diff options
Diffstat (limited to 'net')
200 files changed, 6447 insertions, 3934 deletions
diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c index 94a375c..9055d7b 100644 --- a/net/6lowpan/iphc.c +++ b/net/6lowpan/iphc.c @@ -613,6 +613,8 @@ EXPORT_SYMBOL_GPL(lowpan_header_compress); static int __init lowpan_module_init(void) { + request_module_nowait("ipv6"); + request_module_nowait("nhc_dest"); request_module_nowait("nhc_fragment"); request_module_nowait("nhc_hop"); diff --git a/net/Kconfig b/net/Kconfig index 57a7c5a..7021c1b 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -374,6 +374,13 @@ source "net/caif/Kconfig" source "net/ceph/Kconfig" source "net/nfc/Kconfig" +config LWTUNNEL + bool "Network light weight tunnels" + ---help--- + This feature provides an infrastructure to support light weight + tunnels like mpls. There is no netdevice associated with a light + weight tunnel endpoint. Tunnel encapsulation parameters are stored + with light weight tunnel state associated with fib routes. endif # if NET diff --git a/net/atm/br2684.c b/net/atm/br2684.c index cc78538..aa0047c 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -802,13 +802,10 @@ static int br2684_seq_show(struct seq_file *seq, void *v) (brdev->payload == p_bridged) ? "bridged" : "routed", brvcc->copies_failed, brvcc->copies_needed); #ifdef CONFIG_ATM_BR2684_IPFILTER -#define b1(var, byte) ((u8 *) &brvcc->filter.var)[byte] -#define bs(var) b1(var, 0), b1(var, 1), b1(var, 2), b1(var, 3) if (brvcc->filter.netmask != 0) - seq_printf(seq, " filter=%d.%d.%d.%d/" - "%d.%d.%d.%d\n", bs(prefix), bs(netmask)); -#undef bs -#undef b1 + seq_printf(seq, " filter=%pI4/%pI4\n", + &brvcc->filter.prefix, + &brvcc->filter.netmask); #endif /* CONFIG_ATM_BR2684_IPFILTER */ } return 0; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 2fb7b30..0ffe2e2 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -859,9 +859,22 @@ static int setup_netdev(struct l2cap_chan *chan, struct lowpan_dev **dev) SET_NETDEV_DEV(netdev, &chan->conn->hcon->hdev->dev); SET_NETDEV_DEVTYPE(netdev, &bt_type); + *dev = netdev_priv(netdev); + (*dev)->netdev = netdev; + (*dev)->hdev = chan->conn->hcon->hdev; + INIT_LIST_HEAD(&(*dev)->peers); + + spin_lock(&devices_lock); + INIT_LIST_HEAD(&(*dev)->list); + list_add_rcu(&(*dev)->list, &bt_6lowpan_devices); + spin_unlock(&devices_lock); + err = register_netdev(netdev); if (err < 0) { BT_INFO("register_netdev failed %d", err); + spin_lock(&devices_lock); + list_del_rcu(&(*dev)->list); + spin_unlock(&devices_lock); free_netdev(netdev); goto out; } @@ -871,16 +884,6 @@ static int setup_netdev(struct l2cap_chan *chan, struct lowpan_dev **dev) &chan->src, chan->src_type); set_bit(__LINK_STATE_PRESENT, &netdev->state); - *dev = netdev_priv(netdev); - (*dev)->netdev = netdev; - (*dev)->hdev = chan->conn->hcon->hdev; - INIT_LIST_HEAD(&(*dev)->peers); - - spin_lock(&devices_lock); - INIT_LIST_HEAD(&(*dev)->list); - list_add_rcu(&(*dev)->list, &bt_6lowpan_devices); - spin_unlock(&devices_lock); - return 0; out: diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index b8c794b..95d1a66 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -53,6 +53,11 @@ source "net/bluetooth/cmtp/Kconfig" source "net/bluetooth/hidp/Kconfig" +config BT_HS + bool "Bluetooth High Speed (HS) features" + depends on BT_BREDR + default y + config BT_LE bool "Bluetooth Low Energy (LE) features" depends on BT diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 29c12ae..2b15ae8 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -13,9 +13,10 @@ bluetooth_6lowpan-y := 6lowpan.o bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o lib.o \ - a2mp.o amp.o ecc.o hci_request.o mgmt_util.o + ecc.o hci_request.o mgmt_util.o bluetooth-$(CONFIG_BT_BREDR) += sco.o +bluetooth-$(CONFIG_BT_HS) += a2mp.o amp.o bluetooth-$(CONFIG_BT_DEBUGFS) += hci_debugfs.o bluetooth-$(CONFIG_BT_SELFTEST) += selftest.o diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 5a04eb1..5f123c3 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -16,6 +16,7 @@ #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> +#include "hci_request.h" #include "a2mp.h" #include "amp.h" @@ -286,11 +287,21 @@ static int a2mp_change_notify(struct amp_mgr *mgr, struct sk_buff *skb, return 0; } +static void read_local_amp_info_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + a2mp_send_getinfo_rsp(hdev); +} + static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { struct a2mp_info_req *req = (void *) skb->data; struct hci_dev *hdev; + struct hci_request hreq; + int err = 0; if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; @@ -311,7 +322,11 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, } set_bit(READ_LOC_AMP_INFO, &mgr->state); - hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL); + hci_req_init(&hreq, hdev); + hci_req_add(&hreq, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL); + err = hci_req_run(&hreq, read_local_amp_info_complete); + if (err < 0) + a2mp_send_getinfo_rsp(hdev); done: if (hdev) diff --git a/net/bluetooth/a2mp.h b/net/bluetooth/a2mp.h index 296f665..a4ff3ea 100644 --- a/net/bluetooth/a2mp.h +++ b/net/bluetooth/a2mp.h @@ -130,10 +130,29 @@ struct a2mp_physlink_rsp { #define A2MP_STATUS_SECURITY_VIOLATION 0x06 struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr); + +#if IS_ENABLED(CONFIG_BT_HS) int amp_mgr_put(struct amp_mgr *mgr); struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, struct sk_buff *skb); void a2mp_discover_amp(struct l2cap_chan *chan); +#else +static inline int amp_mgr_put(struct amp_mgr *mgr) +{ + return 0; +} + +static inline struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, + struct sk_buff *skb) +{ + return NULL; +} + +static inline void a2mp_discover_amp(struct l2cap_chan *chan) +{ +} +#endif + void a2mp_send_getinfo_rsp(struct hci_dev *hdev); void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status); void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status); diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index ee016f0..238ddd3 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -16,6 +16,7 @@ #include <net/bluetooth/hci_core.h> #include <crypto/hash.h> +#include "hci_request.h" #include "a2mp.h" #include "amp.h" @@ -220,10 +221,49 @@ int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type) return hmac_sha256(gamp_key, HCI_AMP_LINK_KEY_SIZE, "802b", 4, data); } +static void read_local_amp_assoc_complete(struct hci_dev *hdev, u8 status, + u16 opcode, struct sk_buff *skb) +{ + struct hci_rp_read_local_amp_assoc *rp = (void *)skb->data; + struct amp_assoc *assoc = &hdev->loc_assoc; + size_t rem_len, frag_len; + + BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); + + if (rp->status) + goto send_rsp; + + frag_len = skb->len - sizeof(*rp); + rem_len = __le16_to_cpu(rp->rem_len); + + if (rem_len > frag_len) { + BT_DBG("frag_len %zu rem_len %zu", frag_len, rem_len); + + memcpy(assoc->data + assoc->offset, rp->frag, frag_len); + assoc->offset += frag_len; + + /* Read other fragments */ + amp_read_loc_assoc_frag(hdev, rp->phy_handle); + + return; + } + + memcpy(assoc->data + assoc->offset, rp->frag, rem_len); + assoc->len = assoc->offset + rem_len; + assoc->offset = 0; + +send_rsp: + /* Send A2MP Rsp when all fragments are received */ + a2mp_send_getampassoc_rsp(hdev, rp->status); + a2mp_send_create_phy_link_req(hdev, rp->status); +} + void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle) { struct hci_cp_read_local_amp_assoc cp; struct amp_assoc *loc_assoc = &hdev->loc_assoc; + struct hci_request req; + int err = 0; BT_DBG("%s handle %d", hdev->name, phy_handle); @@ -231,12 +271,18 @@ void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle) cp.max_len = cpu_to_le16(hdev->amp_assoc_size); cp.len_so_far = cpu_to_le16(loc_assoc->offset); - hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + err = hci_req_run_skb(&req, read_local_amp_assoc_complete); + if (err < 0) + a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); } void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr) { struct hci_cp_read_local_amp_assoc cp; + struct hci_request req; + int err = 0; memset(&hdev->loc_assoc, 0, sizeof(struct amp_assoc)); memset(&cp, 0, sizeof(cp)); @@ -244,7 +290,11 @@ void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr) cp.max_len = cpu_to_le16(hdev->amp_assoc_size); set_bit(READ_LOC_AMP_ASSOC, &mgr->state); - hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + hci_req_run_skb(&req, read_local_amp_assoc_complete); + if (err < 0) + a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); } void amp_read_loc_assoc_final_data(struct hci_dev *hdev, @@ -252,6 +302,8 @@ void amp_read_loc_assoc_final_data(struct hci_dev *hdev, { struct hci_cp_read_local_amp_assoc cp; struct amp_mgr *mgr = hcon->amp_mgr; + struct hci_request req; + int err = 0; cp.phy_handle = hcon->handle; cp.len_so_far = cpu_to_le16(0); @@ -260,7 +312,25 @@ void amp_read_loc_assoc_final_data(struct hci_dev *hdev, set_bit(READ_LOC_AMP_ASSOC_FINAL, &mgr->state); /* Read Local AMP Assoc final link information data */ - hci_send_cmd(hdev, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); + hci_req_run_skb(&req, read_local_amp_assoc_complete); + if (err < 0) + a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); +} + +static void write_remote_amp_assoc_complete(struct hci_dev *hdev, u8 status, + u16 opcode, struct sk_buff *skb) +{ + struct hci_rp_write_remote_amp_assoc *rp = (void *)skb->data; + + BT_DBG("%s status 0x%2.2x phy_handle 0x%2.2x", + hdev->name, rp->status, rp->phy_handle); + + if (rp->status) + return; + + amp_write_rem_assoc_continue(hdev, rp->phy_handle); } /* Write AMP Assoc data fragments, returns true with last fragment written*/ @@ -270,6 +340,7 @@ static bool amp_write_rem_assoc_frag(struct hci_dev *hdev, struct hci_cp_write_remote_amp_assoc *cp; struct amp_mgr *mgr = hcon->amp_mgr; struct amp_ctrl *ctrl; + struct hci_request req; u16 frag_len, len; ctrl = amp_ctrl_lookup(mgr, hcon->remote_id); @@ -307,7 +378,9 @@ static bool amp_write_rem_assoc_frag(struct hci_dev *hdev, amp_ctrl_put(ctrl); - hci_send_cmd(hdev, HCI_OP_WRITE_REMOTE_AMP_ASSOC, len, cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_WRITE_REMOTE_AMP_ASSOC, sizeof(cp), &cp); + hci_req_run_skb(&req, write_remote_amp_assoc_complete); kfree(cp); @@ -344,10 +417,37 @@ void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle) amp_write_rem_assoc_frag(hdev, hcon); } +static void create_phylink_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + struct hci_cp_create_phy_link *cp; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_PHY_LINK); + if (!cp) + return; + + hci_dev_lock(hdev); + + if (status) { + struct hci_conn *hcon; + + hcon = hci_conn_hash_lookup_handle(hdev, cp->phy_handle); + if (hcon) + hci_conn_del(hcon); + } else { + amp_write_remote_assoc(hdev, cp->phy_handle); + } + + hci_dev_unlock(hdev); +} + void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, struct hci_conn *hcon) { struct hci_cp_create_phy_link cp; + struct hci_request req; cp.phy_handle = hcon->handle; @@ -360,13 +460,33 @@ void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, return; } - hci_send_cmd(hdev, HCI_OP_CREATE_PHY_LINK, sizeof(cp), &cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_CREATE_PHY_LINK, sizeof(cp), &cp); + hci_req_run(&req, create_phylink_complete); +} + +static void accept_phylink_complete(struct hci_dev *hdev, u8 status, + u16 opcode) +{ + struct hci_cp_accept_phy_link *cp; + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_ACCEPT_PHY_LINK); + if (!cp) + return; + + amp_write_remote_assoc(hdev, cp->phy_handle); } void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, struct hci_conn *hcon) { struct hci_cp_accept_phy_link cp; + struct hci_request req; cp.phy_handle = hcon->handle; @@ -379,7 +499,9 @@ void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, return; } - hci_send_cmd(hdev, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp); + hci_req_init(&req, hdev); + hci_req_add(&req, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp); + hci_req_run(&req, accept_phylink_complete); } void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon) diff --git a/net/bluetooth/amp.h b/net/bluetooth/amp.h index 7ea3db7..8848f81 100644 --- a/net/bluetooth/amp.h +++ b/net/bluetooth/amp.h @@ -44,6 +44,20 @@ void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, struct hci_conn *hcon); void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, struct hci_conn *hcon); + +#if IS_ENABLED(CONFIG_BT_HS) +void amp_create_logical_link(struct l2cap_chan *chan); +void amp_disconnect_logical_link(struct hci_chan *hchan); +#else +static inline void amp_create_logical_link(struct l2cap_chan *chan) +{ +} + +static inline void amp_disconnect_logical_link(struct hci_chan *hchan) +{ +} +#endif + void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle); void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle); void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon); diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index b0c6c6a..9a503387 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -100,9 +100,9 @@ static void cmtp_application_del(struct cmtp_session *session, struct cmtp_appli static struct cmtp_application *cmtp_application_get(struct cmtp_session *session, int pattern, __u16 value) { struct cmtp_application *app; - struct list_head *p, *n; + struct list_head *p; - list_for_each_safe(p, n, &session->applications) { + list_for_each(p, &session->applications) { app = list_entry(p, struct cmtp_application, list); switch (pattern) { case CMTP_MSGNUM: @@ -511,13 +511,13 @@ static int cmtp_proc_show(struct seq_file *m, void *v) struct capi_ctr *ctrl = m->private; struct cmtp_session *session = ctrl->driverdata; struct cmtp_application *app; - struct list_head *p, *n; + struct list_head *p; seq_printf(m, "%s\n\n", cmtp_procinfo(ctrl)); seq_printf(m, "addr %s\n", session->name); seq_printf(m, "ctrl %d\n", session->num); - list_for_each_safe(p, n, &session->applications) { + list_for_each(p, &session->applications) { app = list_entry(p, struct cmtp_application, list); seq_printf(m, "appl %d -> %d\n", app->appl, app->mapping); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2f8fb33..bc43b64 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2822,10 +2822,6 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, { struct hci_conn_params *params; - /* The conn params list only contains identity addresses */ - if (!hci_is_identity_address(addr, addr_type)) - return NULL; - list_for_each_entry(params, &hdev->le_conn_params, list) { if (bacmp(¶ms->addr, addr) == 0 && params->addr_type == addr_type) { @@ -2842,10 +2838,6 @@ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, { struct hci_conn_params *param; - /* The list only contains identity addresses */ - if (!hci_is_identity_address(addr, addr_type)) - return NULL; - list_for_each_entry(param, list, action) { if (bacmp(¶m->addr, addr) == 0 && param->addr_type == addr_type) @@ -2861,9 +2853,6 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, { struct hci_conn_params *params; - if (!hci_is_identity_address(addr, addr_type)) - return NULL; - params = hci_conn_params_lookup(hdev, addr, addr_type); if (params) return params; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 32363c2..218d7df 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -823,7 +823,7 @@ static void hci_cc_read_local_amp_info(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); if (rp->status) - goto a2mp_rsp; + return; hdev->amp_status = rp->amp_status; hdev->amp_total_bw = __le32_to_cpu(rp->total_bw); @@ -835,46 +835,6 @@ static void hci_cc_read_local_amp_info(struct hci_dev *hdev, hdev->amp_assoc_size = __le16_to_cpu(rp->max_assoc_size); hdev->amp_be_flush_to = __le32_to_cpu(rp->be_flush_to); hdev->amp_max_flush_to = __le32_to_cpu(rp->max_flush_to); - -a2mp_rsp: - a2mp_send_getinfo_rsp(hdev); -} - -static void hci_cc_read_local_amp_assoc(struct hci_dev *hdev, - struct sk_buff *skb) -{ - struct hci_rp_read_local_amp_assoc *rp = (void *) skb->data; - struct amp_assoc *assoc = &hdev->loc_assoc; - size_t rem_len, frag_len; - - BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - - if (rp->status) - goto a2mp_rsp; - - frag_len = skb->len - sizeof(*rp); - rem_len = __le16_to_cpu(rp->rem_len); - - if (rem_len > frag_len) { - BT_DBG("frag_len %zu rem_len %zu", frag_len, rem_len); - - memcpy(assoc->data + assoc->offset, rp->frag, frag_len); - assoc->offset += frag_len; - - /* Read other fragments */ - amp_read_loc_assoc_frag(hdev, rp->phy_handle); - - return; - } - - memcpy(assoc->data + assoc->offset, rp->frag, rem_len); - assoc->len = assoc->offset + rem_len; - assoc->offset = 0; - -a2mp_rsp: - /* Send A2MP Rsp when all fragments are received */ - a2mp_send_getampassoc_rsp(hdev, rp->status); - a2mp_send_create_phy_link_req(hdev, rp->status); } static void hci_cc_read_inq_rsp_tx_power(struct hci_dev *hdev, @@ -1409,20 +1369,6 @@ static void hci_cc_set_adv_param(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_unlock(hdev); } -static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev, - struct sk_buff *skb) -{ - struct hci_rp_write_remote_amp_assoc *rp = (void *) skb->data; - - BT_DBG("%s status 0x%2.2x phy_handle 0x%2.2x", - hdev->name, rp->status, rp->phy_handle); - - if (rp->status) - return; - - amp_write_rem_assoc_continue(hdev, rp->phy_handle); -} - static void hci_cc_read_rssi(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_rssi *rp = (void *) skb->data; @@ -1944,47 +1890,6 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) hci_dev_unlock(hdev); } -static void hci_cs_create_phylink(struct hci_dev *hdev, u8 status) -{ - struct hci_cp_create_phy_link *cp; - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_PHY_LINK); - if (!cp) - return; - - hci_dev_lock(hdev); - - if (status) { - struct hci_conn *hcon; - - hcon = hci_conn_hash_lookup_handle(hdev, cp->phy_handle); - if (hcon) - hci_conn_del(hcon); - } else { - amp_write_remote_assoc(hdev, cp->phy_handle); - } - - hci_dev_unlock(hdev); -} - -static void hci_cs_accept_phylink(struct hci_dev *hdev, u8 status) -{ - struct hci_cp_accept_phy_link *cp; - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - if (status) - return; - - cp = hci_sent_cmd_data(hdev, HCI_OP_ACCEPT_PHY_LINK); - if (!cp) - return; - - amp_write_remote_assoc(hdev, cp->phy_handle); -} - static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) { struct hci_cp_le_create_conn *cp; @@ -2998,10 +2903,6 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_read_clock(hdev, skb); break; - case HCI_OP_READ_LOCAL_AMP_ASSOC: - hci_cc_read_local_amp_assoc(hdev, skb); - break; - case HCI_OP_READ_INQ_RSP_TX_POWER: hci_cc_read_inq_rsp_tx_power(hdev, skb); break; @@ -3106,10 +3007,6 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_set_adv_param(hdev, skb); break; - case HCI_OP_WRITE_REMOTE_AMP_ASSOC: - hci_cc_write_remote_amp_assoc(hdev, skb); - break; - case HCI_OP_READ_RSSI: hci_cc_read_rssi(hdev, skb); break; @@ -3193,14 +3090,6 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cs_setup_sync_conn(hdev, ev->status); break; - case HCI_OP_CREATE_PHY_LINK: - hci_cs_create_phylink(hdev, ev->status); - break; - - case HCI_OP_ACCEPT_PHY_LINK: - hci_cs_accept_phylink(hdev, ev->status); - break; - case HCI_OP_SNIFF_MODE: hci_cs_sniff_mode(hdev, ev->status); break; @@ -4399,6 +4288,23 @@ unlock: hci_dev_unlock(hdev); } +#if IS_ENABLED(CONFIG_BT_HS) +static void hci_chan_selected_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_ev_channel_selected *ev = (void *)skb->data; + struct hci_conn *hcon; + + BT_DBG("%s handle 0x%2.2x", hdev->name, ev->phy_handle); + + skb_pull(skb, sizeof(*ev)); + + hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); + if (!hcon) + return; + + amp_read_loc_assoc_final_data(hdev, hcon); +} + static void hci_phy_link_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { @@ -4522,6 +4428,7 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, hci_dev_unlock(hdev); } +#endif static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { @@ -5206,22 +5113,6 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) } } -static void hci_chan_selected_evt(struct hci_dev *hdev, struct sk_buff *skb) -{ - struct hci_ev_channel_selected *ev = (void *) skb->data; - struct hci_conn *hcon; - - BT_DBG("%s handle 0x%2.2x", hdev->name, ev->phy_handle); - - skb_pull(skb, sizeof(*ev)); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - return; - - amp_read_loc_assoc_final_data(hdev, hcon); -} - static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 event, struct sk_buff *skb) { @@ -5442,14 +5333,15 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) hci_le_meta_evt(hdev, skb); break; - case HCI_EV_CHANNEL_SELECTED: - hci_chan_selected_evt(hdev, skb); - break; - case HCI_EV_REMOTE_OOB_DATA_REQUEST: hci_remote_oob_data_request_evt(hdev, skb); break; +#if IS_ENABLED(CONFIG_BT_HS) + case HCI_EV_CHANNEL_SELECTED: + hci_chan_selected_evt(hdev, skb); + break; + case HCI_EV_PHY_LINK_COMPLETE: hci_phy_link_complete_evt(hdev, skb); break; @@ -5465,6 +5357,7 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) case HCI_EV_DISCONN_PHY_LINK_COMPLETE: hci_disconn_phylink_complete_evt(hdev, skb); break; +#endif case HCI_EV_NUM_COMP_BLOCKS: hci_num_comp_blocks_evt(hdev, skb); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 2442877..586b3d5 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1054,18 +1054,23 @@ static void l2cap_sock_kill(struct sock *sk) sock_put(sk); } -static int __l2cap_wait_ack(struct sock *sk) +static int __l2cap_wait_ack(struct sock *sk, struct l2cap_chan *chan) { - struct l2cap_chan *chan = l2cap_pi(sk)->chan; DECLARE_WAITQUEUE(wait, current); int err = 0; - int timeo = HZ/5; + int timeo = L2CAP_WAIT_ACK_POLL_PERIOD; + /* Timeout to prevent infinite loop */ + unsigned long timeout = jiffies + L2CAP_WAIT_ACK_TIMEOUT; add_wait_queue(sk_sleep(sk), &wait); set_current_state(TASK_INTERRUPTIBLE); - while (chan->unacked_frames > 0 && chan->conn) { + do { + BT_DBG("Waiting for %d ACKs, timeout %04d ms", + chan->unacked_frames, time_after(jiffies, timeout) ? 0 : + jiffies_to_msecs(timeout - jiffies)); + if (!timeo) - timeo = HZ/5; + timeo = L2CAP_WAIT_ACK_POLL_PERIOD; if (signal_pending(current)) { err = sock_intr_errno(timeo); @@ -1080,7 +1085,15 @@ static int __l2cap_wait_ack(struct sock *sk) err = sock_error(sk); if (err) break; - } + + if (time_after(jiffies, timeout)) { + err = -ENOLINK; + break; + } + + } while (chan->unacked_frames > 0 && + chan->state == BT_CONNECTED); + set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return err; @@ -1098,7 +1111,12 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) if (!sk) return 0; + /* prevent sk structure from being freed whilst unlocked */ + sock_hold(sk); + chan = l2cap_pi(sk)->chan; + /* prevent chan structure from being freed whilst unlocked */ + l2cap_chan_hold(chan); conn = chan->conn; BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); @@ -1110,8 +1128,10 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) lock_sock(sk); if (!sk->sk_shutdown) { - if (chan->mode == L2CAP_MODE_ERTM) - err = __l2cap_wait_ack(sk); + if (chan->mode == L2CAP_MODE_ERTM && + chan->unacked_frames > 0 && + chan->state == BT_CONNECTED) + err = __l2cap_wait_ack(sk, chan); sk->sk_shutdown = SHUTDOWN_MASK; @@ -1134,6 +1154,11 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) if (conn) mutex_unlock(&conn->chan_lock); + l2cap_chan_put(chan); + sock_put(sk); + + BT_DBG("err: %d", err); + return err; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 92720f3..e435438 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -6226,6 +6226,17 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, else auto_conn = HCI_AUTO_CONN_REPORT; + /* Kernel internally uses conn_params with resolvable private + * address, but Add Device allows only identity addresses. + * Make sure it is enforced before calling + * hci_conn_params_lookup. + */ + if (!hci_is_identity_address(&cp->addr.bdaddr, addr_type)) { + err = cmd->cmd_complete(cmd, MGMT_STATUS_INVALID_PARAMS); + mgmt_pending_remove(cmd); + goto unlock; + } + /* If the connection parameters don't exist for this device, * they will be created and configured with defaults. */ @@ -6340,6 +6351,18 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, else addr_type = ADDR_LE_DEV_RANDOM; + /* Kernel internally uses conn_params with resolvable private + * address, but Remove Device allows only identity addresses. + * Make sure it is enforced before calling + * hci_conn_params_lookup. + */ + if (!hci_is_identity_address(&cp->addr.bdaddr, addr_type)) { + err = cmd->cmd_complete(cmd, + MGMT_STATUS_INVALID_PARAMS); + mgmt_pending_remove(cmd); + goto unlock; + } + params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, addr_type); if (!params) { diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 4ff77a1..0aa8f5c 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -339,6 +339,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_bridge_getlink = br_getlink, .ndo_bridge_setlink = br_setlink, .ndo_bridge_dellink = br_dellink, + .ndo_features_check = passthru_features_check, }; static void br_dev_free(struct net_device *dev) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index a538cb1..45e4757 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -281,6 +281,7 @@ void br_dev_delete(struct net_device *dev, struct list_head *head) br_fdb_delete_by_port(br, NULL, 0, 1); br_vlan_flush(br); + br_multicast_dev_del(br); del_timer_sync(&br->gc_timer); br_sysfs_delbr(br->dev); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index c943219..d747275 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -85,6 +85,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, memset(&e, 0, sizeof(e)); e.ifindex = port->dev->ifindex; e.state = p->state; + e.vid = p->addr.vid; if (p->addr.proto == htons(ETH_P_IP)) e.addr.u.ip4 = p->addr.u.ip4; #if IS_ENABLED(CONFIG_IPV6) @@ -230,7 +231,7 @@ errout: } void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, - struct br_ip *group, int type) + struct br_ip *group, int type, u8 state) { struct br_mdb_entry entry; @@ -241,9 +242,78 @@ void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, #if IS_ENABLED(CONFIG_IPV6) entry.addr.u.ip6 = group->u.ip6; #endif + entry.state = state; + entry.vid = group->vid; __br_mdb_notify(dev, &entry, type); } +static int nlmsg_populate_rtr_fill(struct sk_buff *skb, + struct net_device *dev, + int ifindex, u32 pid, + u32 seq, int type, unsigned int flags) +{ + struct br_port_msg *bpm; + struct nlmsghdr *nlh; + struct nlattr *nest; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + bpm = nlmsg_data(nlh); + memset(bpm, 0, sizeof(*bpm)); + bpm->family = AF_BRIDGE; + bpm->ifindex = dev->ifindex; + nest = nla_nest_start(skb, MDBA_ROUTER); + if (!nest) + goto cancel; + + if (nla_put_u32(skb, MDBA_ROUTER_PORT, ifindex)) + goto end; + + nla_nest_end(skb, nest); + nlmsg_end(skb, nlh); + return 0; + +end: + nla_nest_end(skb, nest); +cancel: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + +static inline size_t rtnl_rtr_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct br_port_msg)) + + nla_total_size(sizeof(__u32)); +} + +void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, + int type) +{ + struct net *net = dev_net(dev); + struct sk_buff *skb; + int err = -ENOBUFS; + int ifindex; + + ifindex = port ? port->dev->ifindex : 0; + skb = nlmsg_new(rtnl_rtr_nlmsg_size(), GFP_ATOMIC); + if (!skb) + goto errout; + + err = nlmsg_populate_rtr_fill(skb, dev, ifindex, 0, 0, type, NTF_SELF); + if (err < 0) { + kfree_skb(skb); + goto errout; + } + + rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_ATOMIC); + return; + +errout: + rtnl_set_sk_err(net, RTNLGRP_MDB, err); +} + static bool is_valid_mdb_entry(struct br_mdb_entry *entry) { if (entry->ifindex == 0) @@ -263,6 +333,8 @@ static bool is_valid_mdb_entry(struct br_mdb_entry *entry) return false; if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) return false; + if (entry->vid >= VLAN_VID_MASK) + return false; return true; } @@ -374,6 +446,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, return -EINVAL; memset(&ip, 0, sizeof(ip)); + ip.vid = entry->vid; ip.proto = entry->addr.proto; if (ip.proto == htons(ETH_P_IP)) ip.u.ip4 = entry->addr.u.ip4; @@ -391,8 +464,11 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); + unsigned short vid = VLAN_N_VID; + struct net_device *dev, *pdev; struct br_mdb_entry *entry; - struct net_device *dev; + struct net_bridge_port *p; + struct net_port_vlans *pv; struct net_bridge *br; int err; @@ -402,9 +478,32 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) br = netdev_priv(dev); - err = __br_mdb_add(net, br, entry); - if (!err) - __br_mdb_notify(dev, entry, RTM_NEWMDB); + /* If vlan filtering is enabled and VLAN is not specified + * install mdb entry on all vlans configured on the port. + */ + pdev = __dev_get_by_index(net, entry->ifindex); + if (!pdev) + return -ENODEV; + + p = br_port_get_rtnl(pdev); + if (!p || p->br != br || p->state == BR_STATE_DISABLED) + return -EINVAL; + + pv = nbp_get_vlan_info(p); + if (br_vlan_enabled(br) && pv && entry->vid == 0) { + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + entry->vid = vid; + err = __br_mdb_add(net, br, entry); + if (err) + break; + __br_mdb_notify(dev, entry, RTM_NEWMDB); + } + } else { + err = __br_mdb_add(net, br, entry); + if (!err) + __br_mdb_notify(dev, entry, RTM_NEWMDB); + } + return err; } @@ -421,6 +520,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) return -EINVAL; memset(&ip, 0, sizeof(ip)); + ip.vid = entry->vid; ip.proto = entry->addr.proto; if (ip.proto == htons(ETH_P_IP)) ip.u.ip4 = entry->addr.u.ip4; @@ -465,8 +565,12 @@ unlock: static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) { - struct net_device *dev; + struct net *net = sock_net(skb->sk); + unsigned short vid = VLAN_N_VID; + struct net_device *dev, *pdev; struct br_mdb_entry *entry; + struct net_bridge_port *p; + struct net_port_vlans *pv; struct net_bridge *br; int err; @@ -476,9 +580,31 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) br = netdev_priv(dev); - err = __br_mdb_del(br, entry); - if (!err) - __br_mdb_notify(dev, entry, RTM_DELMDB); + /* If vlan filtering is enabled and VLAN is not specified + * delete mdb entry on all vlans configured on the port. + */ + pdev = __dev_get_by_index(net, entry->ifindex); + if (!pdev) + return -ENODEV; + + p = br_port_get_rtnl(pdev); + if (!p || p->br != br || p->state == BR_STATE_DISABLED) + return -EINVAL; + + pv = nbp_get_vlan_info(p); + if (br_vlan_enabled(br) && pv && entry->vid == 0) { + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + entry->vid = vid; + err = __br_mdb_del(br, entry); + if (!err) + __br_mdb_notify(dev, entry, RTM_DELMDB); + } + } else { + err = __br_mdb_del(br, entry); + if (!err) + __br_mdb_notify(dev, entry, RTM_DELMDB); + } + return err; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 0b39dcc..0752796 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -283,6 +283,8 @@ static void br_multicast_del_pg(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); + br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB, + p->state); call_rcu_bh(&p->rcu, br_multicast_free_pg); if (!mp->ports && !mp->mglist && @@ -704,7 +706,7 @@ static int br_multicast_add_group(struct net_bridge *br, if (unlikely(!p)) goto err; rcu_assign_pointer(*pp, p); - br_mdb_notify(br->dev, port, group, RTM_NEWMDB); + br_mdb_notify(br->dev, port, group, RTM_NEWMDB, MDB_TEMPORARY); found: mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -764,6 +766,7 @@ static void br_multicast_router_expired(unsigned long data) goto out; hlist_del_init_rcu(&port->rlist); + br_rtr_notify(br->dev, port, RTM_DELMDB); out: spin_unlock(&br->multicast_lock); @@ -924,6 +927,15 @@ void br_multicast_add_port(struct net_bridge_port *port) void br_multicast_del_port(struct net_bridge_port *port) { + struct net_bridge *br = port->br; + struct net_bridge_port_group *pg; + struct hlist_node *n; + + /* Take care of the remaining groups, only perm ones should be left */ + spin_lock_bh(&br->multicast_lock); + hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) + br_multicast_del_pg(br, pg); + spin_unlock_bh(&br->multicast_lock); del_timer_sync(&port->multicast_router_timer); } @@ -963,10 +975,13 @@ void br_multicast_disable_port(struct net_bridge_port *port) spin_lock(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) - br_multicast_del_pg(br, pg); + if (pg->state == MDB_TEMPORARY) + br_multicast_del_pg(br, pg); - if (!hlist_unhashed(&port->rlist)) + if (!hlist_unhashed(&port->rlist)) { hlist_del_init_rcu(&port->rlist); + br_rtr_notify(br->dev, port, RTM_DELMDB); + } del_timer(&port->multicast_router_timer); del_timer(&port->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) @@ -1204,6 +1219,7 @@ static void br_multicast_add_router(struct net_bridge *br, hlist_add_behind_rcu(&port->rlist, slot); else hlist_add_head_rcu(&port->rlist, &br->router_list); + br_rtr_notify(br->dev, port, RTM_NEWMDB); } static void br_multicast_mark_router(struct net_bridge *br, @@ -1437,7 +1453,8 @@ br_multicast_leave_group(struct net_bridge *br, hlist_del_init(&p->mglist); del_timer(&p->timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - br_mdb_notify(br->dev, port, group, RTM_DELMDB); + br_mdb_notify(br->dev, port, group, RTM_DELMDB, + p->state); if (!mp->ports && !mp->mglist && netif_running(br->dev)) @@ -1754,12 +1771,6 @@ void br_multicast_open(struct net_bridge *br) void br_multicast_stop(struct net_bridge *br) { - struct net_bridge_mdb_htable *mdb; - struct net_bridge_mdb_entry *mp; - struct hlist_node *n; - u32 ver; - int i; - del_timer_sync(&br->multicast_router_timer); del_timer_sync(&br->ip4_other_query.timer); del_timer_sync(&br->ip4_own_query.timer); @@ -1767,6 +1778,15 @@ void br_multicast_stop(struct net_bridge *br) del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif +} + +void br_multicast_dev_del(struct net_bridge *br) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct hlist_node *n; + u32 ver; + int i; spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); @@ -1834,8 +1854,10 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) p->multicast_router = val; err = 0; - if (val < 2 && !hlist_unhashed(&p->rlist)) + if (val < 2 && !hlist_unhashed(&p->rlist)) { hlist_del_init_rcu(&p->rlist); + br_rtr_notify(br->dev, p, RTM_DELMDB); + } if (val == 1) break; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index c8b9bcf..0a6f095 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -49,9 +49,9 @@ static struct ctl_table_header *brnf_sysctl_header; static int brnf_call_iptables __read_mostly = 1; static int brnf_call_ip6tables __read_mostly = 1; static int brnf_call_arptables __read_mostly = 1; -static int brnf_filter_vlan_tagged __read_mostly = 0; -static int brnf_filter_pppoe_tagged __read_mostly = 0; -static int brnf_pass_vlan_indev __read_mostly = 0; +static int brnf_filter_vlan_tagged __read_mostly; +static int brnf_filter_pppoe_tagged __read_mostly; +static int brnf_pass_vlan_indev __read_mostly; #else #define brnf_call_iptables 1 #define brnf_call_ip6tables 1 @@ -284,7 +284,7 @@ int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb) nf_bridge->neigh_header, ETH_HLEN-ETH_ALEN); /* tell br_dev_xmit to continue with forwarding */ - nf_bridge->mask |= BRNF_BRIDGED_DNAT; + nf_bridge->bridged_dnat = 1; /* FIXME Need to refragment */ ret = neigh->output(neigh, skb); } @@ -356,7 +356,7 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } - nf_bridge->mask &= ~BRNF_NF_BRIDGE_PREROUTING; + nf_bridge->in_prerouting = 0; if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -444,7 +444,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb) nf_bridge->pkt_otherhost = true; } - nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING; + nf_bridge->in_prerouting = 1; nf_bridge->physindev = skb->dev; skb->dev = brnf_get_logical_dev(skb, skb->dev); @@ -850,10 +850,8 @@ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - if (skb->nf_bridge && - !(skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)) { + if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) return NF_STOP; - } return NF_ACCEPT; } @@ -872,7 +870,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); skb_pull(skb, ETH_HLEN); - nf_bridge->mask &= ~BRNF_BRIDGED_DNAT; + nf_bridge->bridged_dnat = 0; BUILD_BUG_ON(sizeof(nf_bridge->neigh_header) != (ETH_HLEN - ETH_ALEN)); @@ -887,7 +885,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) static int br_nf_dev_xmit(struct sk_buff *skb) { - if (skb->nf_bridge && (skb->nf_bridge->mask & BRNF_BRIDGED_DNAT)) { + if (skb->nf_bridge && skb->nf_bridge->bridged_dnat) { br_nf_pre_routing_finish_bridge_slow(skb); return 1; } diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 13b7d1e..77383bf 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -174,7 +174,7 @@ static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb) skb->pkt_type = PACKET_OTHERHOST; nf_bridge->pkt_otherhost = false; } - nf_bridge->mask &= ~BRNF_NF_BRIDGE_PREROUTING; + nf_bridge->in_prerouting = 0; if (br_nf_ipv6_daddr_was_changed(skb, nf_bridge)) { skb_dst_drop(skb); v6ops->route_input(skb); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4d74a06..0f2408f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -166,8 +166,6 @@ static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start, sizeof(vinfo), &vinfo)) goto nla_put_failure; - vinfo.flags &= ~BRIDGE_VLAN_INFO_RANGE_BEGIN; - vinfo.vid = vid_end; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, @@ -730,6 +728,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, + [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -777,6 +776,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br_stp_set_bridge_priority(br, priority); } + if (data[IFLA_BR_VLAN_FILTERING]) { + u8 vlan_filter = nla_get_u8(data[IFLA_BR_VLAN_FILTERING]); + + err = __br_vlan_filter_toggle(br, vlan_filter); + if (err) + return err; + } + return 0; } @@ -788,6 +795,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */ 0; } @@ -800,13 +808,15 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u32 ageing_time = jiffies_to_clock_t(br->ageing_time); u32 stp_enabled = br->stp_enabled; u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; + u8 vlan_enabled = br_vlan_enabled(br); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) || nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || - nla_put_u16(skb, IFLA_BR_PRIORITY, priority)) + nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || + nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled)) return -EMSGSIZE; return 0; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 8b21146..3d95647 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -466,6 +466,7 @@ void br_multicast_disable_port(struct net_bridge_port *port); void br_multicast_init(struct net_bridge *br); void br_multicast_open(struct net_bridge *br); void br_multicast_stop(struct net_bridge *br); +void br_multicast_dev_del(struct net_bridge *br); void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, struct sk_buff *skb); void br_multicast_forward(struct net_bridge_mdb_entry *mdst, @@ -488,7 +489,9 @@ br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group, void br_mdb_init(void); void br_mdb_uninit(void); void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, - struct br_ip *group, int type); + struct br_ip *group, int type, u8 state); +void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, + int type); #define mlock_dereference(X, br) \ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) @@ -565,6 +568,10 @@ static inline void br_multicast_stop(struct net_bridge *br) { } +static inline void br_multicast_dev_del(struct net_bridge *br) +{ +} + static inline void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, struct sk_buff *skb) { @@ -607,6 +614,7 @@ int br_vlan_delete(struct net_bridge *br, u16 vid); void br_vlan_flush(struct net_bridge *br); bool br_vlan_find(struct net_bridge *br, u16 vid); void br_recalculate_fwd_mask(struct net_bridge *br); +int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); int br_vlan_set_proto(struct net_bridge *br, unsigned long val); int br_vlan_init(struct net_bridge *br); @@ -764,6 +772,12 @@ static inline int br_vlan_enabled(struct net_bridge *br) { return 0; } + +static inline int __br_vlan_filter_toggle(struct net_bridge *br, + unsigned long val) +{ + return -EOPNOTSUPP; +} #endif struct nf_br_ops { diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 0d41f81..3cef689 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -468,21 +468,27 @@ void br_recalculate_fwd_mask(struct net_bridge *br) ~(1u << br->group_addr[5]); } -int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) +int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) { - if (!rtnl_trylock()) - return restart_syscall(); - if (br->vlan_enabled == val) - goto unlock; + return 0; br->vlan_enabled = val; br_manage_promisc(br); recalculate_group_addr(br); br_recalculate_fwd_mask(br); -unlock: + return 0; +} + +int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) +{ + if (!rtnl_trylock()) + return restart_syscall(); + + __br_vlan_filter_toggle(br, val); rtnl_unlock(); + return 0; } diff --git a/net/core/Makefile b/net/core/Makefile index fec0856..086b01f 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -23,3 +23,4 @@ obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o +obj-$(CONFIG_LWTUNNEL) += lwtunnel.o diff --git a/net/core/dev.c b/net/core/dev.c index a8e4dd4..4870c35 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3061,6 +3061,16 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) else skb_dst_force(skb); +#ifdef CONFIG_NET_SWITCHDEV + /* Don't forward if offload device already forwarded */ + if (skb->offload_fwd_mark && + skb->offload_fwd_mark == dev->offload_fwd_mark) { + consume_skb(skb); + rc = NET_XMIT_SUCCESS; + goto out; + } +#endif + txq = netdev_pick_tx(dev, skb, accel_priv); q = rcu_dereference_bh(txq->qdisc); @@ -3645,7 +3655,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, qdisc_skb_cb(skb)->pkt_len = skb->len; skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); - qdisc_bstats_update_cpu(cl->q, skb); + qdisc_bstats_cpu_update(cl->q, skb); switch (tc_classify(skb, cl, &cl_res)) { case TC_ACT_OK: @@ -3653,7 +3663,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, skb->tc_index = TC_H_MIN(cl_res.classid); break; case TC_ACT_SHOT: - qdisc_qstats_drop_cpu(cl->q); + qdisc_qstats_cpu_drop(cl->q); case TC_ACT_STOLEN: case TC_ACT_QUEUED: kfree_skb(skb); @@ -4985,7 +4995,7 @@ EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu); * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold either hold the * RTNL lock or its own locking that guarantees that the neighbour lower - * list will remain unchainged. + * list will remain unchanged. */ void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter) @@ -5040,7 +5050,7 @@ EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); * Gets the next netdev_adjacent from the dev's lower neighbour * list, starting from iter position. The caller must hold RTNL lock or * its own locking that guarantees that the neighbour lower - * list will remain unchainged. + * list will remain unchanged. */ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { @@ -6075,6 +6085,26 @@ int dev_get_phys_port_name(struct net_device *dev, EXPORT_SYMBOL(dev_get_phys_port_name); /** + * dev_change_proto_down - update protocol port state information + * @dev: device + * @proto_down: new value + * + * This info can be used by switch drivers to set the phys state of the + * port. + */ +int dev_change_proto_down(struct net_device *dev, bool proto_down) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_change_proto_down) + return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_change_proto_down(dev, proto_down); +} +EXPORT_SYMBOL(dev_change_proto_down); + +/** * dev_new_index - allocate an ifindex * @net: the applicable net namespace * @@ -7639,7 +7669,7 @@ static int __init net_dev_init(void) open_softirq(NET_RX_SOFTIRQ, net_rx_action); hotcpu_notifier(dev_cpu_callback, 0); - dst_init(); + dst_subsys_init(); rc = 0; out: return rc; diff --git a/net/core/dst.c b/net/core/dst.c index 002144be..f8694d1 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -22,6 +22,7 @@ #include <linux/prefetch.h> #include <net/dst.h> +#include <net/dst_metadata.h> /* * Theory of operations: @@ -158,19 +159,10 @@ const u32 dst_default_metrics[RTAX_MAX + 1] = { [RTAX_MAX] = 0xdeadbeef, }; - -void *dst_alloc(struct dst_ops *ops, struct net_device *dev, - int initial_ref, int initial_obsolete, unsigned short flags) +void dst_init(struct dst_entry *dst, struct dst_ops *ops, + struct net_device *dev, int initial_ref, int initial_obsolete, + unsigned short flags) { - struct dst_entry *dst; - - if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { - if (ops->gc(ops)) - return NULL; - } - dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); - if (!dst) - return NULL; dst->child = NULL; dst->dev = dev; if (dev) @@ -200,6 +192,25 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst->next = NULL; if (!(flags & DST_NOCOUNT)) dst_entries_add(ops, 1); +} +EXPORT_SYMBOL(dst_init); + +void *dst_alloc(struct dst_ops *ops, struct net_device *dev, + int initial_ref, int initial_obsolete, unsigned short flags) +{ + struct dst_entry *dst; + + if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { + if (ops->gc(ops)) + return NULL; + } + + dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); + if (!dst) + return NULL; + + dst_init(dst, ops, dev, initial_ref, initial_obsolete, flags); + return dst; } EXPORT_SYMBOL(dst_alloc); @@ -248,7 +259,11 @@ again: dst->ops->destroy(dst); if (dst->dev) dev_put(dst->dev); - kmem_cache_free(dst->ops->kmem_cachep, dst); + + if (dst->flags & DST_METADATA) + kfree(dst); + else + kmem_cache_free(dst->ops->kmem_cachep, dst); dst = child; if (dst) { @@ -329,6 +344,70 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) } EXPORT_SYMBOL(__dst_destroy_metrics_generic); +static struct dst_ops md_dst_ops = { + .family = AF_UNSPEC, +}; + +static int dst_md_discard_sk(struct sock *sk, struct sk_buff *skb) +{ + WARN_ONCE(1, "Attempting to call output on metadata dst\n"); + kfree_skb(skb); + return 0; +} + +static int dst_md_discard(struct sk_buff *skb) +{ + WARN_ONCE(1, "Attempting to call input on metadata dst\n"); + kfree_skb(skb); + return 0; +} + +static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen) +{ + struct dst_entry *dst; + + dst = &md_dst->dst; + dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE, + DST_METADATA | DST_NOCACHE | DST_NOCOUNT); + + dst->input = dst_md_discard; + dst->output = dst_md_discard_sk; + + memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); + md_dst->opts_len = optslen; +} + +struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags) +{ + struct metadata_dst *md_dst; + + md_dst = kmalloc(sizeof(*md_dst) + optslen, flags); + if (!md_dst) + return NULL; + + __metadata_dst_init(md_dst, optslen); + + return md_dst; +} +EXPORT_SYMBOL_GPL(metadata_dst_alloc); + +struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags) +{ + int cpu; + struct metadata_dst __percpu *md_dst; + + md_dst = __alloc_percpu_gfp(sizeof(struct metadata_dst) + optslen, + __alignof__(struct metadata_dst), flags); + if (!md_dst) + return NULL; + + for_each_possible_cpu(cpu) + __metadata_dst_init(per_cpu_ptr(md_dst, cpu), optslen); + + return md_dst; +} +EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); + /* Dirty hack. We did it in 2.2 (in __dst_free), * we have _very_ good reasons not to repeat * this mistake in 2.3, but we have no choice @@ -393,7 +472,7 @@ static struct notifier_block dst_dev_notifier = { .priority = -10, /* must be called after other network notifiers */ }; -void __init dst_init(void) +void __init dst_subsys_init(void) { register_netdevice_notifier(&dst_dev_notifier); } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 9a12668..ae8306e 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -16,6 +16,7 @@ #include <net/net_namespace.h> #include <net/sock.h> #include <net/fib_rules.h> +#include <net/ip_tunnels.h> int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table, u32 flags) @@ -186,6 +187,9 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) goto out; + if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id)) + goto out; + ret = ops->match(rule, fl, flags); out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; @@ -330,6 +334,9 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) if (tb[FRA_FWMASK]) rule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); + if (tb[FRA_TUN_ID]) + rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); + rule->action = frh->action; rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); @@ -407,6 +414,9 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) if (unresolved) ops->unresolved_rules++; + if (rule->tun_id) + ip_tunnel_need_metadata(); + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); @@ -473,6 +483,10 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) (rule->mark_mask != nla_get_u32(tb[FRA_FWMASK]))) continue; + if (tb[FRA_TUN_ID] && + (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID]))) + continue; + if (!ops->compare(rule, frh, tb)) continue; @@ -487,6 +501,9 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) goto errout; } + if (rule->tun_id) + ip_tunnel_unneed_metadata(); + list_del_rcu(&rule->list); if (rule->action == FR_ACT_GOTO) { @@ -535,7 +552,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ - + nla_total_size(4); /* FRA_FWMASK */ + + nla_total_size(4) /* FRA_FWMASK */ + + nla_total_size(8); /* FRA_TUN_ID */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); @@ -591,7 +609,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, ((rule->mark_mask || rule->mark) && nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || (rule->target && - nla_put_u32(skb, FRA_GOTO, rule->target))) + nla_put_u32(skb, FRA_GOTO, rule->target)) || + (rule->tun_id && + nla_put_be64(skb, FRA_TUN_ID, rule->tun_id))) goto nla_put_failure; if (rule->suppress_ifgroup != -1) { diff --git a/net/core/filter.c b/net/core/filter.c index be3098f..a50dbfa 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -47,6 +47,8 @@ #include <linux/if_vlan.h> #include <linux/bpf.h> #include <net/sch_generic.h> +#include <net/cls_cgroup.h> +#include <net/dst_metadata.h> /** * sk_filter - run a packet through a socket filter @@ -1424,6 +1426,136 @@ const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; +static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return task_get_classid((struct sk_buff *) (unsigned long) r1); +} + +static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { + .func = bpf_get_cgroup_classid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + __be16 vlan_proto = (__force __be16) r2; + + if (unlikely(vlan_proto != htons(ETH_P_8021Q) && + vlan_proto != htons(ETH_P_8021AD))) + vlan_proto = htons(ETH_P_8021Q); + + return skb_vlan_push(skb, vlan_proto, vlan_tci); +} + +const struct bpf_func_proto bpf_skb_vlan_push_proto = { + .func = bpf_skb_vlan_push, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; +EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto); + +static u64 bpf_skb_vlan_pop(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + + return skb_vlan_pop(skb); +} + +const struct bpf_func_proto bpf_skb_vlan_pop_proto = { + .func = bpf_skb_vlan_pop, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; +EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto); + +bool bpf_helper_changes_skb_data(void *func) +{ + if (func == bpf_skb_vlan_push) + return true; + if (func == bpf_skb_vlan_pop) + return true; + return false; +} + +static u64 bpf_skb_get_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + struct bpf_tunnel_key *to = (struct bpf_tunnel_key *) (long) r2; + struct ip_tunnel_info *info = skb_tunnel_info(skb, AF_INET); + + if (unlikely(size != sizeof(struct bpf_tunnel_key) || flags || !info)) + return -EINVAL; + + to->tunnel_id = be64_to_cpu(info->key.tun_id); + to->remote_ipv4 = be32_to_cpu(info->key.ipv4_src); + + return 0; +} + +const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { + .func = bpf_skb_get_tunnel_key, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +static struct metadata_dst __percpu *md_dst; + +static u64 bpf_skb_set_tunnel_key(u64 r1, u64 r2, u64 size, u64 flags, u64 r5) +{ + struct sk_buff *skb = (struct sk_buff *) (long) r1; + struct bpf_tunnel_key *from = (struct bpf_tunnel_key *) (long) r2; + struct metadata_dst *md = this_cpu_ptr(md_dst); + struct ip_tunnel_info *info; + + if (unlikely(size != sizeof(struct bpf_tunnel_key) || flags)) + return -EINVAL; + + skb_dst_drop(skb); + dst_hold((struct dst_entry *) md); + skb_dst_set(skb, (struct dst_entry *) md); + + info = &md->u.tun_info; + info->mode = IP_TUNNEL_INFO_TX; + info->key.tun_id = cpu_to_be64(from->tunnel_id); + info->key.ipv4_dst = cpu_to_be32(from->remote_ipv4); + + return 0; +} + +const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { + .func = bpf_skb_set_tunnel_key, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_STACK, + .arg3_type = ARG_CONST_STACK_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +static const struct bpf_func_proto *bpf_get_skb_set_tunnel_key_proto(void) +{ + if (!md_dst) { + /* race is not possible, since it's called from + * verifier that is holding verifier mutex + */ + md_dst = metadata_dst_alloc_percpu(0, GFP_KERNEL); + if (!md_dst) + return NULL; + } + return &bpf_skb_set_tunnel_key_proto; +} + static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id) { @@ -1461,6 +1593,16 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_l4_csum_replace_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_proto; + case BPF_FUNC_skb_vlan_push: + return &bpf_skb_vlan_push_proto; + case BPF_FUNC_skb_vlan_pop: + return &bpf_skb_vlan_pop_proto; + case BPF_FUNC_skb_get_tunnel_key: + return &bpf_skb_get_tunnel_key_proto; + case BPF_FUNC_skb_set_tunnel_key: + return bpf_get_skb_set_tunnel_key_proto(); default: return sk_filter_func_proto(func_id); } @@ -1569,6 +1711,13 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, offsetof(struct net_device, ifindex)); break; + case offsetof(struct __sk_buff, hash): + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, hash)); + break; + case offsetof(struct __sk_buff, mark): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2a834c6..11e6540 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -590,6 +590,15 @@ void make_flow_keys_digest(struct flow_keys_digest *digest, } EXPORT_SYMBOL(make_flow_keys_digest); +static inline void __skb_set_sw_hash(struct sk_buff *skb, u32 hash, + struct flow_keys *keys) +{ + if (keys->ports.ports) + skb->l4_hash = 1; + skb->sw_hash = 1; + skb->hash = hash; +} + /** * __skb_get_hash: calculate a flow hash * @skb: sk_buff to calculate flow hash from @@ -609,10 +618,8 @@ void __skb_get_hash(struct sk_buff *skb) hash = ___skb_get_hash(skb, &keys, hashrnd); if (!hash) return; - if (keys.ports.ports) - skb->l4_hash = 1; - skb->sw_hash = 1; - skb->hash = hash; + + __skb_set_sw_hash(skb, hash, &keys); } EXPORT_SYMBOL(__skb_get_hash); @@ -624,6 +631,49 @@ __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb) } EXPORT_SYMBOL(skb_get_hash_perturb); +__u32 __skb_get_hash_flowi6(struct sk_buff *skb, struct flowi6 *fl6) +{ + struct flow_keys keys; + + memset(&keys, 0, sizeof(keys)); + + memcpy(&keys.addrs.v6addrs.src, &fl6->saddr, + sizeof(keys.addrs.v6addrs.src)); + memcpy(&keys.addrs.v6addrs.dst, &fl6->daddr, + sizeof(keys.addrs.v6addrs.dst)); + keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + keys.ports.src = fl6->fl6_sport; + keys.ports.dst = fl6->fl6_dport; + keys.keyid.keyid = fl6->fl6_gre_key; + keys.tags.flow_label = (__force u32)fl6->flowlabel; + keys.basic.ip_proto = fl6->flowi6_proto; + + __skb_set_sw_hash(skb, flow_hash_from_keys(&keys), &keys); + + return skb->hash; +} +EXPORT_SYMBOL(__skb_get_hash_flowi6); + +__u32 __skb_get_hash_flowi4(struct sk_buff *skb, struct flowi4 *fl4) +{ + struct flow_keys keys; + + memset(&keys, 0, sizeof(keys)); + + keys.addrs.v4addrs.src = fl4->saddr; + keys.addrs.v4addrs.dst = fl4->daddr; + keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + keys.ports.src = fl4->fl4_sport; + keys.ports.dst = fl4->fl4_dport; + keys.keyid.keyid = fl4->fl4_gre_key; + keys.basic.ip_proto = fl4->flowi4_proto; + + __skb_set_sw_hash(skb, flow_hash_from_keys(&keys), &keys); + + return skb->hash; +} +EXPORT_SYMBOL(__skb_get_hash_flowi4); + u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys *keys, int hlen) { diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c new file mode 100644 index 0000000..5d6d8e3 --- /dev/null +++ b/net/core/lwtunnel.c @@ -0,0 +1,243 @@ +/* + * lwtunnel Infrastructure for light weight tunnels like mpls + * + * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <linux/capability.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/lwtunnel.h> +#include <linux/in.h> +#include <linux/init.h> +#include <linux/err.h> + +#include <net/lwtunnel.h> +#include <net/rtnetlink.h> +#include <net/ip6_fib.h> + +struct lwtunnel_state *lwtunnel_state_alloc(int encap_len) +{ + struct lwtunnel_state *lws; + + lws = kzalloc(sizeof(*lws) + encap_len, GFP_ATOMIC); + + return lws; +} +EXPORT_SYMBOL(lwtunnel_state_alloc); + +static const struct lwtunnel_encap_ops __rcu * + lwtun_encaps[LWTUNNEL_ENCAP_MAX + 1] __read_mostly; + +int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *ops, + unsigned int num) +{ + if (num > LWTUNNEL_ENCAP_MAX) + return -ERANGE; + + return !cmpxchg((const struct lwtunnel_encap_ops **) + &lwtun_encaps[num], + NULL, ops) ? 0 : -1; +} +EXPORT_SYMBOL(lwtunnel_encap_add_ops); + +int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *ops, + unsigned int encap_type) +{ + int ret; + + if (encap_type == LWTUNNEL_ENCAP_NONE || + encap_type > LWTUNNEL_ENCAP_MAX) + return -ERANGE; + + ret = (cmpxchg((const struct lwtunnel_encap_ops **) + &lwtun_encaps[encap_type], + ops, NULL) == ops) ? 0 : -1; + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_encap_del_ops); + +int lwtunnel_build_state(struct net_device *dev, u16 encap_type, + struct nlattr *encap, struct lwtunnel_state **lws) +{ + const struct lwtunnel_encap_ops *ops; + int ret = -EINVAL; + + if (encap_type == LWTUNNEL_ENCAP_NONE || + encap_type > LWTUNNEL_ENCAP_MAX) + return ret; + + ret = -EOPNOTSUPP; + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[encap_type]); + if (likely(ops && ops->build_state)) + ret = ops->build_state(dev, encap, lws); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_build_state); + +int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate) +{ + const struct lwtunnel_encap_ops *ops; + struct nlattr *nest; + int ret = -EINVAL; + + if (!lwtstate) + return 0; + + if (lwtstate->type == LWTUNNEL_ENCAP_NONE || + lwtstate->type > LWTUNNEL_ENCAP_MAX) + return 0; + + ret = -EOPNOTSUPP; + nest = nla_nest_start(skb, RTA_ENCAP); + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[lwtstate->type]); + if (likely(ops && ops->fill_encap)) + ret = ops->fill_encap(skb, lwtstate); + rcu_read_unlock(); + + if (ret) + goto nla_put_failure; + nla_nest_end(skb, nest); + ret = nla_put_u16(skb, RTA_ENCAP_TYPE, lwtstate->type); + if (ret) + goto nla_put_failure; + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + + return (ret == -EOPNOTSUPP ? 0 : ret); +} +EXPORT_SYMBOL(lwtunnel_fill_encap); + +int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) +{ + const struct lwtunnel_encap_ops *ops; + int ret = 0; + + if (!lwtstate) + return 0; + + if (lwtstate->type == LWTUNNEL_ENCAP_NONE || + lwtstate->type > LWTUNNEL_ENCAP_MAX) + return 0; + + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[lwtstate->type]); + if (likely(ops && ops->get_encap_size)) + ret = nla_total_size(ops->get_encap_size(lwtstate)); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_get_encap_size); + +int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + const struct lwtunnel_encap_ops *ops; + int ret = 0; + + if (!a && !b) + return 0; + + if (!a || !b) + return 1; + + if (a->type != b->type) + return 1; + + if (a->type == LWTUNNEL_ENCAP_NONE || + a->type > LWTUNNEL_ENCAP_MAX) + return 0; + + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[a->type]); + if (likely(ops && ops->cmp_encap)) + ret = ops->cmp_encap(a, b); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_cmp_encap); + +int __lwtunnel_output(struct sock *sk, struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + const struct lwtunnel_encap_ops *ops; + int ret = -EINVAL; + + if (!lwtstate) + goto drop; + + if (lwtstate->type == LWTUNNEL_ENCAP_NONE || + lwtstate->type > LWTUNNEL_ENCAP_MAX) + return 0; + + ret = -EOPNOTSUPP; + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[lwtstate->type]); + if (likely(ops && ops->output)) + ret = ops->output(sk, skb); + rcu_read_unlock(); + + if (ret == -EOPNOTSUPP) + goto drop; + + return ret; + +drop: + kfree_skb(skb); + + return ret; +} + +int lwtunnel_output6(struct sock *sk, struct sk_buff *skb) +{ + struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + struct lwtunnel_state *lwtstate = NULL; + + if (rt) { + lwtstate = rt->rt6i_lwtstate; + skb->dev = rt->dst.dev; + } + + skb->protocol = htons(ETH_P_IPV6); + + return __lwtunnel_output(sk, skb, lwtstate); +} +EXPORT_SYMBOL(lwtunnel_output6); + +int lwtunnel_output(struct sock *sk, struct sk_buff *skb) +{ + struct rtable *rt = (struct rtable *)skb_dst(skb); + struct lwtunnel_state *lwtstate = NULL; + + if (rt) { + lwtstate = rt->rt_lwtstate; + skb->dev = rt->dst.dev; + } + + skb->protocol = htons(ETH_P_IP); + + return __lwtunnel_output(sk, skb, lwtstate); +} +EXPORT_SYMBOL(lwtunnel_output); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 84195da..2b515ba 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -274,8 +274,12 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device (entries >= tbl->gc_thresh2 && time_after(now, tbl->last_flush + 5 * HZ))) { if (!neigh_forced_gc(tbl) && - entries >= tbl->gc_thresh3) + entries >= tbl->gc_thresh3) { + net_info_ratelimited("%s: neighbor table overflow!\n", + tbl->id); + NEIGH_CACHE_STAT_INC(tbl, table_fulls); goto out_entries; + } } n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC); @@ -1849,6 +1853,7 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, ndst.ndts_rcv_probes_ucast += st->rcv_probes_ucast; ndst.ndts_periodic_gc_runs += st->periodic_gc_runs; ndst.ndts_forced_gc_runs += st->forced_gc_runs; + ndst.ndts_table_fulls += st->table_fulls; } if (nla_put(skb, NDTA_STATS, sizeof(ndst), &ndst)) @@ -2717,12 +2722,12 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v) struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { - seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards\n"); + seq_printf(seq, "entries allocs destroys hash_grows lookups hits res_failed rcv_probes_mcast rcv_probes_ucast periodic_gc_runs forced_gc_runs unresolved_discards table_fulls\n"); return 0; } seq_printf(seq, "%08x %08lx %08lx %08lx %08lx %08lx %08lx " - "%08lx %08lx %08lx %08lx %08lx\n", + "%08lx %08lx %08lx %08lx %08lx %08lx\n", atomic_read(&tbl->entries), st->allocs, @@ -2739,7 +2744,8 @@ static int neigh_stat_seq_show(struct seq_file *seq, void *v) st->periodic_gc_runs, st->forced_gc_runs, - st->unres_discards + st->unres_discards, + st->table_fulls ); return 0; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 18b34d7..39ec694 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -404,6 +404,19 @@ static ssize_t group_store(struct device *dev, struct device_attribute *attr, NETDEVICE_SHOW(group, fmt_dec); static DEVICE_ATTR(netdev_group, S_IRUGO | S_IWUSR, group_show, group_store); +static int change_proto_down(struct net_device *dev, unsigned long proto_down) +{ + return dev_change_proto_down(dev, (bool) proto_down); +} + +static ssize_t proto_down_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_proto_down); +} +NETDEVICE_SHOW_RW(proto_down, fmt_dec); + static ssize_t phys_port_id_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -501,6 +514,7 @@ static struct attribute *net_class_attrs[] = { &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, + &dev_attr_proto_down.attr, NULL, }; ATTRIBUTE_GROUPS(net_class); @@ -712,14 +726,17 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, old_map = rcu_dereference_protected(queue->rps_map, lockdep_is_held(&rps_map_lock)); rcu_assign_pointer(queue->rps_map, map); - spin_unlock(&rps_map_lock); if (map) static_key_slow_inc(&rps_needed); - if (old_map) { - kfree_rcu(old_map, rcu); + if (old_map) static_key_slow_dec(&rps_needed); - } + + spin_unlock(&rps_map_lock); + + if (old_map) + kfree_rcu(old_map, rcu); + free_cpumask_var(mask); return len; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 1cbd209..de8d5cc 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -273,7 +273,6 @@ struct pktgen_dev { /* runtime counters relating to clone_skb */ - __u64 allocated_skbs; __u32 clone_count; int last_ok; /* Was last skb sent? * Or a failed transmit of some sort? @@ -2279,7 +2278,7 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev) { - pkt_dev->pkt_overhead = 0; + pkt_dev->pkt_overhead = LL_RESERVED_SPACE(pkt_dev->odev); pkt_dev->pkt_overhead += pkt_dev->nr_labels*sizeof(u32); pkt_dev->pkt_overhead += VLAN_TAG_SIZE(pkt_dev); pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev); @@ -2788,6 +2787,7 @@ static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, } else { skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT); } + skb_reserve(skb, LL_RESERVED_SPACE(dev)); return skb; } @@ -3397,7 +3397,6 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) return; } pkt_dev->last_pkt_size = pkt_dev->skb->len; - pkt_dev->allocated_skbs++; pkt_dev->clone_count = 0; /* reset counter */ } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index dc004b1..788ceed 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -896,7 +896,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ - + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(1); /* IFLA_PROTO_DOWN */ + } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -1082,7 +1084,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, (dev->ifalias && nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) || nla_put_u32(skb, IFLA_CARRIER_CHANGES, - atomic_read(&dev->carrier_changes))) + atomic_read(&dev->carrier_changes)) || + nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down)) goto nla_put_failure; if (1) { @@ -1319,6 +1322,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */ [IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, [IFLA_LINK_NETNSID] = { .type = NLA_S32 }, + [IFLA_PROTO_DOWN] = { .type = NLA_U8 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -1861,6 +1865,14 @@ static int do_setlink(const struct sk_buff *skb, } err = 0; + if (tb[IFLA_PROTO_DOWN]) { + err = dev_change_proto_down(dev, + nla_get_u8(tb[IFLA_PROTO_DOWN])); + if (err) + goto errout; + status |= DO_SETLINK_NOTIFY; + } + errout: if (status & DO_SETLINK_MODIFIED) { if (status & DO_SETLINK_NOTIFY) @@ -1951,16 +1963,30 @@ static int rtnl_group_dellink(const struct net *net, int group) return 0; } +int rtnl_delete_link(struct net_device *dev) +{ + const struct rtnl_link_ops *ops; + LIST_HEAD(list_kill); + + ops = dev->rtnl_link_ops; + if (!ops || !ops->dellink) + return -EOPNOTSUPP; + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + + return 0; +} +EXPORT_SYMBOL_GPL(rtnl_delete_link); + static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - const struct rtnl_link_ops *ops; struct net_device *dev; struct ifinfomsg *ifm; char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; int err; - LIST_HEAD(list_kill); err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) @@ -1982,13 +2008,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) if (!dev) return -ENODEV; - ops = dev->rtnl_link_ops; - if (!ops || !ops->dellink) - return -EOPNOTSUPP; - - ops->dellink(dev, &list_kill); - unregister_netdevice_many(&list_kill); - return 0; + return rtnl_delete_link(dev); } int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 43d3dd6..42689d5 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -60,11 +60,15 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) struct phy_device *phydev; unsigned int type; + if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->drv) + return false; + if (skb_headroom(skb) < ETH_HLEN) return false; + __skb_push(skb, ETH_HLEN); - type = classify(skb); + type = ptp_classify_raw(skb); __skb_pull(skb, ETH_HLEN); diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index b445d49..78d4ac9 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -574,7 +574,7 @@ static int dsa_of_probe(struct device *dev) { struct device_node *np = dev->of_node; struct device_node *child, *mdio, *ethernet, *port, *link; - struct mii_bus *mdio_bus; + struct mii_bus *mdio_bus, *mdio_bus_switch; struct net_device *ethernet_dev; struct dsa_platform_data *pd; struct dsa_chip_data *cd; @@ -636,6 +636,16 @@ static int dsa_of_probe(struct device *dev) if (!of_property_read_u32(child, "eeprom-length", &eeprom_len)) cd->eeprom_len = eeprom_len; + mdio = of_parse_phandle(child, "mii-bus", 0); + if (mdio) { + mdio_bus_switch = of_mdio_find_bus(mdio); + if (!mdio_bus_switch) { + ret = -EPROBE_DEFER; + goto out_free_chip; + } + cd->host_dev = &mdio_bus_switch->dev; + } + for_each_available_child_of_node(child, port) { port_reg = of_get_property(port, "reg", NULL); if (!port_reg) diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index d5f1f9b..311796c8 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -13,9 +13,10 @@ #include <linux/phy.h> #include <linux/netdevice.h> +#include <linux/netpoll.h> struct dsa_device_ops { - netdev_tx_t (*xmit)(struct sk_buff *skb, struct net_device *dev); + struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); int (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); }; @@ -26,7 +27,7 @@ struct dsa_slave_priv { * switch port. */ struct net_device *dev; - netdev_tx_t (*xmit)(struct sk_buff *skb, + struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); /* @@ -47,6 +48,9 @@ struct dsa_slave_priv { int old_duplex; struct net_device *bridge_dev; +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *netpoll; +#endif }; /* dsa.c */ diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 35c47dd..aa0266f 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -18,6 +18,7 @@ #include <net/rtnetlink.h> #include <net/switchdev.h> #include <linux/if_bridge.h> +#include <linux/netpoll.h> #include "dsa_priv.h" /* slave mii_bus handling ***************************************************/ @@ -199,103 +200,66 @@ out: return 0; } -static int dsa_slave_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid, u16 nlm_flags) +static int dsa_slave_port_fdb_add(struct net_device *dev, + struct switchdev_obj *obj) { + struct switchdev_obj_fdb *fdb = &obj->u.fdb; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; int ret = -EOPNOTSUPP; - if (ds->drv->fdb_add) - ret = ds->drv->fdb_add(ds, p->port, addr, vid); + if (obj->trans == SWITCHDEV_TRANS_PREPARE) + ret = ds->drv->port_fdb_add ? 0 : -EOPNOTSUPP; + else if (obj->trans == SWITCHDEV_TRANS_COMMIT) + ret = ds->drv->port_fdb_add(ds, p->port, fdb->addr, fdb->vid); return ret; } -static int dsa_slave_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid) +static int dsa_slave_port_fdb_del(struct net_device *dev, + struct switchdev_obj *obj) { + struct switchdev_obj_fdb *fdb = &obj->u.fdb; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; int ret = -EOPNOTSUPP; - if (ds->drv->fdb_del) - ret = ds->drv->fdb_del(ds, p->port, addr, vid); + if (ds->drv->port_fdb_del) + ret = ds->drv->port_fdb_del(ds, p->port, fdb->addr, fdb->vid); return ret; } -static int dsa_slave_fill_info(struct net_device *dev, struct sk_buff *skb, - const unsigned char *addr, u16 vid, - bool is_static, - u32 portid, u32 seq, int type, - unsigned int flags) -{ - struct nlmsghdr *nlh; - struct ndmsg *ndm; - - nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); - if (!nlh) - return -EMSGSIZE; - - ndm = nlmsg_data(nlh); - ndm->ndm_family = AF_BRIDGE; - ndm->ndm_pad1 = 0; - ndm->ndm_pad2 = 0; - ndm->ndm_flags = NTF_EXT_LEARNED; - ndm->ndm_type = 0; - ndm->ndm_ifindex = dev->ifindex; - ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; - - if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) - goto nla_put_failure; - - if (vid && nla_put_u16(skb, NDA_VLAN, vid)) - goto nla_put_failure; - - nlmsg_end(skb, nlh); - return 0; - -nla_put_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; -} - -/* Dump information about entries, in response to GETNEIGH */ -static int dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct net_device *dev, - struct net_device *filter_dev, int idx) +static int dsa_slave_port_fdb_dump(struct net_device *dev, + struct switchdev_obj *obj) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; unsigned char addr[ETH_ALEN] = { 0 }; + u16 vid = 0; int ret; - if (!ds->drv->fdb_getnext) + if (!ds->drv->port_fdb_getnext) return -EOPNOTSUPP; - for (; ; idx++) { + for (;;) { bool is_static; - ret = ds->drv->fdb_getnext(ds, p->port, addr, &is_static); + ret = ds->drv->port_fdb_getnext(ds, p->port, addr, &vid, + &is_static); if (ret < 0) break; - if (idx < cb->args[0]) - continue; + obj->u.fdb.addr = addr; + obj->u.fdb.vid = vid; + obj->u.fdb.ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; - ret = dsa_slave_fill_info(dev, skb, addr, 0, - is_static, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWNEIGH, NLM_F_MULTI); + ret = obj->cb(dev, obj); if (ret < 0) break; } - return idx; + return ret == -ENOENT ? 0 : ret; } static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) @@ -363,6 +327,62 @@ static int dsa_slave_port_attr_set(struct net_device *dev, return ret; } +static int dsa_slave_port_obj_add(struct net_device *dev, + struct switchdev_obj *obj) +{ + int err; + + /* For the prepare phase, ensure the full set of changes is feasable in + * one go in order to signal a failure properly. If an operation is not + * supported, return -EOPNOTSUPP. + */ + + switch (obj->id) { + case SWITCHDEV_OBJ_PORT_FDB: + err = dsa_slave_port_fdb_add(dev, obj); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int dsa_slave_port_obj_del(struct net_device *dev, + struct switchdev_obj *obj) +{ + int err; + + switch (obj->id) { + case SWITCHDEV_OBJ_PORT_FDB: + err = dsa_slave_port_fdb_del(dev, obj); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int dsa_slave_port_obj_dump(struct net_device *dev, + struct switchdev_obj *obj) +{ + int err; + + switch (obj->id) { + case SWITCHDEV_OBJ_PORT_FDB: + err = dsa_slave_port_fdb_dump(dev, obj); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + static int dsa_slave_bridge_port_join(struct net_device *dev, struct net_device *br) { @@ -418,24 +438,53 @@ static int dsa_slave_port_attr_get(struct net_device *dev, return 0; } -static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) +static inline netdev_tx_t dsa_netpoll_send_skb(struct dsa_slave_priv *p, + struct sk_buff *skb) { - struct dsa_slave_priv *p = netdev_priv(dev); - - return p->xmit(skb, dev); +#ifdef CONFIG_NET_POLL_CONTROLLER + if (p->netpoll) + netpoll_send_skb(p->netpoll, skb); +#else + BUG(); +#endif + return NETDEV_TX_OK; } -static netdev_tx_t dsa_slave_notag_xmit(struct sk_buff *skb, - struct net_device *dev) +static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); + struct sk_buff *nskb; + + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; + + /* Transmit function may have to reallocate the original SKB */ + nskb = p->xmit(skb, dev); + if (!nskb) + return NETDEV_TX_OK; + + /* SKB for netpoll still need to be mangled with the protocol-specific + * tag to be successfully transmitted + */ + if (unlikely(netpoll_tx_running(dev))) + return dsa_netpoll_send_skb(p, nskb); - skb->dev = p->parent->dst->master_netdev; - dev_queue_xmit(skb); + /* Queue the SKB for transmission on the parent interface, but + * do not modify its EtherType + */ + nskb->dev = p->parent->dst->master_netdev; + dev_queue_xmit(nskb); return NETDEV_TX_OK; } +static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + /* Just return the original SKB */ + return skb; +} + /* ethtool operations *******************************************************/ static int @@ -665,6 +714,49 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) return ret; } +#ifdef CONFIG_NET_POLL_CONTROLLER +static int dsa_slave_netpoll_setup(struct net_device *dev, + struct netpoll_info *ni) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + struct net_device *master = ds->dst->master_netdev; + struct netpoll *netpoll; + int err = 0; + + netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); + if (!netpoll) + return -ENOMEM; + + err = __netpoll_setup(netpoll, master); + if (err) { + kfree(netpoll); + goto out; + } + + p->netpoll = netpoll; +out: + return err; +} + +static void dsa_slave_netpoll_cleanup(struct net_device *dev) +{ + struct dsa_slave_priv *p = netdev_priv(dev); + struct netpoll *netpoll = p->netpoll; + + if (!netpoll) + return; + + p->netpoll = NULL; + + __netpoll_free_async(netpoll); +} + +static void dsa_slave_poll_controller(struct net_device *dev) +{ +} +#endif + static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_settings = dsa_slave_get_settings, .set_settings = dsa_slave_set_settings, @@ -692,16 +784,24 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_change_rx_flags = dsa_slave_change_rx_flags, .ndo_set_rx_mode = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, - .ndo_fdb_add = dsa_slave_fdb_add, - .ndo_fdb_del = dsa_slave_fdb_del, - .ndo_fdb_dump = dsa_slave_fdb_dump, + .ndo_fdb_add = switchdev_port_fdb_add, + .ndo_fdb_del = switchdev_port_fdb_del, + .ndo_fdb_dump = switchdev_port_fdb_dump, .ndo_do_ioctl = dsa_slave_ioctl, .ndo_get_iflink = dsa_slave_get_iflink, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_netpoll_setup = dsa_slave_netpoll_setup, + .ndo_netpoll_cleanup = dsa_slave_netpoll_cleanup, + .ndo_poll_controller = dsa_slave_poll_controller, +#endif }; static const struct switchdev_ops dsa_slave_switchdev_ops = { .switchdev_port_attr_get = dsa_slave_port_attr_get, .switchdev_port_attr_set = dsa_slave_port_attr_set, + .switchdev_port_obj_add = dsa_slave_port_obj_add, + .switchdev_port_obj_del = dsa_slave_port_obj_del, + .switchdev_port_obj_dump = dsa_slave_port_obj_dump, }; static void dsa_slave_adjust_link(struct net_device *dev) diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 83d3572..e2aadb7 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -58,14 +58,11 @@ #define BRCM_EG_TC_MASK 0x7 #define BRCM_EG_PID_MASK 0x1f -static netdev_tx_t brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev) +static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); u8 *brcm_tag; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - if (skb_cow_head(skb, BRCM_TAG_LEN) < 0) goto out_free; @@ -87,17 +84,11 @@ static netdev_tx_t brcm_tag_xmit(struct sk_buff *skb, struct net_device *dev) brcm_tag[2] = BRCM_IG_DSTMAP2_MASK; brcm_tag[3] = (1 << p->port) & BRCM_IG_DSTMAP1_MASK; - /* Queue the SKB for transmission on the parent interface, but - * do not modify its EtherType - */ - skb->dev = p->parent->dst->master_netdev; - dev_queue_xmit(skb); - - return NETDEV_TX_OK; + return skb; out_free: kfree_skb(skb); - return NETDEV_TX_OK; + return NULL; } static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 2dab270..aa780e4 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -15,14 +15,11 @@ #define DSA_HLEN 4 -static netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev) +static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); u8 *dsa_header; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - /* * Convert the outermost 802.1q tag to a DSA tag for tagged * packets, or insert a DSA tag between the addresses and @@ -63,14 +60,11 @@ static netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev) dsa_header[3] = 0x00; } - skb->dev = p->parent->dst->master_netdev; - dev_queue_xmit(skb); - - return NETDEV_TX_OK; + return skb; out_free: kfree_skb(skb); - return NETDEV_TX_OK; + return NULL; } static int dsa_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 9aeda59..2288c80 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -16,14 +16,11 @@ #define DSA_HLEN 4 #define EDSA_HLEN 8 -static netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev) +static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); u8 *edsa_header; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - /* * Convert the outermost 802.1q tag to a DSA tag and prepend * a DSA ethertype field is the packet is tagged, or insert @@ -76,14 +73,11 @@ static netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev) edsa_header[7] = 0x00; } - skb->dev = p->parent->dst->master_netdev; - dev_queue_xmit(skb); - - return NETDEV_TX_OK; + return skb; out_free: kfree_skb(skb); - return NETDEV_TX_OK; + return NULL; } static int edsa_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index e268f9d..d25efc9 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -13,16 +13,13 @@ #include <linux/slab.h> #include "dsa_priv.h" -static netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev) +static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); struct sk_buff *nskb; int padlen; u8 *trailer; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - /* * We have to make sure that the trailer ends up as the very * last 4 bytes of the packet. This means that we have to pad @@ -36,7 +33,7 @@ static netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev) nskb = alloc_skb(NET_IP_ALIGN + skb->len + padlen + 4, GFP_ATOMIC); if (nskb == NULL) { kfree_skb(skb); - return NETDEV_TX_OK; + return NULL; } skb_reserve(nskb, NET_IP_ALIGN); @@ -57,10 +54,7 @@ static netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev) trailer[2] = 0x10; trailer[3] = 0x00; - nskb->dev = p->parent->dst->master_netdev; - dev_queue_xmit(nskb); - - return NETDEV_TX_OK; + return nskb; } static int trailer_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 77e0f0e..217127c 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -114,7 +114,7 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, EXPORT_SYMBOL(eth_header); /** - * eth_get_headlen - determine the the length of header for an ethernet frame + * eth_get_headlen - determine the length of header for an ethernet frame * @data: pointer to start of frame * @len: total length of frame * diff --git a/net/ieee802154/rdev-ops.h b/net/ieee802154/rdev-ops.h index b2155a1..8d5960a 100644 --- a/net/ieee802154/rdev-ops.h +++ b/net/ieee802154/rdev-ops.h @@ -24,6 +24,26 @@ rdev_del_virtual_intf_deprecated(struct cfg802154_registered_device *rdev, } static inline int +rdev_suspend(struct cfg802154_registered_device *rdev) +{ + int ret; + trace_802154_rdev_suspend(&rdev->wpan_phy); + ret = rdev->ops->suspend(&rdev->wpan_phy); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; +} + +static inline int +rdev_resume(struct cfg802154_registered_device *rdev) +{ + int ret; + trace_802154_rdev_resume(&rdev->wpan_phy); + ret = rdev->ops->resume(&rdev->wpan_phy); + trace_802154_rdev_return_int(&rdev->wpan_phy, ret); + return ret; +} + +static inline int rdev_add_virtual_intf(struct cfg802154_registered_device *rdev, char *name, unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr) diff --git a/net/ieee802154/sysfs.c b/net/ieee802154/sysfs.c index 133b428..bd88525 100644 --- a/net/ieee802154/sysfs.c +++ b/net/ieee802154/sysfs.c @@ -14,11 +14,13 @@ */ #include <linux/device.h> +#include <linux/rtnetlink.h> #include <net/cfg802154.h> #include "core.h" #include "sysfs.h" +#include "rdev-ops.h" static inline struct cfg802154_registered_device * dev_to_rdev(struct device *dev) @@ -62,10 +64,46 @@ static struct attribute *pmib_attrs[] = { }; ATTRIBUTE_GROUPS(pmib); +#ifdef CONFIG_PM_SLEEP +static int wpan_phy_suspend(struct device *dev) +{ + struct cfg802154_registered_device *rdev = dev_to_rdev(dev); + int ret = 0; + + if (rdev->ops->suspend) { + rtnl_lock(); + ret = rdev_suspend(rdev); + rtnl_unlock(); + } + + return ret; +} + +static int wpan_phy_resume(struct device *dev) +{ + struct cfg802154_registered_device *rdev = dev_to_rdev(dev); + int ret = 0; + + if (rdev->ops->resume) { + rtnl_lock(); + ret = rdev_resume(rdev); + rtnl_unlock(); + } + + return ret; +} + +static SIMPLE_DEV_PM_OPS(wpan_phy_pm_ops, wpan_phy_suspend, wpan_phy_resume); +#define WPAN_PHY_PM_OPS (&wpan_phy_pm_ops) +#else +#define WPAN_PHY_PM_OPS NULL +#endif + struct class wpan_phy_class = { .name = "ieee802154", .dev_release = wpan_phy_release, .dev_groups = pmib_groups, + .pm = WPAN_PHY_PM_OPS, }; int wpan_phy_sysfs_init(void) diff --git a/net/ieee802154/trace.h b/net/ieee802154/trace.h index 9b5f0eb..4399b7f 100644 --- a/net/ieee802154/trace.h +++ b/net/ieee802154/trace.h @@ -40,6 +40,28 @@ * rdev->ops traces * *************************************************************/ +DECLARE_EVENT_CLASS(wpan_phy_only_evt, + TP_PROTO(struct wpan_phy *wpan_phy), + TP_ARGS(wpan_phy), + TP_STRUCT__entry( + WPAN_PHY_ENTRY + ), + TP_fast_assign( + WPAN_PHY_ASSIGN; + ), + TP_printk(WPAN_PHY_PR_FMT, WPAN_PHY_PR_ARG) +); + +DEFINE_EVENT(wpan_phy_only_evt, 802154_rdev_suspend, + TP_PROTO(struct wpan_phy *wpan_phy), + TP_ARGS(wpan_phy) +); + +DEFINE_EVENT(wpan_phy_only_evt, 802154_rdev_resume, + TP_PROTO(struct wpan_phy *wpan_phy), + TP_ARGS(wpan_phy) +); + TRACE_EVENT(802154_rdev_add_virtual_intf, TP_PROTO(struct wpan_phy *wpan_phy, char *name, enum nl802154_iftype type, __le64 extended_addr), diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9532ee8..cc4e498 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -112,6 +112,7 @@ #include <net/raw.h> #include <net/icmp.h> #include <net/inet_common.h> +#include <net/ip_tunnels.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/secure_seq.h> @@ -1780,6 +1781,8 @@ static int __init inet_init(void) dev_add_pack(&ip_packet_type); + ip_tunnel_core_init(); + rc = 0; out: return rc; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 6c8b1fb..34a3085 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -291,6 +291,40 @@ static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); } +/* Create and send an arp packet. */ +static void arp_send_dst(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, + const unsigned char *dest_hw, + const unsigned char *src_hw, + const unsigned char *target_hw, struct sk_buff *oskb) +{ + struct sk_buff *skb; + + /* arp on this interface. */ + if (dev->flags & IFF_NOARP) + return; + + skb = arp_create(type, ptype, dest_ip, dev, src_ip, + dest_hw, src_hw, target_hw); + if (!skb) + return; + + if (oskb) + skb_dst_copy(skb, oskb); + + arp_xmit(skb); +} + +void arp_send(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, + const unsigned char *dest_hw, const unsigned char *src_hw, + const unsigned char *target_hw) +{ + arp_send_dst(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, + target_hw, NULL); +} +EXPORT_SYMBOL(arp_send); + static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { __be32 saddr = 0; @@ -346,8 +380,9 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } } - arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, - dst_hw, dev->dev_addr, NULL); + arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, + dst_hw, dev->dev_addr, NULL, + dev->priv_flags & IFF_XMIT_DST_RELEASE ? NULL : skb); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) @@ -597,32 +632,6 @@ void arp_xmit(struct sk_buff *skb) EXPORT_SYMBOL(arp_xmit); /* - * Create and send an arp packet. - */ -void arp_send(int type, int ptype, __be32 dest_ip, - struct net_device *dev, __be32 src_ip, - const unsigned char *dest_hw, const unsigned char *src_hw, - const unsigned char *target_hw) -{ - struct sk_buff *skb; - - /* - * No arp on this interface. - */ - - if (dev->flags&IFF_NOARP) - return; - - skb = arp_create(type, ptype, dest_ip, dev, src_ip, - dest_hw, src_hw, target_hw); - if (!skb) - return; - - arp_xmit(skb); -} -EXPORT_SYMBOL(arp_send); - -/* * Process an arp request. */ diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 574fad9..f915abf 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -74,7 +74,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; - inet_set_txhash(sk); + sk_set_txhash(sk); inet->inet_id = jiffies; sk_dst_set(sk, &rt->dst); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 6bbc549..6b98de0 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -280,6 +280,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_scope = scope; fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0; + fl4.flowi4_tun_key.tun_id = 0; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); } else { @@ -313,6 +314,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.saddr = dst; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_tun_key.tun_id = 0; no_addr = idev->ifa_list == NULL; @@ -591,6 +593,8 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_FLOW] = { .type = NLA_U32 }, + [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, + [RTA_ENCAP] = { .type = NLA_NESTED }, }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, @@ -656,6 +660,12 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, case RTA_TABLE: cfg->fc_table = nla_get_u32(attr); break; + case RTA_ENCAP: + cfg->fc_encap = attr; + break; + case RTA_ENCAP_TYPE: + cfg->fc_encap_type = nla_get_u16(attr); + break; } } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3a06586..558e196 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -42,6 +42,7 @@ #include <net/ip_fib.h> #include <net/netlink.h> #include <net/nexthop.h> +#include <net/lwtunnel.h> #include "fib_lookup.h" @@ -208,6 +209,7 @@ static void free_fib_info_rcu(struct rcu_head *head) change_nexthops(fi) { if (nexthop_nh->nh_dev) dev_put(nexthop_nh->nh_dev); + lwtstate_put(nexthop_nh->nh_lwtstate); free_nh_exceptions(nexthop_nh); rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output); rt_fibinfo_free(&nexthop_nh->nh_rth_input); @@ -266,6 +268,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) #ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid != onh->nh_tclassid || #endif + lwtunnel_cmp_encap(nh->nh_lwtstate, onh->nh_lwtstate) || ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_COMPARE_MASK)) return -1; onh++; @@ -366,6 +369,7 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) payload += nla_total_size((RTAX_MAX * nla_total_size(4))); if (fi->fib_nhs) { + size_t nh_encapsize = 0; /* Also handles the special case fib_nhs == 1 */ /* each nexthop is packed in an attribute */ @@ -374,8 +378,21 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) /* may contain flow and gateway attribute */ nhsize += 2 * nla_total_size(4); + /* grab encap info */ + for_nexthops(fi) { + if (nh->nh_lwtstate) { + /* RTA_ENCAP_TYPE */ + nh_encapsize += lwtunnel_get_encap_size( + nh->nh_lwtstate); + /* RTA_ENCAP */ + nh_encapsize += nla_total_size(2); + } + } endfor_nexthops(fi); + /* all nexthops are packed in a nested attribute */ - payload += nla_total_size(fi->fib_nhs * nhsize); + payload += nla_total_size((fi->fib_nhs * nhsize) + + nh_encapsize); + } return payload; @@ -421,13 +438,15 @@ static int fib_detect_death(struct fib_info *fi, int order, if (n) { state = n->nud_state; neigh_release(n); + } else { + return 0; } if (state == NUD_REACHABLE) return 0; if ((state & NUD_VALID) && order != dflt) return 0; if ((state & NUD_VALID) || - (*last_idx < 0 && order > dflt)) { + (*last_idx < 0 && order > dflt && state != NUD_INCOMPLETE)) { *last_resort = fi; *last_idx = order; } @@ -452,6 +471,9 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, int remaining, struct fib_config *cfg) { + struct net *net = cfg->fc_nlinfo.nl_net; + int ret; + change_nexthops(fi) { int attrlen; @@ -475,18 +497,66 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (nexthop_nh->nh_tclassid) fi->fib_net->ipv4.fib_num_tclassid_users++; #endif + nla = nla_find(attrs, attrlen, RTA_ENCAP); + if (nla) { + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + struct nlattr *nla_entype; + + nla_entype = nla_find(attrs, attrlen, + RTA_ENCAP_TYPE); + if (!nla_entype) + goto err_inval; + if (cfg->fc_oif) + dev = __dev_get_by_index(net, cfg->fc_oif); + ret = lwtunnel_build_state(dev, nla_get_u16( + nla_entype), + nla, &lwtstate); + if (ret) + goto errout; + nexthop_nh->nh_lwtstate = + lwtstate_get(lwtstate); + } } rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); return 0; + +err_inval: + ret = -EINVAL; + +errout: + return ret; } #endif +int fib_encap_match(struct net *net, u16 encap_type, + struct nlattr *encap, + int oif, const struct fib_nh *nh) +{ + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + int ret; + + if (encap_type == LWTUNNEL_ENCAP_NONE) + return 0; + + if (oif) + dev = __dev_get_by_index(net, oif); + ret = lwtunnel_build_state(dev, encap_type, + encap, &lwtstate); + if (!ret) + return lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate); + + return 0; +} + int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) { + struct net *net = cfg->fc_nlinfo.nl_net; #ifdef CONFIG_IP_ROUTE_MULTIPATH struct rtnexthop *rtnh; int remaining; @@ -496,6 +566,12 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) return 1; if (cfg->fc_oif || cfg->fc_gw) { + if (cfg->fc_encap) { + if (fib_encap_match(net, cfg->fc_encap_type, + cfg->fc_encap, cfg->fc_oif, + fi->fib_nh)) + return 1; + } if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) return 0; @@ -882,6 +958,21 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } else { struct fib_nh *nh = fi->fib_nh; + if (cfg->fc_encap) { + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + + if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) + goto err_inval; + if (cfg->fc_oif) + dev = __dev_get_by_index(net, cfg->fc_oif); + err = lwtunnel_build_state(dev, cfg->fc_encap_type, + cfg->fc_encap, &lwtstate); + if (err) + goto failure; + + nh->nh_lwtstate = lwtstate_get(lwtstate); + } nh->nh_oif = cfg->fc_oif; nh->nh_gw = cfg->fc_gw; nh->nh_flags = cfg->fc_flags; @@ -1055,6 +1146,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) goto nla_put_failure; #endif + if (fi->fib_nh->nh_lwtstate) + lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate); } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fi->fib_nhs > 1) { @@ -1090,6 +1183,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) goto nla_put_failure; #endif + if (nh->nh_lwtstate) + lwtunnel_fill_encap(skb, nh->nh_lwtstate); /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; } endfor_nexthops(fi); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 4a7b5b2..d9c552a 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -31,7 +31,6 @@ #include <net/xfrm.h> static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly; -static struct gre_cisco_protocol __rcu *gre_cisco_proto_list[GRE_IP_PROTO_MAX]; int gre_add_protocol(const struct gre_protocol *proto, u8 version) { @@ -61,197 +60,6 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version) } EXPORT_SYMBOL_GPL(gre_del_protocol); -void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi, - int hdr_len) -{ - struct gre_base_hdr *greh; - - skb_push(skb, hdr_len); - - skb_reset_transport_header(skb); - greh = (struct gre_base_hdr *)skb->data; - greh->flags = tnl_flags_to_gre_flags(tpi->flags); - greh->protocol = tpi->proto; - - if (tpi->flags&(TUNNEL_KEY|TUNNEL_CSUM|TUNNEL_SEQ)) { - __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); - - if (tpi->flags&TUNNEL_SEQ) { - *ptr = tpi->seq; - ptr--; - } - if (tpi->flags&TUNNEL_KEY) { - *ptr = tpi->key; - ptr--; - } - if (tpi->flags&TUNNEL_CSUM && - !(skb_shinfo(skb)->gso_type & - (SKB_GSO_GRE|SKB_GSO_GRE_CSUM))) { - *ptr = 0; - *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0, - skb->len, 0)); - } - } -} -EXPORT_SYMBOL_GPL(gre_build_header); - -static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, - bool *csum_err) -{ - const struct gre_base_hdr *greh; - __be32 *options; - int hdr_len; - - if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr)))) - return -EINVAL; - - greh = (struct gre_base_hdr *)skb_transport_header(skb); - if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) - return -EINVAL; - - tpi->flags = gre_flags_to_tnl_flags(greh->flags); - hdr_len = ip_gre_calc_hlen(tpi->flags); - - if (!pskb_may_pull(skb, hdr_len)) - return -EINVAL; - - greh = (struct gre_base_hdr *)skb_transport_header(skb); - tpi->proto = greh->protocol; - - options = (__be32 *)(greh + 1); - if (greh->flags & GRE_CSUM) { - if (skb_checksum_simple_validate(skb)) { - *csum_err = true; - return -EINVAL; - } - - skb_checksum_try_convert(skb, IPPROTO_GRE, 0, - null_compute_pseudo); - - options++; - } - - if (greh->flags & GRE_KEY) { - tpi->key = *options; - options++; - } else - tpi->key = 0; - - if (unlikely(greh->flags & GRE_SEQ)) { - tpi->seq = *options; - options++; - } else - tpi->seq = 0; - - /* WCCP version 1 and 2 protocol decoding. - * - Change protocol to IP - * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header - */ - if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { - tpi->proto = htons(ETH_P_IP); - if ((*(u8 *)options & 0xF0) != 0x40) { - hdr_len += 4; - if (!pskb_may_pull(skb, hdr_len)) - return -EINVAL; - } - } - - return iptunnel_pull_header(skb, hdr_len, tpi->proto); -} - -static int gre_cisco_rcv(struct sk_buff *skb) -{ - struct tnl_ptk_info tpi; - int i; - bool csum_err = false; - -#ifdef CONFIG_NET_IPGRE_BROADCAST - if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { - /* Looped back packet, drop it! */ - if (rt_is_output_route(skb_rtable(skb))) - goto drop; - } -#endif - - if (parse_gre_header(skb, &tpi, &csum_err) < 0) - goto drop; - - rcu_read_lock(); - for (i = 0; i < GRE_IP_PROTO_MAX; i++) { - struct gre_cisco_protocol *proto; - int ret; - - proto = rcu_dereference(gre_cisco_proto_list[i]); - if (!proto) - continue; - ret = proto->handler(skb, &tpi); - if (ret == PACKET_RCVD) { - rcu_read_unlock(); - return 0; - } - } - rcu_read_unlock(); - - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); -drop: - kfree_skb(skb); - return 0; -} - -static void gre_cisco_err(struct sk_buff *skb, u32 info) -{ - /* All the routers (except for Linux) return only - * 8 bytes of packet payload. It means, that precise relaying of - * ICMP in the real Internet is absolutely infeasible. - * - * Moreover, Cisco "wise men" put GRE key to the third word - * in GRE header. It makes impossible maintaining even soft - * state for keyed - * GRE tunnels with enabled checksum. Tell them "thank you". - * - * Well, I wonder, rfc1812 was written by Cisco employee, - * what the hell these idiots break standards established - * by themselves??? - */ - - const int type = icmp_hdr(skb)->type; - const int code = icmp_hdr(skb)->code; - struct tnl_ptk_info tpi; - bool csum_err = false; - int i; - - if (parse_gre_header(skb, &tpi, &csum_err)) { - if (!csum_err) /* ignore csum errors. */ - return; - } - - if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { - ipv4_update_pmtu(skb, dev_net(skb->dev), info, - skb->dev->ifindex, 0, IPPROTO_GRE, 0); - return; - } - if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, 0, - IPPROTO_GRE, 0); - return; - } - - rcu_read_lock(); - for (i = 0; i < GRE_IP_PROTO_MAX; i++) { - struct gre_cisco_protocol *proto; - - proto = rcu_dereference(gre_cisco_proto_list[i]); - if (!proto) - continue; - - if (proto->err_handler(skb, info, &tpi) == PACKET_RCVD) - goto out; - - } -out: - rcu_read_unlock(); -} - static int gre_rcv(struct sk_buff *skb) { const struct gre_protocol *proto; @@ -302,60 +110,19 @@ static const struct net_protocol net_gre_protocol = { .netns_ok = 1, }; -static const struct gre_protocol ipgre_protocol = { - .handler = gre_cisco_rcv, - .err_handler = gre_cisco_err, -}; - -int gre_cisco_register(struct gre_cisco_protocol *newp) -{ - struct gre_cisco_protocol **proto = (struct gre_cisco_protocol **) - &gre_cisco_proto_list[newp->priority]; - - return (cmpxchg(proto, NULL, newp) == NULL) ? 0 : -EBUSY; -} -EXPORT_SYMBOL_GPL(gre_cisco_register); - -int gre_cisco_unregister(struct gre_cisco_protocol *del_proto) -{ - struct gre_cisco_protocol **proto = (struct gre_cisco_protocol **) - &gre_cisco_proto_list[del_proto->priority]; - int ret; - - ret = (cmpxchg(proto, del_proto, NULL) == del_proto) ? 0 : -EINVAL; - - if (ret) - return ret; - - synchronize_net(); - return 0; -} -EXPORT_SYMBOL_GPL(gre_cisco_unregister); - static int __init gre_init(void) { pr_info("GRE over IPv4 demultiplexor driver\n"); if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) { pr_err("can't add protocol\n"); - goto err; - } - - if (gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0) { - pr_info("%s: can't add ipgre handler\n", __func__); - goto err_gre; + return -EAGAIN; } - return 0; -err_gre: - inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); -err: - return -EAGAIN; } static void __exit gre_exit(void) { - gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index f5203fb..c0556f1 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -496,6 +496,7 @@ static struct rtable *icmp_route_lookup(struct net *net, } /* Ugh! */ orefdst = skb_in->_skb_refdst; /* save old refdst */ + skb_dst_set(skb_in, NULL); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, RT_TOS(tos), rt2->dst.dev); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0cb9165..8912019 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -343,7 +343,6 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; - int twrefcnt = 0; spin_lock(lock); @@ -371,21 +370,17 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { - twrefcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); - if (twrefcnt) - inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw); - - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); } return 0; @@ -403,13 +398,12 @@ static u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) +void __inet_hash_nolisten(struct sock *sk, struct sock *osk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; struct inet_ehash_bucket *head; spinlock_t *lock; - int twrefcnt = 0; WARN_ON(!sk_unhashed(sk)); @@ -420,23 +414,22 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) spin_lock(lock); __sk_nulls_add_node_rcu(sk, list); - if (tw) { - WARN_ON(sk->sk_hash != tw->tw_hash); - twrefcnt = inet_twsk_unhash(tw); + if (osk) { + WARN_ON(sk->sk_hash != osk->sk_hash); + sk_nulls_del_node_init_rcu(osk); } spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - return twrefcnt; } EXPORT_SYMBOL_GPL(__inet_hash_nolisten); -int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw) +void __inet_hash(struct sock *sk, struct sock *osk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_listen_hashbucket *ilb; if (sk->sk_state != TCP_LISTEN) - return __inet_hash_nolisten(sk, tw); + return __inet_hash_nolisten(sk, osk); WARN_ON(!sk_unhashed(sk)); ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; @@ -445,7 +438,6 @@ int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw) __sk_nulls_add_node_rcu(sk, &ilb->head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); spin_unlock(&ilb->lock); - return 0; } EXPORT_SYMBOL(__inet_hash); @@ -492,7 +484,6 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct inet_bind_bucket *tb; int ret; struct net *net = sock_net(sk); - int twrefcnt = 1; if (!snum) { int i, remaining, low, high, port; @@ -560,19 +551,14 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - twrefcnt += __inet_hash_nolisten(sk, tw); + __inet_hash_nolisten(sk, (struct sock *)tw); } if (tw) - twrefcnt += inet_twsk_bind_unhash(tw, hinfo); + inet_twsk_bind_unhash(tw, hinfo); spin_unlock(&head->lock); - if (tw) { - inet_twsk_deschedule(tw); - while (twrefcnt) { - twrefcnt--; - inet_twsk_put(tw); - } - } + if (tw) + inet_twsk_deschedule_put(tw); ret = 0; goto out; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 2ffbd16..ae22cc2 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -18,28 +18,6 @@ /** - * inet_twsk_unhash - unhash a timewait socket from established hash - * @tw: timewait socket - * - * unhash a timewait socket from established hash, if hashed. - * ehash lock must be held by caller. - * Returns 1 if caller should call inet_twsk_put() after lock release. - */ -int inet_twsk_unhash(struct inet_timewait_sock *tw) -{ - if (hlist_nulls_unhashed(&tw->tw_node)) - return 0; - - hlist_nulls_del_rcu(&tw->tw_node); - sk_nulls_node_init(&tw->tw_node); - /* - * We cannot call inet_twsk_put() ourself under lock, - * caller must call it for us. - */ - return 1; -} - -/** * inet_twsk_bind_unhash - unhash a timewait socket from bind hash * @tw: timewait socket * @hashinfo: hashinfo pointer @@ -48,35 +26,29 @@ int inet_twsk_unhash(struct inet_timewait_sock *tw) * bind hash lock must be held by caller. * Returns 1 if caller should call inet_twsk_put() after lock release. */ -int inet_twsk_bind_unhash(struct inet_timewait_sock *tw, +void inet_twsk_bind_unhash(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) { struct inet_bind_bucket *tb = tw->tw_tb; if (!tb) - return 0; + return; __hlist_del(&tw->tw_bind_node); tw->tw_tb = NULL; inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); - /* - * We cannot call inet_twsk_put() ourself under lock, - * caller must call it for us. - */ - return 1; + __sock_put((struct sock *)tw); } /* Must be called with locally disabled BHs. */ static void inet_twsk_kill(struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo; - struct inet_bind_hashbucket *bhead; - int refcnt; - /* Unlink from established hashes. */ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); + struct inet_bind_hashbucket *bhead; spin_lock(lock); - refcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); spin_unlock(lock); /* Disassociate with bind bucket. */ @@ -84,11 +56,9 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) hashinfo->bhash_size)]; spin_lock(&bhead->lock); - refcnt += inet_twsk_bind_unhash(tw, hashinfo); + inet_twsk_bind_unhash(tw, hashinfo); spin_unlock(&bhead->lock); - BUG_ON(refcnt >= atomic_read(&tw->tw_refcnt)); - atomic_sub(refcnt, &tw->tw_refcnt); atomic_dec(&tw->tw_dr->tw_count); inet_twsk_put(tw); } @@ -235,13 +205,17 @@ EXPORT_SYMBOL_GPL(inet_twsk_alloc); * tcp_input.c to verify this. */ -/* This is for handling early-kills of TIME_WAIT sockets. */ -void inet_twsk_deschedule(struct inet_timewait_sock *tw) +/* This is for handling early-kills of TIME_WAIT sockets. + * Warning : consume reference. + * Caller should not access tw anymore. + */ +void inet_twsk_deschedule_put(struct inet_timewait_sock *tw) { if (del_timer_sync(&tw->tw_timer)) inet_twsk_kill(tw); + inet_twsk_put(tw); } -EXPORT_SYMBOL(inet_twsk_deschedule); +EXPORT_SYMBOL(inet_twsk_deschedule_put); void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) { @@ -311,9 +285,8 @@ restart: rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule(tw); + inet_twsk_deschedule_put(tw); local_bh_enable(); - inet_twsk_put(tw); goto restart_rcu; } /* If the nulls value we got at the end of this lookup is diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 921138f..d96722a 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -522,7 +522,6 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, int len; int ihlen; int err; - int sum_truesize; u8 ecn; ipq_kill(qp); @@ -590,32 +589,19 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, add_frag_mem_limit(qp->q.net, clone->truesize); } + skb_shinfo(head)->frag_list = head->next; skb_push(head, head->data - skb_network_header(head)); - sum_truesize = head->truesize; - for (fp = head->next; fp;) { - bool headstolen; - int delta; - struct sk_buff *next = fp->next; - - sum_truesize += fp->truesize; + for (fp=head->next; fp; fp = fp->next) { + head->data_len += fp->len; + head->len += fp->len; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); - - if (skb_try_coalesce(head, fp, &headstolen, &delta)) { - kfree_skb_partial(fp, headstolen); - } else { - if (!skb_shinfo(head)->frag_list) - skb_shinfo(head)->frag_list = fp; - head->data_len += fp->len; - head->len += fp->len; - head->truesize += fp->truesize; - } - fp = next; + head->truesize += fp->truesize; } - sub_frag_mem_limit(qp->q.net, sum_truesize); + sub_frag_mem_limit(qp->q.net, head->truesize); head->next = NULL; head->dev = dev; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5fd7064..fb44d69 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -25,6 +25,7 @@ #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/mroute.h> +#include <linux/if_vlan.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> @@ -47,6 +48,7 @@ #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/gre.h> +#include <net/dst_metadata.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -121,8 +123,127 @@ static int ipgre_tunnel_init(struct net_device *dev); static int ipgre_net_id __read_mostly; static int gre_tap_net_id __read_mostly; -static int ipgre_err(struct sk_buff *skb, u32 info, - const struct tnl_ptk_info *tpi) +static int ip_gre_calc_hlen(__be16 o_flags) +{ + int addend = 4; + + if (o_flags & TUNNEL_CSUM) + addend += 4; + if (o_flags & TUNNEL_KEY) + addend += 4; + if (o_flags & TUNNEL_SEQ) + addend += 4; + return addend; +} + +static __be16 gre_flags_to_tnl_flags(__be16 flags) +{ + __be16 tflags = 0; + + if (flags & GRE_CSUM) + tflags |= TUNNEL_CSUM; + if (flags & GRE_ROUTING) + tflags |= TUNNEL_ROUTING; + if (flags & GRE_KEY) + tflags |= TUNNEL_KEY; + if (flags & GRE_SEQ) + tflags |= TUNNEL_SEQ; + if (flags & GRE_STRICT) + tflags |= TUNNEL_STRICT; + if (flags & GRE_REC) + tflags |= TUNNEL_REC; + if (flags & GRE_VERSION) + tflags |= TUNNEL_VERSION; + + return tflags; +} + +static __be16 tnl_flags_to_gre_flags(__be16 tflags) +{ + __be16 flags = 0; + + if (tflags & TUNNEL_CSUM) + flags |= GRE_CSUM; + if (tflags & TUNNEL_ROUTING) + flags |= GRE_ROUTING; + if (tflags & TUNNEL_KEY) + flags |= GRE_KEY; + if (tflags & TUNNEL_SEQ) + flags |= GRE_SEQ; + if (tflags & TUNNEL_STRICT) + flags |= GRE_STRICT; + if (tflags & TUNNEL_REC) + flags |= GRE_REC; + if (tflags & TUNNEL_VERSION) + flags |= GRE_VERSION; + + return flags; +} + +static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, + bool *csum_err) +{ + const struct gre_base_hdr *greh; + __be32 *options; + int hdr_len; + + if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr)))) + return -EINVAL; + + greh = (struct gre_base_hdr *)skb_transport_header(skb); + if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) + return -EINVAL; + + tpi->flags = gre_flags_to_tnl_flags(greh->flags); + hdr_len = ip_gre_calc_hlen(tpi->flags); + + if (!pskb_may_pull(skb, hdr_len)) + return -EINVAL; + + greh = (struct gre_base_hdr *)skb_transport_header(skb); + tpi->proto = greh->protocol; + + options = (__be32 *)(greh + 1); + if (greh->flags & GRE_CSUM) { + if (skb_checksum_simple_validate(skb)) { + *csum_err = true; + return -EINVAL; + } + + skb_checksum_try_convert(skb, IPPROTO_GRE, 0, + null_compute_pseudo); + options++; + } + + if (greh->flags & GRE_KEY) { + tpi->key = *options; + options++; + } else { + tpi->key = 0; + } + if (unlikely(greh->flags & GRE_SEQ)) { + tpi->seq = *options; + options++; + } else { + tpi->seq = 0; + } + /* WCCP version 1 and 2 protocol decoding. + * - Change protocol to IP + * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header + */ + if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { + tpi->proto = htons(ETH_P_IP); + if ((*(u8 *)options & 0xF0) != 0x40) { + hdr_len += 4; + if (!pskb_may_pull(skb, hdr_len)) + return -EINVAL; + } + } + return iptunnel_pull_header(skb, hdr_len, tpi->proto); +} + +static void ipgre_err(struct sk_buff *skb, u32 info, + const struct tnl_ptk_info *tpi) { /* All the routers (except for Linux) return only @@ -148,14 +269,14 @@ static int ipgre_err(struct sk_buff *skb, u32 info, switch (type) { default: case ICMP_PARAMETERPROB: - return PACKET_RCVD; + return; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: case ICMP_PORT_UNREACH: /* Impossible event. */ - return PACKET_RCVD; + return; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, @@ -164,9 +285,10 @@ static int ipgre_err(struct sk_buff *skb, u32 info, break; } break; + case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) - return PACKET_RCVD; + return; break; case ICMP_REDIRECT: @@ -183,26 +305,85 @@ static int ipgre_err(struct sk_buff *skb, u32 info, iph->daddr, iph->saddr, tpi->key); if (!t) - return PACKET_REJECT; + return; if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) - return PACKET_RCVD; + return; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) - return PACKET_RCVD; + return; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; - return PACKET_RCVD; +} + +static void gre_err(struct sk_buff *skb, u32 info) +{ + /* All the routers (except for Linux) return only + * 8 bytes of packet payload. It means, that precise relaying of + * ICMP in the real Internet is absolutely infeasible. + * + * Moreover, Cisco "wise men" put GRE key to the third word + * in GRE header. It makes impossible maintaining even soft + * state for keyed + * GRE tunnels with enabled checksum. Tell them "thank you". + * + * Well, I wonder, rfc1812 was written by Cisco employee, + * what the hell these idiots break standards established + * by themselves??? + */ + + const int type = icmp_hdr(skb)->type; + const int code = icmp_hdr(skb)->code; + struct tnl_ptk_info tpi; + bool csum_err = false; + + if (parse_gre_header(skb, &tpi, &csum_err)) { + if (!csum_err) /* ignore csum errors. */ + return; + } + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { + ipv4_update_pmtu(skb, dev_net(skb->dev), info, + skb->dev->ifindex, 0, IPPROTO_GRE, 0); + return; + } + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, 0, + IPPROTO_GRE, 0); + return; + } + + ipgre_err(skb, info, &tpi); +} + +static __be64 key_to_tunnel_id(__be32 key) +{ +#ifdef __BIG_ENDIAN + return (__force __be64)((__force u32)key); +#else + return (__force __be64)((__force u64)key << 32); +#endif +} + +/* Returns the least-significant 32 bits of a __be64. */ +static __be32 tunnel_id_to_key(__be64 x) +{ +#ifdef __BIG_ENDIAN + return (__force __be32)x; +#else + return (__force __be32)((__force u64)x >> 32); +#endif } static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) { struct net *net = dev_net(skb->dev); + struct metadata_dst *tun_dst = NULL; struct ip_tunnel_net *itn; const struct iphdr *iph; struct ip_tunnel *tunnel; @@ -218,40 +399,194 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) if (tunnel) { skb_pop_mac_header(skb); - ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error); + if (tunnel->collect_md) { + struct ip_tunnel_info *info; + + tun_dst = metadata_dst_alloc(0, GFP_ATOMIC); + if (!tun_dst) + return PACKET_REJECT; + + info = &tun_dst->u.tun_info; + info->key.ipv4_src = iph->saddr; + info->key.ipv4_dst = iph->daddr; + info->key.ipv4_tos = iph->tos; + info->key.ipv4_ttl = iph->ttl; + + info->mode = IP_TUNNEL_INFO_RX; + info->key.tun_flags = tpi->flags & + (TUNNEL_CSUM | TUNNEL_KEY); + info->key.tun_id = key_to_tunnel_id(tpi->key); + + info->key.tp_src = 0; + info->key.tp_dst = 0; + } + + ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_REJECT; } +static int gre_rcv(struct sk_buff *skb) +{ + struct tnl_ptk_info tpi; + bool csum_err = false; + +#ifdef CONFIG_NET_IPGRE_BROADCAST + if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { + /* Looped back packet, drop it! */ + if (rt_is_output_route(skb_rtable(skb))) + goto drop; + } +#endif + + if (parse_gre_header(skb, &tpi, &csum_err) < 0) + goto drop; + + if (ipgre_rcv(skb, &tpi) == PACKET_RCVD) + return 0; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); +drop: + kfree_skb(skb); + return 0; +} + +static void build_header(struct sk_buff *skb, int hdr_len, __be16 flags, + __be16 proto, __be32 key, __be32 seq) +{ + struct gre_base_hdr *greh; + + skb_push(skb, hdr_len); + + skb_reset_transport_header(skb); + greh = (struct gre_base_hdr *)skb->data; + greh->flags = tnl_flags_to_gre_flags(flags); + greh->protocol = proto; + + if (flags & (TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_SEQ)) { + __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); + + if (flags & TUNNEL_SEQ) { + *ptr = seq; + ptr--; + } + if (flags & TUNNEL_KEY) { + *ptr = key; + ptr--; + } + if (flags & TUNNEL_CSUM && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { + *ptr = 0; + *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0, + skb->len, 0)); + } + } +} + static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct tnl_ptk_info tpi; - tpi.flags = tunnel->parms.o_flags; - tpi.proto = proto; - tpi.key = tunnel->parms.o_key; if (tunnel->parms.o_flags & TUNNEL_SEQ) tunnel->o_seqno++; - tpi.seq = htonl(tunnel->o_seqno); /* Push GRE header. */ - gre_build_header(skb, &tpi, tunnel->tun_hlen); - - skb_set_inner_protocol(skb, tpi.proto); + build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, + proto, tunnel->parms.o_key, htonl(tunnel->o_seqno)); + skb_set_inner_protocol(skb, proto); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } +static struct sk_buff *gre_handle_offloads(struct sk_buff *skb, + bool csum) +{ + return iptunnel_handle_offloads(skb, csum, + csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); +} + +static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel_info *tun_info; + struct net *net = dev_net(dev); + const struct ip_tunnel_key *key; + struct flowi4 fl; + struct rtable *rt; + int min_headroom; + int tunnel_hlen; + __be16 df, flags; + int err; + + tun_info = skb_tunnel_info(skb, AF_INET); + if (unlikely(!tun_info || tun_info->mode != IP_TUNNEL_INFO_TX)) + goto err_free_skb; + + key = &tun_info->key; + memset(&fl, 0, sizeof(fl)); + fl.daddr = key->ipv4_dst; + fl.saddr = key->ipv4_src; + fl.flowi4_tos = RT_TOS(key->ipv4_tos); + fl.flowi4_mark = skb->mark; + fl.flowi4_proto = IPPROTO_GRE; + + rt = ip_route_output_key(net, &fl); + if (IS_ERR(rt)) + goto err_free_skb; + + tunnel_hlen = ip_gre_calc_hlen(key->tun_flags); + + min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + + tunnel_hlen + sizeof(struct iphdr); + if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) { + int head_delta = SKB_DATA_ALIGN(min_headroom - + skb_headroom(skb) + + 16); + err = pskb_expand_head(skb, max_t(int, head_delta, 0), + 0, GFP_ATOMIC); + if (unlikely(err)) + goto err_free_rt; + } + + /* Push Tunnel header. */ + skb = gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM)); + if (IS_ERR(skb)) { + skb = NULL; + goto err_free_rt; + } + + flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); + build_header(skb, tunnel_hlen, flags, htons(ETH_P_TEB), + tunnel_id_to_key(tun_info->key.tun_id), 0); + + df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + err = iptunnel_xmit(skb->sk, rt, skb, fl.saddr, + key->ipv4_dst, IPPROTO_GRE, + key->ipv4_tos, key->ipv4_ttl, df, false); + iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + return; + +err_free_rt: + ip_rt_put(rt); +err_free_skb: + kfree_skb(skb); + dev->stats.tx_dropped++; +} + static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; + if (tunnel->collect_md) { + gre_fb_xmit(skb, dev); + return NETDEV_TX_OK; + } + if (dev->header_ops) { /* Need space for new headers */ if (skb_cow_head(skb, dev->needed_headroom - @@ -277,7 +612,6 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, goto out; __gre_xmit(skb, dev, tnl_params, skb->protocol); - return NETDEV_TX_OK; free_skb: @@ -292,6 +626,11 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, { struct ip_tunnel *tunnel = netdev_priv(dev); + if (tunnel->collect_md) { + gre_fb_xmit(skb, dev); + return NETDEV_TX_OK; + } + skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM)); if (IS_ERR(skb)) goto out; @@ -300,7 +639,6 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, goto free_skb; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB)); - return NETDEV_TX_OK; free_skb: @@ -530,10 +868,9 @@ static int ipgre_tunnel_init(struct net_device *dev) return ip_tunnel_init(dev); } -static struct gre_cisco_protocol ipgre_protocol = { - .handler = ipgre_rcv, - .err_handler = ipgre_err, - .priority = 0, +static const struct gre_protocol ipgre_protocol = { + .handler = gre_rcv, + .err_handler = gre_err, }; static int __net_init ipgre_init_net(struct net *net) @@ -596,8 +933,10 @@ out: return ipgre_tunnel_validate(tb, data); } -static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[], - struct ip_tunnel_parm *parms) +static void ipgre_netlink_parms(struct net_device *dev, + struct nlattr *data[], + struct nlattr *tb[], + struct ip_tunnel_parm *parms) { memset(parms, 0, sizeof(*parms)); @@ -635,6 +974,12 @@ static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[], if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); + + if (data[IFLA_GRE_COLLECT_METADATA]) { + struct ip_tunnel *t = netdev_priv(dev); + + t->collect_md = true; + } } /* This function returns true when ENCAP attributes are present in the nl msg */ @@ -712,7 +1057,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, return err; } - ipgre_netlink_parms(data, tb, &p); + ipgre_netlink_parms(dev, data, tb, &p); return ip_tunnel_newlink(dev, tb, &p); } @@ -730,7 +1075,7 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], return err; } - ipgre_netlink_parms(data, tb, &p); + ipgre_netlink_parms(dev, data, tb, &p); return ip_tunnel_changelink(dev, tb, &p); } @@ -765,6 +1110,8 @@ static size_t ipgre_get_size(const struct net_device *dev) nla_total_size(2) + /* IFLA_GRE_ENCAP_DPORT */ nla_total_size(2) + + /* IFLA_GRE_COLLECT_METADATA */ + nla_total_size(0) + 0; } @@ -796,6 +1143,11 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) t->encap.flags)) goto nla_put_failure; + if (t->collect_md) { + if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA)) + goto nla_put_failure; + } + return 0; nla_put_failure: @@ -817,6 +1169,7 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 }, + [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG }, }; static struct rtnl_link_ops ipgre_link_ops __read_mostly = { @@ -849,9 +1202,38 @@ static struct rtnl_link_ops ipgre_tap_ops __read_mostly = { .get_link_net = ip_tunnel_get_link_net, }; +struct net_device *gretap_fb_dev_create(struct net *net, const char *name, + u8 name_assign_type) +{ + struct nlattr *tb[IFLA_MAX + 1]; + struct net_device *dev; + struct ip_tunnel *t; + int err; + + memset(&tb, 0, sizeof(tb)); + + dev = rtnl_create_link(net, name, name_assign_type, + &ipgre_tap_ops, tb); + if (IS_ERR(dev)) + return dev; + + /* Configure flow based GRE device. */ + t = netdev_priv(dev); + t->collect_md = true; + + err = ipgre_newlink(net, dev, tb, NULL); + if (err < 0) + goto out; + return dev; +out: + free_netdev(dev); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(gretap_fb_dev_create); + static int __net_init ipgre_tap_init_net(struct net *net) { - return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, NULL); + return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } static void __net_exit ipgre_tap_exit_net(struct net *net) @@ -881,7 +1263,7 @@ static int __init ipgre_init(void) if (err < 0) goto pnet_tap_faied; - err = gre_cisco_register(&ipgre_protocol); + err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; @@ -900,7 +1282,7 @@ static int __init ipgre_init(void) tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: - gre_cisco_unregister(&ipgre_protocol); + gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: unregister_pernet_device(&ipgre_tap_net_ops); pnet_tap_faied: @@ -912,7 +1294,7 @@ static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); - gre_cisco_unregister(&ipgre_protocol); + gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); unregister_pernet_device(&ipgre_tap_net_ops); unregister_pernet_device(&ipgre_net_ops); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 2db4c87..f4fc8a7 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -146,6 +146,7 @@ #include <net/xfrm.h> #include <linux/mroute.h> #include <linux/netlink.h> +#include <net/dst_metadata.h> /* * Process Router Attention IP option (RFC 2113) @@ -331,7 +332,7 @@ static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb) * Initialise the virtual path cache for the packet. It describes * how the packet travels inside Linux networking. */ - if (!skb_dst(skb)) { + if (!skb_valid_dst(skb)) { int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, iph->tos, skb->dev); if (unlikely(err)) { diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 626d9e5..cbb51f3 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -230,10 +230,13 @@ skip_key_lookup: if (cand) return cand; + t = rcu_dereference(itn->collect_md_tun); + if (t) + return t; + if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP) return netdev_priv(itn->fb_tunnel_dev); - return NULL; } EXPORT_SYMBOL_GPL(ip_tunnel_lookup); @@ -261,11 +264,15 @@ static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t) { struct hlist_head *head = ip_bucket(itn, &t->parms); + if (t->collect_md) + rcu_assign_pointer(itn->collect_md_tun, t); hlist_add_head_rcu(&t->hash_node, head); } -static void ip_tunnel_del(struct ip_tunnel *t) +static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t) { + if (t->collect_md) + rcu_assign_pointer(itn->collect_md_tun, NULL); hlist_del_init_rcu(&t->hash_node); } @@ -419,7 +426,8 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, } int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, - const struct tnl_ptk_info *tpi, bool log_ecn_error) + const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, + bool log_ecn_error) { struct pcpu_sw_netstats *tstats; const struct iphdr *iph = ip_hdr(skb); @@ -478,6 +486,9 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, skb->dev = tunnel->dev; } + if (tun_dst) + skb_dst_set(skb, (struct dst_entry *)tun_dst); + gro_cells_receive(&tunnel->gro_cells, skb); return 0; @@ -806,7 +817,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, struct ip_tunnel_parm *p, bool set_mtu) { - ip_tunnel_del(t); + ip_tunnel_del(itn, t); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; t->parms.i_key = p->i_key; @@ -967,7 +978,7 @@ void ip_tunnel_dellink(struct net_device *dev, struct list_head *head) itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id); if (itn->fb_tunnel_dev != dev) { - ip_tunnel_del(netdev_priv(dev)); + ip_tunnel_del(itn, netdev_priv(dev)); unregister_netdevice_queue(dev, head); } } @@ -1072,8 +1083,13 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], nt = netdev_priv(dev); itn = net_generic(net, nt->ip_tnl_net_id); - if (ip_tunnel_find(itn, p, dev->type)) - return -EEXIST; + if (nt->collect_md) { + if (rtnl_dereference(itn->collect_md_tun)) + return -EEXIST; + } else { + if (ip_tunnel_find(itn, p, dev->type)) + return -EEXIST; + } nt->net = net; nt->parms = *p; @@ -1089,7 +1105,6 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], dev->mtu = mtu; ip_tunnel_add(itn, nt); - out: return err; } @@ -1163,6 +1178,10 @@ int ip_tunnel_init(struct net_device *dev) iph->version = 4; iph->ihl = 5; + if (tunnel->collect_md) { + dev->features |= NETIF_F_NETNS_LOCAL; + netif_keep_dst(dev); + } return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); @@ -1176,7 +1195,7 @@ void ip_tunnel_uninit(struct net_device *dev) itn = net_generic(net, tunnel->ip_tnl_net_id); /* fb_tunnel_dev will be unregisted in net-exit call. */ if (itn->fb_tunnel_dev != dev) - ip_tunnel_del(netdev_priv(dev)); + ip_tunnel_del(itn, netdev_priv(dev)); ip_tunnel_dst_reset_all(tunnel); } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6a51a71..5512f4e 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -32,6 +32,7 @@ #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> +#include <linux/static_key.h> #include <net/ip.h> #include <net/icmp.h> @@ -190,3 +191,123 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, return tot; } EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); + +static const struct nla_policy ip_tun_policy[IP_TUN_MAX + 1] = { + [IP_TUN_ID] = { .type = NLA_U64 }, + [IP_TUN_DST] = { .type = NLA_U32 }, + [IP_TUN_SRC] = { .type = NLA_U32 }, + [IP_TUN_TTL] = { .type = NLA_U8 }, + [IP_TUN_TOS] = { .type = NLA_U8 }, + [IP_TUN_SPORT] = { .type = NLA_U16 }, + [IP_TUN_DPORT] = { .type = NLA_U16 }, + [IP_TUN_FLAGS] = { .type = NLA_U16 }, +}; + +static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr, + struct lwtunnel_state **ts) +{ + struct ip_tunnel_info *tun_info; + struct lwtunnel_state *new_state; + struct nlattr *tb[IP_TUN_MAX + 1]; + int err; + + err = nla_parse_nested(tb, IP_TUN_MAX, attr, ip_tun_policy); + if (err < 0) + return err; + + new_state = lwtunnel_state_alloc(sizeof(*tun_info)); + if (!new_state) + return -ENOMEM; + + new_state->type = LWTUNNEL_ENCAP_IP; + + tun_info = lwt_tun_info(new_state); + + if (tb[IP_TUN_ID]) + tun_info->key.tun_id = nla_get_u64(tb[IP_TUN_ID]); + + if (tb[IP_TUN_DST]) + tun_info->key.ipv4_dst = nla_get_be32(tb[IP_TUN_DST]); + + if (tb[IP_TUN_SRC]) + tun_info->key.ipv4_src = nla_get_be32(tb[IP_TUN_SRC]); + + if (tb[IP_TUN_TTL]) + tun_info->key.ipv4_ttl = nla_get_u8(tb[IP_TUN_TTL]); + + if (tb[IP_TUN_TOS]) + tun_info->key.ipv4_tos = nla_get_u8(tb[IP_TUN_TOS]); + + if (tb[IP_TUN_SPORT]) + tun_info->key.tp_src = nla_get_be16(tb[IP_TUN_SPORT]); + + if (tb[IP_TUN_DPORT]) + tun_info->key.tp_dst = nla_get_be16(tb[IP_TUN_DPORT]); + + if (tb[IP_TUN_FLAGS]) + tun_info->key.tun_flags = nla_get_u16(tb[IP_TUN_FLAGS]); + + tun_info->mode = IP_TUNNEL_INFO_TX; + tun_info->options = NULL; + tun_info->options_len = 0; + + *ts = new_state; + + return 0; +} + +static int ip_tun_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); + + if (nla_put_u64(skb, IP_TUN_ID, tun_info->key.tun_id) || + nla_put_be32(skb, IP_TUN_DST, tun_info->key.ipv4_dst) || + nla_put_be32(skb, IP_TUN_SRC, tun_info->key.ipv4_src) || + nla_put_u8(skb, IP_TUN_TOS, tun_info->key.ipv4_tos) || + nla_put_u8(skb, IP_TUN_TTL, tun_info->key.ipv4_ttl) || + nla_put_u16(skb, IP_TUN_SPORT, tun_info->key.tp_src) || + nla_put_u16(skb, IP_TUN_DPORT, tun_info->key.tp_dst) || + nla_put_u16(skb, IP_TUN_FLAGS, tun_info->key.tun_flags)) + return -ENOMEM; + + return 0; +} + +static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + return nla_total_size(8) /* IP_TUN_ID */ + + nla_total_size(4) /* IP_TUN_DST */ + + nla_total_size(4) /* IP_TUN_SRC */ + + nla_total_size(1) /* IP_TUN_TOS */ + + nla_total_size(1) /* IP_TUN_TTL */ + + nla_total_size(2) /* IP_TUN_SPORT */ + + nla_total_size(2) /* IP_TUN_DPORT */ + + nla_total_size(2); /* IP_TUN_FLAGS */ +} + +static const struct lwtunnel_encap_ops ip_tun_lwt_ops = { + .build_state = ip_tun_build_state, + .fill_encap = ip_tun_fill_encap_info, + .get_encap_size = ip_tun_encap_nlsize, +}; + +void __init ip_tunnel_core_init(void) +{ + lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP); +} + +struct static_key ip_tunnel_metadata_cnt = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL(ip_tunnel_metadata_cnt); + +void ip_tunnel_need_metadata(void) +{ + static_key_slow_inc(&ip_tunnel_metadata_cnt); +} +EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata); + +void ip_tunnel_unneed_metadata(void) +{ + static_key_slow_dec(&ip_tunnel_metadata_cnt); +} +EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 8e7328c..ed4ef09 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -94,7 +94,7 @@ /* Define the timeout for waiting for a DHCP/BOOTP/RARP reply */ #define CONF_OPEN_RETRIES 2 /* (Re)open devices twice */ #define CONF_SEND_RETRIES 6 /* Send six requests per open */ -#define CONF_INTER_TIMEOUT (HZ/2) /* Inter-device timeout: 1/2 second */ +#define CONF_INTER_TIMEOUT (HZ) /* Inter-device timeout: 1 second */ #define CONF_BASE_TIMEOUT (HZ*2) /* Initial timeout: 2 seconds */ #define CONF_TIMEOUT_RANDOM (HZ) /* Maximum amount of randomization */ #define CONF_TIMEOUT_MULT *7/4 /* Rate of timeout growth */ diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 254238d..f34c31d 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -198,7 +198,7 @@ static int ipip_rcv(struct sk_buff *skb) goto drop; if (iptunnel_pull_header(skb, 0, tpi.proto)) goto drop; - return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); + return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error); } return -1; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 92305a1..c416cb3 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -240,7 +240,7 @@ get_entry(const void *base, unsigned int offset) return (struct arpt_entry *)(base + offset); } -static inline __pure +static inline struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) { return (void *)entry + entry->next_offset; @@ -280,6 +280,9 @@ unsigned int arpt_do_table(struct sk_buff *skb, table_base = private->entries; jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; + /* No TEE support for arptables, so no need to switch to alternate + * stack. All targets that reenter must return absolute verdicts. + */ e = get_entry(table_base, private->hook_entry[hook]); acpar.in = state->in; @@ -325,11 +328,6 @@ unsigned int arpt_do_table(struct sk_buff *skb, } if (table_base + v != arpt_next_entry(e)) { - - if (stackidx >= private->stacksize) { - verdict = NF_DROP; - break; - } jumpstack[stackidx++] = e; } @@ -337,9 +335,6 @@ unsigned int arpt_do_table(struct sk_buff *skb, continue; } - /* Targets which reenter must return - * abs. verdicts - */ acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); @@ -372,10 +367,13 @@ static inline bool unconditional(const struct arpt_arp *arp) /* Figures out from what hook each rule can be called: returns 0 if * there are loops. Puts hook bitmask in comefrom. + * + * Keeps track of largest call depth seen and stores it in newinfo->stacksize. */ -static int mark_source_chains(const struct xt_table_info *newinfo, +static int mark_source_chains(struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { + unsigned int calldepth, max_calldepth = 0; unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset @@ -391,6 +389,7 @@ static int mark_source_chains(const struct xt_table_info *newinfo, /* Set initial back pointer. */ e->counters.pcnt = pos; + calldepth = 0; for (;;) { const struct xt_standard_target *t @@ -445,6 +444,8 @@ static int mark_source_chains(const struct xt_table_info *newinfo, (entry0 + pos + size); e->counters.pcnt = pos; pos += size; + if (calldepth > 0) + --calldepth; } else { int newpos = t->verdict; @@ -459,6 +460,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo, return 0; } + if (entry0 + newpos != arpt_next_entry(e) && + ++calldepth > max_calldepth) + max_calldepth = calldepth; + /* This a jump; chase it. */ duprintf("Jump rule %u -> %u\n", pos, newpos); @@ -475,6 +480,7 @@ static int mark_source_chains(const struct xt_table_info *newinfo, next: duprintf("Finished chain %u\n", hook); } + newinfo->stacksize = max_calldepth; return 1; } @@ -664,9 +670,6 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, if (ret != 0) break; ++i; - if (strcmp(arpt_get_target(iter)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; } duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret); if (ret != 0) @@ -1439,9 +1442,6 @@ static int translate_compat_table(const char *name, break; } ++i; - if (strcmp(arpt_get_target(iter1)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; } if (ret) { /* diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 6c72fbb..787f99e 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -276,7 +276,7 @@ static void trace_packet(const struct sk_buff *skb, } #endif -static inline __pure +static inline struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) { return (void *)entry + entry->next_offset; @@ -296,12 +296,13 @@ ipt_do_table(struct sk_buff *skb, const char *indev, *outdev; const void *table_base; struct ipt_entry *e, **jumpstack; - unsigned int *stackptr, origptr, cpu; + unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ + stackidx = 0; ip = ip_hdr(skb); indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; @@ -331,13 +332,21 @@ ipt_do_table(struct sk_buff *skb, smp_read_barrier_depends(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; - stackptr = per_cpu_ptr(private->stackptr, cpu); - origptr = *stackptr; + + /* Switch to alternate jumpstack if we're being invoked via TEE. + * TEE issues XT_CONTINUE verdict on original skb so we must not + * clobber the jumpstack. + * + * For recursion via REJECT or SYNPROXY the stack will be clobbered + * but it is no problem since absolute verdict is issued by these. + */ + if (static_key_false(&xt_tee_enabled)) + jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); e = get_entry(table_base, private->hook_entry[hook]); - pr_debug("Entering %s(hook %u); sp at %u (UF %p)\n", - table->name, hook, origptr, + pr_debug("Entering %s(hook %u), UF %p\n", + table->name, hook, get_entry(table_base, private->underflow[hook])); do { @@ -383,28 +392,24 @@ ipt_do_table(struct sk_buff *skb, verdict = (unsigned int)(-v) - 1; break; } - if (*stackptr <= origptr) { + if (stackidx == 0) { e = get_entry(table_base, private->underflow[hook]); pr_debug("Underflow (this is normal) " "to %p\n", e); } else { - e = jumpstack[--*stackptr]; + e = jumpstack[--stackidx]; pr_debug("Pulled %p out from pos %u\n", - e, *stackptr); + e, stackidx); e = ipt_next_entry(e); } continue; } if (table_base + v != ipt_next_entry(e) && !(e->ip.flags & IPT_F_GOTO)) { - if (*stackptr >= private->stacksize) { - verdict = NF_DROP; - break; - } - jumpstack[(*stackptr)++] = e; + jumpstack[stackidx++] = e; pr_debug("Pushed %p into pos %u\n", - e, *stackptr - 1); + e, stackidx - 1); } e = get_entry(table_base, v); @@ -423,9 +428,8 @@ ipt_do_table(struct sk_buff *skb, /* Verdict */ break; } while (!acpar.hotdrop); - pr_debug("Exiting %s; resetting sp from %u to %u\n", - __func__, *stackptr, origptr); - *stackptr = origptr; + pr_debug("Exiting %s; sp at %u\n", __func__, stackidx); + xt_write_recseq_end(addend); local_bh_enable(); @@ -439,11 +443,15 @@ ipt_do_table(struct sk_buff *skb, } /* Figures out from what hook each rule can be called: returns 0 if - there are loops. Puts hook bitmask in comefrom. */ + * there are loops. Puts hook bitmask in comefrom. + * + * Keeps track of largest call depth seen and stores it in newinfo->stacksize. + */ static int -mark_source_chains(const struct xt_table_info *newinfo, +mark_source_chains(struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { + unsigned int calldepth, max_calldepth = 0; unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset @@ -457,6 +465,7 @@ mark_source_chains(const struct xt_table_info *newinfo, /* Set initial back pointer. */ e->counters.pcnt = pos; + calldepth = 0; for (;;) { const struct xt_standard_target *t @@ -518,6 +527,9 @@ mark_source_chains(const struct xt_table_info *newinfo, (entry0 + pos + size); e->counters.pcnt = pos; pos += size; + WARN_ON_ONCE(calldepth == 0); + if (calldepth > 0) + --calldepth; } else { int newpos = t->verdict; @@ -531,9 +543,14 @@ mark_source_chains(const struct xt_table_info *newinfo, newpos); return 0; } + if (entry0 + newpos != ipt_next_entry(e) && + !(e->ip.flags & IPT_F_GOTO) && + ++calldepth > max_calldepth) + max_calldepth = calldepth; + /* This a jump; chase it. */ - duprintf("Jump rule %u -> %u\n", - pos, newpos); + duprintf("Jump rule %u -> %u, calldepth %d\n", + pos, newpos, calldepth); } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; @@ -547,6 +564,7 @@ mark_source_chains(const struct xt_table_info *newinfo, next: duprintf("Finished chain %u\n", hook); } + newinfo->stacksize = max_calldepth; return 1; } @@ -826,9 +844,6 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, if (ret != 0) return ret; ++i; - if (strcmp(ipt_get_target(iter)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; } if (i != repl->num_entries) { @@ -1744,9 +1759,6 @@ translate_compat_table(struct net *net, if (ret != 0) break; ++i; - if (strcmp(ipt_get_target(iter1)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; } if (ret) { /* diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index c88b7d4..b69e82b 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -49,12 +49,9 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, if (skb->nfct) zone = nf_ct_zone((struct nf_conn *)skb->nfct); #endif - -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - if (skb->nf_bridge && - skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) + if (nf_bridge_in_prerouting(skb)) return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone; -#endif + if (hooknum == NF_INET_PRE_ROUTING) return IP_DEFRAG_CONNTRACK_IN + zone; else diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 05ff44b..e89094a 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -363,7 +363,8 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, scoped); rcu_read_unlock(); - if (!(isk->freebind || isk->transparent || has_addr || + if (!(net->ipv6.sysctl.ip_nonlocal_bind || + isk->freebind || isk->transparent || has_addr || addr_type == IPV6_ADDR_ANY)) return -EADDRNOTAVAIL; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index da5d483..3abd9d7 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -300,6 +300,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE), SNMP_MIB_ITEM("TCPWinProbe", LINUX_MIB_TCPWINPROBE), SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE), + SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL), + SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e681b85..18fd7c9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -91,6 +91,7 @@ #include <linux/slab.h> #include <linux/jhash.h> #include <net/dst.h> +#include <net/dst_metadata.h> #include <net/net_namespace.h> #include <net/protocol.h> #include <net/ip.h> @@ -102,6 +103,7 @@ #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> +#include <net/lwtunnel.h> #include <net/netevent.h> #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL @@ -109,6 +111,7 @@ #include <linux/kmemleak.h> #endif #include <net/secure_seq.h> +#include <net/ip_tunnels.h> #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) @@ -1355,6 +1358,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst) list_del(&rt->rt_uncached); spin_unlock_bh(&ul->lock); } + lwtstate_put(rt->rt_lwtstate); } void rt_flush_dev(struct net_device *dev) @@ -1403,6 +1407,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif + rt->rt_lwtstate = lwtstate_get(nh->nh_lwtstate); if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr); else if (!(rt->dst.flags & DST_NOCACHE)) @@ -1488,6 +1493,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + rth->rt_lwtstate = NULL; if (our) { rth->dst.input= ip_local_deliver; rth->rt_flags |= RTCF_LOCAL; @@ -1546,7 +1552,6 @@ static int __mkroute_input(struct sk_buff *skb, struct rtable *rth; int err; struct in_device *out_dev; - unsigned int flags = 0; bool do_cache; u32 itag = 0; @@ -1610,7 +1615,7 @@ static int __mkroute_input(struct sk_buff *skb, } rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev)); - rth->rt_flags = flags; + rth->rt_flags = 0; rth->rt_type = res->type; rth->rt_is_input = 1; rth->rt_iif = 0; @@ -1618,12 +1623,15 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + rth->rt_lwtstate = NULL; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rth->dst.output = ip_output; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag); + if (lwtunnel_output_redirect(rth->rt_lwtstate)) + rth->dst.output = lwtunnel_output; skb_dst_set(skb, &rth->dst); out: err = 0; @@ -1662,6 +1670,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, { struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); + struct ip_tunnel_info *tun_info; struct flowi4 fl4; unsigned int flags = 0; u32 itag = 0; @@ -1679,6 +1688,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, by fib_lookup. */ + tun_info = skb_tunnel_info(skb, AF_INET); + if (tun_info && tun_info->mode == IP_TUNNEL_INFO_RX) + fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id; + else + fl4.flowi4_tun_key.tun_id = 0; + skb_dst_drop(skb); + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; @@ -1792,6 +1808,8 @@ local_input: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + rth->rt_lwtstate = NULL; + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; @@ -1981,7 +1999,7 @@ add: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); - + rth->rt_lwtstate = NULL; RT_CACHE_STAT_INC(out_slow_tot); if (flags & RTCF_LOCAL) @@ -2004,6 +2022,8 @@ add: } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0); + if (lwtunnel_output_redirect(rth->rt_lwtstate)) + rth->dst.output = lwtunnel_output; return rth; } @@ -2261,7 +2281,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_uses_gateway = ort->rt_uses_gateway; INIT_LIST_HEAD(&rt->rt_uncached); - + rt->rt_lwtstate = NULL; dst_free(new); } diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index c037644..fd1405d 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -146,7 +146,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { bictcp_update(ca, tp->snd_cwnd); diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 8c6fd3d..167b6a3 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -264,7 +264,7 @@ static void tcp_cdg_cong_avoid(struct sock *sk, u32 ack, u32 acked) u32 prior_snd_cwnd; u32 incr; - if (tp->snd_cwnd < tp->snd_ssthresh && hystart_detect) + if (tcp_in_slow_start(tp) && hystart_detect) tcp_cdg_hystart_update(sk); if (after(ack, ca->rtt_seq) && ca->rtt.v64) { diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 84be008..a2ed23c 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -365,10 +365,8 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) */ u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { - u32 cwnd = tp->snd_cwnd + acked; + u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh); - if (cwnd > tp->snd_ssthresh) - cwnd = tp->snd_ssthresh + 1; acked -= cwnd - tp->snd_cwnd; tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp); @@ -413,7 +411,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; /* In "safe" area, increase. */ - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 06d3d66..28011fb 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -320,7 +320,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { if (hystart && after(ack, ca->end_seq)) bictcp_hystart_reset(sk); acked = tcp_slow_start(tp, acked); @@ -439,7 +439,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) ca->delay_min = delay; /* hystart triggers when cwnd is larger than some threshold */ - if (hystart && tp->snd_cwnd <= tp->snd_ssthresh && + if (hystart && tcp_in_slow_start(tp) && tp->snd_cwnd >= hystart_low_window) hystart_update(sk, delay); } diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c index 882c08a..db78424 100644 --- a/net/ipv4/tcp_highspeed.c +++ b/net/ipv4/tcp_highspeed.c @@ -116,7 +116,7 @@ static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { /* Update AIMD parameters. diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 58469ff..82f0d9e 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -236,7 +236,7 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { /* In dangerous area, increase slowly. diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index f963b27..083831e 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -112,7 +112,7 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked) rho_fractions = ca->rho_3ls - (ca->rho << 3); - if (tp->snd_cwnd < tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { /* * slow start * INC = 2^RHO - 1 diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index f71002e..2ab9bbb 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -268,7 +268,7 @@ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; /* In slow start */ - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 728f5b3..4e4d6bc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -109,6 +109,7 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */ #define FLAG_DATA_SACKED 0x20 /* New SACK. */ #define FLAG_ECE 0x40 /* ECE in this ACK */ +#define FLAG_LOST_RETRANS 0x80 /* This ACK marks some retransmission lost */ #define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/ #define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ @@ -196,11 +197,13 @@ static void tcp_enter_quickack_mode(struct sock *sk) * and the session is not interactive. */ -static inline bool tcp_in_quickack_mode(const struct sock *sk) +static bool tcp_in_quickack_mode(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + const struct dst_entry *dst = __sk_dst_get(sk); - return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong; + return (dst && dst_metric(dst, RTAX_QUICKACK)) || + (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong); } static void tcp_ecn_queue_cwr(struct tcp_sock *tp) @@ -1037,7 +1040,7 @@ static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack, * highest SACK block). Also calculate the lowest snd_nxt among the remaining * retransmitted skbs to avoid some costly processing per ACKs. */ -static void tcp_mark_lost_retrans(struct sock *sk) +static void tcp_mark_lost_retrans(struct sock *sk, int *flag) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -1078,7 +1081,7 @@ static void tcp_mark_lost_retrans(struct sock *sk) if (after(received_upto, ack_seq)) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; tp->retrans_out -= tcp_skb_pcount(skb); - + *flag |= FLAG_LOST_RETRANS; tcp_skb_mark_lost_uncond_verify(tp, skb); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT); } else { @@ -1818,7 +1821,7 @@ advance_sp: ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) tcp_update_reordering(sk, tp->fackets_out - state->reord, 0); - tcp_mark_lost_retrans(sk); + tcp_mark_lost_retrans(sk, &state->flag); tcp_verify_left_out(tp); out: @@ -2474,15 +2477,14 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) return false; } -/* The cwnd reduction in CWR and Recovery use the PRR algorithm - * https://datatracker.ietf.org/doc/draft-ietf-tcpm-proportional-rate-reduction/ +/* The cwnd reduction in CWR and Recovery uses the PRR algorithm in RFC 6937. * It computes the number of packets to send (sndcnt) based on packets newly * delivered: * 1) If the packets in flight is larger than ssthresh, PRR spreads the * cwnd reductions across a full RTT. - * 2) If packets in flight is lower than ssthresh (such as due to excess - * losses and/or application stalls), do not perform any further cwnd - * reductions, but instead slow start up to ssthresh. + * 2) Otherwise PRR uses packet conservation to send as much as delivered. + * But when the retransmits are acked without further losses, PRR + * slow starts cwnd up to ssthresh to speed up the recovery. */ static void tcp_init_cwnd_reduction(struct sock *sk) { @@ -2499,7 +2501,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk) } static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, - int fast_rexmit) + int fast_rexmit, int flag) { struct tcp_sock *tp = tcp_sk(sk); int sndcnt = 0; @@ -2508,16 +2510,18 @@ static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, (tp->packets_out - tp->sacked_out); tp->prr_delivered += newly_acked_sacked; - if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { + if (delta < 0) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + tp->prior_cwnd - 1; sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; - } else { + } else if ((flag & FLAG_RETRANS_DATA_ACKED) && + !(flag & FLAG_LOST_RETRANS)) { sndcnt = min_t(int, delta, max_t(int, tp->prr_delivered - tp->prr_out, newly_acked_sacked) + 1); + } else { + sndcnt = min(delta, newly_acked_sacked); } - sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0)); tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; } @@ -2578,7 +2582,7 @@ static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked) if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { tcp_try_keep_open(sk); } else { - tcp_cwnd_reduction(sk, prior_unsacked, 0); + tcp_cwnd_reduction(sk, prior_unsacked, 0, flag); } } @@ -2588,6 +2592,7 @@ static void tcp_mtup_probe_failed(struct sock *sk) icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1; icsk->icsk_mtup.probe_size = 0; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMTUPFAIL); } static void tcp_mtup_probe_success(struct sock *sk) @@ -2607,6 +2612,7 @@ static void tcp_mtup_probe_success(struct sock *sk) icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; icsk->icsk_mtup.probe_size = 0; tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS); } /* Do a simple retransmit without using the backoff mechanisms in @@ -2675,7 +2681,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) tp->prior_ssthresh = 0; tcp_init_undo(tp); - if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { + if (!tcp_in_cwnd_reduction(sk)) { if (!ece_ack) tp->prior_ssthresh = tcp_current_ssthresh(sk); tcp_init_cwnd_reduction(sk); @@ -2735,7 +2741,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) /* Undo during fast recovery after partial ACK. */ static bool tcp_try_undo_partial(struct sock *sk, const int acked, - const int prior_unsacked) + const int prior_unsacked, int flag) { struct tcp_sock *tp = tcp_sk(sk); @@ -2751,7 +2757,7 @@ static bool tcp_try_undo_partial(struct sock *sk, const int acked, * mark more packets lost or retransmit more. */ if (tp->retrans_out) { - tcp_cwnd_reduction(sk, prior_unsacked, 0); + tcp_cwnd_reduction(sk, prior_unsacked, 0, flag); return true; } @@ -2838,7 +2844,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, if (tcp_is_reno(tp) && is_dupack) tcp_add_reno_sack(sk); } else { - if (tcp_try_undo_partial(sk, acked, prior_unsacked)) + if (tcp_try_undo_partial(sk, acked, prior_unsacked, flag)) return; /* Partial ACK arrived. Force fast retransmit. */ do_lost = tcp_is_reno(tp) || @@ -2851,9 +2857,10 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, break; case TCP_CA_Loss: tcp_process_loss(sk, flag, is_dupack); - if (icsk->icsk_ca_state != TCP_CA_Open) + if (icsk->icsk_ca_state != TCP_CA_Open && + !(flag & FLAG_LOST_RETRANS)) return; - /* Fall through to processing in Open state. */ + /* Change state if cwnd is undone or retransmits are lost */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) @@ -2888,7 +2895,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, if (do_lost) tcp_update_scoreboard(sk, fast_rexmit); - tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit); + tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit, flag); tcp_xmit_retransmit_queue(sk); } @@ -3562,10 +3569,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) &sack_state); acked -= tp->packets_out; - /* Advance cwnd if state allows */ - if (tcp_may_raise_cwnd(sk, flag)) - tcp_cong_avoid(sk, ack, acked); - if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, acked, prior_unsacked, @@ -3574,6 +3577,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); + /* Advance cwnd if state allows */ + if (tcp_may_raise_cwnd(sk, flag)) + tcp_cong_avoid(sk, ack, acked); + if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) { struct dst_entry *dst = __sk_dst_get(sk); if (dst) @@ -3947,7 +3954,6 @@ void tcp_reset(struct sock *sk) static void tcp_fin(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - const struct dst_entry *dst; inet_csk_schedule_ack(sk); @@ -3959,9 +3965,7 @@ static void tcp_fin(struct sock *sk) case TCP_ESTABLISHED: /* Move to CLOSE_WAIT */ tcp_set_state(sk, TCP_CLOSE_WAIT); - dst = __sk_dst_get(sk); - if (!dst || !dst_metric(dst, RTAX_QUICKACK)) - inet_csk(sk)->icsk_ack.pingpong = 1; + inet_csk(sk)->icsk_ack.pingpong = 1; break; case TCP_CLOSE_WAIT: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0ea2e1c..93898e0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -222,7 +222,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err) goto failure; - inet_set_txhash(sk); + sk_set_txhash(sk); rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); @@ -1277,7 +1277,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; - inet_set_txhash(newsk); + sk_set_txhash(newsk); if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = newtp->write_seq ^ jiffies; @@ -1683,8 +1683,7 @@ do_time_wait: iph->daddr, th->dest, inet_iif(skb)); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk)); - inet_twsk_put(inet_twsk(sk)); + inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; goto process; } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index a51d63a..b3d64f6 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -461,7 +461,7 @@ void tcp_update_metrics(struct sock *sk) tcp_metric_set(tm, TCP_METRIC_CWND, tp->snd_cwnd); } - } else if (tp->snd_cwnd > tp->snd_ssthresh && + } else if (!tcp_in_slow_start(tp) && icsk->icsk_ca_state == TCP_CA_Open) { /* Cong. avoidance phase, cwnd is reliable. */ if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4bc00cb..6d8795b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -147,8 +147,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, if (!th->fin || TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) { kill_with_rst: - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); return TCP_TW_RST; } @@ -198,8 +197,7 @@ kill_with_rst: */ if (sysctl_tcp_rfc1337 == 0) { kill: - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; } } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b1c218d..7d1efa7 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -163,7 +163,6 @@ static void tcp_event_data_sent(struct tcp_sock *tp, { struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_time_stamp; - const struct dst_entry *dst = __sk_dst_get(sk); if (sysctl_tcp_slow_start_after_idle && (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto)) @@ -174,9 +173,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp, /* If it is a reply for ato after last received * packet, enter pingpong mode. */ - if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato && - (!dst || !dst_metric(dst, RTAX_QUICKACK))) - icsk->icsk_ack.pingpong = 1; + if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) + icsk->icsk_ack.pingpong = 1; } /* Account for an ACK we sent. */ @@ -1776,7 +1774,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto send_now; - if (!((1 << icsk->icsk_ca_state) & (TCPF_CA_Open | TCPF_CA_CWR))) + if (icsk->icsk_ca_state >= TCP_CA_Recovery) goto send_now; /* Avoid bursty behavior by allowing defer diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 333bcb2..bf5ea9e 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -22,7 +22,7 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT), diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 5b752f5..7149ebc 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -649,4 +649,3 @@ void tcp_init_xmit_timers(struct sock *sk) inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); } -EXPORT_SYMBOL(tcp_init_xmit_timers); diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index a6cea1d..13951c4 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -225,7 +225,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) */ diff = tp->snd_cwnd * (rtt-vegas->baseRTT) / vegas->baseRTT; - if (diff > gamma && tp->snd_cwnd <= tp->snd_ssthresh) { + if (diff > gamma && tcp_in_slow_start(tp)) { /* Going too fast. Time to slow down * and switch to congestion avoidance. */ @@ -240,7 +240,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) tp->snd_cwnd = min(tp->snd_cwnd, (u32)target_cwnd+1); tp->snd_ssthresh = tcp_vegas_ssthresh(tp); - } else if (tp->snd_cwnd <= tp->snd_ssthresh) { + } else if (tcp_in_slow_start(tp)) { /* Slow start. */ tcp_slow_start(tp, acked); } else { @@ -281,7 +281,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) vegas->minRTT = 0x7fffffff; } /* Use normal slow start */ - else if (tp->snd_cwnd <= tp->snd_ssthresh) + else if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); } diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 112151e..0d094b9 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -150,7 +150,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked) veno->diff = (tp->snd_cwnd << V_PARAM_SHIFT) - target_cwnd; - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { /* Slow start. */ tcp_slow_start(tp, acked); } else { diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 438a73a..643f613 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -5,16 +5,15 @@ # IPv6 as module will cause a CRASH if you try to unload it menuconfig IPV6 tristate "The IPv6 protocol" - default m + default y ---help--- - This is complemental support for the IP version 6. - You will still be able to do traditional IPv4 networking as well. + Support for IP version 6 (IPv6). For general information about IPv6, see <https://en.wikipedia.org/wiki/IPv6>. - For Linux IPv6 development information, see <http://www.linux-ipv6.org>. - For specific information about IPv6 under Linux, read the HOWTO at - <http://www.bieringer.de/linux/IPv6/>. + For specific information about IPv6 under Linux, see + Documentation/networking/ipv6.txt and read the HOWTO at + <http://www.tldp.org/HOWTO/Linux+IPv6-HOWTO/> To compile this protocol support as a module, choose M here: the module will be called ipv6. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 21c2c81..53e3a9d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -195,6 +195,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_from_local = 0, + .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -211,7 +212,8 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_ra_mtu = 1, .stable_secret = { .initialized = false, - } + }, + .use_oif_addrs_only = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -236,6 +238,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_from_local = 0, + .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -253,6 +256,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .stable_secret = { .initialized = false, }, + .use_oif_addrs_only = 0, }; /* Check if a valid qdisc is available */ @@ -1358,15 +1362,96 @@ out: return ret; } +static int __ipv6_dev_get_saddr(struct net *net, + struct ipv6_saddr_dst *dst, + struct inet6_dev *idev, + struct ipv6_saddr_score *scores, + int hiscore_idx) +{ + struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx]; + + read_lock_bh(&idev->lock); + list_for_each_entry(score->ifa, &idev->addr_list, if_list) { + int i; + + /* + * - Tentative Address (RFC2462 section 5.4) + * - A tentative address is not considered + * "assigned to an interface" in the traditional + * sense, unless it is also flagged as optimistic. + * - Candidate Source Address (section 4) + * - In any case, anycast addresses, multicast + * addresses, and the unspecified address MUST + * NOT be included in a candidate set. + */ + if ((score->ifa->flags & IFA_F_TENTATIVE) && + (!(score->ifa->flags & IFA_F_OPTIMISTIC))) + continue; + + score->addr_type = __ipv6_addr_type(&score->ifa->addr); + + if (unlikely(score->addr_type == IPV6_ADDR_ANY || + score->addr_type & IPV6_ADDR_MULTICAST)) { + net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s", + idev->dev->name); + continue; + } + + score->rule = -1; + bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX); + + for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) { + int minihiscore, miniscore; + + minihiscore = ipv6_get_saddr_eval(net, hiscore, dst, i); + miniscore = ipv6_get_saddr_eval(net, score, dst, i); + + if (minihiscore > miniscore) { + if (i == IPV6_SADDR_RULE_SCOPE && + score->scopedist > 0) { + /* + * special case: + * each remaining entry + * has too small (not enough) + * scope, because ifa entries + * are sorted by their scope + * values. + */ + goto out; + } + break; + } else if (minihiscore < miniscore) { + if (hiscore->ifa) + in6_ifa_put(hiscore->ifa); + + in6_ifa_hold(score->ifa); + + swap(hiscore, score); + hiscore_idx = 1 - hiscore_idx; + + /* restore our iterator */ + score->ifa = hiscore->ifa; + + break; + } + } + } +out: + read_unlock_bh(&idev->lock); + return hiscore_idx; +} + int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, const struct in6_addr *daddr, unsigned int prefs, struct in6_addr *saddr) { - struct ipv6_saddr_score scores[2], - *score = &scores[0], *hiscore = &scores[1]; + struct ipv6_saddr_score scores[2], *hiscore; struct ipv6_saddr_dst dst; + struct inet6_dev *idev; struct net_device *dev; int dst_type; + bool use_oif_addr = false; + int hiscore_idx = 0; dst_type = __ipv6_addr_type(daddr); dst.addr = daddr; @@ -1375,105 +1460,50 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, dst.label = ipv6_addr_label(net, daddr, dst_type, dst.ifindex); dst.prefs = prefs; - hiscore->rule = -1; - hiscore->ifa = NULL; + scores[hiscore_idx].rule = -1; + scores[hiscore_idx].ifa = NULL; rcu_read_lock(); - for_each_netdev_rcu(net, dev) { - struct inet6_dev *idev; - - /* Candidate Source Address (section 4) - * - multicast and link-local destination address, - * the set of candidate source address MUST only - * include addresses assigned to interfaces - * belonging to the same link as the outgoing - * interface. - * (- For site-local destination addresses, the - * set of candidate source addresses MUST only - * include addresses assigned to interfaces - * belonging to the same site as the outgoing - * interface.) - */ - if (((dst_type & IPV6_ADDR_MULTICAST) || - dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL) && - dst.ifindex && dev->ifindex != dst.ifindex) - continue; - - idev = __in6_dev_get(dev); - if (!idev) - continue; - - read_lock_bh(&idev->lock); - list_for_each_entry(score->ifa, &idev->addr_list, if_list) { - int i; - - /* - * - Tentative Address (RFC2462 section 5.4) - * - A tentative address is not considered - * "assigned to an interface" in the traditional - * sense, unless it is also flagged as optimistic. - * - Candidate Source Address (section 4) - * - In any case, anycast addresses, multicast - * addresses, and the unspecified address MUST - * NOT be included in a candidate set. - */ - if ((score->ifa->flags & IFA_F_TENTATIVE) && - (!(score->ifa->flags & IFA_F_OPTIMISTIC))) - continue; - - score->addr_type = __ipv6_addr_type(&score->ifa->addr); + /* Candidate Source Address (section 4) + * - multicast and link-local destination address, + * the set of candidate source address MUST only + * include addresses assigned to interfaces + * belonging to the same link as the outgoing + * interface. + * (- For site-local destination addresses, the + * set of candidate source addresses MUST only + * include addresses assigned to interfaces + * belonging to the same site as the outgoing + * interface.) + * - "It is RECOMMENDED that the candidate source addresses + * be the set of unicast addresses assigned to the + * interface that will be used to send to the destination + * (the 'outgoing' interface)." (RFC 6724) + */ + if (dst_dev) { + idev = __in6_dev_get(dst_dev); + if ((dst_type & IPV6_ADDR_MULTICAST) || + dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL || + (idev && idev->cnf.use_oif_addrs_only)) { + use_oif_addr = true; + } + } - if (unlikely(score->addr_type == IPV6_ADDR_ANY || - score->addr_type & IPV6_ADDR_MULTICAST)) { - net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s", - dev->name); + if (use_oif_addr) { + if (idev) + hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx); + } else { + for_each_netdev_rcu(net, dev) { + idev = __in6_dev_get(dev); + if (!idev) continue; - } - - score->rule = -1; - bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX); - - for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) { - int minihiscore, miniscore; - - minihiscore = ipv6_get_saddr_eval(net, hiscore, &dst, i); - miniscore = ipv6_get_saddr_eval(net, score, &dst, i); - - if (minihiscore > miniscore) { - if (i == IPV6_SADDR_RULE_SCOPE && - score->scopedist > 0) { - /* - * special case: - * each remaining entry - * has too small (not enough) - * scope, because ifa entries - * are sorted by their scope - * values. - */ - goto try_nextdev; - } - break; - } else if (minihiscore < miniscore) { - if (hiscore->ifa) - in6_ifa_put(hiscore->ifa); - - in6_ifa_hold(score->ifa); - - swap(hiscore, score); - - /* restore our iterator */ - score->ifa = hiscore->ifa; - - break; - } - } + hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx); } -try_nextdev: - read_unlock_bh(&idev->lock); } rcu_read_unlock(); + hiscore = &scores[hiscore_idx]; if (!hiscore->ifa) return -EADDRNOTAVAIL; @@ -4560,6 +4590,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; + array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit; array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref; @@ -4586,6 +4617,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu; /* we omit DEVCONF_STABLE_SECRET for now */ + array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; } static inline size_t inet6_ifla6_size(void) @@ -5456,6 +5488,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { + .procname = "accept_ra_min_hop_limit", + .data = &ipv6_devconf.accept_ra_min_hop_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, .maxlen = sizeof(int), @@ -5585,6 +5624,14 @@ static struct addrconf_sysctl_table .proc_handler = addrconf_sysctl_stable_secret, }, { + .procname = "use_oif_addrs_only", + .data = &ipv6_devconf.use_oif_addrs_only, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + + }, + { /* sentinel */ } }, diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index ca09bf4..bfa941f 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -107,7 +107,16 @@ int inet6addr_notifier_call_chain(unsigned long val, void *v) } EXPORT_SYMBOL(inet6addr_notifier_call_chain); -const struct ipv6_stub *ipv6_stub __read_mostly; +static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1, + struct dst_entry **u2, + struct flowi6 *u3) +{ + return -EAFNOSUPPORT; +} + +const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { + .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, +}; EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 7de52b6..44bb66b 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -197,6 +197,7 @@ lookup_protocol: np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; + np->autoflowlabel = ip6_default_np_autolabel(sock_net(sk)); sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; /* Init the ipv4 part of the socket since we can have sockets @@ -342,7 +343,8 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!(inet->freebind || inet->transparent) && + if (!net->ipv6.sysctl.ip_nonlocal_bind && + !(inet->freebind || inet->transparent) && !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; @@ -679,8 +681,8 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct ipv6_pinfo *np = inet6_sk(sk); if (np->rxopt.all) { - if ((opt->hop && (np->rxopt.bits.hopopts || - np->rxopt.bits.ohopopts)) || + if (((opt->flags & IP6SKB_HOPBYHOP) && + (np->rxopt.bits.hopopts || np->rxopt.bits.ohopopts)) || (ip6_flowinfo((struct ipv6hdr *) skb_network_header(skb)) && np->rxopt.bits.rxflow) || (opt->srcrt && (np->rxopt.bits.srcrt || @@ -766,10 +768,10 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; net->ipv6.sysctl.flowlabel_consistency = 1; - net->ipv6.sysctl.auto_flowlabels = 0; + net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS; net->ipv6.sysctl.idgen_retries = 3; net->ipv6.sysctl.idgen_delay = 1 * HZ; - net->ipv6.sysctl.flowlabel_state_ranges = 1; + net->ipv6.sysctl.flowlabel_state_ranges = 0; atomic_set(&net->ipv6.fib6_sernum, 1); err = ipv6_init_mibs(net); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index b10a889..9aadd57 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -199,7 +199,7 @@ ipv4_connected: NULL); sk->sk_state = TCP_ESTABLISHED; - ip6_set_txhash(sk); + sk_set_txhash(sk); out: fl6_sock_release(flowlabel); return err; @@ -568,8 +568,8 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } /* HbH is allowed only once */ - if (np->rxopt.bits.hopopts && opt->hop) { - u8 *ptr = nh + opt->hop; + if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) { + u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr); } @@ -630,8 +630,8 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } - if (np->rxopt.bits.ohopopts && opt->hop) { - u8 *ptr = nh + opt->hop; + if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) { + u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.odstopts && opt->dst0) { diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index a7bbbe4..ce203b0 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -632,7 +632,7 @@ int ipv6_parse_hopopts(struct sk_buff *skb) return -1; } - opt->hop = sizeof(struct ipv6hdr); + opt->flags |= IP6SKB_HOPBYHOP; if (ip6_parse_tlv(tlvprochopopt_lst, skb)) { skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3; opt = IP6CB(skb); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 713d743..6c2b213 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -329,7 +329,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, struct flowi6 fl2; int err; - err = ip6_dst_lookup(sk, &dst, fl6); + err = ip6_dst_lookup(net, sk, &dst, fl6); if (err) return ERR_PTR(err); @@ -361,7 +361,7 @@ static struct dst_entry *icmpv6_route_lookup(struct net *net, if (err) goto relookup_failed; - err = ip6_dst_lookup(sk, &dst2, &fl2); + err = ip6_dst_lookup(net, sk, &dst2, &fl2); if (err) goto relookup_failed; @@ -591,7 +591,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; - err = ip6_dst_lookup(sk, &dst, &fl6); + err = ip6_dst_lookup(net, sk, &dst, &fl6); if (err) goto out; dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0); diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b4fd96d..6ac8dad 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -207,7 +207,6 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; - int twrefcnt = 0; spin_lock(lock); @@ -234,21 +233,17 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { - twrefcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); - if (twrefcnt) - inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw); - - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); } return 0; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 55d1986..5693b5e 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -32,6 +32,7 @@ #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> +#include <net/lwtunnel.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> @@ -177,6 +178,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) static void rt6_release(struct rt6_info *rt) { if (atomic_dec_and_test(&rt->rt6i_ref)) { + lwtstate_put(rt->rt6i_lwtstate); rt6_free_pcpu(rt); dst_free(&rt->dst); } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a38d3ac..34f1218 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -728,7 +728,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, */ ipv6h = ipv6_hdr(skb); ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), - ip6_make_flowlabel(net, skb, fl6->flowlabel, false)); + ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6)); ipv6h->hop_limit = tunnel->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; @@ -1182,7 +1182,8 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb, - t->fl.u.ip6.flowlabel, false)); + t->fl.u.ip6.flowlabel, true, + &t->fl.u.ip6)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = NEXTHDR_GRE; ipv6h->saddr = t->parms.laddr; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 57990c9..adba03a 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -45,6 +45,7 @@ #include <net/addrconf.h> #include <net/xfrm.h> #include <net/inet_ecn.h> +#include <net/dst_metadata.h> int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb) { @@ -55,7 +56,7 @@ int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb) if (ipprot && ipprot->early_demux) ipprot->early_demux(skb); } - if (!skb_dst(skb)) + if (!skb_valid_dst(skb)) ip6_route_input(skb); return dst_input(skb); @@ -98,7 +99,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt * arrived via the sending interface (ethX), because of the * nature of scoping architecture. --yoshfuji */ - IP6CB(skb)->iif = skb_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex; + IP6CB(skb)->iif = skb_valid_dst(skb) ? ip6_dst_idev(skb_dst(skb))->dev->ifindex : dev->ifindex; if (unlikely(!pskb_may_pull(skb, sizeof(*hdr)))) goto err; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d5f7716..26ea479 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -207,7 +207,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel)); + np->autoflowlabel, fl6)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -881,10 +881,9 @@ out: return dst; } -static int ip6_dst_lookup_tail(struct sock *sk, +static int ip6_dst_lookup_tail(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { - struct net *net = sock_net(sk); #ifdef CONFIG_IPV6_OPTIMISTIC_DAD struct neighbour *n; struct rt6_info *rt; @@ -994,10 +993,11 @@ out_err_release: * * It returns zero on success, or a standard errno code on error. */ -int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) +int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, + struct flowi6 *fl6) { *dst = NULL; - return ip6_dst_lookup_tail(sk, dst, fl6); + return ip6_dst_lookup_tail(net, sk, dst, fl6); } EXPORT_SYMBOL_GPL(ip6_dst_lookup); @@ -1018,11 +1018,13 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, struct dst_entry *dst = NULL; int err; - err = ip6_dst_lookup_tail(sk, &dst, fl6); + err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; + if (!fl6->flowi6_oif) + fl6->flowi6_oif = dst->dev->ifindex; return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); } @@ -1050,7 +1052,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, dst = ip6_sk_dst_check(sk, dst, fl6); - err = ip6_dst_lookup_tail(sk, &dst, fl6); + err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) @@ -1647,7 +1649,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel)); + np->autoflowlabel, fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 2e67b66..b0ab420 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1095,7 +1095,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), - ip6_make_flowlabel(net, skb, fl6->flowlabel, false)); + ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6)); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index c53331c..b305461 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1225,18 +1225,16 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); - if (ra_msg->icmph.icmp6_hop_limit) { - /* Only set hop_limit on the interface if it is higher than - * the current hop_limit. - */ - if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) { + if (in6_dev->cnf.accept_ra_min_hop_limit < 256 && + ra_msg->icmph.icmp6_hop_limit) { + if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + if (rt) + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, + ra_msg->icmph.icmp6_hop_limit); } else { - ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n"); + ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n"); } - if (rt) - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, - ra_msg->icmph.icmp6_hop_limit); } skip_defrtr: diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 3c35ced..4e21f80 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -305,7 +305,7 @@ static void trace_packet(const struct sk_buff *skb, } #endif -static inline __pure struct ip6t_entry * +static inline struct ip6t_entry * ip6t_next_entry(const struct ip6t_entry *entry) { return (void *)entry + entry->next_offset; @@ -324,12 +324,13 @@ ip6t_do_table(struct sk_buff *skb, const char *indev, *outdev; const void *table_base; struct ip6t_entry *e, **jumpstack; - unsigned int *stackptr, origptr, cpu; + unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ + stackidx = 0; indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; /* We handle fragments by dealing with the first fragment as @@ -357,8 +358,16 @@ ip6t_do_table(struct sk_buff *skb, cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; - stackptr = per_cpu_ptr(private->stackptr, cpu); - origptr = *stackptr; + + /* Switch to alternate jumpstack if we're being invoked via TEE. + * TEE issues XT_CONTINUE verdict on original skb so we must not + * clobber the jumpstack. + * + * For recursion via REJECT or SYNPROXY the stack will be clobbered + * but it is no problem since absolute verdict is issued by these. + */ + if (static_key_false(&xt_tee_enabled)) + jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); e = get_entry(table_base, private->hook_entry[hook]); @@ -406,20 +415,16 @@ ip6t_do_table(struct sk_buff *skb, verdict = (unsigned int)(-v) - 1; break; } - if (*stackptr <= origptr) + if (stackidx == 0) e = get_entry(table_base, private->underflow[hook]); else - e = ip6t_next_entry(jumpstack[--*stackptr]); + e = ip6t_next_entry(jumpstack[--stackidx]); continue; } if (table_base + v != ip6t_next_entry(e) && !(e->ipv6.flags & IP6T_F_GOTO)) { - if (*stackptr >= private->stacksize) { - verdict = NF_DROP; - break; - } - jumpstack[(*stackptr)++] = e; + jumpstack[stackidx++] = e; } e = get_entry(table_base, v); @@ -437,8 +442,6 @@ ip6t_do_table(struct sk_buff *skb, break; } while (!acpar.hotdrop); - *stackptr = origptr; - xt_write_recseq_end(addend); local_bh_enable(); @@ -452,11 +455,15 @@ ip6t_do_table(struct sk_buff *skb, } /* Figures out from what hook each rule can be called: returns 0 if - there are loops. Puts hook bitmask in comefrom. */ + * there are loops. Puts hook bitmask in comefrom. + * + * Keeps track of largest call depth seen and stores it in newinfo->stacksize. + */ static int -mark_source_chains(const struct xt_table_info *newinfo, +mark_source_chains(struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { + unsigned int calldepth, max_calldepth = 0; unsigned int hook; /* No recursion; use packet counter to save back ptrs (reset @@ -470,6 +477,7 @@ mark_source_chains(const struct xt_table_info *newinfo, /* Set initial back pointer. */ e->counters.pcnt = pos; + calldepth = 0; for (;;) { const struct xt_standard_target *t @@ -531,6 +539,8 @@ mark_source_chains(const struct xt_table_info *newinfo, (entry0 + pos + size); e->counters.pcnt = pos; pos += size; + if (calldepth > 0) + --calldepth; } else { int newpos = t->verdict; @@ -544,6 +554,11 @@ mark_source_chains(const struct xt_table_info *newinfo, newpos); return 0; } + if (entry0 + newpos != ip6t_next_entry(e) && + !(e->ipv6.flags & IP6T_F_GOTO) && + ++calldepth > max_calldepth) + max_calldepth = calldepth; + /* This a jump; chase it. */ duprintf("Jump rule %u -> %u\n", pos, newpos); @@ -560,6 +575,7 @@ mark_source_chains(const struct xt_table_info *newinfo, next: duprintf("Finished chain %u\n", hook); } + newinfo->stacksize = max_calldepth; return 1; } @@ -839,9 +855,6 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, if (ret != 0) return ret; ++i; - if (strcmp(ip6t_get_target(iter)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; } if (i != repl->num_entries) { @@ -1754,9 +1767,6 @@ translate_compat_table(struct net *net, if (ret != 0) break; ++i; - if (strcmp(ip6t_get_target(iter1)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; } if (ret) { /* diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 12331ef..567367a 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -35,14 +35,12 @@ MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>"); MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6"); MODULE_LICENSE("GPL"); - static unsigned int reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_reject_info *reject = par->targinfo; struct net *net = dev_net((par->in != NULL) ? par->in : par->out); - pr_debug("%s: medium point\n", __func__); switch (reject->with) { case IP6T_ICMP6_NO_ROUTE: nf_send_unreach6(net, skb, ICMPV6_NOROUTE, par->hooknum); @@ -65,9 +63,6 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) case IP6T_TCP_RESET: nf_send_reset6(net, skb, par->hooknum); break; - default: - net_info_ratelimited("case %u not handled yet\n", reject->with); - break; } return NF_DROP; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index a45db0b..267fb8d 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -39,12 +39,9 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, if (skb->nfct) zone = nf_ct_zone((struct nf_conn *)skb->nfct); #endif - -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - if (skb->nf_bridge && - skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) + if (nf_bridge_in_prerouting(skb)) return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone; -#endif + if (hooknum == NF_INET_PRE_ROUTING) return IP6_DEFRAG_CONNTRACK_IN + zone; else diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ca4700c..fdbada156 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -295,7 +295,8 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; - if (!(addr_type & IPV6_ADDR_MULTICAST)) { + if (!(addr_type & IPV6_ADDR_MULTICAST) && + !sock_net(sk)->ipv6.sysctl.ip_nonlocal_bind) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9de4d2b..c0fa61e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -58,6 +58,7 @@ #include <net/netevent.h> #include <net/netlink.h> #include <net/nexthop.h> +#include <net/lwtunnel.h> #include <asm/uaccess.h> @@ -544,6 +545,7 @@ static void rt6_probe_deferred(struct work_struct *w) static void rt6_probe(struct rt6_info *rt) { + struct __rt6_probe_work *work; struct neighbour *neigh; /* * Okay, this does not seem to be appropriate @@ -558,34 +560,33 @@ static void rt6_probe(struct rt6_info *rt) rcu_read_lock_bh(); neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (neigh) { - write_lock(&neigh->lock); if (neigh->nud_state & NUD_VALID) goto out; - } - - if (!neigh || - time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { - struct __rt6_probe_work *work; + work = NULL; + write_lock(&neigh->lock); + if (!(neigh->nud_state & NUD_VALID) && + time_after(jiffies, + neigh->updated + + rt->rt6i_idev->cnf.rtr_probe_interval)) { + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) + __neigh_set_probe_once(neigh); + } + write_unlock(&neigh->lock); + } else { work = kmalloc(sizeof(*work), GFP_ATOMIC); + } - if (neigh && work) - __neigh_set_probe_once(neigh); - - if (neigh) - write_unlock(&neigh->lock); + if (work) { + INIT_WORK(&work->work, rt6_probe_deferred); + work->target = rt->rt6i_gateway; + dev_hold(rt->dst.dev); + work->dev = rt->dst.dev; + schedule_work(&work->work); + } - if (work) { - INIT_WORK(&work->work, rt6_probe_deferred); - work->target = rt->rt6i_gateway; - dev_hold(rt->dst.dev); - work->dev = rt->dst.dev; - schedule_work(&work->work); - } - } else { out: - write_unlock(&neigh->lock); - } rcu_read_unlock_bh(); } #else @@ -1770,6 +1771,18 @@ int ip6_route_add(struct fib6_config *cfg) rt->dst.output = ip6_output; + if (cfg->fc_encap) { + struct lwtunnel_state *lwtstate; + + err = lwtunnel_build_state(dev, cfg->fc_encap_type, + cfg->fc_encap, &lwtstate); + if (err) + goto out; + rt->rt6i_lwtstate = lwtstate_get(lwtstate); + if (lwtunnel_output_redirect(rt->rt6i_lwtstate)) + rt->dst.output = lwtunnel_output6; + } + ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->rt6i_dst.plen = cfg->fc_dst_len; if (rt->rt6i_dst.plen == 128) @@ -2149,6 +2162,7 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort) #endif rt->rt6i_prefsrc = ort->rt6i_prefsrc; rt->rt6i_table = ort->rt6i_table; + rt->rt6i_lwtstate = lwtstate_get(ort->rt6i_lwtstate); } #ifdef CONFIG_IPV6_ROUTE_INFO @@ -2597,6 +2611,8 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PREF] = { .type = NLA_U8 }, + [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, + [RTA_ENCAP] = { .type = NLA_NESTED }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2691,6 +2707,12 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_flags |= RTF_PREF(pref); } + if (tb[RTA_ENCAP]) + cfg->fc_encap = tb[RTA_ENCAP]; + + if (tb[RTA_ENCAP_TYPE]) + cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); + err = 0; errout: return err; @@ -2723,6 +2745,10 @@ beginning: r_cfg.fc_gateway = nla_get_in6_addr(nla); r_cfg.fc_flags |= RTF_GATEWAY; } + r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); + nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); + if (nla) + r_cfg.fc_encap_type = nla_get_u16(nla); } err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg); if (err) { @@ -2785,7 +2811,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) return ip6_route_add(&cfg); } -static inline size_t rt6_nlmsg_size(void) +static inline size_t rt6_nlmsg_size(struct rt6_info *rt) { return NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(16) /* RTA_SRC */ @@ -2799,7 +2825,8 @@ static inline size_t rt6_nlmsg_size(void) + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ - + nla_total_size(1); /* RTA_PREF */ + + nla_total_size(1) /* RTA_PREF */ + + lwtunnel_get_encap_size(rt->rt6i_lwtstate); } static int rt6_fill_node(struct net *net, @@ -2947,6 +2974,8 @@ static int rt6_fill_node(struct net *net, if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags))) goto nla_put_failure; + lwtunnel_fill_encap(skb, rt->rt6i_lwtstate); + nlmsg_end(skb, nlh); return 0; @@ -3073,7 +3102,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; - skb = nlmsg_new(rt6_nlmsg_size(), gfp_any()); + skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (!skb) goto errout; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index ac35a28..94428fd 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -742,7 +742,7 @@ static int ipip_rcv(struct sk_buff *skb) goto drop; if (iptunnel_pull_header(skb, 0, tpi.proto)) goto drop; - return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); + return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error); } return 1; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 4e705ad..45243bb 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -17,6 +17,9 @@ #include <net/inet_frag.h> static int one = 1; +static int auto_flowlabels_min; +static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; + static struct ctl_table ipv6_table_template[] = { { @@ -45,7 +48,9 @@ static struct ctl_table ipv6_table_template[] = { .data = &init_net.ipv6.sysctl.auto_flowlabels, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &auto_flowlabels_min, + .extra2 = &auto_flowlabels_max }, { .procname = "fwmark_reflect", @@ -75,6 +80,13 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_nonlocal_bind", + .data = &init_net.ipv6.sysctl.ip_nonlocal_bind, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -117,6 +129,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[5].data = &net->ipv6.sysctl.idgen_retries; ipv6_table[6].data = &net->ipv6.sysctl.idgen_delay; ipv6_table[7].data = &net->ipv6.sysctl.flowlabel_state_ranges; + ipv6_table[8].data = &net->ipv6.sysctl.ip_nonlocal_bind; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7a6cea5..97d9314 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -276,7 +276,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (err) goto late_failure; - ip6_set_txhash(sk); + sk_set_txhash(sk); if (!tp->write_seq && likely(!tp->repair)) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, @@ -1090,7 +1090,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; newsk->sk_bound_dev_if = ireq->ir_iif; - ip6_set_txhash(newsk); + sk_set_txhash(newsk); /* Now IPv6 options... @@ -1481,8 +1481,7 @@ do_time_wait: ntohs(th->dest), tcp_v6_iif(skb)); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); sk = sk2; tcp_v6_restore_cb(skb); goto process; diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c index 317c466..f7ba51e 100644 --- a/net/mac802154/cfg.c +++ b/net/mac802154/cfg.c @@ -44,6 +44,49 @@ static void ieee802154_del_iface_deprecated(struct wpan_phy *wpan_phy, ieee802154_if_remove(sdata); } +#ifdef CONFIG_PM +static int ieee802154_suspend(struct wpan_phy *wpan_phy) +{ + struct ieee802154_local *local = wpan_phy_priv(wpan_phy); + + if (!local->open_count) + goto suspend; + + ieee802154_stop_queue(&local->hw); + synchronize_net(); + + /* stop hardware - this must stop RX */ + ieee802154_stop_device(local); + +suspend: + local->suspended = true; + return 0; +} + +static int ieee802154_resume(struct wpan_phy *wpan_phy) +{ + struct ieee802154_local *local = wpan_phy_priv(wpan_phy); + int ret; + + /* nothing to do if HW shouldn't run */ + if (!local->open_count) + goto wake_up; + + /* restart hardware */ + ret = drv_start(local); + if (ret) + return ret; + +wake_up: + ieee802154_wake_queue(&local->hw); + local->suspended = false; + return 0; +} +#else +#define ieee802154_suspend NULL +#define ieee802154_resume NULL +#endif + static int ieee802154_add_iface(struct wpan_phy *phy, const char *name, unsigned char name_assign_type, @@ -145,13 +188,18 @@ static int ieee802154_set_pan_id(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, __le16 pan_id) { + int ret; + ASSERT_RTNL(); if (wpan_dev->pan_id == pan_id) return 0; - wpan_dev->pan_id = pan_id; - return 0; + ret = mac802154_wpan_update_llsec(wpan_dev->netdev); + if (!ret) + wpan_dev->pan_id = pan_id; + + return ret; } static int @@ -227,6 +275,8 @@ ieee802154_set_lbt_mode(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, const struct cfg802154_ops mac802154_config_ops = { .add_virtual_intf_deprecated = ieee802154_add_iface_deprecated, .del_virtual_intf_deprecated = ieee802154_del_iface_deprecated, + .suspend = ieee802154_suspend, + .resume = ieee802154_resume, .add_virtual_intf = ieee802154_add_iface, .del_virtual_intf = ieee802154_del_iface, .set_channel = ieee802154_set_channel, diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 34755d5..56ccffa 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -56,9 +56,13 @@ struct ieee802154_local { struct hrtimer ifs_timer; bool started; + bool suspended; struct tasklet_struct tasklet; struct sk_buff_head skb_queue; + + struct sk_buff *tx_skb; + struct work_struct tx_work; }; enum { @@ -94,8 +98,6 @@ struct ieee802154_sub_if_data { struct mac802154_llsec sec; }; -#define MAC802154_CHAN_NONE 0xff /* No channel is assigned */ - /* utility functions/constants */ extern const void *const mac802154_wpan_phy_privid; /* for wpan_phy privid */ @@ -125,6 +127,8 @@ ieee802154_sdata_running(struct ieee802154_sub_if_data *sdata) extern struct ieee802154_mlme_ops mac802154_mlme_wpan; +void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb); +void ieee802154_xmit_worker(struct work_struct *work); netdev_tx_t ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t @@ -167,6 +171,8 @@ void mac802154_get_table(struct net_device *dev, struct ieee802154_llsec_table **t); void mac802154_unlock_table(struct net_device *dev); +int mac802154_wpan_update_llsec(struct net_device *dev); + /* interface handling */ int ieee802154_iface_init(void); void ieee802154_iface_exit(void); @@ -176,5 +182,6 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr); void ieee802154_remove_interfaces(struct ieee802154_local *local); +void ieee802154_stop_device(struct ieee802154_local *local); #endif /* __IEEE802154_I_H */ diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 8b69824..416de90 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -30,7 +30,7 @@ #include "ieee802154_i.h" #include "driver-ops.h" -static int mac802154_wpan_update_llsec(struct net_device *dev) +int mac802154_wpan_update_llsec(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); @@ -314,11 +314,8 @@ static int mac802154_slave_close(struct net_device *dev) clear_bit(SDATA_STATE_RUNNING, &sdata->state); - if (!local->open_count) { - flush_workqueue(local->workqueue); - hrtimer_cancel(&local->ifs_timer); - drv_stop(local); - } + if (!local->open_count) + ieee802154_stop_device(local); return 0; } @@ -471,6 +468,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, enum nl802154_iftype type) { struct wpan_dev *wpan_dev = &sdata->wpan_dev; + int ret; u8 tmp; /* set some type-dependent values */ @@ -505,6 +503,10 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, mutex_init(&sdata->sec_mtx); mac802154_llsec_init(&sdata->sec); + ret = mac802154_wpan_update_llsec(sdata->dev); + if (ret < 0) + return ret; + break; case NL802154_IFTYPE_MONITOR: sdata->dev->destructor = free_netdev; diff --git a/net/mac802154/main.c b/net/mac802154/main.c index 356b346..9e55431 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -40,7 +40,7 @@ static void ieee802154_tasklet_handler(unsigned long data) * netstack. */ skb->pkt_type = 0; - ieee802154_rx(&local->hw, skb); + ieee802154_rx(local, skb); break; default: WARN(1, "mac802154: Packet is of unknown type %d\n", @@ -58,11 +58,9 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) struct ieee802154_local *local; size_t priv_size; - if (!ops || !(ops->xmit_async || ops->xmit_sync) || !ops->ed || - !ops->start || !ops->stop || !ops->set_channel) { - pr_err("undefined IEEE802.15.4 device operations\n"); + if (WARN_ON(!ops || !(ops->xmit_async || ops->xmit_sync) || !ops->ed || + !ops->start || !ops->stop || !ops->set_channel)) return NULL; - } /* Ensure 32-byte alignment of our private data and hw private data. * We use the wpan_phy priv data for both our ieee802154_local and for @@ -107,6 +105,8 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops) skb_queue_head_init(&local->skb_queue); + INIT_WORK(&local->tx_work, ieee802154_xmit_worker); + /* init supported flags with 802.15.4 default ranges */ phy->supported.max_minbe = 8; phy->supported.min_maxbe = 3; diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index d93ad2d..d1c33c1 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -246,13 +246,15 @@ ieee802154_monitors_rx(struct ieee802154_local *local, struct sk_buff *skb) } } -void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb) +void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb) { - struct ieee802154_local *local = hw_to_local(hw); u16 crc; WARN_ON_ONCE(softirq_count() == 0); + if (local->suspended) + goto drop; + /* TODO: When a transceiver omits the checksum here, we * add an own calculated one. This is currently an ugly * solution because the monitor needs a crc here. @@ -273,8 +275,7 @@ void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb) crc = crc_ccitt(0, skb->data, skb->len); if (crc) { rcu_read_unlock(); - kfree_skb(skb); - return; + goto drop; } } /* remove crc */ @@ -283,8 +284,11 @@ void ieee802154_rx(struct ieee802154_hw *hw, struct sk_buff *skb) __ieee802154_rx_handle_packet(local, skb); rcu_read_unlock(); + + return; +drop: + kfree_skb(skb); } -EXPORT_SYMBOL(ieee802154_rx); void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi) diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index c62e956..7ed4391 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -30,23 +30,11 @@ #include "ieee802154_i.h" #include "driver-ops.h" -/* IEEE 802.15.4 transceivers can sleep during the xmit session, so process - * packets through the workqueue. - */ -struct ieee802154_xmit_cb { - struct sk_buff *skb; - struct work_struct work; - struct ieee802154_local *local; -}; - -static struct ieee802154_xmit_cb ieee802154_xmit_cb; - -static void ieee802154_xmit_worker(struct work_struct *work) +void ieee802154_xmit_worker(struct work_struct *work) { - struct ieee802154_xmit_cb *cb = - container_of(work, struct ieee802154_xmit_cb, work); - struct ieee802154_local *local = cb->local; - struct sk_buff *skb = cb->skb; + struct ieee802154_local *local = + container_of(work, struct ieee802154_local, tx_work); + struct sk_buff *skb = local->tx_skb; struct net_device *dev = skb->dev; int res; @@ -106,11 +94,8 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; } else { - INIT_WORK(&ieee802154_xmit_cb.work, ieee802154_xmit_worker); - ieee802154_xmit_cb.skb = skb; - ieee802154_xmit_cb.local = local; - - queue_work(local->workqueue, &ieee802154_xmit_cb.work); + local->tx_skb = skb; + queue_work(local->workqueue, &local->tx_work); } return NETDEV_TX_OK; diff --git a/net/mac802154/util.c b/net/mac802154/util.c index 583435f..f9fd095 100644 --- a/net/mac802154/util.c +++ b/net/mac802154/util.c @@ -14,6 +14,7 @@ */ #include "ieee802154_i.h" +#include "driver-ops.h" /* privid for wpan_phys to determine whether they belong to us or not */ const void *const mac802154_wpan_phy_privid = &mac802154_wpan_phy_privid; @@ -92,3 +93,10 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, dev_consume_skb_any(skb); } EXPORT_SYMBOL(ieee802154_xmit_complete); + +void ieee802154_stop_device(struct ieee802154_local *local) +{ + flush_workqueue(local->workqueue); + hrtimer_cancel(&local->ifs_timer); + drv_stop(local); +} diff --git a/net/mpls/Kconfig b/net/mpls/Kconfig index 17bde79..5c467ef 100644 --- a/net/mpls/Kconfig +++ b/net/mpls/Kconfig @@ -24,7 +24,13 @@ config NET_MPLS_GSO config MPLS_ROUTING tristate "MPLS: routing support" - help + ---help--- Add support for forwarding of mpls packets. +config MPLS_IPTUNNEL + tristate "MPLS: IP over MPLS tunnel support" + depends on LWTUNNEL && MPLS_ROUTING + ---help--- + mpls ip tunnel support. + endif # MPLS diff --git a/net/mpls/Makefile b/net/mpls/Makefile index 65bbe68..9ca9236 100644 --- a/net/mpls/Makefile +++ b/net/mpls/Makefile @@ -3,5 +3,6 @@ # obj-$(CONFIG_NET_MPLS_GSO) += mpls_gso.o obj-$(CONFIG_MPLS_ROUTING) += mpls_router.o +obj-$(CONFIG_MPLS_IPTUNNEL) += mpls_iptunnel.o mpls_router-y := af_mpls.o diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 1f93a59..8c5707d 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -15,6 +15,10 @@ #include <net/ip_fib.h> #include <net/netevent.h> #include <net/netns/generic.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6.h> +#include <net/addrconf.h> +#endif #include "internal.h" #define LABEL_NOT_SPECIFIED (1<<20) @@ -23,11 +27,23 @@ /* This maximum ha length copied from the definition of struct neighbour */ #define MAX_VIA_ALEN (ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))) +enum mpls_payload_type { + MPT_UNSPEC, /* IPv4 or IPv6 */ + MPT_IPV4 = 4, + MPT_IPV6 = 6, + + /* Other types not implemented: + * - Pseudo-wire with or without control word (RFC4385) + * - GAL (RFC5586) + */ +}; + struct mpls_route { /* next hop label forwarding entry */ struct net_device __rcu *rt_dev; struct rcu_head rt_rcu; u32 rt_label[MAX_NEW_LABELS]; u8 rt_protocol; /* routing protocol that set this entry */ + u8 rt_payload_type; u8 rt_labels; u8 rt_via_alen; u8 rt_via_table; @@ -58,10 +74,11 @@ static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) return rcu_dereference_rtnl(dev->mpls_ptr); } -static bool mpls_output_possible(const struct net_device *dev) +bool mpls_output_possible(const struct net_device *dev) { return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev); } +EXPORT_SYMBOL_GPL(mpls_output_possible); static unsigned int mpls_rt_header_size(const struct mpls_route *rt) { @@ -69,13 +86,14 @@ static unsigned int mpls_rt_header_size(const struct mpls_route *rt) return rt->rt_labels * sizeof(struct mpls_shim_hdr); } -static unsigned int mpls_dev_mtu(const struct net_device *dev) +unsigned int mpls_dev_mtu(const struct net_device *dev) { /* The amount of data the layer 2 frame can hold */ return dev->mtu; } +EXPORT_SYMBOL_GPL(mpls_dev_mtu); -static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; @@ -85,20 +103,13 @@ static bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) return true; } +EXPORT_SYMBOL_GPL(mpls_pkt_too_big); static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, struct mpls_entry_decoded dec) { - /* RFC4385 and RFC5586 encode other packets in mpls such that - * they don't conflict with the ip version number, making - * decoding by examining the ip version correct in everything - * except for the strangest cases. - * - * The strange cases if we choose to support them will require - * manual configuration. - */ - struct iphdr *hdr4; - bool success = true; + enum mpls_payload_type payload_type; + bool success = false; /* The IPv4 code below accesses through the IPv4 header * checksum, which is 12 bytes into the packet. @@ -113,23 +124,32 @@ static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb, if (!pskb_may_pull(skb, 12)) return false; - /* Use ip_hdr to find the ip protocol version */ - hdr4 = ip_hdr(skb); - if (hdr4->version == 4) { + payload_type = rt->rt_payload_type; + if (payload_type == MPT_UNSPEC) + payload_type = ip_hdr(skb)->version; + + switch (payload_type) { + case MPT_IPV4: { + struct iphdr *hdr4 = ip_hdr(skb); skb->protocol = htons(ETH_P_IP); csum_replace2(&hdr4->check, htons(hdr4->ttl << 8), htons(dec.ttl << 8)); hdr4->ttl = dec.ttl; + success = true; + break; } - else if (hdr4->version == 6) { + case MPT_IPV6: { struct ipv6hdr *hdr6 = ipv6_hdr(skb); skb->protocol = htons(ETH_P_IPV6); hdr6->hop_limit = dec.ttl; + success = true; + break; + } + case MPT_UNSPEC: + break; } - else - /* version 0 and version 1 are used by pseudo wires */ - success = false; + return success; } @@ -248,16 +268,17 @@ static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { }; struct mpls_route_config { - u32 rc_protocol; - u32 rc_ifindex; - u16 rc_via_table; - u16 rc_via_alen; - u8 rc_via[MAX_VIA_ALEN]; - u32 rc_label; - u32 rc_output_labels; - u32 rc_output_label[MAX_NEW_LABELS]; - u32 rc_nlflags; - struct nl_info rc_nlinfo; + u32 rc_protocol; + u32 rc_ifindex; + u16 rc_via_table; + u16 rc_via_alen; + u8 rc_via[MAX_VIA_ALEN]; + u32 rc_label; + u32 rc_output_labels; + u32 rc_output_label[MAX_NEW_LABELS]; + u32 rc_nlflags; + enum mpls_payload_type rc_payload_type; + struct nl_info rc_nlinfo; }; static struct mpls_route *mpls_rt_alloc(size_t alen) @@ -286,7 +307,7 @@ static void mpls_notify_route(struct net *net, unsigned index, struct mpls_route *rt = new ? new : old; unsigned nlm_flags = (old && new) ? NLM_F_REPLACE : 0; /* Ignore reserved labels for now */ - if (rt && (index >= 16)) + if (rt && (index >= MPLS_LABEL_FIRST_UNRESERVED)) rtmsg_lfib(event, index, rt, nlh, net, portid, nlm_flags); } @@ -320,13 +341,96 @@ static unsigned find_free_label(struct net *net) platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; - for (index = 16; index < platform_labels; index++) { + for (index = MPLS_LABEL_FIRST_UNRESERVED; index < platform_labels; + index++) { if (!rtnl_dereference(platform_label[index])) return index; } return LABEL_NOT_SPECIFIED; } +#if IS_ENABLED(CONFIG_INET) +static struct net_device *inet_fib_lookup_dev(struct net *net, void *addr) +{ + struct net_device *dev; + struct rtable *rt; + struct in_addr daddr; + + memcpy(&daddr, addr, sizeof(struct in_addr)); + rt = ip_route_output(net, daddr.s_addr, 0, 0, 0); + if (IS_ERR(rt)) + return ERR_CAST(rt); + + dev = rt->dst.dev; + dev_hold(dev); + + ip_rt_put(rt); + + return dev; +} +#else +static struct net_device *inet_fib_lookup_dev(struct net *net, void *addr) +{ + return ERR_PTR(-EAFNOSUPPORT); +} +#endif + +#if IS_ENABLED(CONFIG_IPV6) +static struct net_device *inet6_fib_lookup_dev(struct net *net, void *addr) +{ + struct net_device *dev; + struct dst_entry *dst; + struct flowi6 fl6; + int err; + + if (!ipv6_stub) + return ERR_PTR(-EAFNOSUPPORT); + + memset(&fl6, 0, sizeof(fl6)); + memcpy(&fl6.daddr, addr, sizeof(struct in6_addr)); + err = ipv6_stub->ipv6_dst_lookup(net, NULL, &dst, &fl6); + if (err) + return ERR_PTR(err); + + dev = dst->dev; + dev_hold(dev); + dst_release(dst); + + return dev; +} +#else +static struct net_device *inet6_fib_lookup_dev(struct net *net, void *addr) +{ + return ERR_PTR(-EAFNOSUPPORT); +} +#endif + +static struct net_device *find_outdev(struct net *net, + struct mpls_route_config *cfg) +{ + struct net_device *dev = NULL; + + if (!cfg->rc_ifindex) { + switch (cfg->rc_via_table) { + case NEIGH_ARP_TABLE: + dev = inet_fib_lookup_dev(net, cfg->rc_via); + break; + case NEIGH_ND_TABLE: + dev = inet6_fib_lookup_dev(net, cfg->rc_via); + break; + case NEIGH_LINK_TABLE: + break; + } + } else { + dev = dev_get_by_index(net, cfg->rc_ifindex); + } + + if (!dev) + return ERR_PTR(-ENODEV); + + return dev; +} + static int mpls_route_add(struct mpls_route_config *cfg) { struct mpls_route __rcu **platform_label; @@ -345,8 +449,8 @@ static int mpls_route_add(struct mpls_route_config *cfg) index = find_free_label(net); } - /* The first 16 labels are reserved, and may not be set */ - if (index < 16) + /* Reserved labels may not be set */ + if (index < MPLS_LABEL_FIRST_UNRESERVED) goto errout; /* The full 20 bit range may not be supported. */ @@ -357,10 +461,12 @@ static int mpls_route_add(struct mpls_route_config *cfg) if (cfg->rc_output_labels > MAX_NEW_LABELS) goto errout; - err = -ENODEV; - dev = dev_get_by_index(net, cfg->rc_ifindex); - if (!dev) + dev = find_outdev(net, cfg); + if (IS_ERR(dev)) { + err = PTR_ERR(dev); + dev = NULL; goto errout; + } /* Ensure this is a supported device */ err = -EINVAL; @@ -401,6 +507,7 @@ static int mpls_route_add(struct mpls_route_config *cfg) rt->rt_label[i] = cfg->rc_output_label[i]; rt->rt_protocol = cfg->rc_protocol; RCU_INIT_POINTER(rt->rt_dev, dev); + rt->rt_payload_type = cfg->rc_payload_type; rt->rt_via_table = cfg->rc_via_table; memcpy(rt->rt_via, cfg->rc_via, cfg->rc_via_alen); @@ -423,8 +530,8 @@ static int mpls_route_del(struct mpls_route_config *cfg) index = cfg->rc_label; - /* The first 16 labels are reserved, and may not be removed */ - if (index < 16) + /* Reserved labels may not be removed */ + if (index < MPLS_LABEL_FIRST_UNRESERVED) goto errout; /* The full 20 bit range may not be supported */ @@ -626,6 +733,7 @@ int nla_put_labels(struct sk_buff *skb, int attrtype, return 0; } +EXPORT_SYMBOL_GPL(nla_put_labels); int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, u32 label[]) @@ -671,6 +779,7 @@ int nla_get_labels(const struct nlattr *nla, *labels = nla_labels; return 0; } +EXPORT_SYMBOL_GPL(nla_get_labels); static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct mpls_route_config *cfg) @@ -740,8 +849,8 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, &cfg->rc_label)) goto errout; - /* The first 16 labels are reserved, and may not be set */ - if (cfg->rc_label < 16) + /* Reserved labels may not be set */ + if (cfg->rc_label < MPLS_LABEL_FIRST_UNRESERVED) goto errout; break; @@ -866,8 +975,8 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) ASSERT_RTNL(); index = cb->args[0]; - if (index < 16) - index = 16; + if (index < MPLS_LABEL_FIRST_UNRESERVED) + index = MPLS_LABEL_FIRST_UNRESERVED; platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; @@ -953,6 +1062,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) goto nort0; RCU_INIT_POINTER(rt0->rt_dev, lo); rt0->rt_protocol = RTPROT_KERNEL; + rt0->rt_payload_type = MPT_IPV4; rt0->rt_via_table = NEIGH_LINK_TABLE; memcpy(rt0->rt_via, lo->dev_addr, lo->addr_len); } @@ -963,6 +1073,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) goto nort2; RCU_INIT_POINTER(rt2->rt_dev, lo); rt2->rt_protocol = RTPROT_KERNEL; + rt2->rt_payload_type = MPT_IPV6; rt2->rt_via_table = NEIGH_LINK_TABLE; memcpy(rt2->rt_via, lo->dev_addr, lo->addr_len); } diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 8cabeb5..2681a4b 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -50,7 +50,12 @@ static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr * return result; } -int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, const u32 label[]); -int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, u32 label[]); +int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, + const u32 label[]); +int nla_get_labels(const struct nlattr *nla, u32 max_labels, u32 *labels, + u32 label[]); +bool mpls_output_possible(const struct net_device *dev); +unsigned int mpls_dev_mtu(const struct net_device *dev); +bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu); #endif /* MPLS_INTERNAL_H */ diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c new file mode 100644 index 0000000..276f8c9 --- /dev/null +++ b/net/mpls/mpls_iptunnel.c @@ -0,0 +1,233 @@ +/* + * mpls tunnels An implementation mpls tunnels using the light weight tunnel + * infrastructure + * + * Authors: Roopa Prabhu, <roopa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ +#include <linux/types.h> +#include <linux/skbuff.h> +#include <linux/net.h> +#include <linux/module.h> +#include <linux/mpls.h> +#include <linux/vmalloc.h> +#include <net/ip.h> +#include <net/dst.h> +#include <net/lwtunnel.h> +#include <net/netevent.h> +#include <net/netns/generic.h> +#include <net/ip6_fib.h> +#include <net/route.h> +#include <net/mpls_iptunnel.h> +#include <linux/mpls_iptunnel.h> +#include "internal.h" + +static const struct nla_policy mpls_iptunnel_policy[MPLS_IPTUNNEL_MAX + 1] = { + [MPLS_IPTUNNEL_DST] = { .type = NLA_U32 }, +}; + +static unsigned int mpls_encap_size(struct mpls_iptunnel_encap *en) +{ + /* The size of the layer 2.5 labels to be added for this route */ + return en->labels * sizeof(struct mpls_shim_hdr); +} + +int mpls_output(struct sock *sk, struct sk_buff *skb) +{ + struct mpls_iptunnel_encap *tun_encap_info; + struct mpls_shim_hdr *hdr; + struct net_device *out_dev; + unsigned int hh_len; + unsigned int new_header_size; + unsigned int mtu; + struct dst_entry *dst = skb_dst(skb); + struct rtable *rt = NULL; + struct rt6_info *rt6 = NULL; + struct lwtunnel_state *lwtstate = NULL; + int err = 0; + bool bos; + int i; + unsigned int ttl; + + /* Obtain the ttl */ + if (skb->protocol == htons(ETH_P_IP)) { + ttl = ip_hdr(skb)->ttl; + rt = (struct rtable *)dst; + lwtstate = rt->rt_lwtstate; + } else if (skb->protocol == htons(ETH_P_IPV6)) { + ttl = ipv6_hdr(skb)->hop_limit; + rt6 = (struct rt6_info *)dst; + lwtstate = rt6->rt6i_lwtstate; + } else { + goto drop; + } + + skb_orphan(skb); + + /* Find the output device */ + out_dev = dst->dev; + if (!mpls_output_possible(out_dev) || + !lwtstate || skb_warn_if_lro(skb)) + goto drop; + + skb_forward_csum(skb); + + tun_encap_info = mpls_lwtunnel_encap(lwtstate); + + /* Verify the destination can hold the packet */ + new_header_size = mpls_encap_size(tun_encap_info); + mtu = mpls_dev_mtu(out_dev); + if (mpls_pkt_too_big(skb, mtu - new_header_size)) + goto drop; + + hh_len = LL_RESERVED_SPACE(out_dev); + if (!out_dev->header_ops) + hh_len = 0; + + /* Ensure there is enough space for the headers in the skb */ + if (skb_cow(skb, hh_len + new_header_size)) + goto drop; + + skb_push(skb, new_header_size); + skb_reset_network_header(skb); + + skb->dev = out_dev; + skb->protocol = htons(ETH_P_MPLS_UC); + + /* Push the new labels */ + hdr = mpls_hdr(skb); + bos = true; + for (i = tun_encap_info->labels - 1; i >= 0; i--) { + hdr[i] = mpls_entry_encode(tun_encap_info->label[i], + ttl, 0, bos); + bos = false; + } + + if (rt) + err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway, + skb); + else if (rt6) + err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt6->rt6i_gateway, + skb); + if (err) + net_dbg_ratelimited("%s: packet transmission failed: %d\n", + __func__, err); + + return 0; + +drop: + kfree_skb(skb); + return -EINVAL; +} + +static int mpls_build_state(struct net_device *dev, struct nlattr *nla, + struct lwtunnel_state **ts) +{ + struct mpls_iptunnel_encap *tun_encap_info; + struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1]; + struct lwtunnel_state *newts; + int tun_encap_info_len; + int ret; + + ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla, + mpls_iptunnel_policy); + if (ret < 0) + return ret; + + if (!tb[MPLS_IPTUNNEL_DST]) + return -EINVAL; + + tun_encap_info_len = sizeof(*tun_encap_info); + + newts = lwtunnel_state_alloc(tun_encap_info_len); + if (!newts) + return -ENOMEM; + + newts->len = tun_encap_info_len; + tun_encap_info = mpls_lwtunnel_encap(newts); + ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], MAX_NEW_LABELS, + &tun_encap_info->labels, tun_encap_info->label); + if (ret) + goto errout; + newts->type = LWTUNNEL_ENCAP_MPLS; + newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + + *ts = newts; + + return 0; + +errout: + kfree(newts); + *ts = NULL; + + return ret; +} + +static int mpls_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct mpls_iptunnel_encap *tun_encap_info; + + tun_encap_info = mpls_lwtunnel_encap(lwtstate); + + if (nla_put_labels(skb, MPLS_IPTUNNEL_DST, tun_encap_info->labels, + tun_encap_info->label)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int mpls_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + struct mpls_iptunnel_encap *tun_encap_info; + + tun_encap_info = mpls_lwtunnel_encap(lwtstate); + + return nla_total_size(tun_encap_info->labels * 4); +} + +static int mpls_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + struct mpls_iptunnel_encap *a_hdr = mpls_lwtunnel_encap(a); + struct mpls_iptunnel_encap *b_hdr = mpls_lwtunnel_encap(b); + int l; + + if (a_hdr->labels != b_hdr->labels) + return 1; + + for (l = 0; l < MAX_NEW_LABELS; l++) + if (a_hdr->label[l] != b_hdr->label[l]) + return 1; + return 0; +} + +static const struct lwtunnel_encap_ops mpls_iptun_ops = { + .build_state = mpls_build_state, + .output = mpls_output, + .fill_encap = mpls_fill_encap_info, + .get_encap_size = mpls_encap_nlsize, + .cmp_encap = mpls_encap_cmp, +}; + +static int __init mpls_iptunnel_init(void) +{ + return lwtunnel_encap_add_ops(&mpls_iptun_ops, LWTUNNEL_ENCAP_MPLS); +} +module_init(mpls_iptunnel_init); + +static void __exit mpls_iptunnel_exit(void) +{ + lwtunnel_encap_del_ops(&mpls_iptun_ops, LWTUNNEL_ENCAP_MPLS); +} +module_exit(mpls_iptunnel_exit); + +MODULE_DESCRIPTION("MultiProtocol Label Switching IP Tunnels"); +MODULE_LICENSE("GPL v2"); diff --git a/net/netfilter/core.c b/net/netfilter/core.c index a0e5497..2a5a070 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -34,6 +34,9 @@ EXPORT_SYMBOL(nf_afinfo); const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_ipv6_ops); +DEFINE_PER_CPU(bool, nf_skb_duplicated); +EXPORT_SYMBOL_GPL(nf_skb_duplicated); + int nf_register_afinfo(const struct nf_afinfo *afinfo) { mutex_lock(&afinfo_mutex); @@ -52,9 +55,6 @@ void nf_unregister_afinfo(const struct nf_afinfo *afinfo) } EXPORT_SYMBOL_GPL(nf_unregister_afinfo); -struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly; -EXPORT_SYMBOL(nf_hooks); - #ifdef HAVE_JUMP_LABEL struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; EXPORT_SYMBOL(nf_hooks_needed); @@ -62,63 +62,166 @@ EXPORT_SYMBOL(nf_hooks_needed); static DEFINE_MUTEX(nf_hook_mutex); -int nf_register_hook(struct nf_hook_ops *reg) +static struct list_head *nf_find_hook_list(struct net *net, + const struct nf_hook_ops *reg) { - struct list_head *nf_hook_list; - struct nf_hook_ops *elem; + struct list_head *hook_list = NULL; - mutex_lock(&nf_hook_mutex); - switch (reg->pf) { - case NFPROTO_NETDEV: + if (reg->pf != NFPROTO_NETDEV) + hook_list = &net->nf.hooks[reg->pf][reg->hooknum]; + else if (reg->hooknum == NF_NETDEV_INGRESS) { #ifdef CONFIG_NETFILTER_INGRESS - if (reg->hooknum == NF_NETDEV_INGRESS) { - BUG_ON(reg->dev == NULL); - nf_hook_list = ®->dev->nf_hooks_ingress; - net_inc_ingress_queue(); - break; - } + if (reg->dev && dev_net(reg->dev) == net) + hook_list = ®->dev->nf_hooks_ingress; #endif - /* Fall through. */ - default: - nf_hook_list = &nf_hooks[reg->pf][reg->hooknum]; - break; + } + return hook_list; +} + +struct nf_hook_entry { + const struct nf_hook_ops *orig_ops; + struct nf_hook_ops ops; +}; + +int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) +{ + struct list_head *hook_list; + struct nf_hook_entry *entry; + struct nf_hook_ops *elem; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + entry->orig_ops = reg; + entry->ops = *reg; + + hook_list = nf_find_hook_list(net, reg); + if (!hook_list) { + kfree(entry); + return -ENOENT; } - list_for_each_entry(elem, nf_hook_list, list) { + mutex_lock(&nf_hook_mutex); + list_for_each_entry(elem, hook_list, list) { if (reg->priority < elem->priority) break; } - list_add_rcu(®->list, elem->list.prev); + list_add_rcu(&entry->ops.list, elem->list.prev); mutex_unlock(&nf_hook_mutex); +#ifdef CONFIG_NETFILTER_INGRESS + if (reg->pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) + net_inc_ingress_queue(); +#endif #ifdef HAVE_JUMP_LABEL static_key_slow_inc(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif return 0; } -EXPORT_SYMBOL(nf_register_hook); +EXPORT_SYMBOL(nf_register_net_hook); -void nf_unregister_hook(struct nf_hook_ops *reg) +void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { + struct list_head *hook_list; + struct nf_hook_entry *entry; + struct nf_hook_ops *elem; + + hook_list = nf_find_hook_list(net, reg); + if (!hook_list) + return; + mutex_lock(&nf_hook_mutex); - list_del_rcu(®->list); - mutex_unlock(&nf_hook_mutex); - switch (reg->pf) { - case NFPROTO_NETDEV: -#ifdef CONFIG_NETFILTER_INGRESS - if (reg->hooknum == NF_NETDEV_INGRESS) { - net_dec_ingress_queue(); + list_for_each_entry(elem, hook_list, list) { + entry = container_of(elem, struct nf_hook_entry, ops); + if (entry->orig_ops == reg) { + list_del_rcu(&entry->ops.list); break; } - break; -#endif - default: - break; } + mutex_unlock(&nf_hook_mutex); + if (&elem->list == hook_list) { + WARN(1, "nf_unregister_net_hook: hook not found!\n"); + return; + } +#ifdef CONFIG_NETFILTER_INGRESS + if (reg->pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) + net_dec_ingress_queue(); +#endif #ifdef HAVE_JUMP_LABEL static_key_slow_dec(&nf_hooks_needed[reg->pf][reg->hooknum]); #endif synchronize_net(); - nf_queue_nf_hook_drop(reg); + nf_queue_nf_hook_drop(net, &entry->ops); + kfree(entry); +} +EXPORT_SYMBOL(nf_unregister_net_hook); + +int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < n; i++) { + err = nf_register_net_hook(net, ®[i]); + if (err) + goto err; + } + return err; + +err: + if (i > 0) + nf_unregister_net_hooks(net, reg, i); + return err; +} +EXPORT_SYMBOL(nf_register_net_hooks); + +void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, + unsigned int n) +{ + while (n-- > 0) + nf_unregister_net_hook(net, ®[n]); +} +EXPORT_SYMBOL(nf_unregister_net_hooks); + +static LIST_HEAD(nf_hook_list); + +int nf_register_hook(struct nf_hook_ops *reg) +{ + struct net *net, *last; + int ret; + + rtnl_lock(); + for_each_net(net) { + ret = nf_register_net_hook(net, reg); + if (ret && ret != -ENOENT) + goto rollback; + } + list_add_tail(®->list, &nf_hook_list); + rtnl_unlock(); + + return 0; +rollback: + last = net; + for_each_net(net) { + if (net == last) + break; + nf_unregister_net_hook(net, reg); + } + rtnl_unlock(); + return ret; +} +EXPORT_SYMBOL(nf_register_hook); + +void nf_unregister_hook(struct nf_hook_ops *reg) +{ + struct net *net; + + rtnl_lock(); + list_del(®->list); + for_each_net(net) + nf_unregister_net_hook(net, reg); + rtnl_unlock(); } EXPORT_SYMBOL(nf_unregister_hook); @@ -295,8 +398,46 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); EXPORT_SYMBOL(nf_nat_decode_session_hook); #endif +static int nf_register_hook_list(struct net *net) +{ + struct nf_hook_ops *elem; + int ret; + + rtnl_lock(); + list_for_each_entry(elem, &nf_hook_list, list) { + ret = nf_register_net_hook(net, elem); + if (ret && ret != -ENOENT) + goto out_undo; + } + rtnl_unlock(); + return 0; + +out_undo: + list_for_each_entry_continue_reverse(elem, &nf_hook_list, list) + nf_unregister_net_hook(net, elem); + rtnl_unlock(); + return ret; +} + +static void nf_unregister_hook_list(struct net *net) +{ + struct nf_hook_ops *elem; + + rtnl_lock(); + list_for_each_entry(elem, &nf_hook_list, list) + nf_unregister_net_hook(net, elem); + rtnl_unlock(); +} + static int __net_init netfilter_net_init(struct net *net) { + int i, h, ret; + + for (i = 0; i < ARRAY_SIZE(net->nf.hooks); i++) { + for (h = 0; h < NF_MAX_HOOKS; h++) + INIT_LIST_HEAD(&net->nf.hooks[i][h]); + } + #ifdef CONFIG_PROC_FS net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter", net->proc_net); @@ -307,11 +448,16 @@ static int __net_init netfilter_net_init(struct net *net) return -ENOMEM; } #endif - return 0; + ret = nf_register_hook_list(net); + if (ret) + remove_proc_entry("netfilter", net->proc_net); + + return ret; } static void __net_exit netfilter_net_exit(struct net *net) { + nf_unregister_hook_list(net); remove_proc_entry("netfilter", net->proc_net); } @@ -322,12 +468,7 @@ static struct pernet_operations netfilter_net_ops = { int __init netfilter_init(void) { - int i, h, ret; - - for (i = 0; i < ARRAY_SIZE(nf_hooks); i++) { - for (h = 0; h < NF_MAX_HOOKS; h++) - INIT_LIST_HEAD(&nf_hooks[i][h]); - } + int ret; ret = register_pernet_subsys(&netfilter_net_ops); if (ret < 0) diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 7e81416..a2ff7d7 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -137,7 +137,7 @@ struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name) void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler) { - if (scheduler && scheduler->module) + if (scheduler) module_put(scheduler->module); } diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index b45da90..6719773 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -42,6 +42,8 @@ static const char *const sctp_conntrack_names[] = { "SHUTDOWN_SENT", "SHUTDOWN_RECD", "SHUTDOWN_ACK_SENT", + "HEARTBEAT_SENT", + "HEARTBEAT_ACKED", }; #define SECS * HZ @@ -57,6 +59,8 @@ static unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] __read_mostly = { [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, + [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, + [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, }; #define sNO SCTP_CONNTRACK_NONE @@ -67,6 +71,8 @@ static unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] __read_mostly = { #define sSS SCTP_CONNTRACK_SHUTDOWN_SENT #define sSR SCTP_CONNTRACK_SHUTDOWN_RECD #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT +#define sHS SCTP_CONNTRACK_HEARTBEAT_SENT +#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED #define sIV SCTP_CONNTRACK_MAX /* @@ -88,6 +94,10 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite to that of the SHUTDOWN chunk. CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. +HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. +HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to + that of the HEARTBEAT chunk. Secondary connection is + established. */ /* TODO @@ -97,36 +107,40 @@ CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of - Check the error type in the reply dir before transitioning from cookie echoed to closed. - Sec 5.2.4 of RFC 2960 - - Multi Homing support. + - Full Multi Homing support. */ /* SCTP conntrack state transitions */ -static const u8 sctp_conntracks[2][9][SCTP_CONNTRACK_MAX] = { +static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA */ -/* init */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA}, -/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA}, -/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA}, -/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't have Stale cookie*/ -/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't come in orig dir */ -/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ +/* init */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, +/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, +/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, +/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, +/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA}, +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/ +/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */ +/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA}, +/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, +/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA} }, { /* REPLY */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA */ -/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA}, -/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA}, -/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA}, -/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA},/* Can't come in reply dir */ -/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA}, -/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ +/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ +/* init_ack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, +/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, +/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, +/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, +/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA}, +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */ +/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA}, +/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA}, +/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, +/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA} } }; @@ -278,9 +292,16 @@ static int sctp_new_state(enum ip_conntrack_dir dir, pr_debug("SCTP_CID_SHUTDOWN_COMPLETE\n"); i = 8; break; + case SCTP_CID_HEARTBEAT: + pr_debug("SCTP_CID_HEARTBEAT"); + i = 9; + break; + case SCTP_CID_HEARTBEAT_ACK: + pr_debug("SCTP_CID_HEARTBEAT_ACK"); + i = 10; + break; default: - /* Other chunks like DATA, SACK, HEARTBEAT and - its ACK do not cause a change in state */ + /* Other chunks like DATA or SACK do not change the state */ pr_debug("Unknown chunk type, Will stay in %s\n", sctp_conntrack_names[cur_state]); return cur_state; @@ -329,6 +350,8 @@ static int sctp_packet(struct nf_conn *ct, !test_bit(SCTP_CID_COOKIE_ECHO, map) && !test_bit(SCTP_CID_ABORT, map) && !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && + !test_bit(SCTP_CID_HEARTBEAT, map) && + !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && sh->vtag != ct->proto.sctp.vtag[dir]) { pr_debug("Verification tag check failed\n"); goto out; @@ -357,6 +380,16 @@ static int sctp_packet(struct nf_conn *ct, /* Sec 8.5.1 (D) */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; + } else if (sch->type == SCTP_CID_HEARTBEAT || + sch->type == SCTP_CID_HEARTBEAT_ACK) { + if (ct->proto.sctp.vtag[dir] == 0) { + pr_debug("Setting vtag %x for dir %d\n", + sh->vtag, dir); + ct->proto.sctp.vtag[dir] = sh->vtag; + } else if (sh->vtag != ct->proto.sctp.vtag[dir]) { + pr_debug("Verification tag check failed\n"); + goto out_unlock; + } } old_state = ct->proto.sctp.state; @@ -466,6 +499,10 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, /* Sec 8.5.1 (A) */ return false; } + } else if (sch->type == SCTP_CID_HEARTBEAT) { + pr_debug("Setting vtag %x for secondary conntrack\n", + sh->vtag); + ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; } /* If it is a shutdown ack OOTB packet, we expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */ @@ -610,6 +647,8 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_SHUTDOWN_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_SHUTDOWN_RECD] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ @@ -658,6 +697,18 @@ static struct ctl_table sctp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "nf_conntrack_sctp_timeout_heartbeat_sent", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "nf_conntrack_sctp_timeout_heartbeat_acked", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, { } }; @@ -730,6 +781,8 @@ static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, pn->ctl_table[4].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT]; pn->ctl_table[5].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD]; pn->ctl_table[6].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]; + pn->ctl_table[7].data = &sn->timeouts[SCTP_CONNTRACK_HEARTBEAT_SENT]; + pn->ctl_table[8].data = &sn->timeouts[SCTP_CONNTRACK_HEARTBEAT_ACKED]; #endif return 0; } diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 3992106..0655225 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -19,7 +19,7 @@ unsigned int nf_iterate(struct list_head *head, struct sk_buff *skb, /* nf_queue.c */ int nf_queue(struct sk_buff *skb, struct nf_hook_ops *elem, struct nf_hook_state *state, unsigned int queuenum); -void nf_queue_nf_hook_drop(struct nf_hook_ops *ops); +void nf_queue_nf_hook_drop(struct net *net, struct nf_hook_ops *ops); int __init netfilter_queue_init(void); /* nf_log.c */ diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 8a8b2ab..96777f9 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -105,21 +105,15 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); -void nf_queue_nf_hook_drop(struct nf_hook_ops *ops) +void nf_queue_nf_hook_drop(struct net *net, struct nf_hook_ops *ops) { const struct nf_queue_handler *qh; - struct net *net; - rtnl_lock(); rcu_read_lock(); qh = rcu_dereference(queue_handler); - if (qh) { - for_each_net(net) { - qh->nf_hook_drop(net, ops); - } - } + if (qh) + qh->nf_hook_drop(net, ops); rcu_read_unlock(); - rtnl_unlock(); } /* diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index cfe6368..4a41eb9 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -130,20 +130,24 @@ static void nft_trans_destroy(struct nft_trans *trans) int nft_register_basechain(struct nft_base_chain *basechain, unsigned int hook_nops) { + struct net *net = read_pnet(&basechain->pnet); + if (basechain->flags & NFT_BASECHAIN_DISABLED) return 0; - return nf_register_hooks(basechain->ops, hook_nops); + return nf_register_net_hooks(net, basechain->ops, hook_nops); } EXPORT_SYMBOL_GPL(nft_register_basechain); void nft_unregister_basechain(struct nft_base_chain *basechain, unsigned int hook_nops) { + struct net *net = read_pnet(&basechain->pnet); + if (basechain->flags & NFT_BASECHAIN_DISABLED) return; - nf_unregister_hooks(basechain->ops, hook_nops); + nf_unregister_net_hooks(net, basechain->ops, hook_nops); } EXPORT_SYMBOL_GPL(nft_unregister_basechain); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index f77bad4..05d0b03 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -114,7 +114,6 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) { const struct nft_chain *chain = ops->priv, *basechain = chain; - const struct net *chain_net = read_pnet(&nft_base_chain(basechain)->pnet); const struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); const struct nft_rule *rule; const struct nft_expr *expr, *last; @@ -125,10 +124,6 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) int rulenum; unsigned int gencursor = nft_genmask_cur(net); - /* Ignore chains that are not for the current network namespace */ - if (!net_eq(net, chain_net)) - return NF_ACCEPT; - do_chain: rulenum = 0; rule = list_entry(&chain->rules, struct nft_rule, list); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 52561e1..cb2f13e 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -166,11 +166,13 @@ void nft_meta_get_eval(const struct nft_expr *expr, goto err; *dest = out->group; break; +#ifdef CONFIG_CGROUP_NET_CLASSID case NFT_META_CGROUP: if (skb->sk == NULL || !sk_fullsock(skb->sk)) goto err; *dest = skb->sk->sk_classid; break; +#endif default: WARN_ON(1); goto err; @@ -246,7 +248,9 @@ int nft_meta_get_init(const struct nft_ctx *ctx, case NFT_META_CPU: case NFT_META_IIFGROUP: case NFT_META_OIFGROUP: +#ifdef CONFIG_CGROUP_NET_CLASSID case NFT_META_CGROUP: +#endif len = sizeof(u32); break; case NFT_META_IIFNAME: diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index d324fe7..9b42b5e 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -67,9 +67,6 @@ static const char *const xt_prefix[NFPROTO_NUMPROTO] = { [NFPROTO_IPV6] = "ip6", }; -/* Allow this many total (re)entries. */ -static const unsigned int xt_jumpstack_multiplier = 2; - /* Registration hooks for targets. */ int xt_register_target(struct xt_target *target) { @@ -688,8 +685,6 @@ void xt_free_table_info(struct xt_table_info *info) kvfree(info->jumpstack); } - free_percpu(info->stackptr); - kvfree(info); } EXPORT_SYMBOL(xt_free_table_info); @@ -732,15 +727,14 @@ EXPORT_SYMBOL_GPL(xt_compat_unlock); DEFINE_PER_CPU(seqcount_t, xt_recseq); EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq); +struct static_key xt_tee_enabled __read_mostly; +EXPORT_SYMBOL_GPL(xt_tee_enabled); + static int xt_jumpstack_alloc(struct xt_table_info *i) { unsigned int size; int cpu; - i->stackptr = alloc_percpu(unsigned int); - if (i->stackptr == NULL) - return -ENOMEM; - size = sizeof(void **) * nr_cpu_ids; if (size > PAGE_SIZE) i->jumpstack = vzalloc(size); @@ -749,8 +743,21 @@ static int xt_jumpstack_alloc(struct xt_table_info *i) if (i->jumpstack == NULL) return -ENOMEM; - i->stacksize *= xt_jumpstack_multiplier; - size = sizeof(void *) * i->stacksize; + /* ruleset without jumps -- no stack needed */ + if (i->stacksize == 0) + return 0; + + /* Jumpstack needs to be able to record two full callchains, one + * from the first rule set traversal, plus one table reentrancy + * via -j TEE without clobbering the callchain that brought us to + * TEE target. + * + * This is done by allocating two jumpstacks per cpu, on reentry + * the upper half of the stack is used. + * + * see the jumpstack setup in ipt_do_table() for more details. + */ + size = sizeof(void *) * i->stacksize * 2u; for_each_possible_cpu(cpu) { if (size > PAGE_SIZE) i->jumpstack[cpu] = vmalloc_node(size, diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index a747eb4..c5d6556 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -37,7 +37,6 @@ struct xt_tee_priv { }; static const union nf_inet_addr tee_zero_address; -static DEFINE_PER_CPU(bool, tee_active); static struct net *pick_net(struct sk_buff *skb) { @@ -88,7 +87,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) const struct xt_tee_tginfo *info = par->targinfo; struct iphdr *iph; - if (__this_cpu_read(tee_active)) + if (__this_cpu_read(nf_skb_duplicated)) return XT_CONTINUE; /* * Copy the skb, and route the copy. Will later return %XT_CONTINUE for @@ -125,9 +124,9 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) ip_send_check(iph); if (tee_tg_route4(skb, info)) { - __this_cpu_write(tee_active, true); + __this_cpu_write(nf_skb_duplicated, true); ip_local_out(skb); - __this_cpu_write(tee_active, false); + __this_cpu_write(nf_skb_duplicated, false); } else { kfree_skb(skb); } @@ -170,7 +169,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; - if (__this_cpu_read(tee_active)) + if (__this_cpu_read(nf_skb_duplicated)) return XT_CONTINUE; skb = pskb_copy(skb, GFP_ATOMIC); if (skb == NULL) @@ -188,9 +187,9 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) --iph->hop_limit; } if (tee_tg_route6(skb, info)) { - __this_cpu_write(tee_active, true); + __this_cpu_write(nf_skb_duplicated, true); ip6_local_out(skb); - __this_cpu_write(tee_active, false); + __this_cpu_write(nf_skb_duplicated, false); } else { kfree_skb(skb); } @@ -252,6 +251,7 @@ static int tee_tg_check(const struct xt_tgchk_param *par) } else info->priv = NULL; + static_key_slow_inc(&xt_tee_enabled); return 0; } @@ -263,6 +263,7 @@ static void tee_tg_destroy(const struct xt_tgdtor_param *par) unregister_netdevice_notifier(&info->priv->notifier); kfree(info->priv); } + static_key_slow_dec(&xt_tee_enabled); } static struct xt_target tee_tg_reg[] __read_mostly = { diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index cca96ce..d0c96c5 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -272,8 +272,7 @@ tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport, hp->source, lport ? lport : hp->dest, skb->dev, NFT_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk)); - inet_twsk_put(inet_twsk(sk)); + inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; } } @@ -437,8 +436,7 @@ tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, tgi->lport ? tgi->lport : hp->dest, skb->dev, NFT_LOOKUP_LISTENER); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk)); - inet_twsk_put(inet_twsk(sk)); + inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; } } diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 1584040..422dc05 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -34,7 +34,7 @@ config OPENVSWITCH config OPENVSWITCH_GRE tristate "Open vSwitch GRE tunneling support" depends on OPENVSWITCH - depends on NET_IPGRE_DEMUX + depends on NET_IPGRE default OPENVSWITCH ---help--- If you say Y here, then the Open vSwitch will be able create GRE diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile index 91b9478..6e1701d 100644 --- a/net/openvswitch/Makefile +++ b/net/openvswitch/Makefile @@ -15,6 +15,6 @@ openvswitch-y := \ vport-internal_dev.o \ vport-netdev.o +obj-$(CONFIG_OPENVSWITCH_VXLAN)+= vport-vxlan.o obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o -obj-$(CONFIG_OPENVSWITCH_VXLAN) += vport-vxlan.o obj-$(CONFIG_OPENVSWITCH_GRE) += vport-gre.o diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ee34f47..14da52d 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -619,7 +619,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, const struct nlattr *actions, int actions_len) { - struct ovs_tunnel_info info; + struct ip_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; @@ -677,9 +677,12 @@ static int sample(struct datapath *dp, struct sk_buff *skb, for (a = nla_data(attr), rem = nla_len(attr); rem > 0; a = nla_next(a, &rem)) { + u32 probability; + switch (nla_type(a)) { case OVS_SAMPLE_ATTR_PROBABILITY: - if (prandom_u32() >= nla_get_u32(a)) + probability = nla_get_u32(a); + if (!probability || prandom_u32() > probability) return 0; break; @@ -741,7 +744,15 @@ static int execute_set_action(struct sk_buff *skb, { /* Only tunnel set execution is supported without a mask. */ if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) { - OVS_CB(skb)->egress_tun_info = nla_data(a); + struct ovs_tunnel_info *tun = nla_data(a); + + skb_dst_drop(skb); + dst_hold((struct dst_entry *)tun->tun_dst); + skb_dst_set(skb, (struct dst_entry *)tun->tun_dst); + + /* FIXME: Remove when all vports have been converted */ + OVS_CB(skb)->egress_tun_info = &tun->tun_dst->u.tun_info; + return 0; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index ff8c4a4..ffe984f 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -176,7 +176,7 @@ static inline struct datapath *get_dp(struct net *net, int dp_ifindex) const char *ovs_dp_name(const struct datapath *dp) { struct vport *vport = ovs_vport_ovsl_rcu(dp, OVSP_LOCAL); - return vport->ops->get_name(vport); + return ovs_vport_name(vport); } static int get_dpifindex(const struct datapath *dp) @@ -188,7 +188,7 @@ static int get_dpifindex(const struct datapath *dp) local = ovs_vport_rcu(dp, OVSP_LOCAL); if (local) - ifindex = netdev_vport_priv(local)->dev->ifindex; + ifindex = local->dev->ifindex; else ifindex = 0; @@ -1018,7 +1018,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) } ovs_unlock(); - ovs_nla_free_flow_actions(old_acts); + ovs_nla_free_flow_actions_rcu(old_acts); ovs_flow_free(new_flow, false); } @@ -1030,7 +1030,7 @@ err_unlock_ovs: ovs_unlock(); kfree_skb(reply); err_kfree_acts: - kfree(acts); + ovs_nla_free_flow_actions(acts); err_kfree_flow: ovs_flow_free(new_flow, false); error: @@ -1157,7 +1157,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) if (reply) ovs_notify(&dp_flow_genl_family, reply, info); if (old_acts) - ovs_nla_free_flow_actions(old_acts); + ovs_nla_free_flow_actions_rcu(old_acts); return 0; @@ -1165,7 +1165,7 @@ err_unlock_ovs: ovs_unlock(); kfree_skb(reply); err_kfree_acts: - kfree(acts); + ovs_nla_free_flow_actions(acts); error: return error; } @@ -1800,7 +1800,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) || nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) || nla_put_string(skb, OVS_VPORT_ATTR_NAME, - vport->ops->get_name(vport))) + ovs_vport_name(vport))) goto nla_put_failure; ovs_vport_get_stats(vport, &vport_stats); @@ -2219,13 +2219,10 @@ static void __net_exit list_vports_from_net(struct net *net, struct net *dnet, struct vport *vport; hlist_for_each_entry(vport, &dp->ports[i], dp_hash_node) { - struct netdev_vport *netdev_vport; - if (vport->ops->type != OVS_VPORT_TYPE_INTERNAL) continue; - netdev_vport = netdev_vport_priv(vport); - if (dev_net(netdev_vport->dev) == dnet) + if (dev_net(vport->dev) == dnet) list_add(&vport->detach_list, head); } } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index cd691e9..6b28c5c 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -25,6 +25,7 @@ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/u64_stats_sync.h> +#include <net/ip_tunnels.h> #include "flow.h" #include "flow_table.h" @@ -98,7 +99,7 @@ struct datapath { * when a packet is received by OVS. */ struct ovs_skb_cb { - struct ovs_tunnel_info *egress_tun_info; + struct ip_tunnel_info *egress_tun_info; struct vport *input_vport; }; #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb) @@ -114,7 +115,7 @@ struct ovs_skb_cb { * @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY. */ struct dp_upcall_info { - const struct ovs_tunnel_info *egress_tun_info; + const struct ip_tunnel_info *egress_tun_info; const struct nlattr *userdata; const struct nlattr *actions; int actions_len; diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index 2c631fe..a7a80a6 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -58,13 +58,10 @@ void ovs_dp_notify_wq(struct work_struct *work) struct hlist_node *n; hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) { - struct netdev_vport *netdev_vport; - if (vport->ops->type != OVS_VPORT_TYPE_NETDEV) continue; - netdev_vport = netdev_vport_priv(vport); - if (!(netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH)) + if (!(vport->dev->priv_flags & IFF_OVS_DATAPATH)) dp_detach_port_notify(vport); } } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index bc7b0ab..8db22ef 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -682,12 +682,12 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key) return key_extract(skb, key); } -int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info, +int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key) { /* Extract metadata from packet. */ if (tun_info) { - memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key)); + memcpy(&key->tun_key, &tun_info->key, sizeof(key->tun_key)); if (tun_info->options) { BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) * diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index a076e44..b62cdb3 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -32,31 +32,11 @@ #include <linux/time.h> #include <linux/flex_array.h> #include <net/inet_ecn.h> +#include <net/ip_tunnels.h> +#include <net/dst_metadata.h> struct sk_buff; -/* Used to memset ovs_key_ipv4_tunnel padding. */ -#define OVS_TUNNEL_KEY_SIZE \ - (offsetof(struct ovs_key_ipv4_tunnel, tp_dst) + \ - FIELD_SIZEOF(struct ovs_key_ipv4_tunnel, tp_dst)) - -struct ovs_key_ipv4_tunnel { - __be64 tun_id; - __be32 ipv4_src; - __be32 ipv4_dst; - __be16 tun_flags; - u8 ipv4_tos; - u8 ipv4_ttl; - __be16 tp_src; - __be16 tp_dst; -} __packed __aligned(4); /* Minimize padding. */ - -struct ovs_tunnel_info { - struct ovs_key_ipv4_tunnel tunnel; - const void *options; - u8 options_len; -}; - /* Store options at the end of the array if they are less than the * maximum size. This allows us to get the benefits of variable length * matching for small options. @@ -66,54 +46,9 @@ struct ovs_tunnel_info { #define TUN_METADATA_OPTS(flow_key, opt_len) \ ((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len))) -static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, - __be32 saddr, __be32 daddr, - u8 tos, u8 ttl, - __be16 tp_src, - __be16 tp_dst, - __be64 tun_id, - __be16 tun_flags, - const void *opts, - u8 opts_len) -{ - tun_info->tunnel.tun_id = tun_id; - tun_info->tunnel.ipv4_src = saddr; - tun_info->tunnel.ipv4_dst = daddr; - tun_info->tunnel.ipv4_tos = tos; - tun_info->tunnel.ipv4_ttl = ttl; - tun_info->tunnel.tun_flags = tun_flags; - - /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of - * the upper tunnel are used. - * E.g: GRE over IPSEC, the tp_src and tp_port are zero. - */ - tun_info->tunnel.tp_src = tp_src; - tun_info->tunnel.tp_dst = tp_dst; - - /* Clear struct padding. */ - if (sizeof(tun_info->tunnel) != OVS_TUNNEL_KEY_SIZE) - memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, - 0, sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE); - - tun_info->options = opts; - tun_info->options_len = opts_len; -} - -static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, - const struct iphdr *iph, - __be16 tp_src, - __be16 tp_dst, - __be64 tun_id, - __be16 tun_flags, - const void *opts, - u8 opts_len) -{ - __ovs_flow_tun_info_init(tun_info, iph->saddr, iph->daddr, - iph->tos, iph->ttl, - tp_src, tp_dst, - tun_id, tun_flags, - opts, opts_len); -} +struct ovs_tunnel_info { + struct metadata_dst *tun_dst; +}; #define OVS_SW_FLOW_KEY_METADATA_SIZE \ (offsetof(struct sw_flow_key, recirc_id) + \ @@ -122,7 +57,7 @@ static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, struct sw_flow_key { u8 tun_opts[255]; u8 tun_opts_len; - struct ovs_key_ipv4_tunnel tun_key; /* Encapsulating tunnel key. */ + struct ip_tunnel_key tun_key; /* Encapsulating tunnel key. */ struct { u32 priority; /* Packet QoS priority. */ u32 skb_mark; /* SKB mark. */ @@ -273,7 +208,7 @@ void ovs_flow_stats_clear(struct sw_flow *); u64 ovs_flow_used_time(unsigned long flow_jiffies); int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key); -int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info, +int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, struct sk_buff *skb, struct sw_flow_key *key); /* Extract key from packet coming from userspace. */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 624e41c..a6eb77a 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -47,9 +47,9 @@ #include <net/ipv6.h> #include <net/ndisc.h> #include <net/mpls.h> +#include <net/vxlan.h> #include "flow_netlink.h" -#include "vport-vxlan.h" struct ovs_len_tbl { int len; @@ -475,7 +475,7 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *a, { struct nlattr *tb[OVS_VXLAN_EXT_MAX+1]; unsigned long opt_key_offset; - struct ovs_vxlan_opts opts; + struct vxlan_metadata opts; int err; BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); @@ -626,7 +626,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, static int vxlan_opt_to_nlattr(struct sk_buff *skb, const void *tun_opts, int swkey_tun_opts_len) { - const struct ovs_vxlan_opts *opts = tun_opts; + const struct vxlan_metadata *opts = tun_opts; struct nlattr *nla; nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS); @@ -641,7 +641,7 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb, } static int __ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ovs_key_ipv4_tunnel *output, + const struct ip_tunnel_key *output, const void *tun_opts, int swkey_tun_opts_len) { if (output->tun_flags & TUNNEL_KEY && @@ -689,7 +689,7 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, } static int ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ovs_key_ipv4_tunnel *output, + const struct ip_tunnel_key *output, const void *tun_opts, int swkey_tun_opts_len) { struct nlattr *nla; @@ -708,9 +708,9 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, } int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb, - const struct ovs_tunnel_info *egress_tun_info) + const struct ip_tunnel_info *egress_tun_info) { - return __ipv4_tun_to_nlattr(skb, &egress_tun_info->tunnel, + return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key, egress_tun_info->options, egress_tun_info->options_len); } @@ -1548,11 +1548,48 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log) return sfa; } +static void ovs_nla_free_set_action(const struct nlattr *a) +{ + const struct nlattr *ovs_key = nla_data(a); + struct ovs_tunnel_info *ovs_tun; + + switch (nla_type(ovs_key)) { + case OVS_KEY_ATTR_TUNNEL_INFO: + ovs_tun = nla_data(ovs_key); + dst_release((struct dst_entry *)ovs_tun->tun_dst); + break; + } +} + +void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +{ + const struct nlattr *a; + int rem; + + if (!sf_acts) + return; + + nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) { + switch (nla_type(a)) { + case OVS_ACTION_ATTR_SET: + ovs_nla_free_set_action(a); + break; + } + } + + kfree(sf_acts); +} + +static void __ovs_nla_free_flow_actions(struct rcu_head *head) +{ + ovs_nla_free_flow_actions(container_of(head, struct sw_flow_actions, rcu)); +} + /* Schedules 'sf_acts' to be freed after the next RCU grace period. * The caller must hold rcu_read_lock for this to be sensible. */ -void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *sf_acts) { - kfree_rcu(sf_acts, rcu); + call_rcu(&sf_acts->rcu, __ovs_nla_free_flow_actions); } static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, @@ -1746,7 +1783,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, { struct sw_flow_match match; struct sw_flow_key key; - struct ovs_tunnel_info *tun_info; + struct metadata_dst *tun_dst; + struct ip_tunnel_info *tun_info; + struct ovs_tunnel_info *ovs_tun; struct nlattr *a; int err = 0, start, opts_type; @@ -1771,13 +1810,23 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, if (start < 0) return start; + tun_dst = metadata_dst_alloc(key.tun_opts_len, GFP_KERNEL); + if (!tun_dst) + return -ENOMEM; + a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL, - sizeof(*tun_info) + key.tun_opts_len, log); - if (IS_ERR(a)) + sizeof(*ovs_tun), log); + if (IS_ERR(a)) { + dst_release((struct dst_entry *)tun_dst); return PTR_ERR(a); + } + + ovs_tun = nla_data(a); + ovs_tun->tun_dst = tun_dst; - tun_info = nla_data(a); - tun_info->tunnel = key.tun_key; + tun_info = &tun_dst->u.tun_info; + tun_info->mode = IP_TUNNEL_INFO_TX; + tun_info->key = key.tun_key; tun_info->options_len = key.tun_opts_len; if (tun_info->options_len) { @@ -2177,7 +2226,7 @@ int ovs_nla_copy_actions(const struct nlattr *attr, err = __ovs_nla_copy_actions(attr, key, 0, sfa, key->eth.type, key->eth.tci, log); if (err) - kfree(*sfa); + ovs_nla_free_flow_actions(*sfa); return err; } @@ -2227,13 +2276,14 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) switch (key_type) { case OVS_KEY_ATTR_TUNNEL_INFO: { - struct ovs_tunnel_info *tun_info = nla_data(ovs_key); + struct ovs_tunnel_info *ovs_tun = nla_data(ovs_key); + struct ip_tunnel_info *tun_info = &ovs_tun->tun_dst->u.tun_info; start = nla_nest_start(skb, OVS_ACTION_ATTR_SET); if (!start) return -EMSGSIZE; - err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel, + err = ipv4_tun_to_nlattr(skb, &tun_info->key, tun_info->options_len ? tun_info->options : NULL, tun_info->options_len); diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 5c3d75b..acd0744 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -55,7 +55,7 @@ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key, const struct nlattr *mask, bool log); int ovs_nla_put_egress_tunnel_key(struct sk_buff *, - const struct ovs_tunnel_info *); + const struct ip_tunnel_info *); bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log); int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid, @@ -69,5 +69,6 @@ int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb); void ovs_nla_free_flow_actions(struct sw_flow_actions *); +void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *); #endif /* flow_netlink.h */ diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 6552394..3a9d1dde76 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -18,6 +18,7 @@ #include "flow.h" #include "datapath.h" +#include "flow_netlink.h" #include <linux/uaccess.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> @@ -143,7 +144,8 @@ static void flow_free(struct sw_flow *flow) if (ovs_identifier_is_key(&flow->id)) kfree(flow->id.unmasked_key); - kfree((struct sw_flow_actions __force *)flow->sf_acts); + if (flow->sf_acts) + ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts); for_each_node(node) if (flow->stats[node]) kmem_cache_free(flow_stats_cache, diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 208c576..1da3a14 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -77,7 +77,7 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb) struct vport *vport = gs->rcv_data; struct genevehdr *geneveh = geneve_hdr(skb); int opts_len; - struct ovs_tunnel_info tun_info; + struct ip_tunnel_info tun_info; __be64 key; __be16 flags; @@ -90,10 +90,9 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb) key = vni_to_tunnel_id(geneveh->vni); - ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), - udp_hdr(skb)->source, udp_hdr(skb)->dest, - key, flags, - geneveh->options, opts_len); + ip_tunnel_info_init(&tun_info, ip_hdr(skb), + udp_hdr(skb)->source, udp_hdr(skb)->dest, + key, flags, geneveh->options, opts_len); ovs_vport_receive(vport, skb, &tun_info); } @@ -165,8 +164,8 @@ error: static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) { - const struct ovs_key_ipv4_tunnel *tun_key; - struct ovs_tunnel_info *tun_info; + const struct ip_tunnel_key *tun_key; + struct ip_tunnel_info *tun_info; struct net *net = ovs_dp_get_net(vport->dp); struct geneve_port *geneve_port = geneve_vport(vport); __be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport; @@ -183,7 +182,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) goto error; } - tun_key = &tun_info->tunnel; + tun_key = &tun_info->key; rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP); if (IS_ERR(rt)) { err = PTR_ERR(rt); @@ -225,7 +224,7 @@ static const char *geneve_get_name(const struct vport *vport) } static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *egress_tun_info) + struct ip_tunnel_info *egress_tun_info) { struct geneve_port *geneve_port = geneve_vport(vport); struct net *net = ovs_dp_get_net(vport->dp); diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index f17ac96..871801d 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -45,239 +45,47 @@ #include "datapath.h" #include "vport.h" +#include "vport-netdev.h" static struct vport_ops ovs_gre_vport_ops; -/* Returns the least-significant 32 bits of a __be64. */ -static __be32 be64_get_low32(__be64 x) +static struct vport *gre_tnl_create(const struct vport_parms *parms) { -#ifdef __BIG_ENDIAN - return (__force __be32)x; -#else - return (__force __be32)((__force u64)x >> 32); -#endif -} - -static __be16 filter_tnl_flags(__be16 flags) -{ - return flags & (TUNNEL_CSUM | TUNNEL_KEY); -} - -static struct sk_buff *__build_header(struct sk_buff *skb, - int tunnel_hlen) -{ - struct tnl_ptk_info tpi; - const struct ovs_key_ipv4_tunnel *tun_key; - - tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - - skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM)); - if (IS_ERR(skb)) - return skb; - - tpi.flags = filter_tnl_flags(tun_key->tun_flags); - tpi.proto = htons(ETH_P_TEB); - tpi.key = be64_get_low32(tun_key->tun_id); - tpi.seq = 0; - gre_build_header(skb, &tpi, tunnel_hlen); - - return skb; -} - -static __be64 key_to_tunnel_id(__be32 key, __be32 seq) -{ -#ifdef __BIG_ENDIAN - return (__force __be64)((__force u64)seq << 32 | (__force u32)key); -#else - return (__force __be64)((__force u64)key << 32 | (__force u32)seq); -#endif -} - -/* Called with rcu_read_lock and BH disabled. */ -static int gre_rcv(struct sk_buff *skb, - const struct tnl_ptk_info *tpi) -{ - struct ovs_tunnel_info tun_info; - struct ovs_net *ovs_net; - struct vport *vport; - __be64 key; - - ovs_net = net_generic(dev_net(skb->dev), ovs_net_id); - vport = rcu_dereference(ovs_net->vport_net.gre_vport); - if (unlikely(!vport)) - return PACKET_REJECT; - - key = key_to_tunnel_id(tpi->key, tpi->seq); - ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), 0, 0, key, - filter_tnl_flags(tpi->flags), NULL, 0); - - ovs_vport_receive(vport, skb, &tun_info); - return PACKET_RCVD; -} - -/* Called with rcu_read_lock and BH disabled. */ -static int gre_err(struct sk_buff *skb, u32 info, - const struct tnl_ptk_info *tpi) -{ - struct ovs_net *ovs_net; + struct net *net = ovs_dp_get_net(parms->dp); + struct net_device *dev; struct vport *vport; - ovs_net = net_generic(dev_net(skb->dev), ovs_net_id); - vport = rcu_dereference(ovs_net->vport_net.gre_vport); - - if (unlikely(!vport)) - return PACKET_REJECT; - else - return PACKET_RCVD; -} - -static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) -{ - struct net *net = ovs_dp_get_net(vport->dp); - const struct ovs_key_ipv4_tunnel *tun_key; - struct flowi4 fl; - struct rtable *rt; - int min_headroom; - int tunnel_hlen; - __be16 df; - int err; - - if (unlikely(!OVS_CB(skb)->egress_tun_info)) { - err = -EINVAL; - goto err_free_skb; - } - - tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_GRE); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - goto err_free_skb; - } - - tunnel_hlen = ip_gre_calc_hlen(tun_key->tun_flags); - - min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len - + tunnel_hlen + sizeof(struct iphdr) - + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); - if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) { - int head_delta = SKB_DATA_ALIGN(min_headroom - - skb_headroom(skb) + - 16); - err = pskb_expand_head(skb, max_t(int, head_delta, 0), - 0, GFP_ATOMIC); - if (unlikely(err)) - goto err_free_rt; - } - - skb = vlan_hwaccel_push_inside(skb); - if (unlikely(!skb)) { - err = -ENOMEM; - goto err_free_rt; - } - - /* Push Tunnel header. */ - skb = __build_header(skb, tunnel_hlen); - if (IS_ERR(skb)) { - err = PTR_ERR(skb); - skb = NULL; - goto err_free_rt; + vport = ovs_vport_alloc(0, &ovs_gre_vport_ops, parms); + if (IS_ERR(vport)) + return vport; + + rtnl_lock(); + dev = gretap_fb_dev_create(net, parms->name, NET_NAME_USER); + if (IS_ERR(dev)) { + rtnl_unlock(); + ovs_vport_free(vport); + return ERR_CAST(dev); } - df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? - htons(IP_DF) : 0; - - skb->ignore_df = 1; - - return iptunnel_xmit(skb->sk, rt, skb, fl.saddr, - tun_key->ipv4_dst, IPPROTO_GRE, - tun_key->ipv4_tos, tun_key->ipv4_ttl, df, false); -err_free_rt: - ip_rt_put(rt); -err_free_skb: - kfree_skb(skb); - return err; -} - -static struct gre_cisco_protocol gre_protocol = { - .handler = gre_rcv, - .err_handler = gre_err, - .priority = 1, -}; - -static int gre_ports; -static int gre_init(void) -{ - int err; - - gre_ports++; - if (gre_ports > 1) - return 0; - - err = gre_cisco_register(&gre_protocol); - if (err) - pr_warn("cannot register gre protocol handler\n"); - - return err; -} - -static void gre_exit(void) -{ - gre_ports--; - if (gre_ports > 0) - return; - - gre_cisco_unregister(&gre_protocol); -} + dev_change_flags(dev, dev->flags | IFF_UP); + rtnl_unlock(); -static const char *gre_get_name(const struct vport *vport) -{ - return vport_priv(vport); + return vport; } static struct vport *gre_create(const struct vport_parms *parms) { - struct net *net = ovs_dp_get_net(parms->dp); - struct ovs_net *ovs_net; struct vport *vport; - int err; - - err = gre_init(); - if (err) - return ERR_PTR(err); - - ovs_net = net_generic(net, ovs_net_id); - if (ovsl_dereference(ovs_net->vport_net.gre_vport)) { - vport = ERR_PTR(-EEXIST); - goto error; - } - vport = ovs_vport_alloc(IFNAMSIZ, &ovs_gre_vport_ops, parms); + vport = gre_tnl_create(parms); if (IS_ERR(vport)) - goto error; - - strncpy(vport_priv(vport), parms->name, IFNAMSIZ); - rcu_assign_pointer(ovs_net->vport_net.gre_vport, vport); - return vport; - -error: - gre_exit(); - return vport; -} - -static void gre_tnl_destroy(struct vport *vport) -{ - struct net *net = ovs_dp_get_net(vport->dp); - struct ovs_net *ovs_net; - - ovs_net = net_generic(net, ovs_net_id); + return vport; - RCU_INIT_POINTER(ovs_net->vport_net.gre_vport, NULL); - ovs_vport_deferred_free(vport); - gre_exit(); + return ovs_netdev_link(vport, parms->name); } static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *egress_tun_info) + struct ip_tunnel_info *egress_tun_info) { return ovs_tunnel_get_egress_info(egress_tun_info, ovs_dp_get_net(vport->dp), @@ -288,10 +96,9 @@ static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, static struct vport_ops ovs_gre_vport_ops = { .type = OVS_VPORT_TYPE_GRE, .create = gre_create, - .destroy = gre_tnl_destroy, - .get_name = gre_get_name, - .send = gre_tnl_send, + .send = ovs_netdev_send, .get_egress_tun_info = gre_get_egress_tun_info, + .destroy = ovs_netdev_tunnel_destroy, .owner = THIS_MODULE, }; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 6a55f71..c058bbf 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -156,49 +156,44 @@ static void do_setup(struct net_device *netdev) static struct vport *internal_dev_create(const struct vport_parms *parms) { struct vport *vport; - struct netdev_vport *netdev_vport; struct internal_dev *internal_dev; int err; - vport = ovs_vport_alloc(sizeof(struct netdev_vport), - &ovs_internal_vport_ops, parms); + vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms); if (IS_ERR(vport)) { err = PTR_ERR(vport); goto error; } - netdev_vport = netdev_vport_priv(vport); - - netdev_vport->dev = alloc_netdev(sizeof(struct internal_dev), - parms->name, NET_NAME_UNKNOWN, - do_setup); - if (!netdev_vport->dev) { + vport->dev = alloc_netdev(sizeof(struct internal_dev), + parms->name, NET_NAME_UNKNOWN, do_setup); + if (!vport->dev) { err = -ENOMEM; goto error_free_vport; } - dev_net_set(netdev_vport->dev, ovs_dp_get_net(vport->dp)); - internal_dev = internal_dev_priv(netdev_vport->dev); + dev_net_set(vport->dev, ovs_dp_get_net(vport->dp)); + internal_dev = internal_dev_priv(vport->dev); internal_dev->vport = vport; /* Restrict bridge port to current netns. */ if (vport->port_no == OVSP_LOCAL) - netdev_vport->dev->features |= NETIF_F_NETNS_LOCAL; + vport->dev->features |= NETIF_F_NETNS_LOCAL; rtnl_lock(); - err = register_netdevice(netdev_vport->dev); + err = register_netdevice(vport->dev); if (err) goto error_free_netdev; - dev_set_promiscuity(netdev_vport->dev, 1); + dev_set_promiscuity(vport->dev, 1); rtnl_unlock(); - netif_start_queue(netdev_vport->dev); + netif_start_queue(vport->dev); return vport; error_free_netdev: rtnl_unlock(); - free_netdev(netdev_vport->dev); + free_netdev(vport->dev); error_free_vport: ovs_vport_free(vport); error: @@ -207,21 +202,19 @@ error: static void internal_dev_destroy(struct vport *vport) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - - netif_stop_queue(netdev_vport->dev); + netif_stop_queue(vport->dev); rtnl_lock(); - dev_set_promiscuity(netdev_vport->dev, -1); + dev_set_promiscuity(vport->dev, -1); /* unregister_netdevice() waits for an RCU grace period. */ - unregister_netdevice(netdev_vport->dev); + unregister_netdevice(vport->dev); rtnl_unlock(); } static int internal_dev_recv(struct vport *vport, struct sk_buff *skb) { - struct net_device *netdev = netdev_vport_priv(vport)->dev; + struct net_device *netdev = vport->dev; int len; if (unlikely(!(netdev->flags & IFF_UP))) { @@ -249,7 +242,6 @@ static struct vport_ops ovs_internal_vport_ops = { .type = OVS_VPORT_TYPE_INTERNAL, .create = internal_dev_create, .destroy = internal_dev_destroy, - .get_name = ovs_netdev_get_name, .send = internal_dev_recv, }; diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 33e6d6e..4b70aaa 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -26,10 +26,13 @@ #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/openvswitch.h> +#include <linux/export.h> -#include <net/llc.h> +#include <net/ip_tunnels.h> +#include <net/rtnetlink.h> #include "datapath.h" +#include "vport.h" #include "vport-internal_dev.h" #include "vport-netdev.h" @@ -54,7 +57,7 @@ static void netdev_port_receive(struct vport *vport, struct sk_buff *skb) skb_push(skb, ETH_HLEN); ovs_skb_postpush_rcsum(skb, skb->data, ETH_HLEN); - ovs_vport_receive(vport, skb, NULL); + ovs_vport_receive(vport, skb, skb_tunnel_info(skb, AF_INET)); return; error: @@ -83,105 +86,112 @@ static struct net_device *get_dpdev(const struct datapath *dp) local = ovs_vport_ovsl(dp, OVSP_LOCAL); BUG_ON(!local); - return netdev_vport_priv(local)->dev; + return local->dev; } -static struct vport *netdev_create(const struct vport_parms *parms) +struct vport *ovs_netdev_link(struct vport *vport, const char *name) { - struct vport *vport; - struct netdev_vport *netdev_vport; int err; - vport = ovs_vport_alloc(sizeof(struct netdev_vport), - &ovs_netdev_vport_ops, parms); - if (IS_ERR(vport)) { - err = PTR_ERR(vport); - goto error; - } - - netdev_vport = netdev_vport_priv(vport); - - netdev_vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), parms->name); - if (!netdev_vport->dev) { + vport->dev = dev_get_by_name(ovs_dp_get_net(vport->dp), name); + if (!vport->dev) { err = -ENODEV; goto error_free_vport; } - if (netdev_vport->dev->flags & IFF_LOOPBACK || - netdev_vport->dev->type != ARPHRD_ETHER || - ovs_is_internal_dev(netdev_vport->dev)) { + if (vport->dev->flags & IFF_LOOPBACK || + vport->dev->type != ARPHRD_ETHER || + ovs_is_internal_dev(vport->dev)) { err = -EINVAL; goto error_put; } rtnl_lock(); - err = netdev_master_upper_dev_link(netdev_vport->dev, + err = netdev_master_upper_dev_link(vport->dev, get_dpdev(vport->dp)); if (err) goto error_unlock; - err = netdev_rx_handler_register(netdev_vport->dev, netdev_frame_hook, + err = netdev_rx_handler_register(vport->dev, netdev_frame_hook, vport); if (err) goto error_master_upper_dev_unlink; - dev_disable_lro(netdev_vport->dev); - dev_set_promiscuity(netdev_vport->dev, 1); - netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH; + dev_disable_lro(vport->dev); + dev_set_promiscuity(vport->dev, 1); + vport->dev->priv_flags |= IFF_OVS_DATAPATH; rtnl_unlock(); return vport; error_master_upper_dev_unlink: - netdev_upper_dev_unlink(netdev_vport->dev, get_dpdev(vport->dp)); + netdev_upper_dev_unlink(vport->dev, get_dpdev(vport->dp)); error_unlock: rtnl_unlock(); error_put: - dev_put(netdev_vport->dev); + dev_put(vport->dev); error_free_vport: ovs_vport_free(vport); -error: return ERR_PTR(err); } +EXPORT_SYMBOL_GPL(ovs_netdev_link); -static void free_port_rcu(struct rcu_head *rcu) +static struct vport *netdev_create(const struct vport_parms *parms) { - struct netdev_vport *netdev_vport = container_of(rcu, - struct netdev_vport, rcu); + struct vport *vport; - dev_put(netdev_vport->dev); - ovs_vport_free(vport_from_priv(netdev_vport)); + vport = ovs_vport_alloc(0, &ovs_netdev_vport_ops, parms); + if (IS_ERR(vport)) + return vport; + + return ovs_netdev_link(vport, parms->name); } -void ovs_netdev_detach_dev(struct vport *vport) +static void vport_netdev_free(struct rcu_head *rcu) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); + struct vport *vport = container_of(rcu, struct vport, rcu); + if (vport->dev) + dev_put(vport->dev); + ovs_vport_free(vport); +} + +void ovs_netdev_detach_dev(struct vport *vport) +{ ASSERT_RTNL(); - netdev_vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; - netdev_rx_handler_unregister(netdev_vport->dev); - netdev_upper_dev_unlink(netdev_vport->dev, - netdev_master_upper_dev_get(netdev_vport->dev)); - dev_set_promiscuity(netdev_vport->dev, -1); + vport->dev->priv_flags &= ~IFF_OVS_DATAPATH; + netdev_rx_handler_unregister(vport->dev); + netdev_upper_dev_unlink(vport->dev, + netdev_master_upper_dev_get(vport->dev)); + dev_set_promiscuity(vport->dev, -1); } +EXPORT_SYMBOL_GPL(ovs_netdev_detach_dev); static void netdev_destroy(struct vport *vport) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - rtnl_lock(); - if (netdev_vport->dev->priv_flags & IFF_OVS_DATAPATH) + if (vport->dev->priv_flags & IFF_OVS_DATAPATH) ovs_netdev_detach_dev(vport); rtnl_unlock(); - call_rcu(&netdev_vport->rcu, free_port_rcu); + call_rcu(&vport->rcu, vport_netdev_free); } -const char *ovs_netdev_get_name(const struct vport *vport) +void ovs_netdev_tunnel_destroy(struct vport *vport) { - const struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - return netdev_vport->dev->name; + rtnl_lock(); + if (vport->dev->priv_flags & IFF_OVS_DATAPATH) + ovs_netdev_detach_dev(vport); + + /* Early release so we can unregister the device */ + dev_put(vport->dev); + rtnl_delete_link(vport->dev); + vport->dev = NULL; + rtnl_unlock(); + + call_rcu(&vport->rcu, vport_netdev_free); } +EXPORT_SYMBOL_GPL(ovs_netdev_tunnel_destroy); static unsigned int packet_length(const struct sk_buff *skb) { @@ -193,20 +203,19 @@ static unsigned int packet_length(const struct sk_buff *skb) return length; } -static int netdev_send(struct vport *vport, struct sk_buff *skb) +int ovs_netdev_send(struct vport *vport, struct sk_buff *skb) { - struct netdev_vport *netdev_vport = netdev_vport_priv(vport); - int mtu = netdev_vport->dev->mtu; + int mtu = vport->dev->mtu; int len; if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) { net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n", - netdev_vport->dev->name, + vport->dev->name, packet_length(skb), mtu); goto drop; } - skb->dev = netdev_vport->dev; + skb->dev = vport->dev; len = skb->len; dev_queue_xmit(skb); @@ -216,6 +225,7 @@ drop: kfree_skb(skb); return 0; } +EXPORT_SYMBOL_GPL(ovs_netdev_send); /* Returns null if this device is not attached to a datapath. */ struct vport *ovs_netdev_get_vport(struct net_device *dev) @@ -231,8 +241,7 @@ static struct vport_ops ovs_netdev_vport_ops = { .type = OVS_VPORT_TYPE_NETDEV, .create = netdev_create, .destroy = netdev_destroy, - .get_name = ovs_netdev_get_name, - .send = netdev_send, + .send = ovs_netdev_send, }; int __init ovs_netdev_init(void) diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h index 6f7038e..497cc81 100644 --- a/net/openvswitch/vport-netdev.h +++ b/net/openvswitch/vport-netdev.h @@ -26,22 +26,12 @@ struct vport *ovs_netdev_get_vport(struct net_device *dev); -struct netdev_vport { - struct rcu_head rcu; - - struct net_device *dev; -}; - -static inline struct netdev_vport * -netdev_vport_priv(const struct vport *vport) -{ - return vport_priv(vport); -} - -const char *ovs_netdev_get_name(const struct vport *); +struct vport *ovs_netdev_link(struct vport *vport, const char *name); +int ovs_netdev_send(struct vport *vport, struct sk_buff *skb); void ovs_netdev_detach_dev(struct vport *); int __init ovs_netdev_init(void); void ovs_netdev_exit(void); +void ovs_netdev_tunnel_destroy(struct vport *vport); #endif /* vport_netdev.h */ diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 6d39766..1e8b00a2 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -17,94 +17,37 @@ * 02110-1301, USA */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/net.h> -#include <linux/rculist.h> -#include <linux/udp.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> +#include <linux/openvswitch.h> #include <linux/module.h> - -#include <net/icmp.h> -#include <net/ip.h> #include <net/udp.h> #include <net/ip_tunnels.h> #include <net/rtnetlink.h> -#include <net/route.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <net/net_namespace.h> -#include <net/netns/generic.h> #include <net/vxlan.h> #include "datapath.h" #include "vport.h" -#include "vport-vxlan.h" - -/** - * struct vxlan_port - Keeps track of open UDP ports - * @vs: vxlan_sock created for the port. - * @name: vport name. - */ -struct vxlan_port { - struct vxlan_sock *vs; - char name[IFNAMSIZ]; - u32 exts; /* VXLAN_F_* in <net/vxlan.h> */ -}; - -static struct vport_ops ovs_vxlan_vport_ops; +#include "vport-netdev.h" -static inline struct vxlan_port *vxlan_vport(const struct vport *vport) -{ - return vport_priv(vport); -} - -/* Called with rcu_read_lock and BH disabled. */ -static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, - struct vxlan_metadata *md) -{ - struct ovs_tunnel_info tun_info; - struct vxlan_port *vxlan_port; - struct vport *vport = vs->data; - struct iphdr *iph; - struct ovs_vxlan_opts opts = { - .gbp = md->gbp, - }; - __be64 key; - __be16 flags; - - flags = TUNNEL_KEY | (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0); - vxlan_port = vxlan_vport(vport); - if (vxlan_port->exts & VXLAN_F_GBP && md->gbp) - flags |= TUNNEL_VXLAN_OPT; - - /* Save outer tunnel values */ - iph = ip_hdr(skb); - key = cpu_to_be64(ntohl(md->vni) >> 8); - ovs_flow_tun_info_init(&tun_info, iph, - udp_hdr(skb)->source, udp_hdr(skb)->dest, - key, flags, &opts, sizeof(opts)); - - ovs_vport_receive(vport, skb, &tun_info); -} +static struct vport_ops ovs_vxlan_netdev_vport_ops; static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) { - struct vxlan_port *vxlan_port = vxlan_vport(vport); - __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport; + struct vxlan_dev *vxlan = netdev_priv(vport->dev); + __be16 dst_port = vxlan->cfg.dst_port; if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port))) return -EMSGSIZE; - if (vxlan_port->exts) { + if (vxlan->flags & VXLAN_F_GBP) { struct nlattr *exts; exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION); if (!exts) return -EMSGSIZE; - if (vxlan_port->exts & VXLAN_F_GBP && + if (vxlan->flags & VXLAN_F_GBP && nla_put_flag(skb, OVS_VXLAN_EXT_GBP)) return -EMSGSIZE; @@ -114,23 +57,14 @@ static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) return 0; } -static void vxlan_tnl_destroy(struct vport *vport) -{ - struct vxlan_port *vxlan_port = vxlan_vport(vport); - - vxlan_sock_release(vxlan_port->vs); - - ovs_vport_deferred_free(vport); -} - -static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX+1] = { +static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX + 1] = { [OVS_VXLAN_EXT_GBP] = { .type = NLA_FLAG, }, }; -static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr) +static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr, + struct vxlan_config *conf) { - struct nlattr *exts[OVS_VXLAN_EXT_MAX+1]; - struct vxlan_port *vxlan_port; + struct nlattr *exts[OVS_VXLAN_EXT_MAX + 1]; int err; if (nla_len(attr) < sizeof(struct nlattr)) @@ -140,10 +74,8 @@ static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr) if (err < 0) return err; - vxlan_port = vxlan_vport(vport); - if (exts[OVS_VXLAN_EXT_GBP]) - vxlan_port->exts |= VXLAN_F_GBP; + conf->flags |= VXLAN_F_GBP; return 0; } @@ -152,128 +84,74 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) { struct net *net = ovs_dp_get_net(parms->dp); struct nlattr *options = parms->options; - struct vxlan_port *vxlan_port; - struct vxlan_sock *vs; + struct net_device *dev; struct vport *vport; struct nlattr *a; - u16 dst_port; int err; + struct vxlan_config conf = { + .no_share = true, + .flags = VXLAN_F_COLLECT_METADATA, + }; if (!options) { err = -EINVAL; goto error; } + a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT); if (a && nla_len(a) == sizeof(u16)) { - dst_port = nla_get_u16(a); + conf.dst_port = htons(nla_get_u16(a)); } else { /* Require destination port from userspace. */ err = -EINVAL; goto error; } - vport = ovs_vport_alloc(sizeof(struct vxlan_port), - &ovs_vxlan_vport_ops, parms); + vport = ovs_vport_alloc(0, &ovs_vxlan_netdev_vport_ops, parms); if (IS_ERR(vport)) return vport; - vxlan_port = vxlan_vport(vport); - strncpy(vxlan_port->name, parms->name, IFNAMSIZ); - a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION); if (a) { - err = vxlan_configure_exts(vport, a); + err = vxlan_configure_exts(vport, a, &conf); if (err) { ovs_vport_free(vport); goto error; } } - vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, - vxlan_port->exts); - if (IS_ERR(vs)) { + rtnl_lock(); + dev = vxlan_dev_create(net, parms->name, NET_NAME_USER, &conf); + if (IS_ERR(dev)) { + rtnl_unlock(); ovs_vport_free(vport); - return (void *)vs; + return ERR_CAST(dev); } - vxlan_port->vs = vs; + dev_change_flags(dev, dev->flags | IFF_UP); + rtnl_unlock(); return vport; - error: return ERR_PTR(err); } -static int vxlan_ext_gbp(struct sk_buff *skb) +static struct vport *vxlan_create(const struct vport_parms *parms) { - const struct ovs_tunnel_info *tun_info; - const struct ovs_vxlan_opts *opts; - - tun_info = OVS_CB(skb)->egress_tun_info; - opts = tun_info->options; - - if (tun_info->tunnel.tun_flags & TUNNEL_VXLAN_OPT && - tun_info->options_len >= sizeof(*opts)) - return opts->gbp; - else - return 0; -} - -static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) -{ - struct net *net = ovs_dp_get_net(vport->dp); - struct vxlan_port *vxlan_port = vxlan_vport(vport); - struct sock *sk = vxlan_port->vs->sock->sk; - __be16 dst_port = inet_sk(sk)->inet_sport; - const struct ovs_key_ipv4_tunnel *tun_key; - struct vxlan_metadata md = {0}; - struct rtable *rt; - struct flowi4 fl; - __be16 src_port; - __be16 df; - int err; - u32 vxflags; - - if (unlikely(!OVS_CB(skb)->egress_tun_info)) { - err = -EINVAL; - goto error; - } - - tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - goto error; - } - - df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? - htons(IP_DF) : 0; + struct vport *vport; - skb->ignore_df = 1; + vport = vxlan_tnl_create(parms); + if (IS_ERR(vport)) + return vport; - src_port = udp_flow_src_port(net, skb, 0, 0, true); - md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8); - md.gbp = vxlan_ext_gbp(skb); - vxflags = vxlan_port->exts | - (tun_key->tun_flags & TUNNEL_CSUM ? VXLAN_F_UDP_CSUM : 0); - - err = vxlan_xmit_skb(rt, sk, skb, fl.saddr, tun_key->ipv4_dst, - tun_key->ipv4_tos, tun_key->ipv4_ttl, df, - src_port, dst_port, - &md, false, vxflags); - if (err < 0) - ip_rt_put(rt); - return err; -error: - kfree_skb(skb); - return err; + return ovs_netdev_link(vport, parms->name); } static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *egress_tun_info) + struct ip_tunnel_info *egress_tun_info) { + struct vxlan_dev *vxlan = netdev_priv(vport->dev); struct net *net = ovs_dp_get_net(vport->dp); - struct vxlan_port *vxlan_port = vxlan_vport(vport); - __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport; + __be16 dst_port = vxlan_dev_dst_port(vxlan); __be16 src_port; int port_min; int port_max; @@ -287,31 +165,23 @@ static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, src_port, dst_port); } -static const char *vxlan_get_name(const struct vport *vport) -{ - struct vxlan_port *vxlan_port = vxlan_vport(vport); - return vxlan_port->name; -} - -static struct vport_ops ovs_vxlan_vport_ops = { - .type = OVS_VPORT_TYPE_VXLAN, - .create = vxlan_tnl_create, - .destroy = vxlan_tnl_destroy, - .get_name = vxlan_get_name, - .get_options = vxlan_get_options, - .send = vxlan_tnl_send, +static struct vport_ops ovs_vxlan_netdev_vport_ops = { + .type = OVS_VPORT_TYPE_VXLAN, + .create = vxlan_create, + .destroy = ovs_netdev_tunnel_destroy, + .get_options = vxlan_get_options, + .send = ovs_netdev_send, .get_egress_tun_info = vxlan_get_egress_tun_info, - .owner = THIS_MODULE, }; static int __init ovs_vxlan_tnl_init(void) { - return ovs_vport_ops_register(&ovs_vxlan_vport_ops); + return ovs_vport_ops_register(&ovs_vxlan_netdev_vport_ops); } static void __exit ovs_vxlan_tnl_exit(void) { - ovs_vport_ops_unregister(&ovs_vxlan_vport_ops); + ovs_vport_ops_unregister(&ovs_vxlan_netdev_vport_ops); } module_init(ovs_vxlan_tnl_init); diff --git a/net/openvswitch/vport-vxlan.h b/net/openvswitch/vport-vxlan.h deleted file mode 100644 index 4b08233e..0000000 --- a/net/openvswitch/vport-vxlan.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef VPORT_VXLAN_H -#define VPORT_VXLAN_H 1 - -#include <linux/kernel.h> -#include <linux/types.h> - -struct ovs_vxlan_opts { - __u32 gbp; -}; - -#endif diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 067a3ff..d14f594 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -113,7 +113,7 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) struct vport *vport; hlist_for_each_entry_rcu(vport, bucket, hash_node) - if (!strcmp(name, vport->ops->get_name(vport)) && + if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; @@ -226,7 +226,7 @@ struct vport *ovs_vport_add(const struct vport_parms *parms) } bucket = hash_bucket(ovs_dp_get_net(vport->dp), - vport->ops->get_name(vport)); + ovs_vport_name(vport)); hlist_add_head_rcu(&vport->hash_node, bucket); return vport; } @@ -469,7 +469,7 @@ u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb) * skb->data should point to the Ethernet header. */ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb, - const struct ovs_tunnel_info *tun_info) + const struct ip_tunnel_info *tun_info) { struct pcpu_sw_netstats *stats; struct sw_flow_key key; @@ -572,22 +572,22 @@ void ovs_vport_deferred_free(struct vport *vport) } EXPORT_SYMBOL_GPL(ovs_vport_deferred_free); -int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, +int ovs_tunnel_get_egress_info(struct ip_tunnel_info *egress_tun_info, struct net *net, - const struct ovs_tunnel_info *tun_info, + const struct ip_tunnel_info *tun_info, u8 ipproto, u32 skb_mark, __be16 tp_src, __be16 tp_dst) { - const struct ovs_key_ipv4_tunnel *tun_key; + const struct ip_tunnel_key *tun_key; struct rtable *rt; struct flowi4 fl; if (unlikely(!tun_info)) return -EINVAL; - tun_key = &tun_info->tunnel; + tun_key = &tun_info->key; /* Route lookup to get srouce IP address. * The process may need to be changed if the corresponding process @@ -602,22 +602,22 @@ int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, /* Generate egress_tun_info based on tun_info, * saddr, tp_src and tp_dst */ - __ovs_flow_tun_info_init(egress_tun_info, - fl.saddr, tun_key->ipv4_dst, - tun_key->ipv4_tos, - tun_key->ipv4_ttl, - tp_src, tp_dst, - tun_key->tun_id, - tun_key->tun_flags, - tun_info->options, - tun_info->options_len); + __ip_tunnel_info_init(egress_tun_info, + fl.saddr, tun_key->ipv4_dst, + tun_key->ipv4_tos, + tun_key->ipv4_ttl, + tp_src, tp_dst, + tun_key->tun_id, + tun_key->tun_flags, + tun_info->options, + tun_info->options_len); return 0; } EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info); int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *info) + struct ip_tunnel_info *info) { /* get_egress_tun_info() is only implemented on tunnel ports. */ if (unlikely(!vport->ops->get_egress_tun_info)) diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index bc85331..1a689c2 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -27,6 +27,7 @@ #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/u64_stats_sync.h> +#include <net/route.h> #include "datapath.h" @@ -58,15 +59,15 @@ u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *); int ovs_vport_send(struct vport *, struct sk_buff *); -int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, +int ovs_tunnel_get_egress_info(struct ip_tunnel_info *egress_tun_info, struct net *net, - const struct ovs_tunnel_info *tun_info, + const struct ip_tunnel_info *tun_info, u8 ipproto, u32 skb_mark, __be16 tp_src, __be16 tp_dst); int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct ovs_tunnel_info *info); + struct ip_tunnel_info *info); /* The following definitions are for implementers of vport devices: */ @@ -106,7 +107,7 @@ struct vport_portids { * @detach_list: list used for detaching vport in net-exit call. */ struct vport { - struct rcu_head rcu; + struct net_device *dev; struct datapath *dp; struct vport_portids __rcu *upcall_portids; u16 port_no; @@ -119,6 +120,7 @@ struct vport { struct vport_err_stats err_stats; struct list_head detach_list; + struct rcu_head rcu; }; /** @@ -176,7 +178,7 @@ struct vport_ops { int (*send)(struct vport *, struct sk_buff *); int (*get_egress_tun_info)(struct vport *, struct sk_buff *, - struct ovs_tunnel_info *); + struct ip_tunnel_info *); struct module *owner; struct list_head list; @@ -226,7 +228,7 @@ static inline struct vport *vport_from_priv(void *priv) } void ovs_vport_receive(struct vport *, struct sk_buff *, - const struct ovs_tunnel_info *); + const struct ip_tunnel_info *); static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) @@ -235,11 +237,16 @@ static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb, skb->csum = csum_add(skb->csum, csum_partial(start, len, 0)); } +static inline const char *ovs_vport_name(struct vport *vport) +{ + return vport->dev ? vport->dev->name : vport->ops->get_name(vport); +} + int ovs_vport_ops_register(struct vport_ops *ops); void ovs_vport_ops_unregister(struct vport_ops *ops); static inline struct rtable *ovs_tunnel_route_lookup(struct net *net, - const struct ovs_key_ipv4_tunnel *key, + const struct ip_tunnel_key *key, u32 mark, struct flowi4 *fl, u8 protocol) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ed458b3..b5afe53 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -518,13 +518,11 @@ static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) } static void prb_shutdown_retire_blk_timer(struct packet_sock *po, - int tx_ring, struct sk_buff_head *rb_queue) { struct tpacket_kbdq_core *pkc; - pkc = tx_ring ? GET_PBDQC_FROM_RB(&po->tx_ring) : - GET_PBDQC_FROM_RB(&po->rx_ring); + pkc = GET_PBDQC_FROM_RB(&po->rx_ring); spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; @@ -4043,7 +4041,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (closing && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) - prb_shutdown_retire_blk_timer(po, tx_ring, rb_queue); + prb_shutdown_retire_blk_timer(po, rb_queue); } release_sock(sk); diff --git a/net/rds/bind.c b/net/rds/bind.c index 4ebd29c..dd666fb 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -185,7 +185,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) ret = 0; goto out; } - trans = rds_trans_get_preferred(sin->sin_addr.s_addr); + trans = rds_trans_get_preferred(sock_net(sock->sk), + sin->sin_addr.s_addr); if (!trans) { ret = -EADDRNOTAVAIL; rds_remove_bound(rs); diff --git a/net/rds/connection.c b/net/rds/connection.c index da6da57..d4fecb2 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -117,7 +117,8 @@ static void rds_conn_reset(struct rds_connection *conn) * For now they are not garbage collected once they're created. They * are torn down as the module is removed, if ever. */ -static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr, +static struct rds_connection *__rds_conn_create(struct net *net, + __be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp, int is_outgoing) { @@ -157,6 +158,7 @@ new_conn: conn->c_faddr = faddr; spin_lock_init(&conn->c_lock); conn->c_next_tx_seq = 1; + rds_conn_net_set(conn, net); init_waitqueue_head(&conn->c_waitq); INIT_LIST_HEAD(&conn->c_send_queue); @@ -174,7 +176,7 @@ new_conn: * can bind to the destination address then we'd rather the messages * flow through loopback rather than either transport. */ - loop_trans = rds_trans_get_preferred(faddr); + loop_trans = rds_trans_get_preferred(net, faddr); if (loop_trans) { rds_trans_put(loop_trans); conn->c_loopback = 1; @@ -260,17 +262,19 @@ out: return conn; } -struct rds_connection *rds_conn_create(__be32 laddr, __be32 faddr, +struct rds_connection *rds_conn_create(struct net *net, + __be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp) { - return __rds_conn_create(laddr, faddr, trans, gfp, 0); + return __rds_conn_create(net, laddr, faddr, trans, gfp, 0); } EXPORT_SYMBOL_GPL(rds_conn_create); -struct rds_connection *rds_conn_create_outgoing(__be32 laddr, __be32 faddr, +struct rds_connection *rds_conn_create_outgoing(struct net *net, + __be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp) { - return __rds_conn_create(laddr, faddr, trans, gfp, 1); + return __rds_conn_create(net, laddr, faddr, trans, gfp, 1); } EXPORT_SYMBOL_GPL(rds_conn_create_outgoing); diff --git a/net/rds/ib.c b/net/rds/ib.c index ba2dffe..1381422 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -317,7 +317,7 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len, * allowed to influence which paths have priority. We could call userspace * asserting this policy "routing". */ -static int rds_ib_laddr_check(__be32 addr) +static int rds_ib_laddr_check(struct net *net, __be32 addr) { int ret; struct rdma_cm_id *cm_id; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 0da2a45..f40d8f5 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -448,8 +448,9 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, (unsigned long long)be64_to_cpu(lguid), (unsigned long long)be64_to_cpu(fguid)); - conn = rds_conn_create(dp->dp_daddr, dp->dp_saddr, &rds_ib_transport, - GFP_KERNEL); + /* RDS/IB is not currently netns aware, thus init_net */ + conn = rds_conn_create(&init_net, dp->dp_daddr, dp->dp_saddr, + &rds_ib_transport, GFP_KERNEL); if (IS_ERR(conn)) { rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn)); conn = NULL; diff --git a/net/rds/iw.c b/net/rds/iw.c index 5899356..5d5a9d2 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -218,7 +218,7 @@ static void rds_iw_ic_info(struct socket *sock, unsigned int len, * allowed to influence which paths have priority. We could call userspace * asserting this policy "routing". */ -static int rds_iw_laddr_check(__be32 addr) +static int rds_iw_laddr_check(struct net *net, __be32 addr) { int ret; struct rdma_cm_id *cm_id; diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c index 8f486fa..a6553a6 100644 --- a/net/rds/iw_cm.c +++ b/net/rds/iw_cm.c @@ -398,8 +398,9 @@ int rds_iw_cm_handle_connect(struct rdma_cm_id *cm_id, &dp->dp_saddr, &dp->dp_daddr, RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version)); - conn = rds_conn_create(dp->dp_daddr, dp->dp_saddr, &rds_iw_transport, - GFP_KERNEL); + /* RDS/IW is not currently netns aware, thus init_net */ + conn = rds_conn_create(&init_net, dp->dp_daddr, dp->dp_saddr, + &rds_iw_transport, GFP_KERNEL); if (IS_ERR(conn)) { rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn)); conn = NULL; diff --git a/net/rds/rds.h b/net/rds/rds.h index 2260c1e4..9005fb0 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -128,8 +128,21 @@ struct rds_connection { /* Protocol version */ unsigned int c_version; + possible_net_t c_net; }; +static inline +struct net *rds_conn_net(struct rds_connection *conn) +{ + return read_pnet(&conn->c_net); +} + +static inline +void rds_conn_net_set(struct rds_connection *conn, struct net *net) +{ + write_pnet(&conn->c_net, net); +} + #define RDS_FLAG_CONG_BITMAP 0x01 #define RDS_FLAG_ACK_REQUIRED 0x02 #define RDS_FLAG_RETRANSMITTED 0x04 @@ -417,7 +430,7 @@ struct rds_transport { unsigned int t_prefer_loopback:1; unsigned int t_type; - int (*laddr_check)(__be32 addr); + int (*laddr_check)(struct net *net, __be32 addr); int (*conn_alloc)(struct rds_connection *conn, gfp_t gfp); void (*conn_free)(void *data); int (*conn_connect)(struct rds_connection *conn); @@ -608,9 +621,11 @@ struct rds_message *rds_cong_update_alloc(struct rds_connection *conn); /* conn.c */ int rds_conn_init(void); void rds_conn_exit(void); -struct rds_connection *rds_conn_create(__be32 laddr, __be32 faddr, +struct rds_connection *rds_conn_create(struct net *net, + __be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp); -struct rds_connection *rds_conn_create_outgoing(__be32 laddr, __be32 faddr, +struct rds_connection *rds_conn_create_outgoing(struct net *net, + __be32 laddr, __be32 faddr, struct rds_transport *trans, gfp_t gfp); void rds_conn_shutdown(struct rds_connection *conn); void rds_conn_destroy(struct rds_connection *conn); @@ -795,7 +810,7 @@ void rds_connect_complete(struct rds_connection *conn); /* transport.c */ int rds_trans_register(struct rds_transport *trans); void rds_trans_unregister(struct rds_transport *trans); -struct rds_transport *rds_trans_get_preferred(__be32 addr); +struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr); void rds_trans_put(struct rds_transport *trans); unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter, unsigned int avail); diff --git a/net/rds/send.c b/net/rds/send.c index e9430f5..2581b8e 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1023,7 +1023,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) if (rs->rs_conn && rs->rs_conn->c_faddr == daddr) conn = rs->rs_conn; else { - conn = rds_conn_create_outgoing(rs->rs_bound_addr, daddr, + conn = rds_conn_create_outgoing(sock_net(sock->sk), + rs->rs_bound_addr, daddr, rs->rs_transport, sock->sk->sk_allocation); if (IS_ERR(conn)) { diff --git a/net/rds/tcp.c b/net/rds/tcp.c index edac9ef..c42b60b 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -35,6 +35,9 @@ #include <linux/in.h> #include <linux/module.h> #include <net/tcp.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <net/tcp.h> #include "rds.h" #include "tcp.h" @@ -189,9 +192,9 @@ out: spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags); } -static int rds_tcp_laddr_check(__be32 addr) +static int rds_tcp_laddr_check(struct net *net, __be32 addr) { - if (inet_addr_type(&init_net, addr) == RTN_LOCAL) + if (inet_addr_type(net, addr) == RTN_LOCAL) return 0; return -EADDRNOTAVAIL; } @@ -250,16 +253,7 @@ static void rds_tcp_destroy_conns(void) } } -static void rds_tcp_exit(void) -{ - rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); - rds_tcp_listen_stop(); - rds_tcp_destroy_conns(); - rds_trans_unregister(&rds_tcp_transport); - rds_tcp_recv_exit(); - kmem_cache_destroy(rds_tcp_conn_slab); -} -module_exit(rds_tcp_exit); +static void rds_tcp_exit(void); struct rds_transport rds_tcp_transport = { .laddr_check = rds_tcp_laddr_check, @@ -281,6 +275,136 @@ struct rds_transport rds_tcp_transport = { .t_prefer_loopback = 1, }; +static int rds_tcp_netid; + +/* per-network namespace private data for this module */ +struct rds_tcp_net { + struct socket *rds_tcp_listen_sock; + struct work_struct rds_tcp_accept_w; +}; + +static void rds_tcp_accept_worker(struct work_struct *work) +{ + struct rds_tcp_net *rtn = container_of(work, + struct rds_tcp_net, + rds_tcp_accept_w); + + while (rds_tcp_accept_one(rtn->rds_tcp_listen_sock) == 0) + cond_resched(); +} + +void rds_tcp_accept_work(struct sock *sk) +{ + struct net *net = sock_net(sk); + struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + + queue_work(rds_wq, &rtn->rds_tcp_accept_w); +} + +static __net_init int rds_tcp_init_net(struct net *net) +{ + struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + + rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net); + if (!rtn->rds_tcp_listen_sock) { + pr_warn("could not set up listen sock\n"); + return -EAFNOSUPPORT; + } + INIT_WORK(&rtn->rds_tcp_accept_w, rds_tcp_accept_worker); + return 0; +} + +static void __net_exit rds_tcp_exit_net(struct net *net) +{ + struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + + /* If rds_tcp_exit_net() is called as a result of netns deletion, + * the rds_tcp_kill_sock() device notifier would already have cleaned + * up the listen socket, thus there is no work to do in this function. + * + * If rds_tcp_exit_net() is called as a result of module unload, + * i.e., due to rds_tcp_exit() -> unregister_pernet_subsys(), then + * we do need to clean up the listen socket here. + */ + if (rtn->rds_tcp_listen_sock) { + rds_tcp_listen_stop(rtn->rds_tcp_listen_sock); + rtn->rds_tcp_listen_sock = NULL; + flush_work(&rtn->rds_tcp_accept_w); + } +} + +static struct pernet_operations rds_tcp_net_ops = { + .init = rds_tcp_init_net, + .exit = rds_tcp_exit_net, + .id = &rds_tcp_netid, + .size = sizeof(struct rds_tcp_net), +}; + +static void rds_tcp_kill_sock(struct net *net) +{ + struct rds_tcp_connection *tc, *_tc; + struct sock *sk; + LIST_HEAD(tmp_list); + struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid); + + rds_tcp_listen_stop(rtn->rds_tcp_listen_sock); + rtn->rds_tcp_listen_sock = NULL; + flush_work(&rtn->rds_tcp_accept_w); + spin_lock_irq(&rds_tcp_conn_lock); + list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) { + struct net *c_net = read_pnet(&tc->conn->c_net); + + if (net != c_net || !tc->t_sock) + continue; + list_move_tail(&tc->t_tcp_node, &tmp_list); + } + spin_unlock_irq(&rds_tcp_conn_lock); + list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) { + sk = tc->t_sock->sk; + sk->sk_prot->disconnect(sk, 0); + tcp_done(sk); + if (tc->conn->c_passive) + rds_conn_destroy(tc->conn->c_passive); + rds_conn_destroy(tc->conn); + } +} + +static int rds_tcp_dev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + /* rds-tcp registers as a pernet subys, so the ->exit will only + * get invoked after network acitivity has quiesced. We need to + * clean up all sockets to quiesce network activity, and use + * the unregistration of the per-net loopback device as a trigger + * to start that cleanup. + */ + if (event == NETDEV_UNREGISTER_FINAL && + dev->ifindex == LOOPBACK_IFINDEX) + rds_tcp_kill_sock(dev_net(dev)); + + return NOTIFY_DONE; +} + +static struct notifier_block rds_tcp_dev_notifier = { + .notifier_call = rds_tcp_dev_event, + .priority = -10, /* must be called after other network notifiers */ +}; + +static void rds_tcp_exit(void) +{ + rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); + unregister_pernet_subsys(&rds_tcp_net_ops); + if (unregister_netdevice_notifier(&rds_tcp_dev_notifier)) + pr_warn("could not unregister rds_tcp_dev_notifier\n"); + rds_tcp_destroy_conns(); + rds_trans_unregister(&rds_tcp_transport); + rds_tcp_recv_exit(); + kmem_cache_destroy(rds_tcp_conn_slab); +} +module_exit(rds_tcp_exit); + static int rds_tcp_init(void) { int ret; @@ -293,6 +417,16 @@ static int rds_tcp_init(void) goto out; } + ret = register_netdevice_notifier(&rds_tcp_dev_notifier); + if (ret) { + pr_warn("could not register rds_tcp_dev_notifier\n"); + goto out; + } + + ret = register_pernet_subsys(&rds_tcp_net_ops); + if (ret) + goto out_slab; + ret = rds_tcp_recv_init(); if (ret) goto out_slab; @@ -301,19 +435,14 @@ static int rds_tcp_init(void) if (ret) goto out_recv; - ret = rds_tcp_listen_init(); - if (ret) - goto out_register; - rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info); goto out; -out_register: - rds_trans_unregister(&rds_tcp_transport); out_recv: rds_tcp_recv_exit(); out_slab: + unregister_pernet_subsys(&rds_tcp_net_ops); kmem_cache_destroy(rds_tcp_conn_slab); out: return ret; diff --git a/net/rds/tcp.h b/net/rds/tcp.h index 0dbdd37..64f873c 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -52,6 +52,7 @@ u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc); u32 rds_tcp_snd_una(struct rds_tcp_connection *tc); u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq); extern struct rds_transport rds_tcp_transport; +void rds_tcp_accept_work(struct sock *sk); /* tcp_connect.c */ int rds_tcp_conn_connect(struct rds_connection *conn); @@ -59,9 +60,11 @@ void rds_tcp_conn_shutdown(struct rds_connection *conn); void rds_tcp_state_change(struct sock *sk); /* tcp_listen.c */ -int rds_tcp_listen_init(void); -void rds_tcp_listen_stop(void); +struct socket *rds_tcp_listen_init(struct net *); +void rds_tcp_listen_stop(struct socket *); void rds_tcp_listen_data_ready(struct sock *sk); +int rds_tcp_accept_one(struct socket *sock); +int rds_tcp_keepalive(struct socket *sock); /* tcp_recv.c */ int rds_tcp_recv_init(void); diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index 973109c7..5cb1687 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -79,7 +79,8 @@ int rds_tcp_conn_connect(struct rds_connection *conn) struct sockaddr_in src, dest; int ret; - ret = sock_create(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); + ret = sock_create_kern(rds_conn_net(conn), PF_INET, + SOCK_STREAM, IPPROTO_TCP, &sock); if (ret < 0) goto out; @@ -111,10 +112,12 @@ int rds_tcp_conn_connect(struct rds_connection *conn) rdsdebug("connect to address %pI4 returned %d\n", &conn->c_faddr, ret); if (ret == -EINPROGRESS) ret = 0; - if (ret == 0) + if (ret == 0) { + rds_tcp_keepalive(sock); sock = NULL; - else + } else { rds_tcp_restore_callbacks(sock, conn->c_transport_data); + } out: if (sock) diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 0da49e3..444d78d 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -38,14 +38,7 @@ #include "rds.h" #include "tcp.h" -/* - * cheesy, but simple.. - */ -static void rds_tcp_accept_worker(struct work_struct *work); -static DECLARE_WORK(rds_tcp_listen_work, rds_tcp_accept_worker); -static struct socket *rds_tcp_listen_sock; - -static int rds_tcp_keepalive(struct socket *sock) +int rds_tcp_keepalive(struct socket *sock) { /* values below based on xs_udp_default_timeout */ int keepidle = 5; /* send a probe 'keepidle' secs after last data */ @@ -77,7 +70,7 @@ bail: return ret; } -static int rds_tcp_accept_one(struct socket *sock) +int rds_tcp_accept_one(struct socket *sock) { struct socket *new_sock = NULL; struct rds_connection *conn; @@ -85,8 +78,9 @@ static int rds_tcp_accept_one(struct socket *sock) struct inet_sock *inet; struct rds_tcp_connection *rs_tcp; - ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type, - sock->sk->sk_protocol, &new_sock); + ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family, + sock->sk->sk_type, sock->sk->sk_protocol, + &new_sock); if (ret) goto out; @@ -108,7 +102,8 @@ static int rds_tcp_accept_one(struct socket *sock) &inet->inet_saddr, ntohs(inet->inet_sport), &inet->inet_daddr, ntohs(inet->inet_dport)); - conn = rds_conn_create(inet->inet_saddr, inet->inet_daddr, + conn = rds_conn_create(sock_net(sock->sk), + inet->inet_saddr, inet->inet_daddr, &rds_tcp_transport, GFP_KERNEL); if (IS_ERR(conn)) { ret = PTR_ERR(conn); @@ -148,12 +143,6 @@ out: return ret; } -static void rds_tcp_accept_worker(struct work_struct *work) -{ - while (rds_tcp_accept_one(rds_tcp_listen_sock) == 0) - cond_resched(); -} - void rds_tcp_listen_data_ready(struct sock *sk) { void (*ready)(struct sock *sk); @@ -174,20 +163,20 @@ void rds_tcp_listen_data_ready(struct sock *sk) * socket */ if (sk->sk_state == TCP_LISTEN) - queue_work(rds_wq, &rds_tcp_listen_work); + rds_tcp_accept_work(sk); out: read_unlock(&sk->sk_callback_lock); ready(sk); } -int rds_tcp_listen_init(void) +struct socket *rds_tcp_listen_init(struct net *net) { struct sockaddr_in sin; struct socket *sock = NULL; int ret; - ret = sock_create(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); + ret = sock_create_kern(net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); if (ret < 0) goto out; @@ -211,17 +200,15 @@ int rds_tcp_listen_init(void) if (ret < 0) goto out; - rds_tcp_listen_sock = sock; - sock = NULL; + return sock; out: if (sock) sock_release(sock); - return ret; + return NULL; } -void rds_tcp_listen_stop(void) +void rds_tcp_listen_stop(struct socket *sock) { - struct socket *sock = rds_tcp_listen_sock; struct sock *sk; if (!sock) @@ -242,5 +229,4 @@ void rds_tcp_listen_stop(void) /* wait for accepts to stop and close the socket */ flush_workqueue(rds_wq); sock_release(sock); - rds_tcp_listen_sock = NULL; } diff --git a/net/rds/transport.c b/net/rds/transport.c index 83498e1..f3afd1d 100644 --- a/net/rds/transport.c +++ b/net/rds/transport.c @@ -77,7 +77,7 @@ void rds_trans_put(struct rds_transport *trans) module_put(trans->t_owner); } -struct rds_transport *rds_trans_get_preferred(__be32 addr) +struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr) { struct rds_transport *ret = NULL; struct rds_transport *trans; @@ -90,7 +90,7 @@ struct rds_transport *rds_trans_get_preferred(__be32 addr) for (i = 0; i < RDS_TRANS_COUNT; i++) { trans = transports[i]; - if (trans && (trans->laddr_check(addr) == 0) && + if (trans && (trans->laddr_check(net, addr) == 0) && (!trans->t_owner || try_module_get(trans->t_owner))) { ret = trans; break; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 43ec926..b087087 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -27,6 +27,15 @@ #include <net/act_api.h> #include <net/netlink.h> +static void free_tcf(struct rcu_head *head) +{ + struct tcf_common *p = container_of(head, struct tcf_common, tcfc_rcu); + + free_percpu(p->cpu_bstats); + free_percpu(p->cpu_qstats); + kfree(p); +} + void tcf_hash_destroy(struct tc_action *a) { struct tcf_common *p = a->priv; @@ -41,7 +50,7 @@ void tcf_hash_destroy(struct tc_action *a) * gen_estimator est_timer() might access p->tcfc_lock * or bstats, wait a RCU grace period before freeing p */ - kfree_rcu(p, tcfc_rcu); + call_rcu(&p->tcfc_rcu, free_tcf); } EXPORT_SYMBOL(tcf_hash_destroy); @@ -231,15 +240,16 @@ void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est) if (est) gen_kill_estimator(&pc->tcfc_bstats, &pc->tcfc_rate_est); - kfree_rcu(pc, tcfc_rcu); + call_rcu(&pc->tcfc_rcu, free_tcf); } EXPORT_SYMBOL(tcf_hash_cleanup); int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, - int size, int bind) + int size, int bind, bool cpustats) { struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = kzalloc(size, GFP_KERNEL); + int err = -ENOMEM; if (unlikely(!p)) return -ENOMEM; @@ -247,18 +257,32 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, if (bind) p->tcfc_bindcnt = 1; + if (cpustats) { + p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); + if (!p->cpu_bstats) { +err1: + kfree(p); + return err; + } + p->cpu_qstats = alloc_percpu(struct gnet_stats_queue); + if (!p->cpu_qstats) { +err2: + free_percpu(p->cpu_bstats); + goto err1; + } + } spin_lock_init(&p->tcfc_lock); INIT_HLIST_NODE(&p->tcfc_head); p->tcfc_index = index ? index : tcf_hash_new_index(hinfo); p->tcfc_tm.install = jiffies; p->tcfc_tm.lastuse = jiffies; if (est) { - int err = gen_new_estimator(&p->tcfc_bstats, NULL, - &p->tcfc_rate_est, - &p->tcfc_lock, est); + err = gen_new_estimator(&p->tcfc_bstats, p->cpu_bstats, + &p->tcfc_rate_est, + &p->tcfc_lock, est); if (err) { - kfree(p); - return err; + free_percpu(p->cpu_qstats); + goto err2; } } @@ -616,10 +640,10 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, if (err < 0) goto errout; - if (gnet_stats_copy_basic(&d, NULL, &p->tcfc_bstats) < 0 || + if (gnet_stats_copy_basic(&d, p->cpu_bstats, &p->tcfc_bstats) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfc_bstats, &p->tcfc_rate_est) < 0 || - gnet_stats_copy_queue(&d, NULL, + gnet_stats_copy_queue(&d, p->cpu_qstats, &p->tcfc_qstats, p->tcfc_qstats.qlen) < 0) goto errout; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index d0edeb7..1b97dab 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -278,7 +278,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct tc_act_bpf *parm; struct tcf_bpf *prog; bool is_bpf, is_ebpf; - int ret; + int ret, res = 0; if (!nla) return -EINVAL; @@ -287,41 +287,43 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (ret < 0) return ret; - is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; - is_ebpf = tb[TCA_ACT_BPF_FD]; - - if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) || - !tb[TCA_ACT_BPF_PARMS]) + if (!tb[TCA_ACT_BPF_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_ACT_BPF_PARMS]); - memset(&cfg, 0, sizeof(cfg)); - - ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : - tcf_bpf_init_from_efd(tb, &cfg); - if (ret < 0) - return ret; - if (!tcf_hash_check(parm->index, act, bind)) { ret = tcf_hash_create(parm->index, est, act, - sizeof(*prog), bind); + sizeof(*prog), bind, false); if (ret < 0) - goto destroy_fp; + return ret; - ret = ACT_P_CREATED; + res = ACT_P_CREATED; } else { /* Don't override defaults. */ if (bind) - goto destroy_fp; + return 0; tcf_hash_release(act, bind); - if (!replace) { - ret = -EEXIST; - goto destroy_fp; - } + if (!replace) + return -EEXIST; } + is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; + is_ebpf = tb[TCA_ACT_BPF_FD]; + + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) { + ret = -EINVAL; + goto out; + } + + memset(&cfg, 0, sizeof(cfg)); + + ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : + tcf_bpf_init_from_efd(tb, &cfg); + if (ret < 0) + goto out; + prog = to_bpf(act); spin_lock_bh(&prog->tcf_lock); @@ -341,15 +343,16 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&prog->tcf_lock); - if (ret == ACT_P_CREATED) + if (res == ACT_P_CREATED) tcf_hash_insert(act); else tcf_bpf_cfg_cleanup(&old); - return ret; + return res; +out: + if (res == ACT_P_CREATED) + tcf_hash_cleanup(act, est); -destroy_fp: - tcf_bpf_cfg_cleanup(&cfg); return ret; } diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 295d14b..f2b5402 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -108,7 +108,8 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_CONNMARK_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*ci), + bind, false); if (ret) return ret; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 4cd5cf1..b07c535 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -62,7 +62,8 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, parm = nla_data(tb[TCA_CSUM_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), + bind, false); if (ret) return ret; ret = ACT_P_CREATED; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 7fffc22..5c1b051 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -28,14 +28,18 @@ #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) { - if (!gact->tcfg_pval || prandom_u32() % gact->tcfg_pval) + smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ + if (prandom_u32() % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } static int gact_determ(struct tcf_gact *gact) { - if (!gact->tcfg_pval || gact->tcf_bstats.packets % gact->tcfg_pval) + u32 pack = atomic_inc_return(&gact->packets); + + smp_rmb(); /* coupled with smp_wmb() in tcf_gact_init() */ + if (pack % gact->tcfg_pval) return gact->tcf_action; return gact->tcfg_paction; } @@ -85,7 +89,8 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, #endif if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), + bind, true); if (ret) return ret; ret = ACT_P_CREATED; @@ -99,16 +104,19 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, gact = to_gact(a); - spin_lock_bh(&gact->tcf_lock); + ASSERT_RTNL(); gact->tcf_action = parm->action; #ifdef CONFIG_GACT_PROB if (p_parm) { gact->tcfg_paction = p_parm->paction; - gact->tcfg_pval = p_parm->pval; + gact->tcfg_pval = max_t(u16, 1, p_parm->pval); + /* Make sure tcfg_pval is written before tcfg_ptype + * coupled with smp_rmb() in gact_net_rand() & gact_determ() + */ + smp_wmb(); gact->tcfg_ptype = p_parm->ptype; } #endif - spin_unlock_bh(&gact->tcf_lock); if (ret == ACT_P_CREATED) tcf_hash_insert(a); return ret; @@ -118,23 +126,21 @@ static int tcf_gact(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_gact *gact = a->priv; - int action = TC_ACT_SHOT; + int action = READ_ONCE(gact->tcf_action); - spin_lock(&gact->tcf_lock); #ifdef CONFIG_GACT_PROB - if (gact->tcfg_ptype) - action = gact_rand[gact->tcfg_ptype](gact); - else - action = gact->tcf_action; -#else - action = gact->tcf_action; + { + u32 ptype = READ_ONCE(gact->tcfg_ptype); + + if (ptype) + action = gact_rand[ptype](gact); + } #endif - gact->tcf_bstats.bytes += qdisc_pkt_len(skb); - gact->tcf_bstats.packets++; + bstats_cpu_update(this_cpu_ptr(gact->common.cpu_bstats), skb); if (action == TC_ACT_SHOT) - gact->tcf_qstats.drops++; - gact->tcf_tm.lastuse = jiffies; - spin_unlock(&gact->tcf_lock); + qstats_drop_inc(this_cpu_ptr(gact->common.cpu_qstats)); + + tcf_lastuse_update(&gact->tcf_tm); return action; } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index cbc8dd7..99c9cc1 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -114,7 +114,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, index = nla_get_u32(tb[TCA_IPT_INDEX]); if (!tcf_hash_check(index, a, bind) ) { - ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind); + ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind, false); if (ret) return ret; ret = ACT_P_CREATED; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 2685450..2d1be4a 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -35,9 +35,11 @@ static LIST_HEAD(mirred_list); static void tcf_mirred_release(struct tc_action *a, int bind) { struct tcf_mirred *m = to_mirred(a); + struct net_device *dev = rcu_dereference_protected(m->tcfm_dev, 1); + list_del(&m->tcfm_list); - if (m->tcfm_dev) - dev_put(m->tcfm_dev); + if (dev) + dev_put(dev); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { @@ -93,7 +95,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, if (!tcf_hash_check(parm->index, a, bind)) { if (dev == NULL) return -EINVAL; - ret = tcf_hash_create(parm->index, est, a, sizeof(*m), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*m), + bind, true); if (ret) return ret; ret = ACT_P_CREATED; @@ -107,18 +110,18 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } m = to_mirred(a); - spin_lock_bh(&m->tcf_lock); + ASSERT_RTNL(); m->tcf_action = parm->action; m->tcfm_eaction = parm->eaction; if (dev != NULL) { m->tcfm_ifindex = parm->ifindex; if (ret != ACT_P_CREATED) - dev_put(m->tcfm_dev); + dev_put(rcu_dereference_protected(m->tcfm_dev, 1)); dev_hold(dev); - m->tcfm_dev = dev; + rcu_assign_pointer(m->tcfm_dev, dev); m->tcfm_ok_push = ok_push; } - spin_unlock_bh(&m->tcf_lock); + if (ret == ACT_P_CREATED) { list_add(&m->tcfm_list, &mirred_list); tcf_hash_insert(a); @@ -133,20 +136,22 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, struct tcf_mirred *m = a->priv; struct net_device *dev; struct sk_buff *skb2; + int retval, err; u32 at; - int retval, err = 1; - spin_lock(&m->tcf_lock); - m->tcf_tm.lastuse = jiffies; - bstats_update(&m->tcf_bstats, skb); + tcf_lastuse_update(&m->tcf_tm); + + bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); - dev = m->tcfm_dev; - if (!dev) { - printk_once(KERN_NOTICE "tc mirred: target device is gone\n"); + rcu_read_lock(); + retval = READ_ONCE(m->tcf_action); + dev = rcu_dereference(m->tcfm_dev); + if (unlikely(!dev)) { + pr_notice_once("tc mirred: target device is gone\n"); goto out; } - if (!(dev->flags & IFF_UP)) { + if (unlikely(!(dev->flags & IFF_UP))) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); goto out; @@ -154,7 +159,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, at = G_TC_AT(skb->tc_verd); skb2 = skb_clone(skb, GFP_ATOMIC); - if (skb2 == NULL) + if (!skb2) goto out; if (!(at & AT_EGRESS)) { @@ -170,16 +175,13 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, skb2->dev = dev; err = dev_queue_xmit(skb2); -out: if (err) { - m->tcf_qstats.overlimits++; +out: + qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats)); if (m->tcfm_eaction != TCA_EGRESS_MIRROR) retval = TC_ACT_SHOT; - else - retval = m->tcf_action; - } else - retval = m->tcf_action; - spin_unlock(&m->tcf_lock); + } + rcu_read_unlock(); return retval; } @@ -218,14 +220,16 @@ static int mirred_device_event(struct notifier_block *unused, struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tcf_mirred *m; + ASSERT_RTNL(); if (event == NETDEV_UNREGISTER) list_for_each_entry(m, &mirred_list, tcfm_list) { - spin_lock_bh(&m->tcf_lock); - if (m->tcfm_dev == dev) { + if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); - m->tcfm_dev = NULL; + /* Note : no rcu grace period necessary, as + * net_device are already rcu protected. + */ + RCU_INIT_POINTER(m->tcfm_dev, NULL); } - spin_unlock_bh(&m->tcf_lock); } return NOTIFY_DONE; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 270a030..5be0b3c 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -55,7 +55,8 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, parm = nla_data(tb[TCA_NAT_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), + bind, false); if (ret) return ret; ret = ACT_P_CREATED; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index ff8b466..e38a770 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -57,7 +57,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (!tcf_hash_check(parm->index, a, bind)) { if (!parm->nkeys) return -EINVAL; - ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), + bind, false); if (ret) return ret; p = to_pedit(a); diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 6a8d948..d6b708d 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -103,7 +103,8 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, defdata = nla_data(tb[TCA_DEF_DATA]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*d), + bind, false); if (ret) return ret; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index fcfeeaf..6751b5f 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,7 +99,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_SKBEDIT_PARMS]); if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*d), + bind, false); if (ret) return ret; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index d735ecf..796785e 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -116,7 +116,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, action = parm->v_action; if (!tcf_hash_check(parm->index, a, bind)) { - ret = tcf_hash_create(parm->index, est, a, sizeof(*v), bind); + ret = tcf_hash_create(parm->index, est, a, sizeof(*v), + bind, false); if (ret) return ret; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index ea611b21..4c85bd3 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -30,35 +30,16 @@ static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct cls_cgroup_head *head = rcu_dereference_bh(tp->root); - u32 classid; - - classid = task_cls_state(current)->classid; - - /* - * Due to the nature of the classifier it is required to ignore all - * packets originating from softirq context as accessing `current' - * would lead to false results. - * - * This test assumes that all callers of dev_queue_xmit() explicitely - * disable bh. Knowing this, it is possible to detect softirq based - * calls by looking at the number of nested bh disable calls because - * softirqs always disables bh. - */ - if (in_serving_softirq()) { - /* If there is an sk_classid we'll use that. */ - if (!skb->sk) - return -1; - classid = skb->sk->sk_classid; - } + u32 classid = task_get_classid(skb); if (!classid) return -1; - if (!tcf_em_tree_match(skb, &head->ematches, NULL)) return -1; res->classid = classid; res->class = 0; + return tcf_exts_exec(skb, &head->exts, res); } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index b8d73bc..ffaeea6 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -186,7 +186,6 @@ struct qfq_sched { u64 oldV, V; /* Precise virtual times. */ struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */ - u32 num_active_agg; /* Num. of active aggregates */ u32 wsum; /* weight sum */ u32 iwsum; /* inverse weight sum */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 59e8035..4345790 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -487,23 +487,35 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, */ rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { + struct net_device *odev; + if (!laddr->valid) continue; - if ((laddr->state == SCTP_ADDR_SRC) && - (AF_INET == laddr->a.sa.sa_family)) { - fl4->fl4_sport = laddr->a.v4.sin_port; - flowi4_update_output(fl4, - asoc->base.sk->sk_bound_dev_if, - RT_CONN_FLAGS(asoc->base.sk), - daddr->v4.sin_addr.s_addr, - laddr->a.v4.sin_addr.s_addr); - - rt = ip_route_output_key(sock_net(sk), fl4); - if (!IS_ERR(rt)) { - dst = &rt->dst; - goto out_unlock; - } - } + if (laddr->state != SCTP_ADDR_SRC || + AF_INET != laddr->a.sa.sa_family) + continue; + + fl4->fl4_sport = laddr->a.v4.sin_port; + flowi4_update_output(fl4, + asoc->base.sk->sk_bound_dev_if, + RT_CONN_FLAGS(asoc->base.sk), + daddr->v4.sin_addr.s_addr, + laddr->a.v4.sin_addr.s_addr); + + rt = ip_route_output_key(sock_net(sk), fl4); + if (IS_ERR(rt)) + continue; + + /* Ensure the src address belongs to the output + * interface. + */ + odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr, + false); + if (!odev || odev->ifindex != fl4->flowi4_oif) + continue; + + dst = &rt->dst; + break; } out_unlock: diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 3ee27b7..d7eaa73 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -853,7 +853,7 @@ nomem: /* * Respond to a normal COOKIE ACK chunk. - * We are the side that is being asked for an association. + * We are the side that is asking for an association. * * RFC 2960 5.1 Normal Establishment of an Association * diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 9f2add3..16c1c43 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -810,7 +810,7 @@ static int switchdev_port_fdb_dump_cb(struct net_device *dev, ndm->ndm_flags = NTF_SELF; ndm->ndm_type = 0; ndm->ndm_ifindex = dev->ifindex; - ndm->ndm_state = NUD_REACHABLE; + ndm->ndm_state = obj->u.fdb.ndm_state; if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, obj->u.fdb.addr)) goto nla_put_failure; @@ -910,13 +910,9 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) if (switchdev_port_attr_get(dev, &attr)) return NULL; - if (nhsel > 0) { - if (prev_attr.u.ppid.id_len != attr.u.ppid.id_len) + if (nhsel > 0 && + !netdev_phys_item_id_same(&prev_attr.u.ppid, &attr.u.ppid)) return NULL; - if (memcmp(prev_attr.u.ppid.id, attr.u.ppid.id, - attr.u.ppid.id_len)) - return NULL; - } prev_attr = attr; } @@ -1043,3 +1039,106 @@ void switchdev_fib_ipv4_abort(struct fib_info *fi) fi->fib_net->ipv4.fib_offload_disabled = true; } EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_abort); + +static bool switchdev_port_same_parent_id(struct net_device *a, + struct net_device *b) +{ + struct switchdev_attr a_attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .flags = SWITCHDEV_F_NO_RECURSE, + }; + struct switchdev_attr b_attr = { + .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .flags = SWITCHDEV_F_NO_RECURSE, + }; + + if (switchdev_port_attr_get(a, &a_attr) || + switchdev_port_attr_get(b, &b_attr)) + return false; + + return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid); +} + +static u32 switchdev_port_fwd_mark_get(struct net_device *dev, + struct net_device *group_dev) +{ + struct net_device *lower_dev; + struct list_head *iter; + + netdev_for_each_lower_dev(group_dev, lower_dev, iter) { + if (lower_dev == dev) + continue; + if (switchdev_port_same_parent_id(dev, lower_dev)) + return lower_dev->offload_fwd_mark; + return switchdev_port_fwd_mark_get(dev, lower_dev); + } + + return dev->ifindex; +} + +static void switchdev_port_fwd_mark_reset(struct net_device *group_dev, + u32 old_mark, u32 *reset_mark) +{ + struct net_device *lower_dev; + struct list_head *iter; + + netdev_for_each_lower_dev(group_dev, lower_dev, iter) { + if (lower_dev->offload_fwd_mark == old_mark) { + if (!*reset_mark) + *reset_mark = lower_dev->ifindex; + lower_dev->offload_fwd_mark = *reset_mark; + } + switchdev_port_fwd_mark_reset(lower_dev, old_mark, reset_mark); + } +} + +/** + * switchdev_port_fwd_mark_set - Set port offload forwarding mark + * + * @dev: port device + * @group_dev: containing device + * @joining: true if dev is joining group; false if leaving group + * + * An ungrouped port's offload mark is just its ifindex. A grouped + * port's (member of a bridge, for example) offload mark is the ifindex + * of one of the ports in the group with the same parent (switch) ID. + * Ports on the same device in the same group will have the same mark. + * + * Example: + * + * br0 ifindex=9 + * sw1p1 ifindex=2 mark=2 + * sw1p2 ifindex=3 mark=2 + * sw2p1 ifindex=4 mark=5 + * sw2p2 ifindex=5 mark=5 + * + * If sw2p2 leaves the bridge, we'll have: + * + * br0 ifindex=9 + * sw1p1 ifindex=2 mark=2 + * sw1p2 ifindex=3 mark=2 + * sw2p1 ifindex=4 mark=4 + * sw2p2 ifindex=5 mark=5 + */ +void switchdev_port_fwd_mark_set(struct net_device *dev, + struct net_device *group_dev, + bool joining) +{ + u32 mark = dev->ifindex; + u32 reset_mark = 0; + + if (group_dev && joining) { + mark = switchdev_port_fwd_mark_get(dev, group_dev); + } else if (group_dev && !joining) { + if (dev->offload_fwd_mark == mark) + /* Ohoh, this port was the mark reference port, + * but it's leaving the group, so reset the + * mark for the remaining ports in the group. + */ + switchdev_port_fwd_mark_reset(group_dev, mark, + &reset_mark); + } + + dev->offload_fwd_mark = mark; +} +EXPORT_SYMBOL_GPL(switchdev_port_fwd_mark_set); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index a816382..8b010c9 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -316,6 +316,29 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, } } +void tipc_bclink_sync_state(struct tipc_node *n, struct tipc_msg *hdr) +{ + u16 last = msg_last_bcast(hdr); + int mtyp = msg_type(hdr); + + if (unlikely(msg_user(hdr) != LINK_PROTOCOL)) + return; + if (mtyp == STATE_MSG) { + tipc_bclink_update_link_state(n, last); + return; + } + /* Compatibility: older nodes don't know BCAST_PROTOCOL synchronization, + * and transfer synch info in LINK_PROTOCOL messages. + */ + if (tipc_node_is_up(n)) + return; + if ((mtyp != RESET_MSG) && (mtyp != ACTIVATE_MSG)) + return; + n->bclink.last_sent = last; + n->bclink.last_in = last; + n->bclink.oos_state = 0; +} + /** * bclink_peek_nack - monitor retransmission requests sent by other nodes * @@ -358,10 +381,9 @@ int tipc_bclink_xmit(struct net *net, struct sk_buff_head *list) /* Prepare clone of message for local node */ skb = tipc_msg_reassemble(list); - if (unlikely(!skb)) { - __skb_queue_purge(list); + if (unlikely(!skb)) return -EHOSTUNREACH; - } + /* Broadcast to all nodes */ if (likely(bclink)) { tipc_bclink_lock(net); @@ -413,7 +435,7 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) * all nodes in the cluster don't ACK at the same time */ if (((seqno - tn->own_addr) % TIPC_MIN_LINK_WIN) == 0) { - tipc_link_proto_xmit(node->active_links[node->addr & 1], + tipc_link_proto_xmit(node_active_link(node, node->addr), STATE_MSG, 0, 0, 0, 0); tn->bcl->stats.sent_acks++; } @@ -925,7 +947,6 @@ int tipc_bclink_init(struct net *net) tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT); bcl->bearer_id = MAX_BEARERS; rcu_assign_pointer(tn->bearer_list[MAX_BEARERS], &bcbearer->bearer); - bcl->state = WORKING_WORKING; bcl->pmsg = (struct tipc_msg *)&bcl->proto_msg; msg_set_prevnode(bcl->pmsg, tn->own_addr); strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 3c290a48..d74c69b 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -133,5 +133,6 @@ void tipc_bclink_wakeup_users(struct net *net); int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg); int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]); void tipc_bclink_input(struct net *net); +void tipc_bclink_sync_state(struct tipc_node *n, struct tipc_msg *msg); #endif diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 00bc0e6..ce9f7bf 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -343,7 +343,7 @@ restart: static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b_ptr) { pr_info("Resetting bearer <%s>\n", b_ptr->name); - tipc_link_delete_list(net, b_ptr->identity); + tipc_node_delete_links(net, b_ptr->identity); tipc_disc_reset(net, b_ptr); return 0; } @@ -361,7 +361,7 @@ static void bearer_disable(struct net *net, struct tipc_bearer *b_ptr) pr_info("Disabling bearer <%s>\n", b_ptr->name); b_ptr->media->disable_media(b_ptr); - tipc_link_delete_list(net, b_ptr->identity); + tipc_node_delete_links(net, b_ptr->identity); if (b_ptr->link_req) tipc_disc_delete(b_ptr->link_req); @@ -470,6 +470,32 @@ void tipc_bearer_send(struct net *net, u32 bearer_id, struct sk_buff *buf, rcu_read_unlock(); } +/* tipc_bearer_xmit() -send buffer to destination over bearer + */ +void tipc_bearer_xmit(struct net *net, u32 bearer_id, + struct sk_buff_head *xmitq, + struct tipc_media_addr *dst) +{ + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_bearer *b; + struct sk_buff *skb, *tmp; + + if (skb_queue_empty(xmitq)) + return; + + rcu_read_lock(); + b = rcu_dereference_rtnl(tn->bearer_list[bearer_id]); + if (likely(b)) { + skb_queue_walk_safe(xmitq, skb, tmp) { + __skb_dequeue(xmitq); + b->media->send_msg(net, skb, b, dst); + /* Until we remove cloning in tipc_l2_send_msg(): */ + kfree_skb(skb); + } + } + rcu_read_unlock(); +} + /** * tipc_l2_rcv_msg - handle incoming TIPC message from an interface * @buf: the received packet diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index dc714d9..6426f24 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -217,5 +217,8 @@ void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); void tipc_bearer_send(struct net *net, u32 bearer_id, struct sk_buff *buf, struct tipc_media_addr *dest); +void tipc_bearer_xmit(struct net *net, u32 bearer_id, + struct sk_buff_head *xmitq, + struct tipc_media_addr *dst); #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/core.h b/net/tipc/core.h index 0fcf133..b96b41e 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -109,6 +109,11 @@ struct tipc_net { atomic_t subscription_count; }; +static inline struct tipc_net *tipc_net(struct net *net) +{ + return net_generic(net, tipc_net_id); +} + static inline u16 mod(u16 x) { return x & 0xffffu; @@ -129,6 +134,11 @@ static inline int less(u16 left, u16 right) return less_eq(left, right) && (mod(right) != mod(left)); } +static inline int in_range(u16 val, u16 min, u16 max) +{ + return !less(val, min) && !more(val, max); +} + #ifdef CONFIG_SYSCTL int tipc_register_sysctl(void); void tipc_unregister_sysctl(void); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 967e292..d14e0a4 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -35,7 +35,7 @@ */ #include "core.h" -#include "link.h" +#include "node.h" #include "discover.h" /* min delay during bearer start up */ @@ -120,30 +120,24 @@ static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr, * @buf: buffer containing message * @bearer: bearer that message arrived on */ -void tipc_disc_rcv(struct net *net, struct sk_buff *buf, +void tipc_disc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *bearer) { struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_node *node; - struct tipc_link *link; struct tipc_media_addr maddr; - struct sk_buff *rbuf; - struct tipc_msg *msg = buf_msg(buf); - u32 ddom = msg_dest_domain(msg); - u32 onode = msg_prevnode(msg); - u32 net_id = msg_bc_netid(msg); - u32 mtyp = msg_type(msg); - u32 signature = msg_node_sig(msg); - u16 caps = msg_node_capabilities(msg); - bool addr_match = false; - bool sign_match = false; - bool link_up = false; - bool accept_addr = false; - bool accept_sign = false; + struct sk_buff *rskb; + struct tipc_msg *hdr = buf_msg(skb); + u32 ddom = msg_dest_domain(hdr); + u32 onode = msg_prevnode(hdr); + u32 net_id = msg_bc_netid(hdr); + u32 mtyp = msg_type(hdr); + u32 signature = msg_node_sig(hdr); + u16 caps = msg_node_capabilities(hdr); bool respond = false; + bool dupl_addr = false; - bearer->media->msg2addr(bearer, &maddr, msg_media_addr(msg)); - kfree_skb(buf); + bearer->media->msg2addr(bearer, &maddr, msg_media_addr(hdr)); + kfree_skb(skb); /* Ensure message from node is valid and communication is permitted */ if (net_id != tn->net_id) @@ -165,102 +159,20 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *buf, if (!tipc_in_scope(bearer->domain, onode)) return; - node = tipc_node_create(net, onode); - if (!node) - return; - tipc_node_lock(node); - node->capabilities = caps; - link = node->links[bearer->identity]; - - /* Prepare to validate requesting node's signature and media address */ - sign_match = (signature == node->signature); - addr_match = link && !memcmp(&link->media_addr, &maddr, sizeof(maddr)); - link_up = link && tipc_link_is_up(link); - - - /* These three flags give us eight permutations: */ - - if (sign_match && addr_match && link_up) { - /* All is fine. Do nothing. */ - } else if (sign_match && addr_match && !link_up) { - /* Respond. The link will come up in due time */ - respond = true; - } else if (sign_match && !addr_match && link_up) { - /* Peer has changed i/f address without rebooting. - * If so, the link will reset soon, and the next - * discovery will be accepted. So we can ignore it. - * It may also be an cloned or malicious peer having - * chosen the same node address and signature as an - * existing one. - * Ignore requests until the link goes down, if ever. - */ - disc_dupl_alert(bearer, onode, &maddr); - } else if (sign_match && !addr_match && !link_up) { - /* Peer link has changed i/f address without rebooting. - * It may also be a cloned or malicious peer; we can't - * distinguish between the two. - * The signature is correct, so we must accept. - */ - accept_addr = true; - respond = true; - } else if (!sign_match && addr_match && link_up) { - /* Peer node rebooted. Two possibilities: - * - Delayed re-discovery; this link endpoint has already - * reset and re-established contact with the peer, before - * receiving a discovery message from that node. - * (The peer happened to receive one from this node first). - * - The peer came back so fast that our side has not - * discovered it yet. Probing from this side will soon - * reset the link, since there can be no working link - * endpoint at the peer end, and the link will re-establish. - * Accept the signature, since it comes from a known peer. - */ - accept_sign = true; - } else if (!sign_match && addr_match && !link_up) { - /* The peer node has rebooted. - * Accept signature, since it is a known peer. - */ - accept_sign = true; - respond = true; - } else if (!sign_match && !addr_match && link_up) { - /* Peer rebooted with new address, or a new/duplicate peer. - * Ignore until the link goes down, if ever. - */ + tipc_node_check_dest(net, onode, bearer, caps, signature, + &maddr, &respond, &dupl_addr); + if (dupl_addr) disc_dupl_alert(bearer, onode, &maddr); - } else if (!sign_match && !addr_match && !link_up) { - /* Peer rebooted with new address, or it is a new peer. - * Accept signature and address. - */ - accept_sign = true; - accept_addr = true; - respond = true; - } - - if (accept_sign) - node->signature = signature; - - if (accept_addr) { - if (!link) - link = tipc_link_create(node, bearer, &maddr); - if (link) { - memcpy(&link->media_addr, &maddr, sizeof(maddr)); - tipc_link_reset(link); - } else { - respond = false; - } - } /* Send response, if necessary */ if (respond && (mtyp == DSC_REQ_MSG)) { - rbuf = tipc_buf_acquire(MAX_H_SIZE); - if (rbuf) { - tipc_disc_init_msg(net, rbuf, DSC_RESP_MSG, bearer); - tipc_bearer_send(net, bearer->identity, rbuf, &maddr); - kfree_skb(rbuf); + rskb = tipc_buf_acquire(MAX_H_SIZE); + if (rskb) { + tipc_disc_init_msg(net, rskb, DSC_RESP_MSG, bearer); + tipc_bearer_send(net, bearer->identity, rskb, &maddr); + kfree_skb(rskb); } } - tipc_node_unlock(node); - tipc_node_put(node); } /** diff --git a/net/tipc/link.c b/net/tipc/link.c index eaa9fe5..f067e54 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -48,9 +48,8 @@ /* * Error message prefixes */ -static const char *link_co_err = "Link changeover error, "; +static const char *link_co_err = "Link tunneling error, "; static const char *link_rst_msg = "Resetting link "; -static const char *link_unk_evt = "Unknown link event "; static const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = { [TIPC_NLA_LINK_UNSPEC] = { .type = NLA_UNSPEC }, @@ -77,256 +76,413 @@ static const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { }; /* + * Interval between NACKs when packets arrive out of order + */ +#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2) +/* * Out-of-range value for link session numbers */ -#define INVALID_SESSION 0x10000 +#define WILDCARD_SESSION 0x10000 -/* - * Link state events: +/* Link FSM states: */ -#define STARTING_EVT 856384768 /* link processing trigger */ -#define TRAFFIC_MSG_EVT 560815u /* rx'd ??? */ -#define SILENCE_EVT 560817u /* timer dicovered silence from peer */ +enum { + LINK_ESTABLISHED = 0xe, + LINK_ESTABLISHING = 0xe << 4, + LINK_RESET = 0x1 << 8, + LINK_RESETTING = 0x2 << 12, + LINK_PEER_RESET = 0xd << 16, + LINK_FAILINGOVER = 0xf << 20, + LINK_SYNCHING = 0xc << 24 +}; -/* - * State value stored in 'failover_pkts' +/* Link FSM state checking routines */ -#define FIRST_FAILOVER 0xffffu - -static void link_handle_out_of_seq_msg(struct tipc_link *link, - struct sk_buff *skb); -static void tipc_link_proto_rcv(struct tipc_link *link, - struct sk_buff *skb); -static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol); -static void link_state_event(struct tipc_link *l_ptr, u32 event); +static int link_is_up(struct tipc_link *l) +{ + return l->state & (LINK_ESTABLISHED | LINK_SYNCHING); +} + +static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq); +static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, + u16 rcvgap, int tolerance, int priority, + struct sk_buff_head *xmitq); static void link_reset_statistics(struct tipc_link *l_ptr); static void link_print(struct tipc_link *l_ptr, const char *str); -static void tipc_link_sync_xmit(struct tipc_link *l); static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf); -static void tipc_link_input(struct tipc_link *l, struct sk_buff *skb); -static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb); -static bool tipc_link_failover_rcv(struct tipc_link *l, struct sk_buff **skb); -static void link_set_timer(struct tipc_link *link, unsigned long time); + /* - * Simple link routines + * Simple non-static link routines (i.e. referenced outside this file) */ -static unsigned int align(unsigned int i) +bool tipc_link_is_up(struct tipc_link *l) { - return (i + 3) & ~3u; + return link_is_up(l); } -static void tipc_link_release(struct kref *kref) +bool tipc_link_is_reset(struct tipc_link *l) { - kfree(container_of(kref, struct tipc_link, ref)); + return l->state & (LINK_RESET | LINK_FAILINGOVER | LINK_ESTABLISHING); } -static void tipc_link_get(struct tipc_link *l_ptr) +bool tipc_link_is_synching(struct tipc_link *l) { - kref_get(&l_ptr->ref); + return l->state == LINK_SYNCHING; } -static void tipc_link_put(struct tipc_link *l_ptr) +bool tipc_link_is_failingover(struct tipc_link *l) { - kref_put(&l_ptr->ref, tipc_link_release); + return l->state == LINK_FAILINGOVER; } -static struct tipc_link *tipc_parallel_link(struct tipc_link *l) +bool tipc_link_is_blocked(struct tipc_link *l) { - if (l->owner->active_links[0] != l) - return l->owner->active_links[0]; - return l->owner->active_links[1]; + return l->state & (LINK_RESETTING | LINK_PEER_RESET | LINK_FAILINGOVER); } -/* - * Simple non-static link routines (i.e. referenced outside this file) - */ -int tipc_link_is_up(struct tipc_link *l_ptr) +int tipc_link_is_active(struct tipc_link *l) { - if (!l_ptr) - return 0; - return link_working_working(l_ptr) || link_working_unknown(l_ptr); + struct tipc_node *n = l->owner; + + return (node_active_link(n, 0) == l) || (node_active_link(n, 1) == l); } -int tipc_link_is_active(struct tipc_link *l_ptr) +static u32 link_own_addr(struct tipc_link *l) { - return (l_ptr->owner->active_links[0] == l_ptr) || - (l_ptr->owner->active_links[1] == l_ptr); + return msg_prevnode(l->pmsg); } /** - * link_timeout - handle expiration of link timer - * @l_ptr: pointer to link + * tipc_link_create - create a new link + * @n: pointer to associated node + * @b: pointer to associated bearer + * @ownnode: identity of own node + * @peer: identity of peer node + * @maddr: media address to be used + * @inputq: queue to put messages ready for delivery + * @namedq: queue to put binding table update messages ready for delivery + * @link: return value, pointer to put the created link + * + * Returns true if link was created, otherwise false */ -static void link_timeout(unsigned long data) +bool tipc_link_create(struct tipc_node *n, struct tipc_bearer *b, u32 session, + u32 ownnode, u32 peer, struct tipc_media_addr *maddr, + struct sk_buff_head *inputq, struct sk_buff_head *namedq, + struct tipc_link **link) { - struct tipc_link *l_ptr = (struct tipc_link *)data; - struct sk_buff *skb; + struct tipc_link *l; + struct tipc_msg *hdr; + char *if_name; + + l = kzalloc(sizeof(*l), GFP_ATOMIC); + if (!l) + return false; + *link = l; + + /* Note: peer i/f name is completed by reset/activate message */ + if_name = strchr(b->name, ':') + 1; + sprintf(l->name, "%u.%u.%u:%s-%u.%u.%u:unknown", + tipc_zone(ownnode), tipc_cluster(ownnode), tipc_node(ownnode), + if_name, tipc_zone(peer), tipc_cluster(peer), tipc_node(peer)); + + l->addr = peer; + l->media_addr = maddr; + l->owner = n; + l->peer_session = WILDCARD_SESSION; + l->bearer_id = b->identity; + l->tolerance = b->tolerance; + l->net_plane = b->net_plane; + l->advertised_mtu = b->mtu; + l->mtu = b->mtu; + l->priority = b->priority; + tipc_link_set_queue_limits(l, b->window); + l->inputq = inputq; + l->namedq = namedq; + l->state = LINK_RESETTING; + l->pmsg = (struct tipc_msg *)&l->proto_msg; + hdr = l->pmsg; + tipc_msg_init(ownnode, hdr, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, peer); + msg_set_size(hdr, sizeof(l->proto_msg)); + msg_set_session(hdr, session); + msg_set_bearer_id(hdr, l->bearer_id); + strcpy((char *)msg_data(hdr), if_name); + __skb_queue_head_init(&l->transmq); + __skb_queue_head_init(&l->backlogq); + __skb_queue_head_init(&l->deferdq); + skb_queue_head_init(&l->wakeupq); + skb_queue_head_init(l->inputq); + return true; +} - tipc_node_lock(l_ptr->owner); +/* tipc_link_build_bcast_sync_msg() - synchronize broadcast link endpoints. + * + * Give a newly added peer node the sequence number where it should + * start receiving and acking broadcast packets. + */ +void tipc_link_build_bcast_sync_msg(struct tipc_link *l, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb; + struct sk_buff_head list; + u16 last_sent; - /* update counters used in statistical profiling of send traffic */ - l_ptr->stats.accu_queue_sz += skb_queue_len(&l_ptr->transmq); - l_ptr->stats.queue_sz_counts++; + skb = tipc_msg_create(BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, + 0, l->addr, link_own_addr(l), 0, 0, 0); + if (!skb) + return; + last_sent = tipc_bclink_get_last_sent(l->owner->net); + msg_set_last_bcast(buf_msg(skb), last_sent); + __skb_queue_head_init(&list); + __skb_queue_tail(&list, skb); + tipc_link_xmit(l, &list, xmitq); +} - skb = skb_peek(&l_ptr->transmq); - if (skb) { - struct tipc_msg *msg = buf_msg(skb); - u32 length = msg_size(msg); +/** + * tipc_link_fsm_evt - link finite state machine + * @l: pointer to link + * @evt: state machine event to be processed + */ +int tipc_link_fsm_evt(struct tipc_link *l, int evt) +{ + int rc = 0; - if ((msg_user(msg) == MSG_FRAGMENTER) && - (msg_type(msg) == FIRST_FRAGMENT)) { - length = msg_size(msg_get_wrapped(msg)); + switch (l->state) { + case LINK_RESETTING: + switch (evt) { + case LINK_PEER_RESET_EVT: + l->state = LINK_PEER_RESET; + break; + case LINK_RESET_EVT: + l->state = LINK_RESET; + break; + case LINK_FAILURE_EVT: + case LINK_FAILOVER_BEGIN_EVT: + case LINK_ESTABLISH_EVT: + case LINK_FAILOVER_END_EVT: + case LINK_SYNCH_BEGIN_EVT: + case LINK_SYNCH_END_EVT: + default: + goto illegal_evt; } - if (length) { - l_ptr->stats.msg_lengths_total += length; - l_ptr->stats.msg_length_counts++; - if (length <= 64) - l_ptr->stats.msg_length_profile[0]++; - else if (length <= 256) - l_ptr->stats.msg_length_profile[1]++; - else if (length <= 1024) - l_ptr->stats.msg_length_profile[2]++; - else if (length <= 4096) - l_ptr->stats.msg_length_profile[3]++; - else if (length <= 16384) - l_ptr->stats.msg_length_profile[4]++; - else if (length <= 32768) - l_ptr->stats.msg_length_profile[5]++; - else - l_ptr->stats.msg_length_profile[6]++; + break; + case LINK_RESET: + switch (evt) { + case LINK_PEER_RESET_EVT: + l->state = LINK_ESTABLISHING; + break; + case LINK_FAILOVER_BEGIN_EVT: + l->state = LINK_FAILINGOVER; + case LINK_FAILURE_EVT: + case LINK_RESET_EVT: + case LINK_ESTABLISH_EVT: + case LINK_FAILOVER_END_EVT: + break; + case LINK_SYNCH_BEGIN_EVT: + case LINK_SYNCH_END_EVT: + default: + goto illegal_evt; + } + break; + case LINK_PEER_RESET: + switch (evt) { + case LINK_RESET_EVT: + l->state = LINK_ESTABLISHING; + break; + case LINK_PEER_RESET_EVT: + case LINK_ESTABLISH_EVT: + case LINK_FAILURE_EVT: + break; + case LINK_SYNCH_BEGIN_EVT: + case LINK_SYNCH_END_EVT: + case LINK_FAILOVER_BEGIN_EVT: + case LINK_FAILOVER_END_EVT: + default: + goto illegal_evt; } + break; + case LINK_FAILINGOVER: + switch (evt) { + case LINK_FAILOVER_END_EVT: + l->state = LINK_RESET; + break; + case LINK_PEER_RESET_EVT: + case LINK_RESET_EVT: + case LINK_ESTABLISH_EVT: + case LINK_FAILURE_EVT: + break; + case LINK_FAILOVER_BEGIN_EVT: + case LINK_SYNCH_BEGIN_EVT: + case LINK_SYNCH_END_EVT: + default: + goto illegal_evt; + } + break; + case LINK_ESTABLISHING: + switch (evt) { + case LINK_ESTABLISH_EVT: + l->state = LINK_ESTABLISHED; + rc |= TIPC_LINK_UP_EVT; + break; + case LINK_FAILOVER_BEGIN_EVT: + l->state = LINK_FAILINGOVER; + break; + case LINK_PEER_RESET_EVT: + case LINK_RESET_EVT: + case LINK_FAILURE_EVT: + case LINK_SYNCH_BEGIN_EVT: + case LINK_FAILOVER_END_EVT: + break; + case LINK_SYNCH_END_EVT: + default: + goto illegal_evt; + } + break; + case LINK_ESTABLISHED: + switch (evt) { + case LINK_PEER_RESET_EVT: + l->state = LINK_PEER_RESET; + rc |= TIPC_LINK_DOWN_EVT; + break; + case LINK_FAILURE_EVT: + l->state = LINK_RESETTING; + rc |= TIPC_LINK_DOWN_EVT; + break; + case LINK_RESET_EVT: + l->state = LINK_RESET; + break; + case LINK_ESTABLISH_EVT: + break; + case LINK_SYNCH_BEGIN_EVT: + l->state = LINK_SYNCHING; + break; + case LINK_SYNCH_END_EVT: + case LINK_FAILOVER_BEGIN_EVT: + case LINK_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case LINK_SYNCHING: + switch (evt) { + case LINK_PEER_RESET_EVT: + l->state = LINK_PEER_RESET; + rc |= TIPC_LINK_DOWN_EVT; + break; + case LINK_FAILURE_EVT: + l->state = LINK_RESETTING; + rc |= TIPC_LINK_DOWN_EVT; + break; + case LINK_RESET_EVT: + l->state = LINK_RESET; + break; + case LINK_ESTABLISH_EVT: + case LINK_SYNCH_BEGIN_EVT: + break; + case LINK_SYNCH_END_EVT: + l->state = LINK_ESTABLISHED; + break; + case LINK_FAILOVER_BEGIN_EVT: + case LINK_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + default: + pr_err("Unknown FSM state %x in %s\n", l->state, l->name); } - - /* do all other link processing performed on a periodic basis */ - if (l_ptr->silent_intv_cnt || tipc_bclink_acks_missing(l_ptr->owner)) - link_state_event(l_ptr, SILENCE_EVT); - l_ptr->silent_intv_cnt++; - if (skb_queue_len(&l_ptr->backlogq)) - tipc_link_push_packets(l_ptr); - link_set_timer(l_ptr, l_ptr->keepalive_intv); - tipc_node_unlock(l_ptr->owner); - tipc_link_put(l_ptr); -} - -static void link_set_timer(struct tipc_link *link, unsigned long time) -{ - if (!mod_timer(&link->timer, jiffies + time)) - tipc_link_get(link); + return rc; +illegal_evt: + pr_err("Illegal FSM event %x in state %x on link %s\n", + evt, l->state, l->name); + return rc; } -/** - * tipc_link_create - create a new link - * @n_ptr: pointer to associated node - * @b_ptr: pointer to associated bearer - * @media_addr: media address to use when sending messages over link - * - * Returns pointer to link. +/* link_profile_stats - update statistical profiling of traffic */ -struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, - struct tipc_bearer *b_ptr, - const struct tipc_media_addr *media_addr) +static void link_profile_stats(struct tipc_link *l) { - struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); - struct tipc_link *l_ptr; + struct sk_buff *skb; struct tipc_msg *msg; - char *if_name; - char addr_string[16]; - u32 peer = n_ptr->addr; + int length; - if (n_ptr->link_cnt >= MAX_BEARERS) { - tipc_addr_string_fill(addr_string, n_ptr->addr); - pr_err("Cannot establish %uth link to %s. Max %u allowed.\n", - n_ptr->link_cnt, addr_string, MAX_BEARERS); - return NULL; - } + /* Update counters used in statistical profiling of send traffic */ + l->stats.accu_queue_sz += skb_queue_len(&l->transmq); + l->stats.queue_sz_counts++; - if (n_ptr->links[b_ptr->identity]) { - tipc_addr_string_fill(addr_string, n_ptr->addr); - pr_err("Attempt to establish second link on <%s> to %s\n", - b_ptr->name, addr_string); - return NULL; - } + skb = skb_peek(&l->transmq); + if (!skb) + return; + msg = buf_msg(skb); + length = msg_size(msg); - l_ptr = kzalloc(sizeof(*l_ptr), GFP_ATOMIC); - if (!l_ptr) { - pr_warn("Link creation failed, no memory\n"); - return NULL; + if (msg_user(msg) == MSG_FRAGMENTER) { + if (msg_type(msg) != FIRST_FRAGMENT) + return; + length = msg_size(msg_get_wrapped(msg)); } - kref_init(&l_ptr->ref); - l_ptr->addr = peer; - if_name = strchr(b_ptr->name, ':') + 1; - sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:unknown", - tipc_zone(tn->own_addr), tipc_cluster(tn->own_addr), - tipc_node(tn->own_addr), - if_name, - tipc_zone(peer), tipc_cluster(peer), tipc_node(peer)); - /* note: peer i/f name is updated by reset/activate message */ - memcpy(&l_ptr->media_addr, media_addr, sizeof(*media_addr)); - l_ptr->owner = n_ptr; - l_ptr->peer_session = INVALID_SESSION; - l_ptr->bearer_id = b_ptr->identity; - link_set_supervision_props(l_ptr, b_ptr->tolerance); - l_ptr->state = RESET_UNKNOWN; - - l_ptr->pmsg = (struct tipc_msg *)&l_ptr->proto_msg; - msg = l_ptr->pmsg; - tipc_msg_init(tn->own_addr, msg, LINK_PROTOCOL, RESET_MSG, INT_H_SIZE, - l_ptr->addr); - msg_set_size(msg, sizeof(l_ptr->proto_msg)); - msg_set_session(msg, (tn->random & 0xffff)); - msg_set_bearer_id(msg, b_ptr->identity); - strcpy((char *)msg_data(msg), if_name); - l_ptr->net_plane = b_ptr->net_plane; - l_ptr->advertised_mtu = b_ptr->mtu; - l_ptr->mtu = l_ptr->advertised_mtu; - l_ptr->priority = b_ptr->priority; - tipc_link_set_queue_limits(l_ptr, b_ptr->window); - l_ptr->snd_nxt = 1; - __skb_queue_head_init(&l_ptr->transmq); - __skb_queue_head_init(&l_ptr->backlogq); - __skb_queue_head_init(&l_ptr->deferdq); - skb_queue_head_init(&l_ptr->wakeupq); - skb_queue_head_init(&l_ptr->inputq); - skb_queue_head_init(&l_ptr->namedq); - link_reset_statistics(l_ptr); - tipc_node_attach_link(n_ptr, l_ptr); - setup_timer(&l_ptr->timer, link_timeout, (unsigned long)l_ptr); - link_state_event(l_ptr, STARTING_EVT); - - return l_ptr; + l->stats.msg_lengths_total += length; + l->stats.msg_length_counts++; + if (length <= 64) + l->stats.msg_length_profile[0]++; + else if (length <= 256) + l->stats.msg_length_profile[1]++; + else if (length <= 1024) + l->stats.msg_length_profile[2]++; + else if (length <= 4096) + l->stats.msg_length_profile[3]++; + else if (length <= 16384) + l->stats.msg_length_profile[4]++; + else if (length <= 32768) + l->stats.msg_length_profile[5]++; + else + l->stats.msg_length_profile[6]++; } -/** - * tipc_link_delete - Delete a link - * @l: link to be deleted +/* tipc_link_timeout - perform periodic task as instructed from node timeout */ -void tipc_link_delete(struct tipc_link *l) +int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq) { - tipc_link_reset(l); - if (del_timer(&l->timer)) - tipc_link_put(l); - l->flags |= LINK_STOPPED; - /* Delete link now, or when timer is finished: */ - tipc_link_reset_fragments(l); - tipc_node_detach_link(l->owner, l); - tipc_link_put(l); -} + int rc = 0; + int mtyp = STATE_MSG; + bool xmit = false; + bool prb = false; + + link_profile_stats(l); + + switch (l->state) { + case LINK_ESTABLISHED: + case LINK_SYNCHING: + if (!l->silent_intv_cnt) { + if (tipc_bclink_acks_missing(l->owner)) + xmit = true; + } else if (l->silent_intv_cnt <= l->abort_limit) { + xmit = true; + prb = true; + } else { + rc |= tipc_link_fsm_evt(l, LINK_FAILURE_EVT); + } + l->silent_intv_cnt++; + break; + case LINK_RESET: + xmit = true; + mtyp = RESET_MSG; + break; + case LINK_ESTABLISHING: + xmit = true; + mtyp = ACTIVATE_MSG; + break; + case LINK_PEER_RESET: + case LINK_RESETTING: + case LINK_FAILINGOVER: + break; + default: + break; + } -void tipc_link_delete_list(struct net *net, unsigned int bearer_id) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct tipc_link *link; - struct tipc_node *node; + if (xmit) + tipc_link_build_proto_msg(l, mtyp, prb, 0, 0, 0, xmitq); - rcu_read_lock(); - list_for_each_entry_rcu(node, &tn->node_list, list) { - tipc_node_lock(node); - link = node->links[bearer_id]; - if (link) - tipc_link_delete(link); - tipc_node_unlock(node); - } - rcu_read_unlock(); + return rc; } /** @@ -334,7 +490,7 @@ void tipc_link_delete_list(struct net *net, unsigned int bearer_id) * @link: congested link * @list: message that was attempted sent * Create pseudo msg to send back to user when congestion abates - * Only consumes message if there is an error + * Does not consume buffer list */ static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) { @@ -347,8 +503,7 @@ static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) /* This really cannot happen... */ if (unlikely(imp > TIPC_CRITICAL_IMPORTANCE)) { pr_warn("%s<%s>, send queue full", link_rst_msg, link->name); - tipc_link_reset(link); - goto err; + return -ENOBUFS; } /* Non-blocking sender: */ if (TIPC_SKB_CB(skb_peek(list))->wakeup_pending) @@ -358,15 +513,12 @@ static int link_schedule_user(struct tipc_link *link, struct sk_buff_head *list) skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, addr, addr, oport, 0, 0); if (!skb) - goto err; + return -ENOBUFS; TIPC_SKB_CB(skb)->chain_sz = skb_queue_len(list); TIPC_SKB_CB(skb)->chain_imp = imp; skb_queue_tail(&link->wakeupq, skb); link->stats.link_congs++; return -ELINKCONG; -err: - __skb_queue_purge(list); - return -ENOBUFS; } /** @@ -388,9 +540,7 @@ void link_prepare_wakeup(struct tipc_link *l) if ((pnd[imp] + l->backlog[imp].len) >= lim) break; skb_unlink(skb, &l->wakeupq); - skb_queue_tail(&l->inputq, skb); - l->owner->inputq = &l->inputq; - l->owner->action_flags |= TIPC_MSG_EVT; + skb_queue_tail(l->inputq, skb); } } @@ -426,208 +576,36 @@ void tipc_link_purge_queues(struct tipc_link *l_ptr) tipc_link_reset_fragments(l_ptr); } -void tipc_link_reset(struct tipc_link *l_ptr) +void tipc_link_reset(struct tipc_link *l) { - u32 prev_state = l_ptr->state; - int was_active_link = tipc_link_is_active(l_ptr); - struct tipc_node *owner = l_ptr->owner; - struct tipc_link *pl = tipc_parallel_link(l_ptr); - - msg_set_session(l_ptr->pmsg, ((msg_session(l_ptr->pmsg) + 1) & 0xffff)); + tipc_link_fsm_evt(l, LINK_RESET_EVT); /* Link is down, accept any session */ - l_ptr->peer_session = INVALID_SESSION; - - /* Prepare for renewed mtu size negotiation */ - l_ptr->mtu = l_ptr->advertised_mtu; - - l_ptr->state = RESET_UNKNOWN; + l->peer_session = WILDCARD_SESSION; - if ((prev_state == RESET_UNKNOWN) || (prev_state == RESET_RESET)) - return; - - tipc_node_link_down(l_ptr->owner, l_ptr); - tipc_bearer_remove_dest(owner->net, l_ptr->bearer_id, l_ptr->addr); + /* If peer is up, it only accepts an incremented session number */ + msg_set_session(l->pmsg, msg_session(l->pmsg) + 1); - if (was_active_link && tipc_node_is_up(l_ptr->owner) && (pl != l_ptr)) { - l_ptr->flags |= LINK_FAILINGOVER; - l_ptr->failover_checkpt = l_ptr->rcv_nxt; - pl->failover_pkts = FIRST_FAILOVER; - pl->failover_checkpt = l_ptr->rcv_nxt; - pl->failover_skb = l_ptr->reasm_buf; - } else { - kfree_skb(l_ptr->reasm_buf); - } - /* Clean up all queues, except inputq: */ - __skb_queue_purge(&l_ptr->transmq); - __skb_queue_purge(&l_ptr->deferdq); - if (!owner->inputq) - owner->inputq = &l_ptr->inputq; - skb_queue_splice_init(&l_ptr->wakeupq, owner->inputq); - if (!skb_queue_empty(owner->inputq)) - owner->action_flags |= TIPC_MSG_EVT; - tipc_link_purge_backlog(l_ptr); - l_ptr->reasm_buf = NULL; - l_ptr->rcv_unacked = 0; - l_ptr->snd_nxt = 1; - l_ptr->silent_intv_cnt = 0; - l_ptr->stale_count = 0; - link_reset_statistics(l_ptr); -} - -static void link_activate(struct tipc_link *link) -{ - struct tipc_node *node = link->owner; - - link->rcv_nxt = 1; - link->stats.recv_info = 1; - link->silent_intv_cnt = 0; - tipc_node_link_up(node, link); - tipc_bearer_add_dest(node->net, link->bearer_id, link->addr); -} - -/** - * link_state_event - link finite state machine - * @l_ptr: pointer to link - * @event: state machine event to process - */ -static void link_state_event(struct tipc_link *l_ptr, unsigned int event) -{ - struct tipc_link *other; - unsigned long timer_intv = l_ptr->keepalive_intv; - - if (l_ptr->flags & LINK_STOPPED) - return; - - if (!(l_ptr->flags & LINK_STARTED) && (event != STARTING_EVT)) - return; /* Not yet. */ - - if (l_ptr->flags & LINK_FAILINGOVER) - return; - - switch (l_ptr->state) { - case WORKING_WORKING: - switch (event) { - case TRAFFIC_MSG_EVT: - case ACTIVATE_MSG: - l_ptr->silent_intv_cnt = 0; - break; - case SILENCE_EVT: - if (!l_ptr->silent_intv_cnt) { - if (tipc_bclink_acks_missing(l_ptr->owner)) - tipc_link_proto_xmit(l_ptr, STATE_MSG, - 0, 0, 0, 0); - break; - } - l_ptr->state = WORKING_UNKNOWN; - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - break; - case RESET_MSG: - pr_debug("%s<%s>, requested by peer\n", - link_rst_msg, l_ptr->name); - tipc_link_reset(l_ptr); - l_ptr->state = RESET_RESET; - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0); - break; - default: - pr_debug("%s%u in WW state\n", link_unk_evt, event); - } - break; - case WORKING_UNKNOWN: - switch (event) { - case TRAFFIC_MSG_EVT: - case ACTIVATE_MSG: - l_ptr->state = WORKING_WORKING; - l_ptr->silent_intv_cnt = 0; - break; - case RESET_MSG: - pr_debug("%s<%s>, requested by peer while probing\n", - link_rst_msg, l_ptr->name); - tipc_link_reset(l_ptr); - l_ptr->state = RESET_RESET; - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0); - break; - case SILENCE_EVT: - if (!l_ptr->silent_intv_cnt) { - l_ptr->state = WORKING_WORKING; - if (tipc_bclink_acks_missing(l_ptr->owner)) - tipc_link_proto_xmit(l_ptr, STATE_MSG, - 0, 0, 0, 0); - } else if (l_ptr->silent_intv_cnt < - l_ptr->abort_limit) { - tipc_link_proto_xmit(l_ptr, STATE_MSG, - 1, 0, 0, 0); - } else { /* Link has failed */ - pr_debug("%s<%s>, peer not responding\n", - link_rst_msg, l_ptr->name); - tipc_link_reset(l_ptr); - l_ptr->state = RESET_UNKNOWN; - tipc_link_proto_xmit(l_ptr, RESET_MSG, - 0, 0, 0, 0); - } - break; - default: - pr_err("%s%u in WU state\n", link_unk_evt, event); - } - break; - case RESET_UNKNOWN: - switch (event) { - case TRAFFIC_MSG_EVT: - break; - case ACTIVATE_MSG: - other = l_ptr->owner->active_links[0]; - if (other && link_working_unknown(other)) - break; - l_ptr->state = WORKING_WORKING; - link_activate(l_ptr); - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - if (l_ptr->owner->working_links == 1) - tipc_link_sync_xmit(l_ptr); - break; - case RESET_MSG: - l_ptr->state = RESET_RESET; - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 1, 0, 0, 0); - break; - case STARTING_EVT: - l_ptr->flags |= LINK_STARTED; - link_set_timer(l_ptr, timer_intv); - break; - case SILENCE_EVT: - tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0); - break; - default: - pr_err("%s%u in RU state\n", link_unk_evt, event); - } - break; - case RESET_RESET: - switch (event) { - case TRAFFIC_MSG_EVT: - case ACTIVATE_MSG: - other = l_ptr->owner->active_links[0]; - if (other && link_working_unknown(other)) - break; - l_ptr->state = WORKING_WORKING; - link_activate(l_ptr); - tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0); - if (l_ptr->owner->working_links == 1) - tipc_link_sync_xmit(l_ptr); - break; - case RESET_MSG: - break; - case SILENCE_EVT: - tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, - 0, 0, 0, 0); - break; - default: - pr_err("%s%u in RR state\n", link_unk_evt, event); - } - break; - default: - pr_err("Unknown link state %u/%u\n", l_ptr->state, event); - } + /* Prepare for renewed mtu size negotiation */ + l->mtu = l->advertised_mtu; + + /* Clean up all queues: */ + __skb_queue_purge(&l->transmq); + __skb_queue_purge(&l->deferdq); + skb_queue_splice_init(&l->wakeupq, l->inputq); + + tipc_link_purge_backlog(l); + kfree_skb(l->reasm_buf); + kfree_skb(l->failover_reasm_skb); + l->reasm_buf = NULL; + l->failover_reasm_skb = NULL; + l->rcv_unacked = 0; + l->snd_nxt = 1; + l->rcv_nxt = 1; + l->silent_intv_cnt = 0; + l->stats.recv_info = 0; + l->stale_count = 0; + link_reset_statistics(l); } /** @@ -635,8 +613,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) * @link: link to use * @list: chain of buffers containing message * - * Consumes the buffer chain, except when returning -ELINKCONG, - * since the caller then may want to make more send attempts. + * Consumes the buffer chain, except when returning an error code, * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted */ @@ -650,7 +627,7 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, u16 ack = mod(link->rcv_nxt - 1); u16 seqno = link->snd_nxt; u16 bc_last_in = link->owner->bclink.last_in; - struct tipc_media_addr *addr = &link->media_addr; + struct tipc_media_addr *addr = link->media_addr; struct sk_buff_head *transmq = &link->transmq; struct sk_buff_head *backlogq = &link->backlogq; struct sk_buff *skb, *bskb; @@ -660,10 +637,9 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, if (unlikely(link->backlog[i].len >= link->backlog[i].limit)) return link_schedule_user(link, list); } - if (unlikely(msg_size(msg) > mtu)) { - __skb_queue_purge(list); + if (unlikely(msg_size(msg) > mtu)) return -EMSGSIZE; - } + /* Prepare each packet for sending, and add to relevant queue: */ while (skb_queue_len(list)) { skb = skb_peek(list); @@ -700,101 +676,76 @@ int __tipc_link_xmit(struct net *net, struct tipc_link *link, return 0; } -static void skb2list(struct sk_buff *skb, struct sk_buff_head *list) -{ - skb_queue_head_init(list); - __skb_queue_tail(list, skb); -} - -static int __tipc_link_xmit_skb(struct tipc_link *link, struct sk_buff *skb) -{ - struct sk_buff_head head; - - skb2list(skb, &head); - return __tipc_link_xmit(link->owner->net, link, &head); -} - -/* tipc_link_xmit_skb(): send single buffer to destination - * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE - * messages, which will not be rejected - * The only exception is datagram messages rerouted after secondary - * lookup, which are rare and safe to dispose of anyway. - * TODO: Return real return value, and let callers use - * tipc_wait_for_sendpkt() where applicable - */ -int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, - u32 selector) -{ - struct sk_buff_head head; - int rc; - - skb2list(skb, &head); - rc = tipc_link_xmit(net, &head, dnode, selector); - if (rc == -ELINKCONG) - kfree_skb(skb); - return 0; -} - /** - * tipc_link_xmit() is the general link level function for message sending - * @net: the applicable net namespace + * tipc_link_xmit(): enqueue buffer list according to queue situation + * @link: link to use * @list: chain of buffers containing message - * @dsz: amount of user data to be sent - * @dnode: address of destination node - * @selector: a number used for deterministic link selection - * Consumes the buffer chain, except when returning -ELINKCONG - * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE + * @xmitq: returned list of packets to be sent by caller + * + * Consumes the buffer chain, except when returning -ELINKCONG, + * since the caller then may want to make more send attempts. + * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS + * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted */ -int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, - u32 selector) +int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, + struct sk_buff_head *xmitq) { - struct tipc_link *link = NULL; - struct tipc_node *node; - int rc = -EHOSTUNREACH; + struct tipc_msg *hdr = buf_msg(skb_peek(list)); + unsigned int maxwin = l->window; + unsigned int i, imp = msg_importance(hdr); + unsigned int mtu = l->mtu; + u16 ack = l->rcv_nxt - 1; + u16 seqno = l->snd_nxt; + u16 bc_last_in = l->owner->bclink.last_in; + struct sk_buff_head *transmq = &l->transmq; + struct sk_buff_head *backlogq = &l->backlogq; + struct sk_buff *skb, *_skb, *bskb; - node = tipc_node_find(net, dnode); - if (node) { - tipc_node_lock(node); - link = node->active_links[selector & 1]; - if (link) - rc = __tipc_link_xmit(net, link, list); - tipc_node_unlock(node); - tipc_node_put(node); - } - if (link) - return rc; - - if (likely(in_own_node(net, dnode))) { - tipc_sk_rcv(net, list); - return 0; + /* Match msg importance against this and all higher backlog limits: */ + for (i = imp; i <= TIPC_SYSTEM_IMPORTANCE; i++) { + if (unlikely(l->backlog[i].len >= l->backlog[i].limit)) + return link_schedule_user(l, list); } + if (unlikely(msg_size(hdr) > mtu)) + return -EMSGSIZE; - __skb_queue_purge(list); - return rc; -} - -/* - * tipc_link_sync_xmit - synchronize broadcast link endpoints. - * - * Give a newly added peer node the sequence number where it should - * start receiving and acking broadcast packets. - * - * Called with node locked - */ -static void tipc_link_sync_xmit(struct tipc_link *link) -{ - struct sk_buff *skb; - struct tipc_msg *msg; - - skb = tipc_buf_acquire(INT_H_SIZE); - if (!skb) - return; + /* Prepare each packet for sending, and add to relevant queue: */ + while (skb_queue_len(list)) { + skb = skb_peek(list); + hdr = buf_msg(skb); + msg_set_seqno(hdr, seqno); + msg_set_ack(hdr, ack); + msg_set_bcast_ack(hdr, bc_last_in); - msg = buf_msg(skb); - tipc_msg_init(link_own_addr(link), msg, BCAST_PROTOCOL, STATE_MSG, - INT_H_SIZE, link->addr); - msg_set_last_bcast(msg, link->owner->bclink.acked); - __tipc_link_xmit_skb(link, skb); + if (likely(skb_queue_len(transmq) < maxwin)) { + _skb = skb_clone(skb, GFP_ATOMIC); + if (!_skb) + return -ENOBUFS; + __skb_dequeue(list); + __skb_queue_tail(transmq, skb); + __skb_queue_tail(xmitq, _skb); + l->rcv_unacked = 0; + seqno++; + continue; + } + if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) { + kfree_skb(__skb_dequeue(list)); + l->stats.sent_bundled++; + continue; + } + if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) { + kfree_skb(__skb_dequeue(list)); + __skb_queue_tail(backlogq, bskb); + l->backlog[msg_importance(buf_msg(bskb))].len++; + l->stats.sent_bundled++; + l->stats.sent_bundles++; + continue; + } + l->backlog[imp].len += skb_queue_len(list); + skb_queue_splice_tail_init(list, backlogq); + } + l->snd_nxt = seqno; + return 0; } /* @@ -842,29 +793,37 @@ void tipc_link_push_packets(struct tipc_link *link) link->rcv_unacked = 0; __skb_queue_tail(&link->transmq, skb); tipc_bearer_send(link->owner->net, link->bearer_id, - skb, &link->media_addr); + skb, link->media_addr); } link->snd_nxt = seqno; } -void tipc_link_reset_all(struct tipc_node *node) +void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) { - char addr_string[16]; - u32 i; - - tipc_node_lock(node); + struct sk_buff *skb, *_skb; + struct tipc_msg *hdr; + u16 seqno = l->snd_nxt; + u16 ack = l->rcv_nxt - 1; - pr_warn("Resetting all links to %s\n", - tipc_addr_string_fill(addr_string, node->addr)); - - for (i = 0; i < MAX_BEARERS; i++) { - if (node->links[i]) { - link_print(node->links[i], "Resetting link\n"); - tipc_link_reset(node->links[i]); - } + while (skb_queue_len(&l->transmq) < l->window) { + skb = skb_peek(&l->backlogq); + if (!skb) + break; + _skb = skb_clone(skb, GFP_ATOMIC); + if (!_skb) + break; + __skb_dequeue(&l->backlogq); + hdr = buf_msg(skb); + l->backlog[msg_importance(hdr)].len--; + __skb_queue_tail(&l->transmq, skb); + __skb_queue_tail(xmitq, _skb); + msg_set_ack(hdr, ack); + msg_set_seqno(hdr, seqno); + msg_set_bcast_ack(hdr, l->owner->bclink.last_in); + l->rcv_unacked = 0; + seqno++; } - - tipc_node_unlock(node); + l->snd_nxt = seqno; } static void link_retransmit_failure(struct tipc_link *l_ptr, @@ -877,9 +836,12 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, if (l_ptr->addr) { /* Handle failure on standard link */ - link_print(l_ptr, "Resetting link\n"); - tipc_link_reset(l_ptr); - + link_print(l_ptr, "Resetting link "); + pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n", + msg_user(msg), msg_type(msg), msg_size(msg), + msg_errcode(msg)); + pr_info("sqno %u, prev: %x, src: %x\n", + msg_seqno(msg), msg_prevnode(msg), msg_orignode(msg)); } else { /* Handle failure on broadcast link */ struct tipc_node *n_ptr; @@ -934,191 +896,45 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *skb, msg_set_ack(msg, mod(l_ptr->rcv_nxt - 1)); msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, skb, - &l_ptr->media_addr); + l_ptr->media_addr); retransmits--; l_ptr->stats.retransmitted++; } } -/* link_synch(): check if all packets arrived before the synch - * point have been consumed - * Returns true if the parallel links are synched, otherwise false - */ -static bool link_synch(struct tipc_link *l) +static int tipc_link_retransm(struct tipc_link *l, int retransm, + struct sk_buff_head *xmitq) { - unsigned int post_synch; - struct tipc_link *pl; + struct sk_buff *_skb, *skb = skb_peek(&l->transmq); + struct tipc_msg *hdr; - pl = tipc_parallel_link(l); - if (pl == l) - goto synched; - - /* Was last pre-synch packet added to input queue ? */ - if (less_eq(pl->rcv_nxt, l->synch_point)) - return false; - - /* Is it still in the input queue ? */ - post_synch = mod(pl->rcv_nxt - l->synch_point) - 1; - if (skb_queue_len(&pl->inputq) > post_synch) - return false; -synched: - l->flags &= ~LINK_SYNCHING; - return true; -} - -static void link_retrieve_defq(struct tipc_link *link, - struct sk_buff_head *list) -{ - u16 seq_no; - - if (skb_queue_empty(&link->deferdq)) - return; - - seq_no = buf_seqno(skb_peek(&link->deferdq)); - if (seq_no == link->rcv_nxt) - skb_queue_splice_tail_init(&link->deferdq, list); -} - -/** - * tipc_rcv - process TIPC packets/messages arriving from off-node - * @net: the applicable net namespace - * @skb: TIPC packet - * @b_ptr: pointer to bearer message arrived on - * - * Invoked with no locks held. Bearer pointer must point to a valid bearer - * structure (i.e. cannot be NULL), but bearer can be inactive. - */ -void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b_ptr) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct sk_buff_head head; - struct tipc_node *n_ptr; - struct tipc_link *l_ptr; - struct sk_buff *skb1, *tmp; - struct tipc_msg *msg; - u16 seq_no; - u16 ackd; - u32 released; - - skb2list(skb, &head); - - while ((skb = __skb_dequeue(&head))) { - /* Ensure message is well-formed */ - if (unlikely(!tipc_msg_validate(skb))) - goto discard; - - /* Handle arrival of a non-unicast link message */ - msg = buf_msg(skb); - if (unlikely(msg_non_seq(msg))) { - if (msg_user(msg) == LINK_CONFIG) - tipc_disc_rcv(net, skb, b_ptr); - else - tipc_bclink_rcv(net, skb); - continue; - } - - /* Discard unicast link messages destined for another node */ - if (unlikely(!msg_short(msg) && - (msg_destnode(msg) != tn->own_addr))) - goto discard; - - /* Locate neighboring node that sent message */ - n_ptr = tipc_node_find(net, msg_prevnode(msg)); - if (unlikely(!n_ptr)) - goto discard; - - tipc_node_lock(n_ptr); - /* Locate unicast link endpoint that should handle message */ - l_ptr = n_ptr->links[b_ptr->identity]; - if (unlikely(!l_ptr)) - goto unlock; - - /* Verify that communication with node is currently allowed */ - if ((n_ptr->action_flags & TIPC_WAIT_PEER_LINKS_DOWN) && - msg_user(msg) == LINK_PROTOCOL && - (msg_type(msg) == RESET_MSG || - msg_type(msg) == ACTIVATE_MSG) && - !msg_redundant_link(msg)) - n_ptr->action_flags &= ~TIPC_WAIT_PEER_LINKS_DOWN; - - if (tipc_node_blocked(n_ptr)) - goto unlock; - - /* Validate message sequence number info */ - seq_no = msg_seqno(msg); - ackd = msg_ack(msg); - - /* Release acked messages */ - if (unlikely(n_ptr->bclink.acked != msg_bcast_ack(msg))) - tipc_bclink_acknowledge(n_ptr, msg_bcast_ack(msg)); - - released = 0; - skb_queue_walk_safe(&l_ptr->transmq, skb1, tmp) { - if (more(buf_seqno(skb1), ackd)) - break; - __skb_unlink(skb1, &l_ptr->transmq); - kfree_skb(skb1); - released = 1; - } - - /* Try sending any messages link endpoint has pending */ - if (unlikely(skb_queue_len(&l_ptr->backlogq))) - tipc_link_push_packets(l_ptr); - - if (released && !skb_queue_empty(&l_ptr->wakeupq)) - link_prepare_wakeup(l_ptr); - - /* Process the incoming packet */ - if (unlikely(!link_working_working(l_ptr))) { - if (msg_user(msg) == LINK_PROTOCOL) { - tipc_link_proto_rcv(l_ptr, skb); - link_retrieve_defq(l_ptr, &head); - skb = NULL; - goto unlock; - } - - /* Traffic message. Conditionally activate link */ - link_state_event(l_ptr, TRAFFIC_MSG_EVT); - - if (link_working_working(l_ptr)) { - /* Re-insert buffer in front of queue */ - __skb_queue_head(&head, skb); - skb = NULL; - goto unlock; - } - goto unlock; - } - - /* Link is now in state WORKING_WORKING */ - if (unlikely(seq_no != l_ptr->rcv_nxt)) { - link_handle_out_of_seq_msg(l_ptr, skb); - link_retrieve_defq(l_ptr, &head); - skb = NULL; - goto unlock; - } - l_ptr->silent_intv_cnt = 0; + if (!skb) + return 0; - /* Synchronize with parallel link if applicable */ - if (unlikely((l_ptr->flags & LINK_SYNCHING) && !msg_dup(msg))) { - if (!link_synch(l_ptr)) - goto unlock; - } - l_ptr->rcv_nxt++; - if (unlikely(!skb_queue_empty(&l_ptr->deferdq))) - link_retrieve_defq(l_ptr, &head); - if (unlikely(++l_ptr->rcv_unacked >= TIPC_MIN_LINK_WIN)) { - l_ptr->stats.sent_acks++; - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0); - } - tipc_link_input(l_ptr, skb); - skb = NULL; -unlock: - tipc_node_unlock(n_ptr); - tipc_node_put(n_ptr); -discard: - if (unlikely(skb)) - kfree_skb(skb); + /* Detect repeated retransmit failures on same packet */ + if (likely(l->last_retransm != buf_seqno(skb))) { + l->last_retransm = buf_seqno(skb); + l->stale_count = 1; + } else if (++l->stale_count > 100) { + link_retransmit_failure(l, skb); + return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); + } + skb_queue_walk(&l->transmq, skb) { + if (!retransm) + return 0; + hdr = buf_msg(skb); + _skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC); + if (!_skb) + return 0; + hdr = buf_msg(_skb); + msg_set_ack(hdr, l->rcv_nxt - 1); + msg_set_bcast_ack(hdr, l->owner->bclink.last_in); + _skb->priority = TC_PRIO_CONTROL; + __skb_queue_tail(xmitq, _skb); + retransm--; + l->stats.retransmitted++; } + return 0; } /* tipc_data_input - deliver data and name distr msgs to upper layer @@ -1126,29 +942,22 @@ discard: * Consumes buffer if message is of right type * Node lock must be held */ -static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb) +static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb, + struct sk_buff_head *inputq) { struct tipc_node *node = link->owner; - struct tipc_msg *msg = buf_msg(skb); - u32 dport = msg_destport(msg); - switch (msg_user(msg)) { + switch (msg_user(buf_msg(skb))) { case TIPC_LOW_IMPORTANCE: case TIPC_MEDIUM_IMPORTANCE: case TIPC_HIGH_IMPORTANCE: case TIPC_CRITICAL_IMPORTANCE: case CONN_MANAGER: - if (tipc_skb_queue_tail(&link->inputq, skb, dport)) { - node->inputq = &link->inputq; - node->action_flags |= TIPC_MSG_EVT; - } + __skb_queue_tail(inputq, skb); return true; case NAME_DISTRIBUTOR: node->bclink.recv_permitted = true; - node->namedq = &link->namedq; - skb_queue_tail(&link->namedq, skb); - if (skb_queue_len(&link->namedq) == 1) - node->action_flags |= TIPC_NAMED_MSG_EVT; + skb_queue_tail(link->namedq, skb); return true; case MSG_BUNDLER: case TUNNEL_PROTOCOL: @@ -1165,54 +974,160 @@ static bool tipc_data_input(struct tipc_link *link, struct sk_buff *skb) /* tipc_link_input - process packet that has passed link protocol check * * Consumes buffer - * Node lock must be held */ -static void tipc_link_input(struct tipc_link *link, struct sk_buff *skb) +static int tipc_link_input(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *inputq) { - struct tipc_node *node = link->owner; - struct tipc_msg *msg = buf_msg(skb); + struct tipc_node *node = l->owner; + struct tipc_msg *hdr = buf_msg(skb); + struct sk_buff **reasm_skb = &l->reasm_buf; struct sk_buff *iskb; + int usr = msg_user(hdr); + int rc = 0; int pos = 0; + int ipos = 0; - if (likely(tipc_data_input(link, skb))) - return; + if (unlikely(usr == TUNNEL_PROTOCOL)) { + if (msg_type(hdr) == SYNCH_MSG) { + __skb_queue_purge(&l->deferdq); + goto drop; + } + if (!tipc_msg_extract(skb, &iskb, &ipos)) + return rc; + kfree_skb(skb); + skb = iskb; + hdr = buf_msg(skb); + if (less(msg_seqno(hdr), l->drop_point)) + goto drop; + if (tipc_data_input(l, skb, inputq)) + return rc; + usr = msg_user(hdr); + reasm_skb = &l->failover_reasm_skb; + } - switch (msg_user(msg)) { - case TUNNEL_PROTOCOL: - if (msg_dup(msg)) { - link->flags |= LINK_SYNCHING; - link->synch_point = msg_seqno(msg_get_wrapped(msg)); - kfree_skb(skb); - break; + if (usr == MSG_BUNDLER) { + l->stats.recv_bundles++; + l->stats.recv_bundled += msg_msgcnt(hdr); + while (tipc_msg_extract(skb, &iskb, &pos)) + tipc_data_input(l, iskb, inputq); + return 0; + } else if (usr == MSG_FRAGMENTER) { + l->stats.recv_fragments++; + if (tipc_buf_append(reasm_skb, &skb)) { + l->stats.recv_fragmented++; + tipc_data_input(l, skb, inputq); + } else if (!*reasm_skb) { + return tipc_link_fsm_evt(l, LINK_FAILURE_EVT); } - if (!tipc_link_failover_rcv(link, &skb)) - break; - if (msg_user(buf_msg(skb)) != MSG_BUNDLER) { - tipc_data_input(link, skb); + return 0; + } else if (usr == BCAST_PROTOCOL) { + tipc_link_sync_rcv(node, skb); + return 0; + } +drop: + kfree_skb(skb); + return 0; +} + +static bool tipc_link_release_pkts(struct tipc_link *l, u16 acked) +{ + bool released = false; + struct sk_buff *skb, *tmp; + + skb_queue_walk_safe(&l->transmq, skb, tmp) { + if (more(buf_seqno(skb), acked)) break; + __skb_unlink(skb, &l->transmq); + kfree_skb(skb); + released = true; + } + return released; +} + +/* tipc_link_rcv - process TIPC packets/messages arriving from off-node + * @link: the link that should handle the message + * @skb: TIPC packet + * @xmitq: queue to place packets to be sent after this call + */ +int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq) +{ + struct sk_buff_head *arrvq = &l->deferdq; + struct sk_buff_head tmpq; + struct tipc_msg *hdr; + u16 seqno, rcv_nxt; + int rc = 0; + + __skb_queue_head_init(&tmpq); + + if (unlikely(!__tipc_skb_queue_sorted(arrvq, skb))) { + if (!(skb_queue_len(arrvq) % TIPC_NACK_INTV)) + tipc_link_build_proto_msg(l, STATE_MSG, 0, + 0, 0, 0, xmitq); + return rc; + } + + while ((skb = skb_peek(arrvq))) { + hdr = buf_msg(skb); + + /* Verify and update link state */ + if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) { + __skb_dequeue(arrvq); + rc = tipc_link_proto_rcv(l, skb, xmitq); + continue; } - case MSG_BUNDLER: - link->stats.recv_bundles++; - link->stats.recv_bundled += msg_msgcnt(msg); - while (tipc_msg_extract(skb, &iskb, &pos)) - tipc_data_input(link, iskb); - break; - case MSG_FRAGMENTER: - link->stats.recv_fragments++; - if (tipc_buf_append(&link->reasm_buf, &skb)) { - link->stats.recv_fragmented++; - tipc_data_input(link, skb); - } else if (!link->reasm_buf) { - tipc_link_reset(link); + if (unlikely(!link_is_up(l))) { + rc = tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); + if (!link_is_up(l)) { + kfree_skb(__skb_dequeue(arrvq)); + goto exit; + } } - break; - case BCAST_PROTOCOL: - tipc_link_sync_rcv(node, skb); - break; - default: - break; - }; + + l->silent_intv_cnt = 0; + + /* Forward queues and wake up waiting users */ + if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) { + tipc_link_advance_backlog(l, xmitq); + if (unlikely(!skb_queue_empty(&l->wakeupq))) + link_prepare_wakeup(l); + } + + /* Defer reception if there is a gap in the sequence */ + seqno = msg_seqno(hdr); + rcv_nxt = l->rcv_nxt; + if (unlikely(less(rcv_nxt, seqno))) { + l->stats.deferred_recv++; + goto exit; + } + + __skb_dequeue(arrvq); + + /* Drop if packet already received */ + if (unlikely(more(rcv_nxt, seqno))) { + l->stats.duplicates++; + kfree_skb(skb); + goto exit; + } + + /* Packet can be delivered */ + l->rcv_nxt++; + l->stats.recv_info++; + if (unlikely(!tipc_data_input(l, skb, &tmpq))) + rc = tipc_link_input(l, skb, &tmpq); + + /* Ack at regular intervals */ + if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) { + l->rcv_unacked = 0; + l->stats.sent_acks++; + tipc_link_build_proto_msg(l, STATE_MSG, + 0, 0, 0, 0, xmitq); + } + } +exit: + tipc_skb_queue_splice_tail(&tmpq, l->inputq); + return rc; } /** @@ -1255,458 +1170,249 @@ u32 tipc_link_defer_pkt(struct sk_buff_head *list, struct sk_buff *skb) } /* - * link_handle_out_of_seq_msg - handle arrival of out-of-sequence packet + * Send protocol message to the other endpoint. */ -static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, - struct sk_buff *buf) +void tipc_link_proto_xmit(struct tipc_link *l, u32 msg_typ, int probe_msg, + u32 gap, u32 tolerance, u32 priority) { - u32 seq_no = buf_seqno(buf); + struct sk_buff *skb = NULL; + struct sk_buff_head xmitq; - if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) { - tipc_link_proto_rcv(l_ptr, buf); + __skb_queue_head_init(&xmitq); + tipc_link_build_proto_msg(l, msg_typ, probe_msg, gap, + tolerance, priority, &xmitq); + skb = __skb_dequeue(&xmitq); + if (!skb) return; - } - - /* Record OOS packet arrival */ - l_ptr->silent_intv_cnt = 0; + tipc_bearer_send(l->owner->net, l->bearer_id, skb, l->media_addr); + l->rcv_unacked = 0; + kfree_skb(skb); +} - /* - * Discard packet if a duplicate; otherwise add it to deferred queue - * and notify peer of gap as per protocol specification - */ - if (less(seq_no, l_ptr->rcv_nxt)) { - l_ptr->stats.duplicates++; - kfree_skb(buf); +/* tipc_link_build_proto_msg: prepare link protocol message for transmission + */ +static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, + u16 rcvgap, int tolerance, int priority, + struct sk_buff_head *xmitq) +{ + struct sk_buff *skb = NULL; + struct tipc_msg *hdr = l->pmsg; + u16 snd_nxt = l->snd_nxt; + u16 rcv_nxt = l->rcv_nxt; + u16 rcv_last = rcv_nxt - 1; + int node_up = l->owner->bclink.recv_permitted; + + /* Don't send protocol message during reset or link failover */ + if (tipc_link_is_blocked(l)) return; - } - if (tipc_link_defer_pkt(&l_ptr->deferdq, buf)) { - l_ptr->stats.deferred_recv++; - if ((skb_queue_len(&l_ptr->deferdq) % TIPC_MIN_LINK_WIN) == 1) - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0); + msg_set_type(hdr, mtyp); + msg_set_net_plane(hdr, l->net_plane); + msg_set_bcast_ack(hdr, l->owner->bclink.last_in); + msg_set_last_bcast(hdr, tipc_bclink_get_last_sent(l->owner->net)); + msg_set_link_tolerance(hdr, tolerance); + msg_set_linkprio(hdr, priority); + msg_set_redundant_link(hdr, node_up); + msg_set_seq_gap(hdr, 0); + + /* Compatibility: created msg must not be in sequence with pkt flow */ + msg_set_seqno(hdr, snd_nxt + U16_MAX / 2); + + if (mtyp == STATE_MSG) { + if (!tipc_link_is_up(l)) + return; + msg_set_next_sent(hdr, snd_nxt); + + /* Override rcvgap if there are packets in deferred queue */ + if (!skb_queue_empty(&l->deferdq)) + rcvgap = buf_seqno(skb_peek(&l->deferdq)) - rcv_nxt; + if (rcvgap) { + msg_set_seq_gap(hdr, rcvgap); + l->stats.sent_nacks++; + } + msg_set_ack(hdr, rcv_last); + msg_set_probe(hdr, probe); + if (probe) + l->stats.sent_probes++; + l->stats.sent_states++; } else { - l_ptr->stats.duplicates++; + /* RESET_MSG or ACTIVATE_MSG */ + msg_set_max_pkt(hdr, l->advertised_mtu); + msg_set_ack(hdr, l->rcv_nxt - 1); + msg_set_next_sent(hdr, 1); } + skb = tipc_buf_acquire(msg_size(hdr)); + if (!skb) + return; + skb_copy_to_linear_data(skb, hdr, msg_size(hdr)); + skb->priority = TC_PRIO_CONTROL; + __skb_queue_tail(xmitq, skb); } -/* - * Send protocol message to the other endpoint. +/* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets + * with contents of the link's tranmsit and backlog queues. */ -void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, - u32 gap, u32 tolerance, u32 priority) +void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, + int mtyp, struct sk_buff_head *xmitq) { - struct sk_buff *buf = NULL; - struct tipc_msg *msg = l_ptr->pmsg; - u32 msg_size = sizeof(l_ptr->proto_msg); - int r_flag; - u16 last_rcv; - - /* Don't send protocol message during link failover */ - if (l_ptr->flags & LINK_FAILINGOVER) - return; + struct sk_buff *skb, *tnlskb; + struct tipc_msg *hdr, tnlhdr; + struct sk_buff_head *queue = &l->transmq; + struct sk_buff_head tmpxq, tnlq; + u16 pktlen, pktcnt, seqno = l->snd_nxt; - /* Abort non-RESET send if communication with node is prohibited */ - if ((tipc_node_blocked(l_ptr->owner)) && (msg_typ != RESET_MSG)) + if (!tnl) return; - /* Create protocol message with "out-of-sequence" sequence number */ - msg_set_type(msg, msg_typ); - msg_set_net_plane(msg, l_ptr->net_plane); - msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); - msg_set_last_bcast(msg, tipc_bclink_get_last_sent(l_ptr->owner->net)); - - if (msg_typ == STATE_MSG) { - u16 next_sent = l_ptr->snd_nxt; + skb_queue_head_init(&tnlq); + skb_queue_head_init(&tmpxq); - if (!tipc_link_is_up(l_ptr)) + /* At least one packet required for safe algorithm => add dummy */ + skb = tipc_msg_create(TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG, + BASIC_H_SIZE, 0, l->addr, link_own_addr(l), + 0, 0, TIPC_ERR_NO_PORT); + if (!skb) { + pr_warn("%sunable to create tunnel packet\n", link_co_err); + return; + } + skb_queue_tail(&tnlq, skb); + tipc_link_xmit(l, &tnlq, &tmpxq); + __skb_queue_purge(&tmpxq); + + /* Initialize reusable tunnel packet header */ + tipc_msg_init(link_own_addr(l), &tnlhdr, TUNNEL_PROTOCOL, + mtyp, INT_H_SIZE, l->addr); + pktcnt = skb_queue_len(&l->transmq) + skb_queue_len(&l->backlogq); + msg_set_msgcnt(&tnlhdr, pktcnt); + msg_set_bearer_id(&tnlhdr, l->peer_bearer_id); +tnl: + /* Wrap each packet into a tunnel packet */ + skb_queue_walk(queue, skb) { + hdr = buf_msg(skb); + if (queue == &l->backlogq) + msg_set_seqno(hdr, seqno++); + pktlen = msg_size(hdr); + msg_set_size(&tnlhdr, pktlen + INT_H_SIZE); + tnlskb = tipc_buf_acquire(pktlen + INT_H_SIZE); + if (!tnlskb) { + pr_warn("%sunable to send packet\n", link_co_err); return; - msg_set_next_sent(msg, next_sent); - if (!skb_queue_empty(&l_ptr->deferdq)) { - last_rcv = buf_seqno(skb_peek(&l_ptr->deferdq)); - gap = mod(last_rcv - l_ptr->rcv_nxt); } - msg_set_seq_gap(msg, gap); - if (gap) - l_ptr->stats.sent_nacks++; - msg_set_link_tolerance(msg, tolerance); - msg_set_linkprio(msg, priority); - msg_set_max_pkt(msg, l_ptr->mtu); - msg_set_ack(msg, mod(l_ptr->rcv_nxt - 1)); - msg_set_probe(msg, probe_msg != 0); - if (probe_msg) - l_ptr->stats.sent_probes++; - l_ptr->stats.sent_states++; - } else { /* RESET_MSG or ACTIVATE_MSG */ - msg_set_ack(msg, mod(l_ptr->failover_checkpt - 1)); - msg_set_seq_gap(msg, 0); - msg_set_next_sent(msg, 1); - msg_set_probe(msg, 0); - msg_set_link_tolerance(msg, l_ptr->tolerance); - msg_set_linkprio(msg, l_ptr->priority); - msg_set_max_pkt(msg, l_ptr->advertised_mtu); + skb_copy_to_linear_data(tnlskb, &tnlhdr, INT_H_SIZE); + skb_copy_to_linear_data_offset(tnlskb, INT_H_SIZE, hdr, pktlen); + __skb_queue_tail(&tnlq, tnlskb); + } + if (queue != &l->backlogq) { + queue = &l->backlogq; + goto tnl; } - r_flag = (l_ptr->owner->working_links > tipc_link_is_up(l_ptr)); - msg_set_redundant_link(msg, r_flag); - msg_set_linkprio(msg, l_ptr->priority); - msg_set_size(msg, msg_size); - - msg_set_seqno(msg, mod(l_ptr->snd_nxt + (0xffff / 2))); - - buf = tipc_buf_acquire(msg_size); - if (!buf) - return; + tipc_link_xmit(tnl, &tnlq, xmitq); - skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg)); - buf->priority = TC_PRIO_CONTROL; - tipc_bearer_send(l_ptr->owner->net, l_ptr->bearer_id, buf, - &l_ptr->media_addr); - l_ptr->rcv_unacked = 0; - kfree_skb(buf); + if (mtyp == FAILOVER_MSG) { + tnl->drop_point = l->rcv_nxt; + tnl->failover_reasm_skb = l->reasm_buf; + l->reasm_buf = NULL; + } } -/* - * Receive protocol message : +/* tipc_link_proto_rcv(): receive link level protocol message : * Note that network plane id propagates through the network, and may - * change at any time. The node with lowest address rules + * change at any time. The node with lowest numerical id determines + * network plane */ -static void tipc_link_proto_rcv(struct tipc_link *l_ptr, - struct sk_buff *buf) +static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq) { - u32 rec_gap = 0; - u32 msg_tol; - struct tipc_msg *msg = buf_msg(buf); + struct tipc_msg *hdr = buf_msg(skb); + u16 rcvgap = 0; + u16 nacked_gap = msg_seq_gap(hdr); + u16 peers_snd_nxt = msg_next_sent(hdr); + u16 peers_tol = msg_link_tolerance(hdr); + u16 peers_prio = msg_linkprio(hdr); + char *if_name; + int rc = 0; - if (l_ptr->flags & LINK_FAILINGOVER) + if (tipc_link_is_blocked(l)) goto exit; - if (l_ptr->net_plane != msg_net_plane(msg)) - if (link_own_addr(l_ptr) > msg_prevnode(msg)) - l_ptr->net_plane = msg_net_plane(msg); - - switch (msg_type(msg)) { + if (link_own_addr(l) > msg_prevnode(hdr)) + l->net_plane = msg_net_plane(hdr); + switch (msg_type(hdr)) { case RESET_MSG: - if (!link_working_unknown(l_ptr) && - (l_ptr->peer_session != INVALID_SESSION)) { - if (less_eq(msg_session(msg), l_ptr->peer_session)) - break; /* duplicate or old reset: ignore */ - } - - if (!msg_redundant_link(msg) && (link_working_working(l_ptr) || - link_working_unknown(l_ptr))) { - /* - * peer has lost contact -- don't allow peer's links - * to reactivate before we recognize loss & clean up - */ - l_ptr->owner->action_flags |= TIPC_WAIT_OWN_LINKS_DOWN; - } - - link_state_event(l_ptr, RESET_MSG); + /* Ignore duplicate RESET with old session number */ + if ((less_eq(msg_session(hdr), l->peer_session)) && + (l->peer_session != WILDCARD_SESSION)) + break; /* fall thru' */ - case ACTIVATE_MSG: - /* Update link settings according other endpoint's values */ - strcpy((strrchr(l_ptr->name, ':') + 1), (char *)msg_data(msg)); - msg_tol = msg_link_tolerance(msg); - if (msg_tol > l_ptr->tolerance) - link_set_supervision_props(l_ptr, msg_tol); - - if (msg_linkprio(msg) > l_ptr->priority) - l_ptr->priority = msg_linkprio(msg); - - if (l_ptr->mtu > msg_max_pkt(msg)) - l_ptr->mtu = msg_max_pkt(msg); - - /* Synchronize broadcast link info, if not done previously */ - if (!tipc_node_is_up(l_ptr->owner)) { - l_ptr->owner->bclink.last_sent = - l_ptr->owner->bclink.last_in = - msg_last_bcast(msg); - l_ptr->owner->bclink.oos_state = 0; - } - - l_ptr->peer_session = msg_session(msg); - l_ptr->peer_bearer_id = msg_bearer_id(msg); - - if (msg_type(msg) == ACTIVATE_MSG) - link_state_event(l_ptr, ACTIVATE_MSG); - break; - case STATE_MSG: + case ACTIVATE_MSG: - msg_tol = msg_link_tolerance(msg); - if (msg_tol) - link_set_supervision_props(l_ptr, msg_tol); - - if (msg_linkprio(msg) && - (msg_linkprio(msg) != l_ptr->priority)) { - pr_debug("%s<%s>, priority change %u->%u\n", - link_rst_msg, l_ptr->name, - l_ptr->priority, msg_linkprio(msg)); - l_ptr->priority = msg_linkprio(msg); - tipc_link_reset(l_ptr); /* Enforce change to take effect */ + /* Complete own link name with peer's interface name */ + if_name = strrchr(l->name, ':') + 1; + if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME) break; - } - - /* Record reception; force mismatch at next timeout: */ - l_ptr->silent_intv_cnt = 0; - - link_state_event(l_ptr, TRAFFIC_MSG_EVT); - l_ptr->stats.recv_states++; - if (link_reset_unknown(l_ptr)) + if (msg_data_sz(hdr) < TIPC_MAX_IF_NAME) break; + strncpy(if_name, msg_data(hdr), TIPC_MAX_IF_NAME); - if (less_eq(l_ptr->rcv_nxt, msg_next_sent(msg))) - rec_gap = mod(msg_next_sent(msg) - l_ptr->rcv_nxt); + /* Update own tolerance if peer indicates a non-zero value */ + if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) + l->tolerance = peers_tol; - if (msg_probe(msg)) - l_ptr->stats.recv_probes++; + /* Update own priority if peer's priority is higher */ + if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) + l->priority = peers_prio; - /* Protocol message before retransmits, reduce loss risk */ - if (l_ptr->owner->bclink.recv_permitted) - tipc_bclink_update_link_state(l_ptr->owner, - msg_last_bcast(msg)); - - if (rec_gap || (msg_probe(msg))) { - tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, - rec_gap, 0, 0); - } - if (msg_seq_gap(msg)) { - l_ptr->stats.recv_nacks++; - tipc_link_retransmit(l_ptr, skb_peek(&l_ptr->transmq), - msg_seq_gap(msg)); + if (msg_type(hdr) == RESET_MSG) { + rc |= tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); + } else if (!link_is_up(l)) { + tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); + rc |= tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); } + l->peer_session = msg_session(hdr); + l->peer_bearer_id = msg_bearer_id(hdr); + if (l->mtu > msg_max_pkt(hdr)) + l->mtu = msg_max_pkt(hdr); break; - } -exit: - kfree_skb(buf); -} - - -/* tipc_link_tunnel_xmit(): Tunnel one packet via a link belonging to - * a different bearer. Owner node is locked. - */ -static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr, - struct tipc_msg *tunnel_hdr, - struct tipc_msg *msg, - u32 selector) -{ - struct tipc_link *tunnel; - struct sk_buff *skb; - u32 length = msg_size(msg); - - tunnel = l_ptr->owner->active_links[selector & 1]; - if (!tipc_link_is_up(tunnel)) { - pr_warn("%stunnel link no longer available\n", link_co_err); - return; - } - msg_set_size(tunnel_hdr, length + INT_H_SIZE); - skb = tipc_buf_acquire(length + INT_H_SIZE); - if (!skb) { - pr_warn("%sunable to send tunnel msg\n", link_co_err); - return; - } - skb_copy_to_linear_data(skb, tunnel_hdr, INT_H_SIZE); - skb_copy_to_linear_data_offset(skb, INT_H_SIZE, msg, length); - __tipc_link_xmit_skb(tunnel, skb); -} - - -/* tipc_link_failover_send_queue(): A link has gone down, but a second - * link is still active. We can do failover. Tunnel the failing link's - * whole send queue via the remaining link. This way, we don't lose - * any packets, and sequence order is preserved for subsequent traffic - * sent over the remaining link. Owner node is locked. - */ -void tipc_link_failover_send_queue(struct tipc_link *l_ptr) -{ - int msgcount; - struct tipc_link *tunnel = l_ptr->owner->active_links[0]; - struct tipc_msg tunnel_hdr; - struct sk_buff *skb; - int split_bundles; - - if (!tunnel) - return; - tipc_msg_init(link_own_addr(l_ptr), &tunnel_hdr, TUNNEL_PROTOCOL, - FAILOVER_MSG, INT_H_SIZE, l_ptr->addr); - - skb_queue_walk(&l_ptr->backlogq, skb) { - msg_set_seqno(buf_msg(skb), l_ptr->snd_nxt); - l_ptr->snd_nxt = mod(l_ptr->snd_nxt + 1); - } - skb_queue_splice_tail_init(&l_ptr->backlogq, &l_ptr->transmq); - tipc_link_purge_backlog(l_ptr); - msgcount = skb_queue_len(&l_ptr->transmq); - msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); - msg_set_msgcnt(&tunnel_hdr, msgcount); - - if (skb_queue_empty(&l_ptr->transmq)) { - skb = tipc_buf_acquire(INT_H_SIZE); - if (skb) { - skb_copy_to_linear_data(skb, &tunnel_hdr, INT_H_SIZE); - msg_set_size(&tunnel_hdr, INT_H_SIZE); - __tipc_link_xmit_skb(tunnel, skb); - } else { - pr_warn("%sunable to send changeover msg\n", - link_co_err); - } - return; - } - - split_bundles = (l_ptr->owner->active_links[0] != - l_ptr->owner->active_links[1]); + case STATE_MSG: - skb_queue_walk(&l_ptr->transmq, skb) { - struct tipc_msg *msg = buf_msg(skb); + /* Update own tolerance if peer indicates a non-zero value */ + if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL)) + l->tolerance = peers_tol; - if ((msg_user(msg) == MSG_BUNDLER) && split_bundles) { - struct tipc_msg *m = msg_get_wrapped(msg); - unchar *pos = (unchar *)m; + l->silent_intv_cnt = 0; + l->stats.recv_states++; + if (msg_probe(hdr)) + l->stats.recv_probes++; + rc = tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); + if (!link_is_up(l)) + break; - msgcount = msg_msgcnt(msg); - while (msgcount--) { - msg_set_seqno(m, msg_seqno(msg)); - tipc_link_tunnel_xmit(l_ptr, &tunnel_hdr, m, - msg_link_selector(m)); - pos += align(msg_size(m)); - m = (struct tipc_msg *)pos; - } - } else { - tipc_link_tunnel_xmit(l_ptr, &tunnel_hdr, msg, - msg_link_selector(msg)); + /* Send NACK if peer has sent pkts we haven't received yet */ + if (more(peers_snd_nxt, l->rcv_nxt)) + rcvgap = peers_snd_nxt - l->rcv_nxt; + if (rcvgap || (msg_probe(hdr))) + tipc_link_build_proto_msg(l, STATE_MSG, 0, rcvgap, + 0, 0, xmitq); + tipc_link_release_pkts(l, msg_ack(hdr)); + + /* If NACK, retransmit will now start at right position */ + if (nacked_gap) { + rc = tipc_link_retransm(l, nacked_gap, xmitq); + l->stats.recv_nacks++; } - } -} - -/* tipc_link_dup_queue_xmit(): A second link has become active. Tunnel a - * duplicate of the first link's send queue via the new link. This way, we - * are guaranteed that currently queued packets from a socket are delivered - * before future traffic from the same socket, even if this is using the - * new link. The last arriving copy of each duplicate packet is dropped at - * the receiving end by the regular protocol check, so packet cardinality - * and sequence order is preserved per sender/receiver socket pair. - * Owner node is locked. - */ -void tipc_link_dup_queue_xmit(struct tipc_link *link, - struct tipc_link *tnl) -{ - struct sk_buff *skb; - struct tipc_msg tnl_hdr; - struct sk_buff_head *queue = &link->transmq; - int mcnt; - u16 seqno; - - tipc_msg_init(link_own_addr(link), &tnl_hdr, TUNNEL_PROTOCOL, - SYNCH_MSG, INT_H_SIZE, link->addr); - mcnt = skb_queue_len(&link->transmq) + skb_queue_len(&link->backlogq); - msg_set_msgcnt(&tnl_hdr, mcnt); - msg_set_bearer_id(&tnl_hdr, link->peer_bearer_id); - -tunnel_queue: - skb_queue_walk(queue, skb) { - struct sk_buff *outskb; - struct tipc_msg *msg = buf_msg(skb); - u32 len = msg_size(msg); - msg_set_ack(msg, mod(link->rcv_nxt - 1)); - msg_set_bcast_ack(msg, link->owner->bclink.last_in); - msg_set_size(&tnl_hdr, len + INT_H_SIZE); - outskb = tipc_buf_acquire(len + INT_H_SIZE); - if (outskb == NULL) { - pr_warn("%sunable to send duplicate msg\n", - link_co_err); - return; - } - skb_copy_to_linear_data(outskb, &tnl_hdr, INT_H_SIZE); - skb_copy_to_linear_data_offset(outskb, INT_H_SIZE, - skb->data, len); - __tipc_link_xmit_skb(tnl, outskb); - if (!tipc_link_is_up(link)) - return; - } - if (queue == &link->backlogq) - return; - seqno = link->snd_nxt; - skb_queue_walk(&link->backlogq, skb) { - msg_set_seqno(buf_msg(skb), seqno); - seqno = mod(seqno + 1); - } - queue = &link->backlogq; - goto tunnel_queue; -} - -/* tipc_link_failover_rcv(): Receive a tunnelled FAILOVER_MSG packet - * Owner node is locked. - */ -static bool tipc_link_failover_rcv(struct tipc_link *link, - struct sk_buff **skb) -{ - struct tipc_msg *msg = buf_msg(*skb); - struct sk_buff *iskb = NULL; - struct tipc_link *pl = NULL; - int bearer_id = msg_bearer_id(msg); - int pos = 0; - - if (msg_type(msg) != FAILOVER_MSG) { - pr_warn("%sunknown tunnel pkt received\n", link_co_err); - goto exit; - } - if (bearer_id >= MAX_BEARERS) - goto exit; - - if (bearer_id == link->bearer_id) - goto exit; - - pl = link->owner->links[bearer_id]; - if (pl && tipc_link_is_up(pl)) - tipc_link_reset(pl); - - if (link->failover_pkts == FIRST_FAILOVER) - link->failover_pkts = msg_msgcnt(msg); - - /* Should we expect an inner packet? */ - if (!link->failover_pkts) - goto exit; - - if (!tipc_msg_extract(*skb, &iskb, &pos)) { - pr_warn("%sno inner failover pkt\n", link_co_err); - *skb = NULL; - goto exit; - } - link->failover_pkts--; - *skb = NULL; - - /* Was this packet already delivered? */ - if (less(buf_seqno(iskb), link->failover_checkpt)) { - kfree_skb(iskb); - iskb = NULL; - goto exit; - } - if (msg_user(buf_msg(iskb)) == MSG_FRAGMENTER) { - link->stats.recv_fragments++; - tipc_buf_append(&link->failover_skb, &iskb); + tipc_link_advance_backlog(l, xmitq); + if (unlikely(!skb_queue_empty(&l->wakeupq))) + link_prepare_wakeup(l); } exit: - if (!link->failover_pkts && pl) - pl->flags &= ~LINK_FAILINGOVER; - kfree_skb(*skb); - *skb = iskb; - return *skb; -} - -static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tol) -{ - unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4; - - if ((tol < TIPC_MIN_LINK_TOL) || (tol > TIPC_MAX_LINK_TOL)) - return; - - l_ptr->tolerance = tol; - l_ptr->keepalive_intv = msecs_to_jiffies(intv); - l_ptr->abort_limit = tol / (jiffies_to_msecs(l_ptr->keepalive_intv)); + kfree_skb(skb); + return rc; } void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) @@ -1743,7 +1449,7 @@ static struct tipc_node *tipc_link_find_owner(struct net *net, list_for_each_entry_rcu(n_ptr, &tn->node_list, list) { tipc_node_lock(n_ptr); for (i = 0; i < MAX_BEARERS; i++) { - l_ptr = n_ptr->links[i]; + l_ptr = n_ptr->links[i].link; if (l_ptr && !strcmp(l_ptr->name, link_name)) { *bearer_id = i; found_node = n_ptr; @@ -1770,27 +1476,16 @@ static void link_reset_statistics(struct tipc_link *l_ptr) l_ptr->stats.recv_info = l_ptr->rcv_nxt; } -static void link_print(struct tipc_link *l_ptr, const char *str) +static void link_print(struct tipc_link *l, const char *str) { - struct tipc_net *tn = net_generic(l_ptr->owner->net, tipc_net_id); - struct tipc_bearer *b_ptr; - - rcu_read_lock(); - b_ptr = rcu_dereference_rtnl(tn->bearer_list[l_ptr->bearer_id]); - if (b_ptr) - pr_info("%s Link %x<%s>:", str, l_ptr->addr, b_ptr->name); - rcu_read_unlock(); - - if (link_working_unknown(l_ptr)) - pr_cont(":WU\n"); - else if (link_reset_reset(l_ptr)) - pr_cont(":RR\n"); - else if (link_reset_unknown(l_ptr)) - pr_cont(":RU\n"); - else if (link_working_working(l_ptr)) - pr_cont(":WW\n"); - else - pr_cont("\n"); + struct sk_buff *hskb = skb_peek(&l->transmq); + u16 head = hskb ? msg_seqno(buf_msg(hskb)) : l->snd_nxt; + u16 tail = l->snd_nxt - 1; + + pr_info("%s Link <%s> state %x\n", str, l->name, l->state); + pr_info("XMTQ: %u [%u-%u], BKLGQ: %u, SNDNX: %u, RCVNX: %u\n", + skb_queue_len(&l->transmq), head, tail, + skb_queue_len(&l->backlogq), l->snd_nxt, l->rcv_nxt); } /* Parse and validate nested (link) properties valid for media, bearer and link @@ -1865,7 +1560,7 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info) tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (!link) { res = -EINVAL; goto out; @@ -1885,7 +1580,7 @@ int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info) u32 tol; tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]); - link_set_supervision_props(link, tol); + link->tolerance = tol; tipc_link_proto_xmit(link, STATE_MSG, 0, 0, tol, 0); } if (props[TIPC_NLA_PROP_PRIO]) { @@ -2055,10 +1750,11 @@ static int __tipc_nl_add_node_links(struct net *net, struct tipc_nl_msg *msg, for (i = *prev_link; i < MAX_BEARERS; i++) { *prev_link = i; - if (!node->links[i]) + if (!node->links[i].link) continue; - err = __tipc_nl_add_link(net, msg, node->links[i], NLM_F_MULTI); + err = __tipc_nl_add_link(net, msg, + node->links[i].link, NLM_F_MULTI); if (err) return err; } @@ -2172,7 +1868,7 @@ int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info) return -EINVAL; tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (!link) { tipc_node_unlock(node); nlmsg_free(msg.skb); @@ -2227,7 +1923,7 @@ int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info) tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (!link) { tipc_node_unlock(node); return -EINVAL; diff --git a/net/tipc/link.h b/net/tipc/link.h index ae0a0ea..39ff8b6 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -49,19 +49,25 @@ */ #define INVALID_LINK_SEQ 0x10000 -/* Link working states +/* Link FSM events: */ -#define WORKING_WORKING 560810u -#define WORKING_UNKNOWN 560811u -#define RESET_UNKNOWN 560812u -#define RESET_RESET 560813u +enum { + LINK_ESTABLISH_EVT = 0xec1ab1e, + LINK_PEER_RESET_EVT = 0x9eed0e, + LINK_FAILURE_EVT = 0xfa110e, + LINK_RESET_EVT = 0x10ca1d0e, + LINK_FAILOVER_BEGIN_EVT = 0xfa110bee, + LINK_FAILOVER_END_EVT = 0xfa110ede, + LINK_SYNCH_BEGIN_EVT = 0xc1ccbee, + LINK_SYNCH_END_EVT = 0xc1ccede +}; -/* Link endpoint execution states +/* Events returned from link at packet reception or at timeout */ -#define LINK_STARTED 0x0001 -#define LINK_STOPPED 0x0002 -#define LINK_SYNCHING 0x0004 -#define LINK_FAILINGOVER 0x0008 +enum { + TIPC_LINK_UP_EVT = 1, + TIPC_LINK_DOWN_EVT = (1 << 1) +}; /* Starting value for maximum packet size negotiation on unicast links * (unless bearer MTU is less) @@ -106,7 +112,6 @@ struct tipc_stats { * @timer: link timer * @owner: pointer to peer node * @refcnt: reference counter for permanent references (owner node & timer) - * @flags: execution state flags for link endpoint instance * @peer_session: link session # being used by peer end of link * @peer_bearer_id: bearer id used by link's peer endpoint * @bearer_id: local bearer id used by link @@ -143,20 +148,17 @@ struct tipc_stats { struct tipc_link { u32 addr; char name[TIPC_MAX_LINK_NAME]; - struct tipc_media_addr media_addr; - struct timer_list timer; + struct tipc_media_addr *media_addr; struct tipc_node *owner; - struct kref ref; /* Management and link supervision data */ - unsigned int flags; u32 peer_session; u32 peer_bearer_id; u32 bearer_id; u32 tolerance; unsigned long keepalive_intv; u32 abort_limit; - int state; + u32 state; u32 silent_intv_cnt; struct { unchar hdr[INT_H_SIZE]; @@ -165,12 +167,10 @@ struct tipc_link { struct tipc_msg *pmsg; u32 priority; char net_plane; - u16 synch_point; - /* Failover */ - u16 failover_pkts; - u16 failover_checkpt; - struct sk_buff *failover_skb; + /* Failover/synch */ + u16 drop_point; + struct sk_buff *failover_reasm_skb; /* Max packet negotiation */ u16 mtu; @@ -192,8 +192,8 @@ struct tipc_link { u16 rcv_nxt; u32 rcv_unacked; struct sk_buff_head deferdq; - struct sk_buff_head inputq; - struct sk_buff_head namedq; + struct sk_buff_head *inputq; + struct sk_buff_head *namedq; /* Congestion handling */ struct sk_buff_head wakeupq; @@ -205,28 +205,29 @@ struct tipc_link { struct tipc_stats stats; }; -struct tipc_port; - -struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, - struct tipc_bearer *b_ptr, - const struct tipc_media_addr *media_addr); -void tipc_link_delete(struct tipc_link *link); -void tipc_link_delete_list(struct net *net, unsigned int bearer_id); -void tipc_link_failover_send_queue(struct tipc_link *l_ptr); -void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *dest); +bool tipc_link_create(struct tipc_node *n, struct tipc_bearer *b, u32 session, + u32 ownnode, u32 peer, struct tipc_media_addr *maddr, + struct sk_buff_head *inputq, struct sk_buff_head *namedq, + struct tipc_link **link); +void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl, + int mtyp, struct sk_buff_head *xmitq); +void tipc_link_build_bcast_sync_msg(struct tipc_link *l, + struct sk_buff_head *xmitq); +int tipc_link_fsm_evt(struct tipc_link *l, int evt); void tipc_link_reset_fragments(struct tipc_link *l_ptr); -int tipc_link_is_up(struct tipc_link *l_ptr); +bool tipc_link_is_up(struct tipc_link *l); +bool tipc_link_is_reset(struct tipc_link *l); +bool tipc_link_is_synching(struct tipc_link *l); +bool tipc_link_is_failingover(struct tipc_link *l); +bool tipc_link_is_blocked(struct tipc_link *l); int tipc_link_is_active(struct tipc_link *l_ptr); void tipc_link_purge_queues(struct tipc_link *l_ptr); void tipc_link_purge_backlog(struct tipc_link *l); -void tipc_link_reset_all(struct tipc_node *node); void tipc_link_reset(struct tipc_link *l_ptr); -int tipc_link_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, - u32 selector); -int tipc_link_xmit(struct net *net, struct sk_buff_head *list, u32 dest, - u32 selector); int __tipc_link_xmit(struct net *net, struct tipc_link *link, struct sk_buff_head *list); +int tipc_link_xmit(struct tipc_link *link, struct sk_buff_head *list, + struct sk_buff_head *xmitq); void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob, u32 gap, u32 tolerance, u32 priority); void tipc_link_push_packets(struct tipc_link *l_ptr); @@ -242,34 +243,8 @@ int tipc_nl_link_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_link_set(struct sk_buff *skb, struct genl_info *info); int tipc_nl_link_reset_stats(struct sk_buff *skb, struct genl_info *info); int tipc_nl_parse_link_prop(struct nlattr *prop, struct nlattr *props[]); -void link_prepare_wakeup(struct tipc_link *l); - -static inline u32 link_own_addr(struct tipc_link *l) -{ - return msg_prevnode(l->pmsg); -} - -/* - * Link status checking routines - */ -static inline int link_working_working(struct tipc_link *l_ptr) -{ - return l_ptr->state == WORKING_WORKING; -} - -static inline int link_working_unknown(struct tipc_link *l_ptr) -{ - return l_ptr->state == WORKING_UNKNOWN; -} - -static inline int link_reset_unknown(struct tipc_link *l_ptr) -{ - return l_ptr->state == RESET_UNKNOWN; -} - -static inline int link_reset_reset(struct tipc_link *l_ptr) -{ - return l_ptr->state == RESET_RESET; -} +int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq); +int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, + struct sk_buff_head *xmitq); #endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 08b4cc7..562c926 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -463,60 +463,72 @@ bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, /** * tipc_msg_reverse(): swap source and destination addresses and add error code - * @buf: buffer containing message to be reversed - * @dnode: return value: node where to send message after reversal - * @err: error code to be set in message - * Consumes buffer if failure + * @own_node: originating node id for reversed message + * @skb: buffer containing message to be reversed; may be replaced. + * @err: error code to be set in message, if any + * Consumes buffer at failure * Returns true if success, otherwise false */ -bool tipc_msg_reverse(u32 own_addr, struct sk_buff *buf, u32 *dnode, - int err) +bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) { - struct tipc_msg *msg = buf_msg(buf); + struct sk_buff *_skb = *skb; + struct tipc_msg *hdr = buf_msg(_skb); struct tipc_msg ohdr; - uint rdsz = min_t(uint, msg_data_sz(msg), MAX_FORWARD_SIZE); + int dlen = min_t(uint, msg_data_sz(hdr), MAX_FORWARD_SIZE); - if (skb_linearize(buf)) + if (skb_linearize(_skb)) goto exit; - msg = buf_msg(buf); - if (msg_dest_droppable(msg)) + hdr = buf_msg(_skb); + if (msg_dest_droppable(hdr)) goto exit; - if (msg_errcode(msg)) + if (msg_errcode(hdr)) goto exit; - memcpy(&ohdr, msg, msg_hdr_sz(msg)); - msg_set_errcode(msg, err); - msg_set_origport(msg, msg_destport(&ohdr)); - msg_set_destport(msg, msg_origport(&ohdr)); - msg_set_prevnode(msg, own_addr); - if (!msg_short(msg)) { - msg_set_orignode(msg, msg_destnode(&ohdr)); - msg_set_destnode(msg, msg_orignode(&ohdr)); + + /* Take a copy of original header before altering message */ + memcpy(&ohdr, hdr, msg_hdr_sz(hdr)); + + /* Never return SHORT header; expand by replacing buffer if necessary */ + if (msg_short(hdr)) { + *skb = tipc_buf_acquire(BASIC_H_SIZE + dlen); + if (!*skb) + goto exit; + memcpy((*skb)->data + BASIC_H_SIZE, msg_data(hdr), dlen); + kfree_skb(_skb); + _skb = *skb; + hdr = buf_msg(_skb); + memcpy(hdr, &ohdr, BASIC_H_SIZE); + msg_set_hdr_sz(hdr, BASIC_H_SIZE); } - msg_set_size(msg, msg_hdr_sz(msg) + rdsz); - skb_trim(buf, msg_size(msg)); - skb_orphan(buf); - *dnode = msg_orignode(&ohdr); + + /* Now reverse the concerned fields */ + msg_set_errcode(hdr, err); + msg_set_origport(hdr, msg_destport(&ohdr)); + msg_set_destport(hdr, msg_origport(&ohdr)); + msg_set_destnode(hdr, msg_prevnode(&ohdr)); + msg_set_prevnode(hdr, own_node); + msg_set_orignode(hdr, own_node); + msg_set_size(hdr, msg_hdr_sz(hdr) + dlen); + skb_trim(_skb, msg_size(hdr)); + skb_orphan(_skb); return true; exit: - kfree_skb(buf); - *dnode = 0; + kfree_skb(_skb); + *skb = NULL; return false; } /** * tipc_msg_lookup_dest(): try to find new destination for named message * @skb: the buffer containing the message. - * @dnode: return value: next-hop node, if destination found - * @err: return value: error code to use, if message to be rejected + * @err: error code to be used by caller if lookup fails * Does not consume buffer * Returns true if a destination is found, false otherwise */ -bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, - u32 *dnode, int *err) +bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) { struct tipc_msg *msg = buf_msg(skb); - u32 dport; - u32 own_addr = tipc_own_addr(net); + u32 dport, dnode; + u32 onode = tipc_own_addr(net); if (!msg_isdata(msg)) return false; @@ -529,15 +541,15 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, return false; if (msg_reroute_cnt(msg)) return false; - *dnode = addr_domain(net, msg_lookup_scope(msg)); + dnode = addr_domain(net, msg_lookup_scope(msg)); dport = tipc_nametbl_translate(net, msg_nametype(msg), - msg_nameinst(msg), dnode); + msg_nameinst(msg), &dnode); if (!dport) return false; msg_incr_reroute_cnt(msg); - if (*dnode != own_addr) - msg_set_prevnode(msg, own_addr); - msg_set_destnode(msg, *dnode); + if (dnode != onode) + msg_set_prevnode(msg, onode); + msg_set_destnode(msg, dnode); msg_set_destport(msg, dport); *err = TIPC_OK; return true; diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 19c45fb..a82c584 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -38,6 +38,7 @@ #define _TIPC_MSG_H #include <linux/tipc.h> +#include "core.h" /* * Constants and routines used to read and write TIPC payload message headers @@ -109,7 +110,6 @@ struct tipc_skb_cb { struct sk_buff *tail; bool validated; bool wakeup_pending; - bool bundling; u16 chain_sz; u16 chain_imp; }; @@ -558,15 +558,6 @@ static inline void msg_set_node_capabilities(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 15, 0x1fff, n); } -static inline bool msg_dup(struct tipc_msg *m) -{ - if (likely(msg_user(m) != TUNNEL_PROTOCOL)) - return false; - if (msg_type(m) != SYNCH_MSG) - return false; - return true; -} - /* * Word 2 */ @@ -620,12 +611,12 @@ static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n) } -static inline u32 msg_next_sent(struct tipc_msg *m) +static inline u16 msg_next_sent(struct tipc_msg *m) { return msg_bits(m, 4, 0, 0xffff); } -static inline void msg_set_next_sent(struct tipc_msg *m, u32 n) +static inline void msg_set_next_sent(struct tipc_msg *m, u16 n) { msg_set_bits(m, 4, 0, 0xffff, n); } @@ -658,12 +649,12 @@ static inline void msg_set_link_selector(struct tipc_msg *m, u32 n) /* * Word 5 */ -static inline u32 msg_session(struct tipc_msg *m) +static inline u16 msg_session(struct tipc_msg *m) { return msg_bits(m, 5, 16, 0xffff); } -static inline void msg_set_session(struct tipc_msg *m, u32 n) +static inline void msg_set_session(struct tipc_msg *m, u16 n) { msg_set_bits(m, 5, 16, 0xffff, n); } @@ -726,12 +717,12 @@ static inline char *msg_media_addr(struct tipc_msg *m) /* * Word 9 */ -static inline u32 msg_msgcnt(struct tipc_msg *m) +static inline u16 msg_msgcnt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } -static inline void msg_set_msgcnt(struct tipc_msg *m, u32 n) +static inline void msg_set_msgcnt(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } @@ -766,10 +757,25 @@ static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) msg_set_bits(m, 9, 0, 0xffff, n); } +static inline bool msg_peer_link_is_up(struct tipc_msg *m) +{ + if (likely(msg_user(m) != LINK_PROTOCOL)) + return true; + if (msg_type(m) == STATE_MSG) + return true; + return false; +} + +static inline bool msg_peer_node_is_up(struct tipc_msg *m) +{ + if (msg_peer_link_is_up(m)) + return true; + return msg_redundant_link(m); +} + struct sk_buff *tipc_buf_acquire(u32 size); bool tipc_msg_validate(struct sk_buff *skb); -bool tipc_msg_reverse(u32 own_addr, struct sk_buff *buf, u32 *dnode, - int err); +bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err); void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode); struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, @@ -782,8 +788,7 @@ bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos); int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); -bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, u32 *dnode, - int *err); +bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err); struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list); static inline u16 buf_seqno(struct sk_buff *skb) @@ -857,26 +862,65 @@ static inline struct sk_buff *tipc_skb_dequeue(struct sk_buff_head *list, return skb; } -/* tipc_skb_queue_tail(): add buffer to tail of list; +/* tipc_skb_queue_sorted(); sort pkt into list according to sequence number * @list: list to be appended to - * @skb: buffer to append. Always appended - * @dport: the destination port of the buffer - * returns true if dport differs from previous destination + * @skb: buffer to add + * Returns true if queue should treated further, otherwise false */ -static inline bool tipc_skb_queue_tail(struct sk_buff_head *list, - struct sk_buff *skb, u32 dport) +static inline bool __tipc_skb_queue_sorted(struct sk_buff_head *list, + struct sk_buff *skb) { - struct sk_buff *_skb = NULL; - bool rv = false; + struct sk_buff *_skb, *tmp; + struct tipc_msg *hdr = buf_msg(skb); + u16 seqno = msg_seqno(hdr); - spin_lock_bh(&list->lock); - _skb = skb_peek_tail(list); - if (!_skb || (msg_destport(buf_msg(_skb)) != dport) || - (skb_queue_len(list) > 32)) - rv = true; + if (skb_queue_empty(list) || (msg_user(hdr) == LINK_PROTOCOL)) { + __skb_queue_head(list, skb); + return true; + } + if (likely(less(seqno, buf_seqno(skb_peek(list))))) { + __skb_queue_head(list, skb); + return true; + } + if (!more(seqno, buf_seqno(skb_peek_tail(list)))) { + skb_queue_walk_safe(list, _skb, tmp) { + if (likely(less(seqno, buf_seqno(_skb)))) { + __skb_queue_before(list, _skb, skb); + return true; + } + } + } __skb_queue_tail(list, skb); + return false; +} + +/* tipc_skb_queue_splice_tail - append an skb list to lock protected list + * @list: the new list to append. Not lock protected + * @head: target list. Lock protected. + */ +static inline void tipc_skb_queue_splice_tail(struct sk_buff_head *list, + struct sk_buff_head *head) +{ + spin_lock_bh(&head->lock); + skb_queue_splice_tail(list, head); + spin_unlock_bh(&head->lock); +} + +/* tipc_skb_queue_splice_tail_init - merge two lock protected skb lists + * @list: the new list to add. Lock protected. Will be reinitialized + * @head: target list. Lock protected. + */ +static inline void tipc_skb_queue_splice_tail_init(struct sk_buff_head *list, + struct sk_buff_head *head) +{ + struct sk_buff_head tmp; + + __skb_queue_head_init(&tmp); + + spin_lock_bh(&list->lock); + skb_queue_splice_tail_init(list, &tmp); spin_unlock_bh(&list->lock); - return rv; + tipc_skb_queue_splice_tail(&tmp, head); } #endif diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 41e7b7e..e6018b7 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -96,13 +96,13 @@ void named_cluster_distribute(struct net *net, struct sk_buff *skb) dnode = node->addr; if (in_own_node(net, dnode)) continue; - if (!tipc_node_active_links(node)) + if (!tipc_node_is_up(node)) continue; oskb = pskb_copy(skb, GFP_ATOMIC); if (!oskb) break; msg_set_destnode(buf_msg(oskb), dnode); - tipc_link_xmit_skb(net, oskb, dnode, dnode); + tipc_node_xmit_skb(net, oskb, dnode, dnode); } rcu_read_unlock(); @@ -223,7 +223,7 @@ void tipc_named_node_up(struct net *net, u32 dnode) &tn->nametbl->publ_list[TIPC_ZONE_SCOPE]); rcu_read_unlock(); - tipc_link_xmit(net, &head, dnode, dnode); + tipc_node_xmit(net, &head, dnode, dnode); } static void tipc_publ_subscribe(struct net *net, struct publication *publ, diff --git a/net/tipc/node.c b/net/tipc/node.c index 0b1d61a..7c19164 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -40,10 +40,42 @@ #include "name_distr.h" #include "socket.h" #include "bcast.h" +#include "discover.h" -static void node_lost_contact(struct tipc_node *n_ptr); +/* Node FSM states and events: + */ +enum { + SELF_DOWN_PEER_DOWN = 0xdd, + SELF_UP_PEER_UP = 0xaa, + SELF_DOWN_PEER_LEAVING = 0xd1, + SELF_UP_PEER_COMING = 0xac, + SELF_COMING_PEER_UP = 0xca, + SELF_LEAVING_PEER_DOWN = 0x1d, + NODE_FAILINGOVER = 0xf0, + NODE_SYNCHING = 0xcc +}; + +enum { + SELF_ESTABL_CONTACT_EVT = 0xece, + SELF_LOST_CONTACT_EVT = 0x1ce, + PEER_ESTABL_CONTACT_EVT = 0x9ece, + PEER_LOST_CONTACT_EVT = 0x91ce, + NODE_FAILOVER_BEGIN_EVT = 0xfbe, + NODE_FAILOVER_END_EVT = 0xfee, + NODE_SYNCH_BEGIN_EVT = 0xcbe, + NODE_SYNCH_END_EVT = 0xcee +}; + +static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, + struct sk_buff_head *xmitq, + struct tipc_media_addr **maddr); +static void tipc_node_link_down(struct tipc_node *n, int bearer_id, + bool delete); +static void node_lost_contact(struct tipc_node *n, struct sk_buff_head *inputq); static void node_established_contact(struct tipc_node *n_ptr); static void tipc_node_delete(struct tipc_node *node); +static void tipc_node_timeout(unsigned long data); +static void tipc_node_fsm_evt(struct tipc_node *n, int evt); struct tipc_sock_conn { u32 port; @@ -110,7 +142,7 @@ struct tipc_node *tipc_node_find(struct net *net, u32 addr) return NULL; } -struct tipc_node *tipc_node_create(struct net *net, u32 addr) +struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) { struct tipc_net *tn = net_generic(net, tipc_net_id); struct tipc_node *n_ptr, *temp_node; @@ -126,12 +158,14 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) } n_ptr->addr = addr; n_ptr->net = net; + n_ptr->capabilities = capabilities; kref_init(&n_ptr->kref); spin_lock_init(&n_ptr->lock); INIT_HLIST_NODE(&n_ptr->hash); INIT_LIST_HEAD(&n_ptr->list); INIT_LIST_HEAD(&n_ptr->publ_list); INIT_LIST_HEAD(&n_ptr->conn_sks); + skb_queue_head_init(&n_ptr->bclink.namedq); __skb_queue_head_init(&n_ptr->bclink.deferdq); hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]); list_for_each_entry_rcu(temp_node, &tn->node_list, list) { @@ -139,14 +173,32 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr) break; } list_add_tail_rcu(&n_ptr->list, &temp_node->list); - n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN; + n_ptr->state = SELF_DOWN_PEER_LEAVING; n_ptr->signature = INVALID_NODE_SIG; + n_ptr->active_links[0] = INVALID_BEARER_ID; + n_ptr->active_links[1] = INVALID_BEARER_ID; tipc_node_get(n_ptr); + setup_timer(&n_ptr->timer, tipc_node_timeout, (unsigned long)n_ptr); + n_ptr->keepalive_intv = U32_MAX; exit: spin_unlock_bh(&tn->node_list_lock); return n_ptr; } +static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l) +{ + unsigned long tol = l->tolerance; + unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4; + unsigned long keepalive_intv = msecs_to_jiffies(intv); + + /* Link with lowest tolerance determines timer interval */ + if (keepalive_intv < n->keepalive_intv) + n->keepalive_intv = keepalive_intv; + + /* Ensure link's abort limit corresponds to current interval */ + l->abort_limit = l->tolerance / jiffies_to_msecs(n->keepalive_intv); +} + static void tipc_node_delete(struct tipc_node *node) { list_del_rcu(&node->list); @@ -160,8 +212,11 @@ void tipc_node_stop(struct net *net) struct tipc_node *node, *t_node; spin_lock_bh(&tn->node_list_lock); - list_for_each_entry_safe(node, t_node, &tn->node_list, list) + list_for_each_entry_safe(node, t_node, &tn->node_list, list) { + if (del_timer(&node->timer)) + tipc_node_put(node); tipc_node_put(node); + } spin_unlock_bh(&tn->node_list_lock); } @@ -219,158 +274,547 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port) tipc_node_put(node); } +/* tipc_node_timeout - handle expiration of node timer + */ +static void tipc_node_timeout(unsigned long data) +{ + struct tipc_node *n = (struct tipc_node *)data; + struct tipc_link_entry *le; + struct sk_buff_head xmitq; + int bearer_id; + int rc = 0; + + __skb_queue_head_init(&xmitq); + + for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { + tipc_node_lock(n); + le = &n->links[bearer_id]; + if (le->link) { + /* Link tolerance may change asynchronously: */ + tipc_node_calculate_timer(n, le->link); + rc = tipc_link_timeout(le->link, &xmitq); + } + tipc_node_unlock(n); + tipc_bearer_xmit(n->net, bearer_id, &xmitq, &le->maddr); + if (rc & TIPC_LINK_DOWN_EVT) + tipc_node_link_down(n, bearer_id, false); + } + if (!mod_timer(&n->timer, jiffies + n->keepalive_intv)) + tipc_node_get(n); + tipc_node_put(n); +} + /** - * tipc_node_link_up - handle addition of link - * + * __tipc_node_link_up - handle addition of link + * Node lock must be held by caller * Link becomes active (alone or shared) or standby, depending on its priority. */ -void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) +static void __tipc_node_link_up(struct tipc_node *n, int bearer_id, + struct sk_buff_head *xmitq) { - struct tipc_link **active = &n_ptr->active_links[0]; + int *slot0 = &n->active_links[0]; + int *slot1 = &n->active_links[1]; + struct tipc_link *ol = node_active_link(n, 0); + struct tipc_link *nl = n->links[bearer_id].link; - n_ptr->working_links++; - n_ptr->action_flags |= TIPC_NOTIFY_LINK_UP; - n_ptr->link_id = l_ptr->peer_bearer_id << 16 | l_ptr->bearer_id; + if (!nl || !tipc_link_is_up(nl)) + return; - pr_debug("Established link <%s> on network plane %c\n", - l_ptr->name, l_ptr->net_plane); + n->working_links++; + n->action_flags |= TIPC_NOTIFY_LINK_UP; + n->link_id = nl->peer_bearer_id << 16 | bearer_id; - if (!active[0]) { - active[0] = active[1] = l_ptr; - node_established_contact(n_ptr); - goto exit; - } - if (l_ptr->priority < active[0]->priority) { - pr_debug("New link <%s> becomes standby\n", l_ptr->name); - goto exit; + /* Leave room for tunnel header when returning 'mtu' to users: */ + n->links[bearer_id].mtu = nl->mtu - INT_H_SIZE; + + tipc_bearer_add_dest(n->net, bearer_id, n->addr); + + pr_debug("Established link <%s> on network plane %c\n", + nl->name, nl->net_plane); + + /* First link? => give it both slots */ + if (!ol) { + *slot0 = bearer_id; + *slot1 = bearer_id; + tipc_link_build_bcast_sync_msg(nl, xmitq); + node_established_contact(n); + return; } - tipc_link_dup_queue_xmit(active[0], l_ptr); - if (l_ptr->priority == active[0]->priority) { - active[0] = l_ptr; - goto exit; + + /* Second link => redistribute slots */ + if (nl->priority > ol->priority) { + pr_debug("Old link <%s> becomes standby\n", ol->name); + *slot0 = bearer_id; + *slot1 = bearer_id; + } else if (nl->priority == ol->priority) { + *slot0 = bearer_id; + } else { + pr_debug("New link <%s> is standby\n", nl->name); } - pr_debug("Old link <%s> becomes standby\n", active[0]->name); - if (active[1] != active[0]) - pr_debug("Old link <%s> becomes standby\n", active[1]->name); - active[0] = active[1] = l_ptr; -exit: - /* Leave room for changeover header when returning 'mtu' to users: */ - n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE; - n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE; + + /* Prepare synchronization with first link */ + tipc_link_tnl_prepare(ol, nl, SYNCH_MSG, xmitq); } /** - * node_select_active_links - select active link + * tipc_node_link_up - handle addition of link + * + * Link becomes active (alone or shared) or standby, depending on its priority. */ -static void node_select_active_links(struct tipc_node *n_ptr) +static void tipc_node_link_up(struct tipc_node *n, int bearer_id, + struct sk_buff_head *xmitq) { - struct tipc_link **active = &n_ptr->active_links[0]; - u32 i; - u32 highest_prio = 0; + tipc_node_lock(n); + __tipc_node_link_up(n, bearer_id, xmitq); + tipc_node_unlock(n); +} - active[0] = active[1] = NULL; +/** + * __tipc_node_link_down - handle loss of link + */ +static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id, + struct sk_buff_head *xmitq, + struct tipc_media_addr **maddr) +{ + struct tipc_link_entry *le = &n->links[*bearer_id]; + int *slot0 = &n->active_links[0]; + int *slot1 = &n->active_links[1]; + int i, highest = 0; + struct tipc_link *l, *_l, *tnl; + + l = n->links[*bearer_id].link; + if (!l || tipc_link_is_reset(l)) + return; - for (i = 0; i < MAX_BEARERS; i++) { - struct tipc_link *l_ptr = n_ptr->links[i]; + n->working_links--; + n->action_flags |= TIPC_NOTIFY_LINK_DOWN; + n->link_id = l->peer_bearer_id << 16 | *bearer_id; - if (!l_ptr || !tipc_link_is_up(l_ptr) || - (l_ptr->priority < highest_prio)) - continue; + tipc_bearer_remove_dest(n->net, *bearer_id, n->addr); + + pr_debug("Lost link <%s> on network plane %c\n", + l->name, l->net_plane); - if (l_ptr->priority > highest_prio) { - highest_prio = l_ptr->priority; - active[0] = active[1] = l_ptr; - } else { - active[1] = l_ptr; + /* Select new active link if any available */ + *slot0 = INVALID_BEARER_ID; + *slot1 = INVALID_BEARER_ID; + for (i = 0; i < MAX_BEARERS; i++) { + _l = n->links[i].link; + if (!_l || !tipc_link_is_up(_l)) + continue; + if (_l == l) + continue; + if (_l->priority < highest) + continue; + if (_l->priority > highest) { + highest = _l->priority; + *slot0 = i; + *slot1 = i; + continue; } + *slot1 = i; + } + + if (!tipc_node_is_up(n)) { + tipc_link_reset(l); + node_lost_contact(n, &le->inputq); + return; } + + /* There is still a working link => initiate failover */ + tnl = node_active_link(n, 0); + n->sync_point = tnl->rcv_nxt + (U16_MAX / 2 - 1); + tipc_link_tnl_prepare(l, tnl, FAILOVER_MSG, xmitq); + tipc_link_reset(l); + tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT); + tipc_node_fsm_evt(n, NODE_FAILOVER_BEGIN_EVT); + *maddr = &n->links[tnl->bearer_id].maddr; + *bearer_id = tnl->bearer_id; } -/** - * tipc_node_link_down - handle loss of link - */ -void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr) +static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) { - struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); - struct tipc_link **active; + struct tipc_link_entry *le = &n->links[bearer_id]; + struct tipc_media_addr *maddr; + struct sk_buff_head xmitq; + + __skb_queue_head_init(&xmitq); + + tipc_node_lock(n); + __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr); + if (delete && le->link) { + kfree(le->link); + le->link = NULL; + n->link_cnt--; + } + tipc_node_unlock(n); - n_ptr->working_links--; - n_ptr->action_flags |= TIPC_NOTIFY_LINK_DOWN; - n_ptr->link_id = l_ptr->peer_bearer_id << 16 | l_ptr->bearer_id; + tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr); + tipc_sk_rcv(n->net, &le->inputq); +} - if (!tipc_link_is_active(l_ptr)) { - pr_debug("Lost standby link <%s> on network plane %c\n", - l_ptr->name, l_ptr->net_plane); - return; - } - pr_debug("Lost link <%s> on network plane %c\n", - l_ptr->name, l_ptr->net_plane); - - active = &n_ptr->active_links[0]; - if (active[0] == l_ptr) - active[0] = active[1]; - if (active[1] == l_ptr) - active[1] = active[0]; - if (active[0] == l_ptr) - node_select_active_links(n_ptr); - if (tipc_node_is_up(n_ptr)) - tipc_link_failover_send_queue(l_ptr); - else - node_lost_contact(n_ptr); - - /* Leave room for changeover header when returning 'mtu' to users: */ - if (active[0]) { - n_ptr->act_mtus[0] = active[0]->mtu - INT_H_SIZE; - n_ptr->act_mtus[1] = active[1]->mtu - INT_H_SIZE; +bool tipc_node_is_up(struct tipc_node *n) +{ + return n->active_links[0] != INVALID_BEARER_ID; +} + +void tipc_node_check_dest(struct net *net, u32 onode, + struct tipc_bearer *b, + u16 capabilities, u32 signature, + struct tipc_media_addr *maddr, + bool *respond, bool *dupl_addr) +{ + struct tipc_node *n; + struct tipc_link *l; + struct tipc_link_entry *le; + bool addr_match = false; + bool sign_match = false; + bool link_up = false; + bool accept_addr = false; + bool reset = true; + + *dupl_addr = false; + *respond = false; + + n = tipc_node_create(net, onode, capabilities); + if (!n) return; + + tipc_node_lock(n); + + le = &n->links[b->identity]; + + /* Prepare to validate requesting node's signature and media address */ + l = le->link; + link_up = l && tipc_link_is_up(l); + addr_match = l && !memcmp(&le->maddr, maddr, sizeof(*maddr)); + sign_match = (signature == n->signature); + + /* These three flags give us eight permutations: */ + + if (sign_match && addr_match && link_up) { + /* All is fine. Do nothing. */ + reset = false; + } else if (sign_match && addr_match && !link_up) { + /* Respond. The link will come up in due time */ + *respond = true; + } else if (sign_match && !addr_match && link_up) { + /* Peer has changed i/f address without rebooting. + * If so, the link will reset soon, and the next + * discovery will be accepted. So we can ignore it. + * It may also be an cloned or malicious peer having + * chosen the same node address and signature as an + * existing one. + * Ignore requests until the link goes down, if ever. + */ + *dupl_addr = true; + } else if (sign_match && !addr_match && !link_up) { + /* Peer link has changed i/f address without rebooting. + * It may also be a cloned or malicious peer; we can't + * distinguish between the two. + * The signature is correct, so we must accept. + */ + accept_addr = true; + *respond = true; + } else if (!sign_match && addr_match && link_up) { + /* Peer node rebooted. Two possibilities: + * - Delayed re-discovery; this link endpoint has already + * reset and re-established contact with the peer, before + * receiving a discovery message from that node. + * (The peer happened to receive one from this node first). + * - The peer came back so fast that our side has not + * discovered it yet. Probing from this side will soon + * reset the link, since there can be no working link + * endpoint at the peer end, and the link will re-establish. + * Accept the signature, since it comes from a known peer. + */ + n->signature = signature; + } else if (!sign_match && addr_match && !link_up) { + /* The peer node has rebooted. + * Accept signature, since it is a known peer. + */ + n->signature = signature; + *respond = true; + } else if (!sign_match && !addr_match && link_up) { + /* Peer rebooted with new address, or a new/duplicate peer. + * Ignore until the link goes down, if ever. + */ + *dupl_addr = true; + } else if (!sign_match && !addr_match && !link_up) { + /* Peer rebooted with new address, or it is a new peer. + * Accept signature and address. + */ + n->signature = signature; + accept_addr = true; + *respond = true; } - /* Loopback link went down? No fragmentation needed from now on. */ - if (n_ptr->addr == tn->own_addr) { - n_ptr->act_mtus[0] = MAX_MSG_SIZE; - n_ptr->act_mtus[1] = MAX_MSG_SIZE; + + if (!accept_addr) + goto exit; + + /* Now create new link if not already existing */ + if (!l) { + if (n->link_cnt == 2) { + pr_warn("Cannot establish 3rd link to %x\n", n->addr); + goto exit; + } + if (!tipc_link_create(n, b, mod(tipc_net(net)->random), + tipc_own_addr(net), onode, &le->maddr, + &le->inputq, &n->bclink.namedq, &l)) { + *respond = false; + goto exit; + } + tipc_link_reset(l); + le->link = l; + n->link_cnt++; + tipc_node_calculate_timer(n, l); + if (n->link_cnt == 1) + if (!mod_timer(&n->timer, jiffies + n->keepalive_intv)) + tipc_node_get(n); } + memcpy(&le->maddr, maddr, sizeof(*maddr)); +exit: + tipc_node_unlock(n); + if (reset) + tipc_node_link_down(n, b->identity, false); + tipc_node_put(n); } -int tipc_node_active_links(struct tipc_node *n_ptr) +void tipc_node_delete_links(struct net *net, int bearer_id) { - return n_ptr->active_links[0] != NULL; + struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_node *n; + + rcu_read_lock(); + list_for_each_entry_rcu(n, &tn->node_list, list) { + tipc_node_link_down(n, bearer_id, true); + } + rcu_read_unlock(); } -int tipc_node_is_up(struct tipc_node *n_ptr) +static void tipc_node_reset_links(struct tipc_node *n) { - return tipc_node_active_links(n_ptr); + char addr_string[16]; + int i; + + pr_warn("Resetting all links to %s\n", + tipc_addr_string_fill(addr_string, n->addr)); + + for (i = 0; i < MAX_BEARERS; i++) { + tipc_node_link_down(n, i, false); + } } -void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) +/* tipc_node_fsm_evt - node finite state machine + * Determines when contact is allowed with peer node + */ +static void tipc_node_fsm_evt(struct tipc_node *n, int evt) { - n_ptr->links[l_ptr->bearer_id] = l_ptr; - n_ptr->link_cnt++; + int state = n->state; + + switch (state) { + case SELF_DOWN_PEER_DOWN: + switch (evt) { + case SELF_ESTABL_CONTACT_EVT: + state = SELF_UP_PEER_COMING; + break; + case PEER_ESTABL_CONTACT_EVT: + state = SELF_COMING_PEER_UP; + break; + case SELF_LOST_CONTACT_EVT: + case PEER_LOST_CONTACT_EVT: + break; + case NODE_SYNCH_END_EVT: + case NODE_SYNCH_BEGIN_EVT: + case NODE_FAILOVER_BEGIN_EVT: + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case SELF_UP_PEER_UP: + switch (evt) { + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_LEAVING; + break; + case PEER_LOST_CONTACT_EVT: + state = SELF_LEAVING_PEER_DOWN; + break; + case NODE_SYNCH_BEGIN_EVT: + state = NODE_SYNCHING; + break; + case NODE_FAILOVER_BEGIN_EVT: + state = NODE_FAILINGOVER; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + case NODE_SYNCH_END_EVT: + case NODE_FAILOVER_END_EVT: + break; + default: + goto illegal_evt; + } + break; + case SELF_DOWN_PEER_LEAVING: + switch (evt) { + case PEER_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_DOWN; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + case SELF_LOST_CONTACT_EVT: + break; + case NODE_SYNCH_END_EVT: + case NODE_SYNCH_BEGIN_EVT: + case NODE_FAILOVER_BEGIN_EVT: + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case SELF_UP_PEER_COMING: + switch (evt) { + case PEER_ESTABL_CONTACT_EVT: + state = SELF_UP_PEER_UP; + break; + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_LEAVING; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_LOST_CONTACT_EVT: + break; + case NODE_SYNCH_END_EVT: + case NODE_SYNCH_BEGIN_EVT: + case NODE_FAILOVER_BEGIN_EVT: + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case SELF_COMING_PEER_UP: + switch (evt) { + case SELF_ESTABL_CONTACT_EVT: + state = SELF_UP_PEER_UP; + break; + case PEER_LOST_CONTACT_EVT: + state = SELF_LEAVING_PEER_DOWN; + break; + case SELF_LOST_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + break; + case NODE_SYNCH_END_EVT: + case NODE_SYNCH_BEGIN_EVT: + case NODE_FAILOVER_BEGIN_EVT: + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case SELF_LEAVING_PEER_DOWN: + switch (evt) { + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_DOWN; + break; + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + case PEER_LOST_CONTACT_EVT: + break; + case NODE_SYNCH_END_EVT: + case NODE_SYNCH_BEGIN_EVT: + case NODE_FAILOVER_BEGIN_EVT: + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + case NODE_FAILINGOVER: + switch (evt) { + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_LEAVING; + break; + case PEER_LOST_CONTACT_EVT: + state = SELF_LEAVING_PEER_DOWN; + break; + case NODE_FAILOVER_END_EVT: + state = SELF_UP_PEER_UP; + break; + case NODE_FAILOVER_BEGIN_EVT: + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + break; + case NODE_SYNCH_BEGIN_EVT: + case NODE_SYNCH_END_EVT: + default: + goto illegal_evt; + } + break; + case NODE_SYNCHING: + switch (evt) { + case SELF_LOST_CONTACT_EVT: + state = SELF_DOWN_PEER_LEAVING; + break; + case PEER_LOST_CONTACT_EVT: + state = SELF_LEAVING_PEER_DOWN; + break; + case NODE_SYNCH_END_EVT: + state = SELF_UP_PEER_UP; + break; + case NODE_FAILOVER_BEGIN_EVT: + state = NODE_FAILINGOVER; + break; + case NODE_SYNCH_BEGIN_EVT: + case SELF_ESTABL_CONTACT_EVT: + case PEER_ESTABL_CONTACT_EVT: + break; + case NODE_FAILOVER_END_EVT: + default: + goto illegal_evt; + } + break; + default: + pr_err("Unknown node fsm state %x\n", state); + break; + } + n->state = state; + return; + +illegal_evt: + pr_err("Illegal node fsm evt %x in state %x\n", evt, state); } -void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) +bool tipc_node_filter_pkt(struct tipc_node *n, struct tipc_msg *hdr) { - int i; + int state = n->state; - for (i = 0; i < MAX_BEARERS; i++) { - if (l_ptr != n_ptr->links[i]) - continue; - n_ptr->links[i] = NULL; - n_ptr->link_cnt--; + if (likely(state == SELF_UP_PEER_UP)) + return true; + + if (state == SELF_LEAVING_PEER_DOWN) + return false; + + if (state == SELF_DOWN_PEER_LEAVING) { + if (msg_peer_node_is_up(hdr)) + return false; } + + return true; } static void node_established_contact(struct tipc_node *n_ptr) { + tipc_node_fsm_evt(n_ptr, SELF_ESTABL_CONTACT_EVT); n_ptr->action_flags |= TIPC_NOTIFY_NODE_UP; n_ptr->bclink.oos_state = 0; n_ptr->bclink.acked = tipc_bclink_get_last_sent(n_ptr->net); tipc_bclink_add_node(n_ptr->net, n_ptr->addr); } -static void node_lost_contact(struct tipc_node *n_ptr) +static void node_lost_contact(struct tipc_node *n_ptr, + struct sk_buff_head *inputq) { char addr_string[16]; struct tipc_sock_conn *conn, *safe; + struct tipc_link *l; struct list_head *conns = &n_ptr->conn_sks; struct sk_buff *skb; struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id); @@ -396,21 +840,13 @@ static void node_lost_contact(struct tipc_node *n_ptr) /* Abort any ongoing link failover */ for (i = 0; i < MAX_BEARERS; i++) { - struct tipc_link *l_ptr = n_ptr->links[i]; - if (!l_ptr) - continue; - l_ptr->flags &= ~LINK_FAILINGOVER; - l_ptr->failover_checkpt = 0; - l_ptr->failover_pkts = 0; - kfree_skb(l_ptr->failover_skb); - l_ptr->failover_skb = NULL; - tipc_link_reset_fragments(l_ptr); + l = n_ptr->links[i].link; + if (l) + tipc_link_fsm_evt(l, LINK_FAILOVER_END_EVT); } - n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN; - /* Prevent re-contact with node until cleanup is done */ - n_ptr->action_flags |= TIPC_WAIT_PEER_LINKS_DOWN; + tipc_node_fsm_evt(n_ptr, SELF_LOST_CONTACT_EVT); /* Notify publications from this node */ n_ptr->action_flags |= TIPC_NOTIFY_NODE_DOWN; @@ -421,10 +857,8 @@ static void node_lost_contact(struct tipc_node *n_ptr) SHORT_H_SIZE, 0, tn->own_addr, conn->peer_node, conn->port, conn->peer_port, TIPC_ERR_NO_NODE); - if (likely(skb)) { - skb_queue_tail(n_ptr->inputq, skb); - n_ptr->action_flags |= TIPC_MSG_EVT; - } + if (likely(skb)) + skb_queue_tail(inputq, skb); list_del(&conn->list); kfree(conn); } @@ -453,7 +887,7 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr, goto exit; tipc_node_lock(node); - link = node->links[bearer_id]; + link = node->links[bearer_id].link; if (link) { strncpy(linkname, link->name, len); err = 0; @@ -471,27 +905,20 @@ void tipc_node_unlock(struct tipc_node *node) u32 flags = node->action_flags; u32 link_id = 0; struct list_head *publ_list; - struct sk_buff_head *inputq = node->inputq; - struct sk_buff_head *namedq; - if (likely(!flags || (flags == TIPC_MSG_EVT))) { - node->action_flags = 0; + if (likely(!flags)) { spin_unlock_bh(&node->lock); - if (flags == TIPC_MSG_EVT) - tipc_sk_rcv(net, inputq); return; } addr = node->addr; link_id = node->link_id; - namedq = node->namedq; publ_list = &node->publ_list; - node->action_flags &= ~(TIPC_MSG_EVT | - TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP | + node->action_flags &= ~(TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP | TIPC_NOTIFY_LINK_DOWN | TIPC_NOTIFY_LINK_UP | TIPC_WAKEUP_BCAST_USERS | TIPC_BCAST_MSG_EVT | - TIPC_NAMED_MSG_EVT | TIPC_BCAST_RESET); + TIPC_BCAST_RESET); spin_unlock_bh(&node->lock); @@ -512,17 +939,11 @@ void tipc_node_unlock(struct tipc_node *node) tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr, link_id, addr); - if (flags & TIPC_MSG_EVT) - tipc_sk_rcv(net, inputq); - - if (flags & TIPC_NAMED_MSG_EVT) - tipc_named_rcv(net, namedq); - if (flags & TIPC_BCAST_MSG_EVT) tipc_bclink_input(net); if (flags & TIPC_BCAST_RESET) - tipc_link_reset_all(node); + tipc_node_reset_links(node); } /* Caller should hold node lock for the passed node */ @@ -559,6 +980,279 @@ msg_full: return -EMSGSIZE; } +static struct tipc_link *tipc_node_select_link(struct tipc_node *n, int sel, + int *bearer_id, + struct tipc_media_addr **maddr) +{ + int id = n->active_links[sel & 1]; + + if (unlikely(id < 0)) + return NULL; + + *bearer_id = id; + *maddr = &n->links[id].maddr; + return n->links[id].link; +} + +/** + * tipc_node_xmit() is the general link level function for message sending + * @net: the applicable net namespace + * @list: chain of buffers containing message + * @dnode: address of destination node + * @selector: a number used for deterministic link selection + * Consumes the buffer chain, except when returning -ELINKCONG + * Returns 0 if success, otherwise errno: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE + */ +int tipc_node_xmit(struct net *net, struct sk_buff_head *list, + u32 dnode, int selector) +{ + struct tipc_link *l = NULL; + struct tipc_node *n; + struct sk_buff_head xmitq; + struct tipc_media_addr *maddr; + int bearer_id; + int rc = -EHOSTUNREACH; + + __skb_queue_head_init(&xmitq); + n = tipc_node_find(net, dnode); + if (likely(n)) { + tipc_node_lock(n); + l = tipc_node_select_link(n, selector, &bearer_id, &maddr); + if (likely(l)) + rc = tipc_link_xmit(l, list, &xmitq); + tipc_node_unlock(n); + if (unlikely(rc == -ENOBUFS)) + tipc_node_link_down(n, bearer_id, false); + tipc_node_put(n); + } + if (likely(!rc)) { + tipc_bearer_xmit(net, bearer_id, &xmitq, maddr); + return 0; + } + if (likely(in_own_node(net, dnode))) { + tipc_sk_rcv(net, list); + return 0; + } + return rc; +} + +/* tipc_node_xmit_skb(): send single buffer to destination + * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE + * messages, which will not be rejected + * The only exception is datagram messages rerouted after secondary + * lookup, which are rare and safe to dispose of anyway. + * TODO: Return real return value, and let callers use + * tipc_wait_for_sendpkt() where applicable + */ +int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dnode, + u32 selector) +{ + struct sk_buff_head head; + int rc; + + skb_queue_head_init(&head); + __skb_queue_tail(&head, skb); + rc = tipc_node_xmit(net, &head, dnode, selector); + if (rc == -ELINKCONG) + kfree_skb(skb); + return 0; +} + +/** + * tipc_node_check_state - check and if necessary update node state + * @skb: TIPC packet + * @bearer_id: identity of bearer delivering the packet + * Returns true if state is ok, otherwise consumes buffer and returns false + */ +static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, + int bearer_id, struct sk_buff_head *xmitq) +{ + struct tipc_msg *hdr = buf_msg(skb); + int usr = msg_user(hdr); + int mtyp = msg_type(hdr); + u16 oseqno = msg_seqno(hdr); + u16 iseqno = msg_seqno(msg_get_wrapped(hdr)); + u16 exp_pkts = msg_msgcnt(hdr); + u16 rcv_nxt, syncpt, dlv_nxt; + int state = n->state; + struct tipc_link *l, *pl = NULL; + struct tipc_media_addr *maddr; + int i, pb_id; + + l = n->links[bearer_id].link; + if (!l) + return false; + rcv_nxt = l->rcv_nxt; + + + if (likely((state == SELF_UP_PEER_UP) && (usr != TUNNEL_PROTOCOL))) + return true; + + /* Find parallel link, if any */ + for (i = 0; i < MAX_BEARERS; i++) { + if ((i != bearer_id) && n->links[i].link) { + pl = n->links[i].link; + break; + } + } + + /* Update node accesibility if applicable */ + if (state == SELF_UP_PEER_COMING) { + if (!tipc_link_is_up(l)) + return true; + if (!msg_peer_link_is_up(hdr)) + return true; + tipc_node_fsm_evt(n, PEER_ESTABL_CONTACT_EVT); + } + + if (state == SELF_DOWN_PEER_LEAVING) { + if (msg_peer_node_is_up(hdr)) + return false; + tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT); + } + + /* Ignore duplicate packets */ + if (less(oseqno, rcv_nxt)) + return true; + + /* Initiate or update failover mode if applicable */ + if ((usr == TUNNEL_PROTOCOL) && (mtyp == FAILOVER_MSG)) { + syncpt = oseqno + exp_pkts - 1; + if (pl && tipc_link_is_up(pl)) { + pb_id = pl->bearer_id; + __tipc_node_link_down(n, &pb_id, xmitq, &maddr); + tipc_skb_queue_splice_tail_init(pl->inputq, l->inputq); + } + /* If pkts arrive out of order, use lowest calculated syncpt */ + if (less(syncpt, n->sync_point)) + n->sync_point = syncpt; + } + + /* Open parallel link when tunnel link reaches synch point */ + if ((n->state == NODE_FAILINGOVER) && !tipc_link_is_failingover(l)) { + if (!more(rcv_nxt, n->sync_point)) + return true; + tipc_node_fsm_evt(n, NODE_FAILOVER_END_EVT); + if (pl) + tipc_link_fsm_evt(pl, LINK_FAILOVER_END_EVT); + return true; + } + + /* Initiate or update synch mode if applicable */ + if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG)) { + syncpt = iseqno + exp_pkts - 1; + if (!tipc_link_is_up(l)) { + tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); + __tipc_node_link_up(n, bearer_id, xmitq); + } + if (n->state == SELF_UP_PEER_UP) { + n->sync_point = syncpt; + tipc_link_fsm_evt(l, LINK_SYNCH_BEGIN_EVT); + tipc_node_fsm_evt(n, NODE_SYNCH_BEGIN_EVT); + } + if (less(syncpt, n->sync_point)) + n->sync_point = syncpt; + } + + /* Open tunnel link when parallel link reaches synch point */ + if ((n->state == NODE_SYNCHING) && tipc_link_is_synching(l)) { + if (pl) + dlv_nxt = mod(pl->rcv_nxt - skb_queue_len(pl->inputq)); + if (!pl || more(dlv_nxt, n->sync_point)) { + tipc_link_fsm_evt(l, LINK_SYNCH_END_EVT); + tipc_node_fsm_evt(n, NODE_SYNCH_END_EVT); + return true; + } + if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG)) + return true; + if (usr == LINK_PROTOCOL) + return true; + return false; + } + return true; +} + +/** + * tipc_rcv - process TIPC packets/messages arriving from off-node + * @net: the applicable net namespace + * @skb: TIPC packet + * @bearer: pointer to bearer message arrived on + * + * Invoked with no locks held. Bearer pointer must point to a valid bearer + * structure (i.e. cannot be NULL), but bearer can be inactive. + */ +void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) +{ + struct sk_buff_head xmitq; + struct tipc_node *n; + struct tipc_msg *hdr = buf_msg(skb); + int usr = msg_user(hdr); + int bearer_id = b->identity; + struct tipc_link_entry *le; + int rc = 0; + + __skb_queue_head_init(&xmitq); + + /* Ensure message is well-formed */ + if (unlikely(!tipc_msg_validate(skb))) + goto discard; + + /* Handle arrival of a non-unicast link packet */ + if (unlikely(msg_non_seq(hdr))) { + if (usr == LINK_CONFIG) + tipc_disc_rcv(net, skb, b); + else + tipc_bclink_rcv(net, skb); + return; + } + + /* Locate neighboring node that sent packet */ + n = tipc_node_find(net, msg_prevnode(hdr)); + if (unlikely(!n)) + goto discard; + le = &n->links[bearer_id]; + + tipc_node_lock(n); + + /* Is reception permitted at the moment ? */ + if (!tipc_node_filter_pkt(n, hdr)) + goto unlock; + + if (unlikely(msg_user(hdr) == LINK_PROTOCOL)) + tipc_bclink_sync_state(n, hdr); + + /* Release acked broadcast packets */ + if (unlikely(n->bclink.acked != msg_bcast_ack(hdr))) + tipc_bclink_acknowledge(n, msg_bcast_ack(hdr)); + + /* Check and if necessary update node state */ + if (likely(tipc_node_check_state(n, skb, bearer_id, &xmitq))) { + rc = tipc_link_rcv(le->link, skb, &xmitq); + skb = NULL; + } +unlock: + tipc_node_unlock(n); + + if (unlikely(rc & TIPC_LINK_UP_EVT)) + tipc_node_link_up(n, bearer_id, &xmitq); + + if (unlikely(rc & TIPC_LINK_DOWN_EVT)) + tipc_node_link_down(n, bearer_id, false); + + if (unlikely(!skb_queue_empty(&n->bclink.namedq))) + tipc_named_rcv(net, &n->bclink.namedq); + + if (!skb_queue_empty(&le->inputq)) + tipc_sk_rcv(net, &le->inputq); + + if (!skb_queue_empty(&xmitq)) + tipc_bearer_xmit(net, bearer_id, &xmitq, &le->maddr); + + tipc_node_put(n); +discard: + kfree_skb(skb); +} + int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb) { int err; diff --git a/net/tipc/node.h b/net/tipc/node.h index 5a834cf..344b3e7 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -45,23 +45,19 @@ /* Out-of-range value for node signature */ #define INVALID_NODE_SIG 0x10000 +#define INVALID_BEARER_ID -1 + /* Flags used to take different actions according to flag type - * TIPC_WAIT_PEER_LINKS_DOWN: wait to see that peer's links are down - * TIPC_WAIT_OWN_LINKS_DOWN: wait until peer node is declared down * TIPC_NOTIFY_NODE_DOWN: notify node is down * TIPC_NOTIFY_NODE_UP: notify node is up * TIPC_DISTRIBUTE_NAME: publish or withdraw link state name type */ enum { - TIPC_MSG_EVT = 1, - TIPC_WAIT_PEER_LINKS_DOWN = (1 << 1), - TIPC_WAIT_OWN_LINKS_DOWN = (1 << 2), TIPC_NOTIFY_NODE_DOWN = (1 << 3), TIPC_NOTIFY_NODE_UP = (1 << 4), TIPC_WAKEUP_BCAST_USERS = (1 << 5), TIPC_NOTIFY_LINK_UP = (1 << 6), TIPC_NOTIFY_LINK_DOWN = (1 << 7), - TIPC_NAMED_MSG_EVT = (1 << 8), TIPC_BCAST_MSG_EVT = (1 << 9), TIPC_BCAST_RESET = (1 << 10) }; @@ -85,10 +81,17 @@ struct tipc_node_bclink { u32 deferred_size; struct sk_buff_head deferdq; struct sk_buff *reasm_buf; - int inputq_map; + struct sk_buff_head namedq; bool recv_permitted; }; +struct tipc_link_entry { + struct tipc_link *link; + u32 mtu; + struct sk_buff_head inputq; + struct tipc_media_addr maddr; +}; + /** * struct tipc_node - TIPC node structure * @addr: network address of node @@ -98,11 +101,12 @@ struct tipc_node_bclink { * @hash: links to adjacent nodes in unsorted hash chain * @inputq: pointer to input queue containing messages for msg event * @namedq: pointer to name table input queue with name table messages - * @curr_link: the link holding the node lock, if any - * @active_links: pointers to active links to node - * @links: pointers to all links to node + * @active_links: bearer ids of active links, used as index into links[] array + * @links: array containing references to all links to node * @action_flags: bit mask of different types of node actions * @bclink: broadcast-related info + * @state: connectivity state vs peer node + * @sync_point: sequence number where synch/failover is finished * @list: links to adjacent nodes in sorted list of cluster's nodes * @working_links: number of working links to node (both active and standby) * @link_cnt: number of links to node @@ -118,14 +122,13 @@ struct tipc_node { spinlock_t lock; struct net *net; struct hlist_node hash; - struct sk_buff_head *inputq; - struct sk_buff_head *namedq; - struct tipc_link *active_links[2]; - u32 act_mtus[2]; - struct tipc_link *links[MAX_BEARERS]; + int active_links[2]; + struct tipc_link_entry links[MAX_BEARERS]; int action_flags; struct tipc_node_bclink bclink; struct list_head list; + int state; + u16 sync_point; int link_cnt; u16 working_links; u16 capabilities; @@ -133,25 +136,32 @@ struct tipc_node { u32 link_id; struct list_head publ_list; struct list_head conn_sks; + unsigned long keepalive_intv; + struct timer_list timer; struct rcu_head rcu; }; struct tipc_node *tipc_node_find(struct net *net, u32 addr); void tipc_node_put(struct tipc_node *node); -struct tipc_node *tipc_node_create(struct net *net, u32 addr); void tipc_node_stop(struct net *net); +void tipc_node_check_dest(struct net *net, u32 onode, + struct tipc_bearer *bearer, + u16 capabilities, u32 signature, + struct tipc_media_addr *maddr, + bool *respond, bool *dupl_addr); +void tipc_node_delete_links(struct net *net, int bearer_id); void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr); -void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr); -void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr); -int tipc_node_active_links(struct tipc_node *n_ptr); -int tipc_node_is_up(struct tipc_node *n_ptr); +bool tipc_node_is_up(struct tipc_node *n); int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, char *linkname, size_t len); void tipc_node_unlock(struct tipc_node *node); +int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, + int selector); +int tipc_node_xmit_skb(struct net *net, struct sk_buff *skb, u32 dest, + u32 selector); int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port); void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port); - int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb); static inline void tipc_node_lock(struct tipc_node *node) @@ -159,26 +169,30 @@ static inline void tipc_node_lock(struct tipc_node *node) spin_lock_bh(&node->lock); } -static inline bool tipc_node_blocked(struct tipc_node *node) +static inline struct tipc_link *node_active_link(struct tipc_node *n, int sel) { - return (node->action_flags & (TIPC_WAIT_PEER_LINKS_DOWN | - TIPC_NOTIFY_NODE_DOWN | TIPC_WAIT_OWN_LINKS_DOWN)); + int bearer_id = n->active_links[sel & 1]; + + if (unlikely(bearer_id == INVALID_BEARER_ID)) + return NULL; + + return n->links[bearer_id].link; } -static inline uint tipc_node_get_mtu(struct net *net, u32 addr, u32 selector) +static inline unsigned int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel) { - struct tipc_node *node; - u32 mtu; - - node = tipc_node_find(net, addr); + struct tipc_node *n; + int bearer_id; + unsigned int mtu = MAX_MSG_SIZE; - if (likely(node)) { - mtu = node->act_mtus[selector & 1]; - tipc_node_put(node); - } else { - mtu = MAX_MSG_SIZE; - } + n = tipc_node_find(net, addr); + if (unlikely(!n)) + return mtu; + bearer_id = n->active_links[sel & 1]; + if (likely(bearer_id != INVALID_BEARER_ID)) + mtu = n->links[bearer_id].mtu; + tipc_node_put(n); return mtu; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3a7567f..1060d52 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -248,6 +248,22 @@ static void tsk_advance_rx_queue(struct sock *sk) kfree_skb(__skb_dequeue(&sk->sk_receive_queue)); } +/* tipc_sk_respond() : send response message back to sender + */ +static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err) +{ + u32 selector; + u32 dnode; + u32 onode = tipc_own_addr(sock_net(sk)); + + if (!tipc_msg_reverse(onode, &skb, err)) + return; + + dnode = msg_destnode(buf_msg(skb)); + selector = msg_origport(buf_msg(skb)); + tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector); +} + /** * tsk_rej_rx_queue - reject all buffers in socket receive queue * @@ -256,13 +272,9 @@ static void tsk_advance_rx_queue(struct sock *sk) static void tsk_rej_rx_queue(struct sock *sk) { struct sk_buff *skb; - u32 dnode; - u32 own_node = tsk_own_node(tipc_sk(sk)); - while ((skb = __skb_dequeue(&sk->sk_receive_queue))) { - if (tipc_msg_reverse(own_node, skb, &dnode, TIPC_ERR_NO_PORT)) - tipc_link_xmit_skb(sock_net(sk), skb, dnode, 0); - } + while ((skb = __skb_dequeue(&sk->sk_receive_queue))) + tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT); } /* tsk_peer_msg - verify if message was sent by connected port's peer @@ -441,9 +453,7 @@ static int tipc_release(struct socket *sock) tsk->connected = 0; tipc_node_remove_conn(net, dnode, tsk->portid); } - if (tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, - TIPC_ERR_NO_PORT)) - tipc_link_xmit_skb(net, skb, dnode, 0); + tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT); } } @@ -456,7 +466,7 @@ static int tipc_release(struct socket *sock) tsk_own_node(tsk), tsk_peer_port(tsk), tsk->portid, TIPC_ERR_NO_PORT); if (skb) - tipc_link_xmit_skb(net, skb, dnode, tsk->portid); + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); tipc_node_remove_conn(net, dnode, tsk->portid); } @@ -686,21 +696,22 @@ new_mtu: do { rc = tipc_bclink_xmit(net, pktchain); - if (likely(rc >= 0)) { - rc = dsz; - break; + if (likely(!rc)) + return dsz; + + if (rc == -ELINKCONG) { + tsk->link_cong = 1; + rc = tipc_wait_for_sndmsg(sock, &timeo); + if (!rc) + continue; } + __skb_queue_purge(pktchain); if (rc == -EMSGSIZE) { msg->msg_iter = save; goto new_mtu; } - if (rc != -ELINKCONG) - break; - tipc_sk(sk)->link_cong = 1; - rc = tipc_wait_for_sndmsg(sock, &timeo); - if (rc) - __skb_queue_purge(pktchain); - } while (!rc); + break; + } while (1); return rc; } @@ -763,35 +774,35 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, /** * tipc_sk_proto_rcv - receive a connection mng protocol message * @tsk: receiving socket - * @skb: pointer to message buffer. Set to NULL if buffer is consumed. + * @skb: pointer to message buffer. */ -static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff **skb) +static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb) { - struct tipc_msg *msg = buf_msg(*skb); + struct sock *sk = &tsk->sk; + struct tipc_msg *hdr = buf_msg(skb); + int mtyp = msg_type(hdr); int conn_cong; - u32 dnode; - u32 own_node = tsk_own_node(tsk); + /* Ignore if connection cannot be validated: */ - if (!tsk_peer_msg(tsk, msg)) + if (!tsk_peer_msg(tsk, hdr)) goto exit; tsk->probing_state = TIPC_CONN_OK; - if (msg_type(msg) == CONN_ACK) { + if (mtyp == CONN_PROBE) { + msg_set_type(hdr, CONN_PROBE_REPLY); + tipc_sk_respond(sk, skb, TIPC_OK); + return; + } else if (mtyp == CONN_ACK) { conn_cong = tsk_conn_cong(tsk); - tsk->sent_unacked -= msg_msgcnt(msg); + tsk->sent_unacked -= msg_msgcnt(hdr); if (conn_cong) - tsk->sk.sk_write_space(&tsk->sk); - } else if (msg_type(msg) == CONN_PROBE) { - if (tipc_msg_reverse(own_node, *skb, &dnode, TIPC_OK)) { - msg_set_type(msg, CONN_PROBE_REPLY); - return; - } + sk->sk_write_space(sk); + } else if (mtyp != CONN_PROBE_REPLY) { + pr_warn("Received unknown CONN_PROTO msg\n"); } - /* Do nothing if msg_type() == CONN_PROBE_REPLY */ exit: - kfree_skb(*skb); - *skb = NULL; + kfree_skb(skb); } static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) @@ -924,24 +935,25 @@ new_mtu: do { skb = skb_peek(pktchain); TIPC_SKB_CB(skb)->wakeup_pending = tsk->link_cong; - rc = tipc_link_xmit(net, pktchain, dnode, tsk->portid); - if (likely(rc >= 0)) { + rc = tipc_node_xmit(net, pktchain, dnode, tsk->portid); + if (likely(!rc)) { if (sock->state != SS_READY) sock->state = SS_CONNECTING; - rc = dsz; - break; + return dsz; } + if (rc == -ELINKCONG) { + tsk->link_cong = 1; + rc = tipc_wait_for_sndmsg(sock, &timeo); + if (!rc) + continue; + } + __skb_queue_purge(pktchain); if (rc == -EMSGSIZE) { m->msg_iter = save; goto new_mtu; } - if (rc != -ELINKCONG) - break; - tsk->link_cong = 1; - rc = tipc_wait_for_sndmsg(sock, &timeo); - if (rc) - __skb_queue_purge(pktchain); - } while (!rc); + break; + } while (1); return rc; } @@ -1043,15 +1055,16 @@ next: return rc; do { if (likely(!tsk_conn_cong(tsk))) { - rc = tipc_link_xmit(net, pktchain, dnode, portid); + rc = tipc_node_xmit(net, pktchain, dnode, portid); if (likely(!rc)) { tsk->sent_unacked++; sent += send; if (sent == dsz) - break; + return dsz; goto next; } if (rc == -EMSGSIZE) { + __skb_queue_purge(pktchain); tsk->max_pkt = tipc_node_get_mtu(net, dnode, portid); m->msg_iter = save; @@ -1059,13 +1072,13 @@ next: } if (rc != -ELINKCONG) break; + tsk->link_cong = 1; } rc = tipc_wait_for_sndpkt(sock, &timeo); - if (rc) - __skb_queue_purge(pktchain); } while (!rc); + __skb_queue_purge(pktchain); return sent ? sent : rc; } @@ -1221,7 +1234,7 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk, uint ack) return; msg = buf_msg(skb); msg_set_msgcnt(msg, ack); - tipc_link_xmit_skb(net, skb, dnode, msg_link_selector(msg)); + tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg)); } static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) @@ -1507,82 +1520,81 @@ static void tipc_data_ready(struct sock *sk) * @tsk: TIPC socket * @skb: pointer to message buffer. Set to NULL if buffer is consumed * - * Returns 0 (TIPC_OK) if everything ok, -TIPC_ERR_NO_PORT otherwise + * Returns true if everything ok, false otherwise */ -static int filter_connect(struct tipc_sock *tsk, struct sk_buff **skb) +static bool filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) { struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); struct socket *sock = sk->sk_socket; - struct tipc_msg *msg = buf_msg(*skb); - int retval = -TIPC_ERR_NO_PORT; + struct tipc_msg *hdr = buf_msg(skb); - if (msg_mcast(msg)) - return retval; + if (unlikely(msg_mcast(hdr))) + return false; switch ((int)sock->state) { case SS_CONNECTED: + /* Accept only connection-based messages sent by peer */ - if (tsk_peer_msg(tsk, msg)) { - if (unlikely(msg_errcode(msg))) { - sock->state = SS_DISCONNECTING; - tsk->connected = 0; - /* let timer expire on it's own */ - tipc_node_remove_conn(net, tsk_peer_node(tsk), - tsk->portid); - } - retval = TIPC_OK; + if (unlikely(!tsk_peer_msg(tsk, hdr))) + return false; + + if (unlikely(msg_errcode(hdr))) { + sock->state = SS_DISCONNECTING; + tsk->connected = 0; + /* Let timer expire on it's own */ + tipc_node_remove_conn(net, tsk_peer_node(tsk), + tsk->portid); } - break; + return true; + case SS_CONNECTING: - /* Accept only ACK or NACK message */ - if (unlikely(!msg_connected(msg))) - break; + /* Accept only ACK or NACK message */ + if (unlikely(!msg_connected(hdr))) + return false; - if (unlikely(msg_errcode(msg))) { + if (unlikely(msg_errcode(hdr))) { sock->state = SS_DISCONNECTING; sk->sk_err = ECONNREFUSED; - retval = TIPC_OK; - break; + return true; } - if (unlikely(msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE)) { + if (unlikely(!msg_isdata(hdr))) { sock->state = SS_DISCONNECTING; sk->sk_err = EINVAL; - retval = TIPC_OK; - break; + return true; } - tipc_sk_finish_conn(tsk, msg_origport(msg), msg_orignode(msg)); - msg_set_importance(&tsk->phdr, msg_importance(msg)); + tipc_sk_finish_conn(tsk, msg_origport(hdr), msg_orignode(hdr)); + msg_set_importance(&tsk->phdr, msg_importance(hdr)); sock->state = SS_CONNECTED; - /* If an incoming message is an 'ACK-', it should be - * discarded here because it doesn't contain useful - * data. In addition, we should try to wake up - * connect() routine if sleeping. - */ - if (msg_data_sz(msg) == 0) { - kfree_skb(*skb); - *skb = NULL; - if (waitqueue_active(sk_sleep(sk))) - wake_up_interruptible(sk_sleep(sk)); - } - retval = TIPC_OK; - break; + /* If 'ACK+' message, add to socket receive queue */ + if (msg_data_sz(hdr)) + return true; + + /* If empty 'ACK-' message, wake up sleeping connect() */ + if (waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); + + /* 'ACK-' message is neither accepted nor rejected: */ + msg_set_dest_droppable(hdr, 1); + return false; + case SS_LISTENING: case SS_UNCONNECTED: + /* Accept only SYN message */ - if (!msg_connected(msg) && !(msg_errcode(msg))) - retval = TIPC_OK; + if (!msg_connected(hdr) && !(msg_errcode(hdr))) + return true; break; case SS_DISCONNECTING: break; default: pr_err("Unknown socket state %u\n", sock->state); } - return retval; + return false; } /** @@ -1617,61 +1629,70 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) /** * filter_rcv - validate incoming message * @sk: socket - * @skb: pointer to message. Set to NULL if buffer is consumed. + * @skb: pointer to message. * * Enqueues message on receive queue if acceptable; optionally handles * disconnect indication for a connected socket. * * Called with socket lock already taken * - * Returns 0 (TIPC_OK) if message was ok, -TIPC error code if rejected + * Returns true if message was added to socket receive queue, otherwise false */ -static int filter_rcv(struct sock *sk, struct sk_buff **skb) +static bool filter_rcv(struct sock *sk, struct sk_buff *skb) { struct socket *sock = sk->sk_socket; struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_msg *msg = buf_msg(*skb); - unsigned int limit = rcvbuf_limit(sk, *skb); - int rc = TIPC_OK; + struct tipc_msg *hdr = buf_msg(skb); + unsigned int limit = rcvbuf_limit(sk, skb); + int err = TIPC_OK; + int usr = msg_user(hdr); - if (unlikely(msg_user(msg) == CONN_MANAGER)) { + if (unlikely(msg_user(hdr) == CONN_MANAGER)) { tipc_sk_proto_rcv(tsk, skb); - return TIPC_OK; + return false; } - if (unlikely(msg_user(msg) == SOCK_WAKEUP)) { - kfree_skb(*skb); + if (unlikely(usr == SOCK_WAKEUP)) { + kfree_skb(skb); tsk->link_cong = 0; sk->sk_write_space(sk); - *skb = NULL; - return TIPC_OK; + return false; } - /* Reject message if it is wrong sort of message for socket */ - if (msg_type(msg) > TIPC_DIRECT_MSG) - return -TIPC_ERR_NO_PORT; + /* Drop if illegal message type */ + if (unlikely(msg_type(hdr) > TIPC_DIRECT_MSG)) { + kfree_skb(skb); + return false; + } - if (sock->state == SS_READY) { - if (msg_connected(msg)) - return -TIPC_ERR_NO_PORT; - } else { - rc = filter_connect(tsk, skb); - if (rc != TIPC_OK || !*skb) - return rc; + /* Reject if wrong message type for current socket state */ + if (unlikely(sock->state == SS_READY)) { + if (msg_connected(hdr)) { + err = TIPC_ERR_NO_PORT; + goto reject; + } + } else if (unlikely(!filter_connect(tsk, skb))) { + err = TIPC_ERR_NO_PORT; + goto reject; } /* Reject message if there isn't room to queue it */ - if (sk_rmem_alloc_get(sk) + (*skb)->truesize >= limit) - return -TIPC_ERR_OVERLOAD; + if (unlikely(sk_rmem_alloc_get(sk) + skb->truesize >= limit)) { + err = TIPC_ERR_OVERLOAD; + goto reject; + } /* Enqueue message */ - TIPC_SKB_CB(*skb)->handle = NULL; - __skb_queue_tail(&sk->sk_receive_queue, *skb); - skb_set_owner_r(*skb, sk); + TIPC_SKB_CB(skb)->handle = NULL; + __skb_queue_tail(&sk->sk_receive_queue, skb); + skb_set_owner_r(skb, sk); sk->sk_data_ready(sk); - *skb = NULL; - return TIPC_OK; + return true; + +reject: + tipc_sk_respond(sk, skb, err); + return false; } /** @@ -1685,22 +1706,10 @@ static int filter_rcv(struct sock *sk, struct sk_buff **skb) */ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) { - int err; - atomic_t *dcnt; - u32 dnode; - struct tipc_sock *tsk = tipc_sk(sk); - struct net *net = sock_net(sk); - uint truesize = skb->truesize; + unsigned int truesize = skb->truesize; - err = filter_rcv(sk, &skb); - if (likely(!skb)) { - dcnt = &tsk->dupl_rcvcnt; - if (atomic_read(dcnt) < TIPC_CONN_OVERLOAD_LIMIT) - atomic_add(truesize, dcnt); - return 0; - } - if (!err || tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, -err)) - tipc_link_xmit_skb(net, skb, dnode, tsk->portid); + if (likely(filter_rcv(sk, skb))) + atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt); return 0; } @@ -1710,45 +1719,43 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) * @inputq: list of incoming buffers with potentially different destinations * @sk: socket where the buffers should be enqueued * @dport: port number for the socket - * @_skb: returned buffer to be forwarded or rejected, if applicable * * Caller must hold socket lock - * - * Returns TIPC_OK if all buffers enqueued, otherwise -TIPC_ERR_OVERLOAD - * or -TIPC_ERR_NO_PORT */ -static int tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, - u32 dport, struct sk_buff **_skb) +static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, + u32 dport) { unsigned int lim; atomic_t *dcnt; - int err; struct sk_buff *skb; unsigned long time_limit = jiffies + 2; while (skb_queue_len(inputq)) { if (unlikely(time_after_eq(jiffies, time_limit))) - return TIPC_OK; + return; + skb = tipc_skb_dequeue(inputq, dport); if (unlikely(!skb)) - return TIPC_OK; + return; + + /* Add message directly to receive queue if possible */ if (!sock_owned_by_user(sk)) { - err = filter_rcv(sk, &skb); - if (likely(!skb)) - continue; - *_skb = skb; - return err; + filter_rcv(sk, skb); + continue; } + + /* Try backlog, compensating for double-counted bytes */ dcnt = &tipc_sk(sk)->dupl_rcvcnt; if (sk->sk_backlog.len) atomic_set(dcnt, 0); lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt); if (likely(!sk_add_backlog(sk, skb, lim))) continue; - *_skb = skb; - return -TIPC_ERR_OVERLOAD; + + /* Overload => reject message back to sender */ + tipc_sk_respond(sk, skb, TIPC_ERR_OVERLOAD); + break; } - return TIPC_OK; } /** @@ -1756,49 +1763,46 @@ static int tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, * @inputq: buffer list containing the buffers * Consumes all buffers in list until inputq is empty * Note: may be called in multiple threads referring to the same queue - * Returns 0 if last buffer was accepted, otherwise -EHOSTUNREACH - * Only node local calls check the return value, sending single-buffer queues */ -int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) +void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) { u32 dnode, dport = 0; int err; - struct sk_buff *skb; struct tipc_sock *tsk; - struct tipc_net *tn; struct sock *sk; + struct sk_buff *skb; while (skb_queue_len(inputq)) { - err = -TIPC_ERR_NO_PORT; - skb = NULL; dport = tipc_skb_peek_port(inputq, dport); tsk = tipc_sk_lookup(net, dport); + if (likely(tsk)) { sk = &tsk->sk; if (likely(spin_trylock_bh(&sk->sk_lock.slock))) { - err = tipc_sk_enqueue(inputq, sk, dport, &skb); + tipc_sk_enqueue(inputq, sk, dport); spin_unlock_bh(&sk->sk_lock.slock); - dport = 0; } sock_put(sk); - } else { - skb = tipc_skb_dequeue(inputq, dport); - } - if (likely(!skb)) continue; - if (tipc_msg_lookup_dest(net, skb, &dnode, &err)) - goto xmit; - if (!err) { - dnode = msg_destnode(buf_msg(skb)); - goto xmit; } - tn = net_generic(net, tipc_net_id); - if (!tipc_msg_reverse(tn->own_addr, skb, &dnode, -err)) + + /* No destination socket => dequeue skb if still there */ + skb = tipc_skb_dequeue(inputq, dport); + if (!skb) + return; + + /* Try secondary lookup if unresolved named message */ + err = TIPC_ERR_NO_PORT; + if (tipc_msg_lookup_dest(net, skb, &err)) + goto xmit; + + /* Prepare for message rejection */ + if (!tipc_msg_reverse(tipc_own_addr(net), &skb, err)) continue; xmit: - tipc_link_xmit_skb(net, skb, dnode, dport); + dnode = msg_destnode(buf_msg(skb)); + tipc_node_xmit_skb(net, skb, dnode, dport); } - return err ? -EHOSTUNREACH : 0; } static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) @@ -2067,7 +2071,10 @@ static int tipc_shutdown(struct socket *sock, int how) struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); struct sk_buff *skb; - u32 dnode; + u32 dnode = tsk_peer_node(tsk); + u32 dport = tsk_peer_port(tsk); + u32 onode = tipc_own_addr(net); + u32 oport = tsk->portid; int res; if (how != SHUT_RDWR) @@ -2080,6 +2087,8 @@ static int tipc_shutdown(struct socket *sock, int how) case SS_CONNECTED: restart: + dnode = tsk_peer_node(tsk); + /* Disconnect and send a 'FIN+' or 'FIN-' message to peer */ skb = __skb_dequeue(&sk->sk_receive_queue); if (skb) { @@ -2087,19 +2096,13 @@ restart: kfree_skb(skb); goto restart; } - if (tipc_msg_reverse(tsk_own_node(tsk), skb, &dnode, - TIPC_CONN_SHUTDOWN)) - tipc_link_xmit_skb(net, skb, dnode, - tsk->portid); + tipc_sk_respond(sk, skb, TIPC_CONN_SHUTDOWN); } else { - dnode = tsk_peer_node(tsk); - skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, - 0, dnode, tsk_own_node(tsk), - tsk_peer_port(tsk), - tsk->portid, TIPC_CONN_SHUTDOWN); - tipc_link_xmit_skb(net, skb, dnode, tsk->portid); + 0, dnode, onode, dport, oport, + TIPC_CONN_SHUTDOWN); + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); } tsk->connected = 0; sock->state = SS_DISCONNECTING; @@ -2161,7 +2164,7 @@ static void tipc_sk_timeout(unsigned long data) } bh_unlock_sock(sk); if (skb) - tipc_link_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid); + tipc_node_xmit_skb(sock_net(sk), skb, peer_node, tsk->portid); exit: sock_put(sk); } diff --git a/net/tipc/socket.h b/net/tipc/socket.h index bf65513..4241f22 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -44,7 +44,7 @@ SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE)) int tipc_socket_init(void); void tipc_socket_stop(void); -int tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq); +void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq); void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct sk_buff_head *inputq); void tipc_sk_reinit(struct net *net); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 66deebc..c170d31 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -194,7 +194,8 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, .saddr = src->ipv6, .flowi6_proto = IPPROTO_UDP }; - err = ipv6_stub->ipv6_dst_lookup(ub->ubsock->sk, &ndst, &fl6); + err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk, &ndst, + &fl6); if (err) goto tx_error; ttl = ip6_dst_hoplimit(ndst); diff --git a/net/wimax/op-rfkill.c b/net/wimax/op-rfkill.c index 7d73054..477364a 100644 --- a/net/wimax/op-rfkill.c +++ b/net/wimax/op-rfkill.c @@ -135,8 +135,7 @@ EXPORT_SYMBOL_GPL(wimax_report_rfkill_hw); * @state: New state of the RF kill switch. %WIMAX_RF_ON radio on, * %WIMAX_RF_OFF radio off. * - * Reports changes in the software RF switch state to the the WiMAX - * stack. + * Reports changes in the software RF switch state to the WiMAX stack. * * The main use is during initialization, so the driver can query the * device for its current software radio kill switch state and feed it diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index bd16c6c..0cebf1f 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2048,7 +2048,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, xfrm_audit_policy_delete(xp, 1, true); } else { // reset the timers here? - WARN(1, "Dont know what to do with soft policy expire\n"); + WARN(1, "Don't know what to do with soft policy expire\n"); } km_policy_expired(xp, p->dir, up->hard, nlh->nlmsg_pid); |