diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-06-24 16:49:49 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-06-24 16:49:49 -0700 |
commit | e0456717e483bb8a9431b80a5bdc99a928b9b003 (patch) | |
tree | 5eb5add2bafd1f20326d70f5cb3b711d00a40b10 /net/core | |
parent | 98ec21a01896751b673b6c731ca8881daa8b2c6d (diff) | |
parent | 1ea2d020ba477cb7011a7174e8501a9e04a325d4 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Add TX fast path in mac80211, from Johannes Berg.
2) Add TSO/GRO support to ibmveth, from Thomas Falcon
3) Move away from cached routes in ipv6, just like ipv4, from Martin
KaFai Lau.
4) Lots of new rhashtable tests, from Thomas Graf.
5) Run ingress qdisc lockless, from Alexei Starovoitov.
6) Allow servers to fetch TCP packet headers for SYN packets of new
connections, for fingerprinting. From Eric Dumazet.
7) Add mode parameter to pktgen, for testing receive. From Alexei
Starovoitov.
8) Cache access optimizations via simplifications of build_skb(), from
Alexander Duyck.
9) Move page frag allocator under mm/, also from Alexander.
10) Add xmit_more support to hv_netvsc, from KY Srinivasan.
11) Add a counter guard in case we try to perform endless reclassify
loops in the packet scheduler.
12) Extern flow dissector to be programmable and use it in new "Flower"
classifier. From Jiri Pirko.
13) AF_PACKET fanout rollover fixes, performance improvements, and new
statistics. From Willem de Bruijn.
14) Add netdev driver for GENEVE tunnels, from John W Linville.
15) Add ingress netfilter hooks and filtering, from Pablo Neira Ayuso.
16) Fix handling of epoll edge triggers in TCP, from Eric Dumazet.
17) Add an ECN retry fallback for the initial TCP handshake, from Daniel
Borkmann.
18) Add tail call support to BPF, from Alexei Starovoitov.
19) Add several pktgen helper scripts, from Jesper Dangaard Brouer.
20) Add zerocopy support to AF_UNIX, from Hannes Frederic Sowa.
21) Favor even port numbers for allocation to connect() requests, and
odd port numbers for bind(0), in an effort to help avoid
ip_local_port_range exhaustion. From Eric Dumazet.
22) Add Cavium ThunderX driver, from Sunil Goutham.
23) Allow bpf programs to access skb_iif and dev->ifindex SKB metadata,
from Alexei Starovoitov.
24) Add support for T6 chips in cxgb4vf driver, from Hariprasad Shenai.
25) Double TCP Small Queues default to 256K to accomodate situations
like the XEN driver and wireless aggregation. From Wei Liu.
26) Add more entropy inputs to flow dissector, from Tom Herbert.
27) Add CDG congestion control algorithm to TCP, from Kenneth Klette
Jonassen.
28) Convert ipset over to RCU locking, from Jozsef Kadlecsik.
29) Track and act upon link status of ipv4 route nexthops, from Andy
Gospodarek.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1670 commits)
bridge: vlan: flush the dynamically learned entries on port vlan delete
bridge: multicast: add a comment to br_port_state_selection about blocking state
net: inet_diag: export IPV6_V6ONLY sockopt
stmmac: troubleshoot unexpected bits in des0 & des1
net: ipv4 sysctl option to ignore routes when nexthop link is down
net: track link-status of ipv4 nexthops
net: switchdev: ignore unsupported bridge flags
net: Cavium: Fix MAC address setting in shutdown state
drivers: net: xgene: fix for ACPI support without ACPI
ip: report the original address of ICMP messages
net/mlx5e: Prefetch skb data on RX
net/mlx5e: Pop cq outside mlx5e_get_cqe
net/mlx5e: Remove mlx5e_cq.sqrq back-pointer
net/mlx5e: Remove extra spaces
net/mlx5e: Avoid TX CQE generation if more xmit packets expected
net/mlx5e: Avoid redundant dev_kfree_skb() upon NOP completion
net/mlx5e: Remove re-assignment of wq type in mlx5e_enable_rq()
net/mlx5e: Use skb_shinfo(skb)->gso_segs rather than counting them
net/mlx5e: Static mapping of netdev priv resources to/from netdev TX queues
net/mlx4_en: Use HW counters for rx/tx bytes/packets in PF device
...
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 220 | ||||
-rw-r--r-- | net/core/ethtool.c | 13 | ||||
-rw-r--r-- | net/core/filter.c | 261 | ||||
-rw-r--r-- | net/core/flow_dissector.c | 656 | ||||
-rw-r--r-- | net/core/neighbour.c | 16 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 10 | ||||
-rw-r--r-- | net/core/net_namespace.c | 133 | ||||
-rw-r--r-- | net/core/netevent.c | 5 | ||||
-rw-r--r-- | net/core/pktgen.c | 110 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 81 | ||||
-rw-r--r-- | net/core/secure_seq.c | 2 | ||||
-rw-r--r-- | net/core/skbuff.c | 387 | ||||
-rw-r--r-- | net/core/sock.c | 55 | ||||
-rw-r--r-- | net/core/sock_diag.c | 85 | ||||
-rw-r--r-- | net/core/stream.c | 6 | ||||
-rw-r--r-- | net/core/utils.c | 12 |
16 files changed, 1498 insertions, 554 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index aa82f9ab6a36..6778a9999d52 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -135,6 +135,7 @@ #include <linux/if_macvlan.h> #include <linux/errqueue.h> #include <linux/hrtimer.h> +#include <linux/netfilter_ingress.h> #include "net-sysfs.h" @@ -468,10 +469,14 @@ EXPORT_SYMBOL(dev_remove_pack); */ void dev_add_offload(struct packet_offload *po) { - struct list_head *head = &offload_base; + struct packet_offload *elem; spin_lock(&offload_lock); - list_add_rcu(&po->list, head); + list_for_each_entry(elem, &offload_base, list) { + if (po->priority < elem->priority) + break; + } + list_add_rcu(&po->list, elem->list.prev); spin_unlock(&offload_lock); } EXPORT_SYMBOL(dev_add_offload); @@ -1630,7 +1635,7 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) } EXPORT_SYMBOL(call_netdevice_notifiers); -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_INGRESS static struct static_key ingress_needed __read_mostly; void net_inc_ingress_queue(void) @@ -2343,6 +2348,34 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); +/* + * 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, 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; + } + + return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; +} +EXPORT_SYMBOL(__skb_tx_hash); + static void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features = 0; @@ -2901,6 +2934,84 @@ int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(dev_loopback_xmit); +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[skb->sender_cpu - 1]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else + queue_index = map->queues[reciprocal_scale(skb_get_hash(skb), + map->len)]; + 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; + +#ifdef CONFIG_XPS + if (skb->sender_cpu == 0) + skb->sender_cpu = raw_smp_processor_id() + 1; +#endif + + 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); +} + /** * __dev_queue_xmit - transmit a buffer * @skb: buffer to transmit @@ -3513,66 +3624,47 @@ int (*br_fdb_test_addr_hook)(struct net_device *dev, EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif -#ifdef CONFIG_NET_CLS_ACT -/* TODO: Maybe we should just force sch_ingress to be compiled in - * 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 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) -{ - struct net_device *dev = skb->dev; - u32 ttl = G_TC_RTTL(skb->tc_verd); - int result = TC_ACT_OK; - struct Qdisc *q; - - if (unlikely(MAX_RED_LOOP < ttl++)) { - net_warn_ratelimited("Redir loop detected Dropping packet (%d->%d)\n", - skb->skb_iif, dev->ifindex); - return TC_ACT_SHOT; - } - - skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl); - skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); - - q = rcu_dereference(rxq->qdisc); - if (q != &noop_qdisc) { - spin_lock(qdisc_lock(q)); - if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) - result = qdisc_enqueue_root(skb, q); - spin_unlock(qdisc_lock(q)); - } - - return result; -} - static inline struct sk_buff *handle_ing(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { - struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue); +#ifdef CONFIG_NET_CLS_ACT + struct tcf_proto *cl = rcu_dereference_bh(skb->dev->ingress_cl_list); + struct tcf_result cl_res; - if (!rxq || rcu_access_pointer(rxq->qdisc) == &noop_qdisc) + /* If there's at least one ingress present somewhere (so + * we get here via enabled static key), remaining devices + * that are not configured with an ingress qdisc will bail + * out here. + */ + if (!cl) return skb; - if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } - switch (ing_filter(skb, rxq)) { + qdisc_skb_cb(skb)->pkt_len = skb->len; + skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); + qdisc_bstats_update_cpu(cl->q, skb); + + switch (tc_classify(skb, cl, &cl_res)) { + case TC_ACT_OK: + case TC_ACT_RECLASSIFY: + skb->tc_index = TC_H_MIN(cl_res.classid); + break; case TC_ACT_SHOT: + qdisc_qstats_drop_cpu(cl->q); case TC_ACT_STOLEN: + case TC_ACT_QUEUED: kfree_skb(skb); return NULL; + default: + break; } - +#endif /* CONFIG_NET_CLS_ACT */ return skb; } -#endif /** * netdev_rx_handler_register - register receive handler @@ -3645,6 +3737,22 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) } } +static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, + int *ret, struct net_device *orig_dev) +{ +#ifdef CONFIG_NETFILTER_INGRESS + if (nf_hook_ingress_active(skb)) { + if (*pt_prev) { + *ret = deliver_skb(skb, *pt_prev, orig_dev); + *pt_prev = NULL; + } + + return nf_hook_ingress(skb); + } +#endif /* CONFIG_NETFILTER_INGRESS */ + return 0; +} + static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) { struct packet_type *ptype, *pt_prev; @@ -3704,13 +3812,17 @@ another_round: } skip_taps: -#ifdef CONFIG_NET_CLS_ACT +#ifdef CONFIG_NET_INGRESS if (static_key_false(&ingress_needed)) { skb = handle_ing(skb, &pt_prev, &ret, orig_dev); if (!skb) goto unlock; - } + if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) + goto unlock; + } +#endif +#ifdef CONFIG_NET_CLS_ACT skb->tc_verd = 0; ncls: #endif @@ -6313,6 +6425,17 @@ static int netif_alloc_netdev_queues(struct net_device *dev) return 0; } +void netif_tx_stop_all_queues(struct net_device *dev) +{ + unsigned int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + netif_tx_stop_queue(txq); + } +} +EXPORT_SYMBOL(netif_tx_stop_all_queues); + /** * register_netdevice - register a network device * @dev: device to register @@ -6862,6 +6985,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->group = INIT_NETDEV_GROUP; if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; + + nf_hook_ingress_init(dev); + return dev; free_all: diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 1d00b8922902..b495ab1797fa 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -98,7 +98,6 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RXALL_BIT] = "rx-all", [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", [NETIF_F_BUSY_POLL_BIT] = "busy-poll", - [NETIF_F_HW_SWITCH_OFFLOAD_BIT] = "hw-switch-offload", }; static const char @@ -107,6 +106,13 @@ rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = { [ETH_RSS_HASH_XOR_BIT] = "xor", }; +static const char +tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN] = { + [ETHTOOL_ID_UNSPEC] = "Unspec", + [ETHTOOL_RX_COPYBREAK] = "rx-copybreak", + [ETHTOOL_TX_COPYBREAK] = "tx-copybreak", +}; + static int ethtool_get_features(struct net_device *dev, void __user *useraddr) { struct ethtool_gfeatures cmd = { @@ -195,6 +201,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) if (sset == ETH_SS_RSS_HASH_FUNCS) return ARRAY_SIZE(rss_hash_func_strings); + if (sset == ETH_SS_TUNABLES) + return ARRAY_SIZE(tunable_strings); + if (ops->get_sset_count && ops->get_strings) return ops->get_sset_count(dev, sset); else @@ -212,6 +221,8 @@ static void __ethtool_get_strings(struct net_device *dev, else if (stringset == ETH_SS_RSS_HASH_FUNCS) memcpy(data, rss_hash_func_strings, sizeof(rss_hash_func_strings)); + else if (stringset == ETH_SS_TUNABLES) + memcpy(data, tunable_strings, sizeof(tunable_strings)); else /* ops->get_strings is valid because checked earlier */ ops->get_strings(dev, stringset, data); diff --git a/net/core/filter.c b/net/core/filter.c index bf831a85c315..be3098fb65e4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -36,6 +36,7 @@ #include <net/netlink.h> #include <linux/skbuff.h> #include <net/sock.h> +#include <net/flow_dissector.h> #include <linux/errno.h> #include <linux/timer.h> #include <asm/uaccess.h> @@ -45,6 +46,7 @@ #include <linux/seccomp.h> #include <linux/if_vlan.h> #include <linux/bpf.h> +#include <net/sch_generic.h> /** * sk_filter - run a packet through a socket filter @@ -355,8 +357,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, * for socket filters: ctx == 'struct sk_buff *', for seccomp: * ctx == 'struct seccomp_data *'. */ -int bpf_convert_filter(struct sock_filter *prog, int len, - struct bpf_insn *new_prog, int *new_len) +static int bpf_convert_filter(struct sock_filter *prog, int len, + struct bpf_insn *new_prog, int *new_len) { int new_flen = 0, pass = 0, target, i; struct bpf_insn *new_insn; @@ -371,7 +373,8 @@ int bpf_convert_filter(struct sock_filter *prog, int len, return -EINVAL; if (new_prog) { - addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL); + addrs = kcalloc(len, sizeof(*addrs), + GFP_KERNEL | __GFP_NOWARN); if (!addrs) return -ENOMEM; } @@ -751,7 +754,8 @@ static bool chk_code_allowed(u16 code_to_probe) * * Returns 0 if the rule set is legal or -EINVAL if not. */ -int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) +static int bpf_check_classic(const struct sock_filter *filter, + unsigned int flen) { bool anc_found; int pc; @@ -825,7 +829,6 @@ int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) return -EINVAL; } -EXPORT_SYMBOL(bpf_check_classic); static int bpf_prog_store_orig_filter(struct bpf_prog *fp, const struct sock_fprog *fprog) @@ -839,7 +842,9 @@ static int bpf_prog_store_orig_filter(struct bpf_prog *fp, fkprog = fp->orig_prog; fkprog->len = fprog->len; - fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL); + + fkprog->filter = kmemdup(fp->insns, fsize, + GFP_KERNEL | __GFP_NOWARN); if (!fkprog->filter) { kfree(fp->orig_prog); return -ENOMEM; @@ -941,7 +946,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) * 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); + GFP_KERNEL | __GFP_NOWARN); if (!old_prog) { err = -ENOMEM; goto out_err; @@ -988,7 +993,8 @@ out_err: return ERR_PTR(err); } -static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp) +static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp, + bpf_aux_classic_check_t trans) { int err; @@ -1001,6 +1007,17 @@ static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp) return ERR_PTR(err); } + /* There might be additional checks and transformations + * needed on classic filters, f.e. in case of seccomp. + */ + if (trans) { + err = trans(fp->insns, fp->len); + if (err) { + __bpf_prog_release(fp); + return ERR_PTR(err); + } + } + /* Probe if we can JIT compile the filter and if so, do * the compilation of the filter. */ @@ -1050,7 +1067,7 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ - fp = bpf_prepare_filter(fp); + fp = bpf_prepare_filter(fp, NULL); if (IS_ERR(fp)) return PTR_ERR(fp); @@ -1059,6 +1076,53 @@ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) } EXPORT_SYMBOL_GPL(bpf_prog_create); +/** + * bpf_prog_create_from_user - create an unattached filter from user buffer + * @pfp: the unattached filter that is created + * @fprog: the filter program + * @trans: post-classic verifier transformation handler + * + * This function effectively does the same as bpf_prog_create(), only + * that it builds up its insns buffer from user space provided buffer. + * It also allows for passing a bpf_aux_classic_check_t handler. + */ +int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, + bpf_aux_classic_check_t trans) +{ + unsigned int fsize = bpf_classic_proglen(fprog); + struct bpf_prog *fp; + + /* Make sure new filter is there and in the right amounts. */ + if (fprog->filter == NULL) + return -EINVAL; + + fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); + if (!fp) + return -ENOMEM; + + if (copy_from_user(fp->insns, fprog->filter, fsize)) { + __bpf_prog_free(fp); + return -EFAULT; + } + + 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; + + /* bpf_prepare_filter() already takes care of freeing + * memory in case something goes wrong. + */ + fp = bpf_prepare_filter(fp, trans); + if (IS_ERR(fp)) + return PTR_ERR(fp); + + *pfp = fp; + return 0; +} + void bpf_prog_destroy(struct bpf_prog *fp) { __bpf_prog_release(fp); @@ -1135,7 +1199,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ - prog = bpf_prepare_filter(prog); + prog = bpf_prepare_filter(prog, NULL); if (IS_ERR(prog)) return PTR_ERR(prog); @@ -1175,21 +1239,6 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) return 0; } -/** - * bpf_skb_clone_not_writable - is the header of a clone not writable - * @skb: buffer to check - * @len: length up to which to write, can be negative - * - * Returns true if modifying the header part of the cloned buffer - * does require the data to be copied. I.e. this version works with - * negative lengths needed for eBPF case! - */ -static bool bpf_skb_clone_unwritable(const struct sk_buff *skb, int len) -{ - return skb_header_cloned(skb) || - (int) skb_headroom(skb) + len > skb->hdr_len; -} - #define BPF_RECOMPUTE_CSUM(flags) ((flags) & 1) static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) @@ -1212,9 +1261,8 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) if (unlikely((u32) offset > 0xffff || len > sizeof(buf))) return -EFAULT; - offset -= skb->data - skb_mac_header(skb); if (unlikely(skb_cloned(skb) && - bpf_skb_clone_unwritable(skb, offset + len))) + !skb_clone_writable(skb, offset + len))) return -EFAULT; ptr = skb_header_pointer(skb, offset, len, buf); @@ -1258,9 +1306,8 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) if (unlikely((u32) offset > 0xffff)) return -EFAULT; - offset -= skb->data - skb_mac_header(skb); if (unlikely(skb_cloned(skb) && - bpf_skb_clone_unwritable(skb, offset + sizeof(sum)))) + !skb_clone_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1306,9 +1353,8 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) if (unlikely((u32) offset > 0xffff)) return -EFAULT; - offset -= skb->data - skb_mac_header(skb); if (unlikely(skb_cloned(skb) && - bpf_skb_clone_unwritable(skb, offset + sizeof(sum)))) + !skb_clone_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1344,6 +1390,40 @@ const struct bpf_func_proto bpf_l4_csum_replace_proto = { .arg5_type = ARG_ANYTHING, }; +#define BPF_IS_REDIRECT_INGRESS(flags) ((flags) & 1) + +static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1, *skb2; + struct net_device *dev; + + dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); + if (unlikely(!dev)) + return -EINVAL; + + if (unlikely(!(dev->flags & IFF_UP))) + return -EINVAL; + + skb2 = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!skb2)) + return -ENOMEM; + + if (BPF_IS_REDIRECT_INGRESS(flags)) + return dev_forward_skb(dev, skb2); + + skb2->dev = dev; + return dev_queue_xmit(skb2); +} + +const struct bpf_func_proto bpf_clone_redirect_proto = { + .func = bpf_clone_redirect, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id) { @@ -1358,6 +1438,12 @@ sk_filter_func_proto(enum bpf_func_id func_id) return &bpf_get_prandom_u32_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; + case BPF_FUNC_tail_call: + return &bpf_tail_call_proto; + case BPF_FUNC_ktime_get_ns: + return &bpf_ktime_get_ns_proto; + case BPF_FUNC_trace_printk: + return bpf_get_trace_printk_proto(); default: return NULL; } @@ -1373,18 +1459,15 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; + case BPF_FUNC_clone_redirect: + return &bpf_clone_redirect_proto; default: return sk_filter_func_proto(func_id); } } -static bool sk_filter_is_valid_access(int off, int size, - enum bpf_access_type type) +static bool __is_valid_access(int off, int size, enum bpf_access_type type) { - /* only read is allowed */ - if (type != BPF_READ) - return false; - /* check bounds */ if (off < 0 || off >= sizeof(struct __sk_buff)) return false; @@ -1400,8 +1483,42 @@ static bool sk_filter_is_valid_access(int off, int size, return true; } -static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, - struct bpf_insn *insn_buf) +static bool sk_filter_is_valid_access(int off, int size, + enum bpf_access_type type) +{ + if (type == BPF_WRITE) { + switch (off) { + case offsetof(struct __sk_buff, cb[0]) ... + offsetof(struct __sk_buff, cb[4]): + break; + default: + return false; + } + } + + return __is_valid_access(off, size, type); +} + +static bool tc_cls_act_is_valid_access(int off, int size, + enum bpf_access_type type) +{ + if (type == BPF_WRITE) { + switch (off) { + case offsetof(struct __sk_buff, mark): + case offsetof(struct __sk_buff, tc_index): + case offsetof(struct __sk_buff, cb[0]) ... + offsetof(struct __sk_buff, cb[4]): + break; + default: + return false; + } + } + return __is_valid_access(off, size, type); +} + +static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, + int src_reg, int ctx_off, + struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; @@ -1434,8 +1551,34 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, offsetof(struct sk_buff, priority)); break; + case offsetof(struct __sk_buff, ingress_ifindex): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, skb_iif) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, skb_iif)); + break; + + case offsetof(struct __sk_buff, ifindex): + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); + + *insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)), + dst_reg, src_reg, + offsetof(struct sk_buff, dev)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, dst_reg, + offsetof(struct net_device, ifindex)); + break; + case offsetof(struct __sk_buff, mark): - return convert_skb_access(SKF_AD_MARK, dst_reg, src_reg, insn); + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, mark)); + else + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, mark)); + break; case offsetof(struct __sk_buff, pkt_type): return convert_skb_access(SKF_AD_PKTTYPE, dst_reg, src_reg, insn); @@ -1450,6 +1593,38 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, case offsetof(struct __sk_buff, vlan_tci): return convert_skb_access(SKF_AD_VLAN_TAG, dst_reg, src_reg, insn); + + case offsetof(struct __sk_buff, cb[0]) ... + offsetof(struct __sk_buff, cb[4]): + BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + + ctx_off -= offsetof(struct __sk_buff, cb[0]); + ctx_off += offsetof(struct sk_buff, cb); + ctx_off += offsetof(struct qdisc_skb_cb, data); + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, ctx_off); + else + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, ctx_off); + break; + + case offsetof(struct __sk_buff, tc_index): +#ifdef CONFIG_NET_SCHED + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2); + + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, tc_index)); + else + *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, + offsetof(struct sk_buff, tc_index)); + break; +#else + if (type == BPF_WRITE) + *insn++ = BPF_MOV64_REG(dst_reg, dst_reg); + else + *insn++ = BPF_MOV64_IMM(dst_reg, 0); + break; +#endif } return insn - insn_buf; @@ -1458,13 +1633,13 @@ static u32 sk_filter_convert_ctx_access(int dst_reg, int src_reg, int ctx_off, static const struct bpf_verifier_ops sk_filter_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, - .convert_ctx_access = sk_filter_convert_ctx_access, + .convert_ctx_access = bpf_net_convert_ctx_access, }; static const struct bpf_verifier_ops tc_cls_act_ops = { .get_func_proto = tc_cls_act_func_proto, - .is_valid_access = sk_filter_is_valid_access, - .convert_ctx_access = sk_filter_convert_ctx_access, + .is_valid_access = tc_cls_act_is_valid_access, + .convert_ctx_access = bpf_net_convert_ctx_access, }; static struct bpf_prog_type_list sk_filter_type __read_mostly = { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2c35c02a931e..476e5dda59e1 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1,3 +1,4 @@ +#include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/export.h> #include <linux/ip.h> @@ -12,19 +13,60 @@ #include <linux/if_tunnel.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> -#include <net/flow_keys.h> +#include <linux/stddef.h> +#include <linux/if_ether.h> +#include <linux/mpls.h> +#include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.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) +static bool skb_flow_dissector_uses_key(struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id) +{ + return flow_dissector->used_keys & (1 << key_id); +} + +static void skb_flow_dissector_set_key(struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id) +{ + flow_dissector->used_keys |= (1 << key_id); +} + +static void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id, + void *target_container) +{ + return ((char *) target_container) + flow_dissector->offset[key_id]; +} + +void skb_flow_dissector_init(struct flow_dissector *flow_dissector, + const struct flow_dissector_key *key, + unsigned int key_count) { - 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)); + unsigned int i; + + memset(flow_dissector, 0, sizeof(*flow_dissector)); + + for (i = 0; i < key_count; i++, key++) { + /* User should make sure that every key target offset is withing + * boundaries of unsigned short. + */ + BUG_ON(key->offset > USHRT_MAX); + BUG_ON(skb_flow_dissector_uses_key(flow_dissector, + key->key_id)); + + skb_flow_dissector_set_key(flow_dissector, key->key_id); + flow_dissector->offset[key->key_id] = key->offset; + } + + /* Ensure that the dissector always includes control and basic key. + * That way we are able to avoid handling lack of these in fast path. + */ + BUG_ON(!skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_CONTROL)); + BUG_ON(!skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_BASIC)); } +EXPORT_SYMBOL(skb_flow_dissector_init); /** * __skb_flow_get_ports - extract the upper layer ports and return them @@ -63,17 +105,30 @@ EXPORT_SYMBOL(__skb_flow_get_ports); /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified + * @flow_dissector: list of keys to dissect + * @target_container: target structure to put dissected values into * @data: raw buffer pointer to the packet, if NULL use skb->data * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb) * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * - * The function will try to retrieve the struct flow_keys from either the skbuff - * or a raw buffer specified by the rest parameters + * The function will try to retrieve individual keys into target specified + * by flow_dissector from either the skbuff or a raw buffer specified by the + * rest parameters. + * + * Caller must take care of zeroing target container memory. */ -bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, +bool __skb_flow_dissect(const struct sk_buff *skb, |