diff options
Diffstat (limited to 'net')
149 files changed, 1899 insertions, 920 deletions
diff --git a/net/9p/Kconfig b/net/9p/Kconfig index e6014e0e51f7..46c39f7da444 100644 --- a/net/9p/Kconfig +++ b/net/9p/Kconfig @@ -32,7 +32,7 @@ config NET_9P_XEN config NET_9P_RDMA - depends on INET && INFINIBAND && INFINIBAND_ADDR_TRANS + depends on INET && INFINIBAND_ADDR_TRANS tristate "9P RDMA Transport (Experimental)" help This builds support for an RDMA transport. diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index 38aa6345bdfa..b718db2085b2 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -16,7 +16,7 @@ #include <linux/module.h> /** - * p9_release_req_pages - Release pages after the transaction. + * p9_release_pages - Release pages after the transaction. */ void p9_release_pages(struct page **pages, int nr_pages) { diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 0cfba919d167..848969fe7979 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -1092,8 +1092,8 @@ static struct p9_trans_module p9_fd_trans = { }; /** - * p9_poll_proc - poll worker thread - * @a: thread state and arguments + * p9_poll_workfn - poll worker thread + * @work: work queue * * polls all v9fs transports for new events and queues the appropriate * work to the work queue diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 6d8e3031978f..3d414acb7015 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -68,8 +68,6 @@ * @pd: Protection Domain pointer * @qp: Queue Pair pointer * @cq: Completion Queue pointer - * @dm_mr: DMA Memory Region pointer - * @lkey: The local access only memory region key * @timeout: Number of uSecs to wait for connection management events * @privport: Whether a privileged port may be used * @port: The port to use @@ -632,7 +630,7 @@ static int p9_rdma_bind_privport(struct p9_trans_rdma *rdma) } /** - * trans_create_rdma - Transport method for creating atransport instance + * rdma_create_trans - Transport method for creating a transport instance * @client: client instance * @addr: IP address string * @args: Mount options string diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 3aa5a93ad107..4d0372263e5d 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -60,7 +60,6 @@ static atomic_t vp_pinned = ATOMIC_INIT(0); /** * struct virtio_chan - per-instance transport information - * @initialized: whether the channel is initialized * @inuse: whether the channel is in use * @lock: protects multiple elements within this structure * @client: client instance @@ -385,8 +384,8 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, * @uidata: user bffer that should be ued for zero copy read * @uodata: user buffer that shoud be user for zero copy write * @inlen: read buffer size - * @olen: write buffer size - * @hdrlen: reader header size, This is the size of response protocol data + * @outlen: write buffer size + * @in_hdr_len: reader header size, This is the size of response protocol data * */ static int diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 086a4abdfa7c..0f19960390a6 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -485,7 +485,7 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, static int xen_9pfs_front_resume(struct xenbus_device *dev) { - dev_warn(&dev->dev, "suspsend/resume unsupported\n"); + dev_warn(&dev->dev, "suspend/resume unsupported\n"); return 0; } diff --git a/net/atm/lec.c b/net/atm/lec.c index 01d5d20a6eb1..3138a869b5c0 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -41,6 +41,9 @@ static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 }; #include <linux/module.h> #include <linux/init.h> +/* Hardening for Spectre-v1 */ +#include <linux/nospec.h> + #include "lec.h" #include "lec_arpc.h" #include "resources.h" @@ -687,8 +690,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc)); if (bytes_left != 0) pr_info("copy from user failed for %d bytes\n", bytes_left); - if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF || - !dev_lec[ioc_data.dev_num]) + if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF) + return -EINVAL; + ioc_data.dev_num = array_index_nospec(ioc_data.dev_num, MAX_LEC_ITF); + if (!dev_lec[ioc_data.dev_num]) return -EINVAL; vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL); if (!vpriv) diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index a11d3d89f012..a35f597e8c8b 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1536,7 +1536,7 @@ out: if (!ret && primary_if) *primary_if = hard_iface; - else + else if (hard_iface) batadv_hardif_put(hard_iface); return ret; diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 0225616d5771..3986551397ca 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, struct batadv_orig_node_vlan *vlan; u8 *tt_change_ptr; - rcu_read_lock(); + spin_lock_bh(&orig_node->vlan_list_lock); hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { num_vlan++; num_entries += atomic_read(&vlan->tt.num_entries); @@ -900,7 +900,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; out: - rcu_read_unlock(); + spin_unlock_bh(&orig_node->vlan_list_lock); return tvlv_len; } @@ -931,15 +931,20 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_softif_vlan *vlan; u16 num_vlan = 0; - u16 num_entries = 0; + u16 vlan_entries = 0; + u16 total_entries = 0; u16 tvlv_len; u8 *tt_change_ptr; int change_offset; - rcu_read_lock(); + spin_lock_bh(&bat_priv->softif_vlan_list_lock); hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { + vlan_entries = atomic_read(&vlan->tt.num_entries); + if (vlan_entries < 1) + continue; + num_vlan++; - num_entries += atomic_read(&vlan->tt.num_entries); + total_entries += vlan_entries; } change_offset = sizeof(**tt_data); @@ -947,7 +952,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, /* if tt_len is negative, allocate the space needed by the full table */ if (*tt_len < 0) - *tt_len = batadv_tt_len(num_entries); + *tt_len = batadv_tt_len(total_entries); tvlv_len = *tt_len; tvlv_len += change_offset; @@ -964,6 +969,10 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, tt_vlan = (struct batadv_tvlv_tt_vlan_data *)(*tt_data + 1); hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) { + vlan_entries = atomic_read(&vlan->tt.num_entries); + if (vlan_entries < 1) + continue; + tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); @@ -974,7 +983,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; out: - rcu_read_unlock(); + spin_unlock_bh(&bat_priv->softif_vlan_list_lock); return tvlv_len; } @@ -1538,6 +1547,8 @@ batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry, * handled by a given originator * @entry: the TT global entry to check * @orig_node: the originator to search in the list + * @flags: a pointer to store TT flags for the given @entry received + * from @orig_node * * find out if an orig_node is already in the list of a tt_global_entry. * @@ -1545,7 +1556,8 @@ batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry, */ static bool batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry, - const struct batadv_orig_node *orig_node) + const struct batadv_orig_node *orig_node, + u8 *flags) { struct batadv_tt_orig_list_entry *orig_entry; bool found = false; @@ -1553,6 +1565,10 @@ batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry, orig_entry = batadv_tt_global_orig_entry_find(entry, orig_node); if (orig_entry) { found = true; + + if (flags) + *flags = orig_entry->flags; + batadv_tt_orig_list_entry_put(orig_entry); } @@ -1731,7 +1747,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, if (!(common->flags & BATADV_TT_CLIENT_TEMP)) goto out; if (batadv_tt_global_entry_has_orig(tt_global_entry, - orig_node)) + orig_node, NULL)) goto out_remove; batadv_tt_global_del_orig_list(tt_global_entry); goto add_orig_entry; @@ -2880,23 +2896,46 @@ unlock: } /** - * batadv_tt_local_valid() - verify that given tt entry is a valid one + * batadv_tt_local_valid() - verify local tt entry and get flags * @entry_ptr: to be checked local tt entry * @data_ptr: not used but definition required to satisfy the callback prototype + * @flags: a pointer to store TT flags for this client to + * + * Checks the validity of the given local TT entry. If it is, then the provided + * flags pointer is updated. * * Return: true if the entry is a valid, false otherwise. */ -static bool batadv_tt_local_valid(const void *entry_ptr, const void *data_ptr) +static bool batadv_tt_local_valid(const void *entry_ptr, + const void *data_ptr, + u8 *flags) { const struct batadv_tt_common_entry *tt_common_entry = entry_ptr; if (tt_common_entry->flags & BATADV_TT_CLIENT_NEW) return false; + + if (flags) + *flags = tt_common_entry->flags; + return true; } +/** + * batadv_tt_global_valid() - verify global tt entry and get flags + * @entry_ptr: to be checked global tt entry + * @data_ptr: an orig_node object (may be NULL) + * @flags: a pointer to store TT flags for this client to + * + * Checks the validity of the given global TT entry. If it is, then the provided + * flags pointer is updated either with the common (summed) TT flags if data_ptr + * is NULL or the specific, per originator TT flags otherwise. + * + * Return: true if the entry is a valid, false otherwise. + */ static bool batadv_tt_global_valid(const void *entry_ptr, - const void *data_ptr) + const void *data_ptr, + u8 *flags) { const struct batadv_tt_common_entry *tt_common_entry = entry_ptr; const struct batadv_tt_global_entry *tt_global_entry; @@ -2910,7 +2949,8 @@ static bool batadv_tt_global_valid(const void *entry_ptr, struct batadv_tt_global_entry, common); - return batadv_tt_global_entry_has_orig(tt_global_entry, orig_node); + return batadv_tt_global_entry_has_orig(tt_global_entry, orig_node, + flags); } /** @@ -2920,25 +2960,34 @@ static bool batadv_tt_global_valid(const void *entry_ptr, * @hash: hash table containing the tt entries * @tt_len: expected tvlv tt data buffer length in number of bytes * @tvlv_buff: pointer to the buffer to fill with the TT data - * @valid_cb: function to filter tt change entries + * @valid_cb: function to filter tt change entries and to return TT flags * @cb_data: data passed to the filter function as argument + * + * Fills the tvlv buff with the tt entries from the specified hash. If valid_cb + * is not provided then this becomes a no-op. */ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, struct batadv_hashtable *hash, void *tvlv_buff, u16 tt_len, bool (*valid_cb)(const void *, - const void *), + const void *, + u8 *flags), void *cb_data) { struct batadv_tt_common_entry *tt_common_entry; struct batadv_tvlv_tt_change *tt_change; struct hlist_head *head; u16 tt_tot, tt_num_entries = 0; + u8 flags; + bool ret; u32 i; tt_tot = batadv_tt_entries(tt_len); tt_change = (struct batadv_tvlv_tt_change *)tvlv_buff; + if (!valid_cb) + return; + rcu_read_lock(); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -2948,11 +2997,12 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, if (tt_tot == tt_num_entries) break; - if ((valid_cb) && (!valid_cb(tt_common_entry, cb_data))) + ret = valid_cb(tt_common_entry, cb_data, &flags); + if (!ret) continue; ether_addr_copy(tt_change->addr, tt_common_entry->addr); - tt_change->flags = tt_common_entry->flags; + tt_change->flags = flags; tt_change->vid = htons(tt_common_entry->vid); memset(tt_change->reserved, 0, sizeof(tt_change->reserved)); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 82c1a6f430b3..5bb6681fa91e 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -518,8 +518,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, return -ELOOP; } - /* Device is already being bridged */ - if (br_port_exists(dev)) + /* Device has master upper dev */ + if (netdev_master_upper_dev_get(dev)) return -EBUSY; /* No bridging devices that dislike that (e.g. wireless) */ diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c index 47ba98db145d..46c1fe7637ea 100644 --- a/net/bridge/netfilter/ebt_stp.c +++ b/net/bridge/netfilter/ebt_stp.c @@ -161,8 +161,8 @@ static int ebt_stp_mt_check(const struct xt_mtchk_param *par) /* Make sure the match only receives stp frames */ if (!par->nft_compat && (!ether_addr_equal(e->destmac, eth_stp_addr) || - !is_broadcast_ether_addr(e->destmsk) || - !(e->bitmask & EBT_DESTMAC))) + !(e->bitmask & EBT_DESTMAC) || + !is_broadcast_ether_addr(e->destmsk))) return -EINVAL; return 0; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 032e0fe45940..28a4c3490359 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1825,13 +1825,14 @@ static int compat_table_info(const struct ebt_table_info *info, { unsigned int size = info->entries_size; const void *entries = info->entries; - int ret; newinfo->entries_size = size; - - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries); - if (ret) - return ret; + if (info->nentries) { + int ret = xt_compat_init_offsets(NFPROTO_BRIDGE, + info->nentries); + if (ret) + return ret; + } return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 53ecda10b790..13e2ae6be620 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -174,7 +174,7 @@ static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow, flow == CAIF_CTRLCMD_DEINIT_RSP ? "CLOSE/DEINIT" : flow == CAIF_CTRLCMD_INIT_FAIL_RSP ? "OPEN_FAIL" : flow == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND ? - "REMOTE_SHUTDOWN" : "UKNOWN CTRL COMMAND"); + "REMOTE_SHUTDOWN" : "UNKNOWN CTRL COMMAND"); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index fcb40c12b1f8..3b3d33ea9ed8 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2569,6 +2569,11 @@ static int try_write(struct ceph_connection *con) int ret = 1; dout("try_write start %p state %lu\n", con, con->state); + if (con->state != CON_STATE_PREOPEN && + con->state != CON_STATE_CONNECTING && + con->state != CON_STATE_NEGOTIATING && + con->state != CON_STATE_OPEN) + return 0; more: dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes); @@ -2594,6 +2599,8 @@ more: } more_kvec: + BUG_ON(!con->sock); + /* kvec data queued? */ if (con->out_kvec_left) { ret = write_partial_kvec(con); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index b3dac24412d3..21ac6e3b96bb 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -209,6 +209,14 @@ static void reopen_session(struct ceph_mon_client *monc) __open_session(monc); } +static void un_backoff(struct ceph_mon_client *monc) +{ + monc->hunt_mult /= 2; /* reduce by 50% */ + if (monc->hunt_mult < 1) + monc->hunt_mult = 1; + dout("%s hunt_mult now %d\n", __func__, monc->hunt_mult); +} + /* * Reschedule delayed work timer. */ @@ -963,6 +971,7 @@ static void delayed_work(struct work_struct *work) if (!monc->hunting) { ceph_con_keepalive(&monc->con); __validate_auth(monc); + un_backoff(monc); } if (is_auth && @@ -1123,9 +1132,8 @@ static void finish_hunting(struct ceph_mon_client *monc) dout("%s found mon%d\n", __func__, monc->cur_mon); monc->hunting = false; monc->had_a_connection = true; - monc->hunt_mult /= 2; /* reduce by 50% */ - if (monc->hunt_mult < 1) - monc->hunt_mult = 1; + un_backoff(monc); + __schedule_delayed(monc); } } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index ea2a6c9fb7ce..d2667e5dddc3 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -157,10 +157,12 @@ static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, #endif /* CONFIG_BLOCK */ static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data, - struct ceph_bvec_iter *bvec_pos) + struct ceph_bvec_iter *bvec_pos, + u32 num_bvecs) { osd_data->type = CEPH_OSD_DATA_TYPE_BVECS; osd_data->bvec_pos = *bvec_pos; + osd_data->num_bvecs = num_bvecs; } #define osd_req_op_data(oreq, whch, typ, fld) \ @@ -237,6 +239,22 @@ void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req, EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio); #endif /* CONFIG_BLOCK */ +void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req, + unsigned int which, + struct bio_vec *bvecs, u32 num_bvecs, + u32 bytes) +{ + struct ceph_osd_data *osd_data; + struct ceph_bvec_iter it = { + .bvecs = bvecs, + .iter = { .bi_size = bytes }, + }; + + osd_data = osd_req_op_data(osd_req, which, extent, osd_data); + ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs); +} +EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvecs); + void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_bvec_iter *bvec_pos) @@ -244,7 +262,7 @@ void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req, struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); - ceph_osd_data_bvecs_init(osd_data, bvec_pos); + ceph_osd_data_bvecs_init(osd_data, bvec_pos, 0); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos); @@ -287,7 +305,8 @@ EXPORT_SYMBOL(osd_req_op_cls_request_data_pages); void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req, unsigned int which, - struct bio_vec *bvecs, u32 bytes) + struct bio_vec *bvecs, u32 num_bvecs, + u32 bytes) { struct ceph_osd_data *osd_data; struct ceph_bvec_iter it = { @@ -296,7 +315,7 @@ void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req, }; osd_data = osd_req_op_data(osd_req, which, cls, request_data); - ceph_osd_data_bvecs_init(osd_data, &it); + ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs); osd_req->r_ops[which].cls.indata_len += bytes; osd_req->r_ops[which].indata_len += bytes; } diff --git a/net/compat.c b/net/compat.c index 5ae7437d3853..7242cce5631b 100644 --- a/net/compat.c +++ b/net/compat.c @@ -377,7 +377,8 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname, optname == SO_ATTACH_REUSEPORT_CBPF) return do_set_attach_filter(sock, level, optname, optval, optlen); - if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO) + if (!COMPAT_USE_64BIT_TIME && + (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) return do_set_sock_timeout(sock, level, optname, optval, optlen); return sock_setsockopt(sock, level, optname, optval, optlen); @@ -448,7 +449,8 @@ static int do_get_sock_timeout(struct socket *sock, int level, int optname, static int compat_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { - if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO) + if (!COMPAT_USE_64BIT_TIME && + (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) return do_get_sock_timeout(sock, level, optname, optval, optlen); return sock_getsockopt(sock, level, optname, optval, optlen); } diff --git a/net/core/dev.c b/net/core/dev.c index 969462ebb296..2af787e8b130 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2124,7 +2124,7 @@ static bool remove_xps_queue_cpu(struct net_device *dev, int i, j; for (i = count, j = offset; i--; j++) { - if (!remove_xps_queue(dev_maps, cpu, j)) + if (!remove_xps_queue(dev_maps, tci, j)) break; } @@ -2969,7 +2969,7 @@ netdev_features_t passthru_features_check(struct sk_buff *skb, } EXPORT_SYMBOL(passthru_features_check); -static netdev_features_t dflt_features_check(const struct sk_buff *skb, +static netdev_features_t dflt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index e3e6a3e2ca22..d884d8f5f0e5 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -839,7 +839,7 @@ void dev_mc_flush(struct net_device *dev) EXPORT_SYMBOL(dev_mc_flush); /** - * dev_mc_flush - Init multicast address list + * dev_mc_init - Init multicast address list * @dev: device * * Init multicast address list. diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 03416e6dd5d7..ba02f0dfe85c 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1032,6 +1032,11 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, info_size = sizeof(info); if (copy_from_user(&info, useraddr, info_size)) return -EFAULT; + /* Since malicious users may modify the original data, + * we need to check whether FLOW_RSS is still requested. + */ + if (!(info.flow_type & FLOW_RSS)) + return -EINVAL; } if (info.cmd == ETHTOOL_GRXCLSRLALL) { diff --git a/net/core/filter.c b/net/core/filter.c index d31aff93270d..201ff36b17a8 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -481,11 +481,18 @@ do_pass: #define BPF_EMIT_JMP \ do { \ + const s32 off_min = S16_MIN, off_max = S16_MAX; \ + s32 off; \ + \ if (target >= len || target < 0) \ goto err; \ - insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0; \ + off = addrs ? addrs[target] - addrs[i] - 1 : 0; \ /* Adjust pc relative offset for 2nd or 3rd insn. */ \ - insn->off -= insn - tmp_insns; \ + off -= insn - tmp_insns; \ + /* Reject anything not fitting into insn->off. */ \ + if (off < off_min || off > off_max) \ + goto err; \ + insn->off = off; \ } while (0) case BPF_JMP | BPF_JA: @@ -3240,6 +3247,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, skb_dst_set(skb, (struct dst_entry *) md); info = &md->u.tun_info; + memset(info, 0, sizeof(*info)); info->mode = IP_TUNNEL_INFO_TX; info->key.tun_flags = TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 7b7a14abba28..ce519861be59 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -55,7 +55,8 @@ static void neigh_timer_handler(struct timer_list *t); static void __neigh_notify(struct neighbour *n, int type, int flags, u32 pid); static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid); -static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev); +static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, + struct net_device *dev); #ifdef CONFIG_PROC_FS static const struct file_operations neigh_stat_seq_fops; @@ -291,8 +292,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) { write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev); - pneigh_ifdown(tbl, dev); - write_unlock_bh(&tbl->lock); + pneigh_ifdown_and_unlock(tbl, dev); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); @@ -681,9 +681,10 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, return -ENOENT; } -static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) +static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, + struct net_device *dev) { - struct pneigh_entry *n, **np; + struct pneigh_entry *n, **np, *freelist = NULL; u32 h; for (h = 0; h <= PNEIGH_HASHMASK; h++) { @@ -691,16 +692,23 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) while ((n = *np) != NULL) { if (!dev || n->dev == dev) { *np = n->next; - if (tbl->pdestructor) - tbl->pdestructor(n); - if (n->dev) - dev_put(n->dev); - kfree(n); + n->next = freelist; + freelist = n; continue; } np = &n->next; } } + write_unlock_bh(&tbl->lock); + while ((n = freelist)) { + freelist = n->next; + n->next = NULL; + if (tbl->pdestructor) + tbl->pdestructor(n); + if (n->dev) + dev_put(n->dev); + kfree(n); + } return -ENOENT; } @@ -2323,12 +2331,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL); if (!err) { - if (tb[NDA_IFINDEX]) + if (tb[NDA_IFINDEX]) { + if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) + return -EINVAL; filter_idx = nla_get_u32(tb[NDA_IFINDEX]); - - if (tb[NDA_MASTER]) + } + if (tb[NDA_MASTER]) { + if (nla_len(tb[NDA_MASTER]) != sizeof(u32)) + return -EINVAL; filter_master_idx = nla_get_u32(tb[NDA_MASTER]); - + } if (filter_idx || filter_master_idx) flags |= NLM_F_DUMP_FILTERED; } diff --git a/net/core/sock.c b/net/core/sock.c index 6444525f610c..3b6d02854e57 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1606,7 +1606,7 @@ static void __sk_free(struct sock *sk) if (likely(sk->sk_net_refcnt)) sock_inuse_add(sock_net(sk), -1); - if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt)) + if (unlikely(sk->sk_net_refcnt && sock_diag_has_destroy_listeners(sk))) sock_diag_broadcast_destroy(sk); else sk_destruct(sk); diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 92d016e87816..385f153fe031 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -126,6 +126,16 @@ static void ccid2_change_l_seq_window(struct sock *sk, u64 val) DCCPF_SEQ_WMAX)); } +static void dccp_tasklet_schedule(struct sock *sk) +{ + struct tasklet_struct *t = &dccp_sk(sk)->dccps_xmitlet; + + if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { + sock_hold(sk); + __tasklet_schedule(t); + } +} + static void ccid2_hc_tx_rto_expire(struct timer_list *t) { struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer); @@ -166,7 +176,7 @@ static void ccid2_hc_tx_rto_expire(struct timer_list *t) /* if we were blocked before, we may now send cwnd=1 packet */ if (sender_was_blocked) - tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet); + dccp_tasklet_schedule(sk); /* restart backed-off timer */ sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); out: @@ -706,7 +716,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) done: /* check if incoming Acks allow pending packets to be sent */ if (sender_was_blocked && !ccid2_cwnd_network_limited(hc)) - tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet); + dccp_tasklet_schedule(sk); dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 84cd4e3fd01b..0d56e36a6db7 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -283,9 +283,7 @@ int dccp_disconnect(struct sock *sk, int flags) dccp_clear_xmit_timers(sk); ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); - ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); dp->dccps_hc_rx_ccid = NULL; - dp->dccps_hc_tx_ccid = NULL; __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_write_queue); diff --git a/net/dccp/timer.c b/net/dccp/timer.c index b50a8732ff43..1501a20a94ca 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -232,6 +232,7 @@ static void dccp_write_xmitlet(unsigned long data) else dccp_write_xmit(sk); bh_unlock_sock(sk); + sock_put(sk); } static void dccp_write_xmit_timer(struct timer_list *t) @@ -240,7 +241,6 @@ static void dccp_write_xmit_timer(struct timer_list *t) struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk; dccp_write_xmitlet((unsigned long)sk); - sock_put(sk); } void dccp_init_xmit_timers(struct sock *sk) diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 8396705deffc..40c851693f77 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -91,9 +91,9 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) next_opt = memchr(opt, '#', end - opt) ?: end; opt_len = next_opt - opt; - if (!opt_len) { - printk(KERN_WARNING - "Empty option to dns_resolver key\n"); + if (opt_len <= 0 || opt_len > 128) { + pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n", + opt_len); return -EINVAL; } @@ -127,10 +127,8 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) } bad_option_value: - printk(KERN_WARNING - "Option '%*.*s' to dns_resolver key:" - " bad/missing value\n", - opt_nlen, opt_nlen, opt); + pr_warn_ratelimited("Option '%*.*s' to dns_resolver key: bad/missing value\n", + opt_nlen, opt_nlen, opt); return -EINVAL; } while (opt = next_opt + 1, opt < end); } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index adf50fbc4c13..47725250b4ca 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -258,11 +258,13 @@ static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst) static int dsa_port_setup(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; - int err; + int err = 0; memset(&dp->devlink_port, 0, sizeof(dp->devlink_port)); - err = devlink_port_register(ds->devlink, &dp->devlink_port, dp->index); + if (dp->type != DSA_PORT_TYPE_UNUSED) + err = devlink_port_register(ds->devlink, &dp->devlink_port, + dp->index); if (err) return err; @@ -293,7 +295,8 @@ static int dsa_port_setup(struct dsa_port *dp) static void dsa_port_teardown(struct dsa_port *dp) { - devlink_port_unregister(&dp->devlink_port); + if (dp->type != DSA_PORT_TYPE_UNUSED) + devlink_port_unregister(&dp->devlink_port); switch (dp->type) { case DSA_PORT_TYPE_UNUSED: diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h index b8d95cb71c25..44a7e16bf3b5 100644 --- a/net/ieee802154/6lowpan/6lowpan_i.h +++ b/net/ieee802154/6lowpan/6lowpan_i.h @@ -20,8 +20,8 @@ typedef unsigned __bitwise lowpan_rx_result; struct frag_lowpan_compare_key { u16 tag; u16 d_size; - const struct ieee802154_addr src; - const struct ieee802154_addr dst; + struct ieee802154_addr src; + struct ieee802154_addr dst; }; /* Equivalent of ipv4 struct ipq diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 1790b65944b3..2cc224106b69 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -75,14 +75,14 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb, { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); - struct frag_lowpan_compare_key key = { - .tag = cb->d_tag, - .d_size = cb->d_size, - .src = *src, - .dst = *dst, - }; + struct frag_lowpan_compare_key key = {}; struct inet_frag_queue *q; + key.tag = cb->d_tag; + key.d_size = cb->d_size; + key.src = *src; + key.dst = *dst; + q = inet_frag_find(&ieee802154_lowpan->frags, &key); if (!q) return NULL; @@ -372,7 +372,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type) struct lowpan_frag_queue *fq; struct net *net = dev_net(skb->dev); struct lowpan_802154_cb *cb = lowpan_802154_cb(skb); - struct ieee802154_hdr hdr; + struct ieee802154_hdr hdr = {}; int err; if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) diff --git a/net/ife/ife.c b/net/ife/ife.c index 7d1ec76e7f43..13bbf8cb6a39 100644 --- a/net/ife/ife.c +++ b/net/ife/ife.c @@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen) int total_pull; u16 ifehdrln; + if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN)) + return NULL; + ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len); ifehdrln = ntohs(ifehdr->metalen); total_pull = skb->dev->hard_header_len + ifehdrln; @@ -92,12 +95,43 @@ struct meta_tlvhdr { __be16 len; }; +static bool __ife_tlv_meta_valid(const unsigned char *skbdata, + const unsigned char *ifehdr_end) +{ + const struct meta_tlvhdr *tlv; + u16 tlvlen; + + if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end)) + return false; + + tlv = (const struct meta_tlvhdr *)skbdata; + tlvlen = ntohs(tlv->len); + + /* tlv length field is inc header, check on minimum */ + if (tlvlen < NLA_HDRLEN) + return false; + + /* overflow by NLA_ALIGN check */ + if (NLA_ALIGN(tlvlen) < tlvlen) + return false; + + if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end)) + return false; + + return true; +} + /* Caller takes care of presenting data in network order */ -void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen) +void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype, + u16 *dlen, u16 *totlen) { - struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata; + struct meta_tlvhdr *tlv; + + if (!__ife_tlv_meta_valid(skbdata, ifehdr_end)) + return NULL; + tlv = (struct meta_tlvhdr *)skbdata; *dlen = ntohs(tlv->len) - NLA_HDRLEN; *attrtype = ntohs(tlv->type); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index f05afaf3235c..e66172aaf241 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -326,10 +326,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, int rpf, struct in_device *idev, u32 *itag) { + struct net *net = dev_net(dev); + struct flow_keys flkeys; int ret, no_addr; struct fib_result res; struct flowi4 fl4; - struct net *net = dev_net(dev); bool dev_match; fl4.flowi4_oif = 0; @@ -347,6 +348,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; + if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) { + fl4.flowi4_proto = 0; + fl4.fl4_sport = 0; + fl4.fl4_dport = 0; + } trace_fib_validate_source(dev, &fl4); @@ -643,6 +649,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, + [RTA_TABLE] = { .type = NLA_U32 }, }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 9c169bb2444d..f200b304f76c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -722,10 +722,12 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); - else + else if (tunnel->erspan_ver == 2) erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); + else + goto free_skb; tunnel->parms.o_flags &= ~TUNNEL_KEY; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN)); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 4c11b810a447..d54abc097800 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1045,7 +1045,8 @@ alloc_new_skb: if (copy > length) copy = length; - if (!(rt->dst.dev->features&NETIF_F_SG)) { + if (!(rt->dst.dev->features&NETIF_F_SG) && + skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; @@ -1109,6 +1110,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, struct ip_options_rcu *opt; struct rtable *rt; + rt = *rtp; + if (unlikely(!rt)) + return -EFAULT; + /* * setup for corking. */ @@ -1124,9 +1129,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->flags |= IPCORK_OPT; cork->addr = ipc->addr; } - rt = *rtp; - if (unlikely(!rt)) - return -EFAULT; + /* * We steal reference to this route, caller should not release it */ diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5ad2d8ed3a3f..57bbb060faaf 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -505,8 +505,6 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) int err; int copied; - WARN_ON_ONCE(sk->sk_family == AF_INET6); - err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (!skb) diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 4fe97723b53f..30221701614c 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -43,7 +43,10 @@ mr_table_alloc(struct net *net, u32 id, write_pnet(&mrt->net, net); mrt->ops = *ops; - rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params); + if (rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params)) { + kfree(mrt); + return NULL; + } INIT_LIST_HEAD(&mrt->mfc_cache_list); INIT_LIST_HEAD(&mrt->mfc_unres_queue); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 44b308d93ec2..e85f35b89c49 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -34,6 +34,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv4 packet filter"); +MODULE_ALIAS("ipt_icmp"); void *ipt_alloc_initial_table(const struct xt_table *info) { diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index fd01f13c896a..12843c9ef142 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -89,10 +89,10 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) return true ^ invert; } + memset(&flow, 0, sizeof(flow)); flow.flowi4_iif = LOOPBACK_IFINDEX; flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); - flow.flowi4_oif = 0; flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; flow.flowi4_tos = RT_TOS(iph->tos); flow.flowi4_scope = RT_SCOPE_UNIVERSE; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 05e47d777009..56a010622f70 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -775,8 +775,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.addr = faddr = daddr; if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; } tos = get_rttos(&ipc, inet); @@ -842,6 +844,7 @@ back_from_confirm: out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ccb25d80f679..2cfa1b518f8d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -709,7 +709,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; - fnhe->fnhe_expires = expires; + fnhe->fnhe_expires = max(1UL, expires); /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception @@ -1297,6 +1297,36 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) { struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions); @@ -1310,8 +1340,14 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) for (fnhe = rcu_dereference(hash[hval].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { - if (fnhe->fnhe_daddr == daddr) + if (fnhe->fnhe_daddr == daddr) { + if (fnhe->fnhe_expires && + time_after(jiffies, fnhe->fnhe_expires)) { + ip_del_fnhe(nh, daddr); + break; + } return fnhe; + } } return NULL; } @@ -1339,6 +1375,7 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, fnhe->fnhe_gw = 0; fnhe->fnhe_pmtu = 0; fnhe->fnhe_expires = 0; + fnhe->fnhe_mtu_locked = false; fnhe_flush_routes(fnhe); orig = NULL; } @@ -1636,36 +1673,6 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } -static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) -{ - struct fnhe_hash_bucket *hash; - struct fib_nh_exception *fnhe, __rcu **fnhe_p; - u32 hval = fnhe_hashfun(daddr); - - spin_lock_bh(&fnhe_lock); - - hash = rcu_dereference_protected(nh->nh_exceptions, - lockdep_is_held(&fnhe_lock)); - hash += hval; - - fnhe_p = &hash->chain; - fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); - while (fnhe) { - if (fnhe->fnhe_daddr == daddr) { - rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( - fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); - fnhe_flush_routes(fnhe); - kfree_rcu(fnhe, rcu); - break; - } - fnhe_p = &fnhe->fnhe_next; - fnhe = rcu_dereference_protected(fnhe->fnhe_next, - lockdep_is_held(&fnhe_lock)); - } - - spin_unlock_bh(&fnhe_lock); -} - /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1719,20 +1726,10 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) { + if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); - if (rth && rth->dst.expires && - time_after(jiffies, rth->dst.expires)) { - ip_del_fnhe(&FIB_RES_NH(*res), daddr); - fnhe = NULL; - } else { - goto rt_cache; - } - } - - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); - -rt_cache: + else + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -1964,8 +1961,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); - if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) + if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) { flkeys = &_flkeys; + } else { + fl4.flowi4_proto = 0; + fl4.fl4_sport = 0; + fl4.fl4_dport = 0; + } err = fib_lookup(net, &fl4, res, 0); if (err != 0) { @@ -2216,39 +2218,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res, * the loopback interface and the IP_PKTINFO ipi_ifindex will * be set to the loopback interface as well. */ - fi = NULL; + do_cache = false; } fnhe = NULL; do_cache &= fi != NULL; - if (do_cache) { + if (fi) { struct rtable __rcu **prth; struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); + if (!do_cache) + goto add; if (fnhe) { prth = &fnhe->fnhe_rth_output; - rth = rcu_dereference(*prth); - if (rth && rth->dst.expires && - time_after(jiffies, rth->dst.expires)) { - ip_del_fnhe(nh, fl4->daddr); - fnhe = NULL; - } else { - goto rt_cache; + } else { + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } - - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; - } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); - -rt_cache: if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bccc4c270087..c9d00ef54dec 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -697,7 +697,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, { return skb->len < size_goal && sock_net(sk)->ipv4.sysctl_tcp_autocorking && - skb != tcp_write_queue_head(sk) && + !tcp_rtx_queue_empty(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } @@ -1204,7 +1204,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) uarg->zerocopy = 0; } - if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) { + if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && + !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; @@ -2368,6 +2369,7 @@ void tcp_write_queue_purge(struct sock *sk) INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); + tcp_sk(sk)->packets_out = 0; } int tcp_disconnect(struct sock *sk, int flags) @@ -2417,7 +2419,6 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; - tp->packets_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; @@ -2673,7 +2674,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_REPAIR_QUEUE: if (!tp->repair) err = -EPERM; - else if (val < TCP_QUEUES_NR) + else if ((unsigned int)val < TCP_QUEUES_NR) tp->repair_queue = val; else err = -EINVAL; @@ -2813,8 +2814,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: - /* Read the IP->Key mappings from userspace */ - err = tp->af_specific->md5_parse(sk, optname, optval, optlen); + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); + else + err = -EINVAL; break; #endif case TCP_USER_TIMEOUT: diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 158d105e76da..58e2f479ffb4 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -806,7 +806,9 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) } } } - bbr->idle_restart = 0; + /* Restart after idle ends only once we process a new S/ACK for data */ + if (rs->delivered > 0) + bbr->idle_restart = 0; } static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 367def6ddeda..e51c644484dc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3868,11 +3868,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) int length = (th->doff << 2) - sizeof(*th); const u8 *ptr = (const u8 *)(th + 1); - /* If the TCP option is too short, we can short cut */ - if (length < TCPOLEN_MD5SIG) - return NULL; - - while (length > 0) { + /* If not enough data remaining, we can short cut */ + while (length >= TCPOLEN_MD5SIG) { int opcode = *ptr++; int opsize; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 383cac0ff0ec..d07e34f8e309 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2833,8 +2833,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) return -EBUSY; if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { - if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) - BUG(); + if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { + WARN_ON_ONCE(1); + return -EINVAL; + } if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) return -ENOMEM; } @@ -3342,6 +3344,7 @@ static void tcp_connect_init(struct sock *sk) sock_reset_flag(sk, SOCK_DONE); tp->snd_wnd = 0; tcp_init_wl(tp, 0); + tcp_write_queue_purge(sk); tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 24b5c59b1c53..b61a770884fa 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -401,9 +401,9 @@ static int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score += 4; } @@ -952,8 +952,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; connected = 0; } @@ -1074,6 +1076,7 @@ do_append_data: out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 6794ddf0547c..11e4e80cf7e9 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -34,16 +34,15 @@ config IPV6_ROUTE_INFO bool "IPv6: Route Information (RFC 4191) support" depends on IPV6_ROUTER_PREF ---help--- - This is experimental support of Route Information. + Support of Route Information. If unsure, say N. config IPV6_OPTIMISTIC_DAD bool "IPv6: Enable RFC 4429 Optimistic DAD" ---help--- - This is experimental support for optimistic Duplicate - Address Detection. It allows for autoconfigured addresses - to be used more quickly. + Support for optimistic Duplicate Address Detection. It allows for + autoconfigured addresses to be used more quickly. If unsure, say N. @@ -280,7 +279,7 @@ config IPV6_MROUTE depends on IPV6 select IP_MROUTE_COMMON ---help--- - Experimental support for IPv6 multicast forwarding. + Support for IPv6 multicast forwarding. If unsure, say N. config IPV6_MROUTE_MULTIPLE_TABLES diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 69727bc168cb..458de353f5d9 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -71,6 +71,7 @@ struct ip6gre_net { struct ip6_tnl __rcu *tunnels[4][IP6_GRE_HASH_SIZE]; struct ip6_tnl __rcu *collect_md_tun; + struct ip6_tnl __rcu *collect_md_tun_erspan; struct net_device *fb_tunnel_dev; }; @@ -81,6 +82,7 @@ static int ip6gre_tunnel_init(struct net_device *dev); static void ip6gre_tunnel_setup(struct net_device *dev); static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t); static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu); +static void ip6erspan_tnl_link_config(struct ip6_tnl *t, int set_mtu); /* Tunnel hash table */ @@ -232,7 +234,12 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, if (cand) return cand; - t = rcu_dereference(ign->collect_md_tun); + if (gre_proto == htons(ETH_P_ERSPAN) || + gre_proto == htons(ETH_P_ERSPAN2)) + t = rcu_dereference(ign->collect_md_tun_erspan); + else + t = rcu_dereference(ign->collect_md_tun); + if (t && t->dev->flags & IFF_UP) return t; @@ -261,6 +268,31 @@ static struct ip6_tnl __rcu **__ip6gre_bucket(struct ip6gre_net *ign, return &ign->tunnels[prio][h]; } +static void ip6gre_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t) +{ + if (t->parms.collect_md) + rcu_assign_pointer(ign->collect_md_tun, t); +} + +static void ip6erspan_tunnel_link_md(struct ip6gre_net *ign, struct ip6_tnl *t) +{ + if (t->parms.collect_md) + rcu_assign_pointer(ign->collect_md_tun_erspan, t); +} + +static void ip6gre_tunnel_unlink_md(struct ip6gre_net *ign, struct ip6_tnl *t) +{ + if (t->parms.collect_md) + rcu_assign_pointer(ign->collect_md_tun, NULL); +} + +static void ip6erspan_tunnel_unlink_md(struct ip6gre_net *ign, + struct ip6_tnl *t) +{ + if (t->parms.collect_md) + rcu_assign_pointer(ign->collect_md_tun_erspan, NULL); +} + static inline struct ip6_tnl __rcu **ip6gre_bucket(struct ip6gre_net *ign, const struct ip6_tnl *t) { @@ -271,9 +303,6 @@ static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = ip6gre_bucket(ign, t); - if (t->parms.collect_md) - rcu_assign_pointer(ign->collect_md_tun, t); - rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } @@ -283,9 +312,6 @@ static void ip6gre_tunnel_unlink(struct ip6gre_net *ign, struct ip6_tnl *t) struct ip6_tnl __rcu **tp; struct ip6_tnl *iter; - if (t->parms.collect_md) - rcu_assign_pointer(ign->collect_md_tun, NULL); - for (tp = ip6gre_bucket(ign, t); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { @@ -374,11 +400,23 @@ failed_free: return NULL; } +static void ip6erspan_tunnel_uninit(struct net_device *dev) +{ + struct ip6_tnl *t = netdev_priv(dev); + struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); + + ip6erspan_tunnel_unlink_md(ign, t); + ip6gre_tunnel_unlink(ign, t); + dst_cache_reset(&t->dst_cache); + dev_put(dev); +} + static void ip6gre_tunnel_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); + ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); dst_cache_reset(&t->dst_cache); dev_put(dev); @@ -698,6 +736,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, else fl6->daddr = tunnel->parms.raddr; + if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) + return -ENOMEM; + /* Push GRE header. */ protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto; @@ -908,7 +949,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, truncate = true; } - if (skb_cow_head(skb, dev->needed_headroom)) + if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen)) goto tx_err; t->parms.o_flags &= ~TUNNEL_KEY; @@ -979,11 +1020,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, erspan_build_header(skb, ntohl(t->parms.o_key), t->parms.index, truncate, false); - else + else if (t->parms.erspan_ver == 2) erspan_build_header_v2(skb, ntohl(t->parms.o_key), t->parms.dir, t->parms.hwid, truncate, false); + else + goto tx_err; + fl6.daddr = t->parms.raddr; } @@ -1019,12 +1063,11 @@ tx_err: return NETDEV_TX_OK; } -static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) +static void ip6gre_tnl_link_config_common(struct ip6_tnl *t) { struct net_device *dev = t->dev; struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; - int t_hlen; if (dev->type != ARPHRD_ETHER) { memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); @@ -1051,12 +1094,13 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) dev->flags |= IFF_POINTOPOINT; else dev->flags &= ~IFF_POINTOPOINT; +} - t->tun_hlen = gre_calc_hlen(t->parms.o_flags); - - t->hlen = t->encap_hlen + t->tun_hlen; - - t_hlen = t->hlen + sizeof(struct ipv6hdr); +static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, + int t_hlen) +{ + const struct __ip6_tnl_parm *p = &t->parms; + struct net_device *dev = t->dev; if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & @@ -1088,8 +1132,26 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) } } -static int ip6gre_tnl_change(struct ip6_tnl *t, - const struct __ip6_tnl_parm *p, int set_mtu) +static int ip6gre_calc_hlen(struct ip6_tnl *tunnel) +{ + int t_hlen; + + tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); + tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; + + t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); + tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen; + return t_hlen; +} + +static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu) +{ + ip6gre_tnl_link_config_common(t); + ip6gre_tnl_link_config_route(t, set_mtu, ip6gre_calc_hlen(t)); +} + +static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t, + const struct __ip6_tnl_parm *p) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; @@ -1105,6 +1167,12 @@ static int ip6gre_tnl_change(struct ip6_tnl *t, t->parms.o_flags = p->o_flags; t->parms.fwmark = p->fwmark; dst_cache_reset(&t->dst_cache); +} + +static int ip6gre_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p, + int set_mtu) +{ + ip6gre_tnl_copy_tnl_parm(t, p); ip6gre_tnl_link_config(t, set_mtu); return 0; } @@ -1381,11 +1449,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) return ret; } - tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); - tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; - t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); - - dev->hard_header_len = LL_MAX_HEADER + t_hlen; + t_hlen = ip6gre_calc_hlen(tunnel); dev->mtu = ETH_DATA_LEN - t_hlen; if (dev->type == ARPHRD_ETHER) dev->mtu -= ETH_HLEN; @@ -1728,6 +1792,19 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = { .ndo_get_iflink = ip6_tnl_get_iflink, }; +static int ip6erspan_calc_hlen(struct ip6_tnl *tunnel) +{ + int t_hlen; + + tunnel->tun_hlen = 8; + tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + + erspan_hdr_len(tunnel->parms.erspan_ver); + + t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); + tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen; + return t_hlen; +} + static int ip6erspan_tap_init(struct net_device *dev) { struct ip6_tnl *tunnel; @@ -1751,12 +1828,7 @@ static int ip6erspan_tap_init(struct net_device *dev) return ret; } - tunnel->tun_hlen = 8; - tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + - erspan_hdr_len(tunnel->parms.erspan_ver); - t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); - - dev->hard_header_len = LL_MAX_HEADER + t_hlen; + t_hlen = ip6erspan_calc_hlen(tunnel); dev->mtu = ETH_DATA_LEN - t_hlen; if (dev->type == ARPHRD_ETHER) dev->mtu -= ETH_HLEN; @@ -1764,14 +1836,14 @@ static int ip6erspan_tap_init(struct net_device *dev) dev->mtu -= 8; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - ip6gre_tnl_link_config(tunnel, 1); + ip6erspan_tnl_link_config(tunnel, 1); return 0; } static const struct net_device_ops ip6erspan_netdev_ops = { .ndo_init = ip6erspan_tap_init, - .ndo_uninit = ip6gre_tunnel_uninit, + .ndo_uninit = ip6erspan_tunnel_uninit, .ndo_start_xmit = ip6erspan_tunnel_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, @@ -1835,13 +1907,11 @@ static bool ip6gre_netlink_encap_parms(struct nlattr *data[], return ret; } -static int ip6gre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], - struct netlink_ext_ack *extack) +static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { struct ip6_tnl *nt; - struct net *net = dev_net(dev); - struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); struct ip_tunnel_encap ipencap; int err; @@ -1854,16 +1924,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev, return err; } - ip6gre_netlink_parms(data, &nt->parms); - - if (nt->parms.collect_md) { - if (rtnl_dereference(ign->collect_md_tun)) - return -EEXIST; - } else { - if (ip6gre_tunnel_find(net, &nt->parms, dev->type)) - return -EEXIST; - } - if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); @@ -1874,51 +1934,94 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev, if (err) goto out; - ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); - if (tb[IFLA_MTU]) ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); dev_hold(dev); - ip6gre_tunnel_link(ign, nt); out: return err; } -static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], - struct nlattr *data[], - struct netlink_ext_ack *extack) +static int ip6gre_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip6_tnl *nt = netdev_priv(dev); + struct net *net = dev_net(dev); + struct ip6gre_net *ign; + int err; + + ip6gre_netlink_parms(data, &nt->parms); + ign = net_generic(net, ip6gre_net_id); + + if (nt->parms.collect_md) { + if (rtnl_dereference(ign->collect_md_tun)) + return -EEXIST; + } else { + if (ip6gre_tunnel_find(net, &nt->parms, dev->type)) + return -EEXIST; + } + + err = ip6gre_newlink_common(src_net, dev, tb, data, extack); + if (!err) { + ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); + ip6gre_tunnel_link_md(ign, nt); + ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt); + } + return err; +} + +static struct ip6_tnl * +ip6gre_changelink_common(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], struct __ip6_tnl_parm *p_p, + struct netlink_ext_ack *extack) { struct ip6_tnl *t, *nt = netdev_priv(dev); struct net *net = nt->net; struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); - struct __ip6_tnl_parm p; struct ip_tunnel_encap ipencap; if (dev == ign->fb_tunnel_dev) - return -EINVAL; + return ERR_PTR(-EINVAL); if (ip6gre_netlink_encap_parms(data, &ipencap)) { int err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) - return err; + return ERR_PTR(err); } - ip6gre_netlink_parms(data, &p); + ip6gre_netlink_parms(data, p_p); - t = ip6gre_tunnel_locate(net, &p, 0); + t = ip6gre_tunnel_locate(net, p_p, 0); if (t) { if (t->dev != dev) - return -EEXIST; + return ERR_PTR(-EEXIST); } else { t = nt; } + return t; +} + +static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id); + struct __ip6_tnl_parm p; + struct ip6_tnl *t; + + t = ip6gre_changelink_common(dev, tb, data, &p, extack); + if (IS_ERR(t)) + return PTR_ERR(t); + + ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]); + ip6gre_tunnel_link_md(ign, t); ip6gre_tunnel_link(ign, t); return 0; } @@ -2068,6 +2171,69 @@ static void ip6erspan_tap_setup(struct net_device *dev) netif_keep_dst(dev); } +static int ip6erspan_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip6_tnl *nt = netdev_priv(dev); + struct net *net = dev_net(dev); + struct ip6gre_net *ign; + int err; + + ip6gre_netlink_parms(data, &nt->parms); + ign = net_generic(net, ip6gre_net_id); + + if (nt->parms.collect_md) { + if (rtnl_dereference(ign->collect_md_tun_erspan)) + return -EEXIST; + } else { + if (ip6gre_tunnel_find(net, &nt->parms, dev->type)) + return -EEXIST; + } + + err = ip6gre_newlink_common(src_net, dev, tb, data, extack); + if (!err) { + ip6erspan_tnl_link_config(nt, !tb[IFLA_MTU]); + ip6erspan_tunnel_link_md(ign, nt); + ip6gre_tunnel_link(net_generic(net, ip6gre_net_id), nt); + } + return err; +} + +static void ip6erspan_tnl_link_config(struct ip6_tnl *t, int set_mtu) +{ + ip6gre_tnl_link_config_common(t); + ip6gre_tnl_link_config_route(t, set_mtu, ip6erspan_calc_hlen(t)); +} + +static int ip6erspan_tnl_change(struct ip6_tnl *t, + const struct __ip6_tnl_parm *p, int set_mtu) +{ + ip6gre_tnl_copy_tnl_parm(t, p); + ip6erspan_tnl_link_config(t, set_mtu); + return 0; +} + +static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id); + struct __ip6_tnl_parm p; + struct ip6_tnl *t; + + t = ip6gre_changelink_common(dev, tb, data, &p, extack); + if (IS_ERR(t)) + return PTR_ERR(t); + + ip6gre_tunnel_unlink_md(ign, t); + ip6gre_tunnel_unlink(ign, t); + ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]); + ip6erspan_tunnel_link_md(ign, t); + ip6gre_tunnel_link(ign, t); + return 0; +} + static struct rtnl_link_ops ip6gre_link_ops __read_mostly = { .kind = "ip6gre", .maxtype = IFLA_GRE_MAX, @@ -2104,8 +2270,8 @@ static struct rtnl_link_ops ip6erspan_tap_ops __read_mostly = { .priv_size = sizeof(struct ip6_tnl), .setup = ip6erspan_tap_setup, .validate = ip6erspan_tap_validate, - .newlink = ip6gre_newlink, - .changelink = ip6gre_changelink, + .newlink = ip6erspan_newlink, + .changelink = ip6erspan_changelink, .get_size = ip6gre_get_size, .fill_info = ip6gre_fill_info, .get_link_net = ip6_tnl_get_link_net, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2e891d2c30ef..7b6d1689087b 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1503,7 +1503,8 @@ alloc_new_skb: if (copy > length) copy = length; - if (!(rt->dst.dev->features&NETIF_F_SG)) { + if (!(rt->dst.dev->features&NETIF_F_SG) && + skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index c214ffec02f0..ca957dd93a29 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -669,7 +669,7 @@ static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu) else mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr); - dev->mtu = max_t(int, mtu, IPV6_MIN_MTU); + dev->mtu = max_t(int, mtu, IPV4_MIN_MTU); } /** @@ -881,7 +881,7 @@ static void vti6_dev_setup(struct net_device *dev) dev->priv_destructor = vti6_dev_free; dev->type = ARPHRD_TUNNEL6; - dev->min_mtu = IPV6_MIN_MTU; + dev->min_mtu = IPV4_MIN_MTU; dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr); dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index ccbfa83e4bb0..ce77bcc2490c 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -48,6 +48,34 @@ config NFT_CHAIN_ROUTE_IPV6 fields such as the source, destination, flowlabel, hop-limit and the packet mark. +if NF_NAT_IPV6 + +config NFT_CHAIN_NAT_IPV6 + tristate "IPv6 nf_tables nat chain support" + help + This option enables the "nat" chain for IPv6 in nf_tables. This + chain type is used to perform Network Address Translation (NAT) + packet transformations such as the source, destination address and + source and destination ports. + +config NFT_MASQ_IPV6 + tristate "IPv6 masquerade support for nf_tables" + depends on NFT_MASQ + select NF_NAT_MASQUERADE_IPV6 + help + This is the expression that provides IPv4 masquerading support for + nf_tables. + +config NFT_REDIR_IPV6 + tristate "IPv6 redirect support for nf_tables" + depends on NFT_REDIR + select NF_NAT_REDIRECT + help + This is the expression that provides IPv4 redirect support for + nf_tables. + +endif # NF_NAT_IPV6 + config NFT_REJECT_IPV6 select NF_REJECT_IPV6 default NFT_REJECT @@ -107,39 +135,12 @@ config NF_NAT_IPV6 if NF_NAT_IPV6 -config NFT_CHAIN_NAT_IPV6 - depends on NF_TABLES_IPV6 - tristate "IPv6 nf_tables nat chain support" - help - This option enables the "nat" chain for IPv6 in nf_tables. This - chain type is used to perform Network Address Translation (NAT) - packet transformations such as the source, destination address and - source and destination ports. - config NF_NAT_MASQUERADE_IPV6 tristate "IPv6 masquerade support" help This is the kernel functionality to provide NAT in the masquerade flavour (automatic source address selection) for IPv6. -config NFT_MASQ_IPV6 - tristate "IPv6 masquerade support for nf_tables" - depends on NF_TABLES_IPV6 - depends on NFT_MASQ - select NF_NAT_MASQUERADE_IPV6 - help - This is the expression that provides IPv4 masquerading support for - nf_tables. - -config NFT_REDIR_IPV6 - tristate "IPv6 redirect support for nf_tables" - depends on NF_TABLES_IPV6 - depends on NFT_REDIR - select NF_NAT_REDIRECT - help - This is the expression that provides IPv4 redirect support for - nf_tables. - endif # NF_NAT_IPV6 config IP6_NF_IPTABLES diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 65c9e1a58305..97f79dc943d7 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -38,6 +38,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("IPv6 packet filter"); +MODULE_ALIAS("ip6t_icmp6"); void *ip6t_alloc_initial_table(const struct xt_table *info) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 49b954d6d0fa..f4d61736c41a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1835,11 +1835,16 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb, const struct ipv6hdr *inner_iph; const struct icmp6hdr *icmph; struct ipv6hdr _inner_iph; + struct icmp6hdr _icmph; if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6)) goto out; - icmph = icmp6_hdr(skb); + icmph = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_icmph), &_icmph); + if (!icmph) + goto out; + if (icmph->icmp6_type != ICMPV6_DEST_UNREACH && icmph->icmp6_type != ICMPV6_PKT_TOOBIG && icmph->icmp6_type != ICMPV6_TIME_EXCEED && @@ -3975,6 +3980,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu) static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, + [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, @@ -3986,6 +3992,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_EXPIRES] = { .type = NLA_U32 }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, + [RTA_TABLE] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index f343e6f0fc95..5fe139484919 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; - set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4ec76a87aeb8..ea0730028e5d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -148,9 +148,9 @@ static int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score++; } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f85f0d7480ac..4a46df8441c9 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -341,6 +341,9 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_flush_gc(); + for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/key/af_key.c b/net/key/af_key.c index 7e2e7188e7f4..e62e52e8f141 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -437,6 +437,24 @@ static int verify_address_len(const void *p) return 0; } +static inline int sadb_key_len(const struct sadb_key *key) +{ + int key_bytes = DIV_ROUND_UP(key->sadb_key_bits, 8); + + return DIV_ROUND_UP(sizeof(struct sadb_key) + key_bytes, + sizeof(uint64_t)); +} + +static int verify_key_len(const void *p) +{ + const struct sadb_key *key = p; + + if (sadb_key_len(key) > key->sadb_key_len) + return -EINVAL; + + return 0; +} + static inline int pfkey_sec_ctx_len(const struct sadb_x_sec_ctx *sec_ctx) { return DIV_ROUND_UP(sizeof(struct sadb_x_sec_ctx) + @@ -533,16 +551,25 @@ static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void * return -EINVAL; if (ext_hdrs[ext_type-1] != NULL) return -EINVAL; - if (ext_type == SADB_EXT_ADDRESS_SRC || - ext_type == SADB_EXT_ADDRESS_DST || - ext_type == SADB_EXT_ADDRESS_PROXY || - ext_type == SADB_X_EXT_NAT_T_OA) { + switch (ext_type) { + case SADB_EXT_ADDRESS_SRC: + case SADB_EXT_ADDRESS_DST: + case SADB_EXT_ADDRESS_PROXY: + case SADB_X_EXT_NAT_T_OA: if (verify_address_len(p)) return -EINVAL; - } - if (ext_type == SADB_X_EXT_SEC_CTX) { + break; + case SADB_X_EXT_SEC_CTX: if (verify_sec_ctx_len(p)) return -EINVAL; + break; + case SADB_EXT_KEY_AUTH: + case SADB_EXT_KEY_ENCRYPT: + if (verify_key_len(p)) + return -EINVAL; + break; + default: + break; } ext_hdrs[ext_type-1] = (void *) p; } @@ -1104,14 +1131,12 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (key != NULL && sa->sadb_sa_auth != SADB_X_AALG_NULL && - ((key->sadb_key_bits+7) / 8 == 0 || - (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t))) + key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); key = ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]; if (key != NULL && sa->sadb_sa_encrypt != SADB_EALG_NULL && - ((key->sadb_key_bits+7) / 8 == 0 || - (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t))) + key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); x = xfrm_state_alloc(net); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 0fbd3ee26165..40261cb68e83 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -183,6 +183,26 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) } EXPORT_SYMBOL_GPL(l2tp_tunnel_get); +struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) +{ + const struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_tunnel *tunnel; + int count = 0; + + rcu_read_lock_bh(); + list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { + if (++count > nth) { + l2tp_tunnel_inc_refcount(tunnel); + rcu_read_unlock_bh(); + return tunnel; + } + } + rcu_read_unlock_bh(); + + return NULL; +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth); + /* Lookup a session. A new reference is held on the returned session. */ struct l2tp_session *l2tp_session_get(const struct net *net, struct l2tp_tunnel *tunnel, @@ -335,26 +355,6 @@ err_tlock: } EXPORT_SYMBOL_GPL(l2tp_session_register); -struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth) -{ - struct l2tp_net *pn = l2tp_pernet(net); - struct l2tp_tunnel *tunnel; - int count = 0; - - rcu_read_lock_bh(); - list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (++count > nth) { - rcu_read_unlock_bh(); - return tunnel; - } - } - - rcu_read_unlock_bh(); - - return NULL; -} -EXPORT_SYMBOL_GPL(l2tp_tunnel_find_nth); - /***************************************************************************** * Receive data handling *****************************************************************************/ diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index ba33cbec71eb..c199020f8a8a 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -212,6 +212,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session) } struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); +struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth); + void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); struct l2tp_session *l2tp_session_get(const struct net *net, @@ -220,7 +222,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net, struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth); struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname); -struct l2tp_tunnel *l2tp_tunnel_find_nth(const struct net *net, int nth); int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 72e713da4733..7f1e842ef05a 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -47,7 +47,11 @@ struct l2tp_dfs_seq_data { static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) { - pd->tunnel = l2tp_tunnel_find_nth(pd->net, pd->tunnel_idx); + /* Drop reference taken during previous invocation */ + if (pd->tunnel) + l2tp_tunnel_dec_refcount(pd->tunnel); + + pd->tunnel = l2tp_tunnel_get_nth(pd->net, pd->tunnel_idx); pd->tunnel_idx++; } @@ -96,7 +100,17 @@ static void *l2tp_dfs_seq_next(struct seq_file *m, void *v, loff_t *pos) static void l2tp_dfs_seq_stop(struct seq_file *p, void *v) { - /* nothing to do */ + struct l2tp_dfs_seq_data *pd = v; + + if (!pd || pd == SEQ_START_TOKEN) + return; + + /* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */ + if (pd->tunnel) { + l2tp_tunnel_dec_refcount(pd->tunnel); + pd->tunnel = NULL; + pd->session = NULL; + } } static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index b05dbd9ffcb2..6616c9fd292f 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -487,14 +487,17 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback struct net *net = sock_net(skb->sk); for (;;) { - tunnel = l2tp_tunnel_find_nth(net, ti); + tunnel = l2tp_tunnel_get_nth(net, ti); if (tunnel == NULL) goto out; if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - tunnel, L2TP_CMD_TUNNEL_GET) < 0) + tunnel, L2TP_CMD_TUNNEL_GET) < 0) { + l2tp_tunnel_dec_refcount(tunnel); goto out; + } + l2tp_tunnel_dec_refcount(tunnel); ti++; } @@ -848,7 +851,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback for (;;) { if (tunnel == NULL) { - tunnel = l2tp_tunnel_find_nth(net, ti); + tunnel = l2tp_tunnel_get_nth(net, ti); if (tunnel == NULL) goto out; } @@ -856,6 +859,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback session = l2tp_session_get_nth(tunnel, si); if (session == NULL) { ti++; + l2tp_tunnel_dec_refcount(tunnel); tunnel = NULL; si = 0; continue; @@ -865,6 +869,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback cb->nlh->nlmsg_seq, NLM_F_MULTI, session, L2TP_CMD_SESSION_GET) < 0) { l2tp_session_dec_refcount(session); + l2tp_tunnel_dec_refcount(tunnel); break; } l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 896bbca9bdaa..1fd9e145076a 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -619,6 +619,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); error = -EINVAL; + + if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6)) + goto end; + if (sp->sa_protocol != PX_PROTO_OL2TP) goto end; @@ -1551,16 +1558,19 @@ struct pppol2tp_seq_data { static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) { + /* Drop reference taken during previous invocation */ + if (pd->tunnel) + l2tp_tunnel_dec_refcount(pd->tunnel); + for (;;) { - pd->tunnel = l2tp_tunnel_find_nth(net, pd->tunnel_idx); + pd->tunnel = l2tp_tunnel_get_nth(net, pd->tunnel_idx); pd->tunnel_idx++; - if (pd->tunnel == NULL) - break; + /* Only accept L2TPv2 tunnels */ + if (!pd->tunnel || pd->tunnel->version == 2) + return; - /* Ignore L2TPv3 tunnels */ - if (pd->tunnel->version < 3) - break; + l2tp_tunnel_dec_refcount(pd->tunnel); } } @@ -1609,7 +1619,17 @@ static void *pppol2tp_seq_next(struct seq_file *m, void *v, loff_t *pos) static void pppol2tp_seq_stop(struct seq_file *p, void *v) { - /* nothing to do */ + struct pppol2tp_seq_data *pd = v; + + if (!pd || pd == SEQ_START_TOKEN) + return; + + /* Drop reference taken by last invocation of pppol2tp_next_tunnel() */ + if (pd->tunnel) { + l2tp_tunnel_dec_refcount(pd->tunnel); + pd->tunnel = NULL; + pd->session = NULL; + } } static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 01dcc0823d1f..1beeea9549fa 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -199,9 +199,19 @@ static int llc_ui_release(struct socket *sock) llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); - if (!sock_flag(sk, SOCK_ZAPPED)) + if (!sock_flag(sk, SOCK_ZAPPED)) { + struct llc_sap *sap = llc->sap; + + /* Hold this for release_sock(), so that llc_backlog_rcv() + * could still use it. + */ + llc_sap_hold(sap); llc_sap_remove_socket(llc->sap, sk); - release_sock(sk); + release_sock(sk); + llc_sap_put(sap); + } else { + release_sock(sk); + } if (llc->dev) dev_put(llc->dev); sock_put(sk); @@ -920,6 +930,9 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (size > llc->dev->mtu) size = llc->dev->mtu; copied = size - hdrlen; + rc = -EINVAL; + if (copied < 0) + goto release; release_sock(sk); skb = sock_alloc_send_skb(sk, size, noblock, &rc); lock_sock(sk); diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 163121192aca..4d78375f9872 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -1099,14 +1099,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb) int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb) { - struct llc_sock *llc = llc_sk(sk); - - del_timer(&llc->pf_cycle_timer.timer); - del_timer(&llc->ack_timer.timer); - del_timer(&llc->rej_sent_timer.timer); - del_timer(&llc->busy_state_timer.timer); - llc->ack_must_be_send = 0; - llc->ack_pf = 0; + llc_sk_stop_all_timers(sk, false); return 0; } diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 110e32bcb399..c0ac522b48a1 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -961,6 +961,26 @@ out: return sk; } +void llc_sk_stop_all_timers(struct sock *sk, bool sync) +{ + struct llc_sock *llc = llc_sk(sk); + + if (sync) { + del_timer_sync(&llc->pf_cycle_timer.timer); + del_timer_sync(&llc->ack_timer.timer); + del_timer_sync(&llc->rej_sent_timer.timer); + del_timer_sync(&llc->busy_state_timer.timer); + } else { + del_timer(&llc->pf_cycle_timer.timer); + del_timer(&llc->ack_timer.timer); + del_timer(&llc->rej_sent_timer.timer); + del_timer(&llc->busy_state_timer.timer); + } + + llc->ack_must_be_send = 0; + llc->ack_pf = 0; +} + /** * llc_sk_free - Frees a LLC socket * @sk - socket to free @@ -973,7 +993,7 @@ void llc_sk_free(struct sock *sk) llc->state = LLC_CONN_OUT_OF_SVC; /* Stop all (possibly) running timers */ - llc_conn_ac_stop_all_timers(sk, NULL); + llc_sk_stop_all_timers(sk, true); #ifdef DEBUG_LLC_CONN_ALLOC printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__, skb_queue_len(&llc->pdu_unack_q), diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 595c662a61e8..ac4295296514 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -8,6 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -970,6 +971,9 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, sta->ampdu_mlme.addba_req_num[tid] = 0; + tid_tx->timeout = + le16_to_cpu(mgmt->u.action.u.addba_resp.timeout); + if (tid_tx->timeout) { mod_timer(&tid_tx->session_timer, TU_TO_EXP_TIME(tid_tx->timeout)); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 0f6c9ca59062..5b5b0f95ffd1 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -401,7 +401,7 @@ u32 mesh_plink_deactivate(struct sta_info *sta) static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, - struct ieee802_11_elems *elems, bool insert) + struct ieee802_11_elems *elems) { struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; @@ -447,7 +447,7 @@ static void mesh_sta_info_init(struct ieee80211_sub_if_data *sdata, sta->sta.bandwidth = IEEE80211_STA_RX_BW_20; } - if (insert) + if (!test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) rate_control_rate_init(sta); else rate_control_rate_update(local, sband, sta, changed); @@ -551,7 +551,7 @@ mesh_sta_info_get(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); sta = sta_info_get(sdata, addr); if (sta) { - mesh_sta_info_init(sdata, sta, elems, false); + mesh_sta_info_init(sdata, sta, elems); } else { rcu_read_unlock(); /* can't run atomic */ @@ -561,7 +561,7 @@ mesh_sta_info_get(struct ieee80211_sub_if_data *sdata, return NULL; } - mesh_sta_info_init(sdata, sta, elems, true); + mesh_sta_info_init(sdata, sta, elems); if (sta_info_insert_rcu(sta)) return NULL; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 69449db7e283..233068756502 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -36,6 +36,7 @@ #define IEEE80211_AUTH_TIMEOUT (HZ / 5) #define IEEE80211_AUTH_TIMEOUT_LONG (HZ / 2) #define IEEE80211_AUTH_TIMEOUT_SHORT (HZ / 10) +#define IEEE80211_AUTH_TIMEOUT_SAE (HZ * 2) #define IEEE80211_AUTH_MAX_TRIES 3 #define IEEE80211_AUTH_WAIT_ASSOC (HZ * 5) #define IEEE80211_ASSOC_TIMEOUT (HZ / 5) @@ -1787,7 +1788,7 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, params[ac].acm = acm; params[ac].uapsd = uapsd; - if (params->cw_min == 0 || + if (params[ac].cw_min == 0 || params[ac].cw_min > params[ac].cw_max) { sdata_info(sdata, "AP has invalid WMM params (CWmin/max=%d/%d for ACI %d), using defaults\n", @@ -3814,16 +3815,19 @@ static int ieee80211_auth(struct ieee80211_sub_if_data *sdata) tx_flags); if (tx_flags == 0) { - auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; - auth_data->timeout_started = true; - run_again(sdata, auth_data->timeout); + if (auth_data->algorithm == WLAN_AUTH_SAE) + auth_data->timeout = jiffies + + IEEE80211_AUTH_TIMEOUT_SAE; + else + auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; } else { auth_data->timeout = round_jiffies_up(jiffies + IEEE80211_AUTH_TIMEOUT_LONG); - auth_data->timeout_started = true; - run_again(sdata, auth_data->timeout); } + auth_data->timeout_started = true; + run_again(sdata, auth_data->timeout); + return 0; } @@ -3894,8 +3898,15 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) ifmgd->status_received = false; if (ifmgd->auth_data && ieee80211_is_auth(fc)) { if (status_acked) { - ifmgd->auth_data->timeout = - jiffies + IEEE80211_AUTH_TIMEOUT_SHORT; + if (ifmgd->auth_data->algorithm == + WLAN_AUTH_SAE) + ifmgd->auth_data->timeout = + jiffies + + IEEE80211_AUTH_TIMEOUT_SAE; + else + ifmgd->auth_data->timeout = + jiffies + + IEEE80211_AUTH_TIMEOUT_SHORT; run_again(sdata, ifmgd->auth_data->timeout); } else { ifmgd->auth_data->timeout = jiffies - 1; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 535de3161a78..05a265cd573d 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4,6 +4,7 @@ * 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 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1135,7 +1136,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, } /* reset session timer */ - if (reset_agg_timer && tid_tx->timeout) + if (reset_agg_timer) tid_tx->last_tx = jiffies; return queued; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 704b3832dbad..44d8a55e9721 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -594,6 +594,7 @@ config NFT_QUOTA config NFT_REJECT default m if NETFILTER_ADVANCED=n tristate "Netfilter nf_tables reject support" + depends on !NF_TABLES_INET || (IPV6!=m || m) help This option adds the "reject" expression that you can use to explicitly deny and notify via TCP reset/ICMP informational errors diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 0f6b8172fb9a..206fb2c4c319 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -585,7 +585,8 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); EXPORT_SYMBOL(nf_nat_decode_session_hook); #endif -static void __net_init __netfilter_net_init(struct nf_hook_entries **e, int max) +static void __net_init +__netfilter_net_init(struct nf_hook_entries __rcu **e, int max) { int h; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 370abbf6f421..75de46576f51 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -232,7 +232,10 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) { unsigned int hash; - bool ret; + bool ret = false; + + if (cp->flags & IP_VS_CONN_F_ONE_PACKET) + return refcount_dec_if_one(&cp->refcnt); hash = ip_vs_conn_hashkey_conn(cp); @@ -240,15 +243,13 @@ static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) spin_lock(&cp->lock); if (cp->flags & IP_VS_CONN_F_HASHED) { - ret = false; /* Decrease refcnt and unlink conn only if we are last user */ if (refcount_dec_if_one(&cp->refcnt)) { hlist_del_rcu(&cp->c_list); cp->flags &= ~IP_VS_CONN_F_HASHED; ret = true; } - } else - ret = refcount_read(&cp->refcnt) ? false : true; + } spin_unlock(&cp->lock); ct_write_unlock_bh(hash); @@ -454,12 +455,6 @@ ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af, } EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto); -static void __ip_vs_conn_put_notimer(struct ip_vs_conn *cp) -{ - __ip_vs_conn_put(cp); - ip_vs_conn_expire(&cp->timer); -} - /* * Put back the conn and restart its timer with its timeout */ @@ -478,7 +473,7 @@ void ip_vs_conn_put(struct ip_vs_conn *cp) (refcount_read(&cp->refcnt) == 1) && !timer_pending(&cp->timer)) /* expire connection immediately */ - __ip_vs_conn_put_notimer(cp); + ip_vs_conn_expire(&cp->timer); else __ip_vs_conn_put_timer(cp); } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 5f6f73cf2174..0679dd101e72 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -119,6 +119,8 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; + local_bh_disable(); + s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; @@ -137,6 +139,8 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->cnt.inpkts++; s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); + + local_bh_enable(); } } @@ -151,6 +155,8 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; + local_bh_disable(); + s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; @@ -169,6 +175,8 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->cnt.outpkts++; s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); + + local_bh_enable(); } } @@ -179,6 +187,8 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_cpu_stats *s; + local_bh_disable(); + s = this_cpu_ptr(cp->dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; @@ -193,6 +203,8 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); + + local_bh_enable(); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5ebde4b15810..f36098887ad0 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2384,11 +2384,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) strlcpy(cfg.mcast_ifn, dm->mcast_ifn, sizeof(cfg.mcast_ifn)); cfg.syncid = dm->syncid; - rtnl_lock(); - mutex_lock(&ipvs->sync_mutex); ret = start_sync_thread(ipvs, &cfg, dm->state); - mutex_unlock(&ipvs->sync_mutex); - rtnl_unlock(); } else { mutex_lock(&ipvs->sync_mutex); ret = stop_sync_thread(ipvs, dm->state); @@ -3481,12 +3477,8 @@ static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs) if (ipvs->mixed_address_family_dests > 0) return -EINVAL; - rtnl_lock(); - mutex_lock(&ipvs->sync_mutex); ret = start_sync_thread(ipvs, &c, nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); - mutex_unlock(&ipvs->sync_mutex); - rtnl_unlock(); return ret; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index fbaf3bd05b2e..001501e25625 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -49,6 +49,7 @@ #include <linux/kthread.h> #include <linux/wait.h> #include <linux/kernel.h> +#include <linux/sched/signal.h> #include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */ @@ -1360,15 +1361,9 @@ static void set_mcast_pmtudisc(struct sock *sk, int val) /* * Specifiy default interface for outgoing multicasts */ -static int set_mcast_if(struct sock *sk, char *ifname) +static int set_mcast_if(struct sock *sk, struct net_device *dev) { - struct net_device *dev; struct inet_sock *inet = inet_sk(sk); - struct net *net = sock_net(sk); - - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -1396,19 +1391,14 @@ static int set_mcast_if(struct sock *sk, char *ifname) * in the in_addr structure passed in as a parameter. */ static int -join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) +join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev) { - struct net *net = sock_net(sk); struct ip_mreqn mreq; - struct net_device *dev; int ret; memset(&mreq, 0, sizeof(mreq)); memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr)); - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -1423,15 +1413,10 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) #ifdef CONFIG_IP_VS_IPV6 static int join_mcast_group6(struct sock *sk, struct in6_addr *addr, - char *ifname) + struct net_device *dev) { - struct net *net = sock_net(sk); - struct net_device *dev; int ret; - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -1443,24 +1428,18 @@ static int join_mcast_group6(struct sock *sk, struct in6_addr *addr, } #endif -static int bind_mcastif_addr(struct socket *sock, char *ifname) +static int bind_mcastif_addr(struct socket *sock, struct net_device *dev) { - struct net *net = sock_net(sock->sk); - struct net_device *dev; __be32 addr; struct sockaddr_in sin; - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; - addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); if (!addr) pr_err("You probably need to specify IP address on " "multicast interface.\n"); IP_VS_DBG(7, "binding socket with (%s) %pI4\n", - ifname, &addr); + dev->name, &addr); /* Now bind the socket with the address of multicast interface */ sin.sin_family = AF_INET; @@ -1493,7 +1472,8 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, /* * Set up sending multicast socket over UDP */ -static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) +static int make_send_sock(struct netns_ipvs *ipvs, int id, + struct net_device *dev, struct socket **sock_ret) { /* multicast addr */ union ipvs_sockaddr mcast_addr; @@ -1505,9 +1485,10 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); - return ERR_PTR(result); + goto error; } - result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn); + *sock_ret = sock; + result = set_mcast_if(sock->sk, dev); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); goto error; @@ -1522,7 +1503,7 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) set_sock_size(sock->sk, 1, result); if (AF_INET == ipvs->mcfg.mcast_af) - result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn); + result = bind_mcastif_addr(sock, dev); else result = 0; if (result < 0) { @@ -1538,19 +1519,18 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) goto error; } - return sock; + return 0; error: - sock_release(sock); - return ERR_PTR(result); + return result; } /* * Set up receiving multicast socket over UDP */ -static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, - int ifindex) +static int make_receive_sock(struct netns_ipvs *ipvs, int id, + struct net_device *dev, struct socket **sock_ret) { /* multicast addr */ union ipvs_sockaddr mcast_addr; @@ -1562,8 +1542,9 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); - return ERR_PTR(result); + goto error; } + *sock_ret = sock; /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = SK_CAN_REUSE; result = sysctl_sync_sock_size(ipvs); @@ -1571,7 +1552,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, set_sock_size(sock->sk, 0, result); get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); - sock->sk->sk_bound_dev_if = ifindex; + sock->sk->sk_bound_dev_if = dev->ifindex; result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); @@ -1582,21 +1563,20 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, #ifdef CONFIG_IP_VS_IPV6 if (ipvs->bcfg.mcast_af == AF_INET6) result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr, - ipvs->bcfg.mcast_ifn); + dev); else #endif result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr, - ipvs->bcfg.mcast_ifn); + dev); if (result < 0) { pr_err("Error joining to the multicast group\n"); goto error; } - return sock; + return 0; error: - sock_release(sock); - return ERR_PTR(result); + return result; } @@ -1778,13 +1758,12 @@ static int sync_thread_backup(void *data) int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, int state) { - struct ip_vs_sync_thread_data *tinfo; + struct ip_vs_sync_thread_data *tinfo = NULL; struct task_struct **array = NULL, *task; - struct socket *sock; struct net_device *dev; char *name; int (*threadfn)(void *data); - int id, count, hlen; + int id = 0, count, hlen; int result = -ENOMEM; u16 mtu, min_mtu; @@ -1792,6 +1771,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); + /* Do not hold one mutex and then to block on another */ + for (;;) { + rtnl_lock(); + if (mutex_trylock(&ipvs->sync_mutex)) + break; + rtnl_unlock(); + mutex_lock(&ipvs->sync_mutex); + if (rtnl_trylock()) + break; + mutex_unlock(&ipvs->sync_mutex); + } + if (!ipvs->sync_state) { count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX); ipvs->threads_mask = count - 1; @@ -1810,7 +1801,8 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, dev = __dev_get_by_name(ipvs->net, c->mcast_ifn); if (!dev) { pr_err("Unknown mcast interface: %s\n", c->mcast_ifn); - return -ENODEV; + result = -ENODEV; + goto out_early; } hlen = (AF_INET6 == c->mcast_af) ? sizeof(struct ipv6hdr) + sizeof(struct udphdr) : @@ -1827,26 +1819,30 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, c->sync_maxlen = mtu - hlen; if (state == IP_VS_STATE_MASTER) { + result = -EEXIST; if (ipvs->ms) - return -EEXIST; + goto out_early; ipvs->mcfg = *c; name = "ipvs-m:%d:%d"; threadfn = sync_thread_master; } else if (state == IP_VS_STATE_BACKUP) { + result = -EEXIST; if (ipvs->backup_threads) - return -EEXIST; + goto out_early; ipvs->bcfg = *c; name = "ipvs-b:%d:%d"; threadfn = sync_thread_backup; } else { - return -EINVAL; + result = -EINVAL; + goto out_early; } if (state == IP_VS_STATE_MASTER) { struct ipvs_master_sync_state *ms; + result = -ENOMEM; ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL); if (!ipvs->ms) goto out; @@ -1862,39 +1858,38 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, } else { array = kcalloc(count, sizeof(struct task_struct *), GFP_KERNEL); + result = -ENOMEM; if (!array) goto out; } - tinfo = NULL; for (id = 0; id < count; id++) { - if (state == IP_VS_STATE_MASTER) - sock = make_send_sock(ipvs, id); - else - sock = make_receive_sock(ipvs, id, dev->ifindex); - if (IS_ERR(sock)) { - result = PTR_ERR(sock); - goto outtinfo; - } + result = -ENOMEM; tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL); if (!tinfo) - goto outsocket; + goto out; tinfo->ipvs = ipvs; - tinfo->sock = sock; + tinfo->sock = NULL; if (state == IP_VS_STATE_BACKUP) { tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen, GFP_KERNEL); if (!tinfo->buf) - goto outtinfo; + goto out; } else { tinfo->buf = NULL; } tinfo->id = id; + if (state == IP_VS_STATE_MASTER) + result = make_send_sock(ipvs, id, dev, &tinfo->sock); + else + result = make_receive_sock(ipvs, id, dev, &tinfo->sock); + if (result < 0) + goto out; task = kthread_run(threadfn, tinfo, name, ipvs->gen, id); if (IS_ERR(task)) { result = PTR_ERR(task); - goto outtinfo; + goto out; } tinfo = NULL; if (state == IP_VS_STATE_MASTER) @@ -1911,20 +1906,20 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, ipvs->sync_state |= state; spin_unlock_bh(&ipvs->sync_buff_lock); + mutex_unlock(&ipvs->sync_mutex); + rtnl_unlock(); + /* increase the module use count */ ip_vs_use_count_inc(); return 0; -outsocket: - sock_release(sock); - -outtinfo: - if (tinfo) { - sock_release(tinfo->sock); - kfree(tinfo->buf); - kfree(tinfo); - } +out: + /* We do not need RTNL lock anymore, release it here so that + * sock_release below and in the kthreads can use rtnl_lock + * to leave the mcast group. + */ + rtnl_unlock(); count = id; while (count-- > 0) { if (state == IP_VS_STATE_MASTER) @@ -1932,13 +1927,23 @@ outtinfo: else kthread_stop(array[count]); } - kfree(array); - -out: if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { kfree(ipvs->ms); ipvs->ms = NULL; } + mutex_unlock(&ipvs->sync_mutex); + if (tinfo) { + if (tinfo->sock) + sock_release(tinfo->sock); + kfree(tinfo->buf); + kfree(tinfo); + } + kfree(array); + return result; + +out_early: + mutex_unlock(&ipvs->sync_mutex); + rtnl_unlock(); return result; } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 8ef21d9f9a00..4b2b3d53acfc 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -252,7 +252,7 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, static inline int expect_matches(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b) { - return a->master == b->master && a->class == b->class && + return a->master == b->master && nf_ct_tuple_equal(&a->tuple, &b->tuple) && nf_ct_tuple_mask_equal(&a->mask, &b->mask) && net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) && @@ -421,6 +421,9 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { if (expect_matches(i, expect)) { + if (i->class != expect->class) + return -EALREADY; + if (nf_ct_remove_expect(i)) break; } else if (expect_clash(i, expect)) { diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 9fe0ddc333fb..277bbfe26478 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -9,6 +9,7 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> +#include <linux/kmemleak.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/rcupdate.h> @@ -71,6 +72,7 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) rcu_read_unlock(); alloc = max(newlen, NF_CT_EXT_PREALLOC); + kmemleak_not_leak(old); new = __krealloc(old, alloc, gfp); if (!new) return NULL; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index e97cdc1cf98c..8e67910185a0 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -981,6 +981,17 @@ static int tcp_packet(struct nf_conn *ct, return NF_ACCEPT; /* Don't change state */ } break; + case TCP_CONNTRACK_SYN_SENT2: + /* tcp_conntracks table is not smart enough to handle + * simultaneous open. + */ + ct->proto.tcp.last_flags |= IP_CT_TCP_SIMULTANEOUS_OPEN; + break; + case TCP_CONNTRACK_SYN_RECV: + if (dir == IP_CT_DIR_REPLY && index == TCP_ACK_SET && + ct->proto.tcp.last_flags & IP_CT_TCP_SIMULTANEOUS_OPEN) + new_state = TCP_CONNTRACK_ESTABLISHED; + break; case TCP_CONNTRACK_CLOSE: if (index == TCP_RST_SET && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 4dbb5bad4363..908e51e2dc2b 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -938,11 +938,19 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, datalen, rtp_exp, rtcp_exp, mediaoff, medialen, daddr); else { - if (nf_ct_expect_related(rtp_exp) == 0) { - if (nf_ct_expect_related(rtcp_exp) != 0) - nf_ct_unexpect_related(rtp_exp); - else + /* -EALREADY handling works around end-points that send + * SDP messages with identical port but different media type, + * we pretend expectation was set up. + */ + int errp = nf_ct_expect_related(rtp_exp); + + if (errp == 0 || errp == -EALREADY) { + int errcp = nf_ct_expect_related(rtcp_exp); + + if (errcp == 0 || errcp == -EALREADY) ret = NF_ACCEPT; + else if (errp == 0) + nf_ct_unexpect_related(rtp_exp); } } nf_ct_expect_put(rtcp_exp); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9134cc429ad4..91e80aa852d6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -214,6 +214,34 @@ static int nft_delchain(struct nft_ctx *ctx) return err; } +static void nft_rule_expr_activate(const struct nft_ctx *ctx, + struct nft_rule *rule) +{ + struct nft_expr *expr; + + expr = nft_expr_first(rule); + while (expr != nft_expr_last(rule) && expr->ops) { + if (expr->ops->activate) + expr->ops->activate(ctx, expr); + + expr = nft_expr_next(expr); + } +} + +static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, + struct nft_rule *rule) +{ + struct nft_expr *expr; + + expr = nft_expr_first(rule); + while (expr != nft_expr_last(rule) && expr->ops) { + if (expr->ops->deactivate) + expr->ops->deactivate(ctx, expr); + + expr = nft_expr_next(expr); + } +} + static int nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule) { @@ -259,6 +287,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule) nft_trans_destroy(trans); return err; } + nft_rule_expr_deactivate(ctx, rule); return 0; } @@ -2238,6 +2267,13 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, kfree(rule); } +static void nf_tables_rule_release(const struct nft_ctx *ctx, + struct nft_rule *rule) +{ + nft_rule_expr_deactivate(ctx, rule); + nf_tables_rule_destroy(ctx, rule); +} + #define NFT_RULE_MAXEXPRS 128 static struct nft_expr_info *info; @@ -2361,43 +2397,48 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } if (nlh->nlmsg_flags & NLM_F_REPLACE) { - if (nft_is_active_next(net, old_rule)) { - trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, - old_rule); - if (trans == NULL) { - err = -ENOMEM; - goto err2; - } - nft_deactivate_next(net, old_rule); - chain->use--; - list_add_tail_rcu(&rule->list, &old_rule->list); - } else { + if (!nft_is_active_next(net, old_rule)) { err = -ENOENT; goto err2; } - } else if (nlh->nlmsg_flags & NLM_F_APPEND) - if (old_rule) - list_add_rcu(&rule->list, &old_rule->list); - else - list_add_tail_rcu(&rule->list, &chain->rules); - else { - if (old_rule) - list_add_tail_rcu(&rule->list, &old_rule->list); - else - list_add_rcu(&rule->list, &chain->rules); - } + trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, + old_rule); + if (trans == NULL) { + err = -ENOMEM; + goto err2; + } + nft_deactivate_next(net, old_rule); + chain->use--; - if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { - err = -ENOMEM; - goto err3; + if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { + err = -ENOMEM; + goto err2; + } + + list_add_tail_rcu(&rule->list, &old_rule->list); + } else { + if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { + err = -ENOMEM; + goto err2; + } + + if (nlh->nlmsg_flags & NLM_F_APPEND) { + if (old_rule) + list_add_rcu(&rule->list, &old_rule->list); + else + list_add_tail_rcu(&rule->list, &chain->rules); + } else { + if (old_rule) + list_add_tail_rcu(&rule->list, &old_rule->list); + else + list_add_rcu(&rule->list, &chain->rules); + } } chain->use++; return 0; -err3: - list_del_rcu(&rule->list); err2: - nf_tables_rule_destroy(&ctx, rule); + nf_tables_rule_release(&ctx, rule); err1: for (i = 0; i < n; i++) { if (info[i].ops != NULL) @@ -3207,18 +3248,20 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err = ops->init(set, &desc, nla); if (err < 0) - goto err2; + goto err3; err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err3; + goto err4; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; -err3: +err4: ops->destroy(set); +err3: + kfree(set->name); err2: kvfree(set); err1: @@ -4037,8 +4080,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^ nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) || nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^ - nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) - return -EBUSY; + nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF)) { + err = -EBUSY; + goto err5; + } if ((nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) && memcmp(nft_set_ext_data(ext), @@ -4123,7 +4168,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, * NFT_GOTO verdicts. This function must be called on active data objects * from the second phase of the commit protocol. */ -static void nft_data_hold(const struct nft_data *data, enum nft_data_types type) +void nft_data_hold(const struct nft_data *data, enum nft_data_types type) { if (type == NFT_DATA_VERDICT) { switch (data->verdict.code) { @@ -5738,7 +5783,7 @@ static void nft_chain_commit_update(struct nft_trans *trans) struct nft_base_chain *basechain; if (nft_trans_chain_name(trans)) - strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans)); + swap(trans->ctx.chain->name, nft_trans_chain_name(trans)); if (!nft_is_base_chain(trans->ctx.chain)) return; @@ -5754,7 +5799,7 @@ static void nft_chain_commit_update(struct nft_trans *trans) } } -static void nf_tables_commit_release(struct nft_trans *trans) +static void nft_commit_release(struct nft_trans *trans) { switch (trans->msg_type) { case NFT_MSG_DELTABLE: @@ -5783,6 +5828,21 @@ static void nf_tables_commit_release(struct nft_trans *trans) kfree(trans); } +static void nf_tables_commit_release(struct net *net) +{ + struct nft_trans *trans, *next; + + if (list_empty(&net->nft.commit_list)) + return; + + synchronize_rcu(); + + list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_del(&trans->list); + nft_commit_release(trans); + } +} + static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nft_trans *trans, *next; @@ -5913,13 +5973,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } } - synchronize_rcu(); - - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { - list_del(&trans->list); - nf_tables_commit_release(trans); - } - + nf_tables_commit_release(net); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); return 0; @@ -5999,10 +6053,12 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWRULE: trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); + nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; nft_clear(trans->ctx.net, nft_trans_rule(trans)); + nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: @@ -6578,7 +6634,7 @@ int __nft_release_basechain(struct nft_ctx *ctx) list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); ctx->chain->use--; - nf_tables_rule_destroy(ctx, rule); + nf_tables_rule_release(ctx, rule); } list_del(&ctx->chain->list); ctx->table->use--; @@ -6616,7 +6672,7 @@ static void __nft_release_tables(struct net *net) list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); chain->use--; - nf_tables_rule_destroy(&ctx, rule); + nf_tables_rule_release(&ctx, rule); } } list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index dfd0bf3810d2..942702a2776f 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -119,15 +119,22 @@ DEFINE_STATIC_KEY_FALSE(nft_counters_enabled); static noinline void nft_update_chain_stats(const struct nft_chain *chain, const struct nft_pktinfo *pkt) { + struct nft_base_chain *base_chain; struct nft_stats *stats; - local_bh_disable(); - stats = this_cpu_ptr(rcu_dereference(nft_base_chain(chain)->stats)); - u64_stats_update_begin(&stats->syncp); - stats->pkts++; - stats->bytes += pkt->skb->len; - u64_stats_update_end(&stats->syncp); - local_bh_enable(); + base_chain = nft_base_chain(chain); + if (!base_chain->stats) + return; + + stats = this_cpu_ptr(rcu_dereference(base_chain->stats)); + if (stats) { + local_bh_disable(); + u64_stats_update_begin(&stats->syncp); + stats->pkts++; + stats->bytes += pkt->skb->len; + u64_stats_update_end(&stats->syncp); + local_bh_enable(); + } } struct nft_jumpstack { diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index b9505bcd3827..6ddf89183e7b 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -115,7 +115,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl, nfacct->flags = flags; } - strncpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX); + nla_strlcpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX); if (tb[NFACCT_BYTES]) { atomic64_set(&nfacct->bytes, diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 4a4b293fb2e5..fa026b269b36 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -149,8 +149,8 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy, !tb[NFCTH_POLICY_EXPECT_TIMEOUT]) return -EINVAL; - strncpy(expect_policy->name, - nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN); + nla_strlcpy(expect_policy->name, + nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN); expect_policy->max_expected = ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX])); if (expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT) @@ -234,7 +234,8 @@ nfnl_cthelper_create(const struct nlattr * const tb[], if (ret < 0) goto err1; - strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN); + nla_strlcpy(helper->name, + nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN); size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); if (size > FIELD_SIZEOF(struct nf_conn_help, data)) { ret = -ENOMEM; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 8e23726b9081..1d99a1efdafc 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -27,14 +27,31 @@ struct nft_xt { struct list_head head; struct nft_expr_ops ops; unsigned int refcnt; + + /* Unlike other expressions, ops doesn't have static storage duration. + * nft core assumes they do. We use kfree_rcu so that nft core can + * can check expr->ops->size even after nft_compat->destroy() frees + * the nft_xt struct that holds the ops structure. + */ + struct rcu_head rcu_head; +}; + +/* Used for matches where *info is larger than X byte */ +#define NFT_MATCH_LARGE_THRESH 192 + +struct nft_xt_match_priv { + void *info; }; -static void nft_xt_put(struct nft_xt *xt) +static bool nft_xt_put(struct nft_xt *xt) { if (--xt->refcnt == 0) { list_del(&xt->head); - kfree(xt); + kfree_rcu(xt, rcu_head); + return true; } + + return false; } static int nft_compat_chain_validate_dependency(const char *tablename, @@ -226,6 +243,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct xt_target *target = expr->ops->data; struct xt_tgchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO])); + struct nft_xt *nft_xt; u16 proto = 0; bool inv = false; union nft_entry e = {}; @@ -236,25 +254,22 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (ctx->nla[NFTA_RULE_COMPAT]) { ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv); if (ret < 0) - goto err; + return ret; } nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv); ret = xt_check_target(&par, size, proto, inv); if (ret < 0) - goto err; + return ret; /* The standard target cannot be used */ - if (target->target == NULL) { - ret = -EINVAL; - goto err; - } + if (!target->target) + return -EINVAL; + nft_xt = container_of(expr->ops, struct nft_xt, ops); + nft_xt->refcnt++; return 0; -err: - module_put(target->me); - return ret; } static void @@ -271,8 +286,8 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) if (par.target->destroy != NULL) par.target->destroy(&par); - nft_xt_put(container_of(expr->ops, struct nft_xt, ops)); - module_put(target->me); + if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) + module_put(target->me); } static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr) @@ -316,11 +331,11 @@ static int nft_target_validate(const struct nft_ctx *ctx, return 0; } -static void nft_match_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static void __nft_match_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt, + void *info) { - void *info = nft_expr_priv(expr); struct xt_match *match = expr->ops->data; struct sk_buff *skb = pkt->skb; bool ret; @@ -344,6 +359,22 @@ static void nft_match_eval(const struct nft_expr *expr, } } +static void nft_match_large_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_xt_match_priv *priv = nft_expr_priv(expr); + + __nft_match_eval(expr, regs, pkt, priv->info); +} + +static void nft_match_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + __nft_match_eval(expr, regs, pkt, nft_expr_priv(expr)); +} + static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = { [NFTA_MATCH_NAME] = { .type = NLA_NUL_STRING }, [NFTA_MATCH_REV] = { .type = NLA_U32 }, @@ -404,13 +435,14 @@ static void match_compat_from_user(struct xt_match *m, void *in, void *out) } static int -nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nlattr * const tb[]) +__nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[], + void *info) { - void *info = nft_expr_priv(expr); struct xt_match *match = expr->ops->data; struct xt_mtchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO])); + struct nft_xt *nft_xt; u16 proto = 0; bool inv = false; union nft_entry e = {}; @@ -421,26 +453,50 @@ nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (ctx->nla[NFTA_RULE_COMPAT]) { ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv); if (ret < 0) - goto err; + return ret; } nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv); ret = xt_check_match(&par, size, proto, inv); if (ret < 0) - goto err; + return ret; + nft_xt = container_of(expr->ops, struct nft_xt, ops); + nft_xt->refcnt++; return 0; -err: - module_put(match->me); +} + +static int +nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + return __nft_match_init(ctx, expr, tb, nft_expr_priv(expr)); +} + +static int +nft_match_large_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_xt_match_priv *priv = nft_expr_priv(expr); + struct xt_match *m = expr->ops->data; + int ret; + + priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL); + if (!priv->info) + return -ENOMEM; + + ret = __nft_match_init(ctx, expr, tb, priv->info); + if (ret) + kfree(priv->info); return ret; } static void -nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) +__nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr, + void *info) { struct xt_match *match = expr->ops->data; - void *info = nft_expr_priv(expr); struct xt_mtdtor_param par; par.net = ctx->net; @@ -450,13 +506,28 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) if (par.match->destroy != NULL) par.match->destroy(&par); - nft_xt_put(container_of(expr->ops, struct nft_xt, ops)); - module_put(match->me); + if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) + module_put(match->me); } -static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr) +static void +nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) +{ + __nft_match_destroy(ctx, expr, nft_expr_priv(expr)); +} + +static void +nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) +{ + struct nft_xt_match_priv *priv = nft_expr_priv(expr); + + __nft_match_destroy(ctx, expr, priv->info); + kfree(priv->info); +} + +static int __nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr, + void *info) { - void *info = nft_expr_priv(expr); struct xt_match *match = expr->ops->data; if (nla_put_string(skb, NFTA_MATCH_NAME, match->name) || @@ -470,6 +541,18 @@ nla_put_failure: return -1; } +static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + return __nft_match_dump(skb, expr, nft_expr_priv(expr)); +} + +static int nft_match_large_dump(struct sk_buff *skb, const struct nft_expr *e) +{ + struct nft_xt_match_priv *priv = nft_expr_priv(e); + + return __nft_match_dump(skb, e, priv->info); +} + static int nft_match_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) @@ -637,6 +720,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, { struct nft_xt *nft_match; struct xt_match *match; + unsigned int matchsize; char *mt_name; u32 rev, family; int err; @@ -654,13 +738,8 @@ nft_match_select_ops(const struct nft_ctx *ctx, list_for_each_entry(nft_match, &nft_match_list, head) { struct xt_match *match = nft_match->ops.data; - if (nft_match_cmp(match, mt_name, rev, family)) { - if (!try_module_get(match->me)) - return ERR_PTR(-ENOENT); - - nft_match->refcnt++; + if (nft_match_cmp(match, mt_name, rev, family)) return &nft_match->ops; - } } match = xt_request_find_match(family, mt_name, rev); @@ -679,9 +758,8 @@ nft_match_select_ops(const struct nft_ctx *ctx, goto err; } - nft_match->refcnt = 1; + nft_match->refcnt = 0; nft_match->ops.type = &nft_match_type; - nft_match->ops.size = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize)); nft_match->ops.eval = nft_match_eval; nft_match->ops.init = nft_match_init; nft_match->ops.destroy = nft_match_destroy; @@ -689,6 +767,18 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.validate = nft_match_validate; nft_match->ops.data = match; + matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize)); + if (matchsize > NFT_MATCH_LARGE_THRESH) { + matchsize = NFT_EXPR_SIZE(sizeof(struct nft_xt_match_priv)); + + nft_match->ops.eval = nft_match_large_eval; + nft_match->ops.init = nft_match_large_init; + nft_match->ops.destroy = nft_match_large_destroy; + nft_match->ops.dump = nft_match_large_dump; + } + + nft_match->ops.size = matchsize; + list_add(&nft_match->head, &nft_match_list); return &nft_match->ops; @@ -739,13 +829,8 @@ nft_target_select_ops(const struct nft_ctx *ctx, list_for_each_entry(nft_target, &nft_target_list, head) { struct xt_target *target = nft_target->ops.data; - if (nft_target_cmp(target, tg_name, rev, family)) { - if (!try_module_get(target->me)) - return ERR_PTR(-ENOENT); - - nft_target->refcnt++; + if (nft_target_cmp(target, tg_name, rev, family)) return &nft_target->ops; - } } target = xt_request_find_target(family, tg_name, rev); @@ -764,7 +849,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, goto err; } - nft_target->refcnt = 1; + nft_target->refcnt = 0; nft_target->ops.type = &nft_target_type; nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); nft_target->ops.init = nft_target_init; @@ -823,6 +908,32 @@ err_match: static void __exit nft_compat_module_exit(void) { + struct nft_xt *xt, *next; + + /* list should be empty here, it can be non-empty only in case there + * was an error that caused nft_xt expr to not be initialized fully + * and noone else requested the same expression later. + * + * In this case, the lists contain 0-refcount entries that still + * hold module reference. + */ + list_for_each_entry_safe(xt, next, &nft_target_list, head) { + struct xt_target *target = xt->ops.data; + + if (WARN_ON_ONCE(xt->refcnt)) + continue; + module_put(target->me); + kfree(xt); + } + + list_for_each_entry_safe(xt, next, &nft_match_list, head) { + struct xt_match *match = xt->ops.data; + + if (WARN_ON_ONCE(xt->refcnt)) + continue; + module_put(match->me); + kfree(xt); + } nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 4717d7796927..aa87ff8beae8 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -69,8 +69,16 @@ err1: return err; } -static void nft_immediate_destroy(const struct nft_ctx *ctx, - const struct nft_expr *expr) +static void nft_immediate_activate(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + const struct nft_immediate_expr *priv = nft_expr_priv(expr); + + return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg)); +} + +static void nft_immediate_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); @@ -108,7 +116,8 @@ static const struct nft_expr_ops nft_imm_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)), .eval = nft_immediate_eval, .init = nft_immediate_init, - .destroy = nft_immediate_destroy, + .activate = nft_immediate_activate, + .deactivate = nft_immediate_deactivate, .dump = nft_immediate_dump, .validate = nft_immediate_validate, }; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 71325fef647d..cb7cb300c3bc 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -183,6 +183,9 @@ struct xt_match *xt_find_match(u8 af, const char *name, u8 revision) struct xt_match *m; int err = -ENOENT; + if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) + return ERR_PTR(-EINVAL); + mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { @@ -229,6 +232,9 @@ struct xt_target *xt_find_target(u8 af, const char *name, u8 revision) struct xt_target *t; int err = -ENOENT; + if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) + return ERR_PTR(-EINVAL); + mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 773da82190dc..94df000abb92 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -36,11 +36,10 @@ MODULE_ALIAS("ipt_connmark"); MODULE_ALIAS("ip6t_connmark"); static unsigned int -connmark_tg_shift(struct sk_buff *skb, - const struct xt_connmark_tginfo1 *info, - u8 shift_bits, u8 shift_dir) +connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) { enum ip_conntrack_info ctinfo; + u_int32_t new_targetmark; struct nf_conn *ct; u_int32_t newmark; @@ -51,34 +50,39 @@ connmark_tg_shift(struct sk_buff *skb, switch (info->mode) { case XT_CONNMARK_SET: newmark = (ct->mark & ~info->ctmask) ^ info->ctmark; - if (shift_dir == D_SHIFT_RIGHT) - newmark >>= shift_bits; + if (info->shift_dir == D_SHIFT_RIGHT) + newmark >>= info->shift_bits; else - newmark <<= shift_bits; + newmark <<= info->shift_bits; + if (ct->mark != newmark) { ct->mark = newmark; nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_SAVE: - newmark = (ct->mark & ~info->ctmask) ^ - (skb->mark & info->nfmask); - if (shift_dir == D_SHIFT_RIGHT) - newmark >>= shift_bits; + new_targetmark = (skb->mark & info->nfmask); + if (info->shift_dir == D_SHIFT_RIGHT) + new_targetmark >>= info->shift_bits; else - newmark <<= shift_bits; + new_targetmark <<= info->shift_bits; + + newmark = (ct->mark & ~info->ctmask) ^ + new_targetmark; if (ct->mark != newmark) { ct->mark = newmark; nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_RESTORE: - newmark = (skb->mark & ~info->nfmask) ^ - (ct->mark & info->ctmask); - if (shift_dir == D_SHIFT_RIGHT) - newmark >>= shift_bits; + new_targetmark = (ct->mark & info->ctmask); + if (info->shift_dir == D_SHIFT_RIGHT) + new_targetmark >>= info->shift_bits; else - newmark <<= shift_bits; + new_targetmark <<= info->shift_bits; + + newmark = (skb->mark & ~info->nfmask) ^ + new_targetmark; skb->mark = newmark; break; } @@ -89,8 +93,14 @@ static unsigned int connmark_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_connmark_tginfo1 *info = par->targinfo; - - return connmark_tg_shift(skb, info, 0, 0); + const struct xt_connmark_tginfo2 info2 = { + .ctmark = info->ctmark, + .ctmask = info->ctmask, + .nfmask = info->nfmask, + .mode = info->mode, + }; + + return connmark_tg_shift(skb, &info2); } static unsigned int @@ -98,8 +108,7 @@ connmark_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_connmark_tginfo2 *info = par->targinfo; - return connmark_tg_shift(skb, (const struct xt_connmark_tginfo1 *)info, - info->shift_bits, info->shift_dir); + return connmark_tg_shift(skb, info); } static int connmark_tg_check(const struct xt_tgchk_param *par) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 55342c4d5cec..2e2dd88fc79f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2606,13 +2606,13 @@ static int netlink_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, - "sk Eth Pid Groups " - "Rmem Wmem Dump Locks Drops Inode\n"); + "sk Eth Pid Groups " + "Rmem Wmem Dump Locks Drops Inode\n"); } else { struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); - seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %d %-8d %-8d %-8lu\n", + seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8d %-8lu\n", s, s->sk_protocol, nlk->portid, diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index d7da99a0b0b8..9696ef96b719 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -57,6 +57,8 @@ int nsh_pop(struct sk_buff *skb) return -ENOMEM; nh = (struct nshhdr *)(skb->data); length = nsh_hdr_len(nh); + if (length < NSH_BASE_HDR_LEN) + return -EINVAL; inner_proto = tun_p_to_eth_p(nh->np); if (!pskb_may_pull(skb, length)) return -ENOMEM; @@ -90,6 +92,8 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) goto out; nsh_len = nsh_hdr_len(nsh_hdr(skb)); + if (nsh_len < NSH_BASE_HDR_LEN) + goto out; if (unlikely(!pskb_may_pull(skb, nsh_len))) goto out; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7322aa1e382e..492ab0c36f7c 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1712,13 +1712,10 @@ static void nlattr_set(struct nlattr *attr, u8 val, /* The nlattr stream should already have been validated */ nla_for_each_nested(nla, attr, rem) { - if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) { - if (tbl[nla_type(nla)].next) - tbl = tbl[nla_type(nla)].next; - nlattr_set(nla, val, tbl); - } else { + if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) + nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl); + else memset(nla_data(nla), val, nla_len(nla)); - } if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE) *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 616cb9c18f88..acb7b86574cd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -329,11 +329,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) skb_set_queue_mapping(skb, queue_index); } -/* register_prot_hook must be invoked with the po->bind_lock held, +/* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ -static void register_prot_hook(struct sock *sk) +static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); @@ -348,8 +348,13 @@ static void register_prot_hook(struct sock *sk) } } -/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock - * held. If the sync parameter is true, we will temporarily drop +static void register_prot_hook(struct sock *sk) +{ + lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); + __register_prot_hook(sk); +} + +/* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the @@ -359,6 +364,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); + lockdep_assert_held_once(&po->bind_lock); + po->running = 0; if (po->fanout) @@ -2896,13 +2903,15 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (skb == NULL) goto out_unlock; - skb_set_network_header(skb, reserve); + skb_reset_network_header(skb); err = -EINVAL; if (sock->type == SOCK_DGRAM) { offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; + } else if (reserve) { + skb_reserve(skb, -reserve); } /* Returns -EFAULT on error */ @@ -3008,6 +3017,7 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); + lock_sock(sk); if (po->rx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); @@ -3017,6 +3027,7 @@ static int packet_release(struct socket *sock) memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); } + release_sock(sk); f = fanout_release(sk); @@ -3250,7 +3261,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, if (proto) { po->prot_hook.type = proto; - register_prot_hook(sk); + __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); @@ -3643,6 +3654,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv union tpacket_req_u req_u; int len; + lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: @@ -3653,12 +3665,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv len = sizeof(req_u.req3); break; } - if (optlen < len) - return -EINVAL; - if (copy_from_user(&req_u.req, optval, len)) - return -EFAULT; - return packet_set_ring(sk, &req_u, 0, - optname == PACKET_TX_RING); + if (optlen < len) { + ret = -EINVAL; + } else { + if (copy_from_user(&req_u.req, optval, len)) + ret = -EFAULT; + else + ret = packet_set_ring(sk, &req_u, 0, + optname == PACKET_TX_RING); + } + release_sock(sk); + return ret; } case PACKET_COPY_THRESH: { @@ -3724,12 +3741,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_loss = !!val; - return 0; + + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_loss = !!val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_AUXDATA: { @@ -3740,7 +3763,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + lock_sock(sk); po->auxdata = !!val; + release_sock(sk); return 0; } case PACKET_ORIGDEV: @@ -3752,7 +3777,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + lock_sock(sk); po->origdev = !!val; + release_sock(sk); return 0; } case PACKET_VNET_HDR: @@ -3761,15 +3788,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (sock->type != SOCK_RAW) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->has_vnet_hdr = !!val; - return 0; + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->has_vnet_hdr = !!val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_TIMESTAMP: { @@ -3807,11 +3839,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_tx_has_off = !!val; + + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_tx_has_off = !!val; + ret = 0; + } + release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: @@ -4208,8 +4246,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; - lock_sock(sk); - rb = tx_ring ? &po->tx_ring : &po->rx_ring; rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; @@ -4347,7 +4383,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: - release_sock(sk); return err; } diff --git a/net/packet/internal.h b/net/packet/internal.h index a1d2b2319ae9..3bb7c5fb3bff 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -112,10 +112,12 @@ struct packet_sock { int copy_thresh; spinlock_t bind_lock; struct mutex pg_vec_lock; - unsigned int running:1, /* prot_hook is attached*/ - auxdata:1, + unsigned int running; /* bind_lock must be held */ + unsigned int auxdata:1, /* writer must hold sock lock */ origdev:1, - has_vnet_hdr:1; + has_vnet_hdr:1, + tp_loss:1, + tp_tx_has_off:1; int pressure; int ifindex; /* bound device */ __be16 num; @@ -125,8 +127,6 @@ struct packet_sock { enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; - unsigned int tp_loss:1; - unsigned int tp_tx_has_off:1; unsigned int tp_tstamp; struct net_device __rcu *cached_dev; int (*xmit)(struct sk_buff *skb); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index b33e5aeb4c06..2aa07b547b16 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -1135,3 +1135,4 @@ module_exit(qrtr_proto_fini); MODULE_DESCRIPTION("Qualcomm IPC-router driver"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_NETPROTO(PF_QIPCRTR); diff --git a/net/rds/Kconfig b/net/rds/Kconfig index bffde4b46c5d..1a31502ee7db 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -8,7 +8,7 @@ config RDS config RDS_RDMA tristate "RDS over Infiniband" - depends on RDS && INFINIBAND && INFINIBAND_ADDR_TRANS + depends on RDS && INFINIBAND_ADDR_TRANS ---help--- Allow RDS to use Infiniband as a transport. This transport supports RDMA operations. diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index eea1d8611b20..13b38ad0fa4a 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -547,7 +547,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd, ic->i_send_cq, ic->i_recv_cq); - return ret; + goto out; sends_out: vfree(ic->i_sends); @@ -572,6 +572,7 @@ send_cq_out: ic->i_send_cq = NULL; rds_ibdev_out: rds_ib_remove_conn(rds_ibdev, conn); +out: rds_ib_dev_put(rds_ibdev); return ret; diff --git a/net/rds/recv.c b/net/rds/recv.c index de50e2126e40..dc67458b52f0 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -558,6 +558,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, struct rds_cmsg_rx_trace t; int i, j; + memset(&t, 0, sizeof(t)); inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock(); t.rx_traces = rs->rs_rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 41bd496531d4..00192a996be0 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -137,13 +137,18 @@ static int rfkill_gpio_probe(struct platform_device *pdev) ret = rfkill_register(rfkill->rfkill_dev); if (ret < 0) - return ret; + goto err_destroy; platform_set_drvdata(pdev, rfkill); dev_info(&pdev->dev, "%s device registered.\n", rfkill->name); return 0; + +err_destroy: + rfkill_destroy(rfkill->rfkill_dev); + + return ret; } static int rfkill_gpio_remove(struct platform_device *pdev) diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 9a2c8e7c000e..2b463047dd7b 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -313,7 +313,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, memset(&cp, 0, sizeof(cp)); cp.local = rx->local; cp.key = key; - cp.security_level = 0; + cp.security_level = rx->min_sec_level; cp.exclusive = false; cp.upgrade = upgrade; cp.service_id = srx->srx_service; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 90d7079e0aa9..19975d2ca9a2 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -476,6 +476,7 @@ enum rxrpc_call_flag { RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ + RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ }; /* diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index c717152070df..1350f1be8037 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -40,7 +40,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, } __attribute__((packed)) pkt; struct rxrpc_ackinfo ack_info; size_t len; - int ioc; + int ret, ioc; u32 serial, mtu, call_id, padding; _enter("%d", conn->debug_id); @@ -135,10 +135,13 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, break; } - kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); conn->params.peer->last_tx_at = ktime_get_real(); + if (ret < 0) + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_fail_call_final_resend); + _leave(""); - return; } /* @@ -236,6 +239,8 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_fail_conn_abort); _debug("sendmsg failed: %d", ret); return -EAGAIN; } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 0410d2277ca2..b5fd6381313d 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -971,7 +971,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, if (timo) { unsigned long now = jiffies, expect_rx_by; - expect_rx_by = jiffies + timo; + expect_rx_by = now + timo; WRITE_ONCE(call->expect_rx_by, expect_rx_by); rxrpc_reduce_call_timer(call, expect_rx_by, now, rxrpc_timer_set_for_normal); diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 93b5d910b4a1..8325f1b86840 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -71,7 +71,8 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, ret = kernel_sendmsg(local->socket, &msg, iov, 2, len); if (ret < 0) - _debug("sendmsg failed: %d", ret); + trace_rxrpc_tx_fail(local->debug_id, 0, ret, + rxrpc_tx_fail_version_reply); _leave(""); } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 8b54e9531d52..b493e6b62740 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -134,22 +134,49 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } } - /* we want to receive ICMP errors */ - opt = 1; - ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, - (char *) &opt, sizeof(opt)); - if (ret < 0) { - _debug("setsockopt failed"); - goto error; - } + switch (local->srx.transport.family) { + case AF_INET: + /* we want to receive ICMP errors */ + opt = 1; + ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } - /* we want to set the don't fragment bit */ - opt = IP_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, - (char *) &opt, sizeof(opt)); - if (ret < 0) { - _debug("setsockopt failed"); - goto error; + /* we want to set the don't fragment bit */ + opt = IP_PMTUDISC_DO; + ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } + break; + + case AF_INET6: + /* we want to receive ICMP errors */ + opt = 1; + ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } + + /* we want to set the don't fragment bit */ + opt = IPV6_PMTUDISC_DO; + ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } + break; + + default: + BUG(); } /* set the socket up */ diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 7f1fc04775b3..f03de1c59ba3 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -210,6 +210,9 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (ping) call->ping_time = now; conn->params.peer->last_tx_at = ktime_get_real(); + if (ret < 0) + trace_rxrpc_tx_fail(call->debug_id, serial, ret, + rxrpc_tx_fail_call_ack); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { @@ -294,6 +297,10 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1, sizeof(pkt)); conn->params.peer->last_tx_at = ktime_get_real(); + if (ret < 0) + trace_rxrpc_tx_fail(call->debug_id, serial, ret, + rxrpc_tx_fail_call_abort); + rxrpc_put_connection(conn); return ret; @@ -387,6 +394,9 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, conn->params.peer->last_tx_at = ktime_get_real(); up_read(&conn->params.local->defrag_sem); + if (ret < 0) + trace_rxrpc_tx_fail(call->debug_id, serial, ret, + rxrpc_tx_fail_call_data_nofrag); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -414,6 +424,17 @@ done: rxrpc_timer_set_for_lost_ack); } } + + if (sp->hdr.seq == 1 && + !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, + &call->flags)) { + unsigned long nowj = jiffies, expect_rx_by; + + expect_rx_by = nowj + call->next_rx_timo; + WRITE_ONCE(call->expect_rx_by, expect_rx_by); + rxrpc_reduce_call_timer(call, expect_rx_by, nowj, + rxrpc_timer_set_for_normal); + } } rxrpc_set_keepalive(call); @@ -465,6 +486,10 @@ send_fragmentable: #endif } + if (ret < 0) + trace_rxrpc_tx_fail(call->debug_id, serial, ret, + rxrpc_tx_fail_call_data_frag); + up_write(&conn->params.local->defrag_sem); goto done; } @@ -482,6 +507,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) struct kvec iov[2]; size_t size; __be32 code; + int ret; _enter("%d", local->debug_id); @@ -516,7 +542,10 @@ void rxrpc_reject_packets(struct rxrpc_local *local) whdr.flags ^= RXRPC_CLIENT_INITIATED; whdr.flags &= RXRPC_CLIENT_INITIATED; - kernel_sendmsg(local->socket, &msg, iov, 2, size); + ret = kernel_sendmsg(local->socket, &msg, iov, 2, size); + if (ret < 0) + trace_rxrpc_tx_fail(local->debug_id, 0, ret, + rxrpc_tx_fail_reject); } rxrpc_free_skb(skb, rxrpc_skb_rx_freed); @@ -567,7 +596,8 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len); if (ret < 0) - _debug("sendmsg failed: %d", ret); + trace_rxrpc_tx_fail(peer->debug_id, 0, ret, + rxrpc_tx_fail_version_keepalive); peer->last_tx_at = ktime_get_real(); _leave(""); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 78c2f95d1f22..0ed8b651cec2 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -28,39 +28,39 @@ static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *); * Find the peer associated with an ICMP packet. */ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, - const struct sk_buff *skb) + const struct sk_buff *skb, + struct sockaddr_rxrpc *srx) { struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); - struct sockaddr_rxrpc srx; _enter(""); - memset(&srx, 0, sizeof(srx)); - srx.transport_type = local->srx.transport_type; - srx.transport_len = local->srx.transport_len; - srx.transport.family = local->srx.transport.family; + memset(srx, 0, sizeof(*srx)); + srx->transport_type = local->srx.transport_type; + srx->transport_len = local->srx.transport_len; + srx->transport.family = local->srx.transport.family; /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice * versa? */ - switch (srx.transport.family) { + switch (srx->transport.family) { case AF_INET: - srx.transport.sin.sin_port = serr->port; + srx->transport.sin.sin_port = serr->port; switch (serr->ee.ee_origin) { case SO_EE_ORIGIN_ICMP: _net("Rx ICMP"); - memcpy(&srx.transport.sin.sin_addr, + memcpy(&srx->transport.sin.sin_addr, skb_network_header(skb) + serr->addr_offset, sizeof(struct in_addr)); break; case SO_EE_ORIGIN_ICMP6: _net("Rx ICMP6 on v4 sock"); - memcpy(&srx.transport.sin.sin_addr, + memcpy(&srx->transport.sin.sin_addr, skb_network_header(skb) + serr->addr_offset + 12, sizeof(struct in_addr)); break; default: - memcpy(&srx.transport.sin.sin_addr, &ip_hdr(skb)->saddr, + memcpy(&srx->transport.sin.sin_addr, &ip_hdr(skb)->saddr, sizeof(struct in_addr)); break; } @@ -68,25 +68,25 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: - srx.transport.sin6.sin6_port = serr->port; + srx->transport.sin6.sin6_port = serr->port; switch (serr->ee.ee_origin) { case SO_EE_ORIGIN_ICMP6: _net("Rx ICMP6"); - memcpy(&srx.transport.sin6.sin6_addr, + memcpy(&srx->transport.sin6.sin6_addr, skb_network_header(skb) + serr->addr_offset, sizeof(struct in6_addr)); break; case SO_EE_ORIGIN_ICMP: _net("Rx ICMP on v6 sock"); - srx.transport.sin6.sin6_addr.s6_addr32[0] = 0; - srx.transport.sin6.sin6_addr.s6_addr32[1] = 0; - srx.transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff); - memcpy(srx.transport.sin6.sin6_addr.s6_addr + 12, + srx->transport.sin6.sin6_addr.s6_addr32[0] = 0; + srx->transport.sin6.sin6_addr.s6_addr32[1] = 0; + srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff); + memcpy(srx->transport.sin6.sin6_addr.s6_addr + 12, skb_network_header(skb) + serr->addr_offset, sizeof(struct in_addr)); break; default: - memcpy(&srx.transport.sin6.sin6_addr, + memcpy(&srx->transport.sin6.sin6_addr, &ipv6_hdr(skb)->saddr, sizeof(struct in6_addr)); break; @@ -98,7 +98,7 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, BUG(); } - return rxrpc_lookup_peer_rcu(local, &srx); + return rxrpc_lookup_peer_rcu(local, srx); } /* @@ -146,6 +146,7 @@ static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *se void rxrpc_error_report(struct sock *sk) { struct sock_exterr_skb *serr; + struct sockaddr_rxrpc srx; struct rxrpc_local *local = sk->sk_user_data; struct rxrpc_peer *peer; struct sk_buff *skb; @@ -166,7 +167,7 @@ void rxrpc_error_report(struct sock *sk) } rcu_read_lock(); - peer = rxrpc_lookup_peer_icmp_rcu(local, skb); + peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx); if (peer && !rxrpc_get_peer_maybe(peer)) peer = NULL; if (!peer) { @@ -176,6 +177,8 @@ void rxrpc_error_report(struct sock *sk) return; } + trace_rxrpc_rx_icmp(peer, &serr->ee, &srx); + if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP && serr->ee.ee_type == ICMP_DEST_UNREACH && serr->ee.ee_code == ICMP_FRAG_NEEDED)) { @@ -209,9 +212,6 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, ee = &serr->ee; - _net("Rx Error o=%d t=%d c=%d e=%d", - ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno); - err = ee->ee_errno; switch (ee->ee_origin) { diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 588fea0dd362..6c0ae27fff84 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -664,7 +664,8 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { - _debug("sendmsg failed: %d", ret); + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_fail_conn_challenge); return -EAGAIN; } @@ -719,7 +720,8 @@ static int rxkad_send_response(struct rxrpc_connection *conn, ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len); if (ret < 0) { - _debug("sendmsg failed: %d", ret); + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_fail_conn_response); return -EAGAIN; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 206e802ccbdc..be01f9c5d963 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -223,6 +223,15 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, ret = rxrpc_send_data_packet(call, skb, false); if (ret < 0) { + switch (ret) { + case -ENETUNREACH: + case -EHOSTUNREACH: + case -ECONNREFUSED: + rxrpc_set_call_completion(call, + RXRPC_CALL_LOCAL_ERROR, + 0, ret); + goto out; + } _debug("need instant resend %d", ret); rxrpc_instant_resend(call, ix); } else { @@ -241,6 +250,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_timer_set_for_send); } +out: rxrpc_free_skb(skb, rxrpc_skb_tx_freed); _leave(""); } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index a5994cf0512b..8527cfdc446d 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -652,7 +652,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, } } - return 0; + return -ENOENT; } static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, @@ -682,7 +682,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u16 mtype; u16 dlen; - curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL); + curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype, + &dlen, NULL); + if (!curr_data) { + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); + return TC_ACT_SHOT; + } if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index ddf69fc01bdf..6138d1d71900 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -121,7 +121,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, return 0; if (!flags) { - tcf_idr_release(*a, bind); + if (exists) + tcf_idr_release(*a, bind); return -EINVAL; } diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index bbcbdce732cc..ad050d7d4b46 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -131,8 +131,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (exists && bind) return 0; - if (!lflags) + if (!lflags) { + if (exists) + tcf_idr_release(*a, bind); return -EINVAL; + } if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 853604685965..1fb39e1f9d07 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -161,6 +161,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, case htons(ETH_P_8021AD): break; default: + if (exists) + tcf_idr_release(*a, bind); return -EPROTONOSUPPORT; } } else { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index b66754f52a9f..a57e112d9b3e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -152,8 +152,8 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, NL_SET_ERR_MSG(extack, "TC classifier not found"); err = -ENOENT; } - goto errout; #endif + goto errout; } tp->classify = tp->ops->classify; tp->protocol = protocol; @@ -1588,7 +1588,7 @@ int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts, return ret; ok_count = ret; - if (!exts) + if (!exts || ok_count) return ok_count; ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop); if (ret < 0) diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index a366e4c9413a..4808713c73b9 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -128,6 +128,28 @@ static bool fq_flow_is_detached(const struct fq_flow *f) return f->next == &detached; } +static bool fq_flow_is_throttled(const struct fq_flow *f) +{ + return f->next == &throttled; +} + +static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow) +{ + if (head->first) + head->last->next = flow; + else + head->first = flow; + head->last = flow; + flow->next = NULL; +} + +static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f) +{ + rb_erase(&f->rate_node, &q->delayed); + q->throttled_flows--; + fq_flow_add_tail(&q->old_flows, f); +} + static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) { struct rb_node **p = &q->delayed.rb_node, *parent = NULL; @@ -155,15 +177,6 @@ static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) static struct kmem_cache *fq_flow_cachep __read_mostly; -static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow) -{ - if (head->first) - head->last->next = flow; - else - head->first = flow; - head->last = flow; - flow->next = NULL; -} /* limit number of collected flows per round */ #define FQ_GC_MAX 8 @@ -267,6 +280,8 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (fq_flow_is_throttled(f)) + fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; } return f; @@ -438,9 +453,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now) q->time_next_delayed_flow = f->time_next_packet; break; } - rb_erase(p, &q->delayed); - q->throttled_flows--; - fq_flow_add_tail(&q->old_flows, f); + fq_flow_unset_throttled(q, f); } } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 16644b3d2362..56c181c3feeb 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -222,10 +222,11 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, extack); if (IS_ERR(child)) return PTR_ERR(child); - } - if (child != &noop_qdisc) + /* child is fifo, no need to check for noop_qdisc */ qdisc_hash_add(child, true); + } + sch_tree_lock(sch); q->flags = ctl->flags; q->limit = ctl->limit; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 03225a8df973..6f74a426f159 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -383,6 +383,9 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, err = PTR_ERR(child); goto done; } + + /* child is fifo, no need to check for noop_qdisc */ + qdisc_hash_add(child, true); } sch_tree_lock(sch); @@ -391,8 +394,6 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; - if (child != &noop_qdisc) - qdisc_hash_add(child, true); } q->limit = qopt->limit; if (tb[TCA_TBF_PBURST]) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 837806dd5799..a47179da24e6 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1024,8 +1024,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) struct sctp_endpoint *ep; struct sctp_chunk *chunk; struct sctp_inq *inqueue; - int state; + int first_time = 1; /* is this the first time through the loop */ int error = 0; + int state; /* The association should be held so we should be safe. */ ep = asoc->ep; @@ -1036,6 +1037,30 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) state = asoc->state; subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type); + /* If the first chunk in the packet is AUTH, do special + * processing specified in Section 6.3 of SCTP-AUTH spec + */ + if (first_time && subtype.chunk == SCTP_CID_AUTH) { + struct sctp_chunkhdr *next_hdr; + + next_hdr = sctp_inq_peek(inqueue); + if (!next_hdr) + goto normal; + + /* If the next chunk is COOKIE-ECHO, skip the AUTH + * chunk while saving a pointer to it so we can do + * Authentication later (during cookie-echo + * processing). + */ + if (next_hdr->type == SCTP_CID_COOKIE_ECHO) { + chunk->auth_chunk = skb_clone(chunk->skb, + GFP_ATOMIC); + chunk->auth = 1; + continue; + } + } + +normal: /* SCTP-AUTH, Section 6.3: * The receiver has a list of chunk types which it expects * to be received only after an AUTH-chunk. This list has @@ -1074,6 +1099,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) /* If there is an error on chunk, discard this packet. */ if (error && chunk) chunk->pdiscard = 1; + + if (first_time) + first_time = 0; } sctp_association_put(asoc); } diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 23ebc5318edc..eb93ffe2408b 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -217,7 +217,7 @@ new_skb: skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - if (chunk->chunk_end + sizeof(*ch) < skb_tail_pointer(chunk->skb)) { + if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 31083b5035ec..0cd2e764f47f 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -556,46 +556,49 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr, addr->v6.sin6_scope_id = 0; } -/* Compare addresses exactly. - * v4-mapped-v6 is also in consideration. - */ -static int sctp_v6_cmp_addr(const union sctp_addr *addr1, - const union sctp_addr *addr2) +static int __sctp_v6_cmp_addr(const union sctp_addr *addr1, + const union sctp_addr *addr2) { if (addr1->sa.sa_family != addr2->sa.sa_family) { if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET6 && - ipv6_addr_v4mapped(&addr2->v6.sin6_addr)) { - if (addr2->v6.sin6_port == addr1->v4.sin_port && - addr2->v6.sin6_addr.s6_addr32[3] == - addr1->v4.sin_addr.s_addr) - return 1; - } + ipv6_addr_v4mapped(&addr2->v6.sin6_addr) && + addr2->v6.sin6_addr.s6_addr32[3] == + addr1->v4.sin_addr.s_addr) + return 1; + if (addr2->sa.sa_family == AF_INET && addr1->sa.sa_family == AF_INET6 && - ipv6_addr_v4mapped(&addr1->v6.sin6_addr)) { - if (addr1->v6.sin6_port == addr2->v4.sin_port && - addr1->v6.sin6_addr.s6_addr32[3] == - addr2->v4.sin_addr.s_addr) - return 1; - } + ipv6_addr_v4mapped(&addr1->v6.sin6_addr) && + addr1->v6.sin6_addr.s6_addr32[3] == + addr2->v4.sin_addr.s_addr) + return 1; + return 0; } - if (addr1->v6.sin6_port != addr2->v6.sin6_port) - return 0; + if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; + /* If this is a linklocal address, compare the scope_id. */ - if (ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) { - if (addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id && - (addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)) { - return 0; - } - } + if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) && + addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id && + addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id) + return 0; return 1; } +/* Compare addresses exactly. + * v4-mapped-v6 is also in consideration. + */ +static int sctp_v6_cmp_addr(const union sctp_addr *addr1, + const union sctp_addr *addr2) +{ + return __sctp_v6_cmp_addr(addr1, addr2) && + addr1->v6.sin6_port == addr2->v6.sin6_port; +} + /* Initialize addr struct to INADDR_ANY. */ static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port) { @@ -875,8 +878,8 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1, const union sctp_addr *addr2, struct sctp_sock *opt) { - struct sctp_af *af1, *af2; struct sock *sk = sctp_opt2sk(opt); + struct sctp_af *af1, *af2; af1 = sctp_get_af_specific(addr1->sa.sa_family); af2 = sctp_get_af_specific(addr2->sa.sa_family); @@ -892,10 +895,10 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1, if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2)) return 1; - if (addr1->sa.sa_family != addr2->sa.sa_family) - return 0; + if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET) + return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr; - return af1->cmp_addr(addr1, addr2); + return __sctp_v6_cmp_addr(addr1, addr2); } /* Verify that the provided sockaddr looks bindable. Common verification, @@ -1003,7 +1006,7 @@ static const struct proto_ops inet6_seqpacket_ops = { .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, - .connect = inet_dgram_connect, + .connect = sctp_inet_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = sctp_getname, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index d685f8456762..6bf0a9971888 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1012,7 +1012,7 @@ static const struct proto_ops inet_seqpacket_ops = { .owner = THIS_MODULE, .release = inet_release, /* Needs to be wrapped... */ .bind = inet_bind, - .connect = inet_dgram_connect, + .connect = sctp_inet_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = inet_getname, /* Semantics are different. */ diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5a4fb1dc8400..e62addb60434 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1152,7 +1152,7 @@ struct sctp_chunk *sctp_make_violation_max_retrans( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { - static const char error[] = "Association exceeded its max_retans count"; + static const char error[] = "Association exceeded its max_retrans count"; size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr); struct sctp_chunk *retval; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index dd0594a10961..c9ae3404b1bb 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -153,10 +153,7 @@ static enum sctp_disposition sctp_sf_violation_chunk( struct sctp_cmd_seq *commands); static enum sctp_ierror sctp_sf_authenticate( - struct net *net, - const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const union sctp_subtype type, struct sctp_chunk *chunk); static enum sctp_disposition __sctp_sf_do_9_1_abort( @@ -626,6 +623,38 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, return SCTP_DISPOSITION_CONSUME; } +static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk, + const struct sctp_association *asoc) +{ + struct sctp_chunk auth; + + if (!chunk->auth_chunk) + return true; + + /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo + * is supposed to be authenticated and we have to do delayed + * authentication. We've just recreated the association using + * the information in the cookie and now it's much easier to + * do the authentication. + */ + + /* Make sure that we and the peer are AUTH capable */ + if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + return false; + + /* set-up our fake chunk so that we can process it */ + auth.skb = chunk->auth_chunk; + auth.asoc = chunk->asoc; + auth.sctp_hdr = chunk->sctp_hdr; + auth.chunk_hdr = (struct sctp_chunkhdr *) + skb_push(chunk->auth_chunk, + sizeof(struct sctp_chunkhdr)); + skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); + auth.transport = chunk->transport; + + return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR; +} + /* * Respond to a normal COOKIE ECHO chunk. * We are the side that is being asked for an association. @@ -763,37 +792,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, if (error) goto nomem_init; - /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo - * is supposed to be authenticated and we have to do delayed - * authentication. We've just recreated the association using - * the information in the cookie and now it's much easier to - * do the authentication. - */ - if (chunk->auth_chunk) { - struct sctp_chunk auth; - enum sctp_ierror ret; - - /* Make sure that we and the peer are AUTH capable */ - if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } - - /* set-up our fake chunk so that we can process it */ - auth.skb = chunk->auth_chunk; - auth.asoc = chunk->asoc; - auth.sctp_hdr = chunk->sctp_hdr; - auth.chunk_hdr = (struct sctp_chunkhdr *) - skb_push(chunk->auth_chunk, - sizeof(struct sctp_chunkhdr)); - skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); - auth.transport = chunk->transport; - - ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); - if (ret != SCTP_IERROR_NO_ERROR) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } repl = sctp_make_cookie_ack(new_asoc, chunk); @@ -1794,13 +1795,18 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( GFP_ATOMIC)) goto nomem; + if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC)) + goto nomem; + + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Make sure no new addresses are being added during the * restart. Though this is a pretty complicated attack * since you'd have to get inside the cookie. */ - if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) { + if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) return SCTP_DISPOSITION_CONSUME; - } /* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes * the peer has restarted (Action A), it MUST NOT setup a new @@ -1906,6 +1912,12 @@ static enum sctp_disposition sctp_sf_do_dupcook_b( GFP_ATOMIC)) goto nomem; + if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC)) + goto nomem; + + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, @@ -2003,6 +2015,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_d( * a COOKIE ACK. */ + if (!sctp_auth_chunk_verify(net, chunk, asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Don't accidentally move back into established state. */ if (asoc->state < SCTP_STATE_ESTABLISHED) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, @@ -2050,7 +2065,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_d( } } - repl = sctp_make_cookie_ack(new_asoc, chunk); + repl = sctp_make_cookie_ack(asoc, chunk); if (!repl) goto nomem; @@ -4165,10 +4180,7 @@ gen_shutdown: * The return value is the disposition of the chunk. */ static enum sctp_ierror sctp_sf_authenticate( - struct net *net, - const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const union sctp_subtype type, struct sctp_chunk *chunk) { struct sctp_shared_key *sh_key = NULL; @@ -4269,7 +4281,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net, commands); auth_hdr = (struct sctp_authhdr *)chunk->skb->data; - error = sctp_sf_authenticate(net, ep, asoc, type, chunk); + error = sctp_sf_authenticate(asoc, chunk); switch (error) { case SCTP_IERROR_AUTH_BAD_HMAC: /* Generate the ERROR chunk and discard the rest diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 80835ac26d2c..ae7e7c606f72 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1086,7 +1086,7 @@ out: */ static int __sctp_connect(struct sock *sk, struct sockaddr *kaddrs, - int addrs_size, + int addrs_size, int flags, sctp_assoc_t *assoc_id) { struct net *net = sock_net(sk); @@ -1104,7 +1104,6 @@ static int __sctp_connect(struct sock *sk, union sctp_addr *sa_addr = NULL; void *addr_buf; unsigned short port; - unsigned int f_flags = 0; sp = sctp_sk(sk); ep = sp->ep; @@ -1254,13 +1253,7 @@ static int __sctp_connect(struct sock *sk, sp->pf->to_sk_daddr(sa_addr, sk); sk->sk_err = 0; - /* in-kernel sockets don't generally have a file allocated to them - * if all they do is call sock_create_kern(). - */ - if (sk->sk_socket->file) - f_flags = sk->sk_socket->file->f_flags; - - timeo = sock_sndtimeo(sk, f_flags & O_NONBLOCK); + timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); if (assoc_id) *assoc_id = asoc->assoc_id; @@ -1348,7 +1341,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk, sctp_assoc_t *assoc_id) { struct sockaddr *kaddrs; - int err = 0; + int err = 0, flags = 0; pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n", __func__, sk, addrs, addrs_size); @@ -1367,7 +1360,13 @@ static int __sctp_setsockopt_connectx(struct sock *sk, if (err) goto out_free; - err = __sctp_connect(sk, kaddrs, addrs_size, assoc_id); + /* in-kernel sockets don't generally have a file allocated to them + * if all they do is call sock_create_kern(). + */ + if (sk->sk_socket->file) + flags = sk->sk_socket->file->f_flags; + + err = __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id); out_free: kvfree(kaddrs); @@ -4397,16 +4396,26 @@ out_nounlock: * len: the size of the address. */ static int sctp_connect(struct sock *sk, struct sockaddr *addr, - int addr_len) + int addr_len, int flags) { - int err = 0; + struct inet_sock *inet = inet_sk(sk); struct sctp_af *af; + int err = 0; lock_sock(sk); pr_debug("%s: sk:%p, sockaddr:%p, addr_len:%d\n", __func__, sk, addr, addr_len); + /* We may need to bind the socket. */ + if (!inet->inet_num) { + if (sk->sk_prot->get_port(sk, 0)) { + release_sock(sk); + return -EAGAIN; + } + inet->inet_sport = htons(inet->inet_num); + } + /* Validate addr_len before calling common connect/connectx routine. */ af = sctp_get_af_specific(addr->sa_family); if (!af || addr_len < af->sockaddr_len) { @@ -4415,13 +4424,25 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr, /* Pass correct addr len to common routine (so it knows there * is only one address being passed. */ - err = __sctp_connect(sk, addr, af->sockaddr_len, NULL); + err = __sctp_connect(sk, addr, af->sockaddr_len, flags, NULL); } release_sock(sk); return err; } +int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr, + int addr_len, int flags) +{ + if (addr_len < sizeof(uaddr->sa_family)) + return -EINVAL; + + if (uaddr->sa_family == AF_UNSPEC) + return -EOPNOTSUPP; + + return sctp_connect(sock->sk, uaddr, addr_len, flags); +} + /* FIXME: Write comments. */ static int sctp_disconnect(struct sock *sk, int flags) { @@ -8724,7 +8745,6 @@ struct proto sctp_prot = { .name = "SCTP", .owner = THIS_MODULE, .close = sctp_close, - .connect = sctp_connect, .disconnect = sctp_disconnect, .accept = sctp_accept, .ioctl = sctp_ioctl, @@ -8767,7 +8787,6 @@ struct proto sctpv6_prot = { .name = "SCTPv6", .owner = THIS_MODULE, .close = sctp_close, - .connect = sctp_connect, .disconnect = sctp_disconnect, .accept = sctp_accept, .ioctl = sctp_ioctl, diff --git a/net/sctp/stream.c b/net/sctp/stream.c index f799043abec9..f1f1d1b232ba 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -240,6 +240,8 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) new->out = NULL; new->in = NULL; + new->outcnt = 0; + new->incnt = 0; } static int sctp_send_reconf(struct sctp_association *asoc, diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 84207ad33e8e..8cb7d9858270 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -715,7 +715,6 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, return event; fail_mark: - sctp_chunk_put(chunk); kfree_skb(skb); fail: return NULL; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5f8046c62d90..544bab42f925 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -292,6 +292,17 @@ static void smc_copy_sock_settings_to_smc(struct smc_sock *smc) smc_copy_sock_settings(&smc->sk, smc->clcsock->sk, SK_FLAGS_CLC_TO_SMC); } +/* register a new rmb */ +static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc) +{ + /* register memory region for new rmb */ + if (smc_wr_reg_send(link, rmb_desc->mr_rx[SMC_SINGLE_LINK])) { + rmb_desc->regerr = 1; + return -EFAULT; + } + return 0; +} + static int smc_clnt_conf_first_link(struct smc_sock *smc) { struct smc_link_group *lgr = smc->conn.lgr; @@ -321,9 +332,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) smc_wr_remember_qp_attr(link); - rc = smc_wr_reg_send(link, - smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]); - if (rc) + if (smc_reg_rmb(link, smc->conn.rmb_desc)) return SMC_CLC_DECL_INTERR; /* send CONFIRM LINK response over RoCE fabric */ @@ -473,13 +482,8 @@ static int smc_connect_rdma(struct smc_sock *smc) goto decline_rdma_unlock; } } else { - struct smc_buf_desc *buf_desc = smc->conn.rmb_desc; - - if (!buf_desc->reused) { - /* register memory region for new rmb */ - rc = smc_wr_reg_send(link, - buf_desc->mr_rx[SMC_SINGLE_LINK]); - if (rc) { + if (!smc->conn.rmb_desc->reused) { + if (smc_reg_rmb(link, smc->conn.rmb_desc)) { reason_code = SMC_CLC_DECL_INTERR; goto decline_rdma_unlock; } @@ -719,9 +723,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc) link = &lgr->lnk[SMC_SINGLE_LINK]; - rc = smc_wr_reg_send(link, - smc->conn.rmb_desc->mr_rx[SMC_SINGLE_LINK]); - if (rc) + if (smc_reg_rmb(link, smc->conn.rmb_desc)) return SMC_CLC_DECL_INTERR; /* send CONFIRM LINK request to client over the RoCE fabric */ @@ -854,13 +856,8 @@ static void smc_listen_work(struct work_struct *work) smc_rx_init(new_smc); if (local_contact != SMC_FIRST_CONTACT) { - struct smc_buf_desc *buf_desc = new_smc->conn.rmb_desc; - - if (!buf_desc->reused) { - /* register memory region for new rmb */ - rc = smc_wr_reg_send(link, - buf_desc->mr_rx[SMC_SINGLE_LINK]); - if (rc) { + if (!new_smc->conn.rmb_desc->reused) { + if (smc_reg_rmb(link, new_smc->conn.rmb_desc)) { reason_code = SMC_CLC_DECL_INTERR; goto decline_rdma_unlock; } @@ -978,10 +975,6 @@ static void smc_tcp_listen_work(struct work_struct *work) } out: - if (lsmc->clcsock) { - sock_release(lsmc->clcsock); - lsmc->clcsock = NULL; - } release_sock(lsk); sock_put(&lsmc->sk); /* sock_hold in smc_listen */ } @@ -1170,13 +1163,15 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, /* delegate to CLC child sock */ release_sock(sk); mask = smc->clcsock->ops->poll(file, smc->clcsock, wait); - /* if non-blocking connect finished ... */ lock_sock(sk); - if ((sk->sk_state == SMC_INIT) && (mask & EPOLLOUT)) { - sk->sk_err = smc->clcsock->sk->sk_err; - if (sk->sk_err) { - mask |= EPOLLERR; - } else { + sk->sk_err = smc->clcsock->sk->sk_err; + if (sk->sk_err) { + mask |= EPOLLERR; + } else { + /* if non-blocking connect finished ... */ + if (sk->sk_state == SMC_INIT && + mask & EPOLLOUT && + smc->clcsock->sk->sk_state != TCP_CLOSE) { rc = smc_connect_rdma(smc); if (rc < 0) mask |= EPOLLERR; @@ -1259,14 +1254,12 @@ static int smc_shutdown(struct socket *sock, int how) rc = smc_close_shutdown_write(smc); break; case SHUT_RD: - if (sk->sk_state == SMC_LISTEN) - rc = smc_close_active(smc); - else - rc = 0; - /* nothing more to do because peer is not involved */ + rc = 0; + /* nothing more to do because peer is not involved */ break; } - rc1 = kernel_sock_shutdown(smc->clcsock, how); + if (smc->clcsock) + rc1 = kernel_sock_shutdown(smc->clcsock, how); /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; @@ -1322,8 +1315,11 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page, smc = smc_sk(sk); lock_sock(sk); - if (sk->sk_state != SMC_ACTIVE) + if (sk->sk_state != SMC_ACTIVE) { + release_sock(sk); goto out; + } + release_sock(sk); if (smc->use_fallback) rc = kernel_sendpage(smc->clcsock, page, offset, size, flags); @@ -1331,7 +1327,6 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page, rc = sock_no_sendpage(sock, page, offset, size, flags); out: - release_sock(sk); return rc; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index f44f6803f7ff..d4bd01bb44e1 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -32,6 +32,9 @@ static u32 smc_lgr_num; /* unique link group number */ +static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk, + bool is_rmb); + static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) { /* client link group creation always follows the server link group @@ -234,9 +237,22 @@ static void smc_buf_unuse(struct smc_connection *conn) conn->sndbuf_size = 0; } if (conn->rmb_desc) { - conn->rmb_desc->reused = true; - conn->rmb_desc->used = 0; - conn->rmbe_size = 0; + if (!conn->rmb_desc->regerr) { + conn->rmb_desc->reused = 1; + conn->rmb_desc->used = 0; + conn->rmbe_size = 0; + } else { + /* buf registration failed, reuse not possible */ + struct smc_link_group *lgr = conn->lgr; + struct smc_link *lnk; + + write_lock_bh(&lgr->rmbs_lock); + list_del(&conn->rmb_desc->list); + write_unlock_bh(&lgr->rmbs_lock); + + lnk = &lgr->lnk[SMC_SINGLE_LINK]; + smc_buf_free(conn->rmb_desc, lnk, true); + } } } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 07e2a393e6d9..5dfcb15d529f 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -123,7 +123,8 @@ struct smc_buf_desc { */ u32 order; /* allocation order */ u32 used; /* currently used / unused */ - bool reused; /* new created / reused */ + u8 reused : 1; /* new created / reused */ + u8 regerr : 1; /* err during registration */ }; struct smc_rtoken { /* address/key of remote RMB */ diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 74568cdbca70..d7b88b2d1b22 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -245,40 +245,45 @@ out: static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem, struct nlattr *tb[]) { - char *string, *ibname = NULL; - int rc = 0; + char *string, *ibname; + int rc; memset(pnetelem, 0, sizeof(*pnetelem)); INIT_LIST_HEAD(&pnetelem->list); - if (tb[SMC_PNETID_NAME]) { - string = (char *)nla_data(tb[SMC_PNETID_NAME]); - if (!smc_pnetid_valid(string, pnetelem->pnet_name)) { - rc = -EINVAL; - goto error; - } - } - if (tb[SMC_PNETID_ETHNAME]) { - string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]); - pnetelem->ndev = dev_get_by_name(net, string); - if (!pnetelem->ndev) - return -ENOENT; - } - if (tb[SMC_PNETID_IBNAME]) { - ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]); - ibname = strim(ibname); - pnetelem->smcibdev = smc_pnet_find_ib(ibname); - if (!pnetelem->smcibdev) { - rc = -ENOENT; - goto error; - } - } - if (tb[SMC_PNETID_IBPORT]) { - pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]); - if (pnetelem->ib_port > SMC_MAX_PORTS) { - rc = -EINVAL; - goto error; - } - } + + rc = -EINVAL; + if (!tb[SMC_PNETID_NAME]) + goto error; + string = (char *)nla_data(tb[SMC_PNETID_NAME]); + if (!smc_pnetid_valid(string, pnetelem->pnet_name)) + goto error; + + rc = -EINVAL; + if (!tb[SMC_PNETID_ETHNAME]) + goto error; + rc = -ENOENT; + string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]); + pnetelem->ndev = dev_get_by_name(net, string); + if (!pnetelem->ndev) + goto error; + + rc = -EINVAL; + if (!tb[SMC_PNETID_IBNAME]) + goto error; + rc = -ENOENT; + ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]); + ibname = strim(ibname); + pnetelem->smcibdev = smc_pnet_find_ib(ibname); + if (!pnetelem->smcibdev) + goto error; + + rc = -EINVAL; + if (!tb[SMC_PNETID_IBPORT]) + goto error; + pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]); + if (pnetelem->ib_port < 1 || pnetelem->ib_port > SMC_MAX_PORTS) + goto error; + return 0; error: @@ -307,6 +312,8 @@ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info) void *hdr; int rc; + if (!info->attrs[SMC_PNETID_NAME]) + return -EINVAL; pnetelem = smc_pnet_find_pnetid( (char *)nla_data(info->attrs[SMC_PNETID_NAME])); if (!pnetelem) @@ -359,6 +366,8 @@ static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info) static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info) { + if (!info->attrs[SMC_PNETID_NAME]) + return -EINVAL; return smc_pnet_remove_by_pnetid( (char *)nla_data(info->attrs[SMC_PNETID_NAME])); } diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index b9283ce5cd85..092bebc70048 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err) static void strp_start_timer(struct strparser *strp, long timeo) { - if (timeo) + if (timeo && timeo != LONG_MAX) mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo); } @@ -296,9 +296,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, strp_start_timer(strp, timeo); } + stm->accum_len += cand_len; strp->need_bytes = stm->strp.full_len - stm->accum_len; - stm->accum_len += cand_len; stm->early_eaten = cand_len; STRP_STATS_ADD(strp->stats.bytes, cand_len); desc->count = 0; /* Stop reading socket */ @@ -321,6 +321,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, /* Hurray, we have a new message! */ cancel_delayed_work(&strp->msg_timer_work); strp->skb_head = NULL; + strp->need_bytes = 0; STRP_STATS_INCR(strp->stats.msgs); /* Give skb to upper layer */ @@ -410,9 +411,7 @@ void strp_data_ready(struct strparser *strp) return; if (strp->need_bytes) { - if (strp_peek_len(strp) >= strp->need_bytes) - strp->need_bytes = 0; - else + if (strp_peek_len(strp) < strp->need_bytes) return; } diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index ac09ca803296..6358e5271070 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -50,7 +50,7 @@ config SUNRPC_DEBUG config SUNRPC_XPRT_RDMA tristate "RPC-over-RDMA transport" - depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS + depends on SUNRPC && INFINIBAND_ADDR_TRANS default SUNRPC && INFINIBAND select SG_POOL help diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 0f08934b2cea..c81ef5e6c981 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1375,6 +1375,7 @@ rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry) struct dentry *clnt_dir = pipe_dentry->d_parent; struct dentry *gssd_dir = clnt_dir->d_parent; + dget(pipe_dentry); __rpc_rmpipe(d_inode(clnt_dir), pipe_dentry); __rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1); __rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1); diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 5cc68a824f45..f2f63959fddd 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -72,6 +72,7 @@ fmr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr) if (IS_ERR(mr->fmr.fm_mr)) goto out_fmr_err; + INIT_LIST_HEAD(&mr->mr_list); return 0; out_fmr_err: @@ -102,10 +103,6 @@ fmr_op_release_mr(struct rpcrdma_mr *mr) LIST_HEAD(unmap_list); int rc; - /* Ensure MW is not on any rl_registered list */ - if (!list_empty(&mr->mr_list)) - list_del(&mr->mr_list); - kfree(mr->fmr.fm_physaddrs); kfree(mr->mr_sg); diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index c5743a0960be..c59c5c788db0 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -110,6 +110,7 @@ frwr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr) if (!mr->mr_sg) goto out_list_err; + INIT_LIST_HEAD(&mr->mr_list); sg_init_table(mr->mr_sg, depth); init_completion(&frwr->fr_linv_done); return 0; @@ -133,10 +134,6 @@ frwr_op_release_mr(struct rpcrdma_mr *mr) { int rc; - /* Ensure MR is not on any rl_registered list */ - if (!list_empty(&mr->mr_list)) - list_del(&mr->mr_list); - rc = ib_dereg_mr(mr->frwr.fr_mr); if (rc) pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n", @@ -195,7 +192,7 @@ frwr_op_recover_mr(struct rpcrdma_mr *mr) return; out_release: - pr_err("rpcrdma: FRWR reset failed %d, %p release\n", rc, mr); + pr_err("rpcrdma: FRWR reset failed %d, %p released\n", rc, mr); r_xprt->rx_stats.mrs_orphaned++; spin_lock(&r_xprt->rx_buf.rb_mrlock); @@ -476,7 +473,7 @@ frwr_op_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) list_for_each_entry(mr, mrs, mr_list) if (mr->mr_handle == rep->rr_inv_rkey) { - list_del(&mr->mr_list); + list_del_init(&mr->mr_list); trace_xprtrdma_remoteinv(mr); mr->frwr.fr_state = FRWR_IS_INVALID; rpcrdma_mr_unmap_and_put(mr); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index fe5eaca2d197..c345d365af88 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1254,6 +1254,11 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) list_del(&mr->mr_all); spin_unlock(&buf->rb_mrlock); + + /* Ensure MW is not on any rl_registered list */ + if (!list_empty(&mr->mr_list)) + list_del(&mr->mr_list); + ia->ri_ops->ro_release_mr(mr); count++; spin_lock(&buf->rb_mrlock); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 3d3b423fa9c1..cb41b12a3bf8 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -380,7 +380,7 @@ rpcrdma_mr_pop(struct list_head *list) struct rpcrdma_mr *mr; mr = list_first_entry(list, struct rpcrdma_mr, mr_list); - list_del(&mr->mr_list); + list_del_init(&mr->mr_list); return mr; } diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 32dc33a94bc7..5453e564da82 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -777,7 +777,7 @@ int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg, ret = tipc_bearer_get_name(net, bearer_name, bearer_id); if (ret || !mon) - return -EINVAL; + return 0; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_MON_GET); diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index b1fe20972aa9..dd1c4fa2eb78 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -241,7 +241,8 @@ err: static struct publication *tipc_service_remove_publ(struct net *net, struct tipc_service *sc, u32 lower, u32 upper, - u32 node, u32 key) + u32 node, u32 key, + struct service_range **rng) { struct tipc_subscription *sub, *tmp; struct service_range *sr; @@ -275,19 +276,15 @@ static struct publication *tipc_service_remove_publ(struct net *net, list_del(&p->all_publ); list_del(&p->local_publ); - - /* Remove service range item if this was its last publication */ - if (list_empty(&sr->all_publ)) { + if (list_empty(&sr->all_publ)) last = true; - rb_erase(&sr->tree_node, &sc->ranges); - kfree(sr); - } /* Notify any waiting subscriptions */ list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_WITHDRAWN, p->port, p->node, p->scope, last); } + *rng = sr; return p; } @@ -379,13 +376,20 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, u32 node, u32 key) { struct tipc_service *sc = tipc_service_find(net, type); + struct service_range *sr = NULL; struct publication *p = NULL; if (!sc) return NULL; spin_lock_bh(&sc->lock); - p = tipc_service_remove_publ(net, sc, lower, upper, node, key); + p = tipc_service_remove_publ(net, sc, lower, upper, node, key, &sr); + + /* Remove service range item if this was its last publication */ + if (sr && list_empty(&sr->all_publ)) { + rb_erase(&sr->tree_node, &sc->ranges); + kfree(sr); + } /* Delete service item if this no more publications and subscriptions */ if (RB_EMPTY_ROOT(&sc->ranges) && list_empty(&sc->subscriptions)) { @@ -665,13 +669,14 @@ int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower, /** * tipc_nametbl_subscribe - add a subscription object to the name table */ -void tipc_nametbl_subscribe(struct tipc_subscription *sub) +bool tipc_nametbl_subscribe(struct tipc_subscription *sub) { struct name_table *nt = tipc_name_table(sub->net); struct tipc_net *tn = tipc_net(sub->net); struct tipc_subscr *s = &sub->evt.s; u32 type = tipc_sub_read(s, seq.type); struct tipc_service *sc; + bool res = true; spin_lock_bh(&tn->nametbl_lock); sc = tipc_service_find(sub->net, type); @@ -685,8 +690,10 @@ void tipc_nametbl_subscribe(struct tipc_subscription *sub) pr_warn("Failed to subscribe for {%u,%u,%u}\n", type, tipc_sub_read(s, seq.lower), tipc_sub_read(s, seq.upper)); + res = false; } spin_unlock_bh(&tn->nametbl_lock); + return res; } /** @@ -744,16 +751,17 @@ int tipc_nametbl_init(struct net *net) static void tipc_service_delete(struct net *net, struct tipc_service *sc) { struct service_range *sr, *tmpr; - struct publication *p, *tmpb; + struct publication *p, *tmp; spin_lock_bh(&sc->lock); rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) { - list_for_each_entry_safe(p, tmpb, - &sr->all_publ, all_publ) { + list_for_each_entry_safe(p, tmp, &sr->all_publ, all_publ) { tipc_service_remove_publ(net, sc, p->lower, p->upper, - p->node, p->key); + p->node, p->key, &sr); kfree_rcu(p, rcu); } + rb_erase(&sr->tree_node, &sc->ranges); + kfree(sr); } hlist_del_init_rcu(&sc->service_list); spin_unlock_bh(&sc->lock); diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 4b14fc28d9e2..0febba41da86 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -126,7 +126,7 @@ struct publication *tipc_nametbl_insert_publ(struct net *net, u32 type, struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, u32 lower, u32 upper, u32 node, u32 key); -void tipc_nametbl_subscribe(struct tipc_subscription *s); +bool tipc_nametbl_subscribe(struct tipc_subscription *s); void tipc_nametbl_unsubscribe(struct tipc_subscription *s); int tipc_nametbl_init(struct net *net); void tipc_nametbl_stop(struct net *net); diff --git a/net/tipc/net.c b/net/tipc/net.c index 856f9e97ea29..4fbaa0464405 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -252,6 +252,8 @@ int __tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info) u64 *w0 = (u64 *)&node_id[0]; u64 *w1 = (u64 *)&node_id[8]; + if (!attrs[TIPC_NLA_NET_NODEID_W1]) + return -EINVAL; *w0 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID]); *w1 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID_W1]); tipc_net_init(net, node_id, 0); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index b76f13f6fea1..6ff2254088f6 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -79,7 +79,10 @@ const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = { const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { [TIPC_NLA_NET_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_NET_ID] = { .type = NLA_U32 } + [TIPC_NLA_NET_ID] = { .type = NLA_U32 }, + [TIPC_NLA_NET_ADDR] = { .type = NLA_U32 }, + [TIPC_NLA_NET_NODEID] = { .type = NLA_U64 }, + [TIPC_NLA_NET_NODEID_W1] = { .type = NLA_U64 }, }; const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = { diff --git a/net/tipc/node.c b/net/tipc/node.c index c77dd2f3c589..f29549de9245 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1950,6 +1950,7 @@ out: int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); + struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1]; struct tipc_nl_msg msg; char *name; int err; @@ -1957,9 +1958,19 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info) msg.portid = info->snd_portid; msg.seq = info->snd_seq; - if (!info->attrs[TIPC_NLA_LINK_NAME]) + if (!info->attrs[TIPC_NLA_LINK]) return -EINVAL; - name = nla_data(info->attrs[TIPC_NLA_LINK_NAME]); + + err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX, + info->attrs[TIPC_NLA_LINK], + tipc_nl_link_policy, info->extack); + if (err) + return err; + + if (!attrs[TIPC_NLA_LINK_NAME]) + return -EINVAL; + + name = nla_data(attrs[TIPC_NLA_LINK_NAME]); msg.skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!msg.skb) @@ -2232,8 +2243,8 @@ int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); u32 prev_bearer = cb->args[0]; struct tipc_nl_msg msg; + int bearer_id; int err; - int i; if (prev_bearer == MAX_BEARERS) return 0; @@ -2243,16 +2254,13 @@ int tipc_nl_node_dump_monitor(struct sk_buff *skb, struct netlink_callback *cb) msg.seq = cb->nlh->nlmsg_seq; rtnl_lock(); - for (i = prev_bearer; i < MAX_BEARERS; i++) { - prev_bearer = i; - err = __tipc_nl_add_monitor(net, &msg, prev_bearer); + for (bearer_id = prev_bearer; bearer_id < MAX_BEARERS; bearer_id++) { + err = __tipc_nl_add_monitor(net, &msg, bearer_id); if (err) - goto out; + break; } - -out: rtnl_unlock(); - cb->args[0] = prev_bearer; + cb->args[0] = bearer_id; return skb->len; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1fd1c8b5ce03..6be21575503a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1278,7 +1278,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) struct tipc_msg *hdr = &tsk->phdr; struct tipc_name_seq *seq; struct sk_buff_head pkts; - u32 dnode, dport; + u32 dport, dnode = 0; u32 type, inst; int mtu, rc; @@ -1348,6 +1348,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) msg_set_destnode(hdr, dnode); msg_set_destport(hdr, dest->addr.id.ref); msg_set_hdr_sz(hdr, BASIC_H_SIZE); + } else { + return -EINVAL; } /* Block or return if destination link is congested */ @@ -1514,10 +1516,10 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) srcaddr->sock.family = AF_TIPC; srcaddr->sock.addrtype = TIPC_ADDR_ID; + srcaddr->sock.scope = 0; srcaddr->sock.addr.id.ref = msg_origport(hdr); srcaddr->sock.addr.id.node = msg_orignode(hdr); srcaddr->sock.addr.name.domain = 0; - srcaddr->sock.scope = 0; m->msg_namelen = sizeof(struct sockaddr_tipc); if (!msg_in_group(hdr)) @@ -1526,6 +1528,7 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) /* Group message users may also want to know sending member's id */ srcaddr->member.family = AF_TIPC; srcaddr->member.addrtype = TIPC_ADDR_NAME; + srcaddr->member.scope = 0; srcaddr->member.addr.name.name.type = msg_nametype(hdr); srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member; srcaddr->member.addr.name.domain = 0; diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index b7d80bc5f4ab..f340e53da625 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -153,7 +153,10 @@ struct tipc_subscription *tipc_sub_subscribe(struct net *net, memcpy(&sub->evt.s, s, sizeof(*s)); spin_lock_init(&sub->lock); kref_init(&sub->kref); - tipc_nametbl_subscribe(sub); + if (!tipc_nametbl_subscribe(sub)) { + kfree(sub); + return NULL; + } timer_setup(&sub->timer, tipc_sub_timeout, 0); timeout = tipc_sub_read(&sub->evt.s, timeout); if (timeout != TIPC_WAIT_FOREVER) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 0d379970960e..20cd93be6236 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -114,6 +114,7 @@ int tls_push_sg(struct sock *sk, size = sg->length - offset; offset += sg->offset; + ctx->in_tcp_sendpages = true; while (1) { if (sg_is_last(sg)) sendpage_flags = flags; @@ -134,6 +135,7 @@ retry: offset -= sg->offset; ctx->partially_sent_offset = offset; ctx->partially_sent_record = (void *)sg; + ctx->in_tcp_sendpages = false; return ret; } @@ -148,6 +150,8 @@ retry: } clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); + ctx->in_tcp_sendpages = false; + ctx->sk_write_space(sk); return 0; } @@ -217,6 +221,10 @@ static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); + /* We are already sending pages, ignore notification */ + if (ctx->in_tcp_sendpages) + return; + if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; int rc; @@ -241,16 +249,13 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) struct tls_context *ctx = tls_get_ctx(sk); long timeo = sock_sndtimeo(sk, 0); void (*sk_proto_close)(struct sock *sk, long timeout); + bool free_ctx = false; lock_sock(sk); sk_proto_close = ctx->sk_proto_close; - if (ctx->conf == TLS_HW_RECORD) - goto skip_tx_cleanup; - - if (ctx->conf == TLS_BASE) { - kfree(ctx); - ctx = NULL; + if (ctx->conf == TLS_BASE || ctx->conf == TLS_HW_RECORD) { + free_ctx = true; goto skip_tx_cleanup; } @@ -287,7 +292,7 @@ skip_tx_cleanup: /* free ctx for TLS_HW_RECORD, used by tcp_set_state * for sk->sk_prot->unhash [tls_hw_unhash] */ - if (ctx && ctx->conf == TLS_HW_RECORD) + if (free_ctx) kfree(ctx); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 4dc766b03f00..e1c93ce74e0f 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -41,6 +41,8 @@ #include <net/strparser.h> #include <net/tls.h> +#define MAX_IV_SIZE TLS_CIPHER_AES_GCM_128_IV_SIZE + static int tls_do_decryption(struct sock *sk, struct scatterlist *sgin, struct scatterlist *sgout, @@ -673,12 +675,11 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); - char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + tls_ctx->rx.iv_size]; + char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + MAX_IV_SIZE]; struct scatterlist sgin_arr[MAX_SKB_FRAGS + 2]; struct scatterlist *sgin = &sgin_arr[0]; struct strp_msg *rxm = strp_msg(skb); int ret, nsg = ARRAY_SIZE(sgin_arr); - char aad_recv[TLS_AAD_SPACE_SIZE]; struct sk_buff *unused; ret = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE, @@ -696,13 +697,13 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, } sg_init_table(sgin, nsg); - sg_set_buf(&sgin[0], aad_recv, sizeof(aad_recv)); + sg_set_buf(&sgin[0], ctx->rx_aad_ciphertext, TLS_AAD_SPACE_SIZE); nsg = skb_to_sgvec(skb, &sgin[1], rxm->offset + tls_ctx->rx.prepend_size, rxm->full_len - tls_ctx->rx.prepend_size); - tls_make_aad(aad_recv, + tls_make_aad(ctx->rx_aad_ciphertext, rxm->full_len - tls_ctx->rx.overhead_size, tls_ctx->rx.rec_seq, tls_ctx->rx.rec_seq_size, @@ -801,12 +802,12 @@ int tls_sw_recvmsg(struct sock *sk, if (to_copy <= len && page_count < MAX_SKB_FRAGS && likely(!(flags & MSG_PEEK))) { struct scatterlist sgin[MAX_SKB_FRAGS + 1]; - char unused[21]; int pages = 0; zc = true; sg_init_table(sgin, MAX_SKB_FRAGS + 1); - sg_set_buf(&sgin[0], unused, 13); + sg_set_buf(&sgin[0], ctx->rx_aad_plaintext, + TLS_AAD_SPACE_SIZE); err = zerocopy_from_iter(sk, &msg->msg_iter, to_copy, &pages, @@ -1094,6 +1095,12 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto free_priv; } + /* Sanity-check the IV size for stack allocations. */ + if (iv_size > MAX_IV_SIZE) { + rc = -EINVAL; + goto free_priv; + } + cctx->prepend_size = TLS_HEADER_SIZE + nonce_size; cctx->tag_size = tag_size; cctx->overhead_size = cctx->prepend_size + cctx->tag_size; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index aac9b8f6552e..c1076c19b858 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -2018,7 +2018,13 @@ const struct vsock_transport *vsock_core_get_transport(void) } EXPORT_SYMBOL_GPL(vsock_core_get_transport); +static void __exit vsock_exit(void) +{ + /* Do nothing. This function makes this module removable. */ +} + module_init(vsock_init_tables); +module_exit(vsock_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMware Virtual Socket Family"); diff --git a/net/wireless/core.c b/net/wireless/core.c index a6f3cac8c640..c0fd8a85e7f7 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -95,6 +95,9 @@ static int cfg80211_dev_check_name(struct cfg80211_registered_device *rdev, ASSERT_RTNL(); + if (strlen(newname) > NL80211_WIPHY_NAME_MAXLEN) + return -EINVAL; + /* prohibit calling the thing phy%d when %d is not its number */ sscanf(newname, PHY_NAME "%d%n", &wiphy_idx, &taken); if (taken == strlen(newname) && wiphy_idx != rdev->wiphy_idx) { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ff28f8feeb09..7c5135a92d76 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9214,6 +9214,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (nla_get_flag(info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])) { if (!info->attrs[NL80211_ATTR_SOCKET_OWNER]) { + kzfree(connkeys); GENL_SET_ERR_MSG(info, "external auth requires connection ownership"); return -EINVAL; @@ -15554,7 +15555,8 @@ void cfg80211_ft_event(struct net_device *netdev, if (!ft_event->target_ap) return; - msg = nlmsg_new(100 + ft_event->ric_ies_len, GFP_KERNEL); + msg = nlmsg_new(100 + ft_event->ies_len + ft_event->ric_ies_len, + GFP_KERNEL); if (!msg) return; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 16c7e4ef5820..5fcec5c94eb7 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -916,6 +916,9 @@ int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr, const struct fwdb_header *hdr = regdb; const struct fwdb_country *country; + if (!regdb) + return -ENODATA; + if (IS_ERR(regdb)) return PTR_ERR(regdb); @@ -1026,6 +1029,7 @@ static int regdb_query_country(const struct fwdb_header *db, if (!tmp_rd) { kfree(regdom); + kfree(wmm_ptrs); return -ENOMEM; } regdom = tmp_rd; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f9d2f2233f09..6c177ae7a6d9 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2175,6 +2175,12 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) return afinfo; } +void xfrm_flush_gc(void) +{ + flush_work(&xfrm_state_gc_work); +} +EXPORT_SYMBOL(xfrm_flush_gc); + /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ void xfrm_state_delete_tunnel(struct xfrm_state *x) { |