diff options
author | David S. Miller <davem@davemloft.net> | 2013-12-10 01:20:14 (GMT) |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2013-12-10 01:20:14 (GMT) |
commit | 34f9f437104b86f6ddfa2770e2cd852846385dc3 (patch) | |
tree | 6c78386b3db9dd47fd2b79efb4dcf8c1472de99e | |
parent | 95dc19299f741c986227ec33e23cbf9b3321f812 (diff) | |
parent | 66e56cd46b93ef407c60adcac62cf33b06119d50 (diff) | |
download | linux-34f9f437104b86f6ddfa2770e2cd852846385dc3.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Merge 'net' into 'net-next' to get the AF_PACKET bug fix that
Daniel's direct transmit changes depend upon.
Signed-off-by: David S. Miller <davem@davemloft.net>
37 files changed, 314 insertions, 208 deletions
diff --git a/Documentation/devicetree/bindings/net/davinci_emac.txt b/Documentation/devicetree/bindings/net/davinci_emac.txt index 48b259e..bad381f 100644 --- a/Documentation/devicetree/bindings/net/davinci_emac.txt +++ b/Documentation/devicetree/bindings/net/davinci_emac.txt @@ -4,7 +4,7 @@ This file provides information, what the device node for the davinci_emac interface contains. Required properties: -- compatible: "ti,davinci-dm6467-emac"; +- compatible: "ti,davinci-dm6467-emac" or "ti,am3517-emac" - reg: Offset and length of the register set for the device - ti,davinci-ctrl-reg-offset: offset to control register - ti,davinci-ctrl-mod-reg-offset: offset to control module register diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index c012236..8e48e3b 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -123,6 +123,16 @@ Transmission process is similar to capture as shown below. [shutdown] close() --------> destruction of the transmission socket and deallocation of all associated resources. +Socket creation and destruction is also straight forward, and is done +the same way as in capturing described in the previous paragraph: + + int fd = socket(PF_PACKET, mode, 0); + +The protocol can optionally be 0 in case we only want to transmit +via this socket, which avoids an expensive call to packet_rcv(). +In this case, you also need to bind(2) the TX_RING with sll_protocol = 0 +set. Otherwise, htons(ETH_P_ALL) or any other protocol, for example. + Binding the socket to your network interface is mandatory (with zero copy) to know the header size of frames used in the circular buffer. diff --git a/MAINTAINERS b/MAINTAINERS index b9ea932..63ae896 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4450,10 +4450,8 @@ M: Bruce Allan <bruce.w.allan@intel.com> M: Carolyn Wyborny <carolyn.wyborny@intel.com> M: Don Skidmore <donald.c.skidmore@intel.com> M: Greg Rose <gregory.v.rose@intel.com> -M: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> M: Alex Duyck <alexander.h.duyck@intel.com> M: John Ronciak <john.ronciak@intel.com> -M: Tushar Dave <tushar.n.dave@intel.com> L: e1000-devel@lists.sourceforge.net W: http://www.intel.com/support/feedback.htm W: http://e1000.sourceforge.net/ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 36eab0c..398e299 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4199,9 +4199,9 @@ static int bond_check_params(struct bond_params *params) (arp_ip_count < BOND_MAX_ARP_TARGETS) && arp_ip_target[i]; i++) { /* not complete check, but should be good enough to catch mistakes */ - __be32 ip = in_aton(arp_ip_target[i]); - if (!isdigit(arp_ip_target[i][0]) || ip == 0 || - ip == htonl(INADDR_BROADCAST)) { + __be32 ip; + if (!in4_pton(arp_ip_target[i], -1, (u8 *)&ip, -1, NULL) || + IS_IP_TARGET_UNUSABLE_ADDRESS(ip)) { pr_warning("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n", arp_ip_target[i]); arp_interval = 0; diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index c778a26..e464676 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -1634,12 +1634,12 @@ static ssize_t bonding_show_packets_per_slave(struct device *d, char *buf) { struct bonding *bond = to_bond(d); - int packets_per_slave = bond->params.packets_per_slave; + unsigned int packets_per_slave = bond->params.packets_per_slave; if (packets_per_slave > 1) packets_per_slave = reciprocal_value(packets_per_slave); - return sprintf(buf, "%d\n", packets_per_slave); + return sprintf(buf, "%u\n", packets_per_slave); } static ssize_t bonding_store_packets_per_slave(struct device *d, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 0216d59..2e46c28 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -3114,6 +3114,11 @@ int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs_param) { struct bnx2x *bp = netdev_priv(pci_get_drvdata(dev)); + if (!IS_SRIOV(bp)) { + BNX2X_ERR("failed to configure SR-IOV since vfdb was not allocated. Check dmesg for errors in probe stage\n"); + return -EINVAL; + } + DP(BNX2X_MSG_IOV, "bnx2x_sriov_configure called with %d, BNX2X_NR_VIRTFN(bp) was %d\n", num_vfs_param, BNX2X_NR_VIRTFN(bp)); diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h index 3e21621..dc88782 100644 --- a/drivers/net/ethernet/emulex/benet/be_hw.h +++ b/drivers/net/ethernet/emulex/benet/be_hw.h @@ -64,6 +64,9 @@ #define SLIPORT_ERROR_NO_RESOURCE1 0x2 #define SLIPORT_ERROR_NO_RESOURCE2 0x9 +#define SLIPORT_ERROR_FW_RESET1 0x2 +#define SLIPORT_ERROR_FW_RESET2 0x0 + /********* Memory BAR register ************/ #define PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET 0xfc /* Host Interrupt Enable, if set interrupts are enabled although "PCI Interrupt diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index fee64bf..0fde69d 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -2464,8 +2464,16 @@ void be_detect_error(struct be_adapter *adapter) */ if (sliport_status & SLIPORT_STATUS_ERR_MASK) { adapter->hw_error = true; - dev_err(&adapter->pdev->dev, - "Error detected in the card\n"); + /* Do not log error messages if its a FW reset */ + if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 && + sliport_err2 == SLIPORT_ERROR_FW_RESET2) { + dev_info(&adapter->pdev->dev, + "Firmware update in progress\n"); + return; + } else { + dev_err(&adapter->pdev->dev, + "Error detected in the card\n"); + } } if (sliport_status & SLIPORT_STATUS_ERR_MASK) { @@ -2932,28 +2940,35 @@ static void be_cancel_worker(struct be_adapter *adapter) } } -static int be_clear(struct be_adapter *adapter) +static void be_mac_clear(struct be_adapter *adapter) { int i; + if (adapter->pmac_id) { + for (i = 0; i < (adapter->uc_macs + 1); i++) + be_cmd_pmac_del(adapter, adapter->if_handle, + adapter->pmac_id[i], 0); + adapter->uc_macs = 0; + + kfree(adapter->pmac_id); + adapter->pmac_id = NULL; + } +} + +static int be_clear(struct be_adapter *adapter) +{ be_cancel_worker(adapter); if (sriov_enabled(adapter)) be_vf_clear(adapter); /* delete the primary mac along with the uc-mac list */ - for (i = 0; i < (adapter->uc_macs + 1); i++) - be_cmd_pmac_del(adapter, adapter->if_handle, - adapter->pmac_id[i], 0); - adapter->uc_macs = 0; + be_mac_clear(adapter); be_cmd_if_destroy(adapter, adapter->if_handle, 0); be_clear_queues(adapter); - kfree(adapter->pmac_id); - adapter->pmac_id = NULL; - be_msix_disable(adapter); return 0; } @@ -3812,6 +3827,8 @@ static int lancer_fw_download(struct be_adapter *adapter, } if (change_status == LANCER_FW_RESET_NEEDED) { + dev_info(&adapter->pdev->dev, + "Resetting adapter to activate new FW\n"); status = lancer_physdev_ctrl(adapter, PHYSDEV_CONTROL_FW_RESET_MASK); if (status) { @@ -4363,13 +4380,13 @@ static int lancer_recover_func(struct be_adapter *adapter) goto err; } - dev_err(dev, "Error recovery successful\n"); + dev_err(dev, "Adapter recovery successful\n"); return 0; err: if (status == -EAGAIN) dev_err(dev, "Waiting for resource provisioning\n"); else - dev_err(dev, "Error recovery failed\n"); + dev_err(dev, "Adapter recovery failed\n"); return status; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index b8e232b..d5f0d72 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1378,7 +1378,7 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp, dev_kfree_skb_any(skb); dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr, - rx_desc->data_size, DMA_FROM_DEVICE); + MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE); } if (rx_done) @@ -1424,7 +1424,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo, } dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr, - rx_desc->data_size, DMA_FROM_DEVICE); + MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE); rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE); diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index d8bdaf6..493a112 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -5149,8 +5149,10 @@ static void nv_self_test(struct net_device *dev, struct ethtool_test *test, u64 { struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); - int result; - memset(buffer, 0, nv_get_sset_count(dev, ETH_SS_TEST)*sizeof(u64)); + int result, count; + + count = nv_get_sset_count(dev, ETH_SS_TEST); + memset(buffer, 0, count * sizeof(u64)); if (!nv_link_test(dev)) { test->flags |= ETH_TEST_FL_FAILED; @@ -5194,7 +5196,7 @@ static void nv_self_test(struct net_device *dev, struct ethtool_test *test, u64 return; } - if (!nv_loopback_test(dev)) { + if (count > NV_TEST_COUNT_BASE && !nv_loopback_test(dev)) { test->flags |= ETH_TEST_FL_FAILED; buffer[3] = 1; } diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h index 0c9c4e8..0351747 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ b/drivers/net/ethernet/qlogic/qlge/qlge.h @@ -18,7 +18,7 @@ */ #define DRV_NAME "qlge" #define DRV_STRING "QLogic 10 Gigabit PCI-E Ethernet Driver " -#define DRV_VERSION "1.00.00.33" +#define DRV_VERSION "1.00.00.34" #define WQ_ADDR_ALIGN 0x3 /* 4 byte alignment */ diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c index 0780e03..8dee1be 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c @@ -181,6 +181,7 @@ static const char ql_gstrings_test[][ETH_GSTRING_LEN] = { }; #define QLGE_TEST_LEN (sizeof(ql_gstrings_test) / ETH_GSTRING_LEN) #define QLGE_STATS_LEN ARRAY_SIZE(ql_gstrings_stats) +#define QLGE_RCV_MAC_ERR_STATS 7 static int ql_update_ring_coalescing(struct ql_adapter *qdev) { @@ -280,6 +281,9 @@ static void ql_update_stats(struct ql_adapter *qdev) iter++; } + /* Update receive mac error statistics */ + iter += QLGE_RCV_MAC_ERR_STATS; + /* * Get Per-priority TX pause frame counter statistics. */ diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index a245dc1..449f506 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -2376,14 +2376,6 @@ static netdev_features_t qlge_fix_features(struct net_device *ndev, netdev_features_t features) { int err; - /* - * Since there is no support for separate rx/tx vlan accel - * enable/disable make sure tx flag is always in same state as rx. - */ - if (features & NETIF_F_HW_VLAN_CTAG_RX) - features |= NETIF_F_HW_VLAN_CTAG_TX; - else - features &= ~NETIF_F_HW_VLAN_CTAG_TX; /* Update the behavior of vlan accel in the adapter */ err = qlge_update_hw_vlan_features(ndev, features); diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 41ba974..cd9b164 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -61,6 +61,7 @@ #include <linux/davinci_emac.h> #include <linux/of.h> #include <linux/of_address.h> +#include <linux/of_device.h> #include <linux/of_irq.h> #include <linux/of_net.h> @@ -1752,10 +1753,14 @@ static const struct net_device_ops emac_netdev_ops = { #endif }; +static const struct of_device_id davinci_emac_of_match[]; + static struct emac_platform_data * davinci_emac_of_get_pdata(struct platform_device *pdev, struct emac_priv *priv) { struct device_node *np; + const struct of_device_id *match; + const struct emac_platform_data *auxdata; struct emac_platform_data *pdata = NULL; const u8 *mac_addr; @@ -1793,7 +1798,20 @@ davinci_emac_of_get_pdata(struct platform_device *pdev, struct emac_priv *priv) priv->phy_node = of_parse_phandle(np, "phy-handle", 0); if (!priv->phy_node) - pdata->phy_id = ""; + pdata->phy_id = NULL; + + auxdata = pdev->dev.platform_data; + if (auxdata) { + pdata->interrupt_enable = auxdata->interrupt_enable; + pdata->interrupt_disable = auxdata->interrupt_disable; + } + + match = of_match_device(davinci_emac_of_match, &pdev->dev); + if (match && match->data) { + auxdata = match->data; + pdata->version = auxdata->version; + pdata->hw_ram_addr = auxdata->hw_ram_addr; + } pdev->dev.platform_data = pdata; @@ -2020,8 +2038,14 @@ static const struct dev_pm_ops davinci_emac_pm_ops = { }; #if IS_ENABLED(CONFIG_OF) +static const struct emac_platform_data am3517_emac_data = { + .version = EMAC_VERSION_2, + .hw_ram_addr = 0x01e20000, +}; + static const struct of_device_id davinci_emac_of_match[] = { {.compatible = "ti,davinci-dm6467-emac", }, + {.compatible = "ti,am3517-emac", .data = &am3517_emac_data, }, {}, }; MODULE_DEVICE_TABLE(of, davinci_emac_of_match); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 4c6f84c..4a34bcb 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -872,6 +872,8 @@ static ssize_t macvtap_aio_read(struct kiocb *iocb, const struct iovec *iv, ret = macvtap_do_read(q, iv, len, file->f_flags & O_NONBLOCK); ret = min_t(ssize_t, ret, len); /* XXX copied from tun.c. Why? */ + if (ret > 0) + iocb->ki_pos = ret; out: return ret; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 6b0b2a0..3c5a8d8 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1355,6 +1355,8 @@ static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv, ret = tun_do_read(tun, tfile, iv, len, file->f_flags & O_NONBLOCK); ret = min_t(ssize_t, ret, len); + if (ret > 0) + iocb->ki_pos = ret; out: tun_put(tun); return ret; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 5c24288..56c2229 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -425,10 +425,10 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) if (unlikely(len < sizeof(struct virtio_net_hdr) + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); dev->stats.rx_length_errors++; - if (vi->big_packets) - give_pages(rq, buf); - else if (vi->mergeable_rx_bufs) + if (vi->mergeable_rx_bufs) put_page(virt_to_head_page(buf)); + else if (vi->big_packets) + give_pages(rq, buf); else dev_kfree_skb(buf); return; @@ -1366,6 +1366,11 @@ static void virtnet_config_changed(struct virtio_device *vdev) static void virtnet_free_queues(struct virtnet_info *vi) { + int i; + + for (i = 0; i < vi->max_queue_pairs; i++) + netif_napi_del(&vi->rq[i].napi); + kfree(vi->rq); kfree(vi->sq); } @@ -1395,10 +1400,10 @@ static void free_unused_bufs(struct virtnet_info *vi) struct virtqueue *vq = vi->rq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) { - if (vi->big_packets) - give_pages(&vi->rq[i], buf); - else if (vi->mergeable_rx_bufs) + if (vi->mergeable_rx_bufs) put_page(virt_to_head_page(buf)); + else if (vi->big_packets) + give_pages(&vi->rq[i], buf); else dev_kfree_skb(buf); --vi->rq[i].num; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 64f0e0d..acf1392 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1149,49 +1149,72 @@ static int xenvif_set_skb_gso(struct xenvif *vif, return 0; } -static inline void maybe_pull_tail(struct sk_buff *skb, unsigned int len) +static inline int maybe_pull_tail(struct sk_buff *skb, unsigned int len, + unsigned int max) { - if (skb_is_nonlinear(skb) && skb_headlen(skb) < len) { - /* If we need to pullup then pullup to the max, so we - * won't need to do it again. - */ - int target = min_t(int, skb->len, MAX_TCP_HEADER); - __pskb_pull_tail(skb, target - skb_headlen(skb)); - } + if (skb_headlen(skb) >= len) + return 0; + + /* If we need to pullup then pullup to the max, so we + * won't need to do it again. + */ + if (max > skb->len) + max = skb->len; + + if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) + return -ENOMEM; + + if (skb_headlen(skb) < len) + return -EPROTO; + + return 0; } +/* This value should be large enough to cover a tagged ethernet header plus + * maximally sized IP and TCP or UDP headers. + */ +#define MAX_IP_HDR_LEN 128 + static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb, int recalculate_partial_csum) { - struct iphdr *iph = (void *)skb->data; - unsigned int header_size; unsigned int off; - int err = -EPROTO; + bool fragment; + int err; + + fragment = false; + + err = maybe_pull_tail(skb, + sizeof(struct iphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; - off = sizeof(struct iphdr); + if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) + fragment = true; - header_size = skb->network_header + off + MAX_IPOPTLEN; - maybe_pull_tail(skb, header_size); + off = ip_hdrlen(skb); - off = iph->ihl * 4; + err = -EPROTO; - switch (iph->protocol) { + switch (ip_hdr(skb)->protocol) { case IPPROTO_TCP: if (!skb_partial_csum_set(skb, off, offsetof(struct tcphdr, check))) goto out; if (recalculate_partial_csum) { - struct tcphdr *tcph = tcp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct tcphdr); - maybe_pull_tail(skb, header_size); - - tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - off, - IPPROTO_TCP, 0); + err = maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + tcp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); } break; case IPPROTO_UDP: @@ -1200,24 +1223,20 @@ static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb, goto out; if (recalculate_partial_csum) { - struct udphdr *udph = udp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct udphdr); - maybe_pull_tail(skb, header_size); - - udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - off, - IPPROTO_UDP, 0); + err = maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + udp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); } break; default: - if (net_ratelimit()) - netdev_err(vif->dev, - "Attempting to checksum a non-TCP/UDP packet, " - "dropping a protocol %d packet\n", - iph->protocol); goto out; } @@ -1227,75 +1246,99 @@ out: return err; } +/* This value should be large enough to cover a tagged ethernet header plus + * an IPv6 header, all options, and a maximal TCP or UDP header. + */ +#define MAX_IPV6_HDR_LEN 256 + +#define OPT_HDR(type, skb, off) \ + (type *)(skb_network_header(skb) + (off)) + static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb, int recalculate_partial_csum) { - int err = -EPROTO; - struct ipv6hdr *ipv6h = (void *)skb->data; + int err; u8 nexthdr; - unsigned int header_size; unsigned int off; + unsigned int len; bool fragment; bool done; + fragment = false; done = false; off = sizeof(struct ipv6hdr); - header_size = skb->network_header + off; - maybe_pull_tail(skb, header_size); + err = maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; - nexthdr = ipv6h->nexthdr; + nexthdr = ipv6_hdr(skb)->nexthdr; - while ((off <= sizeof(struct ipv6hdr) + ntohs(ipv6h->payload_len)) && - !done) { + len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); + while (off <= len && !done) { switch (nexthdr) { case IPPROTO_DSTOPTS: case IPPROTO_HOPOPTS: case IPPROTO_ROUTING: { - struct ipv6_opt_hdr *hp = (void *)(skb->data + off); + struct ipv6_opt_hdr *hp; - header_size = skb->network_header + - off + - sizeof(struct ipv6_opt_hdr); - maybe_pull_tail(skb, header_size); + err = maybe_pull_tail(skb, + off + + sizeof(struct ipv6_opt_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); nexthdr = hp->nexthdr; off += ipv6_optlen(hp); break; } case IPPROTO_AH: { - struct ip_auth_hdr *hp = (void *)(skb->data + off); + struct ip_auth_hdr *hp; + + err = maybe_pull_tail(skb, + off + + sizeof(struct ip_auth_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ip_auth_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_authlen(hp); + break; + } + case IPPROTO_FRAGMENT: { + struct frag_hdr *hp; - header_size = skb->network_header + - off + - sizeof(struct ip_auth_hdr); - maybe_pull_tail(skb, header_size); + err = maybe_pull_tail(skb, + off + + sizeof(struct frag_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct frag_hdr, skb, off); + + if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) + fragment = true; nexthdr = hp->nexthdr; - off += (hp->hdrlen+2)<<2; + off += sizeof(struct frag_hdr); break; } - case IPPROTO_FRAGMENT: - fragment = true; - /* fall through */ default: done = true; break; } } - if (!done) { - if (net_ratelimit()) - netdev_err(vif->dev, "Failed to parse packet header\n"); - goto out; - } + err = -EPROTO; - if (fragment) { - if (net_ratelimit()) - netdev_err(vif->dev, "Packet is a fragment!\n"); + if (!done || fragment) goto out; - } switch (nexthdr) { case IPPROTO_TCP: @@ -1304,17 +1347,17 @@ static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb, goto out; if (recalculate_partial_csum) { - struct tcphdr *tcph = tcp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct tcphdr); - maybe_pull_tail(skb, header_size); - - tcph->check = ~csum_ipv6_magic(&ipv6h->saddr, - &ipv6h->daddr, - skb->len - off, - IPPROTO_TCP, 0); + err = maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + tcp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); } break; case IPPROTO_UDP: @@ -1323,25 +1366,20 @@ static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb, goto out; if (recalculate_partial_csum) { - struct udphdr *udph = udp_hdr(skb); - - header_size = skb->network_header + - off + - sizeof(struct udphdr); - maybe_pull_tail(skb, header_size); - - udph->check = ~csum_ipv6_magic(&ipv6h->saddr, - &ipv6h->daddr, - skb->len - off, - IPPROTO_UDP, 0); + err = maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + udp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); } break; default: - if (net_ratelimit()) - netdev_err(vif->dev, - "Attempting to checksum a non-TCP/UDP packet, " - "dropping a protocol %d packet\n", - nexthdr); goto out; } diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 5d89d1b..c56c350 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -4,6 +4,7 @@ #include <uapi/linux/ipv6.h> #define ipv6_optlen(p) (((p)->hdrlen+1) << 3) +#define ipv6_authlen(p) (((p)->hdrlen+2) << 2) /* * This structure contains configuration options per IPv6 link. */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index eb198ac..488316e 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -110,7 +110,8 @@ struct frag_hdr { __be32 identification; }; -#define IP6_MF 0x0001 +#define IP6_MF 0x0001 +#define IP6_OFFSET 0xFFF8 #include <net/sock.h> diff --git a/include/net/sock.h b/include/net/sock.h index e3a18ff..2ef3c3e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1035,7 +1035,6 @@ enum cg_proto_flags { }; struct cg_proto { - void (*enter_memory_pressure)(struct sock *sk); struct res_counter memory_allocated; /* Current allocated memory. */ struct percpu_counter sockets_allocated; /* Current number of sockets. */ int memory_pressure; @@ -1155,8 +1154,7 @@ static inline void sk_leave_memory_pressure(struct sock *sk) struct proto *prot = sk->sk_prot; for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - if (cg_proto->memory_pressure) - cg_proto->memory_pressure = 0; + cg_proto->memory_pressure = 0; } } @@ -1171,7 +1169,7 @@ static inline void sk_enter_memory_pressure(struct sock *sk) struct proto *prot = sk->sk_prot; for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto)) - cg_proto->enter_memory_pressure(sk); + cg_proto->memory_pressure = 1; } sk->sk_prot->enter_memory_pressure(sk); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 229d820..045d56e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -426,6 +426,16 @@ netdev_features_t br_features_recompute(struct net_bridge *br, int br_handle_frame_finish(struct sk_buff *skb); rx_handler_result_t br_handle_frame(struct sk_buff **pskb); +static inline bool br_rx_handler_check_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->rx_handler) == br_handle_frame; +} + +static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev) +{ + return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL; +} + /* br_ioctl.c */ int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 8660ea3..bdb459d 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -153,7 +153,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0) goto err; - p = br_port_get_rcu(dev); + p = br_port_get_check_rcu(dev); if (!p) goto err; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2718fed..06e72d3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3584,6 +3584,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; + skb->local_df = 0; skb_dst_drop(skb); skb->mark = 0; secpath_reset(skb); diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 269a89e..f7e522c 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -6,13 +6,6 @@ #include <linux/memcontrol.h> #include <linux/module.h> -static void memcg_tcp_enter_memory_pressure(struct sock *sk) -{ - if (sk->sk_cgrp->memory_pressure) - sk->sk_cgrp->memory_pressure = 1; -} -EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure); - int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { /* diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c235da9..e4171dd 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -237,6 +237,30 @@ struct packet_skb_cb { static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); +static struct net_device *packet_cached_dev_get(struct packet_sock *po) +{ + struct net_device *dev; + + rcu_read_lock(); + dev = rcu_dereference(po->cached_dev); + if (likely(dev)) + dev_hold(dev); + rcu_read_unlock(); + + return dev; +} + +static void packet_cached_dev_assign(struct packet_sock *po, + struct net_device *dev) +{ + rcu_assign_pointer(po->cached_dev, dev); +} + +static void packet_cached_dev_reset(struct packet_sock *po) +{ + RCU_INIT_POINTER(po->cached_dev, NULL); +} + /* register_prot_hook must be invoked with the po->bind_lock held, * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). @@ -246,12 +270,10 @@ static void register_prot_hook(struct sock *sk) struct packet_sock *po = pkt_sk(sk); if (!po->running) { - if (po->fanout) { + if (po->fanout) __fanout_link(sk, po); - } else { + else dev_add_pack(&po->prot_hook); - rcu_assign_pointer(po->cached_dev, po->prot_hook.dev); - } sock_hold(sk); po->running = 1; @@ -270,12 +292,11 @@ static void __unregister_prot_hook(struct sock *sk, bool sync) struct packet_sock *po = pkt_sk(sk); po->running = 0; - if (po->fanout) { + + if (po->fanout) __fanout_unlink(sk, po); - } else { + else __dev_remove_pack(&po->prot_hook); - RCU_INIT_POINTER(po->cached_dev, NULL); - } __sock_put(sk); @@ -2061,19 +2082,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, return tp_len; } -static struct net_device *packet_cached_dev_get(struct packet_sock *po) -{ - struct net_device *dev; - - rcu_read_lock(); - dev = rcu_dereference(po->cached_dev); - if (dev) - dev_hold(dev); - rcu_read_unlock(); - - return dev; -} - static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { struct sk_buff *skb; @@ -2090,7 +2098,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) mutex_lock(&po->pg_vec_lock); - if (saddr == NULL) { + if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = po->num; addr = NULL; @@ -2244,7 +2252,7 @@ static int packet_snd(struct socket *sock, * Get and verify the address. */ - if (saddr == NULL) { + if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = po->num; addr = NULL; @@ -2453,6 +2461,8 @@ static int packet_release(struct socket *sock) spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); + packet_cached_dev_reset(po); + if (po->prot_hook.dev) { dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -2508,14 +2518,17 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc spin_lock(&po->bind_lock); unregister_prot_hook(sk, true); + po->num = protocol; po->prot_hook.type = protocol; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); - po->prot_hook.dev = dev; + po->prot_hook.dev = dev; po->ifindex = dev ? dev->ifindex : 0; + packet_cached_dev_assign(po, dev); + if (protocol == 0) goto out_unlock; @@ -2628,7 +2641,8 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, po = pkt_sk(sk); sk->sk_family = PF_PACKET; po->num = proto; - RCU_INIT_POINTER(po->cached_dev, NULL); + + packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; sk_refcnt_debug_inc(sk); @@ -3339,6 +3353,7 @@ static int packet_notifier(struct notifier_block *this, sk->sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { + packet_cached_dev_reset(po); po->ifindex = -1; if (po->prot_hook.dev) dev_put(po->prot_hook.dev); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index fd70728..69cb848 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -270,6 +270,16 @@ int tcf_register_action(struct tc_action_ops *act) { struct tc_action_ops *a, **ap; + /* Must supply act, dump, cleanup and init */ + if (!act->act || !act->dump || !act->cleanup || !act->init) + return -EINVAL; + + /* Supply defaults */ + if (!act->lookup) + act->lookup = tcf_hash_search; + if (!act->walk) + act->walk = tcf_generic_walker; + write_lock(&act_mod_lock); for (ap = &act_base; (a = *ap) != NULL; ap = &a->next) { if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { @@ -381,7 +391,7 @@ int tcf_action_exec(struct sk_buff *skb, const struct tc_action *act, } while ((a = act) != NULL) { repeat: - if (a->ops && a->ops->act) { + if (a->ops) { ret = a->ops->act(skb, a, res); if (TC_MUNGED & skb->tc_verd) { /* copied already, allow trampling */ @@ -405,7 +415,7 @@ void tcf_action_destroy(struct tc_action *act, int bind) struct tc_action *a; for (a = act; a; a = act) { - if (a->ops && a->ops->cleanup) { + if (a->ops) { if (a->ops->cleanup(a, bind) == ACT_P_DELETED) module_put(a->ops->owner); act = act->next; @@ -424,7 +434,7 @@ tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { int err = -EINVAL; - if (a->ops == NULL || a->ops->dump == NULL) + if (a->ops == NULL) return err; return a->ops->dump(skb, a, bind, ref); } @@ -436,7 +446,7 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - if (a->ops == NULL || a->ops->dump == NULL) + if (a->ops == NULL) return err; if (nla_put_string(skb, TCA_KIND, a->ops->kind)) @@ -723,8 +733,6 @@ tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) a->ops = tc_lookup_action(tb[TCA_ACT_KIND]); if (a->ops == NULL) goto err_free; - if (a->ops->lookup == NULL) - goto err_mod; err = -ENOENT; if (a->ops->lookup(a, index) == 0) goto err_mod; @@ -1084,12 +1092,6 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) memset(&a, 0, sizeof(struct tc_action)); a.ops = a_o; - if (a_o->walk == NULL) { - WARN(1, "tc_dump_action: %s !capable of dumping table\n", - a_o->kind); - goto out_module_put; - } - nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*t), 0); if (!nlh) diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 3a4c0ca..5c5edf5 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -585,9 +585,7 @@ static struct tc_action_ops act_csum_ops = { .act = tcf_csum, .dump = tcf_csum_dump, .cleanup = tcf_csum_cleanup, - .lookup = tcf_hash_search, .init = tcf_csum_init, - .walk = tcf_generic_walker }; MODULE_DESCRIPTION("Checksum updating actions"); diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index fd2b3cf..5645a4d 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -206,9 +206,7 @@ static struct tc_action_ops act_gact_ops = { .act = tcf_gact, .dump = tcf_gact_dump, .cleanup = tcf_gact_cleanup, - .lookup = tcf_hash_search, .init = tcf_gact_init, - .walk = tcf_generic_walker }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 60d88b6..882a897 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -298,9 +298,7 @@ static struct tc_action_ops act_ipt_ops = { .act = tcf_ipt, .dump = tcf_ipt_dump, .cleanup = tcf_ipt_cleanup, - .lookup = tcf_hash_search, .init = tcf_ipt_init, - .walk = tcf_generic_walker }; static struct tc_action_ops act_xt_ops = { @@ -312,9 +310,7 @@ static struct tc_action_ops act_xt_ops = { .act = tcf_ipt, .dump = tcf_ipt_dump, .cleanup = tcf_ipt_cleanup, - .lookup = tcf_hash_search, .init = tcf_ipt_init, - .walk = tcf_generic_walker }; MODULE_AUTHOR("Jamal Hadi Salim(2002-13)"); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 977c10e..2523781 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -271,9 +271,7 @@ static struct tc_action_ops act_mirred_ops = { .act = tcf_mirred, .dump = tcf_mirred_dump, .cleanup = tcf_mirred_cleanup, - .lookup = tcf_hash_search, .init = tcf_mirred_init, - .walk = tcf_generic_walker }; MODULE_AUTHOR("Jamal Hadi Salim(2002)"); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 876f0ef..6a15ace 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -308,9 +308,7 @@ static struct tc_action_ops act_nat_ops = { .act = tcf_nat, .dump = tcf_nat_dump, .cleanup = tcf_nat_cleanup, - .lookup = tcf_hash_search, .init = tcf_nat_init, - .walk = tcf_generic_walker }; MODULE_DESCRIPTION("Stateless NAT actions"); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 7ed78c9..03b6767 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -243,9 +243,7 @@ static struct tc_action_ops act_pedit_ops = { .act = tcf_pedit, .dump = tcf_pedit_dump, .cleanup = tcf_pedit_cleanup, - .lookup = tcf_hash_search, .init = tcf_pedit_init, - .walk = tcf_generic_walker }; MODULE_AUTHOR("Jamal Hadi Salim(2002-4)"); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 272d8e9..16a62c3 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -407,7 +407,6 @@ static struct tc_action_ops act_police_ops = { .act = tcf_act_police, .dump = tcf_act_police_dump, .cleanup = tcf_act_police_cleanup, - .lookup = tcf_hash_search, .init = tcf_act_police_locate, .walk = tcf_act_police_walker }; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 7725eb4..31157d3 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -201,7 +201,6 @@ static struct tc_action_ops act_simp_ops = { .dump = tcf_simp_dump, .cleanup = tcf_simp_cleanup, .init = tcf_simp_init, - .walk = tcf_generic_walker, }; MODULE_AUTHOR("Jamal Hadi Salim(2005)"); diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 9119b73..cf20add 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -202,7 +202,6 @@ static struct tc_action_ops act_skbedit_ops = { .dump = tcf_skbedit_dump, .cleanup = tcf_skbedit_cleanup, .init = tcf_skbedit_init, - .walk = tcf_generic_walker, }; MODULE_AUTHOR("Alexander Duyck, <alexander.h.duyck@intel.com>"); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 1d4f3ac..d0810dc 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -572,7 +572,7 @@ void sctp_transport_burst_limited(struct sctp_transport *t) u32 old_cwnd = t->cwnd; u32 max_burst_bytes; - if (t->burst_limited) + if (t->burst_limited || asoc->max_burst == 0) return; max_burst_bytes = t->flight_size + (asoc->max_burst * asoc->pathmtu); |