diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-05-01 21:08:52 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-05-01 21:08:52 (GMT) |
commit | 73287a43cc79ca06629a88d1a199cd283f42456a (patch) | |
tree | acf4456e260115bea77ee31a29f10ce17f0db45c /net/packet/af_packet.c | |
parent | 251df49db3327c64bf917bfdba94491fde2b4ee0 (diff) | |
parent | 20074f357da4a637430aec2879c9d864c5d2c23c (diff) | |
download | linux-fsl-qoriq-73287a43cc79ca06629a88d1a199cd283f42456a.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights (1721 non-merge commits, this has to be a record of some
sort):
1) Add 'random' mode to team driver, from Jiri Pirko and Eric
Dumazet.
2) Make it so that any driver that supports configuration of multiple
MAC addresses can provide the forwarding database add and del
calls by providing a default implementation and hooking that up if
the driver doesn't have an explicit set of handlers. From Vlad
Yasevich.
3) Support GSO segmentation over tunnels and other encapsulating
devices such as VXLAN, from Pravin B Shelar.
4) Support L2 GRE tunnels in the flow dissector, from Michael Dalton.
5) Implement Tail Loss Probe (TLP) detection in TCP, from Nandita
Dukkipati.
6) In the PHY layer, allow supporting wake-on-lan in situations where
the PHY registers have to be written for it to be configured.
Use it to support wake-on-lan in mv643xx_eth.
From Michael Stapelberg.
7) Significantly improve firewire IPV6 support, from YOSHIFUJI
Hideaki.
8) Allow multiple packets to be sent in a single transmission using
network coding in batman-adv, from Martin Hundebøll.
9) Add support for T5 cxgb4 chips, from Santosh Rastapur.
10) Generalize the VXLAN forwarding tables so that there is more
flexibility in configurating various aspects of the endpoints.
From David Stevens.
11) Support RSS and TSO in hardware over GRE tunnels in bxn2x driver,
from Dmitry Kravkov.
12) Zero copy support in nfnelink_queue, from Eric Dumazet and Pablo
Neira Ayuso.
13) Start adding networking selftests.
14) In situations of overload on the same AF_PACKET fanout socket, or
per-cpu packet receive queue, minimize drop by distributing the
load to other cpus/fanouts. From Willem de Bruijn and Eric
Dumazet.
15) Add support for new payload offset BPF instruction, from Daniel
Borkmann.
16) Convert several drivers over to mdoule_platform_driver(), from
Sachin Kamat.
17) Provide a minimal BPF JIT image disassembler userspace tool, from
Daniel Borkmann.
18) Rewrite F-RTO implementation in TCP to match the final
specification of it in RFC4138 and RFC5682. From Yuchung Cheng.
19) Provide netlink socket diag of netlink sockets ("Yo dawg, I hear
you like netlink, so I implemented netlink dumping of netlink
sockets.") From Andrey Vagin.
20) Remove ugly passing of rtnetlink attributes into rtnl_doit
functions, from Thomas Graf.
21) Allow userspace to be able to see if a configuration change occurs
in the middle of an address or device list dump, from Nicolas
Dichtel.
22) Support RFC3168 ECN protection for ipv6 fragments, from Hannes
Frederic Sowa.
23) Increase accuracy of packet length used by packet scheduler, from
Jason Wang.
24) Beginning set of changes to make ipv4/ipv6 fragment handling more
scalable and less susceptible to overload and locking contention,
from Jesper Dangaard Brouer.
25) Get rid of using non-type-safe NLMSG_* macros and use nlmsg_*()
instead. From Hong Zhiguo.
26) Optimize route usage in IPVS by avoiding reference counting where
possible, from Julian Anastasov.
27) Convert IPVS schedulers to RCU, also from Julian Anastasov.
28) Support cpu fanouts in xt_NFQUEUE netfilter target, from Holger
Eitzenberger.
29) Network namespace support for nf_log, ebt_log, xt_LOG, ipt_ULOG,
nfnetlink_log, and nfnetlink_queue. From Gao feng.
30) Implement RFC3168 ECN protection, from Hannes Frederic Sowa.
31) Support several new r8169 chips, from Hayes Wang.
32) Support tokenized interface identifiers in ipv6, from Daniel
Borkmann.
33) Use usbnet_link_change() helper in USB net driver, from Ming Lei.
34) Add 802.1ad vlan offload support, from Patrick McHardy.
35) Support mmap() based netlink communication, also from Patrick
McHardy.
36) Support HW timestamping in mlx4 driver, from Amir Vadai.
37) Rationalize AF_PACKET packet timestamping when transmitting, from
Willem de Bruijn and Daniel Borkmann.
38) Bring parity to what's provided by /proc/net/packet socket dumping
and the info provided by netlink socket dumping of AF_PACKET
sockets. From Nicolas Dichtel.
39) Fix peeking beyond zero sized SKBs in AF_UNIX, from Benjamin
Poirier"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
filter: fix va_list build error
af_unix: fix a fatal race with bit fields
bnx2x: Prevent memory leak when cnic is absent
bnx2x: correct reading of speed capabilities
net: sctp: attribute printl with __printf for gcc fmt checks
netlink: kconfig: move mmap i/o into netlink kconfig
netpoll: convert mutex into a semaphore
netlink: Fix skb ref counting.
net_sched: act_ipt forward compat with xtables
mlx4_en: fix a build error on 32bit arches
Revert "bnx2x: allow nvram test to run when device is down"
bridge: avoid OOPS if root port not found
drivers: net: cpsw: fix kernel warn on cpsw irq enable
sh_eth: use random MAC address if no valid one supplied
3c509.c: call SET_NETDEV_DEV for all device types (ISA/ISAPnP/EISA)
tg3: fix to append hardware time stamping flags
unix/stream: fix peeking with an offset larger than data in queue
unix/dgram: fix peeking with an offset larger than data in queue
unix/dgram: peek beyond 0-sized skbs
openvswitch: Remove unneeded ovs_netdev_get_ifindex()
...
Diffstat (limited to 'net/packet/af_packet.c')
-rw-r--r-- | net/packet/af_packet.c | 302 |
1 files changed, 190 insertions, 112 deletions
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 1d6793d..dd5cd49 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -158,10 +158,16 @@ struct packet_mreq_max { unsigned char mr_address[MAX_ADDR_LEN]; }; +union tpacket_uhdr { + struct tpacket_hdr *h1; + struct tpacket2_hdr *h2; + struct tpacket3_hdr *h3; + void *raw; +}; + static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring); - #define V3_ALIGNMENT (8) #define BLK_HDR_LEN (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT)) @@ -181,6 +187,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, struct packet_sock; static int tpacket_snd(struct packet_sock *po, struct msghdr *msg); +static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev); static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, @@ -288,11 +296,7 @@ static inline __pure struct page *pgv_to_page(void *addr) static void __packet_set_status(struct packet_sock *po, void *frame, int status) { - union { - struct tpacket_hdr *h1; - struct tpacket2_hdr *h2; - void *raw; - } h; + union tpacket_uhdr h; h.raw = frame; switch (po->tp_version) { @@ -315,11 +319,7 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) static int __packet_get_status(struct packet_sock *po, void *frame) { - union { - struct tpacket_hdr *h1; - struct tpacket2_hdr *h2; - void *raw; - } h; + union tpacket_uhdr h; smp_rmb(); @@ -339,17 +339,66 @@ static int __packet_get_status(struct packet_sock *po, void *frame) } } +static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec *ts, + unsigned int flags) +{ + struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); + + if (shhwtstamps) { + if ((flags & SOF_TIMESTAMPING_SYS_HARDWARE) && + ktime_to_timespec_cond(shhwtstamps->syststamp, ts)) + return TP_STATUS_TS_SYS_HARDWARE; + if ((flags & SOF_TIMESTAMPING_RAW_HARDWARE) && + ktime_to_timespec_cond(shhwtstamps->hwtstamp, ts)) + return TP_STATUS_TS_RAW_HARDWARE; + } + + if (ktime_to_timespec_cond(skb->tstamp, ts)) + return TP_STATUS_TS_SOFTWARE; + + return 0; +} + +static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame, + struct sk_buff *skb) +{ + union tpacket_uhdr h; + struct timespec ts; + __u32 ts_status; + + if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp))) + return 0; + + h.raw = frame; + switch (po->tp_version) { + case TPACKET_V1: + h.h1->tp_sec = ts.tv_sec; + h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; + break; + case TPACKET_V2: + h.h2->tp_sec = ts.tv_sec; + h.h2->tp_nsec = ts.tv_nsec; + break; + case TPACKET_V3: + default: + WARN(1, "TPACKET version not supported.\n"); + BUG(); + } + + /* one flush is safe, as both fields always lie on the same cacheline */ + flush_dcache_page(pgv_to_page(&h.h1->tp_sec)); + smp_wmb(); + + return ts_status; +} + static void *packet_lookup_frame(struct packet_sock *po, struct packet_ring_buffer *rb, unsigned int position, int status) { unsigned int pg_vec_pos, frame_offset; - union { - struct tpacket_hdr *h1; - struct tpacket2_hdr *h2; - void *raw; - } h; + union tpacket_uhdr h; pg_vec_pos = position / rb->frames_per_block; frame_offset = position % rb->frames_per_block; @@ -479,7 +528,7 @@ static void init_prb_bdqc(struct packet_sock *po, p1->hdrlen = po->tp_hdrlen; p1->version = po->tp_version; p1->last_kactive_blk_num = 0; - po->stats_u.stats3.tp_freeze_q_cnt = 0; + po->stats.stats3.tp_freeze_q_cnt = 0; if (req_u->req3.tp_retire_blk_tov) p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov; else @@ -647,7 +696,7 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1, struct tpacket3_hdr *last_pkt; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; - if (po->stats.tp_drops) + if (po->stats.stats3.tp_drops) status |= TP_STATUS_LOSING; last_pkt = (struct tpacket3_hdr *)pkc1->prev; @@ -752,7 +801,7 @@ static void prb_freeze_queue(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { pkc->reset_pending_on_curr_blk = 1; - po->stats_u.stats3.tp_freeze_q_cnt++; + po->stats.stats3.tp_freeze_q_cnt++; } #define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT)) @@ -973,11 +1022,11 @@ static void *packet_current_rx_frame(struct packet_sock *po, static void *prb_lookup_block(struct packet_sock *po, struct packet_ring_buffer *rb, - unsigned int previous, + unsigned int idx, int status) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); - struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, previous); + struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx); if (status != BLOCK_STATUS(pbd)) return NULL; @@ -1041,6 +1090,29 @@ static void packet_increment_head(struct packet_ring_buffer *buff) buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } +static bool packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) +{ + struct sock *sk = &po->sk; + bool has_room; + + if (po->prot_hook.func != tpacket_rcv) + return (atomic_read(&sk->sk_rmem_alloc) + skb->truesize) + <= sk->sk_rcvbuf; + + spin_lock(&sk->sk_receive_queue.lock); + if (po->tp_version == TPACKET_V3) + has_room = prb_lookup_block(po, &po->rx_ring, + po->rx_ring.prb_bdqc.kactive_blk_num, + TP_STATUS_KERNEL); + else + has_room = packet_lookup_frame(po, &po->rx_ring, + po->rx_ring.head, + TP_STATUS_KERNEL); + spin_unlock(&sk->sk_receive_queue.lock); + + return has_room; +} + static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); @@ -1066,16 +1138,16 @@ static int fanout_rr_next(struct packet_fanout *f, unsigned int num) return x; } -static struct sock *fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) +static unsigned int fanout_demux_hash(struct packet_fanout *f, + struct sk_buff *skb, + unsigned int num) { - u32 idx, hash = skb->rxhash; - - idx = ((u64)hash * num) >> 32; - - return f->arr[idx]; + return (((u64)skb->rxhash) * num) >> 32; } -static struct sock *fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) +static unsigned int fanout_demux_lb(struct packet_fanout *f, + struct sk_buff *skb, + unsigned int num) { int cur, old; @@ -1083,14 +1155,40 @@ static struct sock *fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb while ((old = atomic_cmpxchg(&f->rr_cur, cur, fanout_rr_next(f, num))) != cur) cur = old; - return f->arr[cur]; + return cur; } -static struct sock *fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) +static unsigned int fanout_demux_cpu(struct packet_fanout *f, + struct sk_buff *skb, + unsigned int num) { - unsigned int cpu = smp_processor_id(); + return smp_processor_id() % num; +} - return f->arr[cpu % num]; +static unsigned int fanout_demux_rollover(struct packet_fanout *f, + struct sk_buff *skb, + unsigned int idx, unsigned int skip, + unsigned int num) +{ + unsigned int i, j; + + i = j = min_t(int, f->next[idx], num - 1); + do { + if (i != skip && packet_rcv_has_room(pkt_sk(f->arr[i]), skb)) { + if (i != j) + f->next[idx] = i; + return i; + } + if (++i == num) + i = 0; + } while (i != j); + + return idx; +} + +static bool fanout_has_flag(struct packet_fanout *f, u16 flag) +{ + return f->flags & (flag >> 8); } static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, @@ -1099,7 +1197,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, struct packet_fanout *f = pt->af_packet_priv; unsigned int num = f->num_members; struct packet_sock *po; - struct sock *sk; + unsigned int idx; if (!net_eq(dev_net(dev), read_pnet(&f->net)) || !num) { @@ -1110,23 +1208,31 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, switch (f->type) { case PACKET_FANOUT_HASH: default: - if (f->defrag) { + if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) { skb = ip_check_defrag(skb, IP_DEFRAG_AF_PACKET); if (!skb) return 0; } skb_get_rxhash(skb); - sk = fanout_demux_hash(f, skb, num); + idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: - sk = fanout_demux_lb(f, skb, num); + idx = fanout_demux_lb(f, skb, num); break; case PACKET_FANOUT_CPU: - sk = fanout_demux_cpu(f, skb, num); + idx = fanout_demux_cpu(f, skb, num); + break; + case PACKET_FANOUT_ROLLOVER: + idx = fanout_demux_rollover(f, skb, 0, (unsigned int) -1, num); break; } - po = pkt_sk(sk); + po = pkt_sk(f->arr[idx]); + if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER) && + unlikely(!packet_rcv_has_room(po, skb))) { + idx = fanout_demux_rollover(f, skb, idx, idx, num); + po = pkt_sk(f->arr[idx]); + } return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } @@ -1175,10 +1281,13 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f, *match; u8 type = type_flags & 0xff; - u8 defrag = (type_flags & PACKET_FANOUT_FLAG_DEFRAG) ? 1 : 0; + u8 flags = type_flags >> 8; int err; switch (type) { + case PACKET_FANOUT_ROLLOVER: + if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER) + return -EINVAL; case PACKET_FANOUT_HASH: case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: @@ -1203,7 +1312,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) } } err = -EINVAL; - if (match && match->defrag != defrag) + if (match && match->flags != flags) goto out; if (!match) { err = -ENOMEM; @@ -1213,7 +1322,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) write_pnet(&match->net, sock_net(sk)); match->id = id; match->type = type; - match->defrag = defrag; + match->flags = flags; atomic_set(&match->rr_cur, 0); INIT_LIST_HEAD(&match->list); spin_lock_init(&match->lock); @@ -1443,13 +1552,14 @@ retry: skb->dev = dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - err = sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); - if (err < 0) - goto out_unlock; + + sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); if (unlikely(extra_len == 4)) skb->no_fcs = 1; + skb_probe_transport_header(skb, 0); + dev_queue_xmit(skb); rcu_read_unlock(); return len; @@ -1577,7 +1687,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, nf_reset(skb); spin_lock(&sk->sk_receive_queue.lock); - po->stats.tp_packets++; + po->stats.stats1.tp_packets++; skb->dropcount = atomic_read(&sk->sk_drops); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); @@ -1586,7 +1696,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, drop_n_acct: spin_lock(&sk->sk_receive_queue.lock); - po->stats.tp_drops++; + po->stats.stats1.tp_drops++; atomic_inc(&sk->sk_drops); spin_unlock(&sk->sk_receive_queue.lock); @@ -1606,21 +1716,15 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct sock *sk; struct packet_sock *po; struct sockaddr_ll *sll; - union { - struct tpacket_hdr *h1; - struct tpacket2_hdr *h2; - struct tpacket3_hdr *h3; - void *raw; - } h; + union tpacket_uhdr h; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; unsigned short macoff, netoff, hdrlen; struct sk_buff *copy_skb = NULL; - struct timeval tv; struct timespec ts; - struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); + __u32 ts_status; if (skb->pkt_type == PACKET_LOOPBACK) goto drop; @@ -1692,10 +1796,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, * Anyways, moving it for V1/V2 only as V3 doesn't need this * at packet level. */ - if (po->stats.tp_drops) + if (po->stats.stats1.tp_drops) status |= TP_STATUS_LOSING; } - po->stats.tp_packets++; + po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; __skb_queue_tail(&sk->sk_receive_queue, copy_skb); @@ -1704,24 +1808,19 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, skb_copy_bits(skb, 0, h.raw + macoff, snaplen); + if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp))) + getnstimeofday(&ts); + + status |= ts_status; + switch (po->tp_version) { case TPACKET_V1: h.h1->tp_len = skb->len; h.h1->tp_snaplen = snaplen; h.h1->tp_mac = macoff; h.h1->tp_net = netoff; - if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE) - && shhwtstamps->syststamp.tv64) - tv = ktime_to_timeval(shhwtstamps->syststamp); - else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE) - && shhwtstamps->hwtstamp.tv64) - tv = ktime_to_timeval(shhwtstamps->hwtstamp); - else if (skb->tstamp.tv64) - tv = ktime_to_timeval(skb->tstamp); - else - do_gettimeofday(&tv); - h.h1->tp_sec = tv.tv_sec; - h.h1->tp_usec = tv.tv_usec; + h.h1->tp_sec = ts.tv_sec; + h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; hdrlen = sizeof(*h.h1); break; case TPACKET_V2: @@ -1729,16 +1828,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_snaplen = snaplen; h.h2->tp_mac = macoff; h.h2->tp_net = netoff; - if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE) - && shhwtstamps->syststamp.tv64) - ts = ktime_to_timespec(shhwtstamps->syststamp); - else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE) - && shhwtstamps->hwtstamp.tv64) - ts = ktime_to_timespec(shhwtstamps->hwtstamp); - else if (skb->tstamp.tv64) - ts = ktime_to_timespec(skb->tstamp); - else - getnstimeofday(&ts); h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; if (vlan_tx_tag_present(skb)) { @@ -1759,16 +1848,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h3->tp_snaplen = snaplen; h.h3->tp_mac = macoff; h.h3->tp_net = netoff; - if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE) - && shhwtstamps->syststamp.tv64) - ts = ktime_to_timespec(shhwtstamps->syststamp); - else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE) - && shhwtstamps->hwtstamp.tv64) - ts = ktime_to_timespec(shhwtstamps->hwtstamp); - else if (skb->tstamp.tv64) - ts = ktime_to_timespec(skb->tstamp); - else - getnstimeofday(&ts); h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; hdrlen = sizeof(*h.h3); @@ -1819,7 +1898,7 @@ drop: return 0; ring_is_full: - po->stats.tp_drops++; + po->stats.stats1.tp_drops++; spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk, 0); @@ -1833,10 +1912,14 @@ static void tpacket_destruct_skb(struct sk_buff *skb) void *ph; if (likely(po->tx_ring.pg_vec)) { + __u32 ts; + ph = skb_shinfo(skb)->destructor_arg; BUG_ON(atomic_read(&po->tx_ring.pending) == 0); atomic_dec(&po->tx_ring.pending); - __packet_set_status(po, ph, TP_STATUS_AVAILABLE); + + ts = __packet_set_timestamp(po, ph, skb); + __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); } sock_wfree(skb); @@ -1846,11 +1929,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, int size_max, __be16 proto, unsigned char *addr, int hlen) { - union { - struct tpacket_hdr *h1; - struct tpacket2_hdr *h2; - void *raw; - } ph; + union tpacket_uhdr ph; int to_write, offset, len, tp_len, nr_frags, len_max; struct socket *sock = po->sk.sk_socket; struct page *page; @@ -1863,6 +1942,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->dev = dev; skb->priority = po->sk.sk_priority; skb->mark = po->sk.sk_mark; + sock_tx_timestamp(&po->sk, &skb_shinfo(skb)->tx_flags); skb_shinfo(skb)->destructor_arg = ph.raw; switch (po->tp_version) { @@ -1880,6 +1960,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb_reserve(skb, hlen); skb_reset_network_header(skb); + skb_probe_transport_header(skb, 0); if (po->tp_tx_has_off) { int off_min, off_max, off; @@ -2247,9 +2328,8 @@ static int packet_snd(struct socket *sock, err = skb_copy_datagram_from_iovec(skb, offset, msg->msg_iov, 0, len); if (err) goto out_free; - err = sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); - if (err < 0) - goto out_free; + + sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); if (!gso_type && (len > dev->mtu + reserve + extra_len)) { /* Earlier code assumed this would be a VLAN pkt, @@ -2289,6 +2369,8 @@ static int packet_snd(struct socket *sock, len += vnet_hdr_len; } + skb_probe_transport_header(skb, reserve); + if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -3165,8 +3247,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); void *data = &val; - struct tpacket_stats st; - union tpacket_stats_u st_u; + union tpacket_stats_u st; if (level != SOL_PACKET) return -ENOPROTOOPT; @@ -3180,22 +3261,18 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, switch (optname) { case PACKET_STATISTICS: spin_lock_bh(&sk->sk_receive_queue.lock); + memcpy(&st, &po->stats, sizeof(st)); + memset(&po->stats, 0, sizeof(po->stats)); + spin_unlock_bh(&sk->sk_receive_queue.lock); + if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); - memcpy(&st_u.stats3, &po->stats, - sizeof(struct tpacket_stats)); - st_u.stats3.tp_freeze_q_cnt = - po->stats_u.stats3.tp_freeze_q_cnt; - st_u.stats3.tp_packets += po->stats.tp_drops; - data = &st_u.stats3; + data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); - st = po->stats; - st.tp_packets += st.tp_drops; - data = &st; + data = &st.stats1; } - memset(&po->stats, 0, sizeof(st)); - spin_unlock_bh(&sk->sk_receive_queue.lock); + break; case PACKET_AUXDATA: val = po->auxdata; @@ -3240,7 +3317,8 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, case PACKET_FANOUT: val = (po->fanout ? ((u32)po->fanout->id | - ((u32)po->fanout->type << 16)) : + ((u32)po->fanout->type << 16) | + ((u32)po->fanout->flags << 24)) : 0); break; case PACKET_TX_HAS_OFF: |