diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt new file mode 100644 index 000000000000..031ef4a63485 --- /dev/null +++ b/Documentation/networking/vrf.txt @@ -0,0 +1,96 @@ +Virtual Routing and Forwarding (VRF) +==================================== +The VRF device combined with ip rules provides the ability to create virtual +routing and forwarding domains (aka VRFs, VRF-lite to be specific) in the +Linux network stack. One use case is the multi-tenancy problem where each +tenant has their own unique routing tables and in the very least need +different default gateways. + +Processes can be "VRF aware" by binding a socket to the VRF device. Packets +through the socket then use the routing table associated with the VRF +device. An important feature of the VRF device implementation is that it +impacts only Layer 3 and above so L2 tools (e.g., LLDP) are not affected +(ie., they do not need to be run in each VRF). The design also allows +the use of higher priority ip rules (Policy Based Routing, PBR) to take +precedence over the VRF device rules directing specific traffic as desired. + +In addition, VRF devices allow VRFs to be nested within namespaces. For +example network namespaces provide separation of network interfaces at L1 +(Layer 1 separation), VLANs on the interfaces within a namespace provide +L2 separation and then VRF devices provide L3 separation. + +Design +------ +A VRF device is created with an associated route table. Network interfaces +are then enslaved to a VRF device: + + +-----------------------------+ + | vrf-blue | ===> route table 10 + +-----------------------------+ + | | | + +------+ +------+ +-------------+ + | eth1 | | eth2 | ... | bond1 | + +------+ +------+ +-------------+ + | | + +------+ +------+ + | eth8 | | eth9 | + +------+ +------+ + +Packets received on an enslaved device and are switched to the VRF device +using an rx_handler which gives the impression that packets flow through +the VRF device. Similarly on egress routing rules are used to send packets +to the VRF device driver before getting sent out the actual interface. This +allows tcpdump on a VRF device to capture all packets into and out of the +VRF as a whole.[1] Similiarly, netfilter [2] and tc rules can be applied +using the VRF device to specify rules that apply to the VRF domain as a whole. + +[1] Packets in the forwarded state do not flow through the device, so those + packets are not seen by tcpdump. Will revisit this limitation in a + future release. + +[2] Iptables on ingress is limited to NF_INET_PRE_ROUTING only with skb->dev + set to real ingress device and egress is limited to NF_INET_POST_ROUTING. + Will revisit this limitation in a future release. + + +Setup +----- +1. VRF device is created with an association to a FIB table. + e.g, ip link add vrf-blue type vrf table 10 + ip link set dev vrf-blue up + +2. Rules are added that send lookups to the associated FIB table when the + iif or oif is the VRF device. e.g., + ip ru add oif vrf-blue table 10 + ip ru add iif vrf-blue table 10 + + Set the default route for the table (and hence default route for the VRF). + e.g, ip route add table 10 prohibit default + +3. Enslave L3 interfaces to a VRF device. + e.g, ip link set dev eth1 master vrf-blue + + Local and connected routes for enslaved devices are automatically moved to + the table associated with VRF device. Any additional routes depending on + the enslaved device will need to be reinserted following the enslavement. + +4. Additional VRF routes are added to associated table. + e.g., ip route add table 10 ... + + +Applications +------------ +Applications that are to work within a VRF need to bind their socket to the +VRF device: + + setsockopt(sd, SOL_SOCKET, SO_BINDTODEVICE, dev, strlen(dev)+1); + +or to specify the output device using cmsg and IP_PKTINFO. + + +Limitations +----------- +VRF device currently only works for IPv4. Support for IPv6 is under development. + +Index of original ingress interface is not available via cmsg. Will address +soon. diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 6294b5186ae5..809ab6efcc74 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -54,13 +54,15 @@ default_qdisc -------------- The default queuing discipline to use for network devices. This allows -overriding the default queue discipline of pfifo_fast with an -alternative. Since the default queuing discipline is created with the -no additional parameters so is best suited to queuing disciplines that -work well without configuration like stochastic fair queue (sfq), -CoDel (codel) or fair queue CoDel (fq_codel). Don't use queuing disciplines -like Hierarchical Token Bucket or Deficit Round Robin which require setting -up classes and bandwidths. +overriding the default of pfifo_fast with an alternative. Since the default +queuing discipline is created without additional parameters so is best suited +to queuing disciplines that work well without configuration like stochastic +fair queue (sfq), CoDel (codel) or fair queue CoDel (fq_codel). Don't use +queuing disciplines like Hierarchical Token Bucket or Deficit Round Robin +which require setting up classes and bandwidths. Note that physical multiqueue +interfaces still use mq as root qdisc, which in turn uses this default for its +leaves. Virtual devices (like e.g. lo or veth) ignore this setting and instead +default to noqueue. Default: pfifo_fast busy_read diff --git a/MAINTAINERS b/MAINTAINERS index 45b06ab43ec0..5de7c7945022 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -808,6 +808,13 @@ S: Maintained F: drivers/video/fbdev/arcfb.c F: drivers/video/fbdev/core/fb_defio.c +ARCNET NETWORK LAYER +M: Michael Grzeschik +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/arcnet/ +F: include/uapi/linux/if_arcnet.h + ARM MFM AND FLOPPY DRIVERS M: Ian Molton S: Maintained @@ -8500,7 +8507,6 @@ F: Documentation/networking/LICENSE.qla3xxx F: drivers/net/ethernet/qlogic/qla3xxx.* QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER -M: Shahed Shaikh M: Dept-GELinuxNICDev@qlogic.com L: netdev@vger.kernel.org S: Supported @@ -11262,6 +11268,7 @@ L: netdev@vger.kernel.org S: Maintained F: drivers/net/vrf.c F: include/net/vrf.h +F: Documentation/networking/vrf.txt VT1211 HARDWARE MONITOR DRIVER M: Juerg Haefliger diff --git a/drivers/atm/he.c b/drivers/atm/he.c index a8da3a50e374..0f5cb37636bc 100644 --- a/drivers/atm/he.c +++ b/drivers/atm/he.c @@ -1578,9 +1578,7 @@ he_stop(struct he_dev *he_dev) kfree(he_dev->rbpl_virt); kfree(he_dev->rbpl_table); - - if (he_dev->rbpl_pool) - dma_pool_destroy(he_dev->rbpl_pool); + dma_pool_destroy(he_dev->rbpl_pool); if (he_dev->rbrq_base) dma_free_coherent(&he_dev->pci_dev->dev, CONFIG_RBRQ_SIZE * sizeof(struct he_rbrq), @@ -1594,8 +1592,7 @@ he_stop(struct he_dev *he_dev) dma_free_coherent(&he_dev->pci_dev->dev, CONFIG_TBRQ_SIZE * sizeof(struct he_tbrq), he_dev->tpdrq_base, he_dev->tpdrq_phys); - if (he_dev->tpd_pool) - dma_pool_destroy(he_dev->tpd_pool); + dma_pool_destroy(he_dev->tpd_pool); if (he_dev->pci_dev) { pci_read_config_word(he_dev->pci_dev, PCI_COMMAND, &command); diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index 74e18b0a6d89..3d7fb6516f74 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -805,7 +805,12 @@ static void solos_bh(unsigned long card_arg) continue; } - skb = alloc_skb(size + 1, GFP_ATOMIC); + /* Use netdev_alloc_skb() because it adds NET_SKB_PAD of + * headroom, and ensures we can route packets back out an + * Ethernet interface (for example) without having to + * reallocate. Adding NET_IP_ALIGN also ensures that both + * PPPoATM and PPPoEoBR2684 packets end up aligned. */ + skb = netdev_alloc_skb_ip_align(NULL, size + 1); if (!skb) { if (net_ratelimit()) dev_warn(&card->dev->dev, "Failed to allocate sk_buff for RX\n"); @@ -869,7 +874,10 @@ static void solos_bh(unsigned long card_arg) /* Allocate RX skbs for any ports which need them */ if (card->using_dma && card->atmdev[port] && !card->rx_skb[port]) { - struct sk_buff *skb = alloc_skb(RX_DMA_SIZE, GFP_ATOMIC); + /* Unlike the MMIO case (qv) we can't add NET_IP_ALIGN + * here; the FPGA can only DMA to addresses which are + * aligned to 4 bytes. */ + struct sk_buff *skb = dev_alloc_skb(RX_DMA_SIZE); if (skb) { SKB_CB(skb)->dma_addr = dma_map_single(&card->dev->dev, skb->data, diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index 10f71c732b59..816d0e94961c 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -326,7 +326,7 @@ static void arcdev_setup(struct net_device *dev) dev->type = ARPHRD_ARCNET; dev->netdev_ops = &arcnet_netdev_ops; dev->header_ops = &arcnet_header_ops; - dev->hard_header_len = sizeof(struct archdr); + dev->hard_header_len = sizeof(struct arc_hardware); dev->mtu = choose_mtu(); dev->addr_len = ARCNET_ALEN; diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 6f13f7206762..f8baa897d1a0 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -2000,6 +2000,7 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) */ reg = _mv88e6xxx_reg_read(ds, REG_PORT(port), PORT_PCS_CTRL); if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) { + reg &= ~PORT_PCS_CTRL_UNFORCED; reg |= PORT_PCS_CTRL_FORCE_LINK | PORT_PCS_CTRL_LINK_UP | PORT_PCS_CTRL_DUPLEX_FULL | diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index cfa37041ab71..c4bb8027b3fb 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -689,16 +689,24 @@ static int xgene_enet_phy_connect(struct net_device *ndev) netdev_dbg(ndev, "No phy-handle found in DT\n"); return -ENODEV; } - pdata->phy_dev = of_phy_find_device(phy_np); - } - phy_dev = pdata->phy_dev; + phy_dev = of_phy_connect(ndev, phy_np, &xgene_enet_adjust_link, + 0, pdata->phy_mode); + if (!phy_dev) { + netdev_err(ndev, "Could not connect to PHY\n"); + return -ENODEV; + } - if (!phy_dev || - phy_connect_direct(ndev, phy_dev, &xgene_enet_adjust_link, - pdata->phy_mode)) { - netdev_err(ndev, "Could not connect to PHY\n"); - return -ENODEV; + pdata->phy_dev = phy_dev; + } else { + phy_dev = pdata->phy_dev; + + if (!phy_dev || + phy_connect_direct(ndev, phy_dev, &xgene_enet_adjust_link, + pdata->phy_mode)) { + netdev_err(ndev, "Could not connect to PHY\n"); + return -ENODEV; + } } pdata->phy_speed = SPEED_UNKNOWN; diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c index f9cb99bfb511..ffd180570920 100644 --- a/drivers/net/ethernet/arc/emac_arc.c +++ b/drivers/net/ethernet/arc/emac_arc.c @@ -78,6 +78,7 @@ static const struct of_device_id emac_arc_dt_ids[] = { { .compatible = "snps,arc-emac" }, { /* Sentinel */ } }; +MODULE_DEVICE_TABLE(of, emac_arc_dt_ids); static struct platform_driver emac_arc_driver = { .probe = emac_arc_probe, diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index b9a5a97ed4dd..f1b5364f3521 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2079,6 +2079,7 @@ static const struct of_device_id bcm_sysport_of_match[] = { { .compatible = "brcm,systemport" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, bcm_sysport_of_match); static struct platform_driver bcm_sysport_driver = { .probe = bcm_sysport_probe, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index ba936635322a..b5e64b02200c 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1946,6 +1946,7 @@ struct bnx2x { u16 vlan_cnt; u16 vlan_credit; u16 vxlan_dst_port; + u8 vxlan_dst_port_count; bool accept_any_vlan; }; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index e3da2bddf143..f1d62d5dbaff 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -3705,16 +3705,14 @@ out: void bnx2x_update_mfw_dump(struct bnx2x *bp) { - struct timeval epoc; u32 drv_ver; u32 valid_dump; if (!SHMEM2_HAS(bp, drv_info)) return; - /* Update Driver load time */ - do_gettimeofday(&epoc); - SHMEM2_WR(bp, drv_info.epoc, epoc.tv_sec); + /* Update Driver load time, possibly broken in y2038 */ + SHMEM2_WR(bp, drv_info.epoc, (u32)ktime_get_real_seconds()); drv_ver = bnx2x_update_mng_version_utility(DRV_MODULE_VERSION, true); SHMEM2_WR(bp, drv_info.drv_ver, drv_ver); @@ -10110,12 +10108,18 @@ static void __bnx2x_add_vxlan_port(struct bnx2x *bp, u16 port) if (!netif_running(bp->dev)) return; - if (bp->vxlan_dst_port || !IS_PF(bp)) { + if (bp->vxlan_dst_port_count && bp->vxlan_dst_port == port) { + bp->vxlan_dst_port_count++; + return; + } + + if (bp->vxlan_dst_port_count || !IS_PF(bp)) { DP(BNX2X_MSG_SP, "Vxlan destination port limit reached\n"); return; } bp->vxlan_dst_port = port; + bp->vxlan_dst_port_count = 1; bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_ADD_VXLAN_PORT, 0); } @@ -10130,10 +10134,14 @@ static void bnx2x_add_vxlan_port(struct net_device *netdev, static void __bnx2x_del_vxlan_port(struct bnx2x *bp, u16 port) { - if (!bp->vxlan_dst_port || bp->vxlan_dst_port != port || !IS_PF(bp)) { + if (!bp->vxlan_dst_port_count || bp->vxlan_dst_port != port || + !IS_PF(bp)) { DP(BNX2X_MSG_SP, "Invalid vxlan port\n"); return; } + bp->vxlan_dst_port--; + if (bp->vxlan_dst_port) + return; if (netif_running(bp->dev)) { bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_DEL_VXLAN_PORT, 0); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index c9bd7f16018e..ff702a707a91 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -4319,8 +4319,16 @@ static int bnx2x_setup_rss(struct bnx2x *bp, /* RSS keys */ if (test_bit(BNX2X_RSS_SET_SRCH, &p->rss_flags)) { - memcpy(&data->rss_key[0], &p->rss_key[0], - sizeof(data->rss_key)); + u8 *dst = (u8 *)(data->rss_key) + sizeof(data->rss_key); + const u8 *src = (const u8 *)p->rss_key; + int i; + + /* Apparently, bnx2x reads this array in reverse order + * We need to byte swap rss_key to comply with Toeplitz specs. + */ + for (i = 0; i < sizeof(data->rss_key); i++) + *--dst = *src++; + caps |= ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY; } diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index fadbd0088d3e..3bc701e4c59e 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3155,6 +3155,7 @@ static const struct of_device_id bcmgenet_match[] = { { .compatible = "brcm,genet-v4", .data = (void *)GENET_V4 }, { }, }; +MODULE_DEVICE_TABLE(of, bcmgenet_match); static int bcmgenet_probe(struct platform_device *pdev) { diff --git a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c index 5d0753cc7e73..04b0d16b210e 100644 --- a/drivers/net/ethernet/brocade/bna/bna_tx_rx.c +++ b/drivers/net/ethernet/brocade/bna/bna_tx_rx.c @@ -2400,6 +2400,7 @@ bna_rx_create(struct bna *bna, struct bnad *bnad, q0->rcb->id = 0; q0->rx_packets = q0->rx_bytes = 0; q0->rx_packets_with_error = q0->rxbuf_alloc_failed = 0; + q0->rxbuf_map_failed = 0; bna_rxq_qpt_setup(q0, rxp, dpage_count, PAGE_SIZE, &dqpt_mem[i], &dsqpt_mem[i], &dpage_mem[i]); @@ -2428,6 +2429,7 @@ bna_rx_create(struct bna *bna, struct bnad *bnad, : rx_cfg->q1_buf_size; q1->rx_packets = q1->rx_bytes = 0; q1->rx_packets_with_error = q1->rxbuf_alloc_failed = 0; + q1->rxbuf_map_failed = 0; bna_rxq_qpt_setup(q1, rxp, hpage_count, PAGE_SIZE, &hqpt_mem[i], &hsqpt_mem[i], diff --git a/drivers/net/ethernet/brocade/bna/bna_types.h b/drivers/net/ethernet/brocade/bna/bna_types.h index e0e797f2ea14..c438d032e8bf 100644 --- a/drivers/net/ethernet/brocade/bna/bna_types.h +++ b/drivers/net/ethernet/brocade/bna/bna_types.h @@ -587,6 +587,7 @@ struct bna_rxq { u64 rx_bytes; u64 rx_packets_with_error; u64 rxbuf_alloc_failed; + u64 rxbuf_map_failed; }; /* RxQ pair */ diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 506047c38607..21a0cfc3e7ec 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -399,7 +399,13 @@ bnad_rxq_refill_page(struct bnad *bnad, struct bna_rcb *rcb, u32 nalloc) } dma_addr = dma_map_page(&bnad->pcidev->dev, page, page_offset, - unmap_q->map_size, DMA_FROM_DEVICE); + unmap_q->map_size, DMA_FROM_DEVICE); + if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) { + put_page(page); + BNAD_UPDATE_CTR(bnad, rxbuf_map_failed); + rcb->rxq->rxbuf_map_failed++; + goto finishing; + } unmap->page = page; unmap->page_offset = page_offset; @@ -454,8 +460,15 @@ bnad_rxq_refill_skb(struct bnad *bnad, struct bna_rcb *rcb, u32 nalloc) rcb->rxq->rxbuf_alloc_failed++; goto finishing; } + dma_addr = dma_map_single(&bnad->pcidev->dev, skb->data, buff_sz, DMA_FROM_DEVICE); + if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) { + dev_kfree_skb_any(skb); + BNAD_UPDATE_CTR(bnad, rxbuf_map_failed); + rcb->rxq->rxbuf_map_failed++; + goto finishing; + } unmap->skb = skb; dma_unmap_addr_set(&unmap->vector, dma_addr, dma_addr); @@ -3025,6 +3038,11 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev) unmap = head_unmap; dma_addr = dma_map_single(&bnad->pcidev->dev, skb->data, len, DMA_TO_DEVICE); + if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) { + dev_kfree_skb_any(skb); + BNAD_UPDATE_CTR(bnad, tx_skb_map_failed); + return NETDEV_TX_OK; + } BNA_SET_DMA_ADDR(dma_addr, &txqent->vector[0].host_addr); txqent->vector[0].length = htons(len); dma_unmap_addr_set(&unmap->vectors[0], dma_addr, dma_addr); @@ -3056,6 +3074,15 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev) dma_addr = skb_frag_dma_map(&bnad->pcidev->dev, frag, 0, size, DMA_TO_DEVICE); + if (dma_mapping_error(&bnad->pcidev->dev, dma_addr)) { + /* Undo the changes starting at tcb->producer_index */ + bnad_tx_buff_unmap(bnad, unmap_q, q_depth, + tcb->producer_index); + dev_kfree_skb_any(skb); + BNAD_UPDATE_CTR(bnad, tx_skb_map_failed); + return NETDEV_TX_OK; + } + dma_unmap_len_set(&unmap->vectors[vect_id], dma_len, size); BNA_SET_DMA_ADDR(dma_addr, &txqent->vector[vect_id].host_addr); txqent->vector[vect_id].length = htons(size); diff --git a/drivers/net/ethernet/brocade/bna/bnad.h b/drivers/net/ethernet/brocade/bna/bnad.h index faedbf24777e..f4ed816b93ee 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.h +++ b/drivers/net/ethernet/brocade/bna/bnad.h @@ -175,6 +175,7 @@ struct bnad_drv_stats { u64 tx_skb_headlen_zero; u64 tx_skb_frag_zero; u64 tx_skb_len_mismatch; + u64 tx_skb_map_failed; u64 hw_stats_updates; u64 netif_rx_dropped; @@ -189,6 +190,7 @@ struct bnad_drv_stats { u64 rx_unmap_q_alloc_failed; u64 rxbuf_alloc_failed; + u64 rxbuf_map_failed; }; /* Complete driver stats */ diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c index 2bdfc5dff4b1..0e4fdc3dd729 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c +++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c @@ -90,6 +90,7 @@ static const char *bnad_net_stats_strings[BNAD_ETHTOOL_STATS_NUM] = { "tx_skb_headlen_zero", "tx_skb_frag_zero", "tx_skb_len_mismatch", + "tx_skb_map_failed", "hw_stats_updates", "netif_rx_dropped", @@ -102,6 +103,7 @@ static const char *bnad_net_stats_strings[BNAD_ETHTOOL_STATS_NUM] = { "tx_unmap_q_alloc_failed", "rx_unmap_q_alloc_failed", "rxbuf_alloc_failed", + "rxbuf_map_failed", "mac_stats_clr_cnt", "mac_frame_64", @@ -807,6 +809,7 @@ bnad_per_q_stats_fill(struct bnad *bnad, u64 *buf, int bi) rx_packets_with_error; buf[bi++] = rcb->rxq-> rxbuf_alloc_failed; + buf[bi++] = rcb->rxq->rxbuf_map_failed; buf[bi++] = rcb->producer_index; buf[bi++] = rcb->consumer_index; } @@ -821,6 +824,7 @@ bnad_per_q_stats_fill(struct bnad *bnad, u64 *buf, int bi) rx_packets_with_error; buf[bi++] = rcb->rxq-> rxbuf_alloc_failed; + buf[bi++] = rcb->rxq->rxbuf_map_failed; buf[bi++] = rcb->producer_index; buf[bi++] = rcb->consumer_index; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index 8353a6cbfcc2..03ed00c49823 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -157,6 +157,11 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x5090), /* Custom T540-CR */ CH_PCI_ID_TABLE_FENTRY(0x5091), /* Custom T522-CR */ CH_PCI_ID_TABLE_FENTRY(0x5092), /* Custom T520-CR */ + CH_PCI_ID_TABLE_FENTRY(0x5093), /* Custom T580-LP-CR */ + CH_PCI_ID_TABLE_FENTRY(0x5094), /* Custom T540-CR */ + CH_PCI_ID_TABLE_FENTRY(0x5095), /* Custom T540-CR-SO */ + CH_PCI_ID_TABLE_FENTRY(0x5096), /* Custom T580-CR */ + CH_PCI_ID_TABLE_FENTRY(0x5097), /* Custom T520-KR */ /* T6 adapters: */ diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 0a27805cbbbd..821540913343 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -582,6 +582,7 @@ struct be_adapter { u16 pvid; __be16 vxlan_port; int vxlan_port_count; + int vxlan_port_aliases; struct phy_info phy; u8 wol_cap; bool wol_en; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 12687bf52b95..7bf51a1a0a77 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -5176,6 +5176,11 @@ static void be_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family, if (lancer_chip(adapter) || BEx_chip(adapter) || be_is_mc(adapter)) return; + if (adapter->vxlan_port == port && adapter->vxlan_port_count) { + adapter->vxlan_port_aliases++; + return; + } + if (adapter->flags & BE_FLAGS_VXLAN_OFFLOADS) { dev_info(dev, "Only one UDP port supported for VxLAN offloads\n"); @@ -5226,6 +5231,11 @@ static void be_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family, if (adapter->vxlan_port != port) goto done; + if (adapter->vxlan_port_aliases) { + adapter->vxlan_port_aliases--; + return; + } + be_disable_vxlan_offloads(adapter); dev_info(&adapter->pdev->dev, diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 4b69d061d90f..710715fcb23d 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1710,8 +1710,10 @@ static void gfar_configure_serdes(struct net_device *dev) * everything for us? Resetting it takes the link down and requires * several seconds for it to come back. */ - if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS) + if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS) { + put_device(&tbiphy->dev); return; + } /* Single clk mode, mii mode off(for serdes communication) */ phy_write(tbiphy, MII_TBICON, TBICON_CLK_SELECT); @@ -1723,6 +1725,8 @@ static void gfar_configure_serdes(struct net_device *dev) phy_write(tbiphy, MII_BMCR, BMCR_ANENABLE | BMCR_ANRESTART | BMCR_FULLDPLX | BMCR_SPEED1000); + + put_device(&tbiphy->dev); } static int __gfar_is_rx_idle(struct gfar_private *priv) @@ -1970,8 +1974,7 @@ static int register_grp_irqs(struct gfar_priv_grp *grp) /* Install our interrupt handlers for Error, * Transmit, and Receive */ - err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, - IRQF_NO_SUSPEND, + err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0, gfar_irq(grp, ER)->name, grp); if (err < 0) { netif_err(priv, intr, dev, "Can't get IRQ %d\n", @@ -1979,6 +1982,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp) goto err_irq_fail; } + enable_irq_wake(gfar_irq(grp, ER)->irq); + err = request_irq(gfar_irq(grp, TX)->irq, gfar_transmit, 0, gfar_irq(grp, TX)->name, grp); if (err < 0) { @@ -1994,14 +1999,14 @@ static int register_grp_irqs(struct gfar_priv_grp *grp) goto rx_irq_fail; } } else { - err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, - IRQF_NO_SUSPEND, + err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0, gfar_irq(grp, TX)->name, grp); if (err < 0) { netif_err(priv, intr, dev, "Can't get IRQ %d\n", gfar_irq(grp, TX)->irq); goto err_irq_fail; } + enable_irq_wake(gfar_irq(grp, TX)->irq); } return 0; diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c index 8e3cd77aa347..664d0c261269 100644 --- a/drivers/net/ethernet/freescale/gianfar_ptp.c +++ b/drivers/net/ethernet/freescale/gianfar_ptp.c @@ -557,6 +557,7 @@ static const struct of_device_id match_table[] = { { .compatible = "fsl,etsec-ptp" }, {}, }; +MODULE_DEVICE_TABLE(of, match_table); static struct platform_driver gianfar_ptp_driver = { .driver = { diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 4dd40e057f40..650f7888e32b 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1384,6 +1384,8 @@ static int adjust_enet_interface(struct ucc_geth_private *ugeth) value = phy_read(tbiphy, ENET_TBI_MII_CR); value &= ~0x1000; /* Turn off autonegotiation */ phy_write(tbiphy, ENET_TBI_MII_CR, value); + + put_device(&tbiphy->dev); } init_check_frame_length_mode(ug_info->lengthCheckRx, &ug_regs->maccfg2); @@ -1702,8 +1704,10 @@ static void uec_configure_serdes(struct net_device *dev) * everything for us? Resetting it takes the link down and requires * several seconds for it to come back. */ - if (phy_read(tbiphy, ENET_TBI_MII_SR) & TBISR_LSTATUS) + if (phy_read(tbiphy, ENET_TBI_MII_SR) & TBISR_LSTATUS) { + put_device(&tbiphy->dev); return; + } /* Single clk mode, mii mode off(for serdes communication) */ phy_write(tbiphy, ENET_TBI_MII_ANA, TBIANA_SETTINGS); @@ -1711,6 +1715,8 @@ static void uec_configure_serdes(struct net_device *dev) phy_write(tbiphy, ENET_TBI_MII_TBICON, TBICON_CLK_SELECT); phy_write(tbiphy, ENET_TBI_MII_CR, TBICR_SETTINGS); + + put_device(&tbiphy->dev); } /* Configure the PHY for dev. diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index fe2299ac4f5c..514df76fc70f 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1479,6 +1479,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo, struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq); struct sk_buff *skb; unsigned char *data; + dma_addr_t phys_addr; u32 rx_status; int rx_bytes, err; @@ -1486,6 +1487,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo, rx_status = rx_desc->status; rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE); data = (unsigned char *)rx_desc->buf_cookie; + phys_addr = rx_desc->buf_phys_addr; if (!mvneta_rxq_desc_is_first_last(rx_status) || (rx_status & MVNETA_RXD_ERR_SUMMARY)) { @@ -1534,7 +1536,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo, if (!skb) goto err_drop_frame; - dma_unmap_single(dev->dev.parent, rx_desc->buf_phys_addr, + dma_unmap_single(dev->dev.parent, phys_addr, MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE); rcvd_pkts++; @@ -3173,6 +3175,8 @@ static int mvneta_probe(struct platform_device *pdev) struct phy_device *phy = of_phy_find_device(dn); mvneta_fixed_link_update(pp, phy); + + put_device(&phy->dev); } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 4c7de8c44659..e7a5000aa12c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -1270,8 +1270,6 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv) rss_context->hash_fn = MLX4_RSS_HASH_TOP; memcpy(rss_context->rss_key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE); - netdev_rss_key_fill(rss_context->rss_key, - MLX4_EN_RSS_KEY_SIZE); } else { en_err(priv, "Unknown RSS hash function requested\n"); err = -EINVAL; diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c index 66d4ab703f45..60f43ec22175 100644 --- a/drivers/net/ethernet/micrel/ks8851.c +++ b/drivers/net/ethernet/micrel/ks8851.c @@ -1601,6 +1601,7 @@ static const struct of_device_id ks8851_match_table[] = { { .compatible = "micrel,ks8851" }, { } }; +MODULE_DEVICE_TABLE(of, ks8851_match_table); static struct spi_driver ks8851_driver = { .driver = { diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index becbb5f1f5a7..a10c928bbd6b 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -552,6 +552,7 @@ static const struct of_device_id moxart_mac_match[] = { { .compatible = "moxa,moxart-mac" }, { } }; +MODULE_DEVICE_TABLE(of, moxart_mac_match); static struct platform_driver moxart_mac_driver = { .probe = moxart_mac_probe, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 06bcc734fe8d..d6696cfa11d2 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -536,6 +536,7 @@ struct qlcnic_hardware_context { u8 extend_lb_time; u8 phys_port_id[ETH_ALEN]; u8 lb_mode; + u8 vxlan_port_count; u16 vxlan_port; struct device *hwmon_dev; u32 post_mode; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 8b08b20e8b30..d4481454b5f8 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -483,11 +483,17 @@ static void qlcnic_add_vxlan_port(struct net_device *netdev, /* Adapter supports only one VXLAN port. Use very first port * for enabling offload */ - if (!qlcnic_encap_rx_offload(adapter) || ahw->vxlan_port) + if (!qlcnic_encap_rx_offload(adapter)) return; + if (!ahw->vxlan_port_count) { + ahw->vxlan_port_count = 1; + ahw->vxlan_port = ntohs(port); + adapter->flags |= QLCNIC_ADD_VXLAN_PORT; + return; + } + if (ahw->vxlan_port == ntohs(port)) + ahw->vxlan_port_count++; - ahw->vxlan_port = ntohs(port); - adapter->flags |= QLCNIC_ADD_VXLAN_PORT; } static void qlcnic_del_vxlan_port(struct net_device *netdev, @@ -496,11 +502,13 @@ static void qlcnic_del_vxlan_port(struct net_device *netdev, struct qlcnic_adapter *adapter = netdev_priv(netdev); struct qlcnic_hardware_context *ahw = adapter->ahw; - if (!qlcnic_encap_rx_offload(adapter) || !ahw->vxlan_port || + if (!qlcnic_encap_rx_offload(adapter) || !ahw->vxlan_port_count || (ahw->vxlan_port != ntohs(port))) return; - adapter->flags |= QLCNIC_DEL_VXLAN_PORT; + ahw->vxlan_port_count--; + if (!ahw->vxlan_port_count) + adapter->flags |= QLCNIC_DEL_VXLAN_PORT; } static netdev_features_t qlcnic_features_check(struct sk_buff *skb, diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index d79e33b3c191..686334f4588d 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -157,6 +157,7 @@ enum { NWayAdvert = 0x66, /* MII ADVERTISE */ NWayLPAR = 0x68, /* MII LPA */ NWayExpansion = 0x6A, /* MII Expansion */ + TxDmaOkLowDesc = 0x82, /* Low 16 bit address of a Tx descriptor. */ Config5 = 0xD8, /* Config5 */ TxPoll = 0xD9, /* Tell chip to check Tx descriptors for work */ RxMaxSize = 0xDA, /* Max size of an Rx packet (8169 only) */ @@ -341,6 +342,7 @@ struct cp_private { unsigned tx_tail; struct cp_desc *tx_ring; struct sk_buff *tx_skb[CP_TX_RING_SIZE]; + u32 tx_opts[CP_TX_RING_SIZE]; unsigned rx_buf_sz; unsigned wol_enabled : 1; /* Is Wake-on-LAN enabled? */ @@ -665,7 +667,7 @@ static void cp_tx (struct cp_private *cp) BUG_ON(!skb); dma_unmap_single(&cp->pdev->dev, le64_to_cpu(txd->addr), - le32_to_cpu(txd->opts1) & 0xffff, + cp->tx_opts[tx_tail] & 0xffff, PCI_DMA_TODEVICE); if (status & LastFrag) { @@ -733,7 +735,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb, { struct cp_private *cp = netdev_priv(dev); unsigned entry; - u32 eor, flags; + u32 eor, opts1; unsigned long intr_flags; __le32 opts2; int mss = 0; @@ -753,6 +755,21 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb, mss = skb_shinfo(skb)->gso_size; opts2 = cpu_to_le32(cp_tx_vlan_tag(skb)); + opts1 = DescOwn; + if (mss) + opts1 |= LargeSend | ((mss & MSSMask) << MSSShift); + else if (skb->ip_summed == CHECKSUM_PARTIAL) { + const struct iphdr *ip = ip_hdr(skb); + if (ip->protocol == IPPROTO_TCP) + opts1 |= IPCS | TCPCS; + else if (ip->protocol == IPPROTO_UDP) + opts1 |= IPCS | UDPCS; + else { + WARN_ONCE(1, + "Net bug: asked to checksum invalid Legacy IP packet\n"); + goto out_dma_error; + } + } if (skb_shinfo(skb)->nr_frags == 0) { struct cp_desc *txd = &cp->tx_ring[entry]; @@ -768,31 +785,20 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb, txd->addr = cpu_to_le64(mapping); wmb(); - flags = eor | len | DescOwn | FirstFrag | LastFrag; + opts1 |= eor | len | FirstFrag | LastFrag; - if (mss) - flags |= LargeSend | ((mss & MSSMask) << MSSShift); - else if (skb->ip_summed == CHECKSUM_PARTIAL) { - const struct iphdr *ip = ip_hdr(skb); - if (ip->protocol == IPPROTO_TCP) - flags |= IPCS | TCPCS; - else if (ip->protocol == IPPROTO_UDP) - flags |= IPCS | UDPCS; - else - WARN_ON(1); /* we need a WARN() */ - } - - txd->opts1 = cpu_to_le32(flags); + txd->opts1 = cpu_to_le32(opts1); wmb(); cp->tx_skb[entry] = skb; - entry = NEXT_TX(entry); + cp->tx_opts[entry] = opts1; + netif_dbg(cp, tx_queued, cp->dev, "tx queued, slot %d, skblen %d\n", + entry, skb->len); } else { struct cp_desc *txd; - u32 first_len, first_eor; + u32 first_len, first_eor, ctrl; dma_addr_t first_mapping; int frag, first_entry = entry; - const struct iphdr *ip = ip_hdr(skb); /* We must give this initial chunk to the device last. * Otherwise we could race with the device. @@ -805,14 +811,14 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb, goto out_dma_error; cp->tx_skb[entry] = skb; - entry = NEXT_TX(entry); for (frag = 0; frag < skb_shinfo(skb)->nr_frags; frag++) { const skb_frag_t *this_frag = &skb_shinfo(skb)->frags[frag]; u32 len; - u32 ctrl; dma_addr_t mapping; + entry = NEXT_TX(entry); + len = skb_frag_size(this_frag); mapping = dma_map_single(&cp->pdev->dev, skb_frag_address(this_frag), @@ -824,19 +830,7 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb, eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0; - ctrl = eor | len | DescOwn; - - if (mss) - ctrl |= LargeSend | - ((mss & MSSMask) << MSSShift); - else if (skb->ip_summed == CHECKSUM_PARTIAL) { - if (ip->protocol == IPPROTO_TCP) - ctrl |= IPCS | TCPCS; - else if (ip->protocol == IPPROTO_UDP) - ctrl |= IPCS | UDPCS; - else - BUG(); - } + ctrl = opts1 | eor | len; if (frag == skb_shinfo(skb)->nr_frags - 1) ctrl |= LastFrag; @@ -849,8 +843,8 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb, txd->opts1 = cpu_to_le32(ctrl); wmb(); + cp->tx_opts[entry] = ctrl; cp->tx_skb[entry] = skb; - entry = NEXT_TX(entry); } txd = &cp->tx_ring[first_entry]; @@ -858,27 +852,17 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb, txd->addr = cpu_to_le64(first_mapping); wmb(); - if (skb->ip_summed == CHECKSUM_PARTIAL) { - if (ip->protocol == IPPROTO_TCP) - txd->opts1 = cpu_to_le32(first_eor | first_len | - FirstFrag | DescOwn | - IPCS | TCPCS); - else if (ip->protocol == IPPROTO_UDP) - txd->opts1 = cpu_to_le32(first_eor | first_len | - FirstFrag | DescOwn | - IPCS | UDPCS); - else - BUG(); - } else - txd->opts1 = cpu_to_le32(first_eor | first_len | - FirstFrag | DescOwn); + ctrl = opts1 | first_eor | first_len | FirstFrag; + txd->opts1 = cpu_to_le32(ctrl); wmb(); + + cp->tx_opts[first_entry] = ctrl; + netif_dbg(cp, tx_queued, cp->dev, "tx queued, slots %d-%d, skblen %d\n", + first_entry, entry, skb->len); } - cp->tx_head = entry; + cp->tx_head = NEXT_TX(entry); netdev_sent_queue(dev, skb->len); - netif_dbg(cp, tx_queued, cp->dev, "tx queued, slot %d, skblen %d\n", - entry, skb->len); if (TX_BUFFS_AVAIL(cp) <= (MAX_SKB_FRAGS + 1)) netif_stop_queue(dev); @@ -1115,6 +1099,7 @@ static int cp_init_rings (struct cp_private *cp) { memset(cp->tx_ring, 0, sizeof(struct cp_desc) * CP_TX_RING_SIZE); cp->tx_ring[CP_TX_RING_SIZE - 1].opts1 = cpu_to_le32(RingEnd); + memset(cp->tx_opts, 0, sizeof(cp->tx_opts)); cp_init_rings_index(cp); @@ -1151,7 +1136,7 @@ static void cp_clean_rings (struct cp_private *cp) desc = cp->rx_ring + i; dma_unmap_single(&cp->pdev->dev,le64_to_cpu(desc->addr), cp->rx_buf_sz, PCI_DMA_FROMDEVICE); - dev_kfree_skb(cp->rx_skb[i]); + dev_kfree_skb_any(cp->rx_skb[i]); } } @@ -1164,7 +1149,7 @@ static void cp_clean_rings (struct cp_private *cp) le32_to_cpu(desc->opts1) & 0xffff, PCI_DMA_TODEVICE); if (le32_to_cpu(desc->opts1) & LastFrag) - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); cp->dev->stats.tx_dropped++; } } @@ -1172,6 +1157,7 @@ static void cp_clean_rings (struct cp_private *cp) memset(cp->rx_ring, 0, sizeof(struct cp_desc) * CP_RX_RING_SIZE); memset(cp->tx_ring, 0, sizeof(struct cp_desc) * CP_TX_RING_SIZE); + memset(cp->tx_opts, 0, sizeof(cp->tx_opts)); memset(cp->rx_skb, 0, sizeof(struct sk_buff *) * CP_RX_RING_SIZE); memset(cp->tx_skb, 0, sizeof(struct sk_buff *) * CP_TX_RING_SIZE); @@ -1249,7 +1235,7 @@ static void cp_tx_timeout(struct net_device *dev) { struct cp_private *cp = netdev_priv(dev); unsigned long flags; - int rc; + int rc, i; netdev_warn(dev, "Transmit timeout, status %2x %4x %4x %4x\n", cpr8(Cmd), cpr16(CpCmd), @@ -1257,13 +1243,26 @@ static void cp_tx_timeout(struct net_device *dev) spin_lock_irqsave(&cp->lock, flags); + netif_dbg(cp, tx_err, cp->dev, "TX ring head %d tail %d desc %x\n", + cp->tx_head, cp->tx_tail, cpr16(TxDmaOkLowDesc)); + for (i = 0; i < CP_TX_RING_SIZE; i++) { + netif_dbg(cp, tx_err, cp->dev, + "TX slot %d @%p: %08x (%08x) %08x %llx %p\n", + i, &cp->tx_ring[i], le32_to_cpu(cp->tx_ring[i].opts1), + cp->tx_opts[i], le32_to_cpu(cp->tx_ring[i].opts2), + le64_to_cpu(cp->tx_ring[i].addr), + cp->tx_skb[i]); + } + cp_stop_hw(cp); cp_clean_rings(cp); rc = cp_init_rings(cp); cp_start_hw(cp); - cp_enable_irq(cp); + __cp_set_rx_mode(dev); + cpw16_f(IntrMask, cp_norx_intr_mask); netif_wake_queue(dev); + napi_schedule_irqoff(&cp->napi); spin_unlock_irqrestore(&cp->lock, flags); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index b735fa22ac95..ebf6abc4853f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -161,11 +161,16 @@ int stmmac_mdio_reset(struct mii_bus *bus) if (!gpio_request(reset_gpio, "mdio-reset")) { gpio_direction_output(reset_gpio, active_low ? 1 : 0); - udelay(data->delays[0]); + if (data->delays[0]) + msleep(DIV_ROUND_UP(data->delays[0], 1000)); + gpio_set_value(reset_gpio, active_low ? 0 : 1); - udelay(data->delays[1]); + if (data->delays[1]) + msleep(DIV_ROUND_UP(data->delays[1], 1000)); + gpio_set_value(reset_gpio, active_low ? 1 : 0); - udelay(data->delays[2]); + if (data->delays[2]) + msleep(DIV_ROUND_UP(data->delays[2], 1000)); } } #endif diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 53fe200e0b79..cc106d892e29 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -1756,7 +1756,8 @@ static const struct net_device_ops vnet_ops = { #endif }; -static struct vnet *vnet_new(const u64 *local_mac) +static struct vnet *vnet_new(const u64 *local_mac, + struct vio_dev *vdev) { struct net_device *dev; struct vnet *vp; @@ -1790,6 +1791,8 @@ static struct vnet *vnet_new(const u64 *local_mac) NETIF_F_HW_CSUM | NETIF_F_SG; dev->features = dev->hw_features; + SET_NETDEV_DEV(dev, &vdev->dev); + err = register_netdev(dev); if (err) { pr_err("Cannot register net device, aborting\n"); @@ -1808,7 +1811,8 @@ err_out_free_dev: return ERR_PTR(err); } -static struct vnet *vnet_find_or_create(const u64 *local_mac) +static struct vnet *vnet_find_or_create(const u64 *local_mac, + struct vio_dev *vdev) { struct vnet *iter, *vp; @@ -1821,7 +1825,7 @@ static struct vnet *vnet_find_or_create(const u64 *local_mac) } } if (!vp) - vp = vnet_new(local_mac); + vp = vnet_new(local_mac, vdev); mutex_unlock(&vnet_list_mutex); return vp; @@ -1848,7 +1852,8 @@ static void vnet_cleanup(void) static const char *local_mac_prop = "local-mac-address"; static struct vnet *vnet_find_parent(struct mdesc_handle *hp, - u64 port_node) + u64 port_node, + struct vio_dev *vdev) { const u64 *local_mac = NULL; u64 a; @@ -1869,7 +1874,7 @@ static struct vnet *vnet_find_parent(struct mdesc_handle *hp, if (!local_mac) return ERR_PTR(-ENODEV); - return vnet_find_or_create(local_mac); + return vnet_find_or_create(local_mac, vdev); } static struct ldc_channel_config vnet_ldc_cfg = { @@ -1923,7 +1928,7 @@ static int vnet_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) hp = mdesc_grab(); - vp = vnet_find_parent(hp, vdev->mp); + vp = vnet_find_parent(hp, vdev->mp, vdev); if (IS_ERR(vp)) { pr_err("Cannot find port parent vnet\n"); err = PTR_ERR(vp); diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 1a5aca55ea9f..9f9832f0dea9 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -291,13 +291,6 @@ static int netcp_module_probe(struct netcp_device *netcp_device, interface_list) { struct netcp_intf_modpriv *intf_modpriv; - /* If interface not registered then register now */ - if (!netcp_intf->netdev_registered) - ret = netcp_register_interface(netcp_intf); - - if (ret) - return -ENODEV; - intf_modpriv = devm_kzalloc(dev, sizeof(*intf_modpriv), GFP_KERNEL); if (!intf_modpriv) @@ -306,6 +299,11 @@ static int netcp_module_probe(struct netcp_device *netcp_device, interface = of_parse_phandle(netcp_intf->node_interface, module->name, 0); + if (!interface) { + devm_kfree(dev, intf_modpriv); + continue; + } + intf_modpriv->netcp_priv = netcp_intf; intf_modpriv->netcp_module = module; list_add_tail(&intf_modpriv->intf_list, @@ -323,6 +321,18 @@ static int netcp_module_probe(struct netcp_device *netcp_device, continue; } } + + /* Now register the interface with netdev */ + list_for_each_entry(netcp_intf, + &netcp_device->interface_head, + interface_list) { + /* If interface not registered then register now */ + if (!netcp_intf->netdev_registered) { + ret = netcp_register_interface(netcp_intf); + if (ret) + return -ENODEV; + } + } return 0; } @@ -357,7 +367,6 @@ int netcp_register_module(struct netcp_module *module) if (ret < 0) goto fail; } - mutex_unlock(&netcp_modules_lock); return 0; @@ -796,7 +805,7 @@ static void netcp_rxpool_free(struct netcp_intf *netcp) netcp->rx_pool = NULL; } -static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) +static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) { struct knav_dma_desc *hwdesc; unsigned int buf_len, dma_sz; @@ -810,7 +819,7 @@ static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) hwdesc = knav_pool_desc_get(netcp->rx_pool); if (IS_ERR_OR_NULL(hwdesc)) { dev_dbg(netcp->ndev_dev, "out of rx pool desc\n"); - return; + return -ENOMEM; } if (likely(fdq == 0)) { @@ -862,25 +871,26 @@ static void netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) knav_pool_desc_map(netcp->rx_pool, hwdesc, sizeof(*hwdesc), &dma, &dma_sz); knav_queue_push(netcp->rx_fdq[fdq], dma, sizeof(*hwdesc), 0); - return; + return 0; fail: knav_pool_desc_put(netcp->rx_pool, hwdesc); + return -ENOMEM; } /* Refill Rx FDQ with descriptors & attached buffers */ static void netcp_rxpool_refill(struct netcp_intf *netcp) { u32 fdq_deficit[KNAV_DMA_FDQ_PER_CHAN] = {0}; - int i; + int i, ret = 0; /* Calculate the FDQ deficit and refill */ for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN && netcp->rx_fdq[i]; i++) { fdq_deficit[i] = netcp->rx_queue_depths[i] - knav_queue_get_count(netcp->rx_fdq[i]); - while (fdq_deficit[i]--) - netcp_allocate_rx_buf(netcp, i); + while (fdq_deficit[i]-- && !ret) + ret = netcp_allocate_rx_buf(netcp, i); } /* end for fdqs */ } @@ -893,12 +903,12 @@ static int netcp_rx_poll(struct napi_struct *napi, int budget) packets = netcp_process_rx_packets(netcp, budget); + netcp_rxpool_refill(netcp); if (packets < budget) { napi_complete(&netcp->rx_napi); knav_queue_enable_notify(netcp->rx_queue); } - netcp_rxpool_refill(netcp); return packets; } @@ -1384,7 +1394,6 @@ static void netcp_addr_sweep_del(struct netcp_intf *netcp) continue; dev_dbg(netcp->ndev_dev, "deleting address %pM, type %x\n", naddr->addr, naddr->type); - mutex_lock(&netcp_modules_lock); for_each_module(netcp, priv) { module = priv->netcp_module; if (!module->del_addr) @@ -1393,7 +1402,6 @@ static void netcp_addr_sweep_del(struct netcp_intf *netcp) naddr); WARN_ON(error); } - mutex_unlock(&netcp_modules_lock); netcp_addr_del(netcp, naddr); } } @@ -1410,7 +1418,7 @@ static void netcp_addr_sweep_add(struct netcp_intf *netcp) continue; dev_dbg(netcp->ndev_dev, "adding address %pM, type %x\n", naddr->addr, naddr->type); - mutex_lock(&netcp_modules_lock); + for_each_module(netcp, priv) { module = priv->netcp_module; if (!module->add_addr) @@ -1418,7 +1426,6 @@ static void netcp_addr_sweep_add(struct netcp_intf *netcp) error = module->add_addr(priv->module_priv, naddr); WARN_ON(error); } - mutex_unlock(&netcp_modules_lock); } } @@ -1432,6 +1439,7 @@ static void netcp_set_rx_mode(struct net_device *ndev) ndev->flags & IFF_ALLMULTI || netdev_mc_count(ndev) > NETCP_MAX_MCAST_ADDR); + spin_lock(&netcp->lock); /* first clear all marks */ netcp_addr_clear_mark(netcp); @@ -1450,6 +1458,7 @@ static void netcp_set_rx_mode(struct net_device *ndev) /* finally sweep and callout into modules */ netcp_addr_sweep_del(netcp); netcp_addr_sweep_add(netcp); + spin_unlock(&netcp->lock); } static void netcp_free_navigator_resources(struct netcp_intf *netcp) @@ -1614,7 +1623,6 @@ static int netcp_ndo_open(struct net_device *ndev) goto fail; } - mutex_lock(&netcp_modules_lock); for_each_module(netcp, intf_modpriv) { module = intf_modpriv->netcp_module; if (module->open) { @@ -1625,7 +1633,6 @@ static int netcp_ndo_open(struct net_device *ndev) } } } - mutex_unlock(&netcp_modules_lock); napi_enable(&netcp->rx_napi); napi_enable(&netcp->tx_napi); @@ -1642,7 +1649,6 @@ fail_open: if (module->close) module->close(intf_modpriv->module_priv, ndev); } - mutex_unlock(&netcp_modules_lock); fail: netcp_free_navigator_resources(netcp); @@ -1666,7 +1672,6 @@ static int netcp_ndo_stop(struct net_device *ndev) napi_disable(&netcp->rx_napi); napi_disable(&netcp->tx_napi); - mutex_lock(&netcp_modules_lock); for_each_module(netcp, intf_modpriv) { module = intf_modpriv->netcp_module; if (module->close) { @@ -1675,7 +1680,6 @@ static int netcp_ndo_stop(struct net_device *ndev) dev_err(netcp->ndev_dev, "Close failed\n"); } } - mutex_unlock(&netcp_modules_lock); /* Recycle Rx descriptors from completion queue */ netcp_empty_rx_queue(netcp); @@ -1703,7 +1707,6 @@ static int netcp_ndo_ioctl(struct net_device *ndev, if (!netif_running(ndev)) return -EINVAL; - mutex_lock(&netcp_modules_lock); for_each_module(netcp, intf_modpriv) { module = intf_modpriv->netcp_module; if (!module->ioctl) @@ -1719,7 +1722,6 @@ static int netcp_ndo_ioctl(struct net_device *ndev, } out: - mutex_unlock(&netcp_modules_lock); return (ret == 0) ? 0 : err; } @@ -1754,11 +1756,12 @@ static int netcp_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) struct netcp_intf *netcp = netdev_priv(ndev); struct netcp_intf_modpriv *intf_modpriv; struct netcp_module *module; + unsigned long flags; int err = 0; dev_dbg(netcp->ndev_dev, "adding rx vlan id: %d\n", vid); - mutex_lock(&netcp_modules_lock); + spin_lock_irqsave(&netcp->lock, flags); for_each_module(netcp, intf_modpriv) { module = intf_modpriv->netcp_module; if ((module->add_vid) && (vid != 0)) { @@ -1770,7 +1773,8 @@ static int netcp_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) } } } - mutex_unlock(&netcp_modules_lock); + spin_unlock_irqrestore(&netcp->lock, flags); + return err; } @@ -1779,11 +1783,12 @@ static int netcp_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) struct netcp_intf *netcp = netdev_priv(ndev); struct netcp_intf_modpriv *intf_modpriv; struct netcp_module *module; + unsigned long flags; int err = 0; dev_dbg(netcp->ndev_dev, "removing rx vlan id: %d\n", vid); - mutex_lock(&netcp_modules_lock); + spin_lock_irqsave(&netcp->lock, flags); for_each_module(netcp, intf_modpriv) { module = intf_modpriv->netcp_module; if (module->del_vid) { @@ -1795,7 +1800,7 @@ static int netcp_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) } } } - mutex_unlock(&netcp_modules_lock); + spin_unlock_irqrestore(&netcp->lock, flags); return err; } @@ -2040,7 +2045,6 @@ static int netcp_probe(struct platform_device *pdev) struct device_node *child, *interfaces; struct netcp_device *netcp_device; struct device *dev = &pdev->dev; - struct netcp_module *module; int ret; if (!node) { @@ -2087,14 +2091,6 @@ static int netcp_probe(struct platform_device *pdev) /* Add the device instance to the list */ list_add_tail(&netcp_device->device_list, &netcp_devices); - /* Probe & attach any modules already registered */ - mutex_lock(&netcp_modules_lock); - for_each_netcp_module(module) { - ret = netcp_module_probe(netcp_device, module); - if (ret < 0) - dev_err(dev, "module(%s) probe failed\n", module->name); - } - mutex_unlock(&netcp_modules_lock); return 0; probe_quit_interface: diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 6f16d6aaf7b7..6bff8d82ceab 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -77,6 +77,7 @@ #define GBENU_ALE_OFFSET 0x1e000 #define GBENU_HOST_PORT_NUM 0 #define GBENU_NUM_ALE_ENTRIES 1024 +#define GBENU_SGMII_MODULE_SIZE 0x100 /* 10G Ethernet SS defines */ #define XGBE_MODULE_NAME "netcp-xgbe" @@ -149,8 +150,8 @@ #define XGBE_STATS2_MODULE 2 /* s: 0-based slave_port */ -#define SGMII_BASE(s) \ - (((s) < 2) ? gbe_dev->sgmii_port_regs : gbe_dev->sgmii_port34_regs) +#define SGMII_BASE(d, s) \ + (((s) < 2) ? (d)->sgmii_port_regs : (d)->sgmii_port34_regs) #define GBE_TX_QUEUE 648 #define GBE_TXHOOK_ORDER 0 @@ -1997,13 +1998,8 @@ static void netcp_ethss_update_link_state(struct gbe_priv *gbe_dev, return; if (!SLAVE_LINK_IS_XGMII(slave)) { - if (gbe_dev->ss_version == GBE_SS_VERSION_14) - sgmii_link_state = - netcp_sgmii_get_port_link(SGMII_BASE(sp), sp); - else - sgmii_link_state = - netcp_sgmii_get_port_link( - gbe_dev->sgmii_port_regs, sp); + sgmii_link_state = + netcp_sgmii_get_port_link(SGMII_BASE(gbe_dev, sp), sp); } phy_link_state = gbe_phy_link_status(slave); @@ -2100,17 +2096,11 @@ static void gbe_port_config(struct gbe_priv *gbe_dev, struct gbe_slave *slave, static void gbe_sgmii_rtreset(struct gbe_priv *priv, struct gbe_slave *slave, bool set) { - void __iomem *sgmii_port_regs; - if (SLAVE_LINK_IS_XGMII(slave)) return; - if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2)) - sgmii_port_regs = priv->sgmii_port34_regs; - else - sgmii_port_regs = priv->sgmii_port_regs; - - netcp_sgmii_rtreset(sgmii_port_regs, slave->slave_num, set); + netcp_sgmii_rtreset(SGMII_BASE(priv, slave->slave_num), + slave->slave_num, set); } static void gbe_slave_stop(struct gbe_intf *intf) @@ -2136,17 +2126,12 @@ static void gbe_slave_stop(struct gbe_intf *intf) static void gbe_sgmii_config(struct gbe_priv *priv, struct gbe_slave *slave) { - void __iomem *sgmii_port_regs; + if (SLAVE_LINK_IS_XGMII(slave)) + return; - sgmii_port_regs = priv->sgmii_port_regs; - if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2)) - sgmii_port_regs = priv->sgmii_port34_regs; - - if (!SLAVE_LINK_IS_XGMII(slave)) { - netcp_sgmii_reset(sgmii_port_regs, slave->slave_num); - netcp_sgmii_config(sgmii_port_regs, slave->slave_num, - slave->link_interface); - } + netcp_sgmii_reset(SGMII_BASE(priv, slave->slave_num), slave->slave_num); + netcp_sgmii_config(SGMII_BASE(priv, slave->slave_num), slave->slave_num, + slave->link_interface); } static int gbe_slave_open(struct gbe_intf *gbe_intf) @@ -2997,6 +2982,14 @@ static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev, gbe_dev->switch_regs = regs; gbe_dev->sgmii_port_regs = gbe_dev->ss_regs + GBENU_SGMII_MODULE_OFFSET; + + /* Although sgmii modules are mem mapped to one contiguous + * region on GBENU devices, setting sgmii_port34_regs allows + * consistent code when accessing sgmii api + */ + gbe_dev->sgmii_port34_regs = gbe_dev->sgmii_port_regs + + (2 * GBENU_SGMII_MODULE_SIZE); + gbe_dev->host_port_regs = gbe_dev->switch_regs + GBENU_HOST_PORT_OFFSET; for (i = 0; i < (gbe_dev->max_num_ports); i++) diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig index 2f1264b882b9..d3d094742a7e 100644 --- a/drivers/net/ethernet/via/Kconfig +++ b/drivers/net/ethernet/via/Kconfig @@ -17,7 +17,7 @@ if NET_VENDOR_VIA config VIA_RHINE tristate "VIA Rhine support" - depends on (PCI || OF_IRQ) + depends on PCI || (OF_IRQ && GENERIC_PCI_IOMAP) depends on HAS_DMA select CRC32 select MII diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 6008eee01a33..cf468c87ce57 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -828,6 +828,8 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev) if (!phydev) dev_info(dev, "MDIO of the phy is not registered yet\n"); + else + put_device(&phydev->dev); return 0; } diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index b5f4a78da828..2d3848c9dc35 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -1011,11 +1011,11 @@ static void fjes_hw_update_zone_task(struct work_struct *work) set_bit(epidx, &irq_bit); break; } + + hw->ep_shm_info[epidx].es_status = + info[epidx].es_status; + hw->ep_shm_info[epidx].zone = info[epidx].zone; } - - hw->ep_shm_info[epidx].es_status = info[epidx].es_status; - hw->ep_shm_info[epidx].zone = info[epidx].zone; - break; } diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index da3259ce7c8d..8f5c02eed47d 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -126,6 +126,8 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb) __be32 addr; int err; + iph = ip_hdr(skb); /* outer IP header... */ + if (gs->collect_md) { static u8 zero_vni[3]; @@ -133,7 +135,6 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb) addr = 0; } else { vni = gnvh->vni; - iph = ip_hdr(skb); /* Still outer IP header... */ addr = iph->saddr; } @@ -178,7 +179,6 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb) skb_reset_network_header(skb); - iph = ip_hdr(skb); /* Now inner IP header... */ err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { @@ -626,6 +626,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) struct geneve_sock *gs = geneve->sock; struct ip_tunnel_info *info = NULL; struct rtable *rt = NULL; + const struct iphdr *iip; /* interior IP header */ struct flowi4 fl4; __u8 tos, ttl; __be16 sport; @@ -653,6 +654,8 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); skb_reset_mac_header(skb); + iip = ip_hdr(skb); + if (info) { const struct ip_tunnel_key *key = &info->key; u8 *opts = NULL; @@ -668,19 +671,16 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(err)) goto err; - tos = key->tos; + tos = ip_tunnel_ecn_encap(key->tos, iip, skb); ttl = key->ttl; df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; } else { - const struct iphdr *iip; /* interior IP header */ - udp_csum = false; err = geneve_build_skb(rt, skb, 0, geneve->vni, 0, NULL, udp_csum); if (unlikely(err)) goto err; - iip = ip_hdr(skb); tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb); ttl = geneve->ttl; if (!ttl && IN_MULTICAST(ntohl(fl4.daddr))) @@ -748,12 +748,8 @@ static void geneve_setup(struct net_device *dev) dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; - dev->vlan_features = dev->features; - dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; - dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; netif_keep_dst(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; @@ -819,7 +815,7 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, static int geneve_configure(struct net *net, struct net_device *dev, __be32 rem_addr, __u32 vni, __u8 ttl, __u8 tos, - __u16 dst_port, bool metadata) + __be16 dst_port, bool metadata) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); @@ -844,10 +840,10 @@ static int geneve_configure(struct net *net, struct net_device *dev, geneve->ttl = ttl; geneve->tos = tos; - geneve->dst_port = htons(dst_port); + geneve->dst_port = dst_port; geneve->collect_md = metadata; - t = geneve_find_dev(gn, htons(dst_port), rem_addr, geneve->vni, + t = geneve_find_dev(gn, dst_port, rem_addr, geneve->vni, &tun_on_same_port, &tun_collect_md); if (t) return -EBUSY; @@ -871,7 +867,7 @@ static int geneve_configure(struct net *net, struct net_device *dev, static int geneve_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - __u16 dst_port = GENEVE_UDP_PORT; + __be16 dst_port = htons(GENEVE_UDP_PORT); __u8 ttl = 0, tos = 0; bool metadata = false; __be32 rem_addr; @@ -890,7 +886,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev, tos = nla_get_u8(data[IFLA_GENEVE_TOS]); if (data[IFLA_GENEVE_PORT]) - dst_port = nla_get_u16(data[IFLA_GENEVE_PORT]); + dst_port = nla_get_be16(data[IFLA_GENEVE_PORT]); if (data[IFLA_GENEVE_COLLECT_METADATA]) metadata = true; @@ -913,7 +909,7 @@ static size_t geneve_get_size(const struct net_device *dev) nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ - nla_total_size(sizeof(__u16)) + /* IFLA_GENEVE_PORT */ + nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */ nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */ 0; } @@ -935,7 +931,7 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos)) goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GENEVE_PORT, ntohs(geneve->dst_port))) + if (nla_put_be16(skb, IFLA_GENEVE_PORT, geneve->dst_port)) goto nla_put_failure; if (geneve->collect_md) { @@ -975,7 +971,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, if (IS_ERR(dev)) return dev; - err = geneve_configure(net, dev, 0, 0, 0, 0, dst_port, true); + err = geneve_configure(net, dev, 0, 0, 0, 0, htons(dst_port), true); if (err) { free_netdev(dev); return ERR_PTR(err); diff --git a/drivers/net/irda/ali-ircc.c b/drivers/net/irda/ali-ircc.c index 58ae11a14bb6..64bb44d5d867 100644 --- a/drivers/net/irda/ali-ircc.c +++ b/drivers/net/irda/ali-ircc.c @@ -1031,7 +1031,6 @@ static void ali_ircc_fir_change_speed(struct ali_ircc_cb *priv, __u32 baud) static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed) { struct ali_ircc_cb *self = priv; - unsigned long flags; int iobase; int fcr; /* FIFO control reg */ int lcr; /* Line control reg */ @@ -1061,8 +1060,6 @@ static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed) /* Update accounting for new speed */ self->io.speed = speed; - spin_lock_irqsave(&self->lock, flags); - divisor = 115200/speed; fcr = UART_FCR_ENABLE_FIFO; @@ -1089,9 +1086,6 @@ static void ali_ircc_sir_change_speed(struct ali_ircc_cb *priv, __u32 speed) /* without this, the connection will be broken after come back from FIR speed, but with this, the SIR connection is harder to established */ outb((UART_MCR_DTR | UART_MCR_RTS | UART_MCR_OUT2), iobase+UART_MCR); - - spin_unlock_irqrestore(&self->lock, flags); - } static void ali_ircc_change_dongle_speed(struct ali_ircc_cb *priv, int speed) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index edd77342773a..248478c6f6e4 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -1111,10 +1111,10 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, return 0; case TUNSETSNDBUF: - if (get_user(u, up)) + if (get_user(s, sp)) return -EFAULT; - q->sk.sk_sndbuf = u; + q->sk.sk_sndbuf = s; return 0; case TUNGETVNETHDRSZ: diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index fb1299c6326e..e23bf5b90e17 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -220,7 +220,7 @@ int fixed_phy_update_state(struct phy_device *phydev, struct fixed_mdio_bus *fmb = &platform_fmb; struct fixed_phy *fp; - if (!phydev || !phydev->bus) + if (!phydev || phydev->bus != fmb->mii_bus) return -EINVAL; list_for_each_entry(fp, &fmb->phys, node) { diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index e6897b6a8a53..5de8d5827536 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -785,6 +785,7 @@ static int marvell_read_status(struct phy_device *phydev) int adv; int err; int lpa; + int lpagb; int status = 0; /* Update the link, but return if there @@ -802,10 +803,17 @@ static int marvell_read_status(struct phy_device *phydev) if (lpa < 0) return lpa; + lpagb = phy_read(phydev, MII_STAT1000); + if (lpagb < 0) + return lpagb; + adv = phy_read(phydev, MII_ADVERTISE); if (adv < 0) return adv; + phydev->lp_advertising = mii_stat1000_to_ethtool_lpa_t(lpagb) | + mii_lpa_to_ethtool_lpa_t(lpa); + lpa &= adv; if (status & MII_M1011_PHY_STATUS_FULLDUPLEX) @@ -853,6 +861,7 @@ static int marvell_read_status(struct phy_device *phydev) phydev->speed = SPEED_10; phydev->pause = phydev->asym_pause = 0; + phydev->lp_advertising = 0; } return 0; diff --git a/drivers/net/phy/mdio-bcm-unimac.c b/drivers/net/phy/mdio-bcm-unimac.c index 6a52a7f0fa0d..4bde5e728fe0 100644 --- a/drivers/net/phy/mdio-bcm-unimac.c +++ b/drivers/net/phy/mdio-bcm-unimac.c @@ -244,6 +244,7 @@ static const struct of_device_id unimac_mdio_ids[] = { { .compatible = "brcm,unimac-mdio", }, { /* sentinel */ }, }; +MODULE_DEVICE_TABLE(of, unimac_mdio_ids); static struct platform_driver unimac_mdio_driver = { .driver = { diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c index 7dc21e56a7aa..3bc9f03349f3 100644 --- a/drivers/net/phy/mdio-gpio.c +++ b/drivers/net/phy/mdio-gpio.c @@ -261,6 +261,7 @@ static const struct of_device_id mdio_gpio_of_match[] = { { .compatible = "virtual,mdio-gpio", }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, mdio_gpio_of_match); static struct platform_driver mdio_gpio_driver = { .probe = mdio_gpio_probe, diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 4d4d25efc1e1..280c7c311f72 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -113,18 +113,18 @@ int mdio_mux_init(struct device *dev, if (!parent_bus_node) return -ENODEV; - parent_bus = of_mdio_find_bus(parent_bus_node); - if (parent_bus == NULL) { - ret_val = -EPROBE_DEFER; - goto err_parent_bus; - } - pb = devm_kzalloc(dev, sizeof(*pb), GFP_KERNEL); if (pb == NULL) { ret_val = -ENOMEM; goto err_parent_bus; } + parent_bus = of_mdio_find_bus(parent_bus_node); + if (parent_bus == NULL) { + ret_val = -EPROBE_DEFER; + goto err_parent_bus; + } + pb->switch_data = data; pb->switch_fn = switch_fn; pb->current_child = -1; @@ -173,6 +173,10 @@ int mdio_mux_init(struct device *dev, dev_info(dev, "Version " DRV_VERSION "\n"); return 0; } + + /* balance the reference of_mdio_find_bus() took */ + put_device(&pb->mii_bus->dev); + err_parent_bus: of_node_put(parent_bus_node); return ret_val; @@ -189,6 +193,9 @@ void mdio_mux_uninit(void *mux_handle) mdiobus_free(cb->mii_bus); cb = cb->next; } + + /* balance the reference of_mdio_find_bus() in mdio_mux_init() took */ + put_device(&pb->mii_bus->dev); } EXPORT_SYMBOL_GPL(mdio_mux_uninit); diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 02a4615b65f8..12f44c53cc8e 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -167,7 +167,9 @@ static int of_mdio_bus_match(struct device *dev, const void *mdio_bus_np) * of_mdio_find_bus - Given an mii_bus node, find the mii_bus. * @mdio_bus_np: Pointer to the mii_bus. * - * Returns a pointer to the mii_bus, or NULL if none found. + * Returns a reference to the mii_bus, or NULL if none found. The + * embedded struct device will have its reference count incremented, + * and this must be put once the bus is finished with. * * Because the association of a device_node and mii_bus is made via * of_mdiobus_register(), the mii_bus cannot be found before it is @@ -234,15 +236,18 @@ static inline void of_mdiobus_link_phydev(struct mii_bus *mdio, #endif /** - * mdiobus_register - bring up all the PHYs on a given bus and attach them to bus + * __mdiobus_register - bring up all the PHYs on a given bus and attach them to bus * @bus: target mii_bus + * @owner: module containing bus accessor functions * * Description: Called by a bus driver to bring up all the PHYs - * on a given bus, and attach them to the bus. + * on a given bus, and attach them to the bus. Drivers should use + * mdiobus_register() rather than __mdiobus_register() unless they + * need to pass a specific owner module. * * Returns 0 on success or < 0 on error. */ -int mdiobus_register(struct mii_bus *bus) +int __mdiobus_register(struct mii_bus *bus, struct module *owner) { int i, err; @@ -253,6 +258,7 @@ int mdiobus_register(struct mii_bus *bus) BUG_ON(bus->state != MDIOBUS_ALLOCATED && bus->state != MDIOBUS_UNREGISTERED); + bus->owner = owner; bus->dev.parent = bus->parent; bus->dev.class = &mdio_bus_class; bus->dev.groups = NULL; @@ -288,13 +294,16 @@ int mdiobus_register(struct mii_bus *bus) error: while (--i >= 0) { - if (bus->phy_map[i]) - device_unregister(&bus->phy_map[i]->dev); + struct phy_device *phydev = bus->phy_map[i]; + if (phydev) { + phy_device_remove(phydev); + phy_device_free(phydev); + } } device_del(&bus->dev); return err; } -EXPORT_SYMBOL(mdiobus_register); +EXPORT_SYMBOL(__mdiobus_register); void mdiobus_unregister(struct mii_bus *bus) { @@ -304,9 +313,11 @@ void mdiobus_unregister(struct mii_bus *bus) bus->state = MDIOBUS_UNREGISTERED; for (i = 0; i < PHY_MAX_ADDR; i++) { - if (bus->phy_map[i]) - device_unregister(&bus->phy_map[i]->dev); - bus->phy_map[i] = NULL; + struct phy_device *phydev = bus->phy_map[i]; + if (phydev) { + phy_device_remove(phydev); + phy_device_free(phydev); + } } device_del(&bus->dev); } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index c0f211127274..f761288abe66 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -383,6 +383,24 @@ int phy_device_register(struct phy_device *phydev) } EXPORT_SYMBOL(phy_device_register); +/** + * phy_device_remove - Remove a previously registered phy device from the MDIO bus + * @phydev: phy_device structure to remove + * + * This doesn't free the phy_device itself, it merely reverses the effects + * of phy_device_register(). Use phy_device_free() to free the device + * after calling this function. + */ +void phy_device_remove(struct phy_device *phydev) +{ + struct mii_bus *bus = phydev->bus; + int addr = phydev->addr; + + device_del(&phydev->dev); + bus->phy_map[addr] = NULL; +} +EXPORT_SYMBOL(phy_device_remove); + /** * phy_find_first - finds the first PHY device on the bus * @bus: the target MII bus @@ -578,14 +596,22 @@ EXPORT_SYMBOL(phy_init_hw); * generic driver is used. The phy_device is given a ptr to * the attaching device, and given a callback for link status * change. The phy_device is returned to the attaching driver. + * This function takes a reference on the phy device. */ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface) { + struct mii_bus *bus = phydev->bus; struct device *d = &phydev->dev; - struct module *bus_module; int err; + if (!try_module_get(bus->owner)) { + dev_err(&dev->dev, "failed to get the bus module\n"); + return -EIO; + } + + get_device(d); + /* Assume that if there is no driver, that it doesn't * exist, and we should use the genphy driver. */ @@ -600,20 +626,13 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, err = device_bind_driver(d); if (err) - return err; + goto error; } if (phydev->attached_dev) { dev_err(&dev->dev, "PHY already attached\n"); - return -EBUSY; - } - - /* Increment the bus module reference count */ - bus_module = phydev->bus->dev.driver ? - phydev->bus->dev.driver->owner : NULL; - if (!try_module_get(bus_module)) { - dev_err(&dev->dev, "failed to get the bus module\n"); - return -EIO; + err = -EBUSY; + goto error; } phydev->attached_dev = dev; @@ -636,6 +655,11 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, phy_resume(phydev); return err; + +error: + put_device(d); + module_put(bus->owner); + return err; } EXPORT_SYMBOL(phy_attach_direct); @@ -677,14 +701,15 @@ EXPORT_SYMBOL(phy_attach); /** * phy_detach - detach a PHY device from its network device * @phydev: target phy_device struct + * + * This detaches the phy device from its network device and the phy + * driver, and drops the reference count taken in phy_attach_direct(). */ void phy_detach(struct phy_device *phydev) { + struct mii_bus *bus; int i; - if (phydev->bus->dev.driver) - module_put(phydev->bus->dev.driver->owner); - phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; phy_suspend(phydev); @@ -700,6 +725,15 @@ void phy_detach(struct phy_device *phydev) break; } } + + /* + * The phydev might go away on the put_device() below, so avoid + * a use-after-free bug by reading the underlying bus first. + */ + bus = phydev->bus; + + put_device(&phydev->dev); + module_put(bus->owner); } EXPORT_SYMBOL(phy_detach); diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 17cad185169d..76cad712ddb2 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -66,7 +66,6 @@ #define PHY_ID_VSC8244 0x000fc6c0 #define PHY_ID_VSC8514 0x00070670 #define PHY_ID_VSC8574 0x000704a0 -#define PHY_ID_VSC8641 0x00070431 #define PHY_ID_VSC8662 0x00070660 #define PHY_ID_VSC8221 0x000fc550 #define PHY_ID_VSC8211 0x000fc4b0 @@ -272,18 +271,6 @@ static struct phy_driver vsc82xx_driver[] = { .ack_interrupt = &vsc824x_ack_interrupt, .config_intr = &vsc82xx_config_intr, .driver = { .owner = THIS_MODULE,}, -}, { - .phy_id = PHY_ID_VSC8641, - .name = "Vitesse VSC8641", - .phy_id_mask = 0x000ffff0, - .features = PHY_GBIT_FEATURES, - .flags = PHY_HAS_INTERRUPT, - .config_init = &vsc824x_config_init, - .config_aneg = &vsc82x4_config_aneg, - .read_status = &genphy_read_status, - .ack_interrupt = &vsc824x_ack_interrupt, - .config_intr = &vsc82xx_config_intr, - .driver = { .owner = THIS_MODULE,}, }, { .phy_id = PHY_ID_VSC8662, .name = "Vitesse VSC8662", @@ -331,7 +318,6 @@ static struct mdio_device_id __maybe_unused vitesse_tbl[] = { { PHY_ID_VSC8244, 0x000fffc0 }, { PHY_ID_VSC8514, 0x000ffff0 }, { PHY_ID_VSC8574, 0x000ffff0 }, - { PHY_ID_VSC8641, 0x000ffff0 }, { PHY_ID_VSC8662, 0x000ffff0 }, { PHY_ID_VSC8221, 0x000ffff0 }, { PHY_ID_VSC8211, 0x000ffff0 }, diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 0481daf9201a..ed00446759b2 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -2755,6 +2755,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit, */ dev_net_set(dev, net); + rtnl_lock(); mutex_lock(&pn->all_ppp_mutex); if (unit < 0) { @@ -2785,7 +2786,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit, ppp->file.index = unit; sprintf(dev->name, "ppp%d", unit); - ret = register_netdev(dev); + ret = register_netdevice(dev); if (ret != 0) { unit_put(&pn->units_idr, unit); netdev_err(ppp->dev, "PPP: couldn't register device %s (%d)\n", @@ -2797,6 +2798,7 @@ static struct ppp *ppp_create_interface(struct net *net, int unit, atomic_inc(&ppp_unit_count); mutex_unlock(&pn->all_ppp_mutex); + rtnl_unlock(); *retp = 0; return ppp; diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 1610b79ae386..fbb9325d1f6e 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -583,4 +583,15 @@ config USB_VL600 http://ubuntuforums.org/showpost.php?p=10589647&postcount=17 +config USB_NET_CH9200 + tristate "QingHeng CH9200 USB ethernet support" + depends on USB_USBNET + select MII + help + Choose this option if you have a USB ethernet adapter with a QinHeng + CH9200 chipset. + + To compile this driver as a module, choose M here: the + module will be called ch9200. + endif # USB_NET_DRIVERS diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile index cf6a0e610a7f..b5f04068dbe4 100644 --- a/drivers/net/usb/Makefile +++ b/drivers/net/usb/Makefile @@ -38,4 +38,4 @@ obj-$(CONFIG_USB_NET_HUAWEI_CDC_NCM) += huawei_cdc_ncm.o obj-$(CONFIG_USB_VL600) += lg-vl600.o obj-$(CONFIG_USB_NET_QMI_WWAN) += qmi_wwan.o obj-$(CONFIG_USB_NET_CDC_MBIM) += cdc_mbim.o - +obj-$(CONFIG_USB_NET_CH9200) += ch9200.o diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c new file mode 100644 index 000000000000..5e151e6a3e09 --- /dev/null +++ b/drivers/net/usb/ch9200.c @@ -0,0 +1,432 @@ +/* + * USB 10M/100M ethernet adapter + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CH9200_VID 0x1A86 +#define CH9200_PID_E092 0xE092 + +#define CTRL_TIMEOUT_MS 1000 + +#define CONTROL_TIMEOUT_MS 1000 + +#define REQUEST_READ 0x0E +#define REQUEST_WRITE 0x0F + +/* Address space: + * 00-63 : MII + * 64-128: MAC + * + * Note: all accesses must be 16-bit + */ + +#define MAC_REG_CTRL 64 +#define MAC_REG_STATUS 66 +#define MAC_REG_INTERRUPT_MASK 68 +#define MAC_REG_PHY_COMMAND 70 +#define MAC_REG_PHY_DATA 72 +#define MAC_REG_STATION_L 74 +#define MAC_REG_STATION_M 76 +#define MAC_REG_STATION_H 78 +#define MAC_REG_HASH_L 80 +#define MAC_REG_HASH_M1 82 +#define MAC_REG_HASH_M2 84 +#define MAC_REG_HASH_H 86 +#define MAC_REG_THRESHOLD 88 +#define MAC_REG_FIFO_DEPTH 90 +#define MAC_REG_PAUSE 92 +#define MAC_REG_FLOW_CONTROL 94 + +/* Control register bits + * + * Note: bits 13 and 15 are reserved + */ +#define LOOPBACK (0x01 << 14) +#define BASE100X (0x01 << 12) +#define MBPS_10 (0x01 << 11) +#define DUPLEX_MODE (0x01 << 10) +#define PAUSE_FRAME (0x01 << 9) +#define PROMISCUOUS (0x01 << 8) +#define MULTICAST (0x01 << 7) +#define BROADCAST (0x01 << 6) +#define HASH (0x01 << 5) +#define APPEND_PAD (0x01 << 4) +#define APPEND_CRC (0x01 << 3) +#define TRANSMITTER_ACTION (0x01 << 2) +#define RECEIVER_ACTION (0x01 << 1) +#define DMA_ACTION (0x01 << 0) + +/* Status register bits + * + * Note: bits 7-15 are reserved + */ +#define ALIGNMENT (0x01 << 6) +#define FIFO_OVER_RUN (0x01 << 5) +#define FIFO_UNDER_RUN (0x01 << 4) +#define RX_ERROR (0x01 << 3) +#define RX_COMPLETE (0x01 << 2) +#define TX_ERROR (0x01 << 1) +#define TX_COMPLETE (0x01 << 0) + +/* FIFO depth register bits + * + * Note: bits 6 and 14 are reserved + */ + +#define ETH_TXBD (0x01 << 15) +#define ETN_TX_FIFO_DEPTH (0x01 << 8) +#define ETH_RXBD (0x01 << 7) +#define ETH_RX_FIFO_DEPTH (0x01 << 0) + +static int control_read(struct usbnet *dev, + unsigned char request, unsigned short value, + unsigned short index, void *data, unsigned short size, + int timeout) +{ + unsigned char *buf = NULL; + unsigned char request_type; + int err = 0; + + if (request == REQUEST_READ) + request_type = (USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_OTHER); + else + request_type = (USB_DIR_IN | USB_TYPE_VENDOR | + USB_RECIP_DEVICE); + + netdev_dbg(dev->net, "Control_read() index=0x%02x size=%d\n", + index, size); + + buf = kmalloc(size, GFP_KERNEL); + if (!buf) { + err = -ENOMEM; + goto err_out; + } + + err = usb_control_msg(dev->udev, + usb_rcvctrlpipe(dev->udev, 0), + request, request_type, value, index, buf, size, + timeout); + if (err == size) + memcpy(data, buf, size); + else if (err >= 0) + err = -EINVAL; + kfree(buf); + + return err; + +err_out: + return err; +} + +static int control_write(struct usbnet *dev, unsigned char request, + unsigned short value, unsigned short index, + void *data, unsigned short size, int timeout) +{ + unsigned char *buf = NULL; + unsigned char request_type; + int err = 0; + + if (request == REQUEST_WRITE) + request_type = (USB_DIR_OUT | USB_TYPE_VENDOR | + USB_RECIP_OTHER); + else + request_type = (USB_DIR_OUT | USB_TYPE_VENDOR | + USB_RECIP_DEVICE); + + netdev_dbg(dev->net, "Control_write() index=0x%02x size=%d\n", + index, size); + + if (data) { + buf = kmalloc(size, GFP_KERNEL); + if (!buf) { + err = -ENOMEM; + goto err_out; + } + memcpy(buf, data, size); + } + + err = usb_control_msg(dev->udev, + usb_sndctrlpipe(dev->udev, 0), + request, request_type, value, index, buf, size, + timeout); + if (err >= 0 && err < size) + err = -EINVAL; + kfree(buf); + + return 0; + +err_out: + return err; +} + +static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc) +{ + struct usbnet *dev = netdev_priv(netdev); + unsigned char buff[2]; + + netdev_dbg(netdev, "ch9200_mdio_read phy_id:%02x loc:%02x\n", + phy_id, loc); + + if (phy_id != 0) + return -ENODEV; + + control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02, + CONTROL_TIMEOUT_MS); + + return (buff[0] | buff[1] << 8); +} + +static void ch9200_mdio_write(struct net_device *netdev, + int phy_id, int loc, int val) +{ + struct usbnet *dev = netdev_priv(netdev); + unsigned char buff[2]; + + netdev_dbg(netdev, "ch9200_mdio_write() phy_id=%02x loc:%02x\n", + phy_id, loc); + + if (phy_id != 0) + return; + + buff[0] = (unsigned char)val; + buff[1] = (unsigned char)(val >> 8); + + control_write(dev, REQUEST_WRITE, 0, loc * 2, buff, 0x02, + CONTROL_TIMEOUT_MS); +} + +static int ch9200_link_reset(struct usbnet *dev) +{ + struct ethtool_cmd ecmd; + + mii_check_media(&dev->mii, 1, 1); + mii_ethtool_gset(&dev->mii, &ecmd); + + netdev_dbg(dev->net, "link_reset() speed:%d duplex:%d\n", + ecmd.speed, ecmd.duplex); + + return 0; +} + +static void ch9200_status(struct usbnet *dev, struct urb *urb) +{ + int link; + unsigned char *buf; + + if (urb->actual_length < 16) + return; + + buf = urb->transfer_buffer; + link = !!(buf[0] & 0x01); + + if (link) { + netif_carrier_on(dev->net); + usbnet_defer_kevent(dev, EVENT_LINK_RESET); + } else { + netif_carrier_off(dev->net); + } +} + +static struct sk_buff *ch9200_tx_fixup(struct usbnet *dev, struct sk_buff *skb, + gfp_t flags) +{ + int i = 0; + int len = 0; + int tx_overhead = 0; + + tx_overhead = 0x40; + + len = skb->len; + if (skb_headroom(skb) < tx_overhead) { + struct sk_buff *skb2; + + skb2 = skb_copy_expand(skb, tx_overhead, 0, flags); + dev_kfree_skb_any(skb); + skb = skb2; + if (!skb) + return NULL; + } + + __skb_push(skb, tx_overhead); + /* usbnet adds padding if length is a multiple of packet size + * if so, adjust length value in header + */ + if ((skb->len % dev->maxpacket) == 0) + len++; + + skb->data[0] = len; + skb->data[1] = len >> 8; + skb->data[2] = 0x00; + skb->data[3] = 0x80; + + for (i = 4; i < 48; i++) + skb->data[i] = 0x00; + + skb->data[48] = len; + skb->data[49] = len >> 8; + skb->data[50] = 0x00; + skb->data[51] = 0x80; + + for (i = 52; i < 64; i++) + skb->data[i] = 0x00; + + return skb; +} + +static int ch9200_rx_fixup(struct usbnet *dev, struct sk_buff *skb) +{ + int len = 0; + int rx_overhead = 0; + + rx_overhead = 64; + + if (unlikely(skb->len < rx_overhead)) { + dev_err(&dev->udev->dev, "unexpected tiny rx frame\n"); + return 0; + } + + len = (skb->data[skb->len - 16] | skb->data[skb->len - 15] << 8); + skb_trim(skb, len); + + return 1; +} + +static int get_mac_address(struct usbnet *dev, unsigned char *data) +{ + int err = 0; + unsigned char mac_addr[0x06]; + int rd_mac_len = 0; + + netdev_dbg(dev->net, "get_mac_address:\n\tusbnet VID:%0x PID:%0x\n", + dev->udev->descriptor.idVendor, + dev->udev->descriptor.idProduct); + + memset(mac_addr, 0, sizeof(mac_addr)); + rd_mac_len = control_read(dev, REQUEST_READ, 0, + MAC_REG_STATION_L, mac_addr, 0x02, + CONTROL_TIMEOUT_MS); + rd_mac_len += control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_M, + mac_addr + 2, 0x02, CONTROL_TIMEOUT_MS); + rd_mac_len += control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_H, + mac_addr + 4, 0x02, CONTROL_TIMEOUT_MS); + if (rd_mac_len != ETH_ALEN) + err = -EINVAL; + + data[0] = mac_addr[5]; + data[1] = mac_addr[4]; + data[2] = mac_addr[3]; + data[3] = mac_addr[2]; + data[4] = mac_addr[1]; + data[5] = mac_addr[0]; + + return err; +} + +static int ch9200_bind(struct usbnet *dev, struct usb_interface *intf) +{ + int retval = 0; + unsigned char data[2]; + + retval = usbnet_get_endpoints(dev, intf); + if (retval) + return retval; + + dev->mii.dev = dev->net; + dev->mii.mdio_read = ch9200_mdio_read; + dev->mii.mdio_write = ch9200_mdio_write; + dev->mii.reg_num_mask = 0x1f; + + dev->mii.phy_id_mask = 0x1f; + + dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; + dev->rx_urb_size = 24 * 64 + 16; + mii_nway_restart(&dev->mii); + + data[0] = 0x01; + data[1] = 0x0F; + retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_THRESHOLD, data, + 0x02, CONTROL_TIMEOUT_MS); + + data[0] = 0xA0; + data[1] = 0x90; + retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_FIFO_DEPTH, data, + 0x02, CONTROL_TIMEOUT_MS); + + data[0] = 0x30; + data[1] = 0x00; + retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_PAUSE, data, + 0x02, CONTROL_TIMEOUT_MS); + + data[0] = 0x17; + data[1] = 0xD8; + retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_FLOW_CONTROL, + data, 0x02, CONTROL_TIMEOUT_MS); + + /* Undocumented register */ + data[0] = 0x01; + data[1] = 0x00; + retval = control_write(dev, REQUEST_WRITE, 0, 254, data, 0x02, + CONTROL_TIMEOUT_MS); + + data[0] = 0x5F; + data[1] = 0x0D; + retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_CTRL, data, 0x02, + CONTROL_TIMEOUT_MS); + + retval = get_mac_address(dev, dev->net->dev_addr); + + return retval; +} + +static const struct driver_info ch9200_info = { + .description = "CH9200 USB to Network Adaptor", + .flags = FLAG_ETHER, + .bind = ch9200_bind, + .rx_fixup = ch9200_rx_fixup, + .tx_fixup = ch9200_tx_fixup, + .status = ch9200_status, + .link_reset = ch9200_link_reset, + .reset = ch9200_link_reset, +}; + +static const struct usb_device_id ch9200_products[] = { + { + USB_DEVICE(0x1A86, 0xE092), + .driver_info = (unsigned long)&ch9200_info, + }, + {}, +}; + +MODULE_DEVICE_TABLE(usb, ch9200_products); + +static struct usb_driver ch9200_driver = { + .name = "ch9200", + .id_table = ch9200_products, + .probe = usbnet_probe, + .disconnect = usbnet_disconnect, + .suspend = usbnet_suspend, + .resume = usbnet_resume, +}; + +module_usb_driver(ch9200_driver); + +MODULE_DESCRIPTION("QinHeng CH9200 USB Network device"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index e7094fbd7568..488c6f50df73 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -193,7 +193,8 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, .flowi4_oif = vrf_dev->ifindex, .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_tos = RT_TOS(ip4h->tos), - .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC, + .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_VRFSRC | + FLOWI_FLAG_SKIP_NH_OIF, .daddr = ip4h->daddr, }; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index cf8b7f0473b3..bbac1d35ed4e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2392,10 +2392,6 @@ static void vxlan_setup(struct net_device *dev) eth_hw_addr_random(dev); ether_setup(dev); - if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6) - dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM; - else - dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM; dev->netdev_ops = &vxlan_netdev_ops; dev->destructor = free_netdev; @@ -2640,8 +2636,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, dst->remote_ip.sa.sa_family = AF_INET; if (dst->remote_ip.sa.sa_family == AF_INET6 || - vxlan->cfg.saddr.sa.sa_family == AF_INET6) + vxlan->cfg.saddr.sa.sa_family == AF_INET6) { + if (!IS_ENABLED(CONFIG_IPV6)) + return -EPFNOSUPPORT; use_ipv6 = true; + } if (conf->remote_ifindex) { struct net_device *lowerdev @@ -2670,8 +2669,12 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, dev->needed_headroom = lowerdev->hard_header_len + (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); - } else if (use_ipv6) + } else if (use_ipv6) { vxlan->flags |= VXLAN_F_IPV6; + dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM; + } else { + dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM; + } memcpy(&vxlan->cfg, conf, sizeof(*conf)); if (!vxlan->cfg.dst_port) diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 1350fa25cdb0..a87a868fed64 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -197,7 +197,8 @@ static int of_phy_match(struct device *dev, void *phy_np) * of_phy_find_device - Give a PHY node, find the phy_device * @phy_np: Pointer to the phy's device tree node * - * Returns a pointer to the phy_device. + * If successful, returns a pointer to the phy_device with the embedded + * struct device refcount incremented by one, or NULL on failure. */ struct phy_device *of_phy_find_device(struct device_node *phy_np) { @@ -217,7 +218,9 @@ EXPORT_SYMBOL(of_phy_find_device); * @hndlr: Link state callback for the network device * @iface: PHY data interface type * - * Returns a pointer to the phy_device if successful. NULL otherwise + * If successful, returns a pointer to the phy_device with the embedded + * struct device refcount incremented by one, or NULL on failure. The + * refcount must be dropped by calling phy_disconnect() or phy_detach(). */ struct phy_device *of_phy_connect(struct net_device *dev, struct device_node *phy_np, @@ -225,13 +228,19 @@ struct phy_device *of_phy_connect(struct net_device *dev, phy_interface_t iface) { struct phy_device *phy = of_phy_find_device(phy_np); + int ret; if (!phy) return NULL; phy->dev_flags = flags; - return phy_connect_direct(dev, phy, hndlr, iface) ? NULL : phy; + ret = phy_connect_direct(dev, phy, hndlr, iface); + + /* refcount is held by phy_connect_direct() on success */ + put_device(&phy->dev); + + return ret ? NULL : phy; } EXPORT_SYMBOL(of_phy_connect); @@ -241,17 +250,27 @@ EXPORT_SYMBOL(of_phy_connect); * @phy_np: Node pointer for the PHY * @flags: flags to pass to the PHY * @iface: PHY data interface type + * + * If successful, returns a pointer to the phy_device with the embedded + * struct device refcount incremented by one, or NULL on failure. The + * refcount must be dropped by calling phy_disconnect() or phy_detach(). */ struct phy_device *of_phy_attach(struct net_device *dev, struct device_node *phy_np, u32 flags, phy_interface_t iface) { struct phy_device *phy = of_phy_find_device(phy_np); + int ret; if (!phy) return NULL; - return phy_attach_direct(dev, phy, flags, iface) ? NULL : phy; + ret = phy_attach_direct(dev, phy, flags, iface); + + /* refcount is held by phy_attach_direct() on success */ + put_device(&phy->dev); + + return ret ? NULL : phy; } EXPORT_SYMBOL(of_phy_attach); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 88a00694eda5..2d15e3831440 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -507,6 +507,7 @@ static inline void napi_enable(struct napi_struct *n) BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); + clear_bit(NAPI_STATE_NPSVC, &n->state); } #ifdef CONFIG_SMP diff --git a/include/linux/phy.h b/include/linux/phy.h index 962387a192f1..4a4e3a092337 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -153,6 +154,7 @@ struct sk_buff; * PHYs should register using this structure */ struct mii_bus { + struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; @@ -198,7 +200,8 @@ static inline struct mii_bus *mdiobus_alloc(void) return mdiobus_alloc_size(0); } -int mdiobus_register(struct mii_bus *bus); +int __mdiobus_register(struct mii_bus *bus, struct module *owner); +#define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); @@ -742,6 +745,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, struct phy_c45_device_ids *c45_ids); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); +void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2738d355cdf9..2b0a30a6e31c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -179,6 +179,9 @@ struct nf_bridge_info { u8 bridged_dnat:1; __u16 frag_max_size; struct net_device *physindev; + + /* always valid & non-NULL from FORWARD on, for physdev match */ + struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; @@ -189,9 +192,6 @@ struct nf_bridge_info { * skb is out in neigh layer. */ char neigh_header[8]; - - /* always valid & non-NULL from FORWARD on, for physdev match */ - struct net_device *physoutdev; }; }; #endif @@ -2707,6 +2707,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) <= len) + skb->ip_summed = CHECKSUM_NONE; } unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); diff --git a/include/net/flow.h b/include/net/flow.h index acd6a096250e..9b85db85f13c 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -35,6 +35,7 @@ struct flowi_common { #define FLOWI_FLAG_ANYSRC 0x01 #define FLOWI_FLAG_KNOWN_NH 0x02 #define FLOWI_FLAG_VRFSRC 0x04 +#define FLOWI_FLAG_SKIP_NH_OIF 0x08 __u32 flowic_secid; struct flowi_tunnel flowic_tun_key; }; diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 879d6e5a973b..186f3a1e1b1f 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -110,7 +110,19 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, struct inet_hashinfo *hashinfo); -void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo); +void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, + bool rearm); + +static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) +{ + __inet_twsk_schedule(tw, timeo, false); +} + +static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo) +{ + __inet_twsk_schedule(tw, timeo, true); +} + void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); void inet_twsk_purge(struct inet_hashinfo *hashinfo, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 063d30474cf6..aaf9700fc9e5 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -275,7 +275,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info, struct mx6_config *mxc); int fib6_del(struct rt6_info *rt, struct nl_info *info); -void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info); +void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, + unsigned int flags); void fib6_run_gc(unsigned long expires, struct net *net, bool force); diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index b8529aa1dae7..fa915fa0f703 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -32,6 +32,12 @@ struct __ip6_tnl_parm { __be32 o_key; }; +struct ip6_tnl_dst { + seqlock_t lock; + struct dst_entry __rcu *dst; + u32 cookie; +}; + /* IPv6 tunnel */ struct ip6_tnl { struct ip6_tnl __rcu *next; /* next tunnel in list */ @@ -39,8 +45,7 @@ struct ip6_tnl { struct net *net; /* netns for packet i/o */ struct __ip6_tnl_parm parms; /* tunnel configuration parameters */ struct flowi fl; /* flowi template for xmit */ - struct dst_entry *dst_cache; /* cached dst */ - u32 dst_cookie; + struct ip6_tnl_dst __percpu *dst_cache; /* cached dst */ int err_count; unsigned long err_time; @@ -60,9 +65,11 @@ struct ipv6_tlv_tnl_enc_lim { __u8 encap_limit; /* tunnel encapsulation limit */ } __packed; -struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t); +struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t); +int ip6_tnl_dst_init(struct ip6_tnl *t); +void ip6_tnl_dst_destroy(struct ip6_tnl *t); void ip6_tnl_dst_reset(struct ip6_tnl *t); -void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst); +void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst); int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, @@ -79,7 +86,7 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, struct net_device_stats *stats = &dev->stats; int pkt_len, err; - pkt_len = skb->len; + pkt_len = skb->len - skb_inner_network_offset(skb); err = ip6_local_out_sk(sk, skb); if (net_xmit_eval(err) == 0) { diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index a37d0432bebd..727d6e9a9685 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -236,8 +236,11 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp, rcu_read_lock(); tb = fib_get_table(net, RT_TABLE_MAIN); - if (tb && !fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF)) - err = 0; + if (tb) + err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF); + + if (err == -EAGAIN) + err = -ENETUNREACH; rcu_read_unlock(); @@ -258,7 +261,7 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; - int err; + int err = -ENETUNREACH; flags |= FIB_LOOKUP_NOREF; if (net->ipv4.fib_has_custom_rules) @@ -268,15 +271,20 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp, res->tclassid = 0; - for (err = 0; !err; err = -ENETUNREACH) { - tb = rcu_dereference_rtnl(net->ipv4.fib_main); - if (tb && !fib_table_lookup(tb, flp, res, flags)) - break; + tb = rcu_dereference_rtnl(net->ipv4.fib_main); + if (tb) + err = fib_table_lookup(tb, flp, res, flags); - tb = rcu_dereference_rtnl(net->ipv4.fib_default); - if (tb && !fib_table_lookup(tb, flp, res, flags)) - break; - } + if (!err) + goto out; + + tb = rcu_dereference_rtnl(net->ipv4.fib_default); + if (tb) + err = fib_table_lookup(tb, flp, res, flags); + +out: + if (err == -EAGAIN) + err = -ENETUNREACH; rcu_read_unlock(); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 9a6a3ba888e8..f6dafec9102c 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -276,6 +276,8 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto); int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, u8 proto, u8 tos, u8 ttl, __be16 df, bool xnet); +struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, + gfp_t flags); struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum, int gso_type_mask); diff --git a/include/net/route.h b/include/net/route.h index cc61cb95f059..f46af256880c 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -255,7 +255,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 flow_flags |= FLOWI_FLAG_ANYSRC; if (netif_index_is_vrf(sock_net(sk), oif)) - flow_flags |= FLOWI_FLAG_VRFSRC; + flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF; flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, protocol, flow_flags, dst, src, dport, sport); diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index 34141a5dfe74..f8b01887a495 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -21,8 +21,6 @@ enum lwtunnel_ip_t { LWTUNNEL_IP_SRC, LWTUNNEL_IP_TTL, LWTUNNEL_IP_TOS, - LWTUNNEL_IP_SPORT, - LWTUNNEL_IP_DPORT, LWTUNNEL_IP_FLAGS, __LWTUNNEL_IP_MAX, }; @@ -36,8 +34,6 @@ enum lwtunnel_ip6_t { LWTUNNEL_IP6_SRC, LWTUNNEL_IP6_HOPLIMIT, LWTUNNEL_IP6_TC, - LWTUNNEL_IP6_SPORT, - LWTUNNEL_IP6_DPORT, LWTUNNEL_IP6_FLAGS, __LWTUNNEL_IP6_MAX, }; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index cc0c69710dcf..a54ff8949f91 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -187,10 +187,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash) head = rht_dereference_bucket(new_tbl->buckets[new_hash], new_tbl, new_hash); - if (rht_is_a_nulls(head)) - INIT_RHT_NULLS_HEAD(entry->next, ht, new_hash); - else - RCU_INIT_POINTER(entry->next, head); + RCU_INIT_POINTER(entry->next, head); rcu_assign_pointer(new_tbl->buckets[new_hash], entry); spin_unlock(new_bucket_lock); diff --git a/net/atm/clip.c b/net/atm/clip.c index 17e55dfecbe2..e07f551a863c 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -317,6 +317,9 @@ static int clip_constructor(struct neighbour *neigh) static int clip_encap(struct atm_vcc *vcc, int mode) { + if (!CLIP_VCC(vcc)) + return -EBADFD; + CLIP_VCC(vcc)->encap = mode; return 0; } diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index ad82324f710f..0510a577a7b5 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2311,12 +2311,6 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) if (!conn) return 1; - chan = conn->smp; - if (!chan) { - BT_ERR("SMP security requested but not available"); - return 1; - } - if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED)) return 1; @@ -2330,6 +2324,12 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) if (smp_ltk_encrypt(conn, hcon->pending_sec_level)) return 0; + chan = conn->smp; + if (!chan) { + BT_ERR("SMP security requested but not available"); + return 1; + } + l2cap_chan_lock(chan); /* If SMP is already in progress ignore this request */ diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 66efdc21f548..480b3de1a0e3 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1006,7 +1006,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); - len = sizeof(*ih); + len = skb_transport_offset(skb) + sizeof(*ih); for (i = 0; i < num; i++) { len += sizeof(*grec); @@ -1067,7 +1067,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, icmp6h = icmp6_hdr(skb); num = ntohs(icmp6h->icmp6_dataun.un_data16[1]); - len = sizeof(*icmp6h); + len = skb_transport_offset(skb) + sizeof(*icmp6h); for (i = 0; i < num; i++) { __be16 *nsrcs, _nsrcs; diff --git a/net/core/dev.c b/net/core/dev.c index 877c84834d81..6bb6470f5b7b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4713,6 +4713,8 @@ void napi_disable(struct napi_struct *n) while (test_and_set_bit(NAPI_STATE_SCHED, &n->state)) msleep(1); + while (test_and_set_bit(NAPI_STATE_NPSVC, &n->state)) + msleep(1); hrtimer_cancel(&n->timer); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index bf77e3639ce0..365de66436ac 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -631,15 +631,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, { int idx = 0; struct fib_rule *rule; + int err = 0; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; - if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWRULE, - NLM_F_MULTI, ops) < 0) + err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWRULE, + NLM_F_MULTI, ops); + if (err) break; skip: idx++; @@ -648,7 +650,7 @@ skip: cb->args[1] = idx; rules_ops_put(ops); - return skb->len; + return err; } static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) @@ -664,7 +666,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) if (ops == NULL) return -EAFNOSUPPORT; - return dump_rules(skb, cb, ops); + dump_rules(skb, cb, ops); + + return skb->len; } rcu_read_lock(); diff --git a/net/core/filter.c b/net/core/filter.c index 13079f03902e..05a04ea87172 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -478,9 +478,9 @@ do_pass: bpf_src = BPF_X; } else { insn->dst_reg = BPF_REG_A; - insn->src_reg = BPF_REG_X; insn->imm = fp->k; bpf_src = BPF_SRC(fp->code); + insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0; } /* Common case where 'jump_false' is next insn. */ diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index b279077c3089..805a95a48107 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1481,6 +1481,15 @@ static int of_dev_node_match(struct device *dev, const void *data) return ret == 0 ? dev->of_node == data : ret; } +/* + * of_find_net_device_by_node - lookup the net device for the device node + * @np: OF device node + * + * Looks up the net_device structure corresponding with the device node. + * If successful, returns a pointer to the net_device with the embedded + * struct device refcount incremented by one, or NULL on failure. The + * refcount must be dropped when done with the net_device. + */ struct net_device *of_find_net_device_by_node(struct device_node *np) { struct device *dev; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 6aa3db8dfc3b..8bdada242a7d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -142,7 +142,7 @@ static void queue_process(struct work_struct *work) */ static int poll_one_napi(struct napi_struct *napi, int budget) { - int work; + int work = 0; /* net_rx_action's ->poll() invocations and our's are * synchronized by this test which is only made while @@ -151,7 +151,12 @@ static int poll_one_napi(struct napi_struct *napi, int budget) if (!test_bit(NAPI_STATE_SCHED, &napi->state)) return budget; - set_bit(NAPI_STATE_NPSVC, &napi->state); + /* If we set this bit but see that it has already been set, + * that indicates that napi has been disabled and we need + * to abort this operation + */ + if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) + goto out; work = napi->poll(napi, budget); WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll); @@ -159,6 +164,7 @@ static int poll_one_napi(struct napi_struct *napi, int budget) clear_bit(NAPI_STATE_NPSVC, &napi->state); +out: return budget - work; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a466821d1441..0ec48403ed68 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3047,6 +3047,7 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) u32 portid = NETLINK_CB(cb->skb).portid; u32 seq = cb->nlh->nlmsg_seq; u32 filter_mask = 0; + int err; if (nlmsg_len(cb->nlh) > sizeof(struct ifinfomsg)) { struct nlattr *extfilt; @@ -3067,20 +3068,25 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *br_dev = netdev_master_upper_dev_get(dev); if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { - if (idx >= cb->args[0] && - br_dev->netdev_ops->ndo_bridge_getlink( - skb, portid, seq, dev, filter_mask, - NLM_F_MULTI) < 0) - break; + if (idx >= cb->args[0]) { + err = br_dev->netdev_ops->ndo_bridge_getlink( + skb, portid, seq, dev, + filter_mask, NLM_F_MULTI); + if (err < 0 && err != -EOPNOTSUPP) + break; + } idx++; } if (ops->ndo_bridge_getlink) { - if (idx >= cb->args[0] && - ops->ndo_bridge_getlink(skb, portid, seq, dev, - filter_mask, - NLM_F_MULTI) < 0) - break; + if (idx >= cb->args[0]) { + err = ops->ndo_bridge_getlink(skb, portid, + seq, dev, + filter_mask, + NLM_F_MULTI); + if (err < 0 && err != -EOPNOTSUPP) + break; + } idx++; } } diff --git a/net/core/sock.c b/net/core/sock.c index ca2984afe16e..3307c02244d3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2740,10 +2740,8 @@ static void req_prot_cleanup(struct request_sock_ops *rsk_prot) return; kfree(rsk_prot->slab_name); rsk_prot->slab_name = NULL; - if (rsk_prot->slab) { - kmem_cache_destroy(rsk_prot->slab); - rsk_prot->slab = NULL; - } + kmem_cache_destroy(rsk_prot->slab); + rsk_prot->slab = NULL; } static int req_prot_init(const struct proto *prot) @@ -2828,10 +2826,8 @@ void proto_unregister(struct proto *prot) list_del(&prot->node); mutex_unlock(&proto_list_mutex); - if (prot->slab != NULL) { - kmem_cache_destroy(prot->slab); - prot->slab = NULL; - } + kmem_cache_destroy(prot->slab); + prot->slab = NULL; req_prot_cleanup(prot->rsk_prot); diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index bd9e718c2a20..3de0d0362d7f 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -398,12 +398,8 @@ out_err: void dccp_ackvec_exit(void) { - if (dccp_ackvec_slab != NULL) { - kmem_cache_destroy(dccp_ackvec_slab); - dccp_ackvec_slab = NULL; - } - if (dccp_ackvec_record_slab != NULL) { - kmem_cache_destroy(dccp_ackvec_record_slab); - dccp_ackvec_record_slab = NULL; - } + kmem_cache_destroy(dccp_ackvec_slab); + dccp_ackvec_slab = NULL; + kmem_cache_destroy(dccp_ackvec_record_slab); + dccp_ackvec_record_slab = NULL; } diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 83498975165f..90f77d08cc37 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -95,8 +95,7 @@ static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_f static void ccid_kmem_cache_destroy(struct kmem_cache *slab) { - if (slab != NULL) - kmem_cache_destroy(slab); + kmem_cache_destroy(slab); } static int __init ccid_activate(struct ccid_operations *ccid_ops) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 30addee2dd03..838f524cf11a 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -48,8 +48,6 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) tw->tw_ipv6only = sk->sk_ipv6only; } #endif - /* Linkage updates. */ - __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) @@ -60,6 +58,8 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) timeo = DCCP_TIMEWAIT_LEN; inet_twsk_schedule(tw, timeo); + /* Linkage updates. */ + __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); inet_twsk_put(tw); } else { /* Sorry, if we're out of memory, just CLOSE this diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 76e3800765f8..c59fa5d9c22c 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -634,6 +634,10 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd) port_index++; } kfree(pd->chip[i].rtable); + + /* Drop our reference to the MDIO bus device */ + if (pd->chip[i].host_dev) + put_device(pd->chip[i].host_dev); } kfree(pd->chip); } @@ -661,16 +665,22 @@ static int dsa_of_probe(struct device *dev) return -EPROBE_DEFER; ethernet = of_parse_phandle(np, "dsa,ethernet", 0); - if (!ethernet) - return -EINVAL; + if (!ethernet) { + ret = -EINVAL; + goto out_put_mdio; + } ethernet_dev = of_find_net_device_by_node(ethernet); - if (!ethernet_dev) - return -EPROBE_DEFER; + if (!ethernet_dev) { + ret = -EPROBE_DEFER; + goto out_put_mdio; + } pd = kzalloc(sizeof(*pd), GFP_KERNEL); - if (!pd) - return -ENOMEM; + if (!pd) { + ret = -ENOMEM; + goto out_put_ethernet; + } dev->platform_data = pd; pd->of_netdev = ethernet_dev; @@ -691,7 +701,9 @@ static int dsa_of_probe(struct device *dev) cd = &pd->chip[chip_index]; cd->of_node = child; - cd->host_dev = &mdio_bus->dev; + + /* When assigning the host device, increment its refcount */ + cd->host_dev = get_device(&mdio_bus->dev); sw_addr = of_get_property(child, "reg", NULL); if (!sw_addr) @@ -711,6 +723,12 @@ static int dsa_of_probe(struct device *dev) ret = -EPROBE_DEFER; goto out_free_chip; } + + /* Drop the mdio_bus device ref, replacing the host + * device with the mdio_bus_switch device, keeping + * the refcount from of_mdio_find_bus() above. + */ + put_device(cd->host_dev); cd->host_dev = &mdio_bus_switch->dev; } @@ -744,6 +762,10 @@ static int dsa_of_probe(struct device *dev) } } + /* The individual chips hold their own refcount on the mdio bus, + * so drop ours */ + put_device(&mdio_bus->dev); + return 0; out_free_chip: @@ -751,6 +773,10 @@ out_free_chip: out_free: kfree(pd); dev->platform_data = NULL; +out_put_ethernet: + put_device(ðernet_dev->dev); +out_put_mdio: + put_device(&mdio_bus->dev); return ret; } @@ -762,6 +788,7 @@ static void dsa_of_remove(struct device *dev) return; dsa_of_free_platform_data(pd); + put_device(&pd->of_netdev->dev); kfree(pd); } #else diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index d25efc93d8f1..b6ca0890d018 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -78,7 +78,7 @@ static int trailer_rcv(struct sk_buff *skb, struct net_device *dev, trailer = skb_tail_pointer(skb) - 4; if (trailer[0] != 0x80 || (trailer[1] & 0xf8) != 0x00 || - (trailer[3] & 0xef) != 0x00 || trailer[3] != 0x00) + (trailer[2] & 0xef) != 0x00 || trailer[3] != 0x00) goto out_drop; source_port = trailer[1] & 7; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 30409b75e925..f03db8b7abee 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -113,6 +113,8 @@ #include #include #include +#include +#include #include @@ -296,7 +298,8 @@ 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) + const unsigned char *target_hw, + struct dst_entry *dst) { struct sk_buff *skb; @@ -309,9 +312,7 @@ static void arp_send_dst(int type, int ptype, __be32 dest_ip, if (!skb) return; - if (oskb) - skb_dst_copy(skb, oskb); - + skb_dst_set(skb, dst); arp_xmit(skb); } @@ -333,6 +334,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) __be32 target = *(__be32 *)neigh->primary_key; int probes = atomic_read(&neigh->probes); struct in_device *in_dev; + struct dst_entry *dst = NULL; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); @@ -381,9 +383,10 @@ 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)); 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); + dst_hw, dev->dev_addr, NULL, dst); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) @@ -649,6 +652,7 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) int addr_type; struct neighbour *n; struct net *net = dev_net(dev); + struct dst_entry *reply_dst = NULL; bool is_garp = false; /* arp_rcv below verifies the ARP header and verifies the device @@ -749,13 +753,18 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) * cache. */ + if (arp->ar_op == htons(ARPOP_REQUEST) && skb_metadata_dst(skb)) + reply_dst = (struct dst_entry *) + iptunnel_metadata_reply(skb_metadata_dst(skb), + GFP_ATOMIC); + /* Special case: IPv4 duplicate address detection packet (RFC2131) */ if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, - dev->dev_addr, sha); + arp_send_dst(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, + sha, dev->dev_addr, sha, reply_dst); goto out; } @@ -774,9 +783,10 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) if (!dont_send) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) { - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, - dev, tip, sha, dev->dev_addr, - sha); + arp_send_dst(ARPOP_REPLY, ETH_P_ARP, + sip, dev, tip, sha, + dev->dev_addr, sha, + reply_dst); neigh_release(n); } } @@ -794,9 +804,10 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED || skb->pkt_type == PACKET_HOST || NEIGH_VAR(in_dev->arp_parms, PROXY_DELAY) == 0) { - arp_send(ARPOP_REPLY, ETH_P_ARP, sip, - dev, tip, sha, dev->dev_addr, - sha); + arp_send_dst(ARPOP_REPLY, ETH_P_ARP, + sip, dev, tip, sha, + dev->dev_addr, sha, + reply_dst); } else { pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 26d6ffb6d23c..6c2af797f2f9 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1426,7 +1426,7 @@ found: nh->nh_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) continue; - if (!(flp->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + if (!(flp->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) { if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif) continue; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 79fe05befcae..e5eb8ac4089d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) fl4.flowi4_mark = mark; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_proto = IPPROTO_ICMP; - fl4.flowi4_oif = vrf_master_ifindex(skb->dev) ? : skb->dev->ifindex; + fl4.flowi4_oif = vrf_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) @@ -461,7 +461,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; - fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev) ? : skb_in->dev->ifindex; + fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key(net, fl4); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 134957159c27..7bb9c39e0a4d 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -685,20 +685,20 @@ void reqsk_queue_hash_req(struct request_sock_queue *queue, req->num_timeout = 0; req->sk = NULL; + setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req); + mod_timer_pinned(&req->rsk_timer, jiffies + timeout); + req->rsk_hash = hash; + /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ smp_wmb(); atomic_set(&req->rsk_refcnt, 2); - setup_timer(&req->rsk_timer, reqsk_timer_handler, (unsigned long)req); - req->rsk_hash = hash; spin_lock(&queue->syn_wait_lock); req->dl_next = lopt->syn_table[hash]; lopt->syn_table[hash] = req; spin_unlock(&queue->syn_wait_lock); - - mod_timer_pinned(&req->rsk_timer, jiffies + timeout); } EXPORT_SYMBOL(reqsk_queue_hash_req); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index ae22cc24fbe8..c67f9bd7699c 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -123,13 +123,15 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, /* * Step 2: Hash TW into tcp ehash chain. * Notes : - * - tw_refcnt is set to 3 because : + * - tw_refcnt is set to 4 because : * - We have one reference from bhash chain. * - We have one reference from ehash chain. + * - We have one reference from timer. + * - One reference for ourself (our caller will release it). * We can use atomic_set() because prior spin_lock()/spin_unlock() * committed into memory all tw fields. */ - atomic_set(&tw->tw_refcnt, 1 + 1 + 1); + atomic_set(&tw->tw_refcnt, 4); inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ @@ -217,7 +219,7 @@ void inet_twsk_deschedule_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL(inet_twsk_deschedule_put); -void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) +void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) { /* timeout := RTO * 3.5 * @@ -245,12 +247,14 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) */ tw->tw_kill = timeo <= 4*HZ; - if (!mod_timer_pinned(&tw->tw_timer, jiffies + timeo)) { - atomic_inc(&tw->tw_refcnt); + if (!rearm) { + BUG_ON(mod_timer_pinned(&tw->tw_timer, jiffies + timeo)); atomic_inc(&tw->tw_dr->tw_count); + } else { + mod_timer_pending(&tw->tw_timer, jiffies + timeo); } } -EXPORT_SYMBOL_GPL(inet_twsk_schedule); +EXPORT_SYMBOL_GPL(__inet_twsk_schedule); void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 29ed6c5a5185..84dce6a92f93 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -46,12 +46,13 @@ #include #include #include +#include int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, __u8 proto, __u8 tos, __u8 ttl, __be16 df, bool xnet) { - int pkt_len = skb->len; + int pkt_len = skb->len - skb_inner_network_offset(skb); struct iphdr *iph; int err; @@ -119,6 +120,33 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) } EXPORT_SYMBOL_GPL(iptunnel_pull_header); +struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, + gfp_t flags) +{ + struct metadata_dst *res; + struct ip_tunnel_info *dst, *src; + + if (!md || md->u.tun_info.mode & IP_TUNNEL_INFO_TX) + return NULL; + + res = metadata_dst_alloc(0, flags); + if (!res) + return NULL; + + dst = &res->u.tun_info; + src = &md->u.tun_info; + dst->key.tun_id = src->key.tun_id; + if (src->mode & IP_TUNNEL_INFO_IPV6) + memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src, + sizeof(struct in6_addr)); + else + dst->key.u.ipv4.dst = src->key.u.ipv4.src; + dst->mode = src->mode | IP_TUNNEL_INFO_TX; + + return res; +} +EXPORT_SYMBOL_GPL(iptunnel_metadata_reply); + struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool csum_help, int gso_type_mask) @@ -198,8 +226,6 @@ static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { [LWTUNNEL_IP_SRC] = { .type = NLA_U32 }, [LWTUNNEL_IP_TTL] = { .type = NLA_U8 }, [LWTUNNEL_IP_TOS] = { .type = NLA_U8 }, - [LWTUNNEL_IP_SPORT] = { .type = NLA_U16 }, - [LWTUNNEL_IP_DPORT] = { .type = NLA_U16 }, [LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 }, }; @@ -239,12 +265,6 @@ static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr, if (tb[LWTUNNEL_IP_TOS]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); - if (tb[LWTUNNEL_IP_SPORT]) - tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP_SPORT]); - - if (tb[LWTUNNEL_IP_DPORT]) - tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP_DPORT]); - if (tb[LWTUNNEL_IP_FLAGS]) tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP_FLAGS]); @@ -266,8 +286,6 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb, nla_put_be32(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || - nla_put_u16(skb, LWTUNNEL_IP_SPORT, tun_info->key.tp_src) || - nla_put_u16(skb, LWTUNNEL_IP_DPORT, tun_info->key.tp_dst) || nla_put_u16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags)) return -ENOMEM; @@ -281,8 +299,6 @@ static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate) + nla_total_size(4) /* LWTUNNEL_IP_SRC */ + nla_total_size(1) /* LWTUNNEL_IP_TOS */ + nla_total_size(1) /* LWTUNNEL_IP_TTL */ - + nla_total_size(2) /* LWTUNNEL_IP_SPORT */ - + nla_total_size(2) /* LWTUNNEL_IP_DPORT */ + nla_total_size(2); /* LWTUNNEL_IP_FLAGS */ } @@ -305,8 +321,6 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { [LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) }, [LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 }, [LWTUNNEL_IP6_TC] = { .type = NLA_U8 }, - [LWTUNNEL_IP6_SPORT] = { .type = NLA_U16 }, - [LWTUNNEL_IP6_DPORT] = { .type = NLA_U16 }, [LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 }, }; @@ -346,12 +360,6 @@ static int ip6_tun_build_state(struct net_device *dev, struct nlattr *attr, if (tb[LWTUNNEL_IP6_TC]) tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); - if (tb[LWTUNNEL_IP6_SPORT]) - tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP6_SPORT]); - - if (tb[LWTUNNEL_IP6_DPORT]) - tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP6_DPORT]); - if (tb[LWTUNNEL_IP6_FLAGS]) tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP6_FLAGS]); @@ -373,8 +381,6 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.ttl) || - nla_put_u16(skb, LWTUNNEL_IP6_SPORT, tun_info->key.tp_src) || - nla_put_u16(skb, LWTUNNEL_IP6_DPORT, tun_info->key.tp_dst) || nla_put_u16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags)) return -ENOMEM; @@ -388,8 +394,6 @@ static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate) + nla_total_size(16) /* LWTUNNEL_IP6_SRC */ + nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */ + nla_total_size(1) /* LWTUNNEL_IP6_TC */ - + nla_total_size(2) /* LWTUNNEL_IP6_SPORT */ - + nla_total_size(2) /* LWTUNNEL_IP6_DPORT */ + nla_total_size(2); /* LWTUNNEL_IP6_FLAGS */ } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5f4a5565ad8b..c6ad99ad0ffb 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2045,6 +2045,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) struct fib_result res; struct rtable *rth; int orig_oif; + int err = -ENETUNREACH; res.tclassid = 0; res.fi = NULL; @@ -2153,7 +2154,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) goto make_route; } - if (fib_lookup(net, fl4, &res, 0)) { + err = fib_lookup(net, fl4, &res, 0); + if (err) { res.fi = NULL; res.table = NULL; if (fl4->flowi4_oif) { @@ -2181,7 +2183,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) res.type = RTN_UNICAST; goto make_route; } - rth = ERR_PTR(-ENETUNREACH); + rth = ERR_PTR(err); goto out; } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index c6ded6b2a79f..448c2615fece 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -154,14 +154,20 @@ static void bictcp_init(struct sock *sk) static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { - s32 delta = tcp_time_stamp - tcp_sk(sk)->lsndtime; struct bictcp *ca = inet_csk_ca(sk); + u32 now = tcp_time_stamp; + s32 delta; + + delta = now - tcp_sk(sk)->lsndtime; /* We were application limited (idle) for a while. * Shift epoch_start to keep cwnd growth to cubic curve. */ - if (ca->epoch_start && delta > 0) + if (ca->epoch_start && delta > 0) { ca->epoch_start += delta; + if (after(ca->epoch_start, now)) + ca->epoch_start = now; + } return; } } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6d8795b066ac..def765911ff8 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -162,9 +162,9 @@ kill_with_rst: if (tcp_death_row.sysctl_tw_recycle && tcptw->tw_ts_recent_stamp && tcp_tw_remember_stamp(tw)) - inet_twsk_schedule(tw, tw->tw_timeout); + inet_twsk_reschedule(tw, tw->tw_timeout); else - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return TCP_TW_ACK; } @@ -201,7 +201,7 @@ kill: return TCP_TW_SUCCESS; } } - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent = tmp_opt.rcv_tsval; @@ -251,7 +251,7 @@ kill: * Do not reschedule in the last case. */ if (paws_reject || th->ack) - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return tcp_timewait_check_oow_rate_limit( tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT); @@ -322,9 +322,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } while (0); #endif - /* Linkage updates. */ - __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); - /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) timeo = rto; @@ -338,6 +335,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } inet_twsk_schedule(tw, timeo); + /* Linkage updates. */ + __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); inet_twsk_put(tw); } else { /* Sorry, if we're out of memory, just CLOSE this diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f9a8a12b62ee..1100ffe4a722 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2897,6 +2897,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); + skb_mstamp_get(&skb->skb_mstamp); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c0a15e7f359f..f7d1d5e19e95 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1024,7 +1024,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (netif_index_is_vrf(net, ipc.oif)) { flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, - (flow_flags | FLOWI_FLAG_VRFSRC), + (flow_flags | FLOWI_FLAG_VRFSRC | + FLOWI_FLAG_SKIP_NH_OIF), faddr, saddr, dport, inet->inet_sport); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index bb919b28619f..c10a9ee68433 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -33,6 +33,8 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, if (saddr) fl4->saddr = saddr->a4; + fl4->flowi4_flags = FLOWI_FLAG_SKIP_NH_OIF; + rt = __ip_route_output_key(net, fl4); if (!IS_ERR(rt)) return &rt->dst; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 030fefdc9aed..900113376d4e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5127,13 +5127,12 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) rt = addrconf_get_prefix_route(&ifp->peer_addr, 128, ifp->idev->dev, 0, 0); - if (rt && ip6_del_rt(rt)) - dst_free(&rt->dst); + if (rt) + ip6_del_rt(rt); } dst_hold(&ifp->rt->dst); - if (ip6_del_rt(ifp->rt)) - dst_free(&ifp->rt->dst); + ip6_del_rt(ifp->rt); rt_genid_bump_ipv6(net); break; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 418d9823692b..7d2e0023c72d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -155,6 +155,11 @@ static void node_free(struct fib6_node *fn) kmem_cache_free(fib6_node_kmem, fn); } +static void rt6_rcu_free(struct rt6_info *rt) +{ + call_rcu(&rt->dst.rcu_head, dst_rcu_free); +} + static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) { int cpu; @@ -169,7 +174,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu); pcpu_rt = *ppcpu_rt; if (pcpu_rt) { - dst_free(&pcpu_rt->dst); + rt6_rcu_free(pcpu_rt); *ppcpu_rt = NULL; } } @@ -181,7 +186,7 @@ static void rt6_release(struct rt6_info *rt) { if (atomic_dec_and_test(&rt->rt6i_ref)) { rt6_free_pcpu(rt); - dst_free(&rt->dst); + rt6_rcu_free(rt); } } @@ -846,7 +851,7 @@ add: *ins = rt; rt->rt6i_node = fn; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info); + inet6_rt_notify(RTM_NEWROUTE, rt, info, 0); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; if (!(fn->fn_flags & RTN_RTINFO)) { @@ -872,7 +877,7 @@ add: rt->rt6i_node = fn; rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info); + inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; @@ -933,6 +938,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, int replace_required = 0; int sernum = fib6_new_sernum(info->nl_net); + if (WARN_ON_ONCE((rt->dst.flags & DST_NOCACHE) && + !atomic_read(&rt->dst.__refcnt))) + return -EINVAL; + if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) allow_create = 0; @@ -1025,6 +1034,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, fib6_start_gc(info->nl_net, rt); if (!(rt->rt6i_flags & RTF_CACHE)) fib6_prune_clones(info->nl_net, pn); + rt->dst.flags &= ~DST_NOCACHE; } out: @@ -1049,7 +1059,8 @@ out: atomic_inc(&pn->leaf->rt6i_ref); } #endif - dst_free(&rt->dst); + if (!(rt->dst.flags & DST_NOCACHE)) + dst_free(&rt->dst); } return err; @@ -1060,7 +1071,8 @@ out: st_failure: if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) fib6_repair_tree(info->nl_net, fn); - dst_free(&rt->dst); + if (!(rt->dst.flags & DST_NOCACHE)) + dst_free(&rt->dst); return err; #endif } @@ -1410,7 +1422,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, fib6_purge_rt(rt, fn, net); - inet6_rt_notify(RTM_DELROUTE, rt, info); + inet6_rt_notify(RTM_DELROUTE, rt, info, 0); rt6_release(rt); } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 4038c694ec03..3c7b9310b33f 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -404,13 +404,13 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct ipv6_tlv_tnl_enc_lim *tel; __u32 mtu; case ICMPV6_DEST_UNREACH: - net_warn_ratelimited("%s: Path to destination invalid or inactive!\n", - t->parms.name); + net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", + t->parms.name); break; case ICMPV6_TIME_EXCEED: if (code == ICMPV6_EXC_HOPLIMIT) { - net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", - t->parms.name); + net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", + t->parms.name); } break; case ICMPV6_PARAMPROB: @@ -421,12 +421,12 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (teli && teli == be32_to_cpu(info) - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { - net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", - t->parms.name); + net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", + t->parms.name); } } else { - net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n", - t->parms.name); + net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n", + t->parms.name); } break; case ICMPV6_PKT_TOOBIG: @@ -634,20 +634,20 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, } if (!fl6->flowi6_mark) - dst = ip6_tnl_dst_check(tunnel); + dst = ip6_tnl_dst_get(tunnel); if (!dst) { - ndst = ip6_route_output(net, NULL, fl6); + dst = ip6_route_output(net, NULL, fl6); - if (ndst->error) + if (dst->error) goto tx_err_link_failure; - ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0); - if (IS_ERR(ndst)) { - err = PTR_ERR(ndst); - ndst = NULL; + dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; goto tx_err_link_failure; } - dst = ndst; + ndst = dst; } tdev = dst->dev; @@ -702,12 +702,9 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb = new_skb; } - if (fl6->flowi6_mark) { - skb_dst_set(skb, dst); - ndst = NULL; - } else { - skb_dst_set_noref(skb, dst); - } + if (!fl6->flowi6_mark && ndst) + ip6_tnl_dst_set(tunnel, ndst); + skb_dst_set(skb, dst); proto = NEXTHDR_GRE; if (encap_limit >= 0) { @@ -762,14 +759,12 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_set_inner_protocol(skb, protocol); ip6tunnel_xmit(NULL, skb, dev); - if (ndst) - ip6_tnl_dst_store(tunnel, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(ndst); + dst_release(dst); return err; } @@ -1223,6 +1218,9 @@ static const struct net_device_ops ip6gre_netdev_ops = { static void ip6gre_dev_free(struct net_device *dev) { + struct ip6_tnl *t = netdev_priv(dev); + + ip6_tnl_dst_destroy(t); free_percpu(dev->tstats); free_netdev(dev); } @@ -1245,9 +1243,10 @@ static void ip6gre_tunnel_setup(struct net_device *dev) netif_keep_dst(dev); } -static int ip6gre_tunnel_init(struct net_device *dev) +static int ip6gre_tunnel_init_common(struct net_device *dev) { struct ip6_tnl *tunnel; + int ret; tunnel = netdev_priv(dev); @@ -1255,16 +1254,37 @@ static int ip6gre_tunnel_init(struct net_device *dev) tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + ret = ip6_tnl_dst_init(tunnel); + if (ret) { + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; + } + + return 0; +} + +static int ip6gre_tunnel_init(struct net_device *dev) +{ + struct ip6_tnl *tunnel; + int ret; + + ret = ip6gre_tunnel_init_common(dev); + if (ret) + return ret; + + tunnel = netdev_priv(dev); + memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &tunnel->parms.raddr, sizeof(struct in6_addr)); if (ipv6_addr_any(&tunnel->parms.raddr)) dev->header_ops = &ip6gre_header_ops; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - return 0; } @@ -1460,19 +1480,16 @@ static void ip6gre_netlink_parms(struct nlattr *data[], static int ip6gre_tap_init(struct net_device *dev) { struct ip6_tnl *tunnel; + int ret; + + ret = ip6gre_tunnel_init_common(dev); + if (ret) + return ret; tunnel = netdev_priv(dev); - tunnel->dev = dev; - tunnel->net = dev_net(dev); - strcpy(tunnel->parms.name, dev->name); - ip6gre_tnl_link_config(tunnel, 1); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 26ea47930740..92b1aa38f121 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -586,20 +586,22 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr); + hroom = LL_RESERVED_SPACE(rt->dst.dev); if (skb_has_frag_list(skb)) { int first_len = skb_pagelen(skb); struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || - skb_cloned(skb)) + skb_cloned(skb) || + skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || - skb_headroom(frag) < hlen) + skb_headroom(frag) < (hlen + hroom + sizeof(struct frag_hdr))) goto slow_path_clean; /* Partially cloned skb? */ @@ -616,8 +618,6 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, err = 0; offset = 0; - frag = skb_shinfo(skb)->frag_list; - skb_frag_list_init(skb); /* BUILD HEADER */ *prevhdr = NEXTHDR_FRAGMENT; @@ -625,8 +625,11 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, if (!tmp_hdr) { IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); - return -ENOMEM; + err = -ENOMEM; + goto fail; } + frag = skb_shinfo(skb)->frag_list; + skb_frag_list_init(skb); __skb_pull(skb, hlen); fh = (struct frag_hdr *)__skb_push(skb, sizeof(struct frag_hdr)); @@ -723,7 +726,6 @@ slow_path: */ *prevhdr = NEXTHDR_FRAGMENT; - hroom = LL_RESERVED_SPACE(rt->dst.dev); troom = rt->dst.dev->needed_tailroom; /* diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b0ab420612bc..eabffbb89795 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -126,36 +126,92 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev) * Locking : hash tables are protected by RCU and RTNL */ -struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) +static void ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst, + struct dst_entry *dst) { - struct dst_entry *dst = t->dst_cache; - - if (dst && dst->obsolete && - !dst->ops->check(dst, t->dst_cookie)) { - t->dst_cache = NULL; - dst_release(dst); - return NULL; + write_seqlock_bh(&idst->lock); + dst_release(rcu_dereference_protected( + idst->dst, + lockdep_is_held(&idst->lock.lock))); + if (dst) { + dst_hold(dst); + idst->cookie = rt6_get_cookie((struct rt6_info *)dst); + } else { + idst->cookie = 0; } + rcu_assign_pointer(idst->dst, dst); + write_sequnlock_bh(&idst->lock); +} +struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t) +{ + struct ip6_tnl_dst *idst; + struct dst_entry *dst; + unsigned int seq; + u32 cookie; + + idst = raw_cpu_ptr(t->dst_cache); + + rcu_read_lock(); + do { + seq = read_seqbegin(&idst->lock); + dst = rcu_dereference(idst->dst); + cookie = idst->cookie; + } while (read_seqretry(&idst->lock, seq)); + + if (dst && !atomic_inc_not_zero(&dst->__refcnt)) + dst = NULL; + rcu_read_unlock(); + + if (dst && dst->obsolete && !dst->ops->check(dst, cookie)) { + ip6_tnl_per_cpu_dst_set(idst, NULL); + dst_release(dst); + dst = NULL; + } return dst; } -EXPORT_SYMBOL_GPL(ip6_tnl_dst_check); +EXPORT_SYMBOL_GPL(ip6_tnl_dst_get); void ip6_tnl_dst_reset(struct ip6_tnl *t) { - dst_release(t->dst_cache); - t->dst_cache = NULL; + int i; + + for_each_possible_cpu(i) + ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), NULL); } EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset); -void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) +void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst) { - struct rt6_info *rt = (struct rt6_info *) dst; - t->dst_cookie = rt6_get_cookie(rt); - dst_release(t->dst_cache); - t->dst_cache = dst; + ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), dst); + } -EXPORT_SYMBOL_GPL(ip6_tnl_dst_store); +EXPORT_SYMBOL_GPL(ip6_tnl_dst_set); + +void ip6_tnl_dst_destroy(struct ip6_tnl *t) +{ + if (!t->dst_cache) + return; + + ip6_tnl_dst_reset(t); + free_percpu(t->dst_cache); +} +EXPORT_SYMBOL_GPL(ip6_tnl_dst_destroy); + +int ip6_tnl_dst_init(struct ip6_tnl *t) +{ + int i; + + t->dst_cache = alloc_percpu(struct ip6_tnl_dst); + if (!t->dst_cache) + return -ENOMEM; + + for_each_possible_cpu(i) + seqlock_init(&per_cpu_ptr(t->dst_cache, i)->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(ip6_tnl_dst_init); /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses @@ -271,6 +327,9 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) static void ip6_dev_free(struct net_device *dev) { + struct ip6_tnl *t = netdev_priv(dev); + + ip6_tnl_dst_destroy(t); free_percpu(dev->tstats); free_netdev(dev); } @@ -510,14 +569,14 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, struct ipv6_tlv_tnl_enc_lim *tel; __u32 mtu; case ICMPV6_DEST_UNREACH: - net_warn_ratelimited("%s: Path to destination invalid or inactive!\n", - t->parms.name); + net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", + t->parms.name); rel_msg = 1; break; case ICMPV6_TIME_EXCEED: if ((*code) == ICMPV6_EXC_HOPLIMIT) { - net_warn_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", - t->parms.name); + net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", + t->parms.name); rel_msg = 1; } break; @@ -529,13 +588,13 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, if (teli && teli == *info - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { - net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", - t->parms.name); + net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", + t->parms.name); rel_msg = 1; } } else { - net_warn_ratelimited("%s: Recipient unable to parse tunneled packet!\n", - t->parms.name); + net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n", + t->parms.name); } break; case ICMPV6_PKT_TOOBIG: @@ -1010,23 +1069,23 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); } else if (!fl6->flowi6_mark) - dst = ip6_tnl_dst_check(t); + dst = ip6_tnl_dst_get(t); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) goto tx_err_link_failure; if (!dst) { - ndst = ip6_route_output(net, NULL, fl6); + dst = ip6_route_output(net, NULL, fl6); - if (ndst->error) + if (dst->error) goto tx_err_link_failure; - ndst = xfrm_lookup(net, ndst, flowi6_to_flowi(fl6), NULL, 0); - if (IS_ERR(ndst)) { - err = PTR_ERR(ndst); - ndst = NULL; + dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; goto tx_err_link_failure; } - dst = ndst; + ndst = dst; } tdev = dst->dev; @@ -1072,12 +1131,11 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, consume_skb(skb); skb = new_skb; } - if (fl6->flowi6_mark) { - skb_dst_set(skb, dst); - ndst = NULL; - } else { - skb_dst_set_noref(skb, dst); - } + + if (!fl6->flowi6_mark && ndst) + ip6_tnl_dst_set(t, ndst); + skb_dst_set(skb, dst); + skb->transport_header = skb->network_header; proto = fl6->flowi6_proto; @@ -1101,14 +1159,12 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, ipv6h->saddr = fl6->saddr; ipv6h->daddr = fl6->daddr; ip6tunnel_xmit(NULL, skb, dev); - if (ndst) - ip6_tnl_dst_store(t, ndst); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: - dst_release(ndst); + dst_release(dst); return err; } @@ -1573,12 +1629,21 @@ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); + int ret; t->dev = dev; t->net = dev_net(dev); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; + + ret = ip6_tnl_dst_init(t); + if (ret) { + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; + } + return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 53617d715188..f204089e854c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1322,8 +1322,7 @@ static void ip6_link_failure(struct sk_buff *skb) if (rt) { if (rt->rt6i_flags & RTF_CACHE) { dst_hold(&rt->dst); - if (ip6_del_rt(rt)) - dst_free(&rt->dst); + ip6_del_rt(rt); } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { rt->rt6i_node->fn_sernum = -1; } @@ -1886,9 +1885,11 @@ int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret) rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: + case RTN_UNREACHABLE: default: rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN - : -ENETUNREACH; + : (cfg->fc_type == RTN_UNREACHABLE) + ? -EHOSTUNREACH : -ENETUNREACH; rt->dst.output = ip6_pkt_discard_out; rt->dst.input = ip6_pkt_discard; break; @@ -2028,7 +2029,8 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) struct fib6_table *table; struct net *net = dev_net(rt->dst.dev); - if (rt == net->ipv6.ip6_null_entry) { + if (rt == net->ipv6.ip6_null_entry || + rt->dst.flags & DST_NOCACHE) { err = -ENOENT; goto out; } @@ -2515,6 +2517,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); + rt->dst.flags |= DST_NOCACHE; atomic_set(&rt->dst.__refcnt, 1); @@ -3303,7 +3306,8 @@ errout: return err; } -void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) +void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, + unsigned int nlm_flags) { struct sk_buff *skb; struct net *net = info->nl_net; @@ -3318,7 +3322,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, - event, info->portid, seq, 0, 0, 0); + event, info->portid, seq, 0, 0, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 17b1fe961c5d..7a77a1470f25 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2474,6 +2474,7 @@ static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy, bss_conf->cqm_rssi_thold = rssi_thold; bss_conf->cqm_rssi_hyst = rssi_hyst; + sdata->u.mgd.last_cqm_event_signal = 0; /* tell the driver upon association, unless already associated */ if (sdata->u.mgd.associated && @@ -2518,15 +2519,17 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, continue; for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) { - if (~sdata->rc_rateidx_mcs_mask[i][j]) + if (~sdata->rc_rateidx_mcs_mask[i][j]) { sdata->rc_has_mcs_mask[i] = true; - - if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) - sdata->rc_has_vht_mcs_mask[i] = true; - - if (sdata->rc_has_mcs_mask[i] && - sdata->rc_has_vht_mcs_mask[i]) break; + } + } + + for (j = 0; j < NL80211_VHT_NSS_MAX; j++) { + if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) { + sdata->rc_has_vht_mcs_mask[i] = true; + break; + } } } diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 675d12c69e32..a5d41dfa9f05 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -107,12 +107,17 @@ EXPORT_SYMBOL(nf_log_register); void nf_log_unregister(struct nf_logger *logger) { + const struct nf_logger *log; int i; mutex_lock(&nf_log_mutex); - for (i = 0; i < NFPROTO_NUMPROTO; i++) - RCU_INIT_POINTER(loggers[i][logger->type], NULL); + for (i = 0; i < NFPROTO_NUMPROTO; i++) { + log = nft_log_dereference(loggers[i][logger->type]); + if (log == logger) + RCU_INIT_POINTER(loggers[i][logger->type], NULL); + } mutex_unlock(&nf_log_mutex); + synchronize_rcu(); } EXPORT_SYMBOL(nf_log_unregister); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 66def315eb56..9c8fab00164b 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -619,6 +619,13 @@ struct nft_xt { static struct nft_expr_type nft_match_type; +static bool nft_match_cmp(const struct xt_match *match, + const char *name, u32 rev, u32 family) +{ + return strcmp(match->name, name) == 0 && match->revision == rev && + (match->family == NFPROTO_UNSPEC || match->family == family); +} + static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -626,7 +633,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, struct nft_xt *nft_match; struct xt_match *match; char *mt_name; - __u32 rev, family; + u32 rev, family; if (tb[NFTA_MATCH_NAME] == NULL || tb[NFTA_MATCH_REV] == NULL || @@ -641,8 +648,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, list_for_each_entry(nft_match, &nft_match_list, head) { struct xt_match *match = nft_match->ops.data; - if (strcmp(match->name, mt_name) == 0 && - match->revision == rev && match->family == family) { + if (nft_match_cmp(match, mt_name, rev, family)) { if (!try_module_get(match->me)) return ERR_PTR(-ENOENT); @@ -693,6 +699,13 @@ static LIST_HEAD(nft_target_list); static struct nft_expr_type nft_target_type; +static bool nft_target_cmp(const struct xt_target *tg, + const char *name, u32 rev, u32 family) +{ + return strcmp(tg->name, name) == 0 && tg->revision == rev && + (tg->family == NFPROTO_UNSPEC || tg->family == family); +} + static const struct nft_expr_ops * nft_target_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -700,7 +713,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, struct nft_xt *nft_target; struct xt_target *target; char *tg_name; - __u32 rev, family; + u32 rev, family; if (tb[NFTA_TARGET_NAME] == NULL || tb[NFTA_TARGET_REV] == NULL || @@ -715,8 +728,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, list_for_each_entry(nft_target, &nft_target_list, head) { struct xt_target *target = nft_target->ops.data; - if (strcmp(target->name, tg_name) == 0 && - target->revision == rev && target->family == family) { + if (nft_target_cmp(target, tg_name, rev, family)) { if (!try_module_get(target->me)) return ERR_PTR(-ENOENT); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 7f86d3b55060..8f060d7f9a0e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -125,6 +125,24 @@ static inline u32 netlink_group_mask(u32 group) return group ? 1 << (group - 1) : 0; } +static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, + gfp_t gfp_mask) +{ + unsigned int len = skb_end_offset(skb); + struct sk_buff *new; + + new = alloc_skb(len, gfp_mask); + if (new == NULL) + return NULL; + + NETLINK_CB(new).portid = NETLINK_CB(skb).portid; + NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group; + NETLINK_CB(new).creds = NETLINK_CB(skb).creds; + + memcpy(skb_put(new, len), skb->data, len); + return new; +} + int netlink_add_tap(struct netlink_tap *nt) { if (unlikely(nt->dev->type != ARPHRD_NETLINK)) @@ -206,7 +224,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, int ret = -ENOMEM; dev_hold(dev); - nskb = skb_clone(skb, GFP_ATOMIC); + + if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head)) + nskb = netlink_to_full_skb(skb, GFP_ATOMIC); + else + nskb = skb_clone(skb, GFP_ATOMIC); if (nskb) { nskb->dev = dev; nskb->protocol = htons((u16) sk->sk_protocol); @@ -279,11 +301,6 @@ static void netlink_rcv_wake(struct sock *sk) } #ifdef CONFIG_NETLINK_MMAP -static bool netlink_skb_is_mmaped(const struct sk_buff *skb) -{ - return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED; -} - static bool netlink_rx_is_mmaped(struct sock *sk) { return nlk_sk(sk)->rx_ring.pg_vec != NULL; @@ -846,7 +863,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb) } #else /* CONFIG_NETLINK_MMAP */ -#define netlink_skb_is_mmaped(skb) false #define netlink_rx_is_mmaped(sk) false #define netlink_tx_is_mmaped(sk) false #define netlink_mmap sock_no_mmap @@ -1094,8 +1110,8 @@ static int netlink_insert(struct sock *sk, u32 portid) lock_sock(sk); - err = -EBUSY; - if (nlk_sk(sk)->portid) + err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY; + if (nlk_sk(sk)->bound) goto err; err = -ENOMEM; @@ -1115,10 +1131,14 @@ static int netlink_insert(struct sock *sk, u32 portid) err = -EOVERFLOW; if (err == -EEXIST) err = -EADDRINUSE; - nlk_sk(sk)->portid = 0; sock_put(sk); + goto err; } + /* We need to ensure that the socket is hashed and visible. */ + smp_wmb(); + nlk_sk(sk)->bound = portid; + err: release_sock(sk); return err; @@ -1503,6 +1523,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err; long unsigned int groups = nladdr->nl_groups; + bool bound; if (addr_len < sizeof(struct sockaddr_nl)) return -EINVAL; @@ -1519,9 +1540,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } - if (nlk->portid) + bound = nlk->bound; + if (bound) { + /* Ensure nlk->portid is up-to-date. */ + smp_rmb(); + if (nladdr->nl_pid != nlk->portid) return -EINVAL; + } if (nlk->netlink_bind && groups) { int group; @@ -1537,7 +1563,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, } } - if (!nlk->portid) { + /* No need for barriers here as we return to user-space without + * using any of the bound attributes. + */ + if (!bound) { err = nladdr->nl_pid ? netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); @@ -1585,7 +1614,10 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; - if (!nlk->portid) + /* No need for barriers here as we return to user-space without + * using any of the bound attributes. + */ + if (!nlk->bound) err = netlink_autobind(sock); if (err == 0) { @@ -2426,10 +2458,13 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) dst_group = nlk->dst_group; } - if (!nlk->portid) { + if (!nlk->bound) { err = netlink_autobind(sock); if (err) goto out; + } else { + /* Ensure nlk is hashed and visible. */ + smp_rmb(); } /* It's a really convoluted way for userland to ask for mmaped diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 89008405d6b4..14437d9b1965 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -35,6 +35,7 @@ struct netlink_sock { unsigned long state; size_t max_recvmsg_len; wait_queue_head_t wait; + bool bound; bool cb_running; struct netlink_callback cb; struct mutex *cb_mutex; @@ -59,6 +60,15 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk) return container_of(sk, struct netlink_sock, sk); } +static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb) +{ +#ifdef CONFIG_NETLINK_MMAP + return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED; +#else + return false; +#endif /* CONFIG_NETLINK_MMAP */ +} + struct netlink_table { struct rhashtable hash; struct hlist_head mc_list; diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 2a071f470d57..d143aa9f6654 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -5,7 +5,8 @@ config OPENVSWITCH tristate "Open vSwitch" depends on INET - depends on (!NF_CONNTRACK || NF_CONNTRACK) + depends on !NF_CONNTRACK || \ + (NF_CONNTRACK && (!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6)) select LIBCRC32C select MPLS select NET_MPLS_GSO diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index e8e524ad8a01..002a755fa07e 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -275,13 +275,15 @@ static int ovs_ct_helper(struct sk_buff *skb, u16 proto) case NFPROTO_IPV6: { u8 nexthdr = ipv6_hdr(skb)->nexthdr; __be16 frag_off; + int ofs; - protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), - &nexthdr, &frag_off); - if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { + ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { pr_debug("proto header not found\n"); return NF_ACCEPT; } + protoff = ofs; break; } default: diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 6fbd2decb19e..b816ff871528 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -952,7 +952,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) if (error) goto err_kfree_flow; - ovs_flow_mask_key(&new_flow->key, &key, &mask); + ovs_flow_mask_key(&new_flow->key, &key, true, &mask); /* Extract flow identifier. */ error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], @@ -1080,7 +1080,7 @@ static struct sw_flow_actions *get_flow_actions(struct net *net, struct sw_flow_key masked_key; int error; - ovs_flow_mask_key(&masked_key, key, mask); + ovs_flow_mask_key(&masked_key, key, true, mask); error = ovs_nla_copy_actions(net, a, &masked_key, &acts, log); if (error) { OVS_NLERR(log, diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index c92d6a262bc5..5c030a4d7338 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -57,6 +57,7 @@ struct ovs_len_tbl { }; #define OVS_ATTR_NESTED -1 +#define OVS_ATTR_VARIABLE -2 static void update_range(struct sw_flow_match *match, size_t offset, size_t size, bool is_mask) @@ -304,6 +305,10 @@ size_t ovs_key_attr_size(void) + nla_total_size(28); /* OVS_KEY_ATTR_ND */ } +static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = { + [OVS_VXLAN_EXT_GBP] = { .len = sizeof(u32) }, +}; + static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = { [OVS_TUNNEL_KEY_ATTR_ID] = { .len = sizeof(u64) }, [OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = { .len = sizeof(u32) }, @@ -315,8 +320,9 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] [OVS_TUNNEL_KEY_ATTR_TP_SRC] = { .len = sizeof(u16) }, [OVS_TUNNEL_KEY_ATTR_TP_DST] = { .len = sizeof(u16) }, [OVS_TUNNEL_KEY_ATTR_OAM] = { .len = 0 }, - [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_NESTED }, - [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED }, + [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_VARIABLE }, + [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED, + .next = ovs_vxlan_ext_key_lens }, }; /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ @@ -349,6 +355,13 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_CT_LABEL] = { .len = sizeof(struct ovs_key_ct_label) }, }; +static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) +{ + return expected_len == attr_len || + expected_len == OVS_ATTR_NESTED || + expected_len == OVS_ATTR_VARIABLE; +} + static bool is_all_zero(const u8 *fp, size_t size) { int i; @@ -388,7 +401,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, } expected_len = ovs_key_lens[type].len; - if (nla_len(nla) != expected_len && expected_len != OVS_ATTR_NESTED) { + if (!check_attr_len(nla_len(nla), expected_len)) { OVS_NLERR(log, "Key %d has unexpected len %d expected %d", type, nla_len(nla), expected_len); return -EINVAL; @@ -473,29 +486,50 @@ static int genev_tun_opt_from_nlattr(const struct nlattr *a, return 0; } -static const struct nla_policy vxlan_opt_policy[OVS_VXLAN_EXT_MAX + 1] = { - [OVS_VXLAN_EXT_GBP] = { .type = NLA_U32 }, -}; - -static int vxlan_tun_opt_from_nlattr(const struct nlattr *a, +static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) { - struct nlattr *tb[OVS_VXLAN_EXT_MAX+1]; + struct nlattr *a; + int rem; unsigned long opt_key_offset; struct vxlan_metadata opts; - int err; BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); - err = nla_parse_nested(tb, OVS_VXLAN_EXT_MAX, a, vxlan_opt_policy); - if (err < 0) - return err; - memset(&opts, 0, sizeof(opts)); + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); - if (tb[OVS_VXLAN_EXT_GBP]) - opts.gbp = nla_get_u32(tb[OVS_VXLAN_EXT_GBP]); + if (type > OVS_VXLAN_EXT_MAX) { + OVS_NLERR(log, "VXLAN extension %d out of range max %d", + type, OVS_VXLAN_EXT_MAX); + return -EINVAL; + } + + if (!check_attr_len(nla_len(a), + ovs_vxlan_ext_key_lens[type].len)) { + OVS_NLERR(log, "VXLAN extension %d has unexpected len %d expected %d", + type, nla_len(a), + ovs_vxlan_ext_key_lens[type].len); + return -EINVAL; + } + + switch (type) { + case OVS_VXLAN_EXT_GBP: + opts.gbp = nla_get_u32(a); + break; + default: + OVS_NLERR(log, "Unknown VXLAN extension attribute %d", + type); + return -EINVAL; + } + } + if (rem) { + OVS_NLERR(log, "VXLAN extension message has %d unknown bytes.", + rem); + return -EINVAL; + } if (!is_mask) SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false); @@ -528,8 +562,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, return -EINVAL; } - if (ovs_tunnel_key_lens[type].len != nla_len(a) && - ovs_tunnel_key_lens[type].len != OVS_ATTR_NESTED) { + if (!check_attr_len(nla_len(a), + ovs_tunnel_key_lens[type].len)) { OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d", type, nla_len(a), ovs_tunnel_key_lens[type].len); return -EINVAL; @@ -1052,10 +1086,13 @@ static void nlattr_set(struct nlattr *attr, u8 val, /* The nlattr stream should already have been validated */ nla_for_each_nested(nla, attr, rem) { - if (tbl && tbl[nla_type(nla)].len == OVS_ATTR_NESTED) - nlattr_set(nla, val, tbl[nla_type(nla)].next); - else + if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) { + if (tbl[nla_type(nla)].next) + tbl = tbl[nla_type(nla)].next; + nlattr_set(nla, val, tbl); + } else { memset(nla_data(nla), val, nla_len(nla)); + } } } @@ -1922,8 +1959,7 @@ static int validate_set(const struct nlattr *a, key_len /= 2; if (key_type > OVS_KEY_ATTR_MAX || - (ovs_key_lens[key_type].len != key_len && - ovs_key_lens[key_type].len != OVS_ATTR_NESTED)) + !check_attr_len(key_len, ovs_key_lens[key_type].len)) return -EINVAL; if (masked && !validate_masked(nla_data(ovs_key), key_len)) diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index d22d8e948d0f..f2ea83ba4763 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -57,20 +57,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range) } void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, - const struct sw_flow_mask *mask) + bool full, const struct sw_flow_mask *mask) { - const long *m = (const long *)((const u8 *)&mask->key + - mask->range.start); - const long *s = (const long *)((const u8 *)src + - mask->range.start); - long *d = (long *)((u8 *)dst + mask->range.start); + int start = full ? 0 : mask->range.start; + int len = full ? sizeof *dst : range_n_bytes(&mask->range); + const long *m = (const long *)((const u8 *)&mask->key + start); + const long *s = (const long *)((const u8 *)src + start); + long *d = (long *)((u8 *)dst + start); int i; - /* The memory outside of the 'mask->range' are not set since - * further operations on 'dst' only uses contents within - * 'mask->range'. + /* If 'full' is true then all of 'dst' is fully initialized. Otherwise, + * if 'full' is false the memory outside of the 'mask->range' is left + * uninitialized. This can be used as an optimization when further + * operations on 'dst' only use contents within 'mask->range'. */ - for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long)) + for (i = 0; i < len; i += sizeof(long)) *d++ = *s++ & *m++; } @@ -475,7 +476,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, u32 hash; struct sw_flow_key masked_key; - ovs_flow_mask_key(&masked_key, unmasked, mask); + ovs_flow_mask_key(&masked_key, unmasked, false, mask); hash = flow_hash(&masked_key, &mask->range); head = find_bucket(ti, hash); hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) { diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index 616eda10d955..2dd9900f533d 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -86,5 +86,5 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *, bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *); void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, - const struct sw_flow_mask *mask); + bool full, const struct sw_flow_mask *mask); #endif /* flow_table.h */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 7b8e39a22387..aa4b15c35884 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -230,6 +230,8 @@ struct packet_skb_cb { } sa; }; +#define vio_le() virtio_legacy_is_little_endian() + #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) #define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc)) @@ -2680,15 +2682,15 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && - (__virtio16_to_cpu(false, vnet_hdr.csum_start) + - __virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2 > - __virtio16_to_cpu(false, vnet_hdr.hdr_len))) - vnet_hdr.hdr_len = __cpu_to_virtio16(false, - __virtio16_to_cpu(false, vnet_hdr.csum_start) + - __virtio16_to_cpu(false, vnet_hdr.csum_offset) + 2); + (__virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) + + __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2 > + __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len))) + vnet_hdr.hdr_len = __cpu_to_virtio16(vio_le(), + __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) + + __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2); err = -EINVAL; - if (__virtio16_to_cpu(false, vnet_hdr.hdr_len) > len) + if (__virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len) > len) goto out_unlock; if (vnet_hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) { @@ -2731,7 +2733,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, - __virtio16_to_cpu(false, vnet_hdr.hdr_len), + __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len), msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; @@ -2778,8 +2780,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (po->has_vnet_hdr) { if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { - u16 s = __virtio16_to_cpu(false, vnet_hdr.csum_start); - u16 o = __virtio16_to_cpu(false, vnet_hdr.csum_offset); + u16 s = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start); + u16 o = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset); if (!skb_partial_csum_set(skb, s, o)) { err = -EINVAL; goto out_free; @@ -2787,7 +2789,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) } skb_shinfo(skb)->gso_size = - __virtio16_to_cpu(false, vnet_hdr.gso_size); + __virtio16_to_cpu(vio_le(), vnet_hdr.gso_size); skb_shinfo(skb)->gso_type = gso_type; /* Header must be checked, and gso_segs computed. */ @@ -3161,9 +3163,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, /* This is a hint as to how much should be linear. */ vnet_hdr.hdr_len = - __cpu_to_virtio16(false, skb_headlen(skb)); + __cpu_to_virtio16(vio_le(), skb_headlen(skb)); vnet_hdr.gso_size = - __cpu_to_virtio16(false, sinfo->gso_size); + __cpu_to_virtio16(vio_le(), sinfo->gso_size); if (sinfo->gso_type & SKB_GSO_TCPV4) vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) @@ -3181,9 +3183,9 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (skb->ip_summed == CHECKSUM_PARTIAL) { vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; - vnet_hdr.csum_start = __cpu_to_virtio16(false, + vnet_hdr.csum_start = __cpu_to_virtio16(vio_le(), skb_checksum_start_offset(skb)); - vnet_hdr.csum_offset = __cpu_to_virtio16(false, + vnet_hdr.csum_offset = __cpu_to_virtio16(vio_le(), skb->csum_offset); } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { vnet_hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 715e01e5910a..f23a3b68bba6 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -33,7 +33,6 @@ struct fw_head { u32 mask; - bool mask_set; struct fw_filter __rcu *ht[HTSIZE]; struct rcu_head rcu; }; @@ -84,7 +83,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, } } } else { - /* old method */ + /* Old method: classify the packet using its skb mark. */ if (id && (TC_H_MAJ(id) == 0 || !(TC_H_MAJ(id ^ tp->q->handle)))) { res->classid = id; @@ -114,14 +113,9 @@ static unsigned long fw_get(struct tcf_proto *tp, u32 handle) static int fw_init(struct tcf_proto *tp) { - struct fw_head *head; - - head = kzalloc(sizeof(struct fw_head), GFP_KERNEL); - if (head == NULL) - return -ENOBUFS; - - head->mask_set = false; - rcu_assign_pointer(tp->root, head); + /* We don't allocate fw_head here, because in the old method + * we don't need it at all. + */ return 0; } @@ -252,7 +246,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, int err; if (!opt) - return handle ? -EINVAL : 0; + return handle ? -EINVAL : 0; /* Succeed if it is old method. */ err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy); if (err < 0) @@ -302,11 +296,17 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, if (!handle) return -EINVAL; - if (!head->mask_set) { - head->mask = 0xFFFFFFFF; + if (!head) { + u32 mask = 0xFFFFFFFF; if (tb[TCA_FW_MASK]) - head->mask = nla_get_u32(tb[TCA_FW_MASK]); - head->mask_set = true; + mask = nla_get_u32(tb[TCA_FW_MASK]); + + head = kzalloc(sizeof(*head), GFP_KERNEL); + if (!head) + return -ENOBUFS; + head->mask = mask; + + rcu_assign_pointer(tp->root, head); } f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index b7143337e4fa..3d9ea9a48289 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1186,7 +1186,7 @@ static void sctp_v4_del_protocol(void) unregister_inetaddr_notifier(&sctp_inetaddr_notifier); } -static int __net_init sctp_net_init(struct net *net) +static int __net_init sctp_defaults_init(struct net *net) { int status; @@ -1279,12 +1279,6 @@ static int __net_init sctp_net_init(struct net *net) sctp_dbg_objcnt_init(net); - /* Initialize the control inode/socket for handling OOTB packets. */ - if ((status = sctp_ctl_sock_init(net))) { - pr_err("Failed to initialize the SCTP control sock\n"); - goto err_ctl_sock_init; - } - /* Initialize the local address list. */ INIT_LIST_HEAD(&net->sctp.local_addr_list); spin_lock_init(&net->sctp.local_addr_lock); @@ -1300,9 +1294,6 @@ static int __net_init sctp_net_init(struct net *net) return 0; -err_ctl_sock_init: - sctp_dbg_objcnt_exit(net); - sctp_proc_exit(net); err_init_proc: cleanup_sctp_mibs(net); err_init_mibs: @@ -1311,15 +1302,12 @@ err_sysctl_register: return status; } -static void __net_exit sctp_net_exit(struct net *net) +static void __net_exit sctp_defaults_exit(struct net *net) { /* Free the local address list */ sctp_free_addr_wq(net); sctp_free_local_addr_list(net); - /* Free the control endpoint. */ - inet_ctl_sock_destroy(net->sctp.ctl_sock); - sctp_dbg_objcnt_exit(net); sctp_proc_exit(net); @@ -1327,9 +1315,32 @@ static void __net_exit sctp_net_exit(struct net *net) sctp_sysctl_net_unregister(net); } -static struct pernet_operations sctp_net_ops = { - .init = sctp_net_init, - .exit = sctp_net_exit, +static struct pernet_operations sctp_defaults_ops = { + .init = sctp_defaults_init, + .exit = sctp_defaults_exit, +}; + +static int __net_init sctp_ctrlsock_init(struct net *net) +{ + int status; + + /* Initialize the control inode/socket for handling OOTB packets. */ + status = sctp_ctl_sock_init(net); + if (status) + pr_err("Failed to initialize the SCTP control sock\n"); + + return status; +} + +static void __net_init sctp_ctrlsock_exit(struct net *net) +{ + /* Free the control endpoint. */ + inet_ctl_sock_destroy(net->sctp.ctl_sock); +} + +static struct pernet_operations sctp_ctrlsock_ops = { + .init = sctp_ctrlsock_init, + .exit = sctp_ctrlsock_exit, }; /* Initialize the universe into something sensible. */ @@ -1462,8 +1473,11 @@ static __init int sctp_init(void) sctp_v4_pf_init(); sctp_v6_pf_init(); - status = sctp_v4_protosw_init(); + status = register_pernet_subsys(&sctp_defaults_ops); + if (status) + goto err_register_defaults; + status = sctp_v4_protosw_init(); if (status) goto err_protosw_init; @@ -1471,9 +1485,9 @@ static __init int sctp_init(void) if (status) goto err_v6_protosw_init; - status = register_pernet_subsys(&sctp_net_ops); + status = register_pernet_subsys(&sctp_ctrlsock_ops); if (status) - goto err_register_pernet_subsys; + goto err_register_ctrlsock; status = sctp_v4_add_protocol(); if (status) @@ -1489,12 +1503,14 @@ out: err_v6_add_protocol: sctp_v4_del_protocol(); err_add_protocol: - unregister_pernet_subsys(&sctp_net_ops); -err_register_pernet_subsys: + unregister_pernet_subsys(&sctp_ctrlsock_ops); +err_register_ctrlsock: sctp_v6_protosw_exit(); err_v6_protosw_init: sctp_v4_protosw_exit(); err_protosw_init: + unregister_pernet_subsys(&sctp_defaults_ops); +err_register_defaults: sctp_v4_pf_exit(); sctp_v6_pf_exit(); sctp_sysctl_unregister(); @@ -1527,12 +1543,14 @@ static __exit void sctp_exit(void) sctp_v6_del_protocol(); sctp_v4_del_protocol(); - unregister_pernet_subsys(&sctp_net_ops); + unregister_pernet_subsys(&sctp_ctrlsock_ops); /* Free protosw registrations */ sctp_v6_protosw_exit(); sctp_v4_protosw_exit(); + unregister_pernet_subsys(&sctp_defaults_ops); + /* Unregister with socket layer. */ sctp_v6_pf_exit(); sctp_v4_pf_exit(); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 562c926a51cc..c5ac436235e0 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -539,6 +539,7 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) *err = -TIPC_ERR_NO_NAME; if (skb_linearize(skb)) return false; + msg = buf_msg(skb); if (msg_reroute_cnt(msg)) return false; dnode = addr_domain(net, msg_lookup_scope(msg));