diff options
Diffstat (limited to 'net')
32 files changed, 254 insertions, 241 deletions
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index daa749c..d8e376a 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -524,6 +524,12 @@ static int p9_virtio_probe(struct virtio_device *vdev) int err; struct virtio_chan *chan; + if (!vdev->config->get) { + dev_err(&vdev->dev, "%s failure: config access disabled\n", + __func__); + return -EINVAL; + } + chan = kmalloc(sizeof(struct virtio_chan), GFP_KERNEL); if (!chan) { pr_err("Failed to allocate virtio 9P channel\n"); diff --git a/net/Kconfig b/net/Kconfig index ff9ffc1..44dd578 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -231,18 +231,18 @@ source "net/hsr/Kconfig" source "net/switchdev/Kconfig" config RPS - boolean + bool depends on SMP && SYSFS default y config RFS_ACCEL - boolean + bool depends on RPS select CPU_RMAP default y config XPS - boolean + bool depends on SMP default y @@ -254,18 +254,18 @@ config CGROUP_NET_PRIO a per-interface basis. config CGROUP_NET_CLASSID - boolean "Network classid cgroup" + bool "Network classid cgroup" depends on CGROUPS ---help--- Cgroup subsystem for use as general purpose socket classid marker that is being used in cls_cgroup and for netfilter matching. config NET_RX_BUSY_POLL - boolean + bool default y config BQL - boolean + bool depends on SYSFS select DQL default y @@ -282,7 +282,7 @@ config BPF_JIT this feature changing /proc/sys/net/core/bpf_jit_enable config NET_FLOW_LIMIT - boolean + bool depends on RPS default y ---help--- diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 65728e0..0ee453f 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -987,15 +987,12 @@ static int __init br_netfilter_init(void) if (brnf_sysctl_header == NULL) { printk(KERN_WARNING "br_netfilter: can't register to sysctl.\n"); - ret = -ENOMEM; - goto err1; + nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); + return -ENOMEM; } #endif printk(KERN_NOTICE "Bridge firewalling registered\n"); return 0; -err1: - nf_unregister_hooks(br_nf_ops, ARRAY_SIZE(br_nf_ops)); - return ret; } static void __exit br_netfilter_fini(void) diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 5d5ab67..ec56550 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -239,6 +239,8 @@ enum { Opt_nocrc, Opt_cephx_require_signatures, Opt_nocephx_require_signatures, + Opt_tcp_nodelay, + Opt_notcp_nodelay, }; static match_table_t opt_tokens = { @@ -259,6 +261,8 @@ static match_table_t opt_tokens = { {Opt_nocrc, "nocrc"}, {Opt_cephx_require_signatures, "cephx_require_signatures"}, {Opt_nocephx_require_signatures, "nocephx_require_signatures"}, + {Opt_tcp_nodelay, "tcp_nodelay"}, + {Opt_notcp_nodelay, "notcp_nodelay"}, {-1, NULL} }; @@ -457,6 +461,7 @@ ceph_parse_options(char *options, const char *dev_name, case Opt_nocrc: opt->flags |= CEPH_OPT_NOCRC; break; + case Opt_cephx_require_signatures: opt->flags &= ~CEPH_OPT_NOMSGAUTH; break; @@ -464,6 +469,13 @@ ceph_parse_options(char *options, const char *dev_name, opt->flags |= CEPH_OPT_NOMSGAUTH; break; + case Opt_tcp_nodelay: + opt->flags |= CEPH_OPT_TCP_NODELAY; + break; + case Opt_notcp_nodelay: + opt->flags &= ~CEPH_OPT_TCP_NODELAY; + break; + default: BUG_ON(token); } @@ -518,10 +530,12 @@ struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, /* msgr */ if (ceph_test_opt(client, MYIP)) myaddr = &client->options->my_addr; + ceph_messenger_init(&client->msgr, myaddr, client->supported_features, client->required_features, - ceph_test_opt(client, NOCRC)); + ceph_test_opt(client, NOCRC), + ceph_test_opt(client, TCP_NODELAY)); /* subsystems */ err = ceph_monc_init(&client->monc, client); diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c index 3056020..139a9cb 100644 --- a/net/ceph/ceph_strings.c +++ b/net/ceph/ceph_strings.c @@ -42,17 +42,3 @@ const char *ceph_osd_state_name(int s) return "???"; } } - -const char *ceph_pool_op_name(int op) -{ - switch (op) { - case POOL_OP_CREATE: return "create"; - case POOL_OP_DELETE: return "delete"; - case POOL_OP_AUID_CHANGE: return "auid change"; - case POOL_OP_CREATE_SNAP: return "create snap"; - case POOL_OP_DELETE_SNAP: return "delete snap"; - case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap"; - case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap"; - } - return "???"; -} diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index d2d5255..14d9995 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -127,8 +127,6 @@ static int monc_show(struct seq_file *s, void *p) op = le16_to_cpu(req->request->hdr.type); if (op == CEPH_MSG_STATFS) seq_printf(s, "%llu statfs\n", req->tid); - else if (op == CEPH_MSG_POOLOP) - seq_printf(s, "%llu poolop\n", req->tid); else if (op == CEPH_MSG_MON_GET_VERSION) seq_printf(s, "%llu mon_get_version", req->tid); else diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 33a2f20..6b3f54e 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -510,6 +510,16 @@ static int ceph_tcp_connect(struct ceph_connection *con) return ret; } + if (con->msgr->tcp_nodelay) { + int optval = 1; + + ret = kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, + (char *)&optval, sizeof(optval)); + if (ret) + pr_err("kernel_setsockopt(TCP_NODELAY) failed: %d", + ret); + } + sk_set_memalloc(sock->sk); con->sock = sock; @@ -2922,7 +2932,8 @@ void ceph_messenger_init(struct ceph_messenger *msgr, struct ceph_entity_addr *myaddr, u64 supported_features, u64 required_features, - bool nocrc) + bool nocrc, + bool tcp_nodelay) { msgr->supported_features = supported_features; msgr->required_features = required_features; @@ -2937,6 +2948,7 @@ void ceph_messenger_init(struct ceph_messenger *msgr, get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce)); encode_my_addr(msgr); msgr->nocrc = nocrc; + msgr->tcp_nodelay = tcp_nodelay; atomic_set(&msgr->stopping, 0); diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index f2148e2..2b3cf05 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -410,7 +410,7 @@ out_unlocked: } /* - * generic requests (e.g., statfs, poolop) + * generic requests (currently statfs, mon_get_version) */ static struct ceph_mon_generic_request *__lookup_generic_req( struct ceph_mon_client *monc, u64 tid) @@ -569,7 +569,7 @@ static void handle_statfs_reply(struct ceph_mon_client *monc, return; bad: - pr_err("corrupt generic reply, tid %llu\n", tid); + pr_err("corrupt statfs reply, tid %llu\n", tid); ceph_msg_dump(msg); } @@ -588,7 +588,6 @@ int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf) kref_init(&req->kref); req->buf = buf; - req->buf_len = sizeof(*buf); init_completion(&req->completion); err = -ENOMEM; @@ -611,7 +610,7 @@ int ceph_monc_do_statfs(struct ceph_mon_client *monc, struct ceph_statfs *buf) err = do_generic_request(monc, req); out: - kref_put(&req->kref, release_generic_request); + put_generic_request(req); return err; } EXPORT_SYMBOL(ceph_monc_do_statfs); @@ -647,7 +646,7 @@ static void handle_get_version_reply(struct ceph_mon_client *monc, return; bad: - pr_err("corrupt mon_get_version reply\n"); + pr_err("corrupt mon_get_version reply, tid %llu\n", tid); ceph_msg_dump(msg); } @@ -670,7 +669,6 @@ int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what, kref_init(&req->kref); req->buf = newest; - req->buf_len = sizeof(*newest); init_completion(&req->completion); req->request = ceph_msg_new(CEPH_MSG_MON_GET_VERSION, @@ -701,134 +699,12 @@ int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what, mutex_unlock(&monc->mutex); out: - kref_put(&req->kref, release_generic_request); + put_generic_request(req); return err; } EXPORT_SYMBOL(ceph_monc_do_get_version); /* - * pool ops - */ -static int get_poolop_reply_buf(const char *src, size_t src_len, - char *dst, size_t dst_len) -{ - u32 buf_len; - - if (src_len != sizeof(u32) + dst_len) - return -EINVAL; - - buf_len = le32_to_cpu(*(__le32 *)src); - if (buf_len != dst_len) - return -EINVAL; - - memcpy(dst, src + sizeof(u32), dst_len); - return 0; -} - -static void handle_poolop_reply(struct ceph_mon_client *monc, - struct ceph_msg *msg) -{ - struct ceph_mon_generic_request *req; - struct ceph_mon_poolop_reply *reply = msg->front.iov_base; - u64 tid = le64_to_cpu(msg->hdr.tid); - - if (msg->front.iov_len < sizeof(*reply)) - goto bad; - dout("handle_poolop_reply %p tid %llu\n", msg, tid); - - mutex_lock(&monc->mutex); - req = __lookup_generic_req(monc, tid); - if (req) { - if (req->buf_len && - get_poolop_reply_buf(msg->front.iov_base + sizeof(*reply), - msg->front.iov_len - sizeof(*reply), - req->buf, req->buf_len) < 0) { - mutex_unlock(&monc->mutex); - goto bad; - } - req->result = le32_to_cpu(reply->reply_code); - get_generic_request(req); - } - mutex_unlock(&monc->mutex); - if (req) { - complete(&req->completion); - put_generic_request(req); - } - return; - -bad: - pr_err("corrupt generic reply, tid %llu\n", tid); - ceph_msg_dump(msg); -} - -/* - * Do a synchronous pool op. - */ -static int do_poolop(struct ceph_mon_client *monc, u32 op, - u32 pool, u64 snapid, - char *buf, int len) -{ - struct ceph_mon_generic_request *req; - struct ceph_mon_poolop *h; - int err; - - req = kzalloc(sizeof(*req), GFP_NOFS); - if (!req) - return -ENOMEM; - - kref_init(&req->kref); - req->buf = buf; - req->buf_len = len; - init_completion(&req->completion); - - err = -ENOMEM; - req->request = ceph_msg_new(CEPH_MSG_POOLOP, sizeof(*h), GFP_NOFS, - true); - if (!req->request) - goto out; - req->reply = ceph_msg_new(CEPH_MSG_POOLOP_REPLY, 1024, GFP_NOFS, - true); - if (!req->reply) - goto out; - - /* fill out request */ - req->request->hdr.version = cpu_to_le16(2); - h = req->request->front.iov_base; - h->monhdr.have_version = 0; - h->monhdr.session_mon = cpu_to_le16(-1); - h->monhdr.session_mon_tid = 0; - h->fsid = monc->monmap->fsid; - h->pool = cpu_to_le32(pool); - h->op = cpu_to_le32(op); - h->auid = 0; - h->snapid = cpu_to_le64(snapid); - h->name_len = 0; - - err = do_generic_request(monc, req); - -out: - kref_put(&req->kref, release_generic_request); - return err; -} - -int ceph_monc_create_snapid(struct ceph_mon_client *monc, - u32 pool, u64 *snapid) -{ - return do_poolop(monc, POOL_OP_CREATE_UNMANAGED_SNAP, - pool, 0, (char *)snapid, sizeof(*snapid)); - -} -EXPORT_SYMBOL(ceph_monc_create_snapid); - -int ceph_monc_delete_snapid(struct ceph_mon_client *monc, - u32 pool, u64 snapid) -{ - return do_poolop(monc, POOL_OP_CREATE_UNMANAGED_SNAP, - pool, snapid, NULL, 0); - -} - -/* * Resend pending generic requests. */ static void __resend_generic_request(struct ceph_mon_client *monc) @@ -1112,10 +988,6 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg) handle_get_version_reply(monc, msg); break; - case CEPH_MSG_POOLOP_REPLY: - handle_poolop_reply(monc, msg); - break; - case CEPH_MSG_MON_MAP: ceph_monc_handle_map(monc, msg); break; @@ -1154,7 +1026,6 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, case CEPH_MSG_MON_SUBSCRIBE_ACK: m = ceph_msg_get(monc->m_subscribe_ack); break; - case CEPH_MSG_POOLOP_REPLY: case CEPH_MSG_STATFS_REPLY: return get_generic_reply(con, hdr, skip); case CEPH_MSG_AUTH_REPLY: diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 53299c7..41a4abc 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1035,10 +1035,11 @@ static void put_osd(struct ceph_osd *osd) { dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref), atomic_read(&osd->o_ref) - 1); - if (atomic_dec_and_test(&osd->o_ref) && osd->o_auth.authorizer) { + if (atomic_dec_and_test(&osd->o_ref)) { struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth; - ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer); + if (osd->o_auth.authorizer) + ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer); kfree(osd); } } @@ -1048,14 +1049,24 @@ static void put_osd(struct ceph_osd *osd) */ static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) { - dout("__remove_osd %p\n", osd); + dout("%s %p osd%d\n", __func__, osd, osd->o_osd); WARN_ON(!list_empty(&osd->o_requests)); WARN_ON(!list_empty(&osd->o_linger_requests)); - rb_erase(&osd->o_node, &osdc->osds); list_del_init(&osd->o_osd_lru); - ceph_con_close(&osd->o_con); - put_osd(osd); + rb_erase(&osd->o_node, &osdc->osds); + RB_CLEAR_NODE(&osd->o_node); +} + +static void remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) +{ + dout("%s %p osd%d\n", __func__, osd, osd->o_osd); + + if (!RB_EMPTY_NODE(&osd->o_node)) { + ceph_con_close(&osd->o_con); + __remove_osd(osdc, osd); + put_osd(osd); + } } static void remove_all_osds(struct ceph_osd_client *osdc) @@ -1065,7 +1076,7 @@ static void remove_all_osds(struct ceph_osd_client *osdc) while (!RB_EMPTY_ROOT(&osdc->osds)) { struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds), struct ceph_osd, o_node); - __remove_osd(osdc, osd); + remove_osd(osdc, osd); } mutex_unlock(&osdc->request_mutex); } @@ -1106,7 +1117,7 @@ static void remove_old_osds(struct ceph_osd_client *osdc) list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) { if (time_before(jiffies, osd->lru_ttl)) break; - __remove_osd(osdc, osd); + remove_osd(osdc, osd); } mutex_unlock(&osdc->request_mutex); } @@ -1121,8 +1132,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) dout("__reset_osd %p osd%d\n", osd, osd->o_osd); if (list_empty(&osd->o_requests) && list_empty(&osd->o_linger_requests)) { - __remove_osd(osdc, osd); - + remove_osd(osdc, osd); return -ENODEV; } @@ -1926,6 +1936,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc) { struct rb_node *p, *n; + dout("%s %p\n", __func__, osdc); for (p = rb_first(&osdc->osds); p; p = n) { struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node); diff --git a/net/core/dev.c b/net/core/dev.c index d030575..8f9710c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4024,6 +4024,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; NAPI_GRO_CB(skb)->udp_mark = 0; + NAPI_GRO_CB(skb)->gro_remcsum_start = 0; /* Setup for GRO checksum validation */ switch (skb->ip_summed) { @@ -5335,7 +5336,7 @@ EXPORT_SYMBOL(netdev_upper_dev_unlink); /** * netdev_bonding_info_change - Dispatch event about slave change * @dev: device - * @netdev_bonding_info: info to dispatch + * @bonding_info: info to dispatch * * Send NETDEV_BONDING_INFO to netdev notifiers with info. * The caller must hold the RTNL lock. diff --git a/net/core/filter.c b/net/core/filter.c index ec9baea..f6bdc2b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -531,7 +531,7 @@ do_pass: *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); break; - /* Unkown instruction. */ + /* Unknown instruction. */ default: goto err; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 9993412..f2aa73b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -614,8 +614,7 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue, { struct rps_map *map; cpumask_var_t mask; - size_t len = 0; - int i; + int i, len; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; @@ -626,17 +625,11 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue, for (i = 0; i < map->len; i++) cpumask_set_cpu(map->cpus[i], mask); - len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask); - if (PAGE_SIZE - len < 3) { - rcu_read_unlock(); - free_cpumask_var(mask); - return -EINVAL; - } + len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); rcu_read_unlock(); - free_cpumask_var(mask); - len += sprintf(buf + len, "\n"); - return len; + + return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t store_rps_map(struct netdev_rx_queue *queue, @@ -1090,8 +1083,7 @@ static ssize_t show_xps_map(struct netdev_queue *queue, struct xps_dev_maps *dev_maps; cpumask_var_t mask; unsigned long index; - size_t len = 0; - int i; + int i, len; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; @@ -1117,15 +1109,9 @@ static ssize_t show_xps_map(struct netdev_queue *queue, } rcu_read_unlock(); - len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask); - if (PAGE_SIZE - len < 3) { - free_cpumask_var(mask); - return -EINVAL; - } - + len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); free_cpumask_var(mask); - len += sprintf(buf + len, "\n"); - return len; + return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t store_xps_map(struct netdev_queue *queue, diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 9fa25b0..b4899f5b 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -97,7 +97,7 @@ * New xmit() return, do_div and misc clean up by Stephen Hemminger * <shemminger@osdl.org> 040923 * - * Randy Dunlap fixed u64 printk compiler waring + * Randy Dunlap fixed u64 printk compiler warning * * Remove FCS from BW calculation. Lennert Buytenhek <buytenh@wantstofly.org> * New time handling. Lennert Buytenhek <buytenh@wantstofly.org> 041213 diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5be499b..ab293a3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2162,7 +2162,14 @@ replay: } err = rtnl_configure_link(dev, ifm); if (err < 0) { - unregister_netdevice(dev); + if (ops->newlink) { + LIST_HEAD(list_kill); + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + } else { + unregister_netdevice(dev); + } goto out; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index eaa51dd..4334248 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -155,7 +155,7 @@ write_unlock: rcu_read_unlock(); len = min(sizeof(kbuf) - 1, *lenp); - len = cpumask_scnprintf(kbuf, len, mask); + len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask)); if (!len) { *lenp = 0; goto done; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d104ae1..f23dead 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -521,10 +521,13 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, struct device_node *phy_dn, *port_dn; bool phy_is_fixed = false; u32 phy_flags = 0; - int ret; + int mode, ret; port_dn = cd->port_dn[p->port]; - p->phy_interface = of_get_phy_mode(port_dn); + mode = of_get_phy_mode(port_dn); + if (mode < 0) + mode = PHY_INTERFACE_MODE_NA; + p->phy_interface = mode; phy_dn = of_parse_phandle(port_dn, "phy-handle", 0); if (of_phy_is_fixed_link(port_dn)) { @@ -559,6 +562,8 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, if (!p->phy) return -ENODEV; + /* Use already configured phy mode */ + p->phy_interface = p->phy->interface; phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link, p->phy_interface); } else { diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index f0b4a31d..3a8985c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1186,7 +1186,7 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) no_in_dev: /* Not loopback addresses on loopback should be preferred - in this case. It is importnat that lo is the first interface + in this case. It is important that lo is the first interface in dev_base list. */ for_each_netdev_rcu(net, dev) { diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 92ddea1..ff069f6 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -22,14 +22,18 @@ static LIST_HEAD(fou_list); struct fou { struct socket *sock; u8 protocol; + u8 flags; u16 port; struct udp_offload udp_offloads; struct list_head list; }; +#define FOU_F_REMCSUM_NOPARTIAL BIT(0) + struct fou_cfg { u16 type; u8 protocol; + u8 flags; struct udp_port_cfg udp_config; }; @@ -64,24 +68,20 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb) } static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, - void *data, size_t hdrlen, u8 ipproto) + void *data, size_t hdrlen, u8 ipproto, + bool nopartial) { __be16 *pd = data; size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); - if (skb->remcsum_offload) { - /* Already processed in GRO path */ - skb->remcsum_offload = 0; - return guehdr; - } - if (!pskb_may_pull(skb, plen)) return NULL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; - skb_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset); + skb_remcsum_process(skb, (void *)guehdr + hdrlen, + start, offset, nopartial); return guehdr; } @@ -142,7 +142,9 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) if (flags & GUE_PFLAG_REMCSUM) { guehdr = gue_remcsum(skb, guehdr, data + doffset, - hdrlen, guehdr->proto_ctype); + hdrlen, guehdr->proto_ctype, + !!(fou->flags & + FOU_F_REMCSUM_NOPARTIAL)); if (!guehdr) goto drop; @@ -214,7 +216,8 @@ out_unlock: static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, struct guehdr *guehdr, void *data, - size_t hdrlen, u8 ipproto) + size_t hdrlen, u8 ipproto, + struct gro_remcsum *grc, bool nopartial) { __be16 *pd = data; size_t start = ntohs(pd[0]); @@ -222,7 +225,7 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); if (skb->remcsum_offload) - return guehdr; + return NULL; if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; @@ -234,7 +237,8 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, return NULL; } - skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset); + skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen, + start, offset, grc, nopartial); skb->remcsum_offload = 1; @@ -254,6 +258,10 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, void *data; u16 doffset = 0; int flush = 1; + struct fou *fou = container_of(uoff, struct fou, udp_offloads); + struct gro_remcsum grc; + + skb_gro_remcsum_init(&grc); off = skb_gro_offset(skb); len = off + sizeof(*guehdr); @@ -295,7 +303,9 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, if (flags & GUE_PFLAG_REMCSUM) { guehdr = gue_gro_remcsum(skb, off, guehdr, data + doffset, hdrlen, - guehdr->proto_ctype); + guehdr->proto_ctype, &grc, + !!(fou->flags & + FOU_F_REMCSUM_NOPARTIAL)); if (!guehdr) goto out; @@ -345,6 +355,7 @@ out_unlock: rcu_read_unlock(); out: NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, &grc); return pp; } @@ -455,6 +466,7 @@ static int fou_create(struct net *net, struct fou_cfg *cfg, sk = sock->sk; + fou->flags = cfg->flags; fou->port = cfg->udp_config.local_udp_port; /* Initial for fou type */ @@ -541,6 +553,7 @@ static struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = { [FOU_ATTR_AF] = { .type = NLA_U8, }, [FOU_ATTR_IPPROTO] = { .type = NLA_U8, }, [FOU_ATTR_TYPE] = { .type = NLA_U8, }, + [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, }; static int parse_nl_config(struct genl_info *info, @@ -571,6 +584,9 @@ static int parse_nl_config(struct genl_info *info, if (info->attrs[FOU_ATTR_TYPE]) cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]); + if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL]) + cfg->flags |= FOU_F_REMCSUM_NOPARTIAL; + return 0; } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 53db2c3..ea82fd4 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -134,6 +134,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, struct tcp_sock *tp; struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; struct sock *child; + u32 end_seq; req->num_retrans = 0; req->num_timeout = 0; @@ -185,20 +186,35 @@ static bool tcp_fastopen_create_child(struct sock *sk, /* Queue the data carried in the SYN packet. We need to first * bump skb's refcnt because the caller will attempt to free it. + * Note that IPv6 might also have used skb_get() trick + * in tcp_v6_conn_request() to keep this SYN around (treq->pktopts) + * So we need to eventually get a clone of the packet, + * before inserting it in sk_receive_queue. * * XXX (TFO) - we honor a zero-payload TFO request for now, * (any reason not to?) but no need to queue the skb since * there is no data. How about SYN+FIN? */ - if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1) { - skb = skb_get(skb); - skb_dst_drop(skb); - __skb_pull(skb, tcp_hdr(skb)->doff * 4); - skb_set_owner_r(skb, child); - __skb_queue_tail(&child->sk_receive_queue, skb); - tp->syn_data_acked = 1; + end_seq = TCP_SKB_CB(skb)->end_seq; + if (end_seq != TCP_SKB_CB(skb)->seq + 1) { + struct sk_buff *skb2; + + if (unlikely(skb_shared(skb))) + skb2 = skb_clone(skb, GFP_ATOMIC); + else + skb2 = skb_get(skb); + + if (likely(skb2)) { + skb_dst_drop(skb2); + __skb_pull(skb2, tcp_hdrlen(skb)); + skb_set_owner_r(skb2, child); + __skb_queue_tail(&child->sk_receive_queue, skb2); + tp->syn_data_acked = 1; + } else { + end_seq = TCP_SKB_CB(skb)->seq + 1; + } } - tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq; sk->sk_data_ready(sk); bh_unlock_sock(child); sock_put(child); diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index c2a75c6..2379c1b 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -47,6 +47,10 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg) return; percpu_counter_destroy(&cg_proto->sockets_allocated); + + if (test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) + static_key_slow_dec(&memcg_socket_limit_enabled); + } EXPORT_SYMBOL(tcp_destroy_cgroup); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index d10f6f4..4915d82 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -402,6 +402,13 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff) } rcu_read_unlock(); + + if (skb->remcsum_offload) + skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM; + + skb->encapsulation = 1; + skb_set_inner_mac_header(skb, nhoff + sizeof(struct udphdr)); + return err; } @@ -410,9 +417,13 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff) const struct iphdr *iph = ip_hdr(skb); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); - if (uh->check) + if (uh->check) { + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr, iph->daddr, 0); + } else { + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; + } return udp_gro_complete(skb, nhoff); } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 2f780cb..f45d6db 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -172,7 +172,7 @@ static void __net_exit ip6_fl_purge(struct net *net) { int i; - spin_lock(&ip6_fl_lock); + spin_lock_bh(&ip6_fl_lock); for (i = 0; i <= FL_HASH_MASK; i++) { struct ip6_flowlabel *fl; struct ip6_flowlabel __rcu **flp; @@ -190,7 +190,7 @@ static void __net_exit ip6_fl_purge(struct net *net) flp = &fl->next; } } - spin_unlock(&ip6_fl_lock); + spin_unlock_bh(&ip6_fl_lock); } static struct ip6_flowlabel *fl_intern(struct net *net, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d33df4c..7deebf1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1273,7 +1273,7 @@ emsgsize: /* If this is the first and only packet and device * supports checksum offloading, let's use it. */ - if (!skb && + if (!skb && sk->sk_protocol == IPPROTO_UDP && length + fragheaderlen < mtu && rt->dst.dev->features & NETIF_F_V6_CSUM && !exthdrlen) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 98565ce..4688bd4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -141,7 +141,7 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) u32 *p = NULL; if (!(rt->dst.flags & DST_HOST)) - return NULL; + return dst_cow_metrics_generic(dst, old); peer = rt6_get_peer_create(rt); if (peer) { diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index a562769..ab889bb 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -161,9 +161,13 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff) const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); - if (uh->check) + if (uh->check) { + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr, &ipv6h->daddr, 0); + } else { + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; + } return udp_gro_complete(skb, nhoff); } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 265e190..c598f74 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -19,6 +19,7 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter_bridge/ebtables.h> #include <net/netfilter/nf_tables.h> static int nft_compat_chain_validate_dependency(const char *tablename, @@ -40,6 +41,7 @@ static int nft_compat_chain_validate_dependency(const char *tablename, union nft_entry { struct ipt_entry e4; struct ip6t_entry e6; + struct ebt_entry ebt; }; static inline void @@ -50,9 +52,9 @@ nft_compat_set_par(struct xt_action_param *par, void *xt, const void *xt_info) par->hotdrop = false; } -static void nft_target_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], - const struct nft_pktinfo *pkt) +static void nft_target_eval_xt(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) { void *info = nft_expr_priv(expr); struct xt_target *target = expr->ops->data; @@ -66,7 +68,7 @@ static void nft_target_eval(const struct nft_expr *expr, if (pkt->xt.hotdrop) ret = NF_DROP; - switch(ret) { + switch (ret) { case XT_CONTINUE: data[NFT_REG_VERDICT].verdict = NFT_CONTINUE; break; @@ -74,7 +76,41 @@ static void nft_target_eval(const struct nft_expr *expr, data[NFT_REG_VERDICT].verdict = ret; break; } - return; +} + +static void nft_target_eval_bridge(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + void *info = nft_expr_priv(expr); + struct xt_target *target = expr->ops->data; + struct sk_buff *skb = pkt->skb; + int ret; + + nft_compat_set_par((struct xt_action_param *)&pkt->xt, target, info); + + ret = target->target(skb, &pkt->xt); + + if (pkt->xt.hotdrop) + ret = NF_DROP; + + switch (ret) { + case EBT_ACCEPT: + data[NFT_REG_VERDICT].verdict = NF_ACCEPT; + break; + case EBT_DROP: + data[NFT_REG_VERDICT].verdict = NF_DROP; + break; + case EBT_CONTINUE: + data[NFT_REG_VERDICT].verdict = NFT_CONTINUE; + break; + case EBT_RETURN: + data[NFT_REG_VERDICT].verdict = NFT_RETURN; + break; + default: + data[NFT_REG_VERDICT].verdict = ret; + break; + } } static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = { @@ -100,6 +136,10 @@ nft_target_set_tgchk_param(struct xt_tgchk_param *par, entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; + case NFPROTO_BRIDGE: + entry->ebt.ethproto = proto; + entry->ebt.invflags = inv ? EBT_IPROTO : 0; + break; } par->entryinfo = entry; par->target = target; @@ -307,6 +347,10 @@ nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; + case NFPROTO_BRIDGE: + entry->ebt.ethproto = proto; + entry->ebt.invflags = inv ? EBT_IPROTO : 0; + break; } par->entryinfo = entry; par->match = match; @@ -490,6 +534,9 @@ nfnl_compat_get(struct sock *nfnl, struct sk_buff *skb, case AF_INET6: fmt = "ip6t_%s"; break; + case NFPROTO_BRIDGE: + fmt = "ebt_%s"; + break; default: pr_err("nft_compat: unsupported protocol %d\n", nfmsg->nfgen_family); @@ -663,13 +710,17 @@ nft_target_select_ops(const struct nft_ctx *ctx, nft_target->ops.type = &nft_target_type; nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); - nft_target->ops.eval = nft_target_eval; nft_target->ops.init = nft_target_init; nft_target->ops.destroy = nft_target_destroy; nft_target->ops.dump = nft_target_dump; nft_target->ops.validate = nft_target_validate; nft_target->ops.data = target; + if (family == NFPROTO_BRIDGE) + nft_target->ops.eval = nft_target_eval_bridge; + else + nft_target->ops.eval = nft_target_eval_xt; + list_add(&nft_target->head, &nft_target_list); return &nft_target->ops; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 6404a72..9615b8b 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -39,6 +39,7 @@ static void nft_lookup_eval(const struct nft_expr *expr, static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = { [NFTA_LOOKUP_SET] = { .type = NLA_STRING }, + [NFTA_LOOKUP_SET_ID] = { .type = NLA_U32 }, [NFTA_LOOKUP_SREG] = { .type = NLA_U32 }, [NFTA_LOOKUP_DREG] = { .type = NLA_U32 }, }; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index e2c348b..50ec42f 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -717,6 +717,8 @@ int ovs_flow_key_extract_userspace(const struct nlattr *attr, { int err; + memset(key, 0, OVS_SW_FLOW_KEY_METADATA_SIZE); + /* Extract metadata from netlink attributes. */ err = ovs_nla_get_flow_metadata(attr, key, log); if (err) diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 993281e..216f20b 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1516,7 +1516,7 @@ int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb) /* Called with ovs_mutex or RCU read lock. */ int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb) { - return ovs_nla_put_key(&flow->mask->key, &flow->key, + return ovs_nla_put_key(&flow->key, &flow->key, OVS_FLOW_ATTR_KEY, false, skb); } @@ -1746,7 +1746,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, struct sw_flow_key key; struct ovs_tunnel_info *tun_info; struct nlattr *a; - int err, start, opts_type; + int err = 0, start, opts_type; ovs_match_init(&match, &key, NULL); opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log); diff --git a/net/rds/cong.c b/net/rds/cong.c index e5b65ac..e6144b8 100644 --- a/net/rds/cong.c +++ b/net/rds/cong.c @@ -221,7 +221,21 @@ void rds_cong_queue_updates(struct rds_cong_map *map) list_for_each_entry(conn, &map->m_conn_list, c_map_item) { if (!test_and_set_bit(0, &conn->c_map_queued)) { rds_stats_inc(s_cong_update_queued); - rds_send_xmit(conn); + /* We cannot inline the call to rds_send_xmit() here + * for two reasons (both pertaining to a TCP transport): + * 1. When we get here from the receive path, we + * are already holding the sock_lock (held by + * tcp_v4_rcv()). So inlining calls to + * tcp_setsockopt and/or tcp_sendmsg will deadlock + * when it tries to get the sock_lock()) + * 2. Interrupts are masked so that we can mark the + * the port congested from both send and recv paths. + * (See comment around declaration of rdc_cong_lock). + * An attempt to get the sock_lock() here will + * therefore trigger warnings. + * Defer the xmit to rds_send_worker() instead. + */ + queue_delayed_work(rds_wq, &conn->c_send_w, 0); } } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 899d031..2274e72 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -348,7 +348,7 @@ config NET_SCH_PLUG comment "Classification" config NET_CLS - boolean + bool config NET_CLS_BASIC tristate "Elementary classification (BASIC)" diff --git a/net/switchdev/Kconfig b/net/switchdev/Kconfig index 1557545..86a47e1 100644 --- a/net/switchdev/Kconfig +++ b/net/switchdev/Kconfig @@ -3,7 +3,7 @@ # config NET_SWITCHDEV - boolean "Switch (and switch-ish) device support (EXPERIMENTAL)" + bool "Switch (and switch-ish) device support (EXPERIMENTAL)" depends on INET ---help--- This module provides glue between core networking code and device |
