diff options
author | David S. Miller <davem@davemloft.net> | 2015-10-20 15:08:27 +0200 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2015-10-20 15:08:27 +0200 |
commit | 26440c835f8b1a491e2704118ac55bf87334366c (patch) | |
tree | 3c2d23b59fd49b252fdbf6c09efc41b354933fc6 /net | |
parent | Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next (diff) | |
parent | Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net (diff) | |
download | linux-26440c835f8b1a491e2704118ac55bf87334366c.tar.xz linux-26440c835f8b1a491e2704118ac55bf87334366c.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Conflicts:
drivers/net/usb/asix_common.c
net/ipv4/inet_connection_sock.c
net/switchdev/switchdev.c
In the inet_connection_sock.c case the request socket hashing scheme
is completely different in net-next.
The other two conflicts were overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
32 files changed, 404 insertions, 224 deletions
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index b4548c739a64..2dda439c8cb8 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -91,10 +91,50 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn) * autoconnect action, remove them completely. If they are, just unmark * them as waiting for connection, by clearing explicit_connect field. */ - if (params->auto_connect == HCI_AUTO_CONN_EXPLICIT) + params->explicit_connect = false; + + list_del_init(¶ms->action); + + switch (params->auto_connect) { + case HCI_AUTO_CONN_EXPLICIT: hci_conn_params_del(conn->hdev, bdaddr, bdaddr_type); - else - params->explicit_connect = false; + /* return instead of break to avoid duplicate scan update */ + return; + case HCI_AUTO_CONN_DIRECT: + case HCI_AUTO_CONN_ALWAYS: + list_add(¶ms->action, &conn->hdev->pend_le_conns); + break; + case HCI_AUTO_CONN_REPORT: + list_add(¶ms->action, &conn->hdev->pend_le_reports); + break; + default: + break; + } + + hci_update_background_scan(conn->hdev); +} + +static void hci_conn_cleanup(struct hci_conn *conn) +{ + struct hci_dev *hdev = conn->hdev; + + if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags)) + hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type); + + hci_chan_list_flush(conn); + + hci_conn_hash_del(hdev, conn); + + if (hdev->notify) + hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); + + hci_conn_del_sysfs(conn); + + debugfs_remove_recursive(conn->debugfs); + + hci_dev_put(hdev); + + hci_conn_put(conn); } /* This function requires the caller holds hdev->lock */ @@ -102,8 +142,13 @@ static void hci_connect_le_scan_remove(struct hci_conn *conn) { hci_connect_le_scan_cleanup(conn); - hci_conn_hash_del(conn->hdev, conn); - hci_update_background_scan(conn->hdev); + /* We can't call hci_conn_del here since that would deadlock + * with trying to call cancel_delayed_work_sync(&conn->disc_work). + * Instead, call just hci_conn_cleanup() which contains the bare + * minimum cleanup operations needed for a connection in this + * state. + */ + hci_conn_cleanup(conn); } static void hci_acl_create_connection(struct hci_conn *conn) @@ -581,27 +626,17 @@ int hci_conn_del(struct hci_conn *conn) } } - hci_chan_list_flush(conn); - if (conn->amp_mgr) amp_mgr_put(conn->amp_mgr); - hci_conn_hash_del(hdev, conn); - if (hdev->notify) - hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); - skb_queue_purge(&conn->data_q); - hci_conn_del_sysfs(conn); - - debugfs_remove_recursive(conn->debugfs); - - if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags)) - hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type); - - hci_dev_put(hdev); - - hci_conn_put(conn); + /* Remove the connection from the list and cleanup its remaining + * state. This is a separate function since for some cases like + * BT_CONNECT_SCAN we *only* want the cleanup part without the + * rest of hci_conn_del. + */ + hci_conn_cleanup(conn); return 0; } @@ -973,15 +1008,23 @@ static int hci_explicit_conn_params_set(struct hci_request *req, if (is_connected(hdev, addr, addr_type)) return -EISCONN; - params = hci_conn_params_add(hdev, addr, addr_type); - if (!params) - return -EIO; + params = hci_conn_params_lookup(hdev, addr, addr_type); + if (!params) { + params = hci_conn_params_add(hdev, addr, addr_type); + if (!params) + return -ENOMEM; - /* If we created new params, or existing params were marked as disabled, - * mark them to be used just once to connect. - */ - if (params->auto_connect == HCI_AUTO_CONN_DISABLED) { + /* If we created new params, mark them to be deleted in + * hci_connect_le_scan_cleanup. It's different case than + * existing disabled params, those will stay after cleanup. + */ params->auto_connect = HCI_AUTO_CONN_EXPLICIT; + } + + /* We're trying to connect, so make sure params are at pend_le_conns */ + if (params->auto_connect == HCI_AUTO_CONN_DISABLED || + params->auto_connect == HCI_AUTO_CONN_REPORT || + params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { list_del_init(¶ms->action); list_add(¶ms->action, &hdev->pend_le_conns); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index d2b3dd32d6cf..e4e53bd663df 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2930,13 +2930,6 @@ struct hci_conn_params *hci_explicit_connect_lookup(struct hci_dev *hdev, return param; } - list_for_each_entry(param, &hdev->pend_le_reports, action) { - if (bacmp(¶m->addr, addr) == 0 && - param->addr_type == addr_type && - param->explicit_connect) - return param; - } - return NULL; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 8acec932123a..b4571d84cafa 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -55,7 +55,12 @@ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb) wake_up_bit(&hdev->flags, HCI_INQUIRY); hci_dev_lock(hdev); - hci_discovery_set_state(hdev, DISCOVERY_STOPPED); + /* Set discovery state to stopped if we're not doing LE active + * scanning. + */ + if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) || + hdev->le_scan_type != LE_SCAN_ACTIVE) + hci_discovery_set_state(hdev, DISCOVERY_STOPPED); hci_dev_unlock(hdev); hci_conn_check_pending(hdev); @@ -4648,8 +4653,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, /* If we're not connectable only connect devices that we have in * our pend_le_conns list. */ - params = hci_explicit_connect_lookup(hdev, addr, addr_type); - + params = hci_pend_le_action_lookup(&hdev->pend_le_conns, addr, + addr_type); if (!params) return NULL; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ccaf5a436d8f..c4fe2fee753f 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -3545,6 +3545,7 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, auth_type); } else { u8 addr_type; + struct hci_conn_params *p; /* Convert from L2CAP channel address type to HCI address type */ @@ -3562,7 +3563,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, * If connection parameters already exist, then they * will be kept and this function does nothing. */ - hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + + if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT) + p->auto_connect = HCI_AUTO_CONN_DISABLED; conn = hci_connect_le_scan(hdev, &cp->addr.bdaddr, addr_type, sec_level, @@ -6117,14 +6121,21 @@ static int hci_conn_params_set(struct hci_request *req, bdaddr_t *addr, __hci_update_background_scan(req); break; case HCI_AUTO_CONN_REPORT: - list_add(¶ms->action, &hdev->pend_le_reports); + if (params->explicit_connect) + list_add(¶ms->action, &hdev->pend_le_conns); + else + list_add(¶ms->action, &hdev->pend_le_reports); __hci_update_background_scan(req); break; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: if (!is_connected(hdev, addr, addr_type)) { list_add(¶ms->action, &hdev->pend_le_conns); - __hci_update_background_scan(req); + /* If we are in scan phase of connecting, we were + * already added to pend_le_conns and scanning. + */ + if (params->auto_connect != HCI_AUTO_CONN_EXPLICIT) + __hci_update_background_scan(req); } break; } @@ -6379,7 +6390,8 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - if (params->auto_connect == HCI_AUTO_CONN_DISABLED) { + if (params->auto_connect == HCI_AUTO_CONN_DISABLED || + params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { err = cmd->cmd_complete(cmd, MGMT_STATUS_INVALID_PARAMS); mgmt_pending_remove(cmd); @@ -6415,6 +6427,10 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, if (p->auto_connect == HCI_AUTO_CONN_DISABLED) continue; device_removed(sk, hdev, &p->addr, p->addr_type); + if (p->explicit_connect) { + p->auto_connect = HCI_AUTO_CONN_EXPLICIT; + continue; + } list_del(&p->action); list_del(&p->list); kfree(p); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 80b94e37c94a..f79ccac6699f 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -285,6 +285,7 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req, switch (op->op) { case CEPH_OSD_OP_READ: case CEPH_OSD_OP_WRITE: + case CEPH_OSD_OP_WRITEFULL: ceph_osd_data_release(&op->extent.osd_data); break; case CEPH_OSD_OP_CALL: @@ -485,13 +486,14 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req, size_t payload_len = 0; BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && - opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE); + opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO && + opcode != CEPH_OSD_OP_TRUNCATE); op->extent.offset = offset; op->extent.length = length; op->extent.truncate_size = truncate_size; op->extent.truncate_seq = truncate_seq; - if (opcode == CEPH_OSD_OP_WRITE) + if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL) payload_len += length; op->payload_len = payload_len; @@ -670,9 +672,11 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, break; case CEPH_OSD_OP_READ: case CEPH_OSD_OP_WRITE: + case CEPH_OSD_OP_WRITEFULL: case CEPH_OSD_OP_ZERO: case CEPH_OSD_OP_TRUNCATE: - if (src->op == CEPH_OSD_OP_WRITE) + if (src->op == CEPH_OSD_OP_WRITE || + src->op == CEPH_OSD_OP_WRITEFULL) request_data_len = src->extent.length; dst->extent.offset = cpu_to_le64(src->extent.offset); dst->extent.length = cpu_to_le64(src->extent.length); @@ -681,7 +685,8 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req, dst->extent.truncate_seq = cpu_to_le32(src->extent.truncate_seq); osd_data = &src->extent.osd_data; - if (src->op == CEPH_OSD_OP_WRITE) + if (src->op == CEPH_OSD_OP_WRITE || + src->op == CEPH_OSD_OP_WRITEFULL) ceph_osdc_msg_data_add(req->r_request, osd_data); else ceph_osdc_msg_data_add(req->r_reply, osd_data); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index b495ab1797fa..29edf74846fc 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1284,7 +1284,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) gstrings.len = ret; - data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER); if (!data) return -ENOMEM; diff --git a/net/core/filter.c b/net/core/filter.c index 0b00094932ab..672eefbfbe99 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1414,6 +1414,7 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) return dev_forward_skb(dev, skb2); skb2->dev = dev; + skb_sender_cpu_clear(skb2); return dev_queue_xmit(skb2); } @@ -1941,9 +1942,13 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, goto out; /* We're copying the filter that has been originally attached, - * so no conversion/decode needed anymore. + * so no conversion/decode needed anymore. eBPF programs that + * have no original program cannot be dumped through this. */ + ret = -EACCES; fprog = filter->prog->orig_prog; + if (!fprog) + goto out; ret = fprog->len; if (!len) diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index aa398bcef9e3..1eba07feb34a 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -22,6 +22,7 @@ #include <linux/of_platform.h> #include <linux/of_net.h> #include <linux/sysfs.h> +#include <linux/phy_fixed.h> #include "dsa_priv.h" char dsa_driver_version[] = "0.1"; @@ -305,7 +306,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) if (ret < 0) goto out; - ds->slave_mii_bus = mdiobus_alloc(); + ds->slave_mii_bus = devm_mdiobus_alloc(parent); if (ds->slave_mii_bus == NULL) { ret = -ENOMEM; goto out; @@ -314,7 +315,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) ret = mdiobus_register(ds->slave_mii_bus); if (ret < 0) - goto out_free; + goto out; /* @@ -367,10 +368,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) return ret; -out_free: - mdiobus_free(ds->slave_mii_bus); out: - kfree(ds); return ret; } @@ -400,7 +398,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, /* * Allocate and initialise switch state. */ - ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL); + ds = devm_kzalloc(parent, sizeof(*ds) + drv->priv_size, GFP_KERNEL); if (ds == NULL) return ERR_PTR(-ENOMEM); @@ -420,10 +418,47 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, static void dsa_switch_destroy(struct dsa_switch *ds) { + struct device_node *port_dn; + struct phy_device *phydev; + struct dsa_chip_data *cd = ds->pd; + int port; + #ifdef CONFIG_NET_DSA_HWMON if (ds->hwmon_dev) hwmon_device_unregister(ds->hwmon_dev); #endif + + /* Disable configuration of the CPU and DSA ports */ + for (port = 0; port < DSA_MAX_PORTS; port++) { + if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))) + continue; + + port_dn = cd->port_dn[port]; + if (of_phy_is_fixed_link(port_dn)) { + phydev = of_phy_find_device(port_dn); + if (phydev) { + int addr = phydev->addr; + + phy_device_free(phydev); + of_node_put(port_dn); + fixed_phy_del(addr); + } + } + } + + /* Destroy network devices for physical switch ports. */ + for (port = 0; port < DSA_MAX_PORTS; port++) { + if (!(ds->phys_port_mask & (1 << port))) + continue; + + if (!ds->ports[port]) + continue; + + unregister_netdev(ds->ports[port]); + free_netdev(ds->ports[port]); + } + + mdiobus_unregister(ds->slave_mii_bus); } #ifdef CONFIG_PM_SLEEP @@ -802,10 +837,11 @@ static inline void dsa_of_remove(struct device *dev) } #endif -static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, - struct device *parent, struct dsa_platform_data *pd) +static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, + struct device *parent, struct dsa_platform_data *pd) { int i; + unsigned configured = 0; dst->pd = pd; dst->master_netdev = dev; @@ -825,9 +861,17 @@ static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, dst->ds[i] = ds; if (ds->drv->poll_link != NULL) dst->link_poll_needed = 1; + + ++configured; } /* + * If no switch was found, exit cleanly + */ + if (!configured) + return -EPROBE_DEFER; + + /* * If we use a tagging format that doesn't have an ethertype * field, make sure that all packets from this point on get * sent to the tag format's receive function. @@ -843,6 +887,8 @@ static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, dst->link_poll_timer.expires = round_jiffies(jiffies + HZ); add_timer(&dst->link_poll_timer); } + + return 0; } static int dsa_probe(struct platform_device *pdev) @@ -883,7 +929,7 @@ static int dsa_probe(struct platform_device *pdev) goto out; } - dst = kzalloc(sizeof(*dst), GFP_KERNEL); + dst = devm_kzalloc(&pdev->dev, sizeof(*dst), GFP_KERNEL); if (dst == NULL) { dev_put(dev); ret = -ENOMEM; @@ -892,7 +938,9 @@ static int dsa_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dst); - dsa_setup_dst(dst, dev, &pdev->dev, pd); + ret = dsa_setup_dst(dst, dev, &pdev->dev, pd); + if (ret) + goto out; return 0; @@ -914,7 +962,7 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) for (i = 0; i < dst->pd->nr_chips; i++) { struct dsa_switch *ds = dst->ds[i]; - if (ds != NULL) + if (ds) dsa_switch_destroy(ds); } } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 01308e6e6127..59b3e0e8fd51 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -312,7 +312,7 @@ static void arp_send_dst(int type, int ptype, __be32 dest_ip, if (!skb) return; - skb_dst_set(skb, dst); + skb_dst_set(skb, dst_clone(dst)); arp_xmit(skb); } @@ -384,7 +384,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE)) - dst = dst_clone(skb_dst(skb)); + dst = skb_dst(skb); arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, dst_hw, dev->dev_addr, NULL, dst); } @@ -816,7 +816,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) } else { pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); - return 0; + goto out_free_dst; } goto out; } @@ -870,6 +870,8 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) out: consume_skb(skb); +out_free_dst: + dst_release(reply_dst); return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f0326aae7a02..d135350495e8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3125,6 +3125,8 @@ static void addrconf_gre_config(struct net_device *dev) } addrconf_addr_gen(idev, true); + if (dev->flags & IFF_POINTOPOINT) + addrconf_add_mroute(dev); } #endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 23f97c4783bb..0c89671e0767 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -389,6 +389,9 @@ int ip6_forward(struct sk_buff *skb) if (skb->pkt_type != PACKET_HOST) goto drop; + if (unlikely(skb->sk)) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5fc1149fe91d..d0619632723a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -143,6 +143,9 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) struct net_device *loopback_dev = net->loopback_dev; int cpu; + if (dev == loopback_dev) + return; + for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); struct rt6_info *rt; @@ -152,14 +155,12 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) struct inet6_dev *rt_idev = rt->rt6i_idev; struct net_device *rt_dev = rt->dst.dev; - if (rt_idev && (rt_idev->dev == dev || !dev) && - rt_idev->dev != loopback_dev) { + if (rt_idev->dev == dev) { rt->rt6i_idev = in6_dev_get(loopback_dev); in6_dev_put(rt_idev); } - if (rt_dev && (rt_dev == dev || !dev) && - rt_dev != loopback_dev) { + if (rt_dev == dev) { rt->dst.dev = loopback_dev; dev_hold(rt->dst.dev); dev_put(rt_dev); @@ -248,12 +249,6 @@ static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, { } -static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst, - unsigned long old) -{ - return NULL; -} - static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, .destroy = ip6_dst_destroy, @@ -262,7 +257,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, .redirect = ip6_rt_blackhole_redirect, - .cow_metrics = ip6_rt_blackhole_cow_metrics, + .cow_metrics = dst_cow_metrics_generic, .neigh_lookup = ip6_neigh_lookup, }; @@ -319,6 +314,15 @@ static const struct rt6_info ip6_blk_hole_entry_template = { #endif +static void rt6_info_init(struct rt6_info *rt) +{ + struct dst_entry *dst = &rt->dst; + + memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); + INIT_LIST_HEAD(&rt->rt6i_siblings); + INIT_LIST_HEAD(&rt->rt6i_uncached); +} + /* allocate dst with ip6_dst_ops */ static struct rt6_info *__ip6_dst_alloc(struct net *net, struct net_device *dev, @@ -327,13 +331,9 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0, DST_OBSOLETE_FORCE_CHK, flags); - if (rt) { - struct dst_entry *dst = &rt->dst; + if (rt) + rt6_info_init(rt); - memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); - INIT_LIST_HEAD(&rt->rt6i_siblings); - INIT_LIST_HEAD(&rt->rt6i_uncached); - } return rt; } @@ -1198,24 +1198,20 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0); if (rt) { - new = &rt->dst; - - memset(new + 1, 0, sizeof(*rt) - sizeof(*new)); + rt6_info_init(rt); + new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; - if (dst_metrics_read_only(&ort->dst)) - new->_metrics = ort->dst._metrics; - else - dst_copy_metrics(new, &ort->dst); + dst_copy_metrics(new, &ort->dst); rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); rt->rt6i_gateway = ort->rt6i_gateway; - rt->rt6i_flags = ort->rt6i_flags; + rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; rt->rt6i_metric = 0; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); @@ -2609,7 +2605,8 @@ void rt6_ifdown(struct net *net, struct net_device *dev) fib6_clean_all(net, fib6_ifdown, &adn); icmp6_clean_all(fib6_ifdown, &adn); - rt6_uncached_list_flush_dev(net, dev); + if (dev) + rt6_uncached_list_flush_dev(net, dev); } struct rt6_mtu_change_arg { diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 3636b45440ab..4d2aaebd4f97 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -151,7 +151,7 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf, for (i = 0; i < NUM_IEEE80211_HW_FLAGS; i++) { if (test_bit(i, local->hw.flags)) - pos += scnprintf(pos, end - pos, "%s", + pos += scnprintf(pos, end - pos, "%s\n", hw_flag_names[i]); } diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 98fd04c4b2a0..9169ccc36534 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -101,6 +101,7 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, * when it wakes up for the next time. */ set_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT); + ieee80211_clear_fast_xmit(sta); /* * This code races in the following way: diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 464ba1a625bd..3478a83187e5 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1218,8 +1218,10 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata, if (!tx->sta) info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; - else if (test_and_clear_sta_flag(tx->sta, WLAN_STA_CLEAR_PS_FILT)) + else if (test_and_clear_sta_flag(tx->sta, WLAN_STA_CLEAR_PS_FILT)) { info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT; + ieee80211_check_fast_xmit(tx->sta); + } info->flags |= IEEE80211_TX_CTL_FIRST_FRAGMENT; @@ -2451,7 +2453,8 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) if (test_sta_flag(sta, WLAN_STA_PS_STA) || test_sta_flag(sta, WLAN_STA_PS_DRIVER) || - test_sta_flag(sta, WLAN_STA_PS_DELIVER)) + test_sta_flag(sta, WLAN_STA_PS_DELIVER) || + test_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT)) goto out; if (sdata->noack_map) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 8f060d7f9a0e..0a49a8c7c564 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2785,6 +2785,7 @@ static int netlink_dump(struct sock *sk) struct sk_buff *skb = NULL; struct nlmsghdr *nlh; int len, err = -ENOBUFS; + int alloc_min_size; int alloc_size; mutex_lock(nlk->cb_mutex); @@ -2793,9 +2794,6 @@ static int netlink_dump(struct sock *sk) goto errout_skb; } - cb = &nlk->cb; - alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); - if (!netlink_rx_is_mmaped(sk) && atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; @@ -2805,23 +2803,35 @@ static int netlink_dump(struct sock *sk) * to reduce number of system calls on dump operations, if user * ever provided a big enough buffer. */ - if (alloc_size < nlk->max_recvmsg_len) { - skb = netlink_alloc_skb(sk, - nlk->max_recvmsg_len, - nlk->portid, + cb = &nlk->cb; + alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); + + if (alloc_min_size < nlk->max_recvmsg_len) { + alloc_size = nlk->max_recvmsg_len; + skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); - /* available room should be exact amount to avoid MSG_TRUNC */ - if (skb) - skb_reserve(skb, skb_tailroom(skb) - - nlk->max_recvmsg_len); } - if (!skb) + if (!skb) { + alloc_size = alloc_min_size; skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL); + } if (!skb) goto errout_skb; + + /* Trim skb to allocated size. User is expected to provide buffer as + * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at + * netlink_recvmsg())). dump will pack as many smaller messages as + * could fit within the allocated skb. skb is typically allocated + * with larger space than required (could be as much as near 2x the + * requested size with align to next power of 2 approach). Allowing + * dump to use the excess space makes it difficult for a user to have a + * reasonable static buffer based on the expected largest dump of a + * single netdev. The outcome is MSG_TRUNC error. + */ + skb_reserve(skb, skb_tailroom(skb) - alloc_size); netlink_skb_set_owner_r(skb, sk); len = cb->dump(skb, cb); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 1d21ab9d2b5c..c6087233d7fc 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -684,7 +684,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, { if (skb_network_offset(skb) > MAX_L2_LEN) { OVS_NLERR(1, "L2 header too long to fragment"); - return; + goto err; } if (ethertype == htons(ETH_P_IP)) { @@ -708,8 +708,7 @@ static void ovs_fragment(struct net *net, struct vport *vport, struct rt6_info ovs_rt; if (!v6ops) { - kfree_skb(skb); - return; + goto err; } prepare_frag(vport, skb); @@ -728,8 +727,12 @@ static void ovs_fragment(struct net *net, struct vport *vport, WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.", ovs_vport_name(vport), ntohs(ethertype), mru, vport->dev->mtu); - kfree_skb(skb); + goto err; } + + return; +err: + kfree_skb(skb); } static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, @@ -969,7 +972,7 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_STATE: case OVS_KEY_ATTR_CT_ZONE: case OVS_KEY_ATTR_CT_MARK: - case OVS_KEY_ATTR_CT_LABEL: + case OVS_KEY_ATTR_CT_LABELS: err = -EINVAL; break; } @@ -1100,6 +1103,12 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; case OVS_ACTION_ATTR_CT: + if (!is_flow_key_valid(key)) { + err = ovs_flow_key_update(skb, key); + if (err) + return err; + } + err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key, nla_data(a)); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index ad614267cc2a..9ed833e9bb7d 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -37,9 +37,9 @@ struct md_mark { }; /* Metadata label for masked write to conntrack label. */ -struct md_label { - struct ovs_key_ct_label value; - struct ovs_key_ct_label mask; +struct md_labels { + struct ovs_key_ct_labels value; + struct ovs_key_ct_labels mask; }; /* Conntrack action context for execution. */ @@ -47,10 +47,10 @@ struct ovs_conntrack_info { struct nf_conntrack_helper *helper; struct nf_conntrack_zone zone; struct nf_conn *ct; - u32 flags; + u8 commit : 1; u16 family; struct md_mark mark; - struct md_label label; + struct md_labels labels; }; static u16 key_to_nfproto(const struct sw_flow_key *key) @@ -109,21 +109,21 @@ static u32 ovs_ct_get_mark(const struct nf_conn *ct) #endif } -static void ovs_ct_get_label(const struct nf_conn *ct, - struct ovs_key_ct_label *label) +static void ovs_ct_get_labels(const struct nf_conn *ct, + struct ovs_key_ct_labels *labels) { struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL; if (cl) { size_t len = cl->words * sizeof(long); - if (len > OVS_CT_LABEL_LEN) - len = OVS_CT_LABEL_LEN; - else if (len < OVS_CT_LABEL_LEN) - memset(label, 0, OVS_CT_LABEL_LEN); - memcpy(label, cl->bits, len); + if (len > OVS_CT_LABELS_LEN) + len = OVS_CT_LABELS_LEN; + else if (len < OVS_CT_LABELS_LEN) + memset(labels, 0, OVS_CT_LABELS_LEN); + memcpy(labels, cl->bits, len); } else { - memset(label, 0, OVS_CT_LABEL_LEN); + memset(labels, 0, OVS_CT_LABELS_LEN); } } @@ -134,7 +134,7 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, key->ct.state = state; key->ct.zone = zone->id; key->ct.mark = ovs_ct_get_mark(ct); - ovs_ct_get_label(ct, &key->ct.label); + ovs_ct_get_labels(ct, &key->ct.labels); } /* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has @@ -167,7 +167,7 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) { - if (nla_put_u8(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) + if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && @@ -179,8 +179,8 @@ int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - nla_put(skb, OVS_KEY_ATTR_CT_LABEL, sizeof(key->ct.label), - &key->ct.label)) + nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(key->ct.labels), + &key->ct.labels)) return -EMSGSIZE; return 0; @@ -213,9 +213,9 @@ static int ovs_ct_set_mark(struct sk_buff *skb, struct sw_flow_key *key, #endif } -static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key, - const struct ovs_key_ct_label *label, - const struct ovs_key_ct_label *mask) +static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_key_ct_labels *labels, + const struct ovs_key_ct_labels *mask) { enum ip_conntrack_info ctinfo; struct nf_conn_labels *cl; @@ -235,15 +235,15 @@ static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key, nf_ct_labels_ext_add(ct); cl = nf_ct_labels_find(ct); } - if (!cl || cl->words * sizeof(long) < OVS_CT_LABEL_LEN) + if (!cl || cl->words * sizeof(long) < OVS_CT_LABELS_LEN) return -ENOSPC; - err = nf_connlabels_replace(ct, (u32 *)label, (u32 *)mask, - OVS_CT_LABEL_LEN / sizeof(u32)); + err = nf_connlabels_replace(ct, (u32 *)labels, (u32 *)mask, + OVS_CT_LABELS_LEN / sizeof(u32)); if (err) return err; - ovs_ct_get_label(ct, &key->ct.label); + ovs_ct_get_labels(ct, &key->ct.labels); return 0; } @@ -465,12 +465,12 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, return 0; } -static bool label_nonzero(const struct ovs_key_ct_label *label) +static bool labels_nonzero(const struct ovs_key_ct_labels *labels) { size_t i; - for (i = 0; i < sizeof(*label); i++) - if (label->ct_label[i]) + for (i = 0; i < sizeof(*labels); i++) + if (labels->ct_labels[i]) return true; return false; @@ -493,7 +493,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, return err; } - if (info->flags & OVS_CT_F_COMMIT) + if (info->commit) err = ovs_ct_commit(net, key, info, skb); else err = ovs_ct_lookup(net, key, info, skb); @@ -506,9 +506,9 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, if (err) goto err; } - if (label_nonzero(&info->label.mask)) - err = ovs_ct_set_label(skb, key, &info->label.value, - &info->label.mask); + if (labels_nonzero(&info->labels.mask)) + err = ovs_ct_set_labels(skb, key, &info->labels.value, + &info->labels.mask); err: skb_push(skb, nh_ofs); return err; @@ -539,14 +539,13 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, } static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { - [OVS_CT_ATTR_FLAGS] = { .minlen = sizeof(u32), - .maxlen = sizeof(u32) }, + [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16), .maxlen = sizeof(u16) }, [OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark), .maxlen = sizeof(struct md_mark) }, - [OVS_CT_ATTR_LABEL] = { .minlen = sizeof(struct md_label), - .maxlen = sizeof(struct md_label) }, + [OVS_CT_ATTR_LABELS] = { .minlen = sizeof(struct md_labels), + .maxlen = sizeof(struct md_labels) }, [OVS_CT_ATTR_HELPER] = { .minlen = 1, .maxlen = NF_CT_HELPER_NAME_LEN } }; @@ -576,8 +575,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, } switch (type) { - case OVS_CT_ATTR_FLAGS: - info->flags = nla_get_u32(a); + case OVS_CT_ATTR_COMMIT: + info->commit = true; break; #ifdef CONFIG_NF_CONNTRACK_ZONES case OVS_CT_ATTR_ZONE: @@ -593,10 +592,10 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, } #endif #ifdef CONFIG_NF_CONNTRACK_LABELS - case OVS_CT_ATTR_LABEL: { - struct md_label *label = nla_data(a); + case OVS_CT_ATTR_LABELS: { + struct md_labels *labels = nla_data(a); - info->label = *label; + info->labels = *labels; break; } #endif @@ -633,7 +632,7 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr) attr == OVS_KEY_ATTR_CT_MARK) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - attr == OVS_KEY_ATTR_CT_LABEL) { + attr == OVS_KEY_ATTR_CT_LABELS) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); return ovs_net->xt_label; @@ -701,7 +700,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, if (!start) return -EMSGSIZE; - if (nla_put_u32(skb, OVS_CT_ATTR_FLAGS, ct_info->flags)) + if (ct_info->commit && nla_put_flag(skb, OVS_CT_ATTR_COMMIT)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) @@ -711,8 +710,8 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, &ct_info->mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - nla_put(skb, OVS_CT_ATTR_LABEL, sizeof(ct_info->label), - &ct_info->label)) + nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels), + &ct_info->labels)) return -EMSGSIZE; if (ct_info->helper) { if (nla_put_string(skb, OVS_CT_ATTR_HELPER, @@ -737,7 +736,7 @@ void ovs_ct_free_action(const struct nlattr *a) void ovs_ct_init(struct net *net) { - unsigned int n_bits = sizeof(struct ovs_key_ct_label) * BITS_PER_BYTE; + unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_net *ovs_net = net_generic(net, ovs_net_id); if (nf_connlabels_get(net, n_bits)) { diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 43f5dd7a5577..da8714942c95 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -34,6 +34,13 @@ int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb); void ovs_ct_free_action(const struct nlattr *a); + +static inline bool ovs_ct_state_supported(u32 state) +{ + return !(state & ~(OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | + OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | + OVS_CS_F_INVALID | OVS_CS_F_TRACKED)); +} #else #include <linux/errno.h> @@ -46,6 +53,11 @@ static inline bool ovs_ct_verify(struct net *net, int attr) return false; } +static inline bool ovs_ct_state_supported(u32 state) +{ + return false; +} + static inline int ovs_ct_copy_action(struct net *net, const struct nlattr *nla, const struct sw_flow_key *key, struct sw_flow_actions **acts, bool log) @@ -72,7 +84,7 @@ static inline void ovs_ct_fill_key(const struct sk_buff *skb, key->ct.state = 0; key->ct.zone = 0; key->ct.mark = 0; - memset(&key->ct.label, 0, sizeof(key->ct.label)); + memset(&key->ct.labels, 0, sizeof(key->ct.labels)); } static inline int ovs_ct_put_key(const struct sw_flow_key *key, diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 5688e33e2de6..1d055c559eaf 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -117,7 +117,7 @@ struct sw_flow_key { u16 zone; u32 mark; u8 state; - struct ovs_key_ct_label label; + struct ovs_key_ct_labels labels; } ct; } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 77850f177a47..6799c8d470c6 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -291,10 +291,10 @@ size_t ovs_key_attr_size(void) + nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */ + nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */ + nla_total_size(4) /* OVS_KEY_ATTR_RECIRC_ID */ - + nla_total_size(1) /* OVS_KEY_ATTR_CT_STATE */ + + nla_total_size(4) /* OVS_KEY_ATTR_CT_STATE */ + nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */ + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ - + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABEL */ + + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ @@ -351,10 +351,10 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED, .next = ovs_tunnel_key_lens, }, [OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) }, - [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u8) }, + [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) }, [OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) }, - [OVS_KEY_ATTR_CT_LABEL] = { .len = sizeof(struct ovs_key_ct_label) }, + [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) @@ -864,7 +864,13 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) && ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) { - u8 ct_state = nla_get_u8(a[OVS_KEY_ATTR_CT_STATE]); + u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]); + + if (!is_mask && !ovs_ct_state_supported(ct_state)) { + OVS_NLERR(log, "ct_state flags %08x unsupported", + ct_state); + return -EINVAL; + } SW_FLOW_KEY_PUT(match, ct.state, ct_state, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_STATE); @@ -883,14 +889,14 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, SW_FLOW_KEY_PUT(match, ct.mark, mark, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_MARK); } - if (*attrs & (1 << OVS_KEY_ATTR_CT_LABEL) && - ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABEL)) { - const struct ovs_key_ct_label *cl; + if (*attrs & (1 << OVS_KEY_ATTR_CT_LABELS) && + ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABELS)) { + const struct ovs_key_ct_labels *cl; - cl = nla_data(a[OVS_KEY_ATTR_CT_LABEL]); - SW_FLOW_KEY_MEMCPY(match, ct.label, cl->ct_label, + cl = nla_data(a[OVS_KEY_ATTR_CT_LABELS]); + SW_FLOW_KEY_MEMCPY(match, ct.labels, cl->ct_labels, sizeof(*cl), is_mask); - *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABEL); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS); } return 0; } @@ -2025,7 +2031,7 @@ static int validate_set(const struct nlattr *a, case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_SKB_MARK: case OVS_KEY_ATTR_CT_MARK: - case OVS_KEY_ATTR_CT_LABEL: + case OVS_KEY_ATTR_CT_LABELS: case OVS_KEY_ATTR_ETHERNET: break; diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 95dbcedf0bd4..d073fff82fdb 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -93,7 +93,8 @@ struct sw_flow *ovs_flow_alloc(void) /* Initialize the default stat node. */ stats = kmem_cache_alloc_node(flow_stats_cache, - GFP_KERNEL | __GFP_ZERO, 0); + GFP_KERNEL | __GFP_ZERO, + node_online(0) ? 0 : NUMA_NO_NODE); if (!stats) goto err; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index dc81dc619aa2..12a36ac21eda 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -280,35 +280,19 @@ void ovs_vport_del(struct vport *vport) */ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) { - struct net_device *dev = vport->dev; - int i; - - memset(stats, 0, sizeof(*stats)); - stats->rx_errors = dev->stats.rx_errors; - stats->tx_errors = dev->stats.tx_errors; - stats->tx_dropped = dev->stats.tx_dropped; - stats->rx_dropped = dev->stats.rx_dropped; - - stats->rx_dropped += atomic_long_read(&dev->rx_dropped); - stats->tx_dropped += atomic_long_read(&dev->tx_dropped); - - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *percpu_stats; - struct pcpu_sw_netstats local_stats; - unsigned int start; - - percpu_stats = per_cpu_ptr(dev->tstats, i); - - do { - start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); - local_stats = *percpu_stats; - } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); - - stats->rx_bytes += local_stats.rx_bytes; - stats->rx_packets += local_stats.rx_packets; - stats->tx_bytes += local_stats.tx_bytes; - stats->tx_packets += local_stats.tx_packets; - } + const struct rtnl_link_stats64 *dev_stats; + struct rtnl_link_stats64 temp; + + dev_stats = dev_get_stats(vport->dev, &temp); + stats->rx_errors = dev_stats->rx_errors; + stats->tx_errors = dev_stats->tx_errors; + stats->tx_dropped = dev_stats->tx_dropped; + stats->rx_dropped = dev_stats->rx_dropped; + + stats->rx_bytes = dev_stats->rx_bytes; + stats->rx_packets = dev_stats->rx_packets; + stats->tx_bytes = dev_stats->tx_bytes; + stats->tx_packets = dev_stats->tx_packets; } /** @@ -460,6 +444,15 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb, OVS_CB(skb)->input_vport = vport; OVS_CB(skb)->mru = 0; + if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) { + u32 mark; + + mark = skb->mark; + skb_scrub_packet(skb, true); + skb->mark = mark; + tun_info = NULL; + } + /* Extract flow from 'skb' into 'key'. */ error = ovs_flow_key_extract(tun_info, skb, &key); if (unlikely(error)) { diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 2d1be4a760fd..32fcdecdb9e2 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -31,13 +31,17 @@ #define MIRRED_TAB_MASK 7 static LIST_HEAD(mirred_list); +static DEFINE_SPINLOCK(mirred_list_lock); 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); + /* We could be called either in a RCU callback or with RTNL lock held. */ + spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); + spin_unlock_bh(&mirred_list_lock); if (dev) dev_put(dev); } @@ -103,10 +107,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } else { if (bind) return 0; - if (!ovr) { - tcf_hash_release(a, bind); + + tcf_hash_release(a, bind); + if (!ovr) return -EEXIST; - } } m = to_mirred(a); @@ -123,7 +127,9 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, } if (ret == ACT_P_CREATED) { + spin_lock_bh(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); + spin_unlock_bh(&mirred_list_lock); tcf_hash_insert(a); } @@ -173,6 +179,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; + skb_sender_cpu_clear(skb2); err = dev_queue_xmit(skb2); if (err) { @@ -221,7 +228,8 @@ static int mirred_device_event(struct notifier_block *unused, struct tcf_mirred *m; ASSERT_RTNL(); - if (event == NETDEV_UNREGISTER) + if (event == NETDEV_UNREGISTER) { + spin_lock_bh(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); @@ -231,6 +239,8 @@ static int mirred_device_event(struct notifier_block *unused, RCU_INIT_POINTER(m->tcfm_dev, NULL); } } + spin_unlock_bh(&mirred_list_lock); + } return NOTIFY_DONE; } diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 9d15cb6b8cb1..86b04e31e60b 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -368,6 +368,15 @@ static unsigned int hhf_drop(struct Qdisc *sch) return bucket - q->buckets; } +static unsigned int hhf_qdisc_drop(struct Qdisc *sch) +{ + unsigned int prev_backlog; + + prev_backlog = sch->qstats.backlog; + hhf_drop(sch); + return prev_backlog - sch->qstats.backlog; +} + static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct hhf_sched_data *q = qdisc_priv(sch); @@ -696,7 +705,7 @@ static struct Qdisc_ops hhf_qdisc_ops __read_mostly = { .enqueue = hhf_enqueue, .dequeue = hhf_dequeue, .peek = qdisc_peek_dequeued, - .drop = hhf_drop, + .drop = hhf_qdisc_drop, .init = hhf_init, .reset = hhf_reset, .destroy = hhf_destroy, diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index cb5174284074..f0c3ff67ca98 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -136,7 +136,8 @@ int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, ctxt->direction = DMA_FROM_DEVICE; ctxt->read_hdr = head; pages_needed = min_t(int, pages_needed, xprt->sc_max_sge_rd); - read = min_t(int, pages_needed << PAGE_SHIFT, rs_length); + read = min_t(int, (pages_needed << PAGE_SHIFT) - *page_offset, + rs_length); for (pno = 0; pno < pages_needed; pno++) { int len = min_t(int, rs_length, PAGE_SIZE - pg_off); @@ -235,7 +236,8 @@ int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt, ctxt->direction = DMA_FROM_DEVICE; ctxt->frmr = frmr; pages_needed = min_t(int, pages_needed, xprt->sc_frmr_pg_list_len); - read = min_t(int, pages_needed << PAGE_SHIFT, rs_length); + read = min_t(int, (pages_needed << PAGE_SHIFT) - *page_offset, + rs_length); frmr->kva = page_address(rqstp->rq_arg.pages[pg_no]); frmr->direction = DMA_FROM_DEVICE; @@ -531,7 +533,7 @@ static int rdma_read_complete(struct svc_rqst *rqstp, rqstp->rq_arg.page_base = head->arg.page_base; /* rq_respages starts after the last arg page */ - rqstp->rq_respages = &rqstp->rq_arg.pages[page_no]; + rqstp->rq_respages = &rqstp->rq_pages[page_no]; rqstp->rq_next_page = rqstp->rq_respages + 1; /* Rebuild rq_arg head and tail. */ diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 64443eb754ad..41e452bc580c 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -270,8 +270,8 @@ xprt_rdma_destroy(struct rpc_xprt *xprt) xprt_clear_connected(xprt); - rpcrdma_buffer_destroy(&r_xprt->rx_buf); rpcrdma_ep_destroy(&r_xprt->rx_ep, &r_xprt->rx_ia); + rpcrdma_buffer_destroy(&r_xprt->rx_buf); rpcrdma_ia_close(&r_xprt->rx_ia); xprt_rdma_free_addresses(xprt); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index eb081ad05e33..5502d4dade74 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -543,11 +543,8 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) } if (memreg == RPCRDMA_FRMR) { - /* Requires both frmr reg and local dma lkey */ - if (((devattr->device_cap_flags & - (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) != - (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) || - (devattr->max_fast_reg_page_list_len == 0)) { + if (!(devattr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) || + (devattr->max_fast_reg_page_list_len == 0)) { dprintk("RPC: %s: FRMR registration " "not supported by HCA\n", __func__); memreg = RPCRDMA_MTHCAFMR; @@ -557,6 +554,7 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) if (!ia->ri_device->alloc_fmr) { dprintk("RPC: %s: MTHCAFMR registration " "not supported by HCA\n", __func__); + rc = -EINVAL; goto out3; } } @@ -755,19 +753,22 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) cancel_delayed_work_sync(&ep->rep_connect_worker); - if (ia->ri_id->qp) { + if (ia->ri_id->qp) rpcrdma_ep_disconnect(ep, ia); + + rpcrdma_clean_cq(ep->rep_attr.recv_cq); + rpcrdma_clean_cq(ep->rep_attr.send_cq); + + if (ia->ri_id->qp) { rdma_destroy_qp(ia->ri_id); ia->ri_id->qp = NULL; } - rpcrdma_clean_cq(ep->rep_attr.recv_cq); rc = ib_destroy_cq(ep->rep_attr.recv_cq); if (rc) dprintk("RPC: %s: ib_destroy_cq returned %i\n", __func__, rc); - rpcrdma_clean_cq(ep->rep_attr.send_cq); rc = ib_destroy_cq(ep->rep_attr.send_cq); if (rc) dprintk("RPC: %s: ib_destroy_cq returned %i\n", diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 73e3895175cf..1eb76956b439 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -19,6 +19,7 @@ #include <linux/if_bridge.h> #include <linux/list.h> #include <linux/workqueue.h> +#include <linux/if_vlan.h> #include <net/ip_fib.h> #include <net/switchdev.h> @@ -846,6 +847,8 @@ static int switchdev_port_br_afspec(struct net_device *dev, if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo = nla_data(attr); + if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK) + return -EINVAL; vlan.flags = vinfo->flags; if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (vlan.vid_begin) diff --git a/net/tipc/msg.h b/net/tipc/msg.h index c784ba05f2aa..9f0ef54be612 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -357,7 +357,7 @@ static inline u32 msg_importance(struct tipc_msg *m) if (likely((usr <= TIPC_CRITICAL_IMPORTANCE) && !msg_errcode(m))) return usr; if ((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER)) - return msg_bits(m, 5, 13, 0x7); + return msg_bits(m, 9, 0, 0x7); return TIPC_SYSTEM_IMPORTANCE; } @@ -366,7 +366,7 @@ static inline void msg_set_importance(struct tipc_msg *m, u32 i) int usr = msg_user(m); if (likely((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER))) - msg_set_bits(m, 5, 13, 0x7, i); + msg_set_bits(m, 9, 0, 0x7, i); else if (i < TIPC_SYSTEM_IMPORTANCE) msg_set_user(m, i); else diff --git a/net/tipc/node.c b/net/tipc/node.c index d1f340116c84..2670751d0e2e 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1133,7 +1133,7 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, } /* Ignore duplicate packets */ - if (less(oseqno, rcv_nxt)) + if ((usr != LINK_PROTOCOL) && less(oseqno, rcv_nxt)) return true; /* Initiate or update failover mode if applicable */ @@ -1163,8 +1163,8 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb, if (!pl || !tipc_link_is_up(pl)) return true; - /* Initiate or update synch mode if applicable */ - if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG)) { + /* Initiate synch mode if applicable */ + if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) { syncpt = iseqno + exp_pkts - 1; if (!tipc_link_is_up(l)) { tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ef31b40ad550..94f658235fb4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2064,6 +2064,11 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) goto out; } + if (flags & MSG_PEEK) + skip = sk_peek_offset(sk, flags); + else + skip = 0; + do { int chunk; struct sk_buff *skb, *last; @@ -2112,7 +2117,6 @@ unlock: break; } - skip = sk_peek_offset(sk, flags); while (skip >= unix_skb_len(skb)) { skip -= unix_skb_len(skb); last = skb; @@ -2179,14 +2183,12 @@ unlock: if (UNIXCB(skb).fp) scm.fp = scm_fp_dup(UNIXCB(skb).fp); - if (skip) { - sk_peek_offset_fwd(sk, chunk); - skip -= chunk; - } + sk_peek_offset_fwd(sk, chunk); if (UNIXCB(skb).fp) break; + skip = 0; last = skb; last_len = skb->len; unix_state_lock(sk); |