diff options
Diffstat (limited to 'net')
189 files changed, 6633 insertions, 1349 deletions
diff --git a/net/802/psnap.c b/net/802/psnap.c index 40ab2aea7b31..4492e8d7ad20 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -30,7 +30,7 @@ static struct datalink_proto *find_snap_client(const unsigned char *desc) { struct datalink_proto *proto = NULL, *p; - list_for_each_entry_rcu(p, &snap_list, node) { + list_for_each_entry_rcu(p, &snap_list, node, lockdep_is_held(&snap_lock)) { if (!memcmp(p->type, desc, 5)) { proto = p; break; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index a313165e7a67..78ec2e1b14d1 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -359,9 +359,8 @@ static void __vlan_vid_del(struct vlan_info *vlan_info, int err; err = vlan_kill_rx_filter_info(dev, proto, vid); - if (err) - pr_warn("failed to kill vid %04x/%d for device %s\n", - proto, vid, dev->name); + if (err && dev->reg_state != NETREG_UNREGISTERING) + netdev_warn(dev, "failed to kill vid %04x/%d\n", proto, vid); list_del(&vid_info->list); kfree(vid_info); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 3d21dd83f8cc..b85da4b7a77b 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -88,7 +88,7 @@ struct batadv_dhcp_packet { __u8 sname[64]; __u8 file[128]; __be32 magic; - __u8 options[0]; + __u8 options[]; }; #define BATADV_DHCP_YIADDR_LEN sizeof(((struct batadv_dhcp_packet *)0)->yiaddr) diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 692306df7b6f..2a234d0ad445 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2020.0" +#define BATADV_SOURCE_VERSION "2020.1" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 852932838ddc..a9635c882fe0 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -862,7 +862,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, u8 *tt_change_ptr; spin_lock_bh(&orig_node->vlan_list_lock); - hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { + hlist_for_each_entry(vlan, &orig_node->vlan_list, list) { num_vlan++; num_entries += atomic_read(&vlan->tt.num_entries); } @@ -888,7 +888,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, (*tt_data)->num_vlan = htons(num_vlan); tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(*tt_data + 1); - hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { + hlist_for_each_entry(vlan, &orig_node->vlan_list, list) { tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); @@ -937,7 +937,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, int change_offset; spin_lock_bh(&bat_priv->softif_vlan_list_lock); - hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { + hlist_for_each_entry(vlan, &bat_priv->softif_vlan_list, list) { vlan_entries = atomic_read(&vlan->tt.num_entries); if (vlan_entries < 1) continue; @@ -967,7 +967,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, (*tt_data)->num_vlan = htons(num_vlan); tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(*tt_data + 1); - hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { + hlist_for_each_entry(vlan, &bat_priv->softif_vlan_list, list) { vlan_entries = atomic_read(&vlan->tt.num_entries); if (vlan_entries < 1) continue; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index d555c0d8657d..562443f94133 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -37,7 +37,7 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, repeat = 1; rcu_read_lock(); - preempt_disable(); + migrate_disable(); time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { bpf_cgroup_storage_set(storage); @@ -54,18 +54,18 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, if (need_resched()) { time_spent += ktime_get_ns() - time_start; - preempt_enable(); + migrate_enable(); rcu_read_unlock(); cond_resched(); rcu_read_lock(); - preempt_disable(); + migrate_disable(); time_start = ktime_get_ns(); } } time_spent += ktime_get_ns() - time_start; - preempt_enable(); + migrate_enable(); rcu_read_unlock(); do_div(time_spent, repeat); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 3ab23f698221..756b63b6f7b3 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -8,6 +8,7 @@ #include <linux/bpf.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> +#include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> static atomic_t cache_idx; @@ -60,7 +61,7 @@ struct bpf_sk_storage_data { * the number of cachelines access during the cache hit case. */ struct bpf_sk_storage_map __rcu *smap; - u8 data[0] __aligned(8); + u8 data[] __aligned(8); }; /* Linked to bpf_sk_storage and bpf_sk_storage_map */ @@ -606,6 +607,14 @@ static void bpf_sk_storage_map_free(struct bpf_map *map) kfree(map); } +/* U16_MAX is much more than enough for sk local storage + * considering a tcp_sock is ~2k. + */ +#define MAX_VALUE_SIZE \ + min_t(u32, \ + (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \ + (U16_MAX - sizeof(struct bpf_sk_storage_elem))) + static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) { if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK || @@ -619,12 +628,7 @@ static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (attr->value_size >= KMALLOC_MAX_SIZE - - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem) || - /* U16_MAX is much more than enough for sk local storage - * considering a tcp_sock is ~2k. - */ - attr->value_size > U16_MAX - sizeof(struct bpf_sk_storage_elem)) + if (attr->value_size > MAX_VALUE_SIZE) return -E2BIG; return 0; @@ -910,3 +914,270 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_SOCKET, }; + +struct bpf_sk_storage_diag { + u32 nr_maps; + struct bpf_map *maps[]; +}; + +/* The reply will be like: + * INET_DIAG_BPF_SK_STORAGES (nla_nest) + * SK_DIAG_BPF_STORAGE (nla_nest) + * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) + * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) + * SK_DIAG_BPF_STORAGE (nla_nest) + * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) + * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) + * .... + */ +static int nla_value_size(u32 value_size) +{ + /* SK_DIAG_BPF_STORAGE (nla_nest) + * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) + * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) + */ + return nla_total_size(0) + nla_total_size(sizeof(u32)) + + nla_total_size_64bit(value_size); +} + +void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag) +{ + u32 i; + + if (!diag) + return; + + for (i = 0; i < diag->nr_maps; i++) + bpf_map_put(diag->maps[i]); + + kfree(diag); +} +EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_free); + +static bool diag_check_dup(const struct bpf_sk_storage_diag *diag, + const struct bpf_map *map) +{ + u32 i; + + for (i = 0; i < diag->nr_maps; i++) { + if (diag->maps[i] == map) + return true; + } + + return false; +} + +struct bpf_sk_storage_diag * +bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) +{ + struct bpf_sk_storage_diag *diag; + struct nlattr *nla; + u32 nr_maps = 0; + int rem, err; + + /* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as + * the map_alloc_check() side also does. + */ + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + nla_for_each_nested(nla, nla_stgs, rem) { + if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) + nr_maps++; + } + + diag = kzalloc(sizeof(*diag) + sizeof(diag->maps[0]) * nr_maps, + GFP_KERNEL); + if (!diag) + return ERR_PTR(-ENOMEM); + + nla_for_each_nested(nla, nla_stgs, rem) { + struct bpf_map *map; + int map_fd; + + if (nla_type(nla) != SK_DIAG_BPF_STORAGE_REQ_MAP_FD) + continue; + + map_fd = nla_get_u32(nla); + map = bpf_map_get(map_fd); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto err_free; + } + if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) { + bpf_map_put(map); + err = -EINVAL; + goto err_free; + } + if (diag_check_dup(diag, map)) { + bpf_map_put(map); + err = -EEXIST; + goto err_free; + } + diag->maps[diag->nr_maps++] = map; + } + + return diag; + +err_free: + bpf_sk_storage_diag_free(diag); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); + +static int diag_get(struct bpf_sk_storage_data *sdata, struct sk_buff *skb) +{ + struct nlattr *nla_stg, *nla_value; + struct bpf_sk_storage_map *smap; + + /* It cannot exceed max nlattr's payload */ + BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < MAX_VALUE_SIZE); + + nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE); + if (!nla_stg) + return -EMSGSIZE; + + smap = rcu_dereference(sdata->smap); + if (nla_put_u32(skb, SK_DIAG_BPF_STORAGE_MAP_ID, smap->map.id)) + goto errout; + + nla_value = nla_reserve_64bit(skb, SK_DIAG_BPF_STORAGE_MAP_VALUE, + smap->map.value_size, + SK_DIAG_BPF_STORAGE_PAD); + if (!nla_value) + goto errout; + + if (map_value_has_spin_lock(&smap->map)) + copy_map_value_locked(&smap->map, nla_data(nla_value), + sdata->data, true); + else + copy_map_value(&smap->map, nla_data(nla_value), sdata->data); + + nla_nest_end(skb, nla_stg); + return 0; + +errout: + nla_nest_cancel(skb, nla_stg); + return -EMSGSIZE; +} + +static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, + int stg_array_type, + unsigned int *res_diag_size) +{ + /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ + unsigned int diag_size = nla_total_size(0); + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage_map *smap; + struct nlattr *nla_stgs; + unsigned int saved_len; + int err = 0; + + rcu_read_lock(); + + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage || hlist_empty(&sk_storage->list)) { + rcu_read_unlock(); + return 0; + } + + nla_stgs = nla_nest_start(skb, stg_array_type); + if (!nla_stgs) + /* Continue to learn diag_size */ + err = -EMSGSIZE; + + saved_len = skb->len; + hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { + smap = rcu_dereference(SDATA(selem)->smap); + diag_size += nla_value_size(smap->map.value_size); + + if (nla_stgs && diag_get(SDATA(selem), skb)) + /* Continue to learn diag_size */ + err = -EMSGSIZE; + } + + rcu_read_unlock(); + + if (nla_stgs) { + if (saved_len == skb->len) + nla_nest_cancel(skb, nla_stgs); + else + nla_nest_end(skb, nla_stgs); + } + + if (diag_size == nla_total_size(0)) { + *res_diag_size = 0; + return 0; + } + + *res_diag_size = diag_size; + return err; +} + +int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, + struct sock *sk, struct sk_buff *skb, + int stg_array_type, + unsigned int *res_diag_size) +{ + /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ + unsigned int diag_size = nla_total_size(0); + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_data *sdata; + struct nlattr *nla_stgs; + unsigned int saved_len; + int err = 0; + u32 i; + + *res_diag_size = 0; + + /* No map has been specified. Dump all. */ + if (!diag->nr_maps) + return bpf_sk_storage_diag_put_all(sk, skb, stg_array_type, + res_diag_size); + + rcu_read_lock(); + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage || hlist_empty(&sk_storage->list)) { + rcu_read_unlock(); + return 0; + } + + nla_stgs = nla_nest_start(skb, stg_array_type); + if (!nla_stgs) + /* Continue to learn diag_size */ + err = -EMSGSIZE; + + saved_len = skb->len; + for (i = 0; i < diag->nr_maps; i++) { + sdata = __sk_storage_lookup(sk_storage, + (struct bpf_sk_storage_map *)diag->maps[i], + false); + + if (!sdata) + continue; + + diag_size += nla_value_size(diag->maps[i]->value_size); + + if (nla_stgs && diag_get(sdata, skb)) + /* Continue to learn diag_size */ + err = -EMSGSIZE; + } + rcu_read_unlock(); + + if (nla_stgs) { + if (saved_len == skb->len) + nla_nest_cancel(skb, nla_stgs); + else + nla_nest_end(skb, nla_stgs); + } + + if (diag_size == nla_total_size(0)) { + *res_diag_size = 0; + return 0; + } + + *res_diag_size = diag_size; + return err; +} +EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_put); diff --git a/net/core/datagram.c b/net/core/datagram.c index a78e7f864c1e..4213081c6ed3 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -166,8 +166,6 @@ done: struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), int *off, int *err, struct sk_buff **last) { @@ -198,8 +196,6 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, refcount_inc(&skb->users); } else { __skb_unlink(skb, queue); - if (destructor) - destructor(sk, skb); } *off = _off; return skb; @@ -212,7 +208,6 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, * @sk: socket * @queue: socket queue from which to receive * @flags: MSG\_ flags - * @destructor: invoked under the receive lock on successful dequeue * @off: an offset in bytes to peek skb from. Returns an offset * within an skb where data actually starts * @err: error code returned @@ -245,10 +240,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, */ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, - unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), - int *off, int *err, + unsigned int flags, int *off, int *err, struct sk_buff **last) { struct sk_buff *skb; @@ -269,8 +261,8 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, * However, this function was correct in any case. 8) */ spin_lock_irqsave(&queue->lock, cpu_flags); - skb = __skb_try_recv_from_queue(sk, queue, flags, destructor, - off, &error, last); + skb = __skb_try_recv_from_queue(sk, queue, flags, off, &error, + last); spin_unlock_irqrestore(&queue->lock, cpu_flags); if (error) goto no_packet; @@ -293,10 +285,7 @@ EXPORT_SYMBOL(__skb_try_recv_datagram); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, - unsigned int flags, - void (*destructor)(struct sock *sk, - struct sk_buff *skb), - int *off, int *err) + unsigned int flags, int *off, int *err) { struct sk_buff *skb, *last; long timeo; @@ -304,8 +293,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { - skb = __skb_try_recv_datagram(sk, sk_queue, flags, destructor, - off, err, &last); + skb = __skb_try_recv_datagram(sk, sk_queue, flags, off, err, + &last); if (skb) return skb; @@ -326,7 +315,7 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, return __skb_recv_datagram(sk, &sk->sk_receive_queue, flags | (noblock ? MSG_DONTWAIT : 0), - NULL, &off, err); + &off, err); } EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/core/dev.c b/net/core/dev.c index c6c985fe7b1b..d84541c24446 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4638,7 +4638,6 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) kfree_skb(skb); } } -EXPORT_SYMBOL_GPL(generic_xdp_tx); static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); @@ -4849,7 +4848,8 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, skb->tc_at_ingress = 1; mini_qdisc_bstats_cpu_update(miniq, skb); - switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) { + switch (tcf_classify_ingress(skb, miniq->block, miniq->filter_list, + &cl_res, false)) { case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(cl_res.classid); @@ -10006,6 +10006,7 @@ EXPORT_SYMBOL(unregister_netdev); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { + struct net *net_old = dev_net(dev); int err, new_nsid, new_ifindex; ASSERT_RTNL(); @@ -10021,7 +10022,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Get out if there is nothing todo */ err = 0; - if (net_eq(dev_net(dev), net)) + if (net_eq(net_old, net)) goto out; /* Pick the destination device name, and ensure @@ -10097,6 +10098,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char err = device_rename(&dev->dev, dev->name); WARN_ON(err); + /* Adapt owner in case owning user namespace of target network + * namespace is different from the original one. + */ + err = netdev_change_owner(dev, net_old, net); + WARN_ON(err); + /* Add the device back in the hashes */ list_netdevice(dev); diff --git a/net/core/devlink.c b/net/core/devlink.c index b831c5545d6a..f51bebc8c33f 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -545,6 +545,7 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, case DEVLINK_PORT_FLAVOUR_PHYSICAL: case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: + case DEVLINK_PORT_FLAVOUR_VIRTUAL: if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER, attrs->phys.port_number)) return -EMSGSIZE; @@ -4239,11 +4240,17 @@ struct devlink_fmsg_item { int attrtype; u8 nla_type; u16 len; - int value[0]; + int value[]; }; struct devlink_fmsg { struct list_head item_list; + bool putting_binary; /* This flag forces enclosing of binary data + * in an array brackets. It forces using + * of designated API: + * devlink_fmsg_binary_pair_nest_start() + * devlink_fmsg_binary_pair_nest_end() + */ }; static struct devlink_fmsg *devlink_fmsg_alloc(void) @@ -4287,17 +4294,26 @@ static int devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); } EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_start); static int devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); } int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_end); @@ -4308,6 +4324,9 @@ static int devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) { struct devlink_fmsg_item *item; + if (fmsg->putting_binary) + return -EINVAL; + if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) return -EMSGSIZE; @@ -4328,6 +4347,9 @@ int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) { int err; + if (fmsg->putting_binary) + return -EINVAL; + err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); if (err) return err; @@ -4342,6 +4364,9 @@ EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_start); int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_end); @@ -4351,6 +4376,9 @@ int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, { int err; + if (fmsg->putting_binary) + return -EINVAL; + err = devlink_fmsg_pair_nest_start(fmsg, name); if (err) return err; @@ -4367,6 +4395,9 @@ int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) { int err; + if (fmsg->putting_binary) + return -EINVAL; + err = devlink_fmsg_nest_end(fmsg); if (err) return err; @@ -4379,6 +4410,30 @@ int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) } EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_end); +int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) +{ + int err; + + err = devlink_fmsg_arr_pair_nest_start(fmsg, name); + if (err) + return err; + + fmsg->putting_binary = true; + return err; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_start); + +int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg) +{ + if (!fmsg->putting_binary) + return -EINVAL; + + fmsg->putting_binary = false; + return devlink_fmsg_arr_pair_nest_end(fmsg); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_end); + static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, const void *value, u16 value_len, u8 value_nla_type) @@ -4403,40 +4458,59 @@ static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); } EXPORT_SYMBOL_GPL(devlink_fmsg_bool_put); int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); } EXPORT_SYMBOL_GPL(devlink_fmsg_u8_put); int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); } EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); } EXPORT_SYMBOL_GPL(devlink_fmsg_u64_put); int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, NLA_NUL_STRING); } EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); -static int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len) +int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) { + if (!fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); } +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, bool value) @@ -4547,10 +4621,11 @@ int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, const void *value, u32 value_len) { u32 data_size; + int end_err; u32 offset; int err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, name); + err = devlink_fmsg_binary_pair_nest_start(fmsg, name); if (err) return err; @@ -4560,14 +4635,18 @@ int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, data_size = DEVLINK_FMSG_MAX_SIZE; err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); if (err) - return err; + break; + /* Exit from loop with a break (instead of + * return) to make sure putting_binary is turned off in + * devlink_fmsg_binary_pair_nest_end + */ } - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; + end_err = devlink_fmsg_binary_pair_nest_end(fmsg); + if (end_err) + err = end_err; - return 0; + return err; } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put); @@ -5469,6 +5548,9 @@ static int devlink_trap_metadata_put(struct sk_buff *msg, if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) && nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT)) goto nla_put_failure; + if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE) && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE)) + goto nla_put_failure; nla_nest_end(msg, attr); @@ -6734,6 +6816,7 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: + case DEVLINK_PORT_FLAVOUR_VIRTUAL: if (!attrs->split) n = snprintf(name, len, "p%u", attrs->phys.port_number); else @@ -7734,6 +7817,8 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(NON_ROUTABLE, DROP), DEVLINK_TRAP(DECAP_ERROR, EXCEPTION), DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP), + DEVLINK_TRAP(INGRESS_FLOW_ACTION_DROP, DROP), + DEVLINK_TRAP(EGRESS_FLOW_ACTION_DROP, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -7747,6 +7832,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(L3_DROPS), DEVLINK_TRAP_GROUP(BUFFER_DROPS), DEVLINK_TRAP_GROUP(TUNNEL_DROPS), + DEVLINK_TRAP_GROUP(ACL_DROPS), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) @@ -8138,12 +8224,14 @@ devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, static void devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata, const struct devlink_trap_item *trap_item, - struct devlink_port *in_devlink_port) + struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie) { struct devlink_trap_group_item *group_item = trap_item->group_item; hw_metadata->trap_group_name = group_item->group->name; hw_metadata->trap_name = trap_item->trap->name; + hw_metadata->fa_cookie = fa_cookie; spin_lock(&in_devlink_port->type_lock); if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) @@ -8157,9 +8245,12 @@ devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata, * @skb: Trapped packet. * @trap_ctx: Trap context. * @in_devlink_port: Input devlink port. + * @fa_cookie: Flow action cookie. Could be NULL. */ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, - void *trap_ctx, struct devlink_port *in_devlink_port) + void *trap_ctx, struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie) + { struct devlink_trap_item *trap_item = trap_ctx; struct net_dm_hw_metadata hw_metadata = {}; @@ -8168,7 +8259,7 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, devlink_trap_stats_update(trap_item->group_item->stats, skb->len); devlink_trap_report_metadata_fill(&hw_metadata, trap_item, - in_devlink_port); + in_devlink_port, fa_cookie); net_dm_hw_report(skb, &hw_metadata); } EXPORT_SYMBOL_GPL(devlink_trap_report); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 31700e0c3928..8e33cec9fc4e 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -29,6 +29,7 @@ #include <net/drop_monitor.h> #include <net/genetlink.h> #include <net/netevent.h> +#include <net/flow_offload.h> #include <trace/events/skb.h> #include <trace/events/napi.h> @@ -67,7 +68,7 @@ struct net_dm_hw_entry { struct net_dm_hw_entries { u32 num_entries; - struct net_dm_hw_entry entries[0]; + struct net_dm_hw_entry entries[]; }; struct per_cpu_dm_data { @@ -701,6 +702,13 @@ static void net_dm_packet_work(struct work_struct *work) } static size_t +net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata) +{ + return hw_metadata->fa_cookie ? + nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0; +} + +static size_t net_dm_hw_packet_report_size(size_t payload_len, const struct net_dm_hw_metadata *hw_metadata) { @@ -717,6 +725,8 @@ net_dm_hw_packet_report_size(size_t payload_len, nla_total_size(strlen(hw_metadata->trap_name) + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + + /* NET_DM_ATTR_FLOW_ACTION_COOKIE */ + net_dm_flow_action_cookie_size(hw_metadata) + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ @@ -762,6 +772,12 @@ static int net_dm_hw_packet_report_fill(struct sk_buff *msg, goto nla_put_failure; } + if (hw_metadata->fa_cookie && + nla_put(msg, NET_DM_ATTR_FLOW_ACTION_COOKIE, + hw_metadata->fa_cookie->cookie_len, + hw_metadata->fa_cookie->cookie)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; @@ -794,11 +810,12 @@ nla_put_failure: static struct net_dm_hw_metadata * net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata) { + const struct flow_action_cookie *fa_cookie; struct net_dm_hw_metadata *n_hw_metadata; const char *trap_group_name; const char *trap_name; - n_hw_metadata = kmalloc(sizeof(*hw_metadata), GFP_ATOMIC); + n_hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC); if (!n_hw_metadata) return NULL; @@ -812,12 +829,25 @@ net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata) goto free_trap_group; n_hw_metadata->trap_name = trap_name; + if (hw_metadata->fa_cookie) { + size_t cookie_size = sizeof(*fa_cookie) + + hw_metadata->fa_cookie->cookie_len; + + fa_cookie = kmemdup(hw_metadata->fa_cookie, cookie_size, + GFP_ATOMIC); + if (!fa_cookie) + goto free_trap_name; + n_hw_metadata->fa_cookie = fa_cookie; + } + n_hw_metadata->input_dev = hw_metadata->input_dev; if (n_hw_metadata->input_dev) dev_hold(n_hw_metadata->input_dev); return n_hw_metadata; +free_trap_name: + kfree(trap_name); free_trap_group: kfree(trap_group_name); free_hw_metadata: @@ -830,6 +860,7 @@ net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata) { if (hw_metadata->input_dev) dev_put(hw_metadata->input_dev); + kfree(hw_metadata->fa_cookie); kfree(hw_metadata->trap_name); kfree(hw_metadata->trap_group_name); kfree(hw_metadata); diff --git a/net/core/filter.c b/net/core/filter.c index c180871e606d..4a08c9fb2be7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3626,7 +3626,6 @@ err: _trace_xdp_redirect_err(dev, xdp_prog, index, err); return err; } -EXPORT_SYMBOL_GPL(xdp_do_generic_redirect); BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { @@ -8620,6 +8619,7 @@ struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, struct bpf_map *, map, void *, key, u32, flags) { + bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; struct sock_reuseport *reuse; struct sock *selected_sk; @@ -8628,26 +8628,20 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, return -ENOENT; reuse = rcu_dereference(selected_sk->sk_reuseport_cb); - if (!reuse) - /* selected_sk is unhashed (e.g. by close()) after the - * above map_lookup_elem(). Treat selected_sk has already - * been removed from the map. + if (!reuse) { + /* reuseport_array has only sk with non NULL sk_reuseport_cb. + * The only (!reuse) case here is - the sk has already been + * unhashed (e.g. by close()), so treat it as -ENOENT. + * + * Other maps (e.g. sock_map) do not provide this guarantee and + * the sk may never be in the reuseport group to begin with. */ - return -ENOENT; + return is_sockarray ? -ENOENT : -EINVAL; + } if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { - struct sock *sk; - - if (unlikely(!reuse_kern->reuseport_id)) - /* There is a small race between adding the - * sk to the map and setting the - * reuse_kern->reuseport_id. - * Treat it as the sk has not been added to - * the bpf map yet. - */ - return -ENOENT; + struct sock *sk = reuse_kern->sk; - sk = reuse_kern->sk; if (sk->sk_protocol != selected_sk->sk_protocol) return -EPROTOTYPE; else if (sk->sk_family != selected_sk->sk_family) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index a1670dff0629..3eff84824c8b 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -920,9 +920,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); flow_keys->flags = flags; - preempt_disable(); - result = BPF_PROG_RUN(prog, ctx); - preempt_enable(); + result = bpf_prog_run_pin_on_cpu(prog, ctx); flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 45b6a59ac124..7440e6117c81 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -167,6 +167,34 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule, } EXPORT_SYMBOL(flow_rule_match_enc_opts); +struct flow_action_cookie *flow_action_cookie_create(void *data, + unsigned int len, + gfp_t gfp) +{ + struct flow_action_cookie *cookie; + + cookie = kmalloc(sizeof(*cookie) + len, gfp); + if (!cookie) + return NULL; + cookie->cookie_len = len; + memcpy(cookie->cookie, data, len); + return cookie; +} +EXPORT_SYMBOL(flow_action_cookie_create); + +void flow_action_cookie_destroy(struct flow_action_cookie *cookie) +{ + kfree(cookie); +} +EXPORT_SYMBOL(flow_action_cookie_destroy); + +void flow_rule_match_ct(const struct flow_rule *rule, + struct flow_match_ct *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CT, out); +} +EXPORT_SYMBOL(flow_rule_match_ct); + struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 789a73aa7bd8..5bf8d22a47ec 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3553,9 +3553,6 @@ static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write, #define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies) -#define NEIGH_SYSCTL_MS_JIFFIES_ENTRY(attr, name) \ - NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies) - #define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \ NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4c826b8bf9b1..cf0215734ceb 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -944,6 +944,24 @@ err: kobject_put(kobj); return error; } + +static int rx_queue_change_owner(struct net_device *dev, int index, kuid_t kuid, + kgid_t kgid) +{ + struct netdev_rx_queue *queue = dev->_rx + index; + struct kobject *kobj = &queue->kobj; + int error; + + error = sysfs_change_owner(kobj, kuid, kgid); + if (error) + return error; + + if (dev->sysfs_rx_queue_group) + error = sysfs_group_change_owner( + kobj, dev->sysfs_rx_queue_group, kuid, kgid); + + return error; +} #endif /* CONFIG_SYSFS */ int @@ -981,6 +999,29 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) #endif } +static int net_rx_queue_change_owner(struct net_device *dev, int num, + kuid_t kuid, kgid_t kgid) +{ +#ifdef CONFIG_SYSFS + int error = 0; + int i; + +#ifndef CONFIG_RPS + if (!dev->sysfs_rx_queue_group) + return 0; +#endif + for (i = 0; i < num; i++) { + error = rx_queue_change_owner(dev, i, kuid, kgid); + if (error) + break; + } + + return error; +#else + return 0; +#endif +} + #ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. @@ -1486,6 +1527,23 @@ err: kobject_put(kobj); return error; } + +static int tx_queue_change_owner(struct net_device *ndev, int index, + kuid_t kuid, kgid_t kgid) +{ + struct netdev_queue *queue = ndev->_tx + index; + struct kobject *kobj = &queue->kobj; + int error; + + error = sysfs_change_owner(kobj, kuid, kgid); + if (error) + return error; + +#ifdef CONFIG_BQL + error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); +#endif + return error; +} #endif /* CONFIG_SYSFS */ int @@ -1520,6 +1578,25 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) #endif /* CONFIG_SYSFS */ } +static int net_tx_queue_change_owner(struct net_device *dev, int num, + kuid_t kuid, kgid_t kgid) +{ +#ifdef CONFIG_SYSFS + int error = 0; + int i; + + for (i = 0; i < num; i++) { + error = tx_queue_change_owner(dev, i, kuid, kgid); + if (error) + break; + } + + return error; +#else + return 0; +#endif /* CONFIG_SYSFS */ +} + static int register_queue_kobjects(struct net_device *dev) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; @@ -1554,6 +1631,31 @@ error: return error; } +static int queue_change_owner(struct net_device *ndev, kuid_t kuid, kgid_t kgid) +{ + int error = 0, real_rx = 0, real_tx = 0; + +#ifdef CONFIG_SYSFS + if (ndev->queues_kset) { + error = sysfs_change_owner(&ndev->queues_kset->kobj, kuid, kgid); + if (error) + return error; + } + real_rx = ndev->real_num_rx_queues; +#endif + real_tx = ndev->real_num_tx_queues; + + error = net_rx_queue_change_owner(ndev, real_rx, kuid, kgid); + if (error) + return error; + + error = net_tx_queue_change_owner(ndev, real_tx, kuid, kgid); + if (error) + return error; + + return 0; +} + static void remove_queue_kobjects(struct net_device *dev) { int real_rx = 0, real_tx = 0; @@ -1767,6 +1869,37 @@ int netdev_register_kobject(struct net_device *ndev) return error; } +/* Change owner for sysfs entries when moving network devices across network + * namespaces owned by different user namespaces. + */ +int netdev_change_owner(struct net_device *ndev, const struct net *net_old, + const struct net *net_new) +{ + struct device *dev = &ndev->dev; + kuid_t old_uid, new_uid; + kgid_t old_gid, new_gid; + int error; + + net_ns_get_ownership(net_old, &old_uid, &old_gid); + net_ns_get_ownership(net_new, &new_uid, &new_gid); + + /* The network namespace was changed but the owning user namespace is + * identical so there's no need to change the owner of sysfs entries. + */ + if (uid_eq(old_uid, new_uid) && gid_eq(old_gid, new_gid)) + return 0; + + error = device_change_owner(dev, new_uid, new_gid); + if (error) + return error; + + error = queue_change_owner(ndev, new_uid, new_gid); + if (error) + return error; + + return 0; +} + int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns) { diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index 006876c7b78d..8a5b04c2699a 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -8,5 +8,7 @@ void netdev_unregister_kobject(struct net_device *); int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); int netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num); +int netdev_change_owner(struct net_device *, const struct net *net_old, + const struct net *net_new); #endif diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 10d2b255df5e..626db912fce4 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -96,7 +96,7 @@ struct page_pool *page_pool_create(const struct page_pool_params *params) } EXPORT_SYMBOL(page_pool_create); -static void __page_pool_return_page(struct page_pool *pool, struct page *page); +static void page_pool_return_page(struct page_pool *pool, struct page *page); noinline static struct page *page_pool_refill_alloc_cache(struct page_pool *pool) @@ -136,7 +136,7 @@ static struct page *page_pool_refill_alloc_cache(struct page_pool *pool) * (2) break out to fallthrough to alloc_pages_node. * This limit stress on page buddy alloactor. */ - __page_pool_return_page(pool, page); + page_pool_return_page(pool, page); page = NULL; break; } @@ -274,18 +274,25 @@ static s32 page_pool_inflight(struct page_pool *pool) return inflight; } -/* Cleanup page_pool state from page */ -static void __page_pool_clean_page(struct page_pool *pool, - struct page *page) +/* Disconnects a page (from a page_pool). API users can have a need + * to disconnect a page (from a page_pool), to allow it to be used as + * a regular page (that will eventually be returned to the normal + * page-allocator via put_page). + */ +void page_pool_release_page(struct page_pool *pool, struct page *page) { dma_addr_t dma; int count; if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + /* Always account for inflight pages, even if we didn't + * map them + */ goto skip_dma_unmap; dma = page->dma_addr; - /* DMA unmap */ + + /* When page is unmapped, it cannot be returned our pool */ dma_unmap_page_attrs(pool->p.dev, dma, PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC); @@ -297,21 +304,12 @@ skip_dma_unmap: count = atomic_inc_return(&pool->pages_state_release_cnt); trace_page_pool_state_release(pool, page, count); } - -/* unmap the page and clean our state */ -void page_pool_unmap_page(struct page_pool *pool, struct page *page) -{ - /* When page is unmapped, this implies page will not be - * returned to page_pool. - */ - __page_pool_clean_page(pool, page); -} -EXPORT_SYMBOL(page_pool_unmap_page); +EXPORT_SYMBOL(page_pool_release_page); /* Return a page to the page allocator, cleaning up our state */ -static void __page_pool_return_page(struct page_pool *pool, struct page *page) +static void page_pool_return_page(struct page_pool *pool, struct page *page) { - __page_pool_clean_page(pool, page); + page_pool_release_page(pool, page); put_page(page); /* An optimization would be to call __free_pages(page, pool->p.order) @@ -320,8 +318,7 @@ static void __page_pool_return_page(struct page_pool *pool, struct page *page) */ } -static bool __page_pool_recycle_into_ring(struct page_pool *pool, - struct page *page) +static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page) { int ret; /* BH protection not needed if current is serving softirq */ @@ -338,7 +335,7 @@ static bool __page_pool_recycle_into_ring(struct page_pool *pool, * * Caller must provide appropriate safe context. */ -static bool __page_pool_recycle_direct(struct page *page, +static bool page_pool_recycle_in_cache(struct page *page, struct page_pool *pool) { if (unlikely(pool->alloc.count == PP_ALLOC_CACHE_SIZE)) @@ -357,8 +354,14 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page) return !page_is_pfmemalloc(page); } -void __page_pool_put_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct) +/* If the page refcnt == 1, this will try to recycle the page. + * if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for + * the configured size min(dma_sync_size, pool->max_len). + * If the page refcnt != 1, then the page will be returned to memory + * subsystem. + */ +void page_pool_put_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct) { /* This allocator is optimized for the XDP mode that uses * one-frame-per-page, but have fallbacks that act like the @@ -375,12 +378,12 @@ void __page_pool_put_page(struct page_pool *pool, struct page *page, dma_sync_size); if (allow_direct && in_serving_softirq()) - if (__page_pool_recycle_direct(page, pool)) + if (page_pool_recycle_in_cache(page, pool)) return; - if (!__page_pool_recycle_into_ring(pool, page)) { + if (!page_pool_recycle_in_ring(pool, page)) { /* Cache full, fallback to free pages */ - __page_pool_return_page(pool, page); + page_pool_return_page(pool, page); } return; } @@ -397,12 +400,13 @@ void __page_pool_put_page(struct page_pool *pool, struct page *page, * doing refcnt based recycle tricks, meaning another process * will be invoking put_page. */ - __page_pool_clean_page(pool, page); + /* Do not replace this with page_pool_return_page() */ + page_pool_release_page(pool, page); put_page(page); } -EXPORT_SYMBOL(__page_pool_put_page); +EXPORT_SYMBOL(page_pool_put_page); -static void __page_pool_empty_ring(struct page_pool *pool) +static void page_pool_empty_ring(struct page_pool *pool) { struct page *page; @@ -413,7 +417,7 @@ static void __page_pool_empty_ring(struct page_pool *pool) pr_crit("%s() page_pool refcnt %d violation\n", __func__, page_ref_count(page)); - __page_pool_return_page(pool, page); + page_pool_return_page(pool, page); } } @@ -443,7 +447,7 @@ static void page_pool_empty_alloc_cache_once(struct page_pool *pool) */ while (pool->alloc.count) { page = pool->alloc.cache[--pool->alloc.count]; - __page_pool_return_page(pool, page); + page_pool_return_page(pool, page); } } @@ -455,7 +459,7 @@ static void page_pool_scrub(struct page_pool *pool) /* No more consumers should exist, but producers could still * be in-flight. */ - __page_pool_empty_ring(pool); + page_pool_empty_ring(pool); } static int page_pool_release(struct page_pool *pool) @@ -529,7 +533,7 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) /* Flush pool alloc cache, as refill will check NUMA node */ while (pool->alloc.count) { page = pool->alloc.cache[--pool->alloc.count]; - __page_pool_return_page(pool, page); + page_pool_return_page(pool, page); } } EXPORT_SYMBOL(page_pool_update_nid); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index acc849df60b5..f2b3d8dd40f4 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2003,8 +2003,8 @@ static int pktgen_setup_dev(const struct pktgen_net *pn, return -ENODEV; } - if (odev->type != ARPHRD_ETHER) { - pr_err("not an ethernet device: \"%s\"\n", ifname); + if (odev->type != ARPHRD_ETHER && odev->type != ARPHRD_LOOPBACK) { + pr_err("not an ethernet or loopback device: \"%s\"\n", ifname); err = -EINVAL; } else if (!netif_running(odev)) { pr_err("device is down: \"%s\"\n", ifname); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e1152f4ffe33..14e6ea21c378 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3909,7 +3909,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, /* Support fdb on master device the net/bridge default case */ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && - (dev->priv_flags & IFF_BRIDGE_PORT)) { + netif_is_bridge_port(dev)) { struct net_device *br_dev = netdev_master_upper_dev_get(dev); const struct net_device_ops *ops = br_dev->netdev_ops; @@ -4020,7 +4020,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, /* Support fdb on master device the net/bridge default case */ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && - (dev->priv_flags & IFF_BRIDGE_PORT)) { + netif_is_bridge_port(dev)) { struct net_device *br_dev = netdev_master_upper_dev_get(dev); const struct net_device_ops *ops = br_dev->netdev_ops; @@ -4246,13 +4246,13 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; if (!br_idx) { /* user did not specify a specific bridge */ - if (dev->priv_flags & IFF_BRIDGE_PORT) { + if (netif_is_bridge_port(dev)) { br_dev = netdev_master_upper_dev_get(dev); cops = br_dev->netdev_ops; } } else { if (dev != br_dev && - !(dev->priv_flags & IFF_BRIDGE_PORT)) + !netif_is_bridge_port(dev)) continue; if (br_dev != netdev_master_upper_dev_get(dev) && @@ -4264,7 +4264,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) if (idx < s_idx) goto cont; - if (dev->priv_flags & IFF_BRIDGE_PORT) { + if (netif_is_bridge_port(dev)) { if (cops && cops->ndo_fdb_dump) { err = cops->ndo_fdb_dump(skb, cb, br_dev, dev, @@ -4414,7 +4414,7 @@ static int rtnl_fdb_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (dev) { if (!ndm_flags || (ndm_flags & NTF_MASTER)) { - if (!(dev->priv_flags & IFF_BRIDGE_PORT)) { + if (!netif_is_bridge_port(dev)) { NL_SET_ERR_MSG(extack, "Device is not a bridge port"); return -EINVAL; } @@ -4553,7 +4553,11 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, brport_nla_put_flag(skb, flags, mask, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD) || brport_nla_put_flag(skb, flags, mask, - IFLA_BRPORT_PROXYARP, BR_PROXYARP)) { + IFLA_BRPORT_PROXYARP, BR_PROXYARP) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD)) { nla_nest_cancel(skb, protinfo); goto nla_put_failure; } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index ded2d5227678..c479372f2cd2 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -512,7 +512,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED); refcount_set(&psock->refcnt, 1); - rcu_assign_sk_user_data(sk, psock); + rcu_assign_sk_user_data_nocopy(sk, psock); sock_hold(sk); return psock; @@ -628,7 +628,6 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct bpf_prog *prog; int ret; - preempt_disable(); rcu_read_lock(); prog = READ_ONCE(psock->progs.msg_parser); if (unlikely(!prog)) { @@ -638,7 +637,7 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, sk_msg_compute_data_pointers(msg); msg->sk = sk; - ret = BPF_PROG_RUN(prog, msg); + ret = bpf_prog_run_pin_on_cpu(prog, msg); ret = sk_psock_map_verd(ret, msg->sk_redir); psock->apply_bytes = msg->apply_bytes; if (ret == __SK_REDIRECT) { @@ -653,7 +652,6 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, } out: rcu_read_unlock(); - preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); @@ -665,9 +663,7 @@ static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, skb->sk = psock->sk; bpf_compute_data_end_sk_skb(skb); - preempt_disable(); - ret = BPF_PROG_RUN(prog, skb); - preempt_enable(); + ret = bpf_prog_run_pin_on_cpu(prog, skb); /* strparser clones the skb before handing it to a upper layer, * meaning skb_orphan has been called. We NULL sk on the way out * to ensure we don't trigger a BUG_ON() in skb/sk operations diff --git a/net/core/sock.c b/net/core/sock.c index 8f71684305c3..0fc8937a7ff4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1572,13 +1572,14 @@ static inline void sock_lock_init(struct sock *sk) */ static void sock_copy(struct sock *nsk, const struct sock *osk) { + const struct proto *prot = READ_ONCE(osk->sk_prot); #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, - osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); + prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; @@ -1792,16 +1793,17 @@ static void sk_init_common(struct sock *sk) */ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { + struct proto *prot = READ_ONCE(sk->sk_prot); struct sock *newsk; bool is_charged = true; - newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family); + newsk = sk_prot_alloc(prot, priority, sk->sk_family); if (newsk != NULL) { struct sk_filter *filter; sock_copy(newsk, sk); - newsk->sk_prot_creator = sk->sk_prot; + newsk->sk_prot_creator = prot; /* SANITY */ if (likely(newsk->sk_net_refcnt)) @@ -1866,6 +1868,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) goto out; } + /* Clear sk_user_data if parent had the pointer tagged + * as not suitable for copying when cloning. + */ + if (sk_user_data_is_nocopy(newsk)) + RCU_INIT_POINTER(newsk->sk_user_data, NULL); + newsk->sk_err = 0; newsk->sk_err_soft = 0; newsk->sk_priority = 0; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 085cef5857bb..2e0f465295c3 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -10,6 +10,7 @@ #include <linux/skmsg.h> #include <linux/list.h> #include <linux/jhash.h> +#include <linux/sock_diag.h> struct bpf_stab { struct bpf_map map; @@ -31,7 +32,8 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) return ERR_PTR(-EPERM); if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || + (attr->value_size != sizeof(u32) && + attr->value_size != sizeof(u64)) || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); @@ -228,6 +230,30 @@ out: return ret; } +static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk) +{ + struct sk_psock *psock; + int ret; + + psock = sk_psock_get_checked(sk); + if (IS_ERR(psock)) + return PTR_ERR(psock); + + if (psock) { + tcp_bpf_reinit(sk); + return 0; + } + + psock = sk_psock_init(sk, map->numa_node); + if (!psock) + return -ENOMEM; + + ret = tcp_bpf_init(sk); + if (ret < 0) + sk_psock_put(sk, psock); + return ret; +} + static void sock_map_free(struct bpf_map *map) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); @@ -275,7 +301,22 @@ static struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) static void *sock_map_lookup(struct bpf_map *map, void *key) { - return ERR_PTR(-EOPNOTSUPP); + return __sock_map_lookup_elem(map, *(u32 *)key); +} + +static void *sock_map_lookup_sys(struct bpf_map *map, void *key) +{ + struct sock *sk; + + if (map->value_size != sizeof(u64)) + return ERR_PTR(-ENOSPC); + + sk = __sock_map_lookup_elem(map, *(u32 *)key); + if (!sk) + return ERR_PTR(-ENOENT); + + sock_gen_cookie(sk); + return &sk->sk_cookie; } static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, @@ -334,6 +375,11 @@ static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next) return 0; } +static bool sock_map_redirect_allowed(const struct sock *sk) +{ + return sk->sk_state != TCP_LISTEN; +} + static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags) { @@ -356,7 +402,14 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, if (!link) return -ENOMEM; - ret = sock_map_link(map, &stab->progs, sk); + /* Only sockets we can redirect into/from in BPF need to hold + * refs to parser/verdict progs and have their sk_data_ready + * and sk_write_space callbacks overridden. + */ + if (sock_map_redirect_allowed(sk)) + ret = sock_map_link(map, &stab->progs, sk); + else + ret = sock_map_link_no_progs(map, sk); if (ret < 0) goto out_free; @@ -391,7 +444,8 @@ out_free: static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops) { return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB || - ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB; + ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB || + ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB; } static bool sock_map_sk_is_suitable(const struct sock *sk) @@ -400,14 +454,26 @@ static bool sock_map_sk_is_suitable(const struct sock *sk) sk->sk_protocol == IPPROTO_TCP; } +static bool sock_map_sk_state_allowed(const struct sock *sk) +{ + return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); +} + static int sock_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { - u32 ufd = *(u32 *)value; u32 idx = *(u32 *)key; struct socket *sock; struct sock *sk; int ret; + u64 ufd; + + if (map->value_size == sizeof(u64)) + ufd = *(u64 *)value; + else + ufd = *(u32 *)value; + if (ufd > S32_MAX) + return -EINVAL; sock = sockfd_lookup(ufd, &ret); if (!sock) @@ -423,7 +489,7 @@ static int sock_map_update_elem(struct bpf_map *map, void *key, } sock_map_sk_acquire(sk); - if (sk->sk_state != TCP_ESTABLISHED) + if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; else ret = sock_map_update_common(map, idx, sk, flags); @@ -460,13 +526,17 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, struct bpf_map *, map, u32, key, u64, flags) { struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; - tcb->bpf.flags = flags; - tcb->bpf.sk_redir = __sock_map_lookup_elem(map, key); - if (!tcb->bpf.sk_redir) + + sk = __sock_map_lookup_elem(map, key); + if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + + tcb->bpf.flags = flags; + tcb->bpf.sk_redir = sk; return SK_PASS; } @@ -483,12 +553,17 @@ const struct bpf_func_proto bpf_sk_redirect_map_proto = { BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, struct bpf_map *, map, u32, key, u64, flags) { + struct sock *sk; + if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; - msg->flags = flags; - msg->sk_redir = __sock_map_lookup_elem(map, key); - if (!msg->sk_redir) + + sk = __sock_map_lookup_elem(map, key); + if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + + msg->flags = flags; + msg->sk_redir = sk; return SK_PASS; } @@ -506,6 +581,7 @@ const struct bpf_map_ops sock_map_ops = { .map_alloc = sock_map_alloc, .map_free = sock_map_free, .map_get_next_key = sock_map_get_next_key, + .map_lookup_elem_sys_only = sock_map_lookup_sys, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_map_delete_elem, .map_lookup_elem = sock_map_lookup, @@ -518,7 +594,7 @@ struct bpf_htab_elem { u32 hash; struct sock *sk; struct hlist_node node; - u8 key[0]; + u8 key[]; }; struct bpf_htab_bucket { @@ -680,7 +756,14 @@ static int sock_hash_update_common(struct bpf_map *map, void *key, if (!link) return -ENOMEM; - ret = sock_map_link(map, &htab->progs, sk); + /* Only sockets we can redirect into/from in BPF need to hold + * refs to parser/verdict progs and have their sk_data_ready + * and sk_write_space callbacks overridden. + */ + if (sock_map_redirect_allowed(sk)) + ret = sock_map_link(map, &htab->progs, sk); + else + ret = sock_map_link_no_progs(map, sk); if (ret < 0) goto out_free; @@ -729,10 +812,17 @@ out_free: static int sock_hash_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { - u32 ufd = *(u32 *)value; struct socket *sock; struct sock *sk; int ret; + u64 ufd; + + if (map->value_size == sizeof(u64)) + ufd = *(u64 *)value; + else + ufd = *(u32 *)value; + if (ufd > S32_MAX) + return -EINVAL; sock = sockfd_lookup(ufd, &ret); if (!sock) @@ -748,7 +838,7 @@ static int sock_hash_update_elem(struct bpf_map *map, void *key, } sock_map_sk_acquire(sk); - if (sk->sk_state != TCP_ESTABLISHED) + if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; else ret = sock_hash_update_common(map, key, sk, flags); @@ -808,7 +898,8 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) return ERR_PTR(-EPERM); if (attr->max_entries == 0 || attr->key_size == 0 || - attr->value_size != 4 || + (attr->value_size != sizeof(u32) && + attr->value_size != sizeof(u64)) || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->key_size > MAX_BPF_STACK) @@ -885,6 +976,26 @@ static void sock_hash_free(struct bpf_map *map) kfree(htab); } +static void *sock_hash_lookup_sys(struct bpf_map *map, void *key) +{ + struct sock *sk; + + if (map->value_size != sizeof(u64)) + return ERR_PTR(-ENOSPC); + + sk = __sock_hash_lookup_elem(map, key); + if (!sk) + return ERR_PTR(-ENOENT); + + sock_gen_cookie(sk); + return &sk->sk_cookie; +} + +static void *sock_hash_lookup(struct bpf_map *map, void *key) +{ + return __sock_hash_lookup_elem(map, key); +} + static void sock_hash_release_progs(struct bpf_map *map) { psock_progs_drop(&container_of(map, struct bpf_htab, map)->progs); @@ -916,13 +1027,17 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, struct bpf_map *, map, void *, key, u64, flags) { struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; - tcb->bpf.flags = flags; - tcb->bpf.sk_redir = __sock_hash_lookup_elem(map, key); - if (!tcb->bpf.sk_redir) + + sk = __sock_hash_lookup_elem(map, key); + if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + + tcb->bpf.flags = flags; + tcb->bpf.sk_redir = sk; return SK_PASS; } @@ -939,12 +1054,17 @@ const struct bpf_func_proto bpf_sk_redirect_hash_proto = { BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, struct bpf_map *, map, void *, key, u64, flags) { + struct sock *sk; + if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; - msg->flags = flags; - msg->sk_redir = __sock_hash_lookup_elem(map, key); - if (!msg->sk_redir) + + sk = __sock_hash_lookup_elem(map, key); + if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + + msg->flags = flags; + msg->sk_redir = sk; return SK_PASS; } @@ -964,7 +1084,8 @@ const struct bpf_map_ops sock_hash_ops = { .map_get_next_key = sock_hash_get_next_key, .map_update_elem = sock_hash_update_elem, .map_delete_elem = sock_hash_delete_elem, - .map_lookup_elem = sock_map_lookup, + .map_lookup_elem = sock_hash_lookup, + .map_lookup_elem_sys_only = sock_hash_lookup_sys, .map_release_uref = sock_hash_release_progs, .map_check_btf = map_check_no_btf, }; diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 91e9f2223c39..adcb3aea576d 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -16,27 +16,8 @@ DEFINE_SPINLOCK(reuseport_lock); -#define REUSEPORT_MIN_ID 1 static DEFINE_IDA(reuseport_ida); -int reuseport_get_id(struct sock_reuseport *reuse) -{ - int id; - - if (reuse->reuseport_id) - return reuse->reuseport_id; - - id = ida_simple_get(&reuseport_ida, REUSEPORT_MIN_ID, 0, - /* Called under reuseport_lock */ - GFP_ATOMIC); - if (id < 0) - return id; - - reuse->reuseport_id = id; - - return reuse->reuseport_id; -} - static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { unsigned int size = sizeof(struct sock_reuseport) + @@ -55,6 +36,7 @@ static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) int reuseport_alloc(struct sock *sk, bool bind_inany) { struct sock_reuseport *reuse; + int id, ret = 0; /* bh lock used since this function call may precede hlist lock in * soft irq of receive path or setsockopt from process context @@ -78,10 +60,18 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) { - spin_unlock_bh(&reuseport_lock); - return -ENOMEM; + ret = -ENOMEM; + goto out; } + id = ida_alloc(&reuseport_ida, GFP_ATOMIC); + if (id < 0) { + kfree(reuse); + ret = id; + goto out; + } + + reuse->reuseport_id = id; reuse->socks[0] = sk; reuse->num_socks = 1; reuse->bind_inany = bind_inany; @@ -90,7 +80,7 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) out: spin_unlock_bh(&reuseport_lock); - return 0; + return ret; } EXPORT_SYMBOL(reuseport_alloc); @@ -134,8 +124,7 @@ static void reuseport_free_rcu(struct rcu_head *head) reuse = container_of(head, struct sock_reuseport, rcu); sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1)); - if (reuse->reuseport_id) - ida_simple_remove(&reuseport_ida, reuse->reuseport_id); + ida_free(&reuseport_ida, reuse->reuseport_id); kfree(reuse); } @@ -199,12 +188,15 @@ void reuseport_detach_sock(struct sock *sk) reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); - /* At least one of the sk in this reuseport group is added to - * a bpf map. Notify the bpf side. The bpf map logic will - * remove the sk if it is indeed added to a bpf map. + /* Notify the bpf side. The sk may be added to a sockarray + * map. If so, sockarray logic will remove it from the map. + * + * Other bpf map types that work with reuseport, like sockmap, + * don't need an explicit callback from here. They override sk + * unhash/close ops to remove the sk from the map before we + * get to this point. */ - if (reuse->reuseport_id) - bpf_sk_reuseport_detach(sk); + bpf_sk_reuseport_detach(sk); rcu_assign_pointer(sk->sk_reuseport_cb, NULL); diff --git a/net/core/xdp.c b/net/core/xdp.c index 8310714c47fd..4c7ea85486af 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -372,7 +372,7 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); napi_direct &= !xdp_return_frame_no_direct(); - page_pool_put_page(xa->page_pool, page, napi_direct); + page_pool_put_full_page(xa->page_pool, page, napi_direct); rcu_read_unlock(); break; case MEM_TYPE_PAGE_SHARED: diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 70f88f2b4456..105f3734dadb 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -95,7 +95,7 @@ void ccid_cleanup_builtins(void); struct ccid { struct ccid_operations *ccid_ops; - char ccid_priv[0]; + char ccid_priv[]; }; static inline void *ccid_priv(const struct ccid *ccid) diff --git a/net/dccp/diag.c b/net/dccp/diag.c index 73ef73a218ff..8a82c5a2c5a8 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -46,16 +46,15 @@ static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } static void dccp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r) { - inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r, bc); + inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r); } -static int dccp_diag_dump_one(struct sk_buff *in_skb, - const struct nlmsghdr *nlh, +static int dccp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { - return inet_diag_dump_one_icsk(&dccp_hashinfo, in_skb, nlh, req); + return inet_diag_dump_one_icsk(&dccp_hashinfo, cb, req); } static const struct inet_diag_handler dccp_diag_handler = { diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 25187528c308..c5c74a34d139 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -216,6 +216,7 @@ EXPORT_SYMBOL_GPL(dccp_check_req); */ int dccp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb) + __releases(child) { int ret = 0; const int state = child->sk_state; diff --git a/net/dsa/port.c b/net/dsa/port.c index ec13dc666788..e6875d8f944d 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -513,9 +513,11 @@ static void dsa_port_phylink_mac_link_down(struct phylink_config *config, } static void dsa_port_phylink_mac_link_up(struct phylink_config *config, + struct phy_device *phydev, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -526,7 +528,8 @@ static void dsa_port_phylink_mac_link_up(struct phylink_config *config, return; } - ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev); + ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev, + speed, duplex, tx_pause, rx_pause); } const struct phylink_mac_ops dsa_port_phylink_mac_ops = { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index ddc0f9236928..c5beb3031a72 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -861,6 +861,10 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, if (!flow_offload_has_one_action(&cls->rule->action)) return err; + if (!flow_action_basic_hw_stats_types_check(&cls->rule->action, + cls->common.extack)) + return err; + act = &cls->rule->action.entries[0]; if (act->id == FLOW_ACTION_MIRRED && protocol == htons(ETH_P_ALL)) { @@ -942,6 +946,64 @@ static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev, } } +static int dsa_slave_add_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->cls_flower_add) + return -EOPNOTSUPP; + + return ds->ops->cls_flower_add(ds, port, cls, ingress); +} + +static int dsa_slave_del_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->cls_flower_del) + return -EOPNOTSUPP; + + return ds->ops->cls_flower_del(ds, port, cls, ingress); +} + +static int dsa_slave_stats_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->cls_flower_stats) + return -EOPNOTSUPP; + + return ds->ops->cls_flower_stats(ds, port, cls, ingress); +} + +static int dsa_slave_setup_tc_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) +{ + switch (cls->command) { + case FLOW_CLS_REPLACE: + return dsa_slave_add_cls_flower(dev, cls, ingress); + case FLOW_CLS_DESTROY: + return dsa_slave_del_cls_flower(dev, cls, ingress); + case FLOW_CLS_STATS: + return dsa_slave_stats_cls_flower(dev, cls, ingress); + default: + return -EOPNOTSUPP; + } +} + static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv, bool ingress) { @@ -953,6 +1015,8 @@ static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSMATCHALL: return dsa_slave_setup_tc_cls_matchall(dev, type_data, ingress); + case TC_SETUP_CLSFLOWER: + return dsa_slave_setup_tc_cls_flower(dev, type_data, ingress); default: return -EOPNOTSUPP; } diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 8e3e7283d430..59de1315100f 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -153,7 +153,8 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, memset(injection, 0, OCELOT_TAG_LEN); - src = dsa_upstream_port(ds, port); + /* Set the source port as the CPU port module and not the NPI port */ + src = ocelot->num_phys_ports; dest = BIT(port); bypass = true; qos_class = skb->priority; diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 424545a4aaec..b0bd3decad02 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -5,4 +5,5 @@ obj-y += ioctl.o common.o obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ - linkstate.o debug.o wol.o + linkstate.o debug.o wol.o features.o privflags.o rings.o \ + channels.o diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index ef9197541cb3..dae7402eaca3 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -588,6 +588,100 @@ int ethnl_update_bitset32(u32 *bitmap, unsigned int nbits, return 0; } +/** + * ethnl_parse_bitset() - Compute effective value and mask from bitset nest + * @val: unsigned long based bitmap to put value into + * @mask: unsigned long based bitmap to put mask into + * @nbits: size of @val and @mask bitmaps + * @attr: nest attribute to parse and apply + * @names: array of bit names; may be null for compact format + * @extack: extack for error reporting + * + * Provide @nbits size long bitmaps for value and mask so that + * x = (val & mask) | (x & ~mask) would modify any @nbits sized bitmap x + * the same way ethnl_update_bitset() with the same bitset attribute would. + * + * Return: negative error code on failure, 0 on success + */ +int ethnl_parse_bitset(unsigned long *val, unsigned long *mask, + unsigned int nbits, const struct nlattr *attr, + ethnl_string_array_t names, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[ETHTOOL_A_BITSET_MAX + 1]; + const struct nlattr *bit_attr; + bool no_mask; + int rem; + int ret; + + if (!attr) + return 0; + ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_MAX, attr, bitset_policy, + extack); + if (ret < 0) + return ret; + no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; + + if (!tb[ETHTOOL_A_BITSET_BITS]) { + unsigned int change_bits; + + ret = ethnl_compact_sanity_checks(nbits, attr, tb, extack); + if (ret < 0) + return ret; + + change_bits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]); + bitmap_from_arr32(val, nla_data(tb[ETHTOOL_A_BITSET_VALUE]), + change_bits); + if (change_bits < nbits) + bitmap_clear(val, change_bits, nbits - change_bits); + if (no_mask) { + bitmap_fill(mask, nbits); + } else { + bitmap_from_arr32(mask, + nla_data(tb[ETHTOOL_A_BITSET_MASK]), + change_bits); + if (change_bits < nbits) + bitmap_clear(mask, change_bits, + nbits - change_bits); + } + + return 0; + } + + if (tb[ETHTOOL_A_BITSET_VALUE]) { + NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_VALUE], + "value only allowed in compact bitset"); + return -EINVAL; + } + if (tb[ETHTOOL_A_BITSET_MASK]) { + NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_BITSET_MASK], + "mask only allowed in compact bitset"); + return -EINVAL; + } + + bitmap_zero(val, nbits); + if (no_mask) + bitmap_fill(mask, nbits); + else + bitmap_zero(mask, nbits); + + nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { + unsigned int idx; + bool bit_val; + + ret = ethnl_parse_bit(&idx, &bit_val, nbits, bit_attr, no_mask, + names, extack); + if (ret < 0) + return ret; + if (bit_val) + __set_bit(idx, val); + if (!no_mask) + __set_bit(idx, mask); + } + + return 0; +} + #if BITS_PER_LONG == 64 && defined(__BIG_ENDIAN) /* 64-bit big endian architectures are the only case when u32 based bitmaps diff --git a/net/ethtool/bitset.h b/net/ethtool/bitset.h index b849f9d19676..c2c2e0051d00 100644 --- a/net/ethtool/bitset.h +++ b/net/ethtool/bitset.h @@ -26,5 +26,9 @@ int ethnl_update_bitset(unsigned long *bitmap, unsigned int nbits, int ethnl_update_bitset32(u32 *bitmap, unsigned int nbits, const struct nlattr *attr, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod); +int ethnl_parse_bitset(unsigned long *val, unsigned long *mask, + unsigned int nbits, const struct nlattr *attr, + ethnl_string_array_t names, + struct netlink_ext_ack *extack); #endif /* _NET_ETHTOOL_BITSET_H */ diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c new file mode 100644 index 000000000000..8dc5485333a4 --- /dev/null +++ b/net/ethtool/channels.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <net/xdp_sock.h> + +#include "netlink.h" +#include "common.h" + +struct channels_req_info { + struct ethnl_req_info base; +}; + +struct channels_reply_data { + struct ethnl_reply_data base; + struct ethtool_channels channels; +}; + +#define CHANNELS_REPDATA(__reply_base) \ + container_of(__reply_base, struct channels_reply_data, base) + +static const struct nla_policy +channels_get_policy[ETHTOOL_A_CHANNELS_MAX + 1] = { + [ETHTOOL_A_CHANNELS_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_CHANNELS_RX_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_TX_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_OTHER_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_COMBINED_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_RX_COUNT] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_TX_COUNT] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_OTHER_COUNT] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_COMBINED_COUNT] = { .type = NLA_REJECT }, +}; + +static int channels_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct channels_reply_data *data = CHANNELS_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + if (!dev->ethtool_ops->get_channels) + return -EOPNOTSUPP; + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + dev->ethtool_ops->get_channels(dev, &data->channels); + ethnl_ops_complete(dev); + + return 0; +} + +static int channels_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u32)) + /* _CHANNELS_RX_MAX */ + nla_total_size(sizeof(u32)) + /* _CHANNELS_TX_MAX */ + nla_total_size(sizeof(u32)) + /* _CHANNELS_OTHER_MAX */ + nla_total_size(sizeof(u32)) + /* _CHANNELS_COMBINED_MAX */ + nla_total_size(sizeof(u32)) + /* _CHANNELS_RX_COUNT */ + nla_total_size(sizeof(u32)) + /* _CHANNELS_TX_COUNT */ + nla_total_size(sizeof(u32)) + /* _CHANNELS_OTHER_COUNT */ + nla_total_size(sizeof(u32)); /* _CHANNELS_COMBINED_COUNT */ +} + +static int channels_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct channels_reply_data *data = CHANNELS_REPDATA(reply_base); + const struct ethtool_channels *channels = &data->channels; + + if ((channels->max_rx && + (nla_put_u32(skb, ETHTOOL_A_CHANNELS_RX_MAX, + channels->max_rx) || + nla_put_u32(skb, ETHTOOL_A_CHANNELS_RX_COUNT, + channels->rx_count))) || + (channels->max_tx && + (nla_put_u32(skb, ETHTOOL_A_CHANNELS_TX_MAX, + channels->max_tx) || + nla_put_u32(skb, ETHTOOL_A_CHANNELS_TX_COUNT, + channels->tx_count))) || + (channels->max_other && + (nla_put_u32(skb, ETHTOOL_A_CHANNELS_OTHER_MAX, + channels->max_other) || + nla_put_u32(skb, ETHTOOL_A_CHANNELS_OTHER_COUNT, + channels->other_count))) || + (channels->max_combined && + (nla_put_u32(skb, ETHTOOL_A_CHANNELS_COMBINED_MAX, + channels->max_combined) || + nla_put_u32(skb, ETHTOOL_A_CHANNELS_COMBINED_COUNT, + channels->combined_count)))) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_channels_request_ops = { + .request_cmd = ETHTOOL_MSG_CHANNELS_GET, + .reply_cmd = ETHTOOL_MSG_CHANNELS_GET_REPLY, + .hdr_attr = ETHTOOL_A_CHANNELS_HEADER, + .max_attr = ETHTOOL_A_CHANNELS_MAX, + .req_info_size = sizeof(struct channels_req_info), + .reply_data_size = sizeof(struct channels_reply_data), + .request_policy = channels_get_policy, + + .prepare_data = channels_prepare_data, + .reply_size = channels_reply_size, + .fill_reply = channels_fill_reply, +}; + +/* CHANNELS_SET */ + +static const struct nla_policy +channels_set_policy[ETHTOOL_A_CHANNELS_MAX + 1] = { + [ETHTOOL_A_CHANNELS_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_CHANNELS_RX_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_TX_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_OTHER_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_COMBINED_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_CHANNELS_RX_COUNT] = { .type = NLA_U32 }, + [ETHTOOL_A_CHANNELS_TX_COUNT] = { .type = NLA_U32 }, + [ETHTOOL_A_CHANNELS_OTHER_COUNT] = { .type = NLA_U32 }, + [ETHTOOL_A_CHANNELS_COMBINED_COUNT] = { .type = NLA_U32 }, +}; + +int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ETHTOOL_A_CHANNELS_MAX + 1]; + unsigned int from_channel, old_total, i; + struct ethtool_channels channels = {}; + struct ethnl_req_info req_info = {}; + const struct nlattr *err_attr; + const struct ethtool_ops *ops; + struct net_device *dev; + u32 max_rx_in_use = 0; + bool mod = false; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, + ETHTOOL_A_CHANNELS_MAX, channels_set_policy, + info->extack); + if (ret < 0) + return ret; + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_CHANNELS_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + ops = dev->ethtool_ops; + ret = -EOPNOTSUPP; + if (!ops->get_channels || !ops->set_channels) + goto out_dev; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + ops->get_channels(dev, &channels); + old_total = channels.combined_count + + max(channels.rx_count, channels.tx_count); + + ethnl_update_u32(&channels.rx_count, tb[ETHTOOL_A_CHANNELS_RX_COUNT], + &mod); + ethnl_update_u32(&channels.tx_count, tb[ETHTOOL_A_CHANNELS_TX_COUNT], + &mod); + ethnl_update_u32(&channels.other_count, + tb[ETHTOOL_A_CHANNELS_OTHER_COUNT], &mod); + ethnl_update_u32(&channels.combined_count, + tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT], &mod); + ret = 0; + if (!mod) + goto out_ops; + + /* ensure new channel counts are within limits */ + if (channels.rx_count > channels.max_rx) + err_attr = tb[ETHTOOL_A_CHANNELS_RX_COUNT]; + else if (channels.tx_count > channels.max_tx) + err_attr = tb[ETHTOOL_A_CHANNELS_TX_COUNT]; + else if (channels.other_count > channels.max_other) + err_attr = tb[ETHTOOL_A_CHANNELS_OTHER_COUNT]; + else if (channels.combined_count > channels.max_combined) + err_attr = tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT]; + else + err_attr = NULL; + if (err_attr) { + ret = -EINVAL; + NL_SET_ERR_MSG_ATTR(info->extack, err_attr, + "requested channel count exceeeds maximum"); + goto out_ops; + } + + /* ensure the new Rx count fits within the configured Rx flow + * indirection table settings + */ + if (netif_is_rxfh_configured(dev) && + !ethtool_get_max_rxfh_channel(dev, &max_rx_in_use) && + (channels.combined_count + channels.rx_count) <= max_rx_in_use) { + GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing indirection table settings"); + return -EINVAL; + } + + /* Disabling channels, query zero-copy AF_XDP sockets */ + from_channel = channels.combined_count + + min(channels.rx_count, channels.tx_count); + for (i = from_channel; i < old_total; i++) + if (xdp_get_umem_from_qid(dev, i)) { + GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets"); + return -EINVAL; + } + + ret = dev->ethtool_ops->set_channels(dev, &channels); + if (ret < 0) + goto out_ops; + ethtool_notify(dev, ETHTOOL_MSG_CHANNELS_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); +out_dev: + dev_put(dev); + return ret; +} diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 636ec6d5110e..0b22741b2f8f 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -168,6 +168,7 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(400000, LR8_ER8_FR8, Full), __DEFINE_LINK_MODE_NAME(400000, DR8, Full), __DEFINE_LINK_MODE_NAME(400000, CR8, Full), + __DEFINE_SPECIAL_MODE_NAME(FEC_LLRS, "LLRS"), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -257,3 +258,34 @@ int __ethtool_get_link(struct net_device *dev) return netif_running(dev) && dev->ethtool_ops->get_link(dev); } + +int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max) +{ + u32 dev_size, current_max = 0; + u32 *indir; + int ret; + + if (!dev->ethtool_ops->get_rxfh_indir_size || + !dev->ethtool_ops->get_rxfh) + return -EOPNOTSUPP; + dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); + if (dev_size == 0) + return -EOPNOTSUPP; + + indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); + if (!indir) + return -ENOMEM; + + ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL); + if (ret) + goto out; + + while (dev_size--) + current_max = max(current_max, indir[dev_size]); + + *max = current_max; + +out: + kfree(indir); + return ret; +} diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 40ba74e0b9bb..03946e16e623 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -6,6 +6,8 @@ #include <linux/netdevice.h> #include <linux/ethtool.h> +#define ETHTOOL_DEV_FEATURE_WORDS DIV_ROUND_UP(NETDEV_FEATURE_COUNT, 32) + /* compose link mode index from speed, type and duplex */ #define ETHTOOL_LINK_MODE(speed, type, duplex) \ ETHTOOL_LINK_MODE_ ## speed ## base ## type ## _ ## duplex ## _BIT @@ -27,5 +29,6 @@ int __ethtool_get_link(struct net_device *dev); bool convert_legacy_settings_to_link_ksettings( struct ethtool_link_ksettings *link_ksettings, const struct ethtool_cmd *legacy_settings); +int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max); #endif /* _ETHTOOL_COMMON_H */ diff --git a/net/ethtool/debug.c b/net/ethtool/debug.c index aaef4843e6ba..87f288ee20c8 100644 --- a/net/ethtool/debug.c +++ b/net/ethtool/debug.c @@ -102,8 +102,10 @@ int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info) info->extack); if (ret < 0) return ret; - ret = ethnl_parse_header(&req_info, tb[ETHTOOL_A_DEBUG_HEADER], - genl_info_net(info), info->extack, true); + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_DEBUG_HEADER], + genl_info_net(info), info->extack, + true); if (ret < 0) return ret; dev = req_info.dev; diff --git a/net/ethtool/features.c b/net/ethtool/features.c new file mode 100644 index 000000000000..4e632dc987d8 --- /dev/null +++ b/net/ethtool/features.c @@ -0,0 +1,304 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +struct features_req_info { + struct ethnl_req_info base; +}; + +struct features_reply_data { + struct ethnl_reply_data base; + u32 hw[ETHTOOL_DEV_FEATURE_WORDS]; + u32 wanted[ETHTOOL_DEV_FEATURE_WORDS]; + u32 active[ETHTOOL_DEV_FEATURE_WORDS]; + u32 nochange[ETHTOOL_DEV_FEATURE_WORDS]; + u32 all[ETHTOOL_DEV_FEATURE_WORDS]; +}; + +#define FEATURES_REPDATA(__reply_base) \ + container_of(__reply_base, struct features_reply_data, base) + +static const struct nla_policy +features_get_policy[ETHTOOL_A_FEATURES_MAX + 1] = { + [ETHTOOL_A_FEATURES_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_FEATURES_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_FEATURES_HW] = { .type = NLA_REJECT }, + [ETHTOOL_A_FEATURES_WANTED] = { .type = NLA_REJECT }, + [ETHTOOL_A_FEATURES_ACTIVE] = { .type = NLA_REJECT }, + [ETHTOOL_A_FEATURES_NOCHANGE] = { .type = NLA_REJECT }, +}; + +static void ethnl_features_to_bitmap32(u32 *dest, netdev_features_t src) +{ + unsigned int i; + + for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; i++) + dest[i] = src >> (32 * i); +} + +static int features_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct features_reply_data *data = FEATURES_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + netdev_features_t all_features; + + ethnl_features_to_bitmap32(data->hw, dev->hw_features); + ethnl_features_to_bitmap32(data->wanted, dev->wanted_features); + ethnl_features_to_bitmap32(data->active, dev->features); + ethnl_features_to_bitmap32(data->nochange, NETIF_F_NEVER_CHANGE); + all_features = GENMASK_ULL(NETDEV_FEATURE_COUNT - 1, 0); + ethnl_features_to_bitmap32(data->all, all_features); + + return 0; +} + +static int features_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct features_reply_data *data = FEATURES_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + unsigned int len = 0; + int ret; + + ret = ethnl_bitset32_size(data->hw, data->all, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + return ret; + len += ret; + ret = ethnl_bitset32_size(data->wanted, NULL, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + return ret; + len += ret; + ret = ethnl_bitset32_size(data->active, NULL, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + return ret; + len += ret; + ret = ethnl_bitset32_size(data->nochange, NULL, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + return ret; + len += ret; + + return len; +} + +static int features_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct features_reply_data *data = FEATURES_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + int ret; + + ret = ethnl_put_bitset32(skb, ETHTOOL_A_FEATURES_HW, data->hw, + data->all, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + return ret; + ret = ethnl_put_bitset32(skb, ETHTOOL_A_FEATURES_WANTED, data->wanted, + NULL, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + return ret; + ret = ethnl_put_bitset32(skb, ETHTOOL_A_FEATURES_ACTIVE, data->active, + NULL, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + return ret; + return ethnl_put_bitset32(skb, ETHTOOL_A_FEATURES_NOCHANGE, + data->nochange, NULL, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); +} + +const struct ethnl_request_ops ethnl_features_request_ops = { + .request_cmd = ETHTOOL_MSG_FEATURES_GET, + .reply_cmd = ETHTOOL_MSG_FEATURES_GET_REPLY, + .hdr_attr = ETHTOOL_A_FEATURES_HEADER, + .max_attr = ETHTOOL_A_FEATURES_MAX, + .req_info_size = sizeof(struct features_req_info), + .reply_data_size = sizeof(struct features_reply_data), + .request_policy = features_get_policy, + + .prepare_data = features_prepare_data, + .reply_size = features_reply_size, + .fill_reply = features_fill_reply, +}; + +/* FEATURES_SET */ + +static const struct nla_policy +features_set_policy[ETHTOOL_A_FEATURES_MAX + 1] = { + [ETHTOOL_A_FEATURES_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_FEATURES_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_FEATURES_HW] = { .type = NLA_REJECT }, + [ETHTOOL_A_FEATURES_WANTED] = { .type = NLA_NESTED }, + [ETHTOOL_A_FEATURES_ACTIVE] = { .type = NLA_REJECT }, + [ETHTOOL_A_FEATURES_NOCHANGE] = { .type = NLA_REJECT }, +}; + +static void ethnl_features_to_bitmap(unsigned long *dest, netdev_features_t val) +{ + const unsigned int words = BITS_TO_LONGS(NETDEV_FEATURE_COUNT); + unsigned int i; + + bitmap_zero(dest, NETDEV_FEATURE_COUNT); + for (i = 0; i < words; i++) + dest[i] = (unsigned long)(val >> (i * BITS_PER_LONG)); +} + +static netdev_features_t ethnl_bitmap_to_features(unsigned long *src) +{ + const unsigned int nft_bits = sizeof(netdev_features_t) * BITS_PER_BYTE; + const unsigned int words = BITS_TO_LONGS(NETDEV_FEATURE_COUNT); + netdev_features_t ret = 0; + unsigned int i; + + for (i = 0; i < words; i++) + ret |= (netdev_features_t)(src[i]) << (i * BITS_PER_LONG); + ret &= ~(netdev_features_t)0 >> (nft_bits - NETDEV_FEATURE_COUNT); + return ret; +} + +static int features_send_reply(struct net_device *dev, struct genl_info *info, + const unsigned long *wanted, + const unsigned long *wanted_mask, + const unsigned long *active, + const unsigned long *active_mask, bool compact) +{ + struct sk_buff *rskb; + void *reply_payload; + int reply_len = 0; + int ret; + + reply_len = ethnl_reply_header_size(); + ret = ethnl_bitset_size(wanted, wanted_mask, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + goto err; + reply_len += ret; + ret = ethnl_bitset_size(active, active_mask, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + goto err; + reply_len += ret; + + ret = -ENOMEM; + rskb = ethnl_reply_init(reply_len, dev, ETHTOOL_MSG_FEATURES_SET_REPLY, + ETHTOOL_A_FEATURES_HEADER, info, + &reply_payload); + if (!rskb) + goto err; + + ret = ethnl_put_bitset(rskb, ETHTOOL_A_FEATURES_WANTED, wanted, + wanted_mask, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + goto nla_put_failure; + ret = ethnl_put_bitset(rskb, ETHTOOL_A_FEATURES_ACTIVE, active, + active_mask, NETDEV_FEATURE_COUNT, + netdev_features_strings, compact); + if (ret < 0) + goto nla_put_failure; + + genlmsg_end(rskb, reply_payload); + ret = genlmsg_reply(rskb, info); + return ret; + +nla_put_failure: + nlmsg_free(rskb); + WARN_ONCE(1, "calculated message payload length (%d) not sufficient\n", + reply_len); +err: + GENL_SET_ERR_MSG(info, "failed to send reply message"); + return ret; +} + +int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) +{ + DECLARE_BITMAP(wanted_diff_mask, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(active_diff_mask, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(old_active, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(new_active, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(req_wanted, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(req_mask, NETDEV_FEATURE_COUNT); + struct nlattr *tb[ETHTOOL_A_FEATURES_MAX + 1]; + struct ethnl_req_info req_info = {}; + struct net_device *dev; + bool mod; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, + ETHTOOL_A_FEATURES_MAX, features_set_policy, + info->extack); + if (ret < 0) + return ret; + if (!tb[ETHTOOL_A_FEATURES_WANTED]) + return -EINVAL; + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_FEATURES_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + + rtnl_lock(); + ethnl_features_to_bitmap(old_active, dev->features); + ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT, + tb[ETHTOOL_A_FEATURES_WANTED], + netdev_features_strings, info->extack); + if (ret < 0) + goto out_rtnl; + if (ethnl_bitmap_to_features(req_mask) & ~NETIF_F_ETHTOOL_BITS) { + GENL_SET_ERR_MSG(info, "attempt to change non-ethtool features"); + ret = -EINVAL; + goto out_rtnl; + } + + /* set req_wanted bits not in req_mask from old_active */ + bitmap_and(req_wanted, req_wanted, req_mask, NETDEV_FEATURE_COUNT); + bitmap_andnot(new_active, old_active, req_mask, NETDEV_FEATURE_COUNT); + bitmap_or(req_wanted, new_active, req_wanted, NETDEV_FEATURE_COUNT); + if (bitmap_equal(req_wanted, old_active, NETDEV_FEATURE_COUNT)) { + ret = 0; + goto out_rtnl; + } + + dev->wanted_features = ethnl_bitmap_to_features(req_wanted); + __netdev_update_features(dev); + ethnl_features_to_bitmap(new_active, dev->features); + mod = !bitmap_equal(old_active, new_active, NETDEV_FEATURE_COUNT); + + ret = 0; + if (!(req_info.flags & ETHTOOL_FLAG_OMIT_REPLY)) { + bool compact = req_info.flags & ETHTOOL_FLAG_COMPACT_BITSETS; + + bitmap_xor(wanted_diff_mask, req_wanted, new_active, + NETDEV_FEATURE_COUNT); + bitmap_xor(active_diff_mask, old_active, new_active, + NETDEV_FEATURE_COUNT); + bitmap_and(wanted_diff_mask, wanted_diff_mask, req_mask, + NETDEV_FEATURE_COUNT); + bitmap_and(req_wanted, req_wanted, wanted_diff_mask, + NETDEV_FEATURE_COUNT); + bitmap_and(new_active, new_active, active_diff_mask, + NETDEV_FEATURE_COUNT); + + ret = features_send_reply(dev, info, req_wanted, + wanted_diff_mask, new_active, + active_diff_mask, compact); + } + if (mod) + ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL); + +out_rtnl: + rtnl_unlock(); + dev_put(dev); + return ret; +} diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index b987052d91ef..258840b19fb5 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -56,8 +56,6 @@ EXPORT_SYMBOL(ethtool_op_get_ts_info); /* Handlers for each ethtool command */ -#define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32) - static int ethtool_get_features(struct net_device *dev, void __user *useraddr) { struct ethtool_gfeatures cmd = { @@ -198,13 +196,14 @@ static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd) switch (eth_cmd) { case ETHTOOL_GTXCSUM: case ETHTOOL_STXCSUM: - return NETIF_F_CSUM_MASK | NETIF_F_SCTP_CRC; + return NETIF_F_CSUM_MASK | NETIF_F_FCOE_CRC_BIT | + NETIF_F_SCTP_CRC; case ETHTOOL_GRXCSUM: case ETHTOOL_SRXCSUM: return NETIF_F_RXCSUM; case ETHTOOL_GSG: case ETHTOOL_SSG: - return NETIF_F_SG; + return NETIF_F_SG | NETIF_F_FRAGLIST; case ETHTOOL_GTSO: case ETHTOOL_STSO: return NETIF_F_ALL_TSO; @@ -459,6 +458,24 @@ static int load_link_ksettings_from_user(struct ethtool_link_ksettings *to, return 0; } +/* Check if the user is trying to change anything besides speed/duplex */ +bool ethtool_virtdev_validate_cmd(const struct ethtool_link_ksettings *cmd) +{ + struct ethtool_link_settings base2 = {}; + + base2.speed = cmd->base.speed; + base2.port = PORT_OTHER; + base2.duplex = cmd->base.duplex; + base2.cmd = cmd->base.cmd; + base2.link_mode_masks_nwords = cmd->base.link_mode_masks_nwords; + + return !memcmp(&base2, &cmd->base, sizeof(base2)) && + bitmap_empty(cmd->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS) && + bitmap_empty(cmd->link_modes.lp_advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); +} + /* convert a kernel internal ethtool_link_ksettings to * ethtool_link_usettings in user space. return 0 on success, errno on * error. @@ -581,6 +598,27 @@ static int ethtool_set_link_ksettings(struct net_device *dev, return err; } +int ethtool_virtdev_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd, + u32 *dev_speed, u8 *dev_duplex) +{ + u32 speed; + u8 duplex; + + speed = cmd->base.speed; + duplex = cmd->base.duplex; + /* don't allow custom speed and duplex */ + if (!ethtool_validate_speed(speed) || + !ethtool_validate_duplex(duplex) || + !ethtool_virtdev_validate_cmd(cmd)) + return -EINVAL; + *dev_speed = speed; + *dev_duplex = duplex; + + return 0; +} +EXPORT_SYMBOL(ethtool_virtdev_set_link_ksettings); + /* Query device for its ethtool_cmd settings. * * Backward compatibility note: for compatibility with legacy ethtool, this is @@ -891,37 +929,6 @@ void netdev_rss_key_fill(void *buffer, size_t len) } EXPORT_SYMBOL(netdev_rss_key_fill); -static int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max) -{ - u32 dev_size, current_max = 0; - u32 *indir; - int ret; - - if (!dev->ethtool_ops->get_rxfh_indir_size || - !dev->ethtool_ops->get_rxfh) - return -EOPNOTSUPP; - dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); - if (dev_size == 0) - return -EOPNOTSUPP; - - indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); - if (!indir) - return -ENOMEM; - - ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL); - if (ret) - goto out; - - while (dev_size--) - current_max = max(current_max, indir[dev_size]); - - *max = current_max; - -out: - kfree(indir); - return ret; -} - static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, void __user *useraddr) { @@ -1505,6 +1512,64 @@ static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, return 0; } +static bool +ethtool_set_coalesce_supported(struct net_device *dev, + struct ethtool_coalesce *coalesce) +{ + u32 supported_params = dev->ethtool_ops->supported_coalesce_params; + u32 nonzero_params = 0; + + if (!supported_params) + return true; + + if (coalesce->rx_coalesce_usecs) + nonzero_params |= ETHTOOL_COALESCE_RX_USECS; + if (coalesce->rx_max_coalesced_frames) + nonzero_params |= ETHTOOL_COALESCE_RX_MAX_FRAMES; + if (coalesce->rx_coalesce_usecs_irq) + nonzero_params |= ETHTOOL_COALESCE_RX_USECS_IRQ; + if (coalesce->rx_max_coalesced_frames_irq) + nonzero_params |= ETHTOOL_COALESCE_RX_MAX_FRAMES_IRQ; + if (coalesce->tx_coalesce_usecs) + nonzero_params |= ETHTOOL_COALESCE_TX_USECS; + if (coalesce->tx_max_coalesced_frames) + nonzero_params |= ETHTOOL_COALESCE_TX_MAX_FRAMES; + if (coalesce->tx_coalesce_usecs_irq) + nonzero_params |= ETHTOOL_COALESCE_TX_USECS_IRQ; + if (coalesce->tx_max_coalesced_frames_irq) + nonzero_params |= ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ; + if (coalesce->stats_block_coalesce_usecs) + nonzero_params |= ETHTOOL_COALESCE_STATS_BLOCK_USECS; + if (coalesce->use_adaptive_rx_coalesce) + nonzero_params |= ETHTOOL_COALESCE_USE_ADAPTIVE_RX; + if (coalesce->use_adaptive_tx_coalesce) + nonzero_params |= ETHTOOL_COALESCE_USE_ADAPTIVE_TX; + if (coalesce->pkt_rate_low) + nonzero_params |= ETHTOOL_COALESCE_PKT_RATE_LOW; + if (coalesce->rx_coalesce_usecs_low) + nonzero_params |= ETHTOOL_COALESCE_RX_USECS_LOW; + if (coalesce->rx_max_coalesced_frames_low) + nonzero_params |= ETHTOOL_COALESCE_RX_MAX_FRAMES_LOW; + if (coalesce->tx_coalesce_usecs_low) + nonzero_params |= ETHTOOL_COALESCE_TX_USECS_LOW; + if (coalesce->tx_max_coalesced_frames_low) + nonzero_params |= ETHTOOL_COALESCE_TX_MAX_FRAMES_LOW; + if (coalesce->pkt_rate_high) + nonzero_params |= ETHTOOL_COALESCE_PKT_RATE_HIGH; + if (coalesce->rx_coalesce_usecs_high) + nonzero_params |= ETHTOOL_COALESCE_RX_USECS_HIGH; + if (coalesce->rx_max_coalesced_frames_high) + nonzero_params |= ETHTOOL_COALESCE_RX_MAX_FRAMES_HIGH; + if (coalesce->tx_coalesce_usecs_high) + nonzero_params |= ETHTOOL_COALESCE_TX_USECS_HIGH; + if (coalesce->tx_max_coalesced_frames_high) + nonzero_params |= ETHTOOL_COALESCE_TX_MAX_FRAMES_HIGH; + if (coalesce->rate_sample_interval) + nonzero_params |= ETHTOOL_COALESCE_RATE_SAMPLE_INTERVAL; + + return (supported_params & nonzero_params) == nonzero_params; +} + static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) { @@ -1516,6 +1581,9 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, if (copy_from_user(&coalesce, useraddr, sizeof(coalesce))) return -EFAULT; + if (!ethtool_set_coalesce_supported(dev, &coalesce)) + return -EOPNOTSUPP; + return dev->ethtool_ops->set_coalesce(dev, &coalesce); } @@ -1536,6 +1604,7 @@ static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr) static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) { struct ethtool_ringparam ringparam, max = { .cmd = ETHTOOL_GRINGPARAM }; + int ret; if (!dev->ethtool_ops->set_ringparam || !dev->ethtool_ops->get_ringparam) return -EOPNOTSUPP; @@ -1552,7 +1621,10 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) ringparam.tx_pending > max.tx_max_pending) return -EINVAL; - return dev->ethtool_ops->set_ringparam(dev, &ringparam); + ret = dev->ethtool_ops->set_ringparam(dev, &ringparam); + if (!ret) + ethtool_notify(dev, ETHTOOL_MSG_RINGS_NTF, NULL); + return ret; } static noinline_for_stack int ethtool_get_channels(struct net_device *dev, @@ -1577,6 +1649,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, u16 from_channel, to_channel; u32 max_rx_in_use = 0; unsigned int i; + int ret; if (!dev->ethtool_ops->set_channels || !dev->ethtool_ops->get_channels) return -EOPNOTSUPP; @@ -1608,7 +1681,10 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, if (xdp_get_umem_from_qid(dev, i)) return -EINVAL; - return dev->ethtool_ops->set_channels(dev, &channels); + ret = dev->ethtool_ops->set_channels(dev, &channels); + if (!ret) + ethtool_notify(dev, ETHTOOL_MSG_CHANNELS_NTF, NULL); + return ret; } static int ethtool_get_pauseparam(struct net_device *dev, void __user *useraddr) @@ -2297,6 +2373,11 @@ ethtool_set_per_queue_coalesce(struct net_device *dev, goto roll_back; } + if (!ethtool_set_coalesce_supported(dev, &coalesce)) { + ret = -EOPNOTSUPP; + goto roll_back; + } + ret = dev->ethtool_ops->set_per_queue_coalesce(dev, bit, &coalesce); if (ret != 0) goto roll_back; @@ -2612,6 +2693,8 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GPFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, dev->ethtool_ops->get_priv_flags); + if (!rc) + ethtool_notify(dev, ETHTOOL_MSG_PRIVFLAGS_NTF, NULL); break; case ETHTOOL_SPFLAGS: rc = ethtool_set_value(dev, useraddr, diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c index 5d16cb4e8693..2df420068cbb 100644 --- a/net/ethtool/linkinfo.c +++ b/net/ethtool/linkinfo.c @@ -121,8 +121,10 @@ int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info) info->extack); if (ret < 0) return ret; - ret = ethnl_parse_header(&req_info, tb[ETHTOOL_A_LINKINFO_HEADER], - genl_info_net(info), info->extack, true); + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_LINKINFO_HEADER], + genl_info_net(info), info->extack, + true); if (ret < 0) return ret; dev = req_info.dev; diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index 96f20be64553..cb29cc8c5960 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -237,6 +237,7 @@ static const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(400000, LR8_ER8_FR8, Full), __DEFINE_LINK_MODE_PARAMS(400000, DR8, Full), __DEFINE_LINK_MODE_PARAMS(400000, CR8, Full), + __DEFINE_SPECIAL_MODE_PARAMS(FEC_LLRS), }; static const struct nla_policy @@ -333,8 +334,10 @@ int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info) info->extack); if (ret < 0) return ret; - ret = ethnl_parse_header(&req_info, tb[ETHTOOL_A_LINKMODES_HEADER], - genl_info_net(info), info->extack, true); + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_LINKMODES_HEADER], + genl_info_net(info), info->extack, + true); if (ret < 0) return ret; dev = req_info.dev; diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 180c194fab07..55c8ce4019d9 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -18,7 +18,7 @@ static const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_MAX + 1] = { }; /** - * ethnl_parse_header() - parse request header + * ethnl_parse_header_dev_get() - parse request header * @req_info: structure to put results into * @header: nest attribute with request header * @net: request netns @@ -33,9 +33,9 @@ static const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_MAX + 1] = { * * Return: 0 on success or negative error code */ -int ethnl_parse_header(struct ethnl_req_info *req_info, - const struct nlattr *header, struct net *net, - struct netlink_ext_ack *extack, bool require_dev) +int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, + const struct nlattr *header, struct net *net, + struct netlink_ext_ack *extack, bool require_dev) { struct nlattr *tb[ETHTOOL_A_HEADER_MAX + 1]; const struct nlattr *devname_attr; @@ -215,6 +215,10 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_LINKSTATE_GET] = ðnl_linkstate_request_ops, [ETHTOOL_MSG_DEBUG_GET] = ðnl_debug_request_ops, [ETHTOOL_MSG_WOL_GET] = ðnl_wol_request_ops, + [ETHTOOL_MSG_FEATURES_GET] = ðnl_features_request_ops, + [ETHTOOL_MSG_PRIVFLAGS_GET] = ðnl_privflags_request_ops, + [ETHTOOL_MSG_RINGS_GET] = ðnl_rings_request_ops, + [ETHTOOL_MSG_CHANNELS_GET] = ðnl_channels_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -253,8 +257,8 @@ static int ethnl_default_parse(struct ethnl_req_info *req_info, request_ops->request_policy, extack); if (ret < 0) goto out; - ret = ethnl_parse_header(req_info, tb[request_ops->hdr_attr], net, - extack, require_dev); + ret = ethnl_parse_header_dev_get(req_info, tb[request_ops->hdr_attr], + net, extack, require_dev); if (ret < 0) goto out; @@ -527,6 +531,10 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_LINKMODES_NTF] = ðnl_linkmodes_request_ops, [ETHTOOL_MSG_DEBUG_NTF] = ðnl_debug_request_ops, [ETHTOOL_MSG_WOL_NTF] = ðnl_wol_request_ops, + [ETHTOOL_MSG_FEATURES_NTF] = ðnl_features_request_ops, + [ETHTOOL_MSG_PRIVFLAGS_NTF] = ðnl_privflags_request_ops, + [ETHTOOL_MSG_RINGS_NTF] = ðnl_rings_request_ops, + [ETHTOOL_MSG_CHANNELS_NTF] = ðnl_channels_request_ops, }; /* default notification handler */ @@ -612,6 +620,10 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_LINKMODES_NTF] = ethnl_default_notify, [ETHTOOL_MSG_DEBUG_NTF] = ethnl_default_notify, [ETHTOOL_MSG_WOL_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_FEATURES_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_PRIVFLAGS_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_RINGS_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_CHANNELS_NTF] = ethnl_default_notify, }; void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) @@ -629,6 +641,29 @@ void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) } EXPORT_SYMBOL(ethtool_notify); +static void ethnl_notify_features(struct netdev_notifier_info *info) +{ + struct net_device *dev = netdev_notifier_info_to_dev(info); + + ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL); +} + +static int ethnl_netdev_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + switch (event) { + case NETDEV_FEAT_CHANGE: + ethnl_notify_features(ptr); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block ethnl_netdev_notifier = { + .notifier_call = ethnl_netdev_event, +}; + /* genetlink setup */ static const struct genl_ops ethtool_genl_ops[] = { @@ -695,6 +730,54 @@ static const struct genl_ops ethtool_genl_ops[] = { .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_wol, }, + { + .cmd = ETHTOOL_MSG_FEATURES_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_FEATURES_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_features, + }, + { + .cmd = ETHTOOL_MSG_PRIVFLAGS_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_PRIVFLAGS_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_privflags, + }, + { + .cmd = ETHTOOL_MSG_RINGS_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_RINGS_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_rings, + }, + { + .cmd = ETHTOOL_MSG_CHANNELS_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + }, + { + .cmd = ETHTOOL_MSG_CHANNELS_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_channels, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { @@ -723,7 +806,9 @@ static int __init ethnl_init(void) return ret; ethnl_ok = true; - return 0; + ret = register_netdevice_notifier(ðnl_netdev_notifier); + WARN(ret < 0, "ethtool: net device notifier registration failed"); + return ret; } subsys_initcall(ethnl_init); diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 60efd87686ad..45aad99a6021 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -10,9 +10,10 @@ struct ethnl_req_info; -int ethnl_parse_header(struct ethnl_req_info *req_info, - const struct nlattr *nest, struct net *net, - struct netlink_ext_ack *extack, bool require_dev); +int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, + const struct nlattr *nest, struct net *net, + struct netlink_ext_ack *extack, + bool require_dev); int ethnl_fill_reply_header(struct sk_buff *skb, struct net_device *dev, u16 attrtype); struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd, @@ -336,10 +337,18 @@ extern const struct ethnl_request_ops ethnl_linkmodes_request_ops; extern const struct ethnl_request_ops ethnl_linkstate_request_ops; extern const struct ethnl_request_ops ethnl_debug_request_ops; extern const struct ethnl_request_ops ethnl_wol_request_ops; +extern const struct ethnl_request_ops ethnl_features_request_ops; +extern const struct ethnl_request_ops ethnl_privflags_request_ops; +extern const struct ethnl_request_ops ethnl_rings_request_ops; +extern const struct ethnl_request_ops ethnl_channels_request_ops; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info); int ethnl_set_wol(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_privflags(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info); #endif /* _NET_ETHTOOL_NETLINK_H */ diff --git a/net/ethtool/privflags.c b/net/ethtool/privflags.c new file mode 100644 index 000000000000..e8f03b33db9b --- /dev/null +++ b/net/ethtool/privflags.c @@ -0,0 +1,209 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +struct privflags_req_info { + struct ethnl_req_info base; +}; + +struct privflags_reply_data { + struct ethnl_reply_data base; + const char (*priv_flag_names)[ETH_GSTRING_LEN]; + unsigned int n_priv_flags; + u32 priv_flags; +}; + +#define PRIVFLAGS_REPDATA(__reply_base) \ + container_of(__reply_base, struct privflags_reply_data, base) + +static const struct nla_policy +privflags_get_policy[ETHTOOL_A_PRIVFLAGS_MAX + 1] = { + [ETHTOOL_A_PRIVFLAGS_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_PRIVFLAGS_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_PRIVFLAGS_FLAGS] = { .type = NLA_REJECT }, +}; + +static int ethnl_get_priv_flags_info(struct net_device *dev, + unsigned int *count, + const char (**names)[ETH_GSTRING_LEN]) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + int nflags; + + nflags = ops->get_sset_count(dev, ETH_SS_PRIV_FLAGS); + if (nflags < 0) + return nflags; + + if (names) { + *names = kcalloc(nflags, ETH_GSTRING_LEN, GFP_KERNEL); + if (!*names) + return -ENOMEM; + ops->get_strings(dev, ETH_SS_PRIV_FLAGS, (u8 *)*names); + } + + /* We can pass more than 32 private flags to userspace via netlink but + * we cannot get more with ethtool_ops::get_priv_flags(). Note that we + * must not adjust nflags before allocating the space for flag names + * as the buffer must be large enough for all flags. + */ + if (WARN_ONCE(nflags > 32, + "device %s reports more than 32 private flags (%d)\n", + netdev_name(dev), nflags)) + nflags = 32; + *count = nflags; + + return 0; +} + +static int privflags_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + const char (*names)[ETH_GSTRING_LEN]; + const struct ethtool_ops *ops; + unsigned int nflags; + int ret; + + ops = dev->ethtool_ops; + if (!ops->get_priv_flags || !ops->get_sset_count || !ops->get_strings) + return -EOPNOTSUPP; + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + ret = ethnl_get_priv_flags_info(dev, &nflags, &names); + if (ret < 0) + goto out_ops; + data->priv_flags = ops->get_priv_flags(dev); + data->priv_flag_names = names; + data->n_priv_flags = nflags; + +out_ops: + ethnl_ops_complete(dev); + return ret; +} + +static int privflags_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const u32 all_flags = ~(u32)0 >> (32 - data->n_priv_flags); + + return ethnl_bitset32_size(&data->priv_flags, &all_flags, + data->n_priv_flags, + data->priv_flag_names, compact); +} + +static int privflags_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_base); + bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; + const u32 all_flags = ~(u32)0 >> (32 - data->n_priv_flags); + + return ethnl_put_bitset32(skb, ETHTOOL_A_PRIVFLAGS_FLAGS, + &data->priv_flags, &all_flags, + data->n_priv_flags, data->priv_flag_names, + compact); +} + +static void privflags_cleanup_data(struct ethnl_reply_data *reply_data) +{ + struct privflags_reply_data *data = PRIVFLAGS_REPDATA(reply_data); + + kfree(data->priv_flag_names); +} + +const struct ethnl_request_ops ethnl_privflags_request_ops = { + .request_cmd = ETHTOOL_MSG_PRIVFLAGS_GET, + .reply_cmd = ETHTOOL_MSG_PRIVFLAGS_GET_REPLY, + .hdr_attr = ETHTOOL_A_PRIVFLAGS_HEADER, + .max_attr = ETHTOOL_A_PRIVFLAGS_MAX, + .req_info_size = sizeof(struct privflags_req_info), + .reply_data_size = sizeof(struct privflags_reply_data), + .request_policy = privflags_get_policy, + + .prepare_data = privflags_prepare_data, + .reply_size = privflags_reply_size, + .fill_reply = privflags_fill_reply, + .cleanup_data = privflags_cleanup_data, +}; + +/* PRIVFLAGS_SET */ + +static const struct nla_policy +privflags_set_policy[ETHTOOL_A_PRIVFLAGS_MAX + 1] = { + [ETHTOOL_A_PRIVFLAGS_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_PRIVFLAGS_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_PRIVFLAGS_FLAGS] = { .type = NLA_NESTED }, +}; + +int ethnl_set_privflags(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ETHTOOL_A_PRIVFLAGS_MAX + 1]; + const char (*names)[ETH_GSTRING_LEN] = NULL; + struct ethnl_req_info req_info = {}; + const struct ethtool_ops *ops; + struct net_device *dev; + unsigned int nflags; + bool mod = false; + bool compact; + u32 flags; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, + ETHTOOL_A_PRIVFLAGS_MAX, privflags_set_policy, + info->extack); + if (ret < 0) + return ret; + if (!tb[ETHTOOL_A_PRIVFLAGS_FLAGS]) + return -EINVAL; + ret = ethnl_bitset_is_compact(tb[ETHTOOL_A_PRIVFLAGS_FLAGS], &compact); + if (ret < 0) + return ret; + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_PRIVFLAGS_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + ops = dev->ethtool_ops; + if (!ops->get_priv_flags || !ops->set_priv_flags || + !ops->get_sset_count || !ops->get_strings) + return -EOPNOTSUPP; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + ret = ethnl_get_priv_flags_info(dev, &nflags, compact ? NULL : &names); + if (ret < 0) + goto out_ops; + flags = ops->get_priv_flags(dev); + + ret = ethnl_update_bitset32(&flags, nflags, + tb[ETHTOOL_A_PRIVFLAGS_FLAGS], names, + info->extack, &mod); + if (ret < 0 || !mod) + goto out_free; + ret = ops->set_priv_flags(dev, flags); + if (ret < 0) + goto out_free; + ethtool_notify(dev, ETHTOOL_MSG_PRIVFLAGS_NTF, NULL); + +out_free: + kfree(names); +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); + dev_put(dev); + return ret; +} diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c new file mode 100644 index 000000000000..c2ebf72be217 --- /dev/null +++ b/net/ethtool/rings.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" + +struct rings_req_info { + struct ethnl_req_info base; +}; + +struct rings_reply_data { + struct ethnl_reply_data base; + struct ethtool_ringparam ringparam; +}; + +#define RINGS_REPDATA(__reply_base) \ + container_of(__reply_base, struct rings_reply_data, base) + +static const struct nla_policy +rings_get_policy[ETHTOOL_A_RINGS_MAX + 1] = { + [ETHTOOL_A_RINGS_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_RINGS_RX_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_RX_MINI_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_RX_JUMBO_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_TX_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_RX] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_RX_MINI] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_RX_JUMBO] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_TX] = { .type = NLA_REJECT }, +}; + +static int rings_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct rings_reply_data *data = RINGS_REPDATA(reply_base); + struct net_device *dev = reply_base->dev; + int ret; + + if (!dev->ethtool_ops->get_ringparam) + return -EOPNOTSUPP; + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + dev->ethtool_ops->get_ringparam(dev, &data->ringparam); + ethnl_ops_complete(dev); + + return 0; +} + +static int rings_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + return nla_total_size(sizeof(u32)) + /* _RINGS_RX_MAX */ + nla_total_size(sizeof(u32)) + /* _RINGS_RX_MINI_MAX */ + nla_total_size(sizeof(u32)) + /* _RINGS_RX_JUMBO_MAX */ + nla_total_size(sizeof(u32)) + /* _RINGS_TX_MAX */ + nla_total_size(sizeof(u32)) + /* _RINGS_RX */ + nla_total_size(sizeof(u32)) + /* _RINGS_RX_MINI */ + nla_total_size(sizeof(u32)) + /* _RINGS_RX_JUMBO */ + nla_total_size(sizeof(u32)); /* _RINGS_TX */ +} + +static int rings_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct rings_reply_data *data = RINGS_REPDATA(reply_base); + const struct ethtool_ringparam *ringparam = &data->ringparam; + + if ((ringparam->rx_max_pending && + (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_MAX, + ringparam->rx_max_pending) || + nla_put_u32(skb, ETHTOOL_A_RINGS_RX, + ringparam->rx_pending))) || + (ringparam->rx_mini_max_pending && + (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_MINI_MAX, + ringparam->rx_mini_max_pending) || + nla_put_u32(skb, ETHTOOL_A_RINGS_RX_MINI, + ringparam->rx_mini_pending))) || + (ringparam->rx_jumbo_max_pending && + (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_JUMBO_MAX, + ringparam->rx_jumbo_max_pending) || + nla_put_u32(skb, ETHTOOL_A_RINGS_RX_JUMBO, + ringparam->rx_jumbo_pending))) || + (ringparam->tx_max_pending && + (nla_put_u32(skb, ETHTOOL_A_RINGS_TX_MAX, + ringparam->tx_max_pending) || + nla_put_u32(skb, ETHTOOL_A_RINGS_TX, + ringparam->tx_pending)))) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_rings_request_ops = { + .request_cmd = ETHTOOL_MSG_RINGS_GET, + .reply_cmd = ETHTOOL_MSG_RINGS_GET_REPLY, + .hdr_attr = ETHTOOL_A_RINGS_HEADER, + .max_attr = ETHTOOL_A_RINGS_MAX, + .req_info_size = sizeof(struct rings_req_info), + .reply_data_size = sizeof(struct rings_reply_data), + .request_policy = rings_get_policy, + + .prepare_data = rings_prepare_data, + .reply_size = rings_reply_size, + .fill_reply = rings_fill_reply, +}; + +/* RINGS_SET */ + +static const struct nla_policy +rings_set_policy[ETHTOOL_A_RINGS_MAX + 1] = { + [ETHTOOL_A_RINGS_UNSPEC] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_HEADER] = { .type = NLA_NESTED }, + [ETHTOOL_A_RINGS_RX_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_RX_MINI_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_RX_JUMBO_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_TX_MAX] = { .type = NLA_REJECT }, + [ETHTOOL_A_RINGS_RX] = { .type = NLA_U32 }, + [ETHTOOL_A_RINGS_RX_MINI] = { .type = NLA_U32 }, + [ETHTOOL_A_RINGS_RX_JUMBO] = { .type = NLA_U32 }, + [ETHTOOL_A_RINGS_TX] = { .type = NLA_U32 }, +}; + +int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ETHTOOL_A_RINGS_MAX + 1]; + struct ethtool_ringparam ringparam = {}; + struct ethnl_req_info req_info = {}; + const struct nlattr *err_attr; + const struct ethtool_ops *ops; + struct net_device *dev; + bool mod = false; + int ret; + + ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, + ETHTOOL_A_RINGS_MAX, rings_set_policy, + info->extack); + if (ret < 0) + return ret; + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_RINGS_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + ops = dev->ethtool_ops; + ret = -EOPNOTSUPP; + if (!ops->get_ringparam || !ops->set_ringparam) + goto out_dev; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + ops->get_ringparam(dev, &ringparam); + + ethnl_update_u32(&ringparam.rx_pending, tb[ETHTOOL_A_RINGS_RX], &mod); + ethnl_update_u32(&ringparam.rx_mini_pending, + tb[ETHTOOL_A_RINGS_RX_MINI], &mod); + ethnl_update_u32(&ringparam.rx_jumbo_pending, + tb[ETHTOOL_A_RINGS_RX_JUMBO], &mod); + ethnl_update_u32(&ringparam.tx_pending, tb[ETHTOOL_A_RINGS_TX], &mod); + ret = 0; + if (!mod) + goto out_ops; + + /* ensure new ring parameters are within limits */ + if (ringparam.rx_pending > ringparam.rx_max_pending) + err_attr = tb[ETHTOOL_A_RINGS_RX]; + else if (ringparam.rx_mini_pending > ringparam.rx_mini_max_pending) + err_attr = tb[ETHTOOL_A_RINGS_RX_MINI]; + else if (ringparam.rx_jumbo_pending > ringparam.rx_jumbo_max_pending) + err_attr = tb[ETHTOOL_A_RINGS_RX_JUMBO]; + else if (ringparam.tx_pending > ringparam.tx_max_pending) + err_attr = tb[ETHTOOL_A_RINGS_TX]; + else + err_attr = NULL; + if (err_attr) { + ret = -EINVAL; + NL_SET_ERR_MSG_ATTR(info->extack, err_attr, + "requested ring size exceeeds maximum"); + goto out_ops; + } + + ret = dev->ethtool_ops->set_ringparam(dev, &ringparam); + if (ret < 0) + goto out_ops; + ethtool_notify(dev, ETHTOOL_MSG_RINGS_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); +out_dev: + dev_put(dev); + return ret; +} diff --git a/net/ethtool/wol.c b/net/ethtool/wol.c index e1b8a65b64c4..1d2bcabee554 100644 --- a/net/ethtool/wol.c +++ b/net/ethtool/wol.c @@ -123,8 +123,9 @@ int ethnl_set_wol(struct sk_buff *skb, struct genl_info *info) wol_set_policy, info->extack); if (ret < 0) return ret; - ret = ethnl_parse_header(&req_info, tb[ETHTOOL_A_WOL_HEADER], - genl_info_net(info), info->extack, true); + ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_WOL_HEADER], + genl_info_net(info), info->extack, + true); if (ret < 0) return ret; dev = req_info.dev; diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index d5f709b940ff..9787ef11ca71 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -113,7 +113,6 @@ void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) priv->node_tbl_root = NULL; return; } - priv->node_tbl_file = de; } /* hsr_debugfs_term - Tear down debugfs intrastructure @@ -125,9 +124,7 @@ void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) void hsr_debugfs_term(struct hsr_priv *priv) { - debugfs_remove(priv->node_tbl_file); - priv->node_tbl_file = NULL; - debugfs_remove(priv->node_tbl_root); + debugfs_remove_recursive(priv->node_tbl_root); priv->node_tbl_root = NULL; } diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index c7bd6c49fadf..fc7027314ad8 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -57,24 +57,19 @@ static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; - bool has_carrier; - has_carrier = false; + ASSERT_RTNL(); - rcu_read_lock(); - hsr_for_each_port(master->hsr, port) + hsr_for_each_port(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { - has_carrier = true; - break; + netif_carrier_on(master->dev); + return true; } - rcu_read_unlock(); + } - if (has_carrier) - netif_carrier_on(master->dev); - else - netif_carrier_off(master->dev); + netif_carrier_off(master->dev); - return has_carrier; + return false; } static void hsr_check_announce(struct net_device *hsr_dev, @@ -118,11 +113,9 @@ int hsr_get_max_mtu(struct hsr_priv *hsr) struct hsr_port *port; mtu_max = ETH_DATA_LEN; - rcu_read_lock(); hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); - rcu_read_unlock(); if (mtu_max < HSR_HLEN) return 0; @@ -157,7 +150,6 @@ static int hsr_dev_open(struct net_device *dev) hsr = netdev_priv(dev); designation = '\0'; - rcu_read_lock(); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; @@ -175,7 +167,6 @@ static int hsr_dev_open(struct net_device *dev) netdev_warn(dev, "Slave %c (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } - rcu_read_unlock(); if (designation == '\0') netdev_warn(dev, "No slave devices configured\n"); @@ -350,22 +341,33 @@ static void hsr_announce(struct timer_list *t) rcu_read_unlock(); } +static void hsr_del_ports(struct hsr_priv *hsr) +{ + struct hsr_port *port; + + port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); + if (port) + hsr_del_port(port); + + port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); + if (port) + hsr_del_port(port); + + port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + if (port) + hsr_del_port(port); +} + /* This has to be called after all the readers are gone. * Otherwise we would have to check the return value of * hsr_port_get_hsr(). */ static void hsr_dev_destroy(struct net_device *hsr_dev) { - struct hsr_priv *hsr; - struct hsr_port *port; - struct hsr_port *tmp; - - hsr = netdev_priv(hsr_dev); + struct hsr_priv *hsr = netdev_priv(hsr_dev); hsr_debugfs_term(hsr); - - list_for_each_entry_safe(port, tmp, &hsr->ports, port_list) - hsr_del_port(port); + hsr_del_ports(hsr); del_timer_sync(&hsr->prune_timer); del_timer_sync(&hsr->announce_timer); @@ -431,11 +433,10 @@ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], - unsigned char multicast_spec, u8 protocol_version) + unsigned char multicast_spec, u8 protocol_version, + struct netlink_ext_ack *extack) { struct hsr_priv *hsr; - struct hsr_port *port; - struct hsr_port *tmp; int res; hsr = netdev_priv(hsr_dev); @@ -478,7 +479,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); - res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER); + res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; @@ -486,11 +487,11 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], if (res) goto err_unregister; - res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A); + res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) goto err_add_slaves; - res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B); + res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) goto err_add_slaves; @@ -502,8 +503,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], err_add_slaves: unregister_netdevice(hsr_dev); err_unregister: - list_for_each_entry_safe(port, tmp, &hsr->ports, port_list) - hsr_del_port(port); + hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); diff --git a/net/hsr/hsr_device.h b/net/hsr/hsr_device.h index 6d7759c4f5f9..a099d7de7e79 100644 --- a/net/hsr/hsr_device.h +++ b/net/hsr/hsr_device.h @@ -13,7 +13,8 @@ void hsr_dev_setup(struct net_device *dev); int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], - unsigned char multicast_spec, u8 protocol_version); + unsigned char multicast_spec, u8 protocol_version, + struct netlink_ext_ack *extack); void hsr_check_carrier_and_operstate(struct hsr_priv *hsr); bool is_hsr_master(struct net_device *dev); int hsr_get_max_mtu(struct hsr_priv *hsr); diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 3ba7f61be107..d46d22c7105c 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -318,7 +318,8 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, node_dst = find_node_by_addr_A(&port->hsr->node_db, eth_hdr(skb)->h_dest); if (!node_dst) { - WARN_ONCE(1, "%s: Unknown node\n", __func__); + if (net_ratelimit()) + netdev_err(skb->dev, "%s: Unknown node\n", __func__); return; } if (port->type != node_dst->addr_B_port) diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 9e389accbfc7..26d6c39f24e1 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -85,7 +85,8 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, master->dev->mtu = mtu_max; break; case NETDEV_UNREGISTER: - hsr_del_port(port); + if (!is_hsr_master(dev)) + hsr_del_port(port); break; case NETDEV_PRE_TYPE_CHANGE: /* HSR works only on Ethernet devices. Refuse slave to change diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 754d84b217f0..7321cf8d6d2c 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -166,7 +166,6 @@ struct hsr_priv { unsigned char sup_multicast_addr[ETH_ALEN]; #ifdef CONFIG_DEBUG_FS struct dentry *node_tbl_root; - struct dentry *node_tbl_file; #endif }; diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 8dc0547f01d0..64d39c1e93a2 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -35,26 +35,34 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, unsigned char multicast_spec, hsr_version; if (!data) { - netdev_info(dev, "HSR: No slave devices specified\n"); + NL_SET_ERR_MSG_MOD(extack, "No slave devices specified"); return -EINVAL; } if (!data[IFLA_HSR_SLAVE1]) { - netdev_info(dev, "HSR: Slave1 device not specified\n"); + NL_SET_ERR_MSG_MOD(extack, "Slave1 device not specified"); return -EINVAL; } link[0] = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_SLAVE1])); + if (!link[0]) { + NL_SET_ERR_MSG_MOD(extack, "Slave1 does not exist"); + return -EINVAL; + } if (!data[IFLA_HSR_SLAVE2]) { - netdev_info(dev, "HSR: Slave2 device not specified\n"); + NL_SET_ERR_MSG_MOD(extack, "Slave2 device not specified"); return -EINVAL; } link[1] = __dev_get_by_index(src_net, nla_get_u32(data[IFLA_HSR_SLAVE2])); + if (!link[1]) { + NL_SET_ERR_MSG_MOD(extack, "Slave2 does not exist"); + return -EINVAL; + } - if (!link[0] || !link[1]) - return -ENODEV; - if (link[0] == link[1]) + if (link[0] == link[1]) { + NL_SET_ERR_MSG_MOD(extack, "Slave1 and Slave2 are same"); return -EINVAL; + } if (!data[IFLA_HSR_MULTICAST_SPEC]) multicast_spec = 0; @@ -66,34 +74,25 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, else hsr_version = nla_get_u8(data[IFLA_HSR_VERSION]); - return hsr_dev_finalize(dev, link, multicast_spec, hsr_version); + return hsr_dev_finalize(dev, link, multicast_spec, hsr_version, extack); } static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) { - struct hsr_priv *hsr; + struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *port; - int res; - - hsr = netdev_priv(dev); - - res = 0; - rcu_read_lock(); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); - if (port) - res = nla_put_u32(skb, IFLA_HSR_SLAVE1, port->dev->ifindex); - rcu_read_unlock(); - if (res) - goto nla_put_failure; + if (port) { + if (nla_put_u32(skb, IFLA_HSR_SLAVE1, port->dev->ifindex)) + goto nla_put_failure; + } - rcu_read_lock(); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); - if (port) - res = nla_put_u32(skb, IFLA_HSR_SLAVE2, port->dev->ifindex); - rcu_read_unlock(); - if (res) - goto nla_put_failure; + if (port) { + if (nla_put_u32(skb, IFLA_HSR_SLAVE2, port->dev->ifindex)) + goto nla_put_failure; + } if (nla_put(skb, IFLA_HSR_SUPERVISION_ADDR, ETH_ALEN, hsr->sup_multicast_addr) || diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index fbfd0db182b7..d3547e8c6d5b 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -25,7 +25,6 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) return RX_HANDLER_PASS; } - rcu_read_lock(); /* hsr->node_db, hsr->ports */ port = hsr_port_get_rcu(skb->dev); if (!port) goto finish_pass; @@ -45,11 +44,9 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) hsr_forward_skb(skb, port); finish_consume: - rcu_read_unlock(); /* hsr->node_db, hsr->ports */ return RX_HANDLER_CONSUMED; finish_pass: - rcu_read_unlock(); /* hsr->node_db, hsr->ports */ return RX_HANDLER_PASS; } @@ -58,33 +55,37 @@ bool hsr_port_exists(const struct net_device *dev) return rcu_access_pointer(dev->rx_handler) == hsr_handle_frame; } -static int hsr_check_dev_ok(struct net_device *dev) +static int hsr_check_dev_ok(struct net_device *dev, + struct netlink_ext_ack *extack) { /* Don't allow HSR on non-ethernet like devices */ if ((dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN) { - netdev_info(dev, "Cannot use loopback or non-ethernet device as HSR slave.\n"); + NL_SET_ERR_MSG_MOD(extack, "Cannot use loopback or non-ethernet device as HSR slave."); return -EINVAL; } /* Don't allow enslaving hsr devices */ if (is_hsr_master(dev)) { - netdev_info(dev, "Cannot create trees of HSR devices.\n"); + NL_SET_ERR_MSG_MOD(extack, + "Cannot create trees of HSR devices."); return -EINVAL; } if (hsr_port_exists(dev)) { - netdev_info(dev, "This device is already a HSR slave.\n"); + NL_SET_ERR_MSG_MOD(extack, + "This device is already a HSR slave."); return -EINVAL; } if (is_vlan_dev(dev)) { - netdev_info(dev, "HSR on top of VLAN is not yet supported in this driver.\n"); + NL_SET_ERR_MSG_MOD(extack, "HSR on top of VLAN is not yet supported in this driver."); return -EINVAL; } if (dev->priv_flags & IFF_DONT_BRIDGE) { - netdev_info(dev, "This device does not support bridging.\n"); + NL_SET_ERR_MSG_MOD(extack, + "This device does not support bridging."); return -EOPNOTSUPP; } @@ -96,19 +97,25 @@ static int hsr_check_dev_ok(struct net_device *dev) } /* Setup device to be added to the HSR bridge. */ -static int hsr_portdev_setup(struct net_device *dev, struct hsr_port *port) +static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev, + struct hsr_port *port, + struct netlink_ext_ack *extack) + { + struct net_device *hsr_dev; + struct hsr_port *master; int res; - dev_hold(dev); res = dev_set_promiscuity(dev, 1); if (res) - goto fail_promiscuity; + return res; - /* FIXME: - * What does net device "adjacency" mean? Should we do - * res = netdev_master_upper_dev_link(port->dev, port->hsr->dev); ? - */ + master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); + hsr_dev = master->dev; + + res = netdev_upper_dev_link(dev, hsr_dev, extack); + if (res) + goto fail_upper_dev_link; res = netdev_rx_handler_register(dev, hsr_handle_frame, port); if (res) @@ -118,21 +125,20 @@ static int hsr_portdev_setup(struct net_device *dev, struct hsr_port *port) return 0; fail_rx_handler: + netdev_upper_dev_unlink(dev, hsr_dev); +fail_upper_dev_link: dev_set_promiscuity(dev, -1); -fail_promiscuity: - dev_put(dev); - return res; } int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, - enum hsr_port_type type) + enum hsr_port_type type, struct netlink_ext_ack *extack) { struct hsr_port *port, *master; int res; if (type != HSR_PT_MASTER) { - res = hsr_check_dev_ok(dev); + res = hsr_check_dev_ok(dev, extack); if (res) return res; } @@ -146,7 +152,7 @@ int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, return -ENOMEM; if (type != HSR_PT_MASTER) { - res = hsr_portdev_setup(dev, port); + res = hsr_portdev_setup(hsr, dev, port, extack); if (res) goto fail_dev_setup; } @@ -179,21 +185,14 @@ void hsr_del_port(struct hsr_port *port) list_del_rcu(&port->port_list); if (port != master) { - if (master) { - netdev_update_features(master->dev); - dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); - } + netdev_update_features(master->dev); + dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); netdev_rx_handler_unregister(port->dev); dev_set_promiscuity(port->dev, -1); + netdev_upper_dev_unlink(port->dev, master->dev); } - /* FIXME? - * netdev_upper_dev_unlink(port->dev, port->hsr->dev); - */ - synchronize_rcu(); - if (port != master) - dev_put(port->dev); kfree(port); } diff --git a/net/hsr/hsr_slave.h b/net/hsr/hsr_slave.h index 64b549529592..8953ea279ce9 100644 --- a/net/hsr/hsr_slave.h +++ b/net/hsr/hsr_slave.h @@ -13,7 +13,7 @@ #include "hsr_main.h" int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, - enum hsr_port_type pt); + enum hsr_port_type pt, struct netlink_ext_ack *extack); void hsr_del_port(struct hsr_port *port); bool hsr_port_exists(const struct net_device *dev); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 2fe295432c24..bd7b4e92e07f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -872,7 +872,7 @@ int inet_shutdown(struct socket *sock, int how) err = -ENOTCONN; /* Hack to wake up other listeners, who can poll for EPOLLHUP, even on eg. unconnected UDP sockets -- RR */ - /* fall through */ + fallthrough; default: sk->sk_shutdown |= how; if (sk->sk_prot->shutdown) @@ -886,7 +886,7 @@ int inet_shutdown(struct socket *sock, int how) case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; - /* fall through */ + fallthrough; case TCP_SYN_SENT: err = sk->sk_prot->disconnect(sk, O_NONBLOCK); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 974179b3b314..d99e1be94019 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -107,7 +107,7 @@ static int ip_clear_mutable_options(const struct iphdr *iph, __be32 *daddr) if (optlen < 6) return -EINVAL; memcpy(daddr, optptr+optlen-4, 4); - /* Fall through */ + fallthrough; default: memset(optptr, 0, optlen); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 05eb42f347e8..687971d83b4e 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1181,7 +1181,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCSARP: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - /* fall through */ + fallthrough; case SIOCGARP: err = copy_from_user(&r, arg, sizeof(struct arpreq)); if (err) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e4632bd2026d..30fa42f5997d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1566,11 +1566,11 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, } } ip_mc_up(in_dev); - /* fall through */ + fallthrough; case NETDEV_CHANGEADDR: if (!IN_DEV_ARP_NOTIFY(in_dev)) break; - /* fall through */ + fallthrough; case NETDEV_NOTIFY_PEERS: /* Send gratuitous ARP to notify of link change */ inetdev_send_gratuitous_arp(dev, in_dev); @@ -1588,7 +1588,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ - /* fall through */ + fallthrough; case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a803cdd9400a..e4c62b8f57a8 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1962,7 +1962,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force) case NETDEV_DOWN: case NETDEV_UNREGISTER: nexthop_nh->fib_nh_flags |= RTNH_F_DEAD; - /* fall through */ + fallthrough; case NETDEV_CHANGE: nexthop_nh->fib_nh_flags |= RTNH_F_LINKDOWN; break; @@ -1984,7 +1984,7 @@ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force) case NETDEV_DOWN: case NETDEV_UNREGISTER: fi->fib_flags |= RTNH_F_DEAD; - /* fall through */ + fallthrough; case NETDEV_CHANGE: fi->fib_flags |= RTNH_F_LINKDOWN; break; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index ff0c24371e33..f4c2ac445b3f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -35,9 +35,6 @@ * Paul E. McKenney <paulmck@us.ibm.com> * Patrick McHardy <kaber@trash.net> */ - -#define VERSION "0.409" - #include <linux/cache.h> #include <linux/uaccess.h> #include <linux/bitops.h> @@ -304,8 +301,6 @@ static inline void alias_free_mem_rcu(struct fib_alias *fa) call_rcu(&fa->rcu, __alias_free_mem); } -#define TNODE_KMALLOC_MAX \ - ilog2((PAGE_SIZE - TNODE_SIZE(0)) / sizeof(struct key_vector *)) #define TNODE_VMALLOC_MAX \ ilog2((SIZE_MAX - TNODE_SIZE(0)) / sizeof(struct key_vector *)) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index f369e7ce685b..fc61f51d87a3 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -865,7 +865,7 @@ static bool icmp_unreach(struct sk_buff *skb) case 3: if (!icmp_tag_validation(iph->protocol)) goto out; - /* fall through */ + fallthrough; case 0: info = ntohs(icmph->un.frag.mtu); } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3b9c7a2725a9..47f0502b2101 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -107,8 +107,6 @@ #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ -#define IGMP_V2_UNSOLICITED_REPORT_INTERVAL (10*HZ) -#define IGMP_V3_UNSOLICITED_REPORT_INTERVAL (1*HZ) #define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d545fb99a8a1..5f34eb951627 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -131,7 +131,7 @@ static int inet_csk_bind_conflict(const struct sock *sk, { struct sock *sk2; bool reuse = sk->sk_reuse; - bool reuseport = !!sk->sk_reuseport && reuseport_ok; + bool reuseport = !!sk->sk_reuseport; kuid_t uid = sock_i_uid((struct sock *)sk); /* @@ -146,17 +146,21 @@ static int inet_csk_bind_conflict(const struct sock *sk, (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { - if ((!reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) && - (!reuseport || !sk2->sk_reuseport || - rcu_access_pointer(sk->sk_reuseport_cb) || - (sk2->sk_state != TCP_TIME_WAIT && - !uid_eq(uid, sock_i_uid(sk2))))) { - if (inet_rcv_saddr_equal(sk, sk2, true)) - break; - } - if (!relax && reuse && sk2->sk_reuse && + if (reuse && sk2->sk_reuse && sk2->sk_state != TCP_LISTEN) { + if ((!relax || + (!reuseport_ok && + reuseport && sk2->sk_reuseport && + !rcu_access_pointer(sk->sk_reuseport_cb) && + (sk2->sk_state == TCP_TIME_WAIT || + uid_eq(uid, sock_i_uid(sk2))))) && + inet_rcv_saddr_equal(sk, sk2, true)) + break; + } else if (!reuseport_ok || + !reuseport || !sk2->sk_reuseport || + rcu_access_pointer(sk->sk_reuseport_cb) || + (sk2->sk_state != TCP_TIME_WAIT && + !uid_eq(uid, sock_i_uid(sk2)))) { if (inet_rcv_saddr_equal(sk, sk2, true)) break; } @@ -176,12 +180,14 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int * int port = 0; struct inet_bind_hashbucket *head; struct net *net = sock_net(sk); + bool relax = false; int i, low, high, attempt_half; struct inet_bind_bucket *tb; u32 remaining, offset; int l3mdev; l3mdev = inet_sk_bound_l3mdev(sk); +ports_exhausted: attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0; other_half_scan: inet_get_local_port_range(net, &low, &high); @@ -219,7 +225,7 @@ other_parity_scan: inet_bind_bucket_for_each(tb, &head->chain) if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev && tb->port == port) { - if (!inet_csk_bind_conflict(sk, tb, false, false)) + if (!inet_csk_bind_conflict(sk, tb, relax, false)) goto success; goto next_port; } @@ -239,6 +245,12 @@ next_port: attempt_half = 2; goto other_half_scan; } + + if (net->ipv4.sysctl_ip_autobind_reuse && !relax) { + /* We still have a chance to connect to different destinations */ + relax = true; + goto ports_exhausted; + } return NULL; success: *port_ret = port; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8c8377568a78..5d50aad3cdbf 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -23,6 +23,7 @@ #include <net/inet_hashtables.h> #include <net/inet_timewait_sock.h> #include <net/inet6_hashtables.h> +#include <net/bpf_sk_storage.h> #include <net/netlink.h> #include <linux/inet.h> @@ -170,26 +171,28 @@ errout: } EXPORT_SYMBOL_GPL(inet_diag_msg_attrs_fill); +#define MAX_DUMP_ALLOC_SIZE (KMALLOC_MAX_SIZE - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) + int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, - struct sk_buff *skb, const struct inet_diag_req_v2 *req, - struct user_namespace *user_ns, - u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh, - bool net_admin) + struct sk_buff *skb, struct netlink_callback *cb, + const struct inet_diag_req_v2 *req, + u16 nlmsg_flags, bool net_admin) { const struct tcp_congestion_ops *ca_ops; const struct inet_diag_handler *handler; + struct inet_diag_dump_data *cb_data; int ext = req->idiag_ext; struct inet_diag_msg *r; struct nlmsghdr *nlh; struct nlattr *attr; void *info = NULL; + cb_data = cb->data; handler = inet_diag_table[req->sdiag_protocol]; BUG_ON(!handler); - nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), - nlmsg_flags); + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; @@ -201,7 +204,9 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_timer = 0; r->idiag_retrans = 0; - if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) + if (inet_diag_msg_attrs_fill(sk, skb, r, ext, + sk_user_ns(NETLINK_CB(cb->skb).sk), + net_admin)) goto errout; if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { @@ -298,6 +303,48 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } + /* Keep it at the end for potential retry with a larger skb, + * or else do best-effort fitting, which is only done for the + * first_nlmsg. + */ + if (cb_data->bpf_stg_diag) { + bool first_nlmsg = ((unsigned char *)nlh == skb->data); + unsigned int prev_min_dump_alloc; + unsigned int total_nla_size = 0; + unsigned int msg_len; + int err; + + msg_len = skb_tail_pointer(skb) - (unsigned char *)nlh; + err = bpf_sk_storage_diag_put(cb_data->bpf_stg_diag, sk, skb, + INET_DIAG_SK_BPF_STORAGES, + &total_nla_size); + + if (!err) + goto out; + + total_nla_size += msg_len; + prev_min_dump_alloc = cb->min_dump_alloc; + if (total_nla_size > prev_min_dump_alloc) + cb->min_dump_alloc = min_t(u32, total_nla_size, + MAX_DUMP_ALLOC_SIZE); + + if (!first_nlmsg) + goto errout; + + if (cb->min_dump_alloc > prev_min_dump_alloc) + /* Retry with pskb_expand_head() with + * __GFP_DIRECT_RECLAIM + */ + goto errout; + + WARN_ON_ONCE(total_nla_size <= prev_min_dump_alloc); + + /* Send what we have for this sk + * and move on to the next sk in the following + * dump() + */ + } + out: nlmsg_end(skb, nlh); return 0; @@ -308,30 +355,19 @@ errout: } EXPORT_SYMBOL_GPL(inet_sk_diag_fill); -static int inet_csk_diag_fill(struct sock *sk, - struct sk_buff *skb, - const struct inet_diag_req_v2 *req, - struct user_namespace *user_ns, - u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh, - bool net_admin) -{ - return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns, - portid, seq, nlmsg_flags, unlh, net_admin); -} - static int inet_twsk_diag_fill(struct sock *sk, struct sk_buff *skb, - u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh) + struct netlink_callback *cb, + u16 nlmsg_flags) { struct inet_timewait_sock *tw = inet_twsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; - nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), - nlmsg_flags); + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, + sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; @@ -355,16 +391,16 @@ static int inet_twsk_diag_fill(struct sock *sk, } static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, - u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh, bool net_admin) + struct netlink_callback *cb, + u16 nlmsg_flags, bool net_admin) { struct request_sock *reqsk = inet_reqsk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; long tmo; - nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), - nlmsg_flags); + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + cb->nlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; @@ -393,21 +429,18 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, + struct netlink_callback *cb, const struct inet_diag_req_v2 *r, - struct user_namespace *user_ns, - u32 portid, u32 seq, u16 nlmsg_flags, - const struct nlmsghdr *unlh, bool net_admin) + u16 nlmsg_flags, bool net_admin) { if (sk->sk_state == TCP_TIME_WAIT) - return inet_twsk_diag_fill(sk, skb, portid, seq, - nlmsg_flags, unlh); + return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags); if (sk->sk_state == TCP_NEW_SYN_RECV) - return inet_req_diag_fill(sk, skb, portid, seq, - nlmsg_flags, unlh, net_admin); + return inet_req_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); - return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, - nlmsg_flags, unlh, net_admin); + return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, r, nlmsg_flags, + net_admin); } struct sock *inet_diag_find_one_icsk(struct net *net, @@ -455,10 +488,10 @@ struct sock *inet_diag_find_one_icsk(struct net *net, EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk); int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, - struct sk_buff *in_skb, - const struct nlmsghdr *nlh, + struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { + struct sk_buff *in_skb = cb->skb; bool net_admin = netlink_net_capable(in_skb, CAP_NET_ADMIN); struct net *net = sock_net(in_skb->sk); struct sk_buff *rep; @@ -475,10 +508,7 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, goto out; } - err = sk_diag_fill(sk, rep, req, - sk_user_ns(NETLINK_CB(in_skb).sk), - NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh, net_admin); + err = sk_diag_fill(sk, rep, cb, req, 0, net_admin); if (err < 0) { WARN_ON(err == -EMSGSIZE); nlmsg_free(rep); @@ -505,14 +535,21 @@ static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, int err; handler = inet_diag_lock_handler(req->sdiag_protocol); - if (IS_ERR(handler)) + if (IS_ERR(handler)) { err = PTR_ERR(handler); - else if (cmd == SOCK_DIAG_BY_FAMILY) - err = handler->dump_one(in_skb, nlh, req); - else if (cmd == SOCK_DESTROY && handler->destroy) + } else if (cmd == SOCK_DIAG_BY_FAMILY) { + struct inet_diag_dump_data empty_dump_data = {}; + struct netlink_callback cb = { + .nlh = nlh, + .skb = in_skb, + .data = &empty_dump_data, + }; + err = handler->dump_one(&cb, req); + } else if (cmd == SOCK_DESTROY && handler->destroy) { err = handler->destroy(in_skb, req); - else + } else { err = -EOPNOTSUPP; + } inet_diag_unlock_handler(handler); return err; @@ -843,23 +880,6 @@ static int inet_diag_bc_audit(const struct nlattr *attr, return len == 0 ? 0 : -EINVAL; } -static int inet_csk_diag_dump(struct sock *sk, - struct sk_buff *skb, - struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, - const struct nlattr *bc, - bool net_admin) -{ - if (!inet_diag_bc_sk(bc, sk)) - return 0; - - return inet_csk_diag_fill(sk, skb, r, - sk_user_ns(NETLINK_CB(cb->skb).sk), - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, - net_admin); -} - static void twsk_build_assert(void) { BUILD_BUG_ON(offsetof(struct inet_timewait_sock, tw_family) != @@ -888,14 +908,17 @@ static void twsk_build_assert(void) void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r) { bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); + struct inet_diag_dump_data *cb_data = cb->data; struct net *net = sock_net(skb->sk); u32 idiag_states = r->idiag_states; int i, num, s_i, s_num; + struct nlattr *bc; struct sock *sk; + bc = cb_data->inet_diag_nla_bc; if (idiag_states & TCPF_SYN_RECV) idiag_states |= TCPF_NEW_SYN_RECV; s_i = cb->args[1]; @@ -931,8 +954,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, r->id.idiag_sport) goto next_listen; - if (inet_csk_diag_dump(sk, skb, cb, r, - bc, net_admin) < 0) { + if (!inet_diag_bc_sk(bc, sk)) + goto next_listen; + + if (inet_sk_diag_fill(sk, inet_csk(sk), skb, + cb, r, NLM_F_MULTI, + net_admin) < 0) { spin_unlock(&ilb->lock); goto done; } @@ -1010,11 +1037,8 @@ next_normal: res = 0; for (idx = 0; idx < accum; idx++) { if (res >= 0) { - res = sk_diag_fill(sk_arr[idx], skb, r, - sk_user_ns(NETLINK_CB(cb->skb).sk), - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->nlh, net_admin); + res = sk_diag_fill(sk_arr[idx], skb, cb, r, + NLM_F_MULTI, net_admin); if (res < 0) num = num_arr[idx]; } @@ -1038,31 +1062,101 @@ out: EXPORT_SYMBOL_GPL(inet_diag_dump_icsk); static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, - struct nlattr *bc) + const struct inet_diag_req_v2 *r) { const struct inet_diag_handler *handler; + u32 prev_min_dump_alloc; int err = 0; +again: + prev_min_dump_alloc = cb->min_dump_alloc; handler = inet_diag_lock_handler(r->sdiag_protocol); if (!IS_ERR(handler)) - handler->dump(skb, cb, r, bc); + handler->dump(skb, cb, r); else err = PTR_ERR(handler); inet_diag_unlock_handler(handler); + /* The skb is not large enough to fit one sk info and + * inet_sk_diag_fill() has requested for a larger skb. + */ + if (!skb->len && cb->min_dump_alloc > prev_min_dump_alloc) { + err = pskb_expand_head(skb, 0, cb->min_dump_alloc, GFP_KERNEL); + if (!err) + goto again; + } + return err ? : skb->len; } static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { - int hdrlen = sizeof(struct inet_diag_req_v2); - struct nlattr *bc = NULL; + return __inet_diag_dump(skb, cb, nlmsg_data(cb->nlh)); +} - if (nlmsg_attrlen(cb->nlh, hdrlen)) - bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE); +static int __inet_diag_dump_start(struct netlink_callback *cb, int hdrlen) +{ + const struct nlmsghdr *nlh = cb->nlh; + struct inet_diag_dump_data *cb_data; + struct sk_buff *skb = cb->skb; + struct nlattr *nla; + int rem, err; + + cb_data = kzalloc(sizeof(*cb_data), GFP_KERNEL); + if (!cb_data) + return -ENOMEM; + + nla_for_each_attr(nla, nlmsg_attrdata(nlh, hdrlen), + nlmsg_attrlen(nlh, hdrlen), rem) { + int type = nla_type(nla); + + if (type < __INET_DIAG_REQ_MAX) + cb_data->req_nlas[type] = nla; + } + + nla = cb_data->inet_diag_nla_bc; + if (nla) { + err = inet_diag_bc_audit(nla, skb); + if (err) { + kfree(cb_data); + return err; + } + } + + nla = cb_data->inet_diag_nla_bpf_stgs; + if (nla) { + struct bpf_sk_storage_diag *bpf_stg_diag; + + bpf_stg_diag = bpf_sk_storage_diag_alloc(nla); + if (IS_ERR(bpf_stg_diag)) { + kfree(cb_data); + return PTR_ERR(bpf_stg_diag); + } + cb_data->bpf_stg_diag = bpf_stg_diag; + } + + cb->data = cb_data; + return 0; +} + +static int inet_diag_dump_start(struct netlink_callback *cb) +{ + return __inet_diag_dump_start(cb, sizeof(struct inet_diag_req_v2)); +} + +static int inet_diag_dump_start_compat(struct netlink_callback *cb) +{ + return __inet_diag_dump_start(cb, sizeof(struct inet_diag_req)); +} - return __inet_diag_dump(skb, cb, nlmsg_data(cb->nlh), bc); +static int inet_diag_dump_done(struct netlink_callback *cb) +{ + struct inet_diag_dump_data *cb_data = cb->data; + + bpf_sk_storage_diag_free(cb_data->bpf_stg_diag); + kfree(cb->data); + + return 0; } static int inet_diag_type2proto(int type) @@ -1081,9 +1175,7 @@ static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *cb) { struct inet_diag_req *rc = nlmsg_data(cb->nlh); - int hdrlen = sizeof(struct inet_diag_req); struct inet_diag_req_v2 req; - struct nlattr *bc = NULL; req.sdiag_family = AF_UNSPEC; /* compatibility */ req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type); @@ -1091,10 +1183,7 @@ static int inet_diag_dump_compat(struct sk_buff *skb, req.idiag_states = rc->idiag_states; req.id = rc->id; - if (nlmsg_attrlen(cb->nlh, hdrlen)) - bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE); - - return __inet_diag_dump(skb, cb, &req, bc); + return __inet_diag_dump(skb, cb, &req); } static int inet_diag_get_exact_compat(struct sk_buff *in_skb, @@ -1122,22 +1211,12 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; if (nlh->nlmsg_flags & NLM_F_DUMP) { - if (nlmsg_attrlen(nlh, hdrlen)) { - struct nlattr *attr; - int err; - - attr = nlmsg_find_attr(nlh, hdrlen, - INET_DIAG_REQ_BYTECODE); - err = inet_diag_bc_audit(attr, skb); - if (err) - return err; - } - { - struct netlink_dump_control c = { - .dump = inet_diag_dump_compat, - }; - return netlink_dump_start(net->diag_nlsk, skb, nlh, &c); - } + struct netlink_dump_control c = { + .start = inet_diag_dump_start_compat, + .done = inet_diag_dump_done, + .dump = inet_diag_dump_compat, + }; + return netlink_dump_start(net->diag_nlsk, skb, nlh, &c); } return inet_diag_get_exact_compat(skb, nlh); @@ -1153,22 +1232,12 @@ static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h) if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY && h->nlmsg_flags & NLM_F_DUMP) { - if (nlmsg_attrlen(h, hdrlen)) { - struct nlattr *attr; - int err; - - attr = nlmsg_find_attr(h, hdrlen, - INET_DIAG_REQ_BYTECODE); - err = inet_diag_bc_audit(attr, skb); - if (err) - return err; - } - { - struct netlink_dump_control c = { - .dump = inet_diag_dump, - }; - return netlink_dump_start(net->diag_nlsk, skb, h, &c); - } + struct netlink_dump_control c = { + .start = inet_diag_dump_start, + .done = inet_diag_dump_done, + .dump = inet_diag_dump, + }; + return netlink_dump_start(net->diag_nlsk, skb, h, &c); } return inet_diag_cmd_exact(h->nlmsg_type, skb, h, nlmsg_data(h)); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index d84819893db9..aaaaf907e0d8 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -333,7 +333,7 @@ static int ip_mc_finish_output(struct net *net, struct sock *sk, switch (ret) { case NET_XMIT_CN: do_cn = true; - /* fall through */ + fallthrough; case NET_XMIT_SUCCESS: break; default: diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 6e68def66822..9cf83cc85e4a 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1465,7 +1465,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, case MRT_ADD_MFC: case MRT_DEL_MFC: parent = -1; - /* fall through */ + fallthrough; case MRT_ADD_MFC_PROXY: case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) { diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 4b2d49cc9f1a..0c72156130b6 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -173,7 +173,7 @@ static void dump_ipv4_packet(struct net *net, struct nf_log_buf *m, case ICMP_REDIRECT: /* Max length: 24 "GATEWAY=255.255.255.255 " */ nf_log_buf_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); - /* Fall through */ + fallthrough; case ICMP_DEST_UNREACH: case ICMP_SOURCE_QUENCH: case ICMP_TIME_EXCEEDED: diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index b2aeb7bf5dac..3c25a467b3ef 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -168,7 +168,7 @@ pptp_outbound_pkt(struct sk_buff *skb, pr_debug("unknown outbound packet 0x%04x:%s\n", msg, msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0]); - /* fall through */ + fallthrough; case PPTP_SET_LINK_INFO: /* only need to NAT in case PAC is behind NAT box */ case PPTP_START_SESSION_REQUEST: @@ -271,7 +271,7 @@ pptp_inbound_pkt(struct sk_buff *skb, pr_debug("unknown inbound packet %s\n", msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0]); - /* fall through */ + fallthrough; case PPTP_START_SESSION_REQUEST: case PPTP_START_SESSION_REPLY: case PPTP_STOP_SESSION_REQUEST: diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index d072c326dd64..fdfca534d094 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1327,7 +1327,7 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, case AF_UNSPEC: if (tb[NHA_GROUP]) break; - /* fallthrough */ + fallthrough; default: NL_SET_ERR_MSG(extack, "Invalid address family"); goto out; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 3183413ebc6c..47665919048f 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -1034,6 +1034,7 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos) } void *raw_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(&h->lock) { struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); @@ -1056,6 +1057,7 @@ void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos) EXPORT_SYMBOL_GPL(raw_seq_next); void raw_seq_stop(struct seq_file *seq, void *v) + __releases(&h->lock) { struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index a93e7d1e1251..1b5b8af27aaf 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -87,15 +87,16 @@ out_unlock: return sk ? sk : ERR_PTR(-ENOENT); } -static int raw_diag_dump_one(struct sk_buff *in_skb, - const struct nlmsghdr *nlh, +static int raw_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { - struct net *net = sock_net(in_skb->sk); + struct sk_buff *in_skb = cb->skb; struct sk_buff *rep; struct sock *sk; + struct net *net; int err; + net = sock_net(in_skb->sk); sk = raw_sock_get(net, r); if (IS_ERR(sk)) return PTR_ERR(sk); @@ -109,10 +110,7 @@ static int raw_diag_dump_one(struct sk_buff *in_skb, return -ENOMEM; } - err = inet_sk_diag_fill(sk, NULL, rep, r, - sk_user_ns(NETLINK_CB(in_skb).sk), - NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh, + err = inet_sk_diag_fill(sk, NULL, rep, cb, r, 0, netlink_net_capable(in_skb, CAP_NET_ADMIN)); sock_put(sk); @@ -137,25 +135,25 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, if (!inet_diag_bc_sk(bc, sk)) return 0; - return inet_sk_diag_fill(sk, NULL, skb, r, - sk_user_ns(NETLINK_CB(cb->skb).sk), - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->nlh, net_admin); + return inet_sk_diag_fill(sk, NULL, skb, cb, r, NLM_F_MULTI, net_admin); } static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r) { bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct raw_hashinfo *hashinfo = raw_get_hashinfo(r); struct net *net = sock_net(skb->sk); + struct inet_diag_dump_data *cb_data; int num, s_num, slot, s_slot; struct sock *sk = NULL; + struct nlattr *bc; if (IS_ERR(hashinfo)) return; + cb_data = cb->data; + bc = cb_data->inet_diag_nla_bc; s_slot = cb->args[0]; num = s_num = cb->args[1]; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ebe7060d0fc9..042599cc691d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2774,6 +2774,54 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, } EXPORT_SYMBOL_GPL(ip_route_output_flow); +struct rtable *ip_route_output_tunnel(struct sk_buff *skb, + struct net_device *dev, + struct net *net, __be32 *saddr, + const struct ip_tunnel_info *info, + u8 protocol, bool use_cache) +{ +#ifdef CONFIG_DST_CACHE + struct dst_cache *dst_cache; +#endif + struct rtable *rt = NULL; + struct flowi4 fl4; + __u8 tos; + +#ifdef CONFIG_DST_CACHE + dst_cache = (struct dst_cache *)&info->dst_cache; + if (use_cache) { + rt = dst_cache_get_ip4(dst_cache, saddr); + if (rt) + return rt; + } +#endif + memset(&fl4, 0, sizeof(fl4)); + fl4.flowi4_mark = skb->mark; + fl4.flowi4_proto = protocol; + fl4.daddr = info->key.u.ipv4.dst; + fl4.saddr = info->key.u.ipv4.src; + tos = info->key.tos; + fl4.flowi4_tos = RT_TOS(tos); + + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) { + netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); + return ERR_PTR(-ENETUNREACH); + } + if (rt->dst.dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr); + ip_rt_put(rt); + return ERR_PTR(-ELOOP); + } +#ifdef CONFIG_DST_CACHE + if (use_cache) + dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr); +#endif + *saddr = fl4.saddr; + return rt; +} +EXPORT_SYMBOL_GPL(ip_route_output_tunnel); + /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, struct flowi4 *fl4, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 9684af02e0a5..81b267e990a1 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -555,18 +555,6 @@ static struct ctl_table ipv4_table[] = { }, #endif /* CONFIG_NETLABEL */ { - .procname = "tcp_available_congestion_control", - .maxlen = TCP_CA_BUF_MAX, - .mode = 0444, - .proc_handler = proc_tcp_available_congestion_control, - }, - { - .procname = "tcp_allowed_congestion_control", - .maxlen = TCP_CA_BUF_MAX, - .mode = 0644, - .proc_handler = proc_allowed_congestion_control, - }, - { .procname = "tcp_available_ulp", .maxlen = TCP_ULP_BUF_MAX, .mode = 0444, @@ -776,6 +764,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { + .procname = "ip_autobind_reuse", + .data = &init_net.ipv4.sysctl_ip_autobind_reuse, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { .procname = "fwmark_reflect", .data = &init_net.ipv4.sysctl_fwmark_reflect, .maxlen = sizeof(int), @@ -886,6 +883,18 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_tcp_congestion_control, }, { + .procname = "tcp_available_congestion_control", + .maxlen = TCP_CA_BUF_MAX, + .mode = 0444, + .proc_handler = proc_tcp_available_congestion_control, + }, + { + .procname = "tcp_allowed_congestion_control", + .maxlen = TCP_CA_BUF_MAX, + .mode = 0644, + .proc_handler = proc_allowed_congestion_control, + }, + { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index eb2d80519f8e..5c57850fab4b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2251,7 +2251,7 @@ void tcp_set_state(struct sock *sk, int state) if (inet_csk(sk)->icsk_bind_hash && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); - /* fall through */ + fallthrough; default: if (oldstate == TCP_ESTABLISHED) TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); @@ -3344,6 +3344,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */ nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ 0; } @@ -3399,6 +3400,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); + nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, + max_t(int, 0, tp->write_seq - tp->snd_nxt)); return stats; } @@ -3667,13 +3670,35 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (get_user(len, optlen)) return -EFAULT; - if (len != sizeof(zc)) + if (len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; + if (len > sizeof(zc)) { + len = sizeof(zc); + if (put_user(len, optlen)) + return -EFAULT; + } if (copy_from_user(&zc, optval, len)) return -EFAULT; lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc); release_sock(sk); + if (len == sizeof(zc)) + goto zerocopy_rcv_sk_err; + switch (len) { + case offsetofend(struct tcp_zerocopy_receive, err): + goto zerocopy_rcv_sk_err; + case offsetofend(struct tcp_zerocopy_receive, inq): + goto zerocopy_rcv_inq; + case offsetofend(struct tcp_zerocopy_receive, length): + default: + goto zerocopy_rcv_out; + } +zerocopy_rcv_sk_err: + if (!err) + zc.err = sock_error(sk); +zerocopy_rcv_inq: + zc.inq = tcp_inq_hint(sk); +zerocopy_rcv_out: if (!err && copy_to_user(optval, &zc, len)) err = -EFAULT; return err; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 8a01428f80c1..7d6e1b75d4d4 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -645,8 +645,10 @@ static void tcp_bpf_reinit_sk_prot(struct sock *sk, struct sk_psock *psock) /* Reinit occurs when program types change e.g. TCP_BPF_TX is removed * or added requiring sk_prot hook updates. We keep original saved * hooks in this case. + * + * Pairs with lockless read in sk_clone_lock(). */ - sk->sk_prot = &tcp_bpf_prots[family][config]; + WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]); } static int tcp_bpf_assert_proto_ops(struct proto *ops) @@ -691,3 +693,17 @@ int tcp_bpf_init(struct sock *sk) rcu_read_unlock(); return 0; } + +/* If a child got cloned from a listening socket that had tcp_bpf + * protocol callbacks installed, we need to restore the callbacks to + * the default ones because the child does not inherit the psock state + * that tcp_bpf callbacks expect. + */ +void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) +{ + int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; + struct proto *prot = newsk->sk_prot; + + if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE]) + newsk->sk_prot = sk->sk_prot_creator; +} diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 0d08f9e2d8d0..75a1c985f49a 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -179,15 +179,15 @@ static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin) } static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r) { - inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r, bc); + inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r); } -static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, +static int tcp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { - return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req); + return inet_diag_dump_one_icsk(&tcp_hashinfo, cb, req); } #ifdef CONFIG_INET_DIAG_DESTROY diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6b6b57000dad..bf4ced9273e8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2865,7 +2865,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, (*ack_flag & FLAG_LOST_RETRANS))) return; /* Change state if cwnd is undone or retransmits are lost */ - /* fall through */ + fallthrough; default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) @@ -6367,7 +6367,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) mptcp_incoming_options(sk, skb, &tp->rx_opt); break; } - /* fall through */ + fallthrough; case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: /* RFC 793 says to queue data in these states, @@ -6382,7 +6382,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) return 1; } } - /* Fall through */ + fallthrough; case TCP_ESTABLISHED: tcp_data_queue(sk, skb); queued = 1; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index df1166b76126..83a5d24e13b8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1019,7 +1019,8 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, if (!md5sig) return NULL; - hlist_for_each_entry_rcu(key, &md5sig->head, node) { + hlist_for_each_entry_rcu(key, &md5sig->head, node, + lockdep_sock_is_held(sk)) { if (key->family != family) continue; if (key->l3index && key->l3index != l3index) @@ -1064,7 +1065,8 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, if (family == AF_INET6) size = sizeof(struct in6_addr); #endif - hlist_for_each_entry_rcu(key, &md5sig->head, node) { + hlist_for_each_entry_rcu(key, &md5sig->head, node, + lockdep_sock_is_held(sk)) { if (key->family != family) continue; if (key->l3index && key->l3index != l3index) @@ -2070,7 +2072,7 @@ do_time_wait: } } /* to ACK */ - /* fall through */ + fallthrough; case TCP_TW_ACK: tcp_v4_timewait_ack(sk, skb); break; @@ -2366,7 +2368,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq) break; st->bucket = 0; st->state = TCP_SEQ_STATE_ESTABLISHED; - /* Fallthrough */ + fallthrough; case TCP_SEQ_STATE_ESTABLISHED: if (st->bucket > tcp_hashinfo.ehash_mask) break; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ad3b56d9fa71..03af7c3e75ef 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -548,6 +548,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fastopen_req = NULL; RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); + tcp_bpf_clone(sk, newsk); + __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); return newsk; @@ -817,6 +819,7 @@ EXPORT_SYMBOL(tcp_check_req); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb) + __releases(&((child)->sk_lock.slock)) { int ret = 0; int state = child->sk_state; diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 38d3ad141161..2703f24c5d1a 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -22,7 +22,8 @@ static struct tcp_ulp_ops *tcp_ulp_find(const char *name) { struct tcp_ulp_ops *e; - list_for_each_entry_rcu(e, &tcp_ulp_list, list) { + list_for_each_entry_rcu(e, &tcp_ulp_list, list, + lockdep_is_held(&tcp_ulp_list_lock)) { if (strcmp(e->name, name) == 0) return e; } @@ -106,7 +107,8 @@ void tcp_update_ulp(struct sock *sk, struct proto *proto, if (!icsk->icsk_ulp_ops) { sk->sk_write_space = write_space; - sk->sk_prot = proto; + /* Pairs with lockless read in sk_clone_lock() */ + WRITE_ONCE(sk->sk_prot, proto); return; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 08a41f1e1cd2..2633fc231593 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1671,10 +1671,11 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, error = -EAGAIN; do { spin_lock_bh(&queue->lock); - skb = __skb_try_recv_from_queue(sk, queue, flags, - udp_skb_destructor, - off, err, &last); + skb = __skb_try_recv_from_queue(sk, queue, flags, off, + err, &last); if (skb) { + if (!(flags & MSG_PEEK)) + udp_skb_destructor(sk, skb); spin_unlock_bh(&queue->lock); return skb; } @@ -1692,9 +1693,10 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, queue); - skb = __skb_try_recv_from_queue(sk, queue, flags, - udp_skb_dtor_locked, - off, err, &last); + skb = __skb_try_recv_from_queue(sk, queue, flags, off, + err, &last); + if (skb && !(flags & MSG_PEEK)) + udp_skb_dtor_locked(sk, skb); spin_unlock(&sk_queue->lock); spin_unlock_bh(&queue->lock); if (skb) @@ -2561,7 +2563,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, case UDP_ENCAP_ESPINUDP_NON_IKE: up->encap_rcv = xfrm4_udp_encap_rcv; #endif - /* FALLTHROUGH */ + fallthrough; case UDP_ENCAP_L2TPINUDP: up->encap_type = val; lock_sock(sk); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index dccd2286bc28..1dbece34496e 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -21,16 +21,15 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, if (!inet_diag_bc_sk(bc, sk)) return 0; - return inet_sk_diag_fill(sk, NULL, skb, req, - sk_user_ns(NETLINK_CB(cb->skb).sk), - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, net_admin); + return inet_sk_diag_fill(sk, NULL, skb, cb, req, NLM_F_MULTI, + net_admin); } -static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, - const struct nlmsghdr *nlh, +static int udp_dump_one(struct udp_table *tbl, + struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { + struct sk_buff *in_skb = cb->skb; int err = -EINVAL; struct sock *sk = NULL; struct sk_buff *rep; @@ -71,11 +70,8 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, if (!rep) goto out; - err = inet_sk_diag_fill(sk, NULL, rep, req, - sk_user_ns(NETLINK_CB(in_skb).sk), - NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0, nlh, - netlink_net_capable(in_skb, CAP_NET_ADMIN)); + err = inet_sk_diag_fill(sk, NULL, rep, cb, req, 0, + netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(rep); @@ -94,12 +90,16 @@ out_nosk: static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r) { bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct net *net = sock_net(skb->sk); + struct inet_diag_dump_data *cb_data; int num, s_num, slot, s_slot; + struct nlattr *bc; + cb_data = cb->data; + bc = cb_data->inet_diag_nla_bc; s_slot = cb->args[0]; num = s_num = cb->args[1]; @@ -147,15 +147,15 @@ done: } static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r) { - udp_dump(&udp_table, skb, cb, r, bc); + udp_dump(&udp_table, skb, cb, r); } -static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, +static int udp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { - return udp_dump_one(&udp_table, in_skb, nlh, req); + return udp_dump_one(&udp_table, cb, req); } static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, @@ -250,16 +250,15 @@ static const struct inet_diag_handler udp_diag_handler = { }; static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, - struct nlattr *bc) + const struct inet_diag_req_v2 *r) { - udp_dump(&udplite_table, skb, cb, r, bc); + udp_dump(&udplite_table, skb, cb, r); } -static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, +static int udplite_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { - return udp_dump_one(&udplite_table, in_skb, nlh, req); + return udp_dump_one(&udplite_table, cb, req); } static const struct inet_diag_handler udplite_diag_handler = { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 46d614b611db..5b9de773ce73 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3301,7 +3301,7 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) switch (idev->cnf.addr_gen_mode) { case IN6_ADDR_GEN_MODE_RANDOM: ipv6_gen_mode_random_init(idev); - /* fallthrough */ + fallthrough; case IN6_ADDR_GEN_MODE_STABLE_PRIVACY: if (!ipv6_generate_stable_address(&addr, 0, idev)) addrconf_add_linklocal(idev, &addr, @@ -3523,9 +3523,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, break; run_pending = 1; - - /* fall through */ - + fallthrough; case NETDEV_UP: case NETDEV_CHANGE: if (dev->flags & IFF_SLAVE) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 95835e8d99aa..45e2adc56610 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -36,7 +36,7 @@ struct tmp_ext { struct in6_addr saddr; #endif struct in6_addr daddr; - char hdrs[0]; + char hdrs[]; }; struct ah_skb_cb { @@ -259,7 +259,7 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) case NEXTHDR_DEST: if (dir == XFRM_POLICY_OUT) ipv6_rearrange_destopt(iph, exthdr.opth); - /* fall through */ + fallthrough; case NEXTHDR_HOP: if (!zero_out_mutable_opts(exthdr.opth)) { net_dbg_ratelimited("overrun %sopts\n", diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index ab5add0fe6b4..bcb9f5e62808 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -97,7 +97,7 @@ static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff, */ if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) break; - /* fall through */ + fallthrough; case 2: /* send ICMP PARM PROB regardless and drop packet */ icmpv6_param_prob(skb, ICMPV6_UNK_OPTION, optoff); return false; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index ef408a5090a2..2688f3e82165 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -898,7 +898,7 @@ static int icmpv6_rcv(struct sk_buff *skb) hdr = icmp6_hdr(skb); /* to notify */ - /* fall through */ + fallthrough; case ICMPV6_DEST_UNREACH: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 72abf892302f..46ed56719476 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2068,8 +2068,8 @@ static int fib6_walk_continue(struct fib6_walker *w) continue; } w->state = FWS_L; + fallthrough; #endif - /* fall through */ case FWS_L: left = rcu_dereference_protected(fn->left, 1); if (left) { @@ -2078,7 +2078,7 @@ static int fib6_walk_continue(struct fib6_walker *w) continue; } w->state = FWS_R; - /* fall through */ + fallthrough; case FWS_R: right = rcu_dereference_protected(fn->right, 1); if (right) { @@ -2088,7 +2088,7 @@ static int fib6_walk_continue(struct fib6_walker *w) } w->state = FWS_C; w->leaf = rcu_dereference_protected(fn->leaf, 1); - /* fall through */ + fallthrough; case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; @@ -2107,7 +2107,7 @@ static int fib6_walk_continue(struct fib6_walker *w) } skip: w->state = FWS_U; - /* fall through */ + fallthrough; case FWS_U: if (fn == w->root) return 0; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 087304427bbb..8a8c2d0cfcc8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -54,6 +54,7 @@ #include <linux/mroute6.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> +#include <net/ip_tunnels.h> static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -1196,6 +1197,75 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); +/** + * ip6_dst_lookup_tunnel - perform route lookup on tunnel + * @skb: Packet for which lookup is done + * @dev: Tunnel device + * @net: Network namespace of tunnel device + * @sk: Socket which provides route info + * @saddr: Memory to store the src ip address + * @info: Tunnel information + * @protocol: IP protocol + * @use_cahce: Flag to enable cache usage + * This function performs a route lookup on a tunnel + * + * It returns a valid dst pointer and stores src address to be used in + * tunnel in param saddr on success, else a pointer encoded error code. + */ + +struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb, + struct net_device *dev, + struct net *net, + struct socket *sock, + struct in6_addr *saddr, + const struct ip_tunnel_info *info, + u8 protocol, + bool use_cache) +{ + struct dst_entry *dst = NULL; +#ifdef CONFIG_DST_CACHE + struct dst_cache *dst_cache; +#endif + struct flowi6 fl6; + __u8 prio; + +#ifdef CONFIG_DST_CACHE + dst_cache = (struct dst_cache *)&info->dst_cache; + if (use_cache) { + dst = dst_cache_get_ip6(dst_cache, saddr); + if (dst) + return dst; + } +#endif + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = protocol; + fl6.daddr = info->key.u.ipv6.dst; + fl6.saddr = info->key.u.ipv6.src; + prio = info->key.tos; + fl6.flowlabel = ip6_make_flowinfo(RT_TOS(prio), + info->key.label); + + dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6, + NULL); + if (IS_ERR(dst)) { + netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); + return ERR_PTR(-ENETUNREACH); + } + if (dst->dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); + dst_release(dst); + return ERR_PTR(-ELOOP); + } +#ifdef CONFIG_DST_CACHE + if (use_cache) + dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); +#endif + *saddr = fl6.saddr; + return dst; +} +EXPORT_SYMBOL_GPL(ip6_dst_lookup_tunnel); + static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, gfp_t gfp) { diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index bfa49ff70531..65a54d74acc1 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -97,7 +97,8 @@ static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES #define ip6mr_for_each_table(mrt, net) \ - list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list) + list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list, \ + lockdep_rtnl_is_held()) static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) @@ -1690,7 +1691,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns case MRT6_ADD_MFC: case MRT6_DEL_MFC: parent = -1; - /* fall through */ + fallthrough; case MRT6_ADD_MFC_PROXY: case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 53caf59c591e..4a3feccd5b10 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1782,7 +1782,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); fib6_run_gc(0, net, false); - /* fallthrough */ + fallthrough; case NETDEV_UP: idev = in6_dev_get(dev); if (!idev) diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index 22b80db6d882..da64550a5707 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -248,7 +248,7 @@ static void dump_ipv6_packet(struct net *net, struct nf_log_buf *m, /* Max length: 17 "POINTER=ffffffff " */ nf_log_buf_add(m, "POINTER=%08x ", ntohl(ic->icmp6_pointer)); - /* Fall through */ + fallthrough; case ICMPV6_DEST_UNREACH: case ICMPV6_PKT_TOOBIG: case ICMPV6_TIME_EXCEED: diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index dfe5e603ffe1..0028aa1d7869 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1076,7 +1076,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; - /* fall through */ + fallthrough; default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } @@ -1099,7 +1099,7 @@ static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; - /* fall through */ + fallthrough; default: return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); @@ -1161,7 +1161,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; - /* fall through */ + fallthrough; default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } @@ -1184,7 +1184,7 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; - /* fall through */ + fallthrough; default: return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2931224b674e..2430c2f6819a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4370,7 +4370,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); break; } - /* FALLTHROUGH */ + fallthrough; case IPSTATS_MIB_OUTNOROUTES: IP6_INC_STATS(net, idev, ipstats_mib_noroutes); break; diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 8c52efe299cc..ac837afb9040 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -29,7 +29,7 @@ struct seg6_lwt { struct dst_cache cache; - struct seg6_iptunnel_encap tuninfo[0]; + struct seg6_iptunnel_encap tuninfo[]; }; static inline struct seg6_lwt *seg6_lwt_lwtunnel(struct lwtunnel_state *lwt) diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index ec8fcfc60a27..63b657aa8d29 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -203,29 +203,16 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; - int err; + int err, i; err = -ENOMEM; ipv6_table = kmemdup(ipv6_table_template, sizeof(ipv6_table_template), GFP_KERNEL); if (!ipv6_table) goto out; - ipv6_table[0].data = &net->ipv6.sysctl.bindv6only; - ipv6_table[1].data = &net->ipv6.sysctl.anycast_src_echo_reply; - ipv6_table[2].data = &net->ipv6.sysctl.flowlabel_consistency; - ipv6_table[3].data = &net->ipv6.sysctl.auto_flowlabels; - ipv6_table[4].data = &net->ipv6.sysctl.fwmark_reflect; - ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries; - ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay; - ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges; - ipv6_table[8].data = &net->ipv6.sysctl.ip_nonlocal_bind; - ipv6_table[9].data = &net->ipv6.sysctl.flowlabel_reflect; - ipv6_table[10].data = &net->ipv6.sysctl.max_dst_opts_cnt; - ipv6_table[11].data = &net->ipv6.sysctl.max_hbh_opts_cnt; - ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len; - ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len; - ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy, - ipv6_table[15].data = &net->ipv6.sysctl.seg6_flowlabel; + /* Update the variables to point into the current struct net */ + for (i = 0; i < ARRAY_SIZE(ipv6_table_template) - 1; i++) + ipv6_table[i].data += (void *)net - (void *)&init_net; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index eaf09e6b7844..413b3425ac66 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1742,7 +1742,7 @@ do_time_wait: } } /* to ACK */ - /* fall through */ + fallthrough; case TCP_TW_ACK: tcp_v6_timewait_ack(sk, skb); break; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index ea9e73428ed9..56fac24a627a 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -380,9 +380,7 @@ static int kcm_parse_func_strparser(struct strparser *strp, struct sk_buff *skb) struct bpf_prog *prog = psock->bpf_prog; int res; - preempt_disable(); - res = BPF_PROG_RUN(prog, skb); - preempt_enable(); + res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 2db3d50d10a4..10cf7c3dcbb3 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -116,7 +116,7 @@ struct l2tp_session { void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len); void (*session_close)(struct l2tp_session *session); void (*show)(struct seq_file *m, void *priv); - uint8_t priv[0]; /* private data */ + u8 priv[]; /* private data */ }; /* Describes the tunnel. It contains info to track all the associated diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2922d4150d88..54fb8d452a7b 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -47,7 +47,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout); #if 0 #define dprintk(args...) printk(KERN_DEBUG args) #else -#define dprintk(args...) +#define dprintk(args...) do {} while (0) #endif /* Maybe we'll add some more in the future. */ diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index f3a36c16a5e7..a4eccb98220a 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -56,7 +56,7 @@ found: return sk; } -static void *llc_seq_start(struct seq_file *seq, loff_t *pos) +static void *llc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { loff_t l = *pos; diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c index 57748cab0e28..b31f1021ad9c 100644 --- a/net/mac80211/aes_cmac.c +++ b/net/mac80211/aes_cmac.c @@ -26,12 +26,20 @@ void ieee80211_aes_cmac(struct crypto_shash *tfm, const u8 *aad, { SHASH_DESC_ON_STACK(desc, tfm); u8 out[AES_BLOCK_SIZE]; + const __le16 *fc; desc->tfm = tfm; crypto_shash_init(desc); crypto_shash_update(desc, aad, AAD_LEN); - crypto_shash_update(desc, data, data_len - CMAC_TLEN); + fc = (const __le16 *)aad; + if (ieee80211_is_beacon(*fc)) { + /* mask Timestamp field to zero */ + crypto_shash_update(desc, zero, 8); + crypto_shash_update(desc, data + 8, data_len - 8 - CMAC_TLEN); + } else { + crypto_shash_update(desc, data, data_len - CMAC_TLEN); + } crypto_shash_finup(desc, zero, CMAC_TLEN, out); memcpy(mic, out, CMAC_TLEN); @@ -41,12 +49,21 @@ void ieee80211_aes_cmac_256(struct crypto_shash *tfm, const u8 *aad, const u8 *data, size_t data_len, u8 *mic) { SHASH_DESC_ON_STACK(desc, tfm); + const __le16 *fc; desc->tfm = tfm; crypto_shash_init(desc); crypto_shash_update(desc, aad, AAD_LEN); - crypto_shash_update(desc, data, data_len - CMAC_TLEN_256); + fc = (const __le16 *)aad; + if (ieee80211_is_beacon(*fc)) { + /* mask Timestamp field to zero */ + crypto_shash_update(desc, zero, 8); + crypto_shash_update(desc, data + 8, + data_len - 8 - CMAC_TLEN_256); + } else { + crypto_shash_update(desc, data, data_len - CMAC_TLEN_256); + } crypto_shash_finup(desc, zero, CMAC_TLEN_256, mic); } diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c index 363ad1c1dc0c..16ba09cb5def 100644 --- a/net/mac80211/aes_gmac.c +++ b/net/mac80211/aes_gmac.c @@ -17,10 +17,11 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, const u8 *data, size_t data_len, u8 *mic) { - struct scatterlist sg[4]; + struct scatterlist sg[5]; u8 *zero, *__aad, iv[AES_BLOCK_SIZE]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); + const __le16 *fc; if (data_len < GMAC_MIC_LEN) return -EINVAL; @@ -33,11 +34,22 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, __aad = zero + GMAC_MIC_LEN; memcpy(__aad, aad, GMAC_AAD_LEN); - sg_init_table(sg, 4); - sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN); - sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN); - sg_set_buf(&sg[2], zero, GMAC_MIC_LEN); - sg_set_buf(&sg[3], mic, GMAC_MIC_LEN); + fc = (const __le16 *)aad; + if (ieee80211_is_beacon(*fc)) { + /* mask Timestamp field to zero */ + sg_init_table(sg, 5); + sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN); + sg_set_buf(&sg[1], zero, 8); + sg_set_buf(&sg[2], data + 8, data_len - 8 - GMAC_MIC_LEN); + sg_set_buf(&sg[3], zero, GMAC_MIC_LEN); + sg_set_buf(&sg[4], mic, GMAC_MIC_LEN); + } else { + sg_init_table(sg, 4); + sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN); + sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN); + sg_set_buf(&sg[2], zero, GMAC_MIC_LEN); + sg_set_buf(&sg[3], mic, GMAC_MIC_LEN); + } memcpy(iv, nonce, GMAC_NONCE_LEN); memset(iv + GMAC_NONCE_LEN, 0, sizeof(iv) - GMAC_NONCE_LEN); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 6aee699deb28..7b654d2b8bb2 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -568,7 +568,8 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, if (pairwise && key_idx < NUM_DEFAULT_KEYS) key = rcu_dereference(sta->ptk[key_idx]); else if (!pairwise && - key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) + key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) key = rcu_dereference(sta->gtk[key_idx]); } else key = rcu_dereference(sdata->keys[key_idx]); @@ -680,6 +681,17 @@ static int ieee80211_config_default_mgmt_key(struct wiphy *wiphy, return 0; } +static int ieee80211_config_default_beacon_key(struct wiphy *wiphy, + struct net_device *dev, + u8 key_idx) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + ieee80211_set_default_beacon_key(sdata, key_idx); + + return 0; +} + void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo) @@ -981,7 +993,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER | BSS_CHANGED_TWT | - BSS_CHANGED_HE_OBSS_PD; + BSS_CHANGED_HE_OBSS_PD | + BSS_CHANGED_HE_BSS_COLOR; int err; int prev_beacon_int; @@ -989,20 +1002,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (old) return -EALREADY; - switch (params->smps_mode) { - case NL80211_SMPS_OFF: - sdata->smps_mode = IEEE80211_SMPS_OFF; - break; - case NL80211_SMPS_STATIC: - sdata->smps_mode = IEEE80211_SMPS_STATIC; - break; - case NL80211_SMPS_DYNAMIC: - sdata->smps_mode = IEEE80211_SMPS_DYNAMIC; - break; - default: - return -EINVAL; - } - sdata->u.ap.req_smps = sdata->smps_mode; + if (params->smps_mode != NL80211_SMPS_OFF) + return -ENOTSUPP; + + sdata->smps_mode = IEEE80211_SMPS_OFF; sdata->needed_rx_chains = sdata->local->rx_chains; @@ -1054,6 +1057,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.twt_responder = params->twt_responder; memcpy(&sdata->vif.bss_conf.he_obss_pd, ¶ms->he_obss_pd, sizeof(struct ieee80211_he_obss_pd)); + memcpy(&sdata->vif.bss_conf.he_bss_color, ¶ms->he_bss_color, + sizeof(struct ieee80211_he_bss_color)); sdata->vif.bss_conf.ssid_len = params->ssid_len; if (params->ssid_len) @@ -1166,7 +1171,6 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) kfree_rcu(old_beacon, rcu_head); if (old_probe_resp) kfree_rcu(old_probe_resp, rcu_head); - sdata->u.ap.driver_smps_mode = IEEE80211_SMPS_OFF; kfree(sdata->vif.bss_conf.ftmr_params); sdata->vif.bss_conf.ftmr_params = NULL; @@ -1691,20 +1695,6 @@ static int ieee80211_change_station(struct wiphy *wiphy, mutex_unlock(&local->sta_mtx); - if ((sdata->vif.type == NL80211_IFTYPE_AP || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && - sta->known_smps_mode != sta->sdata->bss->req_smps && - test_sta_flag(sta, WLAN_STA_AUTHORIZED) && - sta_info_tx_streams(sta) != 1) { - ht_dbg(sta->sdata, - "%pM just authorized and MIMO capable - update SMPS\n", - sta->sta.addr); - ieee80211_send_smps_action(sta->sdata, - sta->sdata->bss->req_smps, - sta->sta.addr, - sta->sdata->vif.bss_conf.bssid); - } - if (sdata->vif.type == NL80211_IFTYPE_STATION && params->sta_flags_mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { ieee80211_recalc_ps(local); @@ -2636,74 +2626,6 @@ static int ieee80211_testmode_dump(struct wiphy *wiphy, } #endif -int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata, - enum ieee80211_smps_mode smps_mode) -{ - struct sta_info *sta; - enum ieee80211_smps_mode old_req; - - if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP)) - return -EINVAL; - - if (sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT) - return 0; - - old_req = sdata->u.ap.req_smps; - sdata->u.ap.req_smps = smps_mode; - - /* AUTOMATIC doesn't mean much for AP - don't allow it */ - if (old_req == smps_mode || - smps_mode == IEEE80211_SMPS_AUTOMATIC) - return 0; - - ht_dbg(sdata, - "SMPS %d requested in AP mode, sending Action frame to %d stations\n", - smps_mode, atomic_read(&sdata->u.ap.num_mcast_sta)); - - mutex_lock(&sdata->local->sta_mtx); - list_for_each_entry(sta, &sdata->local->sta_list, list) { - /* - * Only stations associated to our AP and - * associated VLANs - */ - if (sta->sdata->bss != &sdata->u.ap) - continue; - - /* This station doesn't support MIMO - skip it */ - if (sta_info_tx_streams(sta) == 1) - continue; - - /* - * Don't wake up a STA just to send the action frame - * unless we are getting more restrictive. - */ - if (test_sta_flag(sta, WLAN_STA_PS_STA) && - !ieee80211_smps_is_restrictive(sta->known_smps_mode, - smps_mode)) { - ht_dbg(sdata, "Won't send SMPS to sleeping STA %pM\n", - sta->sta.addr); - continue; - } - - /* - * If the STA is not authorized, wait until it gets - * authorized and the action frame will be sent then. - */ - if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) - continue; - - ht_dbg(sdata, "Sending SMPS to %pM\n", sta->sta.addr); - ieee80211_send_smps_action(sdata, smps_mode, sta->sta.addr, - sdata->vif.bss_conf.bssid); - } - mutex_unlock(&sdata->local->sta_mtx); - - sdata->smps_mode = smps_mode; - ieee80211_queue_work(&sdata->local->hw, &sdata->recalc_smps); - - return 0; -} - int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps_mode) { @@ -3964,6 +3886,60 @@ ieee80211_abort_pmsr(struct wiphy *wiphy, struct wireless_dev *dev, return drv_abort_pmsr(local, sdata, request); } +static int ieee80211_set_tid_config(struct wiphy *wiphy, + struct net_device *dev, + struct cfg80211_tid_config *tid_conf) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct sta_info *sta; + int ret; + + if (!sdata->local->ops->set_tid_config) + return -EOPNOTSUPP; + + if (!tid_conf->peer) + return drv_set_tid_config(sdata->local, sdata, NULL, tid_conf); + + mutex_lock(&sdata->local->sta_mtx); + sta = sta_info_get_bss(sdata, tid_conf->peer); + if (!sta) { + mutex_unlock(&sdata->local->sta_mtx); + return -ENOENT; + } + + ret = drv_set_tid_config(sdata->local, sdata, &sta->sta, tid_conf); + mutex_unlock(&sdata->local->sta_mtx); + + return ret; +} + +static int ieee80211_reset_tid_config(struct wiphy *wiphy, + struct net_device *dev, + const u8 *peer, u8 tid) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct sta_info *sta; + int ret; + + if (!sdata->local->ops->reset_tid_config) + return -EOPNOTSUPP; + + if (!peer) + return drv_reset_tid_config(sdata->local, sdata, NULL, tid); + + mutex_lock(&sdata->local->sta_mtx); + sta = sta_info_get_bss(sdata, peer); + if (!sta) { + mutex_unlock(&sdata->local->sta_mtx); + return -ENOENT; + } + + ret = drv_reset_tid_config(sdata->local, sdata, &sta->sta, tid); + mutex_unlock(&sdata->local->sta_mtx); + + return ret; +} + const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -3975,6 +3951,7 @@ const struct cfg80211_ops mac80211_config_ops = { .get_key = ieee80211_get_key, .set_default_key = ieee80211_config_default_key, .set_default_mgmt_key = ieee80211_config_default_mgmt_key, + .set_default_beacon_key = ieee80211_config_default_beacon_key, .start_ap = ieee80211_start_ap, .change_beacon = ieee80211_change_beacon, .stop_ap = ieee80211_stop_ap, @@ -4063,4 +4040,6 @@ const struct cfg80211_ops mac80211_config_ops = { .start_pmsr = ieee80211_start_pmsr, .abort_pmsr = ieee80211_abort_pmsr, .probe_mesh_link = ieee80211_probe_mesh_link, + .set_tid_config = ieee80211_set_tid_config, + .reset_tid_config = ieee80211_reset_tid_config, }; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index ad41d74530c6..54080290d6e2 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -150,6 +150,59 @@ static const struct file_operations aqm_ops = { .llseek = default_llseek, }; +static ssize_t airtime_flags_read(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + char buf[128] = {}, *pos, *end; + + pos = buf; + end = pos + sizeof(buf) - 1; + + if (local->airtime_flags & AIRTIME_USE_TX) + pos += scnprintf(pos, end - pos, "AIRTIME_TX\t(%lx)\n", + AIRTIME_USE_TX); + if (local->airtime_flags & AIRTIME_USE_RX) + pos += scnprintf(pos, end - pos, "AIRTIME_RX\t(%lx)\n", + AIRTIME_USE_RX); + + return simple_read_from_buffer(user_buf, count, ppos, buf, + strlen(buf)); +} + +static ssize_t airtime_flags_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + char buf[16]; + size_t len; + + if (count > sizeof(buf)) + return -EINVAL; + + if (copy_from_user(buf, user_buf, count)) + return -EFAULT; + + buf[sizeof(buf) - 1] = 0; + len = strlen(buf); + if (len > 0 && buf[len - 1] == '\n') + buf[len - 1] = 0; + + if (kstrtou16(buf, 0, &local->airtime_flags)) + return -EINVAL; + + return count; +} + +static const struct file_operations airtime_flags_ops = { + .write = airtime_flags_write, + .read = airtime_flags_read, + .open = simple_open, + .llseek = default_llseek, +}; + static ssize_t aql_txq_limit_read(struct file *file, char __user *user_buf, size_t count, @@ -522,8 +575,7 @@ void debugfs_hw_add(struct ieee80211_local *local) if (local->ops->wake_tx_queue) DEBUGFS_ADD_MODE(aqm, 0600); - debugfs_create_u16("airtime_flags", 0600, - phyd, &local->airtime_flags); + DEBUGFS_ADD_MODE(airtime_flags, 0600); DEBUGFS_ADD(aql_txq_limit); debugfs_create_u32("aql_threshold", 0600, diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 7b8735ced2a1..98a713475e0f 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -433,6 +433,37 @@ void ieee80211_debugfs_key_remove_mgmt_default(struct ieee80211_sub_if_data *sda sdata->debugfs.default_mgmt_key = NULL; } +void +ieee80211_debugfs_key_add_beacon_default(struct ieee80211_sub_if_data *sdata) +{ + char buf[50]; + struct ieee80211_key *key; + + if (!sdata->vif.debugfs_dir) + return; + + key = key_mtx_dereference(sdata->local, + sdata->default_beacon_key); + if (key) { + sprintf(buf, "../keys/%d", key->debugfs.cnt); + sdata->debugfs.default_beacon_key = + debugfs_create_symlink("default_beacon_key", + sdata->vif.debugfs_dir, buf); + } else { + ieee80211_debugfs_key_remove_beacon_default(sdata); + } +} + +void +ieee80211_debugfs_key_remove_beacon_default(struct ieee80211_sub_if_data *sdata) +{ + if (!sdata) + return; + + debugfs_remove(sdata->debugfs.default_beacon_key); + sdata->debugfs.default_beacon_key = NULL; +} + void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, struct sta_info *sta) { diff --git a/net/mac80211/debugfs_key.h b/net/mac80211/debugfs_key.h index 1cd7b8bff56c..af7cf495f8d1 100644 --- a/net/mac80211/debugfs_key.h +++ b/net/mac80211/debugfs_key.h @@ -10,6 +10,10 @@ void ieee80211_debugfs_key_add_mgmt_default( struct ieee80211_sub_if_data *sdata); void ieee80211_debugfs_key_remove_mgmt_default( struct ieee80211_sub_if_data *sdata); +void ieee80211_debugfs_key_add_beacon_default( + struct ieee80211_sub_if_data *sdata); +void ieee80211_debugfs_key_remove_beacon_default( + struct ieee80211_sub_if_data *sdata); void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, struct sta_info *sta); #else @@ -26,6 +30,12 @@ static inline void ieee80211_debugfs_key_add_mgmt_default( static inline void ieee80211_debugfs_key_remove_mgmt_default( struct ieee80211_sub_if_data *sdata) {} +static inline void ieee80211_debugfs_key_add_beacon_default( + struct ieee80211_sub_if_data *sdata) +{} +static inline void ieee80211_debugfs_key_remove_beacon_default( + struct ieee80211_sub_if_data *sdata) +{} static inline void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, struct sta_info *sta) {} diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 64b544ae9966..3dbe7c5cefd1 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -2,6 +2,7 @@ /* * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> + * Copyright (C) 2020 Intel Corporation */ #include <linux/kernel.h> @@ -254,15 +255,11 @@ static int ieee80211_set_smps(struct ieee80211_sub_if_data *sdata, smps_mode == IEEE80211_SMPS_AUTOMATIC)) return -EINVAL; - if (sdata->vif.type != NL80211_IFTYPE_STATION && - sdata->vif.type != NL80211_IFTYPE_AP) + if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; sdata_lock(sdata); - if (sdata->vif.type == NL80211_IFTYPE_STATION) - err = __ieee80211_request_smps_mgd(sdata, smps_mode); - else - err = __ieee80211_request_smps_ap(sdata, smps_mode); + err = __ieee80211_request_smps_mgd(sdata, smps_mode); sdata_unlock(sdata); return err; @@ -282,10 +279,6 @@ static ssize_t ieee80211_if_fmt_smps(const struct ieee80211_sub_if_data *sdata, return snprintf(buf, buflen, "request: %s\nused: %s\n", smps_modes[sdata->u.mgd.req_smps], smps_modes[sdata->smps_mode]); - if (sdata->vif.type == NL80211_IFTYPE_AP) - return snprintf(buf, buflen, "request: %s\nused: %s\n", - smps_modes[sdata->u.ap.req_smps], - smps_modes[sdata->smps_mode]); return -EINVAL; } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index c80b1e163ea4..266d63819415 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -1025,12 +1025,10 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD_COUNTER(rx_fragments, rx_stats.fragments); DEBUGFS_ADD_COUNTER(tx_filtered, status_stats.filtered); - if (local->ops->wake_tx_queue) + if (local->ops->wake_tx_queue) { DEBUGFS_ADD(aqm); - - if (wiphy_ext_feature_isset(local->hw.wiphy, - NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) DEBUGFS_ADD(airtime); + } if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 2c9b3eb8b652..3877710e3b48 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1358,4 +1358,31 @@ static inline void drv_del_nan_func(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline int drv_set_tid_config(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + struct cfg80211_tid_config *tid_conf) +{ + int ret; + + might_sleep(); + ret = local->ops->set_tid_config(&local->hw, &sdata->vif, sta, + tid_conf); + trace_drv_return_int(local, ret); + + return ret; +} + +static inline int drv_reset_tid_config(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, u8 tid) +{ + int ret; + + might_sleep(); + ret = local->ops->reset_tid_config(&local->hw, &sdata->vif, sta, tid); + trace_drv_return_int(local, ret); + + return ret; +} #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/he.c b/net/mac80211/he.c index 736da0035135..1087f715338b 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -3,6 +3,7 @@ * HE handling * * Copyright(c) 2017 Intel Deutschland GmbH + * Copyright(c) 2019 - 2020 Intel Corporation */ #include "ieee80211_i.h" @@ -49,6 +50,9 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, he_ppe_size); he_cap->has_he = true; + + sta->cur_max_bandwidth = ieee80211_sta_cap_rx_bw(sta); + sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta); } void diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index a2e4d6b8fd98..e32906202575 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -9,6 +9,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright 2017 Intel Deutschland GmbH + * Copyright(c) 2020 Intel Corporation */ #include <linux/ieee80211.h> @@ -144,7 +145,6 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, int i, max_tx_streams; bool changed; enum ieee80211_sta_rx_bandwidth bw; - enum ieee80211_smps_mode smps_mode; memset(&ht_cap, 0, sizeof(ht_cap)); @@ -270,24 +270,30 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20; - switch ((ht_cap.cap & IEEE80211_HT_CAP_SM_PS) - >> IEEE80211_HT_CAP_SM_PS_SHIFT) { - case WLAN_HT_CAP_SM_PS_INVALID: - case WLAN_HT_CAP_SM_PS_STATIC: - smps_mode = IEEE80211_SMPS_STATIC; - break; - case WLAN_HT_CAP_SM_PS_DYNAMIC: - smps_mode = IEEE80211_SMPS_DYNAMIC; - break; - case WLAN_HT_CAP_SM_PS_DISABLED: - smps_mode = IEEE80211_SMPS_OFF; - break; - } - - if (smps_mode != sta->sta.smps_mode) - changed = true; - sta->sta.smps_mode = smps_mode; + if (sta->sdata->vif.type == NL80211_IFTYPE_AP || + sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + enum ieee80211_smps_mode smps_mode; + + switch ((ht_cap.cap & IEEE80211_HT_CAP_SM_PS) + >> IEEE80211_HT_CAP_SM_PS_SHIFT) { + case WLAN_HT_CAP_SM_PS_INVALID: + case WLAN_HT_CAP_SM_PS_STATIC: + smps_mode = IEEE80211_SMPS_STATIC; + break; + case WLAN_HT_CAP_SM_PS_DYNAMIC: + smps_mode = IEEE80211_SMPS_DYNAMIC; + break; + case WLAN_HT_CAP_SM_PS_DISABLED: + smps_mode = IEEE80211_SMPS_OFF; + break; + } + if (smps_mode != sta->sta.smps_mode) + changed = true; + sta->sta.smps_mode = smps_mode; + } else { + sta->sta.smps_mode = IEEE80211_SMPS_OFF; + } return changed; } @@ -544,19 +550,6 @@ void ieee80211_request_smps_mgd_work(struct work_struct *work) sdata_unlock(sdata); } -void ieee80211_request_smps_ap_work(struct work_struct *work) -{ - struct ieee80211_sub_if_data *sdata = - container_of(work, struct ieee80211_sub_if_data, - u.ap.request_smps_work); - - sdata_lock(sdata); - if (sdata_dereference(sdata->u.ap.beacon, sdata)) - __ieee80211_request_smps_ap(sdata, - sdata->u.ap.driver_smps_mode); - sdata_unlock(sdata); -} - void ieee80211_request_smps(struct ieee80211_vif *vif, enum ieee80211_smps_mode smps_mode) { @@ -572,15 +565,6 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, sdata->u.mgd.driver_smps_mode = smps_mode; ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.request_smps_work); - } else { - /* AUTOMATIC is meaningless in AP mode */ - if (WARN_ON_ONCE(smps_mode == IEEE80211_SMPS_AUTOMATIC)) - return; - if (sdata->u.ap.driver_smps_mode == smps_mode) - return; - sdata->u.ap.driver_smps_mode = smps_mode; - ieee80211_queue_work(&sdata->local->hw, - &sdata->u.ap.request_smps_work); } } /* this might change ... don't want non-open drivers using it */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ad15b3be8bb3..de39f9ca9935 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2015 Intel Mobile Communications GmbH - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #ifndef IEEE80211_I_H @@ -292,10 +292,7 @@ struct ieee80211_if_ap { struct ps_data ps; atomic_t num_mcast_sta; /* number of stations receiving multicast */ - enum ieee80211_smps_mode req_smps, /* requested smps mode */ - driver_smps_mode; /* smps mode request */ - struct work_struct request_smps_work; bool multicast_to_unicast; }; @@ -904,10 +901,13 @@ struct ieee80211_sub_if_data { /* bit field of ACM bits (BIT(802.1D tag)) */ u8 wmm_acm; - struct ieee80211_key __rcu *keys[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; + struct ieee80211_key __rcu *keys[NUM_DEFAULT_KEYS + + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS]; struct ieee80211_key __rcu *default_unicast_key; struct ieee80211_key __rcu *default_multicast_key; struct ieee80211_key __rcu *default_mgmt_key; + struct ieee80211_key __rcu *default_beacon_key; u16 sequence_number; __be16 control_port_protocol; @@ -981,9 +981,12 @@ struct ieee80211_sub_if_data { struct dentry *default_unicast_key; struct dentry *default_multicast_key; struct dentry *default_mgmt_key; + struct dentry *default_beacon_key; } debugfs; #endif + bool hw_80211_encap; + /* must be last, dynamically sized area in this! */ struct ieee80211_vif vif; }; @@ -1473,6 +1476,7 @@ struct ieee802_11_elems { const struct ieee80211_tim_ie *tim; const u8 *challenge; const u8 *rsn; + const u8 *rsnx; const u8 *erp_info; const u8 *ext_supp_rates; const u8 *wmm_info; @@ -1520,6 +1524,7 @@ struct ieee802_11_elems { u8 tim_len; u8 challenge_len; u8 rsn_len; + u8 rsnx_len; u8 ext_supp_rates_len; u8 wmm_info_len; u8 wmm_param_len; @@ -1727,6 +1732,13 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params); /* interface handling */ +#define MAC80211_SUPPORTED_FEATURES_TX (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \ + NETIF_F_HW_CSUM | NETIF_F_SG | \ + NETIF_F_HIGHDMA | NETIF_F_GSO_SOFTWARE) +#define MAC80211_SUPPORTED_FEATURES_RX (NETIF_F_RXCSUM) +#define MAC80211_SUPPORTED_FEATURES (MAC80211_SUPPORTED_FEATURES_TX | \ + MAC80211_SUPPORTED_FEATURES_RX) + int ieee80211_iface_init(void); void ieee80211_iface_exit(void); int ieee80211_if_add(struct ieee80211_local *local, const char *name, @@ -1762,6 +1774,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb, + struct net_device *dev); void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags, @@ -1948,6 +1962,11 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid, enum nl80211_band band, u32 txdata_flags); +/* sta_out needs to be checked for ERR_PTR() before using */ +int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + struct sta_info **sta_out); + static inline void ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid, @@ -2132,8 +2151,6 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, enum nl80211_band band, u32 *basic_rates); int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps_mode); -int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata, - enum ieee80211_smps_mode smps_mode); void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata); void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index af8b09214786..128b3468d13e 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -8,7 +8,7 @@ * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> @@ -824,9 +824,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_ADHOC: ieee80211_ibss_stop(sdata); break; - case NL80211_IFTYPE_AP: - cancel_work_sync(&sdata->u.ap.request_smps_work); - break; case NL80211_IFTYPE_MONITOR: if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) break; @@ -1205,6 +1202,72 @@ static const struct net_device_ops ieee80211_monitorif_ops = { .ndo_get_stats64 = ieee80211_get_stats64, }; +static const struct net_device_ops ieee80211_dataif_8023_ops = { + .ndo_open = ieee80211_open, + .ndo_stop = ieee80211_stop, + .ndo_uninit = ieee80211_uninit, + .ndo_start_xmit = ieee80211_subif_start_xmit_8023, + .ndo_set_rx_mode = ieee80211_set_multicast_list, + .ndo_set_mac_address = ieee80211_change_mac, + .ndo_select_queue = ieee80211_netdev_select_queue, + .ndo_get_stats64 = ieee80211_get_stats64, +}; + +static void __ieee80211_set_hw_80211_encap(struct ieee80211_sub_if_data *sdata, + bool enable) +{ + sdata->dev->netdev_ops = enable ? &ieee80211_dataif_8023_ops : + &ieee80211_dataif_ops; + sdata->hw_80211_encap = enable; +} + +bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_local *local = sdata->local; + struct ieee80211_sub_if_data *iter; + struct ieee80211_key *key; + + mutex_lock(&local->iflist_mtx); + list_for_each_entry(iter, &local->interfaces, list) { + struct ieee80211_sub_if_data *disable = NULL; + + if (vif->type == NL80211_IFTYPE_MONITOR) { + disable = iter; + __ieee80211_set_hw_80211_encap(iter, false); + } else if (iter->vif.type == NL80211_IFTYPE_MONITOR) { + disable = sdata; + enable = false; + } + if (disable) + sdata_dbg(disable, + "disable hw 80211 encap due to mon co-exist\n"); + } + mutex_unlock(&local->iflist_mtx); + + if (enable == sdata->hw_80211_encap) + return enable; + + if (!sdata->dev) + return false; + + if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG) && + (local->hw.wiphy->frag_threshold != (u32)-1)) + enable = false; + + mutex_lock(&sdata->local->key_mtx); + list_for_each_entry(key, &sdata->key_list, list) { + if (key->conf.cipher == WLAN_CIPHER_SUITE_TKIP) + enable = false; + } + mutex_unlock(&sdata->local->key_mtx); + + __ieee80211_set_hw_80211_encap(sdata, enable); + + return enable; +} +EXPORT_SYMBOL(ieee80211_set_hw_80211_encap); + static void ieee80211_if_free(struct net_device *dev) { free_percpu(dev->tstats); @@ -1402,8 +1465,10 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, sdata->control_port_no_encrypt = false; sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; sdata->vif.bss_conf.idle = true; + sdata->vif.bss_conf.txpower = INT_MIN; /* unset */ sdata->noack_map = 0; + sdata->hw_80211_encap = false; /* only monitor/p2p-device differ */ if (sdata->dev) { @@ -1427,10 +1492,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_AP: skb_queue_head_init(&sdata->u.ap.ps.bc_buf); INIT_LIST_HEAD(&sdata->u.ap.vlans); - INIT_WORK(&sdata->u.ap.request_smps_work, - ieee80211_request_smps_ap_work); sdata->vif.bss_conf.bssid = sdata->vif.addr; - sdata->u.ap.req_smps = IEEE80211_SMPS_OFF; break; case NL80211_IFTYPE_P2P_CLIENT: type = NL80211_IFTYPE_STATION; @@ -1772,6 +1834,10 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, if_setup, txqs, 1); if (!ndev) return -ENOMEM; + + if (!local->ops->wake_tx_queue && local->hw.wiphy->tx_queue_len) + ndev->tx_queue_len = local->hw.wiphy->tx_queue_len; + dev_net_set(ndev, wiphy_net(local->hw.wiphy)); ndev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); @@ -1871,6 +1937,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sdata->u.mgd.use_4addr = params->use_4addr; ndev->features |= local->hw.netdev_features; + ndev->hw_features |= ndev->features & + MAC80211_SUPPORTED_FEATURES_TX; netdev_set_default_ethtool_ops(ndev, &ieee80211_ethtool_ops); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 0f889b919b06..6354491c5a09 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -177,6 +177,13 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) } } + /* TKIP countermeasures don't work in encap offload mode */ + if (key->conf.cipher == WLAN_CIPHER_SUITE_TKIP && + sdata->hw_80211_encap) { + sdata_dbg(sdata, "TKIP is not allowed in hw 80211 encap mode\n"); + return -EINVAL; + } + ret = drv_set_key(key->local, SET_KEY, sdata, sta ? &sta->sta : NULL, &key->conf); @@ -210,12 +217,20 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + /* We cannot do software crypto of data frames with + * encapsulation offload enabled. However for 802.11w to + * function properly we need cmac/gmac keys. + */ + if (sdata->hw_80211_encap) + return -EINVAL; + /* Fall through */ + case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: - case WLAN_CIPHER_SUITE_GCMP: - case WLAN_CIPHER_SUITE_GCMP_256: /* all of these we can do in software - if driver can */ if (ret == 1) return 0; @@ -392,6 +407,31 @@ void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata, mutex_unlock(&sdata->local->key_mtx); } +static void +__ieee80211_set_default_beacon_key(struct ieee80211_sub_if_data *sdata, int idx) +{ + struct ieee80211_key *key = NULL; + + assert_key_lock(sdata->local); + + if (idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS && + idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) + key = key_mtx_dereference(sdata->local, sdata->keys[idx]); + + rcu_assign_pointer(sdata->default_beacon_key, key); + + ieee80211_debugfs_key_update_default(sdata); +} + +void ieee80211_set_default_beacon_key(struct ieee80211_sub_if_data *sdata, + int idx) +{ + mutex_lock(&sdata->local->key_mtx); + __ieee80211_set_default_beacon_key(sdata, idx); + mutex_unlock(&sdata->local->key_mtx); +} + static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, bool pairwise, @@ -400,7 +440,7 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, { int idx; int ret = 0; - bool defunikey, defmultikey, defmgmtkey; + bool defunikey, defmultikey, defmgmtkey, defbeaconkey; /* caller must provide at least one old/new */ if (WARN_ON(!new && !old)) @@ -465,6 +505,9 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, defmgmtkey = old && old == key_mtx_dereference(sdata->local, sdata->default_mgmt_key); + defbeaconkey = old && + old == key_mtx_dereference(sdata->local, + sdata->default_beacon_key); if (defunikey && !new) __ieee80211_set_default_key(sdata, -1, true, false); @@ -472,6 +515,8 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, __ieee80211_set_default_key(sdata, -1, false, true); if (defmgmtkey && !new) __ieee80211_set_default_mgmt_key(sdata, -1); + if (defbeaconkey && !new) + __ieee80211_set_default_beacon_key(sdata, -1); rcu_assign_pointer(sdata->keys[idx], new); if (defunikey && new) @@ -483,6 +528,9 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, if (defmgmtkey && new) __ieee80211_set_default_mgmt_key(sdata, new->conf.keyidx); + if (defbeaconkey && new) + __ieee80211_set_default_beacon_key(sdata, + new->conf.keyidx); } if (old) @@ -500,7 +548,9 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, struct ieee80211_key *key; int i, j, err; - if (WARN_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS)) + if (WARN_ON(idx < 0 || + idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS)) return ERR_PTR(-EINVAL); key = kzalloc(sizeof(struct ieee80211_key) + key_len, GFP_KERNEL); @@ -963,6 +1013,7 @@ static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata, sdata->crypto_tx_tailroom_pending_dec = 0; ieee80211_debugfs_key_remove_mgmt_default(sdata); + ieee80211_debugfs_key_remove_beacon_default(sdata); list_for_each_entry_safe(key, tmp, &sdata->key_list, list) { ieee80211_key_replace(key->sdata, key->sta, diff --git a/net/mac80211/key.h b/net/mac80211/key.h index d6d6e89cf7dd..7ad72e9b4991 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -17,6 +17,7 @@ #define NUM_DEFAULT_KEYS 4 #define NUM_DEFAULT_MGMT_KEYS 2 +#define NUM_DEFAULT_BEACON_KEYS 2 #define INVALID_PTK_KEYIDX 2 /* Keyidx always pointing to a NULL key for PTK */ struct ieee80211_local; @@ -153,6 +154,8 @@ void ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, int idx, bool uni, bool multi); void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata, int idx); +void ieee80211_set_default_beacon_key(struct ieee80211_sub_if_data *sdata, + int idx); void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, bool force_synchronize); void ieee80211_free_sta_keys(struct ieee80211_local *local, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4c2b5ba3ac09..944e86da5c65 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -146,6 +146,8 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local) continue; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) continue; + if (sdata->vif.bss_conf.txpower == INT_MIN) + continue; power = min(power, sdata->vif.bss_conf.txpower); } rcu_read_unlock(); @@ -416,7 +418,20 @@ ieee80211_default_mgmt_stypes[NUM_NL80211_IFTYPES] = { }, [NL80211_IFTYPE_STATION] = { .tx = 0xffff, + /* + * To support Pre Association Security Negotiation (PASN) while + * already associated to one AP, allow user space to register to + * Rx authentication frames, so that the user space logic would + * be able to receive/handle authentication frames from a + * different AP as part of PASN. + * It is expected that user space would intelligently register + * for Rx authentication frames, i.e., only when PASN is used + * and configure a match filter only for PASN authentication + * algorithm, as otherwise the MLME functionality of mac80211 + * would be broken. + */ .rx = BIT(IEEE80211_STYPE_ACTION >> 4) | + BIT(IEEE80211_STYPE_AUTH >> 4) | BIT(IEEE80211_STYPE_PROBE_REQ >> 4), }, [NL80211_IFTYPE_AP] = { @@ -872,7 +887,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) enum nl80211_band band; int channels, max_bitrates; bool supp_ht, supp_vht, supp_he; - netdev_features_t feature_whitelist; struct cfg80211_chan_def dflt_chandef = {}; if (ieee80211_hw_check(hw, QUEUE_CONTROL) && @@ -931,10 +945,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } /* Only HW csum features are currently compatible with mac80211 */ - feature_whitelist = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | - NETIF_F_GSO_SOFTWARE | NETIF_F_RXCSUM; - if (WARN_ON(hw->netdev_features & ~feature_whitelist)) + if (WARN_ON(hw->netdev_features & ~MAC80211_SUPPORTED_FEATURES)) return -EINVAL; if (hw->max_report_rates == 0) @@ -981,6 +992,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (!supp_he) supp_he = !!ieee80211_get_he_sta_cap(sband); + /* HT, VHT, HE require QoS, thus >= 4 queues */ + if (WARN_ON(local->hw.queues < IEEE80211_NUM_ACS && + (supp_ht || supp_vht || supp_he))) + return -EINVAL; + if (!sband->ht_cap.ht_supported) continue; @@ -1184,10 +1200,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (!local->hw.weight_multiplier) local->hw.weight_multiplier = 1; - result = ieee80211_wep_init(local); - if (result < 0) - wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n", - result); + ieee80211_wep_init(local); local->hw.conf.flags = IEEE80211_CONF_IDLE; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 88d7a692a965..8a2f2fa21916 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -164,7 +164,9 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, chandef->center_freq1 = channel->center_freq; if (!ht_oper || !sta_ht_cap.ht_supported) { - ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; + ret = IEEE80211_STA_DISABLE_HT | + IEEE80211_STA_DISABLE_VHT | + IEEE80211_STA_DISABLE_HE; goto out; } @@ -185,7 +187,9 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n", channel->center_freq, ht_cfreq, ht_oper->primary_chan, channel->band); - ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; + ret = IEEE80211_STA_DISABLE_HT | + IEEE80211_STA_DISABLE_VHT | + IEEE80211_STA_DISABLE_HE; goto out; } @@ -301,13 +305,18 @@ out: IEEE80211_CHAN_DISABLED)) { if (WARN_ON(chandef->width == NL80211_CHAN_WIDTH_20_NOHT)) { ret = IEEE80211_STA_DISABLE_HT | - IEEE80211_STA_DISABLE_VHT; + IEEE80211_STA_DISABLE_VHT | + IEEE80211_STA_DISABLE_HE; break; } ret |= ieee80211_chandef_downgrade(chandef); } + if (!he_oper || !cfg80211_chandef_usable(sdata->wdev.wiphy, chandef, + IEEE80211_CHAN_NO_HE)) + ret |= IEEE80211_STA_DISABLE_HE; + if (chandef->width != vht_chandef.width && !tracking) sdata_info(sdata, "capabilities/regulatory prevented using AP HT/VHT configuration, downgraded\n"); @@ -393,6 +402,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, if (flags != (ifmgd->flags & (IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT | + IEEE80211_STA_DISABLE_HE | IEEE80211_STA_DISABLE_40MHZ | IEEE80211_STA_DISABLE_80P80MHZ | IEEE80211_STA_DISABLE_160MHZ)) || @@ -616,10 +626,21 @@ static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata, { u8 *pos; const struct ieee80211_sta_he_cap *he_cap = NULL; + struct ieee80211_chanctx_conf *chanctx_conf; u8 he_cap_size; + bool reg_cap = false; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!WARN_ON_ONCE(!chanctx_conf)) + reg_cap = cfg80211_chandef_usable(sdata->wdev.wiphy, + &chanctx_conf->def, + IEEE80211_CHAN_NO_HE); + + rcu_read_unlock(); he_cap = ieee80211_get_he_sta_cap(sband); - if (!he_cap) + if (!he_cap || !reg_cap) return; /* @@ -650,6 +671,13 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_channel *chan; u32 rates = 0; + struct element *ext_capa = NULL; + + /* we know it's writable, cast away the const */ + if (assoc_data->ie_len) + ext_capa = (void *)cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, + assoc_data->ie, + assoc_data->ie_len); sdata_assert_lock(sdata); @@ -800,7 +828,15 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) *pos++ = ieee80211_chandef_max_power(&chanctx_conf->def); } - if (capab & WLAN_CAPABILITY_SPECTRUM_MGMT) { + /* + * Per spec, we shouldn't include the list of channels if we advertise + * support for extended channel switching, but we've always done that; + * (for now?) apply this restriction only on the (new) 6 GHz band. + */ + if (capab & WLAN_CAPABILITY_SPECTRUM_MGMT && + (sband->band != NL80211_BAND_6GHZ || + !ext_capa || ext_capa->datalen < 1 || + !(ext_capa->data[0] & WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING))) { /* TODO: get this in reg domain format */ pos = skb_put(skb, 2 * sband->n_channels + 2); *pos++ = WLAN_EID_SUPPORTED_CHANNELS; @@ -814,18 +850,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) /* Set MBSSID support for HE AP if needed */ if (ieee80211_hw_check(&local->hw, SUPPORTS_ONLY_HE_MULTI_BSSID) && - !(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && assoc_data->ie_len) { - struct element *elem; - - /* we know it's writable, cast away the const */ - elem = (void *)cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, - assoc_data->ie, - assoc_data->ie_len); - - /* We can probably assume both always true */ - if (elem && elem->datalen >= 3) - elem->data[2] |= WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT; - } + !(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && assoc_data->ie_len && + ext_capa && ext_capa->datalen >= 3) + ext_capa->data[2] |= WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT; /* if present, add any custom IEs that go before HT */ if (assoc_data->ie_len) { @@ -2460,7 +2487,7 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, if (!ieee80211_is_data(hdr->frame_control)) return; - if (ieee80211_is_nullfunc(hdr->frame_control) && + if (ieee80211_is_any_nullfunc(hdr->frame_control) && sdata->u.mgd.probe_send_count > 0) { if (ack) ieee80211_sta_reset_conn_monitor(sdata); @@ -3364,9 +3391,16 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, } if (bss_conf->he_support) { - bss_conf->bss_color = + bss_conf->he_bss_color.color = le32_get_bits(elems->he_operation->he_oper_params, IEEE80211_HE_OPERATION_BSS_COLOR_MASK); + bss_conf->he_bss_color.partial = + le32_get_bits(elems->he_operation->he_oper_params, + IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR); + bss_conf->he_bss_color.disabled = + le32_get_bits(elems->he_operation->he_oper_params, + IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED); + changed |= BSS_CHANGED_HE_BSS_COLOR; bss_conf->htc_trig_based_pkt_ext = le32_get_bits(elems->he_operation->he_oper_params, @@ -3645,13 +3679,28 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_if_managed *ifmgd; struct ieee80211_rx_status *rx_status = (void *) skb->cb; + struct ieee80211_channel *channel; size_t baselen, len = skb->len; ifmgd = &sdata->u.mgd; sdata_assert_lock(sdata); - if (!ether_addr_equal(mgmt->da, sdata->vif.addr)) + /* + * According to Draft P802.11ax D6.0 clause 26.17.2.3.2: + * "If a 6 GHz AP receives a Probe Request frame and responds with + * a Probe Response frame [..], the Address 1 field of the Probe + * Response frame shall be set to the broadcast address [..]" + * So, on 6GHz band we should also accept broadcast responses. + */ + channel = ieee80211_get_channel(sdata->local->hw.wiphy, + rx_status->freq); + if (!channel) + return; + + if (!ether_addr_equal(mgmt->da, sdata->vif.addr) && + (channel->band != NL80211_BAND_6GHZ || + !is_broadcast_ether_addr(mgmt->da))) return; /* ignore ProbeResp to foreign address */ baselen = (u8 *) mgmt->u.probe_resp.variable - (u8 *) mgmt; @@ -4749,10 +4798,22 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, IEEE80211_STA_DISABLE_80P80MHZ | IEEE80211_STA_DISABLE_160MHZ); + /* disable HT/VHT/HE if we don't support them */ + if (!sband->ht_cap.ht_supported) { + ifmgd->flags |= IEEE80211_STA_DISABLE_HT; + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + } + + if (!sband->vht_cap.vht_supported) + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + + if (!ieee80211_get_he_sta_cap(sband)) + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + rcu_read_lock(); - if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT) && - sband->ht_cap.ht_supported) { + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) { const u8 *ht_oper_ie, *ht_cap_ie; ht_oper_ie = ieee80211_bss_get_ie(cbss, WLAN_EID_HT_OPERATION); @@ -4769,8 +4830,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } } - if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT) && - sband->vht_cap.vht_supported) { + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) { const u8 *vht_oper_ie, *vht_cap; vht_oper_ie = ieee80211_bss_get_ie(cbss, @@ -4780,9 +4840,10 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, if (vht_oper && !ht_oper) { vht_oper = NULL; sdata_info(sdata, - "AP advertised VHT without HT, disabling both\n"); + "AP advertised VHT without HT, disabling HT/VHT/HE\n"); ifmgd->flags |= IEEE80211_STA_DISABLE_HT; ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } vht_cap = ieee80211_bss_get_ie(cbss, WLAN_EID_VHT_CAPABILITY); @@ -4792,9 +4853,6 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } } - if (!ieee80211_get_he_sta_cap(sband)) - ifmgd->flags |= IEEE80211_STA_DISABLE_HE; - if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) { const struct cfg80211_bss_ies *ies; const u8 *he_oper_ie; @@ -5293,27 +5351,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, } } - /* Also disable HT if we don't support it or the AP doesn't use WMM */ sband = local->hw.wiphy->bands[req->bss->channel->band]; - if (!sband->ht_cap.ht_supported || - local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used || - ifmgd->flags & IEEE80211_STA_DISABLE_WMM) { - ifmgd->flags |= IEEE80211_STA_DISABLE_HT; - if (!bss->wmm_used && - !(ifmgd->flags & IEEE80211_STA_DISABLE_WMM)) - netdev_info(sdata->dev, - "disabling HT as WMM/QoS is not supported by the AP\n"); - } - /* disable VHT if we don't support it or the AP doesn't use WMM */ - if (!sband->vht_cap.vht_supported || - local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used || - ifmgd->flags & IEEE80211_STA_DISABLE_WMM) { + /* also disable HT/VHT/HE if the AP doesn't use WMM */ + if (!bss->wmm_used) { + ifmgd->flags |= IEEE80211_STA_DISABLE_HT; ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; - if (!bss->wmm_used && - !(ifmgd->flags & IEEE80211_STA_DISABLE_WMM)) - netdev_info(sdata->dev, - "disabling VHT as WMM/QoS is not supported by the AP\n"); + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + netdev_info(sdata->dev, + "disabling HT/VHT/HE as WMM/QoS is not supported by the AP\n"); } memcpy(&ifmgd->ht_capa, &req->ht_capa, sizeof(ifmgd->ht_capa)); @@ -5445,6 +5491,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (req->flags & ASSOC_REQ_DISABLE_HT) { ifmgd->flags |= IEEE80211_STA_DISABLE_HT; ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } if (req->flags & ASSOC_REQ_DISABLE_VHT) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0ba98ad9bc85..2ffb4ee467e1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -6,7 +6,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #include <linux/jiffies.h> @@ -983,7 +983,8 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) if (skb->len < 24 + sizeof(*mmie) || !is_multicast_ether_addr(hdr->da)) return -1; - if (!ieee80211_is_robust_mgmt_frame(skb)) + if (!ieee80211_is_robust_mgmt_frame(skb) && + !ieee80211_is_beacon(hdr->frame_control)) return -1; /* not a robust management frame */ mmie = (struct ieee80211_mmie *) @@ -1450,8 +1451,7 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx) return RX_CONTINUE; if (ieee80211_is_ctl(hdr->frame_control) || - ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control) || + ieee80211_is_any_nullfunc(hdr->frame_control) || is_multicast_ether_addr(hdr->addr1)) return RX_CONTINUE; @@ -1838,8 +1838,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) * Drop (qos-)data::nullfunc frames silently, since they * are used only to control station power saving mode. */ - if (ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control)) { + if (ieee80211_is_any_nullfunc(hdr->frame_control)) { I802_DEBUG_INC(rx->local->rx_handlers_drop_nullfunc); /* @@ -1870,6 +1869,41 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) return RX_CONTINUE; } /* ieee80211_rx_h_sta_process */ +static struct ieee80211_key * +ieee80211_rx_get_bigtk(struct ieee80211_rx_data *rx, int idx) +{ + struct ieee80211_key *key = NULL; + struct ieee80211_sub_if_data *sdata = rx->sdata; + int idx2; + + /* Make sure key gets set if either BIGTK key index is set so that + * ieee80211_drop_unencrypted_mgmt() can properly drop both unprotected + * Beacon frames and Beacon frames that claim to use another BIGTK key + * index (i.e., a key that we do not have). + */ + + if (idx < 0) { + idx = NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS; + idx2 = idx + 1; + } else { + if (idx == NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) + idx2 = idx + 1; + else + idx2 = idx - 1; + } + + if (rx->sta) + key = rcu_dereference(rx->sta->gtk[idx]); + if (!key) + key = rcu_dereference(sdata->keys[idx]); + if (!key && rx->sta) + key = rcu_dereference(rx->sta->gtk[idx2]); + if (!key) + key = rcu_dereference(sdata->keys[idx2]); + + return key; +} + static ieee80211_rx_result debug_noinline ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) { @@ -1887,17 +1921,18 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) /* * Key selection 101 * - * There are four types of keys: + * There are five types of keys: * - GTK (group keys) * - IGTK (group keys for management frames) + * - BIGTK (group keys for Beacon frames) * - PTK (pairwise keys) * - STK (station-to-station pairwise keys) * * When selecting a key, we have to distinguish between multicast * (including broadcast) and unicast frames, the latter can only - * use PTKs and STKs while the former always use GTKs and IGTKs. - * Unless, of course, actual WEP keys ("pre-RSNA") are used, then - * unicast frames can also use key indices like GTKs. Hence, if we + * use PTKs and STKs while the former always use GTKs, IGTKs, and + * BIGTKs. Unless, of course, actual WEP keys ("pre-RSNA") are used, + * then unicast frames can also use key indices like GTKs. Hence, if we * don't have a PTK/STK we check the key index for a WEP key. * * Note that in a regular BSS, multicast frames are sent by the @@ -1941,6 +1976,20 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) /* Skip decryption if the frame is not protected. */ if (!ieee80211_has_protected(fc)) return RX_CONTINUE; + } else if (mmie_keyidx >= 0 && ieee80211_is_beacon(fc)) { + /* Broadcast/multicast robust management frame / BIP */ + if ((status->flag & RX_FLAG_DECRYPTED) && + (status->flag & RX_FLAG_IV_STRIPPED)) + return RX_CONTINUE; + + if (mmie_keyidx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS || + mmie_keyidx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) + return RX_DROP_MONITOR; /* unexpected BIP keyidx */ + + rx->key = ieee80211_rx_get_bigtk(rx, mmie_keyidx); + if (!rx->key) + return RX_CONTINUE; /* Beacon protection not in use */ } else if (mmie_keyidx >= 0) { /* Broadcast/multicast robust management frame / BIP */ if ((status->flag & RX_FLAG_DECRYPTED) && @@ -1970,11 +2019,12 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) struct ieee80211_sub_if_data *sdata = rx->sdata; int i; - if (ieee80211_is_mgmt(fc) && - is_multicast_ether_addr(hdr->addr1) && - (key = rcu_dereference(rx->sdata->default_mgmt_key))) - rx->key = key; - else { + if (ieee80211_is_beacon(fc)) { + key = ieee80211_rx_get_bigtk(rx, -1); + } else if (ieee80211_is_mgmt(fc) && + is_multicast_ether_addr(hdr->addr1)) { + key = rcu_dereference(rx->sdata->default_mgmt_key); + } else { if (rx->sta) { for (i = 0; i < NUM_DEFAULT_KEYS; i++) { key = rcu_dereference(rx->sta->gtk[i]); @@ -1989,9 +2039,9 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) break; } } - if (key) - rx->key = key; } + if (key) + rx->key = key; return RX_CONTINUE; } else { /* @@ -2319,7 +2369,7 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) /* Drop unencrypted frames if key is set. */ if (unlikely(!ieee80211_has_protected(fc) && - !ieee80211_is_nullfunc(fc) && + !ieee80211_is_any_nullfunc(fc) && ieee80211_is_data(fc) && rx->key)) return -EACCES; @@ -2360,6 +2410,9 @@ static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) rx->skb->len); return -EACCES; } + if (unlikely(ieee80211_is_beacon(fc) && rx->key && + ieee80211_get_mmie_keyidx(rx->skb) < 0)) + return -EACCES; /* * When using MFP, Action frames are not allowed prior to * having configured keys. @@ -3084,6 +3137,10 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) enum ieee80211_smps_mode smps_mode; struct sta_opmode_info sta_opmode = {}; + if (sdata->vif.type != NL80211_IFTYPE_AP && + sdata->vif.type != NL80211_IFTYPE_AP_VLAN) + goto handled; + /* convert to HT capability */ switch (mgmt->u.action.u.ht_smps.smps_control) { case WLAN_HT_SMPS_CONTROL_DISABLED: diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 4d31d9688dc2..fdac8192a519 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -201,8 +201,7 @@ ieee80211_bss_info_update(struct ieee80211_local *local, mgmt->bssid, cbss->bssid); /* In case the signal is invalid update the status */ - signal_valid = abs(channel->center_freq - cbss->channel->center_freq) - <= local->hw.wiphy->max_adj_channel_rssi_comp; + signal_valid = channel == cbss->channel; if (!signal_valid) rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 0f5f40678885..f357156b86ee 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -4,7 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #include <linux/module.h> @@ -1351,20 +1351,6 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) atomic_dec(&ps->num_sta_ps); - /* This station just woke up and isn't aware of our SMPS state */ - if (!ieee80211_vif_is_mesh(&sdata->vif) && - !ieee80211_smps_is_restrictive(sta->known_smps_mode, - sdata->smps_mode) && - sta->known_smps_mode != sdata->bss->req_smps && - sta_info_tx_streams(sta) != 1) { - ht_dbg(sdata, - "%pM just woke up and MIMO capable - update SMPS\n", - sta->sta.addr); - ieee80211_send_smps_action(sdata, sdata->bss->req_smps, - sta->sta.addr, - sdata->vif.bss_conf.bssid); - } - local->total_ps_buffered -= buffered; sta_info_recalc_tim(sta); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index c00e28585f9d..364a35414d05 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -533,7 +533,9 @@ struct sta_info { u8 addr[ETH_ALEN]; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; - struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; + struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS]; struct ieee80211_key __rcu *ptk[NUM_DEFAULT_KEYS]; u8 ptk_idx; struct rate_control_ref *rate_ctrl; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index b720feaf9a74..22512805eafb 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -643,8 +643,7 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, rcu_read_lock(); sdata = ieee80211_sdata_from_skb(local, skb); if (sdata) { - if (ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control)) + if (ieee80211_is_any_nullfunc(hdr->frame_control)) cfg80211_probe_status(sdata->dev, hdr->addr1, cookie, acked, info->status.ack_signal, @@ -888,6 +887,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, int rates_idx; bool send_to_cooked; bool acked; + bool noack_success; struct ieee80211_bar *bar; int shift = 0; int tid = IEEE80211_NUM_TIDS; @@ -906,6 +906,8 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, clear_sta_flag(sta, WLAN_STA_SP); acked = !!(info->flags & IEEE80211_TX_STAT_ACK); + noack_success = !!(info->flags & + IEEE80211_TX_STAT_NOACK_TRANSMITTED); /* mesh Peer Service Period support */ if (ieee80211_vif_is_mesh(&sta->sdata->vif) && @@ -970,12 +972,12 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, ieee80211_handle_filtered_frame(local, sta, skb); return; } else { - if (!acked) + if (!acked && !noack_success) sta->status_stats.retry_failed++; sta->status_stats.retry_count += retry_count; if (ieee80211_is_data_present(fc)) { - if (!acked) + if (!acked && !noack_success) sta->status_stats.msdu_failed[tid]++; sta->status_stats.msdu_retries[tid] += @@ -1013,7 +1015,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, } if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { - if (info->flags & IEEE80211_TX_STAT_ACK) { + if (acked) { if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; @@ -1021,6 +1023,8 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) sta->status_stats.last_tdls_pkt_time = jiffies; + } else if (noack_success) { + /* nothing to do here, do not account as lost */ } else { ieee80211_lost_packet(sta, info); } @@ -1056,7 +1060,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, I802_DEBUG_INC(local->dot11FailedCount); } - if ((ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)) && + if (ieee80211_is_any_nullfunc(fc) && ieee80211_has_pm(fc) && ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) && !(info->flags & IEEE80211_TX_CTL_INJECTED) && @@ -1141,7 +1145,7 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, sta = container_of(pubsta, struct sta_info, sta); - if (!acked) + if (!acked && !noack_success) sta->status_stats.retry_failed++; sta->status_stats.retry_count += retry_count; @@ -1156,6 +1160,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, sta->status_stats.last_tdls_pkt_time = jiffies; } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { return; + } else if (noack_success) { + /* nothing to do here, do not account as lost */ } else { ieee80211_lost_packet(sta, info); } @@ -1198,6 +1204,77 @@ void ieee80211_tx_rate_update(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_tx_rate_update); +void ieee80211_tx_status_8023(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct sk_buff *skb) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_sub_if_data *sdata; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct sta_info *sta; + int retry_count; + int rates_idx; + bool acked; + + sdata = vif_to_sdata(vif); + + acked = info->flags & IEEE80211_TX_STAT_ACK; + rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count); + + rcu_read_lock(); + + if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) + goto counters_update; + + if (IS_ERR(sta)) + goto counters_update; + + if (!acked) + sta->status_stats.retry_failed++; + + if (rates_idx != -1) + sta->tx_stats.last_rate = info->status.rates[rates_idx]; + + sta->status_stats.retry_count += retry_count; + + if (ieee80211_hw_check(hw, REPORTS_TX_ACK_STATUS)) { + if (acked && vif->type == NL80211_IFTYPE_STATION) + ieee80211_sta_reset_conn_monitor(sdata); + + sta->status_stats.last_ack = jiffies; + if (info->flags & IEEE80211_TX_STAT_ACK) { + if (sta->status_stats.lost_packets) + sta->status_stats.lost_packets = 0; + + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) + sta->status_stats.last_tdls_pkt_time = jiffies; + } else { + ieee80211_lost_packet(sta, info); + } + } + +counters_update: + rcu_read_unlock(); + ieee80211_led_tx(local); + + if (!(info->flags & IEEE80211_TX_STAT_ACK) && + !(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED)) + goto skip_stats_update; + + I802_DEBUG_INC(local->dot11TransmittedFrameCount); + if (is_multicast_ether_addr(skb->data)) + I802_DEBUG_INC(local->dot11MulticastTransmittedFrameCount); + if (retry_count > 0) + I802_DEBUG_INC(local->dot11RetryCount); + if (retry_count > 1) + I802_DEBUG_INC(local->dot11MultipleRetryCount); + +skip_stats_update: + ieee80211_report_used_skb(local, skb, false); + dev_kfree_skb(skb); +} +EXPORT_SYMBOL(ieee80211_tx_status_8023); + void ieee80211_report_low_ack(struct ieee80211_sta *pubsta, u32 num_packets) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 87def9cb91ff..83147385c200 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation * * Transmit and frame generation functions. */ @@ -297,7 +297,7 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) if (unlikely(test_bit(SCAN_SW_SCANNING, &tx->local->scanning)) && test_bit(SDATA_STATE_OFFCHANNEL, &tx->sdata->state) && !ieee80211_is_probe_req(hdr->frame_control) && - !ieee80211_is_nullfunc(hdr->frame_control)) + !ieee80211_is_any_nullfunc(hdr->frame_control)) /* * When software scanning only nullfunc frames (to notify * the sleep state to the AP) and probe requests (for the @@ -1250,7 +1250,8 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)) return NULL; - if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) { + if (!(info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) && + unlikely(!ieee80211_is_data_present(hdr->frame_control))) { if ((!ieee80211_is_mgmt(hdr->frame_control) || ieee80211_is_bufferable_mmpdu(hdr->frame_control) || vif->type == NL80211_IFTYPE_STATION) && @@ -2360,9 +2361,9 @@ static inline bool ieee80211_is_tdls_setup(struct sk_buff *skb) skb->data[14] == WLAN_TDLS_SNAP_RFTYPE; } -static int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, - struct sta_info **sta_out) +int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + struct sta_info **sta_out) { struct sta_info *sta; @@ -3616,6 +3617,9 @@ begin: else info->flags &= ~IEEE80211_TX_CTL_AMPDU; + if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) + goto encap_out; + if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) { struct sta_info *sta = container_of(txq->sta, struct sta_info, sta); @@ -3675,9 +3679,11 @@ begin: break; } +encap_out: IEEE80211_SKB_CB(skb)->control.vif = vif; - if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { + if (vif && + wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { u32 airtime; airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta, @@ -4103,6 +4109,153 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } +static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, int led_len, + struct sta_info *sta, + bool txpending) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_tx_control control = {}; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_sta *pubsta = NULL; + unsigned long flags; + int q = info->hw_queue; + + if (ieee80211_queue_skb(local, sdata, sta, skb)) + return true; + + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + + if (local->queue_stop_reasons[q] || + (!txpending && !skb_queue_empty(&local->pending[q]))) { + if (txpending) + skb_queue_head(&local->pending[q], skb); + else + skb_queue_tail(&local->pending[q], skb); + + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + + return false; + } + + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + + if (sta && sta->uploaded) + pubsta = &sta->sta; + + control.sta = pubsta; + + drv_tx(local, &control, skb); + + return true; +} + +static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, + struct net_device *dev, struct sta_info *sta, + struct sk_buff *skb) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ethhdr *ehdr = (struct ethhdr *)skb->data; + struct ieee80211_local *local = sdata->local; + bool authorized = false; + bool multicast; + unsigned char *ra = ehdr->h_dest; + + if (IS_ERR(sta) || (sta && !sta->uploaded)) + sta = NULL; + + if (sdata->vif.type == NL80211_IFTYPE_STATION && + (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER))) + ra = sdata->u.mgd.bssid; + + if (!is_valid_ether_addr(ra)) + goto out_free; + + multicast = is_multicast_ether_addr(ra); + + if (sta) + authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); + + if (!multicast && !authorized && + (ehdr->h_proto != sdata->control_port_protocol || + !ether_addr_equal(sdata->vif.addr, ehdr->h_source))) + goto out_free; + + if (multicast && sdata->vif.type == NL80211_IFTYPE_AP && + !atomic_read(&sdata->u.ap.num_mcast_sta)) + goto out_free; + + if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning)) && + test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) + goto out_free; + + if (unlikely(!multicast && skb->sk && + skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) + ieee80211_store_ack_skb(local, skb, &info->flags); + + memset(info, 0, sizeof(*info)); + + if (unlikely(sdata->control_port_protocol == ehdr->h_proto)) { + if (sdata->control_port_no_encrypt) + info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; + info->control.flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + } + + if (multicast) + info->flags |= IEEE80211_TX_CTL_NO_ACK; + + info->hw_queue = sdata->vif.hw_queue[skb_get_queue_mapping(skb)]; + + ieee80211_tx_stats(dev, skb->len); + + if (sta) { + sta->tx_stats.bytes[skb_get_queue_mapping(skb)] += skb->len; + sta->tx_stats.packets[skb_get_queue_mapping(skb)]++; + } + + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + sdata = container_of(sdata->bss, + struct ieee80211_sub_if_data, u.ap); + + info->control.flags |= IEEE80211_TX_CTRL_HW_80211_ENCAP; + info->control.vif = &sdata->vif; + + ieee80211_tx_8023(sdata, skb, skb->len, sta, false); + + return; + +out_free: + kfree_skb(skb); +} + +netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb, + struct net_device *dev) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct sta_info *sta; + + if (WARN_ON(!sdata->hw_80211_encap)) { + kfree_skb(skb); + return NETDEV_TX_OK; + } + + if (unlikely(skb->len < ETH_HLEN)) { + kfree_skb(skb); + return NETDEV_TX_OK; + } + + rcu_read_lock(); + + if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) + kfree_skb(skb); + else + ieee80211_8023_xmit(sdata, dev, sta, skb); + + rcu_read_unlock(); + + return NETDEV_TX_OK; +} + struct sk_buff * ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 info_flags) @@ -4181,6 +4334,16 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, } info->band = chanctx_conf->def.chan->band; result = ieee80211_tx(sdata, NULL, skb, true, 0); + } else if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) { + if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) { + dev_kfree_skb(skb); + return true; + } + + if (IS_ERR(sta) || (sta && !sta->uploaded)) + sta = NULL; + + result = ieee80211_tx_8023(sdata, skb, skb->len, sta, true); } else { struct sk_buff_head skbs; @@ -4501,6 +4664,28 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) } EXPORT_SYMBOL(ieee80211_csa_is_complete); +static int ieee80211_beacon_protect(struct sk_buff *skb, + struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + ieee80211_tx_result res; + struct ieee80211_tx_data tx; + + memset(&tx, 0, sizeof(tx)); + tx.key = rcu_dereference(sdata->default_beacon_key); + if (!tx.key) + return 0; + tx.local = local; + tx.sdata = sdata; + __skb_queue_head_init(&tx.skbs); + __skb_queue_tail(&tx.skbs, skb); + res = ieee80211_tx_h_encrypt(&tx); + if (WARN_ON_ONCE(res != TX_CONTINUE)) + return -1; + + return 0; +} + static struct sk_buff * __ieee80211_beacon_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -4568,6 +4753,9 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (beacon->tail) skb_put_data(skb, beacon->tail, beacon->tail_len); + + if (ieee80211_beacon_protect(skb, local, sdata) < 0) + goto out; } else goto out; } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { diff --git a/net/mac80211/util.c b/net/mac80211/util.c index decd46b38393..ea7d277a8c45 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -6,7 +6,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation * * utilities for mac80211 */ @@ -39,7 +39,6 @@ const void *const mac80211_wiphy_privid = &mac80211_wiphy_privid; struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy) { struct ieee80211_local *local; - BUG_ON(!wiphy); local = wiphy_priv(wiphy); return &local->hw; @@ -891,6 +890,51 @@ void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_queue_delayed_work); +static void ieee80211_parse_extension_element(u32 *crc, + const struct element *elem, + struct ieee802_11_elems *elems) +{ + const void *data = elem->data + 1; + u8 len = elem->datalen - 1; + + switch (elem->data[0]) { + case WLAN_EID_EXT_HE_MU_EDCA: + if (len == sizeof(*elems->mu_edca_param_set)) { + elems->mu_edca_param_set = data; + if (crc) + *crc = crc32_be(*crc, (void *)elem, + elem->datalen + 2); + } + break; + case WLAN_EID_EXT_HE_CAPABILITY: + elems->he_cap = data; + elems->he_cap_len = len; + break; + case WLAN_EID_EXT_HE_OPERATION: + if (len >= sizeof(*elems->he_operation) && + len == ieee80211_he_oper_size(data) - 1) + elems->he_operation = data; + break; + case WLAN_EID_EXT_UORA: + if (len == 1) + elems->uora_element = data; + break; + case WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME: + if (len == 3) + elems->max_channel_switch_time = data; + break; + case WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION: + if (len == sizeof(*elems->mbssid_config_ie)) + elems->mbssid_config_ie = data; + break; + case WLAN_EID_EXT_HE_SPR: + if (len >= sizeof(*elems->he_spr) && + len >= ieee80211_he_spr_size(data)) + elems->he_spr = data; + break; + } +} + static u32 _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, struct ieee802_11_elems *elems, @@ -950,6 +994,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, case WLAN_EID_CHAN_SWITCH_TIMING: case WLAN_EID_LINK_ID: case WLAN_EID_BSS_MAX_IDLE_PERIOD: + case WLAN_EID_RSNX: /* * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible * that if the content gets bigger it might be needed more than once @@ -1226,34 +1271,14 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, if (elen >= sizeof(*elems->max_idle_period_ie)) elems->max_idle_period_ie = (void *)pos; break; + case WLAN_EID_RSNX: + elems->rsnx = pos; + elems->rsnx_len = elen; + break; case WLAN_EID_EXTENSION: - if (pos[0] == WLAN_EID_EXT_HE_MU_EDCA && - elen >= (sizeof(*elems->mu_edca_param_set) + 1)) { - elems->mu_edca_param_set = (void *)&pos[1]; - if (calc_crc) - crc = crc32_be(crc, pos - 2, elen + 2); - } else if (pos[0] == WLAN_EID_EXT_HE_CAPABILITY) { - elems->he_cap = (void *)&pos[1]; - elems->he_cap_len = elen - 1; - } else if (pos[0] == WLAN_EID_EXT_HE_OPERATION && - elen >= sizeof(*elems->he_operation) && - elen >= ieee80211_he_oper_size(&pos[1])) { - elems->he_operation = (void *)&pos[1]; - } else if (pos[0] == WLAN_EID_EXT_UORA && elen >= 1) { - elems->uora_element = (void *)&pos[1]; - } else if (pos[0] == - WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME && - elen == 4) { - elems->max_channel_switch_time = pos + 1; - } else if (pos[0] == - WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION && - elen == 3) { - elems->mbssid_config_ie = (void *)&pos[1]; - } else if (pos[0] == WLAN_EID_EXT_HE_SPR && - elen >= sizeof(*elems->he_spr) && - elen >= ieee80211_he_spr_size(&pos[1])) { - elems->he_spr = (void *)&pos[1]; - } + ieee80211_parse_extension_element(calc_crc ? + &crc : NULL, + elem, elems); break; default: break; diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index ccdcb9ad9ac7..632f07401850 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -333,11 +333,33 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, } } +/* FIXME: move this to some better location - parses HE now */ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct sta_info *sta) { struct ieee80211_sta_vht_cap *vht_cap = &sta->sta.vht_cap; + struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap; u32 cap_width; + if (he_cap->has_he) { + u8 info = he_cap->he_cap_elem.phy_cap_info[0]; + + if (sta->sdata->vif.bss_conf.chandef.chan->band == + NL80211_BAND_2GHZ) { + if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) + return IEEE80211_STA_RX_BW_40; + else + return IEEE80211_STA_RX_BW_20; + } + + if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G || + info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) + return IEEE80211_STA_RX_BW_160; + else if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) + return IEEE80211_STA_RX_BW_80; + + return IEEE80211_STA_RX_BW_20; + } + if (!vht_cap->vht_supported) return sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? IEEE80211_STA_RX_BW_40 : @@ -433,6 +455,7 @@ ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width) } } +/* FIXME: rename/move - this deals with everything not just VHT */ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; @@ -458,12 +481,40 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) void ieee80211_sta_set_rx_nss(struct sta_info *sta) { - u8 ht_rx_nss = 0, vht_rx_nss = 0; + u8 ht_rx_nss = 0, vht_rx_nss = 0, he_rx_nss = 0, rx_nss; /* if we received a notification already don't overwrite it */ if (sta->sta.rx_nss) return; + if (sta->sta.he_cap.has_he) { + int i; + u8 rx_mcs_80 = 0, rx_mcs_160 = 0; + const struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap; + u16 mcs_160_map = + le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_160); + u16 mcs_80_map = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_80); + + for (i = 7; i >= 0; i--) { + u8 mcs_160 = (mcs_160_map >> (2 * i)) & 3; + + if (mcs_160 != IEEE80211_VHT_MCS_NOT_SUPPORTED) { + rx_mcs_160 = i + 1; + break; + } + } + for (i = 7; i >= 0; i--) { + u8 mcs_80 = (mcs_80_map >> (2 * i)) & 3; + + if (mcs_80 != IEEE80211_VHT_MCS_NOT_SUPPORTED) { + rx_mcs_80 = i + 1; + break; + } + } + + he_rx_nss = min(rx_mcs_80, rx_mcs_160); + } + if (sta->sta.ht_cap.ht_supported) { if (sta->sta.ht_cap.mcs.rx_mask[0]) ht_rx_nss++; @@ -493,8 +544,9 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta) /* FIXME: consider rx_highest? */ } - ht_rx_nss = max(ht_rx_nss, vht_rx_nss); - sta->sta.rx_nss = max_t(u8, 1, ht_rx_nss); + rx_nss = max(vht_rx_nss, ht_rx_nss); + rx_nss = max(he_rx_nss, rx_nss); + sta->sta.rx_nss = max_t(u8, 1, rx_nss); } u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index b75c2c54e665..9a6e11d7b4db 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -22,12 +22,10 @@ #include "wep.h" -int ieee80211_wep_init(struct ieee80211_local *local) +void ieee80211_wep_init(struct ieee80211_local *local) { /* start WEP IV from a random value */ get_random_bytes(&local->wep_iv, IEEE80211_WEP_IV_LEN); - - return 0; } static inline bool ieee80211_wep_weak_iv(u32 iv, int keylen) diff --git a/net/mac80211/wep.h b/net/mac80211/wep.h index 997a034233c2..4ffe83554c67 100644 --- a/net/mac80211/wep.h +++ b/net/mac80211/wep.h @@ -13,7 +13,7 @@ #include "ieee80211_i.h" #include "key.h" -int ieee80211_wep_init(struct ieee80211_local *local); +void ieee80211_wep_init(struct ieee80211_local *local); int ieee80211_wep_encrypt_data(struct arc4_ctx *ctx, u8 *rc4key, size_t klen, u8 *data, size_t data_len); int ieee80211_wep_encrypt(struct ieee80211_local *local, diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 768a302879b4..0e9aa94adc07 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -98,7 +98,7 @@ struct mpls_nh { /* next hop label forwarding entry */ u8 nh_via_table; u8 nh_reserved1; - u32 nh_label[0]; + u32 nh_label[]; }; /* offset of via from beginning of mpls_nh */ @@ -154,7 +154,7 @@ struct mpls_route { /* next hop label forwarding entry */ u8 rt_nh_size; u8 rt_via_offset; u8 rt_reserved1; - struct mpls_nh rt_nh[0]; + struct mpls_nh rt_nh[]; }; #define for_nexthops(rt) { \ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index fd2c3150e591..9c71f427e6e3 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -304,21 +304,22 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, struct mptcp_ext *ext) { - ext->data_fin = 1; - if (!ext->use_map) { /* RFC6824 requires a DSS mapping with specific values * if DATA_FIN is set but no data payload is mapped */ + ext->data_fin = 1; ext->use_map = 1; ext->dsn64 = 1; - ext->data_seq = mptcp_sk(subflow->conn)->write_seq; + ext->data_seq = subflow->data_fin_tx_seq; ext->subflow_seq = 0; ext->data_len = 1; - } else { - /* If there's an existing DSS mapping, DATA_FIN consumes - * 1 additional byte of mapping space. + } else if (ext->data_seq + ext->data_len == subflow->data_fin_tx_seq) { + /* If there's an existing DSS mapping and it is the + * final mapping, DATA_FIN consumes 1 additional byte of + * mapping space. */ + ext->data_fin = 1; ext->data_len++; } } @@ -356,8 +357,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, if (mpext) opts->ext_copy = *mpext; - if (skb && tcp_fin && - subflow->conn->sk_state != TCP_ESTABLISHED) + if (skb && tcp_fin && subflow->data_fin_tx_enable) mptcp_write_data_fin(subflow, &opts->ext_copy); ret = true; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3c19a8efdcea..c0cef07f4382 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -31,6 +31,12 @@ struct mptcp6_sock { }; #endif +struct mptcp_skb_cb { + u32 offset; +}; + +#define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0])) + /* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not * completed yet or has failed, return the subflow socket. * Otherwise return NULL. @@ -111,6 +117,143 @@ static struct sock *mptcp_subflow_get(const struct mptcp_sock *msk) return NULL; } +static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, + struct sk_buff *skb, + unsigned int offset, size_t copy_len) +{ + struct sock *sk = (struct sock *)msk; + + __skb_unlink(skb, &ssk->sk_receive_queue); + skb_set_owner_r(skb, sk); + __skb_queue_tail(&sk->sk_receive_queue, skb); + + msk->ack_seq += copy_len; + MPTCP_SKB_CB(skb)->offset = offset; +} + +static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, + struct sock *ssk, + unsigned int *bytes) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct sock *sk = (struct sock *)msk; + unsigned int moved = 0; + bool more_data_avail; + struct tcp_sock *tp; + bool done = false; + + if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { + int rcvbuf = max(ssk->sk_rcvbuf, sk->sk_rcvbuf); + + if (rcvbuf > sk->sk_rcvbuf) + sk->sk_rcvbuf = rcvbuf; + } + + tp = tcp_sk(ssk); + do { + u32 map_remaining, offset; + u32 seq = tp->copied_seq; + struct sk_buff *skb; + bool fin; + + /* try to move as much data as available */ + map_remaining = subflow->map_data_len - + mptcp_subflow_get_map_offset(subflow); + + skb = skb_peek(&ssk->sk_receive_queue); + if (!skb) + break; + + offset = seq - TCP_SKB_CB(skb)->seq; + fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; + if (fin) { + done = true; + seq++; + } + + if (offset < skb->len) { + size_t len = skb->len - offset; + + if (tp->urg_data) + done = true; + + __mptcp_move_skb(msk, ssk, skb, offset, len); + seq += len; + moved += len; + + if (WARN_ON_ONCE(map_remaining < len)) + break; + } else { + WARN_ON_ONCE(!fin); + sk_eat_skb(ssk, skb); + done = true; + } + + WRITE_ONCE(tp->copied_seq, seq); + more_data_avail = mptcp_subflow_data_available(ssk); + + if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) { + done = true; + break; + } + } while (more_data_avail); + + *bytes = moved; + + return done; +} + +/* In most cases we will be able to lock the mptcp socket. If its already + * owned, we need to defer to the work queue to avoid ABBA deadlock. + */ +static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) +{ + struct sock *sk = (struct sock *)msk; + unsigned int moved = 0; + + if (READ_ONCE(sk->sk_lock.owned)) + return false; + + if (unlikely(!spin_trylock_bh(&sk->sk_lock.slock))) + return false; + + /* must re-check after taking the lock */ + if (!READ_ONCE(sk->sk_lock.owned)) + __mptcp_move_skbs_from_subflow(msk, ssk, &moved); + + spin_unlock_bh(&sk->sk_lock.slock); + + return moved > 0; +} + +void mptcp_data_ready(struct sock *sk, struct sock *ssk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + set_bit(MPTCP_DATA_READY, &msk->flags); + + if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) && + move_skbs_to_msk(msk, ssk)) + goto wake; + + /* don't schedule if mptcp sk is (still) over limit */ + if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) + goto wake; + + /* mptcp socket is owned, release_cb should retry */ + if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, + &sk->sk_tsq_flags)) { + sock_hold(sk); + + /* need to try again, its possible release_cb() has already + * been called after the test_and_set_bit() above. + */ + move_skbs_to_msk(msk, ssk); + } +wake: + sk->sk_data_ready(sk); +} + static bool mptcp_ext_cache_refill(struct mptcp_sock *msk) { if (!msk->cached_ext) @@ -278,6 +421,15 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) return -EOPNOTSUPP; lock_sock(sk); + + timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + + if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { + ret = sk_stream_wait_connect(sk, &timeo); + if (ret) + goto out; + } + ssock = __mptcp_tcp_fallback(msk); if (unlikely(ssock)) { fallback: @@ -286,8 +438,6 @@ fallback: return ret >= 0 ? ret + copied : (copied ? copied : ret); } - timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); - ssk = mptcp_subflow_get(msk); if (!ssk) { release_sock(sk); @@ -319,65 +469,88 @@ fallback: ssk_check_wmem(msk, ssk); release_sock(ssk); +out: release_sock(sk); return ret; } -int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb, - unsigned int offset, size_t len) +static void mptcp_wait_data(struct sock *sk, long *timeo) { - struct mptcp_read_arg *arg = desc->arg.data; - size_t copy_len; + DEFINE_WAIT_FUNC(wait, woken_wake_function); + struct mptcp_sock *msk = mptcp_sk(sk); + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - copy_len = min(desc->count, len); + sk_wait_event(sk, timeo, + test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait); - if (likely(arg->msg)) { + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); +} + +static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, + struct msghdr *msg, + size_t len) +{ + struct sock *sk = (struct sock *)msk; + struct sk_buff *skb; + int copied = 0; + + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { + u32 offset = MPTCP_SKB_CB(skb)->offset; + u32 data_len = skb->len - offset; + u32 count = min_t(size_t, len - copied, data_len); int err; - err = skb_copy_datagram_msg(skb, offset, arg->msg, copy_len); - if (err) { - pr_debug("error path"); - desc->error = err; - return err; + err = skb_copy_datagram_msg(skb, offset, msg, count); + if (unlikely(err < 0)) { + if (!copied) + return err; + break; } - } else { - pr_debug("Flushing skb payload"); - } - desc->count -= copy_len; + copied += count; + + if (count < data_len) { + MPTCP_SKB_CB(skb)->offset += count; + break; + } + + __skb_unlink(skb, &sk->sk_receive_queue); + __kfree_skb(skb); + + if (copied >= len) + break; + } - pr_debug("consumed %zu bytes, %zu left", copy_len, desc->count); - return copy_len; + return copied; } -static void mptcp_wait_data(struct sock *sk, long *timeo) +static bool __mptcp_move_skbs(struct mptcp_sock *msk) { - DEFINE_WAIT_FUNC(wait, woken_wake_function); - struct mptcp_sock *msk = mptcp_sk(sk); + unsigned int moved = 0; + bool done; - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + do { + struct sock *ssk = mptcp_subflow_recv_lookup(msk); - sk_wait_event(sk, timeo, - test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait); + if (!ssk) + break; - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); + lock_sock(ssk); + done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); + release_sock(ssk); + } while (!done); + + return moved > 0; } static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { struct mptcp_sock *msk = mptcp_sk(sk); - struct mptcp_subflow_context *subflow; - bool more_data_avail = false; - struct mptcp_read_arg arg; - read_descriptor_t desc; - bool wait_data = false; struct socket *ssock; - struct tcp_sock *tp; - bool done = false; - struct sock *ssk; int copied = 0; int target; long timeo; @@ -395,65 +568,26 @@ fallback: return copied; } - arg.msg = msg; - desc.arg.data = &arg; - desc.error = 0; - timeo = sock_rcvtimeo(sk, nonblock); len = min_t(size_t, len, INT_MAX); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - while (!done) { - u32 map_remaining; + while (len > (size_t)copied) { int bytes_read; - ssk = mptcp_subflow_recv_lookup(msk); - pr_debug("msk=%p ssk=%p", msk, ssk); - if (!ssk) - goto wait_for_data; - - subflow = mptcp_subflow_ctx(ssk); - tp = tcp_sk(ssk); - - lock_sock(ssk); - do { - /* try to read as much data as available */ - map_remaining = subflow->map_data_len - - mptcp_subflow_get_map_offset(subflow); - desc.count = min_t(size_t, len - copied, map_remaining); - pr_debug("reading %zu bytes, copied %d", desc.count, - copied); - bytes_read = tcp_read_sock(ssk, &desc, - mptcp_read_actor); - if (bytes_read < 0) { - if (!copied) - copied = bytes_read; - done = true; - goto next; - } + bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied); + if (unlikely(bytes_read < 0)) { + if (!copied) + copied = bytes_read; + goto out_err; + } - pr_debug("msk ack_seq=%llx -> %llx", msk->ack_seq, - msk->ack_seq + bytes_read); - msk->ack_seq += bytes_read; - copied += bytes_read; - if (copied >= len) { - done = true; - goto next; - } - if (tp->urg_data && tp->urg_seq == tp->copied_seq) { - pr_err("Urgent data present, cannot proceed"); - done = true; - goto next; - } -next: - more_data_avail = mptcp_subflow_data_available(ssk); - } while (more_data_avail && !done); - release_sock(ssk); - continue; + copied += bytes_read; -wait_for_data: - more_data_avail = false; + if (skb_queue_empty(&sk->sk_receive_queue) && + __mptcp_move_skbs(msk)) + continue; /* only the master socket status is relevant here. The exit * conditions mirror closely tcp_recvmsg() @@ -494,26 +628,25 @@ wait_for_data: } pr_debug("block timeout %ld", timeo); - wait_data = true; mptcp_wait_data(sk, &timeo); if (unlikely(__mptcp_tcp_fallback(msk))) goto fallback; } - if (more_data_avail) { - if (!test_bit(MPTCP_DATA_READY, &msk->flags)) - set_bit(MPTCP_DATA_READY, &msk->flags); - } else if (!wait_data) { + if (skb_queue_empty(&sk->sk_receive_queue)) { + /* entire backlog drained, clear DATA_READY. */ clear_bit(MPTCP_DATA_READY, &msk->flags); - /* .. race-breaker: ssk might get new data after last - * data_available() returns false. + /* .. race-breaker: ssk might have gotten new data + * after last __mptcp_move_skbs() returned false. */ - ssk = mptcp_subflow_recv_lookup(msk); - if (unlikely(ssk)) + if (unlikely(__mptcp_move_skbs(msk))) set_bit(MPTCP_DATA_READY, &msk->flags); + } else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) { + /* data to read but mptcp_wait_data() cleared DATA_READY */ + set_bit(MPTCP_DATA_READY, &msk->flags); } - +out_err: release_sock(sk); return copied; } @@ -548,12 +681,24 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) return 0; } +static void mptcp_worker(struct work_struct *work) +{ + struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); + struct sock *sk = &msk->sk.icsk_inet.sk; + + lock_sock(sk); + __mptcp_move_skbs(msk); + release_sock(sk); + sock_put(sk); +} + static int __mptcp_init_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); INIT_LIST_HEAD(&msk->conn_list); __set_bit(MPTCP_SEND_SPACE, &msk->flags); + INIT_WORK(&msk->work, mptcp_worker); msk->first = NULL; inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; @@ -569,7 +714,16 @@ static int mptcp_init_sock(struct sock *sk) return __mptcp_init_sock(sk); } -static void mptcp_subflow_shutdown(struct sock *ssk, int how) +static void mptcp_cancel_work(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + if (cancel_work_sync(&msk->work)) + sock_put(sk); +} + +static void mptcp_subflow_shutdown(struct sock *ssk, int how, + bool data_fin_tx_enable, u64 data_fin_tx_seq) { lock_sock(ssk); @@ -582,6 +736,14 @@ static void mptcp_subflow_shutdown(struct sock *ssk, int how) tcp_disconnect(ssk, O_NONBLOCK); break; default: + if (data_fin_tx_enable) { + struct mptcp_subflow_context *subflow; + + subflow = mptcp_subflow_ctx(ssk); + subflow->data_fin_tx_seq = data_fin_tx_seq; + subflow->data_fin_tx_enable = 1; + } + ssk->sk_shutdown |= how; tcp_shutdown(ssk, how); break; @@ -598,6 +760,7 @@ static void mptcp_close(struct sock *sk, long timeout) struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); LIST_HEAD(conn_list); + u64 data_fin_tx_seq; lock_sock(sk); @@ -606,14 +769,22 @@ static void mptcp_close(struct sock *sk, long timeout) list_splice_init(&msk->conn_list, &conn_list); + data_fin_tx_seq = msk->write_seq; + release_sock(sk); list_for_each_entry_safe(subflow, tmp, &conn_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + subflow->data_fin_tx_seq = data_fin_tx_seq; + subflow->data_fin_tx_enable = 1; __mptcp_close_ssk(sk, ssk, subflow, timeout); } + mptcp_cancel_work(sk); + + __skb_queue_purge(&sk->sk_receive_queue); + sk_common_release(sk); } @@ -699,7 +870,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, *err = -ENOBUFS; local_bh_enable(); release_sock(sk); - mptcp_subflow_shutdown(newsk, SHUT_RDWR + 1); + mptcp_subflow_shutdown(newsk, SHUT_RDWR + 1, 0, 0); tcp_close(newsk, 0); return NULL; } @@ -807,6 +978,32 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; } +#define MPTCP_DEFERRED_ALL TCPF_DELACK_TIMER_DEFERRED + +/* this is very alike tcp_release_cb() but we must handle differently a + * different set of events + */ +static void mptcp_release_cb(struct sock *sk) +{ + unsigned long flags, nflags; + + do { + flags = sk->sk_tsq_flags; + if (!(flags & MPTCP_DEFERRED_ALL)) + return; + nflags = flags & ~MPTCP_DEFERRED_ALL; + } while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags); + + if (flags & TCPF_DELACK_TIMER_DEFERRED) { + struct mptcp_sock *msk = mptcp_sk(sk); + struct sock *ssk; + + ssk = mptcp_subflow_recv_lookup(msk); + if (!ssk || !schedule_work(&msk->work)) + __sock_put(sk); + } +} + static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -852,6 +1049,10 @@ void mptcp_finish_connect(struct sock *ssk) WRITE_ONCE(msk->write_seq, subflow->idsn + 1); WRITE_ONCE(msk->ack_seq, ack_seq); WRITE_ONCE(msk->can_ack, 1); + if (inet_sk_state_load(sk) != TCP_ESTABLISHED) { + inet_sk_state_store(sk, TCP_ESTABLISHED); + sk->sk_state_change(sk); + } } static void mptcp_sock_graft(struct sock *sk, struct socket *parent) @@ -882,6 +1083,7 @@ static struct proto mptcp_prot = { .destroy = mptcp_destroy, .sendmsg = mptcp_sendmsg, .recvmsg = mptcp_recvmsg, + .release_cb = mptcp_release_cb, .hash = inet_hash, .unhash = inet_unhash, .get_port = mptcp_get_port, @@ -1127,7 +1329,7 @@ static int mptcp_shutdown(struct socket *sock, int how) mptcp_for_each_subflow(msk, subflow) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); - mptcp_subflow_shutdown(tcp_sk, how); + mptcp_subflow_shutdown(tcp_sk, how, 1, msk->write_seq); } out_unlock: @@ -1180,6 +1382,8 @@ void mptcp_proto_init(void) panic("Failed to register MPTCP proto.\n"); inet_register_protosw(&mptcp_protosw); + + BUILD_BUG_ON(sizeof(struct mptcp_skb_cb) > sizeof_field(struct sk_buff, cb)); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 9f8663b30456..313558fa8185 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -70,6 +70,7 @@ struct mptcp_sock { u32 token; unsigned long flags; bool can_ack; + struct work_struct work; struct list_head conn_list; struct skb_ext *cached_ext; /* for the next sendmsg */ struct socket *subflow; /* outgoing connect/listener/!mp_capable */ @@ -124,7 +125,9 @@ struct mptcp_subflow_context { mpc_map : 1, data_avail : 1, rx_eof : 1, + data_fin_tx_enable : 1, can_ack : 1; /* only after processing the remote a key */ + u64 data_fin_tx_seq; struct sock *tcp_sock; /* tcp sk backpointer */ struct sock *conn; /* parent mptcp_sock */ @@ -190,17 +193,11 @@ void mptcp_proto_init(void); int mptcp_proto_v6_init(void); #endif -struct mptcp_read_arg { - struct msghdr *msg; -}; - -int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb, - unsigned int offset, size_t len); - void mptcp_get_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx); void mptcp_finish_connect(struct sock *sk); +void mptcp_data_ready(struct sock *sk, struct sock *ssk); int mptcp_token_new_request(struct request_sock *req); void mptcp_token_destroy_request(u32 token); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 65122edf60aa..0de2a44bdaa0 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -408,6 +408,18 @@ validate_seq: return MAPPING_OK; } +static int subflow_read_actor(read_descriptor_t *desc, + struct sk_buff *skb, + unsigned int offset, size_t len) +{ + size_t copy_len = min(desc->count, len); + + desc->count -= copy_len; + + pr_debug("flushed %zu bytes, %zu left", copy_len, desc->count); + return copy_len; +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -482,16 +494,12 @@ static bool subflow_check_data_avail(struct sock *ssk) pr_debug("discarding %zu bytes, current map len=%d", delta, map_remaining); if (delta) { - struct mptcp_read_arg arg = { - .msg = NULL, - }; read_descriptor_t desc = { .count = delta, - .arg.data = &arg, }; int ret; - ret = tcp_read_sock(ssk, &desc, mptcp_read_actor); + ret = tcp_read_sock(ssk, &desc, subflow_read_actor); if (ret < 0) { ssk->sk_err = -ret; goto fatal; @@ -554,11 +562,8 @@ static void subflow_data_ready(struct sock *sk) return; } - if (mptcp_subflow_data_available(sk)) { - set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags); - - parent->sk_data_ready(parent); - } + if (mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); } static void subflow_write_space(struct sock *sk) @@ -690,11 +695,8 @@ static void subflow_state_change(struct sock *sk) * a fin packet carrying a DSS can be unnoticed if we don't trigger * the data available machinery here. */ - if (parent && subflow->mp_capable && mptcp_subflow_data_available(sk)) { - set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags); - - parent->sk_data_ready(parent); - } + if (parent && subflow->mp_capable && mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); if (parent && !(parent->sk_shutdown & RCV_SHUTDOWN) && !subflow->rx_eof && subflow_is_done(sk)) { diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 8af28e10b4e6..9a477bd563b7 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -252,6 +252,19 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) } EXPORT_SYMBOL_GPL(flow_offload_add); +void flow_offload_refresh(struct nf_flowtable *flow_table, + struct flow_offload *flow) +{ + flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; + + if (likely(!nf_flowtable_hw_offload(flow_table) || + !test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags))) + return; + + nf_flow_offload_add(flow_table, flow); +} +EXPORT_SYMBOL_GPL(flow_offload_refresh); + static inline bool nf_flow_has_expired(const struct flow_offload *flow) { return nf_flow_timeout_delta(flow->timeout) <= 0; @@ -372,6 +385,50 @@ static void nf_flow_offload_work_gc(struct work_struct *work) queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } +int nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, + flow_setup_cb_t *cb, void *cb_priv) +{ + struct flow_block *block = &flow_table->flow_block; + struct flow_block_cb *block_cb; + int err = 0; + + mutex_lock(&flow_table->flow_block_lock); + block_cb = flow_block_cb_lookup(block, cb, cb_priv); + if (block_cb) { + err = -EEXIST; + goto unlock; + } + + block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL); + if (IS_ERR(block_cb)) { + err = PTR_ERR(block_cb); + goto unlock; + } + + list_add_tail(&block_cb->list, &block->cb_list); + +unlock: + mutex_unlock(&flow_table->flow_block_lock); + return err; +} +EXPORT_SYMBOL_GPL(nf_flow_table_offload_add_cb); + +void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, + flow_setup_cb_t *cb, void *cb_priv) +{ + struct flow_block *block = &flow_table->flow_block; + struct flow_block_cb *block_cb; + + mutex_lock(&flow_table->flow_block_lock); + block_cb = flow_block_cb_lookup(block, cb, cb_priv); + if (block_cb) + list_del(&block_cb->list); + else + WARN_ON(true); + mutex_unlock(&flow_table->flow_block_lock); +} +EXPORT_SYMBOL_GPL(nf_flow_table_offload_del_cb); + static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, __be16 port, __be16 new_port) { @@ -494,6 +551,7 @@ int nf_flow_table_init(struct nf_flowtable *flowtable) INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc); flow_block_init(&flowtable->flow_block); + mutex_init(&flowtable->flow_block_lock); err = rhashtable_init(&flowtable->rhashtable, &nf_flow_offload_rhash_params); @@ -550,11 +608,13 @@ void nf_flow_table_free(struct nf_flowtable *flow_table) mutex_lock(&flowtable_lock); list_del(&flow_table->list); mutex_unlock(&flowtable_lock); + cancel_delayed_work_sync(&flow_table->gc_work); nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL); nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, flow_table); nf_flow_table_offload_flush(flow_table); rhashtable_destroy(&flow_table->rhashtable); + mutex_destroy(&flow_table->flow_block_lock); } EXPORT_SYMBOL_GPL(nf_flow_table_free); diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 9e563fd3da0f..5272721080f8 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -232,13 +232,6 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } -static bool nf_flow_offload_refresh(struct nf_flowtable *flow_table, - struct flow_offload *flow) -{ - return nf_flowtable_hw_offload(flow_table) && - test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags); -} - unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -279,8 +272,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff)) return NF_ACCEPT; - if (unlikely(nf_flow_offload_refresh(flow_table, flow))) - nf_flow_offload_add(flow_table, flow); + flow_offload_refresh(flow_table, flow); if (nf_flow_offload_dst_check(&rt->dst)) { flow_offload_teardown(flow); @@ -290,7 +282,6 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0) return NF_DROP; - flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; iph = ip_hdr(skb); ip_decrease_ttl(iph); skb->tstamp = 0; @@ -508,8 +499,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, sizeof(*ip6h))) return NF_ACCEPT; - if (unlikely(nf_flow_offload_refresh(flow_table, flow))) - nf_flow_offload_add(flow_table, flow); + flow_offload_refresh(flow_table, flow); if (nf_flow_offload_dst_check(&rt->dst)) { flow_offload_teardown(flow); @@ -522,7 +512,6 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (nf_flow_nat_ipv6(flow, skb, dir) < 0) return NF_DROP; - flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; ip6h = ipv6_hdr(skb); ip6h->hop_limit--; skb->tstamp = 0; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 06f00cdc3891..42b73a084a63 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -23,29 +23,6 @@ struct flow_offload_work { struct flow_offload *flow; }; -struct nf_flow_key { - struct flow_dissector_key_meta meta; - struct flow_dissector_key_control control; - struct flow_dissector_key_basic basic; - union { - struct flow_dissector_key_ipv4_addrs ipv4; - struct flow_dissector_key_ipv6_addrs ipv6; - }; - struct flow_dissector_key_tcp tcp; - struct flow_dissector_key_ports tp; -} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ - -struct nf_flow_match { - struct flow_dissector dissector; - struct nf_flow_key key; - struct nf_flow_key mask; -}; - -struct nf_flow_rule { - struct nf_flow_match match; - struct flow_rule *rule; -}; - #define NF_FLOW_DISSECTOR(__match, __type, __field) \ (__match)->dissector.offset[__type] = \ offsetof(struct nf_flow_key, __field) @@ -610,6 +587,7 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, if (cmd == FLOW_CLS_REPLACE) cls_flow.rule = flow_rule->rule; + mutex_lock(&flowtable->flow_block_lock); list_for_each_entry(block_cb, block_cb_list, list) { err = block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); @@ -618,6 +596,7 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, i++; } + mutex_unlock(&flowtable->flow_block_lock); return i; } @@ -692,8 +671,10 @@ static void flow_offload_tuple_stats(struct flow_offload_work *offload, FLOW_CLS_STATS, &offload->flow->tuplehash[dir].tuple, &extack); + mutex_lock(&flowtable->flow_block_lock); list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); + mutex_unlock(&flowtable->flow_block_lock); memcpy(stats, &cls_flow.stats, sizeof(*stats)); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 5313f1cec170..ed77c75bf63f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -71,7 +71,7 @@ struct listeners { struct rcu_head rcu; - unsigned long masks[0]; + unsigned long masks[]; }; /* state bits */ @@ -2583,6 +2583,7 @@ static void *__netlink_seq_next(struct seq_file *seq) } static void *netlink_seq_start(struct seq_file *seq, loff_t *posp) + __acquires(RCU) { struct nl_seq_iter *iter = seq->private; void *obj = SEQ_START_TOKEN; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 58d5373c513c..7b1a74f74aad 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1230,6 +1230,7 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) #ifdef CONFIG_PROC_FS static void *nr_info_start(struct seq_file *seq, loff_t *pos) + __acquires(&nr_list_lock) { spin_lock_bh(&nr_list_lock); return seq_hlist_start_head(&nr_list, *pos); @@ -1241,6 +1242,7 @@ static void *nr_info_next(struct seq_file *seq, void *v, loff_t *pos) } static void nr_info_stop(struct seq_file *seq, void *v) + __releases(&nr_list_lock) { spin_unlock_bh(&nr_list_lock); } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index d41335bad1f8..79f12d8c7b86 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -838,6 +838,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) #ifdef CONFIG_PROC_FS static void *nr_node_start(struct seq_file *seq, loff_t *pos) + __acquires(&nr_node_list_lock) { spin_lock_bh(&nr_node_list_lock); return seq_hlist_start_head(&nr_node_list, *pos); @@ -849,6 +850,7 @@ static void *nr_node_next(struct seq_file *seq, void *v, loff_t *pos) } static void nr_node_stop(struct seq_file *seq, void *v) + __releases(&nr_node_list_lock) { spin_unlock_bh(&nr_node_list_lock); } @@ -893,6 +895,7 @@ const struct seq_operations nr_node_seqops = { }; static void *nr_neigh_start(struct seq_file *seq, loff_t *pos) + __acquires(&nr_neigh_list_lock) { spin_lock_bh(&nr_neigh_list_lock); return seq_hlist_start_head(&nr_neigh_list, *pos); @@ -904,6 +907,7 @@ static void *nr_neigh_next(struct seq_file *seq, void *v, loff_t *pos) } static void nr_neigh_stop(struct seq_file *seq, void *v) + __releases(&nr_neigh_list_lock) { spin_unlock_bh(&nr_neigh_list_lock); } diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c index 65aaa9d7c813..304b1a9bb18a 100644 --- a/net/nfc/digital_dep.c +++ b/net/nfc/digital_dep.c @@ -71,7 +71,7 @@ struct digital_atr_req { u8 bs; u8 br; u8 pp; - u8 gb[0]; + u8 gb[]; } __packed; struct digital_atr_res { @@ -83,7 +83,7 @@ struct digital_atr_res { u8 br; u8 to; u8 pp; - u8 gb[0]; + u8 gb[]; } __packed; struct digital_psl_req { diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 7fbfe2adfffa..fc0efd8833c8 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -964,6 +964,25 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, return ovs_dp_upcall(dp, skb, key, &upcall, cutlen); } +static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, + const struct nlattr *attr, bool last) +{ + /* The first action is always 'OVS_DEC_TTL_ATTR_ARG'. */ + struct nlattr *dec_ttl_arg = nla_data(attr); + int rem = nla_len(attr); + + if (nla_len(dec_ttl_arg)) { + struct nlattr *actions = nla_next(dec_ttl_arg, &rem); + + if (actions) + return clone_execute(dp, skb, key, 0, actions, rem, + last, false); + } + consume_skb(skb); + return 0; +} + /* When 'last' is true, sample() should always consume the 'skb'. * Otherwise, sample() should keep 'skb' intact regardless what * actions are executed within sample(). @@ -1180,6 +1199,45 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, nla_len(actions), last, clone_flow_key); } +static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key) +{ + int err; + + if (skb->protocol == htons(ETH_P_IPV6)) { + struct ipv6hdr *nh; + + err = skb_ensure_writable(skb, skb_network_offset(skb) + + sizeof(*nh)); + if (unlikely(err)) + return err; + + nh = ipv6_hdr(skb); + + if (nh->hop_limit <= 1) + return -EHOSTUNREACH; + + key->ip.ttl = --nh->hop_limit; + } else { + struct iphdr *nh; + u8 old_ttl; + + err = skb_ensure_writable(skb, skb_network_offset(skb) + + sizeof(*nh)); + if (unlikely(err)) + return err; + + nh = ip_hdr(skb); + if (nh->ttl <= 1) + return -EHOSTUNREACH; + + old_ttl = nh->ttl--; + csum_replace2(&nh->check, htons(old_ttl << 8), + htons(nh->ttl << 8)); + key->ip.ttl = nh->ttl; + } + return 0; +} + /* Execute a list of actions against 'skb'. */ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, @@ -1365,6 +1423,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; } + + case OVS_ACTION_ATTR_DEC_TTL: + err = execute_dec_ttl(skb, key); + if (err == -EHOSTUNREACH) { + err = dec_ttl_exception_handler(dp, skb, key, + a, true); + return err; + } + break; } if (unlikely(err)) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 288122eec7c8..79252d4887ff 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -80,6 +80,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_METER: case OVS_ACTION_ATTR_CHECK_PKT_LEN: case OVS_ACTION_ATTR_ADD_MPLS: + case OVS_ACTION_ATTR_DEC_TTL: default: return true; } @@ -2495,6 +2496,39 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, return 0; } +static int validate_and_copy_dec_ttl(struct net *net, + const struct nlattr *attr, + const struct sw_flow_key *key, + struct sw_flow_actions **sfa, + __be16 eth_type, __be16 vlan_tci, + u32 mpls_label_count, bool log) +{ + int start, err; + u32 nested = true; + + if (!nla_len(attr)) + return ovs_nla_add_action(sfa, OVS_ACTION_ATTR_DEC_TTL, + NULL, 0, log); + + start = add_nested_action_start(sfa, OVS_ACTION_ATTR_DEC_TTL, log); + if (start < 0) + return start; + + err = ovs_nla_add_action(sfa, OVS_DEC_TTL_ATTR_ACTION, &nested, + sizeof(nested), log); + + if (err) + return err; + + err = __ovs_nla_copy_actions(net, attr, key, sfa, eth_type, + vlan_tci, mpls_label_count, log); + if (err) + return err; + + add_nested_action_end(*sfa, start); + return 0; +} + static int validate_and_copy_clone(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, @@ -3009,6 +3043,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_CLONE] = (u32)-1, [OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1, [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), + [OVS_ACTION_ATTR_DEC_TTL] = (u32)-1, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3269,6 +3304,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, break; } + case OVS_ACTION_ATTR_DEC_TTL: + err = validate_and_copy_dec_ttl(net, a, key, sfa, + eth_type, vlan_tci, + mpls_label_count, log); + if (err) + return err; + skip_copy = true; + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; @@ -3440,6 +3484,26 @@ out: return err; } +static int dec_ttl_action_to_attr(const struct nlattr *attr, + struct sk_buff *skb) +{ + int err = 0, rem = nla_len(attr); + struct nlattr *start; + + start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_DEC_TTL); + + if (!start) + return -EMSGSIZE; + + err = ovs_nla_put_actions(nla_data(attr), rem, skb); + if (err) + nla_nest_cancel(skb, start); + else + nla_nest_end(skb, start); + + return err; +} + static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) { const struct nlattr *ovs_key = nla_data(a); @@ -3540,6 +3604,12 @@ int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb) return err; break; + case OVS_ACTION_ATTR_DEC_TTL: + err = dec_ttl_action_to_attr(a, skb); + if (err) + return err; + break; + default: if (nla_put(skb, type, nla_len(a), nla_data(a))) return -EMSGSIZE; diff --git a/net/qrtr/Makefile b/net/qrtr/Makefile index 1c6d6c120fb7..32d4e923925d 100644 --- a/net/qrtr/Makefile +++ b/net/qrtr/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_QRTR) := qrtr.o +obj-$(CONFIG_QRTR) := qrtr.o ns.o obj-$(CONFIG_QRTR_SMD) += qrtr-smd.o qrtr-smd-y := smd.o diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c new file mode 100644 index 000000000000..e7d0fe3f4330 --- /dev/null +++ b/net/qrtr/ns.c @@ -0,0 +1,757 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Copyright (c) 2015, Sony Mobile Communications Inc. + * Copyright (c) 2013, The Linux Foundation. All rights reserved. + * Copyright (c) 2020, Linaro Ltd. + */ + +#include <linux/module.h> +#include <linux/qrtr.h> +#include <linux/workqueue.h> +#include <net/sock.h> + +#include "qrtr.h" + +static RADIX_TREE(nodes, GFP_KERNEL); + +static struct { + struct socket *sock; + struct sockaddr_qrtr bcast_sq; + struct list_head lookups; + struct workqueue_struct *workqueue; + struct work_struct work; + int local_node; +} qrtr_ns; + +static const char * const qrtr_ctrl_pkt_strings[] = { + [QRTR_TYPE_HELLO] = "hello", + [QRTR_TYPE_BYE] = "bye", + [QRTR_TYPE_NEW_SERVER] = "new-server", + [QRTR_TYPE_DEL_SERVER] = "del-server", + [QRTR_TYPE_DEL_CLIENT] = "del-client", + [QRTR_TYPE_RESUME_TX] = "resume-tx", + [QRTR_TYPE_EXIT] = "exit", + [QRTR_TYPE_PING] = "ping", + [QRTR_TYPE_NEW_LOOKUP] = "new-lookup", + [QRTR_TYPE_DEL_LOOKUP] = "del-lookup", +}; + +struct qrtr_server_filter { + unsigned int service; + unsigned int instance; + unsigned int ifilter; +}; + +struct qrtr_lookup { + unsigned int service; + unsigned int instance; + + struct sockaddr_qrtr sq; + struct list_head li; +}; + +struct qrtr_server { + unsigned int service; + unsigned int instance; + + unsigned int node; + unsigned int port; + + struct list_head qli; +}; + +struct qrtr_node { + unsigned int id; + struct radix_tree_root servers; +}; + +static struct qrtr_node *node_get(unsigned int node_id) +{ + struct qrtr_node *node; + + node = radix_tree_lookup(&nodes, node_id); + if (node) + return node; + + /* If node didn't exist, allocate and insert it to the tree */ + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return NULL; + + node->id = node_id; + + radix_tree_insert(&nodes, node_id, node); + + return node; +} + +static int server_match(const struct qrtr_server *srv, + const struct qrtr_server_filter *f) +{ + unsigned int ifilter = f->ifilter; + + if (f->service != 0 && srv->service != f->service) + return 0; + if (!ifilter && f->instance) + ifilter = ~0; + + return (srv->instance & ifilter) == f->instance; +} + +static int service_announce_new(struct sockaddr_qrtr *dest, + struct qrtr_server *srv) +{ + struct qrtr_ctrl_pkt pkt; + struct msghdr msg = { }; + struct kvec iv; + + trace_printk("advertising new server [%d:%x]@[%d:%d]\n", + srv->service, srv->instance, srv->node, srv->port); + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = cpu_to_le32(QRTR_TYPE_NEW_SERVER); + pkt.server.service = cpu_to_le32(srv->service); + pkt.server.instance = cpu_to_le32(srv->instance); + pkt.server.node = cpu_to_le32(srv->node); + pkt.server.port = cpu_to_le32(srv->port); + + msg.msg_name = (struct sockaddr *)dest; + msg.msg_namelen = sizeof(*dest); + + return kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); +} + +static int service_announce_del(struct sockaddr_qrtr *dest, + struct qrtr_server *srv) +{ + struct qrtr_ctrl_pkt pkt; + struct msghdr msg = { }; + struct kvec iv; + int ret; + + trace_printk("advertising removal of server [%d:%x]@[%d:%d]\n", + srv->service, srv->instance, srv->node, srv->port); + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = cpu_to_le32(QRTR_TYPE_DEL_SERVER); + pkt.server.service = cpu_to_le32(srv->service); + pkt.server.instance = cpu_to_le32(srv->instance); + pkt.server.node = cpu_to_le32(srv->node); + pkt.server.port = cpu_to_le32(srv->port); + + msg.msg_name = (struct sockaddr *)dest; + msg.msg_namelen = sizeof(*dest); + + ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); + if (ret < 0) + pr_err("failed to announce del service\n"); + + return ret; +} + +static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv, + bool new) +{ + struct qrtr_ctrl_pkt pkt; + struct msghdr msg = { }; + struct kvec iv; + int ret; + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = new ? cpu_to_le32(QRTR_TYPE_NEW_SERVER) : + cpu_to_le32(QRTR_TYPE_DEL_SERVER); + if (srv) { + pkt.server.service = cpu_to_le32(srv->service); + pkt.server.instance = cpu_to_le32(srv->instance); + pkt.server.node = cpu_to_le32(srv->node); + pkt.server.port = cpu_to_le32(srv->port); + } + + msg.msg_name = (struct sockaddr *)to; + msg.msg_namelen = sizeof(*to); + + ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); + if (ret < 0) + pr_err("failed to send lookup notification\n"); +} + +static int announce_servers(struct sockaddr_qrtr *sq) +{ + struct radix_tree_iter iter; + struct qrtr_server *srv; + struct qrtr_node *node; + void __rcu **slot; + int ret; + + node = node_get(qrtr_ns.local_node); + if (!node) + return 0; + + /* Announce the list of servers registered in this node */ + radix_tree_for_each_slot(slot, &node->servers, &iter, 0) { + srv = radix_tree_deref_slot(slot); + + ret = service_announce_new(sq, srv); + if (ret < 0) { + pr_err("failed to announce new service\n"); + return ret; + } + } + + return 0; +} + +static struct qrtr_server *server_add(unsigned int service, + unsigned int instance, + unsigned int node_id, + unsigned int port) +{ + struct qrtr_server *srv; + struct qrtr_server *old; + struct qrtr_node *node; + + if (!service || !port) + return NULL; + + srv = kzalloc(sizeof(*srv), GFP_KERNEL); + if (!srv) + return NULL; + + srv->service = service; + srv->instance = instance; + srv->node = node_id; + srv->port = port; + + node = node_get(node_id); + if (!node) + goto err; + + /* Delete the old server on the same port */ + old = radix_tree_lookup(&node->servers, port); + if (old) { + radix_tree_delete(&node->servers, port); + kfree(old); + } + + radix_tree_insert(&node->servers, port, srv); + + trace_printk("add server [%d:%x]@[%d:%d]\n", srv->service, + srv->instance, srv->node, srv->port); + + return srv; + +err: + kfree(srv); + return NULL; +} + +static int server_del(struct qrtr_node *node, unsigned int port) +{ + struct qrtr_lookup *lookup; + struct qrtr_server *srv; + struct list_head *li; + + srv = radix_tree_lookup(&node->servers, port); + if (!srv) + return -ENOENT; + + radix_tree_delete(&node->servers, port); + + /* Broadcast the removal of local servers */ + if (srv->node == qrtr_ns.local_node) + service_announce_del(&qrtr_ns.bcast_sq, srv); + + /* Announce the service's disappearance to observers */ + list_for_each(li, &qrtr_ns.lookups) { + lookup = container_of(li, struct qrtr_lookup, li); + if (lookup->service && lookup->service != srv->service) + continue; + if (lookup->instance && lookup->instance != srv->instance) + continue; + + lookup_notify(&lookup->sq, srv, false); + } + + kfree(srv); + + return 0; +} + +static int say_hello(struct sockaddr_qrtr *dest) +{ + struct qrtr_ctrl_pkt pkt; + struct msghdr msg = { }; + struct kvec iv; + int ret; + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = cpu_to_le32(QRTR_TYPE_HELLO); + + msg.msg_name = (struct sockaddr *)dest; + msg.msg_namelen = sizeof(*dest); + + ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); + if (ret < 0) + pr_err("failed to send hello msg\n"); + + return ret; +} + +/* Announce the list of servers registered on the local node */ +static int ctrl_cmd_hello(struct sockaddr_qrtr *sq) +{ + int ret; + + ret = say_hello(sq); + if (ret < 0) + return ret; + + return announce_servers(sq); +} + +static int ctrl_cmd_bye(struct sockaddr_qrtr *from) +{ + struct qrtr_node *local_node; + struct radix_tree_iter iter; + struct qrtr_ctrl_pkt pkt; + struct qrtr_server *srv; + struct sockaddr_qrtr sq; + struct msghdr msg = { }; + struct qrtr_node *node; + void __rcu **slot; + struct kvec iv; + int ret; + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + node = node_get(from->sq_node); + if (!node) + return 0; + + /* Advertise removal of this client to all servers of remote node */ + radix_tree_for_each_slot(slot, &node->servers, &iter, 0) { + srv = radix_tree_deref_slot(slot); + server_del(node, srv->port); + } + + /* Advertise the removal of this client to all local servers */ + local_node = node_get(qrtr_ns.local_node); + if (!local_node) + return 0; + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = cpu_to_le32(QRTR_TYPE_BYE); + pkt.client.node = cpu_to_le32(from->sq_node); + + radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) { + srv = radix_tree_deref_slot(slot); + + sq.sq_family = AF_QIPCRTR; + sq.sq_node = srv->node; + sq.sq_port = srv->port; + + msg.msg_name = (struct sockaddr *)&sq; + msg.msg_namelen = sizeof(sq); + + ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); + if (ret < 0) { + pr_err("failed to send bye cmd\n"); + return ret; + } + } + + return 0; +} + +static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, + unsigned int node_id, unsigned int port) +{ + struct qrtr_node *local_node; + struct radix_tree_iter iter; + struct qrtr_lookup *lookup; + struct qrtr_ctrl_pkt pkt; + struct msghdr msg = { }; + struct qrtr_server *srv; + struct sockaddr_qrtr sq; + struct qrtr_node *node; + struct list_head *tmp; + struct list_head *li; + void __rcu **slot; + struct kvec iv; + int ret; + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + /* Don't accept spoofed messages */ + if (from->sq_node != node_id) + return -EINVAL; + + /* Local DEL_CLIENT messages comes from the port being closed */ + if (from->sq_node == qrtr_ns.local_node && from->sq_port != port) + return -EINVAL; + + /* Remove any lookups by this client */ + list_for_each_safe(li, tmp, &qrtr_ns.lookups) { + lookup = container_of(li, struct qrtr_lookup, li); + if (lookup->sq.sq_node != node_id) + continue; + if (lookup->sq.sq_port != port) + continue; + + list_del(&lookup->li); + kfree(lookup); + } + + /* Remove the server belonging to this port */ + node = node_get(node_id); + if (node) + server_del(node, port); + + /* Advertise the removal of this client to all local servers */ + local_node = node_get(qrtr_ns.local_node); + if (!local_node) + return 0; + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = cpu_to_le32(QRTR_TYPE_DEL_CLIENT); + pkt.client.node = cpu_to_le32(node_id); + pkt.client.port = cpu_to_le32(port); + + radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) { + srv = radix_tree_deref_slot(slot); + + sq.sq_family = AF_QIPCRTR; + sq.sq_node = srv->node; + sq.sq_port = srv->port; + + msg.msg_name = (struct sockaddr *)&sq; + msg.msg_namelen = sizeof(sq); + + ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); + if (ret < 0) { + pr_err("failed to send del client cmd\n"); + return ret; + } + } + + return 0; +} + +static int ctrl_cmd_new_server(struct sockaddr_qrtr *from, + unsigned int service, unsigned int instance, + unsigned int node_id, unsigned int port) +{ + struct qrtr_lookup *lookup; + struct qrtr_server *srv; + struct list_head *li; + int ret = 0; + + /* Ignore specified node and port for local servers */ + if (from->sq_node == qrtr_ns.local_node) { + node_id = from->sq_node; + port = from->sq_port; + } + + /* Don't accept spoofed messages */ + if (from->sq_node != node_id) + return -EINVAL; + + srv = server_add(service, instance, node_id, port); + if (!srv) + return -EINVAL; + + if (srv->node == qrtr_ns.local_node) { + ret = service_announce_new(&qrtr_ns.bcast_sq, srv); + if (ret < 0) { + pr_err("failed to announce new service\n"); + return ret; + } + } + + /* Notify any potential lookups about the new server */ + list_for_each(li, &qrtr_ns.lookups) { + lookup = container_of(li, struct qrtr_lookup, li); + if (lookup->service && lookup->service != service) + continue; + if (lookup->instance && lookup->instance != instance) + continue; + + lookup_notify(&lookup->sq, srv, true); + } + + return ret; +} + +static int ctrl_cmd_del_server(struct sockaddr_qrtr *from, + unsigned int service, unsigned int instance, + unsigned int node_id, unsigned int port) +{ + struct qrtr_node *node; + + /* Ignore specified node and port for local servers*/ + if (from->sq_node == qrtr_ns.local_node) { + node_id = from->sq_node; + port = from->sq_port; + } + + /* Don't accept spoofed messages */ + if (from->sq_node != node_id) + return -EINVAL; + + /* Local servers may only unregister themselves */ + if (from->sq_node == qrtr_ns.local_node && from->sq_port != port) + return -EINVAL; + + node = node_get(node_id); + if (!node) + return -ENOENT; + + return server_del(node, port); +} + +static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, + unsigned int service, unsigned int instance) +{ + struct radix_tree_iter node_iter; + struct qrtr_server_filter filter; + struct radix_tree_iter srv_iter; + struct qrtr_lookup *lookup; + struct qrtr_node *node; + void __rcu **node_slot; + void __rcu **srv_slot; + + /* Accept only local observers */ + if (from->sq_node != qrtr_ns.local_node) + return -EINVAL; + + lookup = kzalloc(sizeof(*lookup), GFP_KERNEL); + if (!lookup) + return -ENOMEM; + + lookup->sq = *from; + lookup->service = service; + lookup->instance = instance; + list_add_tail(&lookup->li, &qrtr_ns.lookups); + + memset(&filter, 0, sizeof(filter)); + filter.service = service; + filter.instance = instance; + + radix_tree_for_each_slot(node_slot, &nodes, &node_iter, 0) { + node = radix_tree_deref_slot(node_slot); + + radix_tree_for_each_slot(srv_slot, &node->servers, + &srv_iter, 0) { + struct qrtr_server *srv; + + srv = radix_tree_deref_slot(srv_slot); + if (!server_match(srv, &filter)) + continue; + + lookup_notify(from, srv, true); + } + } + + /* Empty notification, to indicate end of listing */ + lookup_notify(from, NULL, true); + + return 0; +} + +static void ctrl_cmd_del_lookup(struct sockaddr_qrtr *from, + unsigned int service, unsigned int instance) +{ + struct qrtr_lookup *lookup; + struct list_head *tmp; + struct list_head *li; + + list_for_each_safe(li, tmp, &qrtr_ns.lookups) { + lookup = container_of(li, struct qrtr_lookup, li); + if (lookup->sq.sq_node != from->sq_node) + continue; + if (lookup->sq.sq_port != from->sq_port) + continue; + if (lookup->service != service) + continue; + if (lookup->instance && lookup->instance != instance) + continue; + + list_del(&lookup->li); + kfree(lookup); + } +} + +static void qrtr_ns_worker(struct work_struct *work) +{ + const struct qrtr_ctrl_pkt *pkt; + size_t recv_buf_size = 4096; + struct sockaddr_qrtr sq; + struct msghdr msg = { }; + unsigned int cmd; + ssize_t msglen; + void *recv_buf; + struct kvec iv; + int ret; + + msg.msg_name = (struct sockaddr *)&sq; + msg.msg_namelen = sizeof(sq); + + recv_buf = kzalloc(recv_buf_size, GFP_KERNEL); + if (!recv_buf) + return; + + for (;;) { + iv.iov_base = recv_buf; + iv.iov_len = recv_buf_size; + + msglen = kernel_recvmsg(qrtr_ns.sock, &msg, &iv, 1, + iv.iov_len, MSG_DONTWAIT); + + if (msglen == -EAGAIN) + break; + + if (msglen < 0) { + pr_err("error receiving packet: %zd\n", msglen); + break; + } + + pkt = recv_buf; + cmd = le32_to_cpu(pkt->cmd); + if (cmd < ARRAY_SIZE(qrtr_ctrl_pkt_strings) && + qrtr_ctrl_pkt_strings[cmd]) + trace_printk("%s from %d:%d\n", + qrtr_ctrl_pkt_strings[cmd], sq.sq_node, + sq.sq_port); + + ret = 0; + switch (cmd) { + case QRTR_TYPE_HELLO: + ret = ctrl_cmd_hello(&sq); + break; + case QRTR_TYPE_BYE: + ret = ctrl_cmd_bye(&sq); + break; + case QRTR_TYPE_DEL_CLIENT: + ret = ctrl_cmd_del_client(&sq, + le32_to_cpu(pkt->client.node), + le32_to_cpu(pkt->client.port)); + break; + case QRTR_TYPE_NEW_SERVER: + ret = ctrl_cmd_new_server(&sq, + le32_to_cpu(pkt->server.service), + le32_to_cpu(pkt->server.instance), + le32_to_cpu(pkt->server.node), + le32_to_cpu(pkt->server.port)); + break; + case QRTR_TYPE_DEL_SERVER: + ret = ctrl_cmd_del_server(&sq, + le32_to_cpu(pkt->server.service), + le32_to_cpu(pkt->server.instance), + le32_to_cpu(pkt->server.node), + le32_to_cpu(pkt->server.port)); + break; + case QRTR_TYPE_EXIT: + case QRTR_TYPE_PING: + case QRTR_TYPE_RESUME_TX: + break; + case QRTR_TYPE_NEW_LOOKUP: + ret = ctrl_cmd_new_lookup(&sq, + le32_to_cpu(pkt->server.service), + le32_to_cpu(pkt->server.instance)); + break; + case QRTR_TYPE_DEL_LOOKUP: + ctrl_cmd_del_lookup(&sq, + le32_to_cpu(pkt->server.service), + le32_to_cpu(pkt->server.instance)); + break; + } + + if (ret < 0) + pr_err("failed while handling packet from %d:%d", + sq.sq_node, sq.sq_port); + } + + kfree(recv_buf); +} + +static void qrtr_ns_data_ready(struct sock *sk) +{ + queue_work(qrtr_ns.workqueue, &qrtr_ns.work); +} + +void qrtr_ns_init(void) +{ + struct sockaddr_qrtr sq; + int ret; + + INIT_LIST_HEAD(&qrtr_ns.lookups); + INIT_WORK(&qrtr_ns.work, qrtr_ns_worker); + + ret = sock_create_kern(&init_net, AF_QIPCRTR, SOCK_DGRAM, + PF_QIPCRTR, &qrtr_ns.sock); + if (ret < 0) + return; + + ret = kernel_getsockname(qrtr_ns.sock, (struct sockaddr *)&sq); + if (ret < 0) { + pr_err("failed to get socket name\n"); + goto err_sock; + } + + qrtr_ns.sock->sk->sk_data_ready = qrtr_ns_data_ready; + + sq.sq_port = QRTR_PORT_CTRL; + qrtr_ns.local_node = sq.sq_node; + + ret = kernel_bind(qrtr_ns.sock, (struct sockaddr *)&sq, sizeof(sq)); + if (ret < 0) { + pr_err("failed to bind to socket\n"); + goto err_sock; + } + + qrtr_ns.bcast_sq.sq_family = AF_QIPCRTR; + qrtr_ns.bcast_sq.sq_node = QRTR_NODE_BCAST; + qrtr_ns.bcast_sq.sq_port = QRTR_PORT_CTRL; + + qrtr_ns.workqueue = alloc_workqueue("qrtr_ns_handler", WQ_UNBOUND, 1); + if (!qrtr_ns.workqueue) + goto err_sock; + + ret = say_hello(&qrtr_ns.bcast_sq); + if (ret < 0) + goto err_wq; + + return; + +err_wq: + destroy_workqueue(qrtr_ns.workqueue); +err_sock: + sock_release(qrtr_ns.sock); +} +EXPORT_SYMBOL_GPL(qrtr_ns_init); + +void qrtr_ns_remove(void) +{ + cancel_work_sync(&qrtr_ns.work); + destroy_workqueue(qrtr_ns.workqueue); + sock_release(qrtr_ns.sock); +} +EXPORT_SYMBOL_GPL(qrtr_ns_remove); + +MODULE_AUTHOR("Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>"); +MODULE_DESCRIPTION("Qualcomm IPC Router Nameservice"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 5a8e42ad1504..e22092e4a783 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -7,7 +7,6 @@ #include <linux/netlink.h> #include <linux/qrtr.h> #include <linux/termios.h> /* For TIOCINQ/OUTQ */ -#include <linux/numa.h> #include <linux/spinlock.h> #include <linux/wait.h> @@ -96,7 +95,7 @@ static inline struct qrtr_sock *qrtr_sk(struct sock *sk) return container_of(sk, struct qrtr_sock, sk); } -static unsigned int qrtr_local_nid = NUMA_NO_NODE; +static unsigned int qrtr_local_nid = 1; /* for node ids */ static RADIX_TREE(qrtr_nodes, GFP_ATOMIC); @@ -1241,38 +1240,6 @@ static int qrtr_create(struct net *net, struct socket *sock, return 0; } -static const struct nla_policy qrtr_policy[IFA_MAX + 1] = { - [IFA_LOCAL] = { .type = NLA_U32 }, -}; - -static int qrtr_addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct nlattr *tb[IFA_MAX + 1]; - struct ifaddrmsg *ifm; - int rc; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!netlink_capable(skb, CAP_SYS_ADMIN)) - return -EPERM; - - ASSERT_RTNL(); - - rc = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - qrtr_policy, extack); - if (rc < 0) - return rc; - - ifm = nlmsg_data(nlh); - if (!tb[IFA_LOCAL]) - return -EINVAL; - - qrtr_local_nid = nla_get_u32(tb[IFA_LOCAL]); - return 0; -} - static const struct net_proto_family qrtr_family = { .owner = THIS_MODULE, .family = AF_QIPCRTR, @@ -1293,11 +1260,7 @@ static int __init qrtr_proto_init(void) return rc; } - rc = rtnl_register_module(THIS_MODULE, PF_QIPCRTR, RTM_NEWADDR, qrtr_addr_doit, NULL, 0); - if (rc) { - sock_unregister(qrtr_family.family); - proto_unregister(&qrtr_proto); - } + qrtr_ns_init(); return rc; } @@ -1305,7 +1268,7 @@ postcore_initcall(qrtr_proto_init); static void __exit qrtr_proto_fini(void) { - rtnl_unregister(PF_QIPCRTR, RTM_NEWADDR); + qrtr_ns_remove(); sock_unregister(qrtr_family.family); proto_unregister(&qrtr_proto); } diff --git a/net/qrtr/qrtr.h b/net/qrtr/qrtr.h index b81e6953c04b..dc2b67f17927 100644 --- a/net/qrtr/qrtr.h +++ b/net/qrtr/qrtr.h @@ -29,4 +29,8 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep); int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len); +void qrtr_ns_init(void); + +void qrtr_ns_remove(void); + #endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index edde0e519438..bfbefb7bff9d 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -972,7 +972,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" - depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT + depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT && NF_FLOW_TABLE help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 8c466a712cda..aa7b737fed2e 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -185,6 +185,7 @@ static size_t tcf_action_shared_attrs_size(const struct tc_action *act) return nla_total_size(0) /* action number nested */ + nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */ + cookie_len /* TCA_ACT_COOKIE */ + + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_HW_STATS_TYPE */ + nla_total_size(0) /* TCA_ACT_STATS nested */ + nla_total_size(sizeof(struct nla_bitfield32)) /* TCA_ACT_FLAGS */ /* TCA_STATS_BASIC */ @@ -788,6 +789,17 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) } rcu_read_unlock(); + if (a->hw_stats_type != TCA_ACT_HW_STATS_TYPE_ANY) { + struct nla_bitfield32 hw_stats_type = { + a->hw_stats_type, + TCA_ACT_HW_STATS_TYPE_ANY, + }; + + if (nla_put(skb, TCA_ACT_HW_STATS_TYPE, sizeof(hw_stats_type), + &hw_stats_type)) + goto nla_put_failure; + } + if (a->tcfa_flags) { struct nla_bitfield32 flags = { a->tcfa_flags, a->tcfa_flags, }; @@ -854,7 +866,23 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) return c; } +static u8 tcf_action_hw_stats_type_get(struct nlattr *hw_stats_type_attr) +{ + struct nla_bitfield32 hw_stats_type_bf; + + /* If the user did not pass the attr, that means he does + * not care about the type. Return "any" in that case + * which is setting on all supported types. + */ + if (!hw_stats_type_attr) + return TCA_ACT_HW_STATS_TYPE_ANY; + hw_stats_type_bf = nla_get_bitfield32(hw_stats_type_attr); + return hw_stats_type_bf.value; +} + static const u32 tca_act_flags_allowed = TCA_ACT_FLAGS_NO_PERCPU_STATS; +static const u32 tca_act_hw_stats_type_allowed = TCA_ACT_HW_STATS_TYPE_ANY; + static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { [TCA_ACT_KIND] = { .type = NLA_STRING }, [TCA_ACT_INDEX] = { .type = NLA_U32 }, @@ -863,6 +891,8 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { [TCA_ACT_OPTIONS] = { .type = NLA_NESTED }, [TCA_ACT_FLAGS] = { .type = NLA_BITFIELD32, .validation_data = &tca_act_flags_allowed }, + [TCA_ACT_HW_STATS_TYPE] = { .type = NLA_BITFIELD32, + .validation_data = &tca_act_hw_stats_type_allowed }, }; struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, @@ -871,6 +901,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { + u8 hw_stats_type = TCA_ACT_HW_STATS_TYPE_ANY; struct nla_bitfield32 flags = { 0, 0 }; struct tc_action *a; struct tc_action_ops *a_o; @@ -903,6 +934,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, goto err_out; } } + hw_stats_type = + tcf_action_hw_stats_type_get(tb[TCA_ACT_HW_STATS_TYPE]); if (tb[TCA_ACT_FLAGS]) flags = nla_get_bitfield32(tb[TCA_ACT_FLAGS]); } else { @@ -953,6 +986,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (!name && tb[TCA_ACT_COOKIE]) tcf_set_action_cookie(&a->act_cookie, cookie); + if (!name) + a->hw_stats_type = hw_stats_type; + /* module count goes up only when brand new policy is created * if it exists and is only bound to in a_o->init() then * ACT_P_CREATED is not returned (a zero is). diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index f685c0d73708..56b66d215a89 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -15,6 +15,7 @@ #include <linux/pkt_cls.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <linux/rhashtable.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -24,6 +25,7 @@ #include <uapi/linux/tc_act/tc_ct.h> #include <net/tc_act/tc_ct.h> +#include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_zones.h> @@ -31,6 +33,523 @@ #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <uapi/linux/netfilter/nf_nat.h> +static struct workqueue_struct *act_ct_wq; +static struct rhashtable zones_ht; +static DEFINE_MUTEX(zones_mutex); + +struct tcf_ct_flow_table { + struct rhash_head node; /* In zones tables */ + + struct rcu_work rwork; + struct nf_flowtable nf_ft; + refcount_t ref; + u16 zone; + + bool dying; +}; + +static const struct rhashtable_params zones_params = { + .head_offset = offsetof(struct tcf_ct_flow_table, node), + .key_offset = offsetof(struct tcf_ct_flow_table, zone), + .key_len = sizeof_field(struct tcf_ct_flow_table, zone), + .automatic_shrinking = true, +}; + +static struct flow_action_entry * +tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action) +{ + int i = flow_action->num_entries++; + + return &flow_action->entries[i]; +} + +static void tcf_ct_add_mangle_action(struct flow_action *action, + enum flow_action_mangle_base htype, + u32 offset, + u32 mask, + u32 val) +{ + struct flow_action_entry *entry; + + entry = tcf_ct_flow_table_flow_action_get_next(action); + entry->id = FLOW_ACTION_MANGLE; + entry->mangle.htype = htype; + entry->mangle.mask = ~mask; + entry->mangle.offset = offset; + entry->mangle.val = val; +} + +/* The following nat helper functions check if the inverted reverse tuple + * (target) is different then the current dir tuple - meaning nat for ports + * and/or ip is needed, and add the relevant mangle actions. + */ +static void +tcf_ct_flow_table_add_action_nat_ipv4(const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple target, + struct flow_action *action) +{ + if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3))) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4, + offsetof(struct iphdr, saddr), + 0xFFFFFFFF, + be32_to_cpu(target.src.u3.ip)); + if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3))) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4, + offsetof(struct iphdr, daddr), + 0xFFFFFFFF, + be32_to_cpu(target.dst.u3.ip)); +} + +static void +tcf_ct_add_ipv6_addr_mangle_action(struct flow_action *action, + union nf_inet_addr *addr, + u32 offset) +{ + int i; + + for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP6, + i * sizeof(u32) + offset, + 0xFFFFFFFF, be32_to_cpu(addr->ip6[i])); +} + +static void +tcf_ct_flow_table_add_action_nat_ipv6(const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple target, + struct flow_action *action) +{ + if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3))) + tcf_ct_add_ipv6_addr_mangle_action(action, &target.src.u3, + offsetof(struct ipv6hdr, + saddr)); + if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3))) + tcf_ct_add_ipv6_addr_mangle_action(action, &target.dst.u3, + offsetof(struct ipv6hdr, + daddr)); +} + +static void +tcf_ct_flow_table_add_action_nat_tcp(const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple target, + struct flow_action *action) +{ + __be16 target_src = target.src.u.tcp.port; + __be16 target_dst = target.dst.u.tcp.port; + + if (target_src != tuple->src.u.tcp.port) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, + offsetof(struct tcphdr, source), + 0xFFFF, be16_to_cpu(target_src)); + if (target_dst != tuple->dst.u.tcp.port) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, + offsetof(struct tcphdr, dest), + 0xFFFF, be16_to_cpu(target_dst)); +} + +static void +tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple target, + struct flow_action *action) +{ + __be16 target_src = target.src.u.udp.port; + __be16 target_dst = target.dst.u.udp.port; + + if (target_src != tuple->src.u.udp.port) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, + offsetof(struct udphdr, source), + 0xFFFF, be16_to_cpu(target_src)); + if (target_dst != tuple->dst.u.udp.port) + tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, + offsetof(struct udphdr, dest), + 0xFFFF, be16_to_cpu(target_dst)); +} + +static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, + enum ip_conntrack_dir dir, + struct flow_action *action) +{ + struct nf_conn_labels *ct_labels; + struct flow_action_entry *entry; + enum ip_conntrack_info ctinfo; + u32 *act_ct_labels; + + entry = tcf_ct_flow_table_flow_action_get_next(action); + entry->id = FLOW_ACTION_CT_METADATA; +#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) + entry->ct_metadata.mark = ct->mark; +#endif + ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED : + IP_CT_ESTABLISHED_REPLY; + /* aligns with the CT reference on the SKB nf_ct_set */ + entry->ct_metadata.cookie = (unsigned long)ct | ctinfo; + + act_ct_labels = entry->ct_metadata.labels; + ct_labels = nf_ct_labels_find(ct); + if (ct_labels) + memcpy(act_ct_labels, ct_labels->bits, NF_CT_LABELS_MAX_SIZE); + else + memset(act_ct_labels, 0, NF_CT_LABELS_MAX_SIZE); +} + +static int tcf_ct_flow_table_add_action_nat(struct net *net, + struct nf_conn *ct, + enum ip_conntrack_dir dir, + struct flow_action *action) +{ + const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; + struct nf_conntrack_tuple target; + + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); + + switch (tuple->src.l3num) { + case NFPROTO_IPV4: + tcf_ct_flow_table_add_action_nat_ipv4(tuple, target, + action); + break; + case NFPROTO_IPV6: + tcf_ct_flow_table_add_action_nat_ipv6(tuple, target, + action); + break; + default: + return -EOPNOTSUPP; + } + + switch (nf_ct_protonum(ct)) { + case IPPROTO_TCP: + tcf_ct_flow_table_add_action_nat_tcp(tuple, target, action); + break; + case IPPROTO_UDP: + tcf_ct_flow_table_add_action_nat_udp(tuple, target, action); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int tcf_ct_flow_table_fill_actions(struct net *net, + const struct flow_offload *flow, + enum flow_offload_tuple_dir tdir, + struct nf_flow_rule *flow_rule) +{ + struct flow_action *action = &flow_rule->rule->action; + int num_entries = action->num_entries; + struct nf_conn *ct = flow->ct; + enum ip_conntrack_dir dir; + int i, err; + + switch (tdir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + dir = IP_CT_DIR_ORIGINAL; + break; + case FLOW_OFFLOAD_DIR_REPLY: + dir = IP_CT_DIR_REPLY; + break; + default: + return -EOPNOTSUPP; + } + + err = tcf_ct_flow_table_add_action_nat(net, ct, dir, action); + if (err) + goto err_nat; + + tcf_ct_flow_table_add_action_meta(ct, dir, action); + return 0; + +err_nat: + /* Clear filled actions */ + for (i = num_entries; i < action->num_entries; i++) + memset(&action->entries[i], 0, sizeof(action->entries[i])); + action->num_entries = num_entries; + + return err; +} + +static struct nf_flowtable_type flowtable_ct = { + .action = tcf_ct_flow_table_fill_actions, + .owner = THIS_MODULE, +}; + +static int tcf_ct_flow_table_get(struct tcf_ct_params *params) +{ + struct tcf_ct_flow_table *ct_ft; + int err = -ENOMEM; + + mutex_lock(&zones_mutex); + ct_ft = rhashtable_lookup_fast(&zones_ht, ¶ms->zone, zones_params); + if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) + goto out_unlock; + + ct_ft = kzalloc(sizeof(*ct_ft), GFP_KERNEL); + if (!ct_ft) + goto err_alloc; + refcount_set(&ct_ft->ref, 1); + + ct_ft->zone = params->zone; + err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params); + if (err) + goto err_insert; + + ct_ft->nf_ft.type = &flowtable_ct; + ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD; + err = nf_flow_table_init(&ct_ft->nf_ft); + if (err) + goto err_init; + + __module_get(THIS_MODULE); +out_unlock: + params->ct_ft = ct_ft; + params->nf_ft = &ct_ft->nf_ft; + mutex_unlock(&zones_mutex); + + return 0; + +err_init: + rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); +err_insert: + kfree(ct_ft); +err_alloc: + mutex_unlock(&zones_mutex); + return err; +} + +static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) +{ + struct tcf_ct_flow_table *ct_ft; + + ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table, + rwork); + nf_flow_table_free(&ct_ft->nf_ft); + kfree(ct_ft); + + module_put(THIS_MODULE); +} + +static void tcf_ct_flow_table_put(struct tcf_ct_params *params) +{ + struct tcf_ct_flow_table *ct_ft = params->ct_ft; + + if (refcount_dec_and_test(¶ms->ct_ft->ref)) { + rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); + INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work); + queue_rcu_work(act_ct_wq, &ct_ft->rwork); + } +} + +static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, + struct nf_conn *ct, + bool tcp) +{ + struct flow_offload *entry; + int err; + + if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status)) + return; + + entry = flow_offload_alloc(ct); + if (!entry) { + WARN_ON_ONCE(1); + goto err_alloc; + } + + if (tcp) { + ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; + ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; + } + + err = flow_offload_add(&ct_ft->nf_ft, entry); + if (err) + goto err_add; + + return; + +err_add: + flow_offload_free(entry); +err_alloc: + clear_bit(IPS_OFFLOAD_BIT, &ct->status); +} + +static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + bool tcp = false; + + if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) + return; + + switch (nf_ct_protonum(ct)) { + case IPPROTO_TCP: + tcp = true; + if (ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED) + return; + break; + case IPPROTO_UDP: + break; + default: + return; + } + + if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || + ct->status & IPS_SEQ_ADJUST) + return; + + tcf_ct_flow_table_add(ct_ft, ct, tcp); +} + +static bool +tcf_ct_flow_table_fill_tuple_ipv4(struct sk_buff *skb, + struct flow_offload_tuple *tuple, + struct tcphdr **tcph) +{ + struct flow_ports *ports; + unsigned int thoff; + struct iphdr *iph; + + if (!pskb_network_may_pull(skb, sizeof(*iph))) + return false; + + iph = ip_hdr(skb); + thoff = iph->ihl * 4; + + if (ip_is_fragment(iph) || + unlikely(thoff != sizeof(struct iphdr))) + return false; + + if (iph->protocol != IPPROTO_TCP && + iph->protocol != IPPROTO_UDP) + return false; + + if (iph->ttl <= 1) + return false; + + if (!pskb_network_may_pull(skb, iph->protocol == IPPROTO_TCP ? + thoff + sizeof(struct tcphdr) : + thoff + sizeof(*ports))) + return false; + + iph = ip_hdr(skb); + if (iph->protocol == IPPROTO_TCP) + *tcph = (void *)(skb_network_header(skb) + thoff); + + ports = (struct flow_ports *)(skb_network_header(skb) + thoff); + tuple->src_v4.s_addr = iph->saddr; + tuple->dst_v4.s_addr = iph->daddr; + tuple->src_port = ports->source; + tuple->dst_port = ports->dest; + tuple->l3proto = AF_INET; + tuple->l4proto = iph->protocol; + + return true; +} + +static bool +tcf_ct_flow_table_fill_tuple_ipv6(struct sk_buff *skb, + struct flow_offload_tuple *tuple, + struct tcphdr **tcph) +{ + struct flow_ports *ports; + struct ipv6hdr *ip6h; + unsigned int thoff; + + if (!pskb_network_may_pull(skb, sizeof(*ip6h))) + return false; + + ip6h = ipv6_hdr(skb); + + if (ip6h->nexthdr != IPPROTO_TCP && + ip6h->nexthdr != IPPROTO_UDP) + return false; + + if (ip6h->hop_limit <= 1) + return false; + + thoff = sizeof(*ip6h); + if (!pskb_network_may_pull(skb, ip6h->nexthdr == IPPROTO_TCP ? + thoff + sizeof(struct tcphdr) : + thoff + sizeof(*ports))) + return false; + + ip6h = ipv6_hdr(skb); + if (ip6h->nexthdr == IPPROTO_TCP) + *tcph = (void *)(skb_network_header(skb) + thoff); + + ports = (struct flow_ports *)(skb_network_header(skb) + thoff); + tuple->src_v6 = ip6h->saddr; + tuple->dst_v6 = ip6h->daddr; + tuple->src_port = ports->source; + tuple->dst_port = ports->dest; + tuple->l3proto = AF_INET6; + tuple->l4proto = ip6h->nexthdr; + + return true; +} + +static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, + struct sk_buff *skb, + u8 family) +{ + struct nf_flowtable *nf_ft = &p->ct_ft->nf_ft; + struct flow_offload_tuple_rhash *tuplehash; + struct flow_offload_tuple tuple = {}; + enum ip_conntrack_info ctinfo; + struct tcphdr *tcph = NULL; + struct flow_offload *flow; + struct nf_conn *ct; + u8 dir; + + /* Previously seen or loopback */ + ct = nf_ct_get(skb, &ctinfo); + if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED) + return false; + + switch (family) { + case NFPROTO_IPV4: + if (!tcf_ct_flow_table_fill_tuple_ipv4(skb, &tuple, &tcph)) + return false; + break; + case NFPROTO_IPV6: + if (!tcf_ct_flow_table_fill_tuple_ipv6(skb, &tuple, &tcph)) + return false; + break; + default: + return false; + } + + tuplehash = flow_offload_lookup(nf_ft, &tuple); + if (!tuplehash) + return false; + + dir = tuplehash->tuple.dir; + flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); + ct = flow->ct; + + if (tcph && (unlikely(tcph->fin || tcph->rst))) { + flow_offload_teardown(flow); + return false; + } + + ctinfo = dir == FLOW_OFFLOAD_DIR_ORIGINAL ? IP_CT_ESTABLISHED : + IP_CT_ESTABLISHED_REPLY; + + flow_offload_refresh(nf_ft, flow); + nf_conntrack_get(&ct->ct_general); + nf_ct_set(skb, ct, ctinfo); + + return true; +} + +static int tcf_ct_flow_tables_init(void) +{ + return rhashtable_init(&zones_ht, &zones_params); +} + +static void tcf_ct_flow_tables_uninit(void) +{ + rhashtable_destroy(&zones_ht); +} + static struct tc_action_ops act_ct_ops; static unsigned int ct_net_id; @@ -207,6 +726,8 @@ static void tcf_ct_params_free(struct rcu_head *head) struct tcf_ct_params *params = container_of(head, struct tcf_ct_params, rcu); + tcf_ct_flow_table_put(params); + if (params->tmpl) nf_conntrack_put(¶ms->tmpl->ct_general); kfree(params); @@ -387,6 +908,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, struct nf_hook_state state; int nh_ofs, err, retval; struct tcf_ct_params *p; + bool skip_add = false; struct nf_conn *ct; u8 family; @@ -436,6 +958,11 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, */ cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force); if (!cached) { + if (!commit && tcf_ct_flow_table_lookup(p, skb, family)) { + skip_add = true; + goto do_nat; + } + /* Associate skb with specified zone. */ if (tmpl) { ct = nf_ct_get(skb, &ctinfo); @@ -453,6 +980,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, goto out_push; } +do_nat: ct = nf_ct_get(skb, &ctinfo); if (!ct) goto out_push; @@ -470,6 +998,8 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, * even if the connection is already confirmed. */ nf_conntrack_confirm(skb); + } else if (!skip_add) { + tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo); } out_push: @@ -730,6 +1260,10 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, if (err) goto cleanup; + err = tcf_ct_flow_table_get(params); + if (err) + goto cleanup; + spin_lock_bh(&c->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); params = rcu_replace_pointer(c->params, params, @@ -974,13 +1508,46 @@ static struct pernet_operations ct_net_ops = { static int __init ct_init_module(void) { - return tcf_register_action(&act_ct_ops, &ct_net_ops); + int err; + + act_ct_wq = alloc_ordered_workqueue("act_ct_workqueue", 0); + if (!act_ct_wq) + return -ENOMEM; + + err = tcf_ct_flow_tables_init(); + if (err) + goto err_tbl_init; + + err = tcf_register_action(&act_ct_ops, &ct_net_ops); + if (err) + goto err_register; + + return 0; + +err_tbl_init: + destroy_workqueue(act_ct_wq); +err_register: + tcf_ct_flow_tables_uninit(); + return err; } static void __exit ct_cleanup_module(void) { tcf_unregister_action(&act_ct_ops, &ct_net_ops); + tcf_ct_flow_tables_uninit(); + destroy_workqueue(act_ct_wq); +} + +void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie) +{ + enum ip_conntrack_info ctinfo = cookie & NFCT_INFOMASK; + struct nf_conn *ct; + + ct = (struct nf_conn *)(cookie & NFCT_PTRMASK); + nf_conntrack_get(&ct->ct_general); + nf_ct_set(skb, ct, ctinfo); } +EXPORT_SYMBOL_GPL(tcf_ct_flow_table_restore_skb); module_init(ct_init_module); module_exit(ct_cleanup_module); diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index ce948c1e24dc..5e2df590bb58 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -267,14 +267,12 @@ tcf_sample_get_group(const struct tc_action *a, struct tcf_sample *s = to_sample(a); struct psample_group *group; - spin_lock_bh(&s->tcf_lock); group = rcu_dereference_protected(s->psample_group, lockdep_is_held(&s->tcf_lock)); if (group) { psample_group_take(group); *destructor = tcf_psample_group_put; } - spin_unlock_bh(&s->tcf_lock); return group; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index c2cdd0fc2e70..2046102a763e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -22,6 +22,7 @@ #include <linux/idr.h> #include <linux/rhashtable.h> #include <linux/jhash.h> +#include <linux/rculist.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -354,7 +355,7 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block, chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (!chain) return NULL; - list_add_tail(&chain->list, &block->chain_list); + list_add_tail_rcu(&chain->list, &block->chain_list); mutex_init(&chain->filter_chain_lock); chain->block = block; chain->index = chain_index; @@ -394,7 +395,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain) ASSERT_BLOCK_LOCKED(block); - list_del(&chain->list); + list_del_rcu(&chain->list); if (!chain->index) block->chain0.chain = NULL; @@ -453,6 +454,20 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block, return NULL; } +#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) +static struct tcf_chain *tcf_chain_lookup_rcu(const struct tcf_block *block, + u32 chain_index) +{ + struct tcf_chain *chain; + + list_for_each_entry_rcu(chain, &block->chain_list, list) { + if (chain->index == chain_index) + return chain; + } + return NULL; +} +#endif + static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, u32 seq, u16 flags, int event, bool unicast); @@ -1559,12 +1574,15 @@ static int tcf_block_setup(struct tcf_block *block, * to this qdisc, (optionally) tests for protocol and asks * specific classifiers. */ -int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res, bool compat_mode) +static inline int __tcf_classify(struct sk_buff *skb, + const struct tcf_proto *tp, + const struct tcf_proto *orig_tp, + struct tcf_result *res, + bool compat_mode, + u32 *last_executed_chain) { #ifdef CONFIG_NET_CLS_ACT const int max_reclassify_loop = 4; - const struct tcf_proto *orig_tp = tp; const struct tcf_proto *first_tp; int limit = 0; @@ -1582,21 +1600,11 @@ reclassify: #ifdef CONFIG_NET_CLS_ACT if (unlikely(err == TC_ACT_RECLASSIFY && !compat_mode)) { first_tp = orig_tp; + *last_executed_chain = first_tp->chain->index; goto reset; } else if (unlikely(TC_ACT_EXT_CMP(err, TC_ACT_GOTO_CHAIN))) { first_tp = res->goto_tp; - -#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - { - struct tc_skb_ext *ext; - - ext = skb_ext_add(skb, TC_SKB_EXT); - if (WARN_ON_ONCE(!ext)) - return TC_ACT_SHOT; - - ext->chain = err & TC_ACT_EXT_VAL_MASK; - } -#endif + *last_executed_chain = err & TC_ACT_EXT_VAL_MASK; goto reset; } #endif @@ -1619,8 +1627,64 @@ reset: goto reclassify; #endif } + +int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ + u32 last_executed_chain = 0; + + return __tcf_classify(skb, tp, tp, res, compat_mode, + &last_executed_chain); +} EXPORT_SYMBOL(tcf_classify); +int tcf_classify_ingress(struct sk_buff *skb, + const struct tcf_block *ingress_block, + const struct tcf_proto *tp, + struct tcf_result *res, bool compat_mode) +{ +#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + u32 last_executed_chain = 0; + + return __tcf_classify(skb, tp, tp, res, compat_mode, + &last_executed_chain); +#else + u32 last_executed_chain = tp ? tp->chain->index : 0; + const struct tcf_proto *orig_tp = tp; + struct tc_skb_ext *ext; + int ret; + + ext = skb_ext_find(skb, TC_SKB_EXT); + + if (ext && ext->chain) { + struct tcf_chain *fchain; + + fchain = tcf_chain_lookup_rcu(ingress_block, ext->chain); + if (!fchain) + return TC_ACT_SHOT; + + /* Consume, so cloned/redirect skbs won't inherit ext */ + skb_ext_del(skb, TC_SKB_EXT); + + tp = rcu_dereference_bh(fchain->filter_chain); + } + + ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode, + &last_executed_chain); + + /* If we missed on some chain */ + if (ret == TC_ACT_UNSPEC && last_executed_chain) { + ext = skb_ext_add(skb, TC_SKB_EXT); + if (WARN_ON_ONCE(!ext)) + return TC_ACT_SHOT; + ext->chain = last_executed_chain; + } + + return ret; +#endif +} +EXPORT_SYMBOL(tcf_classify_ingress); + struct tcf_chain_info { struct tcf_proto __rcu **pprev; struct tcf_proto __rcu *next; @@ -3382,14 +3446,40 @@ int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp, } EXPORT_SYMBOL(tc_setup_cb_reoffload); +static int tcf_act_get_cookie(struct flow_action_entry *entry, + const struct tc_action *act) +{ + struct tc_cookie *cookie; + int err = 0; + + rcu_read_lock(); + cookie = rcu_dereference(act->act_cookie); + if (cookie) { + entry->cookie = flow_action_cookie_create(cookie->data, + cookie->len, + GFP_ATOMIC); + if (!entry->cookie) + err = -ENOMEM; + } + rcu_read_unlock(); + return err; +} + +static void tcf_act_put_cookie(struct flow_action_entry *entry) +{ + flow_action_cookie_destroy(entry->cookie); +} + void tc_cleanup_flow_action(struct flow_action *flow_action) { struct flow_action_entry *entry; int i; - flow_action_for_each(i, entry, flow_action) + flow_action_for_each(i, entry, flow_action) { + tcf_act_put_cookie(entry); if (entry->destructor) entry->destructor(entry->destructor_priv); + } } EXPORT_SYMBOL(tc_cleanup_flow_action); @@ -3433,22 +3523,30 @@ static void tcf_sample_get_group(struct flow_action_entry *entry, } int tc_setup_flow_action(struct flow_action *flow_action, - const struct tcf_exts *exts, bool rtnl_held) + const struct tcf_exts *exts) { - const struct tc_action *act; + struct tc_action *act; int i, j, k, err = 0; + BUILD_BUG_ON(TCA_ACT_HW_STATS_TYPE_ANY != FLOW_ACTION_HW_STATS_TYPE_ANY); + BUILD_BUG_ON(TCA_ACT_HW_STATS_TYPE_IMMEDIATE != FLOW_ACTION_HW_STATS_TYPE_IMMEDIATE); + BUILD_BUG_ON(TCA_ACT_HW_STATS_TYPE_DELAYED != FLOW_ACTION_HW_STATS_TYPE_DELAYED); + if (!exts) return 0; - if (!rtnl_held) - rtnl_lock(); - j = 0; tcf_exts_for_each_action(i, act, exts) { struct flow_action_entry *entry; entry = &flow_action->entries[j]; + spin_lock_bh(&act->tcfa_lock); + err = tcf_act_get_cookie(entry, act); + if (err) + goto err_out_locked; + + entry->hw_stats_type = act->hw_stats_type; + if (is_tcf_gact_ok(act)) { entry->id = FLOW_ACTION_ACCEPT; } else if (is_tcf_gact_shot(act)) { @@ -3489,13 +3587,13 @@ int tc_setup_flow_action(struct flow_action *flow_action, break; default: err = -EOPNOTSUPP; - goto err_out; + goto err_out_locked; } } else if (is_tcf_tunnel_set(act)) { entry->id = FLOW_ACTION_TUNNEL_ENCAP; err = tcf_tunnel_encap_get_tunnel(entry, act); if (err) - goto err_out; + goto err_out_locked; } else if (is_tcf_tunnel_release(act)) { entry->id = FLOW_ACTION_TUNNEL_DECAP; } else if (is_tcf_pedit(act)) { @@ -3509,7 +3607,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, break; default: err = -EOPNOTSUPP; - goto err_out; + goto err_out_locked; } entry->mangle.htype = tcf_pedit_htype(act, k); entry->mangle.mask = tcf_pedit_mask(act, k); @@ -3538,6 +3636,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->id = FLOW_ACTION_CT; entry->ct.action = tcf_ct_action(act); entry->ct.zone = tcf_ct_zone(act); + entry->ct.flow_table = tcf_ct_ft(act); } else if (is_tcf_mpls(act)) { switch (tcf_mpls_action(act)) { case TCA_MPLS_ACT_PUSH: @@ -3560,28 +3659,29 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->mpls_mangle.ttl = tcf_mpls_ttl(act); break; default: - goto err_out; + goto err_out_locked; } } else if (is_tcf_skbedit_ptype(act)) { entry->id = FLOW_ACTION_PTYPE; entry->ptype = tcf_skbedit_ptype(act); } else { err = -EOPNOTSUPP; - goto err_out; + goto err_out_locked; } + spin_unlock_bh(&act->tcfa_lock); if (!is_tcf_pedit(act)) j++; } err_out: - if (!rtnl_held) - rtnl_unlock(); - if (err) tc_cleanup_flow_action(flow_action); return err; +err_out_locked: + spin_unlock_bh(&act->tcfa_lock); + goto err_out; } EXPORT_SYMBOL(tc_setup_flow_action); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index d32d4233d337..258dc45ab7e3 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -450,8 +450,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.rule->match.key = &f->mkey; cls_flower.classid = f->res.classid; - err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts, - rtnl_held); + err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); if (err) { kfree(cls_flower.rule); if (skip_sw) { @@ -2001,8 +2000,7 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, cls_flower.rule->match.mask = &f->mask->key; cls_flower.rule->match.key = &f->mkey; - err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts, - true); + err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); if (err) { kfree(cls_flower.rule); if (tc_skip_sw(f->flags)) { diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 610a0b728161..a34b36adb9b7 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -97,7 +97,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, cls_mall.command = TC_CLSMATCHALL_REPLACE; cls_mall.cookie = cookie; - err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts, true); + err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts); if (err) { kfree(cls_mall.rule); mall_destroy_hw_filter(tp, head, cookie, NULL); @@ -302,7 +302,7 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY; cls_mall.cookie = (unsigned long)head; - err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts, true); + err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts); if (err) { kfree(cls_mall.rule); if (add && tc_skip_sw(head->flags)) { diff --git a/net/sched/em_ipt.c b/net/sched/em_ipt.c index 9fff6480acc6..eecfe072c508 100644 --- a/net/sched/em_ipt.c +++ b/net/sched/em_ipt.c @@ -22,7 +22,7 @@ struct em_ipt_match { const struct xt_match *match; u32 hook; u8 nfproto; - u8 match_data[0] __aligned(8); + u8 match_data[] __aligned(8); }; struct em_ipt_xt_match { diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index 88c7ce42df7e..2c1192a2ee5e 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -16,7 +16,7 @@ struct nbyte_data { struct tcf_em_nbyte hdr; - char pattern[0]; + char pattern[]; }; static int em_nbyte_change(struct net *net, void *data, int data_len, diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index f4f9b8cdbffb..ee12ca9f55b4 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -58,7 +58,7 @@ struct atm_flow_data { struct atm_flow_data *excess; /* flow for excess traffic; NULL to set CLP instead */ int hdr_len; - unsigned char hdr[0]; /* header data; MUST BE LAST */ + unsigned char hdr[]; /* header data; MUST BE LAST */ }; struct atm_qdisc_data { diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 37c8aa75d70c..a579a4131d22 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -12,6 +12,7 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> /* 1 band FIFO pseudo-"scheduler" */ @@ -51,8 +52,49 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, return NET_XMIT_CN; } -static int fifo_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) +static void fifo_offload_init(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_fifo_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_FIFO_REPLACE; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_FIFO, &qopt); +} + +static void fifo_offload_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct tc_fifo_qopt_offload qopt; + + if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) + return; + + qopt.command = TC_FIFO_DESTROY; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_FIFO, &qopt); +} + +static int fifo_offload_dump(struct Qdisc *sch) +{ + struct tc_fifo_qopt_offload qopt; + + qopt.command = TC_FIFO_STATS; + qopt.handle = sch->handle; + qopt.parent = sch->parent; + qopt.stats.bstats = &sch->bstats; + qopt.stats.qstats = &sch->qstats; + + return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_FIFO, &qopt); +} + +static int __fifo_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) { bool bypass; bool is_bfifo = sch->ops == &bfifo_qdisc_ops; @@ -82,10 +124,35 @@ static int fifo_init(struct Qdisc *sch, struct nlattr *opt, sch->flags |= TCQ_F_CAN_BYPASS; else sch->flags &= ~TCQ_F_CAN_BYPASS; + return 0; } -static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb) +static int fifo_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + int err; + + err = __fifo_init(sch, opt, extack); + if (err) + return err; + + fifo_offload_init(sch); + return 0; +} + +static int fifo_hd_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + return __fifo_init(sch, opt, extack); +} + +static void fifo_destroy(struct Qdisc *sch) +{ + fifo_offload_destroy(sch); +} + +static int __fifo_dump(struct Qdisc *sch, struct sk_buff *skb) { struct tc_fifo_qopt opt = { .limit = sch->limit }; @@ -97,6 +164,22 @@ nla_put_failure: return -1; } +static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + int err; + + err = fifo_offload_dump(sch); + if (err) + return err; + + return __fifo_dump(sch, skb); +} + +static int fifo_hd_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + return __fifo_dump(sch, skb); +} + struct Qdisc_ops pfifo_qdisc_ops __read_mostly = { .id = "pfifo", .priv_size = 0, @@ -104,6 +187,7 @@ struct Qdisc_ops pfifo_qdisc_ops __read_mostly = { .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, .init = fifo_init, + .destroy = fifo_destroy, .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, @@ -118,6 +202,7 @@ struct Qdisc_ops bfifo_qdisc_ops __read_mostly = { .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, .init = fifo_init, + .destroy = fifo_destroy, .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, @@ -131,10 +216,10 @@ struct Qdisc_ops pfifo_head_drop_qdisc_ops __read_mostly = { .enqueue = pfifo_tail_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, - .init = fifo_init, + .init = fifo_hd_init, .reset = qdisc_reset_queue, - .change = fifo_init, - .dump = fifo_dump, + .change = fifo_hd_init, + .dump = fifo_hd_dump, .owner = THIS_MODULE, }; diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 214657eb3dfd..a9da8776bf5b 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -189,7 +189,6 @@ static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, out: q->stats.dropped++; sel_flow->vars.accu_prob = 0; - sel_flow->vars.accu_prob_overflows = 0; __qdisc_drop(skb, to_free); qdisc_qstats_drop(sch); return NET_XMIT_CN; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 6c9595f1048a..2efd5b61acef 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1391,6 +1391,14 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, } EXPORT_SYMBOL(mini_qdisc_pair_swap); +void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, + struct tcf_block *block) +{ + miniqp->miniq1.block = block; + miniqp->miniq2.block = block; +} +EXPORT_SYMBOL(mini_qdisc_pair_block_init); + void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, struct mini_Qdisc __rcu **p_miniq) { diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index bf56aa519797..84838128b9c5 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -78,6 +78,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, { struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); + int err; net_inc_ingress_queue(); @@ -87,7 +88,13 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, q->block_info.chain_head_change = clsact_chain_head_change; q->block_info.chain_head_change_priv = &q->miniqp; - return tcf_block_get_ext(&q->block, sch, &q->block_info, extack); + err = tcf_block_get_ext(&q->block, sch, &q->block_info, extack); + if (err) + return err; + + mini_qdisc_pair_block_init(&q->miniqp, q->block); + + return 0; } static void ingress_destroy(struct Qdisc *sch) @@ -226,6 +233,8 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, if (err) return err; + mini_qdisc_pair_block_init(&q->miniqp_ingress, q->ingress_block); + mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress); q->egress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 42e557d48e4e..84f82771cdf5 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -66,7 +66,7 @@ struct disttable { u32 size; - s16 table[0]; + s16 table[]; }; struct netem_sched_data { diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index 915bcdb59a9f..c65077f0c0f3 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -31,7 +31,7 @@ struct pie_sched_data { }; bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, - struct pie_vars *vars, u32 qlen, u32 packet_size) + struct pie_vars *vars, u32 backlog, u32 packet_size) { u64 rnd; u64 local_prob = vars->prob; @@ -51,7 +51,7 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, /* If we have fewer than 2 mtu-sized packets, disable pie_drop_early, * similar to min_th in RED */ - if (qlen < 2 * mtu) + if (backlog < 2 * mtu) return false; /* If bytemode is turned on, use packet size to compute new @@ -62,27 +62,19 @@ bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, else local_prob = vars->prob; - if (local_prob == 0) { + if (local_prob == 0) vars->accu_prob = 0; - vars->accu_prob_overflows = 0; - } - - if (local_prob > MAX_PROB - vars->accu_prob) - vars->accu_prob_overflows++; - - vars->accu_prob += local_prob; + else + vars->accu_prob += local_prob; - if (vars->accu_prob_overflows == 0 && - vars->accu_prob < (MAX_PROB / 100) * 85) + if (vars->accu_prob < (MAX_PROB / 100) * 85) return false; - if (vars->accu_prob_overflows == 8 && - vars->accu_prob >= MAX_PROB / 2) + if (vars->accu_prob >= (MAX_PROB / 2) * 17) return true; prandom_bytes(&rnd, 8); - if (rnd < local_prob) { + if ((rnd >> BITS_PER_BYTE) < local_prob) { vars->accu_prob = 0; - vars->accu_prob_overflows = 0; return true; } @@ -129,7 +121,6 @@ static int pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, out: q->stats.dropped++; q->vars.accu_prob = 0; - q->vars.accu_prob_overflows = 0; return qdisc_drop(skb, sch, to_free); } @@ -215,7 +206,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, } void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, - struct pie_vars *vars, u32 qlen) + struct pie_vars *vars, u32 backlog) { psched_time_t now = psched_get_time(); u32 dtime = 0; @@ -231,7 +222,7 @@ void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, vars->dq_tstamp = now; - if (qlen == 0) + if (backlog == 0) vars->qdelay = 0; if (dtime == 0) @@ -244,7 +235,7 @@ void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, * we have enough packets to calculate the drain rate. Save * current time as dq_tstamp and start measurement cycle. */ - if (qlen >= QUEUE_THRESHOLD && vars->dq_count == DQCOUNT_INVALID) { + if (backlog >= QUEUE_THRESHOLD && vars->dq_count == DQCOUNT_INVALID) { vars->dq_tstamp = psched_get_time(); vars->dq_count = 0; } @@ -283,7 +274,7 @@ void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, * dq_count to 0 to re-enter the if block when the next * packet is dequeued */ - if (qlen < QUEUE_THRESHOLD) { + if (backlog < QUEUE_THRESHOLD) { vars->dq_count = DQCOUNT_INVALID; } else { vars->dq_count = 0; @@ -307,7 +298,7 @@ burst_allowance_reduction: EXPORT_SYMBOL_GPL(pie_process_dequeue); void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, - u32 qlen) + u32 backlog) { psched_time_t qdelay = 0; /* in pschedtime */ psched_time_t qdelay_old = 0; /* in pschedtime */ @@ -322,7 +313,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, vars->qdelay_old = vars->qdelay; if (vars->avg_dq_rate > 0) - qdelay = (qlen << PIE_SCALE) / vars->avg_dq_rate; + qdelay = (backlog << PIE_SCALE) / vars->avg_dq_rate; else qdelay = 0; } else { @@ -330,10 +321,10 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, qdelay_old = vars->qdelay_old; } - /* If qdelay is zero and qlen is not, it means qlen is very small, + /* If qdelay is zero and backlog is not, it means backlog is very small, * so we do not update probabilty in this round. */ - if (qdelay == 0 && qlen != 0) + if (qdelay == 0 && backlog != 0) update_prob = false; /* In the algorithm, alpha and beta are between 0 and 2 with typical @@ -363,8 +354,8 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, } /* alpha and beta should be between 0 and 32, in multiples of 1/16 */ - delta += alpha * (u64)(qdelay - params->target); - delta += beta * (u64)(qdelay - qdelay_old); + delta += alpha * (qdelay - params->target); + delta += beta * (qdelay - qdelay_old); oldprob = vars->prob; @@ -409,7 +400,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, vars->prob -= vars->prob / 64; vars->qdelay = qdelay; - vars->qlen_old = qlen; + vars->backlog_old = backlog; /* We restart the measurement cycle if the following conditions are met * 1. If the delay has been low for 2 consecutive Tupdate periods @@ -502,7 +493,7 @@ static int pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct pie_sched_data *q = qdisc_priv(sch); struct tc_pie_xstats st = { - .prob = q->vars.prob, + .prob = q->vars.prob << BITS_PER_BYTE, .delay = ((u32)PSCHED_TICKS2NS(q->vars.qdelay)) / NSEC_PER_USEC, .packets_in = q->stats.packets_in, diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 1069d7af3672..493fc01e5d2b 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -428,11 +428,12 @@ static void sctp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, sctp_get_sctp_info(sk, infox->asoc, infox->sctpinfo); } -static int sctp_diag_dump_one(struct sk_buff *in_skb, - const struct nlmsghdr *nlh, +static int sctp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { + struct sk_buff *in_skb = cb->skb; struct net *net = sock_net(in_skb->sk); + const struct nlmsghdr *nlh = cb->nlh; union sctp_addr laddr, paddr; struct sctp_comm_param commp = { .skb = in_skb, @@ -466,7 +467,7 @@ static int sctp_diag_dump_one(struct sk_buff *in_skb, } static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, - const struct inet_diag_req_v2 *r, struct nlattr *bc) + const struct inet_diag_req_v2 *r) { u32 idiag_states = r->idiag_states; struct net *net = sock_net(skb->sk); diff --git a/net/sctp/input.c b/net/sctp/input.c index efaaefc3bb1c..55d4fc6f371d 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -548,6 +548,7 @@ out: /* Common cleanup code for icmp/icmpv6 error handler. */ void sctp_err_finish(struct sock *sk, struct sctp_transport *t) + __releases(&((__sk)->sk_lock.slock)) { bh_unlock_sock(sk); sctp_transport_put(t); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1b56fc440606..fed26a1e9518 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5333,14 +5333,14 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, EXPORT_SYMBOL_GPL(sctp_get_sctp_info); /* use callback to avoid exporting the core structure */ -void sctp_transport_walk_start(struct rhashtable_iter *iter) +void sctp_transport_walk_start(struct rhashtable_iter *iter) __acquires(RCU) { rhltable_walk_enter(&sctp_transport_hashtable, iter); rhashtable_walk_start(iter); } -void sctp_transport_walk_stop(struct rhashtable_iter *iter) +void sctp_transport_walk_stop(struct rhashtable_iter *iter) __releases(RCU) { rhashtable_walk_stop(iter); rhashtable_walk_exit(iter); diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 86cccc24e52e..ea0068f0173c 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -349,7 +349,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, smc->peer_diagnosis = ntohl(dclc->peer_diagnosis); if (((struct smc_clc_msg_decline *)buf)->hdr.flag) { smc->conn.lgr->sync_err = 1; - smc_lgr_terminate(smc->conn.lgr, true); + smc_lgr_terminate_sched(smc->conn.lgr); } } @@ -372,7 +372,8 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); dclc.hdr.version = SMC_CLC_V1; dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0; - if (smc->conn.lgr && !smc->conn.lgr->is_smcd) + if ((!smc->conn.lgr || !smc->conn.lgr->is_smcd) && + smc_ib_is_valid_local_systemid()) memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid)); dclc.peer_diagnosis = htonl(peer_diag_info); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 5b085efa3bce..824c5211b027 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -46,6 +46,7 @@ static DECLARE_WAIT_QUEUE_HEAD(lgrs_deleted); static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc); +static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft); /* return head of link group list and its lock for a given link group */ static inline struct list_head *smc_lgr_list_head(struct smc_link_group *lgr, @@ -241,7 +242,7 @@ static void smc_lgr_terminate_work(struct work_struct *work) struct smc_link_group *lgr = container_of(work, struct smc_link_group, terminate_work); - smc_lgr_terminate(lgr, true); + __smc_lgr_terminate(lgr, true); } /* create a new SMC link group */ @@ -588,15 +589,15 @@ static void smc_lgr_cleanup(struct smc_link_group *lgr) } else { struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK]; - wake_up(&lnk->wr_reg_wait); - if (lnk->state != SMC_LNK_INACTIVE) { - smc_link_send_delete(lnk, false); + if (lnk->state != SMC_LNK_INACTIVE) smc_llc_link_inactive(lnk); - } } } -/* terminate link group */ +/* terminate link group + * @soft: true if link group shutdown can take its time + * false if immediate link group shutdown is required + */ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) { struct smc_connection *conn; @@ -634,25 +635,20 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) smc_lgr_free(lgr); } -/* unlink and terminate link group - * @soft: true if link group shutdown can take its time - * false if immediate link group shutdown is required - */ -void smc_lgr_terminate(struct smc_link_group *lgr, bool soft) +/* unlink link group and schedule termination */ +void smc_lgr_terminate_sched(struct smc_link_group *lgr) { spinlock_t *lgr_lock; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); - if (lgr->terminating) { + if (list_empty(&lgr->list) || lgr->terminating || lgr->freeing) { spin_unlock_bh(lgr_lock); return; /* lgr already terminating */ } - if (!soft) - lgr->freeing = 1; list_del_init(&lgr->list); spin_unlock_bh(lgr_lock); - __smc_lgr_terminate(lgr, soft); + schedule_work(&lgr->terminate_work); } /* Called when IB port is terminated */ diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 234ae25f0025..8041db20c753 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -285,19 +285,13 @@ static inline struct smc_connection *smc_lgr_find_conn( return res; } -static inline void smc_lgr_terminate_sched(struct smc_link_group *lgr) -{ - if (!lgr->terminating && !lgr->freeing) - schedule_work(&lgr->terminate_work); -} - struct smc_sock; struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; void smc_lgr_forget(struct smc_link_group *lgr); void smc_lgr_cleanup_early(struct smc_connection *conn); -void smc_lgr_terminate(struct smc_link_group *lgr, bool soft); +void smc_lgr_terminate_sched(struct smc_link_group *lgr); void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan); diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 05b825b3cfa4..04b6fefb8bce 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -37,11 +37,7 @@ struct smc_ib_devices smc_ib_devices = { /* smc-registered ib devices */ .list = LIST_HEAD_INIT(smc_ib_devices.list), }; -#define SMC_LOCAL_SYSTEMID_RESET "%%%%%%%" - -u8 local_systemid[SMC_SYSTEMID_LEN] = SMC_LOCAL_SYSTEMID_RESET; /* unique system - * identifier - */ +u8 local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */ static int smc_ib_modify_qp_init(struct smc_link *lnk) { @@ -168,6 +164,15 @@ static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev, { memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1], sizeof(smcibdev->mac[ibport - 1])); +} + +bool smc_ib_is_valid_local_systemid(void) +{ + return !is_zero_ether_addr(&local_systemid[2]); +} + +static void smc_ib_init_local_systemid(void) +{ get_random_bytes(&local_systemid[0], 2); } @@ -224,8 +229,7 @@ static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) rc = smc_ib_fill_mac(smcibdev, ibport); if (rc) goto out; - if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET, - sizeof(local_systemid)) && + if (!smc_ib_is_valid_local_systemid() && smc_ib_port_active(smcibdev, ibport)) /* create unique system identifier */ smc_ib_define_local_systemid(smcibdev, ibport); @@ -257,6 +261,7 @@ static void smc_ib_global_event_handler(struct ib_event_handler *handler, struct ib_event *ibevent) { struct smc_ib_device *smcibdev; + bool schedule = false; u8 port_idx; smcibdev = container_of(handler, struct smc_ib_device, event_handler); @@ -266,22 +271,35 @@ static void smc_ib_global_event_handler(struct ib_event_handler *handler, /* terminate all ports on device */ for (port_idx = 0; port_idx < SMC_MAX_PORTS; port_idx++) { set_bit(port_idx, &smcibdev->port_event_mask); - set_bit(port_idx, smcibdev->ports_going_away); + if (!test_and_set_bit(port_idx, + smcibdev->ports_going_away)) + schedule = true; } - schedule_work(&smcibdev->port_event_work); + if (schedule) + schedule_work(&smcibdev->port_event_work); break; - case IB_EVENT_PORT_ERR: case IB_EVENT_PORT_ACTIVE: - case IB_EVENT_GID_CHANGE: port_idx = ibevent->element.port_num - 1; - if (port_idx < SMC_MAX_PORTS) { - set_bit(port_idx, &smcibdev->port_event_mask); - if (ibevent->event == IB_EVENT_PORT_ERR) - set_bit(port_idx, smcibdev->ports_going_away); - else if (ibevent->event == IB_EVENT_PORT_ACTIVE) - clear_bit(port_idx, smcibdev->ports_going_away); + if (port_idx >= SMC_MAX_PORTS) + break; + set_bit(port_idx, &smcibdev->port_event_mask); + if (test_and_clear_bit(port_idx, smcibdev->ports_going_away)) schedule_work(&smcibdev->port_event_work); - } + break; + case IB_EVENT_PORT_ERR: + port_idx = ibevent->element.port_num - 1; + if (port_idx >= SMC_MAX_PORTS) + break; + set_bit(port_idx, &smcibdev->port_event_mask); + if (!test_and_set_bit(port_idx, smcibdev->ports_going_away)) + schedule_work(&smcibdev->port_event_work); + break; + case IB_EVENT_GID_CHANGE: + port_idx = ibevent->element.port_num - 1; + if (port_idx >= SMC_MAX_PORTS) + break; + set_bit(port_idx, &smcibdev->port_event_mask); + schedule_work(&smcibdev->port_event_work); break; default: break; @@ -316,11 +334,11 @@ static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) case IB_EVENT_QP_FATAL: case IB_EVENT_QP_ACCESS_ERR: port_idx = ibevent->element.qp->port - 1; - if (port_idx < SMC_MAX_PORTS) { - set_bit(port_idx, &smcibdev->port_event_mask); - set_bit(port_idx, smcibdev->ports_going_away); + if (port_idx >= SMC_MAX_PORTS) + break; + set_bit(port_idx, &smcibdev->port_event_mask); + if (!test_and_set_bit(port_idx, smcibdev->ports_going_away)) schedule_work(&smcibdev->port_event_work); - } break; default: break; @@ -594,6 +612,7 @@ static struct ib_client smc_ib_client = { int __init smc_ib_register_client(void) { + smc_ib_init_local_systemid(); return ib_register_client(&smc_ib_client); } diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 255db87547d3..5c2b115d36da 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -84,4 +84,5 @@ void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev, enum dma_data_direction data_direction); int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index); +bool smc_ib_is_valid_local_systemid(void); #endif diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a9f6431dd69a..0e52aab53d97 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -614,7 +614,7 @@ static void smc_llc_testlink_work(struct work_struct *work) rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp, SMC_LLC_WAIT_TIME); if (rc <= 0) { - smc_lgr_terminate(smc_get_lgr(link), true); + smc_lgr_terminate_sched(smc_get_lgr(link)); return; } next_interval = link->llc_testlink_time; diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 0d42e7716b91..9f1ade86d70e 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -284,7 +284,7 @@ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL); if (rc) - smc_lgr_terminate(lgr, true); + smc_lgr_terminate_sched(lgr); return rc; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 3a1d428c1336..f25604d68337 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -29,7 +29,7 @@ struct switchdev_deferred_item { struct list_head list; struct net_device *dev; switchdev_deferred_func_t *func; - unsigned long data[0]; + unsigned long data[]; }; static struct switchdev_deferred_item *switchdev_deferred_dequeue(void) @@ -475,6 +475,9 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev, * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { + if (netif_is_bridge_master(lower_dev)) + continue; + err = __switchdev_handle_port_obj_add(lower_dev, port_obj_info, check_cb, add_cb); if (err && err != -EOPNOTSUPP) @@ -526,6 +529,9 @@ static int __switchdev_handle_port_obj_del(struct net_device *dev, * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { + if (netif_is_bridge_master(lower_dev)) + continue; + err = __switchdev_handle_port_obj_del(lower_dev, port_obj_info, check_cb, del_cb); if (err && err != -EOPNOTSUPP) @@ -576,6 +582,9 @@ static int __switchdev_handle_port_attr_set(struct net_device *dev, * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { + if (netif_is_bridge_master(lower_dev)) + continue; + err = __switchdev_handle_port_attr_set(lower_dev, port_attr_info, check_cb, set_cb); if (err && err != -EOPNOTSUPP) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 94774c0e5ff3..82225bcc1117 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -742,7 +742,8 @@ static void tls_update(struct sock *sk, struct proto *p, ctx->sk_write_space = write_space; ctx->sk_proto = p; } else { - sk->sk_prot = p; + /* Pairs with lockless read in sk_clone_lock(). */ + WRITE_ONCE(sk->sk_prot, p); sk->sk_write_space = write_space; } } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 68debcb28fa4..3385a7a0b231 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -690,7 +690,8 @@ static void unix_show_fdinfo(struct seq_file *m, struct socket *sock) if (sk) { u = unix_sk(sock->sk); - seq_printf(m, "scm_fds: %u\n", READ_ONCE(u->scm_stat.nr_fds)); + seq_printf(m, "scm_fds: %u\n", + atomic_read(&u->scm_stat.nr_fds)); } } #else @@ -1211,6 +1212,7 @@ out: } static long unix_wait_for_peer(struct sock *other, long timeo) + __releases(&unix_sk(other)->lock) { struct unix_sock *u = unix_sk(other); int sched; @@ -1601,10 +1603,8 @@ static void scm_stat_add(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - lockdep_assert_held(&sk->sk_receive_queue.lock); - if (unlikely(fp && fp->count)) - u->scm_stat.nr_fds += fp->count; + atomic_add(fp->count, &u->scm_stat.nr_fds); } static void scm_stat_del(struct sock *sk, struct sk_buff *skb) @@ -1612,10 +1612,8 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - lockdep_assert_held(&sk->sk_receive_queue.lock); - if (unlikely(fp && fp->count)) - u->scm_stat.nr_fds -= fp->count; + atomic_sub(fp->count, &u->scm_stat.nr_fds); } /* @@ -1804,10 +1802,8 @@ restart_locked: if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); maybe_add_creds(skb, sock, other); - spin_lock(&other->sk_receive_queue.lock); scm_stat_add(other, skb); - __skb_queue_tail(&other->sk_receive_queue, skb); - spin_unlock(&other->sk_receive_queue.lock); + skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); other->sk_data_ready(other); sock_put(other); @@ -1909,10 +1905,8 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto pipe_err_free; maybe_add_creds(skb, sock, other); - spin_lock(&other->sk_receive_queue.lock); scm_stat_add(other, skb); - __skb_queue_tail(&other->sk_receive_queue, skb); - spin_unlock(&other->sk_receive_queue.lock); + skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); other->sk_data_ready(other); sent += size; @@ -2112,9 +2106,12 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, skip = sk_peek_offset(sk, flags); skb = __skb_try_recv_datagram(sk, &sk->sk_receive_queue, flags, - scm_stat_del, &skip, &err, &last); - if (skb) + &skip, &err, &last); + if (skb) { + if (!(flags & MSG_PEEK)) + scm_stat_del(sk, skb); break; + } mutex_unlock(&u->iolock); @@ -2408,9 +2405,7 @@ unlock: sk_peek_offset_bwd(sk, chunk); if (UNIXCB(skb).fp) { - spin_lock(&sk->sk_receive_queue.lock); scm_stat_del(sk, skb); - spin_unlock(&sk->sk_receive_queue.lock); unix_detach_fds(&scm, skb); } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index f3c4bab2f737..709038a4783e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1151,6 +1151,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, virtio_transport_free_pkt(pkt); break; default: + (void)virtio_transport_reset_no_sock(t, pkt); virtio_transport_free_pkt(pkt); break; } diff --git a/net/wireless/core.h b/net/wireless/core.h index ed487e324571..bb897a803ffe 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -385,7 +385,7 @@ void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, struct net_device *dev); int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, u16 frame_type, const u8 *match_data, - int match_len); + int match_len, struct netlink_ext_ack *extack); void cfg80211_mlme_unreg_wk(struct work_struct *wk); void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid); void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index f9462010575f..e4805a3bd310 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -4,6 +4,7 @@ * * Copyright (c) 2009, Jouni Malinen <j@w1.fi> * Copyright (c) 2015 Intel Deutschland GmbH + * Copyright (C) 2019 Intel Corporation */ #include <linux/kernel.h> @@ -470,7 +471,7 @@ void cfg80211_mlme_unreg_wk(struct work_struct *wk) int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, u16 frame_type, const u8 *match_data, - int match_len) + int match_len, struct netlink_ext_ack *extack) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); @@ -481,15 +482,38 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, if (!wdev->wiphy->mgmt_stypes) return -EOPNOTSUPP; - if ((frame_type & IEEE80211_FCTL_FTYPE) != IEEE80211_FTYPE_MGMT) + if ((frame_type & IEEE80211_FCTL_FTYPE) != IEEE80211_FTYPE_MGMT) { + NL_SET_ERR_MSG(extack, "frame type not management"); return -EINVAL; + } - if (frame_type & ~(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) + if (frame_type & ~(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) { + NL_SET_ERR_MSG(extack, "Invalid frame type"); return -EINVAL; + } mgmt_type = (frame_type & IEEE80211_FCTL_STYPE) >> 4; - if (!(wdev->wiphy->mgmt_stypes[wdev->iftype].rx & BIT(mgmt_type))) + if (!(wdev->wiphy->mgmt_stypes[wdev->iftype].rx & BIT(mgmt_type))) { + NL_SET_ERR_MSG(extack, + "Registration to specific type not supported"); + return -EINVAL; + } + + /* + * To support Pre Association Security Negotiation (PASN), registration + * for authentication frames should be supported. However, as some + * versions of the user space daemons wrongly register to all types of + * authentication frames (which might result in unexpected behavior) + * allow such registration if the request is for a specific + * authentication algorithm number. + */ + if (wdev->iftype == NL80211_IFTYPE_STATION && + (frame_type & IEEE80211_FCTL_STYPE) == IEEE80211_STYPE_AUTH && + !(match_data && match_len >= 2)) { + NL_SET_ERR_MSG(extack, + "Authentication algorithm number required"); return -EINVAL; + } nreg = kzalloc(sizeof(*reg) + match_len, GFP_KERNEL); if (!nreg) @@ -504,6 +528,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, continue; if (memcmp(reg->match, match_data, mlen) == 0) { + NL_SET_ERR_MSG(extack, "Match already configured"); err = -EALREADY; break; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ec5d67794aab..750b73a52fd8 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -322,6 +322,29 @@ he_obss_pd_policy[NL80211_HE_OBSS_PD_ATTR_MAX + 1] = { NLA_POLICY_RANGE(NLA_U8, 1, 20), }; +static const struct nla_policy +he_bss_color_policy[NL80211_HE_BSS_COLOR_ATTR_MAX + 1] = { + [NL80211_HE_BSS_COLOR_ATTR_COLOR] = NLA_POLICY_RANGE(NLA_U8, 1, 63), + [NL80211_HE_BSS_COLOR_ATTR_DISABLED] = { .type = NLA_FLAG }, + [NL80211_HE_BSS_COLOR_ATTR_PARTIAL] = { .type = NLA_FLAG }, +}; + +static const struct nla_policy +nl80211_tid_config_attr_policy[NL80211_TID_CONFIG_ATTR_MAX + 1] = { + [NL80211_TID_CONFIG_ATTR_VIF_SUPP] = { .type = NLA_U64 }, + [NL80211_TID_CONFIG_ATTR_PEER_SUPP] = { .type = NLA_U64 }, + [NL80211_TID_CONFIG_ATTR_OVERRIDE] = { .type = NLA_FLAG }, + [NL80211_TID_CONFIG_ATTR_TIDS] = NLA_POLICY_RANGE(NLA_U16, 1, 0xff), + [NL80211_TID_CONFIG_ATTR_NOACK] = + NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), + [NL80211_TID_CONFIG_ATTR_RETRY_SHORT] = NLA_POLICY_MIN(NLA_U8, 1), + [NL80211_TID_CONFIG_ATTR_RETRY_LONG] = NLA_POLICY_MIN(NLA_U8, 1), + [NL80211_TID_CONFIG_ATTR_AMPDU_CTRL] = + NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), + [NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL] = + NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), +}; + const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -362,7 +385,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_KEY] = { .type = NLA_NESTED, }, [NL80211_ATTR_KEY_DATA] = { .type = NLA_BINARY, .len = WLAN_MAX_KEY_LEN }, - [NL80211_ATTR_KEY_IDX] = NLA_POLICY_MAX(NLA_U8, 5), + [NL80211_ATTR_KEY_IDX] = NLA_POLICY_MAX(NLA_U8, 7), [NL80211_ATTR_KEY_CIPHER] = { .type = NLA_U32 }, [NL80211_ATTR_KEY_DEFAULT] = { .type = NLA_FLAG }, [NL80211_ATTR_KEY_SEQ] = { .type = NLA_BINARY, .len = 16 }, @@ -632,6 +655,9 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_TWT_RESPONDER] = { .type = NLA_FLAG }, [NL80211_ATTR_HE_OBSS_PD] = NLA_POLICY_NESTED(he_obss_pd_policy), [NL80211_ATTR_VLAN_ID] = NLA_POLICY_RANGE(NLA_U16, 1, VLAN_N_VID - 2), + [NL80211_ATTR_HE_BSS_COLOR] = NLA_POLICY_NESTED(he_bss_color_policy), + [NL80211_ATTR_TID_CONFIG] = + NLA_POLICY_NESTED_ARRAY(nl80211_tid_config_attr_policy), }; /* policy for the key attributes */ @@ -971,6 +997,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_NO_10MHZ) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_10MHZ)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_NO_HE) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_HE)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, @@ -1032,7 +1061,7 @@ struct key_parse { struct key_params p; int idx; int type; - bool def, defmgmt; + bool def, defmgmt, defbeacon; bool def_uni, def_multi; }; @@ -1048,12 +1077,13 @@ static int nl80211_parse_key_new(struct genl_info *info, struct nlattr *key, k->def = !!tb[NL80211_KEY_DEFAULT]; k->defmgmt = !!tb[NL80211_KEY_DEFAULT_MGMT]; + k->defbeacon = !!tb[NL80211_KEY_DEFAULT_BEACON]; if (k->def) { k->def_uni = true; k->def_multi = true; } - if (k->defmgmt) + if (k->defmgmt || k->defbeacon) k->def_multi = true; if (tb[NL80211_KEY_IDX]) @@ -1160,14 +1190,17 @@ static int nl80211_parse_key(struct genl_info *info, struct key_parse *k) if (err) return err; - if (k->def && k->defmgmt) { - GENL_SET_ERR_MSG(info, "key with def && defmgmt is invalid"); + if ((k->def ? 1 : 0) + (k->defmgmt ? 1 : 0) + + (k->defbeacon ? 1 : 0) > 1) { + GENL_SET_ERR_MSG(info, + "key with multiple default flags is invalid"); return -EINVAL; } - if (k->defmgmt) { + if (k->defmgmt || k->defbeacon) { if (k->def_uni || !k->def_multi) { - GENL_SET_ERR_MSG(info, "defmgmt key must be mcast"); + GENL_SET_ERR_MSG(info, + "defmgmt/defbeacon key must be mcast"); return -EINVAL; } } @@ -1179,14 +1212,20 @@ static int nl80211_parse_key(struct genl_info *info, struct key_parse *k) "defmgmt key idx not 4 or 5"); return -EINVAL; } + } else if (k->defbeacon) { + if (k->idx < 6 || k->idx > 7) { + GENL_SET_ERR_MSG(info, + "defbeacon key idx not 6 or 7"); + return -EINVAL; + } } else if (k->def) { if (k->idx < 0 || k->idx > 3) { GENL_SET_ERR_MSG(info, "def key idx not 0-3"); return -EINVAL; } } else { - if (k->idx < 0 || k->idx > 5) { - GENL_SET_ERR_MSG(info, "key idx not 0-5"); + if (k->idx < 0 || k->idx > 7) { + GENL_SET_ERR_MSG(info, "key idx not 0-7"); return -EINVAL; } } @@ -1892,6 +1931,88 @@ static int nl80211_send_pmsr_capa(struct cfg80211_registered_device *rdev, return 0; } +static int +nl80211_put_iftype_akm_suites(struct cfg80211_registered_device *rdev, + struct sk_buff *msg) +{ + int i; + struct nlattr *nested, *nested_akms; + const struct wiphy_iftype_akm_suites *iftype_akms; + + if (!rdev->wiphy.num_iftype_akm_suites || + !rdev->wiphy.iftype_akm_suites) + return 0; + + nested = nla_nest_start(msg, NL80211_ATTR_IFTYPE_AKM_SUITES); + if (!nested) + return -ENOBUFS; + + for (i = 0; i < rdev->wiphy.num_iftype_akm_suites; i++) { + nested_akms = nla_nest_start(msg, i + 1); + if (!nested_akms) + return -ENOBUFS; + + iftype_akms = &rdev->wiphy.iftype_akm_suites[i]; + + if (nl80211_put_iftypes(msg, NL80211_IFTYPE_AKM_ATTR_IFTYPES, + iftype_akms->iftypes_mask)) + return -ENOBUFS; + + if (nla_put(msg, NL80211_IFTYPE_AKM_ATTR_SUITES, + sizeof(u32) * iftype_akms->n_akm_suites, + iftype_akms->akm_suites)) { + return -ENOBUFS; + } + nla_nest_end(msg, nested_akms); + } + + nla_nest_end(msg, nested); + + return 0; +} + +static int +nl80211_put_tid_config_support(struct cfg80211_registered_device *rdev, + struct sk_buff *msg) +{ + struct nlattr *supp; + + if (!rdev->wiphy.tid_config_support.vif && + !rdev->wiphy.tid_config_support.peer) + return 0; + + supp = nla_nest_start(msg, NL80211_ATTR_TID_CONFIG); + if (!supp) + return -ENOSPC; + + if (rdev->wiphy.tid_config_support.vif && + nla_put_u64_64bit(msg, NL80211_TID_CONFIG_ATTR_VIF_SUPP, + rdev->wiphy.tid_config_support.vif, + NL80211_TID_CONFIG_ATTR_PAD)) + goto fail; + + if (rdev->wiphy.tid_config_support.peer && + nla_put_u64_64bit(msg, NL80211_TID_CONFIG_ATTR_PEER_SUPP, + rdev->wiphy.tid_config_support.peer, + NL80211_TID_CONFIG_ATTR_PAD)) + goto fail; + + /* for now we just use the same value ... makes more sense */ + if (nla_put_u8(msg, NL80211_TID_CONFIG_ATTR_RETRY_SHORT, + rdev->wiphy.tid_config_support.max_retry)) + goto fail; + if (nla_put_u8(msg, NL80211_TID_CONFIG_ATTR_RETRY_LONG, + rdev->wiphy.tid_config_support.max_retry)) + goto fail; + + nla_nest_end(msg, supp); + + return 0; +fail: + nla_nest_cancel(msg, supp); + return -ENOBUFS; +} + struct nl80211_dump_wiphy_state { s64 filter_wiphy; long start; @@ -2450,6 +2571,12 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.akm_suites)) goto nla_put_failure; + if (nl80211_put_iftype_akm_suites(rdev, msg)) + goto nla_put_failure; + + if (nl80211_put_tid_config_support(rdev, msg)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -3481,7 +3608,7 @@ static int nl80211_valid_4addr(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype) { if (!use_4addr) { - if (netdev && (netdev->priv_flags & IFF_BRIDGE_PORT)) + if (netdev && netif_is_bridge_port(netdev)) return -EBUSY; return 0; } @@ -3769,8 +3896,14 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) void *hdr; struct sk_buff *msg; - if (info->attrs[NL80211_ATTR_KEY_IDX]) + if (info->attrs[NL80211_ATTR_KEY_IDX]) { key_idx = nla_get_u8(info->attrs[NL80211_ATTR_KEY_IDX]); + if (key_idx > 5 && + !wiphy_ext_feature_isset( + &rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION)) + return -EINVAL; + } if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); @@ -3846,7 +3979,7 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) /* Only support setting default key and * Extended Key ID action NL80211_KEY_SET_TX. */ - if (!key.def && !key.defmgmt && + if (!key.def && !key.defmgmt && !key.defbeacon && !(key.p.mode == NL80211_KEY_SET_TX)) return -EINVAL; @@ -3893,6 +4026,24 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_CFG80211_WEXT dev->ieee80211_ptr->wext.default_mgmt_key = key.idx; #endif + } else if (key.defbeacon) { + if (key.def_uni || !key.def_multi) { + err = -EINVAL; + goto out; + } + + if (!rdev->ops->set_default_beacon_key) { + err = -EOPNOTSUPP; + goto out; + } + + err = nl80211_key_allowed(dev->ieee80211_ptr); + if (err) + goto out; + + err = rdev_set_default_beacon_key(rdev, dev, key.idx); + if (err) + goto out; } else if (key.p.mode == NL80211_KEY_SET_TX && wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_EXT_KEY_ID)) { @@ -3930,8 +4081,10 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) if (err) return err; - if (!key.p.key) + if (!key.p.key) { + GENL_SET_ERR_MSG(info, "no key"); return -EINVAL; + } if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); @@ -3945,8 +4098,10 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) /* for now */ if (key.type != NL80211_KEYTYPE_PAIRWISE && - key.type != NL80211_KEYTYPE_GROUP) + key.type != NL80211_KEYTYPE_GROUP) { + GENL_SET_ERR_MSG(info, "key type not pairwise or group"); return -EINVAL; + } if (key.type == NL80211_KEYTYPE_GROUP && info->attrs[NL80211_ATTR_VLAN_ID]) @@ -3957,15 +4112,22 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) if (cfg80211_validate_key_settings(rdev, &key.p, key.idx, key.type == NL80211_KEYTYPE_PAIRWISE, - mac_addr)) + mac_addr)) { + GENL_SET_ERR_MSG(info, "key setting validation failed"); return -EINVAL; + } wdev_lock(dev->ieee80211_ptr); err = nl80211_key_allowed(dev->ieee80211_ptr); - if (!err) + if (err) + GENL_SET_ERR_MSG(info, "key not allowed"); + if (!err) { err = rdev_add_key(rdev, dev, key.idx, key.type == NL80211_KEYTYPE_PAIRWISE, mac_addr, &key.p); + if (err) + GENL_SET_ERR_MSG(info, "key addition failed"); + } wdev_unlock(dev->ieee80211_ptr); return err; @@ -4518,6 +4680,30 @@ static int nl80211_parse_he_obss_pd(struct nlattr *attrs, return 0; } +static int nl80211_parse_he_bss_color(struct nlattr *attrs, + struct cfg80211_he_bss_color *he_bss_color) +{ + struct nlattr *tb[NL80211_HE_BSS_COLOR_ATTR_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NL80211_HE_BSS_COLOR_ATTR_MAX, attrs, + he_bss_color_policy, NULL); + if (err) + return err; + + if (!tb[NL80211_HE_BSS_COLOR_ATTR_COLOR]) + return -EINVAL; + + he_bss_color->color = + nla_get_u8(tb[NL80211_HE_BSS_COLOR_ATTR_COLOR]); + he_bss_color->disabled = + nla_get_flag(tb[NL80211_HE_BSS_COLOR_ATTR_DISABLED]); + he_bss_color->partial = + nla_get_flag(tb[NL80211_HE_BSS_COLOR_ATTR_PARTIAL]); + + return 0; +} + static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params, const u8 *rates) { @@ -4809,6 +4995,14 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) goto out; } + if (info->attrs[NL80211_ATTR_HE_BSS_COLOR]) { + err = nl80211_parse_he_bss_color( + info->attrs[NL80211_ATTR_HE_BSS_COLOR], + ¶ms.he_bss_color); + if (err) + return err; + } + nl80211_calculate_ap_params(¶ms); if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) @@ -10545,8 +10739,9 @@ static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; return cfg80211_mlme_register_mgmt(wdev, info->snd_portid, frame_type, - nla_data(info->attrs[NL80211_ATTR_FRAME_MATCH]), - nla_len(info->attrs[NL80211_ATTR_FRAME_MATCH])); + nla_data(info->attrs[NL80211_ATTR_FRAME_MATCH]), + nla_len(info->attrs[NL80211_ATTR_FRAME_MATCH]), + info->extack); } static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) @@ -13808,6 +14003,141 @@ static int nl80211_probe_mesh_link(struct sk_buff *skb, struct genl_info *info) return rdev_probe_mesh_link(rdev, dev, dest, buf, len); } +static int parse_tid_conf(struct cfg80211_registered_device *rdev, + struct nlattr *attrs[], struct net_device *dev, + struct cfg80211_tid_cfg *tid_conf, + struct genl_info *info, const u8 *peer) +{ + struct netlink_ext_ack *extack = info->extack; + u64 mask; + int err; + + if (!attrs[NL80211_TID_CONFIG_ATTR_TIDS]) + return -EINVAL; + + tid_conf->config_override = + nla_get_flag(attrs[NL80211_TID_CONFIG_ATTR_OVERRIDE]); + tid_conf->tids = nla_get_u16(attrs[NL80211_TID_CONFIG_ATTR_TIDS]); + + if (tid_conf->config_override) { + if (rdev->ops->reset_tid_config) { + err = rdev_reset_tid_config(rdev, dev, peer, + tid_conf->tids); + /* If peer is there no other configuration will be + * allowed + */ + if (err || peer) + return err; + } else { + return -EINVAL; + } + } + + if (attrs[NL80211_TID_CONFIG_ATTR_NOACK]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_NOACK); + tid_conf->noack = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_NOACK]); + } + + if (attrs[NL80211_TID_CONFIG_ATTR_RETRY_SHORT]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_RETRY_SHORT); + tid_conf->retry_short = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_RETRY_SHORT]); + + if (tid_conf->retry_short > rdev->wiphy.max_data_retry_count) + return -EINVAL; + } + + if (attrs[NL80211_TID_CONFIG_ATTR_RETRY_LONG]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_RETRY_LONG); + tid_conf->retry_long = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_RETRY_LONG]); + + if (tid_conf->retry_long > rdev->wiphy.max_data_retry_count) + return -EINVAL; + } + + if (attrs[NL80211_TID_CONFIG_ATTR_AMPDU_CTRL]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_AMPDU_CTRL); + tid_conf->ampdu = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_AMPDU_CTRL]); + } + + if (attrs[NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL); + tid_conf->rtscts = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL]); + } + + if (peer) + mask = rdev->wiphy.tid_config_support.peer; + else + mask = rdev->wiphy.tid_config_support.vif; + + if (tid_conf->mask & ~mask) { + NL_SET_ERR_MSG(extack, "unsupported TID configuration"); + return -ENOTSUPP; + } + + return 0; +} + +static int nl80211_set_tid_config(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct nlattr *attrs[NL80211_TID_CONFIG_ATTR_MAX + 1]; + struct net_device *dev = info->user_ptr[1]; + struct cfg80211_tid_config *tid_config; + struct nlattr *tid; + int conf_idx = 0, rem_conf; + int ret = -EINVAL; + u32 num_conf = 0; + + if (!info->attrs[NL80211_ATTR_TID_CONFIG]) + return -EINVAL; + + if (!rdev->ops->set_tid_config) + return -EOPNOTSUPP; + + nla_for_each_nested(tid, info->attrs[NL80211_ATTR_TID_CONFIG], + rem_conf) + num_conf++; + + tid_config = kzalloc(struct_size(tid_config, tid_conf, num_conf), + GFP_KERNEL); + if (!tid_config) + return -ENOMEM; + + tid_config->n_tid_conf = num_conf; + + if (info->attrs[NL80211_ATTR_MAC]) + tid_config->peer = nla_data(info->attrs[NL80211_ATTR_MAC]); + + nla_for_each_nested(tid, info->attrs[NL80211_ATTR_TID_CONFIG], + rem_conf) { + ret = nla_parse_nested(attrs, NL80211_TID_CONFIG_ATTR_MAX, + tid, NULL, NULL); + + if (ret) + goto bad_tid_conf; + + ret = parse_tid_conf(rdev, attrs, dev, + &tid_config->tid_conf[conf_idx], + info, tid_config->peer); + if (ret) + goto bad_tid_conf; + + conf_idx++; + } + + ret = rdev_set_tid_config(rdev, dev, tid_config); + +bad_tid_conf: + kfree(tid_config); + return ret; +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -14762,6 +15092,13 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_TID_CONFIG, + .doit = nl80211_set_tid_config, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, + }, }; static struct genl_family nl80211_fam __ro_after_init = { diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index e0d34f796d0b..99462f0c4e08 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -136,6 +136,19 @@ rdev_set_default_mgmt_key(struct cfg80211_registered_device *rdev, return ret; } +static inline int +rdev_set_default_beacon_key(struct cfg80211_registered_device *rdev, + struct net_device *netdev, u8 key_index) +{ + int ret; + + trace_rdev_set_default_beacon_key(&rdev->wiphy, netdev, key_index); + ret = rdev->ops->set_default_beacon_key(&rdev->wiphy, netdev, + key_index); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + static inline int rdev_start_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ap_settings *settings) @@ -1313,4 +1326,28 @@ rdev_probe_mesh_link(struct cfg80211_registered_device *rdev, return ret; } +static inline int rdev_set_tid_config(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_tid_config *tid_conf) +{ + int ret; + + trace_rdev_set_tid_config(&rdev->wiphy, dev, tid_conf); + ret = rdev->ops->set_tid_config(&rdev->wiphy, dev, tid_conf); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_reset_tid_config(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *peer, + u8 tids) +{ + int ret; + + trace_rdev_reset_tid_config(&rdev->wiphy, dev, peer, tids); + ret = rdev->ops->reset_tid_config(&rdev->wiphy, dev, peer, tids); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 1a8218f1bbe0..d476d4da0d09 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1569,6 +1569,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_80MHZ; if (rd_flags & NL80211_RRF_NO_160MHZ) channel_flags |= IEEE80211_CHAN_NO_160MHZ; + if (rd_flags & NL80211_RRF_NO_HE) + channel_flags |= IEEE80211_CHAN_NO_HE; return channel_flags; } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index aef240fdf8df..dd41e41f9d26 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -556,9 +556,8 @@ cfg80211_find_sched_scan_req(struct cfg80211_registered_device *rdev, u64 reqid) { struct cfg80211_sched_scan_request *pos; - WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); - - list_for_each_entry_rcu(pos, &rdev->sched_scan_req_list, list) { + list_for_each_entry_rcu(pos, &rdev->sched_scan_req_list, list, + lockdep_rtnl_is_held()) { if (pos->reqid == reqid) return pos; } @@ -1434,8 +1433,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, } rcu_assign_pointer(tmp.pub.ies, ies); - signal_valid = abs(data->chan->center_freq - channel->center_freq) <= - wiphy->max_adj_channel_rssi_comp; + signal_valid = data->chan == channel; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, ts); if (!res) return NULL; @@ -1852,8 +1850,7 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, memcpy(tmp.pub.chain_signal, data->chain_signal, IEEE80211_MAX_CHAINS); ether_addr_copy(tmp.parent_bssid, data->parent_bssid); - signal_valid = abs(data->chan->center_freq - channel->center_freq) <= - wiphy->max_adj_channel_rssi_comp; + signal_valid = data->chan == channel; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, jiffies); if (!res) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index d32a2ec4d96a..ac3e60aa1fc8 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1111,9 +1111,16 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. */ - if (rdev->ops->del_key) - for (i = 0; i < 6; i++) + if (rdev->ops->del_key) { + int max_key_idx = 5; + + if (wiphy_ext_feature_isset( + wdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION)) + max_key_idx = 7; + for (i = 0; i <= max_key_idx; i++) rdev_del_key(rdev, dev, i, false, NULL); + } rdev_set_qos_map(rdev, dev, NULL); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 3ef1679b0e66..839df54cee21 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -510,6 +510,23 @@ TRACE_EVENT(rdev_set_default_mgmt_key, WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->key_index) ); +TRACE_EVENT(rdev_set_default_beacon_key, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index), + TP_ARGS(wiphy, netdev, key_index), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u8, key_index) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->key_index = key_index; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", key index: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->key_index) +); + TRACE_EVENT(rdev_start_ap, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, struct cfg80211_ap_settings *settings), @@ -3463,6 +3480,43 @@ TRACE_EVENT(rdev_probe_mesh_link, WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(dest)) ); +TRACE_EVENT(rdev_set_tid_config, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_tid_config *tid_conf), + TP_ARGS(wiphy, netdev, tid_conf), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, tid_conf->peer); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer)) +); + +TRACE_EVENT(rdev_reset_tid_config, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + const u8 *peer, u8 tids), + TP_ARGS(wiphy, netdev, peer, tids), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + __field(u8, tids) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, peer); + __entry->tids = tids; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT ", tids: 0x%x", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->tids) +); #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/wireless/util.c b/net/wireless/util.c index 8481e9ac33da..6590efbbcbb9 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -231,7 +231,12 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr) { - if (key_idx < 0 || key_idx > 5) + int max_key_idx = 5; + + if (wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION)) + max_key_idx = 7; + if (key_idx < 0 || key_idx > max_key_idx) return -EINVAL; if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) @@ -934,7 +939,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, return -EOPNOTSUPP; /* if it's part of a bridge, reject changing type to station/ibss */ - if ((dev->priv_flags & IFF_BRIDGE_PORT) && + if (netif_is_bridge_port(dev) && (ntype == NL80211_IFTYPE_ADHOC || ntype == NL80211_IFTYPE_STATION || ntype == NL80211_IFTYPE_P2P_CLIENT)) diff --git a/net/x25/x25_forward.c b/net/x25/x25_forward.c index c82999941d3f..d48ad6d29197 100644 --- a/net/x25/x25_forward.c +++ b/net/x25/x25_forward.c @@ -131,13 +131,11 @@ out: void x25_clear_forward_by_lci(unsigned int lci) { - struct x25_forward *fwd; - struct list_head *entry, *tmp; + struct x25_forward *fwd, *tmp; write_lock_bh(&x25_forward_list_lock); - list_for_each_safe(entry, tmp, &x25_forward_list) { - fwd = list_entry(entry, struct x25_forward, node); + list_for_each_entry_safe(fwd, tmp, &x25_forward_list, node) { if (fwd->lci == lci) { list_del(&fwd->node); kfree(fwd); @@ -149,13 +147,11 @@ void x25_clear_forward_by_lci(unsigned int lci) void x25_clear_forward_by_dev(struct net_device *dev) { - struct x25_forward *fwd; - struct list_head *entry, *tmp; + struct x25_forward *fwd, *tmp; write_lock_bh(&x25_forward_list_lock); - list_for_each_safe(entry, tmp, &x25_forward_list) { - fwd = list_entry(entry, struct x25_forward, node); + list_for_each_entry_safe(fwd, tmp, &x25_forward_list, node) { if ((fwd->dev1 == dev) || (fwd->dev2 == dev)){ list_del(&fwd->node); kfree(fwd); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 89a01ac4e079..b50bb5c76da5 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -19,13 +19,13 @@ struct xdp_ring { /* Used for the RX and TX queues for packets */ struct xdp_rxtx_ring { struct xdp_ring ptrs; - struct xdp_desc desc[0] ____cacheline_aligned_in_smp; + struct xdp_desc desc[] ____cacheline_aligned_in_smp; }; /* Used for the fill and completion queues for buffers */ struct xdp_umem_ring { struct xdp_ring ptrs; - u64 desc[0] ____cacheline_aligned_in_smp; + u64 desc[] ____cacheline_aligned_in_smp; }; struct xsk_queue { diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index f15d6a564b0e..037ea156d2f9 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -100,7 +100,7 @@ static int espintcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, flags |= nonblock ? MSG_DONTWAIT : 0; - skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, NULL, &off, &err); + skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, &off, &err); if (!skb) return err; |