) ? - p->ucast_probes : - p->ucast_probes + p->app_probes + p->mcast_probes; + int max_probes = NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES); + if (!(n->nud_state & NUD_PROBE)) + max_probes += NEIGH_VAR(p, MCAST_PROBES); + return max_probes; } static void neigh_invalidate(struct neighbour *neigh) @@ -849,7 +849,7 @@ static void neigh_invalidate(struct neighbour *neigh) struct sk_buff *skb; NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); - NEIGH_PRINTK2("neigh %p is failed.\n", neigh); + neigh_dbg(2, "neigh %p is failed\n", neigh); neigh->updated = jiffies; /* It is very thin place. report_unreachable is very complicated @@ -863,7 +863,21 @@ static void neigh_invalidate(struct neighbour *neigh) neigh->ops->error_report(neigh, skb); write_lock(&neigh->lock); } - skb_queue_purge(&neigh->arp_queue); + __skb_queue_purge(&neigh->arp_queue); + neigh->arp_queue_len_bytes = 0; +} + +static void neigh_probe(struct neighbour *neigh) + __releases(neigh->lock) +{ + struct sk_buff *skb = skb_peek_tail(&neigh->arp_queue); + /* keep skb alive even if arp_queue overflows */ + if (skb) + skb = skb_copy(skb, GFP_ATOMIC); + write_unlock(&neigh->lock); + neigh->ops->solicit(neigh, skb); + atomic_inc(&neigh->probes); + kfree_skb(skb); } /* Called when a timer expires for a neighbour entry. */ @@ -872,7 +886,7 @@ static void neigh_timer_handler(unsigned long arg) { unsigned long now, next; struct neighbour *neigh = (struct neighbour *)arg; - unsigned state; + unsigned int state; int notify = 0; write_lock(&neigh->lock); @@ -881,27 +895,24 @@ static void neigh_timer_handler(unsigned long arg) now = jiffies; next = now + HZ; - if (!(state & NUD_IN_TIMER)) { -#ifndef CONFIG_SMP - printk(KERN_WARNING "neigh: timer & !nud_in_timer\n"); -#endif + if (!(state & NUD_IN_TIMER)) goto out; - } if (state & NUD_REACHABLE) { if (time_before_eq(now, neigh->confirmed + neigh->parms->reachable_time)) { - NEIGH_PRINTK2("neigh %p is still alive.\n", neigh); + neigh_dbg(2, "neigh %p is still alive\n", neigh); next = neigh->confirmed + neigh->parms->reachable_time; } else if (time_before_eq(now, - neigh->used + neigh->parms->delay_probe_time)) { - NEIGH_PRINTK2("neigh %p is delayed.\n", neigh); + neigh->used + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { + neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_suspect(neigh); - next = now + neigh->parms->delay_probe_time; + next = now + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME); } else { - NEIGH_PRINTK2("neigh %p is suspected.\n", neigh); + neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->nud_state = NUD_STALE; neigh->updated = jiffies; neigh_suspect(neigh); @@ -909,23 +920,24 @@ static void neigh_timer_handler(unsigned long arg) } } else if (state & NUD_DELAY) { if (time_before_eq(now, - neigh->confirmed + neigh->parms->delay_probe_time)) { - NEIGH_PRINTK2("neigh %p is now reachable.\n", neigh); + neigh->confirmed + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { + neigh_dbg(2, "neigh %p is now reachable\n", neigh); neigh->nud_state = NUD_REACHABLE; neigh->updated = jiffies; neigh_connect(neigh); notify = 1; next = neigh->confirmed + neigh->parms->reachable_time; } else { - NEIGH_PRINTK2("neigh %p is probed.\n", neigh); + neigh_dbg(2, "neigh %p is probed\n", neigh); neigh->nud_state = NUD_PROBE; neigh->updated = jiffies; atomic_set(&neigh->probes, 0); - next = now + neigh->parms->retrans_time; + next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } } else { /* NUD_PROBE|NUD_INCOMPLETE */ - next = now + neigh->parms->retrans_time; + next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && @@ -933,6 +945,7 @@ static void neigh_timer_handler(unsigned long arg) neigh->nud_state = NUD_FAILED; notify = 1; neigh_invalidate(neigh); + goto out; } if (neigh->nud_state & NUD_IN_TIMER) { @@ -942,14 +955,7 @@ static void neigh_timer_handler(unsigned long arg) neigh_hold(neigh); } if (neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) { - struct sk_buff *skb = skb_peek(&neigh->arp_queue); - /* keep skb alive even if arp_queue overflows */ - if (skb) - skb = skb_copy(skb, GFP_ATOMIC); - write_unlock(&neigh->lock); - neigh->ops->solicit(neigh, skb); - atomic_inc(&neigh->probes); - kfree_skb(skb); + neigh_probe(neigh); } else { out: write_unlock(&neigh->lock); @@ -964,7 +970,7 @@ out: int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { int rc; - unsigned long now; + bool immediate_probe = false; write_lock_bh(&neigh->lock); @@ -972,14 +978,19 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE)) goto out_unlock_bh; - now = jiffies; - if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { - if (neigh->parms->mcast_probes + neigh->parms->app_probes) { - atomic_set(&neigh->probes, neigh->parms->ucast_probes); + if (NEIGH_VAR(neigh->parms, MCAST_PROBES) + + NEIGH_VAR(neigh->parms, APP_PROBES)) { + unsigned long next, now = jiffies; + + atomic_set(&neigh->probes, + NEIGH_VAR(neigh->parms, UCAST_PROBES)); neigh->nud_state = NUD_INCOMPLETE; - neigh->updated = jiffies; - neigh_add_timer(neigh, now + 1); + neigh->updated = now; + next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), + HZ/2); + neigh_add_timer(neigh, next); + immediate_probe = true; } else { neigh->nud_state = NUD_FAILED; neigh->updated = jiffies; @@ -989,34 +1000,43 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) return 1; } } else if (neigh->nud_state & NUD_STALE) { - NEIGH_PRINTK2("neigh %p is delayed.\n", neigh); + neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; - neigh_add_timer(neigh, - jiffies + neigh->parms->delay_probe_time); + neigh_add_timer(neigh, jiffies + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME)); } if (neigh->nud_state == NUD_INCOMPLETE) { if (skb) { - if (skb_queue_len(&neigh->arp_queue) >= - neigh->parms->queue_len) { + while (neigh->arp_queue_len_bytes + skb->truesize > + NEIGH_VAR(neigh->parms, QUEUE_LEN_BYTES)) { struct sk_buff *buff; + buff = __skb_dequeue(&neigh->arp_queue); + if (!buff) + break; + neigh->arp_queue_len_bytes -= buff->truesize; kfree_skb(buff); NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards); } skb_dst_force(skb); __skb_queue_tail(&neigh->arp_queue, skb); + neigh->arp_queue_len_bytes += skb->truesize; } rc = 1; } out_unlock_bh: - write_unlock_bh(&neigh->lock); + if (immediate_probe) + neigh_probe(neigh); + else + write_unlock(&neigh->lock); + local_bh_enable(); return rc; } EXPORT_SYMBOL(__neigh_event_send); -static void neigh_update_hhs(const struct neighbour *neigh) +static void neigh_update_hhs(struct neighbour *neigh) { struct hh_cache *hh; void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *) @@ -1026,7 +1046,8 @@ static void neigh_update_hhs(const struct neighbour *neigh) update = neigh->dev->header_ops->cache_update; if (update) { - for (hh = neigh->hh; hh; hh = hh->hh_next) { + hh = &neigh->hh; + if (hh->hh_len) { write_seqlock_bh(&hh->hh_lock); update(hh, neigh->dev, neigh->ha); write_sequnlock_bh(&hh->hh_lock); @@ -1149,6 +1170,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh->parms->reachable_time : 0))); neigh->nud_state = new; + notify = 1; } if (lladdr != neigh->ha) { @@ -1158,7 +1180,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh_update_hhs(neigh); if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - - (neigh->parms->base_reachable_time << 1); + (NEIGH_VAR(neigh->parms, BASE_REACHABLE_TIME) << 1); notify = 1; } if (new == old) @@ -1174,15 +1196,34 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, while (neigh->nud_state & NUD_VALID && (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { - struct neighbour *n1 = neigh; + struct dst_entry *dst = skb_dst(skb); + struct neighbour *n2, *n1 = neigh; write_unlock_bh(&neigh->lock); - /* On shaper/eql skb->dst->neighbour != neigh :( */ - if (skb_dst(skb) && skb_dst(skb)->neighbour) - n1 = skb_dst(skb)->neighbour; - n1->output(skb); + + rcu_read_lock(); + + /* Why not just use 'neigh' as-is? The problem is that + * things such as shaper, eql, and sch_teql can end up + * using alternative, different, neigh objects to output + * the packet in the output path. So what we need to do + * here is re-lookup the top-level neigh in the path so + * we can reinject the packet there. + */ + n2 = NULL; + if (dst) { + n2 = dst_neigh_lookup_skb(dst, skb); + if (n2) + n1 = n2; + } + n1->output(n1, skb); + if (n2) + neigh_release(n2); + rcu_read_unlock(); + write_lock_bh(&neigh->lock); } - skb_queue_purge(&neigh->arp_queue); + __skb_queue_purge(&neigh->arp_queue); + neigh->arp_queue_len_bytes = 0; } out: if (update_isrouter) { @@ -1199,6 +1240,21 @@ out: } EXPORT_SYMBOL(neigh_update); +/* Update the neigh to listen temporarily for probe responses, even if it is + * in a NUD_FAILED state. The caller has to hold neigh->lock for writing. + */ +void __neigh_set_probe_once(struct neighbour *neigh) +{ + neigh->updated = jiffies; + if (!(neigh->nud_state & NUD_FAILED)) + return; + neigh->nud_state = NUD_INCOMPLETE; + atomic_set(&neigh->probes, neigh_max_probes(neigh)); + neigh_add_timer(neigh, + jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME)); +} +EXPORT_SYMBOL(__neigh_set_probe_once); + struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev) @@ -1212,67 +1268,21 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl, } EXPORT_SYMBOL(neigh_event_ns); -static inline bool neigh_hh_lookup(struct neighbour *n, struct dst_entry *dst, - __be16 protocol) -{ - struct hh_cache *hh; - - smp_rmb(); /* paired with smp_wmb() in neigh_hh_init() */ - for (hh = n->hh; hh; hh = hh->hh_next) { - if (hh->hh_type == protocol) { - atomic_inc(&hh->hh_refcnt); - if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL)) - hh_cache_put(hh); - return true; - } - } - return false; -} - /* called with read_lock_bh(&n->lock); */ -static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst, - __be16 protocol) +static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst) { - struct hh_cache *hh; struct net_device *dev = dst->dev; - - if (likely(neigh_hh_lookup(n, dst, protocol))) - return; - - /* slow path */ - hh = kzalloc(sizeof(*hh), GFP_ATOMIC); - if (!hh) - return; - - seqlock_init(&hh->hh_lock); - hh->hh_type = protocol; - atomic_set(&hh->hh_refcnt, 2); - - if (dev->header_ops->cache(n, hh)) { - kfree(hh); - return; - } + __be16 prot = dst->ops->protocol; + struct hh_cache *hh = &n->hh; write_lock_bh(&n->lock); - /* must check if another thread already did the insert */ - if (neigh_hh_lookup(n, dst, protocol)) { - kfree(hh); - goto end; - } - - if (n->nud_state & NUD_CONNECTED) - hh->hh_output = n->ops->hh_output; - else - hh->hh_output = n->ops->output; - - hh->hh_next = n->hh; - smp_wmb(); /* paired with smp_rmb() in neigh_hh_lookup() */ - n->hh = hh; + /* Only one thread can come in here and initialize the + * hh_cache entry. + */ + if (!hh->hh_len) + dev->header_ops->cache(n, hh, prot); - if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL)) - hh_cache_put(hh); -end: write_unlock_bh(&n->lock); } @@ -1281,7 +1291,7 @@ end: * but resolution is not made yet. */ -int neigh_compat_output(struct sk_buff *skb) +int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -1289,7 +1299,7 @@ int neigh_compat_output(struct sk_buff *skb) if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL, skb->len) < 0 && - dev->header_ops->rebuild(skb)) + dev_rebuild_header(skb)) return 0; return dev_queue_xmit(skb); @@ -1298,43 +1308,38 @@ EXPORT_SYMBOL(neigh_compat_output); /* Slow and careful. */ -int neigh_resolve_output(struct sk_buff *skb) +int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - struct neighbour *neigh; int rc = 0; - if (!dst || !(neigh = dst->neighbour)) + if (!dst) goto discard; - __skb_pull(skb, skb_network_offset(skb)); - if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; unsigned int seq; - if (dev->header_ops->cache && - !dst->hh && - !(dst->flags & DST_NOCACHE)) - neigh_hh_init(neigh, dst, dst->ops->protocol); + if (dev->header_ops->cache && !neigh->hh.hh_len) + neigh_hh_init(neigh, dst); do { + __skb_pull(skb, skb_network_offset(skb)); seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); } while (read_seqretry(&neigh->ha_lock, seq)); if (err >= 0) - rc = neigh->ops->queue_xmit(skb); + rc = dev_queue_xmit(skb); else goto out_kfree_skb; } out: return rc; discard: - NEIGH_PRINTK1("neigh_resolve_output: dst=%p neigh=%p\n", - dst, dst ? dst->neighbour : NULL); + neigh_dbg(1, "%s: dst=%p neigh=%p\n", __func__, dst, neigh); out_kfree_skb: rc = -EINVAL; kfree_skb(skb); @@ -1344,24 +1349,21 @@ EXPORT_SYMBOL(neigh_resolve_output); /* As fast as possible without hh cache */ -int neigh_connected_output(struct sk_buff *skb) +int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb) { - int err; - struct dst_entry *dst = skb_dst(skb); - struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; unsigned int seq; - - __skb_pull(skb, skb_network_offset(skb)); + int err; do { + __skb_pull(skb, skb_network_offset(skb)); seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); } while (read_seqretry(&neigh->ha_lock, seq)); if (err >= 0) - err = neigh->ops->queue_xmit(skb); + err = dev_queue_xmit(skb); else { err = -EINVAL; kfree_skb(skb); @@ -1370,6 +1372,12 @@ int neigh_connected_output(struct sk_buff *skb) } EXPORT_SYMBOL(neigh_connected_output); +int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb) +{ + return dev_queue_xmit(skb); +} +EXPORT_SYMBOL(neigh_direct_output); + static void neigh_proxy_process(unsigned long arg) { struct neigh_table *tbl = (struct neigh_table *)arg; @@ -1384,11 +1392,15 @@ static void neigh_proxy_process(unsigned long arg) if (tdif <= 0) { struct net_device *dev = skb->dev; + __skb_unlink(skb, &tbl->proxy_queue); - if (tbl->proxy_redo && netif_running(dev)) + if (tbl->proxy_redo && netif_running(dev)) { + rcu_read_lock(); tbl->proxy_redo(skb); - else + rcu_read_unlock(); + } else { kfree_skb(skb); + } dev_put(dev); } else if (!sched_next || tdif < sched_next) @@ -1404,9 +1416,11 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb) { unsigned long now = jiffies; - unsigned long sched_next = now + (net_random() % p->proxy_delay); - if (tbl->proxy_queue.qlen > p->proxy_qlen) { + unsigned long sched_next = now + (prandom_u32() % + NEIGH_VAR(p, PROXY_DELAY)); + + if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); return; } @@ -1434,7 +1448,7 @@ static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl, for (p = &tbl->parms; p; p = p->next) { if ((p->dev && p->dev->ifindex == ifindex && net_eq(neigh_parms_net(p), net)) || - (!p->dev && !ifindex)) + (!p->dev && !ifindex && net_eq(net, &init_net))) return p; } @@ -1444,34 +1458,34 @@ static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl, struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl) { - struct neigh_parms *p, *ref; + struct neigh_parms *p; struct net *net = dev_net(dev); const struct net_device_ops *ops = dev->netdev_ops; - ref = lookup_neigh_parms(tbl, net, 0); - if (!ref) - return NULL; - - p = kmemdup(ref, sizeof(*p), GFP_KERNEL); + p = kmemdup(&tbl->parms, sizeof(*p), GFP_KERNEL); if (p) { p->tbl = tbl; atomic_set(&p->refcnt, 1); p->reachable_time = - neigh_rand_reach_time(p->base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); + dev_hold(dev); + p->dev = dev; + write_pnet(&p->net, hold_net(net)); + p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { + release_net(net); + dev_put(dev); kfree(p); return NULL; } - dev_hold(dev); - p->dev = dev; - write_pnet(&p->net, hold_net(net)); - p->sysctl_table = NULL; write_lock_bh(&tbl->lock); p->next = tbl->parms.next; tbl->parms.next = p; write_unlock_bh(&tbl->lock); + + neigh_parms_data_state_cleanall(p); } return p; } @@ -1504,7 +1518,7 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) } } write_unlock_bh(&tbl->lock); - NEIGH_PRINTK1("neigh_parms_release: not found\n"); + neigh_dbg(1, "%s: not found\n", __func__); } EXPORT_SYMBOL(neigh_parms_release); @@ -1516,7 +1530,7 @@ static void neigh_parms_destroy(struct neigh_parms *parms) static struct lock_class_key neigh_table_proxy_queue_class; -void neigh_table_init_no_netlink(struct neigh_table *tbl) +static void neigh_table_init_no_netlink(struct neigh_table *tbl) { unsigned long now = jiffies; unsigned long phsize; @@ -1524,13 +1538,8 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) write_pnet(&tbl->parms.net, &init_net); atomic_set(&tbl->parms.refcnt, 1); tbl->parms.reachable_time = - neigh_rand_reach_time(tbl->parms.base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); - if (!tbl->kmem_cachep) - tbl->kmem_cachep = - kmem_cache_create(tbl->id, tbl->entry_size, 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, - NULL); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) panic("cannot create neighbour cache statistics"); @@ -1541,7 +1550,7 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) panic("cannot create neighbour proc dir entry"); #endif - tbl->nht = neigh_hash_alloc(8); + RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(3)); phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *); tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL); @@ -1549,9 +1558,16 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) if (!tbl->nht || !tbl->phash_buckets) panic("cannot allocate neighbour cache hashes"); + if (!tbl->entry_size) + tbl->entry_size = ALIGN(offsetof(struct neighbour, primary_key) + + tbl->key_len, NEIGH_PRIV_ALIGN); + else + WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); + rwlock_init(&tbl->lock); - INIT_DELAYED_WORK_DEFERRABLE(&tbl->gc_work, neigh_periodic_work); - schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); + INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); + queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, + tbl->parms.reachable_time); setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); @@ -1559,7 +1575,6 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) tbl->last_flush = now; tbl->last_rand = now + tbl->parms.reachable_time * 20; } -EXPORT_SYMBOL(neigh_table_init_no_netlink); void neigh_table_init(struct neigh_table *tbl) { @@ -1576,8 +1591,8 @@ void neigh_table_init(struct neigh_table *tbl) write_unlock(&neigh_tbl_lock); if (unlikely(tmp)) { - printk(KERN_ERR "NEIGH: Registering multiple tables for " - "family %d\n", tbl->family); + pr_err("Registering multiple tables for family %d\n", + tbl->family); dump_stack(); } } @@ -1593,7 +1608,7 @@ int neigh_table_clear(struct neigh_table *tbl) pneigh_queue_purge(&tbl->proxy_queue); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) - printk(KERN_CRIT "neighbour leakage\n"); + pr_crit("neighbour leakage\n"); write_lock(&neigh_tbl_lock); for (tp = &neigh_tables; *tp; tp = &(*tp)->next) { if (*tp == tbl) { @@ -1603,7 +1618,8 @@ int neigh_table_clear(struct neigh_table *tbl) } write_unlock(&neigh_tbl_lock); - call_rcu(&tbl->nht->rcu, neigh_hash_free_rcu); + call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu, + neigh_hash_free_rcu); tbl->nht = NULL; kfree(tbl->phash_buckets); @@ -1614,14 +1630,11 @@ int neigh_table_clear(struct neigh_table *tbl) free_percpu(tbl->stats); tbl->stats = NULL; - kmem_cache_destroy(tbl->kmem_cachep); - tbl->kmem_cachep = NULL; - return 0; } EXPORT_SYMBOL(neigh_table_clear); -static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ndmsg *ndm; @@ -1685,7 +1698,7 @@ out: return err; } -static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ndmsg *ndm; @@ -1791,25 +1804,36 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) if (nest == NULL) return -ENOBUFS; - if (parms->dev) - NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); - - NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); - NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); - NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); - NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); - NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); - NLA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); - NLA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); - NLA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, - parms->base_reachable_time); - NLA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); - NLA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); - NLA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); - NLA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); - NLA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); - NLA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); - + if ((parms->dev && + nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || + nla_put_u32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)) || + nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, + NEIGH_VAR(parms, QUEUE_LEN_BYTES)) || + /* approximative value for deprecated QUEUE_LEN (in packets) */ + nla_put_u32(skb, NDTPA_QUEUE_LEN, + NEIGH_VAR(parms, QUEUE_LEN_BYTES) / SKB_TRUESIZE(ETH_FRAME_LEN)) || + nla_put_u32(skb, NDTPA_PROXY_QLEN, NEIGH_VAR(parms, PROXY_QLEN)) || + nla_put_u32(skb, NDTPA_APP_PROBES, NEIGH_VAR(parms, APP_PROBES)) || + nla_put_u32(skb, NDTPA_UCAST_PROBES, + NEIGH_VAR(parms, UCAST_PROBES)) || + nla_put_u32(skb, NDTPA_MCAST_PROBES, + NEIGH_VAR(parms, MCAST_PROBES)) || + nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) || + nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, + NEIGH_VAR(parms, BASE_REACHABLE_TIME)) || + nla_put_msecs(skb, NDTPA_GC_STALETIME, + NEIGH_VAR(parms, GC_STALETIME)) || + nla_put_msecs(skb, NDTPA_DELAY_PROBE_TIME, + NEIGH_VAR(parms, DELAY_PROBE_TIME)) || + nla_put_msecs(skb, NDTPA_RETRANS_TIME, + NEIGH_VAR(parms, RETRANS_TIME)) || + nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, + NEIGH_VAR(parms, ANYCAST_DELAY)) || + nla_put_msecs(skb, NDTPA_PROXY_DELAY, + NEIGH_VAR(parms, PROXY_DELAY)) || + nla_put_msecs(skb, NDTPA_LOCKTIME, + NEIGH_VAR(parms, LOCKTIME))) + goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: @@ -1834,12 +1858,12 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; - NLA_PUT_STRING(skb, NDTA_NAME, tbl->id); - NLA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); - NLA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); - NLA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); - NLA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); - + if (nla_put_string(skb, NDTA_NAME, tbl->id) || + nla_put_msecs(skb, NDTA_GC_INTERVAL, tbl->gc_interval) || + nla_put_u32(skb, NDTA_THRESH1, tbl->gc_thresh1) || + nla_put_u32(skb, NDTA_THRESH2, tbl->gc_thresh2) || + nla_put_u32(skb, NDTA_THRESH3, tbl->gc_thresh3)) + goto nla_put_failure; { unsigned long now = jiffies; unsigned int flush_delta = now - tbl->last_flush; @@ -1856,11 +1880,12 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - ndc.ndtc_hash_rnd = nht->hash_rnd; - ndc.ndtc_hash_mask = nht->hash_mask; + ndc.ndtc_hash_rnd = nht->hash_rnd[0]; + ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1); rcu_read_unlock_bh(); - NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); + if (nla_put(skb, NDTA_CONFIG, sizeof(ndc), &ndc)) + goto nla_put_failure; } { @@ -1885,7 +1910,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, ndst.ndts_forced_gc_runs += st->forced_gc_runs; } - NLA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); + if (nla_put(skb, NDTA_STATS, sizeof(ndst), &ndst)) + goto nla_put_failure; } BUG_ON(tbl->parms.dev); @@ -1958,7 +1984,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_LOCKTIME] = { .type = NLA_U64 }, }; -static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct neigh_table *tbl; @@ -2022,45 +2048,68 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) switch (i) { case NDTPA_QUEUE_LEN: - p->queue_len = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, + nla_get_u32(tbp[i]) * + SKB_TRUESIZE(ETH_FRAME_LEN)); + break; + case NDTPA_QUEUE_LENBYTES: + NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, + nla_get_u32(tbp[i])); break; case NDTPA_PROXY_QLEN: - p->proxy_qlen = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, PROXY_QLEN, + nla_get_u32(tbp[i])); break; case NDTPA_APP_PROBES: - p->app_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, APP_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_UCAST_PROBES: - p->ucast_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, UCAST_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_MCAST_PROBES: - p->mcast_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, MCAST_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_BASE_REACHABLE_TIME: - p->base_reachable_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, BASE_REACHABLE_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_GC_STALETIME: - p->gc_staletime = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, GC_STALETIME, + nla_get_msecs(tbp[i])); break; case NDTPA_DELAY_PROBE_TIME: - p->delay_probe_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, DELAY_PROBE_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_RETRANS_TIME: - p->retrans_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, RETRANS_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_ANYCAST_DELAY: - p->anycast_delay = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, ANYCAST_DELAY, + nla_get_msecs(tbp[i])); break; case NDTPA_PROXY_DELAY: - p->proxy_delay = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, PROXY_DELAY, + nla_get_msecs(tbp[i])); break; case NDTPA_LOCKTIME: - p->locktime = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, LOCKTIME, + nla_get_msecs(tbp[i])); break; } } } + err = -ENOENT; + if ((tb[NDTA_THRESH1] || tb[NDTA_THRESH2] || + tb[NDTA_THRESH3] || tb[NDTA_GC_INTERVAL]) && + !net_eq(net, &init_net)) + goto errout_tbl_lock; + if (tb[NDTA_THRESH1]) tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]); @@ -2100,7 +2149,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) if (tidx < tbl_skip || (family && tbl->family != family)) continue; - if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).pid, + if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) <= 0) break; @@ -2113,7 +2162,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) goto next; if (neightbl_fill_param_info(skb, tbl, p, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) <= 0) @@ -2152,7 +2201,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, ndm->ndm_type = neigh->type; ndm->ndm_ifindex = neigh->dev->ifindex; - NLA_PUT(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key); + if (nla_put(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key)) + goto nla_put_failure; read_lock_bh(&neigh->lock); ndm->ndm_state = neigh->nud_state; @@ -2172,8 +2222,39 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; read_unlock_bh(&neigh->lock); - NLA_PUT_U32(skb, NDA_PROBES, atomic_read(&neigh->probes)); - NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); + if (nla_put_u32(skb, NDA_PROBES, atomic_read(&neigh->probes)) || + nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, + u32 pid, u32 seq, int type, unsigned int flags, + struct neigh_table *tbl) +{ + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); + if (nlh == NULL) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = tbl->family; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = pn->flags | NTF_PROXY; + ndm->ndm_type = RTN_UNICAST; + ndm->ndm_ifindex = pn->dev->ifindex; + ndm->ndm_state = NUD_NONE; + + if (nla_put(skb, NDA_DST, tbl->key_len, pn->key)) + goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -2200,9 +2281,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - for (h = 0; h <= nht->hash_mask; h++) { - if (h < s_h) - continue; + for (h = s_h; h < (1 << nht->hash_shift); h++) { if (h > s_h) s_idx = 0; for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0; @@ -2212,7 +2291,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, continue; if (idx < s_idx) goto next; - if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, + if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI) <= 0) { @@ -2231,22 +2310,77 @@ out: return rc; } +static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct pneigh_entry *n; + struct net *net = sock_net(skb->sk); + int rc, h, s_h = cb->args[3]; + int idx, s_idx = idx = cb->args[4]; + + read_lock_bh(&tbl->lock); + + for (h = s_h; h <= PNEIGH_HASHMASK; h++) { + if (h > s_h) + s_idx = 0; + for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { + if (dev_net(n->dev) != net) + continue; + if (idx < s_idx) + goto next; + if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI, tbl) <= 0) { + read_unlock_bh(&tbl->lock); + rc = -1; + goto out; + } + next: + idx++; + } + } + + read_unlock_bh(&tbl->lock); + rc = skb->len; +out: + cb->args[3] = h; + cb->args[4] = idx; + return rc; + +} + static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { struct neigh_table *tbl; int t, family, s_t; + int proxy = 0; + int err; read_lock(&neigh_tbl_lock); family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; + + /* check for full ndmsg structure presence, family member is + * the same for both structures + */ + if (nlmsg_len(cb->nlh) >= sizeof(struct ndmsg) && + ((struct ndmsg *) nlmsg_data(cb->nlh))->ndm_flags == NTF_PROXY) + proxy = 1; + s_t = cb->args[0]; - for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) { + for (tbl = neigh_tables, t = 0; tbl; + tbl = tbl->next, t++) { if (t < s_t || (family && tbl->family != family)) continue; if (t > s_t) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); - if (neigh_dump_table(tbl, skb, cb) < 0) + if (proxy) + err = pneigh_dump_table(tbl, skb, cb); + else + err = neigh_dump_table(tbl, skb, cb); + if (err < 0) break; } read_unlock(&neigh_tbl_lock); @@ -2264,7 +2398,7 @@ void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void nht = rcu_dereference_bh(tbl->nht); read_lock(&tbl->lock); /* avoid resizes */ - for (chain = 0; chain <= nht->hash_mask; chain++) { + for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; for (n = rcu_dereference_bh(nht->hash_buckets[chain]); @@ -2286,7 +2420,7 @@ void __neigh_for_each_release(struct neigh_table *tbl, nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - for (chain = 0; chain <= nht->hash_mask; chain++) { + for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; struct neighbour __rcu **np; @@ -2323,7 +2457,7 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) int bucket = state->bucket; state->flags &= ~NEIGH_SEQ_IS_PNEIGH; - for (bucket = 0; bucket <= nht->hash_mask; bucket++) { + for (bucket = 0; bucket < (1 << nht->hash_shift); bucket++) { n = rcu_dereference_bh(nht->hash_buckets[bucket]); while (n) { @@ -2390,7 +2524,7 @@ next: if (n) break; - if (++state->bucket > nht->hash_mask) + if (++state->bucket >= (1 << nht->hash_shift)) break; n = rcu_dereference_bh(nht->hash_buckets[state->bucket]); @@ -2445,7 +2579,10 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; - pn = pn->next; + do { + pn = pn->next; + } while (pn && !net_eq(pneigh_net(pn), net)); + while (!pn) { if (++state->bucket > PNEIGH_HASHMASK) break; @@ -2625,7 +2762,7 @@ static int neigh_stat_seq_open(struct inode *inode, struct file *file) if (!ret) { struct seq_file *sf = file->private_data; - sf->private = PDE(inode)->data; + sf->private = PDE_DATA(inode); } return ret; }; @@ -2673,219 +2810,299 @@ errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } -#ifdef CONFIG_ARPD void neigh_app_ns(struct neighbour *n) { __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST); } EXPORT_SYMBOL(neigh_app_ns); -#endif /* CONFIG_ARPD */ #ifdef CONFIG_SYSCTL +static int zero; +static int int_max = INT_MAX; +static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN); + +static int proc_unres_qlen(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int size, ret; + struct ctl_table tmp = *ctl; -#define NEIGH_VARS_MAX 19 + tmp.extra1 = &zero; + tmp.extra2 = &unres_qlen_max; + tmp.data = &size; + + size = *(int *)ctl->data / SKB_TRUESIZE(ETH_FRAME_LEN); + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + + if (write && !ret) + *(int *)ctl->data = size * SKB_TRUESIZE(ETH_FRAME_LEN); + return ret; +} + +static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, + int family) +{ + switch (family) { + case AF_INET: + return __in_dev_arp_parms_get_rcu(dev); + case AF_INET6: + return __in6_dev_nd_parms_get_rcu(dev); + } + return NULL; +} + +static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, + int index) +{ + struct net_device *dev; + int family = neigh_parms_family(p); + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + struct neigh_parms *dst_p = + neigh_get_dev_parms_rcu(dev, family); + + if (dst_p && !test_bit(index, dst_p->data_state)) + dst_p->data[index] = p->data[index]; + } + rcu_read_unlock(); +} + +static void neigh_proc_update(struct ctl_table *ctl, int write) +{ + struct net_device *dev = ctl->extra1; + struct neigh_parms *p = ctl->extra2; + struct net *net = neigh_parms_net(p); + int index = (int *) ctl->data - p->data; + + if (!write) + return; + + set_bit(index, p->data_state); + if (!dev) /* NULL dev means this is default value */ + neigh_copy_dflt_parms(net, p, index); +} + +static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + struct ctl_table tmp = *ctl; + int ret; + + tmp.extra1 = &zero; + tmp.extra2 = &int_max; + + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + neigh_proc_update(ctl, write); + return ret; +} + +int neigh_proc_dointvec(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec); + +int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec_jiffies); + +static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} + +int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies); + +static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} + +#define NEIGH_PARMS_DATA_OFFSET(index) \ + (&((struct neigh_parms *) 0)->data[index]) + +#define NEIGH_SYSCTL_ENTRY(attr, data_attr, name, mval, proc) \ + [NEIGH_VAR_ ## attr] = { \ + .procname = name, \ + .data = NEIGH_PARMS_DATA_OFFSET(NEIGH_VAR_ ## data_attr), \ + .maxlen = sizeof(int), \ + .mode = mval, \ + .proc_handler = proc, \ + } + +#define NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_zero_intmax) + +#define NEIGH_SYSCTL_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_jiffies) + +#define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies) + +#define NEIGH_SYSCTL_MS_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies) + +#define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies) + +#define NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(attr, data_attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_unres_qlen) static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; - struct ctl_table neigh_vars[NEIGH_VARS_MAX]; - char *dev_name; + struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; } neigh_sysctl_template __read_mostly = { .neigh_vars = { - { - .procname = "mcast_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "ucast_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "app_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "retrans_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - { - .procname = "base_reachable_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "delay_first_probe_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "gc_stale_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "unres_qlen", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "proxy_qlen", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "anycast_delay", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - { - .procname = "proxy_delay", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - { - .procname = "locktime", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - { - .procname = "retrans_time_ms", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_ms_jiffies, - }, - { - .procname = "base_reachable_time_ms", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_ms_jiffies, - }, - { + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(GC_STALETIME, "gc_stale_time"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(QUEUE_LEN_BYTES, "unres_qlen_bytes"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(PROXY_QLEN, "proxy_qlen"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(ANYCAST_DELAY, "anycast_delay"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(PROXY_DELAY, "proxy_delay"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(LOCKTIME, "locktime"), + NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(QUEUE_LEN, QUEUE_LEN_BYTES, "unres_qlen"), + NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(RETRANS_TIME_MS, RETRANS_TIME, "retrans_time_ms"), + NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(BASE_REACHABLE_TIME_MS, BASE_REACHABLE_TIME, "base_reachable_time_ms"), + [NEIGH_VAR_GC_INTERVAL] = { .procname = "gc_interval", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { + [NEIGH_VAR_GC_THRESH1] = { .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, - { + [NEIGH_VAR_GC_THRESH2] = { .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, - { + [NEIGH_VAR_GC_THRESH3] = { .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, {}, }, }; int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, - char *p_name, proc_handler *handler) + proc_handler *handler) { + int i; struct neigh_sysctl_table *t; - const char *dev_name_source = NULL; - -#define NEIGH_CTL_PATH_ROOT 0 -#define NEIGH_CTL_PATH_PROTO 1 -#define NEIGH_CTL_PATH_NEIGH 2 -#define NEIGH_CTL_PATH_DEV 3 - - struct ctl_path neigh_path[] = { - { .procname = "net", }, - { .procname = "proto", }, - { .procname = "neigh", }, - { .procname = "default", }, - { }, - }; + const char *dev_name_source; + char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ]; + char *p_name; t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL); if (!t) goto err; - t->neigh_vars[0].data = &p->mcast_probes; - t->neigh_vars[1].data = &p->ucast_probes; - t->neigh_vars[2].data = &p->app_probes; - t->neigh_vars[3].data = &p->retrans_time; - t->neigh_vars[4].data = &p->base_reachable_time; - t->neigh_vars[5].data = &p->delay_probe_time; - t->neigh_vars[6].data = &p->gc_staletime; - t->neigh_vars[7].data = &p->queue_len; - t->neigh_vars[8].data = &p->proxy_qlen; - t->neigh_vars[9].data = &p->anycast_delay; - t->neigh_vars[10].data = &p->proxy_delay; - t->neigh_vars[11].data = &p->locktime; - t->neigh_vars[12].data = &p->retrans_time; - t->neigh_vars[13].data = &p->base_reachable_time; + for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) { + t->neigh_vars[i].data += (long) p; + t->neigh_vars[i].extra1 = dev; + t->neigh_vars[i].extra2 = p; + } if (dev) { dev_name_source = dev->name; /* Terminate the table early */ - memset(&t->neigh_vars[14], 0, sizeof(t->neigh_vars[14])); + memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0, + sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL])); } else { - dev_name_source = neigh_path[NEIGH_CTL_PATH_DEV].procname; - t->neigh_vars[14].data = (int *)(p + 1); - t->neigh_vars[15].data = (int *)(p + 1) + 1; - t->neigh_vars[16].data = (int *)(p + 1) + 2; - t->neigh_vars[17].data = (int *)(p + 1) + 3; + struct neigh_table *tbl = p->tbl; + dev_name_source = "default"; + t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = &tbl->gc_interval; + t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = &tbl->gc_thresh1; + t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = &tbl->gc_thresh2; + t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = &tbl->gc_thresh3; } - if (handler) { /* RetransTime */ - t->neigh_vars[3].proc_handler = handler; - t->neigh_vars[3].extra1 = dev; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler; /* ReachableTime */ - t->neigh_vars[4].proc_handler = handler; - t->neigh_vars[4].extra1 = dev; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler; /* RetransTime (in milliseconds)*/ - t->neigh_vars[12].proc_handler = handler; - t->neigh_vars[12].extra1 = dev; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler; /* ReachableTime (in milliseconds) */ - t->neigh_vars[13].proc_handler = handler; - t->neigh_vars[13].extra1 = dev; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler; } - t->dev_name = kstrdup(dev_name_source, GFP_KERNEL); - if (!t->dev_name) - goto free; + /* Don't export sysctls to unprivileged users */ + if (neigh_parms_net(p)->user_ns != &init_user_ns) + t->neigh_vars[0].procname = NULL; - neigh_path[NEIGH_CTL_PATH_DEV].procname = t->dev_name; - neigh_path[NEIGH_CTL_PATH_PROTO].procname = p_name; + switch (neigh_parms_family(p)) { + case AF_INET: + p_name = "ipv4"; + break; + case AF_INET6: + p_name = "ipv6"; + break; + default: + BUG(); + } + snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s", + p_name, dev_name_source); t->sysctl_header = - register_net_sysctl_table(neigh_parms_net(p), neigh_path, t->neigh_vars); + register_net_sysctl(neigh_parms_net(p), neigh_path, t->neigh_vars); if (!t->sysctl_header) - goto free_procname; + goto free; p->sysctl_table = t; return 0; -free_procname: - kfree(t->dev_name); free: kfree(t); err: @@ -2898,8 +3115,7 @@ void neigh_sysctl_unregister(struct neigh_parms *p) if (p->sysctl_table) { struct neigh_sysctl_table *t = p->sysctl_table; p->sysctl_table = NULL; - unregister_sysctl_table(t->sysctl_header); - kfree(t->dev_name); + unregister_net_sysctl_table(t->sysctl_header); kfree(t); } } @@ -2909,12 +3125,13 @@ EXPORT_SYMBOL(neigh_sysctl_unregister); static int __init neigh_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL); - rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL); - rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info); + rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, NULL); - rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info); - rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info, + NULL); + rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, NULL); return 0; } diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c new file mode 100644 index 00000000000..2bf83299600 --- /dev/null +++ b/net/core/net-procfs.c @@ -0,0 +1,423 @@ +#include <linux/netdevice.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <net/wext.h> + +#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) + +#define get_bucket(x) ((x) >> BUCKET_SPACE) +#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) +#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) + +extern struct list_head ptype_all __read_mostly; +extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; + +static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) +{ + struct net *net = seq_file_net(seq); + struct net_device *dev; + struct hlist_head *h; + unsigned int count = 0, offset = get_offset(*pos); + + h = &net->dev_name_head[get_bucket(*pos)]; + hlist_for_each_entry_rcu(dev, h, name_hlist) { + if (++count == offset) + return dev; + } + + return NULL; +} + +static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos) +{ + struct net_device *dev; + unsigned int bucket; + + do { + dev = dev_from_same_bucket(seq, pos); + if (dev) + return dev; + + bucket = get_bucket(*pos) + 1; + *pos = set_bucket_offset(bucket, 1); + } while (bucket < NETDEV_HASHENTRIES); + + return NULL; +} + +/* + * This is invoked by the /proc filesystem handler to display a device + * in detail. + */ +static void *dev_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) +{ + rcu_read_lock(); + if (!*pos) + return SEQ_START_TOKEN; + + if (get_bucket(*pos) >= NETDEV_HASHENTRIES) + return NULL; + + return dev_from_bucket(seq, pos); +} + +static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + return dev_from_bucket(seq, pos); +} + +static void dev_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) +{ + rcu_read_unlock(); +} + +static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) +{ + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); + + seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " + "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", + dev->name, stats->rx_bytes, stats->rx_packets, + stats->rx_errors, + stats->rx_dropped + stats->rx_missed_errors, + stats->rx_fifo_errors, + stats->rx_length_errors + stats->rx_over_errors + + stats->rx_crc_errors + stats->rx_frame_errors, + stats->rx_compressed, stats->multicast, + stats->tx_bytes, stats->tx_packets, + stats->tx_errors, stats->tx_dropped, + stats->tx_fifo_errors, stats->collisions, + stats->tx_carrier_errors + + stats->tx_aborted_errors + + stats->tx_window_errors + + stats->tx_heartbeat_errors, + stats->tx_compressed); +} + +/* + * Called from the PROCfs module. This now uses the new arbitrary sized + * /proc/net interface to create /proc/net/dev + */ +static int dev_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) + seq_puts(seq, "Inter-| Receive " + " | Transmit\n" + " face |bytes packets errs drop fifo frame " + "compressed multicast|bytes packets errs " + "drop fifo colls carrier compressed\n"); + else + dev_seq_printf_stats(seq, v); + return 0; +} + +static struct softnet_data *softnet_get_online(loff_t *pos) +{ + struct softnet_data *sd = NULL; + + while (*pos < nr_cpu_ids) + if (cpu_online(*pos)) { + sd = &per_cpu(softnet_data, *pos); + break; + } else + ++*pos; + return sd; +} + +static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) +{ + return softnet_get_online(pos); +} + +static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + ++*pos; + return softnet_get_online(pos); +} + +static void softnet_seq_stop(struct seq_file *seq, void *v) +{ +} + +static int softnet_seq_show(struct seq_file *seq, void *v) +{ + struct softnet_data *sd = v; + unsigned int flow_limit_count = 0; + +#ifdef CONFIG_NET_FLOW_LIMIT + struct sd_flow_limit *fl; + + rcu_read_lock(); + fl = rcu_dereference(sd->flow_limit); + if (fl) + flow_limit_count = fl->count; + rcu_read_unlock(); +#endif + + seq_printf(seq, + "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", + sd->processed, sd->dropped, sd->time_squeeze, 0, + 0, 0, 0, 0, /* was fastroute */ + sd->cpu_collision, sd->received_rps, flow_limit_count); + return 0; +} + +static const struct seq_operations dev_seq_ops = { + .start = dev_seq_start, + .next = dev_seq_next, + .stop = dev_seq_stop, + .show = dev_seq_show, +}; + +static int dev_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &dev_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations dev_seq_fops = { + .owner = THIS_MODULE, + .open = dev_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +static const struct seq_operations softnet_seq_ops = { + .start = softnet_seq_start, + .next = softnet_seq_next, + .stop = softnet_seq_stop, + .show = softnet_seq_show, +}; + +static int softnet_seq_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &softnet_seq_ops); +} + +static const struct file_operations softnet_seq_fops = { + .owner = THIS_MODULE, + .open = softnet_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static void *ptype_get_idx(loff_t pos) +{ + struct packet_type *pt = NULL; + loff_t i = 0; + int t; + + list_for_each_entry_rcu(pt, &ptype_all, list) { + if (i == pos) + return pt; + ++i; + } + + for (t = 0; t < PTYPE_HASH_SIZE; t++) { + list_for_each_entry_rcu(pt, &ptype_base[t], list) { + if (i == pos) + return pt; + ++i; + } + } + return NULL; +} + +static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) +{ + rcu_read_lock(); + return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; +} + +static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct packet_type *pt; + struct list_head *nxt; + int hash; + + ++*pos; + if (v == SEQ_START_TOKEN) + return ptype_get_idx(0); + + pt = v; + nxt = pt->list.next; + if (pt->type == htons(ETH_P_ALL)) { + if (nxt != &ptype_all) + goto found; + hash = 0; + nxt = ptype_base[0].next; + } else + hash = ntohs(pt->type) & PTYPE_HASH_MASK; + + while (nxt == &ptype_base[hash]) { + if (++hash >= PTYPE_HASH_SIZE) + return NULL; + nxt = ptype_base[hash].next; + } +found: + return list_entry(nxt, struct packet_type, list); +} + +static void ptype_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) +{ + rcu_read_unlock(); +} + +static int ptype_seq_show(struct seq_file *seq, void *v) +{ + struct packet_type *pt = v; + + if (v == SEQ_START_TOKEN) + seq_puts(seq, "Type Device Function\n"); + else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { + if (pt->type == htons(ETH_P_ALL)) + seq_puts(seq, "ALL "); + else + seq_printf(seq, "%04x", ntohs(pt->type)); + + seq_printf(seq, " %-8s %pf\n", + pt->dev ? pt->dev->name : "", pt->func); + } + + return 0; +} + +static const struct seq_operations ptype_seq_ops = { + .start = ptype_seq_start, + .next = ptype_seq_next, + .stop = ptype_seq_stop, + .show = ptype_seq_show, +}; + +static int ptype_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &ptype_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations ptype_seq_fops = { + .owner = THIS_MODULE, + .open = ptype_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + + +static int __net_init dev_proc_net_init(struct net *net) +{ + int rc = -ENOMEM; + + if (!proc_create("dev", S_IRUGO, net->proc_net, &dev_seq_fops)) + goto out; + if (!proc_create("softnet_stat", S_IRUGO, net->proc_net, + &softnet_seq_fops)) + goto out_dev; + if (!proc_create("ptype", S_IRUGO, net->proc_net, &ptype_seq_fops)) + goto out_softnet; + + if (wext_proc_init(net)) + goto out_ptype; + rc = 0; +out: + return rc; +out_ptype: + remove_proc_entry("ptype", net->proc_net); +out_softnet: + remove_proc_entry("softnet_stat", net->proc_net); +out_dev: + remove_proc_entry("dev", net->proc_net); + goto out; +} + +static void __net_exit dev_proc_net_exit(struct net *net) +{ + wext_proc_exit(net); + + remove_proc_entry("ptype", net->proc_net); + remove_proc_entry("softnet_stat", net->proc_net); + remove_proc_entry("dev", net->proc_net); +} + +static struct pernet_operations __net_initdata dev_proc_ops = { + .init = dev_proc_net_init, + .exit = dev_proc_net_exit, +}; + +static int dev_mc_seq_show(struct seq_file *seq, void *v) +{ + struct netdev_hw_addr *ha; + struct net_device *dev = v; + + if (v == SEQ_START_TOKEN) + return 0; + + netif_addr_lock_bh(dev); + netdev_for_each_mc_addr(ha, dev) { + int i; + + seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, + dev->name, ha->refcount, ha->global_use); + + for (i = 0; i < dev->addr_len; i++) + seq_printf(seq, "%02x", ha->addr[i]); + + seq_putc(seq, '\n'); + } + netif_addr_unlock_bh(dev); + return 0; +} + +static const struct seq_operations dev_mc_seq_ops = { + .start = dev_seq_start, + .next = dev_seq_next, + .stop = dev_seq_stop, + .show = dev_mc_seq_show, +}; + +static int dev_mc_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &dev_mc_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations dev_mc_seq_fops = { + .owner = THIS_MODULE, + .open = dev_mc_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +static int __net_init dev_mc_net_init(struct net *net) +{ + if (!proc_create("dev_mcast", 0, net->proc_net, &dev_mc_seq_fops)) + return -ENOMEM; + return 0; +} + +static void __net_exit dev_mc_net_exit(struct net *net) +{ + remove_proc_entry("dev_mcast", net->proc_net); +} + +static struct pernet_operations __net_initdata dev_mc_net_ops = { + .init = dev_mc_net_init, + .exit = dev_mc_net_exit, +}; + +int __init dev_proc_init(void) +{ + int ret = register_pernet_subsys(&dev_proc_ops); + if (!ret) + return register_pernet_subsys(&dev_mc_net_ops); + return ret; +} diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 85e8b5326dd..1cac29ebb05 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -18,9 +18,10 @@ #include <net/sock.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> -#include <linux/wireless.h> #include <linux/vmalloc.h> -#include <net/wext.h> +#include <linux/export.h> +#include <linux/jiffies.h> +#include <linux/pm_runtime.h> #include "net-sysfs.h" @@ -28,6 +29,7 @@ static const char fmt_hex[] = "%#x\n"; static const char fmt_long_hex[] = "%#lx\n"; static const char fmt_dec[] = "%d\n"; +static const char fmt_udec[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; @@ -58,35 +60,42 @@ static ssize_t format_##field(const struct net_device *net, char *buf) \ { \ return sprintf(buf, format_string, net->field); \ } \ -static ssize_t show_##field(struct device *dev, \ +static ssize_t field##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ return netdev_show(dev, attr, buf, format_##field); \ -} +} \ + +#define NETDEVICE_SHOW_RO(field, format_string) \ +NETDEVICE_SHOW(field, format_string); \ +static DEVICE_ATTR_RO(field) +#define NETDEVICE_SHOW_RW(field, format_string) \ +NETDEVICE_SHOW(field, format_string); \ +static DEVICE_ATTR_RW(field) /* use same locking and permission rules as SIF* ioctl's */ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len, int (*set)(struct net_device *, unsigned long)) { - struct net_device *net = to_net_dev(dev); - char *endp; + struct net_device *netdev = to_net_dev(dev); + struct net *net = dev_net(netdev); unsigned long new; int ret = -EINVAL; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - new = simple_strtoul(buf, &endp, 0); - if (endp == buf) + ret = kstrtoul(buf, 0, &new); + if (ret) goto err; if (!rtnl_trylock()) return restart_syscall(); - if (dev_isalive(net)) { - if ((ret = (*set)(net, new)) == 0) + if (dev_isalive(netdev)) { + if ((ret = (*set)(netdev, new)) == 0) ret = len; } rtnl_unlock(); @@ -94,17 +103,17 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, return ret; } -NETDEVICE_SHOW(dev_id, fmt_hex); -NETDEVICE_SHOW(addr_assign_type, fmt_dec); -NETDEVICE_SHOW(addr_len, fmt_dec); -NETDEVICE_SHOW(iflink, fmt_dec); -NETDEVICE_SHOW(ifindex, fmt_dec); -NETDEVICE_SHOW(features, fmt_long_hex); -NETDEVICE_SHOW(type, fmt_dec); -NETDEVICE_SHOW(link_mode, fmt_dec); +NETDEVICE_SHOW_RO(dev_id, fmt_hex); +NETDEVICE_SHOW_RO(dev_port, fmt_dec); +NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); +NETDEVICE_SHOW_RO(addr_len, fmt_dec); +NETDEVICE_SHOW_RO(iflink, fmt_dec); +NETDEVICE_SHOW_RO(ifindex, fmt_dec); +NETDEVICE_SHOW_RO(type, fmt_dec); +NETDEVICE_SHOW_RO(link_mode, fmt_dec); /* use same locking rules as GIFHWADDR ioctl's */ -static ssize_t show_address(struct device *dev, struct device_attribute *attr, +static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *net = to_net_dev(dev); @@ -116,17 +125,32 @@ static ssize_t show_address(struct device *dev, struct device_attribute *attr, read_unlock(&dev_base_lock); return ret; } +static DEVICE_ATTR_RO(address); -static ssize_t show_broadcast(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t broadcast_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct net_device *net = to_net_dev(dev); if (dev_isalive(net)) return sysfs_format_mac(buf, net->broadcast, net->addr_len); return -EINVAL; } +static DEVICE_ATTR_RO(broadcast); + +static int change_carrier(struct net_device *net, unsigned long new_carrier) +{ + if (!netif_running(net)) + return -EINVAL; + return dev_change_carrier(net, (bool) new_carrier); +} -static ssize_t show_carrier(struct device *dev, +static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_carrier); +} + +static ssize_t carrier_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); @@ -135,8 +159,9 @@ static ssize_t show_carrier(struct device *dev, } return -EINVAL; } +static DEVICE_ATTR_RW(carrier); -static ssize_t show_speed(struct device *dev, +static ssize_t speed_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); @@ -145,19 +170,17 @@ static ssize_t show_speed(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && - netdev->ethtool_ops && - netdev->ethtool_ops->get_settings) { - struct ethtool_cmd cmd = { ETHTOOL_GSET }; - - if (!netdev->ethtool_ops->get_settings(netdev, &cmd)) - ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd)); + if (netif_running(netdev)) { + struct ethtool_cmd cmd; + if (!__ethtool_get_settings(netdev, &cmd)) + ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd)); } rtnl_unlock(); return ret; } +static DEVICE_ATTR_RO(speed); -static ssize_t show_duplex(struct device *dev, +static ssize_t duplex_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); @@ -166,19 +189,30 @@ static ssize_t show_duplex(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && - netdev->ethtool_ops && - netdev->ethtool_ops->get_settings) { - struct ethtool_cmd cmd = { ETHTOOL_GSET }; - - if (!netdev->ethtool_ops->get_settings(netdev, &cmd)) - ret = sprintf(buf, "%s\n", cmd.duplex ? "full" : "half"); + if (netif_running(netdev)) { + struct ethtool_cmd cmd; + if (!__ethtool_get_settings(netdev, &cmd)) { + const char *duplex; + switch (cmd.duplex) { + case DUPLEX_HALF: + duplex = "half"; + break; + case DUPLEX_FULL: + duplex = "full"; + break; + default: + duplex = "unknown"; + break; + } + ret = sprintf(buf, "%s\n", duplex); + } } rtnl_unlock(); return ret; } +static DEVICE_ATTR_RO(duplex); -static ssize_t show_dormant(struct device *dev, +static ssize_t dormant_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); @@ -188,6 +222,7 @@ static ssize_t show_dormant(struct device *dev, return -EINVAL; } +static DEVICE_ATTR_RO(dormant); static const char *const operstates[] = { "unknown", @@ -199,7 +234,7 @@ static const char *const operstates[] = { "up" }; -static ssize_t show_operstate(struct device *dev, +static ssize_t operstate_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); @@ -216,35 +251,43 @@ static ssize_t show_operstate(struct device *dev, return sprintf(buf, "%s\n", operstates[operstate]); } +static DEVICE_ATTR_RO(operstate); + +static ssize_t carrier_changes_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + return sprintf(buf, fmt_dec, + atomic_read(&netdev->carrier_changes)); +} +static DEVICE_ATTR_RO(carrier_changes); /* read-write attributes */ -NETDEVICE_SHOW(mtu, fmt_dec); static int change_mtu(struct net_device *net, unsigned long new_mtu) { return dev_set_mtu(net, (int) new_mtu); } -static ssize_t store_mtu(struct device *dev, struct device_attribute *attr, +static ssize_t mtu_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_mtu); } - -NETDEVICE_SHOW(flags, fmt_hex); +NETDEVICE_SHOW_RW(mtu, fmt_dec); static int change_flags(struct net_device *net, unsigned long new_flags) { - return dev_change_flags(net, (unsigned) new_flags); + return dev_change_flags(net, (unsigned int) new_flags); } -static ssize_t store_flags(struct device *dev, struct device_attribute *attr, +static ssize_t flags_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_flags); } - -NETDEVICE_SHOW(tx_queue_len, fmt_ulong); +NETDEVICE_SHOW_RW(flags, fmt_hex); static int change_tx_queue_len(struct net_device *net, unsigned long new_len) { @@ -252,21 +295,26 @@ static int change_tx_queue_len(struct net_device *net, unsigned long new_len) return 0; } -static ssize_t store_tx_queue_len(struct device *dev, +static ssize_t tx_queue_len_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + return netdev_store(dev, attr, buf, len, change_tx_queue_len); } +NETDEVICE_SHOW_RW(tx_queue_len, fmt_ulong); -static ssize_t store_ifalias(struct device *dev, struct device_attribute *attr, +static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); + struct net *net = dev_net(netdev); size_t count = len; ssize_t ret; - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* ignore trailing newline */ @@ -281,7 +329,7 @@ static ssize_t store_ifalias(struct device *dev, struct device_attribute *attr, return ret < 0 ? ret : len; } -static ssize_t show_ifalias(struct device *dev, +static ssize_t ifalias_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); @@ -294,30 +342,70 @@ static ssize_t show_ifalias(struct device *dev, rtnl_unlock(); return ret; } +static DEVICE_ATTR_RW(ifalias); -static struct device_attribute net_class_attributes[] = { - __ATTR(addr_assign_type, S_IRUGO, show_addr_assign_type, NULL), - __ATTR(addr_len, S_IRUGO, show_addr_len, NULL), - __ATTR(dev_id, S_IRUGO, show_dev_id, NULL), - __ATTR(ifalias, S_IRUGO | S_IWUSR, show_ifalias, store_ifalias), - __ATTR(iflink, S_IRUGO, show_iflink, NULL), - __ATTR(ifindex, S_IRUGO, show_ifindex, NULL), - __ATTR(features, S_IRUGO, show_features, NULL), - __ATTR(type, S_IRUGO, show_type, NULL), - __ATTR(link_mode, S_IRUGO, show_link_mode, NULL), - __ATTR(address, S_IRUGO, show_address, NULL), - __ATTR(broadcast, S_IRUGO, show_broadcast, NULL), - __ATTR(carrier, S_IRUGO, show_carrier, NULL), - __ATTR(speed, S_IRUGO, show_speed, NULL), - __ATTR(duplex, S_IRUGO, show_duplex, NULL), - __ATTR(dormant, S_IRUGO, show_dormant, NULL), - __ATTR(operstate, S_IRUGO, show_operstate, NULL), - __ATTR(mtu, S_IRUGO | S_IWUSR, show_mtu, store_mtu), - __ATTR(flags, S_IRUGO | S_IWUSR, show_flags, store_flags), - __ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len, - store_tx_queue_len), - {} +static int change_group(struct net_device *net, unsigned long new_group) +{ + dev_set_group(net, (int) new_group); + return 0; +} + +static ssize_t group_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_group); +} +NETDEVICE_SHOW(group, fmt_dec); +static DEVICE_ATTR(netdev_group, S_IRUGO | S_IWUSR, group_show, group_store); + +static ssize_t phys_port_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + ssize_t ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (dev_isalive(netdev)) { + struct netdev_phys_port_id ppid; + + ret = dev_get_phys_port_id(netdev, &ppid); + if (!ret) + ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); + } + rtnl_unlock(); + + return ret; +} +static DEVICE_ATTR_RO(phys_port_id); + +static struct attribute *net_class_attrs[] = { + &dev_attr_netdev_group.attr, + &dev_attr_type.attr, + &dev_attr_dev_id.attr, + &dev_attr_dev_port.attr, + &dev_attr_iflink.attr, + &dev_attr_ifindex.attr, + &dev_attr_addr_assign_type.attr, + &dev_attr_addr_len.attr, + &dev_attr_link_mode.attr, + &dev_attr_address.attr, + &dev_attr_broadcast.attr, + &dev_attr_speed.attr, + &dev_attr_duplex.attr, + &dev_attr_dormant.attr, + &dev_attr_operstate.attr, + &dev_attr_carrier_changes.attr, + &dev_attr_ifalias.attr, + &dev_attr_carrier.attr, + &dev_attr_mtu.attr, + &dev_attr_flags.attr, + &dev_attr_tx_queue_len.attr, + &dev_attr_phys_port_id.attr, + NULL, }; +ATTRIBUTE_GROUPS(net_class); /* Show a given an attribute in the statistics group */ static ssize_t netstat_show(const struct device *d, @@ -343,13 +431,13 @@ static ssize_t netstat_show(const struct device *d, /* generate a read-only statistics attribute */ #define NETSTAT_ENTRY(name) \ -static ssize_t show_##name(struct device *d, \ +static ssize_t name##_show(struct device *d, \ struct device_attribute *attr, char *buf) \ { \ return netstat_show(d, attr, buf, \ offsetof(struct rtnl_link_stats64, name)); \ } \ -static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL) +static DEVICE_ATTR_RO(name) NETSTAT_ENTRY(rx_packets); NETSTAT_ENTRY(tx_packets); @@ -408,63 +496,8 @@ static struct attribute_group netstat_group = { .attrs = netstat_attrs, }; -#ifdef CONFIG_WIRELESS_EXT_SYSFS -/* helper function that does all the locking etc for wireless stats */ -static ssize_t wireless_show(struct device *d, char *buf, - ssize_t (*format)(const struct iw_statistics *, - char *)) -{ - struct net_device *dev = to_net_dev(d); - const struct iw_statistics *iw; - ssize_t ret = -EINVAL; - - if (!rtnl_trylock()) - return restart_syscall(); - if (dev_isalive(dev)) { - iw = get_wireless_stats(dev); - if (iw) - ret = (*format)(iw, buf); - } - rtnl_unlock(); - - return ret; -} - -/* show function template for wireless fields */ -#define WIRELESS_SHOW(name, field, format_string) \ -static ssize_t format_iw_##name(const struct iw_statistics *iw, char *buf) \ -{ \ - return sprintf(buf, format_string, iw->field); \ -} \ -static ssize_t show_iw_##name(struct device *d, \ - struct device_attribute *attr, char *buf) \ -{ \ - return wireless_show(d, buf, format_iw_##name); \ -} \ -static DEVICE_ATTR(name, S_IRUGO, show_iw_##name, NULL) - -WIRELESS_SHOW(status, status, fmt_hex); -WIRELESS_SHOW(link, qual.qual, fmt_dec); -WIRELESS_SHOW(level, qual.level, fmt_dec); -WIRELESS_SHOW(noise, qual.noise, fmt_dec); -WIRELESS_SHOW(nwid, discard.nwid, fmt_dec); -WIRELESS_SHOW(crypt, discard.code, fmt_dec); -WIRELESS_SHOW(fragment, discard.fragment, fmt_dec); -WIRELESS_SHOW(misc, discard.misc, fmt_dec); -WIRELESS_SHOW(retries, discard.retries, fmt_dec); -WIRELESS_SHOW(beacon, miss.beacon, fmt_dec); - +#if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) static struct attribute *wireless_attrs[] = { - &dev_attr_status.attr, - &dev_attr_link.attr, - &dev_attr_level.attr, - &dev_attr_noise.attr, - &dev_attr_nwid.attr, - &dev_attr_crypt.attr, - &dev_attr_fragment.attr, - &dev_attr_retries.attr, - &dev_attr_misc.attr, - &dev_attr_beacon.attr, NULL }; @@ -473,19 +506,12 @@ static struct attribute_group wireless_group = { .attrs = wireless_attrs, }; #endif + +#else /* CONFIG_SYSFS */ +#define net_class_groups NULL #endif /* CONFIG_SYSFS */ -#ifdef CONFIG_RPS -/* - * RX queue sysfs structures and functions. - */ -struct rx_queue_attribute { - struct attribute attr; - ssize_t (*show)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, char *buf); - ssize_t (*store)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, const char *buf, size_t len); -}; +#ifdef CONFIG_SYSFS #define to_rx_queue_attr(_attr) container_of(_attr, \ struct rx_queue_attribute, attr) @@ -520,6 +546,7 @@ static const struct sysfs_ops rx_queue_sysfs_ops = { .store = rx_queue_attr_store, }; +#ifdef CONFIG_RPS static ssize_t show_rps_map(struct netdev_rx_queue *queue, struct rx_queue_attribute *attribute, char *buf) { @@ -550,13 +577,6 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue, return len; } -static void rps_map_release(struct rcu_head *rcu) -{ - struct rps_map *map = container_of(rcu, struct rps_map, rcu); - - kfree(map); -} - static ssize_t store_rps_map(struct netdev_rx_queue *queue, struct rx_queue_attribute *attribute, const char *buf, size_t len) @@ -578,7 +598,7 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, return err; } - map = kzalloc(max_t(unsigned, + map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); if (!map) { @@ -603,9 +623,12 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, rcu_assign_pointer(queue->rps_map, map); spin_unlock(&rps_map_lock); - if (old_map) - call_rcu(&old_map->rcu, rps_map_release); - + if (map) + static_key_slow_inc(&rps_needed); + if (old_map) { + kfree_rcu(old_map, rcu); + static_key_slow_dec(&rps_needed); + } free_cpumask_var(mask); return len; } @@ -615,65 +638,68 @@ static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, char *buf) { struct rps_dev_flow_table *flow_table; - unsigned int val = 0; + unsigned long val = 0; rcu_read_lock(); flow_table = rcu_dereference(queue->rps_flow_table); if (flow_table) - val = flow_table->mask + 1; + val = (unsigned long)flow_table->mask + 1; rcu_read_unlock(); - return sprintf(buf, "%u\n", val); -} - -static void rps_dev_flow_table_release_work(struct work_struct *work) -{ - struct rps_dev_flow_table *table = container_of(work, - struct rps_dev_flow_table, free_work); - - vfree(table); + return sprintf(buf, "%lu\n", val); } static void rps_dev_flow_table_release(struct rcu_head *rcu) { struct rps_dev_flow_table *table = container_of(rcu, struct rps_dev_flow_table, rcu); - - INIT_WORK(&table->free_work, rps_dev_flow_table_release_work); - schedule_work(&table->free_work); + vfree(table); } static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, struct rx_queue_attribute *attr, const char *buf, size_t len) { - unsigned int count; - char *endp; + unsigned long mask, count; struct rps_dev_flow_table *table, *old_table; static DEFINE_SPINLOCK(rps_dev_flow_lock); + int rc; if (!capable(CAP_NET_ADMIN)) return -EPERM; - count = simple_strtoul(buf, &endp, 0); - if (endp == buf) - return -EINVAL; + rc = kstrtoul(buf, 0, &count); + if (rc < 0) + return rc; if (count) { - int i; - - if (count > 1<<30) { + mask = count - 1; + /* mask = roundup_pow_of_two(count) - 1; + * without overflows... + */ + while ((mask | (mask >> 1)) != mask) + mask |= (mask >> 1); + /* On 64 bit arches, must check mask fits in table->mask (u32), + * and on 32bit arches, must check + * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow. + */ +#if BITS_PER_LONG > 32 + if (mask > (unsigned long)(u32)mask) + return -EINVAL; +#else + if (mask > (ULONG_MAX - RPS_DEV_FLOW_TABLE_SIZE(1)) + / sizeof(struct rps_dev_flow)) { /* Enforce a limit to prevent overflow */ return -EINVAL; } - count = roundup_pow_of_two(count); - table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count)); +#endif + table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(mask + 1)); if (!table) return -ENOMEM; - table->mask = count - 1; - for (i = 0; i < count; i++) - table->flows[i].cpu = RPS_NO_CPU; + table->mask = mask; + for (count = 0; count <= mask; count++) + table->flows[count].cpu = RPS_NO_CPU; } else table = NULL; @@ -696,40 +722,58 @@ static struct rx_queue_attribute rps_cpus_attribute = static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute = __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); +#endif /* CONFIG_RPS */ static struct attribute *rx_queue_default_attrs[] = { +#ifdef CONFIG_RPS &rps_cpus_attribute.attr, &rps_dev_flow_table_cnt_attribute.attr, +#endif NULL }; static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); +#ifdef CONFIG_RPS struct rps_map *map; struct rps_dev_flow_table *flow_table; - map = rcu_dereference_raw(queue->rps_map); + map = rcu_dereference_protected(queue->rps_map, 1); if (map) { RCU_INIT_POINTER(queue->rps_map, NULL); - call_rcu(&map->rcu, rps_map_release); + kfree_rcu(map, rcu); } - flow_table = rcu_dereference_raw(queue->rps_flow_table); + flow_table = rcu_dereference_protected(queue->rps_flow_table, 1); if (flow_table) { RCU_INIT_POINTER(queue->rps_flow_table, NULL); call_rcu(&flow_table->rcu, rps_dev_flow_table_release); } +#endif memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } +static const void *rx_queue_namespace(struct kobject *kobj) +{ + struct netdev_rx_queue *queue = to_rx_queue(kobj); + struct device *dev = &queue->dev->dev; + const void *ns = NULL; + + if (dev->class && dev->class->ns_type) + ns = dev->class->namespace(dev); + + return ns; +} + static struct kobj_type rx_queue_ktype = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, .default_attrs = rx_queue_default_attrs, + .namespace = rx_queue_namespace }; static int rx_queue_add_kobject(struct net_device *net, int index) @@ -741,25 +785,36 @@ static int rx_queue_add_kobject(struct net_device *net, int index) kobj->kset = net->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); - if (error) { - kobject_put(kobj); - return error; + if (error) + goto exit; + + if (net->sysfs_rx_queue_group) { + error = sysfs_create_group(kobj, net->sysfs_rx_queue_group); + if (error) + goto exit; } kobject_uevent(kobj, KOBJ_ADD); dev_hold(queue->dev); return error; +exit: + kobject_put(kobj); + return error; } -#endif /* CONFIG_RPS */ +#endif /* CONFIG_SYSFS */ int net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS int i; int error = 0; +#ifndef CONFIG_RPS + if (!net->sysfs_rx_queue_group) + return 0; +#endif for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(net, i); if (error) { @@ -768,8 +823,12 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) } } - while (--i >= new_num) + while (--i >= new_num) { + if (net->sysfs_rx_queue_group) + sysfs_remove_group(&net->_rx[i].kobj, + net->sysfs_rx_queue_group); kobject_put(&net->_rx[i].kobj); + } return error; #else @@ -777,7 +836,7 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) #endif } -#ifdef CONFIG_XPS +#ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. */ @@ -823,15 +882,139 @@ static const struct sysfs_ops netdev_queue_sysfs_ops = { .store = netdev_queue_attr_store, }; -static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) +static ssize_t show_trans_timeout(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + char *buf) { - struct net_device *dev = queue->dev; - int i; + unsigned long trans_timeout; - for (i = 0; i < dev->num_tx_queues; i++) - if (queue == &dev->_tx[i]) - break; + spin_lock_irq(&queue->_xmit_lock); + trans_timeout = queue->trans_timeout; + spin_unlock_irq(&queue->_xmit_lock); + + return sprintf(buf, "%lu", trans_timeout); +} + +static struct netdev_queue_attribute queue_trans_timeout = + __ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL); + +#ifdef CONFIG_BQL +/* + * Byte queue limits sysfs structures and functions. + */ +static ssize_t bql_show(char *buf, unsigned int value) +{ + return sprintf(buf, "%u\n", value); +} + +static ssize_t bql_set(const char *buf, const size_t count, + unsigned int *pvalue) +{ + unsigned int value; + int err; + if (!strcmp(buf, "max") || !strcmp(buf, "max\n")) + value = DQL_MAX_LIMIT; + else { + err = kstrtouint(buf, 10, &value); + if (err < 0) + return err; + if (value > DQL_MAX_LIMIT) + return -EINVAL; + } + + *pvalue = value; + + return count; +} + +static ssize_t bql_show_hold_time(struct netdev_queue *queue, + struct netdev_queue_attribute *attr, + char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time)); +} + +static ssize_t bql_set_hold_time(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + const char *buf, size_t len) +{ + struct dql *dql = &queue->dql; + unsigned int value; + int err; + + err = kstrtouint(buf, 10, &value); + if (err < 0) + return err; + + dql->slack_hold_time = msecs_to_jiffies(value); + + return len; +} + +static struct netdev_queue_attribute bql_hold_time_attribute = + __ATTR(hold_time, S_IRUGO | S_IWUSR, bql_show_hold_time, + bql_set_hold_time); + +static ssize_t bql_show_inflight(struct netdev_queue *queue, + struct netdev_queue_attribute *attr, + char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%u\n", dql->num_queued - dql->num_completed); +} + +static struct netdev_queue_attribute bql_inflight_attribute = + __ATTR(inflight, S_IRUGO, bql_show_inflight, NULL); + +#define BQL_ATTR(NAME, FIELD) \ +static ssize_t bql_show_ ## NAME(struct netdev_queue *queue, \ + struct netdev_queue_attribute *attr, \ + char *buf) \ +{ \ + return bql_show(buf, queue->dql.FIELD); \ +} \ + \ +static ssize_t bql_set_ ## NAME(struct netdev_queue *queue, \ + struct netdev_queue_attribute *attr, \ + const char *buf, size_t len) \ +{ \ + return bql_set(buf, len, &queue->dql.FIELD); \ +} \ + \ +static struct netdev_queue_attribute bql_ ## NAME ## _attribute = \ + __ATTR(NAME, S_IRUGO | S_IWUSR, bql_show_ ## NAME, \ + bql_set_ ## NAME); + +BQL_ATTR(limit, limit) +BQL_ATTR(limit_max, max_limit) +BQL_ATTR(limit_min, min_limit) + +static struct attribute *dql_attrs[] = { + &bql_limit_attribute.attr, + &bql_limit_max_attribute.attr, + &bql_limit_min_attribute.attr, + &bql_hold_time_attribute.attr, + &bql_inflight_attribute.attr, + NULL +}; + +static struct attribute_group dql_group = { + .name = "byte_queue_limits", + .attrs = dql_attrs, +}; +#endif /* CONFIG_BQL */ + +#ifdef CONFIG_XPS +static unsigned int get_netdev_queue_index(struct netdev_queue *queue) +{ + struct net_device *dev = queue->dev; + unsigned int i; + + i = queue - dev->_tx; BUG_ON(i >= dev->num_tx_queues); return i; @@ -883,37 +1066,14 @@ static ssize_t show_xps_map(struct netdev_queue *queue, return len; } -static void xps_map_release(struct rcu_head *rcu) -{ - struct xps_map *map = container_of(rcu, struct xps_map, rcu); - - kfree(map); -} - -static void xps_dev_maps_release(struct rcu_head *rcu) -{ - struct xps_dev_maps *dev_maps = - container_of(rcu, struct xps_dev_maps, rcu); - - kfree(dev_maps); -} - -static DEFINE_MUTEX(xps_map_mutex); -#define xmap_dereference(P) \ - rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) - static ssize_t store_xps_map(struct netdev_queue *queue, struct netdev_queue_attribute *attribute, const char *buf, size_t len) { struct net_device *dev = queue->dev; - cpumask_var_t mask; - int err, i, cpu, pos, map_len, alloc_len, need_set; unsigned long index; - struct xps_map *map, *new_map; - struct xps_dev_maps *dev_maps, *new_dev_maps; - int nonempty = 0; - int numa_node = -2; + cpumask_var_t mask; + int err; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -929,169 +1089,50 @@ static ssize_t store_xps_map(struct netdev_queue *queue, return err; } - new_dev_maps = kzalloc(max_t(unsigned, - XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES), GFP_KERNEL); - if (!new_dev_maps) { - free_cpumask_var(mask); - return -ENOMEM; - } - - mutex_lock(&xps_map_mutex); - - dev_maps = xmap_dereference(dev->xps_maps); - - for_each_possible_cpu(cpu) { - map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; - new_map = map; - if (map) { - for (pos = 0; pos < map->len; pos++) - if (map->queues[pos] == index) - break; - map_len = map->len; - alloc_len = map->alloc_len; - } else - pos = map_len = alloc_len = 0; - - need_set = cpu_isset(cpu, *mask) && cpu_online(cpu); -#ifdef CONFIG_NUMA - if (need_set) { - if (numa_node == -2) - numa_node = cpu_to_node(cpu); - else if (numa_node != cpu_to_node(cpu)) - numa_node = -1; - } -#endif - if (need_set && pos >= map_len) { - /* Need to add queue to this CPU's map */ - if (map_len >= alloc_len) { - alloc_len = alloc_len ? - 2 * alloc_len : XPS_MIN_MAP_ALLOC; - new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), - GFP_KERNEL, - cpu_to_node(cpu)); - if (!new_map) - goto error; - new_map->alloc_len = alloc_len; - for (i = 0; i < map_len; i++) - new_map->queues[i] = map->queues[i]; - new_map->len = map_len; - } - new_map->queues[new_map->len++] = index; - } else if (!need_set && pos < map_len) { - /* Need to remove queue from this CPU's map */ - if (map_len > 1) - new_map->queues[pos] = - new_map->queues[--new_map->len]; - else - new_map = NULL; - } - RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], new_map); - } - - /* Cleanup old maps */ - for_each_possible_cpu(cpu) { - map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; - if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map) - call_rcu(&map->rcu, xps_map_release); - if (new_dev_maps->cpu_map[cpu]) - nonempty = 1; - } - - if (nonempty) - rcu_assign_pointer(dev->xps_maps, new_dev_maps); - else { - kfree(new_dev_maps); - rcu_assign_pointer(dev->xps_maps, NULL); - } - - if (dev_maps) - call_rcu(&dev_maps->rcu, xps_dev_maps_release); - - netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node : -1); - - mutex_unlock(&xps_map_mutex); + err = netif_set_xps_queue(dev, mask, index); free_cpumask_var(mask); - return len; -error: - mutex_unlock(&xps_map_mutex); - - if (new_dev_maps) - for_each_possible_cpu(i) - kfree(rcu_dereference_protected( - new_dev_maps->cpu_map[i], - 1)); - kfree(new_dev_maps); - free_cpumask_var(mask); - return -ENOMEM; + return err ? : len; } static struct netdev_queue_attribute xps_cpus_attribute = __ATTR(xps_cpus, S_IRUGO | S_IWUSR, show_xps_map, store_xps_map); +#endif /* CONFIG_XPS */ static struct attribute *netdev_queue_default_attrs[] = { + &queue_trans_timeout.attr, +#ifdef CONFIG_XPS &xps_cpus_attribute.attr, +#endif NULL }; static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); - struct net_device *dev = queue->dev; - struct xps_dev_maps *dev_maps; - struct xps_map *map; - unsigned long index; - int i, pos, nonempty = 0; - - index = get_netdev_queue_index(queue); - mutex_lock(&xps_map_mutex); - dev_maps = xmap_dereference(dev->xps_maps); - - if (dev_maps) { - for_each_possible_cpu(i) { - map = xmap_dereference(dev_maps->cpu_map[i]); - if (!map) - continue; - - for (pos = 0; pos < map->len; pos++) - if (map->queues[pos] == index) - break; - - if (pos < map->len) { - if (map->len > 1) - map->queues[pos] = - map->queues[--map->len]; - else { - RCU_INIT_POINTER(dev_maps->cpu_map[i], - NULL); - call_rcu(&map->rcu, xps_map_release); - map = NULL; - } - } - if (map) - nonempty = 1; - } + memset(kobj, 0, sizeof(*kobj)); + dev_put(queue->dev); +} - if (!nonempty) { - RCU_INIT_POINTER(dev->xps_maps, NULL); - call_rcu(&dev_maps->rcu, xps_dev_maps_release); - } - } +static const void *netdev_queue_namespace(struct kobject *kobj) +{ + struct netdev_queue *queue = to_netdev_queue(kobj); + struct device *dev = &queue->dev->dev; + const void *ns = NULL; - mutex_unlock(&xps_map_mutex); + if (dev->class && dev->class->ns_type) + ns = dev->class->namespace(dev); - memset(kobj, 0, sizeof(*kobj)); - dev_put(queue->dev); + return ns; } static struct kobj_type netdev_queue_ktype = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, .default_attrs = netdev_queue_default_attrs, + .namespace = netdev_queue_namespace, }; static int netdev_queue_add_kobject(struct net_device *net, int index) @@ -1103,22 +1144,29 @@ static int netdev_queue_add_kobject(struct net_device *net, int index) kobj->kset = net->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); - if (error) { - kobject_put(kobj); - return error; - } + if (error) + goto exit; + +#ifdef CONFIG_BQL + error = sysfs_create_group(kobj, &dql_group); + if (error) + goto exit; +#endif kobject_uevent(kobj, KOBJ_ADD); dev_hold(queue->dev); + return 0; +exit: + kobject_put(kobj); return error; } -#endif /* CONFIG_XPS */ +#endif /* CONFIG_SYSFS */ int netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { -#ifdef CONFIG_XPS +#ifdef CONFIG_SYSFS int i; int error = 0; @@ -1130,27 +1178,30 @@ netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) } } - while (--i >= new_num) - kobject_put(&net->_tx[i].kobj); + while (--i >= new_num) { + struct netdev_queue *queue = net->_tx + i; + +#ifdef CONFIG_BQL + sysfs_remove_group(&queue->kobj, &dql_group); +#endif + kobject_put(&queue->kobj); + } return error; #else return 0; -#endif +#endif /* CONFIG_SYSFS */ } static int register_queue_kobjects(struct net_device *net) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; -#if defined(CONFIG_RPS) || defined(CONFIG_XPS) +#ifdef CONFIG_SYSFS net->queues_kset = kset_create_and_add("queues", NULL, &net->dev.kobj); if (!net->queues_kset) return -ENOMEM; -#endif - -#ifdef CONFIG_RPS real_rx = net->real_num_rx_queues; #endif real_tx = net->real_num_tx_queues; @@ -1177,21 +1228,33 @@ static void remove_queue_kobjects(struct net_device *net) { int real_rx = 0, real_tx = 0; -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS real_rx = net->real_num_rx_queues; #endif real_tx = net->real_num_tx_queues; net_rx_queue_update_kobjects(net, real_rx, 0); netdev_queue_update_kobjects(net, real_tx, 0); -#if defined(CONFIG_RPS) || defined(CONFIG_XPS) +#ifdef CONFIG_SYSFS kset_unregister(net->queues_kset); #endif } -static const void *net_current_ns(void) +static bool net_current_may_mount(void) +{ + struct net *net = current->nsproxy->net_ns; + + return ns_capable(net->user_ns, CAP_SYS_ADMIN); +} + +static void *net_grab_current_ns(void) { - return current->nsproxy->net_ns; + struct net *ns = current->nsproxy->net_ns; +#ifdef CONFIG_NET_NS + if (ns) + atomic_inc(&ns->passive); +#endif + return ns; } static const void *net_initial_ns(void) @@ -1206,23 +1269,14 @@ static const void *net_netlink_ns(struct sock *sk) struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, - .current_ns = net_current_ns, + .current_may_mount = net_current_may_mount, + .grab_current_ns = net_grab_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, + .drop_ns = net_drop_ns, }; EXPORT_SYMBOL_GPL(net_ns_type_operations); -static void net_kobj_ns_exit(struct net *net) -{ - kobj_ns_exit(KOBJ_NS_TYPE_NET, net); -} - -static struct pernet_operations kobj_net_ops = { - .exit = net_kobj_ns_exit, -}; - - -#ifdef CONFIG_HOTPLUG static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) { struct net_device *dev = to_net_dev(d); @@ -1241,7 +1295,6 @@ static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) exit: return retval; } -#endif /* * netdev_release -- destroy and free a dead device. @@ -1254,7 +1307,7 @@ static void netdev_release(struct device *d) BUG_ON(dev->reg_state != NETREG_RELEASED); kfree(dev->ifalias); - kfree((char *)dev - dev->padded); + netdev_freemem(dev); } static const void *net_namespace(struct device *d) @@ -1267,12 +1320,8 @@ static const void *net_namespace(struct device *d) static struct class net_class = { .name = "net", .dev_release = netdev_release, -#ifdef CONFIG_SYSFS - .dev_attrs = net_class_attributes, -#endif /* CONFIG_SYSFS */ -#ifdef CONFIG_HOTPLUG + .dev_groups = net_class_groups, .dev_uevent = netdev_uevent, -#endif .ns_type = &net_ns_type_operations, .namespace = net_namespace, }; @@ -1288,6 +1337,8 @@ void netdev_unregister_kobject(struct net_device * net) remove_queue_kobjects(net); + pm_runtime_set_memalloc_noio(dev, false); + device_del(dev); } @@ -1311,10 +1362,11 @@ int netdev_register_kobject(struct net_device *net) groups++; *groups++ = &netstat_group; -#ifdef CONFIG_WIRELESS_EXT_SYSFS + +#if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) if (net->ieee80211_ptr) *groups++ = &wireless_group; -#ifdef CONFIG_WIRELESS_EXT +#if IS_ENABLED(CONFIG_WIRELESS_EXT) else if (net->wireless_handlers) *groups++ = &wireless_group; #endif @@ -1331,24 +1383,27 @@ int netdev_register_kobject(struct net_device *net) return error; } + pm_runtime_set_memalloc_noio(dev, true); + return error; } -int netdev_class_create_file(struct class_attribute *class_attr) +int netdev_class_create_file_ns(struct class_attribute *class_attr, + const void *ns) { - return class_create_file(&net_class, class_attr); + return class_create_file_ns(&net_class, class_attr, ns); } -EXPORT_SYMBOL(netdev_class_create_file); +EXPORT_SYMBOL(netdev_class_create_file_ns); -void netdev_class_remove_file(struct class_attribute *class_attr) +void netdev_class_remove_file_ns(struct class_attribute *class_attr, + const void *ns) { - class_remove_file(&net_class, class_attr); + class_remove_file_ns(&net_class, class_attr, ns); } -EXPORT_SYMBOL(netdev_class_remove_file); +EXPORT_SYMBOL(netdev_class_remove_file_ns); -int netdev_kobject_init(void) +int __init netdev_kobject_init(void) { kobj_ns_type_register(&net_ns_type_operations); - register_pernet_subsys(&kobj_net_ops); return class_register(&net_class); } diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index bd7751ec1c4..2745a1b51e0 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -1,7 +1,7 @@ #ifndef __NET_SYSFS_H__ #define __NET_SYSFS_H__ -int netdev_kobject_init(void); +int __init netdev_kobject_init(void); int netdev_register_kobject(struct net_device *); void netdev_unregister_kobject(struct net_device *); int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 7f1bb2aba03..ba3c0120786 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -11,6 +11,7 @@ #include <linux/inetdevice.h> #include <linux/inet.h> #include <linux/interrupt.h> +#include <linux/export.h> #include <linux/netpoll.h> #include <linux/sched.h> #include <linux/delay.h> @@ -28,6 +29,8 @@ #include <trace/events/skb.h> #include <trace/events/net.h> #include <trace/events/napi.h> +#include <trace/events/sock.h> +#include <trace/events/udp.h> EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 3f860261c5e..85b62691f4f 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -1,3 +1,5 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/workqueue.h> #include <linux/rtnetlink.h> #include <linux/cache.h> @@ -8,6 +10,11 @@ #include <linux/idr.h> #include <linux/rculist.h> #include <linux/nsproxy.h> +#include <linux/fs.h> +#include <linux/proc_ns.h> +#include <linux/file.h> +#include <linux/export.h> +#include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -17,22 +24,30 @@ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; -static DEFINE_MUTEX(net_mutex); +DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); -struct net init_net; +struct net init_net = { + .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), +}; EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ -static void net_generic_release(struct rcu_head *rcu) +static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; + +static struct net_generic *net_alloc_generic(void) { struct net_generic *ng; + size_t generic_size = offsetof(struct net_generic, ptr[max_gen_ptrs]); - ng = container_of(rcu, struct net_generic, rcu); - kfree(ng); + ng = kzalloc(generic_size, GFP_KERNEL); + if (ng) + ng->len = max_gen_ptrs; + + return ng; } static int net_assign_generic(struct net *net, int id, void *data) @@ -48,8 +63,7 @@ static int net_assign_generic(struct net *net, int id, void *data) if (old_ng->len >= id) goto assign; - ng = kzalloc(sizeof(struct net_generic) + - id * sizeof(void *), GFP_KERNEL); + ng = net_alloc_generic(); if (ng == NULL) return -ENOMEM; @@ -64,11 +78,10 @@ static int net_assign_generic(struct net *net, int id, void *data) * the old copy for kfree after a grace period. */ - ng->len = id; memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); rcu_assign_pointer(net->gen, ng); - call_rcu(&old_ng->rcu, net_generic_release); + kfree_rcu(old_ng, rcu); assign: ng->ptr[id - 1] = data; return 0; @@ -76,21 +89,29 @@ assign: static int ops_init(const struct pernet_operations *ops, struct net *net) { - int err; + int err = -ENOMEM; + void *data = NULL; + if (ops->id && ops->size) { - void *data = kzalloc(ops->size, GFP_KERNEL); + data = kzalloc(ops->size, GFP_KERNEL); if (!data) - return -ENOMEM; + goto out; err = net_assign_generic(net, *ops->id, data); - if (err) { - kfree(data); - return err; - } + if (err) + goto cleanup; } + err = 0; if (ops->init) - return ops->init(net); - return 0; + err = ops->init(net); + if (!err) + return 0; + +cleanup: + kfree(data); + +out: + return err; } static void ops_free(const struct pernet_operations *ops, struct net *net) @@ -126,7 +147,7 @@ static void ops_free_list(const struct pernet_operations *ops, /* * setup_net runs the initializers for the network namespace object. */ -static __net_init int setup_net(struct net *net) +static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) { /* Must be called with net_mutex held */ const struct pernet_operations *ops, *saved_ops; @@ -134,6 +155,9 @@ static __net_init int setup_net(struct net *net) LIST_HEAD(net_exit_list); atomic_set(&net->count, 1); + atomic_set(&net->passive, 1); + net->dev_base_seq = 1; + net->user_ns = user_ns; #ifdef NETNS_REFCNT_DEBUG atomic_set(&net->use_count, 0); @@ -164,18 +188,6 @@ out_undo: goto out; } -static struct net_generic *net_alloc_generic(void) -{ - struct net_generic *ng; - size_t generic_size = sizeof(struct net_generic) + - INITIAL_NET_GEN_PTRS * sizeof(void *); - - ng = kzalloc(generic_size, GFP_KERNEL); - if (ng) - ng->len = INITIAL_NET_GEN_PTRS; - - return ng; -} #ifdef CONFIG_NET_NS static struct kmem_cache *net_cachep; @@ -207,8 +219,8 @@ static void net_free(struct net *net) { #ifdef NETNS_REFCNT_DEBUG if (unlikely(atomic_read(&net->use_count) != 0)) { - printk(KERN_EMERG "network namespace not free! Usage: %d\n", - atomic_read(&net->use_count)); + pr_emerg("network namespace not free! Usage: %d\n", + atomic_read(&net->use_count)); return; } #endif @@ -216,16 +228,30 @@ static void net_free(struct net *net) kmem_cache_free(net_cachep, net); } -static struct net *net_create(void) +void net_drop_ns(void *p) +{ + struct net *ns = p; + if (ns && atomic_dec_and_test(&ns->passive)) + net_free(ns); +} + +struct net *copy_net_ns(unsigned long flags, + struct user_namespace *user_ns, struct net *old_net) { struct net *net; int rv; + if (!(flags & CLONE_NEWNET)) + return get_net(old_net); + net = net_alloc(); if (!net) return ERR_PTR(-ENOMEM); + + get_user_ns(user_ns); + mutex_lock(&net_mutex); - rv = setup_net(net); + rv = setup_net(net, user_ns); if (rv == 0) { rtnl_lock(); list_add_tail_rcu(&net->list, &net_namespace_list); @@ -233,19 +259,13 @@ static struct net *net_create(void) } mutex_unlock(&net_mutex); if (rv < 0) { - net_free(net); + put_user_ns(user_ns); + net_drop_ns(net); return ERR_PTR(rv); } return net; } -struct net *copy_net_ns(unsigned long flags, struct net *old_net) -{ - if (!(flags & CLONE_NEWNET)) - return get_net(old_net); - return net_create(); -} - static DEFINE_SPINLOCK(cleanup_list_lock); static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ @@ -253,7 +273,7 @@ static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; struct net *net, *tmp; - LIST_HEAD(net_kill_list); + struct list_head net_kill_list; LIST_HEAD(net_exit_list); /* Atomically snapshot the list of namespaces to cleanup */ @@ -296,7 +316,8 @@ static void cleanup_net(struct work_struct *work) /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); - net_free(net); + put_user_ns(net->user_ns); + net_drop_ns(net); } } static DECLARE_WORK(net_cleanup_work, cleanup_net); @@ -314,12 +335,30 @@ void __put_net(struct net *net) } EXPORT_SYMBOL_GPL(__put_net); +struct net *get_net_ns_by_fd(int fd) +{ + struct proc_ns *ei; + struct file *file; + struct net *net; + + file = proc_ns_fget(fd); + if (IS_ERR(file)) + return ERR_CAST(file); + + ei = get_proc_ns(file_inode(file)); + if (ei->ns_ops == &netns_operations) + net = get_net(ei->ns); + else + net = ERR_PTR(-EINVAL); + + fput(file); + return net; +} + #else -struct net *copy_net_ns(unsigned long flags, struct net *old_net) +struct net *get_net_ns_by_fd(int fd) { - if (flags & CLONE_NEWNET) - return ERR_PTR(-EINVAL); - return old_net; + return ERR_PTR(-EINVAL); } #endif @@ -343,6 +382,21 @@ struct net *get_net_ns_by_pid(pid_t pid) } EXPORT_SYMBOL_GPL(get_net_ns_by_pid); +static __net_init int net_ns_net_init(struct net *net) +{ + return proc_alloc_inum(&net->proc_inum); +} + +static __net_exit void net_ns_net_exit(struct net *net) +{ + proc_free_inum(net->proc_inum); +} + +static struct pernet_operations __net_initdata net_ns_ops = { + .init = net_ns_net_init, + .exit = net_ns_net_exit, +}; + static int __init net_ns_init(void) { struct net_generic *ng; @@ -365,7 +419,7 @@ static int __init net_ns_init(void) rcu_assign_pointer(init_net.gen, ng); mutex_lock(&net_mutex); - if (setup_net(&init_net)) + if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); rtnl_lock(); @@ -374,6 +428,8 @@ static int __init net_ns_init(void) mutex_unlock(&net_mutex); + register_pernet_subsys(&net_ns_ops); + return 0; } @@ -423,12 +479,7 @@ static void __unregister_pernet_operations(struct pernet_operations *ops) static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { - int err = 0; - err = ops_init(ops, &init_net); - if (err) - ops_free(ops, &init_net); - return err; - + return ops_init(ops, &init_net); } static void __unregister_pernet_operations(struct pernet_operations *ops) @@ -458,6 +509,7 @@ again: } return error; } + max_gen_ptrs = max_t(unsigned int, max_gen_ptrs, *ops->id); } error = __register_pernet_operations(list, ops); if (error) { @@ -573,3 +625,52 @@ void unregister_pernet_device(struct pernet_operations *ops) mutex_unlock(&net_mutex); } EXPORT_SYMBOL_GPL(unregister_pernet_device); + +#ifdef CONFIG_NET_NS +static void *netns_get(struct task_struct *task) +{ + struct net *net = NULL; + struct nsproxy *nsproxy; + + rcu_read_lock(); + nsproxy = task_nsproxy(task); + if (nsproxy) + net = get_net(nsproxy->net_ns); + rcu_read_unlock(); + + return net; +} + +static void netns_put(void *ns) +{ + put_net(ns); +} + +static int netns_install(struct nsproxy *nsproxy, void *ns) +{ + struct net *net = ns; + + if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) || + !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) + return -EPERM; + + put_net(nsproxy->net_ns); + nsproxy->net_ns = get_net(net); + return 0; +} + +static unsigned int netns_inum(void *ns) +{ + struct net *net = ns; + return net->proc_inum; +} + +const struct proc_ns_operations netns_operations = { + .name = "net", + .type = CLONE_NEWNET, + .get = netns_get, + .put = netns_put, + .install = netns_install, + .inum = netns_inum, +}; +#endif diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c new file mode 100644 index 00000000000..30d903b19c6 --- /dev/null +++ b/net/core/netclassid_cgroup.c @@ -0,0 +1,111 @@ +/* + * net/core/netclassid_cgroup.c Classid Cgroupfs Handling + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Thomas Graf <tgraf@suug.ch> + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/cgroup.h> +#include <linux/fdtable.h> +#include <net/cls_cgroup.h> +#include <net/sock.h> + +static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct cgroup_cls_state, css) : NULL; +} + +struct cgroup_cls_state *task_cls_state(struct task_struct *p) +{ + return css_cls_state(task_css(p, net_cls_cgrp_id)); +} +EXPORT_SYMBOL_GPL(task_cls_state); + +static struct cgroup_subsys_state * +cgrp_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_cls_state *cs; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + return &cs->css; +} + +static int cgrp_css_online(struct cgroup_subsys_state *css) +{ + struct cgroup_cls_state *cs = css_cls_state(css); + struct cgroup_cls_state *parent = css_cls_state(css->parent); + + if (parent) + cs->classid = parent->classid; + + return 0; +} + +static void cgrp_css_free(struct cgroup_subsys_state *css) +{ + kfree(css_cls_state(css)); +} + +static int update_classid(const void *v, struct file *file, unsigned n) +{ + int err; + struct socket *sock = sock_from_file(file, &err); + + if (sock) + sock->sk->sk_classid = (u32)(unsigned long)v; + + return 0; +} + +static void cgrp_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct cgroup_cls_state *cs = css_cls_state(css); + void *v = (void *)(unsigned long)cs->classid; + struct task_struct *p; + + cgroup_taskset_for_each(p, tset) { + task_lock(p); + iterate_fd(p->files, 0, update_classid, v); + task_unlock(p); + } +} + +static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return css_cls_state(css)->classid; +} + +static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, + u64 value) +{ + css_cls_state(css)->classid = (u32) value; + + return 0; +} + +static struct cftype ss_files[] = { + { + .name = "classid", + .read_u64 = read_classid, + .write_u64 = write_classid, + }, + { } /* terminate */ +}; + +struct cgroup_subsys net_cls_cgrp_subsys = { + .css_alloc = cgrp_css_alloc, + .css_online = cgrp_css_online, + .css_free = cgrp_css_free, + .attach = cgrp_attach, + .base_cftypes = ss_files, +}; diff --git a/net/core/netevent.c b/net/core/netevent.c index 865f0ceb81f..f17ccd291d3 100644 --- a/net/core/netevent.c +++ b/net/core/netevent.c @@ -15,6 +15,7 @@ #include <linux/rtnetlink.h> #include <linux/notifier.h> +#include <linux/export.h> #include <net/netevent.h> static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index ee38acb6d46..e33937fb32a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -9,7 +9,10 @@ * Copyright (C) 2002 Red Hat, Inc. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/moduleparam.h> +#include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> @@ -23,8 +26,13 @@ #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/slab.h> +#include <linux/export.h> +#include <linux/if_vlan.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/addrconf.h> +#include <net/ndisc.h> +#include <net/ip6_checksum.h> #include <asm/unaligned.h> #include <trace/events/napi.h> @@ -35,26 +43,63 @@ #define MAX_UDP_CHUNK 1460 #define MAX_SKBS 32 -#define MAX_QUEUE_DEPTH (MAX_SKBS / 2) static struct sk_buff_head skb_pool; -static atomic_t trapped; +DEFINE_STATIC_SRCU(netpoll_srcu); #define USEC_PER_POLL 50 -#define NETPOLL_RX_ENABLED 1 -#define NETPOLL_RX_DROP 2 -#define MAX_SKB_SIZE \ - (MAX_UDP_CHUNK + sizeof(struct udphdr) + \ - sizeof(struct iphdr) + sizeof(struct ethhdr)) +#define MAX_SKB_SIZE \ + (sizeof(struct ethhdr) + \ + sizeof(struct iphdr) + \ + sizeof(struct udphdr) + \ + MAX_UDP_CHUNK) static void zap_completion_queue(void); -static void arp_reply(struct sk_buff *skb); +static void netpoll_async_cleanup(struct work_struct *work); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); +#define np_info(np, fmt, ...) \ + pr_info("%s: " fmt, np->name, ##__VA_ARGS__) +#define np_err(np, fmt, ...) \ + pr_err("%s: " fmt, np->name, ##__VA_ARGS__) +#define np_notice(np, fmt, ...) \ + pr_notice("%s: " fmt, np->name, ##__VA_ARGS__) + +static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, + struct netdev_queue *txq) +{ + const struct net_device_ops *ops = dev->netdev_ops; + int status = NETDEV_TX_OK; + netdev_features_t features; + + features = netif_skb_features(skb); + + if (vlan_tx_tag_present(skb) && + !vlan_hw_offload_capable(features, skb->vlan_proto)) { + skb = __vlan_put_tag(skb, skb->vlan_proto, + vlan_tx_tag_get(skb)); + if (unlikely(!skb)) { + /* This is actually a packet drop, but we + * don't want the code that calls this + * function to try and operate on a NULL skb. + */ + goto out; + } + skb->vlan_tci = 0; + } + + status = ops->ndo_start_xmit(skb, dev); + if (status == NETDEV_TX_OK) + txq_trans_update(txq); + +out: + return status; +} + static void queue_process(struct work_struct *work) { struct netpoll_info *npinfo = @@ -64,51 +109,31 @@ static void queue_process(struct work_struct *work) while ((skb = skb_dequeue(&npinfo->txq))) { struct net_device *dev = skb->dev; - const struct net_device_ops *ops = dev->netdev_ops; struct netdev_queue *txq; if (!netif_device_present(dev) || !netif_running(dev)) { - __kfree_skb(skb); + kfree_skb(skb); continue; } txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); local_irq_save(flags); - __netif_tx_lock(txq, smp_processor_id()); - if (netif_tx_queue_frozen_or_stopped(txq) || - ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) { + HARD_TX_LOCK(dev, txq, smp_processor_id()); + if (netif_xmit_frozen_or_stopped(txq) || + netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) { skb_queue_head(&npinfo->txq, skb); - __netif_tx_unlock(txq); + HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); schedule_delayed_work(&npinfo->tx_work, HZ/10); return; } - __netif_tx_unlock(txq); + HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); } } -static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh, - unsigned short ulen, __be32 saddr, __be32 daddr) -{ - __wsum psum; - - if (uh->check == 0 || skb_csum_unnecessary(skb)) - return 0; - - psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); - - if (skb->ip_summed == CHECKSUM_COMPLETE && - !csum_fold(csum_add(psum, skb->csum))) - return 0; - - skb->csum = psum; - - return __skb_checksum_complete(skb); -} - /* * Check whether delayed processing was scheduled for our NIC. If so, * we attempt to grab the poll lock and use ->poll() to pump the card. @@ -119,14 +144,8 @@ static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh, * trylock here and interrupts are already disabled in the softirq * case. Further, we test the poll_owner to avoid recursion on UP * systems where the lock doesn't exist. - * - * In cases where there is bi-directional communications, reading only - * one message at a time can lead to packets being dropped by the - * network adapter, forcing superfluous retries and possibly timeouts. - * Thus, we set our budget to greater than 1. */ -static int poll_one_napi(struct netpoll_info *npinfo, - struct napi_struct *napi, int budget) +static int poll_one_napi(struct napi_struct *napi, int budget) { int work; @@ -137,74 +156,87 @@ static int poll_one_napi(struct netpoll_info *npinfo, if (!test_bit(NAPI_STATE_SCHED, &napi->state)) return budget; - npinfo->rx_flags |= NETPOLL_RX_DROP; - atomic_inc(&trapped); set_bit(NAPI_STATE_NPSVC, &napi->state); work = napi->poll(napi, budget); + WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll); trace_napi_poll(napi); clear_bit(NAPI_STATE_NPSVC, &napi->state); - atomic_dec(&trapped); - npinfo->rx_flags &= ~NETPOLL_RX_DROP; return budget - work; } -static void poll_napi(struct net_device *dev) +static void poll_napi(struct net_device *dev, int budget) { struct napi_struct *napi; - int budget = 16; list_for_each_entry(napi, &dev->napi_list, dev_list) { if (napi->poll_owner != smp_processor_id() && spin_trylock(&napi->poll_lock)) { - budget = poll_one_napi(dev->npinfo, napi, budget); + budget = poll_one_napi(napi, budget); spin_unlock(&napi->poll_lock); - - if (!budget) - break; } } } -static void service_arp_queue(struct netpoll_info *npi) -{ - if (npi) { - struct sk_buff *skb; - - while ((skb = skb_dequeue(&npi->arp_tx))) - arp_reply(skb); - } -} - -void netpoll_poll_dev(struct net_device *dev) +static void netpoll_poll_dev(struct net_device *dev) { const struct net_device_ops *ops; + struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); + int budget = 0; - if (!dev || !netif_running(dev)) + /* Don't do any rx activity if the dev_lock mutex is held + * the dev_open/close paths use this to block netpoll activity + * while changing device state + */ + if (down_trylock(&ni->dev_lock)) return; + if (!netif_running(dev)) { + up(&ni->dev_lock); + return; + } + ops = dev->netdev_ops; - if (!ops->ndo_poll_controller) + if (!ops->ndo_poll_controller) { + up(&ni->dev_lock); return; + } /* Process pending work on NIC */ ops->ndo_poll_controller(dev); - poll_napi(dev); + poll_napi(dev, budget); - service_arp_queue(dev->npinfo); + up(&ni->dev_lock); zap_completion_queue(); } -EXPORT_SYMBOL(netpoll_poll_dev); -void netpoll_poll(struct netpoll *np) +void netpoll_poll_disable(struct net_device *dev) { - netpoll_poll_dev(np->dev); + struct netpoll_info *ni; + int idx; + might_sleep(); + idx = srcu_read_lock(&netpoll_srcu); + ni = srcu_dereference(dev->npinfo, &netpoll_srcu); + if (ni) + down(&ni->dev_lock); + srcu_read_unlock(&netpoll_srcu, idx); } -EXPORT_SYMBOL(netpoll_poll); +EXPORT_SYMBOL(netpoll_poll_disable); + +void netpoll_poll_enable(struct net_device *dev) +{ + struct netpoll_info *ni; + rcu_read_lock(); + ni = rcu_dereference(dev->npinfo); + if (ni) + up(&ni->dev_lock); + rcu_read_unlock(); +} +EXPORT_SYMBOL(netpoll_poll_enable); static void refill_skbs(void) { @@ -238,7 +270,7 @@ static void zap_completion_queue(void) while (clist != NULL) { struct sk_buff *skb = clist; clist = clist->next; - if (skb->destructor) { + if (!skb_irq_freeable(skb)) { atomic_inc(&skb->users); dev_kfree_skb_any(skb); /* put this one back */ } else { @@ -265,7 +297,7 @@ repeat: if (!skb) { if (++count < 10) { - netpoll_poll(np); + netpoll_poll_dev(np->dev); goto repeat; } return NULL; @@ -287,40 +319,37 @@ static int netpoll_owner_active(struct net_device *dev) return 0; } +/* call with IRQ disabled */ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, struct net_device *dev) { int status = NETDEV_TX_BUSY; unsigned long tries; - const struct net_device_ops *ops = dev->netdev_ops; /* It is up to the caller to keep npinfo alive. */ - struct netpoll_info *npinfo = np->dev->npinfo; + struct netpoll_info *npinfo; + + WARN_ON_ONCE(!irqs_disabled()); + npinfo = rcu_dereference_bh(np->dev->npinfo); if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { - __kfree_skb(skb); + dev_kfree_skb_irq(skb); return; } /* don't get messages out of order, and no recursion */ if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) { struct netdev_queue *txq; - unsigned long flags; - txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); + txq = netdev_pick_tx(dev, skb, NULL); - local_irq_save(flags); /* try until next clock tick */ for (tries = jiffies_to_usecs(1)/USEC_PER_POLL; tries > 0; --tries) { - if (__netif_tx_trylock(txq)) { - if (!netif_tx_queue_stopped(txq)) { - dev->priv_flags |= IFF_IN_NETPOLL; - status = ops->ndo_start_xmit(skb, dev); - dev->priv_flags &= ~IFF_IN_NETPOLL; - if (status == NETDEV_TX_OK) - txq_trans_update(txq); - } - __netif_tx_unlock(txq); + if (HARD_TX_TRYLOCK(dev, txq)) { + if (!netif_xmit_stopped(txq)) + status = netpoll_start_xmit(skb, dev, txq); + + HARD_TX_UNLOCK(dev, txq); if (status == NETDEV_TX_OK) break; @@ -328,16 +357,15 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, } /* tickle device maybe there is some cleanup */ - netpoll_poll(np); + netpoll_poll_dev(np->dev); udelay(USEC_PER_POLL); } WARN_ONCE(!irqs_disabled(), - "netpoll_send_skb(): %s enabled interrupts in poll (%pF)\n", - dev->name, ops->ndo_start_xmit); + "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n", + dev->name, dev->netdev_ops->ndo_start_xmit); - local_irq_restore(flags); } if (status != NETDEV_TX_OK) { @@ -349,22 +377,29 @@ EXPORT_SYMBOL(netpoll_send_skb_on_dev); void netpoll_send_udp(struct netpoll *np, const char *msg, int len) { - int total_len, eth_len, ip_len, udp_len; + int total_len, ip_len, udp_len; struct sk_buff *skb; struct udphdr *udph; struct iphdr *iph; struct ethhdr *eth; + static atomic_t ip_ident; + struct ipv6hdr *ip6h; udp_len = len + sizeof(*udph); - ip_len = eth_len = udp_len + sizeof(*iph); - total_len = eth_len + ETH_HLEN + NET_IP_ALIGN; + if (np->ipv6) + ip_len = udp_len + sizeof(*ip6h); + else + ip_len = udp_len + sizeof(*iph); + + total_len = ip_len + LL_RESERVED_SPACE(np->dev); - skb = find_skb(np, total_len, total_len - len); + skb = find_skb(np, total_len + np->dev->needed_tailroom, + total_len - len); if (!skb) return; skb_copy_to_linear_data(skb, msg, len); - skb->len += len; + skb_put(skb, len); skb_push(skb, sizeof(*udph)); skb_reset_transport_header(skb); @@ -372,36 +407,68 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) udph->source = htons(np->local_port); udph->dest = htons(np->remote_port); udph->len = htons(udp_len); - udph->check = 0; - udph->check = csum_tcpudp_magic(np->local_ip, - np->remote_ip, - udp_len, IPPROTO_UDP, - csum_partial(udph, udp_len, 0)); - if (udph->check == 0) - udph->check = CSUM_MANGLED_0; - - skb_push(skb, sizeof(*iph)); - skb_reset_network_header(skb); - iph = ip_hdr(skb); - - /* iph->version = 4; iph->ihl = 5; */ - put_unaligned(0x45, (unsigned char *)iph); - iph->tos = 0; - put_unaligned(htons(ip_len), &(iph->tot_len)); - iph->id = 0; - iph->frag_off = 0; - iph->ttl = 64; - iph->protocol = IPPROTO_UDP; - iph->check = 0; - put_unaligned(np->local_ip, &(iph->saddr)); - put_unaligned(np->remote_ip, &(iph->daddr)); - iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); - - eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); - skb_reset_mac_header(skb); - skb->protocol = eth->h_proto = htons(ETH_P_IP); - memcpy(eth->h_source, np->dev->dev_addr, ETH_ALEN); - memcpy(eth->h_dest, np->remote_mac, ETH_ALEN); + + if (np->ipv6) { + udph->check = 0; + udph->check = csum_ipv6_magic(&np->local_ip.in6, + &np->remote_ip.in6, + udp_len, IPPROTO_UDP, + csum_partial(udph, udp_len, 0)); + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + + skb_push(skb, sizeof(*ip6h)); + skb_reset_network_header(skb); + ip6h = ipv6_hdr(skb); + + /* ip6h->version = 6; ip6h->priority = 0; */ + put_unaligned(0x60, (unsigned char *)ip6h); + ip6h->flow_lbl[0] = 0; + ip6h->flow_lbl[1] = 0; + ip6h->flow_lbl[2] = 0; + + ip6h->payload_len = htons(sizeof(struct udphdr) + len); + ip6h->nexthdr = IPPROTO_UDP; + ip6h->hop_limit = 32; + ip6h->saddr = np->local_ip.in6; + ip6h->daddr = np->remote_ip.in6; + + eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth->h_proto = htons(ETH_P_IPV6); + } else { + udph->check = 0; + udph->check = csum_tcpudp_magic(np->local_ip.ip, + np->remote_ip.ip, + udp_len, IPPROTO_UDP, + csum_partial(udph, udp_len, 0)); + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + + skb_push(skb, sizeof(*iph)); + skb_reset_network_header(skb); + iph = ip_hdr(skb); + + /* iph->version = 4; iph->ihl = 5; */ + put_unaligned(0x45, (unsigned char *)iph); + iph->tos = 0; + put_unaligned(htons(ip_len), &(iph->tot_len)); + iph->id = htons(atomic_inc_return(&ip_ident)); + iph->frag_off = 0; + iph->ttl = 64; + iph->protocol = IPPROTO_UDP; + iph->check = 0; + put_unaligned(np->local_ip.ip, &(iph->saddr)); + put_unaligned(np->remote_ip.ip, &(iph->daddr)); + iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + + eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth->h_proto = htons(ETH_P_IP); + } + + ether_addr_copy(eth->h_source, np->dev->dev_addr); + ether_addr_copy(eth->h_dest, np->remote_mac); skb->dev = np->dev; @@ -409,251 +476,69 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) } EXPORT_SYMBOL(netpoll_send_udp); -static void arp_reply(struct sk_buff *skb) +void netpoll_print_options(struct netpoll *np) { - struct netpoll_info *npinfo = skb->dev->npinfo; - struct arphdr *arp; - unsigned char *arp_ptr; - int size, type = ARPOP_REPLY, ptype = ETH_P_ARP; - __be32 sip, tip; - unsigned char *sha; - struct sk_buff *send_skb; - struct netpoll *np, *tmp; - unsigned long flags; - int hits = 0; - - if (list_empty(&npinfo->rx_np)) - return; - - /* Before checking the packet, we do some early - inspection whether this is interesting at all */ - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (np->dev == skb->dev) - hits++; - } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - - /* No netpoll struct is using this dev */ - if (!hits) - return; - - /* No arp on this interface */ - if (skb->dev->flags & IFF_NOARP) - return; - - if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) - return; - - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - arp = arp_hdr(skb); - - if ((arp->ar_hrd != htons(ARPHRD_ETHER) && - arp->ar_hrd != htons(ARPHRD_IEEE802)) || - arp->ar_pro != htons(ETH_P_IP) || - arp->ar_op != htons(ARPOP_REQUEST)) - return; - - arp_ptr = (unsigned char *)(arp+1); - /* save the location of the src hw addr */ - sha = arp_ptr; - arp_ptr += skb->dev->addr_len; - memcpy(&sip, arp_ptr, 4); - arp_ptr += 4; - /* If we actually cared about dst hw addr, - it would get copied here */ - arp_ptr += skb->dev->addr_len; - memcpy(&tip, arp_ptr, 4); - - /* Should we ignore arp? */ - if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) - return; - - size = arp_hdr_len(skb->dev); - - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (tip != np->local_ip) - continue; - - send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev), - LL_RESERVED_SPACE(np->dev)); - if (!send_skb) - continue; - - skb_reset_network_header(send_skb); - arp = (struct arphdr *) skb_put(send_skb, size); - send_skb->dev = skb->dev; - send_skb->protocol = htons(ETH_P_ARP); - - /* Fill the device header for the ARP frame */ - if (dev_hard_header(send_skb, skb->dev, ptype, - sha, np->dev->dev_addr, - send_skb->len) < 0) { - kfree_skb(send_skb); - continue; - } - - /* - * Fill out the arp protocol part. - * - * we only support ethernet device type, - * which (according to RFC 1390) should - * always equal 1 (Ethernet). - */ - - arp->ar_hrd = htons(np->dev->type); - arp->ar_pro = htons(ETH_P_IP); - arp->ar_hln = np->dev->addr_len; - arp->ar_pln = 4; - arp->ar_op = htons(type); - - arp_ptr = (unsigned char *)(arp + 1); - memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &tip, 4); - arp_ptr += 4; - memcpy(arp_ptr, sha, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &sip, 4); - - netpoll_send_skb(np, send_skb); - - /* If there are several rx_hooks for the same address, - we're fine by sending a single reply */ - break; - } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); + np_info(np, "local port %d\n", np->local_port); + if (np->ipv6) + np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); + else + np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); + np_info(np, "interface '%s'\n", np->dev_name); + np_info(np, "remote port %d\n", np->remote_port); + if (np->ipv6) + np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); + else + np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); + np_info(np, "remote ethernet address %pM\n", np->remote_mac); } +EXPORT_SYMBOL(netpoll_print_options); -int __netpoll_rx(struct sk_buff *skb) +static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) { - int proto, len, ulen; - int hits = 0; - struct iphdr *iph; - struct udphdr *uh; - struct netpoll_info *npinfo = skb->dev->npinfo; - struct netpoll *np, *tmp; + const char *end; - if (list_empty(&npinfo->rx_np)) - goto out; - - if (skb->dev->type != ARPHRD_ETHER) - goto out; - - /* check if netpoll clients need ARP */ - if (skb->protocol == htons(ETH_P_ARP) && - atomic_read(&trapped)) { - skb_queue_tail(&npinfo->arp_tx, skb); - return 1; + if (!strchr(str, ':') && + in4_pton(str, -1, (void *)addr, -1, &end) > 0) { + if (!*end) + return 0; } - - proto = ntohs(eth_hdr(skb)->h_proto); - if (proto != ETH_P_IP) - goto out; - if (skb->pkt_type == PACKET_OTHERHOST) - goto out; - if (skb_shared(skb)) - goto out; - - iph = (struct iphdr *)skb->data; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto out; - if (iph->ihl < 5 || iph->version != 4) - goto out; - if (!pskb_may_pull(skb, iph->ihl*4)) - goto out; - if (ip_fast_csum((u8 *)iph, iph->ihl) != 0) - goto out; - - len = ntohs(iph->tot_len); - if (skb->len < len || len < iph->ihl*4) - goto out; - - /* - * Our transport medium may have padded the buffer out. - * Now We trim to the true length of the frame. - */ - if (pskb_trim_rcsum(skb, len)) - goto out; - - if (iph->protocol != IPPROTO_UDP) - goto out; - - len -= iph->ihl*4; - uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); - ulen = ntohs(uh->len); - - if (ulen != len) - goto out; - if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) - goto out; - - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (np->local_ip && np->local_ip != iph->daddr) - continue; - if (np->remote_ip && np->remote_ip != iph->saddr) - continue; - if (np->local_port && np->local_port != ntohs(uh->dest)) - continue; - - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); - hits++; - } - - if (!hits) - goto out; - - kfree_skb(skb); - return 1; - -out: - if (atomic_read(&trapped)) { - kfree_skb(skb); - return 1; + if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { +#if IS_ENABLED(CONFIG_IPV6) + if (!*end) + return 1; +#else + return -1; +#endif } - - return 0; -} - -void netpoll_print_options(struct netpoll *np) -{ - printk(KERN_INFO "%s: local port %d\n", - np->name, np->local_port); - printk(KERN_INFO "%s: local IP %pI4\n", - np->name, &np->local_ip); - printk(KERN_INFO "%s: interface '%s'\n", - np->name, np->dev_name); - printk(KERN_INFO "%s: remote port %d\n", - np->name, np->remote_port); - printk(KERN_INFO "%s: remote IP %pI4\n", - np->name, &np->remote_ip); - printk(KERN_INFO "%s: remote ethernet address %pM\n", - np->name, np->remote_mac); + return -1; } -EXPORT_SYMBOL(netpoll_print_options); int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; + int ipv6; + bool ipversion_set = false; if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) goto parse_failed; *delim = 0; - np->local_port = simple_strtol(cur, NULL, 10); + if (kstrtou16(cur, 10, &np->local_port)) + goto parse_failed; cur = delim; } cur++; if (*cur != '/') { + ipversion_set = true; if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; - np->local_ip = in_aton(cur); + ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip); + if (ipv6 < 0) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; cur = delim; } cur++; @@ -674,9 +559,9 @@ int netpoll_parse_options(struct netpoll *np, char *opt) goto parse_failed; *delim = 0; if (*cur == ' ' || *cur == '\t') - printk(KERN_INFO "%s: warning: whitespace" - "is not allowed\n", np->name); - np->remote_port = simple_strtol(cur, NULL, 10); + np_info(np, "warning: whitespace is not allowed\n"); + if (kstrtou16(cur, 10, &np->remote_port)) + goto parse_failed; cur = delim; } cur++; @@ -685,37 +570,19 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; - np->remote_ip = in_aton(cur); + ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); + if (ipv6 < 0) + goto parse_failed; + else if (ipversion_set && np->ipv6 != (bool)ipv6) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; cur = delim + 1; if (*cur != 0) { /* MAC address */ - if ((delim = strchr(cur, ':')) == NULL) + if (!mac_pton(cur, np->remote_mac)) goto parse_failed; - *delim = 0; - np->remote_mac[0] = simple_strtol(cur, NULL, 16); - cur = delim + 1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim = 0; - np->remote_mac[1] = simple_strtol(cur, NULL, 16); - cur = delim + 1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim = 0; - np->remote_mac[2] = simple_strtol(cur, NULL, 16); - cur = delim + 1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim = 0; - np->remote_mac[3] = simple_strtol(cur, NULL, 16); - cur = delim + 1; - if ((delim = strchr(cur, ':')) == NULL) - goto parse_failed; - *delim = 0; - np->remote_mac[4] = simple_strtol(cur, NULL, 16); - cur = delim + 1; - np->remote_mac[5] = simple_strtol(cur, NULL, 16); } netpoll_print_options(np); @@ -723,24 +590,25 @@ int netpoll_parse_options(struct netpoll *np, char *opt) return 0; parse_failed: - printk(KERN_INFO "%s: couldn't parse config at '%s'!\n", - np->name, cur); + np_info(np, "couldn't parse config at '%s'!\n", cur); return -1; } EXPORT_SYMBOL(netpoll_parse_options); -int __netpoll_setup(struct netpoll *np) +int __netpoll_setup(struct netpoll *np, struct net_device *ndev) { - struct net_device *ndev = np->dev; struct netpoll_info *npinfo; const struct net_device_ops *ops; - unsigned long flags; int err; + np->dev = ndev; + strlcpy(np->dev_name, ndev->name, IFNAMSIZ); + INIT_WORK(&np->cleanup_work, netpoll_async_cleanup); + if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || !ndev->netdev_ops->ndo_poll_controller) { - printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n", - np->name, np->dev_name); + np_err(np, "%s doesn't support polling, aborting\n", + np->dev_name); err = -ENOTSUPP; goto out; } @@ -752,11 +620,7 @@ int __netpoll_setup(struct netpoll *np) goto out; } - npinfo->rx_flags = 0; - INIT_LIST_HEAD(&npinfo->rx_np); - - spin_lock_init(&npinfo->rx_lock); - skb_queue_head_init(&npinfo->arp_tx); + sema_init(&npinfo->dev_lock, 1); skb_queue_head_init(&npinfo->txq); INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); @@ -769,19 +633,12 @@ int __netpoll_setup(struct netpoll *np) goto free_npinfo; } } else { - npinfo = ndev->npinfo; + npinfo = rtnl_dereference(ndev->npinfo); atomic_inc(&npinfo->refcnt); } npinfo->netpoll = np; - if (np->rx_hook) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - npinfo->rx_flags |= NETPOLL_RX_ENABLED; - list_add_tail(&np->rx, &npinfo->rx_np); - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } - /* last thing to do is link it to the net device structure */ rcu_assign_pointer(ndev->npinfo, npinfo); @@ -800,37 +657,42 @@ int netpoll_setup(struct netpoll *np) struct in_device *in_dev; int err; - if (np->dev_name) - ndev = dev_get_by_name(&init_net, np->dev_name); + rtnl_lock(); + if (np->dev_name) { + struct net *net = current->nsproxy->net_ns; + ndev = __dev_get_by_name(net, np->dev_name); + } if (!ndev) { - printk(KERN_ERR "%s: %s doesn't exist, aborting.\n", - np->name, np->dev_name); - return -ENODEV; + np_err(np, "%s doesn't exist, aborting\n", np->dev_name); + err = -ENODEV; + goto unlock; + } + dev_hold(ndev); + + if (netdev_master_upper_dev_get(ndev)) { + np_err(np, "%s is a slave device, aborting\n", np->dev_name); + err = -EBUSY; + goto put; } if (!netif_running(ndev)) { unsigned long atmost, atleast; - printk(KERN_INFO "%s: device %s not up yet, forcing it\n", - np->name, np->dev_name); + np_info(np, "device %s not up yet, forcing it\n", np->dev_name); - rtnl_lock(); err = dev_open(ndev); - rtnl_unlock(); if (err) { - printk(KERN_ERR "%s: failed to open %s\n", - np->name, ndev->name); + np_err(np, "failed to open %s\n", ndev->name); goto put; } + rtnl_unlock(); atleast = jiffies + HZ/10; atmost = jiffies + carrier_timeout * HZ; while (!netif_carrier_ok(ndev)) { if (time_after(jiffies, atmost)) { - printk(KERN_NOTICE - "%s: timeout waiting for carrier\n", - np->name); + np_notice(np, "timeout waiting for carrier\n"); break; } msleep(1); @@ -842,46 +704,73 @@ int netpoll_setup(struct netpoll *np) */ if (time_before(jiffies, atleast)) { - printk(KERN_NOTICE "%s: carrier detect appears" - " untrustworthy, waiting 4 seconds\n", - np->name); + np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n"); msleep(4000); } + rtnl_lock(); } - if (!np->local_ip) { - rcu_read_lock(); - in_dev = __in_dev_get_rcu(ndev); + if (!np->local_ip.ip) { + if (!np->ipv6) { + in_dev = __in_dev_get_rtnl(ndev); + + if (!in_dev || !in_dev->ifa_list) { + np_err(np, "no IP address for %s, aborting\n", + np->dev_name); + err = -EDESTADDRREQ; + goto put; + } + + np->local_ip.ip = in_dev->ifa_list->ifa_local; + np_info(np, "local IP %pI4\n", &np->local_ip.ip); + } else { +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_dev *idev; - if (!in_dev || !in_dev->ifa_list) { - rcu_read_unlock(); - printk(KERN_ERR "%s: no IP address for %s, aborting\n", - np->name, np->dev_name); err = -EDESTADDRREQ; + idev = __in6_dev_get(ndev); + if (idev) { + struct inet6_ifaddr *ifp; + + read_lock_bh(&idev->lock); + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) + continue; + np->local_ip.in6 = ifp->addr; + err = 0; + break; + } + read_unlock_bh(&idev->lock); + } + if (err) { + np_err(np, "no IPv6 address for %s, aborting\n", + np->dev_name); + goto put; + } else + np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6); +#else + np_err(np, "IPv6 is not supported %s, aborting\n", + np->dev_name); + err = -EINVAL; goto put; +#endif } - - np->local_ip = in_dev->ifa_list->ifa_local; - rcu_read_unlock(); - printk(KERN_INFO "%s: local IP %pI4\n", np->name, &np->local_ip); } - np->dev = ndev; - /* fill up the skb queue */ refill_skbs(); - rtnl_lock(); - err = __netpoll_setup(np); - rtnl_unlock(); - + err = __netpoll_setup(np, ndev); if (err) goto put; + rtnl_unlock(); return 0; put: dev_put(ndev); +unlock: + rtnl_unlock(); return err; } EXPORT_SYMBOL(netpoll_setup); @@ -893,22 +782,36 @@ static int __init netpoll_init(void) } core_initcall(netpoll_init); +static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) +{ + struct netpoll_info *npinfo = + container_of(rcu_head, struct netpoll_info, rcu); + + skb_queue_purge(&npinfo->txq); + + /* we can't call cancel_delayed_work_sync here, as we are in softirq */ + cancel_delayed_work(&npinfo->tx_work); + + /* clean after last, unfinished work */ + __skb_queue_purge(&npinfo->txq); + /* now cancel it again */ + cancel_delayed_work(&npinfo->tx_work); + kfree(npinfo); +} + void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; - unsigned long flags; - npinfo = np->dev->npinfo; + /* rtnl_dereference would be preferable here but + * rcu_cleanup_netpoll path can put us in here safely without + * holding the rtnl, so plain rcu_dereference it is + */ + npinfo = rtnl_dereference(np->dev->npinfo); if (!npinfo) return; - if (!list_empty(&npinfo->rx_np)) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_del(&np->rx); - if (list_empty(&npinfo->rx_np)) - npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } + synchronize_srcu(&netpoll_srcu); if (atomic_dec_and_test(&npinfo->refcnt)) { const struct net_device_ops *ops; @@ -917,47 +820,37 @@ void __netpoll_cleanup(struct netpoll *np) if (ops->ndo_netpoll_cleanup) ops->ndo_netpoll_cleanup(np->dev); - rcu_assign_pointer(np->dev->npinfo, NULL); - - /* avoid racing with NAPI reading npinfo */ - synchronize_rcu_bh(); - - skb_queue_purge(&npinfo->arp_tx); - skb_queue_purge(&npinfo->txq); - cancel_rearming_delayed_work(&npinfo->tx_work); - - /* clean after last, unfinished work */ - __skb_queue_purge(&npinfo->txq); - kfree(npinfo); + RCU_INIT_POINTER(np->dev->npinfo, NULL); + call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info); } } EXPORT_SYMBOL_GPL(__netpoll_cleanup); -void netpoll_cleanup(struct netpoll *np) +static void netpoll_async_cleanup(struct work_struct *work) { - if (!np->dev) - return; + struct netpoll *np = container_of(work, struct netpoll, cleanup_work); rtnl_lock(); __netpoll_cleanup(np); rtnl_unlock(); - - dev_put(np->dev); - np->dev = NULL; + kfree(np); } -EXPORT_SYMBOL(netpoll_cleanup); -int netpoll_trap(void) +void __netpoll_free_async(struct netpoll *np) { - return atomic_read(&trapped); + schedule_work(&np->cleanup_work); } -EXPORT_SYMBOL(netpoll_trap); +EXPORT_SYMBOL_GPL(__netpoll_free_async); -void netpoll_set_trap(int trap) +void netpoll_cleanup(struct netpoll *np) { - if (trap) - atomic_inc(&trapped); - else - atomic_dec(&trapped); + rtnl_lock(); + if (!np->dev) + goto out; + __netpoll_cleanup(np); + dev_put(np->dev); + np->dev = NULL; +out: + rtnl_unlock(); } -EXPORT_SYMBOL(netpoll_set_trap); +EXPORT_SYMBOL(netpoll_cleanup); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c new file mode 100644 index 00000000000..2f385b9bccc --- /dev/null +++ b/net/core/netprio_cgroup.c @@ -0,0 +1,288 @@ +/* + * net/core/netprio_cgroup.c Priority Control Group + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Neil Horman <nhorman@tuxdriver.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/cgroup.h> +#include <linux/rcupdate.h> +#include <linux/atomic.h> +#include <net/rtnetlink.h> +#include <net/pkt_cls.h> +#include <net/sock.h> +#include <net/netprio_cgroup.h> + +#include <linux/fdtable.h> + +#define PRIOMAP_MIN_SZ 128 + +/* + * Extend @dev->priomap so that it's large enough to accommodate + * @target_idx. @dev->priomap.priomap_len > @target_idx after successful + * return. Must be called under rtnl lock. + */ +static int extend_netdev_table(struct net_device *dev, u32 target_idx) +{ + struct netprio_map *old, *new; + size_t new_sz, new_len; + + /* is the existing priomap large enough? */ + old = rtnl_dereference(dev->priomap); + if (old && old->priomap_len > target_idx) + return 0; + + /* + * Determine the new size. Let's keep it power-of-two. We start + * from PRIOMAP_MIN_SZ and double it until it's large enough to + * accommodate @target_idx. + */ + new_sz = PRIOMAP_MIN_SZ; + while (true) { + new_len = (new_sz - offsetof(struct netprio_map, priomap)) / + sizeof(new->priomap[0]); + if (new_len > target_idx) + break; + new_sz *= 2; + /* overflowed? */ + if (WARN_ON(new_sz < PRIOMAP_MIN_SZ)) + return -ENOSPC; + } + + /* allocate & copy */ + new = kzalloc(new_sz, GFP_KERNEL); + if (!new) + return -ENOMEM; + + if (old) + memcpy(new->priomap, old->priomap, + old->priomap_len * sizeof(old->priomap[0])); + + new->priomap_len = new_len; + + /* install the new priomap */ + rcu_assign_pointer(dev->priomap, new); + if (old) + kfree_rcu(old, rcu); + return 0; +} + +/** + * netprio_prio - return the effective netprio of a cgroup-net_device pair + * @css: css part of the target pair + * @dev: net_device part of the target pair + * + * Should be called under RCU read or rtnl lock. + */ +static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev) +{ + struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); + int id = css->cgroup->id; + + if (map && id < map->priomap_len) + return map->priomap[id]; + return 0; +} + +/** + * netprio_set_prio - set netprio on a cgroup-net_device pair + * @css: css part of the target pair + * @dev: net_device part of the target pair + * @prio: prio to set + * + * Set netprio to @prio on @css-@dev pair. Should be called under rtnl + * lock and may fail under memory pressure for non-zero @prio. + */ +static int netprio_set_prio(struct cgroup_subsys_state *css, + struct net_device *dev, u32 prio) +{ + struct netprio_map *map; + int id = css->cgroup->id; + int ret; + + /* avoid extending priomap for zero writes */ + map = rtnl_dereference(dev->priomap); + if (!prio && (!map || map->priomap_len <= id)) + return 0; + + ret = extend_netdev_table(dev, id); + if (ret) + return ret; + + map = rtnl_dereference(dev->priomap); + map->priomap[id] = prio; + return 0; +} + +static struct cgroup_subsys_state * +cgrp_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_subsys_state *css; + + css = kzalloc(sizeof(*css), GFP_KERNEL); + if (!css) + return ERR_PTR(-ENOMEM); + + return css; +} + +static int cgrp_css_online(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys_state *parent_css = css->parent; + struct net_device *dev; + int ret = 0; + + if (!parent_css) + return 0; + + rtnl_lock(); + /* + * Inherit prios from the parent. As all prios are set during + * onlining, there is no need to clear them on offline. + */ + for_each_netdev(&init_net, dev) { + u32 prio = netprio_prio(parent_css, dev); + + ret = netprio_set_prio(css, dev, prio); + if (ret) + break; + } + rtnl_unlock(); + return ret; +} + +static void cgrp_css_free(struct cgroup_subsys_state *css) +{ + kfree(css); +} + +static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return css->cgroup->id; +} + +static int read_priomap(struct seq_file *sf, void *v) +{ + struct net_device *dev; + + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) + seq_printf(sf, "%s %u\n", dev->name, + netprio_prio(seq_css(sf), dev)); + rcu_read_unlock(); + return 0; +} + +static ssize_t write_priomap(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + char devname[IFNAMSIZ + 1]; + struct net_device *dev; + u32 prio; + int ret; + + if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2) + return -EINVAL; + + dev = dev_get_by_name(&init_net, devname); + if (!dev) + return -ENODEV; + + rtnl_lock(); + + ret = netprio_set_prio(of_css(of), dev, prio); + + rtnl_unlock(); + dev_put(dev); + return ret ?: nbytes; +} + +static int update_netprio(const void *v, struct file *file, unsigned n) +{ + int err; + struct socket *sock = sock_from_file(file, &err); + if (sock) + sock->sk->sk_cgrp_prioidx = (u32)(unsigned long)v; + return 0; +} + +static void net_prio_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct task_struct *p; + void *v = (void *)(unsigned long)css->cgroup->id; + + cgroup_taskset_for_each(p, tset) { + task_lock(p); + iterate_fd(p->files, 0, update_netprio, v); + task_unlock(p); + } +} + +static struct cftype ss_files[] = { + { + .name = "prioidx", + .read_u64 = read_prioidx, + }, + { + .name = "ifpriomap", + .seq_show = read_priomap, + .write = write_priomap, + }, + { } /* terminate */ +}; + +struct cgroup_subsys net_prio_cgrp_subsys = { + .css_alloc = cgrp_css_alloc, + .css_online = cgrp_css_online, + .css_free = cgrp_css_free, + .attach = net_prio_attach, + .base_cftypes = ss_files, +}; + +static int netprio_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netprio_map *old; + + /* + * Note this is called with rtnl_lock held so we have update side + * protection on our rcu assignments + */ + + switch (event) { + case NETDEV_UNREGISTER: + old = rtnl_dereference(dev->priomap); + RCU_INIT_POINTER(dev->priomap, NULL); + if (old) + kfree_rcu(old, rcu); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block netprio_device_notifier = { + .notifier_call = netprio_device_event +}; + +static int __init init_cgroup_netprio(void) +{ + register_netdevice_notifier(&netprio_device_notifier); + return 0; +} + +subsys_initcall(init_cgroup_netprio); +MODULE_LICENSE("GPL v2"); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 2953b2abc97..fc17a9d309a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -156,13 +156,17 @@ #include <linux/wait.h> #include <linux/etherdevice.h> #include <linux/kthread.h> +#include <linux/prefetch.h> #include <net/net_namespace.h> #include <net/checksum.h> #include <net/ipv6.h> +#include <net/udp.h> +#include <net/ip6_checksum.h> #include <net/addrconf.h> #ifdef CONFIG_XFRM #include <net/xfrm.h> #endif +#include <net/netns/generic.h> #include <asm/byteorder.h> #include <linux/rcupdate.h> #include <linux/bitops.h> @@ -196,6 +200,7 @@ #define F_QUEUE_MAP_RND (1<<13) /* queue map Random */ #define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */ #define F_NODE (1<<15) /* Node memory alloc*/ +#define F_UDPCSUM (1<<16) /* Include UDP checksum */ /* Thread control flag bits */ #define T_STOP (1<<0) /* Stop run */ @@ -211,7 +216,6 @@ #define PKTGEN_MAGIC 0xbe9be955 #define PG_PROC_DIR "pktgen" #define PGCTRL "pgctrl" -static struct proc_dir_entry *pg_proc_dir; #define MAX_CFLOWS 65536 @@ -247,10 +251,11 @@ struct pktgen_dev { int removal_mark; /* non-zero => the device is marked for * removal by worker thread */ - int min_pkt_size; /* = ETH_ZLEN; */ - int max_pkt_size; /* = ETH_ZLEN; */ + int min_pkt_size; + int max_pkt_size; int pkt_overhead; /* overhead for MPLS, VLANs, IPSEC etc */ int nfrags; + struct page *page; u64 delay; /* nano-seconds */ __u64 count; /* Default No packets to send */ @@ -318,7 +323,7 @@ struct pktgen_dev { (see RFC 3260, sec. 4) */ /* MPLS */ - unsigned nr_labels; /* Depth of stack, 0 = no MPLS */ + unsigned int nr_labels; /* Depth of stack, 0 = no MPLS */ __be32 labels[MAX_MPLS_LABELS]; /* VLAN/SVLAN (802.1Q/Q-in-Q) */ @@ -371,10 +376,10 @@ struct pktgen_dev { */ char odevname[32]; struct flow_state *flows; - unsigned cflows; /* Concurrent flows (config) */ - unsigned lflow; /* Flow length (config) */ - unsigned nflows; /* accumulated flows (stats) */ - unsigned curfl; /* current sequenced flow (state)*/ + unsigned int cflows; /* Concurrent flows (config) */ + unsigned int lflow; /* Flow length (config) */ + unsigned int nflows; /* accumulated flows (stats) */ + unsigned int curfl; /* current sequenced flow (state)*/ u16 queue_map_min; u16 queue_map_max; @@ -384,6 +389,9 @@ struct pktgen_dev { #ifdef CONFIG_XFRM __u8 ipsmode; /* IPSEC mode (config) */ __u8 ipsproto; /* IPSEC type (config) */ + __u32 spi; + struct dst_entry dst; + struct dst_ops dstops; #endif char result[512]; }; @@ -395,7 +403,15 @@ struct pktgen_hdr { __be32 tv_usec; }; -static bool pktgen_exiting __read_mostly; + +static int pg_net_id __read_mostly; + +struct pktgen_net { + struct net *net; + struct proc_dir_entry *proc_dir; + struct list_head pktgen_threads; + bool pktgen_exiting; +}; struct pktgen_thread { spinlock_t if_lock; /* for list of devices */ @@ -412,25 +428,12 @@ struct pktgen_thread { wait_queue_head_t queue; struct completion start_done; + struct pktgen_net *net; }; #define REMOVE 1 #define FIND 0 -static inline ktime_t ktime_now(void) -{ - struct timespec ts; - ktime_get_ts(&ts); - - return timespec_to_ktime(ts); -} - -/* This works even if 32 bit because of careful byte order choice */ -static inline int ktime_lt(const ktime_t cmp1, const ktime_t cmp2) -{ - return cmp1.tv64 < cmp2.tv64; -} - static const char version[] = "Packet Generator for packet performance testing. " "Version: " VERSION "\n"; @@ -440,16 +443,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, const char *ifname, bool exact); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); -static void pktgen_run_all_threads(void); -static void pktgen_reset_all_threads(void); -static void pktgen_stop_all_threads_ifs(void); +static void pktgen_run_all_threads(struct pktgen_net *pn); +static void pktgen_reset_all_threads(struct pktgen_net *pn); +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn); static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); -static unsigned int scan_ip6(const char *s, char ip[16]); -static unsigned int fmt_ip6(char *s, const char ip[16]); - /* Module parameters, defaults. */ static int pg_count_d __read_mostly = 1000; static int pg_delay_d __read_mostly; @@ -457,7 +457,6 @@ static int pg_clone_skb_d __read_mostly; static int debug __read_mostly; static DEFINE_MUTEX(pktgen_thread_lock); -static LIST_HEAD(pktgen_threads); static struct notifier_block pktgen_notifier_block = { .notifier_call = pktgen_device_event, @@ -477,44 +476,41 @@ static int pgctrl_show(struct seq_file *seq, void *v) static ssize_t pgctrl_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - int err = 0; char data[128]; + struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id); - if (!capable(CAP_NET_ADMIN)) { - err = -EPERM; - goto out; - } + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (count == 0) + return -EINVAL; if (count > sizeof(data)) count = sizeof(data); - if (copy_from_user(data, buf, count)) { - err = -EFAULT; - goto out; - } - data[count - 1] = 0; /* Make string */ + if (copy_from_user(data, buf, count)) + return -EFAULT; + + data[count - 1] = 0; /* Strip trailing '\n' and terminate string */ if (!strcmp(data, "stop")) - pktgen_stop_all_threads_ifs(); + pktgen_stop_all_threads_ifs(pn); else if (!strcmp(data, "start")) - pktgen_run_all_threads(); + pktgen_run_all_threads(pn); else if (!strcmp(data, "reset")) - pktgen_reset_all_threads(); + pktgen_reset_all_threads(pn); else pr_warning("Unknown command: %s\n", data); - err = count; - -out: - return err; + return count; } static int pgctrl_open(struct inode *inode, struct file *file) { - return single_open(file, pgctrl_show, PDE(inode)->data); + return single_open(file, pgctrl_show, PDE_DATA(inode)); } static const struct file_operations pktgen_fops = { @@ -555,21 +551,13 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->skb_priority); if (pkt_dev->flags & F_IPV6) { - char b1[128], b2[128], b3[128]; - fmt_ip6(b1, pkt_dev->in6_saddr.s6_addr); - fmt_ip6(b2, pkt_dev->min_in6_saddr.s6_addr); - fmt_ip6(b3, pkt_dev->max_in6_saddr.s6_addr); - seq_printf(seq, - " saddr: %s min_saddr: %s max_saddr: %s\n", b1, - b2, b3); - - fmt_ip6(b1, pkt_dev->in6_daddr.s6_addr); - fmt_ip6(b2, pkt_dev->min_in6_daddr.s6_addr); - fmt_ip6(b3, pkt_dev->max_in6_daddr.s6_addr); seq_printf(seq, - " daddr: %s min_daddr: %s max_daddr: %s\n", b1, - b2, b3); - + " saddr: %pI6c min_saddr: %pI6c max_saddr: %pI6c\n" + " daddr: %pI6c min_daddr: %pI6c max_daddr: %pI6c\n", + &pkt_dev->in6_saddr, + &pkt_dev->min_in6_saddr, &pkt_dev->max_in6_saddr, + &pkt_dev->in6_daddr, + &pkt_dev->min_in6_daddr, &pkt_dev->max_in6_daddr); } else { seq_printf(seq, " dst_min: %s dst_max: %s\n", @@ -585,7 +573,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) is_zero_ether_addr(pkt_dev->src_mac) ? pkt_dev->odev->dev_addr : pkt_dev->src_mac); - seq_printf(seq, "dst_mac: "); + seq_puts(seq, "dst_mac: "); seq_printf(seq, "%pM\n", pkt_dev->dst_mac); seq_printf(seq, @@ -599,8 +587,8 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->src_mac_count, pkt_dev->dst_mac_count); if (pkt_dev->nr_labels) { - unsigned i; - seq_printf(seq, " mpls: "); + unsigned int i; + seq_puts(seq, " mpls: "); for (i = 0; i < pkt_dev->nr_labels; i++) seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]), i == pkt_dev->nr_labels-1 ? "\n" : ", "); @@ -625,66 +613,72 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->node >= 0) seq_printf(seq, " node: %d\n", pkt_dev->node); - seq_printf(seq, " Flags: "); + seq_puts(seq, " Flags: "); if (pkt_dev->flags & F_IPV6) - seq_printf(seq, "IPV6 "); + seq_puts(seq, "IPV6 "); if (pkt_dev->flags & F_IPSRC_RND) - seq_printf(seq, "IPSRC_RND "); + seq_puts(seq, "IPSRC_RND "); if (pkt_dev->flags & F_IPDST_RND) - seq_printf(seq, "IPDST_RND "); + seq_puts(seq, "IPDST_RND "); if (pkt_dev->flags & F_TXSIZE_RND) - seq_printf(seq, "TXSIZE_RND "); + seq_puts(seq, "TXSIZE_RND "); if (pkt_dev->flags & F_UDPSRC_RND) - seq_printf(seq, "UDPSRC_RND "); + seq_puts(seq, "UDPSRC_RND "); if (pkt_dev->flags & F_UDPDST_RND) - seq_printf(seq, "UDPDST_RND "); + seq_puts(seq, "UDPDST_RND "); + + if (pkt_dev->flags & F_UDPCSUM) + seq_puts(seq, "UDPCSUM "); if (pkt_dev->flags & F_MPLS_RND) - seq_printf(seq, "MPLS_RND "); + seq_puts(seq, "MPLS_RND "); if (pkt_dev->flags & F_QUEUE_MAP_RND) - seq_printf(seq, "QUEUE_MAP_RND "); + seq_puts(seq, "QUEUE_MAP_RND "); if (pkt_dev->flags & F_QUEUE_MAP_CPU) - seq_printf(seq, "QUEUE_MAP_CPU "); + seq_puts(seq, "QUEUE_MAP_CPU "); if (pkt_dev->cflows) { if (pkt_dev->flags & F_FLOW_SEQ) - seq_printf(seq, "FLOW_SEQ "); /*in sequence flows*/ + seq_puts(seq, "FLOW_SEQ "); /*in sequence flows*/ else - seq_printf(seq, "FLOW_RND "); + seq_puts(seq, "FLOW_RND "); } #ifdef CONFIG_XFRM - if (pkt_dev->flags & F_IPSEC_ON) - seq_printf(seq, "IPSEC "); + if (pkt_dev->flags & F_IPSEC_ON) { + seq_puts(seq, "IPSEC "); + if (pkt_dev->spi) + seq_printf(seq, "spi:%u", pkt_dev->spi); + } #endif if (pkt_dev->flags & F_MACSRC_RND) - seq_printf(seq, "MACSRC_RND "); + seq_puts(seq, "MACSRC_RND "); if (pkt_dev->flags & F_MACDST_RND) - seq_printf(seq, "MACDST_RND "); + seq_puts(seq, "MACDST_RND "); if (pkt_dev->flags & F_VID_RND) - seq_printf(seq, "VID_RND "); + seq_puts(seq, "VID_RND "); if (pkt_dev->flags & F_SVID_RND) - seq_printf(seq, "SVID_RND "); + seq_puts(seq, "SVID_RND "); if (pkt_dev->flags & F_NODE) - seq_printf(seq, "NODE_ALLOC "); + seq_puts(seq, "NODE_ALLOC "); seq_puts(seq, "\n"); /* not really stopped, more like last-running-at */ - stopped = pkt_dev->running ? ktime_now() : pkt_dev->stopped_at; + stopped = pkt_dev->running ? ktime_get() : pkt_dev->stopped_at; idle = pkt_dev->idle_acc; do_div(idle, NSEC_PER_USEC); @@ -705,13 +699,12 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->cur_src_mac_offset); if (pkt_dev->flags & F_IPV6) { - char b1[128], b2[128]; - fmt_ip6(b1, pkt_dev->cur_in6_daddr.s6_addr); - fmt_ip6(b2, pkt_dev->cur_in6_saddr.s6_addr); - seq_printf(seq, " cur_saddr: %s cur_daddr: %s\n", b2, b1); + seq_printf(seq, " cur_saddr: %pI6c cur_daddr: %pI6c\n", + &pkt_dev->cur_in6_saddr, + &pkt_dev->cur_in6_daddr); } else - seq_printf(seq, " cur_saddr: 0x%x cur_daddr: 0x%x\n", - pkt_dev->cur_saddr, pkt_dev->cur_daddr); + seq_printf(seq, " cur_saddr: %pI4 cur_daddr: %pI4\n", + &pkt_dev->cur_saddr, &pkt_dev->cur_daddr); seq_printf(seq, " cur_udp_dst: %d cur_udp_src: %d\n", pkt_dev->cur_udp_dst, pkt_dev->cur_udp_src); @@ -723,7 +716,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->result[0]) seq_printf(seq, "Result: %s\n", pkt_dev->result); else - seq_printf(seq, "Result: Idle\n"); + seq_puts(seq, "Result: Idle\n"); return 0; } @@ -775,8 +768,8 @@ done: return i; } -static unsigned long num_arg(const char __user * user_buffer, - unsigned long maxlen, unsigned long *num) +static long num_arg(const char __user *user_buffer, unsigned long maxlen, + unsigned long *num) { int i; *num = 0; @@ -820,7 +813,7 @@ done_str: static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) { - unsigned n = 0; + unsigned int n = 0; char c; ssize_t i = 0; int len; @@ -899,8 +892,8 @@ static ssize_t pktgen_if_write(struct file *file, if (copy_from_user(tb, user_buffer, copy)) return -EFAULT; tb[copy] = 0; - printk(KERN_DEBUG "pktgen: %s,%lu buffer -:%s:-\n", name, - (unsigned long)count, tb); + pr_debug("%s,%lu buffer -:%s:-\n", + name, (unsigned long)count, tb); } if (!strcmp(name, "min_pkt_size")) { @@ -1078,7 +1071,9 @@ static ssize_t pktgen_if_write(struct file *file, len = num_arg(&user_buffer[i], 10, &value); if (len < 0) return len; - + if ((value > 0) && + (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))) + return -ENOTSUPP; i += len; pkt_dev->clone_skb = value; @@ -1134,6 +1129,10 @@ static ssize_t pktgen_if_write(struct file *file, if (node_possible(value)) { pkt_dev->node = value; sprintf(pg_result, "OK: node=%d", pkt_dev->node); + if (pkt_dev->page) { + put_page(pkt_dev->page); + pkt_dev->page = NULL; + } } else sprintf(pg_result, "ERROR: node not possible"); @@ -1237,12 +1236,24 @@ static ssize_t pktgen_if_write(struct file *file, else if (strcmp(f, "!NODE_ALLOC") == 0) pkt_dev->flags &= ~F_NODE; + else if (strcmp(f, "UDPCSUM") == 0) + pkt_dev->flags |= F_UDPCSUM; + + else if (strcmp(f, "!UDPCSUM") == 0) + pkt_dev->flags &= ~F_UDPCSUM; + else { sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", f, "IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, " - "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC, NODE_ALLOC\n"); + "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, " + "MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, " + "QUEUE_MAP_RND, QUEUE_MAP_CPU, UDPCSUM, " +#ifdef CONFIG_XFRM + "IPSEC, " +#endif + "NODE_ALLOC\n"); return count; } sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags); @@ -1263,8 +1274,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_daddr = pkt_dev->daddr_min; } if (debug) - printk(KERN_DEBUG "pktgen: dst_min set to: %s\n", - pkt_dev->dst_min); + pr_debug("dst_min set to: %s\n", pkt_dev->dst_min); i += len; sprintf(pg_result, "OK: dst_min=%s", pkt_dev->dst_min); return count; @@ -1286,8 +1296,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_daddr = pkt_dev->daddr_max; } if (debug) - printk(KERN_DEBUG "pktgen: dst_max set to: %s\n", - pkt_dev->dst_max); + pr_debug("dst_max set to: %s\n", pkt_dev->dst_max); i += len; sprintf(pg_result, "OK: dst_max=%s", pkt_dev->dst_max); return count; @@ -1303,13 +1312,13 @@ static ssize_t pktgen_if_write(struct file *file, return -EFAULT; buf[len] = 0; - scan_ip6(buf, pkt_dev->in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->in6_daddr.s6_addr); + in6_pton(buf, -1, pkt_dev->in6_daddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_daddr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->in6_daddr); + pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr; if (debug) - printk(KERN_DEBUG "pktgen: dst6 set to: %s\n", buf); + pr_debug("dst6 set to: %s\n", buf); i += len; sprintf(pg_result, "OK: dst6=%s", buf); @@ -1326,13 +1335,12 @@ static ssize_t pktgen_if_write(struct file *file, return -EFAULT; buf[len] = 0; - scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); + in6_pton(buf, -1, pkt_dev->min_in6_daddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_daddr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, - &pkt_dev->min_in6_daddr); + pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr; if (debug) - printk(KERN_DEBUG "pktgen: dst6_min set to: %s\n", buf); + pr_debug("dst6_min set to: %s\n", buf); i += len; sprintf(pg_result, "OK: dst6_min=%s", buf); @@ -1349,11 +1357,11 @@ static ssize_t pktgen_if_write(struct file *file, return -EFAULT; buf[len] = 0; - scan_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); + in6_pton(buf, -1, pkt_dev->max_in6_daddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->max_in6_daddr); if (debug) - printk(KERN_DEBUG "pktgen: dst6_max set to: %s\n", buf); + pr_debug("dst6_max set to: %s\n", buf); i += len; sprintf(pg_result, "OK: dst6_max=%s", buf); @@ -1370,13 +1378,13 @@ static ssize_t pktgen_if_write(struct file *file, return -EFAULT; buf[len] = 0; - scan_ip6(buf, pkt_dev->in6_saddr.s6_addr); - fmt_ip6(buf, pkt_dev->in6_saddr.s6_addr); + in6_pton(buf, -1, pkt_dev->in6_saddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_saddr); - ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &pkt_dev->in6_saddr); + pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr; if (debug) - printk(KERN_DEBUG "pktgen: src6 set to: %s\n", buf); + pr_debug("src6 set to: %s\n", buf); i += len; sprintf(pg_result, "OK: src6=%s", buf); @@ -1397,8 +1405,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_saddr = pkt_dev->saddr_min; } if (debug) - printk(KERN_DEBUG "pktgen: src_min set to: %s\n", - pkt_dev->src_min); + pr_debug("src_min set to: %s\n", pkt_dev->src_min); i += len; sprintf(pg_result, "OK: src_min=%s", pkt_dev->src_min); return count; @@ -1418,18 +1425,12 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_saddr = pkt_dev->saddr_max; } if (debug) - printk(KERN_DEBUG "pktgen: src_max set to: %s\n", - pkt_dev->src_max); + pr_debug("src_max set to: %s\n", pkt_dev->src_max); i += len; sprintf(pg_result, "OK: src_max=%s", pkt_dev->src_max); return count; } if (!strcmp(name, "dst_mac")) { - char *v = valstr; - unsigned char old_dmac[ETH_ALEN]; - unsigned char *m = pkt_dev->dst_mac; - memcpy(old_dmac, pkt_dev->dst_mac, ETH_ALEN); - len = strn_len(&user_buffer[i], sizeof(valstr) - 1); if (len < 0) return len; @@ -1437,35 +1438,16 @@ static ssize_t pktgen_if_write(struct file *file, memset(valstr, 0, sizeof(valstr)); if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; - i += len; - - for (*m = 0; *v && m < pkt_dev->dst_mac + 6; v++) { - int value; - - value = hex_to_bin(*v); - if (value >= 0) - *m = *m * 16 + value; - - if (*v == ':') { - m++; - *m = 0; - } - } + if (!mac_pton(valstr, pkt_dev->dst_mac)) + return -EINVAL; /* Set up Dest MAC */ - if (compare_ether_addr(old_dmac, pkt_dev->dst_mac)) - memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); + ether_addr_copy(&pkt_dev->hh[0], pkt_dev->dst_mac); - sprintf(pg_result, "OK: dstmac"); + sprintf(pg_result, "OK: dstmac %pM", pkt_dev->dst_mac); return count; } if (!strcmp(name, "src_mac")) { - char *v = valstr; - unsigned char old_smac[ETH_ALEN]; - unsigned char *m = pkt_dev->src_mac; - - memcpy(old_smac, pkt_dev->src_mac, ETH_ALEN); - len = strn_len(&user_buffer[i], sizeof(valstr) - 1); if (len < 0) return len; @@ -1473,26 +1455,13 @@ static ssize_t pktgen_if_write(struct file *file, memset(valstr, 0, sizeof(valstr)); if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; - i += len; - - for (*m = 0; *v && m < pkt_dev->src_mac + 6; v++) { - int value; - - value = hex_to_bin(*v); - if (value >= 0) - *m = *m * 16 + value; - - if (*v == ':') { - m++; - *m = 0; - } - } + if (!mac_pton(valstr, pkt_dev->src_mac)) + return -EINVAL; /* Set up Src MAC */ - if (compare_ether_addr(old_smac, pkt_dev->src_mac)) - memcpy(&(pkt_dev->hh[6]), pkt_dev->src_mac, ETH_ALEN); + ether_addr_copy(&pkt_dev->hh[6], pkt_dev->src_mac); - sprintf(pg_result, "OK: srcmac"); + sprintf(pg_result, "OK: srcmac %pM", pkt_dev->src_mac); return count; } @@ -1515,7 +1484,18 @@ static ssize_t pktgen_if_write(struct file *file, sprintf(pg_result, "OK: flows=%u", pkt_dev->cflows); return count; } +#ifdef CONFIG_XFRM + if (!strcmp(name, "spi")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + i += len; + pkt_dev->spi = value; + sprintf(pg_result, "OK: spi=%u", pkt_dev->spi); + return count; + } +#endif if (!strcmp(name, "flowlen")) { len = num_arg(&user_buffer[i], 10, &value); if (len < 0) @@ -1550,7 +1530,7 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "mpls")) { - unsigned n, cnt; + unsigned int n, cnt; len = get_labels(&user_buffer[i], pkt_dev); if (len < 0) @@ -1567,7 +1547,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->svlan_id = 0xffff; if (debug) - printk(KERN_DEBUG "pktgen: VLAN/SVLAN auto turned off\n"); + pr_debug("VLAN/SVLAN auto turned off\n"); } return count; } @@ -1582,10 +1562,10 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->vlan_id = value; /* turn on VLAN */ if (debug) - printk(KERN_DEBUG "pktgen: VLAN turned on\n"); + pr_debug("VLAN turned on\n"); if (debug && pkt_dev->nr_labels) - printk(KERN_DEBUG "pktgen: MPLS auto turned off\n"); + pr_debug("MPLS auto turned off\n"); pkt_dev->nr_labels = 0; /* turn off MPLS */ sprintf(pg_result, "OK: vlan_id=%u", pkt_dev->vlan_id); @@ -1594,7 +1574,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->svlan_id = 0xffff; if (debug) - printk(KERN_DEBUG "pktgen: VLAN/SVLAN turned off\n"); + pr_debug("VLAN/SVLAN turned off\n"); } return count; } @@ -1639,10 +1619,10 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->svlan_id = value; /* turn on SVLAN */ if (debug) - printk(KERN_DEBUG "pktgen: SVLAN turned on\n"); + pr_debug("SVLAN turned on\n"); if (debug && pkt_dev->nr_labels) - printk(KERN_DEBUG "pktgen: MPLS auto turned off\n"); + pr_debug("MPLS auto turned off\n"); pkt_dev->nr_labels = 0; /* turn off MPLS */ sprintf(pg_result, "OK: svlan_id=%u", pkt_dev->svlan_id); @@ -1651,7 +1631,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->svlan_id = 0xffff; if (debug) - printk(KERN_DEBUG "pktgen: VLAN/SVLAN turned off\n"); + pr_debug("VLAN/SVLAN turned off\n"); } return count; } @@ -1736,7 +1716,7 @@ static ssize_t pktgen_if_write(struct file *file, static int pktgen_if_open(struct inode *inode, struct file *file) { - return single_open(file, pktgen_if_show, PDE(inode)->data); + return single_open(file, pktgen_if_show, PDE_DATA(inode)); } static const struct file_operations pktgen_if_fops = { @@ -1755,14 +1735,14 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) BUG_ON(!t); - seq_printf(seq, "Running: "); + seq_puts(seq, "Running: "); if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) if (pkt_dev->running) seq_printf(seq, "%s ", pkt_dev->odevname); - seq_printf(seq, "\nStopped: "); + seq_puts(seq, "\nStopped: "); list_for_each_entry(pkt_dev, &t->if_list, list) if (!pkt_dev->running) @@ -1771,7 +1751,7 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); else - seq_printf(seq, "\nResult: NA\n"); + seq_puts(seq, "\nResult: NA\n"); if_unlock(t); @@ -1819,8 +1799,7 @@ static ssize_t pktgen_thread_write(struct file *file, i += len; if (debug) - printk(KERN_DEBUG "pktgen: t=%s, count=%lu\n", - name, (unsigned long)count); + pr_debug("t=%s, count=%lu\n", name, (unsigned long)count); if (!t) { pr_err("ERROR: No thread\n"); @@ -1842,10 +1821,13 @@ static ssize_t pktgen_thread_write(struct file *file, return -EFAULT; i += len; mutex_lock(&pktgen_thread_lock); - pktgen_add_device(t, f); + ret = pktgen_add_device(t, f); mutex_unlock(&pktgen_thread_lock); - ret = count; - sprintf(pg_result, "OK: add_device=%s", f); + if (!ret) { + ret = count; + sprintf(pg_result, "OK: add_device=%s", f); + } else + sprintf(pg_result, "ERROR: can not add device %s", f); goto out; } @@ -1872,7 +1854,7 @@ out: static int pktgen_thread_open(struct inode *inode, struct file *file) { - return single_open(file, pktgen_thread_show, PDE(inode)->data); + return single_open(file, pktgen_thread_show, PDE_DATA(inode)); } static const struct file_operations pktgen_thread_fops = { @@ -1885,13 +1867,14 @@ static const struct file_operations pktgen_thread_fops = { }; /* Think find or remove for NN */ -static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) +static struct pktgen_dev *__pktgen_NN_threads(const struct pktgen_net *pn, + const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; bool exact = (remove == FIND); - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { @@ -1909,7 +1892,7 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) /* * mark a device for removal */ -static void pktgen_mark_device(const char *ifname) +static void pktgen_mark_device(const struct pktgen_net *pn, const char *ifname) { struct pktgen_dev *pkt_dev = NULL; const int max_tries = 10, msec_per_try = 125; @@ -1920,7 +1903,7 @@ static void pktgen_mark_device(const char *ifname) while (1) { - pkt_dev = __pktgen_NN_threads(ifname, REMOVE); + pkt_dev = __pktgen_NN_threads(pn, ifname, REMOVE); if (pkt_dev == NULL) break; /* success */ @@ -1941,21 +1924,21 @@ static void pktgen_mark_device(const char *ifname) mutex_unlock(&pktgen_thread_lock); } -static void pktgen_change_name(struct net_device *dev) +static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *dev) { struct pktgen_thread *t; - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { struct pktgen_dev *pkt_dev; list_for_each_entry(pkt_dev, &t->if_list, list) { if (pkt_dev->odev != dev) continue; - remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); + proc_remove(pkt_dev->entry); pkt_dev->entry = proc_create_data(dev->name, 0600, - pg_proc_dir, + pn->proc_dir, &pktgen_if_fops, pkt_dev); if (!pkt_dev->entry) @@ -1969,9 +1952,10 @@ static void pktgen_change_name(struct net_device *dev) static int pktgen_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id); - if (!net_eq(dev_net(dev), &init_net)) + if (pn->pktgen_exiting) return NOTIFY_DONE; /* It is OK that we do not hold the group lock right now, @@ -1980,18 +1964,19 @@ static int pktgen_device_event(struct notifier_block *unused, switch (event) { case NETDEV_CHANGENAME: - pktgen_change_name(dev); + pktgen_change_name(pn, dev); break; case NETDEV_UNREGISTER: - pktgen_mark_device(dev->name); + pktgen_mark_device(pn, dev->name); break; } return NOTIFY_DONE; } -static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, +static struct net_device *pktgen_dev_get_by_name(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, const char *ifname) { char b[IFNAMSIZ+5]; @@ -2005,13 +1990,14 @@ static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, } b[i] = 0; - return dev_get_by_name(&init_net, b); + return dev_get_by_name(pn->net, b); } /* Associate pktgen_dev with a device. */ -static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) +static int pktgen_setup_dev(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, const char *ifname) { struct net_device *odev; int err; @@ -2022,7 +2008,7 @@ static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) pkt_dev->odev = NULL; } - odev = pktgen_dev_get_by_name(pkt_dev, ifname); + odev = pktgen_dev_get_by_name(pn, pkt_dev, ifname); if (!odev) { pr_err("no such netdevice: \"%s\"\n", ifname); return -ENODEV; @@ -2064,36 +2050,34 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) pr_warning("WARNING: Requested queue_map_min (zero-based) (%d) exceeds valid range [0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, pkt_dev->odevname); - pkt_dev->queue_map_min = ntxq - 1; + pkt_dev->queue_map_min = (ntxq ?: 1) - 1; } if (pkt_dev->queue_map_max >= ntxq) { pr_warning("WARNING: Requested queue_map_max (zero-based) (%d) exceeds valid range [0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, pkt_dev->odevname); - pkt_dev->queue_map_max = ntxq - 1; + pkt_dev->queue_map_max = (ntxq ?: 1) - 1; } /* Default to the interface's mac if not explicitly set. */ if (is_zero_ether_addr(pkt_dev->src_mac)) - memcpy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr, ETH_ALEN); + ether_addr_copy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr); /* Set up Dest MAC */ - memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); - - /* Set up pkt size */ - pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size; + ether_addr_copy(&(pkt_dev->hh[0]), pkt_dev->dst_mac); if (pkt_dev->flags & F_IPV6) { - /* - * Skip this automatic address setting until locks or functions - * gets exported - */ - -#ifdef NOTNOW int i, set = 0, err = 1; struct inet6_dev *idev; + if (pkt_dev->min_pkt_size == 0) { + pkt_dev->min_pkt_size = 14 + sizeof(struct ipv6hdr) + + sizeof(struct udphdr) + + sizeof(struct pktgen_hdr) + + pkt_dev->pkt_overhead; + } + for (i = 0; i < IN6_ADDR_HSIZE; i++) if (pkt_dev->cur_in6_saddr.s6_addr[i]) { set = 1; @@ -2114,13 +2098,10 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp = idev->addr_list; ifp; - ifp = ifp->if_next) { - if (ifp->scope == IFA_LINK && + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if ((ifp->scope & IFA_LINK) && !(ifp->flags & IFA_F_TENTATIVE)) { - ipv6_addr_copy(&pkt_dev-> - cur_in6_saddr, - &ifp->addr); + pkt_dev->cur_in6_saddr = ifp->addr; err = 0; break; } @@ -2131,8 +2112,14 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) if (err) pr_err("ERROR: IPv6 link address not available\n"); } -#endif } else { + if (pkt_dev->min_pkt_size == 0) { + pkt_dev->min_pkt_size = 14 + sizeof(struct iphdr) + + sizeof(struct udphdr) + + sizeof(struct pktgen_hdr) + + pkt_dev->pkt_overhead; + } + pkt_dev->saddr_min = 0; pkt_dev->saddr_max = 0; if (strlen(pkt_dev->src_min) == 0) { @@ -2158,6 +2145,10 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) pkt_dev->daddr_max = in_aton(pkt_dev->dst_max); } /* Initialize current values. */ + pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size; + if (pkt_dev->min_pkt_size > pkt_dev->max_pkt_size) + pkt_dev->max_pkt_size = pkt_dev->min_pkt_size; + pkt_dev->cur_dst_mac_offset = 0; pkt_dev->cur_src_mac_offset = 0; pkt_dev->cur_saddr = pkt_dev->saddr_min; @@ -2183,10 +2174,13 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) return; } - start_time = ktime_now(); - if (remaining < 100000) - ndelay(remaining); /* really small just spin */ - else { + start_time = ktime_get(); + if (remaining < 100000) { + /* for small delays (<100us), just loop until limit is reached */ + do { + end_time = ktime_get(); + } while (ktime_compare(end_time, spin_until) < 0); + } else { /* see do_nanosleep */ hrtimer_init_sleeper(&t, current); do { @@ -2201,8 +2195,8 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) hrtimer_cancel(&t.timer); } while (t.task && pkt_dev->running && !signal_pending(current)); __set_current_state(TASK_RUNNING); + end_time = ktime_get(); } - end_time = ktime_now(); pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time)); pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay); @@ -2235,7 +2229,7 @@ static inline int f_pick(struct pktgen_dev *pkt_dev) pkt_dev->curfl = 0; /*reset */ } } else { - flow = random32() % pkt_dev->cflows; + flow = prandom_u32() % pkt_dev->cflows; pkt_dev->curfl = flow; if (pkt_dev->flows[flow].count > pkt_dev->lflow) { @@ -2256,14 +2250,23 @@ static inline int f_pick(struct pktgen_dev *pkt_dev) static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) { struct xfrm_state *x = pkt_dev->flows[flow].x; + struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id); if (!x) { - /*slow path: we dont already have xfrm_state*/ - x = xfrm_stateonly_find(&init_net, DUMMY_MARK, - (xfrm_address_t *)&pkt_dev->cur_daddr, - (xfrm_address_t *)&pkt_dev->cur_saddr, - AF_INET, - pkt_dev->ipsmode, - pkt_dev->ipsproto, 0); + + if (pkt_dev->spi) { + /* We need as quick as possible to find the right SA + * Searching with minimum criteria to archieve this. + */ + x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); + } else { + /* slow path: we dont already have xfrm_state */ + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, + (xfrm_address_t *)&pkt_dev->cur_daddr, + (xfrm_address_t *)&pkt_dev->cur_saddr, + AF_INET, + pkt_dev->ipsmode, + pkt_dev->ipsproto, 0); + } if (x) { pkt_dev->flows[flow].x = x; set_pkt_overhead(pkt_dev); @@ -2282,7 +2285,7 @@ static void set_cur_queue_map(struct pktgen_dev *pkt_dev) else if (pkt_dev->queue_map_min <= pkt_dev->queue_map_max) { __u16 t; if (pkt_dev->flags & F_QUEUE_MAP_RND) { - t = random32() % + t = prandom_u32() % (pkt_dev->queue_map_max - pkt_dev->queue_map_min + 1) + pkt_dev->queue_map_min; @@ -2314,7 +2317,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 tmp; if (pkt_dev->flags & F_MACSRC_RND) - mc = random32() % pkt_dev->src_mac_count; + mc = prandom_u32() % pkt_dev->src_mac_count; else { mc = pkt_dev->cur_src_mac_offset++; if (pkt_dev->cur_src_mac_offset >= @@ -2340,7 +2343,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 tmp; if (pkt_dev->flags & F_MACDST_RND) - mc = random32() % pkt_dev->dst_mac_count; + mc = prandom_u32() % pkt_dev->dst_mac_count; else { mc = pkt_dev->cur_dst_mac_offset++; @@ -2363,25 +2366,25 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) } if (pkt_dev->flags & F_MPLS_RND) { - unsigned i; + unsigned int i; for (i = 0; i < pkt_dev->nr_labels; i++) if (pkt_dev->labels[i] & MPLS_STACK_BOTTOM) pkt_dev->labels[i] = MPLS_STACK_BOTTOM | - ((__force __be32)random32() & + ((__force __be32)prandom_u32() & htonl(0x000fffff)); } if ((pkt_dev->flags & F_VID_RND) && (pkt_dev->vlan_id != 0xffff)) { - pkt_dev->vlan_id = random32() & (4096-1); + pkt_dev->vlan_id = prandom_u32() & (4096 - 1); } if ((pkt_dev->flags & F_SVID_RND) && (pkt_dev->svlan_id != 0xffff)) { - pkt_dev->svlan_id = random32() & (4096 - 1); + pkt_dev->svlan_id = prandom_u32() & (4096 - 1); } if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { if (pkt_dev->flags & F_UDPSRC_RND) - pkt_dev->cur_udp_src = random32() % + pkt_dev->cur_udp_src = prandom_u32() % (pkt_dev->udp_src_max - pkt_dev->udp_src_min) + pkt_dev->udp_src_min; @@ -2394,7 +2397,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->udp_dst_min < pkt_dev->udp_dst_max) { if (pkt_dev->flags & F_UDPDST_RND) { - pkt_dev->cur_udp_dst = random32() % + pkt_dev->cur_udp_dst = prandom_u32() % (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min) + pkt_dev->udp_dst_min; } else { @@ -2411,7 +2414,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (imn < imx) { __u32 t; if (pkt_dev->flags & F_IPSRC_RND) - t = random32() % (imx - imn) + imn; + t = prandom_u32() % (imx - imn) + imn; else { t = ntohl(pkt_dev->cur_saddr); t++; @@ -2432,17 +2435,15 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __be32 s; if (pkt_dev->flags & F_IPDST_RND) { - t = random32() % (imx - imn) + imn; - s = htonl(t); - - while (ipv4_is_loopback(s) || - ipv4_is_multicast(s) || - ipv4_is_lbcast(s) || - ipv4_is_zeronet(s) || - ipv4_is_local_multicast(s)) { - t = random32() % (imx - imn) + imn; + do { + t = prandom_u32() % + (imx - imn) + imn; s = htonl(t); - } + } while (ipv4_is_loopback(s) || + ipv4_is_multicast(s) || + ipv4_is_lbcast(s) || + ipv4_is_zeronet(s) || + ipv4_is_local_multicast(s)); pkt_dev->cur_daddr = s; } else { t = ntohl(pkt_dev->cur_daddr); @@ -2466,18 +2467,14 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) } } else { /* IPV6 * */ - if (pkt_dev->min_in6_daddr.s6_addr32[0] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[1] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[2] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[3] == 0) ; - else { + if (!ipv6_addr_any(&pkt_dev->min_in6_daddr)) { int i; /* Only random destinations yet */ for (i = 0; i < 4; i++) { pkt_dev->cur_in6_daddr.s6_addr32[i] = - (((__force __be32)random32() | + (((__force __be32)prandom_u32() | pkt_dev->min_in6_daddr.s6_addr32[i]) & pkt_dev->max_in6_daddr.s6_addr32[i]); } @@ -2487,7 +2484,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) { __u32 t; if (pkt_dev->flags & F_TXSIZE_RND) { - t = random32() % + t = prandom_u32() % (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size) + pkt_dev->min_pkt_size; } else { @@ -2505,33 +2502,47 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) #ifdef CONFIG_XFRM +static u32 pktgen_dst_metrics[RTAX_MAX + 1] = { + + [RTAX_HOPLIMIT] = 0x5, /* Set a static hoplimit */ +}; + static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) { struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; int err = 0; - struct iphdr *iph; + struct net *net = dev_net(pkt_dev->odev); if (!x) return 0; /* XXX: we dont support tunnel mode for now until * we resolve the dst issue */ - if (x->props.mode != XFRM_MODE_TRANSPORT) + if ((x->props.mode != XFRM_MODE_TRANSPORT) && (pkt_dev->spi == 0)) return 0; - spin_lock(&x->lock); - iph = ip_hdr(skb); + /* But when user specify an valid SPI, transformation + * supports both transport/tunnel mode + ESP/AH type. + */ + if ((x->props.mode == XFRM_MODE_TUNNEL) && (pkt_dev->spi != 0)) + skb->_skb_refdst = (unsigned long)&pkt_dev->dst | SKB_DST_NOREF; + rcu_read_lock_bh(); err = x->outer_mode->output(x, skb); - if (err) + rcu_read_unlock_bh(); + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); goto error; + } err = x->type->output(x, skb); - if (err) + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR); goto error; - + } + spin_lock_bh(&x->lock); x->curlft.bytes += skb->len; x->curlft.packets++; + spin_unlock_bh(&x->lock); error: - spin_unlock(&x->lock); return err; } @@ -2559,6 +2570,8 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, if (x) { int ret; __u8 *eth; + struct iphdr *iph; + nhead = x->props.header_len - skb_headroom(skb); if (nhead > 0) { ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC); @@ -2580,6 +2593,11 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, eth = (__u8 *) skb_push(skb, ETH_HLEN); memcpy(eth, pkt_dev->hh, 12); *(u16 *) ð[12] = protocol; + + /* Update IPv4 header len as well as checksum value */ + iph = ip_hdr(skb); + iph->tot_len = htons(skb->len - ETH_HLEN); + ip_send_check(iph); } } return 1; @@ -2591,7 +2609,7 @@ err: static void mpls_push(__be32 *mpls, struct pktgen_dev *pkt_dev) { - unsigned i; + unsigned int i; for (i = 0; i < pkt_dev->nr_labels; i++) *mpls++ = pkt_dev->labels[i] & ~MPLS_STACK_BOTTOM; @@ -2605,6 +2623,95 @@ static inline __be16 build_tci(unsigned int id, unsigned int cfi, return htons(id | (cfi << 12) | (prio << 13)); } +static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, + int datalen) +{ + struct timeval timestamp; + struct pktgen_hdr *pgh; + + pgh = (struct pktgen_hdr *)skb_put(skb, sizeof(*pgh)); + datalen -= sizeof(*pgh); + + if (pkt_dev->nfrags <= 0) { + memset(skb_put(skb, datalen), 0, datalen); + } else { + int frags = pkt_dev->nfrags; + int i, len; + int frag_len; + + + if (frags > MAX_SKB_FRAGS) + frags = MAX_SKB_FRAGS; + len = datalen - frags * PAGE_SIZE; + if (len > 0) { + memset(skb_put(skb, len), 0, len); + datalen = frags * PAGE_SIZE; + } + + i = 0; + frag_len = (datalen/frags) < PAGE_SIZE ? + (datalen/frags) : PAGE_SIZE; + while (datalen > 0) { + if (unlikely(!pkt_dev->page)) { + int node = numa_node_id(); + + if (pkt_dev->node >= 0 && (pkt_dev->flags & F_NODE)) + node = pkt_dev->node; + pkt_dev->page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!pkt_dev->page) + break; + } + get_page(pkt_dev->page); + skb_frag_set_page(skb, i, pkt_dev->page); + skb_shinfo(skb)->frags[i].page_offset = 0; + /*last fragment, fill rest of data*/ + if (i == (frags - 1)) + skb_frag_size_set(&skb_shinfo(skb)->frags[i], + (datalen < PAGE_SIZE ? datalen : PAGE_SIZE)); + else + skb_frag_size_set(&skb_shinfo(skb)->frags[i], frag_len); + datalen -= skb_frag_size(&skb_shinfo(skb)->frags[i]); + skb->len += skb_frag_size(&skb_shinfo(skb)->frags[i]); + skb->data_len += skb_frag_size(&skb_shinfo(skb)->frags[i]); + i++; + skb_shinfo(skb)->nr_frags = i; + } + } + + /* Stamp the time, and sequence number, + * convert them to network byte order + */ + pgh->pgh_magic = htonl(PKTGEN_MAGIC); + pgh->seq_num = htonl(pkt_dev->seq_num); + + do_gettimeofday(×tamp); + pgh->tv_sec = htonl(timestamp.tv_sec); + pgh->tv_usec = htonl(timestamp.tv_usec); +} + +static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, + struct pktgen_dev *pkt_dev, + unsigned int extralen) +{ + struct sk_buff *skb = NULL; + unsigned int size = pkt_dev->cur_pkt_size + 64 + extralen + + pkt_dev->pkt_overhead; + + if (pkt_dev->flags & F_NODE) { + int node = pkt_dev->node >= 0 ? pkt_dev->node : numa_node_id(); + + skb = __alloc_skb(NET_SKB_PAD + size, GFP_NOWAIT, 0, node); + if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); + skb->dev = dev; + } + } else { + skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT); + } + + return skb; +} + static struct sk_buff *fill_packet_ipv4(struct net_device *odev, struct pktgen_dev *pkt_dev) { @@ -2613,7 +2720,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, struct udphdr *udph; int datalen, iplen; struct iphdr *iph; - struct pktgen_hdr *pgh = NULL; __be16 protocol = htons(ETH_P_IP); __be32 *mpls; __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ @@ -2636,31 +2742,13 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, datalen = (odev->hard_header_len + 16) & ~0xf; - if (pkt_dev->flags & F_NODE) { - int node; - - if (pkt_dev->node >= 0) - node = pkt_dev->node; - else - node = numa_node_id(); - - skb = __alloc_skb(NET_SKB_PAD + pkt_dev->cur_pkt_size + 64 - + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT, 0, node); - if (likely(skb)) { - skb_reserve(skb, NET_SKB_PAD); - skb->dev = odev; - } - } - else - skb = __netdev_alloc_skb(odev, - pkt_dev->cur_pkt_size + 64 - + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT); - + skb = pktgen_alloc_skb(odev, pkt_dev, datalen); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; } + prefetchw(skb->data); skb_reserve(skb, datalen); /* Reserve for ethernet and IP header */ @@ -2686,28 +2774,28 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, *vlan_encapsulated_proto = htons(ETH_P_IP); } - skb->network_header = skb->tail; - skb->transport_header = skb->network_header + sizeof(struct iphdr); - skb_put(skb, sizeof(struct iphdr) + sizeof(struct udphdr)); + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, skb->len); + iph = (struct iphdr *) skb_put(skb, sizeof(struct iphdr)); + + skb_set_transport_header(skb, skb->len); + udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr)); skb_set_queue_mapping(skb, queue_map); skb->priority = pkt_dev->skb_priority; - iph = ip_hdr(skb); - udph = udp_hdr(skb); - memcpy(eth, pkt_dev->hh, 12); *(__be16 *) & eth[12] = protocol; /* Eth + IPh + UDPh + mpls */ datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8 - pkt_dev->pkt_overhead; - if (datalen < sizeof(struct pktgen_hdr)) + if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) datalen = sizeof(struct pktgen_hdr); udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); udph->len = htons(datalen + 8); /* DATA + udphdr */ - udph->check = 0; /* No checksum */ + udph->check = 0; iph->ihl = 5; iph->version = 4; @@ -2721,83 +2809,29 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, iph->frag_off = 0; iplen = 20 + 8 + datalen; iph->tot_len = htons(iplen); - iph->check = 0; - iph->check = ip_fast_csum((void *)iph, iph->ihl); + ip_send_check(iph); skb->protocol = protocol; - skb->mac_header = (skb->network_header - ETH_HLEN - - pkt_dev->pkt_overhead); skb->dev = odev; skb->pkt_type = PACKET_HOST; - if (pkt_dev->nfrags <= 0) { - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - memset(pgh + 1, 0, datalen - sizeof(struct pktgen_hdr)); + if (!(pkt_dev->flags & F_UDPCSUM)) { + skb->ip_summed = CHECKSUM_NONE; + } else if (odev->features & NETIF_F_V4_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum = 0; + udp4_hwcsum(skb, udph->source, udph->dest); } else { - int frags = pkt_dev->nfrags; - int i, len; - - pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); - - if (frags > MAX_SKB_FRAGS) - frags = MAX_SKB_FRAGS; - if (datalen > frags * PAGE_SIZE) { - len = datalen - frags * PAGE_SIZE; - memset(skb_put(skb, len), 0, len); - datalen = frags * PAGE_SIZE; - } - - i = 0; - while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); - skb_shinfo(skb)->frags[i].page = page; - skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; - i++; - skb_shinfo(skb)->nr_frags = i; - } - - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; + __wsum csum = udp_csum(skb); - skb_shinfo(skb)->frags[i - 1].size -= rem; + /* add protocol-dependent pseudo-header */ + udph->check = csum_tcpudp_magic(udph->source, udph->dest, + datalen + 8, IPPROTO_UDP, csum); - skb_shinfo(skb)->frags[i] = - skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = - skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += - skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; } - /* Stamp the time, and sequence number, - * convert them to network byte order - */ - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } + pktgen_finalize_skb(pkt_dev, skb, datalen); #ifdef CONFIG_XFRM if (!process_ipsec(pkt_dev, skb, protocol)) @@ -2807,179 +2841,14 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, return skb; } -/* - * scan_ip6, fmt_ip taken from dietlibc-0.21 - * Author Felix von Leitner <felix-dietlibc@fefe.de> - * - * Slightly modified for kernel. - * Should be candidate for net/ipv4/utils.c - * --ro - */ - -static unsigned int scan_ip6(const char *s, char ip[16]) -{ - unsigned int i; - unsigned int len = 0; - unsigned long u; - char suffix[16]; - unsigned int prefixlen = 0; - unsigned int suffixlen = 0; - __be32 tmp; - char *pos; - - for (i = 0; i < 16; i++) - ip[i] = 0; - - for (;;) { - if (*s == ':') { - len++; - if (s[1] == ':') { /* Found "::", skip to part 2 */ - s += 2; - len++; - break; - } - s++; - } - - u = simple_strtoul(s, &pos, 16); - i = pos - s; - if (!i) - return 0; - if (prefixlen == 12 && s[i] == '.') { - - /* the last 4 bytes may be written as IPv4 address */ - - tmp = in_aton(s); - memcpy((struct in_addr *)(ip + 12), &tmp, sizeof(tmp)); - return i + len; - } - ip[prefixlen++] = (u >> 8); - ip[prefixlen++] = (u & 255); - s += i; - len += i; - if (prefixlen == 16) - return len; - } - -/* part 2, after "::" */ - for (;;) { - if (*s == ':') { - if (suffixlen == 0) - break; - s++; - len++; - } else if (suffixlen != 0) - break; - - u = simple_strtol(s, &pos, 16); - i = pos - s; - if (!i) { - if (*s) - len--; - break; - } - if (suffixlen + prefixlen <= 12 && s[i] == '.') { - tmp = in_aton(s); - memcpy((struct in_addr *)(suffix + suffixlen), &tmp, - sizeof(tmp)); - suffixlen += 4; - len += strlen(s); - break; - } - suffix[suffixlen++] = (u >> 8); - suffix[suffixlen++] = (u & 255); - s += i; - len += i; - if (prefixlen + suffixlen == 16) - break; - } - for (i = 0; i < suffixlen; i++) - ip[16 - suffixlen + i] = suffix[i]; - return len; -} - -static char tohex(char hexdigit) -{ - return hexdigit > 9 ? hexdigit + 'a' - 10 : hexdigit + '0'; -} - -static int fmt_xlong(char *s, unsigned int i) -{ - char *bak = s; - *s = tohex((i >> 12) & 0xf); - if (s != bak || *s != '0') - ++s; - *s = tohex((i >> 8) & 0xf); - if (s != bak || *s != '0') - ++s; - *s = tohex((i >> 4) & 0xf); - if (s != bak || *s != '0') - ++s; - *s = tohex(i & 0xf); - return s - bak + 1; -} - -static unsigned int fmt_ip6(char *s, const char ip[16]) -{ - unsigned int len; - unsigned int i; - unsigned int temp; - unsigned int compressing; - int j; - - len = 0; - compressing = 0; - for (j = 0; j < 16; j += 2) { - -#ifdef V4MAPPEDPREFIX - if (j == 12 && !memcmp(ip, V4mappedprefix, 12)) { - inet_ntoa_r(*(struct in_addr *)(ip + 12), s); - temp = strlen(s); - return len + temp; - } -#endif - temp = ((unsigned long)(unsigned char)ip[j] << 8) + - (unsigned long)(unsigned char)ip[j + 1]; - if (temp == 0) { - if (!compressing) { - compressing = 1; - if (j == 0) { - *s++ = ':'; - ++len; - } - } - } else { - if (compressing) { - compressing = 0; - *s++ = ':'; - ++len; - } - i = fmt_xlong(s, temp); - len += i; - s += i; - if (j < 14) { - *s++ = ':'; - ++len; - } - } - } - if (compressing) { - *s++ = ':'; - ++len; - } - *s = 0; - return len; -} - static struct sk_buff *fill_packet_ipv6(struct net_device *odev, struct pktgen_dev *pkt_dev) { struct sk_buff *skb = NULL; __u8 *eth; struct udphdr *udph; - int datalen; + int datalen, udplen; struct ipv6hdr *iph; - struct pktgen_hdr *pgh = NULL; __be16 protocol = htons(ETH_P_IPV6); __be32 *mpls; __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ @@ -3000,14 +2869,13 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, mod_cur_headers(pkt_dev); queue_map = pkt_dev->cur_queue_map; - skb = __netdev_alloc_skb(odev, - pkt_dev->cur_pkt_size + 64 - + 16 + pkt_dev->pkt_overhead, GFP_NOWAIT); + skb = pktgen_alloc_skb(odev, pkt_dev, 16); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; } + prefetchw(skb->data); skb_reserve(skb, 16); /* Reserve for ethernet and IP header */ @@ -3033,13 +2901,14 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, *vlan_encapsulated_proto = htons(ETH_P_IPV6); } - skb->network_header = skb->tail; - skb->transport_header = skb->network_header + sizeof(struct ipv6hdr); - skb_put(skb, sizeof(struct ipv6hdr) + sizeof(struct udphdr)); + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, skb->len); + iph = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr)); + + skb_set_transport_header(skb, skb->len); + udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr)); skb_set_queue_mapping(skb, queue_map); skb->priority = pkt_dev->skb_priority; - iph = ipv6_hdr(skb); - udph = udp_hdr(skb); memcpy(eth, pkt_dev->hh, 12); *(__be16 *) ð[12] = protocol; @@ -3049,16 +2918,16 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, sizeof(struct ipv6hdr) - sizeof(struct udphdr) - pkt_dev->pkt_overhead; - if (datalen < sizeof(struct pktgen_hdr)) { + if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) { datalen = sizeof(struct pktgen_hdr); - if (net_ratelimit()) - pr_info("increased datalen to %d\n", datalen); + net_info_ratelimited("increased datalen to %d\n", datalen); } + udplen = datalen + sizeof(struct udphdr); udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); - udph->len = htons(datalen + sizeof(struct udphdr)); - udph->check = 0; /* No checksum */ + udph->len = htons(udplen); + udph->check = 0; *(__be32 *) iph = htonl(0x60000000); /* Version + flow */ @@ -3069,87 +2938,34 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, iph->hop_limit = 32; - iph->payload_len = htons(sizeof(struct udphdr) + datalen); + iph->payload_len = htons(udplen); iph->nexthdr = IPPROTO_UDP; - ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr); - ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr); + iph->daddr = pkt_dev->cur_in6_daddr; + iph->saddr = pkt_dev->cur_in6_saddr; - skb->mac_header = (skb->network_header - ETH_HLEN - - pkt_dev->pkt_overhead); skb->protocol = protocol; skb->dev = odev; skb->pkt_type = PACKET_HOST; - if (pkt_dev->nfrags <= 0) - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - else { - int frags = pkt_dev->nfrags; - int i; - - pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); - - if (frags > MAX_SKB_FRAGS) - frags = MAX_SKB_FRAGS; - if (datalen > frags * PAGE_SIZE) { - skb_put(skb, datalen - frags * PAGE_SIZE); - datalen = frags * PAGE_SIZE; - } - - i = 0; - while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL, 0); - skb_shinfo(skb)->frags[i].page = page; - skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; - i++; - skb_shinfo(skb)->nr_frags = i; - } - - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; + if (!(pkt_dev->flags & F_UDPCSUM)) { + skb->ip_summed = CHECKSUM_NONE; + } else if (odev->features & NETIF_F_V6_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + udph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, 0); + } else { + __wsum csum = udp_csum(skb); - skb_shinfo(skb)->frags[i - 1].size -= rem; + /* add protocol-dependent pseudo-header */ + udph->check = csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, csum); - skb_shinfo(skb)->frags[i] = - skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = - skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += - skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; } - /* Stamp the time, and sequence number, - * convert them to network byte order - * should we update cloned packets too ? - */ - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } - /* pkt_dev->seq_num++; FF: you really mean this? */ + pktgen_finalize_skb(pkt_dev, skb, datalen); return skb; } @@ -3193,8 +3009,7 @@ static void pktgen_run(struct pktgen_thread *t) pktgen_clear_counters(pkt_dev); pkt_dev->running = 1; /* Cranke yeself! */ pkt_dev->skb = NULL; - pkt_dev->started_at = - pkt_dev->next_tx = ktime_now(); + pkt_dev->started_at = pkt_dev->next_tx = ktime_get(); set_pkt_overhead(pkt_dev); @@ -3208,7 +3023,7 @@ static void pktgen_run(struct pktgen_thread *t) t->control &= ~(T_STOP); } -static void pktgen_stop_all_threads_ifs(void) +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -3216,7 +3031,7 @@ static void pktgen_stop_all_threads_ifs(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= T_STOP; mutex_unlock(&pktgen_thread_lock); @@ -3252,28 +3067,28 @@ signal: return 0; } -static int pktgen_wait_all_threads_run(void) +static int pktgen_wait_all_threads_run(struct pktgen_net *pn) { struct pktgen_thread *t; int sig = 1; mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { sig = pktgen_wait_thread_run(t); if (sig == 0) break; } if (sig == 0) - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_STOP); mutex_unlock(&pktgen_thread_lock); return sig; } -static void pktgen_run_all_threads(void) +static void pktgen_run_all_threads(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -3281,7 +3096,7 @@ static void pktgen_run_all_threads(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_RUN); mutex_unlock(&pktgen_thread_lock); @@ -3289,10 +3104,10 @@ static void pktgen_run_all_threads(void) /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); - pktgen_wait_all_threads_run(); + pktgen_wait_all_threads_run(pn); } -static void pktgen_reset_all_threads(void) +static void pktgen_reset_all_threads(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -3300,7 +3115,7 @@ static void pktgen_reset_all_threads(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_REMDEVALL); mutex_unlock(&pktgen_thread_lock); @@ -3308,7 +3123,7 @@ static void pktgen_reset_all_threads(void) /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); - pktgen_wait_all_threads_run(); + pktgen_wait_all_threads_run(pn); } static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) @@ -3319,7 +3134,7 @@ static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) pkt_dev->started_at); ktime_t idle = ns_to_ktime(pkt_dev->idle_acc); - p += sprintf(p, "OK: %llu(c%llu+d%llu) nsec, %llu (%dbyte,%dfrags)\n", + p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n", (unsigned long long)ktime_to_us(elapsed), (unsigned long long)ktime_to_us(ktime_sub(elapsed, idle)), (unsigned long long)ktime_to_us(idle), @@ -3353,7 +3168,7 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev) kfree_skb(pkt_dev->skb); pkt_dev->skb = NULL; - pkt_dev->stopped_at = ktime_now(); + pkt_dev->stopped_at = ktime_get(); pkt_dev->running = 0; show_results(pkt_dev, nr_frags); @@ -3372,7 +3187,7 @@ static struct pktgen_dev *next_to_run(struct pktgen_thread *t) continue; if (best == NULL) best = pkt_dev; - else if (ktime_lt(pkt_dev->next_tx, best->next_tx)) + else if (ktime_compare(pkt_dev->next_tx, best->next_tx) < 0) best = pkt_dev; } if_unlock(t); @@ -3450,21 +3265,19 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) static void pktgen_rem_thread(struct pktgen_thread *t) { /* Remove from the thread list */ - - remove_proc_entry(t->tsk->comm, pg_proc_dir); - + remove_proc_entry(t->tsk->comm, t->net->proc_dir); } static void pktgen_resched(struct pktgen_dev *pkt_dev) { - ktime_t idle_start = ktime_now(); + ktime_t idle_start = ktime_get(); schedule(); - pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start)); + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start)); } static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) { - ktime_t idle_start = ktime_now(); + ktime_t idle_start = ktime_get(); while (atomic_read(&(pkt_dev->skb->users)) != 1) { if (signal_pending(current)) @@ -3475,7 +3288,7 @@ static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) else cpu_relax(); } - pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start)); + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start)); } static void pktgen_xmit(struct pktgen_dev *pkt_dev) @@ -3497,7 +3310,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) * "never transmit" */ if (unlikely(pkt_dev->delay == ULLONG_MAX)) { - pkt_dev->next_tx = ktime_add_ns(ktime_now(), ULONG_MAX); + pkt_dev->next_tx = ktime_add_ns(ktime_get(), ULONG_MAX); return; } @@ -3525,9 +3338,11 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) queue_map = skb_get_queue_mapping(pkt_dev->skb); txq = netdev_get_tx_queue(odev, queue_map); - __netif_tx_lock_bh(txq); + local_bh_disable(); - if (unlikely(netif_tx_queue_frozen_or_stopped(txq))) { + HARD_TX_LOCK(odev, txq, smp_processor_id()); + + if (unlikely(netif_xmit_frozen_or_drv_stopped(txq))) { ret = NETDEV_TX_BUSY; pkt_dev->last_ok = 0; goto unlock; @@ -3550,9 +3365,8 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->errors++; break; default: /* Drivers are not supposed to return other values! */ - if (net_ratelimit()) - pr_info("pktgen: %s xmit error: %d\n", - pkt_dev->odevname, ret); + net_info_ratelimited("%s xmit error: %d\n", + pkt_dev->odevname, ret); pkt_dev->errors++; /* fallthru */ case NETDEV_TX_LOCKED: @@ -3562,7 +3376,9 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->last_ok = 0; } unlock: - __netif_tx_unlock_bh(txq); + HARD_TX_UNLOCK(odev, txq); + + local_bh_enable(); /* If pkt_dev->count is zero, then run forever */ if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) { @@ -3599,7 +3415,7 @@ static int pktgen_thread_worker(void *arg) pkt_dev = next_to_run(t); if (unlikely(!pkt_dev && t->control == 0)) { - if (pktgen_exiting) + if (t->net->pktgen_exiting) break; wait_event_interruptible_timeout(t->queue, t->control != 0, @@ -3721,7 +3537,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) /* We don't allow a device to be on several threads */ - pkt_dev = __pktgen_NN_threads(ifname, FIND); + pkt_dev = __pktgen_NN_threads(t->net, ifname, FIND); if (pkt_dev) { pr_err("ERROR: interface already used\n"); return -EBUSY; @@ -3732,19 +3548,15 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) return -ENOMEM; strcpy(pkt_dev->odevname, ifname); - pkt_dev->flows = vmalloc_node(MAX_CFLOWS * sizeof(struct flow_state), + pkt_dev->flows = vzalloc_node(MAX_CFLOWS * sizeof(struct flow_state), node); if (pkt_dev->flows == NULL) { kfree(pkt_dev); return -ENOMEM; } - memset(pkt_dev->flows, 0, MAX_CFLOWS * sizeof(struct flow_state)); pkt_dev->removal_mark = 0; - pkt_dev->min_pkt_size = ETH_ZLEN; - pkt_dev->max_pkt_size = ETH_ZLEN; pkt_dev->nfrags = 0; - pkt_dev->clone_skb = pg_clone_skb_d; pkt_dev->delay = pg_delay_d; pkt_dev->count = pg_count_d; pkt_dev->sofar = 0; @@ -3752,7 +3564,6 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->udp_src_max = 9; pkt_dev->udp_dst_min = 9; pkt_dev->udp_dst_max = 9; - pkt_dev->vlan_p = 0; pkt_dev->vlan_cfi = 0; pkt_dev->vlan_id = 0xffff; @@ -3761,11 +3572,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->svlan_id = 0xffff; pkt_dev->node = -1; - err = pktgen_setup_dev(pkt_dev, ifname); + err = pktgen_setup_dev(t->net, pkt_dev, ifname); if (err) goto out1; + if (pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING) + pkt_dev->clone_skb = pg_clone_skb_d; - pkt_dev->entry = proc_create_data(ifname, 0600, pg_proc_dir, + pkt_dev->entry = proc_create_data(ifname, 0600, t->net->proc_dir, &pktgen_if_fops, pkt_dev); if (!pkt_dev->entry) { pr_err("cannot create %s/%s procfs entry\n", @@ -3776,6 +3589,17 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) #ifdef CONFIG_XFRM pkt_dev->ipsmode = XFRM_MODE_TRANSPORT; pkt_dev->ipsproto = IPPROTO_ESP; + + /* xfrm tunnel mode needs additional dst to extract outter + * ip header protocol/ttl/id field, here creat a phony one. + * instead of looking for a valid rt, which definitely hurting + * performance under such circumstance. + */ + pkt_dev->dstops.family = AF_INET; + pkt_dev->dst.dev = pkt_dev->odev; + dst_init_metrics(&pkt_dev->dst, pktgen_dst_metrics, false); + pkt_dev->dst.child = &pkt_dev->dst; + pkt_dev->dst.ops = &pkt_dev->dstops; #endif return add_dev_to_thread(t, pkt_dev); @@ -3790,7 +3614,7 @@ out1: return err; } -static int __init pktgen_create_thread(int cpu) +static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) { struct pktgen_thread *t; struct proc_dir_entry *pe; @@ -3808,10 +3632,13 @@ static int __init pktgen_create_thread(int cpu) INIT_LIST_HEAD(&t->if_list); - list_add_tail(&t->th_list, &pktgen_threads); + list_add_tail(&t->th_list, &pn->pktgen_threads); init_completion(&t->start_done); - p = kthread_create(pktgen_thread_worker, t, "kpktgend_%d", cpu); + p = kthread_create_on_node(pktgen_thread_worker, + t, + cpu_to_node(cpu), + "kpktgend_%d", cpu); if (IS_ERR(p)) { pr_err("kernel_thread() failed for cpu %d\n", t->cpu); list_del(&t->th_list); @@ -3821,7 +3648,7 @@ static int __init pktgen_create_thread(int cpu) kthread_bind(p, cpu); t->tsk = p; - pe = proc_create_data(t->tsk->comm, 0600, pg_proc_dir, + pe = proc_create_data(t->tsk->comm, 0600, pn->proc_dir, &pktgen_thread_fops, t); if (!pe) { pr_err("cannot create %s/%s procfs entry\n", @@ -3832,6 +3659,7 @@ static int __init pktgen_create_thread(int cpu) return -EINVAL; } + t->net = pn; wake_up_process(p); wait_for_completion(&t->start_done); @@ -3857,7 +3685,6 @@ static void _rem_dev_from_if_list(struct pktgen_thread *t, static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) { - pr_debug("remove_device pkt_dev=%p\n", pkt_dev); if (pkt_dev->running) { @@ -3877,77 +3704,114 @@ static int pktgen_remove_device(struct pktgen_thread *t, _rem_dev_from_if_list(t, pkt_dev); if (pkt_dev->entry) - remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); + proc_remove(pkt_dev->entry); #ifdef CONFIG_XFRM free_SAs(pkt_dev); #endif vfree(pkt_dev->flows); + if (pkt_dev->page) + put_page(pkt_dev->page); kfree(pkt_dev); return 0; } -static int __init pg_init(void) +static int __net_init pg_net_init(struct net *net) { - int cpu; + struct pktgen_net *pn = net_generic(net, pg_net_id); struct proc_dir_entry *pe; - - pr_info("%s", version); - - pg_proc_dir = proc_mkdir(PG_PROC_DIR, init_net.proc_net); - if (!pg_proc_dir) + int cpu, ret = 0; + + pn->net = net; + INIT_LIST_HEAD(&pn->pktgen_threads); + pn->pktgen_exiting = false; + pn->proc_dir = proc_mkdir(PG_PROC_DIR, pn->net->proc_net); + if (!pn->proc_dir) { + pr_warn("cannot create /proc/net/%s\n", PG_PROC_DIR); return -ENODEV; - - pe = proc_create(PGCTRL, 0600, pg_proc_dir, &pktgen_fops); + } + pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_fops); if (pe == NULL) { - pr_err("ERROR: cannot create %s procfs entry\n", PGCTRL); - proc_net_remove(&init_net, PG_PROC_DIR); - return -EINVAL; + pr_err("cannot create %s procfs entry\n", PGCTRL); + ret = -EINVAL; + goto remove; } - /* Register us to receive netdevice events */ - register_netdevice_notifier(&pktgen_notifier_block); - for_each_online_cpu(cpu) { int err; - err = pktgen_create_thread(cpu); + err = pktgen_create_thread(cpu, pn); if (err) - pr_warning("WARNING: Cannot create thread for cpu %d (%d)\n", + pr_warn("Cannot create thread for cpu %d (%d)\n", cpu, err); } - if (list_empty(&pktgen_threads)) { - pr_err("ERROR: Initialization failed for all threads\n"); - unregister_netdevice_notifier(&pktgen_notifier_block); - remove_proc_entry(PGCTRL, pg_proc_dir); - proc_net_remove(&init_net, PG_PROC_DIR); - return -ENODEV; + if (list_empty(&pn->pktgen_threads)) { + pr_err("Initialization failed for all threads\n"); + ret = -ENODEV; + goto remove_entry; } return 0; + +remove_entry: + remove_proc_entry(PGCTRL, pn->proc_dir); +remove: + remove_proc_entry(PG_PROC_DIR, pn->net->proc_net); + return ret; } -static void __exit pg_cleanup(void) +static void __net_exit pg_net_exit(struct net *net) { + struct pktgen_net *pn = net_generic(net, pg_net_id); struct pktgen_thread *t; struct list_head *q, *n; + LIST_HEAD(list); /* Stop all interfaces & threads */ - pktgen_exiting = true; + pn->pktgen_exiting = true; - list_for_each_safe(q, n, &pktgen_threads) { + mutex_lock(&pktgen_thread_lock); + list_splice_init(&pn->pktgen_threads, &list); + mutex_unlock(&pktgen_thread_lock); + + list_for_each_safe(q, n, &list) { t = list_entry(q, struct pktgen_thread, th_list); + list_del(&t->th_list); kthread_stop(t->tsk); kfree(t); } - /* Un-register us from receiving netdevice events */ - unregister_netdevice_notifier(&pktgen_notifier_block); + remove_proc_entry(PGCTRL, pn->proc_dir); + remove_proc_entry(PG_PROC_DIR, pn->net->proc_net); +} + +static struct pernet_operations pg_net_ops = { + .init = pg_net_init, + .exit = pg_net_exit, + .id = &pg_net_id, + .size = sizeof(struct pktgen_net), +}; + +static int __init pg_init(void) +{ + int ret = 0; + + pr_info("%s", version); + ret = register_pernet_subsys(&pg_net_ops); + if (ret) + return ret; + ret = register_netdevice_notifier(&pktgen_notifier_block); + if (ret) + unregister_pernet_subsys(&pg_net_ops); - /* Clean up proc file system */ - remove_proc_entry(PGCTRL, pg_proc_dir); - proc_net_remove(&init_net, PG_PROC_DIR); + return ret; +} + +static void __exit pg_cleanup(void) +{ + unregister_netdevice_notifier(&pktgen_notifier_block); + unregister_pernet_subsys(&pg_net_ops); } module_init(pg_init); diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c new file mode 100644 index 00000000000..d3027a73fd4 --- /dev/null +++ b/net/core/ptp_classifier.c @@ -0,0 +1,141 @@ +/* PTP classifier + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +/* The below program is the bpf_asm (tools/net/) representation of + * the opcode array in the ptp_filter structure. + * + * For convenience, this can easily be altered and reviewed with + * bpf_asm and bpf_dbg, e.g. `./bpf_asm -c prog` where prog is a + * simple file containing the below program: + * + * ldh [12] ; load ethertype + * + * ; PTP over UDP over IPv4 over Ethernet + * test_ipv4: + * jneq #0x800, test_ipv6 ; ETH_P_IP ? + * ldb [23] ; load proto + * jneq #17, drop_ipv4 ; IPPROTO_UDP ? + * ldh [20] ; load frag offset field + * jset #0x1fff, drop_ipv4 ; don't allow fragments + * ldxb 4*([14]&0xf) ; load IP header len + * ldh [x + 16] ; load UDP dst port + * jneq #319, drop_ipv4 ; is port PTP_EV_PORT ? + * ldh [x + 22] ; load payload + * and #0xf ; mask PTP_CLASS_VMASK + * or #0x10 ; PTP_CLASS_IPV4 + * ret a ; return PTP class + * drop_ipv4: ret #0x0 ; PTP_CLASS_NONE + * + * ; PTP over UDP over IPv6 over Ethernet + * test_ipv6: + * jneq #0x86dd, test_8021q ; ETH_P_IPV6 ? + * ldb [20] ; load proto + * jneq #17, drop_ipv6 ; IPPROTO_UDP ? + * ldh [56] ; load UDP dst port + * jneq #319, drop_ipv6 ; is port PTP_EV_PORT ? + * ldh [62] ; load payload + * and #0xf ; mask PTP_CLASS_VMASK + * or #0x20 ; PTP_CLASS_IPV6 + * ret a ; return PTP class + * drop_ipv6: ret #0x0 ; PTP_CLASS_NONE + * + * ; PTP over 802.1Q over Ethernet + * test_8021q: + * jneq #0x8100, test_ieee1588 ; ETH_P_8021Q ? + * ldh [16] ; load inner type + * jneq #0x88f7, drop_ieee1588 ; ETH_P_1588 ? + * ldb [18] ; load payload + * and #0x8 ; as we don't have ports here, test + * jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these + * ldh [18] ; reload payload + * and #0xf ; mask PTP_CLASS_VMASK + * or #0x40 ; PTP_CLASS_V2_VLAN + * ret a ; return PTP class + * + * ; PTP over Ethernet + * test_ieee1588: + * jneq #0x88f7, drop_ieee1588 ; ETH_P_1588 ? + * ldb [14] ; load payload + * and #0x8 ; as we don't have ports here, test + * jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these + * ldh [14] ; reload payload + * and #0xf ; mask PTP_CLASS_VMASK + * or #0x30 ; PTP_CLASS_L2 + * ret a ; return PTP class + * drop_ieee1588: ret #0x0 ; PTP_CLASS_NONE + */ + +#include <linux/skbuff.h> +#include <linux/filter.h> +#include <linux/ptp_classify.h> + +static struct sk_filter *ptp_insns __read_mostly; + +unsigned int ptp_classify_raw(const struct sk_buff *skb) +{ + return SK_RUN_FILTER(ptp_insns, skb); +} +EXPORT_SYMBOL_GPL(ptp_classify_raw); + +void __init ptp_classifier_init(void) +{ + static struct sock_filter ptp_filter[] __initdata = { + { 0x28, 0, 0, 0x0000000c }, + { 0x15, 0, 12, 0x00000800 }, + { 0x30, 0, 0, 0x00000017 }, + { 0x15, 0, 9, 0x00000011 }, + { 0x28, 0, 0, 0x00000014 }, + { 0x45, 7, 0, 0x00001fff }, + { 0xb1, 0, 0, 0x0000000e }, + { 0x48, 0, 0, 0x00000010 }, + { 0x15, 0, 4, 0x0000013f }, + { 0x48, 0, 0, 0x00000016 }, + { 0x54, 0, 0, 0x0000000f }, + { 0x44, 0, 0, 0x00000010 }, + { 0x16, 0, 0, 0x00000000 }, + { 0x06, 0, 0, 0x00000000 }, + { 0x15, 0, 9, 0x000086dd }, + { 0x30, 0, 0, 0x00000014 }, + { 0x15, 0, 6, 0x00000011 }, + { 0x28, 0, 0, 0x00000038 }, + { 0x15, 0, 4, 0x0000013f }, + { 0x28, 0, 0, 0x0000003e }, + { 0x54, 0, 0, 0x0000000f }, + { 0x44, 0, 0, 0x00000020 }, + { 0x16, 0, 0, 0x00000000 }, + { 0x06, 0, 0, 0x00000000 }, + { 0x15, 0, 9, 0x00008100 }, + { 0x28, 0, 0, 0x00000010 }, + { 0x15, 0, 15, 0x000088f7 }, + { 0x30, 0, 0, 0x00000012 }, + { 0x54, 0, 0, 0x00000008 }, + { 0x15, 0, 12, 0x00000000 }, + { 0x28, 0, 0, 0x00000012 }, + { 0x54, 0, 0, 0x0000000f }, + { 0x44, 0, 0, 0x00000040 }, + { 0x16, 0, 0, 0x00000000 }, + { 0x15, 0, 7, 0x000088f7 }, + { 0x30, 0, 0, 0x0000000e }, + { 0x54, 0, 0, 0x00000008 }, + { 0x15, 0, 4, 0x00000000 }, + { 0x28, 0, 0, 0x0000000e }, + { 0x54, 0, 0, 0x0000000f }, + { 0x44, 0, 0, 0x00000030 }, + { 0x16, 0, 0, 0x00000000 }, + { 0x06, 0, 0, 0x00000000 }, + }; + struct sock_fprog_kern ptp_prog = { + .len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter, + }; + + BUG_ON(sk_unattached_filter_create(&ptp_insns, &ptp_prog)); +} diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 41d99435f62..467f326126e 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -15,6 +15,7 @@ #include <linux/random.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/tcp.h> #include <linux/vmalloc.h> #include <net/request_sock.h> @@ -26,10 +27,11 @@ * but then some measure against one socket starving all other sockets * would be needed. * - * It was 128 by default. Experiments with real servers show, that + * The minimum value of it is 128. Experiments with real servers show that * it is absolutely not enough even at 100conn/sec. 256 cures most - * of problems. This value is adjusted to 128 for very small machines - * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb). + * of problems. + * This value is adjusted to 128 for low memory machines, + * and it will increase in proportion to the memory of machine. * Note : Dont forget somaxconn that may limit backlog too. */ int sysctl_max_syn_backlog = 256; @@ -46,9 +48,7 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, nr_table_entries = roundup_pow_of_two(nr_table_entries + 1); lopt_size += nr_table_entries * sizeof(struct request_sock *); if (lopt_size > PAGE_SIZE) - lopt = __vmalloc(lopt_size, - GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, - PAGE_KERNEL); + lopt = vzalloc(lopt_size); else lopt = kzalloc(lopt_size, GFP_KERNEL); if (lopt == NULL) @@ -131,3 +131,94 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) kfree(lopt); } +/* + * This function is called to set a Fast Open socket's "fastopen_rsk" field + * to NULL when a TFO socket no longer needs to access the request_sock. + * This happens only after 3WHS has been either completed or aborted (e.g., + * RST is received). + * + * Before TFO, a child socket is created only after 3WHS is completed, + * hence it never needs to access the request_sock. things get a lot more + * complex with TFO. A child socket, accepted or not, has to access its + * request_sock for 3WHS processing, e.g., to retransmit SYN-ACK pkts, + * until 3WHS is either completed or aborted. Afterwards the req will stay + * until either the child socket is accepted, or in the rare case when the + * listener is closed before the child is accepted. + * + * In short, a request socket is only freed after BOTH 3WHS has completed + * (or aborted) and the child socket has been accepted (or listener closed). + * When a child socket is accepted, its corresponding req->sk is set to + * NULL since it's no longer needed. More importantly, "req->sk == NULL" + * will be used by the code below to determine if a child socket has been + * accepted or not, and the check is protected by the fastopenq->lock + * described below. + * + * Note that fastopen_rsk is only accessed from the child socket's context + * with its socket lock held. But a request_sock (req) can be accessed by + * both its child socket through fastopen_rsk, and a listener socket through + * icsk_accept_queue.rskq_accept_head. To protect the access a simple spin + * lock per listener "icsk->icsk_accept_queue.fastopenq->lock" is created. + * only in the rare case when both the listener and the child locks are held, + * e.g., in inet_csk_listen_stop() do we not need to acquire the lock. + * The lock also protects other fields such as fastopenq->qlen, which is + * decremented by this function when fastopen_rsk is no longer needed. + * + * Note that another solution was to simply use the existing socket lock + * from the listener. But first socket lock is difficult to use. It is not + * a simple spin lock - one must consider sock_owned_by_user() and arrange + * to use sk_add_backlog() stuff. But what really makes it infeasible is the + * locking hierarchy violation. E.g., inet_csk_listen_stop() may try to + * acquire a child's lock while holding listener's socket lock. A corner + * case might also exist in tcp_v4_hnd_req() that will trigger this locking + * order. + * + * When a TFO req is created, it needs to sock_hold its listener to prevent + * the latter data structure from going away. + * + * This function also sets "treq->listener" to NULL and unreference listener + * socket. treq->listener is used by the listener so it is protected by the + * fastopenq->lock in this function. + */ +void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, + bool reset) +{ + struct sock *lsk = tcp_rsk(req)->listener; + struct fastopen_queue *fastopenq = + inet_csk(lsk)->icsk_accept_queue.fastopenq; + + tcp_sk(sk)->fastopen_rsk = NULL; + spin_lock_bh(&fastopenq->lock); + fastopenq->qlen--; + tcp_rsk(req)->listener = NULL; + if (req->sk) /* the child socket hasn't been accepted yet */ + goto out; + + if (!reset || lsk->sk_state != TCP_LISTEN) { + /* If the listener has been closed don't bother with the + * special RST handling below. + */ + spin_unlock_bh(&fastopenq->lock); + sock_put(lsk); + reqsk_free(req); + return; + } + /* Wait for 60secs before removing a req that has triggered RST. + * This is a simple defense against TFO spoofing attack - by + * counting the req against fastopen.max_qlen, and disabling + * TFO when the qlen exceeds max_qlen. + * + * For more details see CoNext'11 "TCP Fast Open" paper. + */ + req->expires = jiffies + 60*HZ; + if (fastopenq->rskq_rst_head == NULL) + fastopenq->rskq_rst_head = req; + else + fastopenq->rskq_rst_tail->dl_next = req; + + req->dl_next = NULL; + fastopenq->rskq_rst_tail = req; + fastopenq->qlen++; +out: + spin_unlock_bh(&fastopenq->lock); + sock_put(lsk); +} diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 750db57f3bb..1063996f831 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -35,10 +35,11 @@ #include <linux/security.h> #include <linux/mutex.h> #include <linux/if_addr.h> +#include <linux/if_bridge.h> #include <linux/pci.h> +#include <linux/etherdevice.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/inet.h> #include <linux/netdevice.h> @@ -56,6 +57,7 @@ struct rtnl_link { rtnl_doit_func doit; rtnl_dumpit_func dumpit; + rtnl_calcit_func calcit; }; static DEFINE_MUTEX(rtnl_mutex); @@ -126,7 +128,7 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex) if (tab == NULL || tab[msgindex].doit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; - return tab ? tab[msgindex].doit : NULL; + return tab[msgindex].doit; } static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) @@ -141,7 +143,22 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) if (tab == NULL || tab[msgindex].dumpit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; - return tab ? tab[msgindex].dumpit : NULL; + return tab[msgindex].dumpit; +} + +static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex) +{ + struct rtnl_link *tab; + + if (protocol <= RTNL_FAMILY_MAX) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + + if (tab == NULL || tab[msgindex].calcit == NULL) + tab = rtnl_msg_handlers[PF_UNSPEC]; + + return tab[msgindex].calcit; } /** @@ -150,6 +167,7 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message + * @calcit: Function pointer to calc size of dump message * * Registers the specified function pointers (at least one of them has * to be non-NULL) to be called whenever a request message for the @@ -162,7 +180,8 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) * Returns 0 on success or a negative error code. */ int __rtnl_register(int protocol, int msgtype, - rtnl_doit_func doit, rtnl_dumpit_func dumpit) + rtnl_doit_func doit, rtnl_dumpit_func dumpit, + rtnl_calcit_func calcit) { struct rtnl_link *tab; int msgindex; @@ -185,6 +204,9 @@ int __rtnl_register(int protocol, int msgtype, if (dumpit) tab[msgindex].dumpit = dumpit; + if (calcit) + tab[msgindex].calcit = calcit; + return 0; } EXPORT_SYMBOL_GPL(__rtnl_register); @@ -196,12 +218,13 @@ EXPORT_SYMBOL_GPL(__rtnl_register); * as failure of this function is very unlikely, it can only happen due * to lack of memory when allocating the chain to store all message * handlers for a protocol. Meant for use in init functions where lack - * of memory implies no sense in continueing. + * of memory implies no sense in continuing. */ void rtnl_register(int protocol, int msgtype, - rtnl_doit_func doit, rtnl_dumpit_func dumpit) + rtnl_doit_func doit, rtnl_dumpit_func dumpit, + rtnl_calcit_func calcit) { - if (__rtnl_register(protocol, msgtype, doit, dumpit) < 0) + if (__rtnl_register(protocol, msgtype, doit, dumpit, calcit) < 0) panic("Unable to register rtnetlink message handler, " "protocol = %d, message type = %d\n", protocol, msgtype); @@ -250,6 +273,17 @@ EXPORT_SYMBOL_GPL(rtnl_unregister_all); static LIST_HEAD(link_ops); +static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind) +{ + const struct rtnl_link_ops *ops; + + list_for_each_entry(ops, &link_ops, list) { + if (!strcmp(ops->kind, kind)) + return ops; + } + return NULL; +} + /** * __rtnl_link_register - Register rtnl_link_ops with rtnetlink. * @ops: struct rtnl_link_ops * to register @@ -262,6 +296,9 @@ static LIST_HEAD(link_ops); */ int __rtnl_link_register(struct rtnl_link_ops *ops) { + if (rtnl_link_ops_get(ops->kind)) + return -EEXIST; + if (!ops->dellink) ops->dellink = unregister_netdevice_queue; @@ -316,27 +353,63 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops) } EXPORT_SYMBOL_GPL(__rtnl_link_unregister); +/* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace. + */ +static void rtnl_lock_unregistering_all(void) +{ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + for_each_net(net) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + /** * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister */ void rtnl_link_unregister(struct rtnl_link_ops *ops) { - rtnl_lock(); + /* Close the race with cleanup_net() */ + mutex_lock(&net_mutex); + rtnl_lock_unregistering_all(); __rtnl_link_unregister(ops); rtnl_unlock(); + mutex_unlock(&net_mutex); } EXPORT_SYMBOL_GPL(rtnl_link_unregister); -static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind) +static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev) { + struct net_device *master_dev; const struct rtnl_link_ops *ops; - list_for_each_entry(ops, &link_ops, list) { - if (!strcmp(ops->kind, kind)) - return ops; - } - return NULL; + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (!master_dev) + return 0; + ops = master_dev->rtnl_link_ops; + if (!ops || !ops->get_slave_size) + return 0; + /* IFLA_INFO_SLAVE_DATA + nested data */ + return nla_total_size(sizeof(struct nlattr)) + + ops->get_slave_size(master_dev, dev); } static size_t rtnl_link_get_size(const struct net_device *dev) @@ -359,6 +432,8 @@ static size_t rtnl_link_get_size(const struct net_device *dev) /* IFLA_INFO_XSTATS */ size += nla_total_size(ops->get_xstats_size(dev)); + size += rtnl_link_get_slave_info_data_size(dev); + return size; } @@ -377,34 +452,16 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) } /** - * __rtnl_af_register - Register rtnl_af_ops with rtnetlink. - * @ops: struct rtnl_af_ops * to register - * - * The caller must hold the rtnl_mutex. - * - * Returns 0 on success or a negative error code. - */ -int __rtnl_af_register(struct rtnl_af_ops *ops) -{ - list_add_tail(&ops->list, &rtnl_af_ops); - return 0; -} -EXPORT_SYMBOL_GPL(__rtnl_af_register); - -/** * rtnl_af_register - Register rtnl_af_ops with rtnetlink. * @ops: struct rtnl_af_ops * to register * * Returns 0 on success or a negative error code. */ -int rtnl_af_register(struct rtnl_af_ops *ops) +void rtnl_af_register(struct rtnl_af_ops *ops) { - int err; - rtnl_lock(); - err = __rtnl_af_register(ops); + list_add_tail(&ops->list, &rtnl_af_ops); rtnl_unlock(); - return err; } EXPORT_SYMBOL_GPL(rtnl_af_register); @@ -451,84 +508,107 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev) return size; } -static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) +static bool rtnl_have_link_slave_info(const struct net_device *dev) { - const struct rtnl_link_ops *ops = dev->rtnl_link_ops; - struct nlattr *linkinfo, *data; - int err = -EMSGSIZE; + struct net_device *master_dev; - linkinfo = nla_nest_start(skb, IFLA_LINKINFO); - if (linkinfo == NULL) - goto out; + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (master_dev && master_dev->rtnl_link_ops) + return true; + return false; +} + +static int rtnl_link_slave_info_fill(struct sk_buff *skb, + const struct net_device *dev) +{ + struct net_device *master_dev; + const struct rtnl_link_ops *ops; + struct nlattr *slave_data; + int err; + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (!master_dev) + return 0; + ops = master_dev->rtnl_link_ops; + if (!ops) + return 0; + if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0) + return -EMSGSIZE; + if (ops->fill_slave_info) { + slave_data = nla_nest_start(skb, IFLA_INFO_SLAVE_DATA); + if (!slave_data) + return -EMSGSIZE; + err = ops->fill_slave_info(skb, master_dev, dev); + if (err < 0) + goto err_cancel_slave_data; + nla_nest_end(skb, slave_data); + } + return 0; + +err_cancel_slave_data: + nla_nest_cancel(skb, slave_data); + return err; +} + +static int rtnl_link_info_fill(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct rtnl_link_ops *ops = dev->rtnl_link_ops; + struct nlattr *data; + int err; + + if (!ops) + return 0; if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0) - goto err_cancel_link; + return -EMSGSIZE; if (ops->fill_xstats) { err = ops->fill_xstats(skb, dev); if (err < 0) - goto err_cancel_link; + return err; } if (ops->fill_info) { data = nla_nest_start(skb, IFLA_INFO_DATA); if (data == NULL) - goto err_cancel_link; + return -EMSGSIZE; err = ops->fill_info(skb, dev); if (err < 0) goto err_cancel_data; nla_nest_end(skb, data); } - - nla_nest_end(skb, linkinfo); return 0; err_cancel_data: nla_nest_cancel(skb, data); -err_cancel_link: - nla_nest_cancel(skb, linkinfo); -out: return err; } -static const int rtm_min[RTM_NR_FAMILIES] = +static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) { - [RTM_FAM(RTM_NEWLINK)] = NLMSG_LENGTH(sizeof(struct ifinfomsg)), - [RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)), - [RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), - [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)), - [RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)), - [RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)), - [RTM_FAM(RTM_NEWTFILTER)] = NLMSG_LENGTH(sizeof(struct tcmsg)), - [RTM_FAM(RTM_NEWACTION)] = NLMSG_LENGTH(sizeof(struct tcamsg)), - [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), - [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), -}; + struct nlattr *linkinfo; + int err = -EMSGSIZE; -static const int rta_max[RTM_NR_FAMILIES] = -{ - [RTM_FAM(RTM_NEWLINK)] = IFLA_MAX, - [RTM_FAM(RTM_NEWADDR)] = IFA_MAX, - [RTM_FAM(RTM_NEWROUTE)] = RTA_MAX, - [RTM_FAM(RTM_NEWRULE)] = FRA_MAX, - [RTM_FAM(RTM_NEWQDISC)] = TCA_MAX, - [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, - [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX, - [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, -}; + linkinfo = nla_nest_start(skb, IFLA_LINKINFO); + if (linkinfo == NULL) + goto out; -void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data) -{ - struct rtattr *rta; - int size = RTA_LENGTH(attrlen); + err = rtnl_link_info_fill(skb, dev); + if (err < 0) + goto err_cancel_link; + + err = rtnl_link_slave_info_fill(skb, dev); + if (err < 0) + goto err_cancel_link; + + nla_nest_end(skb, linkinfo); + return 0; - rta = (struct rtattr *)skb_put(skb, RTA_ALIGN(size)); - rta->rta_type = attrtype; - rta->rta_len = size; - memcpy(RTA_DATA(rta), data, attrlen); - memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size); +err_cancel_link: + nla_nest_cancel(skb, linkinfo); +out: + return err; } -EXPORT_SYMBOL(__rta_fill); -int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo) +int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo) { struct sock *rtnl = net->rtnl; int err = 0; @@ -583,7 +663,8 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) for (i = 0; i < RTAX_MAX; i++) { if (metrics[i]) { valid++; - NLA_PUT_U32(skb, i+1, metrics[i]); + if (nla_put_u32(skb, i+1, metrics[i])) + goto nla_put_failure; } } @@ -601,21 +682,23 @@ nla_put_failure: EXPORT_SYMBOL(rtnetlink_put_metrics); int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, - u32 ts, u32 tsage, long expires, u32 error) + long expires, u32 error) { struct rta_cacheinfo ci = { - .rta_lastuse = jiffies_to_clock_t(jiffies - dst->lastuse), + .rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse), .rta_used = dst->__use, .rta_clntref = atomic_read(&(dst->__refcnt)), .rta_error = error, .rta_id = id, - .rta_ts = ts, - .rta_tsage = tsage, }; - if (expires) - ci.rta_expires = jiffies_to_clock_t(expires); + if (expires) { + unsigned long clock; + clock = jiffies_to_clock_t(abs(expires)); + clock = min_t(unsigned long, clock, INT_MAX); + ci.rta_expires = (expires > 0) ? clock : -clock; + } return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci); } EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo); @@ -647,6 +730,12 @@ static void set_operstate(struct net_device *dev, unsigned char transition) } } +static unsigned int rtnl_dev_get_flags(const struct net_device *dev) +{ + return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) | + (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); +} + static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, const struct ifinfomsg *ifm) { @@ -655,7 +744,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, /* bugwards compatibility: ifi_change == 0 is treated as ~0 */ if (ifm->ifi_change) flags = (flags & ifm->ifi_change) | - (dev->flags & ~ifm->ifi_change); + (rtnl_dev_get_flags(dev) & ~ifm->ifi_change); return flags; } @@ -698,23 +787,26 @@ static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b) } /* All VF info */ -static inline int rtnl_vfinfo_size(const struct net_device *dev) +static inline int rtnl_vfinfo_size(const struct net_device *dev, + u32 ext_filter_mask) { - if (dev->dev.parent && dev_is_pci(dev->dev.parent)) { - + if (dev->dev.parent && dev_is_pci(dev->dev.parent) && + (ext_filter_mask & RTEXT_FILTER_VF)) { int num_vfs = dev_num_vf(dev->dev.parent); size_t size = nla_total_size(sizeof(struct nlattr)); size += nla_total_size(num_vfs * sizeof(struct nlattr)); size += num_vfs * (nla_total_size(sizeof(struct ifla_vf_mac)) + nla_total_size(sizeof(struct ifla_vf_vlan)) + - nla_total_size(sizeof(struct ifla_vf_tx_rate))); + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_rate))); return size; } else return 0; } -static size_t rtnl_port_size(const struct net_device *dev) +static size_t rtnl_port_size(const struct net_device *dev, + u32 ext_filter_mask) { size_t port_size = nla_total_size(4) /* PORT_VF */ + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ @@ -730,7 +822,8 @@ static size_t rtnl_port_size(const struct net_device *dev) size_t port_self_size = nla_total_size(sizeof(struct nlattr)) + port_size; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; if (dev_num_vf(dev->dev.parent)) return port_self_size + vf_ports_size + @@ -739,7 +832,8 @@ static size_t rtnl_port_size(const struct net_device *dev) return port_self_size; } -static noinline size_t if_nlmsg_size(const struct net_device *dev) +static noinline size_t if_nlmsg_size(const struct net_device *dev, + u32 ext_filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ @@ -755,13 +849,20 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(4) /* IFLA_MASTER */ + + nla_total_size(1) /* IFLA_CARRIER */ + + nla_total_size(4) /* IFLA_PROMISCUITY */ + + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ - + nla_total_size(4) /* IFLA_NUM_VF */ - + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */ - + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ + + nla_total_size(ext_filter_mask + & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ + + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ - + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */ + + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */ } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -779,7 +880,8 @@ static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) vf_port = nla_nest_start(skb, IFLA_VF_PORT); if (!vf_port) goto nla_put_failure; - NLA_PUT_U32(skb, IFLA_PORT_VF, vf); + if (nla_put_u32(skb, IFLA_PORT_VF, vf)) + goto nla_put_failure; err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb); if (err == -EMSGSIZE) goto nla_put_failure; @@ -819,11 +921,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) return 0; } -static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) +static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev, + u32 ext_filter_mask) { int err; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; err = rtnl_port_self_fill(skb, dev); @@ -839,9 +943,27 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) return 0; } +static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev) +{ + int err; + struct netdev_phys_port_id ppid; + + err = dev_get_phys_port_id(dev, &ppid); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + if (nla_put(skb, IFLA_PHYS_PORT_ID, ppid.id_len, ppid.id)) + return -EMSGSIZE; + + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, - unsigned int flags) + unsigned int flags, u32 ext_filter_mask) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -849,7 +971,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, const struct rtnl_link_stats64 *stats; struct nlattr *attr, *af_spec; struct rtnl_af_ops *af_ops; + struct net_device *upper_dev = netdev_master_upper_dev_get(dev); + ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -862,24 +986,30 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, ifm->ifi_flags = dev_get_flags(dev); ifm->ifi_change = change; - NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); - NLA_PUT_U32(skb, IFLA_TXQLEN, dev->tx_queue_len); - NLA_PUT_U8(skb, IFLA_OPERSTATE, - netif_running(dev) ? dev->operstate : IF_OPER_DOWN); - NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode); - NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); - - if (dev->ifindex != dev->iflink) - NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); - - if (dev->master) - NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex); - - if (dev->qdisc) - NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc->ops->id); - - if (dev->ifalias) - NLA_PUT_STRING(skb, IFLA_IFALIAS, dev->ifalias); + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) || + nla_put_u8(skb, IFLA_OPERSTATE, + netif_running(dev) ? dev->operstate : IF_OPER_DOWN) || + nla_put_u8(skb, IFLA_LINKMODE, dev->link_mode) || + nla_put_u32(skb, IFLA_MTU, dev->mtu) || + nla_put_u32(skb, IFLA_GROUP, dev->group) || + nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) || + nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || +#ifdef CONFIG_RPS + nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || +#endif + (dev->ifindex != dev->iflink && + nla_put_u32(skb, IFLA_LINK, dev->iflink)) || + (upper_dev && + nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) || + nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || + (dev->qdisc && + nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || + (dev->ifalias && + nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) || + nla_put_u32(skb, IFLA_CARRIER_CHANGES, + atomic_read(&dev->carrier_changes))) + goto nla_put_failure; if (1) { struct rtnl_link_ifmap map = { @@ -890,14 +1020,19 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, .dma = dev->dma, .port = dev->if_port, }; - NLA_PUT(skb, IFLA_MAP, sizeof(map), &map); + if (nla_put(skb, IFLA_MAP, sizeof(map), &map)) + goto nla_put_failure; } if (dev->addr_len) { - NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); - NLA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast); + if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) || + nla_put(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast)) + goto nla_put_failure; } + if (rtnl_phys_port_id_fill(skb, dev)) + goto nla_put_failure; + attr = nla_reserve(skb, IFLA_STATS, sizeof(struct rtnl_link_stats)); if (attr == NULL) @@ -912,10 +1047,12 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; copy_rtnl_link_stats64(nla_data(attr), stats); - if (dev->dev.parent) - NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)); + if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) && + nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent))) + goto nla_put_failure; - if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent + && (ext_filter_mask & RTEXT_FILTER_VF)) { int i; struct nlattr *vfinfo, *vf; @@ -928,31 +1065,65 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct ifla_vf_info ivi; struct ifla_vf_mac vf_mac; struct ifla_vf_vlan vf_vlan; + struct ifla_vf_rate vf_rate; struct ifla_vf_tx_rate vf_tx_rate; + struct ifla_vf_spoofchk vf_spoofchk; + struct ifla_vf_link_state vf_linkstate; + + /* + * Not all SR-IOV capable drivers support the + * spoofcheck query. Preset to -1 so the user + * space tool can detect that the driver didn't + * report anything. + */ + ivi.spoofchk = -1; + memset(ivi.mac, 0, sizeof(ivi.mac)); + /* The default value for VF link state is "auto" + * IFLA_VF_LINK_STATE_AUTO which equals zero + */ + ivi.linkstate = 0; if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi)) break; - vf_mac.vf = vf_vlan.vf = vf_tx_rate.vf = ivi.vf; + vf_mac.vf = + vf_vlan.vf = + vf_rate.vf = + vf_tx_rate.vf = + vf_spoofchk.vf = + vf_linkstate.vf = ivi.vf; + memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; vf_vlan.qos = ivi.qos; - vf_tx_rate.rate = ivi.tx_rate; + vf_tx_rate.rate = ivi.max_tx_rate; + vf_rate.min_tx_rate = ivi.min_tx_rate; + vf_rate.max_tx_rate = ivi.max_tx_rate; + vf_spoofchk.setting = ivi.spoofchk; + vf_linkstate.link_state = ivi.linkstate; vf = nla_nest_start(skb, IFLA_VF_INFO); if (!vf) { nla_nest_cancel(skb, vfinfo); goto nla_put_failure; } - NLA_PUT(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac); - NLA_PUT(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan); - NLA_PUT(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), &vf_tx_rate); + if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || + nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || + nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), + &vf_rate) || + nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), + &vf_tx_rate) || + nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), + &vf_spoofchk) || + nla_put(skb, IFLA_VF_LINK_STATE, sizeof(vf_linkstate), + &vf_linkstate)) + goto nla_put_failure; nla_nest_end(skb, vf); } nla_nest_end(skb, vfinfo); } - if (rtnl_port_fill(skb, dev)) + if (rtnl_port_fill(skb, dev, ext_filter_mask)) goto nla_put_failure; - if (dev->rtnl_link_ops) { + if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) { if (rtnl_link_fill(skb, dev) < 0) goto nla_put_failure; } @@ -994,64 +1165,40 @@ nla_put_failure: return -EMSGSIZE; } -static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct net *net = sock_net(skb->sk); - int h, s_h; - int idx = 0, s_idx; - struct net_device *dev; - struct hlist_head *head; - struct hlist_node *node; - - s_h = cb->args[0]; - s_idx = cb->args[1]; - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - hlist_for_each_entry(dev, node, head, index_hlist) { - if (idx < s_idx) - goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI) <= 0) - goto out; -cont: - idx++; - } - } -out: - cb->args[1] = idx; - cb->args[0] = h; - - return skb->len; -} - -const struct nla_policy ifla_policy[IFLA_MAX+1] = { +static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 }, [IFLA_ADDRESS] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [IFLA_BROADCAST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) }, [IFLA_MTU] = { .type = NLA_U32 }, [IFLA_LINK] = { .type = NLA_U32 }, + [IFLA_MASTER] = { .type = NLA_U32 }, + [IFLA_CARRIER] = { .type = NLA_U8 }, [IFLA_TXQLEN] = { .type = NLA_U32 }, [IFLA_WEIGHT] = { .type = NLA_U32 }, [IFLA_OPERSTATE] = { .type = NLA_U8 }, [IFLA_LINKMODE] = { .type = NLA_U8 }, [IFLA_LINKINFO] = { .type = NLA_NESTED }, [IFLA_NET_NS_PID] = { .type = NLA_U32 }, + [IFLA_NET_NS_FD] = { .type = NLA_U32 }, [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 }, [IFLA_VFINFO_LIST] = {. type = NLA_NESTED }, [IFLA_VF_PORTS] = { .type = NLA_NESTED }, [IFLA_PORT_SELF] = { .type = NLA_NESTED }, [IFLA_AF_SPEC] = { .type = NLA_NESTED }, + [IFLA_EXT_MASK] = { .type = NLA_U32 }, + [IFLA_PROMISCUITY] = { .type = NLA_U32 }, + [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 }, + [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 }, + [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN }, + [IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */ }; -EXPORT_SYMBOL(ifla_policy); static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_KIND] = { .type = NLA_STRING }, [IFLA_INFO_DATA] = { .type = NLA_NESTED }, + [IFLA_INFO_SLAVE_KIND] = { .type = NLA_STRING }, + [IFLA_INFO_SLAVE_DATA] = { .type = NLA_NESTED }, }; static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { @@ -1065,6 +1212,12 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { .len = sizeof(struct ifla_vf_vlan) }, [IFLA_VF_TX_RATE] = { .type = NLA_BINARY, .len = sizeof(struct ifla_vf_tx_rate) }, + [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_spoofchk) }, + [IFLA_VF_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_rate) }, + [IFLA_VF_LINK_STATE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_link_state) }, }; static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@ -1081,6 +1234,78 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { [IFLA_PORT_RESPONSE] = { .type = NLA_U16, }, }; +static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + int h, s_h; + int idx = 0, s_idx; + struct net_device *dev; + struct hlist_head *head; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; + int err; + int hdrlen; + + s_h = cb->args[0]; + s_idx = cb->args[1]; + + rcu_read_lock(); + cb->seq = net->dev_base_seq; + + /* A hack to preserve kernel<->userspace interface. + * The correct header is ifinfomsg. It is consistent with rtnl_getlink. + * However, before Linux v3.9 the code here assumed rtgenmsg and that's + * what iproute2 < v3.9.0 used. + * We can detect the old iproute2. Even including the IFLA_EXT_MASK + * attribute, its netlink message is shorter than struct ifinfomsg. + */ + hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); + + if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + } + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI, + ext_filter_mask); + /* If we ran out of room on the first message, + * we're in trouble + */ + WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); + + if (err <= 0) + goto out; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); +cont: + idx++; + } + } +out: + rcu_read_unlock(); + cb->args[1] = idx; + cb->args[0] = h; + + return skb->len; +} + +int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len) +{ + return nla_parse(tb, IFLA_MAX, head, len, ifla_policy); +} +EXPORT_SYMBOL(rtnl_nla_parse_ifla); + struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) { struct net *net; @@ -1089,6 +1314,8 @@ struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) */ if (tb[IFLA_NET_NS_PID]) net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID])); + else if (tb[IFLA_NET_NS_FD]) + net = get_net_ns_by_fd(nla_get_u32(tb[IFLA_NET_NS_FD])); else net = get_net(src_net); return net; @@ -1121,8 +1348,7 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return -EOPNOTSUPP; if (af_ops->validate_link_af) { - err = af_ops->validate_link_af(dev, - tb[IFLA_AF_SPEC]); + err = af_ops->validate_link_af(dev, af); if (err < 0) return err; } @@ -1161,11 +1387,47 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) } case IFLA_VF_TX_RATE: { struct ifla_vf_tx_rate *ivt; + struct ifla_vf_info ivf; + ivt = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_get_vf_config) + err = ops->ndo_get_vf_config(dev, ivt->vf, + &ivf); + if (err) + break; + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivf.min_tx_rate, + ivt->rate); + break; + } + case IFLA_VF_RATE: { + struct ifla_vf_rate *ivt; ivt = nla_data(vf); err = -EOPNOTSUPP; - if (ops->ndo_set_vf_tx_rate) - err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, - ivt->rate); + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivt->min_tx_rate, + ivt->max_tx_rate); + break; + } + case IFLA_VF_SPOOFCHK: { + struct ifla_vf_spoofchk *ivs; + ivs = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_spoofchk) + err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, + ivs->setting); + break; + } + case IFLA_VF_LINK_STATE: { + struct ifla_vf_link_state *ivl; + ivl = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_link_state) + err = ops->ndo_set_vf_link_state(dev, ivl->vf, + ivl->link_state); break; } default: @@ -1178,19 +1440,58 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) return err; } -static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, +static int do_set_master(struct net_device *dev, int ifindex) +{ + struct net_device *upper_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops; + int err; + + if (upper_dev) { + if (upper_dev->ifindex == ifindex) + return 0; + ops = upper_dev->netdev_ops; + if (ops->ndo_del_slave) { + err = ops->ndo_del_slave(upper_dev, dev); + if (err) + return err; + } else { + return -EOPNOTSUPP; + } + } + + if (ifindex) { + upper_dev = __dev_get_by_index(dev_net(dev), ifindex); + if (!upper_dev) + return -EINVAL; + ops = upper_dev->netdev_ops; + if (ops->ndo_add_slave) { + err = ops->ndo_add_slave(upper_dev, dev); + if (err) + return err; + } else { + return -EOPNOTSUPP; + } + } + return 0; +} + +static int do_setlink(const struct sk_buff *skb, + struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; - int send_addr_notify = 0; int err; - if (tb[IFLA_NET_NS_PID]) { + if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) { struct net *net = rtnl_link_get_net(dev_net(dev), tb); if (IS_ERR(net)) { err = PTR_ERR(net); goto errout; } + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + err = -EPERM; + goto errout; + } err = dev_change_net_namespace(dev, net, ifname); put_net(net); if (err) @@ -1231,16 +1532,6 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, struct sockaddr *sa; int len; - if (!ops->ndo_set_mac_address) { - err = -EOPNOTSUPP; - goto errout; - } - - if (!netif_device_present(dev)) { - err = -ENODEV; - goto errout; - } - len = sizeof(sa_family_t) + dev->addr_len; sa = kmalloc(len, GFP_KERNEL); if (!sa) { @@ -1250,11 +1541,10 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, sa->sa_family = dev->type; memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]), dev->addr_len); - err = ops->ndo_set_mac_address(dev, sa); + err = dev_set_mac_address(dev, sa); kfree(sa); if (err) goto errout; - send_addr_notify = 1; modified = 1; } @@ -1265,6 +1555,11 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, modified = 1; } + if (tb[IFLA_GROUP]) { + dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); + modified = 1; + } + /* * Interface selected by interface index but interface * name provided implies that a name change has been @@ -1287,7 +1582,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, if (tb[IFLA_BROADCAST]) { nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len); - send_addr_notify = 1; + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); } if (ifm->ifi_flags || ifm->ifi_change) { @@ -1296,6 +1591,20 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, goto errout; } + if (tb[IFLA_MASTER]) { + err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER])); + if (err) + goto errout; + modified = 1; + } + + if (tb[IFLA_CARRIER]) { + err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER])); + if (err) + goto errout; + modified = 1; + } + if (tb[IFLA_TXQLEN]) dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); @@ -1390,18 +1699,14 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, err = 0; errout: - if (err < 0 && modified && net_ratelimit()) - printk(KERN_WARNING "A link change request failed with " - "some changes comitted already. Interface %s may " - "have been left with an inconsistent configuration, " - "please check.\n", dev->name); + if (err < 0 && modified) + net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n", + dev->name); - if (send_addr_notify) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } -static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; @@ -1437,12 +1742,12 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (err < 0) goto errout; - err = do_setlink(dev, ifm, tb, ifname, 0); + err = do_setlink(skb, dev, ifm, tb, ifname, 0); errout: return err; } -static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; @@ -1451,6 +1756,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; int err; + LIST_HEAD(list_kill); err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) @@ -1474,7 +1780,8 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (!ops) return -EOPNOTSUPP; - ops->dellink(dev, NULL); + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); return 0; } @@ -1491,48 +1798,47 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) } dev->rtnl_link_state = RTNL_LINK_INITIALIZED; - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); - __dev_notify_flags(dev, old_flags); + __dev_notify_flags(dev, old_flags, ~0U); return 0; } EXPORT_SYMBOL(rtnl_configure_link); -struct net_device *rtnl_create_link(struct net *src_net, struct net *net, +struct net_device *rtnl_create_link(struct net *net, char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]) { int err; struct net_device *dev; - unsigned int num_queues = 1; - unsigned int real_num_queues = 1; + unsigned int num_tx_queues = 1; + unsigned int num_rx_queues = 1; + + if (tb[IFLA_NUM_TX_QUEUES]) + num_tx_queues = nla_get_u32(tb[IFLA_NUM_TX_QUEUES]); + else if (ops->get_num_tx_queues) + num_tx_queues = ops->get_num_tx_queues(); + + if (tb[IFLA_NUM_RX_QUEUES]) + num_rx_queues = nla_get_u32(tb[IFLA_NUM_RX_QUEUES]); + else if (ops->get_num_rx_queues) + num_rx_queues = ops->get_num_rx_queues(); - if (ops->get_tx_queues) { - err = ops->get_tx_queues(src_net, tb, &num_queues, - &real_num_queues); - if (err) - goto err; - } err = -ENOMEM; - dev = alloc_netdev_mq(ops->priv_size, ifname, ops->setup, num_queues); + dev = alloc_netdev_mqs(ops->priv_size, ifname, ops->setup, + num_tx_queues, num_rx_queues); if (!dev) goto err; dev_net_set(dev, net); dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; - dev->real_num_tx_queues = real_num_queues; - - if (strchr(dev->name, '%')) { - err = dev_alloc_name(dev, dev->name); - if (err < 0) - goto err_free; - } if (tb[IFLA_MTU]) dev->mtu = nla_get_u32(tb[IFLA_MTU]); - if (tb[IFLA_ADDRESS]) + if (tb[IFLA_ADDRESS]) { memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]), nla_len(tb[IFLA_ADDRESS])); + dev->addr_assign_type = NET_ADDR_SET; + } if (tb[IFLA_BROADCAST]) memcpy(dev->broadcast, nla_data(tb[IFLA_BROADCAST]), nla_len(tb[IFLA_BROADCAST])); @@ -1542,21 +1848,42 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net, set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); if (tb[IFLA_LINKMODE]) dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]); + if (tb[IFLA_GROUP]) + dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); return dev; -err_free: - free_netdev(dev); err: return ERR_PTR(err); } EXPORT_SYMBOL(rtnl_create_link); -static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int rtnl_group_changelink(const struct sk_buff *skb, + struct net *net, int group, + struct ifinfomsg *ifm, + struct nlattr **tb) +{ + struct net_device *dev; + int err; + + for_each_netdev(net, dev) { + if (dev->group == group) { + err = do_setlink(skb, dev, ifm, tb, NULL, 0); + if (err < 0) + return err; + } + } + + return 0; +} + +static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; + const struct rtnl_link_ops *m_ops = NULL; struct net_device *dev; + struct net_device *master_dev = NULL; struct ifinfomsg *ifm; char kind[MODULE_NAME_LEN]; char ifname[IFNAMSIZ]; @@ -1579,10 +1906,18 @@ replay: ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); - else if (ifname[0]) - dev = __dev_get_by_name(net, ifname); - else - dev = NULL; + else { + if (ifname[0]) + dev = __dev_get_by_name(net, ifname); + else + dev = NULL; + } + + if (dev) { + master_dev = netdev_master_upper_dev_get(dev); + if (master_dev) + m_ops = master_dev->rtnl_link_ops; + } err = validate_linkmsg(dev, tb); if (err < 0) @@ -1605,7 +1940,10 @@ replay: } if (1) { - struct nlattr *attr[ops ? ops->maxtype + 1 : 0], **data = NULL; + struct nlattr *attr[ops ? ops->maxtype + 1 : 0]; + struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 0]; + struct nlattr **data = NULL; + struct nlattr **slave_data = NULL; struct net *dest_net; if (ops) { @@ -1624,6 +1962,24 @@ replay: } } + if (m_ops) { + if (m_ops->slave_maxtype && + linkinfo[IFLA_INFO_SLAVE_DATA]) { + err = nla_parse_nested(slave_attr, + m_ops->slave_maxtype, + linkinfo[IFLA_INFO_SLAVE_DATA], + m_ops->slave_policy); + if (err < 0) + return err; + slave_data = slave_attr; + } + if (m_ops->slave_validate) { + err = m_ops->slave_validate(tb, slave_data); + if (err < 0) + return err; + } + } + if (dev) { int modified = 0; @@ -1643,14 +1999,28 @@ replay: modified = 1; } - return do_setlink(dev, ifm, tb, ifname, modified); + if (linkinfo[IFLA_INFO_SLAVE_DATA]) { + if (!m_ops || !m_ops->slave_changelink) + return -EOPNOTSUPP; + + err = m_ops->slave_changelink(master_dev, dev, + tb, slave_data); + if (err < 0) + return err; + modified = 1; + } + + return do_setlink(skb, dev, ifm, tb, ifname, modified); } - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { + if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) + return rtnl_group_changelink(skb, net, + nla_get_u32(tb[IFLA_GROUP]), + ifm, tb); return -ENODEV; + } - if (ifm->ifi_index) - return -EOPNOTSUPP; if (tb[IFLA_MAP] || tb[IFLA_MASTER] || tb[IFLA_PROTINFO]) return -EOPNOTSUPP; @@ -1672,20 +2042,36 @@ replay: snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind); dest_net = rtnl_link_get_net(net, tb); - dev = rtnl_create_link(net, dest_net, ifname, ops, tb); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); - if (IS_ERR(dev)) + dev = rtnl_create_link(dest_net, ifname, ops, tb); + if (IS_ERR(dev)) { err = PTR_ERR(dev); - else if (ops->newlink) - err = ops->newlink(net, dev, tb, data); - else - err = register_netdevice(dev); - - if (err < 0 && !IS_ERR(dev)) - free_netdev(dev); - if (err < 0) goto out; + } + dev->ifindex = ifm->ifi_index; + + if (ops->newlink) { + err = ops->newlink(net, dev, tb, data); + /* Drivers should call free_netdev() in ->destructor + * and unregister it on failure after registration + * so that device could be finally freed in rtnl_unlock. + */ + if (err < 0) { + /* If device is not registered at all, free it now */ + if (dev->reg_state == NETREG_UNINITIALIZED) + free_netdev(dev); + goto out; + } + } else { + err = register_netdevice(dev); + if (err < 0) { + free_netdev(dev); + goto out; + } + } err = rtnl_configure_link(dev, ifm); if (err < 0) unregister_netdevice(dev); @@ -1695,7 +2081,7 @@ out: } } -static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh) { struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; @@ -1704,6 +2090,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) struct net_device *dev = NULL; struct sk_buff *nskb; int err; + u32 ext_filter_mask = 0; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) @@ -1712,6 +2099,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); @@ -1723,22 +2113,55 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (dev == NULL) return -ENODEV; - nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL); + nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL); if (nskb == NULL) return -ENOBUFS; - err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid, - nlh->nlmsg_seq, 0, 0); + err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, + nlh->nlmsg_seq, 0, 0, ext_filter_mask); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); kfree_skb(nskb); } else - err = rtnl_unicast(nskb, net, NETLINK_CB(skb).pid); + err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid); return err; } +static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; + u16 min_ifinfo_dump_size = 0; + int hdrlen; + + /* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */ + hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); + + if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + } + + if (!ext_filter_mask) + return NLMSG_GOODSIZE; + /* + * traverse the list of net devices and compute the minimum + * buffer size based upon the filter mask. + */ + list_for_each_entry(dev, &net->dev_base_head, dev_list) { + min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size, + if_nlmsg_size(dev, + ext_filter_mask)); + } + + return min_ifinfo_dump_size; +} + static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) { int idx; @@ -1753,8 +2176,11 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) if (rtnl_msg_handlers[idx] == NULL || rtnl_msg_handlers[idx][type].dumpit == NULL) continue; - if (idx > s_idx) + if (idx > s_idx) { memset(&cb->args[0], 0, sizeof(cb->args)); + cb->prev_seq = 0; + cb->seq = 0; + } if (rtnl_msg_handlers[idx][type].dumpit(skb, cb)) break; } @@ -1763,33 +2189,653 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) +void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, + gfp_t flags) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; + size_t if_info_size; - skb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL); + skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), flags); if (skb == NULL) goto errout; - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL); + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags); return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_LINK, err); } +EXPORT_SYMBOL(rtmsg_ifinfo); + +static int nlmsg_populate_fdb_fill(struct sk_buff *skb, + struct net_device *dev, + u8 *addr, u32 pid, u32 seq, + int type, unsigned int flags, + int nlflags) +{ + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), nlflags); + if (!nlh) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = AF_BRIDGE; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = flags; + ndm->ndm_type = 0; + ndm->ndm_ifindex = dev->ifindex; + ndm->ndm_state = NUD_PERMANENT; + + if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static inline size_t rtnl_fdb_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN); +} + +static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type) +{ + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC); + if (!skb) + goto errout; + + err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF, 0); + if (err < 0) { + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + return; +errout: + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); +} + +/** + * ndo_dflt_fdb_add - default netdevice operation to add an FDB entry + */ +int ndo_dflt_fdb_add(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, + u16 flags) +{ + int err = -EINVAL; + + /* If aging addresses are supported device will need to + * implement its own handler for this. + */ + if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) { + pr_info("%s: FDB only supports static addresses\n", dev->name); + return err; + } + + if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) + err = dev_uc_add_excl(dev, addr); + else if (is_multicast_ether_addr(addr)) + err = dev_mc_add_excl(dev, addr); + + /* Only return duplicate errors if NLM_F_EXCL is set */ + if (err == -EEXIST && !(flags & NLM_F_EXCL)) + err = 0; + + return err; +} +EXPORT_SYMBOL(ndo_dflt_fdb_add); + +static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX+1]; + struct net_device *dev; + u8 *addr; + int err; + + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) + return err; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex == 0) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (dev == NULL) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n"); + return -ENODEV; + } + + if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n"); + return -EINVAL; + } -/* Protected by RTNL sempahore. */ -static struct rtattr **rta_buf; -static int rtattr_max; + addr = nla_data(tb[NDA_LLADDR]); + + err = -EOPNOTSUPP; + + /* Support fdb on master device the net/bridge default case */ + if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && + (dev->priv_flags & IFF_BRIDGE_PORT)) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops = br_dev->netdev_ops; + + err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags); + if (err) + goto out; + else + ndm->ndm_flags &= ~NTF_MASTER; + } + + /* Embedded bridge, macvlan, and any other device support */ + if ((ndm->ndm_flags & NTF_SELF)) { + if (dev->netdev_ops->ndo_fdb_add) + err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr, + nlh->nlmsg_flags); + else + err = ndo_dflt_fdb_add(ndm, tb, dev, addr, + nlh->nlmsg_flags); + + if (!err) { + rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH); + ndm->ndm_flags &= ~NTF_SELF; + } + } +out: + return err; +} + +/** + * ndo_dflt_fdb_del - default netdevice operation to delete an FDB entry + */ +int ndo_dflt_fdb_del(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr) +{ + int err = -EOPNOTSUPP; + + /* If aging addresses are supported device will need to + * implement its own handler for this. + */ + if (!(ndm->ndm_state & NUD_PERMANENT)) { + pr_info("%s: FDB only supports static addresses\n", dev->name); + return -EINVAL; + } + + if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) + err = dev_uc_del(dev, addr); + else if (is_multicast_ether_addr(addr)) + err = dev_mc_del(dev, addr); + else + err = -EINVAL; + + return err; +} +EXPORT_SYMBOL(ndo_dflt_fdb_del); + +static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX+1]; + struct net_device *dev; + int err = -EINVAL; + __u8 *addr; + + if (!netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) + return err; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex == 0) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n"); + return -EINVAL; + } + + dev = __dev_get_by_index(net, ndm->ndm_ifindex); + if (dev == NULL) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n"); + return -ENODEV; + } + + if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n"); + return -EINVAL; + } + + addr = nla_data(tb[NDA_LLADDR]); + + err = -EOPNOTSUPP; + + /* Support fdb on master device the net/bridge default case */ + if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && + (dev->priv_flags & IFF_BRIDGE_PORT)) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops = br_dev->netdev_ops; + + if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del(ndm, tb, dev, addr); + + if (err) + goto out; + else + ndm->ndm_flags &= ~NTF_MASTER; + } + + /* Embedded bridge, macvlan, and any other device support */ + if (ndm->ndm_flags & NTF_SELF) { + if (dev->netdev_ops->ndo_fdb_del) + err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr); + else + err = ndo_dflt_fdb_del(ndm, tb, dev, addr); + + if (!err) { + rtnl_fdb_notify(dev, addr, RTM_DELNEIGH); + ndm->ndm_flags &= ~NTF_SELF; + } + } +out: + return err; +} + +static int nlmsg_populate_fdb(struct sk_buff *skb, + struct netlink_callback *cb, + struct net_device *dev, + int *idx, + struct netdev_hw_addr_list *list) +{ + struct netdev_hw_addr *ha; + int err; + u32 portid, seq; + + portid = NETLINK_CB(cb->skb).portid; + seq = cb->nlh->nlmsg_seq; + + list_for_each_entry(ha, &list->list, list) { + if (*idx < cb->args[0]) + goto skip; + + err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, + portid, seq, + RTM_NEWNEIGH, NTF_SELF, + NLM_F_MULTI); + if (err < 0) + return err; +skip: + *idx += 1; + } + return 0; +} + +/** + * ndo_dflt_fdb_dump - default netdevice operation to dump an FDB table. + * @nlh: netlink message header + * @dev: netdevice + * + * Default netdevice operation to dump the existing unicast address list. + * Returns number of addresses from list put in skb. + */ +int ndo_dflt_fdb_dump(struct sk_buff *skb, + struct netlink_callback *cb, + struct net_device *dev, + int idx) +{ + int err; + + netif_addr_lock_bh(dev); + err = nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->uc); + if (err) + goto out; + nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc); +out: + netif_addr_unlock_bh(dev); + return idx; +} +EXPORT_SYMBOL(ndo_dflt_fdb_dump); + +static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int idx = 0; + struct net *net = sock_net(skb->sk); + struct net_device *dev; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + if (dev->priv_flags & IFF_BRIDGE_PORT) { + struct net_device *br_dev; + const struct net_device_ops *ops; + + br_dev = netdev_master_upper_dev_get(dev); + ops = br_dev->netdev_ops; + if (ops->ndo_fdb_dump) + idx = ops->ndo_fdb_dump(skb, cb, dev, idx); + } + + if (dev->netdev_ops->ndo_fdb_dump) + idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx); + else + idx = ndo_dflt_fdb_dump(skb, cb, dev, idx); + } + rcu_read_unlock(); + + cb->args[0] = idx; + return skb->len; +} + +int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u16 mode) +{ + struct nlmsghdr *nlh; + struct ifinfomsg *ifm; + struct nlattr *br_afspec; + u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI); + if (nlh == NULL) + return -EMSGSIZE; + + ifm = nlmsg_data(nlh); + ifm->ifi_family = AF_BRIDGE; + ifm->__ifi_pad = 0; + ifm->ifi_type = dev->type; + ifm->ifi_index = dev->ifindex; + ifm->ifi_flags = dev_get_flags(dev); + ifm->ifi_change = 0; + + + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + nla_put_u32(skb, IFLA_MTU, dev->mtu) || + nla_put_u8(skb, IFLA_OPERSTATE, operstate) || + (br_dev && + nla_put_u32(skb, IFLA_MASTER, br_dev->ifindex)) || + (dev->addr_len && + nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || + (dev->ifindex != dev->iflink && + nla_put_u32(skb, IFLA_LINK, dev->iflink))) + goto nla_put_failure; + + br_afspec = nla_nest_start(skb, IFLA_AF_SPEC); + if (!br_afspec) + goto nla_put_failure; + + if (nla_put_u16(skb, IFLA_BRIDGE_FLAGS, BRIDGE_FLAGS_SELF) || + nla_put_u16(skb, IFLA_BRIDGE_MODE, mode)) { + nla_nest_cancel(skb, br_afspec); + goto nla_put_failure; + } + nla_nest_end(skb, br_afspec); + + return nlmsg_end(skb, nlh); +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} +EXPORT_SYMBOL(ndo_dflt_bridge_getlink); + +static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int idx = 0; + u32 portid = NETLINK_CB(cb->skb).portid; + u32 seq = cb->nlh->nlmsg_seq; + struct nlattr *extfilt; + u32 filter_mask = 0; + + extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg), + IFLA_EXT_MASK); + if (extfilt) + filter_mask = nla_get_u32(extfilt); + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + const struct net_device_ops *ops = dev->netdev_ops; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { + if (idx >= cb->args[0] && + br_dev->netdev_ops->ndo_bridge_getlink( + skb, portid, seq, dev, filter_mask) < 0) + break; + idx++; + } + + if (ops->ndo_bridge_getlink) { + if (idx >= cb->args[0] && + ops->ndo_bridge_getlink(skb, portid, seq, dev, + filter_mask) < 0) + break; + idx++; + } + } + rcu_read_unlock(); + cb->args[0] = idx; + + return skb->len; +} + +static inline size_t bridge_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + + nla_total_size(sizeof(u32)) /* IFLA_MASTER */ + + nla_total_size(sizeof(u32)) /* IFLA_MTU */ + + nla_total_size(sizeof(u32)) /* IFLA_LINK */ + + nla_total_size(sizeof(u32)) /* IFLA_OPERSTATE */ + + nla_total_size(sizeof(u8)) /* IFLA_PROTINFO */ + + nla_total_size(sizeof(struct nlattr)) /* IFLA_AF_SPEC */ + + nla_total_size(sizeof(u16)) /* IFLA_BRIDGE_FLAGS */ + + nla_total_size(sizeof(u16)); /* IFLA_BRIDGE_MODE */ +} + +static int rtnl_bridge_notify(struct net_device *dev, u16 flags) +{ + struct net *net = dev_net(dev); + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + struct sk_buff *skb; + int err = -EOPNOTSUPP; + + skb = nlmsg_new(bridge_nlmsg_size(), GFP_ATOMIC); + if (!skb) { + err = -ENOMEM; + goto errout; + } + + if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) && + br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { + err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); + if (err < 0) + goto errout; + } + + if ((flags & BRIDGE_FLAGS_SELF) && + dev->netdev_ops->ndo_bridge_getlink) { + err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); + if (err < 0) + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); + return 0; +errout: + WARN_ON(err == -EMSGSIZE); + kfree_skb(skb); + rtnl_set_sk_err(net, RTNLGRP_LINK, err); + return err; +} + +static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ifinfomsg *ifm; + struct net_device *dev; + struct nlattr *br_spec, *attr = NULL; + int rem, err = -EOPNOTSUPP; + u16 oflags, flags = 0; + bool have_flags = false; + + if (nlmsg_len(nlh) < sizeof(*ifm)) + return -EINVAL; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_family != AF_BRIDGE) + return -EPFNOSUPPORT; + + dev = __dev_get_by_index(net, ifm->ifi_index); + if (!dev) { + pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + return -ENODEV; + } + + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (br_spec) { + nla_for_each_nested(attr, br_spec, rem) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + have_flags = true; + flags = nla_get_u16(attr); + break; + } + } + } + + oflags = flags; + + if (!flags || (flags & BRIDGE_FLAGS_MASTER)) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (!br_dev || !br_dev->netdev_ops->ndo_bridge_setlink) { + err = -EOPNOTSUPP; + goto out; + } + + err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh); + if (err) + goto out; + + flags &= ~BRIDGE_FLAGS_MASTER; + } + + if ((flags & BRIDGE_FLAGS_SELF)) { + if (!dev->netdev_ops->ndo_bridge_setlink) + err = -EOPNOTSUPP; + else + err = dev->netdev_ops->ndo_bridge_setlink(dev, nlh); + + if (!err) + flags &= ~BRIDGE_FLAGS_SELF; + } + + if (have_flags) + memcpy(nla_data(attr), &flags, sizeof(flags)); + /* Generate event to notify upper layer of bridge change */ + if (!err) + err = rtnl_bridge_notify(dev, oflags); +out: + return err; +} + +static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + struct net *net = sock_net(skb->sk); + struct ifinfomsg *ifm; + struct net_device *dev; + struct nlattr *br_spec, *attr = NULL; + int rem, err = -EOPNOTSUPP; + u16 oflags, flags = 0; + bool have_flags = false; + + if (nlmsg_len(nlh) < sizeof(*ifm)) + return -EINVAL; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_family != AF_BRIDGE) + return -EPFNOSUPPORT; + + dev = __dev_get_by_index(net, ifm->ifi_index); + if (!dev) { + pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + return -ENODEV; + } + + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (br_spec) { + nla_for_each_nested(attr, br_spec, rem) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + have_flags = true; + flags = nla_get_u16(attr); + break; + } + } + } + + oflags = flags; + + if (!flags || (flags & BRIDGE_FLAGS_MASTER)) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (!br_dev || !br_dev->netdev_ops->ndo_bridge_dellink) { + err = -EOPNOTSUPP; + goto out; + } + + err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh); + if (err) + goto out; + + flags &= ~BRIDGE_FLAGS_MASTER; + } + + if ((flags & BRIDGE_FLAGS_SELF)) { + if (!dev->netdev_ops->ndo_bridge_dellink) + err = -EOPNOTSUPP; + else + err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh); + + if (!err) + flags &= ~BRIDGE_FLAGS_SELF; + } + + if (have_flags) + memcpy(nla_data(attr), &flags, sizeof(flags)); + /* Generate event to notify upper layer of bridge change */ + if (!err) + err = rtnl_bridge_notify(dev, oflags); +out: + return err; +} /* Process one rtnetlink message. */ @@ -1798,7 +2844,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct net *net = sock_net(skb->sk); rtnl_doit_func doit; int sz_idx, kind; - int min_len; int family; int type; int err; @@ -1810,57 +2855,47 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) type -= RTM_BASE; /* All the messages must have at least 1 byte length */ - if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct rtgenmsg))) + if (nlmsg_len(nlh) < sizeof(struct rtgenmsg)) return 0; - family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family; + family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family; sz_idx = type>>2; kind = type&3; - if (kind != 2 && security_netlink_recv(skb, CAP_NET_ADMIN)) + if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { struct sock *rtnl; rtnl_dumpit_func dumpit; + rtnl_calcit_func calcit; + u16 min_dump_alloc = 0; dumpit = rtnl_get_dumpit(family, type); if (dumpit == NULL) return -EOPNOTSUPP; + calcit = rtnl_get_calcit(family, type); + if (calcit) + min_dump_alloc = calcit(skb, nlh); __rtnl_unlock(); rtnl = net->rtnl; - err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL); + { + struct netlink_dump_control c = { + .dump = dumpit, + .min_dump_alloc = min_dump_alloc, + }; + err = netlink_dump_start(rtnl, skb, nlh, &c); + } rtnl_lock(); return err; } - memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *))); - - min_len = rtm_min[sz_idx]; - if (nlh->nlmsg_len < min_len) - return -EINVAL; - - if (nlh->nlmsg_len > min_len) { - int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len); - struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len); - - while (RTA_OK(attr, attrlen)) { - unsigned flavor = attr->rta_type; - if (flavor) { - if (flavor > rta_max[sz_idx]) - return -EINVAL; - rta_buf[flavor-1] = attr; - } - attr = RTA_NEXT(attr, attrlen); - } - } - doit = rtnl_get_doit(family, type); if (doit == NULL) return -EOPNOTSUPP; - return doit(skb, nlh, (void *)&rta_buf[0]); + return doit(skb, nlh); } static void rtnetlink_rcv(struct sk_buff *skb) @@ -1872,7 +2907,7 @@ static void rtnetlink_rcv(struct sk_buff *skb) static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_UP: @@ -1884,10 +2919,12 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_PRE_TYPE_CHANGE: case NETDEV_GOING_DOWN: case NETDEV_UNREGISTER: - case NETDEV_UNREGISTER_BATCH: + case NETDEV_UNREGISTER_FINAL: + case NETDEV_RELEASE: + case NETDEV_JOIN: break; default: - rtmsg_ifinfo(RTM_NEWLINK, dev, 0); + rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); break; } return NOTIFY_DONE; @@ -1901,8 +2938,14 @@ static struct notifier_block rtnetlink_dev_notifier = { static int __net_init rtnetlink_net_init(struct net *net) { struct sock *sk; - sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX, - rtnetlink_rcv, &rtnl_mutex, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .groups = RTNLGRP_MAX, + .input = rtnetlink_rcv, + .cb_mutex = &rtnl_mutex, + .flags = NL_CFG_F_NONROOT_RECV, + }; + + sk = netlink_kernel_create(net, NETLINK_ROUTE, &cfg); if (!sk) return -ENOMEM; net->rtnl = sk; @@ -1922,28 +2965,26 @@ static struct pernet_operations rtnetlink_net_ops = { void __init rtnetlink_init(void) { - int i; - - rtattr_max = 0; - for (i = 0; i < ARRAY_SIZE(rta_max); i++) - if (rta_max[i] > rtattr_max) - rtattr_max = rta_max[i]; - rta_buf = kmalloc(rtattr_max * sizeof(struct rtattr *), GFP_KERNEL); - if (!rta_buf) - panic("rtnetlink_init: cannot allocate rta_buf\n"); - if (register_pernet_subsys(&rtnetlink_net_ops)) panic("rtnetlink_init: cannot initialize rtnetlink\n"); - netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV); register_netdevice_notifier(&rtnetlink_dev_notifier); - rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, rtnl_dump_ifinfo); - rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL); - rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL); - rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL); + rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, + rtnl_dump_ifinfo, rtnl_calcit); + rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, NULL); + + rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL); + rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL); + + rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL); - rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all); - rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all); + rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, NULL); + rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, NULL); + rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL); } diff --git a/net/core/scm.c b/net/core/scm.c index bbe45445080..b442e7e25e6 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -24,11 +24,11 @@ #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/security.h> +#include <linux/pid_namespace.h> #include <linux/pid.h> #include <linux/nsproxy.h> #include <linux/slab.h> -#include <asm/system.h> #include <asm/uaccess.h> #include <net/protocol.h> @@ -36,6 +36,7 @@ #include <net/sock.h> #include <net/compat.h> #include <net/scm.h> +#include <net/cls_cgroup.h> /* @@ -46,12 +47,18 @@ static __inline__ int scm_check_creds(struct ucred *creds) { const struct cred *cred = current_cred(); + kuid_t uid = make_kuid(cred->user_ns, creds->uid); + kgid_t gid = make_kgid(cred->user_ns, creds->gid); - if ((creds->pid == task_tgid_vnr(current) || capable(CAP_SYS_ADMIN)) && - ((creds->uid == cred->uid || creds->uid == cred->euid || - creds->uid == cred->suid) || capable(CAP_SETUID)) && - ((creds->gid == cred->gid || creds->gid == cred->egid || - creds->gid == cred->sgid) || capable(CAP_SETGID))) { + if (!uid_valid(uid) || !gid_valid(gid)) + return -EINVAL; + + if ((creds->pid == task_tgid_vnr(current) || + ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) && + ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || + uid_eq(uid, cred->suid)) || ns_capable(cred->user_ns, CAP_SETUID)) && + ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || + gid_eq(gid, cred->sgid)) || ns_capable(cred->user_ns, CAP_SETGID))) { return 0; } return -EPERM; @@ -95,7 +102,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) int fd = fdp[i]; struct file *file; - if (fd < 0 || !(file = fget(fd))) + if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; *fpp++ = file; fpl->count++; @@ -110,25 +117,9 @@ void __scm_destroy(struct scm_cookie *scm) if (fpl) { scm->fp = NULL; - if (current->scm_work_list) { - list_add_tail(&fpl->list, current->scm_work_list); - } else { - LIST_HEAD(work_list); - - current->scm_work_list = &work_list; - - list_add(&fpl->list, &work_list); - while (!list_empty(&work_list)) { - fpl = list_first_entry(&work_list, struct scm_fp_list, list); - - list_del(&fpl->list); - for (i=fpl->count-1; i>=0; i--) - fput(fpl->fp[i]); - kfree(fpl); - } - - current->scm_work_list = NULL; - } + for (i=fpl->count-1; i>=0; i--) + fput(fpl->fp[i]); + kfree(fpl); } } EXPORT_SYMBOL(__scm_destroy); @@ -166,37 +157,38 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) goto error; break; case SCM_CREDENTIALS: + { + struct ucred creds; + kuid_t uid; + kgid_t gid; if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct ucred))) goto error; - memcpy(&p->creds, CMSG_DATA(cmsg), sizeof(struct ucred)); - err = scm_check_creds(&p->creds); + memcpy(&creds, CMSG_DATA(cmsg), sizeof(struct ucred)); + err = scm_check_creds(&creds); if (err) goto error; - if (pid_vnr(p->pid) != p->creds.pid) { + p->creds.pid = creds.pid; + if (!p->pid || pid_vnr(p->pid) != creds.pid) { struct pid *pid; err = -ESRCH; - pid = find_get_pid(p->creds.pid); + pid = find_get_pid(creds.pid); if (!pid) goto error; put_pid(p->pid); p->pid = pid; } - if ((p->cred->euid != p->creds.uid) || - (p->cred->egid != p->creds.gid)) { - struct cred *cred; - err = -ENOMEM; - cred = prepare_creds(); - if (!cred) - goto error; + err = -EINVAL; + uid = make_kuid(current_user_ns(), creds.uid); + gid = make_kgid(current_user_ns(), creds.gid); + if (!uid_valid(uid) || !gid_valid(gid)) + goto error; - cred->uid = cred->euid = p->creds.uid; - cred->gid = cred->egid = p->creds.uid; - put_cred(p->cred); - p->cred = cred; - } + p->creds.uid = uid; + p->creds.gid = gid; break; + } default: goto error; } @@ -280,6 +272,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) for (i=0, cmfptr=(__force int __user *)CMSG_DATA(cm); i<fdmax; i++, cmfptr++) { + struct socket *sock; int new_fd; err = security_file_receive(fp[i]); if (err) @@ -295,8 +288,12 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) break; } /* Bump the usage count and install the file. */ - get_file(fp[i]); - fd_install(new_fd, fp[i]); + sock = sock_from_file(fp[i], &err); + if (sock) { + sock_update_netprioidx(sock->sk); + sock_update_classid(sock->sk); + } + fd_install(new_fd, get_file(fp[i])); } if (i > 0) diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c new file mode 100644 index 00000000000..ba71212f025 --- /dev/null +++ b/net/core/secure_seq.c @@ -0,0 +1,173 @@ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/cryptohash.h> +#include <linux/module.h> +#include <linux/cache.h> +#include <linux/random.h> +#include <linux/hrtimer.h> +#include <linux/ktime.h> +#include <linux/string.h> +#include <linux/net.h> + +#include <net/secure_seq.h> + +#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET) +#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4) + +static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned; + +static __always_inline void net_secret_init(void) +{ + net_get_random_once(net_secret, sizeof(net_secret)); +} +#endif + +#ifdef CONFIG_INET +static u32 seq_scale(u32 seq) +{ + /* + * As close as possible to RFC 793, which + * suggests using a 250 kHz clock. + * Further reading shows this assumes 2 Mb/s networks. + * For 10 Mb/s Ethernet, a 1 MHz clock is appropriate. + * For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but + * we also need to limit the resolution so that the u32 seq + * overlaps less than one time per MSL (2 minutes). + * Choosing a clock of 64 ns period is OK. (period of 274 s) + */ + return seq + (ktime_to_ns(ktime_get_real()) >> 6); +} +#endif + +#if IS_ENABLED(CONFIG_IPV6) +__u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u32 i; + + net_secret_init(); + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + (__force u32)daddr[i]; + secret[4] = net_secret[4] + + (((__force u16)sport << 16) + (__force u16)dport); + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + return seq_scale(hash[0]); +} +EXPORT_SYMBOL(secure_tcpv6_sequence_number); + +u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, + __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u32 i; + + net_secret_init(); + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + (__force u32) daddr[i]; + secret[4] = net_secret[4] + (__force u32)dport; + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + return hash[0]; +} +EXPORT_SYMBOL(secure_ipv6_port_ephemeral); +#endif + +#ifdef CONFIG_INET + +__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + + net_secret_init(); + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = ((__force u16)sport << 16) + (__force u16)dport; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return seq_scale(hash[0]); +} + +u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + + net_secret_init(); + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = (__force u32)dport ^ net_secret[14]; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return hash[0]; +} +EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); +#endif + +#if IS_ENABLED(CONFIG_IP_DCCP) +u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + u64 seq; + + net_secret_init(); + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = ((__force u16)sport << 16) + (__force u16)dport; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + seq = hash[0] | (((u64)hash[1]) << 32); + seq += ktime_to_ns(ktime_get_real()); + seq &= (1ull << 48) - 1; + + return seq; +} +EXPORT_SYMBOL(secure_dccp_sequence_number); + +#if IS_ENABLED(CONFIG_IPV6) +u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u64 seq; + u32 i; + + net_secret_init(); + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + daddr[i]; + secret[4] = net_secret[4] + + (((__force u16)sport << 16) + (__force u16)dport); + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + seq = hash[0] | (((u64)hash[1]) << 32); + seq += ktime_to_ns(ktime_get_real()); + seq &= (1ull << 48) - 1; + + return seq; +} +EXPORT_SYMBOL(secure_dccpv6_sequence_number); +#endif +#endif diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8814a9a52f4..c1a33033cbe 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -36,6 +36,8 @@ * The functions in this file will not compile correctly with gcc 2.4.x */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> @@ -45,6 +47,8 @@ #include <linux/in.h> #include <linux/inet.h> #include <linux/slab.h> +#include <linux/tcp.h> +#include <linux/udp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> @@ -57,93 +61,89 @@ #include <linux/init.h> #include <linux/scatterlist.h> #include <linux/errqueue.h> +#include <linux/prefetch.h> #include <net/protocol.h> #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/ip6_checksum.h> #include <net/xfrm.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <trace/events/skb.h> +#include <linux/highmem.h> -#include "kmap_skb.h" - -static struct kmem_cache *skbuff_head_cache __read_mostly; +struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; -static void sock_pipe_buf_release(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +/** + * skb_panic - private function for out-of-line support + * @skb: buffer + * @sz: size + * @addr: address + * @msg: skb_over_panic or skb_under_panic + * + * Out-of-line support for skb_put() and skb_push(). + * Called via the wrapper skb_over_panic() or skb_under_panic(). + * Keep out of line to prevent kernel bloat. + * __builtin_return_address is not used because it is not always reliable. + */ +static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, + const char msg[]) { - put_page(buf->page); + pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", + msg, addr, skb->len, sz, skb->head, skb->data, + (unsigned long)skb->tail, (unsigned long)skb->end, + skb->dev ? skb->dev->name : "<NULL>"); + BUG(); } -static void sock_pipe_buf_get(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr) { - get_page(buf->page); + skb_panic(skb, sz, addr, __func__); } -static int sock_pipe_buf_steal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) { - return 1; + skb_panic(skb, sz, addr, __func__); } - -/* Pipe buffer operations for a socket. */ -static const struct pipe_buf_operations sock_pipe_buf_ops = { - .can_merge = 0, - .map = generic_pipe_buf_map, - .unmap = generic_pipe_buf_unmap, - .confirm = generic_pipe_buf_confirm, - .release = sock_pipe_buf_release, - .steal = sock_pipe_buf_steal, - .get = sock_pipe_buf_get, -}; - /* - * Keep out-of-line to prevent kernel bloat. - * __builtin_return_address is not used because it is not always - * reliable. + * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells + * the caller if emergency pfmemalloc reserves are being used. If it is and + * the socket is later found to be SOCK_MEMALLOC then PFMEMALLOC reserves + * may be used. Otherwise, the packet data may be discarded until enough + * memory is free */ +#define kmalloc_reserve(size, gfp, node, pfmemalloc) \ + __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) -/** - * skb_over_panic - private function - * @skb: buffer - * @sz: size - * @here: address - * - * Out of line support code for skb_put(). Not user callable. - */ -static void skb_over_panic(struct sk_buff *skb, int sz, void *here) +static void *__kmalloc_reserve(size_t size, gfp_t flags, int node, + unsigned long ip, bool *pfmemalloc) { - printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p " - "data:%p tail:%#lx end:%#lx dev:%s\n", - here, skb->len, sz, skb->head, skb->data, - (unsigned long)skb->tail, (unsigned long)skb->end, - skb->dev ? skb->dev->name : "<NULL>"); - BUG(); -} + void *obj; + bool ret_pfmemalloc = false; -/** - * skb_under_panic - private function - * @skb: buffer - * @sz: size - * @here: address - * - * Out of line support code for skb_push(). Not user callable. - */ + /* + * Try a regular allocation, when that fails and we're not entitled + * to the reserves, fail. + */ + obj = kmalloc_node_track_caller(size, + flags | __GFP_NOMEMALLOC | __GFP_NOWARN, + node); + if (obj || !(gfp_pfmemalloc_allowed(flags))) + goto out; -static void skb_under_panic(struct sk_buff *skb, int sz, void *here) -{ - printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p " - "data:%p tail:%#lx end:%#lx dev:%s\n", - here, skb->len, sz, skb->head, skb->data, - (unsigned long)skb->tail, (unsigned long)skb->end, - skb->dev ? skb->dev->name : "<NULL>"); - BUG(); + /* Try again but now we are using pfmemalloc reserves */ + ret_pfmemalloc = true; + obj = kmalloc_node_track_caller(size, flags, node); + +out: + if (pfmemalloc) + *pfmemalloc = ret_pfmemalloc; + + return obj; } /* Allocate a new skbuff. We do this ourselves so we can fill in a few @@ -152,30 +152,62 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) * */ +struct sk_buff *__alloc_skb_head(gfp_t gfp_mask, int node) +{ + struct sk_buff *skb; + + /* Get the HEAD */ + skb = kmem_cache_alloc_node(skbuff_head_cache, + gfp_mask & ~__GFP_DMA, node); + if (!skb) + goto out; + + /* + * Only clear those fields we need to clear, not those that we will + * actually initialise below. Hence, don't put any more fields after + * the tail pointer in struct sk_buff! + */ + memset(skb, 0, offsetof(struct sk_buff, tail)); + skb->head = NULL; + skb->truesize = sizeof(struct sk_buff); + atomic_set(&skb->users, 1); + + skb->mac_header = (typeof(skb->mac_header))~0U; +out: + return skb; +} + /** * __alloc_skb - allocate a network buffer * @size: size to allocate * @gfp_mask: allocation mask - * @fclone: allocate from fclone cache instead of head cache - * and allocate a cloned (child) skb + * @flags: If SKB_ALLOC_FCLONE is set, allocate from fclone cache + * instead of head cache and allocate a cloned (child) skb. + * If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for + * allocations in case the data is required for writeback * @node: numa node to allocate memory on * * Allocate a new &sk_buff. The returned buffer has no headroom and a - * tail room of size bytes. The object has a reference count of one. - * The return is the buffer. On a failure the return is %NULL. + * tail room of at least size bytes. The object has a reference count + * of one. The return is the buffer. On a failure the return is %NULL. * * Buffers may only be allocated from interrupts using a @gfp_mask of * %GFP_ATOMIC. */ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, - int fclone, int node) + int flags, int node) { struct kmem_cache *cache; struct skb_shared_info *shinfo; struct sk_buff *skb; u8 *data; + bool pfmemalloc; + + cache = (flags & SKB_ALLOC_FCLONE) + ? skbuff_fclone_cache : skbuff_head_cache; - cache = fclone ? skbuff_fclone_cache : skbuff_head_cache; + if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) + gfp_mask |= __GFP_MEMALLOC; /* Get the HEAD */ skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); @@ -183,11 +215,21 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, goto out; prefetchw(skb); + /* We do our best to align skb_shared_info on a separate cache + * line. It usually works because kmalloc(X > SMP_CACHE_BYTES) gives + * aligned memory blocks, unless SLUB/SLAB debug is enabled. + * Both skb->head and skb_shared_info are cache line aligned. + */ size = SKB_DATA_ALIGN(size); - data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info), - gfp_mask, node); + size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + data = kmalloc_reserve(size, gfp_mask, node, &pfmemalloc); if (!data) goto nodata; + /* kmalloc(size) might give us more room than requested. + * Put skb_shared_info exactly at the end of allocated zone, + * to allow max possible filling before reallocation. + */ + size = SKB_WITH_OVERHEAD(ksize(data)); prefetchw(data + size); /* @@ -196,22 +238,24 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); - skb->truesize = size + sizeof(struct sk_buff); + /* Account for allocated memory : skb + skb->head */ + skb->truesize = SKB_TRUESIZE(size); + skb->pfmemalloc = pfmemalloc; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; skb_reset_tail_pointer(skb); skb->end = skb->tail + size; -#ifdef NET_SKBUFF_DATA_USES_OFFSET - skb->mac_header = ~0U; -#endif + skb->mac_header = (typeof(skb->mac_header))~0U; + skb->transport_header = (typeof(skb->transport_header))~0U; /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); + kmemcheck_annotate_variable(shinfo->destructor_arg); - if (fclone) { + if (flags & SKB_ALLOC_FCLONE) { struct sk_buff *child = skb + 1; atomic_t *fclone_ref = (atomic_t *) (child + 1); @@ -221,6 +265,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, atomic_set(fclone_ref, 1); child->fclone = SKB_FCLONE_UNAVAILABLE; + child->pfmemalloc = pfmemalloc; } out: return skb; @@ -232,6 +277,124 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** + * build_skb - build a network buffer + * @data: data buffer provided by caller + * @frag_size: size of fragment, or 0 if head was kmalloced + * + * Allocate a new &sk_buff. Caller provides space holding head and + * skb_shared_info. @data must have been allocated by kmalloc() only if + * @frag_size is 0, otherwise data should come from the page allocator. + * The return is the new skb buffer. + * On a failure the return is %NULL, and @data is not freed. + * Notes : + * Before IO, driver allocates only data buffer where NIC put incoming frame + * Driver should add room at head (NET_SKB_PAD) and + * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info)) + * After IO, driver calls build_skb(), to allocate sk_buff and populate it + * before giving packet to stack. + * RX rings only contains data buffers, not full skbs. + */ +struct sk_buff *build_skb(void *data, unsigned int frag_size) +{ + struct skb_shared_info *shinfo; + struct sk_buff *skb; + unsigned int size = frag_size ? : ksize(data); + + skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + if (!skb) + return NULL; + + size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + memset(skb, 0, offsetof(struct sk_buff, tail)); + skb->truesize = SKB_TRUESIZE(size); + skb->head_frag = frag_size != 0; + atomic_set(&skb->users, 1); + skb->head = data; + skb->data = data; + skb_reset_tail_pointer(skb); + skb->end = skb->tail + size; + skb->mac_header = (typeof(skb->mac_header))~0U; + skb->transport_header = (typeof(skb->transport_header))~0U; + + /* make sure we initialize shinfo sequentially */ + shinfo = skb_shinfo(skb); + memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); + atomic_set(&shinfo->dataref, 1); + kmemcheck_annotate_variable(shinfo->destructor_arg); + + return skb; +} +EXPORT_SYMBOL(build_skb); + +struct netdev_alloc_cache { + struct page_frag frag; + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_count every time we allocate a fragment. + */ + unsigned int pagecnt_bias; +}; +static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); + +static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) +{ + struct netdev_alloc_cache *nc; + void *data = NULL; + int order; + unsigned long flags; + + local_irq_save(flags); + nc = &__get_cpu_var(netdev_alloc_cache); + if (unlikely(!nc->frag.page)) { +refill: + for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) { + gfp_t gfp = gfp_mask; + + if (order) + gfp |= __GFP_COMP | __GFP_NOWARN; + nc->frag.page = alloc_pages(gfp, order); + if (likely(nc->frag.page)) + break; + if (--order < 0) + goto end; + } + nc->frag.size = PAGE_SIZE << order; +recycle: + atomic_set(&nc->frag.page->_count, NETDEV_PAGECNT_MAX_BIAS); + nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS; + nc->frag.offset = 0; + } + + if (nc->frag.offset + fragsz > nc->frag.size) { + /* avoid unnecessary locked operations if possible */ + if ((atomic_read(&nc->frag.page->_count) == nc->pagecnt_bias) || + atomic_sub_and_test(nc->pagecnt_bias, &nc->frag.page->_count)) + goto recycle; + goto refill; + } + + data = page_address(nc->frag.page) + nc->frag.offset; + nc->frag.offset += fragsz; + nc->pagecnt_bias--; +end: + local_irq_restore(flags); + return data; +} + +/** + * netdev_alloc_frag - allocate a page fragment + * @fragsz: fragment size + * + * Allocates a frag from a page for receive buffer. + * Uses GFP_ATOMIC allocations. + */ +void *netdev_alloc_frag(unsigned int fragsz) +{ + return __netdev_alloc_frag(fragsz, GFP_ATOMIC | __GFP_COLD); +} +EXPORT_SYMBOL(netdev_alloc_frag); + +/** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate @@ -245,11 +408,29 @@ EXPORT_SYMBOL(__alloc_skb); * %NULL is returned if there is no free memory. */ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, - unsigned int length, gfp_t gfp_mask) + unsigned int length, gfp_t gfp_mask) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; + unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE); + if (fragsz <= PAGE_SIZE && !(gfp_mask & (__GFP_WAIT | GFP_DMA))) { + void *data; + + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + + data = __netdev_alloc_frag(fragsz, gfp_mask); + + if (likely(data)) { + skb = build_skb(data, fragsz); + if (unlikely(!skb)) + put_page(virt_to_head_page(data)); + } + } else { + skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, + SKB_ALLOC_RX, NUMA_NO_NODE); + } if (likely(skb)) { skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; @@ -259,48 +440,31 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, EXPORT_SYMBOL(__netdev_alloc_skb); void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, - int size) + int size, unsigned int truesize) { skb_fill_page_desc(skb, i, page, off, size); skb->len += size; skb->data_len += size; - skb->truesize += size; + skb->truesize += truesize; } EXPORT_SYMBOL(skb_add_rx_frag); -/** - * dev_alloc_skb - allocate an skbuff for receiving - * @length: length to allocate - * - * Allocate a new &sk_buff and assign it a usage count of one. The - * buffer has unspecified headroom built in. Users should allocate - * the headroom they think they need without accounting for the - * built in space. The built in space is used for optimisations. - * - * %NULL is returned if there is no free memory. Although this function - * allocates memory it can be called from an interrupt. - */ -struct sk_buff *dev_alloc_skb(unsigned int length) +void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, + unsigned int truesize) { - /* - * There is more code here than it seems: - * __dev_alloc_skb is an inline - */ - return __dev_alloc_skb(length, GFP_ATOMIC); + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + skb_frag_size_add(frag, size); + skb->len += size; + skb->data_len += size; + skb->truesize += truesize; } -EXPORT_SYMBOL(dev_alloc_skb); +EXPORT_SYMBOL(skb_coalesce_rx_frag); static void skb_drop_list(struct sk_buff **listp) { - struct sk_buff *list = *listp; - + kfree_skb_list(*listp); *listp = NULL; - - do { - struct sk_buff *this = list; - list = list->next; - kfree_skb(this); - } while (list); } static inline void skb_drop_fraglist(struct sk_buff *skb) @@ -316,6 +480,14 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } +static void skb_free_head(struct sk_buff *skb) +{ + if (skb->head_frag) + put_page(virt_to_head_page(skb->head)); + else + kfree(skb->head); +} + static void skb_release_data(struct sk_buff *skb) { if (!skb->cloned || @@ -324,13 +496,25 @@ static void skb_release_data(struct sk_buff *skb) if (skb_shinfo(skb)->nr_frags) { int i; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - put_page(skb_shinfo(skb)->frags[i].page); + skb_frag_unref(skb, i); + } + + /* + * If skb buf is from userspace, we need to notify the caller + * the lower device DMA has done; + */ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + struct ubuf_info *uarg; + + uarg = skb_shinfo(skb)->destructor_arg; + if (uarg->callback) + uarg->callback(uarg, true); } if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); - kfree(skb->head); + skb_free_head(skb); } } @@ -378,9 +562,8 @@ static void skb_release_head_state(struct sk_buff *skb) WARN_ON(in_irq()); skb->destructor(skb); } -#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) +#if IS_ENABLED(CONFIG_NF_CONNTRACK) nf_conntrack_put(skb->nfct); - nf_conntrack_put_reasm(skb->nfct_reasm); #endif #ifdef CONFIG_BRIDGE_NETFILTER nf_bridge_put(skb->nf_bridge); @@ -398,7 +581,8 @@ static void skb_release_head_state(struct sk_buff *skb) static void skb_release_all(struct sk_buff *skb) { skb_release_head_state(skb); - skb_release_data(skb); + if (likely(skb->head)) + skb_release_data(skb); } /** @@ -437,6 +621,37 @@ void kfree_skb(struct sk_buff *skb) } EXPORT_SYMBOL(kfree_skb); +void kfree_skb_list(struct sk_buff *segs) +{ + while (segs) { + struct sk_buff *next = segs->next; + + kfree_skb(segs); + segs = next; + } +} +EXPORT_SYMBOL(kfree_skb_list); + +/** + * skb_tx_error - report an sk_buff xmit error + * @skb: buffer that triggered an error + * + * Report xmit error if a device callback is tracking this skb. + * skb must be freed afterwards. + */ +void skb_tx_error(struct sk_buff *skb) +{ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + struct ubuf_info *uarg; + + uarg = skb_shinfo(skb)->destructor_arg; + if (uarg->callback) + uarg->callback(uarg, false); + skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; + } +} +EXPORT_SYMBOL(skb_tx_error); + /** * consume_skb - free an skbuff * @skb: buffer to free @@ -458,49 +673,6 @@ void consume_skb(struct sk_buff *skb) } EXPORT_SYMBOL(consume_skb); -/** - * skb_recycle_check - check if skb can be reused for receive - * @skb: buffer - * @skb_size: minimum receive buffer size - * - * Checks that the skb passed in is not shared or cloned, and - * that it is linear and its head portion at least as large as - * skb_size so that it can be recycled as a receive buffer. - * If these conditions are met, this function does any necessary - * reference count dropping and cleans up the skbuff as if it - * just came from __alloc_skb(). - */ -bool skb_recycle_check(struct sk_buff *skb, int skb_size) -{ - struct skb_shared_info *shinfo; - - if (irqs_disabled()) - return false; - - if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE) - return false; - - skb_size = SKB_DATA_ALIGN(skb_size + NET_SKB_PAD); - if (skb_end_pointer(skb) - skb->head < skb_size) - return false; - - if (skb_shared(skb) || skb_cloned(skb)) - return false; - - skb_release_head_state(skb); - - shinfo = skb_shinfo(skb); - memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); - atomic_set(&shinfo->dataref, 1); - - memset(skb, 0, offsetof(struct sk_buff, tail)); - skb->data = skb->head + NET_SKB_PAD; - skb_reset_tail_pointer(skb); - - return true; -} -EXPORT_SYMBOL(skb_recycle_check); - static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { new->tstamp = old->tstamp; @@ -508,39 +680,50 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->transport_header = old->transport_header; new->network_header = old->network_header; new->mac_header = old->mac_header; + new->inner_protocol = old->inner_protocol; + new->inner_transport_header = old->inner_transport_header; + new->inner_network_header = old->inner_network_header; + new->inner_mac_header = old->inner_mac_header; skb_dst_copy(new, old); - new->rxhash = old->rxhash; + skb_copy_hash(new, old); + new->ooo_okay = old->ooo_okay; + new->no_fcs = old->no_fcs; + new->encapsulation = old->encapsulation; + new->encap_hdr_csum = old->encap_hdr_csum; + new->csum_valid = old->csum_valid; + new->csum_complete_sw = old->csum_complete_sw; #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); #endif memcpy(new->cb, old->cb, sizeof(old->cb)); new->csum = old->csum; - new->local_df = old->local_df; + new->ignore_df = old->ignore_df; new->pkt_type = old->pkt_type; new->ip_summed = old->ip_summed; skb_copy_queue_mapping(new, old); new->priority = old->priority; - new->deliver_no_wcard = old->deliver_no_wcard; -#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) +#if IS_ENABLED(CONFIG_IP_VS) new->ipvs_property = old->ipvs_property; #endif + new->pfmemalloc = old->pfmemalloc; new->protocol = old->protocol; new->mark = old->mark; new->skb_iif = old->skb_iif; __nf_copy(new, old); -#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ - defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) - new->nf_trace = old->nf_trace; -#endif #ifdef CONFIG_NET_SCHED new->tc_index = old->tc_index; #ifdef CONFIG_NET_CLS_ACT new->tc_verd = old->tc_verd; #endif #endif + new->vlan_proto = old->vlan_proto; new->vlan_tci = old->vlan_tci; skb_copy_secmark(new, old); + +#ifdef CONFIG_NET_RX_BUSY_POLL + new->napi_id = old->napi_id; +#endif } /* @@ -565,6 +748,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) C(tail); C(end); C(head); + C(head_frag); C(data); C(truesize); atomic_set(&n->users, 1); @@ -594,6 +778,67 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) EXPORT_SYMBOL_GPL(skb_morph); /** + * skb_copy_ubufs - copy userspace skb frags buffers to kernel + * @skb: the skb to modify + * @gfp_mask: allocation priority + * + * This must be called on SKBTX_DEV_ZEROCOPY skb. + * It will copy all frags into kernel and drop the reference + * to userspace pages. + * + * If this function is called from an interrupt gfp_mask() must be + * %GFP_ATOMIC. + * + * Returns 0 on success or a negative error code on failure + * to allocate kernel memory to copy to. + */ +int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) +{ + int i; + int num_frags = skb_shinfo(skb)->nr_frags; + struct page *page, *head = NULL; + struct ubuf_info *uarg = skb_shinfo(skb)->destructor_arg; + + for (i = 0; i < num_frags; i++) { + u8 *vaddr; + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; + + page = alloc_page(gfp_mask); + if (!page) { + while (head) { + struct page *next = (struct page *)page_private(head); + put_page(head); + head = next; + } + return -ENOMEM; + } + vaddr = kmap_atomic(skb_frag_page(f)); + memcpy(page_address(page), + vaddr + f->page_offset, skb_frag_size(f)); + kunmap_atomic(vaddr); + set_page_private(page, (unsigned long)head); + head = page; + } + + /* skb frags release userspace buffers */ + for (i = 0; i < num_frags; i++) + skb_frag_unref(skb, i); + + uarg->callback(uarg, false); + + /* skb frags point to kernel buffers */ + for (i = num_frags - 1; i >= 0; i--) { + __skb_fill_page_desc(skb, i, head, 0, + skb_shinfo(skb)->frags[i].size); + head = (struct page *)page_private(head); + } + + skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; + return 0; +} +EXPORT_SYMBOL_GPL(skb_copy_ubufs); + +/** * skb_clone - duplicate an sk_buff * @skb: buffer to clone * @gfp_mask: allocation priority @@ -611,6 +856,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; + if (skb_orphan_frags(skb, gfp_mask)) + return NULL; + n = skb + 1; if (skb->fclone == SKB_FCLONE_ORIG && n->fclone == SKB_FCLONE_UNAVAILABLE) { @@ -618,6 +866,9 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) n->fclone = SKB_FCLONE_CLONE; atomic_inc(fclone_ref); } else { + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); if (!n) return NULL; @@ -631,29 +882,37 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) } EXPORT_SYMBOL(skb_clone); -static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) +static void skb_headers_offset_update(struct sk_buff *skb, int off) { -#ifndef NET_SKBUFF_DATA_USES_OFFSET - /* - * Shift between the two data areas in bytes - */ - unsigned long offset = new->data - old->data; -#endif + /* Only adjust this if it actually is csum_start rather than csum */ + if (skb->ip_summed == CHECKSUM_PARTIAL) + skb->csum_start += off; + /* {transport,network,mac}_header and tail are relative to skb->head */ + skb->transport_header += off; + skb->network_header += off; + if (skb_mac_header_was_set(skb)) + skb->mac_header += off; + skb->inner_transport_header += off; + skb->inner_network_header += off; + skb->inner_mac_header += off; +} +static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) +{ __copy_skb_header(new, old); -#ifndef NET_SKBUFF_DATA_USES_OFFSET - /* {transport,network,mac}_header are relative to skb->head */ - new->transport_header += offset; - new->network_header += offset; - if (skb_mac_header_was_set(new)) - new->mac_header += offset; -#endif skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } +static inline int skb_alloc_rx_flag(const struct sk_buff *skb) +{ + if (skb_pfmemalloc(skb)) + return SKB_ALLOC_RX; + return 0; +} + /** * skb_copy - create private copy of an sk_buff * @skb: buffer to copy @@ -674,8 +933,9 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { int headerlen = skb_headroom(skb); - unsigned int size = (skb_end_pointer(skb) - skb->head) + skb->data_len; - struct sk_buff *n = alloc_skb(size, gfp_mask); + unsigned int size = skb_end_offset(skb) + skb->data_len; + struct sk_buff *n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; @@ -694,9 +954,13 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) EXPORT_SYMBOL(skb_copy); /** - * pskb_copy - create copy of an sk_buff with private head. + * __pskb_copy_fclone - create copy of an sk_buff with private head. * @skb: buffer to copy + * @headroom: headroom of new skb * @gfp_mask: allocation priority + * @fclone: if true allocate the copy of the skb from the fclone + * cache instead of the head cache; it is recommended to set this + * to true for the cases where the copy will likely be cloned * * Make a copy of both an &sk_buff and part of its data, located * in header. Fragmented data remain shared. This is used when @@ -706,16 +970,18 @@ EXPORT_SYMBOL(skb_copy); * The returned buffer has a reference count of 1. */ -struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) +struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, + gfp_t gfp_mask, bool fclone) { - unsigned int size = skb_end_pointer(skb) - skb->head; - struct sk_buff *n = alloc_skb(size, gfp_mask); + unsigned int size = skb_headlen(skb) + headroom; + int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0); + struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE); if (!n) goto out; /* Set the data pointer */ - skb_reserve(n, skb_headroom(skb)); + skb_reserve(n, headroom); /* Set the tail pointer and length */ skb_put(n, skb_headlen(skb)); /* Copy the bytes */ @@ -728,9 +994,14 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) if (skb_shinfo(skb)->nr_frags) { int i; + if (skb_orphan_frags(skb, gfp_mask)) { + kfree_skb(n); + n = NULL; + goto out; + } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; - get_page(skb_shinfo(n)->frags[i].page); + skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; } @@ -744,7 +1015,7 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) out: return n; } -EXPORT_SYMBOL(pskb_copy); +EXPORT_SYMBOL(__pskb_copy_fclone); /** * pskb_expand_head - reallocate header of &sk_buff @@ -753,8 +1024,8 @@ EXPORT_SYMBOL(pskb_copy); * @ntail: room to add at tail * @gfp_mask: allocation priority * - * Expands (or creates identical copy, if &nhead and &ntail are zero) - * header of skb. &sk_buff itself is not changed. &sk_buff MUST have + * Expands (or creates identical copy, if @nhead and @ntail are zero) + * header of @skb. &sk_buff itself is not changed. &sk_buff MUST have * reference count of 1. Returns zero in the case of success or error, * if expansion failed. In the last case, &sk_buff is not changed. * @@ -767,9 +1038,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, { int i; u8 *data; - int size = nhead + (skb_end_pointer(skb) - skb->head) + ntail; + int size = nhead + skb_end_offset(skb) + ntail; long off; - bool fastpath; BUG_ON(nhead < 0); @@ -778,31 +1048,13 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, size = SKB_DATA_ALIGN(size); - /* Check if we can avoid taking references on fragments if we own - * the last reference on skb->head. (see skb_release_data()) - */ - if (!skb->cloned) - fastpath = true; - else { - int delta = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; - - fastpath = atomic_read(&skb_shinfo(skb)->dataref) == delta; - } - - if (fastpath && - size + sizeof(struct skb_shared_info) <= ksize(skb->head)) { - memmove(skb->head + size, skb_shinfo(skb), - offsetof(struct skb_shared_info, - frags[skb_shinfo(skb)->nr_frags])); - memmove(skb->head + nhead, skb->head, - skb_tail_pointer(skb) - skb->head); - off = nhead; - goto adjust_others; - } - - data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask); + if (skb_pfmemalloc(skb)) + gfp_mask |= __GFP_MEMALLOC; + data = kmalloc_reserve(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; + size = SKB_WITH_OVERHEAD(ksize(data)); /* Copy only real data... and, alas, header. This should be * optimized for the cases when header is void. @@ -813,21 +1065,29 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); - if (fastpath) { - kfree(skb->head); - } else { + /* + * if shinfo is shared we must drop the old head gracefully, but if it + * is not we can just drop the old head and let the existing refcount + * be since all we did is relocate the values + */ + if (skb_cloned(skb)) { + /* copy this zero copy skb frags */ + if (skb_orphan_frags(skb, gfp_mask)) + goto nofrags; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - get_page(skb_shinfo(skb)->frags[i].page); + skb_frag_ref(skb, i); if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); skb_release_data(skb); + } else { + skb_free_head(skb); } off = (data + nhead) - skb->head; skb->head = data; -adjust_others: + skb->head_frag = 0; skb->data += off; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->end = size; @@ -835,21 +1095,16 @@ adjust_others: #else skb->end = skb->head + size; #endif - /* {transport,network,mac}_header and tail are relative to skb->head */ skb->tail += off; - skb->transport_header += off; - skb->network_header += off; - if (skb_mac_header_was_set(skb)) - skb->mac_header += off; - /* Only adjust this if it actually is csum_start rather than csum */ - if (skb->ip_summed == CHECKSUM_PARTIAL) - skb->csum_start += nhead; + skb_headers_offset_update(skb, nhead); skb->cloned = 0; skb->hdr_len = 0; skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; +nofrags: + kfree(data); nodata: return -ENOMEM; } @@ -901,11 +1156,11 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask); + struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; - int off; if (!n) return NULL; @@ -929,15 +1184,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, copy_skb_header(n, skb); - off = newheadroom - oldheadroom; - if (n->ip_summed == CHECKSUM_PARTIAL) - n->csum_start += off; -#ifdef NET_SKBUFF_DATA_USES_OFFSET - n->transport_header += off; - n->network_header += off; - if (skb_mac_header_was_set(skb)) - n->mac_header += off; -#endif + skb_headers_offset_update(n, newheadroom - oldheadroom); return n; } @@ -990,6 +1237,29 @@ free_skb: EXPORT_SYMBOL(skb_pad); /** + * pskb_put - add data to the tail of a potentially fragmented buffer + * @skb: start of the buffer to use + * @tail: tail fragment of the buffer to use + * @len: amount of data to add + * + * This function extends the used data area of the potentially + * fragmented buffer. @tail must be the last fragment of @skb -- or + * @skb itself. If this would exceed the total buffer size the kernel + * will panic. A pointer to the first byte of the extra data is + * returned. + */ + +unsigned char *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len) +{ + if (tail != skb) { + skb->data_len += len; + skb->len += len; + } + return skb_put(tail, len); +} +EXPORT_SYMBOL_GPL(pskb_put); + +/** * skb_put - add data to a buffer * @skb: buffer to use * @len: amount of data to add @@ -1082,20 +1352,20 @@ int ___pskb_trim(struct sk_buff *skb, unsigned int len) goto drop_pages; for (; i < nfrags; i++) { - int end = offset + skb_shinfo(skb)->frags[i].size; + int end = offset + skb_frag_size(&skb_shinfo(skb)->frags[i]); if (end < len) { offset = end; continue; } - skb_shinfo(skb)->frags[i++].size = len - offset; + skb_frag_size_set(&skb_shinfo(skb)->frags[i++], len - offset); drop_pages: skb_shinfo(skb)->nr_frags = i; for (; i < nfrags; i++) - put_page(skb_shinfo(skb)->frags[i].page); + skb_frag_unref(skb, i); if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); @@ -1114,7 +1384,7 @@ drop_pages: return -ENOMEM; nfrag->next = frag->next; - kfree_skb(frag); + consume_skb(frag); frag = nfrag; *fragp = frag; } @@ -1198,9 +1468,11 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta) /* Estimate size of pulled pages. */ eat = delta; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - if (skb_shinfo(skb)->frags[i].size >= eat) + int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); + + if (size >= eat) goto pull_pages; - eat -= skb_shinfo(skb)->frags[i].size; + eat -= size; } /* If we need update frag list, we are in troubles. @@ -1263,14 +1535,16 @@ pull_pages: eat = delta; k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - if (skb_shinfo(skb)->frags[i].size <= eat) { - put_page(skb_shinfo(skb)->frags[i].page); - eat -= skb_shinfo(skb)->frags[i].size; + int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); + + if (size <= eat) { + skb_frag_unref(skb, i); + eat -= size; } else { skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i]; if (eat) { skb_shinfo(skb)->frags[k].page_offset += eat; - skb_shinfo(skb)->frags[k].size -= eat; + skb_frag_size_sub(&skb_shinfo(skb)->frags[k], eat); eat = 0; } k++; @@ -1285,8 +1559,21 @@ pull_pages: } EXPORT_SYMBOL(__pskb_pull_tail); -/* Copy some data bits from skb to kernel buffer. */ - +/** + * skb_copy_bits - copy bits from skb to kernel buffer + * @skb: source skb + * @offset: offset in source + * @to: destination buffer + * @len: number of bytes to copy + * + * Copy the specified number of bytes from the source skb to the + * destination buffer. + * + * CAUTION ! : + * If its prototype is ever changed, + * check arch/{*}/net/{*}.S files, + * since it is called from BPF assembly code. + */ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { int start = skb_headlen(skb); @@ -1309,21 +1596,22 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(f); if ((copy = end - offset) > 0) { u8 *vaddr; if (copy > len) copy = len; - vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]); + vaddr = kmap_atomic(skb_frag_page(f)); memcpy(to, - vaddr + skb_shinfo(skb)->frags[i].page_offset+ - offset - start, copy); - kunmap_skb_frag(vaddr); + vaddr + f->page_offset + offset - start, + copy); + kunmap_atomic(vaddr); if ((len -= copy) == 0) return 0; @@ -1351,6 +1639,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) } start = end; } + if (!len) return 0; @@ -1368,140 +1657,122 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) put_page(spd->pages[i]); } -static inline struct page *linear_to_page(struct page *page, unsigned int *len, - unsigned int *offset, - struct sk_buff *skb, struct sock *sk) +static struct page *linear_to_page(struct page *page, unsigned int *len, + unsigned int *offset, + struct sock *sk) { - struct page *p = sk->sk_sndmsg_page; - unsigned int off; - - if (!p) { -new_page: - p = sk->sk_sndmsg_page = alloc_pages(sk->sk_allocation, 0); - if (!p) - return NULL; + struct page_frag *pfrag = sk_page_frag(sk); - off = sk->sk_sndmsg_off = 0; - /* hold one ref to this page until it's full */ - } else { - unsigned int mlen; + if (!sk_page_frag_refill(sk, pfrag)) + return NULL; - off = sk->sk_sndmsg_off; - mlen = PAGE_SIZE - off; - if (mlen < 64 && mlen < *len) { - put_page(p); - goto new_page; - } + *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset); - *len = min_t(unsigned int, *len, mlen); - } + memcpy(page_address(pfrag->page) + pfrag->offset, + page_address(page) + *offset, *len); + *offset = pfrag->offset; + pfrag->offset += *len; - memcpy(page_address(p) + off, page_address(page) + *offset, *len); - sk->sk_sndmsg_off += *len; - *offset = off; - get_page(p); + return pfrag->page; +} - return p; +static bool spd_can_coalesce(const struct splice_pipe_desc *spd, + struct page *page, + unsigned int offset) +{ + return spd->nr_pages && + spd->pages[spd->nr_pages - 1] == page && + (spd->partial[spd->nr_pages - 1].offset + + spd->partial[spd->nr_pages - 1].len == offset); } /* * Fill page/offset/length into spd, if it can hold more pages. */ -static inline int spd_fill_page(struct splice_pipe_desc *spd, - struct pipe_inode_info *pipe, struct page *page, - unsigned int *len, unsigned int offset, - struct sk_buff *skb, int linear, - struct sock *sk) +static bool spd_fill_page(struct splice_pipe_desc *spd, + struct pipe_inode_info *pipe, struct page *page, + unsigned int *len, unsigned int offset, + bool linear, + struct sock *sk) { - if (unlikely(spd->nr_pages == pipe->buffers)) - return 1; + if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) + return true; if (linear) { - page = linear_to_page(page, len, &offset, skb, sk); + page = linear_to_page(page, len, &offset, sk); if (!page) - return 1; - } else - get_page(page); - + return true; + } + if (spd_can_coalesce(spd, page, offset)) { + spd->partial[spd->nr_pages - 1].len += *len; + return false; + } + get_page(page); spd->pages[spd->nr_pages] = page; spd->partial[spd->nr_pages].len = *len; spd->partial[spd->nr_pages].offset = offset; spd->nr_pages++; - return 0; + return false; } -static inline void __segment_seek(struct page **page, unsigned int *poff, - unsigned int *plen, unsigned int off) -{ - unsigned long n; - - *poff += off; - n = *poff / PAGE_SIZE; - if (n) - *page = nth_page(*page, n); - - *poff = *poff % PAGE_SIZE; - *plen -= off; -} - -static inline int __splice_segment(struct page *page, unsigned int poff, - unsigned int plen, unsigned int *off, - unsigned int *len, struct sk_buff *skb, - struct splice_pipe_desc *spd, int linear, - struct sock *sk, - struct pipe_inode_info *pipe) +static bool __splice_segment(struct page *page, unsigned int poff, + unsigned int plen, unsigned int *off, + unsigned int *len, + struct splice_pipe_desc *spd, bool linear, + struct sock *sk, + struct pipe_inode_info *pipe) { if (!*len) - return 1; + return true; /* skip this segment if already processed */ if (*off >= plen) { *off -= plen; - return 0; + return false; } /* ignore any bits we already processed */ - if (*off) { - __segment_seek(&page, &poff, &plen, *off); - *off = 0; - } + poff += *off; + plen -= *off; + *off = 0; do { unsigned int flen = min(*len, plen); - /* the linear region may spread across several pages */ - flen = min_t(unsigned int, flen, PAGE_SIZE - poff); - - if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk)) - return 1; - - __segment_seek(&page, &poff, &plen, flen); + if (spd_fill_page(spd, pipe, page, &flen, poff, + linear, sk)) + return true; + poff += flen; + plen -= flen; *len -= flen; - } while (*len && plen); - return 0; + return false; } /* - * Map linear and fragment data from the skb to spd. It reports failure if the + * Map linear and fragment data from the skb to spd. It reports true if the * pipe is full or if we already spliced the requested length. */ -static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, - unsigned int *offset, unsigned int *len, - struct splice_pipe_desc *spd, struct sock *sk) +static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, + unsigned int *offset, unsigned int *len, + struct splice_pipe_desc *spd, struct sock *sk) { int seg; - /* - * map the linear part + /* map the linear part : + * If skb->head_frag is set, this 'linear' part is backed by a + * fragment, and if the head is not shared with any clones then + * we can avoid a copy since we own the head portion of this page. */ if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd, 1, sk, pipe)) - return 1; + offset, len, spd, + skb_head_is_locked(skb), + sk, pipe)) + return true; /* * then map the fragments @@ -1509,12 +1780,13 @@ static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; - if (__splice_segment(f->page, f->page_offset, f->size, - offset, len, skb, spd, 0, sk, pipe)) - return 1; + if (__splice_segment(skb_frag_page(f), + f->page_offset, skb_frag_size(f), + offset, len, spd, false, sk, pipe)) + return true; } - return 0; + return false; } /* @@ -1527,22 +1799,20 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct pipe_inode_info *pipe, unsigned int tlen, unsigned int flags) { - struct partial_page partial[PIPE_DEF_BUFFERS]; - struct page *pages[PIPE_DEF_BUFFERS]; + struct partial_page partial[MAX_SKB_FRAGS]; + struct page *pages[MAX_SKB_FRAGS]; struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = MAX_SKB_FRAGS, .flags = flags, - .ops = &sock_pipe_buf_ops, + .ops = &nosteal_pipe_buf_ops, .spd_release = sock_spd_release, }; struct sk_buff *frag_iter; struct sock *sk = skb->sk; int ret = 0; - if (splice_grow_spd(pipe, &spd)) - return -ENOMEM; - /* * __skb_splice_bits() only fails if the output has no room left, * so no point in going over the frag_list for the error case. @@ -1578,7 +1848,6 @@ done: lock_sock(sk); } - splice_shrink_spd(pipe, &spd); return ret; } @@ -1619,17 +1888,17 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) WARN_ON(start > offset + len); - end = start + frag->size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { u8 *vaddr; if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); memcpy(vaddr + frag->page_offset + offset - start, from, copy); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); if ((len -= copy) == 0) return 0; @@ -1667,9 +1936,8 @@ fault: EXPORT_SYMBOL(skb_store_bits); /* Checksum skb data. */ - -__wsum skb_checksum(const struct sk_buff *skb, int offset, - int len, __wsum csum) +__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, + __wsum csum, const struct skb_checksum_ops *ops) { int start = skb_headlen(skb); int i, copy = start - offset; @@ -1680,7 +1948,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, if (copy > 0) { if (copy > len) copy = len; - csum = csum_partial(skb->data + offset, copy, csum); + csum = ops->update(skb->data + offset, copy, csum); if ((len -= copy) == 0) return csum; offset += copy; @@ -1689,22 +1957,22 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { __wsum csum2; u8 *vaddr; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); - csum2 = csum_partial(vaddr + frag->page_offset + - offset - start, copy, 0); - kunmap_skb_frag(vaddr); - csum = csum_block_add(csum, csum2, pos); + vaddr = kmap_atomic(skb_frag_page(frag)); + csum2 = ops->update(vaddr + frag->page_offset + + offset - start, copy, 0); + kunmap_atomic(vaddr); + csum = ops->combine(csum, csum2, pos, copy); if (!(len -= copy)) return csum; offset += copy; @@ -1723,9 +1991,9 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, __wsum csum2; if (copy > len) copy = len; - csum2 = skb_checksum(frag_iter, offset - start, - copy, 0); - csum = csum_block_add(csum, csum2, pos); + csum2 = __skb_checksum(frag_iter, offset - start, + copy, 0, ops); + csum = ops->combine(csum, csum2, pos, copy); if ((len -= copy) == 0) return csum; offset += copy; @@ -1737,6 +2005,18 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, return csum; } +EXPORT_SYMBOL(__skb_checksum); + +__wsum skb_checksum(const struct sk_buff *skb, int offset, + int len, __wsum csum) +{ + const struct skb_checksum_ops ops = { + .update = csum_partial_ext, + .combine = csum_block_add_ext, + }; + + return __skb_checksum(skb, offset, len, csum, &ops); +} EXPORT_SYMBOL(skb_checksum); /* Both of above in one bottle. */ @@ -1767,7 +2047,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { __wsum csum2; u8 *vaddr; @@ -1775,12 +2055,12 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, if (copy > len) copy = len; - vaddr = kmap_skb_frag(frag); + vaddr = kmap_atomic(skb_frag_page(frag)); csum2 = csum_partial_copy_nocheck(vaddr + frag->page_offset + offset - start, to, copy, 0); - kunmap_skb_frag(vaddr); + kunmap_atomic(vaddr); csum = csum_block_add(csum, csum2, pos); if (!(len -= copy)) return csum; @@ -1818,13 +2098,111 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, } EXPORT_SYMBOL(skb_copy_and_csum_bits); + /** + * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() + * @from: source buffer + * + * Calculates the amount of linear headroom needed in the 'to' skb passed + * into skb_zerocopy(). + */ +unsigned int +skb_zerocopy_headlen(const struct sk_buff *from) +{ + unsigned int hlen = 0; + + if (!from->head_frag || + skb_headlen(from) < L1_CACHE_BYTES || + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + hlen = skb_headlen(from); + + if (skb_has_frag_list(from)) + hlen = from->len; + + return hlen; +} +EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); + +/** + * skb_zerocopy - Zero copy skb to skb + * @to: destination buffer + * @from: source buffer + * @len: number of bytes to copy from source buffer + * @hlen: size of linear headroom in destination buffer + * + * Copies up to `len` bytes from `from` to `to` by creating references + * to the frags in the source buffer. + * + * The `hlen` as calculated by skb_zerocopy_headlen() specifies the + * headroom in the `to` buffer. + * + * Return value: + * 0: everything is OK + * -ENOMEM: couldn't orphan frags of @from due to lack of memory + * -EFAULT: skb_copy_bits() found some problem with skb geometry + */ +int +skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen) +{ + int i, j = 0; + int plen = 0; /* length of skb->head fragment */ + int ret; + struct page *page; + unsigned int offset; + + BUG_ON(!from->head_frag && !hlen); + + /* dont bother with small payloads */ + if (len <= skb_tailroom(to)) + return skb_copy_bits(from, 0, skb_put(to, len), len); + + if (hlen) { + ret = skb_copy_bits(from, 0, skb_put(to, hlen), hlen); + if (unlikely(ret)) + return ret; + len -= hlen; + } else { + plen = min_t(int, skb_headlen(from), len); + if (plen) { + page = virt_to_head_page(from->head); + offset = from->data - (unsigned char *)page_address(page); + __skb_fill_page_desc(to, 0, page, offset, plen); + get_page(page); + j = 1; + len -= plen; + } + } + + to->truesize += len + plen; + to->len += len + plen; + to->data_len += len + plen; + + if (unlikely(skb_orphan_frags(from, GFP_ATOMIC))) { + skb_tx_error(from); + return -ENOMEM; + } + + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { + if (!len) + break; + skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; + skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len); + len -= skb_shinfo(to)->frags[j].size; + skb_frag_ref(to, j); + j++; + } + skb_shinfo(to)->nr_frags = j; + + return 0; +} +EXPORT_SYMBOL_GPL(skb_zerocopy); + void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { __wsum csum; long csstart; if (skb->ip_summed == CHECKSUM_PARTIAL) - csstart = skb->csum_start - skb_headroom(skb); + csstart = skb_checksum_start_offset(skb); else csstart = skb_headlen(skb); @@ -2040,7 +2418,7 @@ static inline void skb_split_no_header(struct sk_buff *skb, skb->data_len = len - pos; for (i = 0; i < nfrags; i++) { - int size = skb_shinfo(skb)->frags[i].size; + int size = skb_frag_size(&skb_shinfo(skb)->frags[i]); if (pos + size > len) { skb_shinfo(skb1)->frags[k] = skb_shinfo(skb)->frags[i]; @@ -2054,10 +2432,10 @@ static inline void skb_split_no_header(struct sk_buff *skb, * where splitting is expensive. * 2. Split is accurately. We make this. */ - get_page(skb_shinfo(skb)->frags[i].page); + skb_frag_ref(skb, i); skb_shinfo(skb1)->frags[0].page_offset += len - pos; - skb_shinfo(skb1)->frags[0].size -= len - pos; - skb_shinfo(skb)->frags[i].size = len - pos; + skb_frag_size_sub(&skb_shinfo(skb1)->frags[0], len - pos); + skb_frag_size_set(&skb_shinfo(skb)->frags[i], len - pos); skb_shinfo(skb)->nr_frags++; } k++; @@ -2078,6 +2456,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); + skb_shinfo(skb1)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ @@ -2101,7 +2480,7 @@ static int skb_prepare_for_shift(struct sk_buff *skb) * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than - * the length of the skb, from tgt to skb. Returns number bytes shifted. + * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. @@ -2129,12 +2508,13 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) * commit all, so that we don't have to undo partial changes */ if (!to || - !skb_can_coalesce(tgt, to, fragfrom->page, fragfrom->page_offset)) { + !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), + fragfrom->page_offset)) { merge = -1; } else { merge = to - 1; - todo -= fragfrom->size; + todo -= skb_frag_size(fragfrom); if (todo < 0) { if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) @@ -2144,8 +2524,8 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[merge]; - fragto->size += shiftlen; - fragfrom->size -= shiftlen; + skb_frag_size_add(fragto, shiftlen); + skb_frag_size_sub(fragfrom, shiftlen); fragfrom->page_offset += shiftlen; goto onlymerged; @@ -2169,20 +2549,20 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragfrom = &skb_shinfo(skb)->frags[from]; fragto = &skb_shinfo(tgt)->frags[to]; - if (todo >= fragfrom->size) { + if (todo >= skb_frag_size(fragfrom)) { *fragto = *fragfrom; - todo -= fragfrom->size; + todo -= skb_frag_size(fragfrom); from++; to++; } else { - get_page(fragfrom->page); + __skb_frag_ref(fragfrom); fragto->page = fragfrom->page; fragto->page_offset = fragfrom->page_offset; - fragto->size = todo; + skb_frag_size_set(fragto, todo); fragfrom->page_offset += todo; - fragfrom->size -= todo; + skb_frag_size_sub(fragfrom, todo); todo = 0; to++; @@ -2197,8 +2577,8 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragfrom = &skb_shinfo(skb)->frags[0]; fragto = &skb_shinfo(tgt)->frags[merge]; - fragto->size += fragfrom->size; - put_page(fragfrom->page); + skb_frag_size_add(fragto, skb_frag_size(fragfrom)); + __skb_frag_unref(fragfrom); } /* Reposition in the original skb */ @@ -2254,18 +2634,18 @@ EXPORT_SYMBOL(skb_prepare_seq_read); * @data: destination pointer for data to be returned * @st: state variable * - * Reads a block of skb data at &consumed relative to the + * Reads a block of skb data at @consumed relative to the * lower offset specified to skb_prepare_seq_read(). Assigns - * the head of the data block to &data and returns the length + * the head of the data block to @data and returns the length * of the block or 0 if the end of the skb data or the upper * offset has been reached. * * The caller is not required to consume all of the data - * returned, i.e. &consumed is typically set to the number + * returned, i.e. @consumed is typically set to the number * of bytes already consumed and the next call to * skb_seq_read() will return the remaining part of the block. * - * Note 1: The size of each block of data returned can be arbitary, + * Note 1: The size of each block of data returned can be arbitrary, * this limitation is the cost for zerocopy seqeuental * reads of potentially non linear data. * @@ -2279,8 +2659,13 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data, unsigned int block_limit, abs_offset = consumed + st->lower_offset; skb_frag_t *frag; - if (unlikely(abs_offset >= st->upper_offset)) + if (unlikely(abs_offset >= st->upper_offset)) { + if (st->frag_data) { + kunmap_atomic(st->frag_data); + st->frag_data = NULL; + } return 0; + } next_skb: block_limit = skb_headlen(st->cur_skb) + st->stepped_offset; @@ -2295,11 +2680,11 @@ next_skb: while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) { frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx]; - block_limit = frag->size + st->stepped_offset; + block_limit = skb_frag_size(frag) + st->stepped_offset; if (abs_offset < block_limit) { if (!st->frag_data) - st->frag_data = kmap_skb_frag(frag); + st->frag_data = kmap_atomic(skb_frag_page(frag)); *data = (u8 *) st->frag_data + frag->page_offset + (abs_offset - st->stepped_offset); @@ -2308,16 +2693,16 @@ next_skb: } if (st->frag_data) { - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); st->frag_data = NULL; } st->frag_idx++; - st->stepped_offset += frag->size; + st->stepped_offset += skb_frag_size(frag); } if (st->frag_data) { - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); st->frag_data = NULL; } @@ -2345,7 +2730,7 @@ EXPORT_SYMBOL(skb_seq_read); void skb_abort_seq_read(struct skb_seq_state *st) { if (st->frag_data) - kunmap_skb_frag(st->frag_data); + kunmap_atomic(st->frag_data); } EXPORT_SYMBOL(skb_abort_seq_read); @@ -2393,7 +2778,7 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, EXPORT_SYMBOL(skb_find_text); /** - * skb_append_datato_frags: - append the user data to a skb + * skb_append_datato_frags - append the user data to a skb * @sk: sock structure * @skb: skb structure to be appened with user data. * @getfrag: call back function to be used for getting the user data @@ -2408,52 +2793,37 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, int len, int odd, struct sk_buff *skb), void *from, int length) { - int frg_cnt = 0; - skb_frag_t *frag = NULL; - struct page *page = NULL; - int copy, left; + int frg_cnt = skb_shinfo(skb)->nr_frags; + int copy; int offset = 0; int ret; + struct page_frag *pfrag = ¤t->task_frag; do { /* Return error if we don't have space for new frag */ - frg_cnt = skb_shinfo(skb)->nr_frags; if (frg_cnt >= MAX_SKB_FRAGS) - return -EFAULT; + return -EMSGSIZE; - /* allocate a new page for next frag */ - page = alloc_pages(sk->sk_allocation, 0); - - /* If alloc_page fails just return failure and caller will - * free previous allocated pages by doing kfree_skb() - */ - if (page == NULL) + if (!sk_page_frag_refill(sk, pfrag)) return -ENOMEM; - /* initialize the next frag */ - sk->sk_sndmsg_page = page; - sk->sk_sndmsg_off = 0; - skb_fill_page_desc(skb, frg_cnt, page, 0, 0); - skb->truesize += PAGE_SIZE; - atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc); - - /* get the new initialized frag */ - frg_cnt = skb_shinfo(skb)->nr_frags; - frag = &skb_shinfo(skb)->frags[frg_cnt - 1]; - /* copy the user data to page */ - left = PAGE_SIZE - frag->page_offset; - copy = (length > left)? left : length; + copy = min_t(int, length, pfrag->size - pfrag->offset); - ret = getfrag(from, (page_address(frag->page) + - frag->page_offset + frag->size), - offset, copy, 0, skb); + ret = getfrag(from, page_address(pfrag->page) + pfrag->offset, + offset, copy, 0, skb); if (ret < 0) return -EFAULT; /* copy was successful so update the size parameters */ - sk->sk_sndmsg_off += copy; - frag->size += copy; + skb_fill_page_desc(skb, frg_cnt, pfrag->page, pfrag->offset, + copy); + frg_cnt++; + pfrag->offset += copy; + get_page(pfrag->page); + + skb->truesize += copy; + atomic_add(copy, &sk->sk_wmem_alloc); skb->len += copy; skb->data_len += copy; offset += copy; @@ -2488,72 +2858,109 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum); /** * skb_segment - Perform protocol segmentation on skb. - * @skb: buffer to segment + * @head_skb: buffer to segment * @features: features for the output path (see dev->features) * * This function performs segmentation on the given skb. It returns * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ -struct sk_buff *skb_segment(struct sk_buff *skb, int features) +struct sk_buff *skb_segment(struct sk_buff *head_skb, + netdev_features_t features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; - struct sk_buff *fskb = skb_shinfo(skb)->frag_list; - unsigned int mss = skb_shinfo(skb)->gso_size; - unsigned int doffset = skb->data - skb_mac_header(skb); + struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; + skb_frag_t *frag = skb_shinfo(head_skb)->frags; + unsigned int mss = skb_shinfo(head_skb)->gso_size; + unsigned int doffset = head_skb->data - skb_mac_header(head_skb); + struct sk_buff *frag_skb = head_skb; unsigned int offset = doffset; + unsigned int tnl_hlen = skb_tnl_header_len(head_skb); unsigned int headroom; unsigned int len; - int sg = features & NETIF_F_SG; - int nfrags = skb_shinfo(skb)->nr_frags; + __be16 proto; + bool csum; + int sg = !!(features & NETIF_F_SG); + int nfrags = skb_shinfo(head_skb)->nr_frags; int err = -ENOMEM; int i = 0; int pos; + int dummy; + + __skb_push(head_skb, doffset); + proto = skb_network_protocol(head_skb, &dummy); + if (unlikely(!proto)) + return ERR_PTR(-EINVAL); + + csum = !head_skb->encap_hdr_csum && + !!can_checksum_protocol(features, proto); - __skb_push(skb, doffset); - headroom = skb_headroom(skb); - pos = skb_headlen(skb); + headroom = skb_headroom(head_skb); + pos = skb_headlen(head_skb); do { struct sk_buff *nskb; - skb_frag_t *frag; + skb_frag_t *nskb_frag; int hsize; int size; - len = skb->len - offset; + len = head_skb->len - offset; if (len > mss) len = mss; - hsize = skb_headlen(skb) - offset; + hsize = skb_headlen(head_skb) - offset; if (hsize < 0) hsize = 0; if (hsize > len || !sg) hsize = len; - if (!hsize && i >= nfrags) { - BUG_ON(fskb->len != len); + if (!hsize && i >= nfrags && skb_headlen(list_skb) && + (skb_headlen(list_skb) == len || sg)) { + BUG_ON(skb_headlen(list_skb) > len); + + i = 0; + nfrags = skb_shinfo(list_skb)->nr_frags; + frag = skb_shinfo(list_skb)->frags; + frag_skb = list_skb; + pos += skb_headlen(list_skb); + + while (pos < offset + len) { + BUG_ON(i >= nfrags); + + size = skb_frag_size(frag); + if (pos + size > offset + len) + break; - pos += len; - nskb = skb_clone(fskb, GFP_ATOMIC); - fskb = fskb->next; + i++; + pos += size; + frag++; + } + + nskb = skb_clone(list_skb, GFP_ATOMIC); + list_skb = list_skb->next; if (unlikely(!nskb)) goto err; - hsize = skb_end_pointer(nskb) - nskb->head; + if (unlikely(pskb_trim(nskb, len))) { + kfree_skb(nskb); + goto err; + } + + hsize = skb_end_offset(nskb); if (skb_cow_head(nskb, doffset + headroom)) { kfree_skb(nskb); goto err; } - nskb->truesize += skb_end_pointer(nskb) - nskb->head - - hsize; + nskb->truesize += skb_end_offset(nskb) - hsize; skb_release_head_state(nskb); __skb_push(nskb, doffset); } else { - nskb = alloc_skb(hsize + doffset + headroom, - GFP_ATOMIC); + nskb = __alloc_skb(hsize + doffset + headroom, + GFP_ATOMIC, skb_alloc_rx_flag(head_skb), + NUMA_NO_NODE); if (unlikely(!nskb)) goto err; @@ -2568,121 +2975,133 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) segs = nskb; tail = nskb; - __copy_skb_header(nskb, skb); - nskb->mac_len = skb->mac_len; + __copy_skb_header(nskb, head_skb); + nskb->mac_len = head_skb->mac_len; - /* nskb and skb might have different headroom */ - if (nskb->ip_summed == CHECKSUM_PARTIAL) - nskb->csum_start += skb_headroom(nskb) - headroom; + skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); - skb_reset_mac_header(nskb); - skb_set_network_header(nskb, skb->mac_len); - nskb->transport_header = (nskb->network_header + - skb_network_header_len(skb)); - skb_copy_from_linear_data(skb, nskb->data, doffset); + skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, + nskb->data - tnl_hlen, + doffset + tnl_hlen); - if (fskb != skb_shinfo(skb)->frag_list) - continue; + if (nskb->len == len + doffset) + goto perform_csum_check; if (!sg) { nskb->ip_summed = CHECKSUM_NONE; - nskb->csum = skb_copy_and_csum_bits(skb, offset, + nskb->csum = skb_copy_and_csum_bits(head_skb, offset, skb_put(nskb, len), len, 0); + SKB_GSO_CB(nskb)->csum_start = + skb_headroom(nskb) + doffset; continue; } - frag = skb_shinfo(nskb)->frags; + nskb_frag = skb_shinfo(nskb)->frags; - skb_copy_from_linear_data_offset(skb, offset, + skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); - while (pos < offset + len && i < nfrags) { - *frag = skb_shinfo(skb)->frags[i]; - get_page(frag->page); - size = frag->size; + skb_shinfo(nskb)->tx_flags = skb_shinfo(head_skb)->tx_flags & + SKBTX_SHARED_FRAG; + + while (pos < offset + len) { + if (i >= nfrags) { + BUG_ON(skb_headlen(list_skb)); + + i = 0; + nfrags = skb_shinfo(list_skb)->nr_frags; + frag = skb_shinfo(list_skb)->frags; + frag_skb = list_skb; + + BUG_ON(!nfrags); + + list_skb = list_skb->next; + } + + if (unlikely(skb_shinfo(nskb)->nr_frags >= + MAX_SKB_FRAGS)) { + net_warn_ratelimited( + "skb_segment: too many frags: %u %u\n", + pos, mss); + goto err; + } + + if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC))) + goto err; + + *nskb_frag = *frag; + __skb_frag_ref(nskb_frag); + size = skb_frag_size(nskb_frag); if (pos < offset) { - frag->page_offset += offset - pos; - frag->size -= offset - pos; + nskb_frag->page_offset += offset - pos; + skb_frag_size_sub(nskb_frag, offset - pos); } skb_shinfo(nskb)->nr_frags++; if (pos + size <= offset + len) { i++; + frag++; pos += size; } else { - frag->size -= pos + size - (offset + len); + skb_frag_size_sub(nskb_frag, pos + size - (offset + len)); goto skip_fraglist; } - frag++; - } - - if (pos < offset + len) { - struct sk_buff *fskb2 = fskb; - - BUG_ON(pos + fskb->len != offset + len); - - pos += fskb->len; - fskb = fskb->next; - - if (fskb2->next) { - fskb2 = skb_clone(fskb2, GFP_ATOMIC); - if (!fskb2) - goto err; - } else - skb_get(fskb2); - - SKB_FRAG_ASSERT(nskb); - skb_shinfo(nskb)->frag_list = fskb2; + nskb_frag++; } skip_fraglist: nskb->data_len = len - hsize; nskb->len += nskb->data_len; nskb->truesize += nskb->data_len; - } while ((offset += len) < skb->len); + +perform_csum_check: + if (!csum) { + nskb->csum = skb_checksum(nskb, doffset, + nskb->len - doffset, 0); + nskb->ip_summed = CHECKSUM_NONE; + SKB_GSO_CB(nskb)->csum_start = + skb_headroom(nskb) + doffset; + } + } while ((offset += len) < head_skb->len); return segs; err: - while ((skb = segs)) { - segs = skb->next; - kfree_skb(skb); - } + kfree_skb_list(segs); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(skb_segment); int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) { - struct sk_buff *p = *head; - struct sk_buff *nskb; - struct skb_shared_info *skbinfo = skb_shinfo(skb); - struct skb_shared_info *pinfo = skb_shinfo(p); - unsigned int headroom; - unsigned int len = skb_gro_len(skb); + struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); unsigned int offset = skb_gro_offset(skb); unsigned int headlen = skb_headlen(skb); + struct sk_buff *nskb, *lp, *p = *head; + unsigned int len = skb_gro_len(skb); + unsigned int delta_truesize; + unsigned int headroom; - if (p->len + len >= 65536) + if (unlikely(p->len + len >= 65536)) return -E2BIG; - if (pinfo->frag_list) - goto merge; - else if (headlen <= offset) { + lp = NAPI_GRO_CB(p)->last; + pinfo = skb_shinfo(lp); + + if (headlen <= offset) { skb_frag_t *frag; skb_frag_t *frag2; int i = skbinfo->nr_frags; int nr_frags = pinfo->nr_frags + i; - offset -= headlen; - if (nr_frags > MAX_SKB_FRAGS) - return -E2BIG; + goto merge; + offset -= headlen; pinfo->nr_frags = nr_frags; skbinfo->nr_frags = 0; @@ -2693,15 +3112,48 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) } while (--i); frag->page_offset += offset; - frag->size -= offset; + skb_frag_size_sub(frag, offset); + + /* all fragments truesize : remove (head size + sk_buff) */ + delta_truesize = skb->truesize - + SKB_TRUESIZE(skb_end_offset(skb)); skb->truesize -= skb->data_len; skb->len -= skb->data_len; skb->data_len = 0; - NAPI_GRO_CB(skb)->free = 1; + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; + goto done; + } else if (skb->head_frag) { + int nr_frags = pinfo->nr_frags; + skb_frag_t *frag = pinfo->frags + nr_frags; + struct page *page = virt_to_head_page(skb->head); + unsigned int first_size = headlen - offset; + unsigned int first_offset; + + if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) + goto merge; + + first_offset = skb->data - + (unsigned char *)page_address(page) + + offset; + + pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; + + frag->page.p = page; + frag->page_offset = first_offset; + skb_frag_size_set(frag, first_size); + + memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); + /* We dont need to clear skbinfo->nr_frags here */ + + delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; - } else if (skb_gro_len(p) != pinfo->gso_size) + } + if (pinfo->frag_list) + goto merge; + if (skb_gro_len(p) != pinfo->gso_size) return -E2BIG; headroom = skb_headroom(p); @@ -2723,15 +3175,14 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) memcpy(skb_mac_header(nskb), skb_mac_header(p), p->data - skb_mac_header(p)); - *NAPI_GRO_CB(nskb) = *NAPI_GRO_CB(p); skb_shinfo(nskb)->frag_list = p; skb_shinfo(nskb)->gso_size = pinfo->gso_size; pinfo->gso_size = 0; skb_header_release(p); - nskb->prev = p; + NAPI_GRO_CB(nskb)->last = p; nskb->data_len += p->len; - nskb->truesize += p->len; + nskb->truesize += p->truesize; nskb->len += p->len; *head = nskb; @@ -2741,24 +3192,37 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) p = nskb; merge: + delta_truesize = skb->truesize; if (offset > headlen) { - skbinfo->frags[0].page_offset += offset - headlen; - skbinfo->frags[0].size -= offset - headlen; + unsigned int eat = offset - headlen; + + skbinfo->frags[0].page_offset += eat; + skb_frag_size_sub(&skbinfo->frags[0], eat); + skb->data_len -= eat; + skb->len -= eat; offset = headlen; } __skb_pull(skb, offset); - p->prev->next = skb; - p->prev = skb; + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + NAPI_GRO_CB(p)->last = skb; skb_header_release(skb); + lp = p; done: NAPI_GRO_CB(p)->count++; p->data_len += len; - p->truesize += len; + p->truesize += delta_truesize; p->len += len; - + if (lp != p) { + lp->data_len += len; + lp->truesize += delta_truesize; + lp->len += len; + } NAPI_GRO_CB(skb)->same_flow = 1; return 0; } @@ -2812,13 +3276,13 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); if ((copy = end - offset) > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; if (copy > len) copy = len; - sg_set_page(&sg[elt], frag->page, copy, + sg_set_page(&sg[elt], skb_frag_page(frag), copy, frag->page_offset+offset-start); elt++; if (!(len -= copy)) @@ -2849,6 +3313,32 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) return elt; } +/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given + * sglist without mark the sg which contain last skb data as the end. + * So the caller can mannipulate sg list as will when padding new data after + * the first call without calling sg_unmark_end to expend sg list. + * + * Scenario to use skb_to_sgvec_nomark: + * 1. sg_init_table + * 2. skb_to_sgvec_nomark(payload1) + * 3. skb_to_sgvec_nomark(payload2) + * + * This is equivalent to: + * 1. sg_init_table + * 2. skb_to_sgvec(payload1) + * 3. sg_unmark_end + * 4. skb_to_sgvec(payload2) + * + * When mapping mutilple payload conditionally, skb_to_sgvec_nomark + * is more preferable. + */ +int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len) +{ + return __skb_to_sgvec(skb, sg, offset, len); +} +EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark); + int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int nsg = __skb_to_sgvec(skb, sg, offset, len); @@ -2982,7 +3472,7 @@ static void sock_rmem_free(struct sk_buff *skb) int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) + (unsigned int)sk->sk_rcvbuf) return -ENOMEM; skb_orphan(skb); @@ -2990,9 +3480,12 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb->destructor = sock_rmem_free; atomic_add(skb->truesize, &sk->sk_rmem_alloc); + /* before exiting rcu section, make sure dst is refcounted */ + skb_dst_force(skb); + skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb->len); + sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@ -3008,12 +3501,8 @@ void skb_tstamp_tx(struct sk_buff *orig_skb, if (!sk) return; - skb = skb_clone(orig_skb, GFP_ATOMIC); - if (!skb) - return; - if (hwtstamps) { - *skb_hwtstamps(skb) = + *skb_hwtstamps(orig_skb) = *hwtstamps; } else { /* @@ -3021,9 +3510,13 @@ void skb_tstamp_tx(struct sk_buff *orig_skb, * so keep the shared tx_flags and only * store software time stamp */ - skb->tstamp = ktime_get_real(); + orig_skb->tstamp = ktime_get_real(); } + skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!skb) + return; + serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; @@ -3036,6 +3529,26 @@ void skb_tstamp_tx(struct sk_buff *orig_skb, } EXPORT_SYMBOL_GPL(skb_tstamp_tx); +void skb_complete_wifi_ack(struct sk_buff *skb, bool acked) +{ + struct sock *sk = skb->sk; + struct sock_exterr_skb *serr; + int err; + + skb->wifi_acked_valid = 1; + skb->wifi_acked = acked; + + serr = SKB_EXT_ERR(skb); + memset(serr, 0, sizeof(*serr)); + serr->ee.ee_errno = ENOMSG; + serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS; + + err = sock_queue_err_skb(sk, skb); + if (err) + kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(skb_complete_wifi_ack); + /** * skb_partial_csum_set - set up and verify partial csum values for packet @@ -3053,23 +3566,396 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { if (unlikely(start > skb_headlen(skb)) || unlikely((int)start + off > skb_headlen(skb) - 2)) { - if (net_ratelimit()) - printk(KERN_WARNING - "bad partial csum: csum=%u/%u len=%u\n", - start, off, skb_headlen(skb)); + net_warn_ratelimited("bad partial csum: csum=%u/%u len=%u\n", + start, off, skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + start; skb->csum_offset = off; + skb_set_transport_header(skb, start); return true; } EXPORT_SYMBOL_GPL(skb_partial_csum_set); +static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, + unsigned int max) +{ + if (skb_headlen(skb) >= len) + return 0; + + /* If we need to pullup then pullup to the max, so we + * won't need to do it again. + */ + if (max > skb->len) + max = skb->len; + + if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) + return -ENOMEM; + + if (skb_headlen(skb) < len) + return -EPROTO; + + return 0; +} + +#define MAX_TCP_HDR_LEN (15 * 4) + +static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, + typeof(IPPROTO_IP) proto, + unsigned int off) +{ + switch (proto) { + int err; + + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), + off + MAX_TCP_HDR_LEN); + if (!err && !skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, + check))) + err = -EPROTO; + return err ? ERR_PTR(err) : &tcp_hdr(skb)->check; + + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, off + sizeof(struct udphdr), + off + sizeof(struct udphdr)); + if (!err && !skb_partial_csum_set(skb, off, + offsetof(struct udphdr, + check))) + err = -EPROTO; + return err ? ERR_PTR(err) : &udp_hdr(skb)->check; + } + + return ERR_PTR(-EPROTO); +} + +/* This value should be large enough to cover a tagged ethernet header plus + * maximally sized IP and TCP or UDP headers. + */ +#define MAX_IP_HDR_LEN 128 + +static int skb_checksum_setup_ipv4(struct sk_buff *skb, bool recalculate) +{ + unsigned int off; + bool fragment; + __sum16 *csum; + int err; + + fragment = false; + + err = skb_maybe_pull_tail(skb, + sizeof(struct iphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) + fragment = true; + + off = ip_hdrlen(skb); + + err = -EPROTO; + + if (fragment) + goto out; + + csum = skb_checksum_setup_ip(skb, ip_hdr(skb)->protocol, off); + if (IS_ERR(csum)) + return PTR_ERR(csum); + + if (recalculate) + *csum = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + ip_hdr(skb)->protocol, 0); + err = 0; + +out: + return err; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * an IPv6 header, all options, and a maximal TCP or UDP header. + */ +#define MAX_IPV6_HDR_LEN 256 + +#define OPT_HDR(type, skb, off) \ + (type *)(skb_network_header(skb) + (off)) + +static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) +{ + int err; + u8 nexthdr; + unsigned int off; + unsigned int len; + bool fragment; + bool done; + __sum16 *csum; + + fragment = false; + done = false; + + off = sizeof(struct ipv6hdr); + + err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + nexthdr = ipv6_hdr(skb)->nexthdr; + + len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); + while (off <= len && !done) { + switch (nexthdr) { + case IPPROTO_DSTOPTS: + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: { + struct ipv6_opt_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ipv6_opt_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_optlen(hp); + break; + } + case IPPROTO_AH: { + struct ip_auth_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ip_auth_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ip_auth_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_authlen(hp); + break; + } + case IPPROTO_FRAGMENT: { + struct frag_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct frag_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct frag_hdr, skb, off); + + if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) + fragment = true; + + nexthdr = hp->nexthdr; + off += sizeof(struct frag_hdr); + break; + } + default: + done = true; + break; + } + } + + err = -EPROTO; + + if (!done || fragment) + goto out; + + csum = skb_checksum_setup_ip(skb, nexthdr, off); + if (IS_ERR(csum)) + return PTR_ERR(csum); + + if (recalculate) + *csum = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, nexthdr, 0); + err = 0; + +out: + return err; +} + +/** + * skb_checksum_setup - set up partial checksum offset + * @skb: the skb to set up + * @recalculate: if true the pseudo-header checksum will be recalculated + */ +int skb_checksum_setup(struct sk_buff *skb, bool recalculate) +{ + int err; + + switch (skb->protocol) { + case htons(ETH_P_IP): + err = skb_checksum_setup_ipv4(skb, recalculate); + break; + + case htons(ETH_P_IPV6): + err = skb_checksum_setup_ipv6(skb, recalculate); + break; + + default: + err = -EPROTO; + break; + } + + return err; +} +EXPORT_SYMBOL(skb_checksum_setup); + void __skb_warn_lro_forwarding(const struct sk_buff *skb) { - if (net_ratelimit()) - pr_warning("%s: received packets cannot be forwarded" - " while LRO is enabled\n", skb->dev->name); + net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", + skb->dev->name); } EXPORT_SYMBOL(__skb_warn_lro_forwarding); + +void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) +{ + if (head_stolen) { + skb_release_head_state(skb); + kmem_cache_free(skbuff_head_cache, skb); + } else { + __kfree_skb(skb); + } +} +EXPORT_SYMBOL(kfree_skb_partial); + +/** + * skb_try_coalesce - try to merge skb to prior one + * @to: prior buffer + * @from: buffer to add + * @fragstolen: pointer to boolean + * @delta_truesize: how much more was allocated than was requested + */ +bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, + bool *fragstolen, int *delta_truesize) +{ + int i, delta, len = from->len; + + *fragstolen = false; + + if (skb_cloned(to)) + return false; + + if (len <= skb_tailroom(to)) { + BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); + *delta_truesize = 0; + return true; + } + + if (skb_has_frag_list(to) || skb_has_frag_list(from)) + return false; + + if (skb_headlen(from) != 0) { + struct page *page; + unsigned int offset; + + if (skb_shinfo(to)->nr_frags + + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + return false; + + if (skb_head_is_locked(from)) + return false; + + delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff)); + + page = virt_to_head_page(from->head); + offset = from->data - (unsigned char *)page_address(page); + + skb_fill_page_desc(to, skb_shinfo(to)->nr_frags, + page, offset, skb_headlen(from)); + *fragstolen = true; + } else { + if (skb_shinfo(to)->nr_frags + + skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS) + return false; + + delta = from->truesize - SKB_TRUESIZE(skb_end_offset(from)); + } + + WARN_ON_ONCE(delta < len); + + memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags, + skb_shinfo(from)->frags, + skb_shinfo(from)->nr_frags * sizeof(skb_frag_t)); + skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags; + + if (!skb_cloned(from)) + skb_shinfo(from)->nr_frags = 0; + + /* if the skb is not cloned this does nothing + * since we set nr_frags to 0. + */ + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) + skb_frag_ref(from, i); + + to->truesize += delta; + to->len += len; + to->data_len += len; + + *delta_truesize = delta; + return true; +} +EXPORT_SYMBOL(skb_try_coalesce); + +/** + * skb_scrub_packet - scrub an skb + * + * @skb: buffer to clean + * @xnet: packet is crossing netns + * + * skb_scrub_packet can be used after encapsulating or decapsulting a packet + * into/from a tunnel. Some information have to be cleared during these + * operations. + * skb_scrub_packet can also be used to clean a skb before injecting it in + * another namespace (@xnet == true). We have to clear all information in the + * skb that could impact namespace isolation. + */ +void skb_scrub_packet(struct sk_buff *skb, bool xnet) +{ + if (xnet) + skb_orphan(skb); + skb->tstamp.tv64 = 0; + skb->pkt_type = PACKET_HOST; + skb->skb_iif = 0; + skb->ignore_df = 0; + skb_dst_drop(skb); + skb->mark = 0; + secpath_reset(skb); + nf_reset(skb); + nf_reset_trace(skb); +} +EXPORT_SYMBOL_GPL(skb_scrub_packet); + +/** + * skb_gso_transport_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_transport_seglen is used to determine the real size of the + * individual segments, including Layer4 headers (TCP/UDP). + * + * The MAC/L2 or network (IP, IPv6) headers are not accounted for. + */ +unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + return tcp_hdrlen(skb) + shinfo->gso_size; + + /* UFO sets gso_size to the size of the fragmentation + * payload, i.e. the size of the L4 (UDP) header is already + * accounted for. + */ + return shinfo->gso_size; +} +EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); diff --git a/net/core/sock.c b/net/core/sock.c index fb608011146..026e01f7027 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -89,8 +89,11 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/capability.h> #include <linux/errno.h> +#include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> @@ -111,9 +114,11 @@ #include <linux/init.h> #include <linux/highmem.h> #include <linux/user_namespace.h> +#include <linux/static_key.h> +#include <linux/memcontrol.h> +#include <linux/prefetch.h> #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/netdevice.h> #include <net/protocol.h> @@ -125,13 +130,107 @@ #include <net/xfrm.h> #include <linux/ipsec.h> #include <net/cls_cgroup.h> +#include <net/netprio_cgroup.h> #include <linux/filter.h> +#include <trace/events/sock.h> + #ifdef CONFIG_INET #include <net/tcp.h> #endif +#include <net/busy_poll.h> + +static DEFINE_MUTEX(proto_list_mutex); +static LIST_HEAD(proto_list); + +/** + * sk_ns_capable - General socket capability test + * @sk: Socket to use a capability on or through + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in the user + * namespace @user_ns. + */ +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap) +{ + return file_ns_capable(sk->sk_socket->file, user_ns, cap) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(sk_ns_capable); + +/** + * sk_capable - Socket global capability test + * @sk: Socket to use a capability on or through + * @cap: The global capbility to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in all user + * namespaces. + */ +bool sk_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, &init_user_ns, cap); +} +EXPORT_SYMBOL(sk_capable); + +/** + * sk_net_capable - Network namespace socket capability test + * @sk: Socket to use a capability on or through + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socke was created + * and the current process has the capability @cap over the network namespace + * the socket is a member of. + */ +bool sk_net_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); +} +EXPORT_SYMBOL(sk_net_capable); + + +#ifdef CONFIG_MEMCG_KMEM +int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) +{ + struct proto *proto; + int ret = 0; + + mutex_lock(&proto_list_mutex); + list_for_each_entry(proto, &proto_list, node) { + if (proto->init_cgroup) { + ret = proto->init_cgroup(memcg, ss); + if (ret) + goto out; + } + } + + mutex_unlock(&proto_list_mutex); + return ret; +out: + list_for_each_entry_continue_reverse(proto, &proto_list, node) + if (proto->destroy_cgroup) + proto->destroy_cgroup(memcg); + mutex_unlock(&proto_list_mutex); + return ret; +} + +void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) +{ + struct proto *proto; + + mutex_lock(&proto_list_mutex); + list_for_each_entry_reverse(proto, &proto_list, node) + if (proto->destroy_cgroup) + proto->destroy_cgroup(memcg); + mutex_unlock(&proto_list_mutex); +} +#endif + /* * Each address family might have different locking rules, so we have * one slock key per address family: @@ -139,6 +238,11 @@ static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; +#if defined(CONFIG_MEMCG_KMEM) +struct static_key memcg_socket_limit_enabled; +EXPORT_SYMBOL(memcg_socket_limit_enabled); +#endif + /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket @@ -157,8 +261,8 @@ static const char *const af_family_key_strings[AF_MAX+1] = { "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , - "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , - "sk_lock-AF_MAX" + "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , + "sk_lock-AF_NFC" , "sk_lock-AF_VSOCK" , "sk_lock-AF_MAX" }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , @@ -173,8 +277,8 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-27" , "slock-28" , "slock-AF_CAN" , "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , - "slock-AF_IEEE802154", "slock-AF_CAIF" , - "slock-AF_MAX" + "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , + "slock-AF_NFC" , "slock-AF_VSOCK" ,"slock-AF_MAX" }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , @@ -189,8 +293,8 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-27" , "clock-28" , "clock-AF_CAN" , "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , - "clock-AF_IEEE802154", "clock-AF_CAIF" , - "clock-AF_MAX" + "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , + "clock-AF_NFC" , "clock-AF_VSOCK" , "clock-AF_MAX" }; /* @@ -205,24 +309,76 @@ static struct lock_class_key af_callback_keys[AF_MAX]; * not depend upon such differences. */ #define _SK_MEM_PACKETS 256 -#define _SK_MEM_OVERHEAD (sizeof(struct sk_buff) + 256) +#define _SK_MEM_OVERHEAD SKB_TRUESIZE(256) #define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) /* Run time adjustable parameters. */ __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; +EXPORT_SYMBOL(sysctl_wmem_max); __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; +EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; -/* Maximal space eaten by iovec or ancilliary data plus some space */ +/* Maximal space eaten by iovec or ancillary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); -#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP) -int net_cls_subsys_id = -1; -EXPORT_SYMBOL_GPL(net_cls_subsys_id); -#endif +struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL_GPL(memalloc_socks); + +/** + * sk_set_memalloc - sets %SOCK_MEMALLOC + * @sk: socket to set it on + * + * Set %SOCK_MEMALLOC on a socket for access to emergency reserves. + * It's the responsibility of the admin to adjust min_free_kbytes + * to meet the requirements + */ +void sk_set_memalloc(struct sock *sk) +{ + sock_set_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation |= __GFP_MEMALLOC; + static_key_slow_inc(&memalloc_socks); +} +EXPORT_SYMBOL_GPL(sk_set_memalloc); + +void sk_clear_memalloc(struct sock *sk) +{ + sock_reset_flag(sk, SOCK_MEMALLOC); + sk->sk_allocation &= ~__GFP_MEMALLOC; + static_key_slow_dec(&memalloc_socks); + + /* + * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward + * progress of swapping. However, if SOCK_MEMALLOC is cleared while + * it has rmem allocations there is a risk that the user of the + * socket cannot make forward progress due to exceeding the rmem + * limits. By rights, sk_clear_memalloc() should only be called + * on sockets being torn down but warn and reset the accounting if + * that assumption breaks. + */ + if (WARN_ON(sk->sk_forward_alloc)) + sk_mem_reclaim(sk); +} +EXPORT_SYMBOL_GPL(sk_clear_memalloc); + +int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) +{ + int ret; + unsigned long pflags = current->flags; + + /* these should have been dropped before queueing */ + BUG_ON(!sock_flag(sk, SOCK_MEMALLOC)); + + current->flags |= PF_MEMALLOC; + ret = sk->sk_backlog_rcv(sk, skb); + tsk_restore_flags(current, pflags, PF_MEMALLOC); + + return ret; +} +EXPORT_SYMBOL(__sk_backlog_rcv); static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -241,9 +397,8 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) *timeo_p = 0; if (warned < 10 && net_ratelimit()) { warned++; - printk(KERN_INFO "sock_set_timeout: `%s' (pid %d) " - "tries to set negative timeout\n", - current->comm, task_pid_nr(current)); + pr_info("%s: `%s' (pid %d) tries to set negative timeout\n", + __func__, current->comm, task_pid_nr(current)); } return 0; } @@ -261,20 +416,20 @@ static void sock_warn_obsolete_bsdism(const char *name) static char warncomm[TASK_COMM_LEN]; if (strcmp(warncomm, current->comm) && warned < 5) { strcpy(warncomm, current->comm); - printk(KERN_WARNING "process `%s' is using obsolete " - "%s SO_BSDCOMPAT\n", warncomm, name); + pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n", + warncomm, name); warned++; } } -static void sock_disable_timestamp(struct sock *sk, int flag) +#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) + +static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { - if (sock_flag(sk, flag)) { - sock_reset_flag(sk, flag); - if (!sock_flag(sk, SOCK_TIMESTAMP) && - !sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) { + if (sk->sk_flags & flags) { + sk->sk_flags &= ~flags; + if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP)) net_disable_timestamp(); - } } } @@ -286,12 +441,9 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; - /* Cast sk->rcvbuf to unsigned... It's pointless, but reduces - number of warnings when compiling with -W --ANK - */ - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) { + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) { atomic_inc(&sk->sk_drops); + trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; } @@ -299,7 +451,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (err) return err; - if (!sk_rmem_schedule(sk, skb->truesize)) { + if (!sk_rmem_schedule(sk, skb, skb->truesize)) { atomic_inc(&sk->sk_drops); return -ENOBUFS; } @@ -325,7 +477,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb_len); + sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(sock_queue_rcv_skb); @@ -339,7 +491,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) skb->dev = NULL; - if (sk_rcvqueues_full(sk, skb)) { + if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) { atomic_inc(&sk->sk_drops); goto discard_and_relse; } @@ -356,7 +508,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); - } else if (sk_add_backlog(sk, skb)) { + } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); goto discard_and_relse; @@ -372,19 +524,13 @@ discard_and_relse: } EXPORT_SYMBOL(sk_receive_skb); -void sk_reset_txq(struct sock *sk) -{ - sk_tx_queue_clear(sk); -} -EXPORT_SYMBOL(sk_reset_txq); - struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); - rcu_assign_pointer(sk->sk_dst_cache, NULL); + RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } @@ -407,7 +553,8 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) } EXPORT_SYMBOL(sk_dst_check); -static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) +static int sock_setbindtodevice(struct sock *sk, char __user *optval, + int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES @@ -417,7 +564,7 @@ static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) /* Sorry... */ ret = -EPERM; - if (!capable(CAP_NET_RAW)) + if (!ns_capable(net->user_ns, CAP_NET_RAW)) goto out; ret = -EINVAL; @@ -464,6 +611,46 @@ out: return ret; } +static int sock_getbindtodevice(struct sock *sk, char __user *optval, + int __user *optlen, int len) +{ + int ret = -ENOPROTOOPT; +#ifdef CONFIG_NETDEVICES + struct net *net = sock_net(sk); + char devname[IFNAMSIZ]; + + if (sk->sk_bound_dev_if == 0) { + len = 0; + goto zero; + } + + ret = -EINVAL; + if (len < IFNAMSIZ) + goto out; + + ret = netdev_get_name(net, devname, sk->sk_bound_dev_if); + if (ret) + goto out; + + len = strlen(devname) + 1; + + ret = -EFAULT; + if (copy_to_user(optval, devname, len)) + goto out; + +zero: + ret = -EFAULT; + if (put_user(len, optlen)) + goto out; + + ret = 0; + +out: +#endif + + return ret; +} + static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) { if (valbool) @@ -491,7 +678,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, */ if (optname == SO_BINDTODEVICE) - return sock_bindtodevice(sk, optval, optlen); + return sock_setbindtodevice(sk, optval, optlen); if (optlen < sizeof(int)) return -EINVAL; @@ -511,7 +698,10 @@ int sock_setsockopt(struct socket *sock, int level, int optname, sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: - sk->sk_reuse = valbool; + sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); + break; + case SO_REUSEPORT: + sk->sk_reuseport = valbool; break; case SO_TYPE: case SO_PROTOCOL: @@ -527,23 +717,15 @@ int sock_setsockopt(struct socket *sock, int level, int optname, break; case SO_SNDBUF: /* Don't error on this BSD doesn't and if you think - about it this is right. Otherwise apps have to - play 'guess the biggest size' games. RCVBUF/SNDBUF - are treated in BSD as hints */ - - if (val > sysctl_wmem_max) - val = sysctl_wmem_max; + * about it this is right. Otherwise apps have to + * play 'guess the biggest size' games. RCVBUF/SNDBUF + * are treated in BSD as hints + */ + val = min_t(u32, val, sysctl_wmem_max); set_sndbuf: sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - if ((val * 2) < SOCK_MIN_SNDBUF) - sk->sk_sndbuf = SOCK_MIN_SNDBUF; - else - sk->sk_sndbuf = val * 2; - - /* - * Wake up sending tasks if we - * upped the value. - */ + sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF); + /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -556,12 +738,11 @@ set_sndbuf: case SO_RCVBUF: /* Don't error on this BSD doesn't and if you think - about it this is right. Otherwise apps have to - play 'guess the biggest size' games. RCVBUF/SNDBUF - are treated in BSD as hints */ - - if (val > sysctl_rmem_max) - val = sysctl_rmem_max; + * about it this is right. Otherwise apps have to + * play 'guess the biggest size' games. RCVBUF/SNDBUF + * are treated in BSD as hints + */ + val = min_t(u32, val, sysctl_rmem_max); set_rcvbuf: sk->sk_userlocks |= SOCK_RCVBUF_LOCK; /* @@ -579,10 +760,7 @@ set_rcvbuf: * returning the value we actually used in getsockopt * is the most desirable behavior. */ - if ((val * 2) < SOCK_MIN_RCVBUF) - sk->sk_rcvbuf = SOCK_MIN_RCVBUF; - else - sk->sk_rcvbuf = val * 2; + sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF); break; case SO_RCVBUFFORCE: @@ -594,7 +772,8 @@ set_rcvbuf: case SO_KEEPALIVE: #ifdef CONFIG_INET - if (sk->sk_protocol == IPPROTO_TCP) + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) tcp_set_keepalive(sk, valbool); #endif sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); @@ -605,11 +784,12 @@ set_rcvbuf: break; case SO_NO_CHECK: - sk->sk_no_check = valbool; + sk->sk_no_check_tx = valbool; break; case SO_PRIORITY: - if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN)) + if ((val >= 0 && val <= 6) || + ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) sk->sk_priority = val; else ret = -EPERM; @@ -679,7 +859,7 @@ set_rcvbuf: SOCK_TIMESTAMPING_RX_SOFTWARE); else sock_disable_timestamp(sk, - SOCK_TIMESTAMPING_RX_SOFTWARE); + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE, val & SOF_TIMESTAMPING_SOFTWARE); sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE, @@ -719,6 +899,13 @@ set_rcvbuf: ret = sk_detach_filter(sk); break; + case SO_LOCK_FILTER: + if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) + ret = -EPERM; + else + sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); + break; + case SO_PASSSEC: if (valbool) set_bit(SOCK_PASSSEC, &sock->flags); @@ -726,7 +913,7 @@ set_rcvbuf: clear_bit(SOCK_PASSSEC, &sock->flags); break; case SO_MARK: - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) ret = -EPERM; else sk->sk_mark = val; @@ -735,11 +922,48 @@ set_rcvbuf: /* We implement the SO_SNDLOWAT etc to not be settable (1003.1g 5.3) */ case SO_RXQ_OVFL: - if (valbool) - sock_set_flag(sk, SOCK_RXQ_OVFL); + sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool); + break; + + case SO_WIFI_STATUS: + sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); + break; + + case SO_PEEK_OFF: + if (sock->ops->set_peek_off) + ret = sock->ops->set_peek_off(sk, val); else - sock_reset_flag(sk, SOCK_RXQ_OVFL); + ret = -EOPNOTSUPP; break; + + case SO_NOFCS: + sock_valbool_flag(sk, SOCK_NOFCS, valbool); + break; + + case SO_SELECT_ERR_QUEUE: + sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); + break; + +#ifdef CONFIG_NET_RX_BUSY_POLL + case SO_BUSY_POLL: + /* allow unprivileged users to decrease the value */ + if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) + ret = -EPERM; + else { + if (val < 0) + ret = -EINVAL; + else + sk->sk_ll_usec = val; + } + break; +#endif + + case SO_MAX_PACING_RATE: + sk->sk_max_pacing_rate = val; + sk->sk_pacing_rate = min(sk->sk_pacing_rate, + sk->sk_max_pacing_rate); + break; + default: ret = -ENOPROTOOPT; break; @@ -750,19 +974,18 @@ set_rcvbuf: EXPORT_SYMBOL(sock_setsockopt); -void cred_to_ucred(struct pid *pid, const struct cred *cred, - struct ucred *ucred) +static void cred_to_ucred(struct pid *pid, const struct cred *cred, + struct ucred *ucred) { ucred->pid = pid_vnr(pid); ucred->uid = ucred->gid = -1; if (cred) { struct user_namespace *current_ns = current_user_ns(); - ucred->uid = user_ns_map_uid(current_ns, cred, cred->euid); - ucred->gid = user_ns_map_gid(current_ns, cred, cred->egid); + ucred->uid = from_kuid_munged(current_ns, cred->euid); + ucred->gid = from_kgid_munged(current_ns, cred->egid); } } -EXPORT_SYMBOL_GPL(cred_to_ucred); int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) @@ -795,7 +1018,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_BROADCAST: - v.val = !!sock_flag(sk, SOCK_BROADCAST); + v.val = sock_flag(sk, SOCK_BROADCAST); break; case SO_SNDBUF: @@ -810,8 +1033,12 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_reuse; break; + case SO_REUSEPORT: + v.val = sk->sk_reuseport; + break; + case SO_KEEPALIVE: - v.val = !!sock_flag(sk, SOCK_KEEPOPEN); + v.val = sock_flag(sk, SOCK_KEEPOPEN); break; case SO_TYPE: @@ -833,11 +1060,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_OOBINLINE: - v.val = !!sock_flag(sk, SOCK_URGINLINE); + v.val = sock_flag(sk, SOCK_URGINLINE); break; case SO_NO_CHECK: - v.val = sk->sk_no_check; + v.val = sk->sk_no_check_tx; break; case SO_PRIORITY: @@ -846,7 +1073,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_LINGER: lv = sizeof(v.ling); - v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER); + v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); v.ling.l_linger = sk->sk_lingertime / HZ; break; @@ -912,7 +1139,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PASSCRED: - v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0; + v.val = !!test_bit(SOCK_PASSCRED, &sock->flags); break; case SO_PEERCRED: @@ -947,7 +1174,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PASSSEC: - v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0; + v.val = !!test_bit(SOCK_PASSSEC, &sock->flags); break; case SO_PEERSEC: @@ -958,7 +1185,53 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_RXQ_OVFL: - v.val = !!sock_flag(sk, SOCK_RXQ_OVFL); + v.val = sock_flag(sk, SOCK_RXQ_OVFL); + break; + + case SO_WIFI_STATUS: + v.val = sock_flag(sk, SOCK_WIFI_STATUS); + break; + + case SO_PEEK_OFF: + if (!sock->ops->set_peek_off) + return -EOPNOTSUPP; + + v.val = sk->sk_peek_off; + break; + case SO_NOFCS: + v.val = sock_flag(sk, SOCK_NOFCS); + break; + + case SO_BINDTODEVICE: + return sock_getbindtodevice(sk, optval, optlen, len); + + case SO_GET_FILTER: + len = sk_get_filter(sk, (struct sock_filter __user *)optval, len); + if (len < 0) + return len; + + goto lenout; + + case SO_LOCK_FILTER: + v.val = sock_flag(sk, SOCK_FILTER_LOCKED); + break; + + case SO_BPF_EXTENSIONS: + v.val = bpf_tell_extensions(); + break; + + case SO_SELECT_ERR_QUEUE: + v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); + break; + +#ifdef CONFIG_NET_RX_BUSY_POLL + case SO_BUSY_POLL: + v.val = sk->sk_ll_usec; + break; +#endif + + case SO_MAX_PACING_RATE: + v.val = sk->sk_max_pacing_rate; break; default: @@ -992,23 +1265,42 @@ static inline void sock_lock_init(struct sock *sk) /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, * even temporarly, because of RCU lookups. sk_node should also be left as is. + * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) { #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif - BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) != - sizeof(osk->sk_node) + sizeof(osk->sk_refcnt) + - sizeof(osk->sk_tx_queue_mapping)); - memcpy(&nsk->sk_copy_start, &osk->sk_copy_start, - osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start)); + memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); + + memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, + osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); + #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); #endif } +void sk_prot_clear_portaddr_nulls(struct sock *sk, int size) +{ + unsigned long nulls1, nulls2; + + nulls1 = offsetof(struct sock, __sk_common.skc_node.next); + nulls2 = offsetof(struct sock, __sk_common.skc_portaddr_node.next); + if (nulls1 > nulls2) + swap(nulls1, nulls2); + + if (nulls1 != 0) + memset((char *)sk, 0, nulls1); + memset((char *)sk + nulls1 + sizeof(void *), 0, + nulls2 - nulls1 - sizeof(void *)); + memset((char *)sk + nulls2 + sizeof(void *), 0, + size - nulls2 - sizeof(void *)); +} +EXPORT_SYMBOL(sk_prot_clear_portaddr_nulls); + static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, int family) { @@ -1021,19 +1313,12 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, if (!sk) return sk; if (priority & __GFP_ZERO) { - /* - * caches using SLAB_DESTROY_BY_RCU should let - * sk_node.next un-modified. Special care is taken - * when initializing object to zero. - */ - if (offsetof(struct sock, sk_node.next) != 0) - memset(sk, 0, offsetof(struct sock, sk_node.next)); - memset(&sk->sk_node.pprev, 0, - prot->obj_size - offsetof(struct sock, - sk_node.pprev)); + if (prot->clear_sk) + prot->clear_sk(sk, prot->obj_size); + else + sk_prot_clear_nulls(sk, prot->obj_size); } - } - else + } else sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { @@ -1075,18 +1360,15 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) module_put(owner); } -#ifdef CONFIG_CGROUPS -void sock_update_classid(struct sock *sk) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) +void sock_update_netprioidx(struct sock *sk) { - u32 classid; + if (in_interrupt()) + return; - rcu_read_lock(); /* doing current task, which cannot vanish. */ - classid = task_cls_classid(current); - rcu_read_unlock(); - if (classid && classid != sk->sk_classid) - sk->sk_classid = classid; + sk->sk_cgrp_prioidx = task_netprioidx(current); } -EXPORT_SYMBOL(sock_update_classid); +EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif /** @@ -1114,6 +1396,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, atomic_set(&sk->sk_wmem_alloc, 1); sock_update_classid(sk); + sock_update_netprioidx(sk); } return sk; @@ -1131,15 +1414,14 @@ static void __sk_free(struct sock *sk) atomic_read(&sk->sk_wmem_alloc) == 0); if (filter) { sk_filter_uncharge(sk, filter); - rcu_assign_pointer(sk->sk_filter, NULL); + RCU_INIT_POINTER(sk->sk_filter, NULL); } - sock_disable_timestamp(sk, SOCK_TIMESTAMP); - sock_disable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); + sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); if (atomic_read(&sk->sk_omem_alloc)) - printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n", - __func__, atomic_read(&sk->sk_omem_alloc)); + pr_debug("%s: optmem leakage (%d bytes) detected\n", + __func__, atomic_read(&sk->sk_omem_alloc)); if (sk->sk_peer_cred) put_cred(sk->sk_peer_cred); @@ -1151,7 +1433,7 @@ static void __sk_free(struct sock *sk) void sk_free(struct sock *sk) { /* - * We substract one from sk_wmem_alloc and can know if + * We subtract one from sk_wmem_alloc and can know if * some packets are still in some tx queue. * If not null, sock_wfree() will call __sk_free(sk) later */ @@ -1161,10 +1443,10 @@ void sk_free(struct sock *sk) EXPORT_SYMBOL(sk_free); /* - * Last sock_put should drop referrence to sk->sk_net. It has already - * been dropped in sk_change_net. Taking referrence to stopping namespace + * Last sock_put should drop reference to sk->sk_net. It has already + * been dropped in sk_change_net. Taking reference to stopping namespace * is not an option. - * Take referrence to a socket to remove it from hash _alive_ and after that + * Take reference to a socket to remove it from hash _alive_ and after that * destroy it in the context of init_net. */ void sk_release_kernel(struct sock *sk) @@ -1180,7 +1462,20 @@ void sk_release_kernel(struct sock *sk) } EXPORT_SYMBOL(sk_release_kernel); -struct sock *sk_clone(const struct sock *sk, const gfp_t priority) +static void sk_update_clone(const struct sock *sk, struct sock *newsk) +{ + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) + sock_update_memcg(newsk); +} + +/** + * sk_clone_lock - clone a socket, and lock its clone + * @sk: the socket to clone + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * + * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) + */ +struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct sock *newsk; @@ -1233,6 +1528,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) /* It is still raw copy of parent, so invalidate * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; + bh_unlock_sock(newsk); sk_free(newsk); newsk = NULL; goto out; @@ -1262,17 +1558,18 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) sk_set_socket(newsk, NULL); newsk->sk_wq = NULL; + sk_update_clone(sk, newsk); + if (newsk->sk_prot->sockets_allocated) - percpu_counter_inc(newsk->sk_prot->sockets_allocated); + sk_sockets_allocated_inc(newsk); - if (sock_flag(newsk, SOCK_TIMESTAMP) || - sock_flag(newsk, SOCK_TIMESTAMPING_RX_SOFTWARE)) + if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); } out: return newsk; } -EXPORT_SYMBOL_GPL(sk_clone); +EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { @@ -1287,24 +1584,12 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = dst->dev->gso_max_size; + sk->sk_gso_max_segs = dst->dev->gso_max_segs; } } } EXPORT_SYMBOL_GPL(sk_setup_caps); -void __init sk_init(void) -{ - if (totalram_pages <= 4096) { - sysctl_wmem_max = 32767; - sysctl_rmem_max = 32767; - sysctl_wmem_default = 32767; - sysctl_rmem_default = 32767; - } else if (totalram_pages >= 131072) { - sysctl_wmem_max = 131071; - sysctl_rmem_max = 131071; - } -} - /* * Simple resource managers for sockets. */ @@ -1336,6 +1621,25 @@ void sock_wfree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_wfree); +void skb_orphan_partial(struct sk_buff *skb) +{ + /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, + * so we do not completely orphan skb, but transfert all + * accounted bytes but one, to avoid unexpected reorders. + */ + if (skb->destructor == sock_wfree +#ifdef CONFIG_INET + || skb->destructor == tcp_wfree +#endif + ) { + atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc); + skb->truesize = 1; + } else { + skb_orphan(skb); + } +} +EXPORT_SYMBOL(skb_orphan_partial); + /* * Read buffer destructor automatically called from kfree_skb. */ @@ -1349,13 +1653,25 @@ void sock_rfree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_rfree); +void sock_edemux(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; -int sock_i_uid(struct sock *sk) +#ifdef CONFIG_INET + if (sk->sk_state == TCP_TIME_WAIT) + inet_twsk_put(inet_twsk(sk)); + else +#endif + sock_put(sk); +} +EXPORT_SYMBOL(sock_edemux); + +kuid_t sock_i_uid(struct sock *sk) { - int uid; + kuid_t uid; read_lock_bh(&sk->sk_callback_lock); - uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0; + uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : GLOBAL_ROOT_UID; read_unlock_bh(&sk->sk_callback_lock); return uid; } @@ -1390,27 +1706,11 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, EXPORT_SYMBOL(sock_wmalloc); /* - * Allocate a skb from the socket's receive buffer. - */ -struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, - gfp_t priority) -{ - if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { - struct sk_buff *skb = alloc_skb(size, priority); - if (skb) { - skb_set_owner_r(skb, sk); - return skb; - } - } - return NULL; -} - -/* * Allocate a memory block from the socket's option memory buffer. */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) { - if ((unsigned)size <= sysctl_optmem_max && + if ((unsigned int)size <= sysctl_optmem_max && atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { void *mem; /* First do the add, to avoid the race if kmalloc @@ -1470,19 +1770,23 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, - int *errcode) + int *errcode, int max_page_order) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; + unsigned long chunk; gfp_t gfp_mask; long timeo; int err; + int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; + struct page *page; + int i; - gfp_mask = sk->sk_allocation; - if (gfp_mask & __GFP_WAIT) - gfp_mask |= __GFP_REPEAT; + err = -EMSGSIZE; + if (npages > MAX_SKB_FRAGS) + goto failure; timeo = sock_sndtimeo(sk, noblock); - while (1) { + while (!skb) { err = sock_error(sk); if (err != 0) goto failure; @@ -1491,54 +1795,54 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, if (sk->sk_shutdown & SEND_SHUTDOWN) goto failure; - if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { - skb = alloc_skb(header_len, gfp_mask); - if (skb) { - int npages; - int i; - - /* No pages, we're done... */ - if (!data_len) - break; - - npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; - skb->truesize += data_len; - skb_shinfo(skb)->nr_frags = npages; - for (i = 0; i < npages; i++) { - struct page *page; - skb_frag_t *frag; - - page = alloc_pages(sk->sk_allocation, 0); - if (!page) { - err = -ENOBUFS; - skb_shinfo(skb)->nr_frags = i; - kfree_skb(skb); - goto failure; - } - - frag = &skb_shinfo(skb)->frags[i]; - frag->page = page; - frag->page_offset = 0; - frag->size = (data_len >= PAGE_SIZE ? - PAGE_SIZE : - data_len); - data_len -= PAGE_SIZE; - } + if (atomic_read(&sk->sk_wmem_alloc) >= sk->sk_sndbuf) { + set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + err = -EAGAIN; + if (!timeo) + goto failure; + if (signal_pending(current)) + goto interrupted; + timeo = sock_wait_for_wmem(sk, timeo); + continue; + } - /* Full success... */ - break; - } - err = -ENOBUFS; + err = -ENOBUFS; + gfp_mask = sk->sk_allocation; + if (gfp_mask & __GFP_WAIT) + gfp_mask |= __GFP_REPEAT; + + skb = alloc_skb(header_len, gfp_mask); + if (!skb) goto failure; + + skb->truesize += data_len; + + for (i = 0; npages > 0; i++) { + int order = max_page_order; + + while (order) { + if (npages >= 1 << order) { + page = alloc_pages(sk->sk_allocation | + __GFP_COMP | + __GFP_NOWARN | + __GFP_NORETRY, + order); + if (page) + goto fill_page; + } + order--; + } + page = alloc_page(sk->sk_allocation); + if (!page) + goto failure; +fill_page: + chunk = min_t(unsigned long, data_len, + PAGE_SIZE << order); + skb_fill_page_desc(skb, i, page, 0, chunk); + data_len -= chunk; + npages -= 1 << order; } - set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - err = -EAGAIN; - if (!timeo) - goto failure; - if (signal_pending(current)) - goto interrupted; - timeo = sock_wait_for_wmem(sk, timeo); } skb_set_owner_w(skb, sk); @@ -1547,6 +1851,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, interrupted: err = sock_intr_errno(timeo); failure: + kfree_skb(skb); *errcode = err; return NULL; } @@ -1555,10 +1860,66 @@ EXPORT_SYMBOL(sock_alloc_send_pskb); struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode) { - return sock_alloc_send_pskb(sk, size, 0, noblock, errcode); + return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); } EXPORT_SYMBOL(sock_alloc_send_skb); +/* On 32bit arches, an skb frag is limited to 2^15 */ +#define SKB_FRAG_PAGE_ORDER get_order(32768) + +/** + * skb_page_frag_refill - check that a page_frag contains enough room + * @sz: minimum size of the fragment we want to get + * @pfrag: pointer to page_frag + * @prio: priority for memory allocation + * + * Note: While this allocator tries to use high order pages, there is + * no guarantee that allocations succeed. Therefore, @sz MUST be + * less or equal than PAGE_SIZE. + */ +bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) +{ + int order; + + if (pfrag->page) { + if (atomic_read(&pfrag->page->_count) == 1) { + pfrag->offset = 0; + return true; + } + if (pfrag->offset + sz <= pfrag->size) + return true; + put_page(pfrag->page); + } + + order = SKB_FRAG_PAGE_ORDER; + do { + gfp_t gfp = prio; + + if (order) + gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; + pfrag->page = alloc_pages(gfp, order); + if (likely(pfrag->page)) { + pfrag->offset = 0; + pfrag->size = PAGE_SIZE << order; + return true; + } + } while (--order >= 0); + + return false; +} +EXPORT_SYMBOL(skb_page_frag_refill); + +bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) +{ + if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation))) + return true; + + sk_enter_memory_pressure(sk); + sk_stream_moderate_sndbuf(sk); + return false; +} +EXPORT_SYMBOL(sk_page_frag_refill); + static void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) @@ -1590,6 +1951,7 @@ static void __release_sock(struct sock *sk) do { struct sk_buff *next = skb->next; + prefetch(next); WARN_ON_ONCE(skb_dst_is_noref(skb)); skb->next = NULL; sk_backlog_rcv(sk, skb); @@ -1654,30 +2016,34 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) struct proto *prot = sk->sk_prot; int amt = sk_mem_pages(size); long allocated; + int parent_status = UNDER_LIMIT; sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - allocated = atomic_long_add_return(amt, prot->memory_allocated); + + allocated = sk_memory_allocated_add(sk, amt, &parent_status); /* Under limit. */ - if (allocated <= prot->sysctl_mem[0]) { - if (prot->memory_pressure && *prot->memory_pressure) - *prot->memory_pressure = 0; + if (parent_status == UNDER_LIMIT && + allocated <= sk_prot_mem_limits(sk, 0)) { + sk_leave_memory_pressure(sk); return 1; } - /* Under pressure. */ - if (allocated > prot->sysctl_mem[1]) - if (prot->enter_memory_pressure) - prot->enter_memory_pressure(sk); + /* Under pressure. (we or our parents) */ + if ((parent_status > SOFT_LIMIT) || + allocated > sk_prot_mem_limits(sk, 1)) + sk_enter_memory_pressure(sk); - /* Over hard limit. */ - if (allocated > prot->sysctl_mem[2]) + /* Over hard limit (we or our parents) */ + if ((parent_status == OVER_LIMIT) || + (allocated > sk_prot_mem_limits(sk, 2))) goto suppress_allocation; /* guarantee minimum buffer size under pressure */ if (kind == SK_MEM_RECV) { if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0]) return 1; + } else { /* SK_MEM_SEND */ if (sk->sk_type == SOCK_STREAM) { if (sk->sk_wmem_queued < prot->sysctl_wmem[0]) @@ -1687,13 +2053,13 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) return 1; } - if (prot->memory_pressure) { + if (sk_has_memory_pressure(sk)) { int alloc; - if (!*prot->memory_pressure) + if (!sk_under_memory_pressure(sk)) return 1; - alloc = percpu_counter_read_positive(prot->sockets_allocated); - if (prot->sysctl_mem[2] > alloc * + alloc = sk_sockets_allocated_read_positive(sk); + if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + atomic_read(&sk->sk_rmem_alloc) + sk->sk_forward_alloc)) @@ -1712,9 +2078,13 @@ suppress_allocation: return 1; } + trace_sock_exceed_buf_limit(sk, prot, allocated); + /* Alas. Undo changes. */ sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM; - atomic_long_sub(amt, prot->memory_allocated); + + sk_memory_allocated_sub(sk, amt); + return 0; } EXPORT_SYMBOL(__sk_mem_schedule); @@ -1725,15 +2095,13 @@ EXPORT_SYMBOL(__sk_mem_schedule); */ void __sk_mem_reclaim(struct sock *sk) { - struct proto *prot = sk->sk_prot; - - atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, - prot->memory_allocated); + sk_memory_allocated_sub(sk, + sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT); sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1; - if (prot->memory_pressure && *prot->memory_pressure && - (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0])) - *prot->memory_pressure = 0; + if (sk_under_memory_pressure(sk) && + (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) + sk_leave_memory_pressure(sk); } EXPORT_SYMBOL(__sk_mem_reclaim); @@ -1877,14 +2245,14 @@ static void sock_def_error_report(struct sock *sk) rcu_read_unlock(); } -static void sock_def_readable(struct sock *sk, int len) +static void sock_def_readable(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (wq_has_sleeper(wq)) - wake_up_interruptible_sync_poll(&wq->wait, POLLIN | + wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI | POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); @@ -1936,7 +2304,7 @@ EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { - if (timer_pending(timer) && del_timer(timer)) + if (del_timer(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer); @@ -1981,8 +2349,9 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_error_report = sock_def_error_report; sk->sk_destruct = sock_def_destruct; - sk->sk_sndmsg_page = NULL; - sk->sk_sndmsg_off = 0; + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; + sk->sk_peek_off = -1; sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; @@ -1993,6 +2362,13 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_stamp = ktime_set(-1L, 0); +#ifdef CONFIG_NET_RX_BUSY_POLL + sk->sk_napi_id = 0; + sk->sk_ll_usec = sysctl_net_busy_read; +#endif + + sk->sk_max_pacing_rate = ~0U; + sk->sk_pacing_rate = ~0U; /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) @@ -2029,7 +2405,14 @@ void release_sock(struct sock *sk) spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); - sk->sk_lock.owned = 0; + + /* Warning : release_cb() might need to release sk ownership, + * ie call sock_release_ownership(sk) before us. + */ + if (sk->sk_prot->release_cb) + sk->sk_prot->release_cb(sk); + + sock_release_ownership(sk); if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); spin_unlock_bh(&sk->sk_lock.slock); @@ -2104,20 +2487,65 @@ EXPORT_SYMBOL(sock_get_timestampns); void sock_enable_timestamp(struct sock *sk, int flag) { if (!sock_flag(sk, flag)) { + unsigned long previous_flags = sk->sk_flags; + sock_set_flag(sk, flag); /* * we just set one of the two flags which require net * time stamping, but time stamping might have been on * already because of the other one */ - if (!sock_flag(sk, - flag == SOCK_TIMESTAMP ? - SOCK_TIMESTAMPING_RX_SOFTWARE : - SOCK_TIMESTAMP)) + if (!(previous_flags & SK_FLAGS_TIMESTAMP)) net_enable_timestamp(); } } +int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, + int level, int type) +{ + struct sock_exterr_skb *serr; + struct sk_buff *skb, *skb2; + int copied, err; + + err = -EAGAIN; + skb = skb_dequeue(&sk->sk_error_queue); + if (skb == NULL) + goto out; + + copied = skb->len; + if (copied > len) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto out_free_skb; + + sock_recv_timestamp(msg, sk, skb); + + serr = SKB_EXT_ERR(skb); + put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee); + + msg->msg_flags |= MSG_ERRQUEUE; + err = copied; + + /* Reset and regenerate socket error */ + spin_lock_bh(&sk->sk_error_queue.lock); + sk->sk_err = 0; + if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { + sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; + spin_unlock_bh(&sk->sk_error_queue.lock); + sk->sk_error_report(sk); + } else + spin_unlock_bh(&sk->sk_error_queue.lock); + +out_free_skb: + kfree_skb(skb); +out: + return err; +} +EXPORT_SYMBOL(sock_recv_errqueue); + /* * Get a socket option on an socket. * @@ -2221,13 +2649,16 @@ void sk_common_release(struct sock *sk) xfrm_sk_free_policy(sk); sk_refcnt_debug_release(sk); + + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + } + sock_put(sk); } EXPORT_SYMBOL(sk_common_release); -static DEFINE_RWLOCK(proto_list_lock); -static LIST_HEAD(proto_list); - #ifdef CONFIG_PROC_FS #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { @@ -2307,7 +2738,7 @@ static void assign_proto_idx(struct proto *prot) prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) { - printk(KERN_ERR "PROTO_INUSE_NR exhausted\n"); + pr_err("PROTO_INUSE_NR exhausted\n"); return; } @@ -2337,8 +2768,8 @@ int proto_register(struct proto *prot, int alloc_slab) NULL); if (prot->slab == NULL) { - printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n", - prot->name); + pr_crit("%s: Can't create sock SLAB cache!\n", + prot->name); goto out; } @@ -2352,8 +2783,8 @@ int proto_register(struct proto *prot, int alloc_slab) SLAB_HWCACHE_ALIGN, NULL); if (prot->rsk_prot->slab == NULL) { - printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n", - prot->name); + pr_crit("%s: Can't create request sock SLAB cache!\n", + prot->name); goto out_free_request_sock_slab_name; } } @@ -2376,10 +2807,10 @@ int proto_register(struct proto *prot, int alloc_slab) } } - write_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); list_add(&prot->node, &proto_list); assign_proto_idx(prot); - write_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); return 0; out_free_timewait_sock_slab_name: @@ -2402,10 +2833,10 @@ EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) { - write_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); release_proto_idx(prot); list_del(&prot->node); - write_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); if (prot->slab != NULL) { kmem_cache_destroy(prot->slab); @@ -2428,9 +2859,9 @@ EXPORT_SYMBOL(proto_unregister); #ifdef CONFIG_PROC_FS static void *proto_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(proto_list_lock) + __acquires(proto_list_mutex) { - read_lock(&proto_list_lock); + mutex_lock(&proto_list_mutex); return seq_list_start_head(&proto_list, *pos); } @@ -2440,25 +2871,36 @@ static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void proto_seq_stop(struct seq_file *seq, void *v) - __releases(proto_list_lock) + __releases(proto_list_mutex) { - read_unlock(&proto_list_lock); + mutex_unlock(&proto_list_mutex); } static char proto_method_implemented(const void *method) { return method == NULL ? 'n' : 'y'; } +static long sock_prot_memory_allocated(struct proto *proto) +{ + return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; +} + +static char *sock_prot_memory_pressure(struct proto *proto) +{ + return proto->memory_pressure != NULL ? + proto_memory_pressure(proto) ? "yes" : "no" : "NI"; +} static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { + seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, sock_prot_inuse_get(seq_file_net(seq), proto), - proto->memory_allocated != NULL ? atomic_long_read(proto->memory_allocated) : -1L, - proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI", + sock_prot_memory_allocated(proto), + sock_prot_memory_pressure(proto), proto->max_header, proto->slab == NULL ? "no" : "yes", module_name(proto->owner), @@ -2524,7 +2966,7 @@ static const struct file_operations proto_seq_fops = { static __net_init int proto_init_net(struct net *net) { - if (!proc_net_fops_create(net, "protocols", S_IRUGO, &proto_seq_fops)) + if (!proc_create("protocols", S_IRUGO, net->proc_net, &proto_seq_fops)) return -ENOMEM; return 0; @@ -2532,7 +2974,7 @@ static __net_init int proto_init_net(struct net *net) static __net_exit void proto_exit_net(struct net *net) { - proc_net_remove(net, "protocols"); + remove_proc_entry("protocols", net->proc_net); } diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c new file mode 100644 index 00000000000..a4216a4c957 --- /dev/null +++ b/net/core/sock_diag.c @@ -0,0 +1,231 @@ +#include <linux/mutex.h> +#include <linux/socket.h> +#include <linux/skbuff.h> +#include <net/netlink.h> +#include <net/net_namespace.h> +#include <linux/module.h> +#include <net/sock.h> + +#include <linux/inet_diag.h> +#include <linux/sock_diag.h> + +static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; +static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); +static DEFINE_MUTEX(sock_diag_table_mutex); + +int sock_diag_check_cookie(void *sk, __u32 *cookie) +{ + if ((cookie[0] != INET_DIAG_NOCOOKIE || + cookie[1] != INET_DIAG_NOCOOKIE) && + ((u32)(unsigned long)sk != cookie[0] || + (u32)((((unsigned long)sk) >> 31) >> 1) != cookie[1])) + return -ESTALE; + else + return 0; +} +EXPORT_SYMBOL_GPL(sock_diag_check_cookie); + +void sock_diag_save_cookie(void *sk, __u32 *cookie) +{ + cookie[0] = (u32)(unsigned long)sk; + cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1); +} +EXPORT_SYMBOL_GPL(sock_diag_save_cookie); + +int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) +{ + u32 mem[SK_MEMINFO_VARS]; + + mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); + mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf; + mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); + mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf; + mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; + mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; + mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); + mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + + return nla_put(skb, attrtype, sizeof(mem), &mem); +} +EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); + +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, + struct sk_buff *skb, int attrtype) +{ + struct sock_fprog_kern *fprog; + struct sk_filter *filter; + struct nlattr *attr; + unsigned int flen; + int err = 0; + + if (!may_report_filterinfo) { + nla_reserve(skb, attrtype, 0); + return 0; + } + + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); + if (!filter) + goto out; + + fprog = filter->orig_prog; + flen = sk_filter_proglen(fprog); + + attr = nla_reserve(skb, attrtype, flen); + if (attr == NULL) { + err = -EMSGSIZE; + goto out; + } + + memcpy(nla_data(attr), fprog->filter, flen); +out: + rcu_read_unlock(); + return err; +} +EXPORT_SYMBOL(sock_diag_put_filterinfo); + +void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) +{ + mutex_lock(&sock_diag_table_mutex); + inet_rcv_compat = fn; + mutex_unlock(&sock_diag_table_mutex); +} +EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat); + +void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) +{ + mutex_lock(&sock_diag_table_mutex); + inet_rcv_compat = NULL; + mutex_unlock(&sock_diag_table_mutex); +} +EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); + +int sock_diag_register(const struct sock_diag_handler *hndl) +{ + int err = 0; + + if (hndl->family >= AF_MAX) + return -EINVAL; + + mutex_lock(&sock_diag_table_mutex); + if (sock_diag_handlers[hndl->family]) + err = -EBUSY; + else + sock_diag_handlers[hndl->family] = hndl; + mutex_unlock(&sock_diag_table_mutex); + + return err; +} +EXPORT_SYMBOL_GPL(sock_diag_register); + +void sock_diag_unregister(const struct sock_diag_handler *hnld) +{ + int family = hnld->family; + + if (family >= AF_MAX) + return; + + mutex_lock(&sock_diag_table_mutex); + BUG_ON(sock_diag_handlers[family] != hnld); + sock_diag_handlers[family] = NULL; + mutex_unlock(&sock_diag_table_mutex); +} +EXPORT_SYMBOL_GPL(sock_diag_unregister); + +static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + int err; + struct sock_diag_req *req = nlmsg_data(nlh); + const struct sock_diag_handler *hndl; + + if (nlmsg_len(nlh) < sizeof(*req)) + return -EINVAL; + + if (req->sdiag_family >= AF_MAX) + return -EINVAL; + + if (sock_diag_handlers[req->sdiag_family] == NULL) + request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, req->sdiag_family); + + mutex_lock(&sock_diag_table_mutex); + hndl = sock_diag_handlers[req->sdiag_family]; + if (hndl == NULL) + err = -ENOENT; + else + err = hndl->dump(skb, nlh); + mutex_unlock(&sock_diag_table_mutex); + + return err; +} + +static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + int ret; + + switch (nlh->nlmsg_type) { + case TCPDIAG_GETSOCK: + case DCCPDIAG_GETSOCK: + if (inet_rcv_compat == NULL) + request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, AF_INET); + + mutex_lock(&sock_diag_table_mutex); + if (inet_rcv_compat != NULL) + ret = inet_rcv_compat(skb, nlh); + else + ret = -EOPNOTSUPP; + mutex_unlock(&sock_diag_table_mutex); + + return ret; + case SOCK_DIAG_BY_FAMILY: + return __sock_diag_rcv_msg(skb, nlh); + default: + return -EINVAL; + } +} + +static DEFINE_MUTEX(sock_diag_mutex); + +static void sock_diag_rcv(struct sk_buff *skb) +{ + mutex_lock(&sock_diag_mutex); + netlink_rcv_skb(skb, &sock_diag_rcv_msg); + mutex_unlock(&sock_diag_mutex); +} + +static int __net_init diag_net_init(struct net *net) +{ + struct netlink_kernel_cfg cfg = { + .input = sock_diag_rcv, + }; + + net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, &cfg); + return net->diag_nlsk == NULL ? -ENOMEM : 0; +} + +static void __net_exit diag_net_exit(struct net *net) +{ + netlink_kernel_release(net->diag_nlsk); + net->diag_nlsk = NULL; +} + +static struct pernet_operations diag_net_ops = { + .init = diag_net_init, + .exit = diag_net_exit, +}; + +static int __init sock_diag_init(void) +{ + return register_pernet_subsys(&diag_net_ops); +} + +static void __exit sock_diag_exit(void) +{ + unregister_pernet_subsys(&diag_net_ops); +} + +module_init(sock_diag_init); +module_exit(sock_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_SOCK_DIAG); diff --git a/net/core/stream.c b/net/core/stream.c index f5df85dcd20..301c05f2606 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -30,7 +30,7 @@ void sk_stream_write_space(struct sock *sk) struct socket *sock = sk->sk_socket; struct socket_wq *wq; - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) { + if (sk_stream_is_writeable(sk) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); @@ -122,7 +122,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) DEFINE_WAIT(wait); if (sk_stream_memory_free(sk)) - current_timeo = vm_wait = (net_random() % (HZ / 5)) + 2; + current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2; while (1) { set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 385b6095fdc..cf9cd13509a 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -14,17 +14,25 @@ #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/kmemleak.h> #include <net/ip.h> #include <net/sock.h> +#include <net/net_ratelimit.h> +#include <net/busy_poll.h> +#include <net/pkt_sched.h> + +static int zero = 0; +static int one = 1; +static int ushort_max = USHRT_MAX; #ifdef CONFIG_RPS -static int rps_sock_flow_sysctl(ctl_table *table, int write, +static int rps_sock_flow_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { unsigned int orig_size, size; int ret, i; - ctl_table tmp = { + struct ctl_table tmp = { .data = &size, .maxlen = sizeof(size), .mode = table->mode @@ -67,8 +75,13 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write, if (sock_table != orig_sock_table) { rcu_assign_pointer(rps_sock_flow_table, sock_table); - synchronize_rcu(); - vfree(orig_sock_table); + if (sock_table) + static_key_slow_inc(&rps_needed); + if (orig_sock_table) { + static_key_slow_dec(&rps_needed); + synchronize_rcu(); + vfree(orig_sock_table); + } } } @@ -78,6 +91,130 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write, } #endif /* CONFIG_RPS */ +#ifdef CONFIG_NET_FLOW_LIMIT +static DEFINE_MUTEX(flow_limit_update_mutex); + +static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + struct sd_flow_limit *cur; + struct softnet_data *sd; + cpumask_var_t mask; + int i, len, ret = 0; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + if (write) { + ret = cpumask_parse_user(buffer, *lenp, mask); + if (ret) + goto done; + + mutex_lock(&flow_limit_update_mutex); + len = sizeof(*cur) + netdev_flow_limit_table_len; + for_each_possible_cpu(i) { + sd = &per_cpu(softnet_data, i); + cur = rcu_dereference_protected(sd->flow_limit, + lockdep_is_held(&flow_limit_update_mutex)); + if (cur && !cpumask_test_cpu(i, mask)) { + RCU_INIT_POINTER(sd->flow_limit, NULL); + synchronize_rcu(); + kfree(cur); + } else if (!cur && cpumask_test_cpu(i, mask)) { + cur = kzalloc_node(len, GFP_KERNEL, + cpu_to_node(i)); + if (!cur) { + /* not unwinding previous changes */ + ret = -ENOMEM; + goto write_unlock; + } + cur->num_buckets = netdev_flow_limit_table_len; + rcu_assign_pointer(sd->flow_limit, cur); + } + } +write_unlock: + mutex_unlock(&flow_limit_update_mutex); + } else { + char kbuf[128]; + + if (*ppos || !*lenp) { + *lenp = 0; + goto done; + } + + cpumask_clear(mask); + rcu_read_lock(); + for_each_possible_cpu(i) { + sd = &per_cpu(softnet_data, i); + if (rcu_dereference(sd->flow_limit)) + cpumask_set_cpu(i, mask); + } + rcu_read_unlock(); + + len = min(sizeof(kbuf) - 1, *lenp); + len = cpumask_scnprintf(kbuf, len, mask); + if (!len) { + *lenp = 0; + goto done; + } + if (len < *lenp) + kbuf[len++] = '\n'; + if (copy_to_user(buffer, kbuf, len)) { + ret = -EFAULT; + goto done; + } + *lenp = len; + *ppos += len; + } + +done: + free_cpumask_var(mask); + return ret; +} + +static int flow_limit_table_len_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + unsigned int old, *ptr; + int ret; + + mutex_lock(&flow_limit_update_mutex); + + ptr = table->data; + old = *ptr; + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (!ret && write && !is_power_of_2(*ptr)) { + *ptr = old; + ret = -EINVAL; + } + + mutex_unlock(&flow_limit_update_mutex); + return ret; +} +#endif /* CONFIG_NET_FLOW_LIMIT */ + +#ifdef CONFIG_NET_SCHED +static int set_default_qdisc(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + char id[IFNAMSIZ]; + struct ctl_table tbl = { + .data = id, + .maxlen = IFNAMSIZ, + }; + int ret; + + qdisc_get_default(id, IFNAMSIZ); + + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) + ret = qdisc_set_default(id); + return ret; +} +#endif + static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { @@ -85,28 +222,32 @@ static struct ctl_table net_core_table[] = { .data = &sysctl_wmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "rmem_max", .data = &sysctl_rmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "wmem_default", .data = &sysctl_wmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "rmem_default", .data = &sysctl_rmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "dev_weight", @@ -122,6 +263,15 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_BPF_JIT + { + .procname = "bpf_jit_enable", + .data = &bpf_jit_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, +#endif { .procname = "netdev_tstamp_prequeue", .data = &netdev_tstamp_prequeue, @@ -158,6 +308,44 @@ static struct ctl_table net_core_table[] = { .proc_handler = rps_sock_flow_sysctl }, #endif +#ifdef CONFIG_NET_FLOW_LIMIT + { + .procname = "flow_limit_cpu_bitmap", + .mode = 0644, + .proc_handler = flow_limit_cpu_sysctl + }, + { + .procname = "flow_limit_table_len", + .data = &netdev_flow_limit_table_len, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = flow_limit_table_len_sysctl + }, +#endif /* CONFIG_NET_FLOW_LIMIT */ +#ifdef CONFIG_NET_RX_BUSY_POLL + { + .procname = "busy_poll", + .data = &sysctl_net_busy_poll, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "busy_read", + .data = &sysctl_net_busy_read, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec + }, +#endif +#ifdef CONFIG_NET_SCHED + { + .procname = "default_qdisc", + .mode = 0644, + .maxlen = IFNAMSIZ, + .proc_handler = set_default_qdisc + }, +#endif #endif /* CONFIG_NET */ { .procname = "netdev_budget", @@ -182,17 +370,13 @@ static struct ctl_table netns_core_table[] = { .data = &init_net.core.sysctl_somaxconn, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .extra1 = &zero, + .extra2 = &ushort_max, + .proc_handler = proc_dointvec_minmax }, { } }; -__net_initdata struct ctl_path net_core_path[] = { - { .procname = "net", }, - { .procname = "core", }, - { }, -}; - static __net_init int sysctl_core_net_init(struct net *net) { struct ctl_table *tbl; @@ -206,10 +390,14 @@ static __net_init int sysctl_core_net_init(struct net *net) goto err_dup; tbl[0].data = &net->core.sysctl_somaxconn; + + /* Don't export any sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) { + tbl[0].procname = NULL; + } } - net->core.sysctl_hdr = register_net_sysctl_table(net, - net_core_path, tbl); + net->core.sysctl_hdr = register_net_sysctl(net, "net/core", tbl); if (net->core.sysctl_hdr == NULL) goto err_reg; @@ -239,10 +427,7 @@ static __net_initdata struct pernet_operations sysctl_core_ops = { static __init int sysctl_core_init(void) { - static struct ctl_table empty[1]; - - register_sysctl_paths(net_core_path, empty); - register_net_sysctl_rotable(net_core_path, net_core_table); + register_net_sysctl(&init_net, "net/core", net_core_table); return register_pernet_subsys(&sysctl_core_ops); } diff --git a/net/core/timestamping.c b/net/core/timestamping.c index b124d28ff1c..6521dfd8b7c 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -21,17 +21,13 @@ #include <linux/phy.h> #include <linux/ptp_classify.h> #include <linux/skbuff.h> - -static struct sock_filter ptp_filter[] = { - PTP_FILTER -}; +#include <linux/export.h> static unsigned int classify(const struct sk_buff *skb) { - if (likely(skb->dev && - skb->dev->phydev && + if (likely(skb->dev && skb->dev->phydev && skb->dev->phydev->drv)) - return sk_run_filter(skb, ptp_filter); + return ptp_classify_raw(skb); else return PTP_CLASS_NONE; } @@ -57,9 +53,15 @@ void skb_clone_tx_timestamp(struct sk_buff *skb) case PTP_CLASS_V2_VLAN: phydev = skb->dev->phydev; if (likely(phydev->drv->txtstamp)) { + if (!atomic_inc_not_zero(&sk->sk_refcnt)) + return; + clone = skb_clone(skb, GFP_ATOMIC); - if (!clone) + if (!clone) { + sock_put(sk); return; + } + clone->sk = sk; phydev->drv->txtstamp(phydev, clone, type); } @@ -68,6 +70,7 @@ void skb_clone_tx_timestamp(struct sk_buff *skb) break; } } +EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp); void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps) @@ -76,16 +79,23 @@ void skb_complete_tx_timestamp(struct sk_buff *skb, struct sock_exterr_skb *serr; int err; - if (!hwtstamps) + if (!hwtstamps) { + sock_put(sk); + kfree_skb(skb); return; + } *skb_hwtstamps(skb) = *hwtstamps; + serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; skb->sk = NULL; + err = sock_queue_err_skb(sk, skb); + + sock_put(sk); if (err) kfree_skb(skb); } @@ -96,11 +106,13 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) struct phy_device *phydev; unsigned int type; - skb_push(skb, ETH_HLEN); + if (skb_headroom(skb) < ETH_HLEN) + return false; + __skb_push(skb, ETH_HLEN); type = classify(skb); - skb_pull(skb, ETH_HLEN); + __skb_pull(skb, ETH_HLEN); switch (type) { case PTP_CLASS_V1_IPV4: @@ -119,8 +131,4 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) return false; } - -void __init skb_timestamping_init(void) -{ - BUG_ON(sk_chk_filter(ptp_filter, ARRAY_SIZE(ptp_filter))); -} +EXPORT_SYMBOL_GPL(skb_defer_rx_timestamp); diff --git a/net/core/tso.c b/net/core/tso.c new file mode 100644 index 00000000000..8c3203c585b --- /dev/null +++ b/net/core/tso.c @@ -0,0 +1,77 @@ +#include <linux/export.h> +#include <net/ip.h> +#include <net/tso.h> + +/* Calculate expected number of TX descriptors */ +int tso_count_descs(struct sk_buff *skb) +{ + /* The Marvell Way */ + return skb_shinfo(skb)->gso_segs * 2 + skb_shinfo(skb)->nr_frags; +} +EXPORT_SYMBOL(tso_count_descs); + +void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso, + int size, bool is_last) +{ + struct iphdr *iph; + struct tcphdr *tcph; + int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + int mac_hdr_len = skb_network_offset(skb); + + memcpy(hdr, skb->data, hdr_len); + iph = (struct iphdr *)(hdr + mac_hdr_len); + iph->id = htons(tso->ip_id); + iph->tot_len = htons(size + hdr_len - mac_hdr_len); + tcph = (struct tcphdr *)(hdr + skb_transport_offset(skb)); + tcph->seq = htonl(tso->tcp_seq); + tso->ip_id++; + + if (!is_last) { + /* Clear all special flags for not last packet */ + tcph->psh = 0; + tcph->fin = 0; + tcph->rst = 0; + } +} +EXPORT_SYMBOL(tso_build_hdr); + +void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size) +{ + tso->tcp_seq += size; + tso->size -= size; + tso->data += size; + + if ((tso->size == 0) && + (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx]; + + /* Move to next segment */ + tso->size = frag->size; + tso->data = page_address(frag->page.p) + frag->page_offset; + tso->next_frag_idx++; + } +} +EXPORT_SYMBOL(tso_build_data); + +void tso_start(struct sk_buff *skb, struct tso_t *tso) +{ + int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + + tso->ip_id = ntohs(ip_hdr(skb)->id); + tso->tcp_seq = ntohl(tcp_hdr(skb)->seq); + tso->next_frag_idx = 0; + + /* Build first data */ + tso->size = skb_headlen(skb) - hdr_len; + tso->data = skb->data + hdr_len; + if ((tso->size == 0) && + (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx]; + + /* Move to next segment */ + tso->size = frag->size; + tso->data = page_address(frag->page.p) + frag->page_offset; + tso->next_frag_idx++; + } +} +EXPORT_SYMBOL(tso_start); diff --git a/net/core/user_dma.c b/net/core/user_dma.c index 25d717ebc92..1b5fefdb819 100644 --- a/net/core/user_dma.c +++ b/net/core/user_dma.c @@ -27,6 +27,7 @@ #include <linux/dmaengine.h> #include <linux/socket.h> +#include <linux/export.h> #include <net/tcp.h> #include <net/netdma.h> @@ -71,14 +72,14 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; WARN_ON(start > offset + len); - end = start + skb_shinfo(skb)->frags[i].size; + end = start + skb_frag_size(frag); copy = end - offset; if (copy > 0) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - struct page *page = frag->page; + struct page *page = skb_frag_page(frag); if (copy > len) copy = len; diff --git a/net/core/utils.c b/net/core/utils.c index 5fea0ab2190..eed34338736 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/jiffies.h> #include <linux/kernel.h> +#include <linux/ctype.h> #include <linux/inet.h> #include <linux/mm.h> #include <linux/net.h> @@ -27,9 +28,9 @@ #include <linux/ratelimit.h> #include <net/sock.h> +#include <net/net_ratelimit.h> #include <asm/byteorder.h> -#include <asm/system.h> #include <asm/uaccess.h> int net_msg_warn __read_mostly = 1; @@ -58,14 +59,11 @@ __be32 in_aton(const char *str) int i; l = 0; - for (i = 0; i < 4; i++) - { + for (i = 0; i < 4; i++) { l <<= 8; - if (*str != '\0') - { + if (*str != '\0') { val = 0; - while (*str != '\0' && *str != '.' && *str != '\n') - { + while (*str != '\0' && *str != '.' && *str != '\n') { val *= 10; val += *str - '0'; str++; @@ -110,6 +108,18 @@ static inline int xdigit2bin(char c, int delim) return IN6PTON_UNKNOWN; } +/** + * in4_pton - convert an IPv4 address from literal to binary representation + * @src: the start of the IPv4 address string + * @srclen: the length of the string, -1 means strlen(src) + * @dst: the binary (u8[4] array) representation of the IPv4 address + * @delim: the delimiter of the IPv4 address in @src, -1 means no delimiter + * @end: A pointer to the end of the parsed string will be placed here + * + * Return one on success, return zero when any error occurs + * and @end will point to the end of the parsed string. + * + */ int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) @@ -164,6 +174,18 @@ out: } EXPORT_SYMBOL(in4_pton); +/** + * in6_pton - convert an IPv6 address from literal to binary representation + * @src: the start of the IPv6 address string + * @srclen: the length of the string, -1 means strlen(src) + * @dst: the binary (u8[16] array) representation of the IPv6 address + * @delim: the delimiter of the IPv6 address in @src, -1 means no delimiter + * @end: A pointer to the end of the parsed string will be placed here + * + * Return one on success, return zero when any error occurs + * and @end will point to the end of the parsed string. + * + */ int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) @@ -296,3 +318,72 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, csum_unfold(*sum))); } EXPORT_SYMBOL(inet_proto_csum_replace4); + +void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, + const __be32 *from, const __be32 *to, + int pseudohdr) +{ + __be32 diff[] = { + ~from[0], ~from[1], ~from[2], ~from[3], + to[0], to[1], to[2], to[3], + }; + if (skb->ip_summed != CHECKSUM_PARTIAL) { + *sum = csum_fold(csum_partial(diff, sizeof(diff), + ~csum_unfold(*sum))); + if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) + skb->csum = ~csum_partial(diff, sizeof(diff), + ~skb->csum); + } else if (pseudohdr) + *sum = ~csum_fold(csum_partial(diff, sizeof(diff), + csum_unfold(*sum))); +} +EXPORT_SYMBOL(inet_proto_csum_replace16); + +struct __net_random_once_work { + struct work_struct work; + struct static_key *key; +}; + +static void __net_random_once_deferred(struct work_struct *w) +{ + struct __net_random_once_work *work = + container_of(w, struct __net_random_once_work, work); + BUG_ON(!static_key_enabled(work->key)); + static_key_slow_dec(work->key); + kfree(work); +} + +static void __net_random_once_disable_jump(struct static_key *key) +{ + struct __net_random_once_work *w; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (!w) + return; + + INIT_WORK(&w->work, __net_random_once_deferred); + w->key = key; + schedule_work(&w->work); +} + +bool __net_get_random_once(void *buf, int nbytes, bool *done, + struct static_key *once_key) +{ + static DEFINE_SPINLOCK(lock); + unsigned long flags; + + spin_lock_irqsave(&lock, flags); + if (*done) { + spin_unlock_irqrestore(&lock, flags); + return false; + } + + get_random_bytes(buf, nbytes); + *done = true; + spin_unlock_irqrestore(&lock, flags); + + __net_random_once_disable_jump(once_key); + + return true; +} +EXPORT_SYMBOL(__net_get_random_once); |