diff options
Diffstat (limited to 'net/packet')
-rw-r--r-- | net/packet/Kconfig | 4 | ||||
-rw-r--r-- | net/packet/af_packet.c | 479 | ||||
-rw-r--r-- | net/packet/internal.h | 14 |
3 files changed, 299 insertions, 198 deletions
diff --git a/net/packet/Kconfig b/net/packet/Kconfig index b4abad135294..2997382d597c 100644 --- a/net/packet/Kconfig +++ b/net/packet/Kconfig @@ -5,7 +5,7 @@ config PACKET tristate "Packet socket" - ---help--- + help The Packet protocol is used by applications which communicate directly with network devices without an intermediate network protocol implemented in the kernel, e.g. tcpdump. If you want them @@ -20,6 +20,6 @@ config PACKET_DIAG tristate "Packet: sockets monitoring interface" depends on PACKET default n - ---help--- + help Support for PF_PACKET sockets monitoring interface used by the ss tool. If unsure, say Y. diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e5b0986215d2..6ce8dd19f33c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -46,6 +46,10 @@ * Copyright (C) 2011, <lokec@ccs.neu.edu> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/ethtool.h> +#include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/capability.h> @@ -88,57 +92,62 @@ #endif #include <linux/bpf.h> #include <net/compat.h> +#include <linux/netfilter_netdev.h> #include "internal.h" /* Assumptions: - - if device has no dev->hard_header routine, it adds and removes ll header - inside itself. In this case ll header is invisible outside of device, - but higher levels still should reserve dev->hard_header_len. - Some devices are enough clever to reallocate skb, when header - will not fit to reserved space (tunnel), another ones are silly - (PPP). + - If the device has no dev->header_ops->create, there is no LL header + visible above the device. In this case, its hard_header_len should be 0. + The device may prepend its own header internally. In this case, its + needed_headroom should be set to the space needed for it to add its + internal header. + For example, a WiFi driver pretending to be an Ethernet driver should + set its hard_header_len to be the Ethernet header length, and set its + needed_headroom to be (the real WiFi header length - the fake Ethernet + header length). - packet socket receives packets with pulled ll header, so that SOCK_RAW should push it back. On receive: ----------- -Incoming, dev->hard_header!=NULL +Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data -Outgoing, dev->hard_header!=NULL +Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header -Incoming, dev->hard_header==NULL - mac_header -> UNKNOWN position. It is very likely, that it points to ll - header. PPP makes it, that is wrong, because introduce - assymetry between rx and tx paths. +Incoming, dev_has_header(dev) == false + mac_header -> data + However drivers often make it point to the ll header. + This is incorrect because the ll header should be invisible to us. data -> data -Outgoing, dev->hard_header==NULL - mac_header -> data. ll header is still not built! +Outgoing, dev_has_header(dev) == false + mac_header -> data. ll header is invisible to us. data -> data Resume - If dev->hard_header==NULL we are unlikely to restore sensible ll header. + If dev_has_header(dev) == false we are unable to restore the ll header, + because it is invisible to us. On transmit: ------------ -dev->hard_header != NULL +dev_has_header(dev) == true mac_header -> ll header data -> ll header -dev->hard_header == NULL (ll header is added by device, we cannot control it) +dev_has_header(dev) == false (ll header is invisible to us) mac_header -> data data -> data - We should set nh.raw on output to correct posistion, + We should set network_header on output to the correct position, packet classifier depends on it. */ @@ -177,7 +186,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, #define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) #define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) #define BLOCK_O2PRIV(x) ((x)->offset_to_priv) -#define BLOCK_PRIV(x) ((void *)((char *)(x) + BLOCK_O2PRIV(x))) struct packet_sock; static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, @@ -235,8 +243,42 @@ struct packet_skb_cb { static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); +#ifdef CONFIG_NETFILTER_EGRESS +static noinline struct sk_buff *nf_hook_direct_egress(struct sk_buff *skb) +{ + struct sk_buff *next, *head = NULL, *tail; + int rc; + + rcu_read_lock(); + for (; skb != NULL; skb = next) { + next = skb->next; + skb_mark_not_on_list(skb); + + if (!nf_hook_egress(skb, &rc, skb->dev)) + continue; + + if (!head) + head = skb; + else + tail->next = skb; + + tail = skb; + } + rcu_read_unlock(); + + return head; +} +#endif + static int packet_direct_xmit(struct sk_buff *skb) { +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_hook_egress_active()) { + skb = nf_hook_direct_egress(skb); + if (!skb) + return NET_XMIT_DROP; + } +#endif return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } @@ -246,8 +288,7 @@ static struct net_device *packet_cached_dev_get(struct packet_sock *po) rcu_read_lock(); dev = rcu_dereference(po->cached_dev); - if (likely(dev)) - dev_hold(dev); + dev_hold(dev); rcu_read_unlock(); return dev; @@ -418,7 +459,8 @@ static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; - if (ktime_to_timespec64_cond(skb->tstamp, ts)) + if ((flags & SOF_TIMESTAMPING_SOFTWARE) && + ktime_to_timespec64_cond(skb_tstamp(skb), ts)) return TP_STATUS_TS_SOFTWARE; return 0; @@ -593,6 +635,7 @@ static void init_prb_bdqc(struct packet_sock *po, req_u->req3.tp_block_size); p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; + rwlock_init(&p1->blk_fill_in_prog_lock); p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); @@ -659,10 +702,9 @@ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) * */ if (BLOCK_NUM_PKTS(pbd)) { - while (atomic_read(&pkc->blk_fill_in_prog)) { - /* Waiting for skb_copy_bits to finish... */ - cpu_relax(); - } + /* Waiting for skb_copy_bits to finish... */ + write_lock(&pkc->blk_fill_in_prog_lock); + write_unlock(&pkc->blk_fill_in_prog_lock); } if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) { @@ -921,10 +963,9 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, * the timer-handler already handled this case. */ if (!(status & TP_STATUS_BLK_TMO)) { - while (atomic_read(&pkc->blk_fill_in_prog)) { - /* Waiting for skb_copy_bits to finish... */ - cpu_relax(); - } + /* Waiting for skb_copy_bits to finish... */ + write_lock(&pkc->blk_fill_in_prog_lock); + write_unlock(&pkc->blk_fill_in_prog_lock); } prb_close_block(pkc, pbd, po, status); return; @@ -942,9 +983,11 @@ static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) } static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) + __releases(&pkc->blk_fill_in_prog_lock) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); - atomic_dec(&pkc->blk_fill_in_prog); + + read_unlock(&pkc->blk_fill_in_prog_lock); } static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, @@ -989,6 +1032,7 @@ static void prb_fill_curr_block(char *curr, struct tpacket_kbdq_core *pkc, struct tpacket_block_desc *pbd, unsigned int len) + __acquires(&pkc->blk_fill_in_prog_lock) { struct tpacket3_hdr *ppd; @@ -998,7 +1042,7 @@ static void prb_fill_curr_block(char *curr, pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_NUM_PKTS(pbd) += 1; - atomic_inc(&pkc->blk_fill_in_prog); + read_lock(&pkc->blk_fill_in_prog_lock); prb_run_all_ft_ops(pkc, ppd); } @@ -1306,7 +1350,7 @@ static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) if (READ_ONCE(history[i]) == rxhash) count++; - victim = prandom_u32() % ROLLOVER_HLEN; + victim = prandom_u32_max(ROLLOVER_HLEN); /* Avoid dirtying the cache line if possible */ if (READ_ONCE(history[victim]) != rxhash) @@ -1353,7 +1397,7 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f, struct packet_sock *po, *po_next, *po_skip = NULL; unsigned int i, j, room = ROOM_NONE; - po = pkt_sk(f->arr[idx]); + po = pkt_sk(rcu_dereference(f->arr[idx])); if (try_self) { room = packet_rcv_has_room(po, skb); @@ -1365,7 +1409,7 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f, i = j = min_t(int, po->rollover->sock, num - 1); do { - po_next = pkt_sk(f->arr[i]); + po_next = pkt_sk(rcu_dereference(f->arr[i])); if (po_next != po_skip && !READ_ONCE(po_next->pressure) && packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) @@ -1460,7 +1504,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER)) idx = fanout_demux_rollover(f, skb, idx, true, num); - po = pkt_sk(f->arr[idx]); + po = pkt_sk(rcu_dereference(f->arr[idx])); return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } @@ -1474,7 +1518,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po) struct packet_fanout *f = po->fanout; spin_lock(&f->lock); - f->arr[f->num_members] = sk; + rcu_assign_pointer(f->arr[f->num_members], sk); smp_wmb(); f->num_members++; if (f->num_members == 1) @@ -1489,11 +1533,14 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po) spin_lock(&f->lock); for (i = 0; i < f->num_members; i++) { - if (f->arr[i] == sk) + if (rcu_dereference_protected(f->arr[i], + lockdep_is_held(&f->lock)) == sk) break; } BUG_ON(i >= f->num_members); - f->arr[i] = f->arr[f->num_members - 1]; + rcu_assign_pointer(f->arr[i], + rcu_dereference_protected(f->arr[f->num_members - 1], + lockdep_is_held(&f->lock))); f->num_members--; if (f->num_members == 0) __dev_remove_pack(&f->prot_hook); @@ -1536,7 +1583,7 @@ static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new) } } -static int fanout_set_data_cbpf(struct packet_sock *po, char __user *data, +static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; @@ -1545,10 +1592,10 @@ static int fanout_set_data_cbpf(struct packet_sock *po, char __user *data, if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; - if (len != sizeof(fprog)) - return -EINVAL; - if (copy_from_user(&fprog, data, len)) - return -EFAULT; + + ret = copy_bpf_fprog_from_user(&fprog, data, len); + if (ret) + return ret; ret = bpf_prog_create_from_user(&new, &fprog, NULL, false); if (ret) @@ -1558,7 +1605,7 @@ static int fanout_set_data_cbpf(struct packet_sock *po, char __user *data, return 0; } -static int fanout_set_data_ebpf(struct packet_sock *po, char __user *data, +static int fanout_set_data_ebpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; @@ -1568,7 +1615,7 @@ static int fanout_set_data_ebpf(struct packet_sock *po, char __user *data, return -EPERM; if (len != sizeof(fd)) return -EINVAL; - if (copy_from_user(&fd, data, len)) + if (copy_from_sockptr(&fd, data, len)) return -EFAULT; new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); @@ -1579,7 +1626,7 @@ static int fanout_set_data_ebpf(struct packet_sock *po, char __user *data, return 0; } -static int fanout_set_data(struct packet_sock *po, char __user *data, +static int fanout_set_data(struct packet_sock *po, sockptr_t data, unsigned int len) { switch (po->fanout->type) { @@ -1631,19 +1678,22 @@ static bool fanout_find_new_id(struct sock *sk, u16 *new_id) return false; } -static int fanout_add(struct sock *sk, u16 id, u16 type_flags) +static int fanout_add(struct sock *sk, struct fanout_args *args) { struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); + u16 type_flags = args->type_flags; struct packet_fanout *f, *match; u8 type = type_flags & 0xff; u8 flags = type_flags >> 8; + u16 id = args->id; int err; switch (type) { case PACKET_FANOUT_ROLLOVER: if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER) return -EINVAL; + break; case PACKET_FANOUT_HASH: case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: @@ -1695,11 +1745,21 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) } } err = -EINVAL; - if (match && match->flags != flags) - goto out; - if (!match) { + if (match) { + if (match->flags != flags) + goto out; + if (args->max_num_members && + args->max_num_members != match->max_num_members) + goto out; + } else { + if (args->max_num_members > PACKET_FANOUT_MAX) + goto out; + if (!args->max_num_members) + /* legacy PACKET_FANOUT_MAX */ + args->max_num_members = 256; err = -ENOMEM; - match = kzalloc(sizeof(*match), GFP_KERNEL); + match = kvzalloc(struct_size(match, arr, args->max_num_members), + GFP_KERNEL); if (!match) goto out; write_pnet(&match->net, sock_net(sk)); @@ -1714,7 +1774,9 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; + match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; + match->max_num_members = args->max_num_members; list_add(&match->list, &fanout_list); } err = -EINVAL; @@ -1725,9 +1787,12 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; - if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) { + if (refcount_read(&match->sk_ref) < match->max_num_members) { __dev_remove_pack(&po->prot_hook); - po->fanout = match; + + /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ + WRITE_ONCE(po->fanout, match); + po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); @@ -1739,7 +1804,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) if (err && !refcount_read(&match->sk_ref)) { list_del(&match->list); - kfree(match); + kvfree(match); } out: @@ -1840,7 +1905,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, */ spkt->spkt_family = dev->type; - strlcpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); + strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); spkt->spkt_protocol = skb->protocol; /* @@ -1859,12 +1924,22 @@ oom: static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { + int depth; + if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && sock->type == SOCK_RAW) { skb_reset_mac_header(skb); skb->protocol = dev_parse_header_protocol(skb); } + /* Move network header to the right position for VLAN tagged packets */ + if (likely(skb->dev->type == ARPHRD_ETHER) && + eth_type_vlan(skb->protocol) && + __vlan_get_protocol(skb, skb->protocol, &depth) != 0) { + if (pskb_may_pull(skb, depth)) + skb_set_network_header(skb, depth); + } + skb_probe_transport_header(skb); } @@ -2038,7 +2113,7 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, * and skb->cb are mangled. It works because (and until) packets * falling here are owned by current CPU. Output packets are cloned * by dev_queue_xmit_nit(), input packets are processed by net_bh - * sequencially, so that if we return skb to original state on exit, + * sequentially, so that if we return skb to original state on exit, * we will not harm anyone. */ @@ -2064,7 +2139,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; - if (dev->header_ops) { + if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * @@ -2134,6 +2209,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; sock_skb_set_dropcount(sk, skb); + skb_clear_delivery_time(skb); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); @@ -2168,11 +2244,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; - unsigned short macoff, netoff, hdrlen; + unsigned short macoff, hdrlen; + unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; bool is_drop_n_account = false; + unsigned int slot_id = 0; bool do_vnet = false; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. @@ -2191,7 +2269,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; - if (dev->header_ops) { + if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { @@ -2236,6 +2314,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } macoff = netoff - maclen; } + if (netoff > USHRT_MAX) { + atomic_inc(&po->tp_drops); + goto drop_n_restore; + } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && @@ -2246,8 +2328,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, copy_skb = skb_get(skb); skb_head = skb->data; } - if (copy_skb) + if (copy_skb) { + memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0, + sizeof(PACKET_SKB_CB(copy_skb)->sa.ll)); skb_set_owner_r(copy_skb, sk); + } } snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) { @@ -2275,11 +2360,21 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (!h.raw) goto drop_n_account; + if (po->tp_version <= TPACKET_V2) { + slot_id = po->rx_ring.head; + if (test_bit(slot_id, po->rx_ring.rx_owner_map)) + goto drop_n_account; + __set_bit(slot_id, po->rx_ring.rx_owner_map); + } + if (do_vnet && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), - vio_le(), true, 0)) + vio_le(), true, 0)) { + if (po->tp_version == TPACKET_V3) + prb_clear_blk_fill_status(&po->rx_ring); goto drop_n_account; + } if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); @@ -2296,13 +2391,19 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; + skb_clear_delivery_time(copy_skb); __skb_queue_tail(&sk->sk_receive_queue, copy_skb); } spin_unlock(&sk->sk_receive_queue.lock); skb_copy_bits(skb, 0, h.raw + macoff, snaplen); - if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp))) + /* Always timestamp; prefer an existing software timestamp taken + * closer to the time of capture. + */ + ts_status = tpacket_get_timestamp(skb, &ts, + po->tp_tstamp | SOF_TIMESTAMPING_SOFTWARE); + if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; @@ -2380,9 +2481,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, #endif if (po->tp_version <= TPACKET_V2) { + spin_lock(&sk->sk_receive_queue.lock); __packet_set_status(po, h.raw, status); + __clear_bit(slot_id, po->rx_ring.rx_owner_map); + spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); - } else { + } else if (po->tp_version == TPACKET_V3) { prb_clear_blk_fill_status(&po->rx_ring); } @@ -2636,7 +2740,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2764,8 +2868,9 @@ tpacket_error: status = TP_STATUS_SEND_REQUEST; err = po->xmit(skb); - if (unlikely(err > 0)) { - err = net_xmit_errno(err); + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ @@ -2849,7 +2954,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2932,8 +3037,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (err) goto out_free; - if (sock->type == SOCK_RAW && - !dev_validate_header(dev, skb->data, len)) { + if ((sock->type == SOCK_RAW && + !dev_validate_header(dev, skb->data, len)) || !skb->len) { err = -EINVAL; goto out_free; } @@ -2952,6 +3057,11 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; + if (unlikely(extra_len == 4)) + skb->no_fcs = 1; + + packet_parse_headers(skb, sock); + if (has_vnet_hdr) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) @@ -2960,14 +3070,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) virtio_net_hdr_set_proto(skb, &vnet_hdr); } - packet_parse_headers(skb, sock); - - if (unlikely(extra_len == 4)) - skb->no_fcs = 1; - err = po->xmit(skb); - if (err > 0 && (err = net_xmit_errno(err)) != 0) - goto out_unlock; + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); + if (err) + goto out_unlock; + } dev_put(dev); @@ -2976,8 +3085,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) out_free: kfree_skb(skb); out_unlock: - if (dev) - dev_put(dev); + dev_put(dev); out: return err; } @@ -2987,10 +3095,13 @@ static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); - if (po->tx_ring.pg_vec) + /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. + * tpacket_snd() will redo the check safely. + */ + if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); - else - return packet_snd(sock, msg, len); + + return packet_snd(sock, msg, len); } /* @@ -3016,16 +3127,14 @@ static int packet_release(struct socket *sock) sk_del_node_init_rcu(sk); mutex_unlock(&net->packet.sklist_lock); - preempt_disable(); sock_prot_inuse_add(net, sk->sk_prot, -1); - preempt_enable(); spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); packet_cached_dev_reset(po); if (po->prot_hook.dev) { - dev_put(po->prot_hook.dev); + netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); @@ -3051,7 +3160,7 @@ static int packet_release(struct socket *sock) kfree(po->rollover); if (f) { fanout_release_data(f); - kfree(f); + kvfree(f); } /* * Now the socket is dead. No more input will appear. @@ -3077,12 +3186,10 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, __be16 proto) { struct packet_sock *po = pkt_sk(sk); - struct net_device *dev_curr; - __be16 proto_curr; - bool need_rehook; struct net_device *dev = NULL; - int ret = 0; bool unlisted = false; + bool need_rehook; + int ret = 0; lock_sock(sk); spin_lock(&po->bind_lock); @@ -3107,46 +3214,42 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, } } - if (dev) - dev_hold(dev); - - proto_curr = po->prot_hook.type; - dev_curr = po->prot_hook.dev; - - need_rehook = proto_curr != proto || dev_curr != dev; + need_rehook = po->prot_hook.type != proto || po->prot_hook.dev != dev; if (need_rehook) { + dev_hold(dev); if (po->running) { rcu_read_unlock(); /* prevents packet_notifier() from calling * register_prot_hook() */ - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); - dev_curr = po->prot_hook.dev; if (dev) unlisted = !dev_get_by_index_rcu(sock_net(sk), dev->ifindex); } BUG_ON(po->running); - po->num = proto; + WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; + netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); + if (unlikely(unlisted)) { - dev_put(dev); po->prot_hook.dev = NULL; - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { + netdev_hold(dev, &po->prot_hook.dev_tracker, + GFP_ATOMIC); po->prot_hook.dev = dev; - po->ifindex = dev ? dev->ifindex : 0; + WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } + dev_put(dev); } - if (dev_curr) - dev_put(dev_curr); if (proto == 0 || !need_rehook) goto out_unlock; @@ -3156,7 +3259,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } out_unlock: @@ -3274,6 +3377,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; + po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; @@ -3284,9 +3388,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock); - preempt_disable(); sock_prot_inuse_add(net, &packet_proto, 1); - preempt_enable(); return 0; out2: @@ -3334,7 +3436,7 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, * but then it will block. */ - skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err); + skb = skb_recv_datagram(sk, flags, &err); /* * An error occurred so return it. Because skb_recv_datagram() @@ -3377,9 +3479,11 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, sll->sll_protocol = skb->protocol; } - sock_recv_ts_and_drops(msg, sk, skb); + sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { + const size_t max_len = min(sizeof(skb->cb), + sizeof(struct sockaddr_storage)); int copy_len; /* If the address length field is there to be filled @@ -3402,6 +3506,10 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, msg->msg_namelen = sizeof(struct sockaddr_ll); } } + if (WARN_ON_ONCE(copy_len > max_len)) { + copy_len = max_len; + msg->msg_namelen = copy_len; + } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } @@ -3455,9 +3563,9 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) - strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); + strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); return sizeof(*uaddr); @@ -3470,16 +3578,18 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); + int ifindex; if (peer) return -EOPNOTSUPP; + ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; - sll->sll_ifindex = po->ifindex; - sll->sll_protocol = po->num; + sll->sll_ifindex = ifindex; + sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; @@ -3641,7 +3751,8 @@ static void packet_flush_mclist(struct sock *sk) } static int -packet_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) +packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, + unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); @@ -3661,7 +3772,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return -EINVAL; if (len > sizeof(mreq)) len = sizeof(mreq); - if (copy_from_user(&mreq, optval, len)) + if (copy_from_sockptr(&mreq, optval, len)) return -EFAULT; if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address))) return -EINVAL; @@ -3692,7 +3803,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen < len) { ret = -EINVAL; } else { - if (copy_from_user(&req_u.req, optval, len)) + if (copy_from_sockptr(&req_u.req, optval, len)) ret = -EFAULT; else ret = packet_set_ring(sk, &req_u, 0, @@ -3707,7 +3818,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; pkt_sk(sk)->copy_thresh = val; @@ -3719,7 +3830,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: @@ -3745,7 +3856,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; @@ -3765,7 +3876,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); @@ -3784,7 +3895,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen < sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); @@ -3798,7 +3909,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen < sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); @@ -3814,7 +3925,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return -EINVAL; if (optlen < sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); @@ -3833,7 +3944,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; po->tp_tstamp = val; @@ -3841,18 +3952,19 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv } case PACKET_FANOUT: { - int val; + struct fanout_args args = { 0 }; - if (optlen != sizeof(val)) + if (optlen != sizeof(int) && optlen != sizeof(args)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&args, optval, optlen)) return -EFAULT; - return fanout_add(sk, val & 0xffff, val >> 16); + return fanout_add(sk, &args); } case PACKET_FANOUT_DATA: { - if (!po->fanout) + /* Paired with the WRITE_ONCE() in fanout_add() */ + if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); @@ -3863,7 +3975,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val < 0 || val > 1) return -EINVAL; @@ -3877,16 +3989,13 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { - ret = -EBUSY; - } else { + if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec) po->tp_tx_has_off = !!val; - ret = 0; - } + release_sock(sk); return 0; } @@ -3896,7 +4005,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (copy_from_user(&val, optval, sizeof(val))) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; po->xmit = val ? packet_direct_xmit : dev_queue_xmit; @@ -4029,28 +4138,6 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, return 0; } - -#ifdef CONFIG_COMPAT -static int compat_packet_setsockopt(struct socket *sock, int level, int optname, - char __user *optval, unsigned int optlen) -{ - struct packet_sock *po = pkt_sk(sock->sk); - - if (level != SOL_PACKET) - return -ENOPROTOOPT; - - if (optname == PACKET_FANOUT_DATA && - po->fanout && po->fanout->type == PACKET_FANOUT_CBPF) { - optval = (char __user *)get_compat_bpf_fprog(optval); - if (!optval) - return -EFAULT; - optlen = sizeof(struct sock_fprog); - } - - return packet_setsockopt(sock, level, optname, optval, optlen); -} -#endif - static int packet_notifier(struct notifier_block *this, unsigned long msg, void *ptr) { @@ -4066,7 +4153,7 @@ static int packet_notifier(struct notifier_block *this, case NETDEV_UNREGISTER: if (po->mclist) packet_dev_mclist_delete(dev, &po->mclist); - /* fallthrough */ + fallthrough; case NETDEV_DOWN: if (dev->ifindex == po->ifindex) { @@ -4075,13 +4162,13 @@ static int packet_notifier(struct notifier_block *this, __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); - po->ifindex = -1; - if (po->prot_hook.dev) - dev_put(po->prot_hook.dev); + WRITE_ONCE(po->ifindex, -1); + netdev_put(po->prot_hook.dev, + &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); @@ -4277,11 +4364,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); + unsigned long *rx_owner_map = NULL; int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; __be16 num; - int err = -EINVAL; + int err; /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; @@ -4362,6 +4450,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } break; default: + if (!tx_ring) { + rx_owner_map = bitmap_alloc(req->tp_frame_nr, + GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); + if (!rx_owner_map) + goto out_free_pg_vec; + } break; } } @@ -4378,7 +4472,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, was_running = po->running; num = po->num; if (was_running) { - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); @@ -4391,6 +4485,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); + if (po->tp_version <= TPACKET_V2) + swap(rb->rx_owner_map, rx_owner_map); rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; @@ -4411,7 +4507,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, spin_lock(&po->bind_lock); if (was_running) { - po->num = num; + WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); @@ -4422,8 +4518,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } out_free_pg_vec: - if (pg_vec) + if (pg_vec) { + bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); + } out: return err; } @@ -4504,8 +4602,6 @@ static const struct proto_ops packet_ops_spkt = { .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, - .setsockopt = sock_no_setsockopt, - .getsockopt = sock_no_getsockopt, .sendmsg = packet_sendmsg_spkt, .recvmsg = packet_recvmsg, .mmap = sock_no_mmap, @@ -4528,9 +4624,6 @@ static const struct proto_ops packet_ops = { .shutdown = sock_no_shutdown, .setsockopt = packet_setsockopt, .getsockopt = packet_getsockopt, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_packet_setsockopt, -#endif .sendmsg = packet_sendmsg, .recvmsg = packet_recvmsg, .mmap = packet_mmap, @@ -4573,7 +4666,9 @@ static void packet_seq_stop(struct seq_file *seq, void *v) static int packet_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) - seq_puts(seq, "sk RefCnt Type Proto Iface R Rmem User Inode\n"); + seq_printf(seq, + "%*sRefCnt Type Proto Iface R Rmem User Inode\n", + IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk"); else { struct sock *s = sk_entry(v); const struct packet_sock *po = pkt_sk(s); @@ -4583,8 +4678,8 @@ static int packet_seq_show(struct seq_file *seq, void *v) s, refcount_read(&s->sk_refcnt), s->sk_type, - ntohs(po->num), - po->ifindex, + ntohs(READ_ONCE(po->num)), + READ_ONCE(po->ifindex), po->running, atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), @@ -4607,9 +4702,11 @@ static int __net_init packet_net_init(struct net *net) mutex_init(&net->packet.sklist_lock); INIT_HLIST_HEAD(&net->packet.sklist); +#ifdef CONFIG_PROC_FS if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; +#endif /* CONFIG_PROC_FS */ return 0; } @@ -4628,37 +4725,37 @@ static struct pernet_operations packet_net_ops = { static void __exit packet_exit(void) { - unregister_netdevice_notifier(&packet_netdev_notifier); - unregister_pernet_subsys(&packet_net_ops); sock_unregister(PF_PACKET); proto_unregister(&packet_proto); + unregister_netdevice_notifier(&packet_netdev_notifier); + unregister_pernet_subsys(&packet_net_ops); } static int __init packet_init(void) { int rc; - rc = proto_register(&packet_proto, 0); - if (rc) - goto out; - rc = sock_register(&packet_family_ops); - if (rc) - goto out_proto; rc = register_pernet_subsys(&packet_net_ops); if (rc) - goto out_sock; + goto out; rc = register_netdevice_notifier(&packet_netdev_notifier); if (rc) goto out_pernet; + rc = proto_register(&packet_proto, 0); + if (rc) + goto out_notifier; + rc = sock_register(&packet_family_ops); + if (rc) + goto out_proto; return 0; -out_pernet: - unregister_pernet_subsys(&packet_net_ops); -out_sock: - sock_unregister(PF_PACKET); out_proto: proto_unregister(&packet_proto); +out_notifier: + unregister_netdevice_notifier(&packet_netdev_notifier); +out_pernet: + unregister_pernet_subsys(&packet_net_ops); out: return rc; } diff --git a/net/packet/internal.h b/net/packet/internal.h index 82fb2b10f790..48af35b1aed2 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -39,7 +39,7 @@ struct tpacket_kbdq_core { char *nxt_offset; struct sk_buff *skb; - atomic_t blk_fill_in_prog; + rwlock_t blk_fill_in_prog_lock; /* Default is set to 8ms */ #define DEFAULT_PRB_RETIRE_TOV (8) @@ -70,15 +70,19 @@ struct packet_ring_buffer { unsigned int __percpu *pending_refcnt; - struct tpacket_kbdq_core prb_bdqc; + union { + unsigned long *rx_owner_map; + struct tpacket_kbdq_core prb_bdqc; + }; }; extern struct mutex fanout_mutex; -#define PACKET_FANOUT_MAX 256 +#define PACKET_FANOUT_MAX (1 << 16) struct packet_fanout { possible_net_t net; unsigned int num_members; + u32 max_num_members; u16 id; u8 type; u8 flags; @@ -87,10 +91,10 @@ struct packet_fanout { struct bpf_prog __rcu *bpf_prog; }; struct list_head list; - struct sock *arr[PACKET_FANOUT_MAX]; spinlock_t lock; refcount_t sk_ref; struct packet_type prot_hook ____cacheline_aligned_in_smp; + struct sock __rcu *arr[]; }; struct packet_rollover { @@ -135,7 +139,7 @@ struct packet_sock { atomic_t tp_drops ____cacheline_aligned_in_smp; }; -static struct packet_sock *pkt_sk(struct sock *sk) +static inline struct packet_sock *pkt_sk(struct sock *sk) { return (struct packet_sock *)sk; } |