diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 133 | ||||
-rw-r--r-- | net/core/dst.c | 16 | ||||
-rw-r--r-- | net/core/ethtool.c | 2 | ||||
-rw-r--r-- | net/core/filter.c | 142 | ||||
-rw-r--r-- | net/core/lwtunnel.c | 4 | ||||
-rw-r--r-- | net/core/neighbour.c | 45 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 11 | ||||
-rw-r--r-- | net/core/netpoll.c | 23 | ||||
-rw-r--r-- | net/core/ptp_classifier.c | 16 | ||||
-rw-r--r-- | net/core/request_sock.c | 88 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 38 | ||||
-rw-r--r-- | net/core/skbuff.c | 8 | ||||
-rw-r--r-- | net/core/sock.c | 81 | ||||
-rw-r--r-- | net/core/sock_diag.c | 14 | ||||
-rw-r--r-- | net/core/tso.c | 18 | ||||
-rw-r--r-- | net/core/utils.c | 49 |
16 files changed, 442 insertions, 246 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 6bb6470f5b7b..ab9b8d0d115e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -99,6 +99,7 @@ #include <linux/rtnetlink.h> #include <linux/stat.h> #include <net/dst.h> +#include <net/dst_metadata.h> #include <net/pkt_sched.h> #include <net/checksum.h> #include <net/xfrm.h> @@ -682,6 +683,32 @@ int dev_get_iflink(const struct net_device *dev) EXPORT_SYMBOL(dev_get_iflink); /** + * dev_fill_metadata_dst - Retrieve tunnel egress information. + * @dev: targeted interface + * @skb: The packet. + * + * For better visibility of tunnel traffic OVS needs to retrieve + * egress tunnel information for a packet. Following API allows + * user to get this info. + */ +int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct ip_tunnel_info *info; + + if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst) + return -EINVAL; + + info = skb_tunnel_info_unclone(skb); + if (!info) + return -ENOMEM; + if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX))) + return -EINVAL; + + return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb); +} +EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); + +/** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find @@ -2915,9 +2942,11 @@ EXPORT_SYMBOL(xmit_recursion); /** * dev_loopback_xmit - loop back @skb + * @net: network namespace this loopback is happening in + * @sk: sk needed to be a netfilter okfn * @skb: buffer to transmit */ -int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb) +int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); @@ -2972,6 +3001,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) new_index = skb_tx_hash(dev, skb); if (queue_index != new_index && sk && + sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); @@ -3143,11 +3173,11 @@ out: return rc; } -int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb) +int dev_queue_xmit(struct sk_buff *skb) { return __dev_queue_xmit(skb, NULL); } -EXPORT_SYMBOL(dev_queue_xmit_sk); +EXPORT_SYMBOL(dev_queue_xmit); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) { @@ -3668,6 +3698,14 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, case TC_ACT_QUEUED: kfree_skb(skb); return NULL; + case TC_ACT_REDIRECT: + /* skb_mac_header check was done by cls/act_bpf, so + * we can safely push the L2 header back before + * redirecting to another netdev + */ + __skb_push(skb, skb->mac_len); + skb_do_redirect(skb); + return NULL; default: break; } @@ -3982,13 +4020,13 @@ static int netif_receive_skb_internal(struct sk_buff *skb) * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ -int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb) +int netif_receive_skb(struct sk_buff *skb) { trace_netif_receive_skb_entry(skb); return netif_receive_skb_internal(skb); } -EXPORT_SYMBOL(netif_receive_skb_sk); +EXPORT_SYMBOL(netif_receive_skb); /* Network device is going away, flush any packets still pending * Called with irqs disabled. @@ -4857,8 +4895,7 @@ struct netdev_adjacent { struct rcu_head rcu; }; -static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, - struct net_device *adj_dev, +static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, struct list_head *adj_list) { struct netdev_adjacent *adj; @@ -4884,7 +4921,7 @@ bool netdev_has_upper_dev(struct net_device *dev, { ASSERT_RTNL(); - return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper); + return __netdev_find_adj(upper_dev, &dev->all_adj_list.upper); } EXPORT_SYMBOL(netdev_has_upper_dev); @@ -5146,7 +5183,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, struct netdev_adjacent *adj; int ret; - adj = __netdev_find_adj(dev, adj_dev, dev_list); + adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { adj->ref_nr++; @@ -5202,7 +5239,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, { struct netdev_adjacent *adj; - adj = __netdev_find_adj(dev, adj_dev, dev_list); + adj = __netdev_find_adj(adj_dev, dev_list); if (!adj) { pr_err("tried to remove device %s from %s\n", @@ -5323,10 +5360,10 @@ static int __netdev_upper_dev_link(struct net_device *dev, return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ - if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper)) + if (__netdev_find_adj(dev, &upper_dev->all_adj_list.upper)) return -EBUSY; - if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper)) + if (__netdev_find_adj(upper_dev, &dev->adj_list.upper)) return -EEXIST; if (master && netdev_master_upper_dev_get(dev)) @@ -5336,6 +5373,12 @@ static int __netdev_upper_dev_link(struct net_device *dev, changeupper_info.master = master; changeupper_info.linking = true; + ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + &changeupper_info.info); + ret = notifier_to_errno(ret); + if (ret) + return ret; + ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private, master); if (ret) @@ -5478,6 +5521,9 @@ void netdev_upper_dev_unlink(struct net_device *dev, changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; changeupper_info.linking = false; + call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev, + &changeupper_info.info); + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); /* Here is the tricky part. We must remove all dev's lower @@ -5604,7 +5650,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev, if (!lower_dev) return NULL; - lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower); + lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower); if (!lower) return NULL; @@ -6242,6 +6288,48 @@ static void rollback_registered(struct net_device *dev) list_del(&single); } +static netdev_features_t netdev_sync_upper_features(struct net_device *lower, + struct net_device *upper, netdev_features_t features) +{ + netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; + netdev_features_t feature; + int feature_bit; + + for_each_netdev_feature(&upper_disables, feature_bit) { + feature = __NETIF_F_BIT(feature_bit); + if (!(upper->wanted_features & feature) + && (features & feature)) { + netdev_dbg(lower, "Dropping feature %pNF, upper dev %s has it off.\n", + &feature, upper->name); + features &= ~feature; + } + } + + return features; +} + +static void netdev_sync_lower_features(struct net_device *upper, + struct net_device *lower, netdev_features_t features) +{ + netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; + netdev_features_t feature; + int feature_bit; + + for_each_netdev_feature(&upper_disables, feature_bit) { + feature = __NETIF_F_BIT(feature_bit); + if (!(features & feature) && (lower->features & feature)) { + netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", + &feature, lower->name); + lower->wanted_features &= ~feature; + netdev_update_features(lower); + + if (unlikely(lower->features & feature)) + netdev_WARN(upper, "failed to disable %pNF on %s!\n", + &feature, lower->name); + } + } +} + static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { @@ -6311,8 +6399,10 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, int __netdev_update_features(struct net_device *dev) { + struct net_device *upper, *lower; netdev_features_t features; - int err = 0; + struct list_head *iter; + int err = -1; ASSERT_RTNL(); @@ -6324,8 +6414,12 @@ int __netdev_update_features(struct net_device *dev) /* driver might be less strict about feature dependencies */ features = netdev_fix_features(dev, features); + /* some features can't be enabled if they're off an an upper device */ + netdev_for_each_upper_dev_rcu(dev, upper, iter) + features = netdev_sync_upper_features(dev, upper, features); + if (dev->features == features) - return 0; + goto sync_lower; netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", &dev->features, &features); @@ -6340,10 +6434,17 @@ int __netdev_update_features(struct net_device *dev) return -1; } +sync_lower: + /* some features must be disabled on lower devices when disabled + * on an upper device (think: bonding master or bridge) + */ + netdev_for_each_lower_dev(dev, lower, iter) + netdev_sync_lower_features(dev, lower, features); + if (!err) dev->features = features; - return 1; + return err < 0 ? 0 : 1; } /** diff --git a/net/core/dst.c b/net/core/dst.c index 0771c8cb9307..e6dc77252fe9 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -144,12 +144,12 @@ loop: mutex_unlock(&dst_gc_mutex); } -int dst_discard_sk(struct sock *sk, struct sk_buff *skb) +int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } -EXPORT_SYMBOL(dst_discard_sk); +EXPORT_SYMBOL(dst_discard_out); const u32 dst_default_metrics[RTAX_MAX + 1] = { /* This initializer is needed to force linker to place this variable @@ -177,7 +177,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, dst->xfrm = NULL; #endif dst->input = dst_discard; - dst->output = dst_discard_sk; + dst->output = dst_discard_out; dst->error = 0; dst->obsolete = initial_obsolete; dst->header_len = 0; @@ -224,7 +224,7 @@ static void ___dst_free(struct dst_entry *dst) */ if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { dst->input = dst_discard; - dst->output = dst_discard_sk; + dst->output = dst_discard_out; } dst->obsolete = DST_OBSOLETE_DEAD; } @@ -306,7 +306,7 @@ void dst_release(struct dst_entry *dst) if (unlikely(newrefcnt < 0)) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); - if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) + if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE)) call_rcu(&dst->rcu_head, dst_destroy_rcu); } } @@ -352,7 +352,7 @@ static struct dst_ops md_dst_ops = { .family = AF_UNSPEC, }; -static int dst_md_discard_sk(struct sock *sk, struct sk_buff *skb) +static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { WARN_ONCE(1, "Attempting to call output on metadata dst\n"); kfree_skb(skb); @@ -375,7 +375,7 @@ static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen) DST_METADATA | DST_NOCACHE | DST_NOCOUNT); dst->input = dst_md_discard; - dst->output = dst_md_discard_sk; + dst->output = dst_md_discard_out; memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); } @@ -430,7 +430,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, if (!unregister) { dst->input = dst_discard; - dst->output = dst_discard_sk; + dst->output = dst_discard_out; } else { dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index b495ab1797fa..29edf74846fc 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1284,7 +1284,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) gstrings.len = ret; - data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER); if (!data) return -ENOMEM; diff --git a/net/core/filter.c b/net/core/filter.c index 05a04ea87172..672eefbfbe99 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -49,16 +49,17 @@ #include <net/sch_generic.h> #include <net/cls_cgroup.h> #include <net/dst_metadata.h> +#include <net/dst.h> /** * sk_filter - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter * - * Run the filter code and then cut skb->data to correct size returned by - * SK_RUN_FILTER. If pkt_len is 0 we toss packet. If skb->len is smaller + * 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 * than pkt_len we keep whole skb->data. This is the socket level - * wrapper to SK_RUN_FILTER. It returns 0 if the packet should + * wrapper to BPF_PROG_RUN. It returns 0 if the packet should * be accepted or -EPERM if the packet should be tossed. * */ @@ -82,7 +83,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter) { - unsigned int pkt_len = SK_RUN_FILTER(filter, skb); + unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb); err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } @@ -148,12 +149,6 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) return raw_smp_processor_id(); } -/* note that this only generates 32-bit random numbers */ -static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) -{ - return prandom_u32(); -} - static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, struct bpf_insn *insn_buf) { @@ -312,7 +307,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp, *insn = BPF_EMIT_CALL(__get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: - *insn = BPF_EMIT_CALL(__get_random_u32); + *insn = BPF_EMIT_CALL(bpf_user_rnd_u32); + bpf_user_rnd_init_once(); break; } break; @@ -1001,7 +997,7 @@ static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp, int err; fp->bpf_func = NULL; - fp->jited = false; + fp->jited = 0; err = bpf_check_classic(fp->insns, fp->len); if (err) { @@ -1083,16 +1079,18 @@ EXPORT_SYMBOL_GPL(bpf_prog_create); * @pfp: the unattached filter that is created * @fprog: the filter program * @trans: post-classic verifier transformation handler + * @save_orig: save classic BPF program * * This function effectively does the same as bpf_prog_create(), only * that it builds up its insns buffer from user space provided buffer. * It also allows for passing a bpf_aux_classic_check_t handler. */ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, - bpf_aux_classic_check_t trans) + bpf_aux_classic_check_t trans, bool save_orig) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; + int err; /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) @@ -1108,12 +1106,16 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, } fp->len = fprog->len; - /* Since unattached filters are not copied back to user - * space through sk_get_filter(), we do not need to hold - * a copy here, and can spare us the work. - */ fp->orig_prog = NULL; + if (save_orig) { + err = bpf_prog_store_orig_filter(fp, fprog); + if (err) { + __bpf_prog_free(fp); + return -ENOMEM; + } + } + /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ @@ -1404,9 +1406,6 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) if (unlikely(!dev)) return -EINVAL; - if (unlikely(!(dev->flags & IFF_UP))) - return -EINVAL; - skb2 = skb_clone(skb, GFP_ATOMIC); if (unlikely(!skb2)) return -ENOMEM; @@ -1415,6 +1414,7 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) return dev_forward_skb(dev, skb2); skb2->dev = dev; + skb_sender_cpu_clear(skb2); return dev_queue_xmit(skb2); } @@ -1427,6 +1427,49 @@ const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; +struct redirect_info { + u32 ifindex; + u32 flags; +}; + +static DEFINE_PER_CPU(struct redirect_info, redirect_info); +static u64 bpf_redirect(u64 ifindex, u64 flags, u64 r3, u64 r4, u64 r5) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + + ri->ifindex = ifindex; + ri->flags = flags; + return TC_ACT_REDIRECT; +} + +int skb_do_redirect(struct sk_buff *skb) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct net_device *dev; + + dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex); + ri->ifindex = 0; + if (unlikely(!dev)) { + kfree_skb(skb); + return -EINVAL; + } + + if (BPF_IS_REDIRECT_INGRESS(ri->flags)) + return dev_forward_skb(dev, skb); + + skb->dev = dev; + skb_sender_cpu_clear(skb); + return dev_queue_xmit(skb); +} + +const struct bpf_func_proto bpf_redirect_proto = { + .func = bpf_redirect, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, +}; + static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return task_get_classid((struct sk_buff *) (unsigned long) r1); @@ -1439,6 +1482,25 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ +#ifdef CONFIG_IP_ROUTE_CLASSID + const struct dst_entry *dst; + + dst = skb_dst((struct sk_buff *) (unsigned long) r1); + if (dst) + return dst->tclassid; +#endif + return 0; +} + +static const struct bpf_func_proto bpf_get_route_realm_proto = { + .func = bpf_get_route_realm, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5) { struct sk_buff *skb = (struct sk_buff *) (long) r1; @@ -1579,7 +1641,8 @@ sk_filter_func_proto(enum bpf_func_id func_id) case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_trace_printk: - return bpf_get_trace_printk_proto(); + if (capable(CAP_SYS_ADMIN)) + return bpf_get_trace_printk_proto(); default: return NULL; } @@ -1607,6 +1670,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_key_proto(); + case BPF_FUNC_redirect: + return &bpf_redirect_proto; + case BPF_FUNC_get_route_realm: + return &bpf_get_route_realm_proto; default: return sk_filter_func_proto(func_id); } @@ -1632,6 +1699,9 @@ static bool __is_valid_access(int off, int size, enum bpf_access_type type) static bool sk_filter_is_valid_access(int off, int size, enum bpf_access_type type) { + if (off == offsetof(struct __sk_buff, tc_classid)) + return false; + if (type == BPF_WRITE) { switch (off) { case offsetof(struct __sk_buff, cb[0]) ... @@ -1648,10 +1718,14 @@ static bool sk_filter_is_valid_access(int off, int size, static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type) { + if (off == offsetof(struct __sk_buff, tc_classid)) + return type == BPF_WRITE ? true : false; + if (type == BPF_WRITE) { switch (off) { case offsetof(struct __sk_buff, mark): case offsetof(struct __sk_buff, tc_index): + case offsetof(struct __sk_buff, priority): case offsetof(struct __sk_buff, cb[0]) ... offsetof(struct __sk_buff, cb[4]): break; @@ -1664,7 +1738,8 @@ static bool tc_cls_act_is_valid_access(int off, int size, static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, - struct bpf_insn *insn_buf) + struct bpf_insn *insn_buf, + struct bpf_prog *prog) { struct bpf_insn *insn = insn_buf; @@ -1693,8 +1768,12 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, case offsetof(struct __sk_buff, priority): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, priority) != 4); - *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, - offsetof(struct sk_buff, priority)); + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, priority)); + else + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, priority)); break; case offsetof(struct __sk_buff, ingress_ifindex): @@ -1751,6 +1830,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, offsetof(struct __sk_buff, cb[4]): BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + prog->cb_access = 1; ctx_off -= offsetof(struct __sk_buff, cb[0]); ctx_off += offsetof(struct sk_buff, cb); ctx_off += offsetof(struct qdisc_skb_cb, data); @@ -1760,6 +1840,14 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, ctx_off); break; + case offsetof(struct __sk_buff, tc_classid): + ctx_off -= offsetof(struct __sk_buff, tc_classid); + ctx_off += offsetof(struct sk_buff, cb); + ctx_off += offsetof(struct qdisc_skb_cb, tc_classid); + WARN_ON(type != BPF_WRITE); + *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off); + break; + case offsetof(struct __sk_buff, tc_index): #ifdef CONFIG_NET_SCHED BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2); @@ -1854,9 +1942,13 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, goto out; /* We're copying the filter that has been originally attached, - * so no conversion/decode needed anymore. + * so no conversion/decode needed anymore. eBPF programs that + * have no original program cannot be dumped through this. */ + ret = -EACCES; fprog = filter->prog->orig_prog; + if (!fprog) + goto out; ret = fprog->len; if (!len) diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index dfb1a9ca0835..299cfc24d888 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -180,7 +180,7 @@ int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) } EXPORT_SYMBOL(lwtunnel_cmp_encap); -int lwtunnel_output(struct sock *sk, struct sk_buff *skb) +int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; @@ -199,7 +199,7 @@ int lwtunnel_output(struct sock *sk, struct sk_buff *skb) rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); if (likely(ops && ops->output)) - ret = ops->output(sk, skb); + ret = ops->output(net, sk, skb); rcu_read_unlock(); if (ret == -EOPNOTSUPP) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2b515ba7e94f..1aa8437ed6c4 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2235,14 +2235,53 @@ static void neigh_update_notify(struct neighbour *neigh) __neigh_notify(neigh, RTM_NEWNEIGH, 0); } +static bool neigh_master_filtered(struct net_device *dev, int master_idx) +{ + struct net_device *master; + + if (!master_idx) + return false; + + master = netdev_master_upper_dev_get(dev); + if (!master || master->ifindex != master_idx) + return true; + + return false; +} + +static bool neigh_ifindex_filtered(struct net_device *dev, int filter_idx) +{ + if (filter_idx && dev->ifindex != filter_idx) + return true; + + return false; +} + static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + const struct nlmsghdr *nlh = cb->nlh; + struct nlattr *tb[NDA_MAX + 1]; struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; struct neigh_hash_table *nht; + int filter_master_idx = 0, filter_idx = 0; + unsigned int flags = NLM_F_MULTI; + int err; + + err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL); + if (!err) { + if (tb[NDA_IFINDEX]) + filter_idx = nla_get_u32(tb[NDA_IFINDEX]); + + if (tb[NDA_MASTER]) + filter_master_idx = nla_get_u32(tb[NDA_MASTER]); + + if (filter_idx || filter_master_idx) + flags |= NLM_F_DUMP_FILTERED; + } rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); @@ -2255,12 +2294,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, n = rcu_dereference_bh(n->next)) { if (!net_eq(dev_net(n->dev), net)) continue; + if (neigh_ifindex_filtered(n->dev, filter_idx)) + continue; + if (neigh_master_filtered(n->dev, filter_master_idx)) + continue; if (idx < s_idx) goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, - NLM_F_MULTI) < 0) { + flags) < 0) { rc = -1; goto out; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 830f8a7c1cb1..f88a62ab019d 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -471,7 +471,7 @@ static ssize_t phys_switch_id_show(struct device *dev, if (dev_isalive(netdev)) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; @@ -1003,15 +1003,12 @@ static ssize_t show_trans_timeout(struct netdev_queue *queue, } #ifdef CONFIG_XPS -static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) +static unsigned int get_netdev_queue_index(struct netdev_queue *queue) { struct net_device *dev = queue->dev; - int i; - - for (i = 0; i < dev->num_tx_queues; i++) - if (queue == &dev->_tx[i]) - break; + unsigned int i; + i = queue - dev->_tx; BUG_ON(i >= dev->num_tx_queues); return i; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 8bdada242a7d..94acfc89ad97 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -140,7 +140,7 @@ static void queue_process(struct work_struct *work) * case. Further, we test the poll_owner to avoid recursion on UP * systems where the lock doesn't exist. */ -static int poll_one_napi(struct napi_struct *napi, int budget) +static void poll_one_napi(struct napi_struct *napi) { int work = 0; @@ -149,33 +149,33 @@ static int poll_one_napi(struct napi_struct *napi, int budget) * holding the napi->poll_lock. */ if (!test_bit(NAPI_STATE_SCHED, &napi->state)) - return budget; + return; /* If we set this bit but see that it has already been set, * that indicates that napi has been disabled and we need * to abort this operation */ if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) - goto out; + return; - work = napi->poll(napi, budget); - WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll); + /* We explicilty pass the polling call a budget of 0 to + * indicate that we are clearing the Tx path only. + */ + work = napi->poll(napi, 0); + WARN_ONCE(work, "%pF exceeded budget in poll\n", napi->poll); trace_napi_poll(napi); clear_bit(NAPI_STATE_NPSVC, &napi->state); - -out: - return budget - work; } -static void poll_napi(struct net_device *dev, int budget) +static void poll_napi(struct net_device *dev) { struct napi_struct *napi; list_for_each_entry(napi, &dev->napi_list, dev_list) { if (napi->poll_owner != smp_processor_id() && spin_trylock(&napi->poll_lock)) { - budget = poll_one_napi(napi, budget); + poll_one_napi(napi); spin_unlock(&napi->poll_lock); } } @@ -185,7 +185,6 @@ static void netpoll_poll_dev(struct net_device *dev) { const struct net_device_ops *ops; struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); - int budget = 0; /* Don't do any rx activity if the dev_lock mutex is held * the dev_open/close paths use this to block netpoll activity @@ -208,7 +207,7 @@ static void netpoll_poll_dev(struct net_device *dev) /* Process pending work on NIC */ ops->ndo_poll_controller(dev); - poll_napi(dev, budget); + poll_napi(dev); up(&ni->dev_lock); diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index 4eab4a94a59d..703cf76aa7c2 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -58,7 +58,7 @@ * jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these * ldh [18] ; reload payload * and #0xf ; mask PTP_CLASS_VMASK - * or #0x70 ; PTP_CLASS_VLAN|PTP_CLASS_L2 + * or #0xc0 ; PTP_CLASS_VLAN|PTP_CLASS_L2 * ret a ; return PTP class * * ; PTP over UDP over IPv4 over 802.1Q over Ethernet @@ -73,7 +73,7 @@ * jneq #319, drop_8021q_ipv4 ; is port PTP_EV_PORT ? * ldh [x + 26] ; load payload * and #0xf ; mask PTP_CLASS_VMASK - * or #0x50 ; PTP_CLASS_VLAN|PTP_CLASS_IPV4 + * or #0x90 ; PTP_CLASS_VLAN|PTP_CLASS_IPV4 * ret a ; return PTP class * drop_8021q_ipv4: ret #0x0 ; PTP_CLASS_NONE * @@ -86,7 +86,7 @@ * jneq #319, drop_8021q_ipv6 ; is port PTP_EV_PORT ? * ldh [66] ; load payload * and #0xf ; mask PTP_CLASS_VMASK - * or #0x60 ; PTP_CLASS_VLAN|PTP_CLASS_IPV6 + * or #0xa0 ; PTP_CLASS_VLAN|PTP_CLASS_IPV6 * ret a ; return PTP class * drop_8021q_ipv6: ret #0x0 ; PTP_CLASS_NONE * @@ -98,7 +98,7 @@ * jneq #0x0, drop_ieee1588 ; for PTP_GEN_BIT and drop these * ldh [14] ; reload payload * and #0xf ; mask PTP_CLASS_VMASK - * or #0x30 ; PTP_CLASS_L2 + * or #0x40 ; PTP_CLASS_L2 * ret a ; return PTP class * drop_ieee1588: ret #0x0 ; PTP_CLASS_NONE */ @@ -150,7 +150,7 @@ void __init ptp_classifier_init(void) { 0x15, 0, 35, 0x00000000 }, { 0x28, 0, 0, 0x00000012 }, { 0x54, 0, 0, 0x0000000f }, - { 0x44, 0, 0, 0x00000070 }, + { 0x44, 0, 0, 0x000000c0 }, { 0x16, 0, 0, 0x00000000 }, { 0x15, 0, 12, 0x00000800 }, { 0x30, 0, 0, 0x0000001b }, @@ -162,7 +162,7 @@ void __init ptp_classifier_init(void) { 0x15, 0, 4, 0x0000013f }, { 0x48, 0, 0, 0x0000001a }, { 0x54, 0, 0, 0x0000000f }, - { 0x44, 0, 0, 0x00000050 }, + { 0x44, 0, 0, 0x00000090 }, { 0x16, 0, 0, 0x00000000 }, { 0x06, 0, 0, 0x00000000 }, { 0x15, 0, 8, 0x000086dd }, @@ -172,7 +172,7 @@ void __init ptp_classifier_init(void) { 0x15, 0, 4, 0x0000013f }, { 0x28, 0, 0, 0x00000042 }, { 0x54, 0, 0, 0x0000000f }, - { 0x44, 0, 0, 0x00000060 }, + { 0x44, 0, 0, 0x000000a0 }, { 0x16, 0, 0, 0x00000000 }, { 0x06, 0, 0, 0x00000000 }, { 0x15, 0, 7, 0x000088f7 }, @@ -181,7 +181,7 @@ void __init ptp_classifier_init(void) { 0x15, 0, 4, 0x00000000 }, { 0x28, 0, 0, 0x0000000e }, { 0x54, 0, 0, 0x0000000f }, - { 0x44, 0, 0, 0x00000030 }, + { 0x44, 0, 0, 0x00000040 }, { 0x16, 0, 0, 0x00000000 }, { 0x06, 0, 0, 0x00000000 }, }; diff --git a/net/core/request_sock.c b/net/core/request_sock.c index b42f0e26f89e..5d26056b6d8f 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -37,90 +37,16 @@ int sysctl_max_syn_backlog = 256; EXPORT_SYMBOL(sysctl_max_syn_backlog); -int reqsk_queue_alloc(struct request_sock_queue *queue, - unsigned int nr_table_entries) +void reqsk_queue_alloc(struct request_sock_queue *queue) { - size_t lopt_size = sizeof(struct listen_sock); - struct listen_sock *lopt = NULL; + spin_lock_init(&queue->rskq_lock); - nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog); - nr_table_entries = max_t(u32, nr_table_entries, 8); - nr_table_entries = roundup_pow_of_two(nr_table_entries + 1); - lopt_size += nr_table_entries * sizeof(struct request_sock *); + spin_lock_init(&queue->fastopenq.lock); + queue->fastopenq.rskq_rst_head = NULL; + queue->fastopenq.rskq_rst_tail = NULL; + queue->fastopenq.qlen = 0; - if (lopt_size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) - lopt = kzalloc(lopt_size, GFP_KERNEL | - __GFP_NOWARN | - __GFP_NORETRY); - if (!lopt) - lopt = vzalloc(lopt_size); - if (!lopt) - return -ENOMEM; - - get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); - spin_lock_init(&queue->syn_wait_lock); queue->rskq_accept_head = NULL; - lopt->nr_table_entries = nr_table_entries; - lopt->max_qlen_log = ilog2(nr_table_entries); - - spin_lock_bh(&queue->syn_wait_lock); - queue->listen_opt = lopt; - spin_unlock_bh(&queue->syn_wait_lock); - - return 0; -} - -void __reqsk_queue_destroy(struct request_sock_queue *queue) -{ - /* This is an error recovery path only, no locking needed */ - kvfree(queue->listen_opt); -} - -static inline struct listen_sock *reqsk_queue_yank_listen_sk( - struct request_sock_queue *queue) -{ - struct listen_sock *lopt; - - spin_lock_bh(&queue->syn_wait_lock); - lopt = queue->listen_opt; - queue->listen_opt = NULL; - spin_unlock_bh(&queue->syn_wait_lock); - - return lopt; -} - -void reqsk_queue_destroy(struct request_sock_queue *queue) -{ - /* make all the listen_opt local to us */ - struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue); - - if (listen_sock_qlen(lopt) != 0) { - unsigned int i; - - for (i = 0; i < lopt->nr_table_entries; i++) { - struct request_sock *req; - - spin_lock_bh(&queue->syn_wait_lock); - while ((req = lopt->syn_table[i]) != NULL) { - lopt->syn_table[i] = req->dl_next; - /* Because of following del_timer_sync(), - * we must release the spinlock here - * or risk a dead lock. - */ - spin_unlock_bh(&queue->syn_wait_lock); - atomic_inc(&lopt->qlen_dec); - if (del_timer_sync(&req->rsk_timer)) - reqsk_put(req); - reqsk_put(req); - spin_lock_bh(&queue->syn_wait_lock); - } - spin_unlock_bh(&queue->syn_wait_lock); - } - } - - if (WARN_ON(listen_sock_qlen(lopt) != 0)) - pr_err("qlen %u\n", listen_sock_qlen(lopt)); - kvfree(lopt); } /* @@ -174,7 +100,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, struct sock *lsk = req->rsk_listener; struct fastopen_queue *fastopenq; - fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq; + fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq; tcp_sk(sk)->fastopen_rsk = NULL; spin_lock_bh(&fastopenq->lock); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 0ec48403ed68..504bd17b7456 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -96,7 +96,7 @@ int rtnl_is_locked(void) EXPORT_SYMBOL(rtnl_is_locked); #ifdef CONFIG_PROVE_LOCKING -int lockdep_rtnl_is_held(void) +bool lockdep_rtnl_is_held(void) { return lockdep_is_held(&rtnl_mutex); } @@ -497,7 +497,8 @@ void rtnl_af_unregister(struct rtnl_af_ops *ops) } EXPORT_SYMBOL_GPL(rtnl_af_unregister); -static size_t rtnl_link_get_af_size(const struct net_device *dev) +static size_t rtnl_link_get_af_size(const struct net_device *dev, + u32 ext_filter_mask) { struct rtnl_af_ops *af_ops; size_t size; @@ -509,7 +510,7 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev) if (af_ops->get_link_af_size) { /* AF_* + nested data */ size += nla_total_size(sizeof(struct nlattr)) + - af_ops->get_link_af_size(dev); + af_ops->get_link_af_size(dev, ext_filter_mask); } } @@ -837,7 +838,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, /* IFLA_VF_STATS_BROADCAST */ nla_total_size(sizeof(__u64)) + /* IFLA_VF_STATS_MULTICAST */ - nla_total_size(sizeof(__u64))); + nla_total_size(sizeof(__u64)) + + nla_total_size(sizeof(struct ifla_vf_trust))); return size; } else return 0; @@ -900,7 +902,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ - + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + + rtnl_link_get_af_size(dev, 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(1); /* IFLA_PROTO_DOWN */ @@ -1025,7 +1027,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { int err; struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; @@ -1160,6 +1162,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct ifla_vf_link_state vf_linkstate; struct ifla_vf_rss_query_en vf_rss_query_en; struct ifla_vf_stats vf_stats; + struct ifla_vf_trust vf_trust; /* * Not all SR-IOV capable drivers support the @@ -1169,6 +1172,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, */ ivi.spoofchk = -1; ivi.rss_query_en = -1; + ivi.trusted = -1; memset(ivi.mac, 0, sizeof(ivi.mac)); /* The default value for VF link state is "auto" * IFLA_VF_LINK_STATE_AUTO which equals zero @@ -1182,7 +1186,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, vf_tx_rate.vf = vf_spoofchk.vf = vf_linkstate.vf = - vf_rss_query_en.vf = ivi.vf; + vf_rss_query_en.vf = + vf_trust.vf = ivi.vf; memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; @@ -1193,6 +1198,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, vf_spoofchk.setting = ivi.spoofchk; vf_linkstate.link_state = ivi.linkstate; vf_rss_query_en.setting = ivi.rss_query_en; + vf_trust.setting = ivi.trusted; vf = nla_nest_start(skb, IFLA_VF_INFO); if (!vf) { nla_nest_cancel(skb, vfinfo); @@ -1210,7 +1216,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, &vf_linkstate) || nla_put(skb, IFLA_VF_RSS_QUERY_EN, sizeof(vf_rss_query_en), - &vf_rss_query_en)) + &vf_rss_query_en) || + nla_put(skb, IFLA_VF_TRUST, + sizeof(vf_trust), &vf_trust)) goto nla_put_failure; memset(&vf_stats, 0, sizeof(vf_stats)); if (dev->netdev_ops->ndo_get_vf_stats) @@ -1272,7 +1280,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (!(af = nla_nest_start(skb, af_ops->family))) goto nla_put_failure; - err = af_ops->fill_link_af(skb, dev); + err = af_ops->fill_link_af(skb, dev, ext_filter_mask); /* * Caller may return ENODATA to indicate that there @@ -1347,6 +1355,7 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_LINK_STATE] = { .len = sizeof(struct ifla_vf_link_state) }, [IFLA_VF_RSS_QUERY_EN] = { .len = sizeof(struct ifla_vf_rss_query_en) }, [IFLA_VF_STATS] = { .type = NLA_NESTED }, + [IFLA_VF_TRUST] = { .len = sizeof(struct ifla_vf_trust) }, }; static const struct nla_policy ifla_vf_stats_policy[IFLA_VF_STATS_MAX + 1] = { @@ -1586,6 +1595,16 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) return err; } + if (tb[IFLA_VF_TRUST]) { + struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_trust) + err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting); + if (err < 0) + return err; + } + return err; } @@ -3443,4 +3462,3 @@ void __init rtnetlink_init(void) rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, NULL); rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL); } - diff --git a/net/core/skbuff.c b/net/core/skbuff.c index fab4599ba8b2..aa41e6dd6429 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -414,7 +414,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, len += NET_SKB_PAD; if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || - (gfp_mask & (__GFP_WAIT | GFP_DMA))) { + (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; @@ -481,7 +481,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, len += NET_SKB_PAD + NET_IP_ALIGN; if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || - (gfp_mask & (__GFP_WAIT | GFP_DMA))) { + (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) goto skb_fail; @@ -4452,7 +4452,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, return NULL; gfp_head = gfp_mask; - if (gfp_head & __GFP_WAIT) + if (gfp_head & __GFP_DIRECT_RECLAIM) gfp_head |= __GFP_REPEAT; *errcode = -ENOBUFS; @@ -4467,7 +4467,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, while (order) { if (npages >= 1 << order) { - page = alloc_pages((gfp_mask & ~__GFP_WAIT) | + page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY, diff --git a/net/core/sock.c b/net/core/sock.c index 3307c02244d3..1e4dd54bfb5a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -422,13 +422,25 @@ static void sock_warn_obsolete_bsdism(const char *name) } } +static bool sock_needs_netstamp(const struct sock *sk) +{ + switch (sk->sk_family) { + case AF_UNSPEC: + case AF_UNIX: + return false; + default: + return true; + } +} + #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { if (sk->sk_flags & flags) { sk->sk_flags &= ~flags; - if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP)) + if (sock_needs_netstamp(sk) && + !(sk->sk_flags & SK_FLAGS_TIMESTAMP)) net_disable_timestamp(); } } @@ -988,6 +1000,10 @@ set_rcvbuf: sk->sk_max_pacing_rate); break; + case SO_INCOMING_CPU: + sk->sk_incoming_cpu = val; + break; + default: ret = -ENOPROTOOPT; break; @@ -1578,7 +1594,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); - if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) + if (sock_needs_netstamp(sk) && + newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); } out: @@ -1639,6 +1656,28 @@ void sock_wfree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_wfree); +void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) +{ + skb_orphan(skb); + skb->sk = sk; +#ifdef CONFIG_INET + if (unlikely(!sk_fullsock(sk))) { + skb->destructor = sock_edemux; + sock_hold(sk); + return; + } +#endif + skb->destructor = sock_wfree; + skb_set_hash_from_sk(skb, sk); + /* + * We used to take a refcount on sk, but following operation + * is enough to guarantee sk_free() wont free this sock until + * all in-flight packets are completed + */ + atomic_add(skb->truesize, &sk->sk_wmem_alloc); +} +EXPORT_SYMBOL(skb_set_owner_w); + void skb_orphan_partial(struct sk_buff *skb) { /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, @@ -1852,6 +1891,32 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, } EXPORT_SYMBOL(sock_alloc_send_skb); +int sock_cmsg_send(struct sock *sk, struct msghdr *msg, + struct sockcm_cookie *sockc) +{ + struct cmsghdr *cmsg; + + for_each_cmsghdr(cmsg, msg) { + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + if (cmsg->cmsg_level != SOL_SOCKET) + continue; + switch (cmsg->cmsg_type) { + case SO_MARK: + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + return -EPERM; + if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) + return -EINVAL; + sockc->mark = *(u32 *)CMSG_DATA(cmsg); + break; + default: + return -EINVAL; + } + } + return 0; +} +EXPORT_SYMBOL(sock_cmsg_send); + /* On 32bit arches, an skb frag is limited to 2^15 */ #define SKB_FRAG_PAGE_ORDER get_order(32768) @@ -1879,8 +1944,10 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) pfrag->offset = 0; if (SKB_FRAG_PAGE_ORDER) { - pfrag->page = alloc_pages((gfp & ~__GFP_WAIT) | __GFP_COMP | - __GFP_NOWARN | __GFP_NORETRY, + /* Avoid direct reclaim but allow kswapd to wake */ + pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | + __GFP_COMP | __GFP_NOWARN | + __GFP_NORETRY, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; @@ -2353,6 +2420,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_max_pacing_rate = ~0U; sk->sk_pacing_rate = ~0U; + sk->sk_incoming_cpu = -1; /* * Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.txt for details) @@ -2479,7 +2547,8 @@ void sock_enable_timestamp(struct sock *sk, int flag) * time stamping, but time stamping might have been on * already because of the other one */ - if (!(previous_flags & SK_FLAGS_TIMESTAMP)) + if (sock_needs_netstamp(sk) && + !(previous_flags & SK_FLAGS_TIMESTAMP)) net_enable_timestamp(); } } @@ -2758,7 +2827,7 @@ static int req_prot_init(const struct proto *prot) rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, - 0, NULL); + prot->slab_flags, NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 817622f3dbb7..0c1d58d43f67 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -1,3 +1,5 @@ +/* License: GPL */ + #include <linux/mutex.h> #include <linux/socket.h> #include <linux/skbuff.h> @@ -323,14 +325,4 @@ static int __init sock_diag_init(void) BUG_ON(!broadcast_wq); return register_pernet_subsys(&diag_net_ops); } - -static void __exit sock_diag_exit(void) -{ - unregister_pernet_subsys(&diag_net_ops); - destroy_workqueue(broadcast_wq); -} - -module_init(sock_diag_init); -module_exit(sock_diag_exit); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_SOCK_DIAG); +device_initcall(sock_diag_init); diff --git a/net/core/tso.c b/net/core/tso.c index 630b30b4fb53..5dca7ce8ee9f 100644 --- a/net/core/tso.c +++ b/net/core/tso.c @@ -1,4 +1,5 @@ #include <linux/export.h> +#include <linux/if_vlan.h> #include <net/ip.h> #include <net/tso.h> #include <asm/unaligned.h> @@ -14,18 +15,24 @@ EXPORT_SYMBOL(tso_count_descs); void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso, int size, bool is_last) { - struct iphdr *iph; struct tcphdr *tcph; int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); int mac_hdr_len = skb_network_offset(skb); memcpy(hdr, skb->data, hdr_len); - iph = (struct iphdr *)(hdr + mac_hdr_len); - iph->id = htons(tso->ip_id); - iph->tot_len = htons(size + hdr_len - mac_hdr_len); + if (!tso->ipv6) { + struct iphdr *iph = (void *)(hdr + mac_hdr_len); + + iph->id = htons(tso->ip_id); + iph->tot_len = htons(size + hdr_len - mac_hdr_len); + tso->ip_id++; + } else { + struct ipv6hdr *iph = (void *)(hdr + mac_hdr_len); + + iph->payload_len = htons(size + tcp_hdrlen(skb)); + } tcph = (struct tcphdr *)(hdr + skb_transport_offset(skb)); put_unaligned_be32(tso->tcp_seq, &tcph->seq); - tso->ip_id++; if (!is_last) { /* Clear all special flags for not last packet */ @@ -61,6 +68,7 @@ void tso_start(struct sk_buff *skb, struct tso_t *tso) tso->ip_id = ntohs(ip_hdr(skb)->id); tso->tcp_seq = ntohl(tcp_hdr(skb)->seq); tso->next_frag_idx = 0; + tso->ipv6 = vlan_get_protocol(skb) == htons(ETH_P_IPV6); /* Build first data */ tso->size = skb_headlen(skb) - hdr_len; diff --git a/net/core/utils.c b/net/core/utils.c index 3dffce953c39..3d17ca8b4744 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -348,52 +348,3 @@ void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, } } EXPORT_SYMBOL(inet_proto_csum_replace_by_diff); - -struct __net_random_once_work { - struct work_struct work; - struct static_key *key; -}; - -static void __net_random_once_deferred(struct work_struct *w) -{ - struct __net_random_once_work *work = - container_of(w, struct __net_random_once_work, work); - BUG_ON(!static_key_enabled(work->key)); - static_key_slow_dec(work->key); - kfree(work); -} - -static void __net_random_once_disable_jump(struct static_key *key) -{ - struct __net_random_once_work *w; - - w = kmalloc(sizeof(*w), GFP_ATOMIC); - if (!w) - return; - - INIT_WORK(&w->work, __net_random_once_deferred); - w->key = key; - schedule_work(&w->work); -} - -bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *once_key) -{ - static DEFINE_SPINLOCK(lock); - unsigned long flags; - - spin_lock_irqsave(&lock, flags); - if (*done) { - spin_unlock_irqrestore(&lock, flags); - return false; - } - - get_random_bytes(buf, nbytes); - *done = true; - spin_unlock_irqrestore(&lock, flags); - - __net_random_once_disable_jump(once_key); - - return true; -} -EXPORT_SYMBOL(__net_get_random_once); |