From 52f993b8e89487ec9ee15a7fb4979e0f09a45b27 Mon Sep 17 00:00:00 2001 From: Yunhong Jiang Date: Wed, 8 Mar 2017 23:13:28 -0800 Subject: Upgrade to 4.4.50-rt62 The current kernel is based on rt kernel v4.4.6-rt14. We will upgrade it to 4.4.50-rt62. The command to achieve it is: a) Clone a git repo from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git b) Get the diff between this two changesets: git diff 640eca2901f3435e616157b11379d3223a44b391 705619beeea1b0b48219a683fd1a901a86fdaf5e where the two commits are: [yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only 640eca2901f3435e616157b11379d3223a44b391 640eca2901f3 v4.4.6-rt14 localversion-rt [yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only 705619beeea1b0b48219a683fd1a901a86fdaf5e 705619beeea1 Linux 4.4.50-rt62 localversion-rt c) One patch has been backported thus revert the patch before applying. filterdiff -p1 -x scripts/package/Makefile ~/tmp/v4.4.6-rt14-4.4.50-rt62.diff |patch -p1 --dry-run Upstream status: backport Change-Id: I244d57a32f6066e5a5b9915f9fbf99e7bbca6e01 Signed-off-by: Yunhong Jiang --- kernel/net/core/dev.c | 139 ++++++++++++++++++++++++--------------- kernel/net/core/drop_monitor.c | 39 ++++++++--- kernel/net/core/filter.c | 61 ++++++++++------- kernel/net/core/flow_dissector.c | 56 ++++++++++++++-- kernel/net/core/neighbour.c | 6 +- kernel/net/core/net_namespace.c | 2 + kernel/net/core/pktgen.c | 38 ++++++----- kernel/net/core/rtnetlink.c | 24 ++++--- kernel/net/core/skbuff.c | 15 +++-- kernel/net/core/sock.c | 5 +- 10 files changed, 256 insertions(+), 129 deletions(-) (limited to 'kernel/net/core') diff --git a/kernel/net/core/dev.c b/kernel/net/core/dev.c index 0e17592ad..aa6165e02 100644 --- a/kernel/net/core/dev.c +++ b/kernel/net/core/dev.c @@ -1682,24 +1682,19 @@ EXPORT_SYMBOL_GPL(net_dec_ingress_queue); static struct static_key netstamp_needed __read_mostly; #ifdef HAVE_JUMP_LABEL -/* We are not allowed to call static_key_slow_dec() from irq context - * If net_disable_timestamp() is called from irq context, defer the - * static_key_slow_dec() calls. - */ static atomic_t netstamp_needed_deferred; -#endif - -void net_enable_timestamp(void) +static void netstamp_clear(struct work_struct *work) { -#ifdef HAVE_JUMP_LABEL int deferred = atomic_xchg(&netstamp_needed_deferred, 0); - if (deferred) { - while (--deferred) - static_key_slow_dec(&netstamp_needed); - return; - } + while (deferred--) + static_key_slow_dec(&netstamp_needed); +} +static DECLARE_WORK(netstamp_work, netstamp_clear); #endif + +void net_enable_timestamp(void) +{ static_key_slow_inc(&netstamp_needed); } EXPORT_SYMBOL(net_enable_timestamp); @@ -1707,12 +1702,12 @@ EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef HAVE_JUMP_LABEL - if (in_interrupt()) { - atomic_inc(&netstamp_needed_deferred); - return; - } -#endif + /* net_disable_timestamp() can be called from non process context */ + atomic_inc(&netstamp_needed_deferred); + schedule_work(&netstamp_work); +#else static_key_slow_dec(&netstamp_needed); +#endif } EXPORT_SYMBOL(net_disable_timestamp); @@ -2470,7 +2465,7 @@ int skb_checksum_help(struct sk_buff *skb) goto out; } - *(__sum16 *)(skb->data + offset) = csum_fold(csum); + *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: @@ -2658,9 +2653,9 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(skb->dev, skb)) { - features &= ~NETIF_F_SG; } + if (illegal_highdma(skb->dev, skb)) + features &= ~NETIF_F_SG; return features; } @@ -2844,6 +2839,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d } return head; } +EXPORT_SYMBOL_GPL(validate_xmit_skb_list); static void qdisc_pkt_len_init(struct sk_buff *skb) { @@ -3797,6 +3793,22 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, return skb; } +/** + * netdev_is_rx_handler_busy - check if receive handler is registered + * @dev: device to check + * + * Check if a receive handler is already registered for a given device. + * Return true if there one. + * + * The caller must hold the rtnl_mutex. + */ +bool netdev_is_rx_handler_busy(struct net_device *dev) +{ + ASSERT_RTNL(); + return dev && rtnl_dereference(dev->rx_handler); +} +EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy); + /** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for @@ -4249,7 +4261,9 @@ static void skb_gro_reset_offset(struct sk_buff *skb) pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); - NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); + NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, + skb_frag_size(frag0), + skb->end - skb->tail); } } @@ -4302,7 +4316,8 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; - NAPI_GRO_CB(skb)->udp_mark = 0; + NAPI_GRO_CB(skb)->encap_mark = 0; + NAPI_GRO_CB(skb)->recursion_counter = 0; NAPI_GRO_CB(skb)->gro_remcsum_start = 0; /* Setup for GRO checksum validation */ @@ -4694,6 +4709,7 @@ void __napi_schedule(struct napi_struct *n) } EXPORT_SYMBOL(__napi_schedule); +#ifndef CONFIG_PREEMPT_RT_FULL /** * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule @@ -4705,6 +4721,7 @@ void __napi_schedule_irqoff(struct napi_struct *n) ____napi_schedule(this_cpu_ptr(&softnet_data), n); } EXPORT_SYMBOL(__napi_schedule_irqoff); +#endif void __napi_complete(struct napi_struct *n) { @@ -4931,13 +4948,21 @@ static void net_rx_action(struct softirq_action *h) struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + 2; int budget = netdev_budget; + struct sk_buff_head tofree_q; + struct sk_buff *skb; LIST_HEAD(list); LIST_HEAD(repoll); + __skb_queue_head_init(&tofree_q); + local_irq_disable(); + skb_queue_splice_init(&sd->tofree_queue, &tofree_q); list_splice_init(&sd->poll_list, &list); local_irq_enable(); + while ((skb = __skb_dequeue(&tofree_q))) + kfree_skb(skb); + for (;;) { struct napi_struct *n; @@ -5270,6 +5295,7 @@ static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, + u16 ref_nr, struct list_head *dev_list, void *private, bool master) { @@ -5279,7 +5305,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { - adj->ref_nr++; + adj->ref_nr += ref_nr; return 0; } @@ -5289,7 +5315,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj->dev = adj_dev; adj->master = master; - adj->ref_nr = 1; + adj->ref_nr = ref_nr; adj->private = private; dev_hold(adj_dev); @@ -5328,6 +5354,7 @@ free_adj: static void __netdev_adjacent_dev_remove(struct net_device *dev, struct net_device *adj_dev, + u16 ref_nr, struct list_head *dev_list) { struct netdev_adjacent *adj; @@ -5340,10 +5367,10 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, BUG(); } - if (adj->ref_nr > 1) { - pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name, - adj->ref_nr-1); - adj->ref_nr--; + if (adj->ref_nr > ref_nr) { + pr_debug("%s to %s ref_nr-%d = %d\n", dev->name, adj_dev->name, + ref_nr, adj->ref_nr-ref_nr); + adj->ref_nr -= ref_nr; return; } @@ -5362,21 +5389,22 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, static int __netdev_adjacent_dev_link_lists(struct net_device *dev, struct net_device *upper_dev, + u16 ref_nr, struct list_head *up_list, struct list_head *down_list, void *private, bool master) { int ret; - ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, - master); + ret = __netdev_adjacent_dev_insert(dev, upper_dev, ref_nr, up_list, + private, master); if (ret) return ret; - ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, - false); + ret = __netdev_adjacent_dev_insert(upper_dev, dev, ref_nr, down_list, + private, false); if (ret) { - __netdev_adjacent_dev_remove(dev, upper_dev, up_list); + __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list); return ret; } @@ -5384,9 +5412,10 @@ static int __netdev_adjacent_dev_link_lists(struct net_device *dev, } static int __netdev_adjacent_dev_link(struct net_device *dev, - struct net_device *upper_dev) + struct net_device *upper_dev, + u16 ref_nr) { - return __netdev_adjacent_dev_link_lists(dev, upper_dev, + return __netdev_adjacent_dev_link_lists(dev, upper_dev, ref_nr, &dev->all_adj_list.upper, &upper_dev->all_adj_list.lower, NULL, false); @@ -5394,17 +5423,19 @@ static int __netdev_adjacent_dev_link(struct net_device *dev, static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, struct net_device *upper_dev, + u16 ref_nr, struct list_head *up_list, struct list_head *down_list) { - __netdev_adjacent_dev_remove(dev, upper_dev, up_list); - __netdev_adjacent_dev_remove(upper_dev, dev, down_list); + __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list); + __netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list); } static void __netdev_adjacent_dev_unlink(struct net_device *dev, - struct net_device *upper_dev) + struct net_device *upper_dev, + u16 ref_nr) { - __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, ref_nr, &dev->all_adj_list.upper, &upper_dev->all_adj_list.lower); } @@ -5413,17 +5444,17 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, struct net_device *upper_dev, void *private, bool master) { - int ret = __netdev_adjacent_dev_link(dev, upper_dev); + int ret = __netdev_adjacent_dev_link(dev, upper_dev, 1); if (ret) return ret; - ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, + ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, 1, &dev->adj_list.upper, &upper_dev->adj_list.lower, private, master); if (ret) { - __netdev_adjacent_dev_unlink(dev, upper_dev); + __netdev_adjacent_dev_unlink(dev, upper_dev, 1); return ret; } @@ -5433,8 +5464,8 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, struct net_device *upper_dev) { - __netdev_adjacent_dev_unlink(dev, upper_dev); - __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + __netdev_adjacent_dev_unlink(dev, upper_dev, 1); + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1, &dev->adj_list.upper, &upper_dev->adj_list.lower); } @@ -5486,7 +5517,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { pr_debug("Interlinking %s with %s, non-neighbour\n", i->dev->name, j->dev->name); - ret = __netdev_adjacent_dev_link(i->dev, j->dev); + ret = __netdev_adjacent_dev_link(i->dev, j->dev, i->ref_nr); if (ret) goto rollback_mesh; } @@ -5496,7 +5527,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { pr_debug("linking %s's upper device %s with %s\n", upper_dev->name, i->dev->name, dev->name); - ret = __netdev_adjacent_dev_link(dev, i->dev); + ret = __netdev_adjacent_dev_link(dev, i->dev, i->ref_nr); if (ret) goto rollback_upper_mesh; } @@ -5505,7 +5536,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, list_for_each_entry(i, &dev->all_adj_list.lower, list) { pr_debug("linking %s's lower device %s with %s\n", dev->name, i->dev->name, upper_dev->name); - ret = __netdev_adjacent_dev_link(i->dev, upper_dev); + ret = __netdev_adjacent_dev_link(i->dev, upper_dev, i->ref_nr); if (ret) goto rollback_lower_mesh; } @@ -5519,7 +5550,7 @@ rollback_lower_mesh: list_for_each_entry(i, &dev->all_adj_list.lower, list) { if (i == to_i) break; - __netdev_adjacent_dev_unlink(i->dev, upper_dev); + __netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr); } i = NULL; @@ -5529,7 +5560,7 @@ rollback_upper_mesh: list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { if (i == to_i) break; - __netdev_adjacent_dev_unlink(dev, i->dev); + __netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr); } i = j = NULL; @@ -5541,7 +5572,7 @@ rollback_mesh: list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { if (i == to_i && j == to_j) break; - __netdev_adjacent_dev_unlink(i->dev, j->dev); + __netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr); } if (i == to_i) break; @@ -5625,16 +5656,16 @@ void netdev_upper_dev_unlink(struct net_device *dev, */ list_for_each_entry(i, &dev->all_adj_list.lower, list) list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) - __netdev_adjacent_dev_unlink(i->dev, j->dev); + __netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr); /* remove also the devices itself from lower/upper device * list */ list_for_each_entry(i, &dev->all_adj_list.lower, list) - __netdev_adjacent_dev_unlink(i->dev, upper_dev); + __netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr); list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) - __netdev_adjacent_dev_unlink(dev, i->dev); + __netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr); call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev, &changeupper_info.info); diff --git a/kernel/net/core/drop_monitor.c b/kernel/net/core/drop_monitor.c index 252e155c8..a2270188b 100644 --- a/kernel/net/core/drop_monitor.c +++ b/kernel/net/core/drop_monitor.c @@ -80,6 +80,7 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) struct nlattr *nla; struct sk_buff *skb; unsigned long flags; + void *msg_header; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); @@ -87,21 +88,41 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) skb = genlmsg_new(al, GFP_KERNEL); - if (skb) { - genlmsg_put(skb, 0, 0, &net_drop_monitor_family, - 0, NET_DM_CMD_ALERT); - nla = nla_reserve(skb, NLA_UNSPEC, - sizeof(struct net_dm_alert_msg)); - msg = nla_data(nla); - memset(msg, 0, al); - } else { - mod_timer(&data->send_timer, jiffies + HZ / 10); + if (!skb) + goto err; + + msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family, + 0, NET_DM_CMD_ALERT); + if (!msg_header) { + nlmsg_free(skb); + skb = NULL; + goto err; + } + nla = nla_reserve(skb, NLA_UNSPEC, + sizeof(struct net_dm_alert_msg)); + if (!nla) { + nlmsg_free(skb); + skb = NULL; + goto err; } + msg = nla_data(nla); + memset(msg, 0, al); + goto out; +err: + mod_timer(&data->send_timer, jiffies + HZ / 10); +out: spin_lock_irqsave(&data->lock, flags); swap(data->skb, skb); spin_unlock_irqrestore(&data->lock, flags); + if (skb) { + struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data; + struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh); + + genlmsg_end(skb, genlmsg_data(gnlh)); + } + return skb; } diff --git a/kernel/net/core/filter.c b/kernel/net/core/filter.c index 37157c4c1..e94355452 100644 --- a/kernel/net/core/filter.c +++ b/kernel/net/core/filter.c @@ -52,9 +52,10 @@ #include /** - * sk_filter - run a packet through a socket filter + * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter + * @cap: limit on how short the eBPF program may trim the packet * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller @@ -63,7 +64,7 @@ * be accepted or -EPERM if the packet should be tossed. * */ -int sk_filter(struct sock *sk, struct sk_buff *skb) +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) { int err; struct sk_filter *filter; @@ -84,14 +85,13 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) filter = rcu_dereference(sk->sk_filter); if (filter) { unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb); - - err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; + err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; } rcu_read_unlock(); return err; } -EXPORT_SYMBOL(sk_filter); +EXPORT_SYMBOL(sk_filter_trim_cap); static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { @@ -1139,7 +1139,8 @@ void bpf_prog_destroy(struct bpf_prog *fp) } EXPORT_SYMBOL_GPL(bpf_prog_destroy); -static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) +static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk, + bool locked) { struct sk_filter *fp, *old_fp; @@ -1155,10 +1156,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) return -ENOMEM; } - old_fp = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + old_fp = rcu_dereference_protected(sk->sk_filter, locked); rcu_assign_pointer(sk->sk_filter, fp); - if (old_fp) sk_filter_uncharge(sk, old_fp); @@ -1175,7 +1174,8 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) * occurs or there is insufficient memory for the filter a negative * errno code is returned. On success the return is zero. */ -int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +int __sk_attach_filter(struct sock_fprog *fprog, struct sock *sk, + bool locked) { unsigned int fsize = bpf_classic_proglen(fprog); unsigned int bpf_fsize = bpf_prog_size(fprog->len); @@ -1213,7 +1213,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (IS_ERR(prog)) return PTR_ERR(prog); - err = __sk_attach_prog(prog, sk); + err = __sk_attach_prog(prog, sk, locked); if (err < 0) { __bpf_prog_release(prog); return err; @@ -1221,7 +1221,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) return 0; } -EXPORT_SYMBOL_GPL(sk_attach_filter); +EXPORT_SYMBOL_GPL(__sk_attach_filter); + +int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) +{ + return __sk_attach_filter(fprog, sk, sock_owned_by_user(sk)); +} int sk_attach_bpf(u32 ufd, struct sock *sk) { @@ -1240,7 +1245,7 @@ int sk_attach_bpf(u32 ufd, struct sock *sk) return -EINVAL; } - err = __sk_attach_prog(prog, sk); + err = __sk_attach_prog(prog, sk, sock_owned_by_user(sk)); if (err < 0) { bpf_prog_put(prog); return err; @@ -1270,9 +1275,7 @@ 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; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + len))) + if (unlikely(skb_try_make_writable(skb, offset + len))) return -EFAULT; ptr = skb_header_pointer(skb, offset, len, buf); @@ -1316,8 +1319,7 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) if (unlikely((u32) offset > 0xffff)) return -EFAULT; - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(sum)))) + if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1362,9 +1364,7 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) if (unlikely((u32) offset > 0xffff)) return -EFAULT; - - if (unlikely(skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(sum)))) + if (unlikely(skb_try_make_writable(skb, offset + sizeof(sum)))) return -EFAULT; ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); @@ -1549,6 +1549,13 @@ bool bpf_helper_changes_skb_data(void *func) return true; if (func == bpf_skb_vlan_pop) return true; + if (func == bpf_skb_store_bytes) + return true; + if (func == bpf_l3_csum_replace) + return true; + if (func == bpf_l4_csum_replace) + return true; + return false; } @@ -1913,7 +1920,7 @@ static int __init register_sk_filter_ops(void) } late_initcall(register_sk_filter_ops); -int sk_detach_filter(struct sock *sk) +int __sk_detach_filter(struct sock *sk, bool locked) { int ret = -ENOENT; struct sk_filter *filter; @@ -1921,8 +1928,7 @@ int sk_detach_filter(struct sock *sk) if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; - filter = rcu_dereference_protected(sk->sk_filter, - sock_owned_by_user(sk)); + filter = rcu_dereference_protected(sk->sk_filter, locked); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); @@ -1931,7 +1937,12 @@ int sk_detach_filter(struct sock *sk) return ret; } -EXPORT_SYMBOL_GPL(sk_detach_filter); +EXPORT_SYMBOL_GPL(__sk_detach_filter); + +int sk_detach_filter(struct sock *sk) +{ + return __sk_detach_filter(sk, sock_owned_by_user(sk)); +} int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len) diff --git a/kernel/net/core/flow_dissector.c b/kernel/net/core/flow_dissector.c index 12e700332..ee9082792 100644 --- a/kernel/net/core/flow_dissector.c +++ b/kernel/net/core/flow_dissector.c @@ -131,7 +131,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_keyid *key_keyid; u8 ip_proto = 0; - bool ret = false; + bool ret; if (!data) { data = skb->data; @@ -492,12 +492,17 @@ ip_proto_again: out_good: ret = true; -out_bad: + key_control->thoff = (u16)nhoff; +out: key_basic->n_proto = proto; key_basic->ip_proto = ip_proto; - key_control->thoff = (u16)nhoff; return ret; + +out_bad: + ret = false; + key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); + goto out; } EXPORT_SYMBOL(__skb_flow_dissect); @@ -662,6 +667,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest, } EXPORT_SYMBOL(make_flow_keys_digest); +static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; + +u32 __skb_get_hash_symmetric(struct sk_buff *skb) +{ + struct flow_keys keys; + + __flow_hash_secret_init(); + + memset(&keys, 0, sizeof(keys)); + __skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, + NULL, 0, 0, 0, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + + return __flow_hash_from_keys(&keys, hashrnd); +} +EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); + /** * __skb_get_hash: calculate a flow hash * @skb: sk_buff to calculate flow hash from @@ -874,6 +896,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = { }, }; +static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { + { + .key_id = FLOW_DISSECTOR_KEY_CONTROL, + .offset = offsetof(struct flow_keys, control), + }, + { + .key_id = FLOW_DISSECTOR_KEY_BASIC, + .offset = offsetof(struct flow_keys, basic), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v4addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v6addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_PORTS, + .offset = offsetof(struct flow_keys, ports), + }, +}; + static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, @@ -895,10 +940,13 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); + skb_flow_dissector_init(&flow_keys_dissector_symmetric, + flow_keys_dissector_symmetric_keys, + ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_buf_dissector, flow_keys_buf_dissector_keys, ARRAY_SIZE(flow_keys_buf_dissector_keys)); return 0; } -late_initcall_sync(init_default_flow_dissectors); +core_initcall(init_default_flow_dissectors); diff --git a/kernel/net/core/neighbour.c b/kernel/net/core/neighbour.c index f18ae91b6..769cece9b 100644 --- a/kernel/net/core/neighbour.c +++ b/kernel/net/core/neighbour.c @@ -2467,13 +2467,17 @@ int neigh_xmit(int index, struct net_device *dev, tbl = neigh_tables[index]; if (!tbl) goto out; + rcu_read_lock_bh(); neigh = __neigh_lookup_noref(tbl, addr, dev); if (!neigh) neigh = __neigh_create(tbl, addr, dev, false); err = PTR_ERR(neigh); - if (IS_ERR(neigh)) + if (IS_ERR(neigh)) { + rcu_read_unlock_bh(); goto out_kfree_skb; + } err = neigh->output(neigh, skb); + rcu_read_unlock_bh(); } else if (index == NEIGH_LINK_TABLE) { err = dev_hard_header(skb, dev, ntohs(skb->protocol), diff --git a/kernel/net/core/net_namespace.c b/kernel/net/core/net_namespace.c index 2c2eb1b62..2e9a1c281 100644 --- a/kernel/net/core/net_namespace.c +++ b/kernel/net/core/net_namespace.c @@ -217,6 +217,8 @@ int peernet2id_alloc(struct net *net, struct net *peer) bool alloc; int id; + if (atomic_read(&net->count) == 0) + return NETNSA_NSID_NOT_ASSIGNED; spin_lock_irqsave(&net->nsid_lock, flags); alloc = atomic_read(&peer->count) == 0 ? false : true; id = __peernet2id_alloc(net, peer, &alloc); diff --git a/kernel/net/core/pktgen.c b/kernel/net/core/pktgen.c index 4da4d51a2..b6327601f 100644 --- a/kernel/net/core/pktgen.c +++ b/kernel/net/core/pktgen.c @@ -215,8 +215,8 @@ #define M_NETIF_RECEIVE 1 /* Inject packets into stack */ /* If lock -- protects updating of if_list */ -#define if_lock(t) spin_lock(&(t->if_lock)); -#define if_unlock(t) spin_unlock(&(t->if_lock)); +#define if_lock(t) mutex_lock(&(t->if_lock)); +#define if_unlock(t) mutex_unlock(&(t->if_lock)); /* Used to help with determining the pkts on receive */ #define PKTGEN_MAGIC 0xbe9be955 @@ -422,7 +422,7 @@ struct pktgen_net { }; struct pktgen_thread { - spinlock_t if_lock; /* for list of devices */ + struct mutex if_lock; /* for list of devices */ struct list_head if_list; /* All device here */ struct list_head th_list; struct task_struct *tsk; @@ -2002,11 +2002,13 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d { struct pktgen_thread *t; + mutex_lock(&pktgen_thread_lock); + list_for_each_entry(t, &pn->pktgen_threads, th_list) { struct pktgen_dev *pkt_dev; - rcu_read_lock(); - list_for_each_entry_rcu(pkt_dev, &t->if_list, list) { + if_lock(t); + list_for_each_entry(pkt_dev, &t->if_list, list) { if (pkt_dev->odev != dev) continue; @@ -2021,8 +2023,9 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d dev->name); break; } - rcu_read_unlock(); + if_unlock(t); } + mutex_unlock(&pktgen_thread_lock); } static int pktgen_device_event(struct notifier_block *unused, @@ -2278,7 +2281,7 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev) { - pkt_dev->pkt_overhead = LL_RESERVED_SPACE(pkt_dev->odev); + pkt_dev->pkt_overhead = 0; pkt_dev->pkt_overhead += pkt_dev->nr_labels*sizeof(u32); pkt_dev->pkt_overhead += VLAN_TAG_SIZE(pkt_dev); pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev); @@ -2769,13 +2772,13 @@ static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, } static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, - struct pktgen_dev *pkt_dev, - unsigned int extralen) + struct pktgen_dev *pkt_dev) { + unsigned int extralen = LL_RESERVED_SPACE(dev); struct sk_buff *skb = NULL; - unsigned int size = pkt_dev->cur_pkt_size + 64 + extralen + - pkt_dev->pkt_overhead; + unsigned int size; + size = pkt_dev->cur_pkt_size + 64 + extralen + pkt_dev->pkt_overhead; if (pkt_dev->flags & F_NODE) { int node = pkt_dev->node >= 0 ? pkt_dev->node : numa_node_id(); @@ -2788,8 +2791,9 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT); } + /* the caller pre-fetches from skb->data and reserves for the mac hdr */ if (likely(skb)) - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, extralen - 16); return skb; } @@ -2822,16 +2826,14 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, mod_cur_headers(pkt_dev); queue_map = pkt_dev->cur_queue_map; - datalen = (odev->hard_header_len + 16) & ~0xf; - - skb = pktgen_alloc_skb(odev, pkt_dev, datalen); + skb = pktgen_alloc_skb(odev, pkt_dev); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; } prefetchw(skb->data); - skb_reserve(skb, datalen); + skb_reserve(skb, 16); /* Reserve for ethernet and IP header */ eth = (__u8 *) skb_push(skb, 14); @@ -2951,7 +2953,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, mod_cur_headers(pkt_dev); queue_map = pkt_dev->cur_queue_map; - skb = pktgen_alloc_skb(odev, pkt_dev, 16); + skb = pktgen_alloc_skb(odev, pkt_dev); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; @@ -3727,7 +3729,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) return -ENOMEM; } - spin_lock_init(&t->if_lock); + mutex_init(&t->if_lock); t->cpu = cpu; INIT_LIST_HEAD(&t->if_list); diff --git a/kernel/net/core/rtnetlink.c b/kernel/net/core/rtnetlink.c index 34ba7a088..b94e165a4 100644 --- a/kernel/net/core/rtnetlink.c +++ b/kernel/net/core/rtnetlink.c @@ -905,6 +905,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_link_get_af_size(dev, ext_filter_mask) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(IFNAMSIZ) /* IFLA_PHYS_PORT_NAME */ + nla_total_size(1); /* IFLA_PROTO_DOWN */ } @@ -1174,14 +1175,16 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb, static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev) { - struct rtnl_link_ifmap map = { - .mem_start = dev->mem_start, - .mem_end = dev->mem_end, - .base_addr = dev->base_addr, - .irq = dev->irq, - .dma = dev->dma, - .port = dev->if_port, - }; + struct rtnl_link_ifmap map; + + memset(&map, 0, sizeof(map)); + map.mem_start = dev->mem_start; + map.mem_end = dev->mem_end; + map.base_addr = dev->base_addr; + map.irq = dev->irq; + map.dma = dev->dma; + map.port = dev->if_port; + if (nla_put(skb, IFLA_MAP, sizeof(map), &map)) return -EMSGSIZE; @@ -2597,7 +2600,10 @@ nla_put_failure: static inline size_t rtnl_fdb_nlmsg_size(void) { - return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN); + return NLMSG_ALIGN(sizeof(struct ndmsg)) + + nla_total_size(ETH_ALEN) + /* NDA_LLADDR */ + nla_total_size(sizeof(u16)) + /* NDA_VLAN */ + 0; } static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type) diff --git a/kernel/net/core/skbuff.c b/kernel/net/core/skbuff.c index 12780dc62..c8d778f40 100644 --- a/kernel/net/core/skbuff.c +++ b/kernel/net/core/skbuff.c @@ -4096,9 +4096,9 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, if (!pskb_may_pull(skb_chk, offset)) goto err; - __skb_pull(skb_chk, offset); + skb_pull_rcsum(skb_chk, offset); ret = skb_chkf(skb_chk); - __skb_push(skb_chk, offset); + skb_push_rcsum(skb_chk, offset); if (ret) goto err; @@ -4421,15 +4421,16 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) __skb_push(skb, offset); err = __vlan_insert_tag(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); - if (err) + if (err) { + __skb_pull(skb, offset); return err; + } + skb->protocol = skb->vlan_proto; skb->mac_len += VLAN_HLEN; - __skb_pull(skb, offset); - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_add(skb->csum, csum_partial(skb->data - + (2 * ETH_ALEN), VLAN_HLEN, 0)); + skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); + __skb_pull(skb, offset); } __vlan_hwaccel_put_tag(skb, vlan_proto, vlan_tci); return 0; diff --git a/kernel/net/core/sock.c b/kernel/net/core/sock.c index 9c3234299..03ba64820 100644 --- a/kernel/net/core/sock.c +++ b/kernel/net/core/sock.c @@ -745,7 +745,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, val = min_t(u32, val, sysctl_wmem_max); set_sndbuf: sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF); + sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -781,7 +781,7 @@ set_rcvbuf: * returning the value we actually used in getsockopt * is the most desirable behavior. */ - sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF); + sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_RCVBUFFORCE: @@ -1562,6 +1562,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) } newsk->sk_err = 0; + newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); atomic64_set(&newsk->sk_cookie, 0); -- cgit 1.2.3-korg