[linux-next] LinuxNextTracking branch, master, updated. next-20130423

The following commit has been merged in the master branch: commit 6e0895c2ea326cc4bb11e8fa2f654628d5754c31 Merge: 55fbbe46e9eb3cbe6c335503f5550855a1128dce 60d509fa6a9c4653a86ad830e4c4b30360b23f0e Author: David S. Miller davem@davemloft.net Date: Mon Apr 22 20:32:51 2013 -0400

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts: drivers/net/ethernet/emulex/benet/be_main.c drivers/net/ethernet/intel/igb/igb_main.c drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c include/net/scm.h net/batman-adv/routing.c net/ipv4/tcp_input.c

The e{uid,gid} --> {uid,gid} credentials fix conflicted with the cleanup in net-next to now pass cred structs around.

The be2net driver had a bug fix in 'net' that overlapped with the VLAN interface changes by Patrick McHardy in net-next.

An IGB conflict existed because in 'net' the build_skb() support was reverted, and in 'net-next' there was a comment style fix within that code.

Several batman-adv conflicts were resolved by making sure that all calls to batadv_is_my_mac() are changed to have a new bat_priv first argument.

Eric Dumazet's TS ECR fix in TCP in 'net' conflicted with the F-RTO rewrite in 'net-next', mostly overlapping changes.

Thanks to Stephen Rothwell and Antonio Quartulli for help with several of these merge resolutions.

Signed-off-by: David S. Miller davem@davemloft.net

diff --combined MAINTAINERS index c39bdc3,8bdd7a7..1ee5d11 --- a/MAINTAINERS +++ b/MAINTAINERS @@@ -1764,7 -1764,7 +1764,7 @@@ F: arch/arm/configs/bcm2835_defconfi F: drivers/*/*bcm2835*

BROADCOM TG3 GIGABIT ETHERNET DRIVER -M: Matt Carlson mcarlson@broadcom.com +M: Nithin Nayak Sujir nsujir@broadcom.com M: Michael Chan mchan@broadcom.com L: netdev@vger.kernel.org S: Supported @@@ -4941,6 -4941,12 +4941,12 @@@ W: logfs.or S: Maintained F: fs/logfs/

+ LPC32XX MACHINE SUPPORT + M: Roland Stigge stigge@antcom.de + L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) + S: Maintained + F: arch/arm/mach-lpc32xx/ + LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI) M: Nagalakshmi Nandigama Nagalakshmi.Nandigama@lsi.com M: Sreekanth Reddy Sreekanth.Reddy@lsi.com @@@ -6330,7 -6336,6 +6336,7 @@@ F: drivers/acpi/apei/erst.

PTP HARDWARE CLOCK SUPPORT M: Richard Cochran richardcochran@gmail.com +L: netdev@vger.kernel.org S: Maintained W: http://linuxptp.sourceforge.net/ F: Documentation/ABI/testing/sysfs-ptp @@@ -6462,7 -6467,6 +6468,7 @@@ S: Supporte F: drivers/net/ethernet/qlogic/qlcnic/

QLOGIC QLGE 10Gb ETHERNET DRIVER +M: Shahed Shaikh shahed.shaikh@qlogic.com M: Jitendra Kalsaria jitendra.kalsaria@qlogic.com M: Ron Mercer ron.mercer@qlogic.com M: linux-driver@qlogic.com @@@ -6627,7 -6631,7 +6633,7 @@@ S: Supporte F: fs/reiserfs/

REGISTER MAP ABSTRACTION - M: Mark Brown broonie@opensource.wolfsonmicro.com + M: Mark Brown broonie@kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regmap.git S: Supported F: drivers/base/regmap/ @@@ -7375,7 -7379,7 +7381,7 @@@ F: sound

SOUND - SOC LAYER / DYNAMIC AUDIO POWER MANAGEMENT (ASoC) M: Liam Girdwood lgirdwood@gmail.com - M: Mark Brown broonie@opensource.wolfsonmicro.com + M: Mark Brown broonie@kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git L: alsa-devel@alsa-project.org (moderated for non-subscribers) W: http://alsa-project.org/main/index.php/ASoC @@@ -7464,7 -7468,7 +7470,7 @@@ F: drivers/clk/spear

SPI SUBSYSTEM M: Grant Likely grant.likely@secretlab.ca - M: Mark Brown broonie@opensource.wolfsonmicro.com + M: Mark Brown broonie@kernel.org L: spi-devel-general@lists.sourceforge.net Q: http://patchwork.kernel.org/project/spi-devel-general/list/ T: git git://git.secretlab.ca/git/linux-2.6.git @@@ -8516,7 -8520,7 +8522,7 @@@ F: drivers/usb/gadget/*uvc*. F: drivers/usb/gadget/webcam.c

USB WIRELESS RNDIS DRIVER (rndis_wlan) -M: Jussi Kivilinna jussi.kivilinna@mbnet.fi +M: Jussi Kivilinna jussi.kivilinna@iki.fi L: linux-wireless@vger.kernel.org S: Maintained F: drivers/net/wireless/rndis_wlan.c @@@ -8709,7 -8713,7 +8715,7 @@@ F: drivers/scsi/vmw_pvscsi.

VOLTAGE AND CURRENT REGULATOR FRAMEWORK M: Liam Girdwood lrg@ti.com - M: Mark Brown broonie@opensource.wolfsonmicro.com + M: Mark Brown broonie@kernel.org W: http://opensource.wolfsonmicro.com/node/15 W: http://www.slimlogic.co.uk/?p=48 T: git git://git.kernel.org/pub/scm/linux/kernel/git/lrg/regulator.git diff --combined drivers/net/bonding/bond_main.c index 5e22126,dbbea0e..532153d --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@@ -428,15 -428,14 +428,15 @@@ int bond_dev_queue_xmit(struct bonding * @bond_dev: bonding net device that got called * @vid: vlan id being added */ -static int bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid) +static int bond_vlan_rx_add_vid(struct net_device *bond_dev, + __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave, *stop_at; int i, res;

bond_for_each_slave(bond, slave, i) { - res = vlan_vid_add(slave->dev, vid); + res = vlan_vid_add(slave->dev, proto, vid); if (res) goto unwind; } @@@ -454,7 -453,7 +454,7 @@@ unwind /* unwind from head to the slave that failed */ stop_at = slave; bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) - vlan_vid_del(slave->dev, vid); + vlan_vid_del(slave->dev, proto, vid);

return res; } @@@ -464,15 -463,14 +464,15 @@@ * @bond_dev: bonding net device that got called * @vid: vlan id being removed */ -static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid) +static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, + __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; int i, res;

bond_for_each_slave(bond, slave, i) - vlan_vid_del(slave->dev, vid); + vlan_vid_del(slave->dev, proto, vid);

res = bond_del_vlan(bond, vid); if (res) { @@@ -490,8 -488,7 +490,8 @@@ static void bond_add_vlans_on_slave(str int res;

list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - res = vlan_vid_add(slave_dev, vlan->vlan_id); + res = vlan_vid_add(slave_dev, htons(ETH_P_8021Q), + vlan->vlan_id); if (res) pr_warning("%s: Failed to add vlan id %d to device %s\n", bond->dev->name, vlan->vlan_id, @@@ -507,7 -504,7 +507,7 @@@ static void bond_del_vlans_from_slave(s list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { if (!vlan->vlan_id) continue; - vlan_vid_del(slave_dev, vlan->vlan_id); + vlan_vid_del(slave_dev, htons(ETH_P_8021Q), vlan->vlan_id); } }

@@@ -782,7 -779,7 +782,7 @@@ static void bond_resend_igmp_join_reque

/* rejoin all groups on vlan devices */ list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - vlan_dev = __vlan_find_dev_deep(bond_dev, + vlan_dev = __vlan_find_dev_deep(bond_dev, htons(ETH_P_8021Q), vlan->vlan_id); if (vlan_dev) __bond_resend_igmp_join_requests(vlan_dev); @@@ -799,8 -796,9 +799,8 @@@ static void bond_resend_igmp_join_reque { struct bonding *bond = container_of(work, struct bonding, mcast_work.work); - rcu_read_lock(); + bond_resend_igmp_join_requests(bond); - rcu_read_unlock(); }

/* @@@ -848,8 -846,10 +848,10 @@@ static void bond_mc_swap(struct bondin if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(old_active->dev, -1);

+ netif_addr_lock_bh(bond->dev); netdev_for_each_mc_addr(ha, bond->dev) dev_mc_del(old_active->dev, ha->addr); + netif_addr_unlock_bh(bond->dev); }

if (new_active) { @@@ -860,8 -860,10 +862,10 @@@ if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(new_active->dev, 1);

+ netif_addr_lock_bh(bond->dev); netdev_for_each_mc_addr(ha, bond->dev) dev_mc_add(new_active->dev, ha->addr); + netif_addr_unlock_bh(bond->dev); } }

@@@ -1903,11 -1905,29 +1907,29 @@@ err_dest_symlinks bond_destroy_slave_symlinks(bond_dev, slave_dev);

err_detach: + if (!USES_PRIMARY(bond->params.mode)) { + netif_addr_lock_bh(bond_dev); + bond_mc_list_flush(bond_dev, slave_dev); + netif_addr_unlock_bh(bond_dev); + } + bond_del_vlans_from_slave(bond, slave_dev); write_lock_bh(&bond->lock); bond_detach_slave(bond, new_slave); + if (bond->primary_slave == new_slave) + bond->primary_slave = NULL; write_unlock_bh(&bond->lock); + if (bond->curr_active_slave == new_slave) { + read_lock(&bond->lock); + write_lock_bh(&bond->curr_slave_lock); + bond_change_active_slave(bond, NULL); + bond_select_active_slave(bond); + write_unlock_bh(&bond->curr_slave_lock); + read_unlock(&bond->lock); + } + slave_disable_netpoll(new_slave);

err_close: + slave_dev->priv_flags &= ~IFF_BONDING; dev_close(slave_dev);

err_unset_master: @@@ -2512,8 -2532,7 +2534,8 @@@ static int bond_has_this_ip(struct bond

list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { rcu_read_lock(); - vlan_dev = __vlan_find_dev_deep(bond->dev, vlan->vlan_id); + vlan_dev = __vlan_find_dev_deep(bond->dev, htons(ETH_P_8021Q), + vlan->vlan_id); rcu_read_unlock(); if (vlan_dev && ip == bond_confirm_addr(vlan_dev, 0, ip)) return 1; @@@ -2542,7 -2561,7 +2564,7 @@@ static void bond_arp_send(struct net_de return; } if (vlan_id) { - skb = vlan_put_tag(skb, vlan_id); + skb = vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_id); if (!skb) { pr_err("failed to insert VLAN tag\n"); return; @@@ -2604,7 -2623,6 +2626,7 @@@ static void bond_arp_send_all(struct bo list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { rcu_read_lock(); vlan_dev = __vlan_find_dev_deep(bond->dev, + htons(ETH_P_8021Q), vlan->vlan_id); rcu_read_unlock(); if (vlan_dev == rt->dst.dev) { @@@ -3172,11 -3190,20 +3194,20 @@@ static int bond_slave_netdev_event(unsi struct net_device *slave_dev) { struct slave *slave = bond_slave_get_rtnl(slave_dev); - struct bonding *bond = slave->bond; - struct net_device *bond_dev = slave->bond->dev; + struct bonding *bond; + struct net_device *bond_dev; u32 old_speed; u8 old_duplex;

+ /* A netdev event can be generated while enslaving a device + * before netdev_rx_handler_register is called in which case + * slave will be NULL + */ + if (!slave) + return NOTIFY_DONE; + bond_dev = slave->bond->dev; + bond = slave->bond; + switch (event) { case NETDEV_UNREGISTER: if (bond->setup_by_slave) @@@ -3290,20 -3317,22 +3321,22 @@@ static int bond_xmit_hash_policy_l2(str */ static int bond_xmit_hash_policy_l23(struct sk_buff *skb, int count) { - struct ethhdr *data = (struct ethhdr *)skb->data; - struct iphdr *iph; - struct ipv6hdr *ipv6h; + const struct ethhdr *data; + const struct iphdr *iph; + const struct ipv6hdr *ipv6h; u32 v6hash; - __be32 *s, *d; + const __be32 *s, *d;

if (skb->protocol == htons(ETH_P_IP) && - skb_network_header_len(skb) >= sizeof(*iph)) { + pskb_network_may_pull(skb, sizeof(*iph))) { iph = ip_hdr(skb); + data = (struct ethhdr *)skb->data; return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^ (data->h_dest[5] ^ data->h_source[5])) % count; } else if (skb->protocol == htons(ETH_P_IPV6) && - skb_network_header_len(skb) >= sizeof(*ipv6h)) { + pskb_network_may_pull(skb, sizeof(*ipv6h))) { ipv6h = ipv6_hdr(skb); + data = (struct ethhdr *)skb->data; s = &ipv6h->saddr.s6_addr32[0]; d = &ipv6h->daddr.s6_addr32[0]; v6hash = (s[1] ^ d[1]) ^ (s[2] ^ d[2]) ^ (s[3] ^ d[3]); @@@ -3322,33 -3351,36 +3355,36 @@@ static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count) { u32 layer4_xor = 0; - struct iphdr *iph; - struct ipv6hdr *ipv6h; - __be32 *s, *d; - __be16 *layer4hdr; + const struct iphdr *iph; + const struct ipv6hdr *ipv6h; + const __be32 *s, *d; + const __be16 *l4 = NULL; + __be16 _l4[2]; + int noff = skb_network_offset(skb); + int poff;

if (skb->protocol == htons(ETH_P_IP) && - skb_network_header_len(skb) >= sizeof(*iph)) { + pskb_may_pull(skb, noff + sizeof(*iph))) { iph = ip_hdr(skb); - if (!ip_is_fragment(iph) && - (iph->protocol == IPPROTO_TCP || - iph->protocol == IPPROTO_UDP) && - (skb_headlen(skb) - skb_network_offset(skb) >= - iph->ihl * sizeof(u32) + sizeof(*layer4hdr) * 2)) { - layer4hdr = (__be16 *)((u32 *)iph + iph->ihl); - layer4_xor = ntohs(*layer4hdr ^ *(layer4hdr + 1)); + poff = proto_ports_offset(iph->protocol); + + if (!ip_is_fragment(iph) && poff >= 0) { + l4 = skb_header_pointer(skb, noff + (iph->ihl << 2) + poff, + sizeof(_l4), &_l4); + if (l4) + layer4_xor = ntohs(l4[0] ^ l4[1]); } return (layer4_xor ^ ((ntohl(iph->saddr ^ iph->daddr)) & 0xffff)) % count; } else if (skb->protocol == htons(ETH_P_IPV6) && - skb_network_header_len(skb) >= sizeof(*ipv6h)) { + pskb_may_pull(skb, noff + sizeof(*ipv6h))) { ipv6h = ipv6_hdr(skb); - if ((ipv6h->nexthdr == IPPROTO_TCP || - ipv6h->nexthdr == IPPROTO_UDP) && - (skb_headlen(skb) - skb_network_offset(skb) >= - sizeof(*ipv6h) + sizeof(*layer4hdr) * 2)) { - layer4hdr = (__be16 *)(ipv6h + 1); - layer4_xor = ntohs(*layer4hdr ^ *(layer4hdr + 1)); + poff = proto_ports_offset(ipv6h->nexthdr); + if (poff >= 0) { + l4 = skb_header_pointer(skb, noff + sizeof(*ipv6h) + poff, + sizeof(_l4), &_l4); + if (l4) + layer4_xor = ntohs(l4[0] ^ l4[1]); } s = &ipv6h->saddr.s6_addr32[0]; d = &ipv6h->daddr.s6_addr32[0]; @@@ -4226,37 -4258,6 +4262,37 @@@ void bond_set_mode_ops(struct bonding * } }

+static int bond_ethtool_get_settings(struct net_device *bond_dev, + struct ethtool_cmd *ecmd) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; + int i; + unsigned long speed = 0; + + ecmd->duplex = DUPLEX_UNKNOWN; + ecmd->port = PORT_OTHER; + + /* Since SLAVE_IS_OK returns false for all inactive or down slaves, we + * do not need to check mode. Though link speed might not represent + * the true receive or transmit bandwidth (not all modes are symmetric) + * this is an accurate maximum. + */ + read_lock(&bond->lock); + bond_for_each_slave(bond, slave, i) { + if (SLAVE_IS_OK(slave)) { + if (slave->speed != SPEED_UNKNOWN) + speed += slave->speed; + if (ecmd->duplex == DUPLEX_UNKNOWN && + slave->duplex != DUPLEX_UNKNOWN) + ecmd->duplex = slave->duplex; + } + } + ethtool_cmd_speed_set(ecmd, speed ? : SPEED_UNKNOWN); + read_unlock(&bond->lock); + return 0; +} + static void bond_ethtool_get_drvinfo(struct net_device *bond_dev, struct ethtool_drvinfo *drvinfo) { @@@ -4268,7 -4269,6 +4304,7 @@@

static const struct ethtool_ops bond_ethtool_ops = { .get_drvinfo = bond_ethtool_get_drvinfo, + .get_settings = bond_ethtool_get_settings, .get_link = ethtool_op_get_link, };

@@@ -4359,9 -4359,9 +4395,9 @@@ static void bond_setup(struct net_devic */

bond_dev->hw_features = BOND_VLAN_FEATURES | - NETIF_F_HW_VLAN_TX | - NETIF_F_HW_VLAN_RX | - NETIF_F_HW_VLAN_FILTER; + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER;

bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_HW_CSUM); bond_dev->features |= bond_dev->hw_features; @@@ -4882,9 -4882,18 +4918,18 @@@ static int __net_init bond_net_init(str static void __net_exit bond_net_exit(struct net *net) { struct bond_net *bn = net_generic(net, bond_net_id); + struct bonding *bond, *tmp_bond; + LIST_HEAD(list);

bond_destroy_sysfs(bn); bond_destroy_proc_dir(bn); + + /* Kill off any bonds created after unregistering bond rtnl ops */ + rtnl_lock(); + list_for_each_entry_safe(bond, tmp_bond, &bn->dev_list, bond_list) + unregister_netdevice_queue(bond->dev, &list); + unregister_netdevice_many(&list); + rtnl_unlock(); }

static struct pernet_operations bond_net_ops = { @@@ -4938,8 -4947,8 +4983,8 @@@ static void __exit bonding_exit(void

bond_destroy_debugfs();

- unregister_pernet_subsys(&bond_net_ops); rtnl_link_unregister(&bond_link_ops); + unregister_pernet_subsys(&bond_net_ops);

#ifdef CONFIG_NET_POLL_CONTROLLER /* diff --combined drivers/net/can/mcp251x.c index 55033dd5,9aa0c64..8cda23b --- a/drivers/net/can/mcp251x.c +++ b/drivers/net/can/mcp251x.c @@@ -269,7 -269,7 +269,7 @@@ struct mcp251x_priv #define MCP251X_IS(_model) \ static inline int mcp251x_is_##_model(struct spi_device *spi) \ { \ - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); \ + struct mcp251x_priv *priv = spi_get_drvdata(spi); \ return priv->model == CAN_MCP251X_MCP##_model; \ }

@@@ -305,7 -305,7 +305,7 @@@ static void mcp251x_clean(struct net_de */ static int mcp251x_spi_trans(struct spi_device *spi, int len) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi); struct spi_transfer t = { .tx_buf = priv->spi_tx_buf, .rx_buf = priv->spi_rx_buf, @@@ -333,7 -333,7 +333,7 @@@

static u8 mcp251x_read_reg(struct spi_device *spi, uint8_t reg) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi); u8 val = 0;

priv->spi_tx_buf[0] = INSTRUCTION_READ; @@@ -348,7 -348,7 +348,7 @@@ static void mcp251x_read_2regs(struct spi_device *spi, uint8_t reg, uint8_t *v1, uint8_t *v2) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi);

priv->spi_tx_buf[0] = INSTRUCTION_READ; priv->spi_tx_buf[1] = reg; @@@ -361,7 -361,7 +361,7 @@@

static void mcp251x_write_reg(struct spi_device *spi, u8 reg, uint8_t val) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi);

priv->spi_tx_buf[0] = INSTRUCTION_WRITE; priv->spi_tx_buf[1] = reg; @@@ -373,7 -373,7 +373,7 @@@ static void mcp251x_write_bits(struct spi_device *spi, u8 reg, u8 mask, uint8_t val) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi);

priv->spi_tx_buf[0] = INSTRUCTION_BIT_MODIFY; priv->spi_tx_buf[1] = reg; @@@ -386,7 -386,7 +386,7 @@@ static void mcp251x_hw_tx_frame(struct spi_device *spi, u8 *buf, int len, int tx_buf_idx) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi);

if (mcp251x_is_2510(spi)) { int i; @@@ -403,7 -403,7 +403,7 @@@ static void mcp251x_hw_tx(struct spi_device *spi, struct can_frame *frame, int tx_buf_idx) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi); u32 sid, eid, exide, rtr; u8 buf[SPI_TRANSFER_BUF_LEN];

@@@ -434,7 -434,7 +434,7 @@@ static void mcp251x_hw_rx_frame(struct spi_device *spi, u8 *buf, int buf_idx) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi);

if (mcp251x_is_2510(spi)) { int i, len; @@@ -454,7 -454,7 +454,7 @@@

static void mcp251x_hw_rx(struct spi_device *spi, int buf_idx) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi); struct sk_buff *skb; struct can_frame *frame; u8 buf[SPI_TRANSFER_BUF_LEN]; @@@ -550,7 -550,7 +550,7 @@@ static int mcp251x_do_set_mode(struct n

static int mcp251x_set_normal_mode(struct spi_device *spi) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi); unsigned long timeout;

/* Enable interrupts */ @@@ -620,7 -620,7 +620,7 @@@ static int mcp251x_setup(struct net_dev

static int mcp251x_hw_reset(struct spi_device *spi) { - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi); int ret; unsigned long timeout;

@@@ -929,6 -929,7 +929,7 @@@ static int mcp251x_open(struct net_devi struct mcp251x_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; struct mcp251x_platform_data *pdata = spi->dev.platform_data; + unsigned long flags; int ret;

ret = open_candev(net); @@@ -945,9 -946,14 +946,14 @@@ priv->tx_skb = NULL; priv->tx_len = 0;

+ flags = IRQF_ONESHOT; + if (pdata->irq_flags) + flags |= pdata->irq_flags; + else + flags |= IRQF_TRIGGER_FALLING; + ret = request_threaded_irq(spi->irq, NULL, mcp251x_can_ist, - pdata->irq_flags ? pdata->irq_flags : IRQF_TRIGGER_FALLING, - DEVICE_NAME, priv); + flags, DEVICE_NAME, priv); if (ret) { dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq); if (pdata->transceiver_enable) @@@ -1020,7 -1026,7 +1026,7 @@@ static int mcp251x_can_probe(struct spi CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY; priv->model = spi_get_device_id(spi)->driver_data; priv->net = net; - dev_set_drvdata(&spi->dev, priv); + spi_set_drvdata(spi, priv);

priv->spi = spi; mutex_init(&priv->mcp_lock); @@@ -1118,7 -1124,7 +1124,7 @@@ error_out static int mcp251x_can_remove(struct spi_device *spi) { struct mcp251x_platform_data *pdata = spi->dev.platform_data; - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi); struct net_device *net = priv->net;

unregister_candev(net); @@@ -1138,13 -1144,11 +1144,13 @@@ return 0; }

-#ifdef CONFIG_PM -static int mcp251x_can_suspend(struct spi_device *spi, pm_message_t state) +#ifdef CONFIG_PM_SLEEP + +static int mcp251x_can_suspend(struct device *dev) { + struct spi_device *spi = to_spi_device(dev); struct mcp251x_platform_data *pdata = spi->dev.platform_data; - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi); struct net_device *net = priv->net;

priv->force_quit = 1; @@@ -1172,11 -1176,10 +1178,11 @@@ return 0; }

-static int mcp251x_can_resume(struct spi_device *spi) +static int mcp251x_can_resume(struct device *dev) { + struct spi_device *spi = to_spi_device(dev); struct mcp251x_platform_data *pdata = spi->dev.platform_data; - struct mcp251x_priv *priv = dev_get_drvdata(&spi->dev); + struct mcp251x_priv *priv = spi_get_drvdata(spi);

if (priv->after_suspend & AFTER_SUSPEND_POWER) { pdata->power_enable(1); @@@ -1194,11 -1197,11 +1200,11 @@@ enable_irq(spi->irq); return 0; } -#else -#define mcp251x_can_suspend NULL -#define mcp251x_can_resume NULL #endif

+static SIMPLE_DEV_PM_OPS(mcp251x_can_pm_ops, mcp251x_can_suspend, + mcp251x_can_resume); + static const struct spi_device_id mcp251x_id_table[] = { { "mcp2510", CAN_MCP251X_MCP2510 }, { "mcp2515", CAN_MCP251X_MCP2515 }, @@@ -1210,15 -1213,29 +1216,15 @@@ MODULE_DEVICE_TABLE(spi, mcp251x_id_tab static struct spi_driver mcp251x_can_driver = { .driver = { .name = DEVICE_NAME, - .bus = &spi_bus_type, .owner = THIS_MODULE, + .pm = &mcp251x_can_pm_ops, },

.id_table = mcp251x_id_table, .probe = mcp251x_can_probe, .remove = mcp251x_can_remove, - .suspend = mcp251x_can_suspend, - .resume = mcp251x_can_resume, }; - -static int __init mcp251x_can_init(void) -{ - return spi_register_driver(&mcp251x_can_driver); -} - -static void __exit mcp251x_can_exit(void) -{ - spi_unregister_driver(&mcp251x_can_driver); -} - -module_init(mcp251x_can_init); -module_exit(mcp251x_can_exit); +module_spi_driver(mcp251x_can_driver);

MODULE_AUTHOR("Chris Elston celston@katalix.com, " "Christian Pellegrin chripell@evolware.org"); diff --combined drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 6b50443,57619dd..d72bd8c --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@@ -451,8 -451,7 +451,8 @@@ static void bnx2x_tpa_start(struct bnx2 * Compute number of aggregated segments, and gso_type. */ static void bnx2x_set_gro_params(struct sk_buff *skb, u16 parsing_flags, - u16 len_on_bd, unsigned int pkt_len) + u16 len_on_bd, unsigned int pkt_len, + u16 num_of_coalesced_segs) { /* TPA aggregation won't have either IP options or TCP options * other than timestamp or IPv6 extension headers. @@@ -481,7 -480,8 +481,7 @@@ /* tcp_gro_complete() will copy NAPI_GRO_CB(skb)->count * to skb_shinfo(skb)->gso_segs */ - NAPI_GRO_CB(skb)->count = DIV_ROUND_UP(pkt_len - hdrs_len, - skb_shinfo(skb)->gso_size); + NAPI_GRO_CB(skb)->count = num_of_coalesced_segs; }

static int bnx2x_alloc_rx_sge(struct bnx2x *bp, @@@ -537,8 -537,7 +537,8 @@@ static int bnx2x_fill_frag_skb(struct b /* This is needed in order to enable forwarding support */ if (frag_size) bnx2x_set_gro_params(skb, tpa_info->parsing_flags, len_on_bd, - le16_to_cpu(cqe->pkt_len)); + le16_to_cpu(cqe->pkt_len), + le16_to_cpu(cqe->num_of_coalesced_segs));

#ifdef BNX2X_STOP_ON_ERROR if (pages > min_t(u32, 8, MAX_SKB_FRAGS) * SGE_PAGES) { @@@ -719,7 -718,7 +719,7 @@@ static void bnx2x_tpa_stop(struct bnx2 if (!bnx2x_fill_frag_skb(bp, fp, tpa_info, pages, skb, cqe, cqe_idx)) { if (tpa_info->parsing_flags & PARSING_FLAGS_VLAN) - __vlan_hwaccel_put_tag(skb, tpa_info->vlan_tag); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tpa_info->vlan_tag); bnx2x_gro_receive(bp, fp, skb); } else { DP(NETIF_MSG_RX_STATUS, @@@ -994,7 -993,7 +994,7 @@@ reuse_rx

if (le16_to_cpu(cqe_fp->pars_flags.flags) & PARSING_FLAGS_VLAN) - __vlan_hwaccel_put_tag(skb, + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), le16_to_cpu(cqe_fp->vlan_tag)); napi_gro_receive(&fp->napi, skb);

@@@ -2010,7 -2009,7 +2010,7 @@@ static int bnx2x_init_hw(struct bnx2x * * Cleans the object that have internal lists without sending * ramrods. Should be run when interrutps are disabled. */ -static void bnx2x_squeeze_objects(struct bnx2x *bp) +void bnx2x_squeeze_objects(struct bnx2x *bp) { int rc; unsigned long ramrod_flags = 0, vlan_mac_flags = 0; @@@ -2615,6 -2614,9 +2615,9 @@@ int bnx2x_nic_load(struct bnx2x *bp, in } }

+ /* initialize FW coalescing state machines in RAM */ + bnx2x_update_coalesce(bp); + /* setup the leading queue */ rc = bnx2x_setup_leading(bp); if (rc) { @@@ -2775,7 -2777,7 +2778,7 @@@ load_error0 #endif /* ! BNX2X_STOP_ON_ERROR */ }

-static int bnx2x_drain_tx_queues(struct bnx2x *bp) +int bnx2x_drain_tx_queues(struct bnx2x *bp) { u8 rc = 0, cos, i;

@@@ -3087,11 -3089,11 +3090,11 @@@ int bnx2x_poll(struct napi_struct *napi * to ease the pain of our fellow microcode engineers * we use one mapping for both BDs */ -static noinline u16 bnx2x_tx_split(struct bnx2x *bp, - struct bnx2x_fp_txdata *txdata, - struct sw_tx_bd *tx_buf, - struct eth_tx_start_bd **tx_bd, u16 hlen, - u16 bd_prod, int nbd) +static u16 bnx2x_tx_split(struct bnx2x *bp, + struct bnx2x_fp_txdata *txdata, + struct sw_tx_bd *tx_buf, + struct eth_tx_start_bd **tx_bd, u16 hlen, + u16 bd_prod) { struct eth_tx_start_bd *h_tx_bd = *tx_bd; struct eth_tx_bd *d_tx_bd; @@@ -3099,10 -3101,11 +3102,10 @@@ int old_len = le16_to_cpu(h_tx_bd->nbytes);

/* first fix first BD */ - h_tx_bd->nbd = cpu_to_le16(nbd); h_tx_bd->nbytes = cpu_to_le16(hlen);

- DP(NETIF_MSG_TX_QUEUED, "TSO split header size is %d (%x:%x) nbd %d\n", - h_tx_bd->nbytes, h_tx_bd->addr_hi, h_tx_bd->addr_lo, h_tx_bd->nbd); + DP(NETIF_MSG_TX_QUEUED, "TSO split header size is %d (%x:%x)\n", + h_tx_bd->nbytes, h_tx_bd->addr_hi, h_tx_bd->addr_lo);

/* now get a new data BD * (after the pbd) and fill it */ @@@ -3131,7 -3134,7 +3134,7 @@@

#define bswab32(b32) ((__force __le32) swab32((__force __u32) (b32))) #define bswab16(b16) ((__force __le16) swab16((__force __u16) (b16))) -static inline __le16 bnx2x_csum_fix(unsigned char *t_header, u16 csum, s8 fix) +static __le16 bnx2x_csum_fix(unsigned char *t_header, u16 csum, s8 fix) { __sum16 tsum = (__force __sum16) csum;

@@@ -3146,47 -3149,30 +3149,47 @@@ return bswab16(tsum); }

-static inline u32 bnx2x_xmit_type(struct bnx2x *bp, struct sk_buff *skb) +static u32 bnx2x_xmit_type(struct bnx2x *bp, struct sk_buff *skb) { u32 rc; + __u8 prot = 0; + __be16 protocol;

if (skb->ip_summed != CHECKSUM_PARTIAL) - rc = XMIT_PLAIN; + return XMIT_PLAIN;

- else { - if (vlan_get_protocol(skb) == htons(ETH_P_IPV6)) { - rc = XMIT_CSUM_V6; - if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP) - rc |= XMIT_CSUM_TCP; + protocol = vlan_get_protocol(skb); + if (protocol == htons(ETH_P_IPV6)) { + rc = XMIT_CSUM_V6; + prot = ipv6_hdr(skb)->nexthdr; + } else { + rc = XMIT_CSUM_V4; + prot = ip_hdr(skb)->protocol; + }

+ if (!CHIP_IS_E1x(bp) && skb->encapsulation) { + if (inner_ip_hdr(skb)->version == 6) { + rc |= XMIT_CSUM_ENC_V6; + if (inner_ipv6_hdr(skb)->nexthdr == IPPROTO_TCP) + rc |= XMIT_CSUM_TCP; } else { - rc = XMIT_CSUM_V4; - if (ip_hdr(skb)->protocol == IPPROTO_TCP) + rc |= XMIT_CSUM_ENC_V4; + if (inner_ip_hdr(skb)->protocol == IPPROTO_TCP) rc |= XMIT_CSUM_TCP; } } + if (prot == IPPROTO_TCP) + rc |= XMIT_CSUM_TCP;

- if (skb_is_gso_v6(skb)) - rc |= XMIT_GSO_V6 | XMIT_CSUM_TCP | XMIT_CSUM_V6; - else if (skb_is_gso(skb)) - rc |= XMIT_GSO_V4 | XMIT_CSUM_V4 | XMIT_CSUM_TCP; + if (skb_is_gso_v6(skb)) { + rc |= (XMIT_GSO_V6 | XMIT_CSUM_TCP | XMIT_CSUM_V6); + if (rc & XMIT_CSUM_ENC) + rc |= XMIT_GSO_ENC_V6; + } else if (skb_is_gso(skb)) { + rc |= (XMIT_GSO_V4 | XMIT_CSUM_V4 | XMIT_CSUM_TCP); + if (rc & XMIT_CSUM_ENC) + rc |= XMIT_GSO_ENC_V4; + }

return rc; } @@@ -3271,23 -3257,14 +3274,23 @@@ exit_lbl } #endif

-static inline void bnx2x_set_pbd_gso_e2(struct sk_buff *skb, u32 *parsing_data, - u32 xmit_type) +static void bnx2x_set_pbd_gso_e2(struct sk_buff *skb, u32 *parsing_data, + u32 xmit_type) { + struct ipv6hdr *ipv6; + *parsing_data |= (skb_shinfo(skb)->gso_size << ETH_TX_PARSE_BD_E2_LSO_MSS_SHIFT) & ETH_TX_PARSE_BD_E2_LSO_MSS; - if ((xmit_type & XMIT_GSO_V6) && - (ipv6_hdr(skb)->nexthdr == NEXTHDR_IPV6)) + + if (xmit_type & XMIT_GSO_ENC_V6) + ipv6 = inner_ipv6_hdr(skb); + else if (xmit_type & XMIT_GSO_V6) + ipv6 = ipv6_hdr(skb); + else + ipv6 = NULL; + + if (ipv6 && ipv6->nexthdr == NEXTHDR_IPV6) *parsing_data |= ETH_TX_PARSE_BD_E2_IPV6_WITH_EXT_HDR; }

@@@ -3298,13 -3275,13 +3301,13 @@@ * @pbd: parse BD * @xmit_type: xmit flags */ -static inline void bnx2x_set_pbd_gso(struct sk_buff *skb, - struct eth_tx_parse_bd_e1x *pbd, - u32 xmit_type) +static void bnx2x_set_pbd_gso(struct sk_buff *skb, + struct eth_tx_parse_bd_e1x *pbd, + u32 xmit_type) { pbd->lso_mss = cpu_to_le16(skb_shinfo(skb)->gso_size); pbd->tcp_send_seq = bswab32(tcp_hdr(skb)->seq); - pbd->tcp_flags = pbd_tcp_flags(skb); + pbd->tcp_flags = pbd_tcp_flags(tcp_hdr(skb));

if (xmit_type & XMIT_GSO_V4) { pbd->ip_id = bswab16(ip_hdr(skb)->id); @@@ -3324,40 -3301,6 +3327,40 @@@ }

/** + * bnx2x_set_pbd_csum_enc - update PBD with checksum and return header length + * + * @bp: driver handle + * @skb: packet skb + * @parsing_data: data to be updated + * @xmit_type: xmit flags + * + * 57712/578xx related, when skb has encapsulation + */ +static u8 bnx2x_set_pbd_csum_enc(struct bnx2x *bp, struct sk_buff *skb, + u32 *parsing_data, u32 xmit_type) +{ + *parsing_data |= + ((((u8 *)skb_inner_transport_header(skb) - skb->data) >> 1) << + ETH_TX_PARSE_BD_E2_L4_HDR_START_OFFSET_W_SHIFT) & + ETH_TX_PARSE_BD_E2_L4_HDR_START_OFFSET_W; + + if (xmit_type & XMIT_CSUM_TCP) { + *parsing_data |= ((inner_tcp_hdrlen(skb) / 4) << + ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW_SHIFT) & + ETH_TX_PARSE_BD_E2_TCP_HDR_LENGTH_DW; + + return skb_inner_transport_header(skb) + + inner_tcp_hdrlen(skb) - skb->data; + } + + /* We support checksum offload for TCP and UDP only. + * No need to pass the UDP header length - it's a constant. + */ + return skb_inner_transport_header(skb) + + sizeof(struct udphdr) - skb->data; +} + +/** * bnx2x_set_pbd_csum_e2 - update PBD with checksum and return header length * * @bp: driver handle @@@ -3365,15 -3308,15 +3368,15 @@@ * @parsing_data: data to be updated * @xmit_type: xmit flags * - * 57712 related + * 57712/578xx related */ -static inline u8 bnx2x_set_pbd_csum_e2(struct bnx2x *bp, struct sk_buff *skb, - u32 *parsing_data, u32 xmit_type) +static u8 bnx2x_set_pbd_csum_e2(struct bnx2x *bp, struct sk_buff *skb, + u32 *parsing_data, u32 xmit_type) { *parsing_data |= ((((u8 *)skb_transport_header(skb) - skb->data) >> 1) << - ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W_SHIFT) & - ETH_TX_PARSE_BD_E2_TCP_HDR_START_OFFSET_W; + ETH_TX_PARSE_BD_E2_L4_HDR_START_OFFSET_W_SHIFT) & + ETH_TX_PARSE_BD_E2_L4_HDR_START_OFFSET_W;

if (xmit_type & XMIT_CSUM_TCP) { *parsing_data |= ((tcp_hdrlen(skb) / 4) << @@@ -3388,15 -3331,17 +3391,15 @@@ return skb_transport_header(skb) + sizeof(struct udphdr) - skb->data; }

-static inline void bnx2x_set_sbd_csum(struct bnx2x *bp, struct sk_buff *skb, - struct eth_tx_start_bd *tx_start_bd, u32 xmit_type) +/* set FW indication according to inner or outer protocols if tunneled */ +static void bnx2x_set_sbd_csum(struct bnx2x *bp, struct sk_buff *skb, + struct eth_tx_start_bd *tx_start_bd, + u32 xmit_type) { tx_start_bd->bd_flags.as_bitfield |= ETH_TX_BD_FLAGS_L4_CSUM;

- if (xmit_type & XMIT_CSUM_V4) - tx_start_bd->bd_flags.as_bitfield |= - ETH_TX_BD_FLAGS_IP_CSUM; - else - tx_start_bd->bd_flags.as_bitfield |= - ETH_TX_BD_FLAGS_IPV6; + if (xmit_type & (XMIT_CSUM_ENC_V6 | XMIT_CSUM_V6)) + tx_start_bd->bd_flags.as_bitfield |= ETH_TX_BD_FLAGS_IPV6;

if (!(xmit_type & XMIT_CSUM_TCP)) tx_start_bd->bd_flags.as_bitfield |= ETH_TX_BD_FLAGS_IS_UDP; @@@ -3410,9 -3355,9 +3413,9 @@@ * @pbd: parse BD to be updated * @xmit_type: xmit flags */ -static inline u8 bnx2x_set_pbd_csum(struct bnx2x *bp, struct sk_buff *skb, - struct eth_tx_parse_bd_e1x *pbd, - u32 xmit_type) +static u8 bnx2x_set_pbd_csum(struct bnx2x *bp, struct sk_buff *skb, + struct eth_tx_parse_bd_e1x *pbd, + u32 xmit_type) { u8 hlen = (skb_network_header(skb) - skb->data) >> 1;

@@@ -3458,70 -3403,6 +3461,70 @@@ return hlen; }

+static void bnx2x_update_pbds_gso_enc(struct sk_buff *skb, + struct eth_tx_parse_bd_e2 *pbd_e2, + struct eth_tx_parse_2nd_bd *pbd2, + u16 *global_data, + u32 xmit_type) +{ + u16 hlen_w = 0; + u8 outerip_off, outerip_len = 0; + /* from outer IP to transport */ + hlen_w = (skb_inner_transport_header(skb) - + skb_network_header(skb)) >> 1; + + /* transport len */ + if (xmit_type & XMIT_CSUM_TCP) + hlen_w += inner_tcp_hdrlen(skb) >> 1; + else + hlen_w += sizeof(struct udphdr) >> 1; + + pbd2->fw_ip_hdr_to_payload_w = hlen_w; + + if (xmit_type & XMIT_CSUM_ENC_V4) { + struct iphdr *iph = ip_hdr(skb); + pbd2->fw_ip_csum_wo_len_flags_frag = + bswab16(csum_fold((~iph->check) - + iph->tot_len - iph->frag_off)); + } else { + pbd2->fw_ip_hdr_to_payload_w = + hlen_w - ((sizeof(struct ipv6hdr)) >> 1); + } + + pbd2->tcp_send_seq = bswab32(inner_tcp_hdr(skb)->seq); + + pbd2->tcp_flags = pbd_tcp_flags(inner_tcp_hdr(skb)); + + if (xmit_type & XMIT_GSO_V4) { + pbd2->hw_ip_id = bswab16(inner_ip_hdr(skb)->id); + + pbd_e2->data.tunnel_data.pseudo_csum = + bswab16(~csum_tcpudp_magic( + inner_ip_hdr(skb)->saddr, + inner_ip_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0)); + + outerip_len = ip_hdr(skb)->ihl << 1; + } else { + pbd_e2->data.tunnel_data.pseudo_csum = + bswab16(~csum_ipv6_magic( + &inner_ipv6_hdr(skb)->saddr, + &inner_ipv6_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0)); + } + + outerip_off = (skb_network_header(skb) - skb->data) >> 1; + + *global_data |= + outerip_off | + (!!(xmit_type & XMIT_CSUM_V6) << + ETH_TX_PARSE_2ND_BD_IP_HDR_TYPE_OUTER_SHIFT) | + (outerip_len << + ETH_TX_PARSE_2ND_BD_IP_HDR_LEN_OUTER_W_SHIFT) | + ((skb->protocol == cpu_to_be16(ETH_P_8021Q)) << + ETH_TX_PARSE_2ND_BD_LLC_SNAP_EN_SHIFT); +} + /* called with netif_tx_lock * bnx2x_tx_int() runs without netif_tx_lock unless it needs to call * netif_wake_queue() @@@ -3537,7 -3418,6 +3540,7 @@@ netdev_tx_t bnx2x_start_xmit(struct sk_ struct eth_tx_bd *tx_data_bd, *total_pkt_bd = NULL; struct eth_tx_parse_bd_e1x *pbd_e1x = NULL; struct eth_tx_parse_bd_e2 *pbd_e2 = NULL; + struct eth_tx_parse_2nd_bd *pbd2 = NULL; u32 pbd_e2_parsing_data = 0; u16 pkt_prod, bd_prod; int nbd, txq_index; @@@ -3605,7 -3485,7 +3608,7 @@@ mac_type = MULTICAST_ADDRESS; }

-#if (MAX_SKB_FRAGS >= MAX_FETCH_BD - 3) +#if (MAX_SKB_FRAGS >= MAX_FETCH_BD - BDS_PER_TX_PKT) /* First, check if we need to linearize the skb (due to FW restrictions). No need to check fragmentation if page size > 8K (there will be no violation to FW restrictions) */ @@@ -3653,9 -3533,12 +3656,9 @@@ first_bd = tx_start_bd;

tx_start_bd->bd_flags.as_bitfield = ETH_TX_BD_FLAGS_START_BD; - SET_FLAG(tx_start_bd->general_data, - ETH_TX_START_BD_PARSE_NBDS, - 0);

- /* header nbd */ - SET_FLAG(tx_start_bd->general_data, ETH_TX_START_BD_HDR_NBDS, 1); + /* header nbd: indirectly zero other flags! */ + tx_start_bd->general_data = 1 << ETH_TX_START_BD_HDR_NBDS_SHIFT;

/* remember the first BD of the packet */ tx_buf->first_bd = txdata->tx_bd_prod; @@@ -3675,16 -3558,19 +3678,16 @@@ /* when transmitting in a vf, start bd must hold the ethertype * for fw to enforce it */ -#ifndef BNX2X_STOP_ON_ERROR - if (IS_VF(bp)) { -#endif + if (IS_VF(bp)) tx_start_bd->vlan_or_ethertype = cpu_to_le16(ntohs(eth->h_proto)); -#ifndef BNX2X_STOP_ON_ERROR - } else { + else /* used by FW for packet accounting */ tx_start_bd->vlan_or_ethertype = cpu_to_le16(pkt_prod); - } -#endif }

+ nbd = 2; /* start_bd + pbd + frags (updated when pages are mapped) */ + /* turn on parsing and get a BD */ bd_prod = TX_BD(NEXT_TX_IDX(bd_prod));

@@@ -3694,58 -3580,23 +3697,58 @@@ if (!CHIP_IS_E1x(bp)) { pbd_e2 = &txdata->tx_desc_ring[bd_prod].parse_bd_e2; memset(pbd_e2, 0, sizeof(struct eth_tx_parse_bd_e2)); - /* Set PBD in checksum offload case */ - if (xmit_type & XMIT_CSUM) + + if (xmit_type & XMIT_CSUM_ENC) { + u16 global_data = 0; + + /* Set PBD in enc checksum offload case */ + hlen = bnx2x_set_pbd_csum_enc(bp, skb, + &pbd_e2_parsing_data, + xmit_type); + + /* turn on 2nd parsing and get a BD */ + bd_prod = TX_BD(NEXT_TX_IDX(bd_prod)); + + pbd2 = &txdata->tx_desc_ring[bd_prod].parse_2nd_bd; + + memset(pbd2, 0, sizeof(*pbd2)); + + pbd_e2->data.tunnel_data.ip_hdr_start_inner_w = + (skb_inner_network_header(skb) - + skb->data) >> 1; + + if (xmit_type & XMIT_GSO_ENC) + bnx2x_update_pbds_gso_enc(skb, pbd_e2, pbd2, + &global_data, + xmit_type); + + pbd2->global_data = cpu_to_le16(global_data); + + /* add addition parse BD indication to start BD */ + SET_FLAG(tx_start_bd->general_data, + ETH_TX_START_BD_PARSE_NBDS, 1); + /* set encapsulation flag in start BD */ + SET_FLAG(tx_start_bd->general_data, + ETH_TX_START_BD_TUNNEL_EXIST, 1); + nbd++; + } else if (xmit_type & XMIT_CSUM) { + /* Set PBD in checksum offload case w/o encapsulation */ hlen = bnx2x_set_pbd_csum_e2(bp, skb, &pbd_e2_parsing_data, xmit_type); + }

- if (IS_MF_SI(bp) || IS_VF(bp)) { - /* fill in the MAC addresses in the PBD - for local - * switching - */ - bnx2x_set_fw_mac_addr(&pbd_e2->src_mac_addr_hi, - &pbd_e2->src_mac_addr_mid, - &pbd_e2->src_mac_addr_lo, + /* Add the macs to the parsing BD this is a vf */ + if (IS_VF(bp)) { + /* override GRE parameters in BD */ + bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.src_hi, + &pbd_e2->data.mac_addr.src_mid, + &pbd_e2->data.mac_addr.src_lo, eth->h_source); - bnx2x_set_fw_mac_addr(&pbd_e2->dst_mac_addr_hi, - &pbd_e2->dst_mac_addr_mid, - &pbd_e2->dst_mac_addr_lo, + + bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.dst_hi, + &pbd_e2->data.mac_addr.dst_mid, + &pbd_e2->data.mac_addr.dst_lo, eth->h_dest); }

@@@ -3767,13 -3618,14 +3770,13 @@@ /* Setup the data pointer of the first BD of the packet */ tx_start_bd->addr_hi = cpu_to_le32(U64_HI(mapping)); tx_start_bd->addr_lo = cpu_to_le32(U64_LO(mapping)); - nbd = 2; /* start_bd + pbd + frags (updated when pages are mapped) */ tx_start_bd->nbytes = cpu_to_le16(skb_headlen(skb)); pkt_size = tx_start_bd->nbytes;

DP(NETIF_MSG_TX_QUEUED, - "first bd @%p addr (%x:%x) nbd %d nbytes %d flags %x vlan %x\n", + "first bd @%p addr (%x:%x) nbytes %d flags %x vlan %x\n", tx_start_bd, tx_start_bd->addr_hi, tx_start_bd->addr_lo, - le16_to_cpu(tx_start_bd->nbd), le16_to_cpu(tx_start_bd->nbytes), + le16_to_cpu(tx_start_bd->nbytes), tx_start_bd->bd_flags.as_bitfield, le16_to_cpu(tx_start_bd->vlan_or_ethertype));

@@@ -3786,12 -3638,10 +3789,12 @@@

tx_start_bd->bd_flags.as_bitfield |= ETH_TX_BD_FLAGS_SW_LSO;

- if (unlikely(skb_headlen(skb) > hlen)) + if (unlikely(skb_headlen(skb) > hlen)) { + nbd++; bd_prod = bnx2x_tx_split(bp, txdata, tx_buf, &tx_start_bd, hlen, - bd_prod, ++nbd); + bd_prod); + } if (!CHIP_IS_E1x(bp)) bnx2x_set_pbd_gso_e2(skb, &pbd_e2_parsing_data, xmit_type); @@@ -3881,13 -3731,9 +3884,13 @@@ if (pbd_e2) DP(NETIF_MSG_TX_QUEUED, "PBD (E2) @%p dst %x %x %x src %x %x %x parsing_data %x\n", - pbd_e2, pbd_e2->dst_mac_addr_hi, pbd_e2->dst_mac_addr_mid, - pbd_e2->dst_mac_addr_lo, pbd_e2->src_mac_addr_hi, - pbd_e2->src_mac_addr_mid, pbd_e2->src_mac_addr_lo, + pbd_e2, + pbd_e2->data.mac_addr.dst_hi, + pbd_e2->data.mac_addr.dst_mid, + pbd_e2->data.mac_addr.dst_lo, + pbd_e2->data.mac_addr.src_hi, + pbd_e2->data.mac_addr.src_mid, + pbd_e2->data.mac_addr.src_lo, pbd_e2->parsing_data); DP(NETIF_MSG_TX_QUEUED, "doorbell: nbd %d bd %u\n", nbd, bd_prod);

@@@ -4737,11 -4583,11 +4740,11 @@@ static void storm_memset_hc_disable(str u32 enable_flag = disable ? 0 : (1 << HC_INDEX_DATA_HC_ENABLED_SHIFT); u32 addr = BAR_CSTRORM_INTMEM + CSTORM_STATUS_BLOCK_DATA_FLAGS_OFFSET(fw_sb_id, sb_index); - u16 flags = REG_RD16(bp, addr); + u8 flags = REG_RD8(bp, addr); /* clear and set */ flags &= ~HC_INDEX_DATA_HC_ENABLED; flags |= enable_flag; - REG_WR16(bp, addr, flags); + REG_WR8(bp, addr, flags); DP(NETIF_MSG_IFUP, "port %x fw_sb_id %d sb_index %d disable %d\n", port, fw_sb_id, sb_index, disable); diff --combined drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 1e60c5d,c50696b..86d1387 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@@ -75,6 -75,8 +75,6 @@@ #define FW_FILE_NAME_E1H "bnx2x/bnx2x-e1h-" FW_FILE_VERSION ".fw" #define FW_FILE_NAME_E2 "bnx2x/bnx2x-e2-" FW_FILE_VERSION ".fw"

-#define MAC_LEADING_ZERO_CNT (ALIGN(ETH_ALEN, sizeof(u32)) - ETH_ALEN) - /* Time in jiffies before concluding the transmitter is hung */ #define TX_TIMEOUT (5*HZ)

@@@ -2953,16 -2955,14 +2953,16 @@@ static unsigned long bnx2x_get_common_f __set_bit(BNX2X_Q_FLG_ACTIVE, &flags);

/* tx only connections collect statistics (on the same index as the - * parent connection). The statistics are zeroed when the parent - * connection is initialized. + * parent connection). The statistics are zeroed when the parent + * connection is initialized. */

__set_bit(BNX2X_Q_FLG_STATS, &flags); if (zero_stats) __set_bit(BNX2X_Q_FLG_ZERO_STATS, &flags);

+ __set_bit(BNX2X_Q_FLG_PCSUM_ON_PKT, &flags); + __set_bit(BNX2X_Q_FLG_TUN_INC_INNER_IP_ID, &flags);

#ifdef BNX2X_STOP_ON_ERROR __set_bit(BNX2X_Q_FLG_TX_SEC, &flags); @@@ -3227,29 -3227,16 +3227,29 @@@ static void bnx2x_drv_info_ether_stat(s { struct eth_stats_info *ether_stat = &bp->slowpath->drv_info_to_mcp.ether_stat; + struct bnx2x_vlan_mac_obj *mac_obj = + &bp->sp_objs->mac_obj; + int i;

strlcpy(ether_stat->version, DRV_MODULE_VERSION, ETH_STAT_INFO_VERSION_LEN);

- bp->sp_objs[0].mac_obj.get_n_elements(bp, &bp->sp_objs[0].mac_obj, - DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED, - ether_stat->mac_local); - + /* get DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED macs, placing them in the + * mac_local field in ether_stat struct. The base address is offset by 2 + * bytes to account for the field being 8 bytes but a mac address is + * only 6 bytes. Likewise, the stride for the get_n_elements function is + * 2 bytes to compensate from the 6 bytes of a mac to the 8 bytes + * allocated by the ether_stat struct, so the macs will land in their + * proper positions. + */ + for (i = 0; i < DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED; i++) + memset(ether_stat->mac_local + i, 0, + sizeof(ether_stat->mac_local[0])); + mac_obj->get_n_elements(bp, &bp->sp_objs[0].mac_obj, + DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED, + ether_stat->mac_local + MAC_PAD, MAC_PAD, + ETH_ALEN); ether_stat->mtu_size = bp->dev->mtu; - if (bp->dev->features & NETIF_F_RXCSUM) ether_stat->feature_flags |= FEATURE_ETH_CHKSUM_OFFLOAD_MASK; if (bp->dev->features & NETIF_F_TSO) @@@ -3271,7 -3258,8 +3271,7 @@@ static void bnx2x_drv_info_fcoe_stat(st if (!CNIC_LOADED(bp)) return;

- memcpy(fcoe_stat->mac_local + MAC_LEADING_ZERO_CNT, - bp->fip_mac, ETH_ALEN); + memcpy(fcoe_stat->mac_local + MAC_PAD, bp->fip_mac, ETH_ALEN);

fcoe_stat->qos_priority = app->traffic_type_priority[LLFC_TRAFFIC_TYPE_FCOE]; @@@ -3373,8 -3361,8 +3373,8 @@@ static void bnx2x_drv_info_iscsi_stat(s if (!CNIC_LOADED(bp)) return;

- memcpy(iscsi_stat->mac_local + MAC_LEADING_ZERO_CNT, - bp->cnic_eth_dev.iscsi_mac, ETH_ALEN); + memcpy(iscsi_stat->mac_local + MAC_PAD, bp->cnic_eth_dev.iscsi_mac, + ETH_ALEN);

iscsi_stat->qos_priority = app->traffic_type_priority[LLFC_TRAFFIC_TYPE_ISCSI]; @@@ -4959,7 -4947,7 +4959,7 @@@ static void bnx2x_after_function_update q); }

- if (!NO_FCOE(bp)) { + if (!NO_FCOE(bp) && CNIC_ENABLED(bp)) { fp = &bp->fp[FCOE_IDX(bp)]; queue_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj;

@@@ -6041,10 -6029,9 +6041,10 @@@ void bnx2x_nic_init(struct bnx2x *bp, u rmb(); bnx2x_init_rx_rings(bp); bnx2x_init_tx_rings(bp); - - if (IS_VF(bp)) + if (IS_VF(bp)) { + bnx2x_memset_stats(bp); return; + }

/* Initialize MOD_ABS interrupts */ bnx2x_init_mod_abs_int(bp, &bp->link_vars, bp->common.chip_id, @@@ -9538,10 -9525,6 +9538,10 @@@ sp_rtnl_not_reset bnx2x_vfpf_storm_rx_mode(bp); }

+ if (test_and_clear_bit(BNX2X_SP_RTNL_HYPERVISOR_VLAN, + &bp->sp_rtnl_state)) + bnx2x_pf_set_vfs_vlan(bp); + /* work which needs rtnl lock not-taken (as it takes the lock itself and * can be called from other contexts as well) */ @@@ -9549,10 -9532,8 +9549,10 @@@

/* enable SR-IOV if applicable */ if (IS_SRIOV(bp) && test_and_clear_bit(BNX2X_SP_RTNL_ENABLE_SRIOV, - &bp->sp_rtnl_state)) + &bp->sp_rtnl_state)) { + bnx2x_disable_sriov(bp); bnx2x_enable_sriov(bp); + } }

static void bnx2x_period_task(struct work_struct *work) @@@ -9720,31 -9701,6 +9720,31 @@@ static struct bnx2x_prev_path_list return NULL; }

+static int bnx2x_prev_path_mark_eeh(struct bnx2x *bp) +{ + struct bnx2x_prev_path_list *tmp_list; + int rc; + + rc = down_interruptible(&bnx2x_prev_sem); + if (rc) { + BNX2X_ERR("Received %d when tried to take lock\n", rc); + return rc; + } + + tmp_list = bnx2x_prev_path_get_entry(bp); + if (tmp_list) { + tmp_list->aer = 1; + rc = 0; + } else { + BNX2X_ERR("path %d: Entry does not exist for eeh; Flow occurs before initial insmod is over ?\n", + BP_PATH(bp)); + } + + up(&bnx2x_prev_sem); + + return rc; +} + static bool bnx2x_prev_is_path_marked(struct bnx2x *bp) { struct bnx2x_prev_path_list *tmp_list; @@@ -9753,15 -9709,14 +9753,15 @@@ if (down_trylock(&bnx2x_prev_sem)) return false;

- list_for_each_entry(tmp_list, &bnx2x_prev_list, list) { - if (PCI_SLOT(bp->pdev->devfn) == tmp_list->slot && - bp->pdev->bus->number == tmp_list->bus && - BP_PATH(bp) == tmp_list->path) { + tmp_list = bnx2x_prev_path_get_entry(bp); + if (tmp_list) { + if (tmp_list->aer) { + DP(NETIF_MSG_HW, "Path %d was marked by AER\n", + BP_PATH(bp)); + } else { rc = true; BNX2X_DEV_INFO("Path %d was already cleaned from previous drivers\n", BP_PATH(bp)); - break; } }

@@@ -9775,28 -9730,6 +9775,28 @@@ static int bnx2x_prev_mark_path(struct struct bnx2x_prev_path_list *tmp_list; int rc;

+ rc = down_interruptible(&bnx2x_prev_sem); + if (rc) { + BNX2X_ERR("Received %d when tried to take lock\n", rc); + return rc; + } + + /* Check whether the entry for this path already exists */ + tmp_list = bnx2x_prev_path_get_entry(bp); + if (tmp_list) { + if (!tmp_list->aer) { + BNX2X_ERR("Re-Marking the path.\n"); + } else { + DP(NETIF_MSG_HW, "Removing AER indication from path %d\n", + BP_PATH(bp)); + tmp_list->aer = 0; + } + up(&bnx2x_prev_sem); + return 0; + } + up(&bnx2x_prev_sem); + + /* Create an entry for this path and add it */ tmp_list = kmalloc(sizeof(struct bnx2x_prev_path_list), GFP_KERNEL); if (!tmp_list) { BNX2X_ERR("Failed to allocate 'bnx2x_prev_path_list'\n"); @@@ -9806,7 -9739,6 +9806,7 @@@ tmp_list->bus = bp->pdev->bus->number; tmp_list->slot = PCI_SLOT(bp->pdev->devfn); tmp_list->path = BP_PATH(bp); + tmp_list->aer = 0; tmp_list->undi = after_undi ? (1 << BP_PORT(bp)) : 0;

rc = down_interruptible(&bnx2x_prev_sem); @@@ -9814,8 -9746,8 +9814,8 @@@ BNX2X_ERR("Received %d when tried to take lock\n", rc); kfree(tmp_list); } else { - BNX2X_DEV_INFO("Marked path [%d] - finished previous unload\n", - BP_PATH(bp)); + DP(NETIF_MSG_HW, "Marked path [%d] - finished previous unload\n", + BP_PATH(bp)); list_add(&tmp_list->list, &bnx2x_prev_list); up(&bnx2x_prev_sem); } @@@ -9946,6 -9878,10 +9946,10 @@@ static int bnx2x_prev_unload_common(str REG_RD(bp, NIG_REG_NIG_INT_STS_CLR_0); } } + if (!CHIP_IS_E1x(bp)) + /* block FW from writing to host */ + REG_WR(bp, PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER, 0); + /* wait until BRB is empty */ tmp_reg = REG_RD(bp, BRB1_REG_NUM_OF_FULL_BLOCKS); while (timer_count) { @@@ -10054,7 -9990,6 +10058,7 @@@ static int bnx2x_prev_unload(struct bnx }

do { + int aer = 0; /* Lock MCP using an unload request */ fw = bnx2x_fw_command(bp, DRV_MSG_CODE_UNLOAD_REQ_WOL_DIS, 0); if (!fw) { @@@ -10063,18 -9998,7 +10067,18 @@@ break; }

- if (fw == FW_MSG_CODE_DRV_UNLOAD_COMMON) { + rc = down_interruptible(&bnx2x_prev_sem); + if (rc) { + BNX2X_ERR("Cannot check for AER; Received %d when tried to take lock\n", + rc); + } else { + /* If Path is marked by EEH, ignore unload status */ + aer = !!(bnx2x_prev_path_get_entry(bp) && + bnx2x_prev_path_get_entry(bp)->aer); + up(&bnx2x_prev_sem); + } + + if (fw == FW_MSG_CODE_DRV_UNLOAD_COMMON || aer) { rc = bnx2x_prev_unload_common(bp); break; } @@@ -10114,12 -10038,8 +10118,12 @@@ static void bnx2x_get_common_hwinfo(str id = ((val & 0xffff) << 16); val = REG_RD(bp, MISC_REG_CHIP_REV); id |= ((val & 0xf) << 12); - val = REG_RD(bp, MISC_REG_CHIP_METAL); - id |= ((val & 0xff) << 4); + + /* Metal is read from PCI regs, but we can't access >=0x400 from + * the configuration space (so we need to reg_rd) + */ + val = REG_RD(bp, PCICFG_OFFSET + PCI_ID_VAL3); + id |= (((val >> 24) & 0xf) << 4); val = REG_RD(bp, MISC_REG_BOND_ID); id |= (val & 0xf); bp->common.chip_id = id; @@@ -10896,12 -10816,14 +10900,12 @@@ static void bnx2x_get_cnic_mac_hwinfo(s } }

- if (IS_MF_STORAGE_SD(bp)) - /* Zero primary MAC configuration */ - memset(bp->dev->dev_addr, 0, ETH_ALEN); - - if (IS_MF_FCOE_AFEX(bp) || IS_MF_FCOE_SD(bp)) - /* use FIP MAC as primary MAC */ + /* If this is a storage-only interface, use SAN mac as + * primary MAC. Notice that for SD this is already the case, + * as the SAN mac was copied from the primary MAC. + */ + if (IS_MF_FCOE_AFEX(bp)) memcpy(bp->dev->dev_addr, fip_mac, ETH_ALEN); - } else { val2 = SHMEM_RD(bp, dev_info.port_hw_config[port]. iscsi_mac_upper); @@@ -11138,9 -11060,6 +11142,9 @@@ static int bnx2x_get_hwinfo(struct bnx2 } else BNX2X_DEV_INFO("illegal OV for SD\n"); break; + case SHARED_FEAT_CFG_FORCE_SF_MODE_FORCED_SF: + bp->mf_config[vn] = 0; + break; default: /* Unknown configuration: reset mf_config */ bp->mf_config[vn] = 0; @@@ -11487,6 -11406,26 +11491,6 @@@ static int bnx2x_init_bp(struct bnx2x * * net_device service functions */

-static int bnx2x_open_epilog(struct bnx2x *bp) -{ - /* Enable sriov via delayed work. This must be done via delayed work - * because it causes the probe of the vf devices to be run, which invoke - * register_netdevice which must have rtnl lock taken. As we are holding - * the lock right now, that could only work if the probe would not take - * the lock. However, as the probe of the vf may be called from other - * contexts as well (such as passthrough to vm failes) it can't assume - * the lock is being held for it. Using delayed work here allows the - * probe code to simply take the lock (i.e. wait for it to be released - * if it is being held). - */ - smp_mb__before_clear_bit(); - set_bit(BNX2X_SP_RTNL_ENABLE_SRIOV, &bp->sp_rtnl_state); - smp_mb__after_clear_bit(); - schedule_delayed_work(&bp->sp_rtnl_task, 0); - - return 0; -} - /* called with rtnl_lock */ static int bnx2x_open(struct net_device *dev) { @@@ -11856,8 -11795,6 +11860,8 @@@ static const struct net_device_ops bnx2 .ndo_setup_tc = bnx2x_setup_tc, #ifdef CONFIG_BNX2X_SRIOV .ndo_set_vf_mac = bnx2x_set_vf_mac, + .ndo_set_vf_vlan = bnx2x_set_vf_vlan, + .ndo_get_vf_config = bnx2x_get_vf_config, #endif #ifdef NETDEV_FCOE_WWNN .ndo_fcoe_get_wwn = bnx2x_fcoe_get_wwn, @@@ -12020,26 -11957,19 +12024,26 @@@ static int bnx2x_init_dev(struct bnx2x dev->watchdog_timeo = TX_TIMEOUT;

dev->netdev_ops = &bnx2x_netdev_ops; - bnx2x_set_ethtool_ops(dev); + bnx2x_set_ethtool_ops(bp, dev);

dev->priv_flags |= IFF_UNICAST_FLT;

dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_GRO | - NETIF_F_RXHASH | NETIF_F_HW_VLAN_TX; + NETIF_F_RXHASH | NETIF_F_HW_VLAN_CTAG_TX; + if (!CHIP_IS_E1x(bp)) { + dev->hw_features |= NETIF_F_GSO_GRE; + dev->hw_enc_features = + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | + NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | + NETIF_F_GSO_GRE; + }

dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_HIGHDMA;

- dev->features |= dev->hw_features | NETIF_F_HW_VLAN_RX; + dev->features |= dev->hw_features | NETIF_F_HW_VLAN_CTAG_RX; if (bp->flags & USING_DAC_FLAG) dev->features |= NETIF_F_HIGHDMA;

@@@ -12521,7 -12451,7 +12525,7 @@@ static int bnx2x_init_one(struct pci_de * l2 connections. */ if (IS_VF(bp)) { - bnx2x_vf_map_doorbells(bp); + bp->doorbells = bnx2x_vf_doorbells(bp); rc = bnx2x_vf_pci_alloc(bp); if (rc) goto init_one_exit; @@@ -12549,8 -12479,13 +12553,8 @@@ goto init_one_exit; }

- /* Enable SRIOV if capability found in configuration space. - * Once the generic SR-IOV framework makes it in from the - * pci tree this will be revised, to allow dynamic control - * over the number of VFs. Right now, change the num of vfs - * param below to enable SR-IOV. - */ - rc = bnx2x_iov_init_one(bp, int_mode, 0/*num vfs*/); + /* Enable SRIOV if capability found in configuration space */ + rc = bnx2x_iov_init_one(bp, int_mode, BNX2X_MAX_NUM_OF_VFS); if (rc) goto init_one_exit;

@@@ -12562,6 -12497,16 +12566,6 @@@ if (CHIP_IS_E1x(bp)) bp->flags |= NO_FCOE_FLAG;

- /* disable FCOE for 57840 device, until FW supports it */ - switch (ent->driver_data) { - case BCM57840_O: - case BCM57840_4_10: - case BCM57840_2_20: - case BCM57840_MFO: - case BCM57840_MF: - bp->flags |= NO_FCOE_FLAG; - } - /* Set bp->num_queues for MSI-X mode*/ bnx2x_set_num_queues(bp);

@@@ -12695,7 -12640,9 +12699,7 @@@ static void bnx2x_remove_one(struct pci

static int bnx2x_eeh_nic_unload(struct bnx2x *bp) { - int i; - - bp->state = BNX2X_STATE_ERROR; + bp->state = BNX2X_STATE_CLOSING_WAIT4_HALT;

bp->rx_mode = BNX2X_RX_MODE_NONE;

@@@ -12704,21 -12651,29 +12708,21 @@@

/* Stop Tx */ bnx2x_tx_disable(bp); - - bnx2x_netif_stop(bp, 0); /* Delete all NAPI objects */ bnx2x_del_all_napi(bp); if (CNIC_LOADED(bp)) bnx2x_del_all_napi_cnic(bp); + netdev_reset_tc(bp->dev);

del_timer_sync(&bp->timer); + cancel_delayed_work(&bp->sp_task); + cancel_delayed_work(&bp->period_task);

- bnx2x_stats_handle(bp, STATS_EVENT_STOP); - - /* Release IRQs */ - bnx2x_free_irq(bp); - - /* Free SKBs, SGEs, TPA pool and driver internals */ - bnx2x_free_skbs(bp); - - for_each_rx_queue(bp, i) - bnx2x_free_rx_sge_range(bp, bp->fp + i, NUM_RX_SGE); - - bnx2x_free_mem(bp); + spin_lock_bh(&bp->stats_lock); + bp->stats_state = STATS_STATE_DISABLED; + spin_unlock_bh(&bp->stats_lock);

- bp->state = BNX2X_STATE_CLOSED; + bnx2x_save_statistics(bp);

netif_carrier_off(bp->dev);

@@@ -12754,8 -12709,6 +12758,8 @@@ static pci_ers_result_t bnx2x_io_error_

rtnl_lock();

+ BNX2X_ERR("IO error detected\n"); + netif_device_detach(dev);

if (state == pci_channel_io_perm_failure) { @@@ -12766,8 -12719,6 +12770,8 @@@ if (netif_running(dev)) bnx2x_eeh_nic_unload(bp);

+ bnx2x_prev_path_mark_eeh(bp); + pci_disable_device(pdev);

rtnl_unlock(); @@@ -12786,10 -12737,9 +12790,10 @@@ static pci_ers_result_t bnx2x_io_slot_r { struct net_device *dev = pci_get_drvdata(pdev); struct bnx2x *bp = netdev_priv(dev); + int i;

rtnl_lock(); - + BNX2X_ERR("IO slot reset initializing...\n"); if (pci_enable_device(pdev)) { dev_err(&pdev->dev, "Cannot re-enable PCI device after reset\n"); @@@ -12803,42 -12753,6 +12807,42 @@@ if (netif_running(dev)) bnx2x_set_power_state(bp, PCI_D0);

+ if (netif_running(dev)) { + BNX2X_ERR("IO slot reset --> driver unload\n"); + if (IS_PF(bp) && SHMEM2_HAS(bp, drv_capabilities_flag)) { + u32 v; + + v = SHMEM2_RD(bp, + drv_capabilities_flag[BP_FW_MB_IDX(bp)]); + SHMEM2_WR(bp, drv_capabilities_flag[BP_FW_MB_IDX(bp)], + v & ~DRV_FLAGS_CAPABILITIES_LOADED_L2); + } + bnx2x_drain_tx_queues(bp); + bnx2x_send_unload_req(bp, UNLOAD_RECOVERY); + bnx2x_netif_stop(bp, 1); + bnx2x_free_irq(bp); + + /* Report UNLOAD_DONE to MCP */ + bnx2x_send_unload_done(bp, true); + + bp->sp_state = 0; + bp->port.pmf = 0; + + bnx2x_prev_unload(bp); + + /* We should have resetted the engine, so It's fair to + * assume the FW will no longer write to the bnx2x driver. + */ + bnx2x_squeeze_objects(bp); + bnx2x_free_skbs(bp); + for_each_rx_queue(bp, i) + bnx2x_free_rx_sge_range(bp, bp->fp + i, NUM_RX_SGE); + bnx2x_free_fp_mem(bp); + bnx2x_free_mem(bp); + + bp->state = BNX2X_STATE_CLOSED; + } + rtnl_unlock();

return PCI_ERS_RESULT_RECOVERED; @@@ -12865,9 -12779,6 +12869,9 @@@ static void bnx2x_io_resume(struct pci_

bnx2x_eeh_recover(bp);

+ bp->fw_seq = SHMEM_RD(bp, func_mb[BP_FW_MB_IDX(bp)].drv_mb_header) & + DRV_MSG_SEQ_NUMBER_MASK; + if (netif_running(dev)) bnx2x_nic_load(bp, LOAD_NORMAL);

@@@ -12890,9 -12801,6 +12894,9 @@@ static struct pci_driver bnx2x_pci_driv .suspend = bnx2x_suspend, .resume = bnx2x_resume, .err_handler = &bnx2x_err_handler, +#ifdef CONFIG_BNX2X_SRIOV + .sriov_configure = bnx2x_sriov_configure, +#endif };

static int __init bnx2x_init(void) @@@ -13450,6 -13358,7 +13454,7 @@@ static int bnx2x_unregister_cnic(struc RCU_INIT_POINTER(bp->cnic_ops, NULL); mutex_unlock(&bp->cnic_mutex); synchronize_rcu(); + bp->cnic_enabled = false; kfree(bp->cnic_kwq); bp->cnic_kwq = NULL;

diff --combined drivers/net/ethernet/emulex/benet/be_main.c index 2180868,2886c9b..654e782 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@@ -1,5 -1,5 +1,5 @@@ /* - * Copyright (C) 2005 - 2011 Emulex + * Copyright (C) 2005 - 2013 Emulex * All rights reserved. * * This program is free software; you can redistribute it and/or @@@ -146,16 -146,20 +146,16 @@@ static int be_queue_alloc(struct be_ada q->entry_size = entry_size; mem->size = len * entry_size; mem->va = dma_alloc_coherent(&adapter->pdev->dev, mem->size, &mem->dma, - GFP_KERNEL); + GFP_KERNEL | __GFP_ZERO); if (!mem->va) return -ENOMEM; return 0; }

-static void be_intr_set(struct be_adapter *adapter, bool enable) +static void be_reg_intr_set(struct be_adapter *adapter, bool enable) { u32 reg, enabled;

- if (adapter->eeh_error) - return; - pci_read_config_dword(adapter->pdev, PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET, &reg); enabled = reg & MEMBAR_CTRL_INT_CTRL_HOSTINTR_MASK; @@@ -171,22 -175,6 +171,22 @@@ PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET, reg); }

+static void be_intr_set(struct be_adapter *adapter, bool enable) +{ + int status = 0; + + /* On lancer interrupts can't be controlled via this register */ + if (lancer_chip(adapter)) + return; + + if (adapter->eeh_error) + return; + + status = be_cmd_intr_set(adapter, enable); + if (status) + be_reg_intr_set(adapter, enable); +} + static void be_rxq_notify(struct be_adapter *adapter, u16 qid, u16 posted) { u32 val = 0; @@@ -197,15 -185,14 +197,15 @@@ iowrite32(val, adapter->db + DB_RQ_OFFSET); }

-static void be_txq_notify(struct be_adapter *adapter, u16 qid, u16 posted) +static void be_txq_notify(struct be_adapter *adapter, struct be_tx_obj *txo, + u16 posted) { u32 val = 0; - val |= qid & DB_TXULP_RING_ID_MASK; + val |= txo->q.id & DB_TXULP_RING_ID_MASK; val |= (posted & DB_TXULP_NUM_POSTED_MASK) << DB_TXULP_NUM_POSTED_SHIFT;

wmb(); - iowrite32(val, adapter->db + DB_TXULP1_OFFSET); + iowrite32(val, adapter->db + txo->db_offset); }

static void be_eq_notify(struct be_adapter *adapter, u16 qid, @@@ -772,8 -759,9 +772,9 @@@ static struct sk_buff *be_insert_vlan_i

if (vlan_tx_tag_present(skb)) { vlan_tag = be_get_tx_vlan_tag(adapter, skb); - __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); - skb->vlan_tci = 0; - skb = __vlan_put_tag(skb, vlan_tag); ++ skb = __vlan_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); + if (skb) + skb->vlan_tci = 0; }

return skb; @@@ -834,7 -822,7 +835,7 @@@ static netdev_tx_t be_xmit(struct sk_bu stopped = true; }

- be_txq_notify(adapter, txq->id, wrb_cnt); + be_txq_notify(adapter, txo, wrb_cnt);

be_tx_stats_update(txo, wrb_cnt, copied, gso_segs, stopped); } else { @@@ -903,7 -891,7 +904,7 @@@ set_vlan_promisc return status; }

-static int be_vlan_add_vid(struct net_device *netdev, u16 vid) +static int be_vlan_add_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct be_adapter *adapter = netdev_priv(netdev); int status = 0; @@@ -929,7 -917,7 +930,7 @@@ ret return status; }

-static int be_vlan_rem_vid(struct net_device *netdev, u16 vid) +static int be_vlan_rem_vid(struct net_device *netdev, __be16 proto, u16 vid) { struct be_adapter *adapter = netdev_priv(netdev); int status = 0; @@@ -1384,7 -1372,7 +1385,7 @@@ static void be_rx_compl_process(struct

if (rxcp->vlanf) - __vlan_hwaccel_put_tag(skb, rxcp->vlan_tag); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), rxcp->vlan_tag);

netif_receive_skb(skb); } @@@ -1440,7 -1428,7 +1441,7 @@@ void be_rx_compl_process_gro(struct be_ skb->rxhash = rxcp->rss_hash;

if (rxcp->vlanf) - __vlan_hwaccel_put_tag(skb, rxcp->vlan_tag); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), rxcp->vlan_tag);

napi_gro_frags(napi); } @@@ -1970,7 -1958,7 +1971,7 @@@ static int be_tx_qs_create(struct be_ad if (status) return status;

- status = be_cmd_txq_create(adapter, &txo->q, &txo->cq); + status = be_cmd_txq_create(adapter, txo); if (status) return status; } @@@ -2448,6 -2436,9 +2449,6 @@@ static int be_close(struct net_device *

be_roce_dev_close(adapter);

- if (!lancer_chip(adapter)) - be_intr_set(adapter, false); - for_all_evt_queues(adapter, eqo, i) napi_disable(&eqo->napi);

@@@ -2535,6 -2526,9 +2536,6 @@@ static int be_open(struct net_device *n

be_irq_register(adapter);

- if (!lancer_chip(adapter)) - be_intr_set(adapter, true); - for_all_rx_queues(adapter, rxo, i) be_cq_notify(adapter, rxo->cq.id, true, 0);

@@@ -2569,9 -2563,10 +2570,9 @@@ static int be_setup_wol(struct be_adapt

cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config); cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma, - GFP_KERNEL); + GFP_KERNEL | __GFP_ZERO); if (cmd.va == NULL) return -1; - memset(cmd.va, 0, cmd.size);

if (enable) { status = pci_write_config_dword(adapter->pdev, @@@ -2719,8 -2714,7 +2720,8 @@@ static int be_vfs_if_create(struct be_a

for_all_vfs(adapter, vf_cfg, vf) { if (!BE3_chip(adapter)) - be_cmd_get_profile_config(adapter, &cap_flags, vf + 1); + be_cmd_get_profile_config(adapter, &cap_flags, + NULL, vf + 1);

/* If a FW profile exists, then cap_flags are updated */ en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED | @@@ -2884,14 -2878,11 +2885,14 @@@ static void be_get_resources(struct be_ u16 dev_num_vfs; int pos, status; bool profile_present = false; + u16 txq_count = 0;

if (!BEx_chip(adapter)) { status = be_cmd_get_func_config(adapter); if (!status) profile_present = true; + } else if (BE3_chip(adapter) && be_physfn(adapter)) { + be_cmd_get_profile_config(adapter, NULL, &txq_count, 0); }

if (profile_present) { @@@ -2929,9 -2920,7 +2930,9 @@@ adapter->max_vlans = BE_NUM_VLANS_SUPPORTED;

adapter->max_mcast_mac = BE_MAX_MC; - adapter->max_tx_queues = MAX_TX_QS; + adapter->max_tx_queues = txq_count ? txq_count : MAX_TX_QS; + adapter->max_tx_queues = min_t(u16, adapter->max_tx_queues, + MAX_TX_QS); adapter->max_rss_queues = (adapter->be3_native) ? BE3_MAX_RSS_QS : BE2_MAX_RSS_QS; adapter->max_event_queues = BE3_MAX_RSS_QS; @@@ -2965,8 -2954,7 +2966,8 @@@ static int be_get_config(struct be_adap

status = be_cmd_query_fw_cfg(adapter, &adapter->port_num, &adapter->function_mode, - &adapter->function_caps); + &adapter->function_caps, + &adapter->asic_rev); if (status) goto err;

@@@ -3227,7 -3215,7 +3228,7 @@@ static int be_flash(struct be_adapter * return 0; }

-/* For BE2 and BE3 */ +/* For BE2, BE3 and BE3-R */ static int be_flash_BEx(struct be_adapter *adapter, const struct firmware *fw, struct be_dma_mem *flash_cmd, @@@ -3470,9 -3458,11 +3471,9 @@@ static int lancer_fw_download(struct be flash_cmd.size = sizeof(struct lancer_cmd_req_write_object) + LANCER_FW_DOWNLOAD_CHUNK; flash_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, flash_cmd.size, - &flash_cmd.dma, GFP_KERNEL); + &flash_cmd.dma, GFP_KERNEL); if (!flash_cmd.va) { status = -ENOMEM; - dev_err(&adapter->pdev->dev, - "Memory allocation failure while flashing\n"); goto lancer_fw_exit; }

@@@ -3540,22 -3530,18 +3541,22 @@@ lancer_fw_exit

#define UFI_TYPE2 2 #define UFI_TYPE3 3 +#define UFI_TYPE3R 10 #define UFI_TYPE4 4 static int be_get_ufi_type(struct be_adapter *adapter, - struct flash_file_hdr_g2 *fhdr) + struct flash_file_hdr_g3 *fhdr) { if (fhdr == NULL) goto be_get_ufi_exit;

if (skyhawk_chip(adapter) && fhdr->build[0] == '4') return UFI_TYPE4; - else if (BE3_chip(adapter) && fhdr->build[0] == '3') - return UFI_TYPE3; - else if (BE2_chip(adapter) && fhdr->build[0] == '2') + else if (BE3_chip(adapter) && fhdr->build[0] == '3') { + if (fhdr->asic_type_rev == 0x10) + return UFI_TYPE3R; + else + return UFI_TYPE3; + } else if (BE2_chip(adapter) && fhdr->build[0] == '2') return UFI_TYPE2;

be_get_ufi_exit: @@@ -3566,6 -3552,7 +3567,6 @@@

static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw) { - struct flash_file_hdr_g2 *fhdr; struct flash_file_hdr_g3 *fhdr3; struct image_hdr *img_hdr_ptr = NULL; struct be_dma_mem flash_cmd; @@@ -3577,41 -3564,29 +3578,41 @@@ &flash_cmd.dma, GFP_KERNEL); if (!flash_cmd.va) { status = -ENOMEM; - dev_err(&adapter->pdev->dev, - "Memory allocation failure while flashing\n"); goto be_fw_exit; }

p = fw->data; - fhdr = (struct flash_file_hdr_g2 *)p; + fhdr3 = (struct flash_file_hdr_g3 *)p;

- ufi_type = be_get_ufi_type(adapter, fhdr); + ufi_type = be_get_ufi_type(adapter, fhdr3);

- fhdr3 = (struct flash_file_hdr_g3 *)fw->data; num_imgs = le32_to_cpu(fhdr3->num_imgs); for (i = 0; i < num_imgs; i++) { img_hdr_ptr = (struct image_hdr *)(fw->data + (sizeof(struct flash_file_hdr_g3) + i * sizeof(struct image_hdr))); if (le32_to_cpu(img_hdr_ptr->imageid) == 1) { - if (ufi_type == UFI_TYPE4) + switch (ufi_type) { + case UFI_TYPE4: status = be_flash_skyhawk(adapter, fw, &flash_cmd, num_imgs); - else if (ufi_type == UFI_TYPE3) + break; + case UFI_TYPE3R: status = be_flash_BEx(adapter, fw, &flash_cmd, num_imgs); + break; + case UFI_TYPE3: + /* Do not flash this ufi on BE3-R cards */ + if (adapter->asic_rev < 0x10) + status = be_flash_BEx(adapter, fw, + &flash_cmd, + num_imgs); + else { + status = -1; + dev_err(&adapter->pdev->dev, + "Can't load BE3 UFI on BE3R\n"); + } + } } }

@@@ -3688,12 -3663,12 +3689,12 @@@ static void be_netdev_init(struct net_d

netdev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | - NETIF_F_HW_VLAN_TX; + NETIF_F_HW_VLAN_CTAG_TX; if (be_multi_rxq(adapter)) netdev->hw_features |= NETIF_F_RXHASH;

netdev->features |= netdev->hw_features | - NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER; + NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER;

netdev->vlan_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; @@@ -3817,13 -3792,12 +3818,13 @@@ static int be_ctrl_init(struct be_adapt

rx_filter->size = sizeof(struct be_cmd_req_rx_filter); rx_filter->va = dma_alloc_coherent(&adapter->pdev->dev, rx_filter->size, - &rx_filter->dma, GFP_KERNEL); + &rx_filter->dma, + GFP_KERNEL | __GFP_ZERO); if (rx_filter->va == NULL) { status = -ENOMEM; goto free_mbox; } - memset(rx_filter->va, 0, rx_filter->size); + mutex_init(&adapter->mbox_lock); spin_lock_init(&adapter->mcc_lock); spin_lock_init(&adapter->mcc_cq_lock); @@@ -3865,9 -3839,10 +3866,9 @@@ static int be_stats_init(struct be_adap cmd->size = sizeof(struct be_cmd_req_get_stats_v1);

cmd->va = dma_alloc_coherent(&adapter->pdev->dev, cmd->size, &cmd->dma, - GFP_KERNEL); + GFP_KERNEL | __GFP_ZERO); if (cmd->va == NULL) return -1; - memset(cmd->va, 0, cmd->size); return 0; }

@@@ -3879,7 -3854,6 +3880,7 @@@ static void be_remove(struct pci_dev *p return;

be_roce_dev_remove(adapter); + be_intr_set(adapter, false);

cancel_delayed_work_sync(&adapter->func_recovery_work);

@@@ -4134,11 -4108,6 +4135,11 @@@ static int be_probe(struct pci_dev *pde

status = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); if (!status) { + status = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); + if (status < 0) { + dev_err(&pdev->dev, "dma_set_coherent_mask failed\n"); + goto free_netdev; + } netdev->features |= NETIF_F_HIGHDMA; } else { status = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); @@@ -4174,11 -4143,11 +4175,11 @@@ goto ctrl_clean; }

- /* The INTR bit may be set in the card when probed by a kdump kernel - * after a crash. - */ - if (!lancer_chip(adapter)) - be_intr_set(adapter, false); + /* Wait for interrupts to quiesce after an FLR */ + msleep(100); + + /* Allow interrupts for other ULPs running on NIC function */ + be_intr_set(adapter, true);

status = be_stats_init(adapter); if (status) diff --combined drivers/net/ethernet/freescale/fec_main.c index 2089087,73195f6..2451ab1 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@@ -29,6 -29,7 +29,6 @@@ #include <linux/ioport.h> #include <linux/slab.h> #include <linux/interrupt.h> -#include <linux/pci.h> #include <linux/init.h> #include <linux/delay.h> #include <linux/netdevice.h> @@@ -52,6 -53,11 +52,6 @@@

#include <asm/cacheflush.h>

-#ifndef CONFIG_ARM -#include <asm/coldfire.h> -#include <asm/mcfsim.h> -#endif - #include "fec.h"

#if defined(CONFIG_ARM) @@@ -101,9 -107,6 +101,9 @@@ static struct platform_device_id fec_de .driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT | FEC_QUIRK_HAS_BUFDESC_EX, }, { + .name = "mvf-fec", + .driver_data = FEC_QUIRK_ENET_MAC, + }, { /* sentinel */ } }; @@@ -114,7 -117,6 +114,7 @@@ enum imx_fec_type IMX27_FEC, /* runs on i.mx27/35/51 */ IMX28_FEC, IMX6Q_FEC, + MVF_FEC, };

static const struct of_device_id fec_dt_ids[] = { @@@ -122,7 -124,6 +122,7 @@@ { .compatible = "fsl,imx27-fec", .data = &fec_devtype[IMX27_FEC], }, { .compatible = "fsl,imx28-fec", .data = &fec_devtype[IMX28_FEC], }, { .compatible = "fsl,imx6q-fec", .data = &fec_devtype[IMX6Q_FEC], }, + { .compatible = "fsl,mvf-fec", .data = &fec_devtype[MVF_FEC], }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, fec_dt_ids); @@@ -261,7 -262,7 +261,7 @@@ fec_enet_start_xmit(struct sk_buff *skb /* Ooops. All transmit buffers are full. Bail out. * This should not happen, since ndev->tbusy should be set. */ - printk("%s: tx queue full!.\n", ndev->name); + netdev_err(ndev, "tx queue full!\n"); return NETDEV_TX_BUSY; }

@@@ -573,7 -574,7 +573,7 @@@ fec_stop(struct net_device *ndev writel(1, fep->hwp + FEC_X_CNTRL); /* Graceful transmit stop */ udelay(10); if (!(readl(fep->hwp + FEC_IEVENT) & FEC_ENET_GRA)) - printk("fec_stop : Graceful transmit stop did not complete !\n"); + netdev_err(ndev, "Graceful transmit stop did not complete!\n"); }

/* Whack a reset. We should wait for this. */ @@@ -671,7 -672,7 +671,7 @@@ fec_enet_tx(struct net_device *ndev }

if (status & BD_ENET_TX_READY) - printk("HEY! Enet xmit interrupt and TX_READY.\n"); + netdev_err(ndev, "HEY! Enet xmit interrupt and TX_READY\n");

/* Deferred means some collisions occurred during transmit, * but we eventually sent the packet OK. @@@ -739,7 -740,7 +739,7 @@@ fec_enet_rx(struct net_device *ndev, in * the last indicator should be set. */ if ((status & BD_ENET_RX_LAST) == 0) - printk("FEC ENET: rcv is not +last\n"); + netdev_err(ndev, "rcv is not +last\n");

if (!fep->opened) goto rx_processing_done; @@@ -790,6 -791,8 +790,6 @@@ skb = netdev_alloc_skb(ndev, pkt_len - 4 + NET_IP_ALIGN);

if (unlikely(!skb)) { - printk("%s: Memory squeeze, dropping packet.\n", - ndev->name); ndev->stats.rx_dropped++; } else { skb_reserve(skb, NET_IP_ALIGN); @@@ -913,6 -916,7 +913,6 @@@ static void fec_get_mac(struct net_devi */ iap = macaddr;

-#ifdef CONFIG_OF /* * 2) from device tree data */ @@@ -924,6 -928,7 +924,6 @@@ iap = (unsigned char *) mac; } } -#endif

/* * 3) from flash or fuse (via platform data) @@@ -997,6 -1002,7 +997,7 @@@ static void fec_enet_adjust_link(struc } else { if (fep->link) { fec_stop(ndev); + fep->link = phy_dev->link; status_change = 1; } } @@@ -1026,7 -1032,7 +1027,7 @@@ static int fec_enet_mdio_read(struct mi usecs_to_jiffies(FEC_MII_TIMEOUT)); if (time_left == 0) { fep->mii_timeout = 1; - printk(KERN_ERR "FEC: MDIO read timeout\n"); + netdev_err(fep->netdev, "MDIO read timeout\n"); return -ETIMEDOUT; }

@@@ -1054,7 -1060,7 +1055,7 @@@ static int fec_enet_mdio_write(struct m usecs_to_jiffies(FEC_MII_TIMEOUT)); if (time_left == 0) { fep->mii_timeout = 1; - printk(KERN_ERR "FEC: MDIO write timeout\n"); + netdev_err(fep->netdev, "MDIO write timeout\n"); return -ETIMEDOUT; }

@@@ -1094,7 -1100,9 +1095,7 @@@ static int fec_enet_mii_probe(struct ne }

if (phy_id >= PHY_MAX_ADDR) { - printk(KERN_INFO - "%s: no PHY, assuming direct connection to switch\n", - ndev->name); + netdev_info(ndev, "no PHY, assuming direct connection to switch\n"); strncpy(mdio_bus_id, "fixed-0", MII_BUS_ID_SIZE); phy_id = 0; } @@@ -1103,7 -1111,7 +1104,7 @@@ phy_dev = phy_connect(ndev, phy_name, &fec_enet_adjust_link, fep->phy_interface); if (IS_ERR(phy_dev)) { - printk(KERN_ERR "%s: could not attach to PHY\n", ndev->name); + netdev_err(ndev, "could not attach to PHY\n"); return PTR_ERR(phy_dev); }

@@@ -1121,9 -1129,11 +1122,9 @@@ fep->link = 0; fep->full_duplex = 0;

- printk(KERN_INFO - "%s: Freescale FEC PHY driver [%s] (mii_bus:phy_addr=%s, irq=%d)\n", - ndev->name, - fep->phy_dev->drv->name, dev_name(&fep->phy_dev->dev), - fep->phy_dev->irq); + netdev_info(ndev, "Freescale FEC PHY driver [%s] (mii_bus:phy_addr=%s, irq=%d)\n", + fep->phy_dev->drv->name, dev_name(&fep->phy_dev->dev), + fep->phy_dev->irq);

return 0; } @@@ -1433,7 -1443,7 +1434,7 @@@ static int fec_enet_alloc_buffers(struc

if (fep->bufdesc_ex) { struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp; - ebdp->cbd_esc = BD_ENET_RX_INT; + ebdp->cbd_esc = BD_ENET_TX_INT; }

bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex); @@@ -1598,7 -1608,7 +1599,7 @@@ fec_set_mac_address(struct net_device * * Polled functionality used by netconsole and others in non interrupt mode * */ -void fec_poll_controller(struct net_device *dev) +static void fec_poll_controller(struct net_device *dev) { int i; struct fec_enet_private *fep = netdev_priv(dev); @@@ -1639,9 -1649,11 +1640,9 @@@ static int fec_enet_init(struct net_dev

/* Allocate memory for buffer descriptors. */ cbd_base = dma_alloc_coherent(NULL, PAGE_SIZE, &fep->bd_dma, - GFP_KERNEL); - if (!cbd_base) { - printk("FEC: allocate descriptor memory failed?\n"); + GFP_KERNEL); + if (!cbd_base) return -ENOMEM; - }

memset(cbd_base, 0, PAGE_SIZE); spin_lock_init(&fep->hw_lock); @@@ -1673,6 -1685,16 +1674,6 @@@ }

#ifdef CONFIG_OF -static int fec_get_phy_mode_dt(struct platform_device *pdev) -{ - struct device_node *np = pdev->dev.of_node; - - if (np) - return of_get_phy_mode(np); - - return -ENODEV; -} - static void fec_reset_phy(struct platform_device *pdev) { int err, phy_reset; @@@ -1701,6 -1723,11 +1702,6 @@@ gpio_set_value(phy_reset, 1); } #else /* CONFIG_OF */ -static int fec_get_phy_mode_dt(struct platform_device *pdev) -{ - return -ENODEV; -} - static void fec_reset_phy(struct platform_device *pdev) { /* @@@ -1731,10 -1758,16 +1732,10 @@@ fec_probe(struct platform_device *pdev if (!r) return -ENXIO;

- r = request_mem_region(r->start, resource_size(r), pdev->name); - if (!r) - return -EBUSY; - /* Init network device */ ndev = alloc_etherdev(sizeof(struct fec_enet_private)); - if (!ndev) { - ret = -ENOMEM; - goto failed_alloc_etherdev; - } + if (!ndev) + return -ENOMEM;

SET_NETDEV_DEV(ndev, &pdev->dev);

@@@ -1746,7 -1779,7 +1747,7 @@@ (pdev->id_entry->driver_data & FEC_QUIRK_HAS_GBIT)) fep->pause_flag |= FEC_PAUSE_FLAG_AUTONEG;

- fep->hwp = ioremap(r->start, resource_size(r)); + fep->hwp = devm_request_and_ioremap(&pdev->dev, r); fep->pdev = pdev; fep->dev_id = dev_id++;

@@@ -1759,7 -1792,7 +1760,7 @@@

platform_set_drvdata(pdev, ndev);

- ret = fec_get_phy_mode_dt(pdev); + ret = of_get_phy_mode(pdev->dev.of_node); if (ret < 0) { pdata = pdev->dev.platform_data; if (pdata) @@@ -1849,9 -1882,6 +1850,9 @@@ if (ret) goto failed_register;

+ if (fep->bufdesc_ex && fep->ptp_clock) + netdev_info(ndev, "registered PHC device %d\n", fep->dev_id); + return 0;

failed_register: @@@ -1871,8 -1901,11 +1872,8 @@@ failed_regulator clk_disable_unprepare(fep->clk_ptp); failed_pin: failed_clk: - iounmap(fep->hwp); failed_ioremap: free_netdev(ndev); -failed_alloc_etherdev: - release_mem_region(r->start, resource_size(r));

return ret; } @@@ -1882,6 -1915,7 +1883,6 @@@ fec_drv_remove(struct platform_device * { struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); - struct resource *r; int i;

unregister_netdev(ndev); @@@ -1897,14 -1931,19 +1898,14 @@@ if (irq > 0) free_irq(irq, ndev); } - iounmap(fep->hwp); free_netdev(ndev);

- r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - BUG_ON(!r); - release_mem_region(r->start, resource_size(r)); - platform_set_drvdata(pdev, NULL);

return 0; }

-#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static int fec_suspend(struct device *dev) { @@@ -1936,15 -1975,24 +1937,15 @@@ fec_resume(struct device *dev

return 0; } +#endif /* CONFIG_PM_SLEEP */

-static const struct dev_pm_ops fec_pm_ops = { - .suspend = fec_suspend, - .resume = fec_resume, - .freeze = fec_suspend, - .thaw = fec_resume, - .poweroff = fec_suspend, - .restore = fec_resume, -}; -#endif +static SIMPLE_DEV_PM_OPS(fec_pm_ops, fec_suspend, fec_resume);

static struct platform_driver fec_driver = { .driver = { .name = DRIVER_NAME, .owner = THIS_MODULE, -#ifdef CONFIG_PM .pm = &fec_pm_ops, -#endif .of_match_table = fec_dt_ids, }, .id_table = fec_devtype, diff --combined drivers/net/ethernet/intel/igb/igb.h index c92115e,ab577a7..9d6c075 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@@ -44,54 -44,54 +44,54 @@@

struct igb_adapter;

-#define E1000_PCS_CFG_IGN_SD 1 +#define E1000_PCS_CFG_IGN_SD 1

/* Interrupt defines */ -#define IGB_START_ITR 648 /* ~6000 ints/sec */ -#define IGB_4K_ITR 980 -#define IGB_20K_ITR 196 -#define IGB_70K_ITR 56 +#define IGB_START_ITR 648 /* ~6000 ints/sec */ +#define IGB_4K_ITR 980 +#define IGB_20K_ITR 196 +#define IGB_70K_ITR 56

/* TX/RX descriptor defines */ -#define IGB_DEFAULT_TXD 256 -#define IGB_DEFAULT_TX_WORK 128 -#define IGB_MIN_TXD 80 -#define IGB_MAX_TXD 4096 +#define IGB_DEFAULT_TXD 256 +#define IGB_DEFAULT_TX_WORK 128 +#define IGB_MIN_TXD 80 +#define IGB_MAX_TXD 4096

-#define IGB_DEFAULT_RXD 256 -#define IGB_MIN_RXD 80 -#define IGB_MAX_RXD 4096 +#define IGB_DEFAULT_RXD 256 +#define IGB_MIN_RXD 80 +#define IGB_MAX_RXD 4096

-#define IGB_DEFAULT_ITR 3 /* dynamic */ -#define IGB_MAX_ITR_USECS 10000 -#define IGB_MIN_ITR_USECS 10 -#define NON_Q_VECTORS 1 -#define MAX_Q_VECTORS 8 +#define IGB_DEFAULT_ITR 3 /* dynamic */ +#define IGB_MAX_ITR_USECS 10000 +#define IGB_MIN_ITR_USECS 10 +#define NON_Q_VECTORS 1 +#define MAX_Q_VECTORS 8

/* Transmit and receive queues */ -#define IGB_MAX_RX_QUEUES 8 -#define IGB_MAX_RX_QUEUES_82575 4 -#define IGB_MAX_RX_QUEUES_I211 2 -#define IGB_MAX_TX_QUEUES 8 -#define IGB_MAX_VF_MC_ENTRIES 30 -#define IGB_MAX_VF_FUNCTIONS 8 -#define IGB_MAX_VFTA_ENTRIES 128 -#define IGB_82576_VF_DEV_ID 0x10CA -#define IGB_I350_VF_DEV_ID 0x1520 +#define IGB_MAX_RX_QUEUES 8 +#define IGB_MAX_RX_QUEUES_82575 4 +#define IGB_MAX_RX_QUEUES_I211 2 +#define IGB_MAX_TX_QUEUES 8 +#define IGB_MAX_VF_MC_ENTRIES 30 +#define IGB_MAX_VF_FUNCTIONS 8 +#define IGB_MAX_VFTA_ENTRIES 128 +#define IGB_82576_VF_DEV_ID 0x10CA +#define IGB_I350_VF_DEV_ID 0x1520

/* NVM version defines */ -#define IGB_MAJOR_MASK 0xF000 -#define IGB_MINOR_MASK 0x0FF0 -#define IGB_BUILD_MASK 0x000F -#define IGB_COMB_VER_MASK 0x00FF -#define IGB_MAJOR_SHIFT 12 -#define IGB_MINOR_SHIFT 4 -#define IGB_COMB_VER_SHFT 8 -#define IGB_NVM_VER_INVALID 0xFFFF -#define IGB_ETRACK_SHIFT 16 -#define NVM_ETRACK_WORD 0x0042 -#define NVM_COMB_VER_OFF 0x0083 -#define NVM_COMB_VER_PTR 0x003d +#define IGB_MAJOR_MASK 0xF000 +#define IGB_MINOR_MASK 0x0FF0 +#define IGB_BUILD_MASK 0x000F +#define IGB_COMB_VER_MASK 0x00FF +#define IGB_MAJOR_SHIFT 12 +#define IGB_MINOR_SHIFT 4 +#define IGB_COMB_VER_SHFT 8 +#define IGB_NVM_VER_INVALID 0xFFFF +#define IGB_ETRACK_SHIFT 16 +#define NVM_ETRACK_WORD 0x0042 +#define NVM_COMB_VER_OFF 0x0083 +#define NVM_COMB_VER_PTR 0x003d

struct vf_data_storage { unsigned char vf_mac_addresses[ETH_ALEN]; @@@ -103,7 -103,6 +103,7 @@@ u16 pf_vlan; /* When set, guest VLAN config not allowed. */ u16 pf_qos; u16 tx_rate; + bool spoofchk_enabled; };

#define IGB_VF_FLAG_CTS 0x00000001 /* VF is clear to send data */ @@@ -122,14 -121,14 +122,14 @@@ * descriptors until either it has this many to write back, or the * ITR timer expires. */ -#define IGB_RX_PTHRESH 8 -#define IGB_RX_HTHRESH 8 -#define IGB_TX_PTHRESH 8 -#define IGB_TX_HTHRESH 1 -#define IGB_RX_WTHRESH ((hw->mac.type == e1000_82576 && \ - adapter->msix_entries) ? 1 : 4) -#define IGB_TX_WTHRESH ((hw->mac.type == e1000_82576 && \ - adapter->msix_entries) ? 1 : 16) +#define IGB_RX_PTHRESH ((hw->mac.type == e1000_i354) ? 12 : 8) +#define IGB_RX_HTHRESH 8 +#define IGB_TX_PTHRESH ((hw->mac.type == e1000_i354) ? 20 : 8) +#define IGB_TX_HTHRESH 1 +#define IGB_RX_WTHRESH ((hw->mac.type == e1000_82576 && \ + adapter->msix_entries) ? 1 : 4) +#define IGB_TX_WTHRESH ((hw->mac.type == e1000_82576 && \ + adapter->msix_entries) ? 1 : 16)

/* this is the size past which hardware will drop packets when setting LPE=0 */ #define MAXIMUM_ETHERNET_VLAN_SIZE 1522 @@@ -141,17 -140,17 +141,17 @@@ #define IGB_RX_BUFSZ IGB_RXBUFFER_2048

/* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define IGB_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define IGB_RX_BUFFER_WRITE 16 /* Must be power of 2 */

-#define AUTO_ALL_MODES 0 -#define IGB_EEPROM_APME 0x0400 +#define AUTO_ALL_MODES 0 +#define IGB_EEPROM_APME 0x0400

#ifndef IGB_MASTER_SLAVE /* Switch to override PHY master/slave setting */ #define IGB_MASTER_SLAVE e1000_ms_hw_default #endif

-#define IGB_MNG_VLAN_NONE -1 +#define IGB_MNG_VLAN_NONE -1

enum igb_tx_flags { /* cmd_type flags */ @@@ -165,10 -164,11 +165,10 @@@ };

/* VLAN info */ -#define IGB_TX_FLAGS_VLAN_MASK 0xffff0000 +#define IGB_TX_FLAGS_VLAN_MASK 0xffff0000 #define IGB_TX_FLAGS_VLAN_SHIFT 16

-/* - * The largest size we can write to the descriptor is 65535. In order to +/* The largest size we can write to the descriptor is 65535. In order to * maintain a power of two alignment we have to limit ourselves to 32K. */ #define IGB_MAX_TXD_PWR 15 @@@ -178,17 -178,8 +178,17 @@@ #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IGB_MAX_DATA_PER_TXD) #define DESC_NEEDED (MAX_SKB_FRAGS + 4)

+/* EEPROM byte offsets */ +#define IGB_SFF_8472_SWAP 0x5C +#define IGB_SFF_8472_COMP 0x5E + +/* Bitmasks */ +#define IGB_SFF_ADDRESSING_MODE 0x4 +#define IGB_SFF_8472_UNSUP 0x00 + /* wrapper around a pointer to a socket buffer, - * so a DMA handle can be stored along with the buffer */ + * so a DMA handle can be stored along with the buffer + */ struct igb_tx_buffer { union e1000_adv_tx_desc *next_to_watch; unsigned long time_stamp; @@@ -293,25 -284,17 +293,17 @@@ struct igb_q_vector enum e1000_ring_flags_t { IGB_RING_FLAG_RX_SCTP_CSUM, IGB_RING_FLAG_RX_LB_VLAN_BSWAP, - IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, IGB_RING_FLAG_TX_CTX_IDX, IGB_RING_FLAG_TX_DETECT_HANG };

- #define ring_uses_build_skb(ring) \ - test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) - #define set_ring_build_skb_enabled(ring) \ - set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) - #define clear_ring_build_skb_enabled(ring) \ - clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) - #define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS)

-#define IGB_RX_DESC(R, i) \ +#define IGB_RX_DESC(R, i) \ (&(((union e1000_adv_rx_desc *)((R)->desc))[i])) -#define IGB_TX_DESC(R, i) \ +#define IGB_TX_DESC(R, i) \ (&(((union e1000_adv_tx_desc *)((R)->desc))[i])) -#define IGB_TX_CTXTDESC(R, i) \ +#define IGB_TX_CTXTDESC(R, i) \ (&(((struct e1000_adv_tx_context_desc *)((R)->desc))[i]))

/* igb_test_staterr - tests bits within Rx descriptor status and error fields */ @@@ -470,12 -453,12 +462,12 @@@ struct igb_adapter #define IGB_FLAG_WOL_SUPPORTED (1 << 8)

/* DMA Coalescing defines */ -#define IGB_MIN_TXPBSIZE 20408 -#define IGB_TX_BUF_4096 4096 -#define IGB_DMCTLX_DCFLUSH_DIS 0x80000000 /* Disable DMA Coal Flush */ +#define IGB_MIN_TXPBSIZE 20408 +#define IGB_TX_BUF_4096 4096 +#define IGB_DMCTLX_DCFLUSH_DIS 0x80000000 /* Disable DMA Coal Flush */

-#define IGB_82576_TSYNC_SHIFT 19 -#define IGB_TS_HDR_LEN 16 +#define IGB_82576_TSYNC_SHIFT 19 +#define IGB_TS_HDR_LEN 16 enum e1000_state_t { __IGB_TESTING, __IGB_RESETTING, diff --combined drivers/net/ethernet/intel/igb/igb_main.c index 9bf08b9,64f7529..dcaa354 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@@ -77,9 -77,6 +77,9 @@@ static const struct e1000_info *igb_inf };

static DEFINE_PCI_DEVICE_TABLE(igb_pci_tbl) = { + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I354_BACKPLANE_1GBPS) }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I354_SGMII) }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_I354_BACKPLANE_2_5GBPS) }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I211_COPPER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_COPPER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_I210_FIBER), board_82575 }, @@@ -159,8 -156,8 +159,8 @@@ static int igb_ioctl(struct net_device static void igb_tx_timeout(struct net_device *); static void igb_reset_task(struct work_struct *); static void igb_vlan_mode(struct net_device *netdev, netdev_features_t features); -static int igb_vlan_rx_add_vid(struct net_device *, u16); -static int igb_vlan_rx_kill_vid(struct net_device *, u16); +static int igb_vlan_rx_add_vid(struct net_device *, __be16, u16); +static int igb_vlan_rx_kill_vid(struct net_device *, __be16, u16); static void igb_restore_vlan(struct igb_adapter *); static void igb_rar_set_qsel(struct igb_adapter *, u8 *, u32 , u8); static void igb_ping_all_vfs(struct igb_adapter *); @@@ -172,8 -169,6 +172,8 @@@ static int igb_ndo_set_vf_mac(struct ne static int igb_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos); static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate); +static int igb_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, + bool setting); static int igb_ndo_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivi); static void igb_check_vf_rate_limit(struct igb_adapter *); @@@ -297,7 -292,9 +297,7 @@@ static const struct igb_reg_info igb_re {} };

-/* - * igb_regdump - register printout routine - */ +/* igb_regdump - register printout routine */ static void igb_regdump(struct e1000_hw *hw, struct igb_reg_info *reginfo) { int n = 0; @@@ -363,7 -360,9 +363,7 @@@ regs[2], regs[3]); }

-/* - * igb_dump - Print registers, tx-rings and rx-rings - */ +/* igb_dump - Print registers, Tx-rings and Rx-rings */ static void igb_dump(struct igb_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@@ -570,13 -569,12 +570,13 @@@ exit return; }

-/* igb_get_i2c_data - Reads the I2C SDA data bit +/** + * igb_get_i2c_data - Reads the I2C SDA data bit * @hw: pointer to hardware structure * @i2cctl: Current value of I2CCTL register * * Returns the I2C data bit value - */ + **/ static int igb_get_i2c_data(void *data) { struct igb_adapter *adapter = (struct igb_adapter *)data; @@@ -586,13 -584,12 +586,13 @@@ return ((i2cctl & E1000_I2C_DATA_IN) != 0); }

-/* igb_set_i2c_data - Sets the I2C data bit +/** + * igb_set_i2c_data - Sets the I2C data bit * @data: pointer to hardware structure * @state: I2C data value (0 or 1) to set * * Sets the I2C data bit - */ + **/ static void igb_set_i2c_data(void *data, int state) { struct igb_adapter *adapter = (struct igb_adapter *)data; @@@ -611,13 -608,12 +611,13 @@@

}

-/* igb_set_i2c_clk - Sets the I2C SCL clock +/** + * igb_set_i2c_clk - Sets the I2C SCL clock * @data: pointer to hardware structure * @state: state to set clock * * Sets the I2C clock line to state - */ + **/ static void igb_set_i2c_clk(void *data, int state) { struct igb_adapter *adapter = (struct igb_adapter *)data; @@@ -635,12 -631,11 +635,12 @@@ wrfl(); }

-/* igb_get_i2c_clk - Gets the I2C SCL clock state +/** + * igb_get_i2c_clk - Gets the I2C SCL clock state * @data: pointer to hardware structure * * Gets the I2C clock state - */ + **/ static int igb_get_i2c_clk(void *data) { struct igb_adapter *adapter = (struct igb_adapter *)data; @@@ -660,10 -655,8 +660,10 @@@ static const struct i2c_algo_bit_data i };

/** - * igb_get_hw_dev - return device - * used by hardware layer to print debugging information + * igb_get_hw_dev - return device + * @hw: pointer to hardware structure + * + * used by hardware layer to print debugging information **/ struct net_device *igb_get_hw_dev(struct e1000_hw *hw) { @@@ -672,10 -665,10 +672,10 @@@ }

/** - * igb_init_module - Driver Registration Routine + * igb_init_module - Driver Registration Routine * - * igb_init_module is the first routine called when the driver is - * loaded. All it does is register with the PCI subsystem. + * igb_init_module is the first routine called when the driver is + * loaded. All it does is register with the PCI subsystem. **/ static int __init igb_init_module(void) { @@@ -695,10 -688,10 +695,10 @@@ module_init(igb_init_module);

/** - * igb_exit_module - Driver Exit Cleanup Routine + * igb_exit_module - Driver Exit Cleanup Routine * - * igb_exit_module is called just before the driver is removed - * from memory. + * igb_exit_module is called just before the driver is removed + * from memory. **/ static void __exit igb_exit_module(void) { @@@ -712,11 -705,11 +712,11 @@@ module_exit(igb_exit_module)

#define Q_IDX_82576(i) (((i & 0x1) << 3) + (i >> 1)) /** - * igb_cache_ring_register - Descriptor ring to register mapping - * @adapter: board private structure to initialize + * igb_cache_ring_register - Descriptor ring to register mapping + * @adapter: board private structure to initialize * - * Once we know the feature-set enabled for the device, we'll cache - * the register offset the descriptor ring is assigned to. + * Once we know the feature-set enabled for the device, we'll cache + * the register offset the descriptor ring is assigned to. **/ static void igb_cache_ring_register(struct igb_adapter *adapter) { @@@ -733,12 -726,11 +733,12 @@@ if (adapter->vfs_allocated_count) { for (; i < adapter->rss_queues; i++) adapter->rx_ring[i]->reg_idx = rbase_offset + - Q_IDX_82576(i); + Q_IDX_82576(i); } case e1000_82575: case e1000_82580: case e1000_i350: + case e1000_i354: case e1000_i210: case e1000_i211: default: @@@ -793,10 -785,9 +793,10 @@@ static void igb_assign_vector(struct ig switch (hw->mac.type) { case e1000_82575: /* The 82575 assigns vectors using a bitmask, which matches the - bitmask for the EICR/EIMS/EIMC registers. To assign one - or more queues to a vector, we write the appropriate bits - into the MSIXBM register for that vector. */ + * bitmask for the EICR/EIMS/EIMC registers. To assign one + * or more queues to a vector, we write the appropriate bits + * into the MSIXBM register for that vector. + */ if (rx_queue > IGB_N0_QUEUE) msixbm = E1000_EICR_RX_QUEUE0 << rx_queue; if (tx_queue > IGB_N0_QUEUE) @@@ -807,7 -798,8 +807,7 @@@ q_vector->eims_value = msixbm; break; case e1000_82576: - /* - * 82576 uses a table that essentially consists of 2 columns + /* 82576 uses a table that essentially consists of 2 columns * with 8 rows. The ordering is column-major so we use the * lower 3 bits as the row index, and the 4th bit as the * column offset. @@@ -824,10 -816,10 +824,10 @@@ break; case e1000_82580: case e1000_i350: + case e1000_i354: case e1000_i210: case e1000_i211: - /* - * On 82580 and newer adapters the scheme is similar to 82576 + /* On 82580 and newer adapters the scheme is similar to 82576 * however instead of ordering column-major we have things * ordered row-major. So we traverse the table by using * bit 0 as the column offset, and the remaining bits as the @@@ -856,11 -848,10 +856,11 @@@ }

/** - * igb_configure_msix - Configure MSI-X hardware + * igb_configure_msix - Configure MSI-X hardware + * @adapter: board private structure to initialize * - * igb_configure_msix sets up the hardware to properly - * generate MSI-X interrupts. + * igb_configure_msix sets up the hardware to properly + * generate MSI-X interrupts. **/ static void igb_configure_msix(struct igb_adapter *adapter) { @@@ -884,7 -875,8 +884,7 @@@ wr32(E1000_CTRL_EXT, tmp);

/* enable msix_other interrupt */ - array_wr32(E1000_MSIXBM(0), vector++, - E1000_EIMS_OTHER); + array_wr32(E1000_MSIXBM(0), vector++, E1000_EIMS_OTHER); adapter->eims_other = E1000_EIMS_OTHER;

break; @@@ -892,15 -884,13 +892,15 @@@ case e1000_82576: case e1000_82580: case e1000_i350: + case e1000_i354: case e1000_i210: case e1000_i211: /* Turn on MSI-X capability first, or our settings - * won't stick. And it will take days to debug. */ + * won't stick. And it will take days to debug. + */ wr32(E1000_GPIE, E1000_GPIE_MSIX_MODE | - E1000_GPIE_PBA | E1000_GPIE_EIAME | - E1000_GPIE_NSICR); + E1000_GPIE_PBA | E1000_GPIE_EIAME | + E1000_GPIE_NSICR);

/* enable msix_other interrupt */ adapter->eims_other = 1 << vector; @@@ -922,11 -912,10 +922,11 @@@ }

/** - * igb_request_msix - Initialize MSI-X interrupts + * igb_request_msix - Initialize MSI-X interrupts + * @adapter: board private structure to initialize * - * igb_request_msix allocates MSI-X vectors and requests interrupts from the - * kernel. + * igb_request_msix allocates MSI-X vectors and requests interrupts from the + * kernel. **/ static int igb_request_msix(struct igb_adapter *adapter) { @@@ -935,7 -924,7 +935,7 @@@ int i, err = 0, vector = 0, free_vector = 0;

err = request_irq(adapter->msix_entries[vector].vector, - igb_msix_other, 0, netdev->name, adapter); + igb_msix_other, 0, netdev->name, adapter); if (err) goto err_out;

@@@ -959,8 -948,8 +959,8 @@@ sprintf(q_vector->name, "%s-unused", netdev->name);

err = request_irq(adapter->msix_entries[vector].vector, - igb_msix_ring, 0, q_vector->name, - q_vector); + igb_msix_ring, 0, q_vector->name, + q_vector); if (err) goto err_free; } @@@ -993,13 -982,13 +993,13 @@@ static void igb_reset_interrupt_capabil }

/** - * igb_free_q_vector - Free memory allocated for specific interrupt vector - * @adapter: board private structure to initialize - * @v_idx: Index of vector to be freed + * igb_free_q_vector - Free memory allocated for specific interrupt vector + * @adapter: board private structure to initialize + * @v_idx: Index of vector to be freed * - * This function frees the memory allocated to the q_vector. In addition if - * NAPI is enabled it will delete any references to the NAPI struct prior - * to freeing the q_vector. + * This function frees the memory allocated to the q_vector. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. **/ static void igb_free_q_vector(struct igb_adapter *adapter, int v_idx) { @@@ -1014,19 -1003,20 +1014,19 @@@ adapter->q_vector[v_idx] = NULL; netif_napi_del(&q_vector->napi);

- /* - * ixgbe_get_stats64() might access the rings on this vector, + /* ixgbe_get_stats64() might access the rings on this vector, * we must wait a grace period before freeing it. */ kfree_rcu(q_vector, rcu); }

/** - * igb_free_q_vectors - Free memory allocated for interrupt vectors - * @adapter: board private structure to initialize + * igb_free_q_vectors - Free memory allocated for interrupt vectors + * @adapter: board private structure to initialize * - * This function frees the memory allocated to the q_vectors. In addition if - * NAPI is enabled it will delete any references to the NAPI struct prior - * to freeing the q_vector. + * This function frees the memory allocated to the q_vectors. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. **/ static void igb_free_q_vectors(struct igb_adapter *adapter) { @@@ -1041,11 -1031,10 +1041,11 @@@ }

/** - * igb_clear_interrupt_scheme - reset the device to a state of no interrupts + * igb_clear_interrupt_scheme - reset the device to a state of no interrupts + * @adapter: board private structure to initialize * - * This function resets the device so that it has 0 rx queues, tx queues, and - * MSI-X interrupts allocated. + * This function resets the device so that it has 0 Rx queues, Tx queues, and + * MSI-X interrupts allocated. */ static void igb_clear_interrupt_scheme(struct igb_adapter *adapter) { @@@ -1054,12 -1043,10 +1054,12 @@@ }

/** - * igb_set_interrupt_capability - set MSI or MSI-X if supported + * igb_set_interrupt_capability - set MSI or MSI-X if supported + * @adapter: board private structure to initialize + * @msix: boolean value of MSIX capability * - * Attempt to configure interrupts using the best available - * capabilities of the hardware and kernel. + * Attempt to configure interrupts using the best available + * capabilities of the hardware and kernel. **/ static void igb_set_interrupt_capability(struct igb_adapter *adapter, bool msix) { @@@ -1076,10 -1063,10 +1076,10 @@@ else adapter->num_tx_queues = adapter->rss_queues;

- /* start with one vector for every rx queue */ + /* start with one vector for every Rx queue */ numvecs = adapter->num_rx_queues;

- /* if tx handler is separate add 1 for every tx queue */ + /* if Tx handler is separate add 1 for every Tx queue */ if (!(adapter->flags & IGB_FLAG_QUEUE_PAIRS)) numvecs += adapter->num_tx_queues;

@@@ -1141,16 -1128,16 +1141,16 @@@ static void igb_add_ring(struct igb_rin }

/** - * igb_alloc_q_vector - Allocate memory for a single interrupt vector - * @adapter: board private structure to initialize - * @v_count: q_vectors allocated on adapter, used for ring interleaving - * @v_idx: index of vector in adapter struct - * @txr_count: total number of Tx rings to allocate - * @txr_idx: index of first Tx ring to allocate - * @rxr_count: total number of Rx rings to allocate - * @rxr_idx: index of first Rx ring to allocate + * igb_alloc_q_vector - Allocate memory for a single interrupt vector + * @adapter: board private structure to initialize + * @v_count: q_vectors allocated on adapter, used for ring interleaving + * @v_idx: index of vector in adapter struct + * @txr_count: total number of Tx rings to allocate + * @txr_idx: index of first Tx ring to allocate + * @rxr_count: total number of Rx rings to allocate + * @rxr_idx: index of first Rx ring to allocate * - * We allocate one q_vector. If allocation fails we return -ENOMEM. + * We allocate one q_vector. If allocation fails we return -ENOMEM. **/ static int igb_alloc_q_vector(struct igb_adapter *adapter, int v_count, int v_idx, @@@ -1192,17 -1179,6 +1192,17 @@@ /* initialize pointer to rings */ ring = q_vector->ring;

+ /* intialize ITR */ + if (rxr_count) { + /* rx or rx/tx vector */ + if (!adapter->rx_itr_setting || adapter->rx_itr_setting > 3) + q_vector->itr_val = adapter->rx_itr_setting; + } else { + /* tx only vector */ + if (!adapter->tx_itr_setting || adapter->tx_itr_setting > 3) + q_vector->itr_val = adapter->tx_itr_setting; + } + if (txr_count) { /* assign generic ring traits */ ring->dev = &adapter->pdev->dev; @@@ -1245,9 -1221,9 +1245,9 @@@ set_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags);

/* - * On i350, i210, and i211, loopback VLAN packets + * On i350, i354, i210, and i211, loopback VLAN packets * have the tag byte-swapped. - * */ + */ if (adapter->hw.mac.type >= e1000_i350) set_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &ring->flags);

@@@ -1264,11 -1240,11 +1264,11 @@@

/** - * igb_alloc_q_vectors - Allocate memory for interrupt vectors - * @adapter: board private structure to initialize + * igb_alloc_q_vectors - Allocate memory for interrupt vectors + * @adapter: board private structure to initialize * - * We allocate one q_vector per queue interrupt. If allocation fails we - * return -ENOMEM. + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. **/ static int igb_alloc_q_vectors(struct igb_adapter *adapter) { @@@ -1322,11 -1298,9 +1322,11 @@@ err_out }

/** - * igb_init_interrupt_scheme - initialize interrupts, allocate queues/vectors + * igb_init_interrupt_scheme - initialize interrupts, allocate queues/vectors + * @adapter: board private structure to initialize + * @msix: boolean value of MSIX capability * - * This function initializes the interrupts and allocates all of the queues. + * This function initializes the interrupts and allocates all of the queues. **/ static int igb_init_interrupt_scheme(struct igb_adapter *adapter, bool msix) { @@@ -1351,11 -1325,10 +1351,11 @@@ err_alloc_q_vectors }

/** - * igb_request_irq - initialize interrupts + * igb_request_irq - initialize interrupts + * @adapter: board private structure to initialize * - * Attempts to configure interrupts using the best available - * capabilities of the hardware and kernel. + * Attempts to configure interrupts using the best available + * capabilities of the hardware and kernel. **/ static int igb_request_irq(struct igb_adapter *adapter) { @@@ -1421,14 -1394,15 +1421,14 @@@ static void igb_free_irq(struct igb_ada }

/** - * igb_irq_disable - Mask off interrupt generation on the NIC - * @adapter: board private structure + * igb_irq_disable - Mask off interrupt generation on the NIC + * @adapter: board private structure **/ static void igb_irq_disable(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw;

- /* - * we need to be careful when disabling interrupts. The VFs are also + /* we need to be careful when disabling interrupts. The VFs are also * mapped into these registers and so clearing the bits can cause * issues on the VF drivers so we only need to clear what we set */ @@@ -1453,8 -1427,8 +1453,8 @@@ }

/** - * igb_irq_enable - Enable default interrupt generation settings - * @adapter: board private structure + * igb_irq_enable - Enable default interrupt generation settings + * @adapter: board private structure **/ static void igb_irq_enable(struct igb_adapter *adapter) { @@@ -1503,12 -1477,13 +1503,12 @@@ static void igb_update_mng_vlan(struct }

/** - * igb_release_hw_control - release control of the h/w to f/w - * @adapter: address of board private structure - * - * igb_release_hw_control resets CTRL_EXT:DRV_LOAD bit. - * For ASF and Pass Through versions of f/w this means that the - * driver is no longer loaded. + * igb_release_hw_control - release control of the h/w to f/w + * @adapter: address of board private structure * + * igb_release_hw_control resets CTRL_EXT:DRV_LOAD bit. + * For ASF and Pass Through versions of f/w this means that the + * driver is no longer loaded. **/ static void igb_release_hw_control(struct igb_adapter *adapter) { @@@ -1522,12 -1497,13 +1522,12 @@@ }

/** - * igb_get_hw_control - get control of the h/w from f/w - * @adapter: address of board private structure - * - * igb_get_hw_control sets CTRL_EXT:DRV_LOAD bit. - * For ASF and Pass Through versions of f/w this means that - * the driver is loaded. + * igb_get_hw_control - get control of the h/w from f/w + * @adapter: address of board private structure * + * igb_get_hw_control sets CTRL_EXT:DRV_LOAD bit. + * For ASF and Pass Through versions of f/w this means that + * the driver is loaded. **/ static void igb_get_hw_control(struct igb_adapter *adapter) { @@@ -1541,8 -1517,8 +1541,8 @@@ }

/** - * igb_configure - configure the hardware for RX and TX - * @adapter: private board structure + * igb_configure - configure the hardware for RX and TX + * @adapter: private board structure **/ static void igb_configure(struct igb_adapter *adapter) { @@@ -1565,8 -1541,7 +1565,8 @@@

/* call igb_desc_unused which always leaves * at least 1 descriptor unused to make sure - * next_to_use != next_to_clean */ + * next_to_use != next_to_clean + */ for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = adapter->rx_ring[i]; igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); @@@ -1574,8 -1549,8 +1574,8 @@@ }

/** - * igb_power_up_link - Power up the phy/serdes link - * @adapter: address of board private structure + * igb_power_up_link - Power up the phy/serdes link + * @adapter: address of board private structure **/ void igb_power_up_link(struct igb_adapter *adapter) { @@@ -1588,8 -1563,8 +1588,8 @@@ }

/** - * igb_power_down_link - Power down the phy/serdes link - * @adapter: address of board private structure + * igb_power_down_link - Power down the phy/serdes link + * @adapter: address of board private structure */ static void igb_power_down_link(struct igb_adapter *adapter) { @@@ -1600,8 -1575,8 +1600,8 @@@ }

/** - * igb_up - Open the interface and prepare it to handle traffic - * @adapter: board private structure + * igb_up - Open the interface and prepare it to handle traffic + * @adapter: board private structure **/ int igb_up(struct igb_adapter *adapter) { @@@ -1649,8 -1624,7 +1649,8 @@@ void igb_down(struct igb_adapter *adapt int i;

/* signal that we're down so the interrupt handler does not - * reschedule our watchdog timer */ + * reschedule our watchdog timer + */ set_bit(__IGB_DOWN, &adapter->state);

/* disable receives in the hardware */ @@@ -1720,7 -1694,6 +1720,7 @@@ void igb_reset(struct igb_adapter *adap */ switch (mac->type) { case e1000_i350: + case e1000_i354: case e1000_82580: pba = rd32(E1000_RXPBS); pba = igb_rxpbs_adjust_82580(pba); @@@ -1747,16 -1720,14 +1747,16 @@@ * rounded up to the next 1KB and expressed in KB. Likewise, * the Rx FIFO should be large enough to accommodate at least * one full receive packet and is similarly rounded up and - * expressed in KB. */ + * expressed in KB. + */ pba = rd32(E1000_PBA); /* upper 16 bits has Tx packet buffer allocation size in KB */ tx_space = pba >> 16; /* lower 16 bits has Rx packet buffer allocation size in KB */ pba &= 0xffff; - /* the tx fifo also stores 16 bytes of information about the tx - * but don't include ethernet FCS because hardware appends it */ + /* the Tx fifo also stores 16 bytes of information about the Tx + * but don't include ethernet FCS because hardware appends it + */ min_tx_space = (adapter->max_frame_size + sizeof(union e1000_adv_tx_desc) - ETH_FCS_LEN) * 2; @@@ -1769,15 -1740,13 +1769,15 @@@

/* If current Tx allocation is less than the min Tx FIFO size, * and the min Tx FIFO size is less than the current Rx FIFO - * allocation, take space away from current Rx allocation */ + * allocation, take space away from current Rx allocation + */ if (tx_space < min_tx_space && ((min_tx_space - tx_space) < pba)) { pba = pba - (min_tx_space - tx_space);

- /* if short on rx space, rx wins and must trump tx - * adjustment */ + /* if short on Rx space, Rx wins and must trump Tx + * adjustment + */ if (pba < min_rx_space) pba = min_rx_space; } @@@ -1789,8 -1758,7 +1789,8 @@@ * (or the size used for early receive) above it in the Rx FIFO. * Set it to the lower of: * - 90% of the Rx FIFO size, or - * - the full Rx FIFO size minus one full frame */ + * - the full Rx FIFO size minus one full frame + */ hwm = min(((pba << 10) * 9 / 10), ((pba << 10) - 2 * adapter->max_frame_size));

@@@ -1821,7 -1789,8 +1821,7 @@@ if (hw->mac.ops.init_hw(hw)) dev_err(&pdev->dev, "Hardware Error\n");

- /* - * Flow control settings reset on hardware reset, so guarantee flow + /* Flow control settings reset on hardware reset, so guarantee flow * control is off when forcing speed. */ if (!hw->mac.autoneg) @@@ -1857,13 -1826,14 +1857,13 @@@ static netdev_features_t igb_fix_features(struct net_device *netdev, netdev_features_t features) { - /* - * Since there is no support for separate rx/tx vlan accel - * enable/disable make sure tx flag is always in same state as rx. + /* 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_RX) - features |= NETIF_F_HW_VLAN_TX; + if (features & NETIF_F_HW_VLAN_CTAG_RX) + features |= NETIF_F_HW_VLAN_CTAG_TX; else - features &= ~NETIF_F_HW_VLAN_TX; + features &= ~NETIF_F_HW_VLAN_CTAG_TX;

return features; } @@@ -1874,7 -1844,7 +1874,7 @@@ static int igb_set_features(struct net_ netdev_features_t changed = netdev->features ^ features; struct igb_adapter *adapter = netdev_priv(netdev);

- if (changed & NETIF_F_HW_VLAN_RX) + if (changed & NETIF_F_HW_VLAN_CTAG_RX) igb_vlan_mode(netdev, features);

if (!(changed & NETIF_F_RXALL)) @@@ -1906,7 -1876,6 +1906,7 @@@ static const struct net_device_ops igb_ .ndo_set_vf_mac = igb_ndo_set_vf_mac, .ndo_set_vf_vlan = igb_ndo_set_vf_vlan, .ndo_set_vf_tx_rate = igb_ndo_set_vf_bw, + .ndo_set_vf_spoofchk = igb_ndo_set_vf_spoofchk, .ndo_get_vf_config = igb_ndo_get_vf_config, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = igb_netpoll, @@@ -1918,6 -1887,7 +1918,6 @@@ /** * igb_set_fw_version - Configure version string for ethtool * @adapter: adapter struct - * **/ void igb_set_fw_version(struct igb_adapter *adapter) { @@@ -1953,10 -1923,10 +1953,10 @@@ return; }

-/* igb_init_i2c - Init I2C interface +/** + * igb_init_i2c - Init I2C interface * @adapter: pointer to adapter structure - * - */ + **/ static s32 igb_init_i2c(struct igb_adapter *adapter) { s32 status = E1000_SUCCESS; @@@ -1981,15 -1951,15 +1981,15 @@@ }

/** - * igb_probe - Device Initialization Routine - * @pdev: PCI device information struct - * @ent: entry in igb_pci_tbl + * igb_probe - Device Initialization Routine + * @pdev: PCI device information struct + * @ent: entry in igb_pci_tbl * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative on failure * - * igb_probe initializes an adapter identified by a pci_dev structure. - * The OS initialization, configuring of the adapter private structure, - * and a hardware reset occur. + * igb_probe initializes an adapter identified by a pci_dev structure. + * The OS initialization, configuring of the adapter private structure, + * and a hardware reset occur. **/ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@@ -2026,19 -1996,18 +2026,19 @@@ } else { err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_coherent_mask(&pdev->dev, + DMA_BIT_MASK(32)); if (err) { - dev_err(&pdev->dev, "No usable DMA " - "configuration, aborting\n"); + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); goto err_dma; } } }

err = pci_request_selected_regions(pdev, pci_select_bars(pdev, - IORESOURCE_MEM), - igb_driver_name); + IORESOURCE_MEM), + igb_driver_name); if (err) goto err_pci_reg;

@@@ -2116,7 -2085,8 +2116,7 @@@ dev_info(&pdev->dev, "PHY reset is blocked due to SOL/IDER session.\n");

- /* - * features is initialized to 0 in allocation, it might have bits + /* features is initialized to 0 in allocation, it might have bits * set by igb_sw_init so we should use an or instead of an * assignment. */ @@@ -2127,15 -2097,15 +2127,15 @@@ NETIF_F_TSO6 | NETIF_F_RXHASH | NETIF_F_RXCSUM | - NETIF_F_HW_VLAN_RX | - NETIF_F_HW_VLAN_TX; + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX;

/* copy netdev features into list of user selectable features */ netdev->hw_features |= netdev->features; netdev->hw_features |= NETIF_F_RXALL;

/* set this bit last since it cannot be part of hw_features */ - netdev->features |= NETIF_F_HW_VLAN_FILTER; + netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;

netdev->vlan_features |= NETIF_F_TSO | NETIF_F_TSO6 | @@@ -2160,11 -2130,11 +2160,11 @@@ adapter->en_mng_pt = igb_enable_mng_pass_thru(hw);

/* before reading the NVM, reset the controller to put the device in a - * known good starting state */ + * known good starting state + */ hw->mac.ops.reset_hw(hw);

- /* - * make sure the NVM is good , i211 parts have special NVM that + /* make sure the NVM is good , i211 parts have special NVM that * doesn't contain a checksum */ if (hw->mac.type != e1000_i211) { @@@ -2191,9 -2161,9 +2191,9 @@@ igb_set_fw_version(adapter);

setup_timer(&adapter->watchdog_timer, igb_watchdog, - (unsigned long) adapter); + (unsigned long) adapter); setup_timer(&adapter->phy_info_timer, igb_update_phy_info, - (unsigned long) adapter); + (unsigned long) adapter);

INIT_WORK(&adapter->reset_task, igb_reset_task); INIT_WORK(&adapter->watchdog_task, igb_watchdog_task); @@@ -2215,8 -2185,8 +2215,8 @@@ /* Check the NVM for wake support on non-port A ports */ if (hw->mac.type >= e1000_82580) hw->nvm.ops.read(hw, NVM_INIT_CONTROL3_PORT_A + - NVM_82580_LAN_FUNC_OFFSET(hw->bus.func), 1, - &eeprom_data); + NVM_82580_LAN_FUNC_OFFSET(hw->bus.func), 1, + &eeprom_data); else if (hw->bus.func == 1) hw->nvm.ops.read(hw, NVM_INIT_CONTROL3_PORT_B, 1, &eeprom_data);

@@@ -2225,8 -2195,7 +2225,8 @@@

/* now that we have the eeprom settings, apply the special cases where * the eeprom may be wrong or the board simply won't support wake on - * lan on a particular port */ + * lan on a particular port + */ switch (pdev->device) { case E1000_DEV_ID_82575GB_QUAD_COPPER: adapter->flags &= ~IGB_FLAG_WOL_SUPPORTED; @@@ -2235,8 -2204,7 +2235,8 @@@ case E1000_DEV_ID_82576_FIBER: case E1000_DEV_ID_82576_SERDES: /* Wake events only supported on port A for dual fiber - * regardless of eeprom setting */ + * regardless of eeprom setting + */ if (rd32(E1000_STATUS) & E1000_STATUS_FUNC_1) adapter->flags &= ~IGB_FLAG_WOL_SUPPORTED; break; @@@ -2306,7 -2274,8 +2306,7 @@@ if (hw->mac.type == e1000_i350 && hw->bus.func == 0) { u16 ets_word;

- /* - * Read the NVM to determine if this i350 device supports an + /* Read the NVM to determine if this i350 device supports an * external thermal sensor. */ hw->nvm.ops.read(hw, NVM_ETS_CFG, 1, &ets_word); @@@ -2325,20 -2294,17 +2325,20 @@@ igb_ptp_init(adapter);

dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n"); - /* print bus type/speed/width info */ - dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n", - netdev->name, - ((hw->bus.speed == e1000_bus_speed_2500) ? "2.5Gb/s" : - (hw->bus.speed == e1000_bus_speed_5000) ? "5.0Gb/s" : - "unknown"), - ((hw->bus.width == e1000_bus_width_pcie_x4) ? "Width x4" : - (hw->bus.width == e1000_bus_width_pcie_x2) ? "Width x2" : - (hw->bus.width == e1000_bus_width_pcie_x1) ? "Width x1" : - "unknown"), - netdev->dev_addr); + /* print bus type/speed/width info, not applicable to i354 */ + if (hw->mac.type != e1000_i354) { + dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n", + netdev->name, + ((hw->bus.speed == e1000_bus_speed_2500) ? "2.5Gb/s" : + (hw->bus.speed == e1000_bus_speed_5000) ? "5.0Gb/s" : + "unknown"), + ((hw->bus.width == e1000_bus_width_pcie_x4) ? + "Width x4" : + (hw->bus.width == e1000_bus_width_pcie_x2) ? + "Width x2" : + (hw->bus.width == e1000_bus_width_pcie_x1) ? + "Width x1" : "unknown"), netdev->dev_addr); + }

ret_val = igb_read_part_string(hw, part_str, E1000_PBANUM_LENGTH); if (ret_val) @@@ -2355,13 -2321,6 +2355,13 @@@ case e1000_i211: igb_set_eee_i350(hw); break; + case e1000_i354: + if (hw->phy.media_type == e1000_media_type_copper) { + if ((rd32(E1000_CTRL_EXT) & + E1000_CTRL_EXT_LINK_MODE_SGMII)) + igb_set_eee_i354(hw); + } + break; default: break; } @@@ -2385,7 -2344,7 +2385,7 @@@ err_ioremap free_netdev(netdev); err_alloc_etherdev: pci_release_selected_regions(pdev, - pci_select_bars(pdev, IORESOURCE_MEM)); + pci_select_bars(pdev, IORESOURCE_MEM)); err_pci_reg: err_dma: pci_disable_device(pdev); @@@ -2485,24 -2444,26 +2485,24 @@@ out }

#endif -/* +/** * igb_remove_i2c - Cleanup I2C interface * @adapter: pointer to adapter structure - * - */ + **/ static void igb_remove_i2c(struct igb_adapter *adapter) { - /* free the adapter bus structure */ i2c_del_adapter(&adapter->i2c_adap); }

/** - * igb_remove - Device Removal Routine - * @pdev: PCI device information struct + * igb_remove - Device Removal Routine + * @pdev: PCI device information struct * - * igb_remove is called by the PCI subsystem to alert the driver - * that it should release a PCI device. The could be caused by a - * Hot-Plug event, or because the driver is going to be removed from - * memory. + * igb_remove is called by the PCI subsystem to alert the driver + * that it should release a PCI device. The could be caused by a + * Hot-Plug event, or because the driver is going to be removed from + * memory. **/ static void igb_remove(struct pci_dev *pdev) { @@@ -2516,7 -2477,8 +2516,7 @@@ #endif igb_remove_i2c(adapter); igb_ptp_stop(adapter); - /* - * The watchdog timer may be rescheduled, so explicitly + /* The watchdog timer may be rescheduled, so explicitly * disable watchdog from being rescheduled. */ set_bit(__IGB_DOWN, &adapter->state); @@@ -2536,8 -2498,7 +2536,8 @@@ #endif

/* Release control of h/w to f/w. If f/w is AMT enabled, this - * would have already happened in close and is redundant. */ + * would have already happened in close and is redundant. + */ igb_release_hw_control(adapter);

unregister_netdev(netdev); @@@ -2552,7 -2513,7 +2552,7 @@@ if (hw->flash_address) iounmap(hw->flash_address); pci_release_selected_regions(pdev, - pci_select_bars(pdev, IORESOURCE_MEM)); + pci_select_bars(pdev, IORESOURCE_MEM));

kfree(adapter->shadow_vfta); free_netdev(netdev); @@@ -2563,13 -2524,13 +2563,13 @@@ }

/** - * igb_probe_vfs - Initialize vf data storage and add VFs to pci config space - * @adapter: board private structure to initialize + * igb_probe_vfs - Initialize vf data storage and add VFs to pci config space + * @adapter: board private structure to initialize * - * This function initializes the vf specific data storage and then attempts to - * allocate the VFs. The reason for ordering it this way is because it is much - * mor expensive time wise to disable SR-IOV than it is to allocate and free - * the memory for the VFs. + * This function initializes the vf specific data storage and then attempts to + * allocate the VFs. The reason for ordering it this way is because it is much + * mor expensive time wise to disable SR-IOV than it is to allocate and free + * the memory for the VFs. **/ static void igb_probe_vfs(struct igb_adapter *adapter) { @@@ -2615,7 -2576,6 +2615,7 @@@ static void igb_init_queue_configuratio } /* fall through */ case e1000_82580: + case e1000_i354: default: max_rss_queues = IGB_MAX_RX_QUEUES; break; @@@ -2630,7 -2590,8 +2630,7 @@@ /* Device supports enough interrupts without queue pairing. */ break; case e1000_82576: - /* - * If VFs are going to be allocated with RSS queues then we + /* If VFs are going to be allocated with RSS queues then we * should pair the queues in order to conserve interrupts due * to limited supply. */ @@@ -2640,10 -2601,10 +2640,10 @@@ /* fall through */ case e1000_82580: case e1000_i350: + case e1000_i354: case e1000_i210: default: - /* - * If rss_queues > half of max_rss_queues, pair the queues in + /* If rss_queues > half of max_rss_queues, pair the queues in * order to conserve interrupts due to limited supply. */ if (adapter->rss_queues > (max_rss_queues / 2)) @@@ -2653,12 -2614,12 +2653,12 @@@ }

/** - * igb_sw_init - Initialize general software structures (struct igb_adapter) - * @adapter: board private structure to initialize + * igb_sw_init - Initialize general software structures (struct igb_adapter) + * @adapter: board private structure to initialize * - * igb_sw_init initializes the Adapter private data structure. - * Fields are initialized based on PCI device information and - * OS network device settings (MTU size). + * igb_sw_init initializes the Adapter private data structure. + * Fields are initialized based on PCI device information and + * OS network device settings (MTU size). **/ static int igb_sw_init(struct igb_adapter *adapter) { @@@ -2728,16 -2689,16 +2728,16 @@@ }

/** - * igb_open - Called when a network interface is made active - * @netdev: network interface device structure + * igb_open - Called when a network interface is made active + * @netdev: network interface device structure * - * Returns 0 on success, negative value on failure + * Returns 0 on success, negative value on failure * - * The open entry point is called when a network interface is made - * active by the system (IFF_UP). At this point all resources needed - * for transmit and receive operations are allocated, the interrupt - * handler is registered with the OS, the watchdog timer is started, - * and the stack is notified that the interface is ready. + * The open entry point is called when a network interface is made + * active by the system (IFF_UP). At this point all resources needed + * for transmit and receive operations are allocated, the interrupt + * handler is registered with the OS, the watchdog timer is started, + * and the stack is notified that the interface is ready. **/ static int __igb_open(struct net_device *netdev, bool resuming) { @@@ -2773,8 -2734,7 +2773,8 @@@ /* before we allocate an interrupt, we must be ready to handle it. * Setting DEBUG_SHIRQ in the kernel makes it fire an interrupt * as soon as we call pci_request_irq, so we have to setup our - * clean_rx handler before we do so. */ + * clean_rx handler before we do so. + */ igb_configure(adapter);

err = igb_request_irq(adapter); @@@ -2843,15 -2803,15 +2843,15 @@@ static int igb_open(struct net_device * }

/** - * igb_close - Disables a network interface - * @netdev: network interface device structure + * igb_close - Disables a network interface + * @netdev: network interface device structure * - * Returns 0, this is not allowed to fail + * Returns 0, this is not allowed to fail * - * The close entry point is called when an interface is de-activated - * by the OS. The hardware is still under the driver's control, but - * needs to be disabled. A global MAC reset is issued to stop the - * hardware, and all transmit and receive resources are freed. + * The close entry point is called when an interface is de-activated + * by the OS. The hardware is still under the driver's control, but + * needs to be disabled. A global MAC reset is issued to stop the + * hardware, and all transmit and receive resources are freed. **/ static int __igb_close(struct net_device *netdev, bool suspending) { @@@ -2880,10 -2840,10 +2880,10 @@@ static int igb_close(struct net_device }

/** - * igb_setup_tx_resources - allocate Tx resources (Descriptors) - * @tx_ring: tx descriptor ring (for a specific queue) to setup + * igb_setup_tx_resources - allocate Tx resources (Descriptors) + * @tx_ring: tx descriptor ring (for a specific queue) to setup * - * Return 0 on success, negative on failure + * Return 0 on success, negative on failure **/ int igb_setup_tx_resources(struct igb_ring *tx_ring) { @@@ -2918,11 -2878,11 +2918,11 @@@ err }

/** - * igb_setup_all_tx_resources - wrapper to allocate Tx resources - * (Descriptors) for all queues - * @adapter: board private structure + * igb_setup_all_tx_resources - wrapper to allocate Tx resources + * (Descriptors) for all queues + * @adapter: board private structure * - * Return 0 on success, negative on failure + * Return 0 on success, negative on failure **/ static int igb_setup_all_tx_resources(struct igb_adapter *adapter) { @@@ -2944,8 -2904,8 +2944,8 @@@ }

/** - * igb_setup_tctl - configure the transmit control registers - * @adapter: Board private structure + * igb_setup_tctl - configure the transmit control registers + * @adapter: Board private structure **/ void igb_setup_tctl(struct igb_adapter *adapter) { @@@ -2970,11 -2930,11 +2970,11 @@@ }

/** - * igb_configure_tx_ring - Configure transmit ring after Reset - * @adapter: board private structure - * @ring: tx ring to configure + * igb_configure_tx_ring - Configure transmit ring after Reset + * @adapter: board private structure + * @ring: tx ring to configure * - * Configure a transmit ring after a reset. + * Configure a transmit ring after a reset. **/ void igb_configure_tx_ring(struct igb_adapter *adapter, struct igb_ring *ring) @@@ -2990,9 -2950,9 +2990,9 @@@ mdelay(10);

wr32(E1000_TDLEN(reg_idx), - ring->count * sizeof(union e1000_adv_tx_desc)); + ring->count * sizeof(union e1000_adv_tx_desc)); wr32(E1000_TDBAL(reg_idx), - tdba & 0x00000000ffffffffULL); + tdba & 0x00000000ffffffffULL); wr32(E1000_TDBAH(reg_idx), tdba >> 32);

ring->tail = hw->hw_addr + E1000_TDT(reg_idx); @@@ -3008,10 -2968,10 +3008,10 @@@ }

/** - * igb_configure_tx - Configure transmit Unit after Reset - * @adapter: board private structure + * igb_configure_tx - Configure transmit Unit after Reset + * @adapter: board private structure * - * Configure the Tx unit of the MAC after a reset. + * Configure the Tx unit of the MAC after a reset. **/ static void igb_configure_tx(struct igb_adapter *adapter) { @@@ -3022,10 -2982,10 +3022,10 @@@ }

/** - * igb_setup_rx_resources - allocate Rx resources (Descriptors) - * @rx_ring: rx descriptor ring (for a specific queue) to setup + * igb_setup_rx_resources - allocate Rx resources (Descriptors) + * @rx_ring: Rx descriptor ring (for a specific queue) to setup * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative on failure **/ int igb_setup_rx_resources(struct igb_ring *rx_ring) { @@@ -3061,11 -3021,11 +3061,11 @@@ err }

/** - * igb_setup_all_rx_resources - wrapper to allocate Rx resources - * (Descriptors) for all queues - * @adapter: board private structure + * igb_setup_all_rx_resources - wrapper to allocate Rx resources + * (Descriptors) for all queues + * @adapter: board private structure * - * Return 0 on success, negative on failure + * Return 0 on success, negative on failure **/ static int igb_setup_all_rx_resources(struct igb_adapter *adapter) { @@@ -3087,8 -3047,8 +3087,8 @@@ }

/** - * igb_setup_mrqc - configure the multiple receive queue control registers - * @adapter: Board private structure + * igb_setup_mrqc - configure the multiple receive queue control registers + * @adapter: Board private structure **/ static void igb_setup_mrqc(struct igb_adapter *adapter) { @@@ -3121,7 -3081,8 +3121,7 @@@ break; }

- /* - * Populate the indirection table 4 entries at a time. To do this + /* Populate the indirection table 4 entries at a time. To do this * we are generating the results for n and n+2 and then interleaving * those with the results with n+1 and n+3. */ @@@ -3137,7 -3098,8 +3137,7 @@@ wr32(E1000_RETA(j), reta); }

- /* - * Disable raw packet checksumming so that RSS hash is placed in + /* Disable raw packet checksumming so that RSS hash is placed in * descriptor on writeback. No need to enable TCP/UDP/IP checksum * offloads as they are enabled by default */ @@@ -3167,8 -3129,7 +3167,8 @@@

/* If VMDq is enabled then we set the appropriate mode for that, else * we default to RSS so that an RSS hash is calculated per packet even - * if we are only using one queue */ + * if we are only using one queue + */ if (adapter->vfs_allocated_count) { if (hw->mac.type > e1000_82575) { /* Set the default pool for the PF's first queue */ @@@ -3193,8 -3154,8 +3193,8 @@@ }

/** - * igb_setup_rctl - configure the receive control registers - * @adapter: Board private structure + * igb_setup_rctl - configure the receive control registers + * @adapter: Board private structure **/ void igb_setup_rctl(struct igb_adapter *adapter) { @@@ -3209,7 -3170,8 +3209,7 @@@ rctl |= E1000_RCTL_EN | E1000_RCTL_BAM | E1000_RCTL_RDMTS_HALF | (hw->mac.mc_filter_type << E1000_RCTL_MO_SHIFT);

- /* - * enable stripping of CRC. It's unlikely this will break BMC + /* enable stripping of CRC. It's unlikely this will break BMC * redirection as it did with e1000. Newer features require * that the HW strips the CRC. */ @@@ -3236,8 -3198,7 +3236,8 @@@ /* This is useful for sniffing bad packets. */ if (adapter->netdev->features & NETIF_F_RXALL) { /* UPE and MPE will be handled by normal PROMISC logic - * in e1000e_set_rx_mode */ + * in e1000e_set_rx_mode + */ rctl |= (E1000_RCTL_SBP | /* Receive bad packets */ E1000_RCTL_BAM | /* RX All Bcast Pkts */ E1000_RCTL_PMCF); /* RX All MAC Ctrl Pkts */ @@@ -3260,8 -3221,7 +3260,8 @@@ static inline int igb_set_vf_rlpml(stru u32 vmolr;

/* if it isn't the PF check to see if VFs are enabled and - * increase the size to support vlan tags */ + * increase the size to support vlan tags + */ if (vfn < adapter->vfs_allocated_count && adapter->vf_data[vfn].vlans_enabled) size += VLAN_TAG_SIZE; @@@ -3275,10 -3235,10 +3275,10 @@@ }

/** - * igb_rlpml_set - set maximum receive packet size - * @adapter: board private structure + * igb_rlpml_set - set maximum receive packet size + * @adapter: board private structure * - * Configure maximum receivable packet size. + * Configure maximum receivable packet size. **/ static void igb_rlpml_set(struct igb_adapter *adapter) { @@@ -3288,7 -3248,8 +3288,7 @@@

if (pf_id) { igb_set_vf_rlpml(adapter, max_frame_size, pf_id); - /* - * If we're in VMDQ or SR-IOV mode, then set global RLPML + /* If we're in VMDQ or SR-IOV mode, then set global RLPML * to our max jumbo frame size, in case we need to enable * jumbo frames on one of the rings later. * This will not pass over-length frames into the default @@@ -3306,16 -3267,17 +3306,16 @@@ static inline void igb_set_vmolr(struc struct e1000_hw *hw = &adapter->hw; u32 vmolr;

- /* - * This register exists only on 82576 and newer so if we are older then + /* This register exists only on 82576 and newer so if we are older then * we should exit and do nothing */ if (hw->mac.type < e1000_82576) return;

vmolr = rd32(E1000_VMOLR(vfn)); - vmolr |= E1000_VMOLR_STRVLAN; /* Strip vlan tags */ + vmolr |= E1000_VMOLR_STRVLAN; /* Strip vlan tags */ if (aupe) - vmolr |= E1000_VMOLR_AUPE; /* Accept untagged packets */ + vmolr |= E1000_VMOLR_AUPE; /* Accept untagged packets */ else vmolr &= ~(E1000_VMOLR_AUPE); /* Tagged packets ONLY */

@@@ -3324,24 -3286,25 +3324,24 @@@

if (adapter->rss_queues > 1 && vfn == adapter->vfs_allocated_count) vmolr |= E1000_VMOLR_RSSE; /* enable RSS */ - /* - * for VMDq only allow the VFs and pool 0 to accept broadcast and + /* for VMDq only allow the VFs and pool 0 to accept broadcast and * multicast packets */ if (vfn <= adapter->vfs_allocated_count) - vmolr |= E1000_VMOLR_BAM; /* Accept broadcast */ + vmolr |= E1000_VMOLR_BAM; /* Accept broadcast */

wr32(E1000_VMOLR(vfn), vmolr); }

/** - * igb_configure_rx_ring - Configure a receive ring after Reset - * @adapter: board private structure - * @ring: receive ring to be configured + * igb_configure_rx_ring - Configure a receive ring after Reset + * @adapter: board private structure + * @ring: receive ring to be configured * - * Configure the Rx unit of the MAC after a reset. + * Configure the Rx unit of the MAC after a reset. **/ void igb_configure_rx_ring(struct igb_adapter *adapter, - struct igb_ring *ring) + struct igb_ring *ring) { struct e1000_hw *hw = &adapter->hw; u64 rdba = ring->dma; @@@ -3356,7 -3319,7 +3356,7 @@@ rdba & 0x00000000ffffffffULL); wr32(E1000_RDBAH(reg_idx), rdba >> 32); wr32(E1000_RDLEN(reg_idx), - ring->count * sizeof(union e1000_adv_rx_desc)); + ring->count * sizeof(union e1000_adv_rx_desc));

/* initialize head and tail */ ring->tail = hw->hw_addr + E1000_RDT(reg_idx); @@@ -3387,25 -3350,11 +3387,11 @@@ wr32(E1000_RXDCTL(reg_idx), rxdctl); }

- static void igb_set_rx_buffer_len(struct igb_adapter *adapter, - struct igb_ring *rx_ring) - { - #define IGB_MAX_BUILD_SKB_SIZE \ - (SKB_WITH_OVERHEAD(IGB_RX_BUFSZ) - \ - (NET_SKB_PAD + NET_IP_ALIGN + IGB_TS_HDR_LEN)) - - /* set build_skb flag */ - if (adapter->max_frame_size <= IGB_MAX_BUILD_SKB_SIZE) - set_ring_build_skb_enabled(rx_ring); - else - clear_ring_build_skb_enabled(rx_ring); - } - /** - * igb_configure_rx - Configure receive Unit after Reset - * @adapter: board private structure + * igb_configure_rx - Configure receive Unit after Reset + * @adapter: board private structure * - * Configure the Rx unit of the MAC after a reset. + * Configure the Rx unit of the MAC after a reset. **/ static void igb_configure_rx(struct igb_adapter *adapter) { @@@ -3416,23 -3365,19 +3402,20 @@@

/* set the correct pool for the PF default MAC address in entry 0 */ igb_rar_set_qsel(adapter, adapter->hw.mac.addr, 0, - adapter->vfs_allocated_count); + adapter->vfs_allocated_count);

/* Setup the HW Rx Head and Tail Descriptor Pointers and - * the Base and Length of the Rx Descriptor Ring */ + * the Base and Length of the Rx Descriptor Ring + */ - for (i = 0; i < adapter->num_rx_queues; i++) { - struct igb_ring *rx_ring = adapter->rx_ring[i]; - igb_set_rx_buffer_len(adapter, rx_ring); - igb_configure_rx_ring(adapter, rx_ring); - } + for (i = 0; i < adapter->num_rx_queues; i++) + igb_configure_rx_ring(adapter, adapter->rx_ring[i]); }

/** - * igb_free_tx_resources - Free Tx Resources per Queue - * @tx_ring: Tx descriptor ring for a specific queue + * igb_free_tx_resources - Free Tx Resources per Queue + * @tx_ring: Tx descriptor ring for a specific queue * - * Free all transmit software resources + * Free all transmit software resources **/ void igb_free_tx_resources(struct igb_ring *tx_ring) { @@@ -3452,10 -3397,10 +3435,10 @@@ }

/** - * igb_free_all_tx_resources - Free Tx Resources for All Queues - * @adapter: board private structure + * igb_free_all_tx_resources - Free Tx Resources for All Queues + * @adapter: board private structure * - * Free all transmit software resources + * Free all transmit software resources **/ static void igb_free_all_tx_resources(struct igb_adapter *adapter) { @@@ -3488,8 -3433,8 +3471,8 @@@ void igb_unmap_and_free_tx_resource(str }

/** - * igb_clean_tx_ring - Free Tx Buffers - * @tx_ring: ring to be cleaned + * igb_clean_tx_ring - Free Tx Buffers + * @tx_ring: ring to be cleaned **/ static void igb_clean_tx_ring(struct igb_ring *tx_ring) { @@@ -3519,8 -3464,8 +3502,8 @@@ }

/** - * igb_clean_all_tx_rings - Free Tx Buffers for all queues - * @adapter: board private structure + * igb_clean_all_tx_rings - Free Tx Buffers for all queues + * @adapter: board private structure **/ static void igb_clean_all_tx_rings(struct igb_adapter *adapter) { @@@ -3531,10 -3476,10 +3514,10 @@@ }

/** - * igb_free_rx_resources - Free Rx Resources - * @rx_ring: ring to clean the resources from + * igb_free_rx_resources - Free Rx Resources + * @rx_ring: ring to clean the resources from * - * Free all receive software resources + * Free all receive software resources **/ void igb_free_rx_resources(struct igb_ring *rx_ring) { @@@ -3554,10 -3499,10 +3537,10 @@@ }

/** - * igb_free_all_rx_resources - Free Rx Resources for All Queues - * @adapter: board private structure + * igb_free_all_rx_resources - Free Rx Resources for All Queues + * @adapter: board private structure * - * Free all receive software resources + * Free all receive software resources **/ static void igb_free_all_rx_resources(struct igb_adapter *adapter) { @@@ -3568,8 -3513,8 +3551,8 @@@ }

/** - * igb_clean_rx_ring - Free Rx Buffers per Queue - * @rx_ring: ring to free buffers from + * igb_clean_rx_ring - Free Rx Buffers per Queue + * @rx_ring: ring to free buffers from **/ static void igb_clean_rx_ring(struct igb_ring *rx_ring) { @@@ -3611,8 -3556,8 +3594,8 @@@ }

/** - * igb_clean_all_rx_rings - Free Rx Buffers for all queues - * @adapter: board private structure + * igb_clean_all_rx_rings - Free Rx Buffers for all queues + * @adapter: board private structure **/ static void igb_clean_all_rx_rings(struct igb_adapter *adapter) { @@@ -3623,11 -3568,11 +3606,11 @@@ }

/** - * igb_set_mac - Change the Ethernet Address of the NIC - * @netdev: network interface device structure - * @p: pointer to an address structure + * igb_set_mac - Change the Ethernet Address of the NIC + * @netdev: network interface device structure + * @p: pointer to an address structure * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative on failure **/ static int igb_set_mac(struct net_device *netdev, void *p) { @@@ -3643,19 -3588,19 +3626,19 @@@

/* set the correct pool for the new PF MAC address in entry 0 */ igb_rar_set_qsel(adapter, hw->mac.addr, 0, - adapter->vfs_allocated_count); + adapter->vfs_allocated_count);

return 0; }

/** - * igb_write_mc_addr_list - write multicast addresses to MTA - * @netdev: network interface device structure + * igb_write_mc_addr_list - write multicast addresses to MTA + * @netdev: network interface device structure * - * Writes multicast address list to the MTA hash table. - * Returns: -ENOMEM on failure - * 0 on no addresses written - * X on writing X addresses to MTA + * Writes multicast address list to the MTA hash table. + * Returns: -ENOMEM on failure + * 0 on no addresses written + * X on writing X addresses to MTA **/ static int igb_write_mc_addr_list(struct net_device *netdev) { @@@ -3688,13 -3633,13 +3671,13 @@@ }

/** - * igb_write_uc_addr_list - write unicast addresses to RAR table - * @netdev: network interface device structure + * igb_write_uc_addr_list - write unicast addresses to RAR table + * @netdev: network interface device structure * - * Writes unicast address list to the RAR table. - * Returns: -ENOMEM on failure/insufficient address space - * 0 on no addresses written - * X on writing X addresses to the RAR table + * Writes unicast address list to the RAR table. + * Returns: -ENOMEM on failure/insufficient address space + * 0 on no addresses written + * X on writing X addresses to the RAR table **/ static int igb_write_uc_addr_list(struct net_device *netdev) { @@@ -3715,8 -3660,8 +3698,8 @@@ if (!rar_entries) break; igb_rar_set_qsel(adapter, ha->addr, - rar_entries--, - vfn); + rar_entries--, + vfn); count++; } } @@@ -3731,13 -3676,13 +3714,13 @@@ }

/** - * igb_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set - * @netdev: network interface device structure + * igb_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set + * @netdev: network interface device structure * - * The set_rx_mode entry point is called whenever the unicast or multicast - * address lists or the network interface flags are updated. This routine is - * responsible for configuring the hardware for proper unicast, multicast, - * promiscuous mode, and all-multi behavior. + * The set_rx_mode entry point is called whenever the unicast or multicast + * address lists or the network interface flags are updated. This routine is + * responsible for configuring the hardware for proper unicast, multicast, + * promiscuous mode, and all-multi behavior. **/ static void igb_set_rx_mode(struct net_device *netdev) { @@@ -3761,7 -3706,8 +3744,7 @@@ rctl |= E1000_RCTL_MPE; vmolr |= E1000_VMOLR_MPME; } else { - /* - * Write addresses to the MTA, if the attempt fails + /* Write addresses to the MTA, if the attempt fails * then we should just turn on promiscuous mode so * that we can at least receive multicast traffic */ @@@ -3773,7 -3719,8 +3756,7 @@@ vmolr |= E1000_VMOLR_ROMPE; } } - /* - * Write addresses to available RAR registers, if there is not + /* Write addresses to available RAR registers, if there is not * sufficient space to store all the addresses then enable * unicast promiscuous mode */ @@@ -3786,7 -3733,8 +3769,7 @@@ } wr32(E1000_RCTL, rctl);

- /* - * In order to support SR-IOV and eventually VMDq it is necessary to set + /* In order to support SR-IOV and eventually VMDq it is necessary to set * the VMOLR to enable the appropriate modes. Without this workaround * we will have issues with VLAN tag stripping not being done for frames * that are only arriving because we are the default pool @@@ -3795,7 -3743,7 +3778,7 @@@ return;

vmolr |= rd32(E1000_VMOLR(vfn)) & - ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE); + ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE); wr32(E1000_VMOLR(vfn), vmolr); igb_restore_vf_multicasts(adapter); } @@@ -3840,8 -3788,7 +3823,8 @@@ static void igb_spoof_check(struct igb_ }

/* Need to wait a few seconds after link up to get diagnostic information from - * the phy */ + * the phy + */ static void igb_update_phy_info(unsigned long data) { struct igb_adapter *adapter = (struct igb_adapter *) data; @@@ -3849,8 -3796,8 +3832,8 @@@ }

/** - * igb_has_link - check shared code for link and determine up/down - * @adapter: pointer to driver private info + * igb_has_link - check shared code for link and determine up/down + * @adapter: pointer to driver private info **/ bool igb_has_link(struct igb_adapter *adapter) { @@@ -3895,16 -3842,17 +3878,16 @@@ static bool igb_thermal_sensor_event(st ctrl_ext = rd32(E1000_CTRL_EXT);

if ((hw->phy.media_type == e1000_media_type_copper) && - !(ctrl_ext & E1000_CTRL_EXT_LINK_MODE_SGMII)) { + !(ctrl_ext & E1000_CTRL_EXT_LINK_MODE_SGMII)) ret = !!(thstat & event); - } }

return ret; }

/** - * igb_watchdog - Timer Call-back - * @data: pointer to adapter cast into an unsigned long + * igb_watchdog - Timer Call-back + * @data: pointer to adapter cast into an unsigned long **/ static void igb_watchdog(unsigned long data) { @@@ -3916,8 -3864,8 +3899,8 @@@ static void igb_watchdog_task(struct work_struct *work) { struct igb_adapter *adapter = container_of(work, - struct igb_adapter, - watchdog_task); + struct igb_adapter, + watchdog_task); struct e1000_hw *hw = &adapter->hw; struct net_device *netdev = adapter->netdev; u32 link; @@@ -3931,8 -3879,8 +3914,8 @@@ if (!netif_carrier_ok(netdev)) { u32 ctrl; hw->mac.ops.get_speed_and_duplex(hw, - &adapter->link_speed, - &adapter->link_duplex); + &adapter->link_speed, + &adapter->link_duplex);

ctrl = rd32(E1000_CTRL); /* Links status message must follow this format */ @@@ -4015,8 -3963,7 +3998,8 @@@ /* We've lost link, so the controller stops DMA, * but we've got queued Tx work that's never going * to get done, so reset controller to flush Tx. - * (Do the reset outside of interrupt context). */ + * (Do the reset outside of interrupt context). + */ if (igb_desc_unused(tx_ring) + 1 < tx_ring->count) { adapter->tx_timeout_count++; schedule_work(&adapter->reset_task); @@@ -4029,7 -3976,7 +4012,7 @@@ set_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags); }

- /* Cause software interrupt to ensure rx ring is cleaned */ + /* Cause software interrupt to ensure Rx ring is cleaned */ if (adapter->msix_entries) { u32 eics = 0; for (i = 0; i < adapter->num_q_vectors; i++) @@@ -4056,20 -4003,20 +4039,20 @@@ enum latency_range };

/** - * igb_update_ring_itr - update the dynamic ITR value based on packet size + * igb_update_ring_itr - update the dynamic ITR value based on packet size + * @q_vector: pointer to q_vector * - * Stores a new ITR value based on strictly on packet size. This - * algorithm is less sophisticated than that used in igb_update_itr, - * due to the difficulty of synchronizing statistics across multiple - * receive rings. The divisors and thresholds used by this function - * were determined based on theoretical maximum wire speed and testing - * data, in order to minimize response time while increasing bulk - * throughput. - * This functionality is controlled by the InterruptThrottleRate module - * parameter (see igb_param.c) - * NOTE: This function is called only when operating in a multiqueue - * receive environment. - * @q_vector: pointer to q_vector + * Stores a new ITR value based on strictly on packet size. This + * algorithm is less sophisticated than that used in igb_update_itr, + * due to the difficulty of synchronizing statistics across multiple + * receive rings. The divisors and thresholds used by this function + * were determined based on theoretical maximum wire speed and testing + * data, in order to minimize response time while increasing bulk + * throughput. + * This functionality is controlled by the InterruptThrottleRate module + * parameter (see igb_param.c) + * NOTE: This function is called only when operating in a multiqueue + * receive environment. **/ static void igb_update_ring_itr(struct igb_q_vector *q_vector) { @@@ -4130,21 -4077,20 +4113,21 @@@ clear_counts }

/** - * igb_update_itr - update the dynamic ITR value based on statistics - * Stores a new ITR value based on packets and byte - * counts during the last interrupt. The advantage of per interrupt - * computation is faster updates and more accurate ITR for the current - * traffic pattern. Constants in this function were computed - * based on theoretical maximum wire speed and thresholds were set based - * on testing data as well as attempting to minimize response time - * while increasing bulk throughput. - * this functionality is controlled by the InterruptThrottleRate module - * parameter (see igb_param.c) - * NOTE: These calculations are only valid when operating in a single- - * queue environment. - * @q_vector: pointer to q_vector - * @ring_container: ring info to update the itr for + * igb_update_itr - update the dynamic ITR value based on statistics + * @q_vector: pointer to q_vector + * @ring_container: ring info to update the itr for + * + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time + * while increasing bulk throughput. + * this functionality is controlled by the InterruptThrottleRate module + * parameter (see igb_param.c) + * NOTE: These calculations are only valid when operating in a single- + * queue environment. **/ static void igb_update_itr(struct igb_q_vector *q_vector, struct igb_ring_container *ring_container) @@@ -4242,12 -4188,12 +4225,12 @@@ set_itr_now if (new_itr != q_vector->itr_val) { /* this attempts to bias the interrupt rate towards Bulk * by adding intermediate steps when interrupt rate is - * increasing */ + * increasing + */ new_itr = new_itr > q_vector->itr_val ? - max((new_itr * q_vector->itr_val) / - (new_itr + (q_vector->itr_val >> 2)), - new_itr) : - new_itr; + max((new_itr * q_vector->itr_val) / + (new_itr + (q_vector->itr_val >> 2)), + new_itr) : new_itr; /* Don't write the value here; it resets the adapter's * internal timer, and causes us to delay far longer than * we should between interrupts. Instead, we write the ITR @@@ -4374,8 -4320,8 +4357,8 @@@ static void igb_tx_csum(struct igb_rin default: if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, - "partial checksum but proto=%x!\n", - first->protocol); + "partial checksum but proto=%x!\n", + first->protocol); } break; } @@@ -4398,8 -4344,8 +4381,8 @@@ default: if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, - "partial checksum but l4 proto=%x!\n", - l4_hdr); + "partial checksum but l4 proto=%x!\n", + l4_hdr); } break; } @@@ -4551,7 -4497,8 +4534,7 @@@ static void igb_tx_map(struct igb_ring /* set the timestamp */ first->time_stamp = jiffies;

- /* - * Force memory writes to complete before letting h/w know there + /* Force memory writes to complete before letting h/w know there * are new descriptors to fetch. (Only applicable for weak-ordered * memory model archs, such as IA-64). * @@@ -4572,8 -4519,7 +4555,8 @@@ writel(i, tx_ring->tail);

/* we need this if more than one processor can write to our tail - * at a time, it syncronizes IO on IA64/Altix systems */ + * at a time, it synchronizes IO on IA64/Altix systems + */ mmiowb();

return; @@@ -4603,13 -4549,11 +4586,13 @@@ static int __igb_maybe_stop_tx(struct i

/* Herbert's original patch had: * smp_mb__after_netif_stop_queue(); - * but since that doesn't exist yet, just open code it. */ + * but since that doesn't exist yet, just open code it. + */ smp_mb();

/* We need to check again in a case another CPU has just - * made room available. */ + * made room available. + */ if (igb_desc_unused(tx_ring) < size) return -EBUSY;

@@@ -4633,6 -4577,7 +4616,6 @@@ static inline int igb_maybe_stop_tx(str netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, struct igb_ring *tx_ring) { - struct igb_adapter *adapter = netdev_priv(tx_ring->netdev); struct igb_tx_buffer *first; int tso; u32 tx_flags = 0; @@@ -4667,18 -4612,15 +4650,18 @@@

skb_tx_timestamp(skb);

- if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - !(adapter->ptp_tx_skb))) { - skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - tx_flags |= IGB_TX_FLAGS_TSTAMP; + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + struct igb_adapter *adapter = netdev_priv(tx_ring->netdev);

- adapter->ptp_tx_skb = skb_get(skb); - adapter->ptp_tx_start = jiffies; - if (adapter->hw.mac.type == e1000_82576) - schedule_work(&adapter->ptp_tx_work); + if (!(adapter->ptp_tx_skb)) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + tx_flags |= IGB_TX_FLAGS_TSTAMP; + + adapter->ptp_tx_skb = skb_get(skb); + adapter->ptp_tx_start = jiffies; + if (adapter->hw.mac.type == e1000_82576) + schedule_work(&adapter->ptp_tx_work); + } }

if (vlan_tx_tag_present(skb)) { @@@ -4735,7 -4677,8 +4718,7 @@@ static netdev_tx_t igb_xmit_frame(struc return NETDEV_TX_OK; }

- /* - * The minimum packet size with TCTL.PSP set is 17 so pad the skb + /* The minimum packet size with TCTL.PSP set is 17 so pad the skb * in order to meet this minimum size requirement. */ if (unlikely(skb->len < 17)) { @@@ -4749,8 -4692,8 +4732,8 @@@ }

/** - * igb_tx_timeout - Respond to a Tx Hang - * @netdev: network interface device structure + * igb_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure **/ static void igb_tx_timeout(struct net_device *netdev) { @@@ -4779,12 -4722,13 +4762,12 @@@ static void igb_reset_task(struct work_ }

/** - * igb_get_stats64 - Get System Network Statistics - * @netdev: network interface device structure - * @stats: rtnl_link_stats64 pointer - * + * igb_get_stats64 - Get System Network Statistics + * @netdev: network interface device structure + * @stats: rtnl_link_stats64 pointer **/ static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *netdev, - struct rtnl_link_stats64 *stats) + struct rtnl_link_stats64 *stats) { struct igb_adapter *adapter = netdev_priv(netdev);

@@@ -4797,11 -4741,11 +4780,11 @@@ }

/** - * igb_change_mtu - Change the Maximum Transfer Unit - * @netdev: network interface device structure - * @new_mtu: new value for maximum frame size + * igb_change_mtu - Change the Maximum Transfer Unit + * @netdev: network interface device structure + * @new_mtu: new value for maximum frame size * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative on failure **/ static int igb_change_mtu(struct net_device *netdev, int new_mtu) { @@@ -4844,9 -4788,10 +4827,9 @@@ }

/** - * igb_update_stats - Update the board statistics counters - * @adapter: board private structure + * igb_update_stats - Update the board statistics counters + * @adapter: board private structure **/ - void igb_update_stats(struct igb_adapter *adapter, struct rtnl_link_stats64 *net_stats) { @@@ -4861,7 -4806,8 +4844,7 @@@

#define PHY_IDLE_ERROR_COUNT_MASK 0x00FF

- /* - * Prevent stats update while adapter is being reset, or if the pci + /* Prevent stats update while adapter is being reset, or if the pci * connection is down. */ if (adapter->link_speed == 0) @@@ -4995,8 -4941,7 +4978,8 @@@ /* Rx Errors */

/* RLEC on some newer hardware can be incorrect so build - * our own version based on RUC and ROC */ + * our own version based on RUC and ROC + */ net_stats->rx_errors = adapter->stats.rxerrc + adapter->stats.crcerrs + adapter->stats.algnerrc + adapter->stats.ruc + adapter->stats.roc + @@@ -5055,8 -5000,7 +5038,8 @@@ static irqreturn_t igb_msix_other(int i adapter->stats.doosync++; /* The DMA Out of Sync is also indication of a spoof event * in IOV mode. Check the Wrong VM Behavior register to - * see if it is really a spoof event. */ + * see if it is really a spoof event. + */ igb_check_wvbr(adapter); }

@@@ -5130,7 -5074,8 +5113,7 @@@ static void igb_update_tx_dca(struct ig if (hw->mac.type != e1000_82575) txctrl <<= E1000_DCA_TXCTRL_CPUID_SHIFT;

- /* - * We can enable relaxed ordering for reads, but not writes when + /* We can enable relaxed ordering for reads, but not writes when * DCA is enabled. This is due to a known issue in some chipsets * which will cause the DCA tag to be cleared. */ @@@ -5151,7 -5096,8 +5134,7 @@@ static void igb_update_rx_dca(struct ig if (hw->mac.type != e1000_82575) rxctrl <<= E1000_DCA_RXCTRL_CPUID_SHIFT;

- /* - * We can enable relaxed ordering for reads, but not writes when + /* We can enable relaxed ordering for reads, but not writes when * DCA is enabled. This is due to a known issue in some chipsets * which will cause the DCA tag to be cleared. */ @@@ -5220,8 -5166,7 +5203,8 @@@ static int __igb_notify_dca(struct devi case DCA_PROVIDER_REMOVE: if (adapter->flags & IGB_FLAG_DCA_ENABLED) { /* without this a class_device is left - * hanging around in the sysfs model */ + * hanging around in the sysfs model + */ dca_remove_requester(dev); dev_info(&pdev->dev, "DCA disabled\n"); adapter->flags &= ~IGB_FLAG_DCA_ENABLED; @@@ -5234,12 -5179,12 +5217,12 @@@ }

static int igb_notify_dca(struct notifier_block *nb, unsigned long event, - void *p) + void *p) { int ret_val;

ret_val = driver_for_each_device(&igb_driver.driver, NULL, &event, - __igb_notify_dca); + __igb_notify_dca);

return ret_val ? NOTIFY_BAD : NOTIFY_DONE; } @@@ -5253,9 -5198,6 +5236,9 @@@ static int igb_vf_configure(struct igb_ eth_zero_addr(mac_addr); igb_set_vf_mac(adapter, vf, mac_addr);

+ /* By default spoof check is enabled for all VFs */ + adapter->vf_data[vf].spoofchk_enabled = true; + return 0; }

@@@ -5314,7 -5256,7 +5297,7 @@@ static int igb_set_vf_promisc(struct ig struct vf_data_storage *vf_data = &adapter->vf_data[vf];

vf_data->flags &= ~(IGB_VF_FLAG_UNI_PROMISC | - IGB_VF_FLAG_MULTI_PROMISC); + IGB_VF_FLAG_MULTI_PROMISC); vmolr &= ~(E1000_VMOLR_ROPE | E1000_VMOLR_ROMPE | E1000_VMOLR_MPME);

if (*msgbuf & E1000_VF_SET_PROMISC_MULTICAST) { @@@ -5322,7 -5264,8 +5305,7 @@@ vf_data->flags |= IGB_VF_FLAG_MULTI_PROMISC; *msgbuf &= ~E1000_VF_SET_PROMISC_MULTICAST; } else { - /* - * if we have hashes and we are clearing a multicast promisc + /* if we have hashes and we are clearing a multicast promisc * flag we need to write the hashes to the MTA as this step * was previously skipped */ @@@ -5343,6 -5286,7 +5326,6 @@@ return -EINVAL;

return 0; - }

static int igb_set_vf_multicasts(struct igb_adapter *adapter, @@@ -5549,20 -5493,22 +5532,20 @@@ static int igb_ndo_set_vf_vlan(struct n "Setting VLAN %d, QOS 0x%x on VF %d\n", vlan, qos, vf); if (test_bit(__IGB_DOWN, &adapter->state)) { dev_warn(&adapter->pdev->dev, - "The VF VLAN has been set," - " but the PF device is not up.\n"); + "The VF VLAN has been set, but the PF device is not up.\n"); dev_warn(&adapter->pdev->dev, - "Bring the PF device up before" - " attempting to use the VF device.\n"); + "Bring the PF device up before attempting to use the VF device.\n"); } } else { igb_vlvf_set(adapter, adapter->vf_data[vf].pf_vlan, - false, vf); + false, vf); igb_set_vmvir(adapter, vlan, vf); igb_set_vmolr(adapter, vf, true); adapter->vf_data[vf].pf_vlan = 0; adapter->vf_data[vf].pf_qos = 0; - } + } out: - return err; + return err; }

static int igb_set_vf_vlan(struct igb_adapter *adapter, u32 *msgbuf, u32 vf) @@@ -5640,7 -5586,8 +5623,7 @@@ static void igb_vf_reset_msg(struct igb

static int igb_set_vf_mac_addr(struct igb_adapter *adapter, u32 *msg, int vf) { - /* - * The VF MAC Address is stored in a packed array of bytes + /* The VF MAC Address is stored in a packed array of bytes * starting at the second 32 bit word of the msg array */ unsigned char *addr = (char *)&msg[1]; @@@ -5689,9 -5636,11 +5672,9 @@@ static void igb_rcv_msg_from_vf(struct if (msgbuf[0] & (E1000_VT_MSGTYPE_ACK | E1000_VT_MSGTYPE_NACK)) return;

- /* - * until the vf completes a reset it should not be + /* until the vf completes a reset it should not be * allowed to start any configuration. */ - if (msgbuf[0] == E1000_VF_RESET) { igb_vf_reset_msg(adapter, vf); return; @@@ -5711,8 -5660,9 +5694,8 @@@ retval = igb_set_vf_mac_addr(adapter, msgbuf, vf); else dev_warn(&pdev->dev, - "VF %d attempted to override administratively " - "set MAC address\nReload the VF driver to " - "resume operations\n", vf); + "VF %d attempted to override administratively set MAC address\nReload the VF driver to resume operations\n", + vf); break; case E1000_VF_SET_PROMISC: retval = igb_set_vf_promisc(adapter, msgbuf, vf); @@@ -5727,8 -5677,9 +5710,8 @@@ retval = -1; if (vf_data->pf_vlan) dev_warn(&pdev->dev, - "VF %d attempted to override administratively " - "set VLAN tag\nReload the VF driver to " - "resume operations\n", vf); + "VF %d attempted to override administratively set VLAN tag\nReload the VF driver to resume operations\n", + vf); else retval = igb_set_vf_vlan(adapter, msgbuf, vf); break; @@@ -5797,9 -5748,9 +5780,9 @@@ static void igb_set_uta(struct igb_adap }

/** - * igb_intr_msi - Interrupt Handler - * @irq: interrupt number - * @data: pointer to a network interface device structure + * igb_intr_msi - Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure **/ static irqreturn_t igb_intr_msi(int irq, void *data) { @@@ -5842,9 -5793,9 +5825,9 @@@ }

/** - * igb_intr - Legacy Interrupt Handler - * @irq: interrupt number - * @data: pointer to a network interface device structure + * igb_intr - Legacy Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure **/ static irqreturn_t igb_intr(int irq, void *data) { @@@ -5852,13 -5803,11 +5835,13 @@@ struct igb_q_vector *q_vector = adapter->q_vector[0]; struct e1000_hw *hw = &adapter->hw; /* Interrupt Auto-Mask...upon reading ICR, interrupts are masked. No - * need for the IMC write */ + * need for the IMC write + */ u32 icr = rd32(E1000_ICR);

/* IMS will not auto-mask if INT_ASSERTED is not set, and if it is - * not set, then the adapter didn't send an interrupt */ + * not set, then the adapter didn't send an interrupt + */ if (!(icr & E1000_ICR_INT_ASSERTED)) return IRQ_NONE;

@@@ -5917,15 -5866,15 +5900,15 @@@ static void igb_ring_irq_enable(struct }

/** - * igb_poll - NAPI Rx polling callback - * @napi: napi polling structure - * @budget: count of how many packets we should handle + * igb_poll - NAPI Rx polling callback + * @napi: napi polling structure + * @budget: count of how many packets we should handle **/ static int igb_poll(struct napi_struct *napi, int budget) { struct igb_q_vector *q_vector = container_of(napi, - struct igb_q_vector, - napi); + struct igb_q_vector, + napi); bool clean_complete = true;

#ifdef CONFIG_IGB_DCA @@@ -5950,10 -5899,10 +5933,10 @@@ }

/** - * igb_clean_tx_irq - Reclaim resources after transmit completes - * @q_vector: pointer to q_vector containing needed info + * igb_clean_tx_irq - Reclaim resources after transmit completes + * @q_vector: pointer to q_vector containing needed info * - * returns true if ring is completely cleaned + * returns true if ring is completely cleaned **/ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) { @@@ -6059,8 -6008,7 +6042,8 @@@ struct e1000_hw *hw = &adapter->hw;

/* Detect a transmit hang in hardware, this serializes the - * check with the clearing of time_stamp and movement of i */ + * check with the clearing of time_stamp and movement of i + */ clear_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags); if (tx_buffer->next_to_watch && time_after(jiffies, tx_buffer->time_stamp + @@@ -6099,8 -6047,8 +6082,8 @@@

#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) if (unlikely(total_packets && - netif_carrier_ok(tx_ring->netdev) && - igb_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD)) { + netif_carrier_ok(tx_ring->netdev) && + igb_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD)) { /* Make sure that anybody stopping the queue after this * sees the new next_to_clean. */ @@@ -6121,11 -6069,11 +6104,11 @@@ }

/** - * igb_reuse_rx_page - page flip buffer and store it back on the ring - * @rx_ring: rx descriptor ring to store buffers on - * @old_buff: donor buffer to have page reused + * igb_reuse_rx_page - page flip buffer and store it back on the ring + * @rx_ring: rx descriptor ring to store buffers on + * @old_buff: donor buffer to have page reused * - * Synchronizes page for reuse by the adapter + * Synchronizes page for reuse by the adapter **/ static void igb_reuse_rx_page(struct igb_ring *rx_ring, struct igb_rx_buffer *old_buff) @@@ -6185,19 -6133,19 +6168,19 @@@ static bool igb_can_reuse_rx_page(struc }

/** - * igb_add_rx_frag - Add contents of Rx buffer to sk_buff - * @rx_ring: rx descriptor ring to transact packets on - * @rx_buffer: buffer containing page to add - * @rx_desc: descriptor containing length of buffer written by hardware - * @skb: sk_buff to place the data into + * igb_add_rx_frag - Add contents of Rx buffer to sk_buff + * @rx_ring: rx descriptor ring to transact packets on + * @rx_buffer: buffer containing page to add + * @rx_desc: descriptor containing length of buffer written by hardware + * @skb: sk_buff to place the data into * - * This function will add the data contained in rx_buffer->page to the skb. - * This is done either through a direct copy if the data in the buffer is - * less than the skb header size, otherwise it will just attach the page as - * a frag to the skb. + * This function will add the data contained in rx_buffer->page to the skb. + * This is done either through a direct copy if the data in the buffer is + * less than the skb header size, otherwise it will just attach the page as + * a frag to the skb. * - * The function will then update the page offset if necessary and return - * true if the buffer can be reused by the adapter. + * The function will then update the page offset if necessary and return + * true if the buffer can be reused by the adapter. **/ static bool igb_add_rx_frag(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, @@@ -6238,78 -6186,6 +6221,6 @@@ return igb_can_reuse_rx_page(rx_buffer, page, truesize); }

- static struct sk_buff *igb_build_rx_buffer(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc) - { - struct igb_rx_buffer *rx_buffer; - struct sk_buff *skb; - struct page *page; - void *page_addr; - unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); - #if (PAGE_SIZE < 8192) - unsigned int truesize = IGB_RX_BUFSZ; - #else - unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(NET_SKB_PAD + - NET_IP_ALIGN + - size); - #endif - - /* If we spanned a buffer we have a huge mess so test for it */ - BUG_ON(unlikely(!igb_test_staterr(rx_desc, E1000_RXD_STAT_EOP))); - - rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); - - page_addr = page_address(page) + rx_buffer->page_offset; - - /* prefetch first cache line of first page */ - prefetch(page_addr + NET_SKB_PAD + NET_IP_ALIGN); - #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES + NET_SKB_PAD + NET_IP_ALIGN); - #endif - - /* build an skb to around the page buffer */ - skb = build_skb(page_addr, truesize); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_failed++; - return NULL; - } - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - IGB_RX_BUFSZ, - DMA_FROM_DEVICE); - - /* update pointers within the skb to store the data */ - skb_reserve(skb, NET_IP_ALIGN + NET_SKB_PAD); - __skb_put(skb, size); - - /* pull timestamp out of packet data */ - if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); - __skb_pull(skb, IGB_TS_HDR_LEN); - } - - if (igb_can_reuse_rx_page(rx_buffer, page, truesize)) { - /* hand second half of page back to the ring */ - igb_reuse_rx_page(rx_ring, rx_buffer); - } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE); - } - - /* clear contents of buffer_info */ - rx_buffer->dma = 0; - rx_buffer->page = NULL; - - return skb; - } - static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) @@@ -6340,7 -6216,8 +6251,7 @@@ return NULL; }

- /* - * we will be copying header into skb->data in + /* we will be copying header into skb->data in * pskb_may_pull so it is in our interest to prefetch * it now to avoid a possible cache miss */ @@@ -6388,7 -6265,8 +6299,7 @@@ static inline void igb_rx_checksum(stru if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_TCPE | E1000_RXDEXT_STATERR_IPE)) { - /* - * work around errata with sctp packets where the TCPE aka + /* work around errata with sctp packets where the TCPE aka * L4E bit is set incorrectly on 64 byte (60 byte w/o crc) * packets, (aka let the stack check the crc32c) */ @@@ -6419,15 -6297,15 +6330,15 @@@ static inline void igb_rx_hash(struct i }

/** - * igb_is_non_eop - process handling of non-EOP buffers - * @rx_ring: Rx ring being processed - * @rx_desc: Rx descriptor for current buffer - * @skb: current socket buffer containing buffer in progress + * igb_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * @skb: current socket buffer containing buffer in progress * - * This function updates next to clean. If the buffer is an EOP buffer - * this function exits returning false, otherwise it will place the - * sk_buff in the next buffer to be chained and return true indicating - * that this is in fact a non-EOP buffer. + * This function updates next to clean. If the buffer is an EOP buffer + * this function exits returning false, otherwise it will place the + * sk_buff in the next buffer to be chained and return true indicating + * that this is in fact a non-EOP buffer. **/ static bool igb_is_non_eop(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc) @@@ -6447,15 -6325,15 +6358,15 @@@ }

/** - * igb_get_headlen - determine size of header for LRO/GRO - * @data: pointer to the start of the headers - * @max_len: total length of section to find headers in + * igb_get_headlen - determine size of header for LRO/GRO + * @data: pointer to the start of the headers + * @max_len: total length of section to find headers in * - * This function is meant to determine the length of headers that will - * be recognized by hardware for LRO, and GRO offloads. The main - * motivation of doing this is to only perform one pull for IPv4 TCP - * packets so that we can do basic things like calculating the gso_size - * based on the average data per packet. + * This function is meant to determine the length of headers that will + * be recognized by hardware for LRO, and GRO offloads. The main + * motivation of doing this is to only perform one pull for IPv4 TCP + * packets so that we can do basic things like calculating the gso_size + * based on the average data per packet. **/ static unsigned int igb_get_headlen(unsigned char *data, unsigned int max_len) @@@ -6506,7 -6384,7 +6417,7 @@@ return hdr.network - data;

/* record next protocol if header is present */ - if (!hdr.ipv4->frag_off) + if (!(hdr.ipv4->frag_off & htons(IP_OFFSET))) nexthdr = hdr.ipv4->protocol; } else if (protocol == __constant_htons(ETH_P_IPV6)) { if ((hdr.network - data) > (max_len - sizeof(struct ipv6hdr))) @@@ -6542,7 -6420,8 +6453,7 @@@ hdr.network += sizeof(struct udphdr); }

- /* - * If everything has gone correctly hdr.network should be the + /* If everything has gone correctly hdr.network should be the * data section of the packet and will be the end of the header. * If not then it probably represents the end of the last recognized * header. @@@ -6554,17 -6433,17 +6465,17 @@@ }

/** - * igb_pull_tail - igb specific version of skb_pull_tail - * @rx_ring: rx descriptor ring packet is being transacted on - * @rx_desc: pointer to the EOP Rx descriptor - * @skb: pointer to current skb being adjusted + * igb_pull_tail - igb specific version of skb_pull_tail + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being adjusted * - * This function is an igb specific version of __pskb_pull_tail. The - * main difference between this version and the original function is that - * this function can make several assumptions about the state of things - * that allow for significant optimizations versus the standard function. - * As a result we can do things like drop a frag and maintain an accurate - * truesize for the skb. + * This function is an igb specific version of __pskb_pull_tail. The + * main difference between this version and the original function is that + * this function can make several assumptions about the state of things + * that allow for significant optimizations versus the standard function. + * As a result we can do things like drop a frag and maintain an accurate + * truesize for the skb. */ static void igb_pull_tail(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, @@@ -6574,7 -6453,8 +6485,7 @@@ unsigned char *va; unsigned int pull_len;

- /* - * it is valid to use page_address instead of kmap since we are + /* it is valid to use page_address instead of kmap since we are * working with pages allocated out of the lomem pool per * alloc_page(GFP_ATOMIC) */ @@@ -6594,7 -6474,8 +6505,7 @@@ va += IGB_TS_HDR_LEN; }

- /* - * we need the header to contain the greater of either ETH_HLEN or + /* we need the header to contain the greater of either ETH_HLEN or * 60 bytes if the skb->len is less than 60 for skb_pad. */ pull_len = igb_get_headlen(va, IGB_RX_HDR_LEN); @@@ -6610,23 -6491,24 +6521,23 @@@ }

/** - * igb_cleanup_headers - Correct corrupted or empty headers - * @rx_ring: rx descriptor ring packet is being transacted on - * @rx_desc: pointer to the EOP Rx descriptor - * @skb: pointer to current skb being fixed + * igb_cleanup_headers - Correct corrupted or empty headers + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being fixed * - * Address the case where we are pulling data in on pages only - * and as such no data is present in the skb header. + * Address the case where we are pulling data in on pages only + * and as such no data is present in the skb header. * - * In addition if skb is not at least 60 bytes we need to pad it so that - * it is large enough to qualify as a valid Ethernet frame. + * In addition if skb is not at least 60 bytes we need to pad it so that + * it is large enough to qualify as a valid Ethernet frame. * - * Returns true if an error was encountered and skb was freed. + * Returns true if an error was encountered and skb was freed. **/ static bool igb_cleanup_headers(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) { - if (unlikely((igb_test_staterr(rx_desc, E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) { struct net_device *netdev = rx_ring->netdev; @@@ -6653,14 -6535,14 +6564,14 @@@ }

/** - * igb_process_skb_fields - Populate skb header fields from Rx descriptor - * @rx_ring: rx descriptor ring packet is being transacted on - * @rx_desc: pointer to the EOP Rx descriptor - * @skb: pointer to current skb being populated + * igb_process_skb_fields - Populate skb header fields from Rx descriptor + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being populated * - * This function checks the ring, descriptor, and packet information in - * order to populate the hash, checksum, VLAN, timestamp, protocol, and - * other fields within the skb. + * This function checks the ring, descriptor, and packet information in + * order to populate the hash, checksum, VLAN, timestamp, protocol, and + * other fields within the skb. **/ static void igb_process_skb_fields(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, @@@ -6674,7 -6556,7 +6585,7 @@@

igb_ptp_rx_hwtstamp(rx_ring->q_vector, rx_desc, skb);

- if ((dev->features & NETIF_F_HW_VLAN_RX) && + if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) && igb_test_staterr(rx_desc, E1000_RXD_STAT_VP)) { u16 vid; if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_LB) && @@@ -6683,7 -6565,7 +6594,7 @@@ else vid = le16_to_cpu(rx_desc->wb.upper.vlan);

- __vlan_hwaccel_put_tag(skb, vid); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); }

skb_record_rx_queue(skb, rx_ring->queue_index); @@@ -6719,10 -6601,7 +6630,7 @@@ static bool igb_clean_rx_irq(struct igb rmb();

/* retrieve a buffer from the ring */ - if (ring_uses_build_skb(rx_ring)) - skb = igb_build_rx_buffer(rx_ring, rx_desc); - else - skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb); + skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb);

/* exit if we failed to retrieve a buffer */ if (!skb) @@@ -6791,7 -6670,8 +6699,7 @@@ static bool igb_alloc_mapped_page(struc /* map page for use */ dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);

- /* - * if mapping failed free memory back to system since + /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { @@@ -6808,17 -6688,9 +6716,9 @@@ return true; }

- static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring) - { - if (ring_uses_build_skb(rx_ring)) - return NET_SKB_PAD + NET_IP_ALIGN; - else - return 0; - } - /** - * igb_alloc_rx_buffers - Replace used receive buffers; packet split - * @adapter: address of board private structure + * igb_alloc_rx_buffers - Replace used receive buffers; packet split + * @adapter: address of board private structure **/ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) { @@@ -6838,12 -6710,11 +6738,10 @@@ if (!igb_alloc_mapped_page(rx_ring, bi)) break;

- /* - * Refresh the desc even if buffer_addrs didn't change + /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + - bi->page_offset + - igb_rx_offset(rx_ring)); + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);

rx_desc++; bi++; @@@ -6869,7 -6740,8 +6767,7 @@@ /* update next to alloc since we have filled the ring */ rx_ring->next_to_alloc = i;

- /* - * Force memory writes to complete before letting h/w + /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, * such as IA-64). @@@ -6954,7 -6826,7 +6852,7 @@@ static void igb_vlan_mode(struct net_de struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u32 ctrl, rctl; - bool enable = !!(features & NETIF_F_HW_VLAN_RX); + bool enable = !!(features & NETIF_F_HW_VLAN_CTAG_RX);

if (enable) { /* enable VLAN tag insert/strip */ @@@ -6976,8 -6848,7 +6874,8 @@@ igb_rlpml_set(adapter); }

-static int igb_vlan_rx_add_vid(struct net_device *netdev, u16 vid) +static int igb_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, u16 vid) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@@ -6994,8 -6865,7 +6892,8 @@@ return 0; }

-static int igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) +static int igb_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, u16 vid) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@@ -7021,7 -6891,7 +6919,7 @@@ static void igb_restore_vlan(struct igb igb_vlan_mode(adapter->netdev, adapter->netdev->features);

for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID) - igb_vlan_rx_add_vid(adapter->netdev, vid); + igb_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), vid); }

int igb_set_spd_dplx(struct igb_adapter *adapter, u32 spd, u8 dplx) @@@ -7032,24 -6902,15 +6930,24 @@@ mac->autoneg = 0;

/* Make sure dplx is at most 1 bit and lsb of speed is not set - * for the switch() below to work */ + * for the switch() below to work + */ if ((spd & 1) || (dplx & ~1)) goto err_inval;

- /* Fiber NIC's only allow 1000 Gbps Full duplex */ - if ((adapter->hw.phy.media_type == e1000_media_type_internal_serdes) && - spd != SPEED_1000 && - dplx != DUPLEX_FULL) - goto err_inval; + /* Fiber NIC's only allow 1000 gbps Full duplex + * and 100Mbps Full duplex for 100baseFx sfp + */ + if (adapter->hw.phy.media_type == e1000_media_type_internal_serdes) { + switch (spd + dplx) { + case SPEED_10 + DUPLEX_HALF: + case SPEED_10 + DUPLEX_FULL: + case SPEED_100 + DUPLEX_HALF: + goto err_inval; + default: + break; + } + }

switch (spd + dplx) { case SPEED_10 + DUPLEX_HALF: @@@ -7148,8 -7009,7 +7046,8 @@@ static int __igb_shutdown(struct pci_de igb_power_up_link(adapter);

/* Release control of h/w to f/w. If f/w is AMT enabled, this - * would have already happened in close and is redundant. */ + * would have already happened in close and is redundant. + */ igb_release_hw_control(adapter);

pci_disable_device(pdev); @@@ -7211,8 -7071,7 +7109,8 @@@ static int igb_resume(struct device *de igb_reset(adapter);

/* let the f/w know that the h/w is now under the control of the - * driver. */ + * driver. + */ igb_get_hw_control(adapter);

wr32(E1000_WUS, ~0); @@@ -7348,7 -7207,8 +7246,7 @@@ static int igb_pci_sriov_configure(stru }

#ifdef CONFIG_NET_POLL_CONTROLLER -/* - * Polling 'interrupt' - used by things like netconsole to send skbs +/* Polling 'interrupt' - used by things like netconsole to send skbs * without having to re-enable interrupts. It's not called while * the interrupt routine is executing. */ @@@ -7371,13 -7231,13 +7269,13 @@@ static void igb_netpoll(struct net_devi #endif /* CONFIG_NET_POLL_CONTROLLER */

/** - * igb_io_error_detected - called when PCI error is detected - * @pdev: Pointer to PCI device - * @state: The current pci connection state + * igb_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state * - * This function is called after a PCI bus error affecting - * this device has been detected. - */ + * This function is called after a PCI bus error affecting + * this device has been detected. + **/ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev, pci_channel_state_t state) { @@@ -7398,12 -7258,12 +7296,12 @@@ }

/** - * igb_io_slot_reset - called after the pci bus has been reset. - * @pdev: Pointer to PCI device + * igb_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device * - * Restart the card from scratch, as if from a cold-boot. Implementation - * resembles the first-half of the igb_resume routine. - */ + * Restart the card from scratch, as if from a cold-boot. Implementation + * resembles the first-half of the igb_resume routine. + **/ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); @@@ -7431,9 -7291,8 +7329,9 @@@

err = pci_cleanup_aer_uncorrect_error_status(pdev); if (err) { - dev_err(&pdev->dev, "pci_cleanup_aer_uncorrect_error_status " - "failed 0x%0x\n", err); + dev_err(&pdev->dev, + "pci_cleanup_aer_uncorrect_error_status failed 0x%0x\n", + err); /* non-fatal, continue */ }

@@@ -7441,12 -7300,12 +7339,12 @@@ }

/** - * igb_io_resume - called when traffic can start flowing again. - * @pdev: Pointer to PCI device + * igb_io_resume - called when traffic can start flowing again. + * @pdev: Pointer to PCI device * - * This callback is called when the error recovery driver tells us that - * its OK to resume normal operation. Implementation resembles the - * second-half of the igb_resume routine. + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. Implementation resembles the + * second-half of the igb_resume routine. */ static void igb_io_resume(struct pci_dev *pdev) { @@@ -7463,13 -7322,12 +7361,13 @@@ netif_device_attach(netdev);

/* let the f/w know that the h/w is now under the control of the - * driver. */ + * driver. + */ igb_get_hw_control(adapter); }

static void igb_rar_set_qsel(struct igb_adapter *adapter, u8 *addr, u32 index, - u8 qsel) + u8 qsel) { u32 rar_low, rar_high; struct e1000_hw *hw = &adapter->hw; @@@ -7478,7 -7336,7 +7376,7 @@@ * from network order (big endian) to little endian */ rar_low = ((u32) addr[0] | ((u32) addr[1] << 8) | - ((u32) addr[2] << 16) | ((u32) addr[3] << 24)); + ((u32) addr[2] << 16) | ((u32) addr[3] << 24)); rar_high = ((u32) addr[4] | ((u32) addr[5] << 8));

/* Indicate to hardware the Address is Valid. */ @@@ -7496,12 -7354,11 +7394,12 @@@ }

static int igb_set_vf_mac(struct igb_adapter *adapter, - int vf, unsigned char *mac_addr) + int vf, unsigned char *mac_addr) { struct e1000_hw *hw = &adapter->hw; /* VF MAC addresses start at end of receive addresses and moves - * torwards the first, as a result a collision should not be possible */ + * towards the first, as a result a collision should not be possible + */ int rar_entry = hw->mac.rar_entry_count - (vf + 1);

memcpy(adapter->vf_data[vf].vf_mac_addresses, mac_addr, ETH_ALEN); @@@ -7518,13 -7375,13 +7416,13 @@@ static int igb_ndo_set_vf_mac(struct ne return -EINVAL; adapter->vf_data[vf].flags |= IGB_VF_FLAG_PF_SET_MAC; dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf); - dev_info(&adapter->pdev->dev, "Reload the VF driver to make this" - " change effective."); + dev_info(&adapter->pdev->dev, + "Reload the VF driver to make this change effective."); if (test_bit(__IGB_DOWN, &adapter->state)) { - dev_warn(&adapter->pdev->dev, "The VF MAC address has been set," - " but the PF device is not up.\n"); - dev_warn(&adapter->pdev->dev, "Bring the PF device up before" - " attempting to use the VF device.\n"); + dev_warn(&adapter->pdev->dev, + "The VF MAC address has been set, but the PF device is not up.\n"); + dev_warn(&adapter->pdev->dev, + "Bring the PF device up before attempting to use the VF device.\n"); } return igb_set_vf_mac(adapter, vf, mac); } @@@ -7551,19 -7408,19 +7449,19 @@@ static void igb_set_vf_rate_limit(struc /* Calculate the rate factor values to set */ rf_int = link_speed / tx_rate; rf_dec = (link_speed - (rf_int * tx_rate)); - rf_dec = (rf_dec * (1<<E1000_RTTBCNRC_RF_INT_SHIFT)) / tx_rate; + rf_dec = (rf_dec * (1 << E1000_RTTBCNRC_RF_INT_SHIFT)) / + tx_rate;

bcnrc_val = E1000_RTTBCNRC_RS_ENA; - bcnrc_val |= ((rf_int<<E1000_RTTBCNRC_RF_INT_SHIFT) & - E1000_RTTBCNRC_RF_INT_MASK); + bcnrc_val |= ((rf_int << E1000_RTTBCNRC_RF_INT_SHIFT) & + E1000_RTTBCNRC_RF_INT_MASK); bcnrc_val |= (rf_dec & E1000_RTTBCNRC_RF_DEC_MASK); } else { bcnrc_val = 0; }

wr32(E1000_RTTDQSEL, vf); /* vf X uses queue X */ - /* - * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM + /* Set global transmit compensation time to the MMW_SIZE in RTTBCNRM * register. MMW_SIZE=0x014 if 9728-byte jumbo is supported. */ wr32(E1000_RTTBCNRM, 0x14); @@@ -7585,7 -7442,8 +7483,7 @@@ static void igb_check_vf_rate_limit(str reset_rate = true; adapter->vf_rate_link_speed = 0; dev_info(&adapter->pdev->dev, - "Link speed has been changed. VF Transmit " - "rate is disabled\n"); + "Link speed has been changed. VF Transmit rate is disabled\n"); }

for (i = 0; i < adapter->vfs_allocated_count; i++) { @@@ -7593,8 -7451,8 +7491,8 @@@ adapter->vf_data[i].tx_rate = 0;

igb_set_vf_rate_limit(&adapter->hw, i, - adapter->vf_data[i].tx_rate, - actual_link_speed); + adapter->vf_data[i].tx_rate, + actual_link_speed); } }

@@@ -7620,33 -7478,6 +7518,33 @@@ static int igb_ndo_set_vf_bw(struct net return 0; }

+static int igb_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, + bool setting) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 reg_val, reg_offset; + + if (!adapter->vfs_allocated_count) + return -EOPNOTSUPP; + + if (vf >= adapter->vfs_allocated_count) + return -EINVAL; + + reg_offset = (hw->mac.type == e1000_82576) ? E1000_DTXSWC : E1000_TXSWC; + reg_val = rd32(reg_offset); + if (setting) + reg_val |= ((1 << vf) | + (1 << (vf + E1000_DTXSWC_VLAN_SPOOF_SHIFT))); + else + reg_val &= ~((1 << vf) | + (1 << (vf + E1000_DTXSWC_VLAN_SPOOF_SHIFT))); + wr32(reg_offset, reg_val); + + adapter->vf_data[vf].spoofchk_enabled = setting; + return E1000_SUCCESS; +} + static int igb_ndo_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivi) { @@@ -7658,7 -7489,6 +7556,7 @@@ ivi->tx_rate = adapter->vf_data[vf].tx_rate; ivi->vlan = adapter->vf_data[vf].pf_vlan; ivi->qos = adapter->vf_data[vf].pf_qos; + ivi->spoofchk = adapter->vf_data[vf].spoofchk_enabled; return 0; }

@@@ -7671,7 -7501,6 +7569,7 @@@ static void igb_vmm_control(struct igb_ case e1000_82575: case e1000_i210: case e1000_i211: + case e1000_i354: default: /* replication is not supported for 82575 */ return; @@@ -7694,7 -7523,7 +7592,7 @@@ igb_vmdq_set_loopback_pf(hw, true); igb_vmdq_set_replication_pf(hw, true); igb_vmdq_set_anti_spoofing_pf(hw, true, - adapter->vfs_allocated_count); + adapter->vfs_allocated_count); } else { igb_vmdq_set_loopback_pf(hw, false); igb_vmdq_set_replication_pf(hw, false); @@@ -7714,7 -7543,8 +7612,7 @@@ static void igb_init_dmac(struct igb_ad /* force threshold to 0. */ wr32(E1000_DMCTXTH, 0);

- /* - * DMA Coalescing high water mark needs to be greater + /* DMA Coalescing high water mark needs to be greater * than the Rx threshold. Set hwm to PBA - max frame * size in 16B units, capping it at PBA - 6KB. */ @@@ -7727,7 -7557,8 +7625,7 @@@ & E1000_FCRTC_RTH_COAL_MASK); wr32(E1000_FCRTC, reg);

- /* - * Set the DMA Coalescing Rx threshold to PBA - 2 * max + /* Set the DMA Coalescing Rx threshold to PBA - 2 * max * frame size, capping it at PBA - 10KB. */ dmac_thr = pba - adapter->max_frame_size / 512; @@@ -7745,12 -7576,11 +7643,12 @@@ reg |= (1000 >> 5);

/* Disable BMC-to-OS Watchdog Enable */ - reg &= ~E1000_DMACR_DC_BMC2OSW_EN; + if (hw->mac.type != e1000_i354) + reg &= ~E1000_DMACR_DC_BMC2OSW_EN; + wr32(E1000_DMACR, reg);

- /* - * no lower threshold to disable + /* no lower threshold to disable * coalescing(smart fifb)-UTRESH=0 */ wr32(E1000_DMCRTRH, 0); @@@ -7759,13 -7589,15 +7657,13 @@@

wr32(E1000_DMCTLX, reg);

- /* - * free space in tx packet buffer to wake from + /* free space in tx packet buffer to wake from * DMA coal */ wr32(E1000_DMCTXTH, (IGB_MIN_TXPBSIZE - (IGB_TX_BUF_4096 + adapter->max_frame_size)) >> 6);

- /* - * make low power state decision controlled + /* make low power state decision controlled * by DMA coal */ reg = rd32(E1000_PCIEMISC); @@@ -7779,8 -7611,7 +7677,8 @@@ } }

-/* igb_read_i2c_byte - Reads 8 bit word over I2C +/** + * igb_read_i2c_byte - Reads 8 bit word over I2C * @hw: pointer to hardware structure * @byte_offset: byte offset to read * @dev_addr: device address @@@ -7788,9 -7619,9 +7686,9 @@@ * * Performs byte read operation over I2C interface at * a specified device address. - */ + **/ s32 igb_read_i2c_byte(struct e1000_hw *hw, u8 byte_offset, - u8 dev_addr, u8 *data) + u8 dev_addr, u8 *data) { struct igb_adapter *adapter = container_of(hw, struct igb_adapter, hw); struct i2c_client *this_client = adapter->i2c_client; @@@ -7817,8 -7648,7 +7715,8 @@@ } }

-/* igb_write_i2c_byte - Writes 8 bit word over I2C +/** + * igb_write_i2c_byte - Writes 8 bit word over I2C * @hw: pointer to hardware structure * @byte_offset: byte offset to write * @dev_addr: device address @@@ -7826,9 -7656,9 +7724,9 @@@ * * Performs byte write operation over I2C interface at * a specified device address. - */ + **/ s32 igb_write_i2c_byte(struct e1000_hw *hw, u8 byte_offset, - u8 dev_addr, u8 data) + u8 dev_addr, u8 data) { struct igb_adapter *adapter = container_of(hw, struct igb_adapter, hw); struct i2c_client *this_client = adapter->i2c_client; diff --combined drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 2d4bdcc,97e3366..1e7d587 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@@ -35,7 -35,7 +35,7 @@@ #include <linux/ip.h> #include <linux/tcp.h> #include <linux/ipv6.h> -#ifdef NETIF_F_HW_VLAN_TX +#ifdef NETIF_F_HW_VLAN_CTAG_TX #include <linux/if_vlan.h> #endif

@@@ -661,7 -661,13 +661,7 @@@ int ixgbe_vf_configuration(struct pci_d bool enable = ((event_mask & 0x10000000U) != 0);

if (enable) { - eth_random_addr(vf_mac_addr); - e_info(probe, "IOV: VF %d is enabled MAC %pM\n", - vfn, vf_mac_addr); - /* - * Store away the VF "permananet" MAC address, it will ask - * for it later. - */ + eth_zero_addr(vf_mac_addr); memcpy(adapter->vfinfo[vfn].vf_mac_addresses, vf_mac_addr, 6); }

@@@ -682,8 -688,7 +682,8 @@@ static int ixgbe_vf_reset_msg(struct ix ixgbe_vf_reset_event(adapter, vf);

/* set vf mac address */ - ixgbe_set_vf_mac(adapter, vf, vf_mac); + if (!is_zero_ether_addr(vf_mac)) + ixgbe_set_vf_mac(adapter, vf, vf_mac);

vf_shift = vf % 32; reg_offset = vf / 32; @@@ -724,16 -729,8 +724,16 @@@ IXGBE_WRITE_REG(hw, IXGBE_VMECM(reg_offset), reg);

/* reply to reset with ack and vf mac address */ - msgbuf[0] = IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK; - memcpy(addr, vf_mac, ETH_ALEN); + msgbuf[0] = IXGBE_VF_RESET; + if (!is_zero_ether_addr(vf_mac)) { + msgbuf[0] |= IXGBE_VT_MSGTYPE_ACK; + memcpy(addr, vf_mac, ETH_ALEN); + } else { + msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK; + dev_warn(&adapter->pdev->dev, + "VF %d has no MAC address assigned, you may have to assign one manually\n", + vf); + }

/* * Piggyback the multicast filter type so VF can compute the @@@ -1052,6 -1049,12 +1052,12 @@@ int ixgbe_ndo_set_vf_vlan(struct net_de if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7)) return -EINVAL; if (vlan || qos) { + if (adapter->vfinfo[vf].pf_vlan) + err = ixgbe_set_vf_vlan(adapter, false, + adapter->vfinfo[vf].pf_vlan, + vf); + if (err) + goto out; err = ixgbe_set_vf_vlan(adapter, true, vlan, vf); if (err) goto out; diff --combined drivers/net/ethernet/marvell/Kconfig index 0051f0e,434e33c..a49e81b --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@@ -21,8 -21,8 +21,8 @@@ if NET_VENDOR_MARVEL config MV643XX_ETH tristate "Marvell Discovery (643XX) and Orion ethernet support" depends on (MV64X60 || PPC32 || PLAT_ORION) && INET - select INET_LRO select PHYLIB + select MVMDIO ---help--- This driver supports the gigabit ethernet MACs in the Marvell Discovery PPC/MIPS chipset family (MV643XX) and @@@ -33,17 -33,19 +33,17 @@@

config MVMDIO tristate "Marvell MDIO interface support" + select PHYLIB ---help--- This driver supports the MDIO interface found in the network interface units of the Marvell EBU SoCs (Kirkwood, Orion5x, Dove, Armada 370 and Armada XP).

- For now, this driver is only needed for the MVNETA driver - (used on Armada 370 and XP), but it could be used in the - future by the MV643XX_ETH driver. + This driver is used by the MV643XX_ETH and MVNETA drivers.

config MVNETA tristate "Marvell Armada 370/XP network interface support" depends on MACH_ARMADA_370_XP - select PHYLIB select MVMDIO ---help--- This driver supports the network interface units in the diff --combined drivers/net/ethernet/marvell/mvneta.c index e48261e,a47a097..c966785 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@@ -374,7 -374,6 +374,6 @@@ static int rxq_number = 8 static int txq_number = 8;

static int rxq_def; - static int txq_def;

#define MVNETA_DRIVER_NAME "mvneta" #define MVNETA_DRIVER_VERSION "1.0" @@@ -1475,7 -1474,8 +1474,8 @@@ error static int mvneta_tx(struct sk_buff *skb, struct net_device *dev) { struct mvneta_port *pp = netdev_priv(dev); - struct mvneta_tx_queue *txq = &pp->txqs[txq_def]; + u16 txq_id = skb_get_queue_mapping(skb); + struct mvneta_tx_queue *txq = &pp->txqs[txq_id]; struct mvneta_tx_desc *tx_desc; struct netdev_queue *nq; int frags = 0; @@@ -1485,7 -1485,7 +1485,7 @@@ goto out;

frags = skb_shinfo(skb)->nr_frags + 1; - nq = netdev_get_tx_queue(dev, txq_def); + nq = netdev_get_tx_queue(dev, txq_id);

/* Get a descriptor for the first part of the packet */ tx_desc = mvneta_txq_next_desc_get(txq); @@@ -1969,8 -1969,13 +1969,8 @@@ static int mvneta_rxq_init(struct mvnet rxq->descs = dma_alloc_coherent(pp->dev->dev.parent, rxq->size * MVNETA_DESC_ALIGNED_SIZE, &rxq->descs_phys, GFP_KERNEL); - if (rxq->descs == NULL) { - netdev_err(pp->dev, - "rxq=%d: Can't allocate %d bytes for %d RX descr\n", - rxq->id, rxq->size * MVNETA_DESC_ALIGNED_SIZE, - rxq->size); + if (rxq->descs == NULL) return -ENOMEM; - }

BUG_ON(rxq->descs != PTR_ALIGN(rxq->descs, MVNETA_CPU_D_CACHE_LINE_SIZE)); @@@ -2024,8 -2029,13 +2024,8 @@@ static int mvneta_txq_init(struct mvnet txq->descs = dma_alloc_coherent(pp->dev->dev.parent, txq->size * MVNETA_DESC_ALIGNED_SIZE, &txq->descs_phys, GFP_KERNEL); - if (txq->descs == NULL) { - netdev_err(pp->dev, - "txQ=%d: Can't allocate %d bytes for %d TX descr\n", - txq->id, txq->size * MVNETA_DESC_ALIGNED_SIZE, - txq->size); + if (txq->descs == NULL) return -ENOMEM; - }

/* Make sure descriptor address is cache line size aligned */ BUG_ON(txq->descs != @@@ -2679,7 -2689,7 +2679,7 @@@ static int mvneta_probe(struct platform return -EINVAL; }

- dev = alloc_etherdev_mq(sizeof(struct mvneta_port), 8); + dev = alloc_etherdev_mqs(sizeof(struct mvneta_port), txq_number, rxq_number); if (!dev) return -ENOMEM;

@@@ -2761,16 -2771,17 +2761,17 @@@

netif_napi_add(dev, &pp->napi, mvneta_poll, pp->weight);

+ dev->features = NETIF_F_SG | NETIF_F_IP_CSUM; + dev->hw_features |= NETIF_F_SG | NETIF_F_IP_CSUM; + dev->vlan_features |= NETIF_F_SG | NETIF_F_IP_CSUM; + dev->priv_flags |= IFF_UNICAST_FLT; + err = register_netdev(dev); if (err < 0) { dev_err(&pdev->dev, "failed to register\n"); goto err_deinit; }

- dev->features = NETIF_F_SG | NETIF_F_IP_CSUM; - dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM; - dev->priv_flags |= IFF_UNICAST_FLT; - netdev_info(dev, "mac: %pM\n", dev->dev_addr);

platform_set_drvdata(pdev, pp->dev); @@@ -2833,4 -2844,3 +2834,3 @@@ module_param(rxq_number, int, S_IRUGO) module_param(txq_number, int, S_IRUGO);

module_param(rxq_def, int, S_IRUGO); - module_param(txq_def, int, S_IRUGO); diff --combined drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 32a95c1,edd63f1..fd0829c --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@@ -6,7 -6,6 +6,7 @@@ */

#include "qlcnic.h" +#include "qlcnic_sriov.h" #include <linux/if_vlan.h> #include <linux/ipv6.h> #include <linux/ethtool.h> @@@ -14,7 -13,100 +14,7 @@@

#define QLCNIC_MAX_TX_QUEUES 1 #define RSS_HASHTYPE_IP_TCP 0x3 - -/* status descriptor mailbox data - * @phy_addr: physical address of buffer - * @sds_ring_size: buffer size - * @intrpt_id: interrupt id - * @intrpt_val: source of interrupt - */ -struct qlcnic_sds_mbx { - u64 phy_addr; - u8 rsvd1[16]; - u16 sds_ring_size; - u16 rsvd2[3]; - u16 intrpt_id; - u8 intrpt_val; - u8 rsvd3[5]; -} __packed; - -/* receive descriptor buffer data - * phy_addr_reg: physical address of regular buffer - * phy_addr_jmb: physical address of jumbo buffer - * reg_ring_sz: size of regular buffer - * reg_ring_len: no. of entries in regular buffer - * jmb_ring_len: no. of entries in jumbo buffer - * jmb_ring_sz: size of jumbo buffer - */ -struct qlcnic_rds_mbx { - u64 phy_addr_reg; - u64 phy_addr_jmb; - u16 reg_ring_sz; - u16 reg_ring_len; - u16 jmb_ring_sz; - u16 jmb_ring_len; -} __packed; - -/* host producers for regular and jumbo rings */ -struct __host_producer_mbx { - u32 reg_buf; - u32 jmb_buf; -} __packed; - -/* Receive context mailbox data outbox registers - * @state: state of the context - * @vport_id: virtual port id - * @context_id: receive context id - * @num_pci_func: number of pci functions of the port - * @phy_port: physical port id - */ -struct qlcnic_rcv_mbx_out { - u8 rcv_num; - u8 sts_num; - u16 ctx_id; - u8 state; - u8 num_pci_func; - u8 phy_port; - u8 vport_id; - u32 host_csmr[QLCNIC_MAX_RING_SETS]; - struct __host_producer_mbx host_prod[QLCNIC_MAX_RING_SETS]; -} __packed; - -struct qlcnic_add_rings_mbx_out { - u8 rcv_num; - u8 sts_num; - u16 ctx_id; - u32 host_csmr[QLCNIC_MAX_RING_SETS]; - struct __host_producer_mbx host_prod[QLCNIC_MAX_RING_SETS]; -} __packed; - -/* Transmit context mailbox inbox registers - * @phys_addr: DMA address of the transmit buffer - * @cnsmr_index: host consumer index - * @size: legth of transmit buffer ring - * @intr_id: interrput id - * @src: src of interrupt - */ -struct qlcnic_tx_mbx { - u64 phys_addr; - u64 cnsmr_index; - u16 size; - u16 intr_id; - u8 src; - u8 rsvd[3]; -} __packed; - -/* Transmit context mailbox outbox registers - * @host_prod: host producer index - * @ctx_id: transmit context id - * @state: state of the transmit context - */ -struct qlcnic_tx_mbx_out { - u32 host_prod; - u16 ctx_id; - u8 state; - u8 rsvd; -} __packed; +#define QLC_83XX_FW_MBX_CMD 0

static const struct qlcnic_mailbox_metadata qlcnic_83xx_mbx_tbl[] = { {QLCNIC_CMD_CONFIGURE_IP_ADDR, 6, 1}, @@@ -64,11 -156,9 +64,11 @@@ {QLCNIC_CMD_SET_LED_CONFIG, 5, 1}, {QLCNIC_CMD_GET_LED_CONFIG, 1, 5}, {QLCNIC_CMD_ADD_RCV_RINGS, 130, 26}, + {QLCNIC_CMD_CONFIG_VPORT, 4, 4}, + {QLCNIC_CMD_BC_EVENT_SETUP, 2, 1}, };

-static const u32 qlcnic_83xx_ext_reg_tbl[] = { +const u32 qlcnic_83xx_ext_reg_tbl[] = { 0x38CC, /* Global Reset */ 0x38F0, /* Wildcard */ 0x38FC, /* Informant */ @@@ -114,7 -204,7 +114,7 @@@ 0x34A4, /* QLC_83XX_ASIC_TEMP */ };

-static const u32 qlcnic_83xx_reg_tbl[] = { +const u32 qlcnic_83xx_reg_tbl[] = { 0x34A8, /* PEG_HALT_STAT1 */ 0x34AC, /* PEG_HALT_STAT2 */ 0x34B0, /* FW_HEARTBEAT */ @@@ -157,8 -247,6 +157,8 @@@ static struct qlcnic_hardware_ops qlcni .process_lb_rcv_ring_diag = qlcnic_83xx_process_rcv_ring_diag, .create_rx_ctx = qlcnic_83xx_create_rx_ctx, .create_tx_ctx = qlcnic_83xx_create_tx_ctx, + .del_rx_ctx = qlcnic_83xx_del_rx_ctx, + .del_tx_ctx = qlcnic_83xx_del_tx_ctx, .setup_link_event = qlcnic_83xx_setup_link_event, .get_nic_info = qlcnic_83xx_get_nic_info, .get_pci_info = qlcnic_83xx_get_pci_info, @@@ -172,7 -260,6 +172,7 @@@ .config_promisc_mode = qlcnic_83xx_nic_set_promisc, .change_l2_filter = qlcnic_83xx_change_l2_filter, .get_board_info = qlcnic_83xx_get_port_info, + .free_mac_list = qlcnic_82xx_free_mac_list, };

static struct qlcnic_nic_template qlcnic_83xx_ops = { @@@ -268,20 -355,14 +268,20 @@@ int qlcnic_83xx_setup_intr(struct qlcni num_intr)); /* account for AEN interrupt MSI-X based interrupts */ num_msix += 1; - num_msix += adapter->max_drv_tx_rings; + + if (!(adapter->flags & QLCNIC_TX_INTR_SHARED)) + num_msix += adapter->max_drv_tx_rings; + err = qlcnic_enable_msix(adapter, num_msix); if (err == -ENOMEM) return err; if (adapter->flags & QLCNIC_MSIX_ENABLED) num_msix = adapter->ahw->num_msix; - else + else { + if (qlcnic_sriov_vf_check(adapter)) + return -EINVAL; num_msix = 1; + } /* setup interrupt mapping table for fw */ ahw->intr_tbl = vzalloc(num_msix * sizeof(struct qlcnic_intrpt_config)); @@@ -340,13 -421,12 +340,13 @@@ inline void qlcnic_83xx_enable_legacy_m writel(0, adapter->ahw->pci_base0 + mask); }

-inline void qlcnic_83xx_disable_mbx_intr(struct qlcnic_adapter *adapter) +void qlcnic_83xx_disable_mbx_intr(struct qlcnic_adapter *adapter) { u32 mask;

mask = QLCRDX(adapter->ahw, QLCNIC_DEF_INT_MASK); writel(1, adapter->ahw->pci_base0 + mask); + QLCWRX(adapter->ahw, QLCNIC_MBX_INTR_ENBL, 0); }

static inline void qlcnic_83xx_get_mbx_data(struct qlcnic_adapter *adapter, @@@ -402,8 -482,7 +402,8 @@@ static void qlcnic_83xx_poll_process_ae

event = readl(QLCNIC_MBX_FW(adapter->ahw, 0)); if (event & QLCNIC_MBX_ASYNC_EVENT) - qlcnic_83xx_process_aen(adapter); + __qlcnic_83xx_process_aen(adapter); + out: qlcnic_83xx_enable_legacy_msix_mbx_intr(adapter); spin_unlock_irqrestore(&adapter->ahw->mbx_lock, flags); @@@ -456,15 -535,17 +456,15 @@@ done

void qlcnic_83xx_free_mbx_intr(struct qlcnic_adapter *adapter) { - u32 val = 0, num_msix = adapter->ahw->num_msix - 1; + u32 num_msix; + + qlcnic_83xx_disable_mbx_intr(adapter);

if (adapter->flags & QLCNIC_MSIX_ENABLED) num_msix = adapter->ahw->num_msix - 1; else num_msix = 0;

- QLCWRX(adapter->ahw, QLCNIC_MBX_INTR_ENBL, val); - - qlcnic_83xx_disable_mbx_intr(adapter); - msleep(20); synchronize_irq(adapter->msix_entries[num_msix].vector); free_irq(adapter->msix_entries[num_msix].vector, adapter); @@@ -514,7 -595,7 +514,7 @@@ int qlcnic_83xx_setup_mbx_intr(struct q void qlcnic_83xx_get_func_no(struct qlcnic_adapter *adapter) { u32 val = QLCRDX(adapter->ahw, QLCNIC_INFORMANT); - adapter->ahw->pci_func = val & 0xf; + adapter->ahw->pci_func = (val >> 24) & 0xff; }

int qlcnic_83xx_cam_lock(struct qlcnic_adapter *adapter) @@@ -626,11 -707,6 +626,11 @@@ void qlcnic_83xx_check_vf(struct qlcnic ahw->fw_hal_version = 2; qlcnic_get_func_no(adapter);

+ if (qlcnic_sriov_vf_check(adapter)) { + qlcnic_sriov_vf_set_ops(adapter); + return; + } + /* Determine function privilege level */ op_mode = QLCRDX(adapter->ahw, QLC_83XX_DRV_OP_MODE); if (op_mode == QLC_83XX_DEFAULT_OPMODE) @@@ -646,9 -722,6 +646,9 @@@ ahw->fw_hal_version); adapter->nic_ops = &qlcnic_vf_ops; } else { + if (pci_find_ext_capability(adapter->pdev, + PCI_EXT_CAP_ID_SRIOV)) + set_bit(__QLCNIC_SRIOV_CAPABLE, &adapter->state); adapter->nic_ops = &qlcnic_83xx_ops; } } @@@ -682,7 -755,7 +682,7 @@@ static void qlcnic_dump_mbx(struct qlcn }

/* Mailbox response for mac rcode */ -static u32 qlcnic_83xx_mac_rcode(struct qlcnic_adapter *adapter) +u32 qlcnic_83xx_mac_rcode(struct qlcnic_adapter *adapter) { u32 fw_data; u8 mac_cmd_rcode; @@@ -696,7 -769,7 +696,7 @@@ return 1; }

-static u32 qlcnic_83xx_mbx_poll(struct qlcnic_adapter *adapter) +u32 qlcnic_83xx_mbx_poll(struct qlcnic_adapter *adapter) { u32 data; unsigned long wait_time = 0; @@@ -759,7 -832,7 +759,7 @@@ poll /* Get the FW response data */ fw_data = readl(QLCNIC_MBX_FW(ahw, 0)); if (fw_data & QLCNIC_MBX_ASYNC_EVENT) { - qlcnic_83xx_process_aen(adapter); + __qlcnic_83xx_process_aen(adapter); mbx_val = QLCRDX(ahw, QLCNIC_HOST_MBX_CTRL); if (mbx_val) goto poll; @@@ -811,7 -884,6 +811,7 @@@ int qlcnic_83xx_alloc_mbx_args(struct q size = ARRAY_SIZE(qlcnic_83xx_mbx_tbl); for (i = 0; i < size; i++) { if (type == mbx_tbl[i].cmd) { + mbx->op_type = QLC_83XX_FW_MBX_CMD; mbx->req.num = mbx_tbl[i].in_args; mbx->rsp.num = mbx_tbl[i].out_args; mbx->req.arg = kcalloc(mbx->req.num, sizeof(u32), @@@ -829,10 -901,10 +829,10 @@@ memset(mbx->rsp.arg, 0, sizeof(u32) * mbx->rsp.num); temp = adapter->ahw->fw_hal_version << 29; mbx->req.arg[0] = (type | (mbx->req.num << 16) | temp); - break; + return 0; } } - return 0; + return -EINVAL; }

void qlcnic_83xx_idc_aen_work(struct work_struct *work) @@@ -863,7 -935,7 +863,7 @@@ static void qlcnic_83xx_handle_idc_comp return; }

-void qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter) +void __qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter) { u32 event[QLC_83XX_MBX_AEN_CNT]; int i; @@@ -888,9 -960,6 +888,9 @@@ break; case QLCNIC_MBX_TIME_EXTEND_EVENT: break; + case QLCNIC_MBX_BC_EVENT: + qlcnic_sriov_handle_bc_event(adapter, event[1]); + break; case QLCNIC_MBX_SFP_INSERT_EVENT: dev_info(&adapter->pdev->dev, "SFP+ Insert AEN:0x%x.\n", QLCNIC_MBX_RSP(event[0])); @@@ -908,53 -977,6 +908,53 @@@ QLCWRX(ahw, QLCNIC_FW_MBX_CTRL, QLCNIC_CLR_OWNER); }

+static void qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + u32 resp, event; + unsigned long flags; + + spin_lock_irqsave(&ahw->mbx_lock, flags); + + resp = QLCRDX(ahw, QLCNIC_FW_MBX_CTRL); + if (resp & QLCNIC_SET_OWNER) { + event = readl(QLCNIC_MBX_FW(ahw, 0)); + if (event & QLCNIC_MBX_ASYNC_EVENT) + __qlcnic_83xx_process_aen(adapter); + } + + spin_unlock_irqrestore(&ahw->mbx_lock, flags); +} + +static void qlcnic_83xx_mbx_poll_work(struct work_struct *work) +{ + struct qlcnic_adapter *adapter; + + adapter = container_of(work, struct qlcnic_adapter, mbx_poll_work.work); + + if (!test_bit(__QLCNIC_MBX_POLL_ENABLE, &adapter->state)) + return; + + qlcnic_83xx_process_aen(adapter); + queue_delayed_work(adapter->qlcnic_wq, &adapter->mbx_poll_work, + (HZ / 10)); +} + +void qlcnic_83xx_enable_mbx_poll(struct qlcnic_adapter *adapter) +{ + if (test_and_set_bit(__QLCNIC_MBX_POLL_ENABLE, &adapter->state)) + return; + + INIT_DELAYED_WORK(&adapter->mbx_poll_work, qlcnic_83xx_mbx_poll_work); +} + +void qlcnic_83xx_disable_mbx_poll(struct qlcnic_adapter *adapter) +{ + if (!test_and_clear_bit(__QLCNIC_MBX_POLL_ENABLE, &adapter->state)) + return; + cancel_delayed_work_sync(&adapter->mbx_poll_work); +} + static int qlcnic_83xx_add_rings(struct qlcnic_adapter *adapter) { int index, i, err, sds_mbx_size; @@@ -982,8 -1004,7 +982,8 @@@ sds = &recv_ctx->sds_rings[i]; sds->consumer = 0; memset(sds->desc_head, 0, STATUS_DESC_RINGSIZE(sds)); - sds_mbx.phy_addr = sds->phys_addr; + sds_mbx.phy_addr_low = LSD(sds->phys_addr); + sds_mbx.phy_addr_high = MSD(sds->phys_addr); sds_mbx.sds_ring_size = sds->num_desc;

if (adapter->flags & QLCNIC_MSIX_ENABLED) @@@ -1029,32 -1050,6 +1029,32 @@@ out return err; }

+void qlcnic_83xx_del_rx_ctx(struct qlcnic_adapter *adapter) +{ + int err; + u32 temp = 0; + struct qlcnic_cmd_args cmd; + struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx; + + if (qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_DESTROY_RX_CTX)) + return; + + if (qlcnic_sriov_pf_check(adapter) || qlcnic_sriov_vf_check(adapter)) + cmd.req.arg[0] |= (0x3 << 29); + + if (qlcnic_sriov_pf_check(adapter)) + qlcnic_pf_set_interface_id_del_rx_ctx(adapter, &temp); + + cmd.req.arg[1] = recv_ctx->context_id | temp; + err = qlcnic_issue_cmd(adapter, &cmd); + if (err) + dev_err(&adapter->pdev->dev, + "Failed to destroy rx ctx in firmware\n"); + + recv_ctx->state = QLCNIC_HOST_CTX_STATE_FREED; + qlcnic_free_mbx_args(&cmd); +} + int qlcnic_83xx_create_rx_ctx(struct qlcnic_adapter *adapter) { int i, err, index, sds_mbx_size, rds_mbx_size; @@@ -1085,17 -1080,9 +1085,17 @@@ /* set mailbox hdr and capabilities */ qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_CREATE_RX_CTX); + + if (qlcnic_sriov_pf_check(adapter) || qlcnic_sriov_vf_check(adapter)) + cmd.req.arg[0] |= (0x3 << 29); + cmd.req.arg[1] = cap; cmd.req.arg[5] = 1 | (num_rds << 5) | (num_sds << 8) | (QLC_83XX_HOST_RDS_MODE_UNIQUE << 16); + + if (qlcnic_sriov_pf_check(adapter)) + qlcnic_pf_set_interface_id_create_rx_ctx(adapter, + &cmd.req.arg[6]); /* set up status rings, mbx 8-57/87 */ index = QLC_83XX_HOST_SDS_MBX_IDX; for (i = 0; i < num_sds; i++) { @@@ -1103,8 -1090,7 +1103,8 @@@ sds = &recv_ctx->sds_rings[i]; sds->consumer = 0; memset(sds->desc_head, 0, STATUS_DESC_RINGSIZE(sds)); - sds_mbx.phy_addr = sds->phys_addr; + sds_mbx.phy_addr_low = LSD(sds->phys_addr); + sds_mbx.phy_addr_high = MSD(sds->phys_addr); sds_mbx.sds_ring_size = sds->num_desc; if (adapter->flags & QLCNIC_MSIX_ENABLED) intrpt_id = ahw->intr_tbl[i].id; @@@ -1124,15 -1110,13 +1124,15 @@@ rds = &recv_ctx->rds_rings[0]; rds->producer = 0; memset(&rds_mbx, 0, rds_mbx_size); - rds_mbx.phy_addr_reg = rds->phys_addr; + rds_mbx.phy_addr_reg_low = LSD(rds->phys_addr); + rds_mbx.phy_addr_reg_high = MSD(rds->phys_addr); rds_mbx.reg_ring_sz = rds->dma_size; rds_mbx.reg_ring_len = rds->num_desc; /* Jumbo ring */ rds = &recv_ctx->rds_rings[1]; rds->producer = 0; - rds_mbx.phy_addr_jmb = rds->phys_addr; + rds_mbx.phy_addr_jmb_low = LSD(rds->phys_addr); + rds_mbx.phy_addr_jmb_high = MSD(rds->phys_addr); rds_mbx.jmb_ring_sz = rds->dma_size; rds_mbx.jmb_ring_len = rds->num_desc; buf = &cmd.req.arg[index]; @@@ -1179,39 -1163,16 +1179,39 @@@ out return err; }

+void qlcnic_83xx_del_tx_ctx(struct qlcnic_adapter *adapter, + struct qlcnic_host_tx_ring *tx_ring) +{ + struct qlcnic_cmd_args cmd; + u32 temp = 0; + + if (qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_DESTROY_TX_CTX)) + return; + + if (qlcnic_sriov_pf_check(adapter) || qlcnic_sriov_vf_check(adapter)) + cmd.req.arg[0] |= (0x3 << 29); + + if (qlcnic_sriov_pf_check(adapter)) + qlcnic_pf_set_interface_id_del_tx_ctx(adapter, &temp); + + cmd.req.arg[1] = tx_ring->ctx_id | temp; + if (qlcnic_issue_cmd(adapter, &cmd)) + dev_err(&adapter->pdev->dev, + "Failed to destroy tx ctx in firmware\n"); + qlcnic_free_mbx_args(&cmd); +} + int qlcnic_83xx_create_tx_ctx(struct qlcnic_adapter *adapter, struct qlcnic_host_tx_ring *tx, int ring) { int err; u16 msix_id; - u32 *buf, intr_mask; + u32 *buf, intr_mask, temp = 0; struct qlcnic_cmd_args cmd; struct qlcnic_tx_mbx mbx; struct qlcnic_tx_mbx_out *mbx_out; struct qlcnic_hardware_context *ahw = adapter->ahw; + u32 msix_vector;

/* Reset host resources */ tx->producer = 0; @@@ -1221,21 -1182,13 +1221,21 @@@ memset(&mbx, 0, sizeof(struct qlcnic_tx_mbx));

/* setup mailbox inbox registerss */ - mbx.phys_addr = tx->phys_addr; - mbx.cnsmr_index = tx->hw_cons_phys_addr; + mbx.phys_addr_low = LSD(tx->phys_addr); + mbx.phys_addr_high = MSD(tx->phys_addr); + mbx.cnsmr_index_low = LSD(tx->hw_cons_phys_addr); + mbx.cnsmr_index_high = MSD(tx->hw_cons_phys_addr); mbx.size = tx->num_desc; - if (adapter->flags & QLCNIC_MSIX_ENABLED) - msix_id = ahw->intr_tbl[adapter->max_sds_rings + ring].id; - else + if (adapter->flags & QLCNIC_MSIX_ENABLED) { + if (!(adapter->flags & QLCNIC_TX_INTR_SHARED)) + msix_vector = adapter->max_sds_rings + ring; + else + msix_vector = adapter->max_sds_rings - 1; + msix_id = ahw->intr_tbl[msix_vector].id; + } else { msix_id = QLCRDX(ahw, QLCNIC_DEF_INT_ID); + } + if (adapter->ahw->diag_test != QLCNIC_LOOPBACK_TEST) mbx.intr_id = msix_id; else @@@ -1243,15 -1196,8 +1243,15 @@@ mbx.src = 0;

qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_CREATE_TX_CTX); + + if (qlcnic_sriov_pf_check(adapter) || qlcnic_sriov_vf_check(adapter)) + cmd.req.arg[0] |= (0x3 << 29); + + if (qlcnic_sriov_pf_check(adapter)) + qlcnic_pf_set_interface_id_create_tx_ctx(adapter, &temp); + cmd.req.arg[1] = QLCNIC_CAP0_LEGACY_CONTEXT; - cmd.req.arg[5] = QLCNIC_MAX_TX_QUEUES; + cmd.req.arg[5] = QLCNIC_MAX_TX_QUEUES | temp; buf = &cmd.req.arg[6]; memcpy(buf, &mbx, sizeof(struct qlcnic_tx_mbx)); /* send the mailbox command*/ @@@ -1264,8 -1210,7 +1264,8 @@@ mbx_out = (struct qlcnic_tx_mbx_out *)&cmd.rsp.arg[2]; tx->crb_cmd_producer = ahw->pci_base0 + mbx_out->host_prod; tx->ctx_id = mbx_out->ctx_id; - if (adapter->flags & QLCNIC_MSIX_ENABLED) { + if ((adapter->flags & QLCNIC_MSIX_ENABLED) && + !(adapter->flags & QLCNIC_TX_INTR_SHARED)) { intr_mask = ahw->intr_tbl[adapter->max_sds_rings + ring].src; tx->crb_intr_mask = ahw->pci_base0 + intr_mask; } @@@ -1322,8 -1267,7 +1322,8 @@@ static int qlcnic_83xx_diag_alloc_res(s

if (adapter->ahw->diag_test == QLCNIC_LOOPBACK_TEST) { /* disable and free mailbox interrupt */ - qlcnic_83xx_free_mbx_intr(adapter); + if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) + qlcnic_83xx_free_mbx_intr(adapter); adapter->ahw->loopback_state = 0; adapter->ahw->hw_ops->setup_link_event(adapter, 1); } @@@ -1351,14 -1295,12 +1351,14 @@@ static void qlcnic_83xx_diag_free_res(s qlcnic_detach(adapter);

if (adapter->ahw->diag_test == QLCNIC_LOOPBACK_TEST) { - err = qlcnic_83xx_setup_mbx_intr(adapter); - if (err) { - dev_err(&adapter->pdev->dev, - "%s: failed to setup mbx interrupt\n", - __func__); - goto out; + if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) { + err = qlcnic_83xx_setup_mbx_intr(adapter); + if (err) { + dev_err(&adapter->pdev->dev, + "%s: failed to setup mbx interrupt\n", + __func__); + goto out; + } } } adapter->ahw->diag_test = 0; @@@ -1431,60 -1373,12 +1431,60 @@@ mbx_err } }

+int qlcnic_83xx_set_led(struct net_device *netdev, + enum ethtool_phys_id_state state) +{ + struct qlcnic_adapter *adapter = netdev_priv(netdev); + int err = -EIO, active = 1; + + if (adapter->ahw->op_mode == QLCNIC_NON_PRIV_FUNC) { + netdev_warn(netdev, + "LED test is not supported in non-privileged mode\n"); + return -EOPNOTSUPP; + } + + switch (state) { + case ETHTOOL_ID_ACTIVE: + if (test_and_set_bit(__QLCNIC_LED_ENABLE, &adapter->state)) + return -EBUSY; + + if (test_bit(__QLCNIC_RESETTING, &adapter->state)) + break; + + err = qlcnic_83xx_config_led(adapter, active, 0); + if (err) + netdev_err(netdev, "Failed to set LED blink state\n"); + break; + case ETHTOOL_ID_INACTIVE: + active = 0; + + if (test_bit(__QLCNIC_RESETTING, &adapter->state)) + break; + + err = qlcnic_83xx_config_led(adapter, active, 0); + if (err) + netdev_err(netdev, "Failed to reset LED blink state\n"); + break; + + default: + return -EINVAL; + } + + if (!active || err) + clear_bit(__QLCNIC_LED_ENABLE, &adapter->state); + + return err; +} + void qlcnic_83xx_register_nic_idc_func(struct qlcnic_adapter *adapter, int enable) { struct qlcnic_cmd_args cmd; int status;

+ if (qlcnic_sriov_vf_check(adapter)) + return; + if (enable) { qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_INIT_NIC_FUNC); cmd.req.arg[1] = BIT_0 | BIT_31; @@@ -1547,35 -1441,24 +1547,35 @@@ int qlcnic_83xx_setup_link_event(struc return err; }

+static void qlcnic_83xx_set_interface_id_promisc(struct qlcnic_adapter *adapter, + u32 *interface_id) +{ + if (qlcnic_sriov_pf_check(adapter)) { + qlcnic_pf_set_interface_id_promisc(adapter, interface_id); + } else { + if (!qlcnic_sriov_vf_check(adapter)) + *interface_id = adapter->recv_ctx->context_id << 16; + } +} + int qlcnic_83xx_nic_set_promisc(struct qlcnic_adapter *adapter, u32 mode) { int err; - u32 temp; + u32 temp = 0; struct qlcnic_cmd_args cmd;

if (adapter->recv_ctx->state == QLCNIC_HOST_CTX_STATE_FREED) return -EIO;

qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_CONFIGURE_MAC_RX_MODE); - temp = adapter->recv_ctx->context_id << 16; + qlcnic_83xx_set_interface_id_promisc(adapter, &temp); cmd.req.arg[1] = (mode ? 1 : 0) | temp; err = qlcnic_issue_cmd(adapter, &cmd); if (err) dev_info(&adapter->pdev->dev, "Promiscous mode config failed\n"); - qlcnic_free_mbx_args(&cmd);

+ qlcnic_free_mbx_args(&cmd); return err; }

@@@ -1607,9 -1490,7 +1607,9 @@@ int qlcnic_83xx_loopback_test(struct ne /* Poll for link up event before running traffic */ do { msleep(500); - qlcnic_83xx_process_aen(adapter); + if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) + qlcnic_83xx_process_aen(adapter); + if (loop++ > QLCNIC_ILB_MAX_RCV_LOOP) { dev_info(&adapter->pdev->dev, "Firmware didn't sent link up event to loopback request\n"); @@@ -1619,6 -1500,12 +1619,12 @@@ } } while ((adapter->ahw->linkup && ahw->has_link_events) != 1);

+ /* Make sure carrier is off and queue is stopped during loopback */ + if (netif_running(netdev)) { + netif_carrier_off(netdev); + netif_stop_queue(netdev); + } + ret = qlcnic_do_lb_test(adapter, mode);

qlcnic_83xx_clear_lb_mode(adapter, mode); @@@ -1663,9 -1550,7 +1669,9 @@@ int qlcnic_83xx_set_lb_mode(struct qlcn /* Wait for Link and IDC Completion AEN */ do { msleep(300); - qlcnic_83xx_process_aen(adapter); + if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) + qlcnic_83xx_process_aen(adapter); + if (loop++ > QLCNIC_ILB_MAX_RCV_LOOP) { dev_err(&adapter->pdev->dev, "FW did not generate IDC completion AEN\n"); @@@ -1705,9 -1590,7 +1711,9 @@@ int qlcnic_83xx_clear_lb_mode(struct ql /* Wait for Link and IDC Completion AEN */ do { msleep(300); - qlcnic_83xx_process_aen(adapter); + if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) + qlcnic_83xx_process_aen(adapter); + if (loop++ > QLCNIC_ILB_MAX_RCV_LOOP) { dev_err(&adapter->pdev->dev, "Firmware didn't sent IDC completion AEN\n"); @@@ -1721,31 -1604,21 +1727,31 @@@ return status; }

+static void qlcnic_83xx_set_interface_id_ipaddr(struct qlcnic_adapter *adapter, + u32 *interface_id) +{ + if (qlcnic_sriov_pf_check(adapter)) { + qlcnic_pf_set_interface_id_ipaddr(adapter, interface_id); + } else { + if (!qlcnic_sriov_vf_check(adapter)) + *interface_id = adapter->recv_ctx->context_id << 16; + } +} + void qlcnic_83xx_config_ipaddr(struct qlcnic_adapter *adapter, __be32 ip, int mode) { int err; - u32 temp, temp_ip; + u32 temp = 0, temp_ip; struct qlcnic_cmd_args cmd;

qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_CONFIGURE_IP_ADDR); - if (mode == QLCNIC_IP_UP) { - temp = adapter->recv_ctx->context_id << 16; + qlcnic_83xx_set_interface_id_ipaddr(adapter, &temp); + + if (mode == QLCNIC_IP_UP) cmd.req.arg[1] = 1 | temp; - } else { - temp = adapter->recv_ctx->context_id << 16; + else cmd.req.arg[1] = 2 | temp; - }

/* * Adapter needs IP address in network byte order. @@@ -1762,7 -1635,6 +1768,7 @@@ dev_err(&adapter->netdev->dev, "could not notify %s IP 0x%x request\n", (mode == QLCNIC_IP_UP) ? "Add" : "Remove", ip); + qlcnic_free_mbx_args(&cmd); }

@@@ -1829,22 -1701,11 +1835,22 @@@ int qlcnic_83xx_config_rss(struct qlcni

}

+static void qlcnic_83xx_set_interface_id_macaddr(struct qlcnic_adapter *adapter, + u32 *interface_id) +{ + if (qlcnic_sriov_pf_check(adapter)) { + qlcnic_pf_set_interface_id_macaddr(adapter, interface_id); + } else { + if (!qlcnic_sriov_vf_check(adapter)) + *interface_id = adapter->recv_ctx->context_id << 16; + } +} + int qlcnic_83xx_sre_macaddr_change(struct qlcnic_adapter *adapter, u8 *addr, - __le16 vlan_id, u8 op) + u16 vlan_id, u8 op) { int err; - u32 *buf; + u32 *buf, temp = 0; struct qlcnic_cmd_args cmd; struct qlcnic_macvlan_mbx mv;

@@@ -1854,21 -1715,11 +1860,21 @@@ err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_CONFIG_MAC_VLAN); if (err) return err; - cmd.req.arg[1] = op | (1 << 8) | - (adapter->recv_ctx->context_id << 16);

- mv.vlan = le16_to_cpu(vlan_id); - memcpy(&mv.mac, addr, ETH_ALEN); + if (vlan_id) + op = (op == QLCNIC_MAC_ADD || op == QLCNIC_MAC_VLAN_ADD) ? + QLCNIC_MAC_VLAN_ADD : QLCNIC_MAC_VLAN_DEL; + + cmd.req.arg[1] = op | (1 << 8); + qlcnic_83xx_set_interface_id_macaddr(adapter, &temp); + cmd.req.arg[1] |= temp; + mv.vlan = vlan_id; + mv.mac_addr0 = addr[0]; + mv.mac_addr1 = addr[1]; + mv.mac_addr2 = addr[2]; + mv.mac_addr3 = addr[3]; + mv.mac_addr4 = addr[4]; + mv.mac_addr5 = addr[5]; buf = &cmd.req.arg[2]; memcpy(buf, &mv, sizeof(struct qlcnic_macvlan_mbx)); err = qlcnic_issue_cmd(adapter, &cmd); @@@ -1881,7 -1732,7 +1887,7 @@@ }

void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *adapter, u64 *addr, - __le16 vlan_id) + u16 vlan_id) { u8 mac[ETH_ALEN]; memcpy(&mac, addr, ETH_ALEN); @@@ -1981,7 -1832,7 +1987,7 @@@ irqreturn_t qlcnic_83xx_handle_aen(int

event = readl(QLCNIC_MBX_FW(adapter->ahw, 0)); if (event & QLCNIC_MBX_ASYNC_EVENT) - qlcnic_83xx_process_aen(adapter); + __qlcnic_83xx_process_aen(adapter); out: mask = QLCRDX(adapter->ahw, QLCNIC_DEF_INT_MASK); writel(0, adapter->ahw->pci_base0 + mask); @@@ -2157,17 -2008,14 +2163,17 @@@ int qlcnic_83xx_get_pci_info(struct qlc int qlcnic_83xx_config_intrpt(struct qlcnic_adapter *adapter, bool op_type) { int i, index, err; - bool type; u8 max_ints; - u32 val, temp; + u32 val, temp, type; struct qlcnic_cmd_args cmd;

max_ints = adapter->ahw->num_msix - 1; qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_CONFIG_INTRPT); cmd.req.arg[1] = max_ints; + + if (qlcnic_sriov_vf_check(adapter)) + cmd.req.arg[1] |= (adapter->ahw->pci_func << 8) | BIT_16; + for (i = 0, index = 2; i < max_ints; i++) { type = op_type ? QLCNIC_INTRPT_ADD : QLCNIC_INTRPT_DEL; val = type | (adapter->ahw->intr_tbl[i].type << 4); @@@ -2321,7 -2169,7 +2327,7 @@@ static int qlcnic_83xx_poll_flash_statu return 0; }

-static int qlcnic_83xx_enable_flash_write_op(struct qlcnic_adapter *adapter) +int qlcnic_83xx_enable_flash_write(struct qlcnic_adapter *adapter) { int ret; u32 cmd; @@@ -2339,7 -2187,7 +2345,7 @@@ return 0; }

-static int qlcnic_83xx_disable_flash_write_op(struct qlcnic_adapter *adapter) +int qlcnic_83xx_disable_flash_write(struct qlcnic_adapter *adapter) { int ret;

@@@ -2413,7 -2261,7 +2419,7 @@@ int qlcnic_83xx_erase_flash_sector(stru return -EIO;

if (adapter->ahw->fdt.mfg_id == adapter->flash_mfg_id) { - ret = qlcnic_83xx_enable_flash_write_op(adapter); + ret = qlcnic_83xx_enable_flash_write(adapter); if (ret) { qlcnic_83xx_unlock_flash(adapter); dev_err(&adapter->pdev->dev, @@@ -2455,7 -2303,7 +2461,7 @@@ }

if (adapter->ahw->fdt.mfg_id == adapter->flash_mfg_id) { - ret = qlcnic_83xx_disable_flash_write_op(adapter); + ret = qlcnic_83xx_disable_flash_write(adapter); if (ret) { qlcnic_83xx_unlock_flash(adapter); dev_err(&adapter->pdev->dev, @@@ -2495,8 -2343,8 +2501,8 @@@ int qlcnic_83xx_flash_bulk_write(struc u32 temp; int ret = -EIO;

- if ((count < QLC_83XX_FLASH_BULK_WRITE_MIN) || - (count > QLC_83XX_FLASH_BULK_WRITE_MAX)) { + if ((count < QLC_83XX_FLASH_WRITE_MIN) || + (count > QLC_83XX_FLASH_WRITE_MAX)) { dev_err(&adapter->pdev->dev, "%s: Invalid word count\n", __func__); return -EIO; @@@ -2774,19 -2622,13 +2780,19 @@@ int qlcnic_83xx_flash_read32(struct qlc

int qlcnic_83xx_test_link(struct qlcnic_adapter *adapter) { + u8 pci_func; int err; u32 config = 0, state; struct qlcnic_cmd_args cmd; struct qlcnic_hardware_context *ahw = adapter->ahw;

- state = readl(ahw->pci_base0 + QLC_83XX_LINK_STATE(ahw->pci_func)); - if (!QLC_83xx_FUNC_VAL(state, ahw->pci_func)) { + if (qlcnic_sriov_vf_check(adapter)) + pci_func = adapter->portnum; + else + pci_func = ahw->pci_func; + + state = readl(ahw->pci_base0 + QLC_83XX_LINK_STATE(pci_func)); + if (!QLC_83xx_FUNC_VAL(state, pci_func)) { dev_info(&adapter->pdev->dev, "link state down\n"); return config; } @@@ -2944,6 -2786,7 +2950,7 @@@ static u64 *qlcnic_83xx_fill_stats(stru void qlcnic_83xx_get_stats(struct qlcnic_adapter *adapter, u64 *data) { struct qlcnic_cmd_args cmd; + struct net_device *netdev = adapter->netdev; int ret = 0;

qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_GET_STATISTICS); @@@ -2953,7 -2796,7 +2960,7 @@@ data = qlcnic_83xx_fill_stats(adapter, &cmd, data, QLC_83XX_STAT_TX, &ret); if (ret) { - dev_info(&adapter->pdev->dev, "Error getting MAC stats\n"); + netdev_err(netdev, "Error getting Tx stats\n"); goto out; } /* Get MAC stats */ @@@ -2963,8 -2806,7 +2970,7 @@@ data = qlcnic_83xx_fill_stats(adapter, &cmd, data, QLC_83XX_STAT_MAC, &ret); if (ret) { - dev_info(&adapter->pdev->dev, - "Error getting Rx stats\n"); + netdev_err(netdev, "Error getting MAC stats\n"); goto out; } /* Get Rx stats */ @@@ -2974,8 -2816,7 +2980,7 @@@ data = qlcnic_83xx_fill_stats(adapter, &cmd, data, QLC_83XX_STAT_RX, &ret); if (ret) - dev_info(&adapter->pdev->dev, - "Error getting Tx stats\n"); + netdev_err(netdev, "Error getting Rx stats\n"); out: qlcnic_free_mbx_args(&cmd); } diff --combined drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 356859b,5fa847f..d3f8797 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@@ -9,7 -9,6 +9,7 @@@ #include <linux/if_vlan.h> #include <net/ip.h> #include <linux/ipv6.h> +#include <net/checksum.h>

#include "qlcnic.h"

@@@ -147,10 -146,7 +147,10 @@@ static inline u8 qlcnic_mac_hash(u64 ma static inline u32 qlcnic_get_ref_handle(struct qlcnic_adapter *adapter, u16 handle, u8 ring_id) { - if (adapter->pdev->device == PCI_DEVICE_ID_QLOGIC_QLE834X) + unsigned short device = adapter->pdev->device; + + if ((device == PCI_DEVICE_ID_QLOGIC_QLE834X) || + (device == PCI_DEVICE_ID_QLOGIC_VF_QLE834X)) return handle | (ring_id << 15); else return handle; @@@ -162,7 -158,7 +162,7 @@@ static inline int qlcnic_82xx_is_lb_pkt }

void qlcnic_add_lb_filter(struct qlcnic_adapter *adapter, struct sk_buff *skb, - int loopback_pkt, __le16 vlan_id) + int loopback_pkt, u16 vlan_id) { struct ethhdr *phdr = (struct ethhdr *)(skb->data); struct qlcnic_filter *fil, *tmp_fil; @@@ -240,7 -236,7 +240,7 @@@ }

void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr, - __le16 vlan_id) + u16 vlan_id) { struct cmd_desc_type0 *hwdesc; struct qlcnic_nic_req *req; @@@ -265,7 -261,7 +265,7 @@@ memcpy(mac_req->mac_addr, &uaddr, ETH_ALEN);

vlan_req = (struct qlcnic_vlan_req *)&req->words[1]; - vlan_req->vlan_id = vlan_id; + vlan_req->vlan_id = cpu_to_le16(vlan_id);

tx_ring->producer = get_next_index(producer, tx_ring->num_desc); smp_mb(); @@@ -281,7 -277,7 +281,7 @@@ static void qlcnic_send_filter(struct q struct net_device *netdev = adapter->netdev; struct ethhdr *phdr = (struct ethhdr *)(skb->data); u64 src_addr = 0; - __le16 vlan_id = 0; + u16 vlan_id = 0; u8 hindex;

if (ether_addr_equal(phdr->h_source, adapter->mac_addr)) @@@ -344,14 -340,14 +344,14 @@@ static int qlcnic_tx_pkt(struct qlcnic_ flags = FLAGS_VLAN_OOB; vlan_tci = vlan_tx_tag_get(skb); } - if (unlikely(adapter->pvid)) { + if (unlikely(adapter->tx_pvid)) { if (vlan_tci && !(adapter->flags & QLCNIC_TAGGING_ENABLED)) return -EIO; if (vlan_tci && (adapter->flags & QLCNIC_TAGGING_ENABLED)) goto set_flags;

flags = FLAGS_VLAN_OOB; - vlan_tci = adapter->pvid; + vlan_tci = adapter->tx_pvid; } set_flags: qlcnic_set_tx_vlan_tci(first_desc, vlan_tci); @@@ -362,8 -358,7 +362,7 @@@ memcpy(&first_desc->eth_addr, skb->data, ETH_ALEN); } opcode = TX_ETHER_PKT; - if ((adapter->netdev->features & (NETIF_F_TSO | NETIF_F_TSO6)) && - skb_shinfo(skb)->gso_size > 0) { + if (skb_is_gso(skb)) { hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); first_desc->mss = cpu_to_le16(skb_shinfo(skb)->gso_size); first_desc->total_hdr_length = hdr_len; @@@ -980,10 -975,10 +979,10 @@@ static inline int qlcnic_check_rx_taggi memmove(skb->data + VLAN_HLEN, eth_hdr, ETH_ALEN * 2); skb_pull(skb, VLAN_HLEN); } - if (!adapter->pvid) + if (!adapter->rx_pvid) return 0;

- if (*vlan_tag == adapter->pvid) { + if (*vlan_tag == adapter->rx_pvid) { /* Outer vlan tag. Packet should follow non-vlan path */ *vlan_tag = 0xffff; return 0; @@@ -1029,7 -1024,8 +1028,7 @@@ qlcnic_process_rcv(struct qlcnic_adapte (adapter->flags & QLCNIC_ESWITCH_ENABLED)) { t_vid = 0; is_lb_pkt = qlcnic_82xx_is_lb_pkt(sts_data0); - qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, - cpu_to_le16(t_vid)); + qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, t_vid); }

if (length > rds_ring->skb_size) @@@ -1049,7 -1045,7 +1048,7 @@@ skb->protocol = eth_type_trans(skb, netdev);

if (vid != 0xffff) - __vlan_hwaccel_put_tag(skb, vid); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);

napi_gro_receive(&sds_ring->napi, skb);

@@@ -1106,7 -1102,8 +1105,7 @@@ qlcnic_process_lro(struct qlcnic_adapte (adapter->flags & QLCNIC_ESWITCH_ENABLED)) { t_vid = 0; is_lb_pkt = qlcnic_82xx_is_lb_pkt(sts_data0); - qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, - cpu_to_le16(t_vid)); + qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, t_vid); }

if (timestamp) @@@ -1134,8 -1131,9 +1133,8 @@@ iph = (struct iphdr *)skb->data; th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); length = (iph->ihl << 2) + (th->doff << 2) + lro_length; + csum_replace2(&iph->check, iph->tot_len, htons(length)); iph->tot_len = htons(length); - iph->check = 0; - iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); }

th->psh = push; @@@ -1151,7 -1149,7 +1150,7 @@@ }

if (vid != 0xffff) - __vlan_hwaccel_put_tag(skb, vid); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); netif_receive_skb(skb);

adapter->stats.lro_pkts++; @@@ -1498,7 -1496,8 +1497,7 @@@ qlcnic_83xx_process_rcv(struct qlcnic_a (adapter->flags & QLCNIC_ESWITCH_ENABLED)) { t_vid = 0; is_lb_pkt = qlcnic_83xx_is_lb_pkt(sts_data[1], 0); - qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, - cpu_to_le16(t_vid)); + qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, t_vid); }

if (length > rds_ring->skb_size) @@@ -1515,7 -1514,7 +1514,7 @@@ skb->protocol = eth_type_trans(skb, netdev);

if (vid != 0xffff) - __vlan_hwaccel_put_tag(skb, vid); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);

napi_gro_receive(&sds_ring->napi, skb);

@@@ -1567,7 -1566,8 +1566,7 @@@ qlcnic_83xx_process_lro(struct qlcnic_a (adapter->flags & QLCNIC_ESWITCH_ENABLED)) { t_vid = 0; is_lb_pkt = qlcnic_83xx_is_lb_pkt(sts_data[1], 1); - qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, - cpu_to_le16(t_vid)); + qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, t_vid); } if (qlcnic_83xx_is_tstamp(sts_data[1])) data_offset = l4_hdr_offset + QLCNIC_TCP_TS_HDR_SIZE; @@@ -1594,8 -1594,9 +1593,8 @@@ iph = (struct iphdr *)skb->data; th = (struct tcphdr *)(skb->data + (iph->ihl << 2)); length = (iph->ihl << 2) + (th->doff << 2) + lro_length; + csum_replace2(&iph->check, iph->tot_len, htons(length)); iph->tot_len = htons(length); - iph->check = 0; - iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); }

th->psh = push; @@@ -1611,7 -1612,7 +1610,7 @@@ }

if (vid != 0xffff) - __vlan_hwaccel_put_tag(skb, vid); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);

netif_receive_skb(skb);

@@@ -1690,29 -1691,6 +1689,29 @@@ skip return count; }

+static int qlcnic_83xx_msix_sriov_vf_poll(struct napi_struct *napi, int budget) +{ + int tx_complete; + int work_done; + struct qlcnic_host_sds_ring *sds_ring; + struct qlcnic_adapter *adapter; + struct qlcnic_host_tx_ring *tx_ring; + + sds_ring = container_of(napi, struct qlcnic_host_sds_ring, napi); + adapter = sds_ring->adapter; + /* tx ring count = 1 */ + tx_ring = adapter->tx_ring; + + tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring, budget); + work_done = qlcnic_83xx_process_rcv_ring(sds_ring, budget); + if ((work_done < budget) && tx_complete) { + napi_complete(&sds_ring->napi); + qlcnic_83xx_enable_intr(adapter, sds_ring); + } + + return work_done; +} + static int qlcnic_83xx_poll(struct napi_struct *napi, int budget) { int tx_complete; @@@ -1790,8 -1768,7 +1789,8 @@@ void qlcnic_83xx_napi_enable(struct qlc qlcnic_83xx_enable_intr(adapter, sds_ring); }

- if (adapter->flags & QLCNIC_MSIX_ENABLED) { + if ((adapter->flags & QLCNIC_MSIX_ENABLED) && + !(adapter->flags & QLCNIC_TX_INTR_SHARED)) { for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { tx_ring = &adapter->tx_ring[ring]; napi_enable(&tx_ring->napi); @@@ -1818,8 -1795,7 +1817,8 @@@ void qlcnic_83xx_napi_disable(struct ql napi_disable(&sds_ring->napi); }

- if (adapter->flags & QLCNIC_MSIX_ENABLED) { + if ((adapter->flags & QLCNIC_MSIX_ENABLED) && + !(adapter->flags & QLCNIC_TX_INTR_SHARED)) { for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { tx_ring = &adapter->tx_ring[ring]; qlcnic_83xx_disable_tx_intr(adapter, tx_ring); @@@ -1832,7 -1808,7 +1831,7 @@@ int qlcnic_83xx_napi_add(struct qlcnic_adapter *adapter, struct net_device *netdev) { - int ring, max_sds_rings; + int ring, max_sds_rings, temp; struct qlcnic_host_sds_ring *sds_ring; struct qlcnic_host_tx_ring *tx_ring; struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx; @@@ -1843,23 -1819,14 +1842,23 @@@ max_sds_rings = adapter->max_sds_rings; for (ring = 0; ring < adapter->max_sds_rings; ring++) { sds_ring = &recv_ctx->sds_rings[ring]; - if (adapter->flags & QLCNIC_MSIX_ENABLED) - netif_napi_add(netdev, &sds_ring->napi, - qlcnic_83xx_rx_poll, - QLCNIC_NETDEV_WEIGHT * 2); - else + if (adapter->flags & QLCNIC_MSIX_ENABLED) { + if (!(adapter->flags & QLCNIC_TX_INTR_SHARED)) { + netif_napi_add(netdev, &sds_ring->napi, + qlcnic_83xx_rx_poll, + QLCNIC_NETDEV_WEIGHT * 2); + } else { + temp = QLCNIC_NETDEV_WEIGHT / max_sds_rings; + netif_napi_add(netdev, &sds_ring->napi, + qlcnic_83xx_msix_sriov_vf_poll, + temp); + } + + } else { netif_napi_add(netdev, &sds_ring->napi, qlcnic_83xx_poll, QLCNIC_NETDEV_WEIGHT / max_sds_rings); + } }

if (qlcnic_alloc_tx_rings(adapter, netdev)) { @@@ -1867,8 -1834,7 +1866,8 @@@ return -ENOMEM; }

- if (adapter->flags & QLCNIC_MSIX_ENABLED) { + if ((adapter->flags & QLCNIC_MSIX_ENABLED) && + !(adapter->flags & QLCNIC_TX_INTR_SHARED)) { for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { tx_ring = &adapter->tx_ring[ring]; netif_napi_add(netdev, &tx_ring->napi, @@@ -1894,8 -1860,7 +1893,8 @@@ void qlcnic_83xx_napi_del(struct qlcnic

qlcnic_free_sds_rings(adapter->recv_ctx);

- if ((adapter->flags & QLCNIC_MSIX_ENABLED)) { + if ((adapter->flags & QLCNIC_MSIX_ENABLED) && + !(adapter->flags & QLCNIC_TX_INTR_SHARED)) { for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) { tx_ring = &adapter->tx_ring[ring]; netif_napi_del(&tx_ring->napi); diff --combined drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index c77675d,5ef328a..4e22e79 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@@ -21,6 -21,8 +21,6 @@@ #include <linux/aer.h> #include <linux/log2.h>

-#include <linux/sysfs.h> - #define QLC_STATUS_UNSUPPORTED_CMD -2

int qlcnicvf_config_bridged_mode(struct qlcnic_adapter *adapter, u32 enable) @@@ -198,10 -200,10 +198,10 @@@ beacon_err }

err = qlcnic_config_led(adapter, b_state, b_rate); - if (!err) + if (!err) { err = len; - else ahw->beacon_state = b_state; + }

if (test_and_clear_bit(__QLCNIC_DIAG_RES_ALLOC, &adapter->state)) qlcnic_diag_free_res(adapter->netdev, max_sds_rings); @@@ -884,244 -886,6 +884,244 @@@ static ssize_t qlcnic_sysfs_read_pci_co return size; }

+static ssize_t qlcnic_83xx_sysfs_flash_read_handler(struct file *filp, + struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t offset, + size_t size) +{ + unsigned char *p_read_buf; + int ret, count; + struct device *dev = container_of(kobj, struct device, kobj); + struct qlcnic_adapter *adapter = dev_get_drvdata(dev); + + if (!size) + return QL_STATUS_INVALID_PARAM; + if (!buf) + return QL_STATUS_INVALID_PARAM; + + count = size / sizeof(u32); + + if (size % sizeof(u32)) + count++; + + p_read_buf = kcalloc(size, sizeof(unsigned char), GFP_KERNEL); + if (!p_read_buf) + return -ENOMEM; + if (qlcnic_83xx_lock_flash(adapter) != 0) { + kfree(p_read_buf); + return -EIO; + } + + ret = qlcnic_83xx_lockless_flash_read32(adapter, offset, p_read_buf, + count); + + if (ret) { + qlcnic_83xx_unlock_flash(adapter); + kfree(p_read_buf); + return ret; + } + + qlcnic_83xx_unlock_flash(adapter); + memcpy(buf, p_read_buf, size); + kfree(p_read_buf); + + return size; +} + +static int qlcnic_83xx_sysfs_flash_bulk_write(struct qlcnic_adapter *adapter, + char *buf, loff_t offset, + size_t size) +{ + int i, ret, count; + unsigned char *p_cache, *p_src; + + p_cache = kcalloc(size, sizeof(unsigned char), GFP_KERNEL); + if (!p_cache) + return -ENOMEM; + + memcpy(p_cache, buf, size); + p_src = p_cache; + count = size / sizeof(u32); + + if (qlcnic_83xx_lock_flash(adapter) != 0) { + kfree(p_cache); + return -EIO; + } + + if (adapter->ahw->fdt.mfg_id == adapter->flash_mfg_id) { + ret = qlcnic_83xx_enable_flash_write(adapter); + if (ret) { + kfree(p_cache); + qlcnic_83xx_unlock_flash(adapter); + return -EIO; + } + } + + for (i = 0; i < count / QLC_83XX_FLASH_WRITE_MAX; i++) { + ret = qlcnic_83xx_flash_bulk_write(adapter, offset, + (u32 *)p_src, + QLC_83XX_FLASH_WRITE_MAX); + + if (ret) { + if (adapter->ahw->fdt.mfg_id == adapter->flash_mfg_id) { + ret = qlcnic_83xx_disable_flash_write(adapter); + if (ret) { + kfree(p_cache); + qlcnic_83xx_unlock_flash(adapter); + return -EIO; + } + } + + kfree(p_cache); + qlcnic_83xx_unlock_flash(adapter); + return -EIO; + } + + p_src = p_src + sizeof(u32)*QLC_83XX_FLASH_WRITE_MAX; + offset = offset + sizeof(u32)*QLC_83XX_FLASH_WRITE_MAX; + } + + if (adapter->ahw->fdt.mfg_id == adapter->flash_mfg_id) { + ret = qlcnic_83xx_disable_flash_write(adapter); + if (ret) { + kfree(p_cache); + qlcnic_83xx_unlock_flash(adapter); + return -EIO; + } + } + + kfree(p_cache); + qlcnic_83xx_unlock_flash(adapter); + + return 0; +} + +static int qlcnic_83xx_sysfs_flash_write(struct qlcnic_adapter *adapter, + char *buf, loff_t offset, size_t size) +{ + int i, ret, count; + unsigned char *p_cache, *p_src; + + p_cache = kcalloc(size, sizeof(unsigned char), GFP_KERNEL); + if (!p_cache) + return -ENOMEM; + + memcpy(p_cache, buf, size); + p_src = p_cache; + count = size / sizeof(u32); + + if (qlcnic_83xx_lock_flash(adapter) != 0) { + kfree(p_cache); + return -EIO; + } + + if (adapter->ahw->fdt.mfg_id == adapter->flash_mfg_id) { + ret = qlcnic_83xx_enable_flash_write(adapter); + if (ret) { + kfree(p_cache); + qlcnic_83xx_unlock_flash(adapter); + return -EIO; + } + } + + for (i = 0; i < count; i++) { + ret = qlcnic_83xx_flash_write32(adapter, offset, (u32 *)p_src); + if (ret) { + if (adapter->ahw->fdt.mfg_id == adapter->flash_mfg_id) { + ret = qlcnic_83xx_disable_flash_write(adapter); + if (ret) { + kfree(p_cache); + qlcnic_83xx_unlock_flash(adapter); + return -EIO; + } + } + kfree(p_cache); + qlcnic_83xx_unlock_flash(adapter); + return -EIO; + } + + p_src = p_src + sizeof(u32); + offset = offset + sizeof(u32); + } + + if (adapter->ahw->fdt.mfg_id == adapter->flash_mfg_id) { + ret = qlcnic_83xx_disable_flash_write(adapter); + if (ret) { + kfree(p_cache); + qlcnic_83xx_unlock_flash(adapter); + return -EIO; + } + } + + kfree(p_cache); + qlcnic_83xx_unlock_flash(adapter); + + return 0; +} + +static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp, + struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t offset, + size_t size) +{ + int ret; + static int flash_mode; + unsigned long data; + struct device *dev = container_of(kobj, struct device, kobj); + struct qlcnic_adapter *adapter = dev_get_drvdata(dev); + + if (!buf) + return QL_STATUS_INVALID_PARAM; + + ret = kstrtoul(buf, 16, &data); + + switch (data) { + case QLC_83XX_FLASH_SECTOR_ERASE_CMD: + flash_mode = QLC_83XX_ERASE_MODE; + ret = qlcnic_83xx_erase_flash_sector(adapter, offset); + if (ret) { + dev_err(&adapter->pdev->dev, + "%s failed at %d\n", __func__, __LINE__); + return -EIO; + } + break; + + case QLC_83XX_FLASH_BULK_WRITE_CMD: + flash_mode = QLC_83XX_BULK_WRITE_MODE; + break; + + case QLC_83XX_FLASH_WRITE_CMD: + flash_mode = QLC_83XX_WRITE_MODE; + break; + default: + if (flash_mode == QLC_83XX_BULK_WRITE_MODE) { + ret = qlcnic_83xx_sysfs_flash_bulk_write(adapter, buf, + offset, size); + if (ret) { + dev_err(&adapter->pdev->dev, + "%s failed at %d\n", + __func__, __LINE__); + return -EIO; + } + } + + if (flash_mode == QLC_83XX_WRITE_MODE) { + ret = qlcnic_83xx_sysfs_flash_write(adapter, buf, + offset, size); + if (ret) { + dev_err(&adapter->pdev->dev, + "%s failed at %d\n", __func__, + __LINE__); + return -EIO; + } + } + } + + return size; +} + static struct device_attribute dev_attr_bridged_mode = { .attr = {.name = "bridged_mode", .mode = (S_IRUGO | S_IWUSR)}, .show = qlcnic_show_bridged_mode, @@@ -1196,13 -960,6 +1196,13 @@@ static struct bin_attribute bin_attr_pm .write = qlcnic_sysfs_write_pm_config, };

+static struct bin_attribute bin_attr_flash = { + .attr = {.name = "flash", .mode = (S_IRUGO | S_IWUSR)}, + .size = 0, + .read = qlcnic_83xx_sysfs_flash_read_handler, + .write = qlcnic_83xx_sysfs_flash_write_handler, +}; + void qlcnic_create_sysfs_entries(struct qlcnic_adapter *adapter) { struct device *dev = &adapter->pdev->dev; @@@ -1291,18 -1048,10 +1291,18 @@@ void qlcnic_82xx_remove_sysfs(struct ql

void qlcnic_83xx_add_sysfs(struct qlcnic_adapter *adapter) { + struct device *dev = &adapter->pdev->dev; + qlcnic_create_diag_entries(adapter); + + if (sysfs_create_bin_file(&dev->kobj, &bin_attr_flash)) + dev_info(dev, "failed to create flash sysfs entry\n"); }

void qlcnic_83xx_remove_sysfs(struct qlcnic_adapter *adapter) { + struct device *dev = &adapter->pdev->dev; + qlcnic_remove_diag_entries(adapter); + sysfs_remove_bin_file(&dev->kobj, &bin_attr_flash); } diff --combined drivers/net/ethernet/qlogic/qlge/qlge_main.c index 44cf72a,8033555..87463bc --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@@ -409,7 -409,7 +409,7 @@@ static int ql_set_mac_addr_reg(struct q (qdev-> func << CAM_OUT_FUNC_SHIFT) | (0 << CAM_OUT_CQ_ID_SHIFT)); - if (qdev->ndev->features & NETIF_F_HW_VLAN_RX) + if (qdev->ndev->features & NETIF_F_HW_VLAN_CTAG_RX) cam_output |= CAM_OUT_RV; /* route to NIC core */ ql_write32(qdev, MAC_ADDR_DATA, cam_output); @@@ -1211,6 -1211,8 +1211,6 @@@ static void ql_update_sbq(struct ql_ada netdev_alloc_skb(qdev->ndev, SMALL_BUFFER_SIZE); if (sbq_desc->p.skb == NULL) { - netif_err(qdev, probe, qdev->ndev, - "Couldn't get an skb.\n"); rx_ring->sbq_clean_idx = clean_idx; return; } @@@ -1432,11 -1434,13 +1432,13 @@@ map_error }

/* Categorizing receive firmware frame errors */ - static void ql_categorize_rx_err(struct ql_adapter *qdev, u8 rx_err) + static void ql_categorize_rx_err(struct ql_adapter *qdev, u8 rx_err, + struct rx_ring *rx_ring) { struct nic_stats *stats = &qdev->nic_stats;

stats->rx_err_count++; + rx_ring->rx_errors++;

switch (rx_err & IB_MAC_IOCB_RSP_ERR_MASK) { case IB_MAC_IOCB_RSP_ERR_CODE_ERR: @@@ -1472,6 -1476,12 +1474,12 @@@ static void ql_process_mac_rx_gro_page( struct bq_desc *lbq_desc = ql_get_curr_lchunk(qdev, rx_ring); struct napi_struct *napi = &rx_ring->napi;

+ /* Frame error, so drop the packet. */ + if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { + ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); + put_page(lbq_desc->p.pg_chunk.page); + return; + } napi->dev = qdev->ndev;

skb = napi_get_frags(napi); @@@ -1498,7 -1508,7 +1506,7 @@@ skb->ip_summed = CHECKSUM_UNNECESSARY; skb_record_rx_queue(skb, rx_ring->cq_id); if (vlan_id != 0xffff) - __vlan_hwaccel_put_tag(skb, vlan_id); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_id); napi_gro_frags(napi); }

@@@ -1517,6 -1527,8 +1525,6 @@@ static void ql_process_mac_rx_page(stru

skb = netdev_alloc_skb(ndev, length); if (!skb) { - netif_err(qdev, drv, qdev->ndev, - "Couldn't get an skb, need to unwind!.\n"); rx_ring->rx_dropped++; put_page(lbq_desc->p.pg_chunk.page); return; @@@ -1525,6 -1537,12 +1533,12 @@@ addr = lbq_desc->p.pg_chunk.va; prefetch(addr);

+ /* Frame error, so drop the packet. */ + if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { + ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); + goto err_out; + } + /* The max framesize filter on this chip is set higher than * MTU since FCoE uses 2k frames. */ @@@ -1574,7 -1592,7 +1588,7 @@@

skb_record_rx_queue(skb, rx_ring->cq_id); if (vlan_id != 0xffff) - __vlan_hwaccel_put_tag(skb, vlan_id); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_id); if (skb->ip_summed == CHECKSUM_UNNECESSARY) napi_gro_receive(napi, skb); else @@@ -1601,6 -1619,8 +1615,6 @@@ static void ql_process_mac_rx_skb(struc /* Allocate new_skb and copy */ new_skb = netdev_alloc_skb(qdev->ndev, length + NET_IP_ALIGN); if (new_skb == NULL) { - netif_err(qdev, probe, qdev->ndev, - "No skb available, drop the packet.\n"); rx_ring->rx_dropped++; return; } @@@ -1608,6 -1628,13 +1622,13 @@@ memcpy(skb_put(new_skb, length), skb->data, length); skb = new_skb;

+ /* Frame error, so drop the packet. */ + if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { + ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); + dev_kfree_skb_any(skb); + return; + } + /* loopback self test for ethtool */ if (test_bit(QL_SELFTEST, &qdev->flags)) { ql_check_lb_frame(qdev, skb); @@@ -1670,7 -1697,7 +1691,7 @@@

skb_record_rx_queue(skb, rx_ring->cq_id); if (vlan_id != 0xffff) - __vlan_hwaccel_put_tag(skb, vlan_id); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_id); if (skb->ip_summed == CHECKSUM_UNNECESSARY) napi_gro_receive(&rx_ring->napi, skb); else @@@ -1913,6 -1940,13 +1934,13 @@@ static void ql_process_mac_split_rx_int return; }

+ /* Frame error, so drop the packet. */ + if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { + ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); + dev_kfree_skb_any(skb); + return; + } + /* The max framesize filter on this chip is set higher than * MTU since FCoE uses 2k frames. */ @@@ -1975,7 -2009,7 +2003,7 @@@ rx_ring->rx_bytes += skb->len; skb_record_rx_queue(skb, rx_ring->cq_id); if ((ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_V) && (vlan_id != 0)) - __vlan_hwaccel_put_tag(skb, vlan_id); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_id); if (skb->ip_summed == CHECKSUM_UNNECESSARY) napi_gro_receive(&rx_ring->napi, skb); else @@@ -1994,12 -2028,6 +2022,6 @@@ static unsigned long ql_process_mac_rx_

QL_DUMP_IB_MAC_RSP(ib_mac_rsp);

- /* Frame error, so drop the packet. */ - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { - ql_categorize_rx_err(qdev, ib_mac_rsp->flags2); - return (unsigned long)length; - } - if (ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HV) { /* The data and headers are split into * separate buffers. @@@ -2279,7 -2307,7 +2301,7 @@@ static void qlge_vlan_mode(struct net_d { struct ql_adapter *qdev = netdev_priv(ndev);

- if (features & NETIF_F_HW_VLAN_RX) { + if (features & NETIF_F_HW_VLAN_CTAG_RX) { ql_write32(qdev, NIC_RCV_CFG, NIC_RCV_CFG_VLAN_MASK | NIC_RCV_CFG_VLAN_MATCH_AND_NON); } else { @@@ -2294,10 -2322,10 +2316,10 @@@ static netdev_features_t qlge_fix_featu * 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_RX) - features |= NETIF_F_HW_VLAN_TX; + if (features & NETIF_F_HW_VLAN_CTAG_RX) + features |= NETIF_F_HW_VLAN_CTAG_TX; else - features &= ~NETIF_F_HW_VLAN_TX; + features &= ~NETIF_F_HW_VLAN_CTAG_TX;

return features; } @@@ -2307,7 -2335,7 +2329,7 @@@ static int qlge_set_features(struct net { netdev_features_t changed = ndev->features ^ features;

- if (changed & NETIF_F_HW_VLAN_RX) + if (changed & NETIF_F_HW_VLAN_CTAG_RX) qlge_vlan_mode(ndev, features);

return 0; @@@ -2326,7 -2354,7 +2348,7 @@@ static int __qlge_vlan_rx_add_vid(struc return err; }

-static int qlge_vlan_rx_add_vid(struct net_device *ndev, u16 vid) +static int qlge_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct ql_adapter *qdev = netdev_priv(ndev); int status; @@@ -2357,7 -2385,7 +2379,7 @@@ static int __qlge_vlan_rx_kill_vid(stru return err; }

-static int qlge_vlan_rx_kill_vid(struct net_device *ndev, u16 vid) +static int qlge_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct ql_adapter *qdev = netdev_priv(ndev); int status; @@@ -4665,9 -4693,9 +4687,9 @@@ static int qlge_probe(struct pci_dev *p SET_NETDEV_DEV(ndev, &pdev->dev); ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | NETIF_F_TSO_ECN | - NETIF_F_HW_VLAN_TX | NETIF_F_RXCSUM; + NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_RXCSUM; ndev->features = ndev->hw_features | - NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER; + NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; ndev->vlan_features = ndev->hw_features;

if (test_bit(QL_DMA64, &qdev->flags)) diff --combined drivers/net/ethernet/ti/cpsw.c index 5cf8d03,4781d3d..25c3642 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@@ -126,13 -126,6 +126,13 @@@ do { #define CPSW_FIFO_DUAL_MAC_MODE (1 << 15) #define CPSW_FIFO_RATE_LIMIT_MODE (2 << 15)

+#define CPSW_INTPACEEN (0x3f << 16) +#define CPSW_INTPRESCALE_MASK (0x7FF << 0) +#define CPSW_CMINTMAX_CNT 63 +#define CPSW_CMINTMIN_CNT 2 +#define CPSW_CMINTMAX_INTVL (1000 / CPSW_CMINTMIN_CNT) +#define CPSW_CMINTMIN_INTVL ((1000 / CPSW_CMINTMAX_CNT) + 1) + #define cpsw_enable_irq(priv) \ do { \ u32 i; \ @@@ -146,10 -139,6 +146,10 @@@ disable_irq_nosync(priv->irqs_table[i]); \ } while (0);

+#define cpsw_slave_index(priv) \ + ((priv->data.dual_emac) ? priv->emac_port : \ + priv->data.active_slave) + static int debug_level; module_param(debug_level, int, 0); MODULE_PARM_DESC(debug_level, "cpsw debug level (NETIF_MSG bits)"); @@@ -171,15 -160,6 +171,15 @@@ struct cpsw_wr_regs u32 rx_en; u32 tx_en; u32 misc_en; + u32 mem_allign1[8]; + u32 rx_thresh_stat; + u32 rx_stat; + u32 tx_stat; + u32 misc_stat; + u32 mem_allign2[8]; + u32 rx_imax; + u32 tx_imax; + };

struct cpsw_ss_regs { @@@ -334,8 -314,6 +334,8 @@@ struct cpsw_priv struct cpsw_host_regs __iomem *host_port_regs; u32 msg_enable; u32 version; + u32 coal_intvl; + u32 bus_freq_mhz; struct net_device_stats stats; int rx_packet_max; int host_port; @@@ -634,77 -612,6 +634,77 @@@ static void cpsw_adjust_link(struct net } }

+static int cpsw_get_coalesce(struct net_device *ndev, + struct ethtool_coalesce *coal) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + + coal->rx_coalesce_usecs = priv->coal_intvl; + return 0; +} + +static int cpsw_set_coalesce(struct net_device *ndev, + struct ethtool_coalesce *coal) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + u32 int_ctrl; + u32 num_interrupts = 0; + u32 prescale = 0; + u32 addnl_dvdr = 1; + u32 coal_intvl = 0; + + if (!coal->rx_coalesce_usecs) + return -EINVAL; + + coal_intvl = coal->rx_coalesce_usecs; + + int_ctrl = readl(&priv->wr_regs->int_control); + prescale = priv->bus_freq_mhz * 4; + + if (coal_intvl < CPSW_CMINTMIN_INTVL) + coal_intvl = CPSW_CMINTMIN_INTVL; + + if (coal_intvl > CPSW_CMINTMAX_INTVL) { + /* Interrupt pacer works with 4us Pulse, we can + * throttle further by dilating the 4us pulse. + */ + addnl_dvdr = CPSW_INTPRESCALE_MASK / prescale; + + if (addnl_dvdr > 1) { + prescale *= addnl_dvdr; + if (coal_intvl > (CPSW_CMINTMAX_INTVL * addnl_dvdr)) + coal_intvl = (CPSW_CMINTMAX_INTVL + * addnl_dvdr); + } else { + addnl_dvdr = 1; + coal_intvl = CPSW_CMINTMAX_INTVL; + } + } + + num_interrupts = (1000 * addnl_dvdr) / coal_intvl; + writel(num_interrupts, &priv->wr_regs->rx_imax); + writel(num_interrupts, &priv->wr_regs->tx_imax); + + int_ctrl |= CPSW_INTPACEEN; + int_ctrl &= (~CPSW_INTPRESCALE_MASK); + int_ctrl |= (prescale & CPSW_INTPRESCALE_MASK); + writel(int_ctrl, &priv->wr_regs->int_control); + + cpsw_notice(priv, timer, "Set coalesce to %d usecs.\n", coal_intvl); + if (priv->data.dual_emac) { + int i; + + for (i = 0; i < priv->data.slaves; i++) { + priv = netdev_priv(priv->slaves[i].ndev); + priv->coal_intvl = coal_intvl; + } + } else { + priv->coal_intvl = coal_intvl; + } + + return 0; +} + static inline int __show_stat(char *buf, int maxlen, const char *name, u32 val) { static char *leader = "........................................"; @@@ -927,14 -834,6 +927,14 @@@ static int cpsw_ndo_open(struct net_dev cpsw_info(priv, ifup, "submitted %d rx descriptors\n", i); }

+ /* Enable Interrupt pacing if configured */ + if (priv->coal_intvl != 0) { + struct ethtool_coalesce coal; + + coal.rx_coalesce_usecs = (priv->coal_intvl << 4); + cpsw_set_coalesce(ndev, &coal); + } + cpdma_ctlr_start(priv->dma); cpsw_intr_enable(priv); napi_enable(&priv->napi); @@@ -1043,7 -942,7 +1043,7 @@@ static void cpsw_ndo_change_rx_flags(st

static void cpsw_hwtstamp_v1(struct cpsw_priv *priv) { - struct cpsw_slave *slave = &priv->slaves[priv->data.cpts_active_slave]; + struct cpsw_slave *slave = &priv->slaves[priv->data.active_slave]; u32 ts_en, seq_id;

if (!priv->cpts->tx_enable && !priv->cpts->rx_enable) { @@@ -1072,7 -971,7 +1072,7 @@@ static void cpsw_hwtstamp_v2(struct cps if (priv->data.dual_emac) slave = &priv->slaves[priv->emac_port]; else - slave = &priv->slaves[priv->data.cpts_active_slave]; + slave = &priv->slaves[priv->data.active_slave];

ctrl = slave_read(slave, CPSW2_CONTROL); ctrl &= ~CTRL_ALL_TS_MASK; @@@ -1157,26 -1056,14 +1157,26 @@@ static int cpsw_hwtstamp_ioctl(struct n

static int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd) { + struct cpsw_priv *priv = netdev_priv(dev); + struct mii_ioctl_data *data = if_mii(req); + int slave_no = cpsw_slave_index(priv); + if (!netif_running(dev)) return -EINVAL;

+ switch (cmd) { #ifdef CONFIG_TI_CPTS - if (cmd == SIOCSHWTSTAMP) + case SIOCSHWTSTAMP: return cpsw_hwtstamp_ioctl(dev, req); #endif - return -ENOTSUPP; + case SIOCGMIIPHY: + data->phy_id = priv->slaves[slave_no].phy->addr; + break; + default: + return -ENOTSUPP; + } + + return 0; }

static void cpsw_ndo_tx_timeout(struct net_device *ndev) @@@ -1251,7 -1138,7 +1251,7 @@@ clean_vid }

static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev, - unsigned short vid) + __be16 proto, u16 vid) { struct cpsw_priv *priv = netdev_priv(ndev);

@@@ -1263,7 -1150,7 +1263,7 @@@ }

static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, - unsigned short vid) + __be16 proto, u16 vid) { struct cpsw_priv *priv = netdev_priv(ndev); int ret; @@@ -1357,39 -1244,12 +1357,39 @@@ static int cpsw_get_ts_info(struct net_ return 0; }

+static int cpsw_get_settings(struct net_device *ndev, + struct ethtool_cmd *ecmd) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + int slave_no = cpsw_slave_index(priv); + + if (priv->slaves[slave_no].phy) + return phy_ethtool_gset(priv->slaves[slave_no].phy, ecmd); + else + return -EOPNOTSUPP; +} + +static int cpsw_set_settings(struct net_device *ndev, struct ethtool_cmd *ecmd) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + int slave_no = cpsw_slave_index(priv); + + if (priv->slaves[slave_no].phy) + return phy_ethtool_sset(priv->slaves[slave_no].phy, ecmd); + else + return -EOPNOTSUPP; +} + static const struct ethtool_ops cpsw_ethtool_ops = { .get_drvinfo = cpsw_get_drvinfo, .get_msglevel = cpsw_get_msglevel, .set_msglevel = cpsw_set_msglevel, .get_link = ethtool_op_get_link, .get_ts_info = cpsw_get_ts_info, + .get_settings = cpsw_get_settings, + .set_settings = cpsw_set_settings, + .get_coalesce = cpsw_get_coalesce, + .set_coalesce = cpsw_set_coalesce, };

static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv, @@@ -1422,12 -1282,12 +1422,12 @@@ static int cpsw_probe_dt(struct cpsw_pl } data->slaves = prop;

- if (of_property_read_u32(node, "cpts_active_slave", &prop)) { - pr_err("Missing cpts_active_slave property in the DT.\n"); + if (of_property_read_u32(node, "active_slave", &prop)) { + pr_err("Missing active_slave property in the DT.\n"); ret = -EINVAL; goto error_ret; } - data->cpts_active_slave = prop; + data->active_slave = prop;

if (of_property_read_u32(node, "cpts_clock_mult", &prop)) { pr_err("Missing cpts_clock_mult property in the DT.\n"); @@@ -1520,7 -1380,7 +1520,7 @@@ memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN);

if (data->dual_emac) { - if (of_property_read_u32(node, "dual_emac_res_vlan", + if (of_property_read_u32(slave_node, "dual_emac_res_vlan", &prop)) { pr_err("Missing dual_emac_res_vlan in DT.\n"); slave_data->dual_emac_res_vlan = i+1; @@@ -1577,9 -1437,6 +1577,9 @@@ static int cpsw_probe_dual_emac(struct priv_sl2->slaves = priv->slaves; priv_sl2->clk = priv->clk;

+ priv_sl2->coal_intvl = 0; + priv_sl2->bus_freq_mhz = priv->bus_freq_mhz; + priv_sl2->cpsw_res = priv->cpsw_res; priv_sl2->regs = priv->regs; priv_sl2->host_port = priv->host_port; @@@ -1599,7 -1456,7 +1599,7 @@@ priv_sl2->num_irqs = priv->num_irqs; }

- ndev->features |= NETIF_F_HW_VLAN_FILTER; + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;

ndev->netdev_ops = &cpsw_netdev_ops; SET_ETHTOOL_OPS(ndev, &cpsw_ethtool_ops); @@@ -1689,8 -1546,6 +1689,8 @@@ static int cpsw_probe(struct platform_d ret = -ENODEV; goto clean_slave_ret; } + priv->coal_intvl = 0; + priv->bus_freq_mhz = clk_get_rate(priv->clk) / 1000000;

priv->cpsw_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!priv->cpsw_res) { @@@ -1837,7 -1692,7 +1837,7 @@@ k++; }

- ndev->features |= NETIF_F_HW_VLAN_FILTER; + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;

ndev->netdev_ops = &cpsw_netdev_ops; SET_ETHTOOL_OPS(ndev, &cpsw_ethtool_ops); diff --combined drivers/net/hyperv/netvsc_drv.c index 4559bb8,8341b62..088c554 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@@ -241,13 -241,11 +241,11 @@@ void netvsc_linkstatus_callback(struct

if (status == 1) { netif_carrier_on(net); - netif_wake_queue(net); ndev_ctx = netdev_priv(net); schedule_delayed_work(&ndev_ctx->dwork, 0); schedule_delayed_work(&ndev_ctx->dwork, msecs_to_jiffies(20)); } else { netif_carrier_off(net); - netif_tx_disable(net); } }

@@@ -431,7 -429,7 +429,7 @@@ static int netvsc_probe(struct hv_devic

/* TODO: Add GSO and Checksum offload */ net->hw_features = NETIF_F_SG; - net->features = NETIF_F_SG | NETIF_F_HW_VLAN_TX; + net->features = NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_TX;

SET_ETHTOOL_OPS(net, &ethtool_ops); SET_NETDEV_DEV(net, &dev->device); diff --combined drivers/net/tun.c index 316c759,729ed53..66109a2 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@@ -409,12 -409,14 +409,12 @@@ static void __tun_detach(struct tun_fil { struct tun_file *ntfile; struct tun_struct *tun; - struct net_device *dev;

tun = rtnl_dereference(tfile->tun);

if (tun && !tfile->detached) { u16 index = tfile->queue_index; BUG_ON(index >= tun->numqueues); - dev = tun->dev;

rcu_assign_pointer(tun->tfiles[index], tun->tfiles[tun->numqueues - 1]); @@@ -1203,8 -1205,6 +1203,8 @@@ static ssize_t tun_get_user(struct tun_ }

skb_reset_network_header(skb); + skb_probe_transport_header(skb, 0); + rxhash = skb_get_rxhash(skb); netif_rx_ni(skb);

@@@ -1594,7 -1594,7 +1594,7 @@@ static int tun_set_iff(struct net *net

if (tun->flags & TUN_TAP_MQ && (tun->numqueues + tun->numdisabled > 1)) - return err; + return -EBUSY; } else { char *name; @@@ -1656,7 -1656,6 +1656,7 @@@ dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | TUN_USER_FEATURES; dev->features = dev->hw_features; + dev->vlan_features = dev->features;

INIT_LIST_HEAD(&tun->disabled); err = tun_attach(tun, file); diff --combined drivers/net/usb/cdc_mbim.c index cc6dfe4,6bd9167..c964544 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@@ -101,7 -101,7 +101,7 @@@ static int cdc_mbim_bind(struct usbnet dev->net->flags |= IFF_NOARP;

/* no need to put the VLAN tci in the packet headers */ - dev->net->features |= NETIF_F_HW_VLAN_TX; + dev->net->features |= NETIF_F_HW_VLAN_CTAG_TX; err: return ret; } @@@ -134,7 -134,7 +134,7 @@@ static struct sk_buff *cdc_mbim_tx_fixu goto error;

if (skb) { - if (skb->len <= sizeof(ETH_HLEN)) + if (skb->len <= ETH_HLEN) goto error;

/* mapping VLANs to MBIM sessions: @@@ -221,7 -221,7 +221,7 @@@ static struct sk_buff *cdc_mbim_process

/* map MBIM session to VLAN */ if (tci) - vlan_put_tag(skb, tci); + vlan_put_tag(skb, htons(ETH_P_8021Q), tci); err: return skb; } diff --combined drivers/net/wireless/b43/phy_n.c index f9339e7,b70f220..63cca9c --- a/drivers/net/wireless/b43/phy_n.c +++ b/drivers/net/wireless/b43/phy_n.c @@@ -2789,6 -2789,10 +2789,6 @@@ static void b43_nphy_iq_cal_gain_params * Tx and Rx **************************************************/

-void b43_nphy_set_rxantenna(struct b43_wldev *dev, int antenna) -{//TODO -} - static void b43_nphy_op_adjust_txpower(struct b43_wldev *dev) {//TODO } @@@ -4888,7 -4892,7 +4888,7 @@@ static void b43_nphy_superswitch_init(s }

/* http://bcm-v4.sipsolutions.net/802.11/PHY/Init/N */ -int b43_phy_initn(struct b43_wldev *dev) +static int b43_phy_initn(struct b43_wldev *dev) { struct ssb_sprom *sprom = dev->dev->bus_sprom; struct b43_phy *phy = &dev->phy; @@@ -5161,7 -5165,8 +5161,8 @@@ static void b43_nphy_pmu_spur_avoid(str #endif #ifdef CONFIG_B43_SSB case B43_BUS_SSB: - /* FIXME */ + ssb_pmu_spuravoid_pllupdate(&dev->dev->sdev->bus->chipco, + avoid); break; #endif } diff --combined drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c index 6269920,78da3ef..e4f1f3c --- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c @@@ -26,7 -26,6 +26,7 @@@ #include <brcmu_wifi.h> #include "dhd.h" #include "dhd_dbg.h" +#include "tracepoint.h" #include "fwil_types.h" #include "p2p.h" #include "wl_cfg80211.h" @@@ -183,6 -182,64 +183,6 @@@ static struct ieee80211_channel __wl_5g CHAN5G(216, 0), };

-static struct ieee80211_channel __wl_5ghz_n_channels[] = { - CHAN5G(32, 0), CHAN5G(34, 0), - CHAN5G(36, 0), CHAN5G(38, 0), - CHAN5G(40, 0), CHAN5G(42, 0), - CHAN5G(44, 0), CHAN5G(46, 0), - CHAN5G(48, 0), CHAN5G(50, 0), - CHAN5G(52, 0), CHAN5G(54, 0), - CHAN5G(56, 0), CHAN5G(58, 0), - CHAN5G(60, 0), CHAN5G(62, 0), - CHAN5G(64, 0), CHAN5G(66, 0), - CHAN5G(68, 0), CHAN5G(70, 0), - CHAN5G(72, 0), CHAN5G(74, 0), - CHAN5G(76, 0), CHAN5G(78, 0), - CHAN5G(80, 0), CHAN5G(82, 0), - CHAN5G(84, 0), CHAN5G(86, 0), - CHAN5G(88, 0), CHAN5G(90, 0), - CHAN5G(92, 0), CHAN5G(94, 0), - CHAN5G(96, 0), CHAN5G(98, 0), - CHAN5G(100, 0), CHAN5G(102, 0), - CHAN5G(104, 0), CHAN5G(106, 0), - CHAN5G(108, 0), CHAN5G(110, 0), - CHAN5G(112, 0), CHAN5G(114, 0), - CHAN5G(116, 0), CHAN5G(118, 0), - CHAN5G(120, 0), CHAN5G(122, 0), - CHAN5G(124, 0), CHAN5G(126, 0), - CHAN5G(128, 0), CHAN5G(130, 0), - CHAN5G(132, 0), CHAN5G(134, 0), - CHAN5G(136, 0), CHAN5G(138, 0), - CHAN5G(140, 0), CHAN5G(142, 0), - CHAN5G(144, 0), CHAN5G(145, 0), - CHAN5G(146, 0), CHAN5G(147, 0), - CHAN5G(148, 0), CHAN5G(149, 0), - CHAN5G(150, 0), CHAN5G(151, 0), - CHAN5G(152, 0), CHAN5G(153, 0), - CHAN5G(154, 0), CHAN5G(155, 0), - CHAN5G(156, 0), CHAN5G(157, 0), - CHAN5G(158, 0), CHAN5G(159, 0), - CHAN5G(160, 0), CHAN5G(161, 0), - CHAN5G(162, 0), CHAN5G(163, 0), - CHAN5G(164, 0), CHAN5G(165, 0), - CHAN5G(166, 0), CHAN5G(168, 0), - CHAN5G(170, 0), CHAN5G(172, 0), - CHAN5G(174, 0), CHAN5G(176, 0), - CHAN5G(178, 0), CHAN5G(180, 0), - CHAN5G(182, 0), CHAN5G(184, 0), - CHAN5G(186, 0), CHAN5G(188, 0), - CHAN5G(190, 0), CHAN5G(192, 0), - CHAN5G(194, 0), CHAN5G(196, 0), - CHAN5G(198, 0), CHAN5G(200, 0), - CHAN5G(202, 0), CHAN5G(204, 0), - CHAN5G(206, 0), CHAN5G(208, 0), - CHAN5G(210, 0), CHAN5G(212, 0), - CHAN5G(214, 0), CHAN5G(216, 0), - CHAN5G(218, 0), CHAN5G(220, 0), - CHAN5G(222, 0), CHAN5G(224, 0), - CHAN5G(226, 0), CHAN5G(228, 0), -}; - static struct ieee80211_supported_band __wl_band_2ghz = { .band = IEEE80211_BAND_2GHZ, .channels = __wl_2ghz_channels, @@@ -199,28 -256,12 +199,28 @@@ static struct ieee80211_supported_band .n_bitrates = wl_a_rates_size, };

-static struct ieee80211_supported_band __wl_band_5ghz_n = { - .band = IEEE80211_BAND_5GHZ, - .channels = __wl_5ghz_n_channels, - .n_channels = ARRAY_SIZE(__wl_5ghz_n_channels), - .bitrates = wl_a_rates, - .n_bitrates = wl_a_rates_size, +/* This is to override regulatory domains defined in cfg80211 module (reg.c) + * By default world regulatory domain defined in reg.c puts the flags + * NL80211_RRF_PASSIVE_SCAN and NL80211_RRF_NO_IBSS for 5GHz channels (for + * 36..48 and 149..165). With respect to these flags, wpa_supplicant doesn't + * start p2p operations on 5GHz channels. All the changes in world regulatory + * domain are to be done here. + */ +static const struct ieee80211_regdomain brcmf_regdom = { + .n_reg_rules = 4, + .alpha2 = "99", + .reg_rules = { + /* IEEE 802.11b/g, channels 1..11 */ + REG_RULE(2412-10, 2472+10, 40, 6, 20, 0), + /* If any */ + /* IEEE 802.11 channel 14 - Only JP enables + * this and for 802.11b only + */ + REG_RULE(2484-10, 2484+10, 20, 6, 20, 0), + /* IEEE 802.11a, channel 36..64 */ + REG_RULE(5150-10, 5350+10, 40, 6, 20, 0), + /* IEEE 802.11a, channel 100..165 */ + REG_RULE(5470-10, 5850+10, 40, 6, 20, 0), } };

static const u32 __wl_cipher_suites[] = { @@@ -482,16 -523,17 +482,16 @@@ static struct wireless_dev *brcmf_cfg80 return ERR_PTR(-EOPNOTSUPP); case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_GO: + case NL80211_IFTYPE_P2P_DEVICE: return brcmf_p2p_add_vif(wiphy, name, type, flags, params); case NL80211_IFTYPE_UNSPECIFIED: - case NL80211_IFTYPE_P2P_DEVICE: default: return ERR_PTR(-EINVAL); } }

-void brcmf_set_mpc(struct net_device *ndev, int mpc) +void brcmf_set_mpc(struct brcmf_if *ifp, int mpc) { - struct brcmf_if *ifp = netdev_priv(ndev); s32 err = 0;

if (check_vif_up(ifp->vif)) { @@@ -504,9 -546,10 +504,9 @@@ } }

-s32 -brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg, - struct net_device *ndev, - bool aborted, bool fw_abort) +s32 brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg, + struct brcmf_if *ifp, bool aborted, + bool fw_abort) { struct brcmf_scan_params_le params_le; struct cfg80211_scan_request *scan_request; @@@ -537,7 -580,7 +537,7 @@@ /* Scan is aborted by setting channel_list[0] to -1 */ params_le.channel_list[0] = cpu_to_le16(-1); /* E-Scan (or anyother type) can be aborted by SCAN */ - err = brcmf_fil_cmd_data_set(netdev_priv(ndev), BRCMF_C_SCAN, + err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SCAN, &params_le, sizeof(params_le)); if (err) brcmf_err("Scan abort failed\n"); @@@ -551,12 -594,12 +551,12 @@@ cfg->sched_escan = false; if (!aborted) cfg80211_sched_scan_results(cfg_to_wiphy(cfg)); - brcmf_set_mpc(ndev, 1); + brcmf_set_mpc(ifp, 1); } else if (scan_request) { brcmf_dbg(SCAN, "ESCAN Completed scan: %s\n", aborted ? "Aborted" : "Done"); cfg80211_scan_done(scan_request, aborted); - brcmf_set_mpc(ndev, 1); + brcmf_set_mpc(ifp, 1); } if (!test_and_clear_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status)) brcmf_dbg(SCAN, "Scan complete, probably P2P scan\n"); @@@ -576,9 -619,9 +576,9 @@@ int brcmf_cfg80211_del_iface(struct wip

if (ndev) { if (test_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status) && - cfg->escan_info.ndev == ndev) - brcmf_notify_escan_complete(cfg, ndev, true, - true); + cfg->escan_info.ifp == netdev_priv(ndev)) + brcmf_notify_escan_complete(cfg, netdev_priv(ndev), + true, true);

brcmf_fil_iovar_int_set(netdev_priv(ndev), "mpc", 1); } @@@ -594,9 -637,9 +594,9 @@@ return -EOPNOTSUPP; case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_GO: + case NL80211_IFTYPE_P2P_DEVICE: return brcmf_p2p_del_vif(wiphy, wdev); case NL80211_IFTYPE_UNSPECIFIED: - case NL80211_IFTYPE_P2P_DEVICE: default: return -EINVAL; } @@@ -760,7 -803,7 +760,7 @@@ static void brcmf_escan_prep(struct brc }

static s32 -brcmf_run_escan(struct brcmf_cfg80211_info *cfg, struct net_device *ndev, +brcmf_run_escan(struct brcmf_cfg80211_info *cfg, struct brcmf_if *ifp, struct cfg80211_scan_request *request, u16 action) { s32 params_size = BRCMF_SCAN_PARAMS_FIXED_SIZE + @@@ -789,7 -832,8 +789,7 @@@ params->action = cpu_to_le16(action); params->sync_id = cpu_to_le16(0x1234);

- err = brcmf_fil_iovar_data_set(netdev_priv(ndev), "escan", - params, params_size); + err = brcmf_fil_iovar_data_set(ifp, "escan", params, params_size); if (err) { if (err == -EBUSY) brcmf_dbg(INFO, "system busy : escan canceled\n"); @@@ -804,7 -848,7 +804,7 @@@ exit

static s32 brcmf_do_escan(struct brcmf_cfg80211_info *cfg, struct wiphy *wiphy, - struct net_device *ndev, struct cfg80211_scan_request *request) + struct brcmf_if *ifp, struct cfg80211_scan_request *request) { s32 err; u32 passive_scan; @@@ -812,35 -856,35 +812,35 @@@ struct escan_info *escan = &cfg->escan_info;

brcmf_dbg(SCAN, "Enter\n"); - escan->ndev = ndev; + escan->ifp = ifp; escan->wiphy = wiphy; escan->escan_state = WL_ESCAN_STATE_SCANNING; passive_scan = cfg->active_scan ? 0 : 1; - err = brcmf_fil_cmd_int_set(netdev_priv(ndev), BRCMF_C_SET_PASSIVE_SCAN, + err = brcmf_fil_cmd_int_set(ifp, BRCMF_C_SET_PASSIVE_SCAN, passive_scan); if (err) { brcmf_err("error (%d)\n", err); return err; } - brcmf_set_mpc(ndev, 0); + brcmf_set_mpc(ifp, 0); results = (struct brcmf_scan_results *)cfg->escan_info.escan_buf; results->version = 0; results->count = 0; results->buflen = WL_ESCAN_RESULTS_FIXED_SIZE;

- err = escan->run(cfg, ndev, request, WL_ESCAN_ACTION_START); + err = escan->run(cfg, ifp, request, WL_ESCAN_ACTION_START); if (err) - brcmf_set_mpc(ndev, 1); + brcmf_set_mpc(ifp, 1); return err; }

static s32 -brcmf_cfg80211_escan(struct wiphy *wiphy, struct net_device *ndev, +brcmf_cfg80211_escan(struct wiphy *wiphy, struct brcmf_cfg80211_vif *vif, struct cfg80211_scan_request *request, struct cfg80211_ssid *this_ssid) { - struct brcmf_if *ifp = netdev_priv(ndev); - struct brcmf_cfg80211_info *cfg = ndev_to_cfg(ndev); + struct brcmf_if *ifp = vif->ifp; + struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy); struct cfg80211_ssid *ssids; struct brcmf_cfg80211_scan_req *sr = &cfg->scan_req_int; u32 passive_scan; @@@ -866,8 -910,10 +866,8 @@@ }

/* If scan req comes for p2p0, send it over primary I/F */ - if (ifp->vif == cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif) { - ifp = cfg->p2p.bss_idx[P2PAPI_BSSCFG_PRIMARY].vif->ifp; - ndev = ifp->ndev; - } + if (vif == cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif) + vif = cfg->p2p.bss_idx[P2PAPI_BSSCFG_PRIMARY].vif;

/* Arm scan timeout timer */ mod_timer(&cfg->escan_timeout, jiffies + @@@ -888,11 -934,11 +888,11 @@@ set_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status); if (escan_req) { cfg->escan_info.run = brcmf_run_escan; - err = brcmf_p2p_scan_prep(wiphy, request, ifp->vif); + err = brcmf_p2p_scan_prep(wiphy, request, vif); if (err) goto scan_out;

- err = brcmf_do_escan(cfg, wiphy, ndev, request); + err = brcmf_do_escan(cfg, wiphy, vif->ifp, request); if (err) goto scan_out; } else { @@@ -916,7 -962,7 +916,7 @@@ brcmf_err("WLC_SET_PASSIVE_SCAN error (%d)\n", err); goto scan_out; } - brcmf_set_mpc(ndev, 0); + brcmf_set_mpc(ifp, 0); err = brcmf_fil_cmd_data_set(ifp, BRCMF_C_SCAN, &sr->ssid_le, sizeof(sr->ssid_le)); if (err) { @@@ -926,7 -972,7 +926,7 @@@ else brcmf_err("WLC_SCAN error (%d)\n", err);

- brcmf_set_mpc(ndev, 1); + brcmf_set_mpc(ifp, 1); goto scan_out; } } @@@ -944,15 -990,16 +944,15 @@@ scan_out static s32 brcmf_cfg80211_scan(struct wiphy *wiphy, struct cfg80211_scan_request *request) { - struct net_device *ndev = request->wdev->netdev; + struct brcmf_cfg80211_vif *vif; s32 err = 0;

brcmf_dbg(TRACE, "Enter\n"); - - if (!check_vif_up(container_of(request->wdev, - struct brcmf_cfg80211_vif, wdev))) + vif = container_of(request->wdev, struct brcmf_cfg80211_vif, wdev); + if (!check_vif_up(vif)) return -EIO;

- err = brcmf_cfg80211_escan(wiphy, ndev, request, NULL); + err = brcmf_cfg80211_escan(wiphy, vif, request, NULL);

if (err) brcmf_err("scan error (%d)\n", err); @@@ -2463,7 -2510,7 +2463,7 @@@ void brcmf_abort_scanning(struct brcmf_ set_bit(BRCMF_SCAN_STATUS_ABORT, &cfg->scan_status); if (cfg->scan_request) { escan->escan_state = WL_ESCAN_STATE_IDLE; - brcmf_notify_escan_complete(cfg, escan->ndev, true, true); + brcmf_notify_escan_complete(cfg, escan->ifp, true, true); } clear_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status); clear_bit(BRCMF_SCAN_STATUS_ABORT, &cfg->scan_status); @@@ -2475,7 -2522,7 +2475,7 @@@ static void brcmf_cfg80211_escan_timeou container_of(work, struct brcmf_cfg80211_info, escan_timeout_work);

- brcmf_notify_escan_complete(cfg, cfg->escan_info.ndev, true, true); + brcmf_notify_escan_complete(cfg, cfg->escan_info.ifp, true, true); }

static void brcmf_escan_timeout(unsigned long data) @@@ -2526,6 -2573,7 +2526,6 @@@ brcmf_cfg80211_escan_handler(struct brc const struct brcmf_event_msg *e, void *data) { struct brcmf_cfg80211_info *cfg = ifp->drvr->config; - struct net_device *ndev = ifp->ndev; s32 status; s32 err = 0; struct brcmf_escan_result_le *escan_result_le; @@@ -2538,8 -2586,9 +2538,8 @@@

status = e->status;

- if (!ndev || !test_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status)) { - brcmf_err("scan not ready ndev %p drv_status %x\n", ndev, - !test_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status)); + if (!test_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status)) { + brcmf_err("scan not ready, bssidx=%d\n", ifp->bssidx); return -EPERM; }

@@@ -2610,7 -2659,7 +2610,7 @@@ cfg->escan_info.escan_buf; brcmf_inform_bss(cfg); aborted = status != BRCMF_E_STATUS_SUCCESS; - brcmf_notify_escan_complete(cfg, ndev, aborted, + brcmf_notify_escan_complete(cfg, ifp, aborted, false); } else brcmf_dbg(SCAN, "Ignored scan complete result 0x%x\n", @@@ -2688,7 -2737,7 +2688,7 @@@ static s32 brcmf_cfg80211_suspend(struc brcmf_abort_scanning(cfg);

/* Turn off watchdog timer */ - brcmf_set_mpc(ndev, 1); + brcmf_set_mpc(netdev_priv(ndev), 1);

exit: brcmf_dbg(TRACE, "Exit\n"); @@@ -2846,6 -2895,7 +2846,6 @@@ brcmf_notify_sched_scan_results(struct const struct brcmf_event_msg *e, void *data) { struct brcmf_cfg80211_info *cfg = ifp->drvr->config; - struct net_device *ndev = ifp->ndev; struct brcmf_pno_net_info_le *netinfo, *netinfo_start; struct cfg80211_scan_request *request = NULL; struct cfg80211_ssid *ssid = NULL; @@@ -2929,7 -2979,7 +2929,7 @@@ }

set_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status); - err = brcmf_do_escan(cfg, wiphy, ndev, request); + err = brcmf_do_escan(cfg, wiphy, ifp, request); if (err) { clear_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status); goto out_err; @@@ -3001,16 -3051,16 +3001,16 @@@ brcmf_cfg80211_sched_scan_start(struct int i; int ret = 0;

- brcmf_dbg(SCAN, "Enter n_match_sets:%d n_ssids:%d\n", + brcmf_dbg(SCAN, "Enter n_match_sets:%d n_ssids:%d\n", request->n_match_sets, request->n_ssids); if (test_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status)) { brcmf_err("Scanning already: status (%lu)\n", cfg->scan_status); return -EAGAIN; }

- if (!request || !request->n_ssids || !request->n_match_sets) { + if (!request->n_ssids || !request->n_match_sets) { brcmf_err("Invalid sched scan req!! n_ssids:%d\n", - request ? request->n_ssids : 0); + request->n_ssids); return -EINVAL; }

@@@ -3086,7 -3136,7 +3086,7 @@@ static int brcmf_cfg80211_sched_scan_st brcmf_dbg(SCAN, "enter\n"); brcmf_dev_pno_clean(ndev); if (cfg->sched_escan) - brcmf_notify_escan_complete(cfg, ndev, true, true); + brcmf_notify_escan_complete(cfg, netdev_priv(ndev), true, true); return 0; }

@@@ -3658,7 -3708,7 +3658,7 @@@ brcmf_cfg80211_start_ap(struct wiphy *w ssid_le.SSID_len = cpu_to_le32((u32)settings->ssid_len); }

- brcmf_set_mpc(ndev, 0); + brcmf_set_mpc(ifp, 0);

/* find the RSN_IE */ rsn_ie = brcmf_parse_tlvs((u8 *)settings->beacon.tail, @@@ -3766,7 -3816,7 +3766,7 @@@

exit: if (err) - brcmf_set_mpc(ndev, 1); + brcmf_set_mpc(ifp, 1); return err; }

@@@ -3806,7 -3856,7 +3806,7 @@@ static int brcmf_cfg80211_stop_ap(struc if (err < 0) brcmf_err("bss_enable config failed %d\n", err); } - brcmf_set_mpc(ndev, 1); + brcmf_set_mpc(ifp, 1); set_bit(BRCMF_VIF_STATUS_AP_CREATING, &ifp->vif->sme_state); clear_bit(BRCMF_VIF_STATUS_AP_CREATED, &ifp->vif->sme_state);

@@@ -3863,13 -3913,13 +3863,13 @@@ brcmf_cfg80211_mgmt_frame_register(stru struct wireless_dev *wdev, u16 frame_type, bool reg) { - struct brcmf_if *ifp = netdev_priv(wdev->netdev); - struct brcmf_cfg80211_vif *vif = ifp->vif; + struct brcmf_cfg80211_vif *vif; u16 mgmt_type;

brcmf_dbg(TRACE, "Enter, frame_type %04x, reg=%d\n", frame_type, reg);

mgmt_type = (frame_type & IEEE80211_FCTL_STYPE) >> 4; + vif = container_of(wdev, struct brcmf_cfg80211_vif, wdev); if (reg) vif->mgmt_rx_reg |= BIT(mgmt_type); else @@@ -3885,6 -3935,7 +3885,6 @@@ brcmf_cfg80211_mgmt_tx(struct wiphy *wi { struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy); const struct ieee80211_mgmt *mgmt; - struct brcmf_if *ifp; struct brcmf_cfg80211_vif *vif; s32 err = 0; s32 ie_offset; @@@ -3920,7 -3971,8 +3920,7 @@@ ie_offset = DOT11_MGMT_HDR_LEN + DOT11_BCN_PRB_FIXED_LEN; ie_len = len - ie_offset; - ifp = netdev_priv(wdev->netdev); - vif = ifp->vif; + vif = container_of(wdev, struct brcmf_cfg80211_vif, wdev); if (vif == cfg->p2p.bss_idx[P2PAPI_BSSCFG_PRIMARY].vif) vif = cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif; err = brcmf_vif_set_mgmt_ie(vif, @@@ -3955,7 -4007,7 +3955,7 @@@ *cookie, le16_to_cpu(action_frame->len), chan->center_freq);

- ack = brcmf_p2p_send_action_frame(cfg, wdev->netdev, + ack = brcmf_p2p_send_action_frame(cfg, cfg_to_ndev(cfg), af_params);

cfg80211_mgmt_tx_status(wdev, *cookie, buf, len, ack, @@@ -4027,8 -4079,6 +4027,8 @@@ static struct cfg80211_ops wl_cfg80211_ .mgmt_tx = brcmf_cfg80211_mgmt_tx, .remain_on_channel = brcmf_p2p_remain_on_channel, .cancel_remain_on_channel = brcmf_cfg80211_cancel_remain_on_channel, + .start_p2p_device = brcmf_p2p_start_device, + .stop_p2p_device = brcmf_p2p_stop_device, #ifdef CONFIG_NL80211_TESTMODE .testmode_cmd = brcmf_cfg80211_testmode #endif @@@ -4078,10 -4128,6 +4078,6 @@@ static const struct ieee80211_iface_lim }, { .max = 1, - .types = BIT(NL80211_IFTYPE_P2P_DEVICE) - }, - { - .max = 1, .types = BIT(NL80211_IFTYPE_P2P_CLIENT) | BIT(NL80211_IFTYPE_P2P_GO) }, @@@ -4116,11 -4162,6 +4112,11 @@@ brcmf_txrx_stypes[NUM_NL80211_IFTYPES] BIT(IEEE80211_STYPE_AUTH >> 4) | BIT(IEEE80211_STYPE_DEAUTH >> 4) | BIT(IEEE80211_STYPE_ACTION >> 4) + }, + [NL80211_IFTYPE_P2P_DEVICE] = { + .tx = 0xffff, + .rx = BIT(IEEE80211_STYPE_ACTION >> 4) | + BIT(IEEE80211_STYPE_PROBE_REQ >> 4) } };

@@@ -4142,11 -4183,17 +4138,10 @@@ static struct wiphy *brcmf_setup_wiphy( BIT(NL80211_IFTYPE_ADHOC) | BIT(NL80211_IFTYPE_AP) | BIT(NL80211_IFTYPE_P2P_CLIENT) | - BIT(NL80211_IFTYPE_P2P_GO) | - BIT(NL80211_IFTYPE_P2P_DEVICE); + BIT(NL80211_IFTYPE_P2P_GO); wiphy->iface_combinations = brcmf_iface_combos; wiphy->n_iface_combinations = ARRAY_SIZE(brcmf_iface_combos); wiphy->bands[IEEE80211_BAND_2GHZ] = &__wl_band_2ghz; - wiphy->bands[IEEE80211_BAND_5GHZ] = &__wl_band_5ghz_a; /* Set - * it as 11a by default. - * This will be updated with - * 11n phy tables in - * "ifconfig up" - * if phy has 11n capability - */ wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM; wiphy->cipher_suites = __wl_cipher_suites; wiphy->n_cipher_suites = ARRAY_SIZE(__wl_cipher_suites); @@@ -4156,9 -4203,6 +4151,9 @@@ wiphy->mgmt_stypes = brcmf_txrx_stypes; wiphy->max_remain_on_channel_duration = 5000; brcmf_wiphy_pno_params(wiphy); + brcmf_dbg(INFO, "Registering custom regulatory\n"); + wiphy->flags |= WIPHY_FLAG_CUSTOM_REGULATORY; + wiphy_apply_custom_regulatory(wiphy, &brcmf_regdom); err = wiphy_register(wiphy); if (err < 0) { brcmf_err("Could not register wiphy device (%d)\n", err); @@@ -4577,11 -4621,9 +4572,11 @@@ static s32 brcmf_notify_vif_event(struc

ifp->vif = vif; vif->ifp = ifp; - vif->wdev.netdev = ifp->ndev; - ifp->ndev->ieee80211_ptr = &vif->wdev; - SET_NETDEV_DEV(ifp->ndev, wiphy_dev(cfg->wiphy)); + if (ifp->ndev) { + vif->wdev.netdev = ifp->ndev; + ifp->ndev->ieee80211_ptr = &vif->wdev; + SET_NETDEV_DEV(ifp->ndev, wiphy_dev(cfg->wiphy)); + } mutex_unlock(&event->vif_event_lock); wake_up(&event->vif_wq); return 0; @@@ -4884,248 -4926,34 +4879,248 @@@ dongle_scantime_out return err; }

-static s32 wl_update_wiphybands(struct brcmf_cfg80211_info *cfg) + +static s32 brcmf_construct_reginfo(struct brcmf_cfg80211_info *cfg, u32 bw_cap) +{ + struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg)); + struct ieee80211_channel *band_chan_arr; + struct brcmf_chanspec_list *list; + s32 err; + u8 *pbuf; + u32 i, j; + u32 total; + u16 chanspec; + enum ieee80211_band band; + u32 channel; + u32 *n_cnt; + bool ht40_allowed; + u32 index; + u32 ht40_flag; + bool update; + u32 array_size; + + pbuf = kzalloc(BRCMF_DCMD_MEDLEN, GFP_KERNEL); + + if (pbuf == NULL) + return -ENOMEM; + + list = (struct brcmf_chanspec_list *)pbuf; + + err = brcmf_fil_iovar_data_get(ifp, "chanspecs", pbuf, + BRCMF_DCMD_MEDLEN); + if (err) { + brcmf_err("get chanspecs error (%d)\n", err); + goto exit; + } + + __wl_band_2ghz.n_channels = 0; + __wl_band_5ghz_a.n_channels = 0; + + total = le32_to_cpu(list->count); + for (i = 0; i < total; i++) { + chanspec = (u16)le32_to_cpu(list->element[i]); + channel = CHSPEC_CHANNEL(chanspec); + + if (CHSPEC_IS40(chanspec)) { + if (CHSPEC_SB_UPPER(chanspec)) + channel += CH_10MHZ_APART; + else + channel -= CH_10MHZ_APART; + } else if (CHSPEC_IS80(chanspec)) { + brcmf_dbg(INFO, "HT80 center channel : %d\n", + channel); + continue; + } + if (CHSPEC_IS2G(chanspec) && (channel >= CH_MIN_2G_CHANNEL) && + (channel <= CH_MAX_2G_CHANNEL)) { + band_chan_arr = __wl_2ghz_channels; + array_size = ARRAY_SIZE(__wl_2ghz_channels); + n_cnt = &__wl_band_2ghz.n_channels; + band = IEEE80211_BAND_2GHZ; + ht40_allowed = (bw_cap == WLC_N_BW_40ALL); + } else if (CHSPEC_IS5G(chanspec) && + channel >= CH_MIN_5G_CHANNEL) { + band_chan_arr = __wl_5ghz_a_channels; + array_size = ARRAY_SIZE(__wl_5ghz_a_channels); + n_cnt = &__wl_band_5ghz_a.n_channels; + band = IEEE80211_BAND_5GHZ; + ht40_allowed = !(bw_cap == WLC_N_BW_20ALL); + } else { + brcmf_err("Invalid channel Sepc. 0x%x.\n", chanspec); + continue; + } + if (!ht40_allowed && CHSPEC_IS40(chanspec)) + continue; + update = false; + for (j = 0; (j < *n_cnt && (*n_cnt < array_size)); j++) { + if (band_chan_arr[j].hw_value == channel) { + update = true; + break; + } + } + if (update) + index = j; + else + index = *n_cnt; + if (index < array_size) { + band_chan_arr[index].center_freq = + ieee80211_channel_to_frequency(channel, band); + band_chan_arr[index].hw_value = channel; + + if (CHSPEC_IS40(chanspec) && ht40_allowed) { + /* assuming the order is HT20, HT40 Upper, + * HT40 lower from chanspecs + */ + ht40_flag = band_chan_arr[index].flags & + IEEE80211_CHAN_NO_HT40; + if (CHSPEC_SB_UPPER(chanspec)) { + if (ht40_flag == IEEE80211_CHAN_NO_HT40) + band_chan_arr[index].flags &= + ~IEEE80211_CHAN_NO_HT40; + band_chan_arr[index].flags |= + IEEE80211_CHAN_NO_HT40PLUS; + } else { + /* It should be one of + * IEEE80211_CHAN_NO_HT40 or + * IEEE80211_CHAN_NO_HT40PLUS + */ + band_chan_arr[index].flags &= + ~IEEE80211_CHAN_NO_HT40; + if (ht40_flag == IEEE80211_CHAN_NO_HT40) + band_chan_arr[index].flags |= + IEEE80211_CHAN_NO_HT40MINUS; + } + } else { + band_chan_arr[index].flags = + IEEE80211_CHAN_NO_HT40; + if (band == IEEE80211_BAND_2GHZ) + channel |= WL_CHANSPEC_BAND_2G; + else + channel |= WL_CHANSPEC_BAND_5G; + channel |= WL_CHANSPEC_BW_20; + err = brcmf_fil_bsscfg_int_get(ifp, + "per_chan_info", + &channel); + if (!err) { + if (channel & WL_CHAN_RADAR) + band_chan_arr[index].flags |= + (IEEE80211_CHAN_RADAR | + IEEE80211_CHAN_NO_IBSS); + if (channel & WL_CHAN_PASSIVE) + band_chan_arr[index].flags |= + IEEE80211_CHAN_PASSIVE_SCAN; + } + } + if (!update) + (*n_cnt)++; + } + } +exit: + kfree(pbuf); + return err; +} + + +static s32 brcmf_update_wiphybands(struct brcmf_cfg80211_info *cfg) { struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg)); struct wiphy *wiphy; s32 phy_list; + u32 band_list[3]; + u32 nmode; + u32 bw_cap = 0; s8 phy; - s32 err = 0; + s32 err; + u32 nband; + s32 i; + struct ieee80211_supported_band *bands[IEEE80211_NUM_BANDS]; + s32 index;

err = brcmf_fil_cmd_data_get(ifp, BRCMF_C_GET_PHYLIST, &phy_list, sizeof(phy_list)); if (err) { - brcmf_err("error (%d)\n", err); + brcmf_err("BRCMF_C_GET_PHYLIST error (%d)\n", err); return err; }

phy = ((char *)&phy_list)[0]; - brcmf_dbg(INFO, "%c phy\n", phy); - if (phy == 'n' || phy == 'a') { - wiphy = cfg_to_wiphy(cfg); - wiphy->bands[IEEE80211_BAND_5GHZ] = &__wl_band_5ghz_n; + brcmf_dbg(INFO, "BRCMF_C_GET_PHYLIST reported: %c phy\n", phy); + + + err = brcmf_fil_cmd_data_get(ifp, BRCMF_C_GET_BANDLIST, + &band_list, sizeof(band_list)); + if (err) { + brcmf_err("BRCMF_C_GET_BANDLIST error (%d)\n", err); + return err; } + brcmf_dbg(INFO, "BRCMF_C_GET_BANDLIST reported: 0x%08x 0x%08x 0x%08x phy\n", + band_list[0], band_list[1], band_list[2]); + + err = brcmf_fil_iovar_int_get(ifp, "nmode", &nmode); + if (err) { + brcmf_err("nmode error (%d)\n", err); + } else { + err = brcmf_fil_iovar_int_get(ifp, "mimo_bw_cap", &bw_cap); + if (err) + brcmf_err("mimo_bw_cap error (%d)\n", err); + } + brcmf_dbg(INFO, "nmode=%d, mimo_bw_cap=%d\n", nmode, bw_cap); + + err = brcmf_construct_reginfo(cfg, bw_cap); + if (err) { + brcmf_err("brcmf_construct_reginfo failed (%d)\n", err); + return err; + } + + nband = band_list[0]; + memset(bands, 0, sizeof(bands)); + + for (i = 1; i <= nband && i < ARRAY_SIZE(band_list); i++) { + index = -1; + if ((band_list[i] == WLC_BAND_5G) && + (__wl_band_5ghz_a.n_channels > 0)) { + index = IEEE80211_BAND_5GHZ; + bands[index] = &__wl_band_5ghz_a; + if ((bw_cap == WLC_N_BW_40ALL) || + (bw_cap == WLC_N_BW_20IN2G_40IN5G)) + bands[index]->ht_cap.cap |= + IEEE80211_HT_CAP_SGI_40; + } else if ((band_list[i] == WLC_BAND_2G) && + (__wl_band_2ghz.n_channels > 0)) { + index = IEEE80211_BAND_2GHZ; + bands[index] = &__wl_band_2ghz; + if (bw_cap == WLC_N_BW_40ALL) + bands[index]->ht_cap.cap |= + IEEE80211_HT_CAP_SGI_40; + } + + if ((index >= 0) && nmode) { + bands[index]->ht_cap.cap |= IEEE80211_HT_CAP_SGI_20; + bands[index]->ht_cap.cap |= IEEE80211_HT_CAP_DSSSCCK40; + bands[index]->ht_cap.ht_supported = true; + bands[index]->ht_cap.ampdu_factor = + IEEE80211_HT_MAX_AMPDU_64K; + bands[index]->ht_cap.ampdu_density = + IEEE80211_HT_MPDU_DENSITY_16; + /* An HT shall support all EQM rates for one spatial + * stream + */ + bands[index]->ht_cap.mcs.rx_mask[0] = 0xff; + } + } + + wiphy = cfg_to_wiphy(cfg); + wiphy->bands[IEEE80211_BAND_2GHZ] = bands[IEEE80211_BAND_2GHZ]; + wiphy->bands[IEEE80211_BAND_5GHZ] = bands[IEEE80211_BAND_5GHZ]; + wiphy_apply_custom_regulatory(wiphy, &brcmf_regdom);

return err; }

+ static s32 brcmf_dongle_probecap(struct brcmf_cfg80211_info *cfg) { - return wl_update_wiphybands(cfg); + return brcmf_update_wiphybands(cfg); }

static s32 brcmf_config_dongle(struct brcmf_cfg80211_info *cfg) diff --combined drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c index cd83786,e2340b2..c837be2 --- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c @@@ -1,6 -1,5 +1,6 @@@ /* * Copyright (c) 2010 Broadcom Corporation + * Copyright (c) 2013 Hauke Mehrtens hauke@hauke-m.de * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@@ -35,7 -34,6 +35,7 @@@ #include "mac80211_if.h" #include "main.h" #include "debug.h" +#include "led.h"

#define N_TX_QUEUES 4 /* #tx queues on mac80211<->driver interface */ #define BRCMS_FLUSH_TIMEOUT 500 /* msec */ @@@ -276,6 -274,130 +276,130 @@@ static void brcms_set_basic_rate(struc } }

+ /** + * This function frees the WL per-device resources. + * + * This function frees resources owned by the WL device pointed to + * by the wl parameter. + * + * precondition: can both be called locked and unlocked + * + */ + static void brcms_free(struct brcms_info *wl) + { + struct brcms_timer *t, *next; + + /* free ucode data */ + if (wl->fw.fw_cnt) + brcms_ucode_data_free(&wl->ucode); + if (wl->irq) + free_irq(wl->irq, wl); + + /* kill dpc */ + tasklet_kill(&wl->tasklet); + + if (wl->pub) { + brcms_debugfs_detach(wl->pub); + brcms_c_module_unregister(wl->pub, "linux", wl); + } + + /* free common resources */ + if (wl->wlc) { + brcms_c_detach(wl->wlc); + wl->wlc = NULL; + wl->pub = NULL; + } + + /* virtual interface deletion is deferred so we cannot spinwait */ + + /* wait for all pending callbacks to complete */ + while (atomic_read(&wl->callbacks) > 0) + schedule(); + + /* free timers */ + for (t = wl->timers; t; t = next) { + next = t->next; + #ifdef DEBUG + kfree(t->name); + #endif + kfree(t); + } + } + + /* + * called from both kernel as from this kernel module (error flow on attach) + * precondition: perimeter lock is not acquired. + */ + static void brcms_remove(struct bcma_device *pdev) + { + struct ieee80211_hw *hw = bcma_get_drvdata(pdev); + struct brcms_info *wl = hw->priv; + + if (wl->wlc) { + wiphy_rfkill_set_hw_state(wl->pub->ieee_hw->wiphy, false); + wiphy_rfkill_stop_polling(wl->pub->ieee_hw->wiphy); + ieee80211_unregister_hw(hw); + } + + brcms_free(wl); + + bcma_set_drvdata(pdev, NULL); + ieee80211_free_hw(hw); + } + + /* + * Precondition: Since this function is called in brcms_pci_probe() context, + * no locking is required. + */ + static void brcms_release_fw(struct brcms_info *wl) + { + int i; + for (i = 0; i < MAX_FW_IMAGES; i++) { + release_firmware(wl->fw.fw_bin[i]); + release_firmware(wl->fw.fw_hdr[i]); + } + } + + /* + * Precondition: Since this function is called in brcms_pci_probe() context, + * no locking is required. + */ + static int brcms_request_fw(struct brcms_info *wl, struct bcma_device *pdev) + { + int status; + struct device *device = &pdev->dev; + char fw_name[100]; + int i; + + memset(&wl->fw, 0, sizeof(struct brcms_firmware)); + for (i = 0; i < MAX_FW_IMAGES; i++) { + if (brcms_firmwares[i] == NULL) + break; + sprintf(fw_name, "%s-%d.fw", brcms_firmwares[i], + UCODE_LOADER_API_VER); + status = request_firmware(&wl->fw.fw_bin[i], fw_name, device); + if (status) { + wiphy_err(wl->wiphy, "%s: fail to load firmware %s\n", + KBUILD_MODNAME, fw_name); + return status; + } + sprintf(fw_name, "%s_hdr-%d.fw", brcms_firmwares[i], + UCODE_LOADER_API_VER); + status = request_firmware(&wl->fw.fw_hdr[i], fw_name, device); + if (status) { + wiphy_err(wl->wiphy, "%s: fail to load firmware %s\n", + KBUILD_MODNAME, fw_name); + return status; + } + wl->fw.hdr_num_entries[i] = + wl->fw.fw_hdr[i]->size / (sizeof(struct firmware_hdr)); + } + wl->fw.fw_cnt = i; + status = brcms_ucode_data_init(wl, &wl->ucode); + brcms_release_fw(wl); + return status; + } + static void brcms_ops_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control, struct sk_buff *skb) @@@ -308,6 -430,14 +432,14 @@@ static int brcms_ops_start(struct ieee8 if (!blocked) wiphy_rfkill_stop_polling(wl->pub->ieee_hw->wiphy);

+ if (!wl->ucode.bcm43xx_bomminor) { + err = brcms_request_fw(wl, wl->wlc->hw->d11core); + if (err) { + brcms_remove(wl->wlc->hw->d11core); + return -ENOENT; + } + } + spin_lock_bh(&wl->lock); /* avoid acknowledging frames before a non-monitor device is added */ wl->mute_tx = true; @@@ -357,26 -487,18 +489,26 @@@ brcms_ops_add_interface(struct ieee8021 { struct brcms_info *wl = hw->priv;

- /* Just STA for now */ - if (vif->type != NL80211_IFTYPE_STATION) { + /* Just STA, AP and ADHOC for now */ + if (vif->type != NL80211_IFTYPE_STATION && + vif->type != NL80211_IFTYPE_AP && + vif->type != NL80211_IFTYPE_ADHOC) { brcms_err(wl->wlc->hw->d11core, - "%s: Attempt to add type %d, only STA for now\n", + "%s: Attempt to add type %d, only STA, AP and AdHoc for now\n", __func__, vif->type); return -EOPNOTSUPP; }

spin_lock_bh(&wl->lock); - memcpy(wl->pub->cur_etheraddr, vif->addr, sizeof(vif->addr)); wl->mute_tx = false; brcms_c_mute(wl->wlc, false); + if (vif->type == NL80211_IFTYPE_STATION) + brcms_c_start_station(wl->wlc, vif->addr); + else if (vif->type == NL80211_IFTYPE_AP) + brcms_c_start_ap(wl->wlc, vif->addr, vif->bss_conf.bssid, + vif->bss_conf.ssid, vif->bss_conf.ssid_len); + else if (vif->type == NL80211_IFTYPE_ADHOC) + brcms_c_start_adhoc(wl->wlc, vif->addr); spin_unlock_bh(&wl->lock);

return 0; @@@ -528,43 -650,14 +660,43 @@@ brcms_ops_bss_info_changed(struct ieee8 brcms_c_set_addrmatch(wl->wlc, RCM_BSSID_OFFSET, info->bssid); spin_unlock_bh(&wl->lock); } - if (changed & BSS_CHANGED_BEACON) + if (changed & BSS_CHANGED_SSID) { + /* BSSID changed, for whatever reason (IBSS and managed mode) */ + spin_lock_bh(&wl->lock); + brcms_c_set_ssid(wl->wlc, info->ssid, info->ssid_len); + spin_unlock_bh(&wl->lock); + } + if (changed & BSS_CHANGED_BEACON) { /* Beacon data changed, retrieve new beacon (beaconing modes) */ - brcms_err(core, "%s: beacon changed\n", __func__); + struct sk_buff *beacon; + u16 tim_offset = 0; + + spin_lock_bh(&wl->lock); + beacon = ieee80211_beacon_get_tim(hw, vif, &tim_offset, NULL); + brcms_c_set_new_beacon(wl->wlc, beacon, tim_offset, + info->dtim_period); + spin_unlock_bh(&wl->lock); + } + + if (changed & BSS_CHANGED_AP_PROBE_RESP) { + struct sk_buff *probe_resp; + + spin_lock_bh(&wl->lock); + probe_resp = ieee80211_proberesp_get(hw, vif); + brcms_c_set_new_probe_resp(wl->wlc, probe_resp); + spin_unlock_bh(&wl->lock); + }

if (changed & BSS_CHANGED_BEACON_ENABLED) { /* Beaconing should be enabled/disabled (beaconing modes) */ brcms_err(core, "%s: Beacon enabled: %s\n", __func__, info->enable_beacon ? "true" : "false"); + if (info->enable_beacon && + hw->wiphy->flags & WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD) { + brcms_c_enable_probe_resp(wl->wlc, true); + } else { + brcms_c_enable_probe_resp(wl->wlc, false); + } }

if (changed & BSS_CHANGED_CQM) { @@@ -762,7 -855,7 +894,7 @@@ static bool brcms_tx_flush_completed(st return result; }

-static void brcms_ops_flush(struct ieee80211_hw *hw, bool drop) +static void brcms_ops_flush(struct ieee80211_hw *hw, u32 queues, bool drop) { struct brcms_info *wl = hw->priv; int ret; @@@ -777,28 -870,6 +909,28 @@@ "ret=%d\n", jiffies_to_msecs(ret)); }

+static u64 brcms_ops_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) +{ + struct brcms_info *wl = hw->priv; + u64 tsf; + + spin_lock_bh(&wl->lock); + tsf = brcms_c_tsf_get(wl->wlc); + spin_unlock_bh(&wl->lock); + + return tsf; +} + +static void brcms_ops_set_tsf(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, u64 tsf) +{ + struct brcms_info *wl = hw->priv; + + spin_lock_bh(&wl->lock); + brcms_c_tsf_set(wl->wlc, tsf); + spin_unlock_bh(&wl->lock); +} + static const struct ieee80211_ops brcms_ops = { .tx = brcms_ops_tx, .start = brcms_ops_start, @@@ -815,8 -886,6 +947,8 @@@ .ampdu_action = brcms_ops_ampdu_action, .rfkill_poll = brcms_ops_rfkill_poll, .flush = brcms_ops_flush, + .get_tsf = brcms_ops_get_tsf, + .set_tsf = brcms_ops_set_tsf, };

void brcms_dpc(unsigned long data) @@@ -856,129 -925,6 +988,6 @@@ wake_up(&wl->tx_flush_wq); }

- /* - * Precondition: Since this function is called in brcms_pci_probe() context, - * no locking is required. - */ - static int brcms_request_fw(struct brcms_info *wl, struct bcma_device *pdev) - { - int status; - struct device *device = &pdev->dev; - char fw_name[100]; - int i; - - memset(&wl->fw, 0, sizeof(struct brcms_firmware)); - for (i = 0; i < MAX_FW_IMAGES; i++) { - if (brcms_firmwares[i] == NULL) - break; - sprintf(fw_name, "%s-%d.fw", brcms_firmwares[i], - UCODE_LOADER_API_VER); - status = request_firmware(&wl->fw.fw_bin[i], fw_name, device); - if (status) { - wiphy_err(wl->wiphy, "%s: fail to load firmware %s\n", - KBUILD_MODNAME, fw_name); - return status; - } - sprintf(fw_name, "%s_hdr-%d.fw", brcms_firmwares[i], - UCODE_LOADER_API_VER); - status = request_firmware(&wl->fw.fw_hdr[i], fw_name, device); - if (status) { - wiphy_err(wl->wiphy, "%s: fail to load firmware %s\n", - KBUILD_MODNAME, fw_name); - return status; - } - wl->fw.hdr_num_entries[i] = - wl->fw.fw_hdr[i]->size / (sizeof(struct firmware_hdr)); - } - wl->fw.fw_cnt = i; - return brcms_ucode_data_init(wl, &wl->ucode); - } - - /* - * Precondition: Since this function is called in brcms_pci_probe() context, - * no locking is required. - */ - static void brcms_release_fw(struct brcms_info *wl) - { - int i; - for (i = 0; i < MAX_FW_IMAGES; i++) { - release_firmware(wl->fw.fw_bin[i]); - release_firmware(wl->fw.fw_hdr[i]); - } - } - - /** - * This function frees the WL per-device resources. - * - * This function frees resources owned by the WL device pointed to - * by the wl parameter. - * - * precondition: can both be called locked and unlocked - * - */ - static void brcms_free(struct brcms_info *wl) - { - struct brcms_timer *t, *next; - - /* free ucode data */ - if (wl->fw.fw_cnt) - brcms_ucode_data_free(&wl->ucode); - if (wl->irq) - free_irq(wl->irq, wl); - - /* kill dpc */ - tasklet_kill(&wl->tasklet); - - if (wl->pub) { - brcms_debugfs_detach(wl->pub); - brcms_c_module_unregister(wl->pub, "linux", wl); - } - - /* free common resources */ - if (wl->wlc) { - brcms_c_detach(wl->wlc); - wl->wlc = NULL; - wl->pub = NULL; - } - - /* virtual interface deletion is deferred so we cannot spinwait */ - - /* wait for all pending callbacks to complete */ - while (atomic_read(&wl->callbacks) > 0) - schedule(); - - /* free timers */ - for (t = wl->timers; t; t = next) { - next = t->next; - #ifdef DEBUG - kfree(t->name); - #endif - kfree(t); - } - } - - /* - * called from both kernel as from this kernel module (error flow on attach) - * precondition: perimeter lock is not acquired. - */ - static void brcms_remove(struct bcma_device *pdev) - { - struct ieee80211_hw *hw = bcma_get_drvdata(pdev); - struct brcms_info *wl = hw->priv; - - if (wl->wlc) { - brcms_led_unregister(wl); - wiphy_rfkill_set_hw_state(wl->pub->ieee_hw->wiphy, false); - wiphy_rfkill_stop_polling(wl->pub->ieee_hw->wiphy); - ieee80211_unregister_hw(hw); - } - - brcms_free(wl); - - bcma_set_drvdata(pdev, NULL); - ieee80211_free_hw(hw); - } - static irqreturn_t brcms_isr(int irq, void *dev_id) { struct brcms_info *wl; @@@ -1058,16 -1004,7 +1067,16 @@@ static int ieee_hw_init(struct ieee8021

/* channel change time is dependent on chip and band */ hw->channel_change_time = 7 * 1000; - hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION); + hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_AP) | + BIT(NL80211_IFTYPE_ADHOC); + + /* + * deactivate sending probe responses by ucude, because this will + * cause problems when WPS is used. + * + * hw->wiphy->flags |= WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD; + */

hw->rate_control_algorithm = "minstrel_ht";

@@@ -1120,18 -1057,8 +1129,8 @@@ static struct brcms_info *brcms_attach( spin_lock_init(&wl->lock); spin_lock_init(&wl->isr_lock);

- /* prepare ucode */ - if (brcms_request_fw(wl, pdev) < 0) { - wiphy_err(wl->wiphy, "%s: Failed to find firmware usually in " - "%s\n", KBUILD_MODNAME, "/lib/firmware/brcm"); - brcms_release_fw(wl); - brcms_remove(pdev); - return NULL; - } - /* common load-time initialization */ wl->wlc = brcms_c_attach((void *)wl, pdev, unit, false, &err); - brcms_release_fw(wl); if (!wl->wlc) { wiphy_err(wl->wiphy, "%s: attach() failed with code %d\n", KBUILD_MODNAME, err); @@@ -1224,8 -1151,6 +1223,8 @@@ static int brcms_bcma_probe(struct bcma pr_err("%s: brcms_attach failed!\n", __func__); return -ENODEV; } + brcms_led_register(wl); + return 0; }

diff --combined drivers/s390/net/qeth_core.h index ab4d286,6ccb745..c4f392d --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@@ -769,6 -769,7 +769,7 @@@ struct qeth_card unsigned long thread_start_mask; unsigned long thread_allowed_mask; unsigned long thread_running_mask; + struct task_struct *recovery_task; spinlock_t ip_lock; struct list_head ip_list; struct list_head *ip_tbd_list; @@@ -862,6 -863,8 +863,8 @@@ extern struct qeth_card_list_struct qet extern struct kmem_cache *qeth_core_header_cache; extern struct qeth_dbf_info qeth_dbf[QETH_DBF_INFOS];

+ void qeth_set_recovery_task(struct qeth_card *); + void qeth_clear_recovery_task(struct qeth_card *); void qeth_set_allowed_threads(struct qeth_card *, unsigned long , int); int qeth_threads_running(struct qeth_card *, unsigned long); int qeth_wait_for_threads(struct qeth_card *, unsigned long); @@@ -915,7 -918,7 +918,7 @@@ int qeth_send_control_data(struct qeth_ int (*reply_cb)(struct qeth_card *, struct qeth_reply*, unsigned long), void *reply_param); int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int); -int qeth_get_elements_no(struct qeth_card *, void *, struct sk_buff *, int); +int qeth_get_elements_no(struct qeth_card *, struct sk_buff *, int); int qeth_get_elements_for_frags(struct sk_buff *); int qeth_do_send_packet_fast(struct qeth_card *, struct qeth_qdio_out_q *, struct sk_buff *, struct qeth_hdr *, int, int, int); @@@ -929,7 -932,7 +932,7 @@@ void qeth_core_get_drvinfo(struct net_d void qeth_dbf_longtext(debug_info_t *id, int level, char *text, ...); int qeth_core_ethtool_get_settings(struct net_device *, struct ethtool_cmd *); int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback); -int qeth_hdr_chk_and_bounce(struct sk_buff *, int); +int qeth_hdr_chk_and_bounce(struct sk_buff *, struct qeth_hdr **, int); int qeth_configure_cq(struct qeth_card *, enum qeth_cq); int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action); int qeth_query_ipassists(struct qeth_card *, enum qeth_prot_versions prot); diff --combined drivers/s390/net/qeth_core_main.c index a86ce07,451f920..6cd0fc1 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@@ -177,6 -177,23 +177,23 @@@ const char *qeth_get_cardname_short(str return "n/a"; }

+ void qeth_set_recovery_task(struct qeth_card *card) + { + card->recovery_task = current; + } + EXPORT_SYMBOL_GPL(qeth_set_recovery_task); + + void qeth_clear_recovery_task(struct qeth_card *card) + { + card->recovery_task = NULL; + } + EXPORT_SYMBOL_GPL(qeth_clear_recovery_task); + + static bool qeth_is_recovery_task(const struct qeth_card *card) + { + return card->recovery_task == current; + } + void qeth_set_allowed_threads(struct qeth_card *card, unsigned long threads, int clear_start_mask) { @@@ -205,6 -222,8 +222,8 @@@ EXPORT_SYMBOL_GPL(qeth_threads_running)

int qeth_wait_for_threads(struct qeth_card *card, unsigned long threads) { + if (qeth_is_recovery_task(card)) + return 0; return wait_event_interruptible(card->wait_q, qeth_threads_running(card, threads) == 0); } @@@ -316,7 -335,7 +335,7 @@@ static inline int qeth_alloc_cq(struct

card->qdio.no_in_queues = 2;

- card->qdio.out_bufstates = (struct qdio_outbuf_state *) + card->qdio.out_bufstates = kzalloc(card->qdio.no_out_queues * QDIO_MAX_BUFFERS_PER_Q * sizeof(struct qdio_outbuf_state), GFP_KERNEL); @@@ -3698,7 -3717,7 +3717,7 @@@ int qeth_get_elements_for_frags(struct } EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);

-int qeth_get_elements_no(struct qeth_card *card, void *hdr, +int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb, int elems) { int dlen = skb->len - skb->data_len; @@@ -3717,7 -3736,7 +3736,7 @@@ } EXPORT_SYMBOL_GPL(qeth_get_elements_no);

-int qeth_hdr_chk_and_bounce(struct sk_buff *skb, int len) +int qeth_hdr_chk_and_bounce(struct sk_buff *skb, struct qeth_hdr **hdr, int len) { int hroom, inpage, rest;

@@@ -3730,8 -3749,6 +3749,8 @@@ return 1; memmove(skb->data - rest, skb->data, skb->len - skb->data_len); skb->data -= rest; + skb->tail -= rest; + *hdr = (struct qeth_hdr *)skb->data; QETH_DBF_MESSAGE(2, "skb bounce len: %d rest: %d\n", len, rest); } return 0; diff --combined drivers/s390/net/qeth_l2_main.c index 2d42541,155b101..ec8ccda --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@@ -302,8 -302,7 +302,8 @@@ static void qeth_l2_process_vlans(struc spin_unlock_bh(&card->vlanlock); }

-static int qeth_l2_vlan_rx_add_vid(struct net_device *dev, unsigned short vid) +static int qeth_l2_vlan_rx_add_vid(struct net_device *dev, + __be16 proto, u16 vid) { struct qeth_card *card = dev->ml_priv; struct qeth_vlan_vid *id; @@@ -332,8 -331,7 +332,8 @@@ return 0; }

-static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid) +static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, + __be16 proto, u16 vid) { struct qeth_vlan_vid *id, *tmpid = NULL; struct qeth_card *card = dev->ml_priv; @@@ -773,7 -771,8 +773,7 @@@ static int qeth_l2_hard_start_xmit(stru } }

- elements = qeth_get_elements_no(card, (void *)hdr, new_skb, - elements_needed); + elements = qeth_get_elements_no(card, new_skb, elements_needed); if (!elements) { if (data_offset >= 0) kmem_cache_free(qeth_core_header_cache, hdr); @@@ -781,7 -780,7 +781,7 @@@ }

if (card->info.type != QETH_CARD_TYPE_IQD) { - if (qeth_hdr_chk_and_bounce(new_skb, + if (qeth_hdr_chk_and_bounce(new_skb, &hdr, sizeof(struct qeth_hdr_layer2))) goto tx_drop; rc = qeth_do_send_packet(card, queue, new_skb, hdr, @@@ -960,7 -959,7 +960,7 @@@ static int qeth_l2_setup_netdev(struct SET_ETHTOOL_OPS(card->dev, &qeth_l2_ethtool_ops); else SET_ETHTOOL_OPS(card->dev, &qeth_l2_osn_ops); - card->dev->features |= NETIF_F_HW_VLAN_FILTER; + card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; card->info.broadcast_capable = 1; qeth_l2_request_initial_mac(card); SET_NETDEV_DEV(card->dev, &card->gdev->dev); @@@ -1144,6 -1143,7 +1144,7 @@@ static int qeth_l2_recover(void *ptr QETH_CARD_TEXT(card, 2, "recover2"); dev_warn(&card->gdev->dev, "A recovery process has been started for the device\n"); + qeth_set_recovery_task(card); __qeth_l2_set_offline(card->gdev, 1); rc = __qeth_l2_set_online(card->gdev, 1); if (!rc) @@@ -1154,6 -1154,7 +1155,7 @@@ dev_warn(&card->gdev->dev, "The qeth device driver " "failed to recover an error on the device\n"); } + qeth_clear_recovery_task(card); qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD); qeth_clear_thread_running_bit(card, QETH_RECOVER_THREAD); return 0; diff --combined drivers/s390/net/qeth_l3_main.c index 449676e,1f7edf1..c1b0b27 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@@ -1659,8 -1659,7 +1659,8 @@@ static void qeth_l3_add_vlan_mc(struct for_each_set_bit(vid, card->active_vlans, VLAN_N_VID) { struct net_device *netdev;

- netdev = __vlan_find_dev_deep(card->dev, vid); + netdev = __vlan_find_dev_deep(card->dev, htons(ETH_P_8021Q), + vid); if (netdev == NULL || !(netdev->flags & IFF_UP)) continue; @@@ -1721,8 -1720,7 +1721,8 @@@ static void qeth_l3_add_vlan_mc6(struc for_each_set_bit(vid, card->active_vlans, VLAN_N_VID) { struct net_device *netdev;

- netdev = __vlan_find_dev_deep(card->dev, vid); + netdev = __vlan_find_dev_deep(card->dev, htons(ETH_P_8021Q), + vid); if (netdev == NULL || !(netdev->flags & IFF_UP)) continue; @@@ -1766,7 -1764,7 +1766,7 @@@ static void qeth_l3_free_vlan_addresses

QETH_CARD_TEXT(card, 4, "frvaddr4");

- netdev = __vlan_find_dev_deep(card->dev, vid); + netdev = __vlan_find_dev_deep(card->dev, htons(ETH_P_8021Q), vid); if (!netdev) return; in_dev = in_dev_get(netdev); @@@ -1796,7 -1794,7 +1796,7 @@@ static void qeth_l3_free_vlan_addresses

QETH_CARD_TEXT(card, 4, "frvaddr6");

- netdev = __vlan_find_dev_deep(card->dev, vid); + netdev = __vlan_find_dev_deep(card->dev, htons(ETH_P_8021Q), vid); if (!netdev) return; in6_dev = in6_dev_get(netdev); @@@ -1826,8 -1824,7 +1826,8 @@@ static void qeth_l3_free_vlan_addresses rcu_read_unlock(); }

-static int qeth_l3_vlan_rx_add_vid(struct net_device *dev, unsigned short vid) +static int qeth_l3_vlan_rx_add_vid(struct net_device *dev, + __be16 proto, u16 vid) { struct qeth_card *card = dev->ml_priv;

@@@ -1835,8 -1832,7 +1835,8 @@@ return 0; }

-static int qeth_l3_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid) +static int qeth_l3_vlan_rx_kill_vid(struct net_device *dev, + __be16 proto, u16 vid) { struct qeth_card *card = dev->ml_priv; unsigned long flags; @@@ -1979,8 -1975,7 +1979,8 @@@ static int qeth_l3_process_inbound_buff &vlan_tag); len = skb->len; if (is_vlan && !card->options.sniffer) - __vlan_hwaccel_put_tag(skb, vlan_tag); + __vlan_hwaccel_put_tag(skb, + htons(ETH_P_8021Q), vlan_tag); napi_gro_receive(&card->napi, skb); } break; @@@ -2089,8 -2084,7 +2089,8 @@@ static int qeth_l3_verify_vlan_dev(stru struct net_device *netdev;

rcu_read_lock(); - netdev = __vlan_find_dev_deep(card->dev, vid); + netdev = __vlan_find_dev_deep(card->dev, htons(ETH_P_8021Q), + vid); rcu_read_unlock(); if (netdev == dev) { rc = QETH_VLAN_CARD; @@@ -3037,7 -3031,8 +3037,7 @@@ static int qeth_l3_hard_start_xmit(stru qeth_l3_hdr_csum(card, hdr, new_skb); }

- elems = qeth_get_elements_no(card, (void *)hdr, new_skb, - elements_needed); + elems = qeth_get_elements_no(card, new_skb, elements_needed); if (!elems) { if (data_offset >= 0) kmem_cache_free(qeth_core_header_cache, hdr); @@@ -3055,7 -3050,7 +3055,7 @@@ else len = sizeof(struct qeth_hdr_layer3);

- if (qeth_hdr_chk_and_bounce(new_skb, len)) + if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len)) goto tx_drop; rc = qeth_do_send_packet(card, queue, new_skb, hdr, elements_needed); @@@ -3299,9 -3294,9 +3299,9 @@@ static int qeth_l3_setup_netdev(struct card->dev->watchdog_timeo = QETH_TX_TIMEOUT; card->dev->mtu = card->info.initial_mtu; SET_ETHTOOL_OPS(card->dev, &qeth_l3_ethtool_ops); - card->dev->features |= NETIF_F_HW_VLAN_TX | - NETIF_F_HW_VLAN_RX | - NETIF_F_HW_VLAN_FILTER; + card->dev->features |= NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER; card->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; card->dev->gso_max_size = 15 * PAGE_SIZE;

@@@ -3520,6 -3515,7 +3520,7 @@@ static int qeth_l3_recover(void *ptr QETH_CARD_TEXT(card, 2, "recover2"); dev_warn(&card->gdev->dev, "A recovery process has been started for the device\n"); + qeth_set_recovery_task(card); __qeth_l3_set_offline(card->gdev, 1); rc = __qeth_l3_set_online(card->gdev, 1); if (!rc) @@@ -3530,6 -3526,7 +3531,7 @@@ dev_warn(&card->gdev->dev, "The qeth device driver " "failed to recover an error on the device\n"); } + qeth_clear_recovery_task(card); qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD); qeth_clear_thread_running_bit(card, QETH_RECOVER_THREAD); return 0; diff --combined drivers/ssb/driver_chipcommon_pmu.c index 791da2c,7b0bce9..23c5dbf --- a/drivers/ssb/driver_chipcommon_pmu.c +++ b/drivers/ssb/driver_chipcommon_pmu.c @@@ -110,8 -110,8 +110,8 @@@ static void ssb_pmu0_pllinit_r0(struct return; }

- ssb_printk(KERN_INFO PFX "Programming PLL to %u.%03u MHz\n", - (crystalfreq / 1000), (crystalfreq % 1000)); + ssb_info("Programming PLL to %u.%03u MHz\n", + crystalfreq / 1000, crystalfreq % 1000);

/* First turn the PLL off. */ switch (bus->chip_id) { @@@ -138,7 -138,7 +138,7 @@@ } tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST); if (tmp & SSB_CHIPCO_CLKCTLST_HAVEHT) - ssb_printk(KERN_EMERG PFX "Failed to turn the PLL off!\n"); + ssb_emerg("Failed to turn the PLL off!\n");

/* Set PDIV in PLL control 0. */ pllctl = ssb_chipco_pll_read(cc, SSB_PMU0_PLLCTL0); @@@ -249,8 -249,8 +249,8 @@@ static void ssb_pmu1_pllinit_r0(struct return; }

- ssb_printk(KERN_INFO PFX "Programming PLL to %u.%03u MHz\n", - (crystalfreq / 1000), (crystalfreq % 1000)); + ssb_info("Programming PLL to %u.%03u MHz\n", + crystalfreq / 1000, crystalfreq % 1000);

/* First turn the PLL off. */ switch (bus->chip_id) { @@@ -275,7 -275,7 +275,7 @@@ } tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST); if (tmp & SSB_CHIPCO_CLKCTLST_HAVEHT) - ssb_printk(KERN_EMERG PFX "Failed to turn the PLL off!\n"); + ssb_emerg("Failed to turn the PLL off!\n");

/* Set p1div and p2div. */ pllctl = ssb_chipco_pll_read(cc, SSB_PMU1_PLLCTL0); @@@ -349,8 -349,9 +349,8 @@@ static void ssb_pmu_pll_init(struct ssb case 43222: break; default: - ssb_printk(KERN_ERR PFX - "ERROR: PLL init unknown for device %04X\n", - bus->chip_id); + ssb_err("ERROR: PLL init unknown for device %04X\n", + bus->chip_id); } }

@@@ -471,8 -472,9 +471,8 @@@ static void ssb_pmu_resources_init(stru max_msk = 0xFFFFF; break; default: - ssb_printk(KERN_ERR PFX - "ERROR: PMU resource config unknown for device %04X\n", - bus->chip_id); + ssb_err("ERROR: PMU resource config unknown for device %04X\n", + bus->chip_id); }

if (updown_tab) { @@@ -524,8 -526,8 +524,8 @@@ void ssb_pmu_init(struct ssb_chipcommo pmucap = chipco_read32(cc, SSB_CHIPCO_PMU_CAP); cc->pmu.rev = (pmucap & SSB_CHIPCO_PMU_CAP_REVISION);

- ssb_dprintk(KERN_DEBUG PFX "Found rev %u PMU (capabilities 0x%08X)\n", - cc->pmu.rev, pmucap); + ssb_dbg("Found rev %u PMU (capabilities 0x%08X)\n", + cc->pmu.rev, pmucap);

if (cc->pmu.rev == 1) chipco_mask32(cc, SSB_CHIPCO_PMU_CTL, @@@ -636,8 -638,9 +636,8 @@@ u32 ssb_pmu_get_alp_clock(struct ssb_ch case 0x5354: ssb_pmu_get_alp_clock_clk0(cc); default: - ssb_printk(KERN_ERR PFX - "ERROR: PMU alp clock unknown for device %04X\n", - bus->chip_id); + ssb_err("ERROR: PMU alp clock unknown for device %04X\n", + bus->chip_id); return 0; } } @@@ -651,8 -654,9 +651,8 @@@ u32 ssb_pmu_get_cpu_clock(struct ssb_ch /* 5354 chip uses a non programmable PLL of frequency 240MHz */ return 240000000; default: - ssb_printk(KERN_ERR PFX - "ERROR: PMU cpu clock unknown for device %04X\n", - bus->chip_id); + ssb_err("ERROR: PMU cpu clock unknown for device %04X\n", + bus->chip_id); return 0; } } @@@ -665,8 -669,38 +665,37 @@@ u32 ssb_pmu_get_controlclock(struct ssb case 0x5354: return 120000000; default: - ssb_printk(KERN_ERR PFX - "ERROR: PMU controlclock unknown for device %04X\n", - bus->chip_id); + ssb_err("ERROR: PMU controlclock unknown for device %04X\n", + bus->chip_id); return 0; } } + + void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid) + { + u32 pmu_ctl = 0; + + switch (cc->dev->bus->chip_id) { + case 0x4322: + ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL0, 0x11100070); + ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL1, 0x1014140a); + ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL5, 0x88888854); + if (spuravoid == 1) + ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL2, 0x05201828); + else + ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL2, 0x05001828); + pmu_ctl = SSB_CHIPCO_PMU_CTL_PLL_UPD; + break; + case 43222: + /* TODO: BCM43222 requires updating PLLs too */ + return; + default: + ssb_printk(KERN_ERR PFX + "Unknown spuravoidance settings for chip 0x%04X, not changing PLL\n", + cc->dev->bus->chip_id); + return; + } + + chipco_set32(cc, SSB_CHIPCO_PMU_CTL, pmu_ctl); + } + EXPORT_SYMBOL_GPL(ssb_pmu_spuravoid_pllupdate); diff --combined include/net/scm.h index 5a4c6a9,b117081..8de2d37 --- a/include/net/scm.h +++ b/include/net/scm.h @@@ -26,6 -26,7 +26,6 @@@ struct scm_fp_list

struct scm_cookie { struct pid *pid; /* Skb credentials */ - const struct cred *cred; struct scm_fp_list *fp; /* Passed files */ struct scm_creds creds; /* Skb credentials */ #ifdef CONFIG_SECURITY_NETWORK @@@ -50,18 -51,23 +50,18 @@@ static __inline__ void unix_get_peersec #endif /* CONFIG_SECURITY_NETWORK */

static __inline__ void scm_set_cred(struct scm_cookie *scm, - struct pid *pid, const struct cred *cred) + struct pid *pid, kuid_t uid, kgid_t gid) { scm->pid = get_pid(pid); - scm->cred = cred ? get_cred(cred) : NULL; scm->creds.pid = pid_vnr(pid); - scm->creds.uid = cred ? cred->uid : INVALID_UID; - scm->creds.gid = cred ? cred->gid : INVALID_GID; + scm->creds.uid = uid; + scm->creds.gid = gid; }

static __inline__ void scm_destroy_cred(struct scm_cookie *scm) { put_pid(scm->pid); scm->pid = NULL; - - if (scm->cred) - put_cred(scm->cred); - scm->cred = NULL; }

static __inline__ void scm_destroy(struct scm_cookie *scm) @@@ -75,10 -81,8 +75,10 @@@ static __inline__ int scm_send(struct s struct scm_cookie *scm, bool forcecreds) { memset(scm, 0, sizeof(*scm)); + scm->creds.uid = INVALID_UID; + scm->creds.gid = INVALID_GID; if (forcecreds) - scm_set_cred(scm, task_tgid(current), current_euid(), current_egid()); - scm_set_cred(scm, task_tgid(current), current_cred()); ++ scm_set_cred(scm, task_tgid(current), current_uid(), current_gid()); unix_get_peersec_dgram(sock, scm); if (msg->msg_controllen <= 0) return 0; diff --combined kernel/signal.c index 497330e,598dc06..06ff776 --- a/kernel/signal.c +++ b/kernel/signal.c @@@ -32,7 -32,6 +32,7 @@@ #include <linux/user_namespace.h> #include <linux/uprobes.h> #include <linux/compat.h> +#include <linux/cn_proc.h> #define CREATE_TRACE_POINTS #include <trace/events/signal.h>

@@@ -2351,7 -2350,6 +2351,7 @@@ relock if (sig_kernel_coredump(signr)) { if (print_fatal_signals) print_fatal_signal(info->si_signo); + proc_coredump_connector(current); /* * If it was able to dump core, this kills all * other threads in the group and synchronizes with @@@ -2950,7 -2948,7 +2950,7 @@@ do_send_specific(pid_t tgid, pid_t pid

static int do_tkill(pid_t tgid, pid_t pid, int sig) { - struct siginfo info; + struct siginfo info = {};

info.si_signo = sig; info.si_errno = 0; diff --combined net/batman-adv/main.c index 6277735,fa563e4..3e30a0f --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@@ -35,7 -35,6 +35,7 @@@ #include "vis.h" #include "hash.h" #include "bat_algo.h" +#include "network-coding.h"

/* List manipulations on hardif_list have to be rtnl_lock()'ed, @@@ -71,7 -70,6 +71,7 @@@ static int __init batadv_init(void batadv_debugfs_init();

register_netdevice_notifier(&batadv_hard_if_notifier); + rtnl_link_register(&batadv_link_ops);

pr_info("B.A.T.M.A.N. advanced %s (compatibility version %i) loaded\n", BATADV_SOURCE_VERSION, BATADV_COMPAT_VERSION); @@@ -82,7 -80,6 +82,7 @@@ static void __exit batadv_exit(void) { batadv_debugfs_destroy(); + rtnl_link_unregister(&batadv_link_ops); unregister_netdevice_notifier(&batadv_hard_if_notifier); batadv_hardif_remove_interfaces();

@@@ -138,10 -135,6 +138,10 @@@ int batadv_mesh_init(struct net_device if (ret < 0) goto err;

+ ret = batadv_nc_init(bat_priv); + if (ret < 0) + goto err; + atomic_set(&bat_priv->gw.reselect, 0); atomic_set(&bat_priv->mesh_state, BATADV_MESH_ACTIVE);

@@@ -164,7 -157,6 +164,7 @@@ void batadv_mesh_free(struct net_devic

batadv_gw_node_purge(bat_priv); batadv_originator_free(bat_priv); + batadv_nc_free(bat_priv);

batadv_tt_free(bat_priv);

@@@ -177,7 -169,7 +177,13 @@@ atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE); }

- int batadv_is_my_mac(const uint8_t *addr) ++/** ++ * batadv_is_my_mac - check if the given mac address belongs to any of the real ++ * interfaces in the current mesh ++ * @bat_priv: the bat priv with all the soft interface information ++ * @addr: the address to check ++ */ + int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr) { const struct batadv_hard_iface *hard_iface;

@@@ -186,6 -178,9 +192,9 @@@ if (hard_iface->if_status != BATADV_IF_ACTIVE) continue;

+ if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + if (batadv_compare_eth(hard_iface->net_dev->dev_addr, addr)) { rcu_read_unlock(); return 1; @@@ -419,7 -414,7 +428,7 @@@ int batadv_algo_seq_print_text(struct s { struct batadv_algo_ops *bat_algo_ops;

- seq_printf(seq, "Available routing algorithms:\n"); + seq_puts(seq, "Available routing algorithms:\n");

hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) { seq_printf(seq, "%s\n", bat_algo_ops->name); diff --combined net/batman-adv/main.h index f90f5bc,d40910d..59a0d6a --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@@ -26,7 -26,7 +26,7 @@@ #define BATADV_DRIVER_DEVICE "batman-adv"

#ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2013.1.0" +#define BATADV_SOURCE_VERSION "2013.2.0" #endif

/* B.A.T.M.A.N. parameters */ @@@ -105,8 -105,6 +105,8 @@@ #define BATADV_RESET_PROTECTION_MS 30000 #define BATADV_EXPECTED_SEQNO_RANGE 65536

+#define BATADV_NC_NODE_TIMEOUT 10000 /* Milliseconds */ + enum batadv_mesh_state { BATADV_MESH_INACTIVE, BATADV_MESH_ACTIVE, @@@ -152,7 -150,6 +152,7 @@@ enum batadv_uev_type #include <linux/percpu.h> #include <linux/slab.h> #include <net/sock.h> /* struct sock */ +#include <net/rtnetlink.h> #include <linux/jiffies.h> #include <linux/seq_file.h> #include "types.h" @@@ -165,7 -162,7 +165,7 @@@ extern struct workqueue_struct *batadv_

int batadv_mesh_init(struct net_device *soft_iface); void batadv_mesh_free(struct net_device *soft_iface); - int batadv_is_my_mac(const uint8_t *addr); + int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_hard_iface * batadv_seq_print_text_primary_if_get(struct seq_file *seq); int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, @@@ -188,7 -185,6 +188,7 @@@ __be32 batadv_skb_crc32(struct sk_buff * @BATADV_DBG_TT: translation table messages * @BATADV_DBG_BLA: bridge loop avoidance messages * @BATADV_DBG_DAT: ARP snooping and DAT related messages + * @BATADV_DBG_NC: network coding related messages * @BATADV_DBG_ALL: the union of all the above log levels */ enum batadv_dbg_level { @@@ -197,8 -193,7 +197,8 @@@ BATADV_DBG_TT = BIT(2), BATADV_DBG_BLA = BIT(3), BATADV_DBG_DAT = BIT(4), - BATADV_DBG_ALL = 31, + BATADV_DBG_NC = BIT(5), + BATADV_DBG_ALL = 63, };

#ifdef CONFIG_BATMAN_ADV_DEBUG @@@ -303,10 -298,4 +303,10 @@@ static inline uint64_t batadv_sum_count return sum; }

+/* Define a macro to reach the control buffer of the skb. The members of the + * control buffer are defined in struct batadv_skb_cb in types.h. + * The macro is inspired by the similar macro TCP_SKB_CB() in tcp.h. + */ +#define BATADV_SKB_CB(__skb) ((struct batadv_skb_cb *)&((__skb)->cb[0])) + #endif /* _NET_BATMAN_ADV_MAIN_H_ */ diff --combined net/batman-adv/network-coding.c index 6b9a544,0000000..f7c5430 mode 100644,000000..100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@@ -1,1821 -1,0 +1,1822 @@@ +/* Copyright (C) 2012-2013 B.A.T.M.A.N. contributors: + * + * Martin Hundebøll, Jeppe Ledet-Pedersen + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA + */ + +#include <linux/debugfs.h> + +#include "main.h" +#include "hash.h" +#include "network-coding.h" +#include "send.h" +#include "originator.h" +#include "hard-interface.h" +#include "routing.h" + +static struct lock_class_key batadv_nc_coding_hash_lock_class_key; +static struct lock_class_key batadv_nc_decoding_hash_lock_class_key; + +static void batadv_nc_worker(struct work_struct *work); +static int batadv_nc_recv_coded_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if); + +/** + * batadv_nc_start_timer - initialise the nc periodic worker + * @bat_priv: the bat priv with all the soft interface information + */ +static void batadv_nc_start_timer(struct batadv_priv *bat_priv) +{ + queue_delayed_work(batadv_event_workqueue, &bat_priv->nc.work, + msecs_to_jiffies(10)); +} + +/** + * batadv_nc_init - initialise coding hash table and start house keeping + * @bat_priv: the bat priv with all the soft interface information + */ +int batadv_nc_init(struct batadv_priv *bat_priv) +{ + bat_priv->nc.timestamp_fwd_flush = jiffies; + bat_priv->nc.timestamp_sniffed_purge = jiffies; + + if (bat_priv->nc.coding_hash || bat_priv->nc.decoding_hash) + return 0; + + bat_priv->nc.coding_hash = batadv_hash_new(128); + if (!bat_priv->nc.coding_hash) + goto err; + + batadv_hash_set_lock_class(bat_priv->nc.coding_hash, + &batadv_nc_coding_hash_lock_class_key); + + bat_priv->nc.decoding_hash = batadv_hash_new(128); + if (!bat_priv->nc.decoding_hash) + goto err; + + batadv_hash_set_lock_class(bat_priv->nc.coding_hash, + &batadv_nc_decoding_hash_lock_class_key); + + /* Register our packet type */ + if (batadv_recv_handler_register(BATADV_CODED, + batadv_nc_recv_coded_packet) < 0) + goto err; + + INIT_DELAYED_WORK(&bat_priv->nc.work, batadv_nc_worker); + batadv_nc_start_timer(bat_priv); + + return 0; + +err: + return -ENOMEM; +} + +/** + * batadv_nc_init_bat_priv - initialise the nc specific bat_priv variables + * @bat_priv: the bat priv with all the soft interface information + */ +void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv) +{ + atomic_set(&bat_priv->network_coding, 1); + bat_priv->nc.min_tq = 200; + bat_priv->nc.max_fwd_delay = 10; + bat_priv->nc.max_buffer_time = 200; +} + +/** + * batadv_nc_init_orig - initialise the nc fields of an orig_node + * @orig_node: the orig_node which is going to be initialised + */ +void batadv_nc_init_orig(struct batadv_orig_node *orig_node) +{ + INIT_LIST_HEAD(&orig_node->in_coding_list); + INIT_LIST_HEAD(&orig_node->out_coding_list); + spin_lock_init(&orig_node->in_coding_list_lock); + spin_lock_init(&orig_node->out_coding_list_lock); +} + +/** + * batadv_nc_node_free_rcu - rcu callback to free an nc node and remove + * its refcount on the orig_node + * @rcu: rcu pointer of the nc node + */ +static void batadv_nc_node_free_rcu(struct rcu_head *rcu) +{ + struct batadv_nc_node *nc_node; + + nc_node = container_of(rcu, struct batadv_nc_node, rcu); + batadv_orig_node_free_ref(nc_node->orig_node); + kfree(nc_node); +} + +/** + * batadv_nc_node_free_ref - decrements the nc node refcounter and possibly + * frees it + * @nc_node: the nc node to free + */ +static void batadv_nc_node_free_ref(struct batadv_nc_node *nc_node) +{ + if (atomic_dec_and_test(&nc_node->refcount)) + call_rcu(&nc_node->rcu, batadv_nc_node_free_rcu); +} + +/** + * batadv_nc_path_free_ref - decrements the nc path refcounter and possibly + * frees it + * @nc_path: the nc node to free + */ +static void batadv_nc_path_free_ref(struct batadv_nc_path *nc_path) +{ + if (atomic_dec_and_test(&nc_path->refcount)) + kfree_rcu(nc_path, rcu); +} + +/** + * batadv_nc_packet_free - frees nc packet + * @nc_packet: the nc packet to free + */ +static void batadv_nc_packet_free(struct batadv_nc_packet *nc_packet) +{ + if (nc_packet->skb) + kfree_skb(nc_packet->skb); + + batadv_nc_path_free_ref(nc_packet->nc_path); + kfree(nc_packet); +} + +/** + * batadv_nc_to_purge_nc_node - checks whether an nc node has to be purged + * @bat_priv: the bat priv with all the soft interface information + * @nc_node: the nc node to check + * + * Returns true if the entry has to be purged now, false otherwise + */ +static bool batadv_nc_to_purge_nc_node(struct batadv_priv *bat_priv, + struct batadv_nc_node *nc_node) +{ + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) + return true; + + return batadv_has_timed_out(nc_node->last_seen, BATADV_NC_NODE_TIMEOUT); +} + +/** + * batadv_nc_to_purge_nc_path_coding - checks whether an nc path has timed out + * @bat_priv: the bat priv with all the soft interface information + * @nc_path: the nc path to check + * + * Returns true if the entry has to be purged now, false otherwise + */ +static bool batadv_nc_to_purge_nc_path_coding(struct batadv_priv *bat_priv, + struct batadv_nc_path *nc_path) +{ + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) + return true; + + /* purge the path when no packets has been added for 10 times the + * max_fwd_delay time + */ + return batadv_has_timed_out(nc_path->last_valid, + bat_priv->nc.max_fwd_delay * 10); +} + +/** + * batadv_nc_to_purge_nc_path_decoding - checks whether an nc path has timed out + * @bat_priv: the bat priv with all the soft interface information + * @nc_path: the nc path to check + * + * Returns true if the entry has to be purged now, false otherwise + */ +static bool batadv_nc_to_purge_nc_path_decoding(struct batadv_priv *bat_priv, + struct batadv_nc_path *nc_path) +{ + if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) + return true; + + /* purge the path when no packets has been added for 10 times the + * max_buffer time + */ + return batadv_has_timed_out(nc_path->last_valid, + bat_priv->nc.max_buffer_time*10); +} + +/** + * batadv_nc_purge_orig_nc_nodes - go through list of nc nodes and purge stale + * entries + * @bat_priv: the bat priv with all the soft interface information + * @list: list of nc nodes + * @lock: nc node list lock + * @to_purge: function in charge to decide whether an entry has to be purged or + * not. This function takes the nc node as argument and has to return + * a boolean value: true if the entry has to be deleted, false + * otherwise + */ +static void +batadv_nc_purge_orig_nc_nodes(struct batadv_priv *bat_priv, + struct list_head *list, + spinlock_t *lock, + bool (*to_purge)(struct batadv_priv *, + struct batadv_nc_node *)) +{ + struct batadv_nc_node *nc_node, *nc_node_tmp; + + /* For each nc_node in list */ + spin_lock_bh(lock); + list_for_each_entry_safe(nc_node, nc_node_tmp, list, list) { + /* if an helper function has been passed as parameter, + * ask it if the entry has to be purged or not + */ + if (to_purge && !to_purge(bat_priv, nc_node)) + continue; + + batadv_dbg(BATADV_DBG_NC, bat_priv, + "Removing nc_node %pM -> %pM\n", + nc_node->addr, nc_node->orig_node->orig); + list_del_rcu(&nc_node->list); + batadv_nc_node_free_ref(nc_node); + } + spin_unlock_bh(lock); +} + +/** + * batadv_nc_purge_orig - purges all nc node data attached of the given + * originator + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig_node with the nc node entries to be purged + * @to_purge: function in charge to decide whether an entry has to be purged or + * not. This function takes the nc node as argument and has to return + * a boolean value: true is the entry has to be deleted, false + * otherwise + */ +void batadv_nc_purge_orig(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + bool (*to_purge)(struct batadv_priv *, + struct batadv_nc_node *)) +{ + /* Check ingoing nc_node's of this orig_node */ + batadv_nc_purge_orig_nc_nodes(bat_priv, &orig_node->in_coding_list, + &orig_node->in_coding_list_lock, + to_purge); + + /* Check outgoing nc_node's of this orig_node */ + batadv_nc_purge_orig_nc_nodes(bat_priv, &orig_node->out_coding_list, + &orig_node->out_coding_list_lock, + to_purge); +} + +/** + * batadv_nc_purge_orig_hash - traverse entire originator hash to check if they + * have timed out nc nodes + * @bat_priv: the bat priv with all the soft interface information + */ +static void batadv_nc_purge_orig_hash(struct batadv_priv *bat_priv) +{ + struct batadv_hashtable *hash = bat_priv->orig_hash; + struct hlist_head *head; + struct batadv_orig_node *orig_node; + uint32_t i; + + if (!hash) + return; + + /* For each orig_node */ + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_node, head, hash_entry) + batadv_nc_purge_orig(bat_priv, orig_node, + batadv_nc_to_purge_nc_node); + rcu_read_unlock(); + } +} + +/** + * batadv_nc_purge_paths - traverse all nc paths part of the hash and remove + * unused ones + * @bat_priv: the bat priv with all the soft interface information + * @hash: hash table containing the nc paths to check + * @to_purge: function in charge to decide whether an entry has to be purged or + * not. This function takes the nc node as argument and has to return + * a boolean value: true is the entry has to be deleted, false + * otherwise + */ +static void batadv_nc_purge_paths(struct batadv_priv *bat_priv, + struct batadv_hashtable *hash, + bool (*to_purge)(struct batadv_priv *, + struct batadv_nc_path *)) +{ + struct hlist_head *head; + struct hlist_node *node_tmp; + struct batadv_nc_path *nc_path; + spinlock_t *lock; /* Protects lists in hash */ + uint32_t i; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + lock = &hash->list_locks[i]; + + /* For each nc_path in this bin */ + spin_lock_bh(lock); + hlist_for_each_entry_safe(nc_path, node_tmp, head, hash_entry) { + /* if an helper function has been passed as parameter, + * ask it if the entry has to be purged or not + */ + if (to_purge && !to_purge(bat_priv, nc_path)) + continue; + + /* purging an non-empty nc_path should never happen, but + * is observed under high CPU load. Delay the purging + * until next iteration to allow the packet_list to be + * emptied first. + */ + if (!unlikely(list_empty(&nc_path->packet_list))) { + net_ratelimited_function(printk, + KERN_WARNING + "Skipping free of non-empty nc_path (%pM -> %pM)!\n", + nc_path->prev_hop, + nc_path->next_hop); + continue; + } + + /* nc_path is unused, so remove it */ + batadv_dbg(BATADV_DBG_NC, bat_priv, + "Remove nc_path %pM -> %pM\n", + nc_path->prev_hop, nc_path->next_hop); + hlist_del_rcu(&nc_path->hash_entry); + batadv_nc_path_free_ref(nc_path); + } + spin_unlock_bh(lock); + } +} + +/** + * batadv_nc_hash_key_gen - computes the nc_path hash key + * @key: buffer to hold the final hash key + * @src: source ethernet mac address going into the hash key + * @dst: destination ethernet mac address going into the hash key + */ +static void batadv_nc_hash_key_gen(struct batadv_nc_path *key, const char *src, + const char *dst) +{ + memcpy(key->prev_hop, src, sizeof(key->prev_hop)); + memcpy(key->next_hop, dst, sizeof(key->next_hop)); +} + +/** + * batadv_nc_hash_choose - compute the hash value for an nc path + * @data: data to hash + * @size: size of the hash table + * + * Returns the selected index in the hash table for the given data. + */ +static uint32_t batadv_nc_hash_choose(const void *data, uint32_t size) +{ + const struct batadv_nc_path *nc_path = data; + uint32_t hash = 0; + + hash = batadv_hash_bytes(hash, &nc_path->prev_hop, + sizeof(nc_path->prev_hop)); + hash = batadv_hash_bytes(hash, &nc_path->next_hop, + sizeof(nc_path->next_hop)); + + hash += (hash << 3); + hash ^= (hash >> 11); + hash += (hash << 15); + + return hash % size; +} + +/** + * batadv_nc_hash_compare - comparing function used in the network coding hash + * tables + * @node: node in the local table + * @data2: second object to compare the node to + * + * Returns 1 if the two entry are the same, 0 otherwise + */ +static int batadv_nc_hash_compare(const struct hlist_node *node, + const void *data2) +{ + const struct batadv_nc_path *nc_path1, *nc_path2; + + nc_path1 = container_of(node, struct batadv_nc_path, hash_entry); + nc_path2 = data2; + + /* Return 1 if the two keys are identical */ + if (memcmp(nc_path1->prev_hop, nc_path2->prev_hop, + sizeof(nc_path1->prev_hop)) != 0) + return 0; + + if (memcmp(nc_path1->next_hop, nc_path2->next_hop, + sizeof(nc_path1->next_hop)) != 0) + return 0; + + return 1; +} + +/** + * batadv_nc_hash_find - search for an existing nc path and return it + * @hash: hash table containing the nc path + * @data: search key + * + * Returns the nc_path if found, NULL otherwise. + */ +static struct batadv_nc_path * +batadv_nc_hash_find(struct batadv_hashtable *hash, + void *data) +{ + struct hlist_head *head; + struct batadv_nc_path *nc_path, *nc_path_tmp = NULL; + int index; + + if (!hash) + return NULL; + + index = batadv_nc_hash_choose(data, hash->size); + head = &hash->table[index]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(nc_path, head, hash_entry) { + if (!batadv_nc_hash_compare(&nc_path->hash_entry, data)) + continue; + + if (!atomic_inc_not_zero(&nc_path->refcount)) + continue; + + nc_path_tmp = nc_path; + break; + } + rcu_read_unlock(); + + return nc_path_tmp; +} + +/** + * batadv_nc_send_packet - send non-coded packet and free nc_packet struct + * @nc_packet: the nc packet to send + */ +static void batadv_nc_send_packet(struct batadv_nc_packet *nc_packet) +{ + batadv_send_skb_packet(nc_packet->skb, + nc_packet->neigh_node->if_incoming, + nc_packet->nc_path->next_hop); + nc_packet->skb = NULL; + batadv_nc_packet_free(nc_packet); +} + +/** + * batadv_nc_sniffed_purge - Checks timestamp of given sniffed nc_packet. + * @bat_priv: the bat priv with all the soft interface information + * @nc_path: the nc path the packet belongs to + * @nc_packet: the nc packet to be checked + * + * Checks whether the given sniffed (overheard) nc_packet has hit its buffering + * timeout. If so, the packet is no longer kept and the entry deleted from the + * queue. Has to be called with the appropriate locks. + * + * Returns false as soon as the entry in the fifo queue has not been timed out + * yet and true otherwise. + */ +static bool batadv_nc_sniffed_purge(struct batadv_priv *bat_priv, + struct batadv_nc_path *nc_path, + struct batadv_nc_packet *nc_packet) +{ + unsigned long timeout = bat_priv->nc.max_buffer_time; + bool res = false; + + /* Packets are added to tail, so the remaining packets did not time + * out and we can stop processing the current queue + */ + if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE && + !batadv_has_timed_out(nc_packet->timestamp, timeout)) + goto out; + + /* purge nc packet */ + list_del(&nc_packet->list); + batadv_nc_packet_free(nc_packet); + + res = true; + +out: + return res; +} + +/** + * batadv_nc_fwd_flush - Checks the timestamp of the given nc packet. + * @bat_priv: the bat priv with all the soft interface information + * @nc_path: the nc path the packet belongs to + * @nc_packet: the nc packet to be checked + * + * Checks whether the given nc packet has hit its forward timeout. If so, the + * packet is no longer delayed, immediately sent and the entry deleted from the + * queue. Has to be called with the appropriate locks. + * + * Returns false as soon as the entry in the fifo queue has not been timed out + * yet and true otherwise. + */ +static bool batadv_nc_fwd_flush(struct batadv_priv *bat_priv, + struct batadv_nc_path *nc_path, + struct batadv_nc_packet *nc_packet) +{ + unsigned long timeout = bat_priv->nc.max_fwd_delay; + + /* Packets are added to tail, so the remaining packets did not time + * out and we can stop processing the current queue + */ + if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_ACTIVE && + !batadv_has_timed_out(nc_packet->timestamp, timeout)) + return false; + + /* Send packet */ + batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD); + batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES, + nc_packet->skb->len + ETH_HLEN); + list_del(&nc_packet->list); + batadv_nc_send_packet(nc_packet); + + return true; +} + +/** + * batadv_nc_process_nc_paths - traverse given nc packet pool and free timed out + * nc packets + * @bat_priv: the bat priv with all the soft interface information + * @hash: to be processed hash table + * @process_fn: Function called to process given nc packet. Should return true + * to encourage this function to proceed with the next packet. + * Otherwise the rest of the current queue is skipped. + */ +static void +batadv_nc_process_nc_paths(struct batadv_priv *bat_priv, + struct batadv_hashtable *hash, + bool (*process_fn)(struct batadv_priv *, + struct batadv_nc_path *, + struct batadv_nc_packet *)) +{ + struct hlist_head *head; + struct batadv_nc_packet *nc_packet, *nc_packet_tmp; + struct batadv_nc_path *nc_path; + bool ret; + int i; + + if (!hash) + return; + + /* Loop hash table bins */ + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + /* Loop coding paths */ + rcu_read_lock(); + hlist_for_each_entry_rcu(nc_path, head, hash_entry) { + /* Loop packets */ + spin_lock_bh(&nc_path->packet_list_lock); + list_for_each_entry_safe(nc_packet, nc_packet_tmp, + &nc_path->packet_list, list) { + ret = process_fn(bat_priv, nc_path, nc_packet); + if (!ret) + break; + } + spin_unlock_bh(&nc_path->packet_list_lock); + } + rcu_read_unlock(); + } +} + +/** + * batadv_nc_worker - periodic task for house keeping related to network coding + * @work: kernel work struct + */ +static void batadv_nc_worker(struct work_struct *work) +{ + struct delayed_work *delayed_work; + struct batadv_priv_nc *priv_nc; + struct batadv_priv *bat_priv; + unsigned long timeout; + + delayed_work = container_of(work, struct delayed_work, work); + priv_nc = container_of(delayed_work, struct batadv_priv_nc, work); + bat_priv = container_of(priv_nc, struct batadv_priv, nc); + + batadv_nc_purge_orig_hash(bat_priv); + batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, + batadv_nc_to_purge_nc_path_coding); + batadv_nc_purge_paths(bat_priv, bat_priv->nc.decoding_hash, + batadv_nc_to_purge_nc_path_decoding); + + timeout = bat_priv->nc.max_fwd_delay; + + if (batadv_has_timed_out(bat_priv->nc.timestamp_fwd_flush, timeout)) { + batadv_nc_process_nc_paths(bat_priv, bat_priv->nc.coding_hash, + batadv_nc_fwd_flush); + bat_priv->nc.timestamp_fwd_flush = jiffies; + } + + if (batadv_has_timed_out(bat_priv->nc.timestamp_sniffed_purge, + bat_priv->nc.max_buffer_time)) { + batadv_nc_process_nc_paths(bat_priv, bat_priv->nc.decoding_hash, + batadv_nc_sniffed_purge); + bat_priv->nc.timestamp_sniffed_purge = jiffies; + } + + /* Schedule a new check */ + batadv_nc_start_timer(bat_priv); +} + +/** + * batadv_can_nc_with_orig - checks whether the given orig node is suitable for + * coding or not + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: neighboring orig node which may be used as nc candidate + * @ogm_packet: incoming ogm packet also used for the checks + * + * Returns true if: + * 1) The OGM must have the most recent sequence number. + * 2) The TTL must be decremented by one and only one. + * 3) The OGM must be received from the first hop from orig_node. + * 4) The TQ value of the OGM must be above bat_priv->nc.min_tq. + */ +static bool batadv_can_nc_with_orig(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + struct batadv_ogm_packet *ogm_packet) +{ + if (orig_node->last_real_seqno != ntohl(ogm_packet->seqno)) + return false; + if (orig_node->last_ttl != ogm_packet->header.ttl + 1) + return false; + if (!batadv_compare_eth(ogm_packet->orig, ogm_packet->prev_sender)) + return false; + if (ogm_packet->tq < bat_priv->nc.min_tq) + return false; + + return true; +} + +/** + * batadv_nc_find_nc_node - search for an existing nc node and return it + * @orig_node: orig node originating the ogm packet + * @orig_neigh_node: neighboring orig node from which we received the ogm packet + * (can be equal to orig_node) + * @in_coding: traverse incoming or outgoing network coding list + * + * Returns the nc_node if found, NULL otherwise. + */ +static struct batadv_nc_node +*batadv_nc_find_nc_node(struct batadv_orig_node *orig_node, + struct batadv_orig_node *orig_neigh_node, + bool in_coding) +{ + struct batadv_nc_node *nc_node, *nc_node_out = NULL; + struct list_head *list; + + if (in_coding) + list = &orig_neigh_node->in_coding_list; + else + list = &orig_neigh_node->out_coding_list; + + /* Traverse list of nc_nodes to orig_node */ + rcu_read_lock(); + list_for_each_entry_rcu(nc_node, list, list) { + if (!batadv_compare_eth(nc_node->addr, orig_node->orig)) + continue; + + if (!atomic_inc_not_zero(&nc_node->refcount)) + continue; + + /* Found a match */ + nc_node_out = nc_node; + break; + } + rcu_read_unlock(); + + return nc_node_out; +} + +/** + * batadv_nc_get_nc_node - retrieves an nc node or creates the entry if it was + * not found + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node originating the ogm packet + * @orig_neigh_node: neighboring orig node from which we received the ogm packet + * (can be equal to orig_node) + * @in_coding: traverse incoming or outgoing network coding list + * + * Returns the nc_node if found or created, NULL in case of an error. + */ +static struct batadv_nc_node +*batadv_nc_get_nc_node(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + struct batadv_orig_node *orig_neigh_node, + bool in_coding) +{ + struct batadv_nc_node *nc_node; + spinlock_t *lock; /* Used to lock list selected by "int in_coding" */ + struct list_head *list; + + /* Check if nc_node is already added */ + nc_node = batadv_nc_find_nc_node(orig_node, orig_neigh_node, in_coding); + + /* Node found */ + if (nc_node) + return nc_node; + + nc_node = kzalloc(sizeof(*nc_node), GFP_ATOMIC); + if (!nc_node) + return NULL; + + if (!atomic_inc_not_zero(&orig_neigh_node->refcount)) + goto free; + + /* Initialize nc_node */ + INIT_LIST_HEAD(&nc_node->list); + memcpy(nc_node->addr, orig_node->orig, ETH_ALEN); + nc_node->orig_node = orig_neigh_node; + atomic_set(&nc_node->refcount, 2); + + /* Select ingoing or outgoing coding node */ + if (in_coding) { + lock = &orig_neigh_node->in_coding_list_lock; + list = &orig_neigh_node->in_coding_list; + } else { + lock = &orig_neigh_node->out_coding_list_lock; + list = &orig_neigh_node->out_coding_list; + } + + batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_node %pM -> %pM\n", + nc_node->addr, nc_node->orig_node->orig); + + /* Add nc_node to orig_node */ + spin_lock_bh(lock); + list_add_tail_rcu(&nc_node->list, list); + spin_unlock_bh(lock); + + return nc_node; + +free: + kfree(nc_node); + return NULL; +} + +/** + * batadv_nc_update_nc_node - updates stored incoming and outgoing nc node structs + * (best called on incoming OGMs) + * @bat_priv: the bat priv with all the soft interface information + * @orig_node: orig node originating the ogm packet + * @orig_neigh_node: neighboring orig node from which we received the ogm packet + * (can be equal to orig_node) + * @ogm_packet: incoming ogm packet + * @is_single_hop_neigh: orig_node is a single hop neighbor + */ +void batadv_nc_update_nc_node(struct batadv_priv *bat_priv, + struct batadv_orig_node *orig_node, + struct batadv_orig_node *orig_neigh_node, + struct batadv_ogm_packet *ogm_packet, + int is_single_hop_neigh) +{ + struct batadv_nc_node *in_nc_node = NULL, *out_nc_node = NULL; + + /* Check if network coding is enabled */ + if (!atomic_read(&bat_priv->network_coding)) + goto out; + + /* accept ogms from 'good' neighbors and single hop neighbors */ + if (!batadv_can_nc_with_orig(bat_priv, orig_node, ogm_packet) && + !is_single_hop_neigh) + goto out; + + /* Add orig_node as in_nc_node on hop */ + in_nc_node = batadv_nc_get_nc_node(bat_priv, orig_node, + orig_neigh_node, true); + if (!in_nc_node) + goto out; + + in_nc_node->last_seen = jiffies; + + /* Add hop as out_nc_node on orig_node */ + out_nc_node = batadv_nc_get_nc_node(bat_priv, orig_neigh_node, + orig_node, false); + if (!out_nc_node) + goto out; + + out_nc_node->last_seen = jiffies; + +out: + if (in_nc_node) + batadv_nc_node_free_ref(in_nc_node); + if (out_nc_node) + batadv_nc_node_free_ref(out_nc_node); +} + +/** + * batadv_nc_get_path - get existing nc_path or allocate a new one + * @bat_priv: the bat priv with all the soft interface information + * @hash: hash table containing the nc path + * @src: ethernet source address - first half of the nc path search key + * @dst: ethernet destination address - second half of the nc path search key + * + * Returns pointer to nc_path if the path was found or created, returns NULL + * on error. + */ +static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, + struct batadv_hashtable *hash, + uint8_t *src, + uint8_t *dst) +{ + int hash_added; + struct batadv_nc_path *nc_path, nc_path_key; + + batadv_nc_hash_key_gen(&nc_path_key, src, dst); + + /* Search for existing nc_path */ + nc_path = batadv_nc_hash_find(hash, (void *)&nc_path_key); + + if (nc_path) { + /* Set timestamp to delay removal of nc_path */ + nc_path->last_valid = jiffies; + return nc_path; + } + + /* No existing nc_path was found; create a new */ + nc_path = kzalloc(sizeof(*nc_path), GFP_ATOMIC); + + if (!nc_path) + return NULL; + + /* Initialize nc_path */ + INIT_LIST_HEAD(&nc_path->packet_list); + spin_lock_init(&nc_path->packet_list_lock); + atomic_set(&nc_path->refcount, 2); + nc_path->last_valid = jiffies; + memcpy(nc_path->next_hop, dst, ETH_ALEN); + memcpy(nc_path->prev_hop, src, ETH_ALEN); + + batadv_dbg(BATADV_DBG_NC, bat_priv, "Adding nc_path %pM -> %pM\n", + nc_path->prev_hop, + nc_path->next_hop); + + /* Add nc_path to hash table */ + hash_added = batadv_hash_add(hash, batadv_nc_hash_compare, + batadv_nc_hash_choose, &nc_path_key, + &nc_path->hash_entry); + + if (hash_added < 0) { + kfree(nc_path); + return NULL; + } + + return nc_path; +} + +/** + * batadv_nc_random_weight_tq - scale the receivers TQ-value to avoid unfair + * selection of a receiver with slightly lower TQ than the other + * @tq: to be weighted tq value + */ +static uint8_t batadv_nc_random_weight_tq(uint8_t tq) +{ + uint8_t rand_val, rand_tq; + + get_random_bytes(&rand_val, sizeof(rand_val)); + + /* randomize the estimated packet loss (max TQ - estimated TQ) */ + rand_tq = rand_val * (BATADV_TQ_MAX_VALUE - tq); + + /* normalize the randomized packet loss */ + rand_tq /= BATADV_TQ_MAX_VALUE; + + /* convert to (randomized) estimated tq again */ + return BATADV_TQ_MAX_VALUE - rand_tq; +} + +/** + * batadv_nc_memxor - XOR destination with source + * @dst: byte array to XOR into + * @src: byte array to XOR from + * @len: length of destination array + */ +static void batadv_nc_memxor(char *dst, const char *src, unsigned int len) +{ + unsigned int i; + + for (i = 0; i < len; ++i) + dst[i] ^= src[i]; +} + +/** + * batadv_nc_code_packets - code a received unicast_packet with an nc packet + * into a coded_packet and send it + * @bat_priv: the bat priv with all the soft interface information + * @skb: data skb to forward + * @ethhdr: pointer to the ethernet header inside the skb + * @nc_packet: structure containing the packet to the skb can be coded with + * @neigh_node: next hop to forward packet to + * + * Returns true if both packets are consumed, false otherwise. + */ +static bool batadv_nc_code_packets(struct batadv_priv *bat_priv, + struct sk_buff *skb, + struct ethhdr *ethhdr, + struct batadv_nc_packet *nc_packet, + struct batadv_neigh_node *neigh_node) +{ + uint8_t tq_weighted_neigh, tq_weighted_coding; + struct sk_buff *skb_dest, *skb_src; + struct batadv_unicast_packet *packet1; + struct batadv_unicast_packet *packet2; + struct batadv_coded_packet *coded_packet; + struct batadv_neigh_node *neigh_tmp, *router_neigh; + struct batadv_neigh_node *router_coding = NULL; + uint8_t *first_source, *first_dest, *second_source, *second_dest; + __be32 packet_id1, packet_id2; + size_t count; + bool res = false; + int coding_len; + int unicast_size = sizeof(*packet1); + int coded_size = sizeof(*coded_packet); + int header_add = coded_size - unicast_size; + + router_neigh = batadv_orig_node_get_router(neigh_node->orig_node); + if (!router_neigh) + goto out; + + neigh_tmp = nc_packet->neigh_node; + router_coding = batadv_orig_node_get_router(neigh_tmp->orig_node); + if (!router_coding) + goto out; + + tq_weighted_neigh = batadv_nc_random_weight_tq(router_neigh->tq_avg); + tq_weighted_coding = batadv_nc_random_weight_tq(router_coding->tq_avg); + + /* Select one destination for the MAC-header dst-field based on + * weighted TQ-values. + */ + if (tq_weighted_neigh >= tq_weighted_coding) { + /* Destination from nc_packet is selected for MAC-header */ + first_dest = nc_packet->nc_path->next_hop; + first_source = nc_packet->nc_path->prev_hop; + second_dest = neigh_node->addr; + second_source = ethhdr->h_source; + packet1 = (struct batadv_unicast_packet *)nc_packet->skb->data; + packet2 = (struct batadv_unicast_packet *)skb->data; + packet_id1 = nc_packet->packet_id; + packet_id2 = batadv_skb_crc32(skb, + skb->data + sizeof(*packet2)); + } else { + /* Destination for skb is selected for MAC-header */ + first_dest = neigh_node->addr; + first_source = ethhdr->h_source; + second_dest = nc_packet->nc_path->next_hop; + second_source = nc_packet->nc_path->prev_hop; + packet1 = (struct batadv_unicast_packet *)skb->data; + packet2 = (struct batadv_unicast_packet *)nc_packet->skb->data; + packet_id1 = batadv_skb_crc32(skb, + skb->data + sizeof(*packet1)); + packet_id2 = nc_packet->packet_id; + } + + /* Instead of zero padding the smallest data buffer, we + * code into the largest. + */ + if (skb->len <= nc_packet->skb->len) { + skb_dest = nc_packet->skb; + skb_src = skb; + } else { + skb_dest = skb; + skb_src = nc_packet->skb; + } + + /* coding_len is used when decoding the packet shorter packet */ + coding_len = skb_src->len - unicast_size; + + if (skb_linearize(skb_dest) < 0 || skb_linearize(skb_src) < 0) + goto out; + + skb_push(skb_dest, header_add); + + coded_packet = (struct batadv_coded_packet *)skb_dest->data; + skb_reset_mac_header(skb_dest); + + coded_packet->header.packet_type = BATADV_CODED; + coded_packet->header.version = BATADV_COMPAT_VERSION; + coded_packet->header.ttl = packet1->header.ttl; + + /* Info about first unicast packet */ + memcpy(coded_packet->first_source, first_source, ETH_ALEN); + memcpy(coded_packet->first_orig_dest, packet1->dest, ETH_ALEN); + coded_packet->first_crc = packet_id1; + coded_packet->first_ttvn = packet1->ttvn; + + /* Info about second unicast packet */ + memcpy(coded_packet->second_dest, second_dest, ETH_ALEN); + memcpy(coded_packet->second_source, second_source, ETH_ALEN); + memcpy(coded_packet->second_orig_dest, packet2->dest, ETH_ALEN); + coded_packet->second_crc = packet_id2; + coded_packet->second_ttl = packet2->header.ttl; + coded_packet->second_ttvn = packet2->ttvn; + coded_packet->coded_len = htons(coding_len); + + /* This is where the magic happens: Code skb_src into skb_dest */ + batadv_nc_memxor(skb_dest->data + coded_size, + skb_src->data + unicast_size, coding_len); + + /* Update counters accordingly */ + if (BATADV_SKB_CB(skb_src)->decoded && + BATADV_SKB_CB(skb_dest)->decoded) { + /* Both packets are recoded */ + count = skb_src->len + ETH_HLEN; + count += skb_dest->len + ETH_HLEN; + batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE, 2); + batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES, count); + } else if (!BATADV_SKB_CB(skb_src)->decoded && + !BATADV_SKB_CB(skb_dest)->decoded) { + /* Both packets are newly coded */ + count = skb_src->len + ETH_HLEN; + count += skb_dest->len + ETH_HLEN; + batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE, 2); + batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES, count); + } else if (BATADV_SKB_CB(skb_src)->decoded && + !BATADV_SKB_CB(skb_dest)->decoded) { + /* skb_src recoded and skb_dest is newly coded */ + batadv_inc_counter(bat_priv, BATADV_CNT_NC_RECODE); + batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES, + skb_src->len + ETH_HLEN); + batadv_inc_counter(bat_priv, BATADV_CNT_NC_CODE); + batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES, + skb_dest->len + ETH_HLEN); + } else if (!BATADV_SKB_CB(skb_src)->decoded && + BATADV_SKB_CB(skb_dest)->decoded) { + /* skb_src is newly coded and skb_dest is recoded */ + batadv_inc_counter(bat_priv, BATADV_CNT_NC_CODE); + batadv_add_counter(bat_priv, BATADV_CNT_NC_CODE_BYTES, + skb_src->len + ETH_HLEN); + batadv_inc_counter(bat_priv, BATADV_CNT_NC_RECODE); + batadv_add_counter(bat_priv, BATADV_CNT_NC_RECODE_BYTES, + skb_dest->len + ETH_HLEN); + } + + /* skb_src is now coded into skb_dest, so free it */ + kfree_skb(skb_src); + + /* avoid duplicate free of skb from nc_packet */ + nc_packet->skb = NULL; + batadv_nc_packet_free(nc_packet); + + /* Send the coded packet and return true */ + batadv_send_skb_packet(skb_dest, neigh_node->if_incoming, first_dest); + res = true; +out: + if (router_neigh) + batadv_neigh_node_free_ref(router_neigh); + if (router_coding) + batadv_neigh_node_free_ref(router_coding); + return res; +} + +/** + * batadv_nc_skb_coding_possible - true if a decoded skb is available at dst. + * @skb: data skb to forward + * @dst: destination mac address of the other skb to code with + * @src: source mac address of skb + * + * Whenever we network code a packet we have to check whether we received it in + * a network coded form. If so, we may not be able to use it for coding because + * some neighbors may also have received (overheard) the packet in the network + * coded form without being able to decode it. It is hard to know which of the + * neighboring nodes was able to decode the packet, therefore we can only + * re-code the packet if the source of the previous encoded packet is involved. + * Since the source encoded the packet we can be certain it has all necessary + * decode information. + * + * Returns true if coding of a decoded packet is allowed. + */ +static bool batadv_nc_skb_coding_possible(struct sk_buff *skb, + uint8_t *dst, uint8_t *src) +{ + if (BATADV_SKB_CB(skb)->decoded && !batadv_compare_eth(dst, src)) + return false; + else + return true; +} + +/** + * batadv_nc_path_search - Find the coding path matching in_nc_node and + * out_nc_node to retrieve a buffered packet that can be used for coding. + * @bat_priv: the bat priv with all the soft interface information + * @in_nc_node: pointer to skb next hop's neighbor nc node + * @out_nc_node: pointer to skb source's neighbor nc node + * @skb: data skb to forward + * @eth_dst: next hop mac address of skb + * + * Returns true if coding of a decoded skb is allowed. + */ +static struct batadv_nc_packet * +batadv_nc_path_search(struct batadv_priv *bat_priv, + struct batadv_nc_node *in_nc_node, + struct batadv_nc_node *out_nc_node, + struct sk_buff *skb, + uint8_t *eth_dst) +{ + struct batadv_nc_path *nc_path, nc_path_key; + struct batadv_nc_packet *nc_packet_out = NULL; + struct batadv_nc_packet *nc_packet, *nc_packet_tmp; + struct batadv_hashtable *hash = bat_priv->nc.coding_hash; + int idx; + + if (!hash) + return NULL; + + /* Create almost path key */ + batadv_nc_hash_key_gen(&nc_path_key, in_nc_node->addr, + out_nc_node->addr); + idx = batadv_nc_hash_choose(&nc_path_key, hash->size); + + /* Check for coding opportunities in this nc_path */ + rcu_read_lock(); + hlist_for_each_entry_rcu(nc_path, &hash->table[idx], hash_entry) { + if (!batadv_compare_eth(nc_path->prev_hop, in_nc_node->addr)) + continue; + + if (!batadv_compare_eth(nc_path->next_hop, out_nc_node->addr)) + continue; + + spin_lock_bh(&nc_path->packet_list_lock); + if (list_empty(&nc_path->packet_list)) { + spin_unlock_bh(&nc_path->packet_list_lock); + continue; + } + + list_for_each_entry_safe(nc_packet, nc_packet_tmp, + &nc_path->packet_list, list) { + if (!batadv_nc_skb_coding_possible(nc_packet->skb, + eth_dst, + in_nc_node->addr)) + continue; + + /* Coding opportunity is found! */ + list_del(&nc_packet->list); + nc_packet_out = nc_packet; + break; + } + + spin_unlock_bh(&nc_path->packet_list_lock); + break; + } + rcu_read_unlock(); + + return nc_packet_out; +} + +/** + * batadv_nc_skb_src_search - Loops through the list of neighoring nodes of the + * skb's sender (may be equal to the originator). + * @bat_priv: the bat priv with all the soft interface information + * @skb: data skb to forward + * @eth_dst: next hop mac address of skb + * @eth_src: source mac address of skb + * @in_nc_node: pointer to skb next hop's neighbor nc node + * + * Returns an nc packet if a suitable coding packet was found, NULL otherwise. + */ +static struct batadv_nc_packet * +batadv_nc_skb_src_search(struct batadv_priv *bat_priv, + struct sk_buff *skb, + uint8_t *eth_dst, + uint8_t *eth_src, + struct batadv_nc_node *in_nc_node) +{ + struct batadv_orig_node *orig_node; + struct batadv_nc_node *out_nc_node; + struct batadv_nc_packet *nc_packet = NULL; + + orig_node = batadv_orig_hash_find(bat_priv, eth_src); + if (!orig_node) + return NULL; + + rcu_read_lock(); + list_for_each_entry_rcu(out_nc_node, + &orig_node->out_coding_list, list) { + /* Check if the skb is decoded and if recoding is possible */ + if (!batadv_nc_skb_coding_possible(skb, + out_nc_node->addr, eth_src)) + continue; + + /* Search for an opportunity in this nc_path */ + nc_packet = batadv_nc_path_search(bat_priv, in_nc_node, + out_nc_node, skb, eth_dst); + if (nc_packet) + break; + } + rcu_read_unlock(); + + batadv_orig_node_free_ref(orig_node); + return nc_packet; +} + +/** + * batadv_nc_skb_store_before_coding - set the ethernet src and dst of the + * unicast skb before it is stored for use in later decoding + * @bat_priv: the bat priv with all the soft interface information + * @skb: data skb to store + * @eth_dst_new: new destination mac address of skb + */ +static void batadv_nc_skb_store_before_coding(struct batadv_priv *bat_priv, + struct sk_buff *skb, + uint8_t *eth_dst_new) +{ + struct ethhdr *ethhdr; + + /* Copy skb header to change the mac header */ + skb = pskb_copy(skb, GFP_ATOMIC); + if (!skb) + return; + + /* Set the mac header as if we actually sent the packet uncoded */ + ethhdr = (struct ethhdr *)skb_mac_header(skb); + memcpy(ethhdr->h_source, ethhdr->h_dest, ETH_ALEN); + memcpy(ethhdr->h_dest, eth_dst_new, ETH_ALEN); + + /* Set data pointer to MAC header to mimic packets from our tx path */ + skb_push(skb, ETH_HLEN); + + /* Add the packet to the decoding packet pool */ + batadv_nc_skb_store_for_decoding(bat_priv, skb); + + /* batadv_nc_skb_store_for_decoding() clones the skb, so we must free + * our ref + */ + kfree_skb(skb); +} + +/** + * batadv_nc_skb_dst_search - Loops through list of neighboring nodes to dst. + * @skb: data skb to forward + * @neigh_node: next hop to forward packet to + * @ethhdr: pointer to the ethernet header inside the skb + * + * Loops through list of neighboring nodes the next hop has a good connection to + * (receives OGMs with a sufficient quality). We need to find a neighbor of our + * next hop that potentially sent a packet which our next hop also received + * (overheard) and has stored for later decoding. + * + * Returns true if the skb was consumed (encoded packet sent) or false otherwise + */ +static bool batadv_nc_skb_dst_search(struct sk_buff *skb, + struct batadv_neigh_node *neigh_node, + struct ethhdr *ethhdr) +{ + struct net_device *netdev = neigh_node->if_incoming->soft_iface; + struct batadv_priv *bat_priv = netdev_priv(netdev); + struct batadv_orig_node *orig_node = neigh_node->orig_node; + struct batadv_nc_node *nc_node; + struct batadv_nc_packet *nc_packet = NULL; + + rcu_read_lock(); + list_for_each_entry_rcu(nc_node, &orig_node->in_coding_list, list) { + /* Search for coding opportunity with this in_nc_node */ + nc_packet = batadv_nc_skb_src_search(bat_priv, skb, + neigh_node->addr, + ethhdr->h_source, nc_node); + + /* Opportunity was found, so stop searching */ + if (nc_packet) + break; + } + rcu_read_unlock(); + + if (!nc_packet) + return false; + + /* Save packets for later decoding */ + batadv_nc_skb_store_before_coding(bat_priv, skb, + neigh_node->addr); + batadv_nc_skb_store_before_coding(bat_priv, nc_packet->skb, + nc_packet->neigh_node->addr); + + /* Code and send packets */ + if (batadv_nc_code_packets(bat_priv, skb, ethhdr, nc_packet, + neigh_node)) + return true; + + /* out of mem ? Coding failed - we have to free the buffered packet + * to avoid memleaks. The skb passed as argument will be dealt with + * by the calling function. + */ + batadv_nc_send_packet(nc_packet); + return false; +} + +/** + * batadv_nc_skb_add_to_path - buffer skb for later encoding / decoding + * @skb: skb to add to path + * @nc_path: path to add skb to + * @neigh_node: next hop to forward packet to + * @packet_id: checksum to identify packet + * + * Returns true if the packet was buffered or false in case of an error. + */ +static bool batadv_nc_skb_add_to_path(struct sk_buff *skb, + struct batadv_nc_path *nc_path, + struct batadv_neigh_node *neigh_node, + __be32 packet_id) +{ + struct batadv_nc_packet *nc_packet; + + nc_packet = kzalloc(sizeof(*nc_packet), GFP_ATOMIC); + if (!nc_packet) + return false; + + /* Initialize nc_packet */ + nc_packet->timestamp = jiffies; + nc_packet->packet_id = packet_id; + nc_packet->skb = skb; + nc_packet->neigh_node = neigh_node; + nc_packet->nc_path = nc_path; + + /* Add coding packet to list */ + spin_lock_bh(&nc_path->packet_list_lock); + list_add_tail(&nc_packet->list, &nc_path->packet_list); + spin_unlock_bh(&nc_path->packet_list_lock); + + return true; +} + +/** + * batadv_nc_skb_forward - try to code a packet or add it to the coding packet + * buffer + * @skb: data skb to forward + * @neigh_node: next hop to forward packet to + * @ethhdr: pointer to the ethernet header inside the skb + * + * Returns true if the skb was consumed (encoded packet sent) or false otherwise + */ +bool batadv_nc_skb_forward(struct sk_buff *skb, + struct batadv_neigh_node *neigh_node, + struct ethhdr *ethhdr) +{ + const struct net_device *netdev = neigh_node->if_incoming->soft_iface; + struct batadv_priv *bat_priv = netdev_priv(netdev); + struct batadv_unicast_packet *packet; + struct batadv_nc_path *nc_path; + __be32 packet_id; + u8 *payload; + + /* Check if network coding is enabled */ + if (!atomic_read(&bat_priv->network_coding)) + goto out; + + /* We only handle unicast packets */ + payload = skb_network_header(skb); + packet = (struct batadv_unicast_packet *)payload; + if (packet->header.packet_type != BATADV_UNICAST) + goto out; + + /* Try to find a coding opportunity and send the skb if one is found */ + if (batadv_nc_skb_dst_search(skb, neigh_node, ethhdr)) + return true; + + /* Find or create a nc_path for this src-dst pair */ + nc_path = batadv_nc_get_path(bat_priv, + bat_priv->nc.coding_hash, + ethhdr->h_source, + neigh_node->addr); + + if (!nc_path) + goto out; + + /* Add skb to nc_path */ + packet_id = batadv_skb_crc32(skb, payload + sizeof(*packet)); + if (!batadv_nc_skb_add_to_path(skb, nc_path, neigh_node, packet_id)) + goto free_nc_path; + + /* Packet is consumed */ + return true; + +free_nc_path: + batadv_nc_path_free_ref(nc_path); +out: + /* Packet is not consumed */ + return false; +} + +/** + * batadv_nc_skb_store_for_decoding - save a clone of the skb which can be used + * when decoding coded packets + * @bat_priv: the bat priv with all the soft interface information + * @skb: data skb to store + */ +void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + struct batadv_unicast_packet *packet; + struct batadv_nc_path *nc_path; + struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); + __be32 packet_id; + u8 *payload; + + /* Check if network coding is enabled */ + if (!atomic_read(&bat_priv->network_coding)) + goto out; + + /* Check for supported packet type */ + payload = skb_network_header(skb); + packet = (struct batadv_unicast_packet *)payload; + if (packet->header.packet_type != BATADV_UNICAST) + goto out; + + /* Find existing nc_path or create a new */ + nc_path = batadv_nc_get_path(bat_priv, + bat_priv->nc.decoding_hash, + ethhdr->h_source, + ethhdr->h_dest); + + if (!nc_path) + goto out; + + /* Clone skb and adjust skb->data to point at batman header */ + skb = skb_clone(skb, GFP_ATOMIC); + if (unlikely(!skb)) + goto free_nc_path; + + if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) + goto free_skb; + + if (unlikely(!skb_pull_rcsum(skb, ETH_HLEN))) + goto free_skb; + + /* Add skb to nc_path */ + packet_id = batadv_skb_crc32(skb, payload + sizeof(*packet)); + if (!batadv_nc_skb_add_to_path(skb, nc_path, NULL, packet_id)) + goto free_skb; + + batadv_inc_counter(bat_priv, BATADV_CNT_NC_BUFFER); + return; + +free_skb: + kfree_skb(skb); +free_nc_path: + batadv_nc_path_free_ref(nc_path); +out: + return; +} + +/** + * batadv_nc_skb_store_sniffed_unicast - check if a received unicast packet + * should be saved in the decoding buffer and, if so, store it there + * @bat_priv: the bat priv with all the soft interface information + * @skb: unicast skb to store + */ +void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); + - if (batadv_is_my_mac(ethhdr->h_dest)) ++ if (batadv_is_my_mac(bat_priv, ethhdr->h_dest)) + return; + + /* Set data pointer to MAC header to mimic packets from our tx path */ + skb_push(skb, ETH_HLEN); + + batadv_nc_skb_store_for_decoding(bat_priv, skb); +} + +/** + * batadv_nc_skb_decode_packet - decode given skb using the decode data stored + * in nc_packet ++ * @bat_priv: the bat priv with all the soft interface information + * @skb: unicast skb to decode + * @nc_packet: decode data needed to decode the skb + * + * Returns pointer to decoded unicast packet if the packet was decoded or NULL + * in case of an error. + */ +static struct batadv_unicast_packet * - batadv_nc_skb_decode_packet(struct sk_buff *skb, ++batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, + struct batadv_nc_packet *nc_packet) +{ + const int h_size = sizeof(struct batadv_unicast_packet); + const int h_diff = sizeof(struct batadv_coded_packet) - h_size; + struct batadv_unicast_packet *unicast_packet; + struct batadv_coded_packet coded_packet_tmp; + struct ethhdr *ethhdr, ethhdr_tmp; + uint8_t *orig_dest, ttl, ttvn; + unsigned int coding_len; + + /* Save headers temporarily */ + memcpy(&coded_packet_tmp, skb->data, sizeof(coded_packet_tmp)); + memcpy(&ethhdr_tmp, skb_mac_header(skb), sizeof(ethhdr_tmp)); + + if (skb_cow(skb, 0) < 0) + return NULL; + + if (unlikely(!skb_pull_rcsum(skb, h_diff))) + return NULL; + + /* Data points to batman header, so set mac header 14 bytes before + * and network to data + */ + skb_set_mac_header(skb, -ETH_HLEN); + skb_reset_network_header(skb); + + /* Reconstruct original mac header */ + ethhdr = (struct ethhdr *)skb_mac_header(skb); + memcpy(ethhdr, &ethhdr_tmp, sizeof(*ethhdr)); + + /* Select the correct unicast header information based on the location + * of our mac address in the coded_packet header + */ - if (batadv_is_my_mac(coded_packet_tmp.second_dest)) { ++ if (batadv_is_my_mac(bat_priv, coded_packet_tmp.second_dest)) { + /* If we are the second destination the packet was overheard, + * so the Ethernet address must be copied to h_dest and + * pkt_type changed from PACKET_OTHERHOST to PACKET_HOST + */ + memcpy(ethhdr->h_dest, coded_packet_tmp.second_dest, ETH_ALEN); + skb->pkt_type = PACKET_HOST; + + orig_dest = coded_packet_tmp.second_orig_dest; + ttl = coded_packet_tmp.second_ttl; + ttvn = coded_packet_tmp.second_ttvn; + } else { + orig_dest = coded_packet_tmp.first_orig_dest; + ttl = coded_packet_tmp.header.ttl; + ttvn = coded_packet_tmp.first_ttvn; + } + + coding_len = ntohs(coded_packet_tmp.coded_len); + + if (coding_len > skb->len) + return NULL; + + /* Here the magic is reversed: + * extract the missing packet from the received coded packet + */ + batadv_nc_memxor(skb->data + h_size, + nc_packet->skb->data + h_size, + coding_len); + + /* Resize decoded skb if decoded with larger packet */ + if (nc_packet->skb->len > coding_len + h_size) + pskb_trim_rcsum(skb, coding_len + h_size); + + /* Create decoded unicast packet */ + unicast_packet = (struct batadv_unicast_packet *)skb->data; + unicast_packet->header.packet_type = BATADV_UNICAST; + unicast_packet->header.version = BATADV_COMPAT_VERSION; + unicast_packet->header.ttl = ttl; + memcpy(unicast_packet->dest, orig_dest, ETH_ALEN); + unicast_packet->ttvn = ttvn; + + batadv_nc_packet_free(nc_packet); + return unicast_packet; +} + +/** + * batadv_nc_find_decoding_packet - search through buffered decoding data to + * find the data needed to decode the coded packet + * @bat_priv: the bat priv with all the soft interface information + * @ethhdr: pointer to the ethernet header inside the coded packet + * @coded: coded packet we try to find decode data for + * + * Returns pointer to nc packet if the needed data was found or NULL otherwise. + */ +static struct batadv_nc_packet * +batadv_nc_find_decoding_packet(struct batadv_priv *bat_priv, + struct ethhdr *ethhdr, + struct batadv_coded_packet *coded) +{ + struct batadv_hashtable *hash = bat_priv->nc.decoding_hash; + struct batadv_nc_packet *tmp_nc_packet, *nc_packet = NULL; + struct batadv_nc_path *nc_path, nc_path_key; + uint8_t *dest, *source; + __be32 packet_id; + int index; + + if (!hash) + return NULL; + + /* Select the correct packet id based on the location of our mac-addr */ + dest = ethhdr->h_source; - if (!batadv_is_my_mac(coded->second_dest)) { ++ if (!batadv_is_my_mac(bat_priv, coded->second_dest)) { + source = coded->second_source; + packet_id = coded->second_crc; + } else { + source = coded->first_source; + packet_id = coded->first_crc; + } + + batadv_nc_hash_key_gen(&nc_path_key, source, dest); + index = batadv_nc_hash_choose(&nc_path_key, hash->size); + + /* Search for matching coding path */ + rcu_read_lock(); + hlist_for_each_entry_rcu(nc_path, &hash->table[index], hash_entry) { + /* Find matching nc_packet */ + spin_lock_bh(&nc_path->packet_list_lock); + list_for_each_entry(tmp_nc_packet, + &nc_path->packet_list, list) { + if (packet_id == tmp_nc_packet->packet_id) { + list_del(&tmp_nc_packet->list); + + nc_packet = tmp_nc_packet; + break; + } + } + spin_unlock_bh(&nc_path->packet_list_lock); + + if (nc_packet) + break; + } + rcu_read_unlock(); + + if (!nc_packet) + batadv_dbg(BATADV_DBG_NC, bat_priv, + "No decoding packet found for %u\n", packet_id); + + return nc_packet; +} + +/** + * batadv_nc_recv_coded_packet - try to decode coded packet and enqueue the + * resulting unicast packet + * @skb: incoming coded packet + * @recv_if: pointer to interface this packet was received on + */ +static int batadv_nc_recv_coded_packet(struct sk_buff *skb, + struct batadv_hard_iface *recv_if) +{ + struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct batadv_unicast_packet *unicast_packet; + struct batadv_coded_packet *coded_packet; + struct batadv_nc_packet *nc_packet; + struct ethhdr *ethhdr; + int hdr_size = sizeof(*coded_packet); + + /* Check if network coding is enabled */ + if (!atomic_read(&bat_priv->network_coding)) + return NET_RX_DROP; + + /* Make sure we can access (and remove) header */ + if (unlikely(!pskb_may_pull(skb, hdr_size))) + return NET_RX_DROP; + + coded_packet = (struct batadv_coded_packet *)skb->data; + ethhdr = (struct ethhdr *)skb_mac_header(skb); + + /* Verify frame is destined for us */ - if (!batadv_is_my_mac(ethhdr->h_dest) && - !batadv_is_my_mac(coded_packet->second_dest)) ++ if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest) && ++ !batadv_is_my_mac(bat_priv, coded_packet->second_dest)) + return NET_RX_DROP; + + /* Update stat counter */ - if (batadv_is_my_mac(coded_packet->second_dest)) ++ if (batadv_is_my_mac(bat_priv, coded_packet->second_dest)) + batadv_inc_counter(bat_priv, BATADV_CNT_NC_SNIFFED); + + nc_packet = batadv_nc_find_decoding_packet(bat_priv, ethhdr, + coded_packet); + if (!nc_packet) { + batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE_FAILED); + return NET_RX_DROP; + } + + /* Make skb's linear, because decoding accesses the entire buffer */ + if (skb_linearize(skb) < 0) + goto free_nc_packet; + + if (skb_linearize(nc_packet->skb) < 0) + goto free_nc_packet; + + /* Decode the packet */ - unicast_packet = batadv_nc_skb_decode_packet(skb, nc_packet); ++ unicast_packet = batadv_nc_skb_decode_packet(bat_priv, skb, nc_packet); + if (!unicast_packet) { + batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE_FAILED); + goto free_nc_packet; + } + + /* Mark packet as decoded to do correct recoding when forwarding */ + BATADV_SKB_CB(skb)->decoded = true; + batadv_inc_counter(bat_priv, BATADV_CNT_NC_DECODE); + batadv_add_counter(bat_priv, BATADV_CNT_NC_DECODE_BYTES, + skb->len + ETH_HLEN); + return batadv_recv_unicast_packet(skb, recv_if); + +free_nc_packet: + batadv_nc_packet_free(nc_packet); + return NET_RX_DROP; +} + +/** + * batadv_nc_free - clean up network coding memory + * @bat_priv: the bat priv with all the soft interface information + */ +void batadv_nc_free(struct batadv_priv *bat_priv) +{ + batadv_recv_handler_unregister(BATADV_CODED); + cancel_delayed_work_sync(&bat_priv->nc.work); + + batadv_nc_purge_paths(bat_priv, bat_priv->nc.coding_hash, NULL); + batadv_hash_destroy(bat_priv->nc.coding_hash); + batadv_nc_purge_paths(bat_priv, bat_priv->nc.decoding_hash, NULL); + batadv_hash_destroy(bat_priv->nc.decoding_hash); +} + +/** + * batadv_nc_nodes_seq_print_text - print the nc node information + * @seq: seq file to print on + * @offset: not used + */ +int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset) +{ + struct net_device *net_dev = (struct net_device *)seq->private; + struct batadv_priv *bat_priv = netdev_priv(net_dev); + struct batadv_hashtable *hash = bat_priv->orig_hash; + struct batadv_hard_iface *primary_if; + struct hlist_head *head; + struct batadv_orig_node *orig_node; + struct batadv_nc_node *nc_node; + int i; + + primary_if = batadv_seq_print_text_primary_if_get(seq); + if (!primary_if) + goto out; + + /* Traverse list of originators */ + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + /* For each orig_node in this bin */ + rcu_read_lock(); + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { + seq_printf(seq, "Node: %pM\n", orig_node->orig); + + seq_puts(seq, " Ingoing: "); + /* For each in_nc_node to this orig_node */ + list_for_each_entry_rcu(nc_node, + &orig_node->in_coding_list, + list) + seq_printf(seq, "%pM ", + nc_node->addr); + seq_puts(seq, "\n"); + + seq_puts(seq, " Outgoing: "); + /* For out_nc_node to this orig_node */ + list_for_each_entry_rcu(nc_node, + &orig_node->out_coding_list, + list) + seq_printf(seq, "%pM ", + nc_node->addr); + seq_puts(seq, "\n\n"); + } + rcu_read_unlock(); + } + +out: + if (primary_if) + batadv_hardif_free_ref(primary_if); + return 0; +} + +/** + * batadv_nc_init_debugfs - create nc folder and related files in debugfs + * @bat_priv: the bat priv with all the soft interface information + */ +int batadv_nc_init_debugfs(struct batadv_priv *bat_priv) +{ + struct dentry *nc_dir, *file; + + nc_dir = debugfs_create_dir("nc", bat_priv->debug_dir); + if (!nc_dir) + goto out; + + file = debugfs_create_u8("min_tq", S_IRUGO | S_IWUSR, nc_dir, + &bat_priv->nc.min_tq); + if (!file) + goto out; + + file = debugfs_create_u32("max_fwd_delay", S_IRUGO | S_IWUSR, nc_dir, + &bat_priv->nc.max_fwd_delay); + if (!file) + goto out; + + file = debugfs_create_u32("max_buffer_time", S_IRUGO | S_IWUSR, nc_dir, + &bat_priv->nc.max_buffer_time); + if (!file) + goto out; + + return 0; + +out: + return -ENOMEM; +} diff --combined net/batman-adv/routing.c index 8f88967,319f290..2f1f889 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@@ -29,7 -29,6 +29,7 @@@ #include "unicast.h" #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" +#include "network-coding.h"

static int batadv_route_unicast_packet(struct sk_buff *skb, struct batadv_hard_iface *recv_if); @@@ -403,7 -402,7 +403,7 @@@ int batadv_recv_icmp_packet(struct sk_b goto out;

/* not for me */ - if (!batadv_is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) goto out;

icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; @@@ -417,7 -416,7 +417,7 @@@ }

/* packet for me */ - if (batadv_is_my_mac(icmp_packet->dst)) + if (batadv_is_my_mac(bat_priv, icmp_packet->dst)) return batadv_recv_my_icmp_packet(bat_priv, skb, hdr_size);

/* TTL exceeded */ @@@ -549,37 -548,28 +549,39 @@@ batadv_find_ifalter_router(struct batad return router; }

+/** + * batadv_check_unicast_packet - Check for malformed unicast packets ++ * @bat_priv: the bat priv with all the soft interface information + * @skb: packet to check + * @hdr_size: size of header to pull + * + * Check for short header and bad addresses in given packet. Returns negative + * value when check fails and 0 otherwise. The negative value depends on the + * reason: -ENODATA for bad header, -EBADR for broadcast destination or source, + * and -EREMOTE for non-local (other host) destination. + */ - static int batadv_check_unicast_packet(struct sk_buff *skb, int hdr_size) + static int batadv_check_unicast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) { struct ethhdr *ethhdr;

/* drop packet if it has not necessary minimum size */ if (unlikely(!pskb_may_pull(skb, hdr_size))) - return -1; + return -ENODATA;

ethhdr = (struct ethhdr *)skb_mac_header(skb);

/* packet with unicast indication but broadcast recipient */ if (is_broadcast_ether_addr(ethhdr->h_dest)) - return -1; + return -EBADR;

/* packet with broadcast sender address */ if (is_broadcast_ether_addr(ethhdr->h_source)) - return -1; + return -EBADR;

/* not for me */ - if (!batadv_is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) - return -1; + return -EREMOTE;

return 0; } @@@ -593,7 -583,7 +595,7 @@@ int batadv_recv_tt_query(struct sk_buf char tt_flag; size_t packet_size;

- if (batadv_check_unicast_packet(skb, hdr_size) < 0) + if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0) return NET_RX_DROP;

/* I could need to modify it */ @@@ -625,7 -615,7 +627,7 @@@ case BATADV_TT_RESPONSE: batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_RX);

- if (batadv_is_my_mac(tt_query->dst)) { + if (batadv_is_my_mac(bat_priv, tt_query->dst)) { /* packet needs to be linearized to access the TT * changes */ @@@ -668,14 -658,15 +670,15 @@@ int batadv_recv_roam_adv(struct sk_buf struct batadv_roam_adv_packet *roam_adv_packet; struct batadv_orig_node *orig_node;

- if (batadv_check_unicast_packet(skb, sizeof(*roam_adv_packet)) < 0) + if (batadv_check_unicast_packet(bat_priv, skb, + sizeof(*roam_adv_packet)) < 0) goto out;

batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_RX);

roam_adv_packet = (struct batadv_roam_adv_packet *)skb->data;

- if (!batadv_is_my_mac(roam_adv_packet->dst)) + if (!batadv_is_my_mac(bat_priv, roam_adv_packet->dst)) return batadv_route_unicast_packet(skb, recv_if);

/* check if it is a backbone gateway. we don't accept @@@ -861,17 -852,14 +864,17 @@@ static int batadv_route_unicast_packet( /* decrement ttl */ unicast_packet->header.ttl--;

- /* Update stats counter */ - batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD); - batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES, - skb->len + ETH_HLEN); - - /* route it */ - if (batadv_send_skb_to_orig(skb, orig_node, recv_if)) + /* network code packet if possible */ + if (batadv_nc_skb_forward(skb, neigh_node, ethhdr)) { ret = NET_RX_SUCCESS; + } else if (batadv_send_skb_to_orig(skb, orig_node, recv_if)) { + ret = NET_RX_SUCCESS; + + /* Update stats counter */ + batadv_inc_counter(bat_priv, BATADV_CNT_FORWARD); + batadv_add_counter(bat_priv, BATADV_CNT_FORWARD_BYTES, + skb->len + ETH_HLEN); + }

out: if (neigh_node) @@@ -981,7 -969,7 +984,7 @@@ static int batadv_check_unicast_ttvn(st * last time) the packet had an updated information or not */ curr_ttvn = (uint8_t)atomic_read(&bat_priv->tt.vn); - if (!batadv_is_my_mac(unicast_packet->dest)) { + if (!batadv_is_my_mac(bat_priv, unicast_packet->dest)) { orig_node = batadv_orig_hash_find(bat_priv, unicast_packet->dest); /* if it is not possible to find the orig_node representing the @@@ -1047,7 -1035,7 +1050,7 @@@ int batadv_recv_unicast_packet(struct s struct batadv_unicast_4addr_packet *unicast_4addr_packet; uint8_t *orig_addr; struct batadv_orig_node *orig_node = NULL; - int hdr_size = sizeof(*unicast_packet); + int check, hdr_size = sizeof(*unicast_packet); bool is4addr;

unicast_packet = (struct batadv_unicast_packet *)skb->data; @@@ -1058,23 -1046,14 +1061,23 @@@ if (is4addr) hdr_size = sizeof(*unicast_4addr_packet);

- if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0) + /* function returns -EREMOTE for promiscuous packets */ - check = batadv_check_unicast_packet(skb, hdr_size); ++ check = batadv_check_unicast_packet(bat_priv, skb, hdr_size); + + /* Even though the packet is not for us, we might save it to use for + * decoding a later received coded packet + */ + if (check == -EREMOTE) + batadv_nc_skb_store_sniffed_unicast(bat_priv, skb); + + if (check < 0) return NET_RX_DROP;

if (!batadv_check_unicast_ttvn(bat_priv, skb)) return NET_RX_DROP;

/* packet for me */ - if (batadv_is_my_mac(unicast_packet->dest)) { + if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { if (is4addr) { batadv_dat_inc_counter(bat_priv, unicast_4addr_packet->subtype); @@@ -1111,7 -1090,7 +1114,7 @@@ int batadv_recv_ucast_frag_packet(struc struct sk_buff *new_skb = NULL; int ret;

- if (batadv_check_unicast_packet(skb, hdr_size) < 0) + if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0) return NET_RX_DROP;

if (!batadv_check_unicast_ttvn(bat_priv, skb)) @@@ -1120,7 -1099,7 +1123,7 @@@ unicast_packet = (struct batadv_unicast_frag_packet *)skb->data;

/* packet for me */ - if (batadv_is_my_mac(unicast_packet->dest)) { + if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { ret = batadv_frag_reassemble_skb(skb, bat_priv, &new_skb);

if (ret == NET_RX_DROP) @@@ -1174,13 -1153,13 +1177,13 @@@ int batadv_recv_bcast_packet(struct sk_ goto out;

/* ignore broadcasts sent by myself */ - if (batadv_is_my_mac(ethhdr->h_source)) + if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto out;

bcast_packet = (struct batadv_bcast_packet *)skb->data;

/* ignore broadcasts originated by myself */ - if (batadv_is_my_mac(bcast_packet->orig)) + if (batadv_is_my_mac(bat_priv, bcast_packet->orig)) goto out;

if (bcast_packet->header.ttl < 2) @@@ -1266,14 -1245,14 +1269,14 @@@ int batadv_recv_vis_packet(struct sk_bu ethhdr = (struct ethhdr *)skb_mac_header(skb);

/* not for me */ - if (!batadv_is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) return NET_RX_DROP;

/* ignore own packets */ - if (batadv_is_my_mac(vis_packet->vis_orig)) + if (batadv_is_my_mac(bat_priv, vis_packet->vis_orig)) return NET_RX_DROP;

- if (batadv_is_my_mac(vis_packet->sender_orig)) + if (batadv_is_my_mac(bat_priv, vis_packet->sender_orig)) return NET_RX_DROP;

switch (vis_packet->vis_type) { diff --combined net/batman-adv/translation-table.c index 9322320,7abee19..5e89dee --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@@ -385,19 -385,25 +385,19 @@@ static void batadv_tt_prepare_packet_bu int *packet_buff_len, int min_packet_len) { - struct batadv_hard_iface *primary_if; int req_len;

- primary_if = batadv_primary_if_get_selected(bat_priv); - req_len = min_packet_len; req_len += batadv_tt_len(atomic_read(&bat_priv->tt.local_changes));

/* if we have too many changes for one packet don't send any * and wait for the tt table request which will be fragmented */ - if ((!primary_if) || (req_len > primary_if->soft_iface->mtu)) + if (req_len > bat_priv->soft_iface->mtu) req_len = min_packet_len;

batadv_tt_realloc_packet_buff(packet_buff, packet_buff_len, min_packet_len, req_len); - - if (primary_if) - batadv_hardif_free_ref(primary_if); }

static int batadv_tt_changes_fill_buff(struct batadv_priv *bat_priv, @@@ -902,7 -908,7 +902,7 @@@ out_remove /* remove address from local hash if present */ local_flags = batadv_tt_local_remove(bat_priv, tt_addr, "global tt received", - !!(flags & BATADV_TT_CLIENT_ROAM)); + flags & BATADV_TT_CLIENT_ROAM); tt_global_entry->common.flags |= local_flags & BATADV_TT_CLIENT_WIFI;

if (!(flags & BATADV_TT_CLIENT_ROAM)) @@@ -1574,7 -1580,7 +1574,7 @@@ static int batadv_tt_global_valid(cons static struct sk_buff * batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, struct batadv_hashtable *hash, - struct batadv_hard_iface *primary_if, + struct batadv_priv *bat_priv, int (*valid_cb)(const void *, const void *), void *cb_data) { @@@ -1588,8 -1594,8 +1588,8 @@@ uint32_t i; size_t len;

- if (tt_query_size + tt_len > primary_if->soft_iface->mtu) { - tt_len = primary_if->soft_iface->mtu - tt_query_size; + if (tt_query_size + tt_len > bat_priv->soft_iface->mtu) { + tt_len = bat_priv->soft_iface->mtu - tt_query_size; tt_len -= tt_len % sizeof(struct batadv_tt_change); } tt_tot = tt_len / sizeof(struct batadv_tt_change); @@@ -1709,6 -1715,7 +1709,6 @@@ batadv_send_other_tt_response(struct ba { struct batadv_orig_node *req_dst_orig_node; struct batadv_orig_node *res_dst_orig_node = NULL; - struct batadv_hard_iface *primary_if = NULL; uint8_t orig_ttvn, req_ttvn, ttvn; int ret = false; unsigned char *tt_buff; @@@ -1733,6 -1740,10 +1733,6 @@@ if (!res_dst_orig_node) goto out;

- primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) - goto out; - orig_ttvn = (uint8_t)atomic_read(&req_dst_orig_node->last_ttvn); req_ttvn = tt_request->ttvn;

@@@ -1780,7 -1791,7 +1780,7 @@@

skb = batadv_tt_response_fill_table(tt_len, ttvn, bat_priv->tt.global_hash, - primary_if, + bat_priv, batadv_tt_global_valid, req_dst_orig_node); if (!skb) @@@ -1817,6 -1828,8 +1817,6 @@@ out batadv_orig_node_free_ref(res_dst_orig_node); if (req_dst_orig_node) batadv_orig_node_free_ref(req_dst_orig_node); - if (primary_if) - batadv_hardif_free_ref(primary_if); if (!ret) kfree_skb(skb); return ret; @@@ -1894,7 -1907,7 +1894,7 @@@ batadv_send_my_tt_response(struct batad

skb = batadv_tt_response_fill_table(tt_len, ttvn, bat_priv->tt.local_hash, - primary_if, + bat_priv, batadv_tt_local_valid_entry, NULL); if (!skb) @@@ -1940,7 -1953,7 +1940,7 @@@ out bool batadv_send_tt_response(struct batadv_priv *bat_priv, struct batadv_tt_query_packet *tt_request) { - if (batadv_is_my_mac(tt_request->dst)) { + if (batadv_is_my_mac(bat_priv, tt_request->dst)) { /* don't answer backbone gws! */ if (batadv_bla_is_backbone_gw_orig(bat_priv, tt_request->src)) return true; @@@ -2515,7 -2528,7 +2515,7 @@@ bool batadv_tt_global_client_is_roaming if (!tt_global_entry) goto out;

- ret = !!(tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM); + ret = tt_global_entry->common.flags & BATADV_TT_CLIENT_ROAM; batadv_tt_global_entry_free_ref(tt_global_entry); out: return ret; diff --combined net/batman-adv/vis.c index 962ccf3,6a1e646..1625e57 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@@ -149,7 -149,7 +149,7 @@@ static void batadv_vis_data_read_prim_s

hlist_for_each_entry(entry, if_list, list) { if (entry->primary) - seq_printf(seq, "PRIMARY, "); + seq_puts(seq, "PRIMARY, "); else seq_printf(seq, "SEC %pM, ", entry->addr); } @@@ -207,7 -207,7 +207,7 @@@ static void batadv_vis_data_read_entrie if (batadv_compare_eth(entry->addr, packet->vis_orig)) batadv_vis_data_read_prim_sec(seq, list);

- seq_printf(seq, "\n"); + seq_puts(seq, "\n"); } }

@@@ -477,7 -477,7 +477,7 @@@ void batadv_receive_client_update_packe

/* Are we the target for this VIS packet? */ if (vis_server == BATADV_VIS_TYPE_SERVER_SYNC && - batadv_is_my_mac(vis_packet->target_orig)) + batadv_is_my_mac(bat_priv, vis_packet->target_orig)) are_target = 1;

spin_lock_bh(&bat_priv->vis.hash_lock); @@@ -496,7 -496,7 +496,7 @@@ batadv_send_list_add(bat_priv, info);

/* ... we're not the recipient (and thus need to forward). */ - } else if (!batadv_is_my_mac(packet->target_orig)) { + } else if (!batadv_is_my_mac(bat_priv, packet->target_orig)) { batadv_send_list_add(bat_priv, info); }

diff --combined net/bridge/br_if.c index f17fcb3,459dab2..4cdba60 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@@ -67,7 -67,8 +67,8 @@@ void br_port_carrier_check(struct net_b struct net_device *dev = p->dev; struct net_bridge *br = p->br;

- if (netif_running(dev) && netif_oper_up(dev)) + if (!(p->flags & BR_ADMIN_COST) && + netif_running(dev) && netif_oper_up(dev)) p->path_cost = port_cost(dev);

if (!netif_running(br->dev)) @@@ -148,6 -149,7 +149,6 @@@ static void del_nbp(struct net_bridge_p dev->priv_flags &= ~IFF_BRIDGE_PORT;

netdev_rx_handler_unregister(dev); - synchronize_net();

netdev_upper_dev_unlink(dev, br->dev);

diff --combined net/can/gw.c index 2dc619d,117814a..3ee690e --- a/net/can/gw.c +++ b/net/can/gw.c @@@ -466,7 -466,7 +466,7 @@@ static int cgw_notifier(struct notifier if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); } } } @@@ -778,7 -778,8 +778,7 @@@ static int cgw_parse_attr(struct nlmsgh return 0; }

-static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, - void *arg) +static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh) { struct rtcanmsg *r; struct cgw_job *gwj; @@@ -863,11 -864,11 +863,11 @@@ static void cgw_remove_all_jobs(void hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); } }

-static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh) { struct cgw_job *gwj = NULL; struct hlist_node *nx; @@@ -919,7 -920,7 +919,7 @@@

hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); err = 0; break; } diff --combined net/core/dev.c index 8a3cb2c,b24ab0e9..9e26b8d --- a/net/core/dev.c +++ b/net/core/dev.c @@@ -200,7 -200,7 +200,7 @@@ static inline void rps_unlock(struct so }

/* Device list insertion */ -static int list_netdevice(struct net_device *dev) +static void list_netdevice(struct net_device *dev) { struct net *net = dev_net(dev);

@@@ -214,6 -214,8 +214,6 @@@ write_unlock_bh(&dev_base_lock);

dev_base_seq_inc(net); - - return 0; }

/* Device list removal @@@ -2146,6 -2148,9 +2146,9 @@@ static void skb_warn_bad_offload(const struct net_device *dev = skb->dev; const char *driver = "";

+ if (!net_ratelimit()) + return; + if (dev && dev->dev.parent) driver = dev_driver_string(dev->dev.parent);

@@@ -2205,40 -2210,30 +2208,40 @@@ out } EXPORT_SYMBOL(skb_checksum_help);

-/** - * skb_mac_gso_segment - mac layer segmentation handler. - * @skb: buffer to segment - * @features: features for the output path (see dev->features) - */ -struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, - netdev_features_t features) +__be16 skb_network_protocol(struct sk_buff *skb) { __be16 type = skb->protocol; int vlan_depth = ETH_HLEN;

- while (type == htons(ETH_P_8021Q)) { + while (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { struct vlan_hdr *vh;

if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) - return ERR_PTR(-EINVAL); + return 0;

vh = (struct vlan_hdr *)(skb->data + vlan_depth); type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; }

+ return type; +} + +/** + * skb_mac_gso_segment - mac layer segmentation handler. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + */ +struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); + struct packet_offload *ptype; + __be16 type = skb_network_protocol(skb); + + if (unlikely(!type)) + return ERR_PTR(-EINVAL); + __skb_pull(skb, skb->mac_len);

rcu_read_lock(); @@@ -2405,12 -2400,24 +2408,12 @@@ static int dev_gso_segment(struct sk_bu return 0; }

-static bool can_checksum_protocol(netdev_features_t features, __be16 protocol) -{ - return ((features & NETIF_F_GEN_CSUM) || - ((features & NETIF_F_V4_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_V6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); -} - static netdev_features_t harmonize_features(struct sk_buff *skb, __be16 protocol, netdev_features_t features) { if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, protocol)) { features &= ~NETIF_F_ALL_CSUM; - features &= ~NETIF_F_SG; } else if (illegal_highdma(skb->dev, skb)) { features &= ~NETIF_F_SG; } @@@ -2426,22 -2433,20 +2429,22 @@@ netdev_features_t netif_skb_features(st if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK;

- if (protocol == htons(ETH_P_8021Q)) { + if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { return harmonize_features(skb, protocol, features); }

- features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_TX); + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX);

- if (protocol != htons(ETH_P_8021Q)) { + if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) { return harmonize_features(skb, protocol, features); } else { features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | - NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_TX; + NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; return harmonize_features(skb, protocol, features); } } @@@ -2482,9 -2487,8 +2485,9 @@@ int dev_hard_start_xmit(struct sk_buff features = netif_skb_features(skb);

if (vlan_tx_tag_present(skb) && - !(features & NETIF_F_HW_VLAN_TX)) { - skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); + !vlan_hw_offload_capable(features, skb->vlan_proto)) { + skb = __vlan_put_tag(skb, skb->vlan_proto, + vlan_tx_tag_get(skb)); if (unlikely(!skb)) goto out;

@@@ -2588,7 -2592,6 +2591,7 @@@ static void qdisc_pkt_len_init(struct s */ if (shinfo->gso_size) { unsigned int hdr_len; + u16 gso_segs = shinfo->gso_segs;

/* mac layer + network layer */ hdr_len = skb_transport_header(skb) - skb_mac_header(skb); @@@ -2598,12 -2601,7 +2601,12 @@@ hdr_len += tcp_hdrlen(skb); else hdr_len += sizeof(struct udphdr); - qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len; + + if (shinfo->gso_type & SKB_GSO_DODGY) + gso_segs = DIV_ROUND_UP(skb->len - hdr_len, + shinfo->gso_size); + + qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } }

@@@ -3331,7 -3329,7 +3334,7 @@@ EXPORT_SYMBOL_GPL(netdev_rx_handler_reg * netdev_rx_handler_unregister - unregister receive handler * @dev: device to unregister a handler from * - * Unregister a receive hander from a device. + * Unregister a receive handler from a device. * * The caller must hold the rtnl_mutex. */ @@@ -3360,7 -3358,6 +3363,7 @@@ static bool skb_pfmemalloc_protocol(str case __constant_htons(ETH_P_IP): case __constant_htons(ETH_P_IPV6): case __constant_htons(ETH_P_8021Q): + case __constant_htons(ETH_P_8021AD): return true; default: return false; @@@ -3401,8 -3398,7 +3404,8 @@@ another_round

__this_cpu_inc(softnet_data.processed);

- if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { + if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || + skb->protocol == cpu_to_be16(ETH_P_8021AD)) { skb = vlan_untag(skb); if (unlikely(!skb)) goto unlock; @@@ -4070,9 -4066,6 +4073,9 @@@ void netif_napi_add(struct net_device * napi->gro_list = NULL; napi->skb = NULL; napi->poll = poll; + if (weight > NAPI_POLL_WEIGHT) + pr_err_once("netif_napi_add() called with weight %d on device %s\n", + weight, dev->name); napi->weight = weight; list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; @@@ -4934,25 -4927,20 +4937,25 @@@ static netdev_features_t netdev_fix_fea features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); }

- /* Fix illegal SG+CSUM combinations. */ - if ((features & NETIF_F_SG) && - !(features & NETIF_F_ALL_CSUM)) { - netdev_dbg(dev, - "Dropping NETIF_F_SG since no checksum feature.\n"); - features &= ~NETIF_F_SG; - } - /* TSO requires that SG is present as well. */ if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); features &= ~NETIF_F_ALL_TSO; }

+ if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) && + !(features & NETIF_F_IP_CSUM)) { + netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n"); + features &= ~NETIF_F_TSO; + features &= ~NETIF_F_TSO_ECN; + } + + if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) && + !(features & NETIF_F_IPV6_CSUM)) { + netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n"); + features &= ~NETIF_F_TSO6; + } + /* TSO ECN requires that TSO is present as well. */ if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) features &= ~NETIF_F_TSO_ECN; @@@ -5183,8 -5171,7 +5186,8 @@@ int register_netdevice(struct net_devic } }

- if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_FILTER) && + if (((dev->hw_features | dev->features) & + NETIF_F_HW_VLAN_CTAG_FILTER) && (!dev->netdev_ops->ndo_vlan_rx_add_vid || !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); @@@ -5221,10 -5208,6 +5224,10 @@@ */ dev->vlan_features |= NETIF_F_HIGHDMA;

+ /* Make NETIF_F_SG inheritable to tunnel devices. + */ + dev->hw_enc_features |= NETIF_F_SG; + ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) diff --combined net/core/rtnetlink.c index 589d0ab,23854b5..18af08a --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@@ -517,6 -517,32 +517,6 @@@ out return err; }

-static const int rtm_min[RTM_NR_FAMILIES] = -{ - [RTM_FAM(RTM_NEWLINK)] = NLMSG_LENGTH(sizeof(struct ifinfomsg)), - [RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)), - [RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), - [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)), - [RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)), - [RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)), - [RTM_FAM(RTM_NEWTFILTER)] = NLMSG_LENGTH(sizeof(struct tcmsg)), - [RTM_FAM(RTM_NEWACTION)] = NLMSG_LENGTH(sizeof(struct tcamsg)), - [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), - [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), -}; - -static const int rta_max[RTM_NR_FAMILIES] = -{ - [RTM_FAM(RTM_NEWLINK)] = IFLA_MAX, - [RTM_FAM(RTM_NEWADDR)] = IFA_MAX, - [RTM_FAM(RTM_NEWROUTE)] = RTA_MAX, - [RTM_FAM(RTM_NEWRULE)] = FRA_MAX, - [RTM_FAM(RTM_NEWQDISC)] = TCA_MAX, - [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, - [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX, - [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, -}; - int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo) { struct sock *rtnl = net->rtnl; @@@ -1046,7 -1072,7 +1046,7 @@@ static int rtnl_dump_ifinfo(struct sk_b rcu_read_lock(); cb->seq = net->dev_base_seq;

- if (nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, ifla_policy) >= 0) {

if (tb[IFLA_EXT_MASK]) @@@ -1513,7 -1539,7 +1513,7 @@@ errout return err; }

-static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; @@@ -1554,7 -1580,7 +1554,7 @@@ errout return err; }

-static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; @@@ -1685,7 -1711,7 +1685,7 @@@ static int rtnl_group_changelink(struc return 0; }

-static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; @@@ -1840,7 -1866,7 +1840,7 @@@ out } }

-static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh) { struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; @@@ -1896,7 -1922,7 +1896,7 @@@ static u16 rtnl_calcit(struct sk_buff * u32 ext_filter_mask = 0; u16 min_ifinfo_dump_size = 0;

- if (nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); @@@ -1931,11 -1957,8 +1931,11 @@@ static int rtnl_dump_all(struct sk_buf if (rtnl_msg_handlers[idx] == NULL || rtnl_msg_handlers[idx][type].dumpit == NULL) continue; - if (idx > s_idx) + if (idx > s_idx) { memset(&cb->args[0], 0, sizeof(cb->args)); + cb->prev_seq = 0; + cb->seq = 0; + } if (rtnl_msg_handlers[idx][type].dumpit(skb, cb)) break; } @@@ -2028,39 -2051,7 +2028,39 @@@ errout rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); }

-static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +/** + * ndo_dflt_fdb_add - default netdevice operation to add an FDB entry + */ +int ndo_dflt_fdb_add(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, + u16 flags) +{ + int err = -EINVAL; + + /* If aging addresses are supported device will need to + * implement its own handler for this. + */ + if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) { + pr_info("%s: FDB only supports static addresses\n", dev->name); + return err; + } + + if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) + err = dev_uc_add_excl(dev, addr); + else if (is_multicast_ether_addr(addr)) + err = dev_mc_add_excl(dev, addr); + + /* Only return duplicate errors if NLM_F_EXCL is set */ + if (err == -EEXIST && !(flags & NLM_F_EXCL)) + err = 0; + + return err; +} +EXPORT_SYMBOL(ndo_dflt_fdb_add); + +static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ndmsg *ndm; @@@ -2091,7 -2082,7 +2091,7 @@@ }

addr = nla_data(tb[NDA_LLADDR]); - if (!is_valid_ether_addr(addr)) { + if (is_zero_ether_addr(addr)) { pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ether address\n"); return -EINVAL; } @@@ -2112,13 -2103,10 +2112,13 @@@ }

/* Embedded bridge, macvlan, and any other device support */ - if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_add) { - err = dev->netdev_ops->ndo_fdb_add(ndm, tb, - dev, addr, - nlh->nlmsg_flags); + if ((ndm->ndm_flags & NTF_SELF)) { + if (dev->netdev_ops->ndo_fdb_add) + err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr, + nlh->nlmsg_flags); + else + err = ndo_dflt_fdb_add(ndm, tb, dev, addr, + nlh->nlmsg_flags);

if (!err) { rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH); @@@ -2129,36 -2117,7 +2129,36 @@@ out return err; }

-static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +/** + * ndo_dflt_fdb_del - default netdevice operation to delete an FDB entry + */ +int ndo_dflt_fdb_del(struct ndmsg *ndm, + struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr) +{ + int err = -EOPNOTSUPP; + + /* If aging addresses are supported device will need to + * implement its own handler for this. + */ + if (ndm->ndm_state & NUD_PERMANENT) { + pr_info("%s: FDB only supports static addresses\n", dev->name); + return -EINVAL; + } + + if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) + err = dev_uc_del(dev, addr); + else if (is_multicast_ether_addr(addr)) + err = dev_mc_del(dev, addr); + else + err = -EINVAL; + + return err; +} +EXPORT_SYMBOL(ndo_dflt_fdb_del); + +static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ndmsg *ndm; @@@ -2215,11 -2174,8 +2215,11 @@@ }

/* Embedded bridge, macvlan, and any other device support */ - if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_del) { - err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr); + if (ndm->ndm_flags & NTF_SELF) { + if (dev->netdev_ops->ndo_fdb_del) + err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr); + else + err = ndo_dflt_fdb_del(ndm, tb, dev, addr);

if (!err) { rtnl_fdb_notify(dev, addr, RTM_DELNEIGH); @@@ -2264,7 -2220,7 +2264,7 @@@ skip * @dev: netdevice * * Default netdevice operation to dump the existing unicast address list. - * Returns zero on success. + * Returns number of addresses from list put in skb. */ int ndo_dflt_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, @@@ -2304,8 -2260,6 +2304,8 @@@ static int rtnl_fdb_dump(struct sk_buf

if (dev->netdev_ops->ndo_fdb_dump) idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx); + else + idx = ndo_dflt_fdb_dump(skb, cb, dev, idx); } rcu_read_unlock();

@@@ -2457,7 -2411,8 +2457,7 @@@ errout return err; }

-static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, - void *arg) +static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; @@@ -2527,7 -2482,8 +2527,7 @@@ out return err; }

-static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, - void *arg) +static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; @@@ -2597,6 -2553,10 +2597,6 @@@ out return err; }

-/* Protected by RTNL sempahore. */ -static struct rtattr **rta_buf; -static int rtattr_max; - /* Process one rtnetlink message. */

static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) @@@ -2604,6 -2564,7 +2604,6 @@@ struct net *net = sock_net(skb->sk); rtnl_doit_func doit; int sz_idx, kind; - int min_len; int family; int type; int err; @@@ -2615,10 -2576,10 +2615,10 @@@ type -= RTM_BASE;

/* All the messages must have at least 1 byte length */ - if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct rtgenmsg))) + if (nlmsg_len(nlh) < sizeof(struct rtgenmsg)) return 0;

- family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family; + family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family; sz_idx = type>>2; kind = type&3;

@@@ -2651,11 -2612,32 +2651,11 @@@ return err; }

- memset(rta_buf, 0, (rtattr_max * sizeof(struct rtattr *))); - - min_len = rtm_min[sz_idx]; - if (nlh->nlmsg_len < min_len) - return -EINVAL; - - if (nlh->nlmsg_len > min_len) { - int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len); - struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len); - - while (RTA_OK(attr, attrlen)) { - unsigned int flavor = attr->rta_type & NLA_TYPE_MASK; - if (flavor) { - if (flavor > rta_max[sz_idx]) - return -EINVAL; - rta_buf[flavor-1] = attr; - } - attr = RTA_NEXT(attr, attrlen); - } - } - doit = rtnl_get_doit(family, type); if (doit == NULL) return -EOPNOTSUPP;

- return doit(skb, nlh, (void *)&rta_buf[0]); + return doit(skb, nlh); }

static void rtnetlink_rcv(struct sk_buff *skb) @@@ -2725,6 -2707,16 +2725,6 @@@ static struct pernet_operations rtnetli

void __init rtnetlink_init(void) { - int i; - - rtattr_max = 0; - for (i = 0; i < ARRAY_SIZE(rta_max); i++) - if (rta_max[i] > rtattr_max) - rtattr_max = rta_max[i]; - rta_buf = kmalloc(rtattr_max * sizeof(struct rtattr *), GFP_KERNEL); - if (!rta_buf) - panic("rtnetlink_init: cannot allocate rta_buf\n"); - if (register_pernet_subsys(&rtnetlink_net_ops)) panic("rtnetlink_init: cannot initialize rtnetlink\n");

diff --combined net/ipv4/devinet.c index 2759dfd,c6287cd..dfc39d4 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@@ -536,7 -536,7 +536,7 @@@ struct in_ifaddr *inet_ifa_byprefix(str return NULL; }

-static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX+1]; @@@ -587,13 -587,16 +587,16 @@@ static void check_lifetime(struct work_ { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; + struct hlist_node *n; int i;

now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY);

- rcu_read_lock(); for (i = 0; i < IN4_ADDR_HSIZE; i++) { + bool change_needed = false; + + rcu_read_lock(); hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) { unsigned long age;

@@@ -606,16 -609,7 +609,7 @@@

if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { - struct in_ifaddr **ifap ; - - rtnl_lock(); - for (ifap = &ifa->ifa_dev->ifa_list; - *ifap != NULL; ifap = &ifa->ifa_next) { - if (*ifap == ifa) - inet_del_ifa(ifa->ifa_dev, - ifap, 1); - } - rtnl_unlock(); + change_needed = true; } else if (ifa->ifa_preferred_lft == INFINITY_LIFE_TIME) { continue; @@@ -625,10 -619,8 +619,8 @@@ next = ifa->ifa_tstamp + ifa->ifa_valid_lft * HZ;

- if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) { - ifa->ifa_flags |= IFA_F_DEPRECATED; - rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); - } + if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) + change_needed = true; } else if (time_before(ifa->ifa_tstamp + ifa->ifa_preferred_lft * HZ, next)) { @@@ -636,8 -628,42 +628,42 @@@ ifa->ifa_preferred_lft * HZ; } } + rcu_read_unlock(); + if (!change_needed) + continue; + rtnl_lock(); + hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) { + unsigned long age; + + if (ifa->ifa_flags & IFA_F_PERMANENT) + continue; + + /* We try to batch several events at once. */ + age = (now - ifa->ifa_tstamp + + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + + if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && + age >= ifa->ifa_valid_lft) { + struct in_ifaddr **ifap; + + for (ifap = &ifa->ifa_dev->ifa_list; + *ifap != NULL; ifap = &(*ifap)->ifa_next) { + if (*ifap == ifa) { + inet_del_ifa(ifa->ifa_dev, + ifap, 1); + break; + } + } + } else if (ifa->ifa_preferred_lft != + INFINITY_LIFE_TIME && + age >= ifa->ifa_preferred_lft && + !(ifa->ifa_flags & IFA_F_DEPRECATED)) { + ifa->ifa_flags |= IFA_F_DEPRECATED; + rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); + } + } + rtnl_unlock(); } - rcu_read_unlock();

next_sec = round_jiffies_up(next); next_sched = next; @@@ -775,7 -801,7 +801,7 @@@ static struct in_ifaddr *find_matching_ return NULL; }

-static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct in_ifaddr *ifa; @@@ -804,6 -830,8 +830,8 @@@ return -EEXIST; ifa = ifa_existing; set_ifa_lifetime(ifa, valid_lft, prefered_lft); + cancel_delayed_work(&check_lifetime_work); + schedule_delayed_work(&check_lifetime_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); } @@@ -1501,8 -1529,6 +1529,8 @@@ static int inet_dump_ifaddr(struct sk_b idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); + cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ + net->dev_base_seq; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@@ -1523,7 -1549,6 +1551,7 @@@ rcu_read_unlock(); goto done; } + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); } cont: idx++; @@@ -1735,7 -1760,8 +1763,7 @@@ static const struct nla_policy devconf_ };

static int inet_netconf_get_devconf(struct sk_buff *in_skb, - struct nlmsghdr *nlh, - void *arg) + struct nlmsghdr *nlh) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX+1]; @@@ -1795,77 -1821,6 +1823,77 @@@ errout return err; }

+static int inet_netconf_dump_devconf(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + int h, s_h; + int idx, s_idx; + struct net_device *dev; + struct in_device *in_dev; + struct hlist_head *head; + + s_h = cb->args[0]; + s_idx = idx = cb->args[1]; + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + rcu_read_lock(); + cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ + net->dev_base_seq; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + goto cont; + + if (inet_netconf_fill_devconf(skb, dev->ifindex, + &in_dev->cnf, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNETCONF, + NLM_F_MULTI, + -1) <= 0) { + rcu_read_unlock(); + goto done; + } + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); +cont: + idx++; + } + rcu_read_unlock(); + } + if (h == NETDEV_HASHENTRIES) { + if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, + net->ipv4.devconf_all, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + -1) <= 0) + goto done; + else + h++; + } + if (h == NETDEV_HASHENTRIES + 1) { + if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, + net->ipv4.devconf_dflt, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + -1) <= 0) + goto done; + else + h++; + } +done: + cb->args[0] = h; + cb->args[1] = idx; + + return skb->len; +} + #ifdef CONFIG_SYSCTL

static void devinet_copy_dflt_conf(struct net *net, int i) @@@ -2270,6 -2225,6 +2298,6 @@@ void __init devinet_init(void rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL); rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL); rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf, - NULL, NULL); + inet_netconf_dump_devconf, NULL); }

diff --combined net/ipv4/ip_fragment.c index 9385206,52c273e..b66910a --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@@ -79,11 -79,40 +79,11 @@@ struct ipq struct inet_peer *peer; };

-/* RFC 3168 support : - * We want to check ECN values of all fragments, do detect invalid combinations. - * In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value. - */ -#define IPFRAG_ECN_NOT_ECT 0x01 /* one frag had ECN_NOT_ECT */ -#define IPFRAG_ECN_ECT_1 0x02 /* one frag had ECN_ECT_1 */ -#define IPFRAG_ECN_ECT_0 0x04 /* one frag had ECN_ECT_0 */ -#define IPFRAG_ECN_CE 0x08 /* one frag had ECN_CE */ - static inline u8 ip4_frag_ecn(u8 tos) { return 1 << (tos & INET_ECN_MASK); }

-/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements - * Value : 0xff if frame should be dropped. - * 0 or INET_ECN_CE value, to be ORed in to final iph->tos field - */ -static const u8 ip4_frag_ecn_table[16] = { - /* at least one fragment had CE, and others ECT_0 or ECT_1 */ - [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = INET_ECN_CE, - [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = INET_ECN_CE, - [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = INET_ECN_CE, - - /* invalid combinations : drop frame */ - [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff, - [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff, - [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff, - [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff, - [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff, - [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff, - [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff, -}; - static struct inet_frags ip4_frags;

int ip_frag_nqueues(struct net *net) @@@ -219,8 -248,7 +219,7 @@@ static void ip_expire(unsigned long arg if (!head->dev) goto out_rcu_unlock;

- /* skb dst is stale, drop it, and perform route lookup again */ - skb_dst_drop(head); + /* skb has no dst, perform route lookup again */ iph = ip_hdr(head); err = ip_route_input_noref(head, iph->daddr, iph->saddr, iph->tos, head->dev); @@@ -494,9 -522,16 +493,16 @@@ found qp->q.max_size = skb->len + ihl;

if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - qp->q.meat == qp->q.len) - return ip_frag_reasm(qp, prev, dev); + qp->q.meat == qp->q.len) { + unsigned long orefdst = skb->_skb_refdst;

+ skb->_skb_refdst = 0UL; + err = ip_frag_reasm(qp, prev, dev); + skb->_skb_refdst = orefdst; + return err; + } + + skb_dst_drop(skb); inet_frag_lru_move(&qp->q); return -EINPROGRESS;

@@@ -522,7 -557,7 +528,7 @@@ static int ip_frag_reasm(struct ipq *qp

ipq_kill(qp);

- ecn = ip4_frag_ecn_table[qp->ecn]; + ecn = ip_frag_ecn_table[qp->ecn]; if (unlikely(ecn == 0xff)) { err = -EINVAL; goto out_fail; diff --combined net/ipv4/syncookies.c index 7f4a5cb,397e0f6..b05c96e --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@@ -267,6 -267,7 +267,6 @@@ struct sock *cookie_v4_check(struct soc struct ip_options *opt) { struct tcp_options_received tcp_opt; - const u8 *hash_location; struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct tcp_sock *tp = tcp_sk(sk); @@@ -293,7 -294,7 +293,7 @@@

/* check for timestamp cookie support */ memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); + tcp_parse_options(skb, &tcp_opt, 0, NULL);

if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok)) goto out; @@@ -348,8 -349,8 +348,8 @@@ * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk), - RT_SCOPE_UNIVERSE, IPPROTO_TCP, + flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark, + RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, ireq->loc_addr, th->source, th->dest); diff --combined net/ipv4/tcp_input.c index 6d9ca35,13b9c08..aafd052 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@@ -93,11 -93,12 +93,11 @@@ int sysctl_tcp_stdurg __read_mostly int sysctl_tcp_rfc1337 __read_mostly; int sysctl_tcp_max_orphans __read_mostly = NR_FILE; int sysctl_tcp_frto __read_mostly = 2; -int sysctl_tcp_frto_response __read_mostly;

int sysctl_tcp_thin_dupack __read_mostly;

int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; -int sysctl_tcp_early_retrans __read_mostly = 2; +int sysctl_tcp_early_retrans __read_mostly = 3;

#define FLAG_DATA 0x01 /* Incoming frame contained data. */ #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ @@@ -107,15 -108,18 +107,16 @@@ #define FLAG_DATA_SACKED 0x20 /* New SACK. */ #define FLAG_ECE 0x40 /* ECE in this ACK */ #define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/ -#define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */ +#define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ -#define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ + #define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */

#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED) #define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED) #define FLAG_CA_ALERT (FLAG_DATA_SACKED|FLAG_ECE) #define FLAG_FORWARD_PROGRESS (FLAG_ACKED|FLAG_DATA_SACKED) -#define FLAG_ANY_PROGRESS (FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED)

#define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH) #define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH)) @@@ -1156,8 -1160,10 +1157,8 @@@ static u8 tcp_sacktag_one(struct sock * tcp_highest_sack_seq(tp))) state->reord = min(fack_count, state->reord); - - /* SACK enhanced F-RTO (RFC4138; Appendix B) */ - if (!after(end_seq, tp->frto_highmark)) - state->flag |= FLAG_ONLY_ORIG_SACKED; + if (!after(end_seq, tp->high_seq)) + state->flag |= FLAG_ORIG_SACK_ACKED; }

if (sacked & TCPCB_LOST) { @@@ -1550,6 -1556,7 +1551,6 @@@ static in tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, u32 prior_snd_una) { - const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); const unsigned char *ptr = (skb_transport_header(ack_skb) + TCP_SKB_CB(ack_skb)->sacked); @@@ -1722,6 -1729,12 +1723,6 @@@ walk start_seq, end_seq, dup_sack);

advance_sp: - /* SACK enhanced FRTO (RFC4138, Appendix B): Clearing correct - * due to in-order walk - */ - if (after(end_seq, tp->frto_highmark)) - state.flag &= ~FLAG_ONLY_ORIG_SACKED; - i++; }

@@@ -1738,7 -1751,8 +1739,7 @@@ tcp_verify_left_out(tp);

if ((state.reord < tp->fackets_out) && - ((icsk->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker) && - (!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark))) + ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) tcp_update_reordering(sk, tp->fackets_out - state.reord, 0);

out: @@@ -1812,6 -1826,197 +1813,6 @@@ static inline void tcp_reset_reno_sack( tp->sacked_out = 0; }

-static int tcp_is_sackfrto(const struct tcp_sock *tp) -{ - return (sysctl_tcp_frto == 0x2) && !tcp_is_reno(tp); -} - -/* F-RTO can only be used if TCP has never retransmitted anything other than - * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here) - */ -bool tcp_use_frto(struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - const struct inet_connection_sock *icsk = inet_csk(sk); - struct sk_buff *skb; - - if (!sysctl_tcp_frto) - return false; - - /* MTU probe and F-RTO won't really play nicely along currently */ - if (icsk->icsk_mtup.probe_size) - return false; - - if (tcp_is_sackfrto(tp)) - return true; - - /* Avoid expensive walking of rexmit queue if possible */ - if (tp->retrans_out > 1) - return false; - - skb = tcp_write_queue_head(sk); - if (tcp_skb_is_last(sk, skb)) - return true; - skb = tcp_write_queue_next(sk, skb); /* Skips head */ - tcp_for_write_queue_from(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) - return false; - /* Short-circuit when first non-SACKed skb has been checked */ - if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) - break; - } - return true; -} - -/* RTO occurred, but do not yet enter Loss state. Instead, defer RTO - * recovery a bit and use heuristics in tcp_process_frto() to detect if - * the RTO was spurious. Only clear SACKED_RETRANS of the head here to - * keep retrans_out counting accurate (with SACK F-RTO, other than head - * may still have that bit set); TCPCB_LOST and remaining SACKED_RETRANS - * bits are handled if the Loss state is really to be entered (in - * tcp_enter_frto_loss). - * - * Do like tcp_enter_loss() would; when RTO expires the second time it - * does: - * "Reduce ssthresh if it has not yet been made inside this window." - */ -void tcp_enter_frto(struct sock *sk) -{ - const struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - - if ((!tp->frto_counter && icsk->icsk_ca_state <= TCP_CA_Disorder) || - tp->snd_una == tp->high_seq || - ((icsk->icsk_ca_state == TCP_CA_Loss || tp->frto_counter) && - !icsk->icsk_retransmits)) { - tp->prior_ssthresh = tcp_current_ssthresh(sk); - /* Our state is too optimistic in ssthresh() call because cwnd - * is not reduced until tcp_enter_frto_loss() when previous F-RTO - * recovery has not yet completed. Pattern would be this: RTO, - * Cumulative ACK, RTO (2xRTO for the same segment does not end - * up here twice). - * RFC4138 should be more specific on what to do, even though - * RTO is quite unlikely to occur after the first Cumulative ACK - * due to back-off and complexity of triggering events ... - */ - if (tp->frto_counter) { - u32 stored_cwnd; - stored_cwnd = tp->snd_cwnd; - tp->snd_cwnd = 2; - tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); - tp->snd_cwnd = stored_cwnd; - } else { - tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); - } - /* ... in theory, cong.control module could do "any tricks" in - * ssthresh(), which means that ca_state, lost bits and lost_out - * counter would have to be faked before the call occurs. We - * consider that too expensive, unlikely and hacky, so modules - * using these in ssthresh() must deal these incompatibility - * issues if they receives CA_EVENT_FRTO and frto_counter != 0 - */ - tcp_ca_event(sk, CA_EVENT_FRTO); - } - - tp->undo_marker = tp->snd_una; - tp->undo_retrans = 0; - - skb = tcp_write_queue_head(sk); - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) - tp->undo_marker = 0; - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; - tp->retrans_out -= tcp_skb_pcount(skb); - } - tcp_verify_left_out(tp); - - /* Too bad if TCP was application limited */ - tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp) + 1); - - /* Earlier loss recovery underway (see RFC4138; Appendix B). - * The last condition is necessary at least in tp->frto_counter case. - */ - if (tcp_is_sackfrto(tp) && (tp->frto_counter || - ((1 << icsk->icsk_ca_state) & (TCPF_CA_Recovery|TCPF_CA_Loss))) && - after(tp->high_seq, tp->snd_una)) { - tp->frto_highmark = tp->high_seq; - } else { - tp->frto_highmark = tp->snd_nxt; - } - tcp_set_ca_state(sk, TCP_CA_Disorder); - tp->high_seq = tp->snd_nxt; - tp->frto_counter = 1; -} - -/* Enter Loss state after F-RTO was applied. Dupack arrived after RTO, - * which indicates that we should follow the traditional RTO recovery, - * i.e. mark everything lost and do go-back-N retransmission. - */ -static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) -{ - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - - tp->lost_out = 0; - tp->retrans_out = 0; - if (tcp_is_reno(tp)) - tcp_reset_reno_sack(tp); - - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - - TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; - /* - * Count the retransmission made on RTO correctly (only when - * waiting for the first ACK and did not get it)... - */ - if ((tp->frto_counter == 1) && !(flag & FLAG_DATA_ACKED)) { - /* For some reason this R-bit might get cleared? */ - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) - tp->retrans_out += tcp_skb_pcount(skb); - /* ...enter this if branch just for the first segment */ - flag |= FLAG_DATA_ACKED; - } else { - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) - tp->undo_marker = 0; - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; - } - - /* Marking forward transmissions that were made after RTO lost - * can cause unnecessary retransmissions in some scenarios, - * SACK blocks will mitigate that in some but not in all cases. - * We used to not mark them but it was causing break-ups with - * receivers that do only in-order receival. - * - * TODO: we could detect presence of such receiver and select - * different behavior per flow. - */ - if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { - TCP_SKB_CB(skb)->sacked |= TCPCB_LOST; - tp->lost_out += tcp_skb_pcount(skb); - tp->retransmit_high = TCP_SKB_CB(skb)->end_seq; - } - } - tcp_verify_left_out(tp); - - tp->snd_cwnd = tcp_packets_in_flight(tp) + allowed_segments; - tp->snd_cwnd_cnt = 0; - tp->snd_cwnd_stamp = tcp_time_stamp; - tp->frto_counter = 0; - - tp->reordering = min_t(unsigned int, tp->reordering, - sysctl_tcp_reordering); - tcp_set_ca_state(sk, TCP_CA_Loss); - tp->high_seq = tp->snd_nxt; - TCP_ECN_queue_cwr(tp); - - tcp_clear_all_retrans_hints(tp); -} - static void tcp_clear_retrans_partial(struct tcp_sock *tp) { tp->retrans_out = 0; @@@ -1838,13 -2043,10 +1839,13 @@@ void tcp_enter_loss(struct sock *sk, in const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; + bool new_recovery = false;

/* Reduce ssthresh if it has not yet been made inside this window. */ - if (icsk->icsk_ca_state <= TCP_CA_Disorder || tp->snd_una == tp->high_seq || + if (icsk->icsk_ca_state <= TCP_CA_Disorder || + !after(tp->high_seq, tp->snd_una) || (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) { + new_recovery = true; tp->prior_ssthresh = tcp_current_ssthresh(sk); tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); tcp_ca_event(sk, CA_EVENT_LOSS); @@@ -1886,14 -2088,8 +1887,14 @@@ tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; TCP_ECN_queue_cwr(tp); - /* Abort F-RTO algorithm if one is in progress */ - tp->frto_counter = 0; + + /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous + * loss recovery is underway except recurring timeout(s) on + * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing + */ + tp->frto = sysctl_tcp_frto && + (new_recovery || icsk->icsk_retransmits) && + !inet_csk(sk)->icsk_mtup.probe_size; }

/* If ACK arrived pointing to a remembered SACK, it means that our @@@ -1952,16 -2148,15 +1953,16 @@@ static bool tcp_pause_early_retransmit( * max(RTT/4, 2msec) unless ack has ECE mark, no RTT samples * available, or RTO is scheduled to fire first. */ - if (sysctl_tcp_early_retrans < 2 || (flag & FLAG_ECE) || !tp->srtt) + if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 || + (flag & FLAG_ECE) || !tp->srtt) return false;

delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2)); if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay))) return false;

- inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, TCP_RTO_MAX); - tp->early_retrans_delayed = 1; + inet_csk_reset_xmit_timer(sk, ICSK_TIME_EARLY_RETRANS, delay, + TCP_RTO_MAX); return true; }

@@@ -2077,6 -2272,10 +2078,6 @@@ static bool tcp_time_to_recover(struct struct tcp_sock *tp = tcp_sk(sk); __u32 packets_out;

- /* Do not perform any recovery during F-RTO algorithm */ - if (tp->frto_counter) - return false; - /* Trick#1: The loss is proven. */ if (tp->lost_out) return true; @@@ -2120,7 -2319,7 +2121,7 @@@ * interval if appropriate. */ if (tp->do_early_retrans && !tp->retrans_out && tp->sacked_out && - (tp->packets_out == (tp->sacked_out + 1) && tp->packets_out < 4) && + (tp->packets_out >= (tp->sacked_out + 1) && tp->packets_out < 4) && !tcp_may_send_now(sk)) return !tcp_pause_early_retransmit(sk, flag);

@@@ -2437,12 -2636,12 +2438,12 @@@ static int tcp_try_undo_partial(struct return failed; }

-/* Undo during loss recovery after partial ACK. */ -static bool tcp_try_undo_loss(struct sock *sk) +/* Undo during loss recovery after partial ACK or using F-RTO. */ +static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) { struct tcp_sock *tp = tcp_sk(sk);

- if (tcp_may_undo(tp)) { + if (frto_undo || tcp_may_undo(tp)) { struct sk_buff *skb; tcp_for_write_queue(skb, sk) { if (skb == tcp_send_head(sk)) @@@ -2456,12 -2655,9 +2457,12 @@@ tp->lost_out = 0; tcp_undo_cwr(sk, true); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO); + if (frto_undo) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPSPURIOUSRTOS); inet_csk(sk)->icsk_retransmits = 0; tp->undo_marker = 0; - if (tcp_is_sack(tp)) + if (frto_undo || tcp_is_sack(tp)) tcp_set_ca_state(sk, TCP_CA_Open); return true; } @@@ -2483,7 -2679,6 +2484,7 @@@ static void tcp_init_cwnd_reduction(str struct tcp_sock *tp = tcp_sk(sk);

tp->high_seq = tp->snd_nxt; + tp->tlp_high_seq = 0; tp->snd_cwnd_cnt = 0; tp->prior_cwnd = tp->snd_cwnd; tp->prr_delivered = 0; @@@ -2561,7 -2756,7 +2562,7 @@@ static void tcp_try_to_open(struct soc

tcp_verify_left_out(tp);

- if (!tp->frto_counter && !tcp_any_retrans_done(sk)) + if (!tcp_any_retrans_done(sk)) tp->retrans_stamp = 0;

if (flag & FLAG_ECE) @@@ -2678,58 -2873,6 +2679,58 @@@ static void tcp_enter_recovery(struct s tcp_set_ca_state(sk, TCP_CA_Recovery); }

+/* Process an ACK in CA_Loss state. Move to CA_Open if lost data are + * recovered or spurious. Otherwise retransmits more on partial ACKs. + */ +static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + bool recovered = !before(tp->snd_una, tp->high_seq); + + if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ + if (flag & FLAG_ORIG_SACK_ACKED) { + /* Step 3.b. A timeout is spurious if not all data are + * lost, i.e., never-retransmitted data are (s)acked. + */ + tcp_try_undo_loss(sk, true); + return; + } + if (after(tp->snd_nxt, tp->high_seq) && + (flag & FLAG_DATA_SACKED || is_dupack)) { + tp->frto = 0; /* Loss was real: 2nd part of step 3.a */ + } else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) { + tp->high_seq = tp->snd_nxt; + __tcp_push_pending_frames(sk, tcp_current_mss(sk), + TCP_NAGLE_OFF); + if (after(tp->snd_nxt, tp->high_seq)) + return; /* Step 2.b */ + tp->frto = 0; + } + } + + if (recovered) { + /* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */ + icsk->icsk_retransmits = 0; + tcp_try_undo_recovery(sk); + return; + } + if (flag & FLAG_DATA_ACKED) + icsk->icsk_retransmits = 0; + if (tcp_is_reno(tp)) { + /* A Reno DUPACK means new data in F-RTO step 2.b above are + * delivered. Lower inflight to clock out (re)tranmissions. + */ + if (after(tp->snd_nxt, tp->high_seq) && is_dupack) + tcp_add_reno_sack(sk); + else if (flag & FLAG_SND_UNA_ADVANCED) + tcp_reset_reno_sack(tp); + } + if (tcp_try_undo_loss(sk, false)) + return; + tcp_xmit_retransmit_queue(sk); +} + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@@ -2776,6 -2919,12 +2777,6 @@@ static void tcp_fastretrans_alert(struc tp->retrans_stamp = 0; } else if (!before(tp->snd_una, tp->high_seq)) { switch (icsk->icsk_ca_state) { - case TCP_CA_Loss: - icsk->icsk_retransmits = 0; - if (tcp_try_undo_recovery(sk)) - return; - break; - case TCP_CA_CWR: /* CWR is to be held something *above* high_seq * is ACKed for CWR bit to reach receiver. */ @@@ -2806,10 -2955,18 +2807,10 @@@ newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked; break; case TCP_CA_Loss: - if (flag & FLAG_DATA_ACKED) - icsk->icsk_retransmits = 0; - if (tcp_is_reno(tp) && flag & FLAG_SND_UNA_ADVANCED) - tcp_reset_reno_sack(tp); - if (!tcp_try_undo_loss(sk)) { - tcp_moderate_cwnd(tp); - tcp_xmit_retransmit_queue(sk); - return; - } + tcp_process_loss(sk, flag, is_dupack); if (icsk->icsk_ca_state != TCP_CA_Open) return; - /* Loss is undone; fall through to processing in Open state. */ + /* Fall through to processing in Open state. */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) @@@ -2922,7 -3079,6 +2923,7 @@@ static void tcp_cong_avoid(struct sock */ void tcp_rearm_rto(struct sock *sk) { + const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk);

/* If the retrans timer is currently being used by Fast Open @@@ -2936,13 -3092,12 +2937,13 @@@ } else { u32 rto = inet_csk(sk)->icsk_rto; /* Offset the time elapsed after installing regular RTO */ - if (tp->early_retrans_delayed) { + if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { struct sk_buff *skb = tcp_write_queue_head(sk); const u32 rto_time_stamp = TCP_SKB_CB(skb)->when + rto; s32 delta = (s32)(rto_time_stamp - tcp_time_stamp); /* delta may not be positive if the socket is locked - * when the delayed ER timer fires and is rescheduled. + * when the retrans timer fires and is rescheduled. */ if (delta > 0) rto = delta; @@@ -2950,6 -3105,7 +2951,6 @@@ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, TCP_RTO_MAX); } - tp->early_retrans_delayed = 0; }

/* This function is called when the delayed ER timer fires. TCP enters @@@ -3037,6 -3193,8 +3038,6 @@@ static int tcp_clean_rtx_queue(struct s flag |= FLAG_RETRANS_DATA_ACKED; ca_seq_rtt = -1; seq_rtt = -1; - if ((flag & FLAG_DATA_ACKED) || (acked_pcount > 1)) - flag |= FLAG_NONHEAD_RETRANS_ACKED; } else { ca_seq_rtt = now - scb->when; last_ackt = skb->tstamp; @@@ -3045,8 -3203,6 +3046,8 @@@ } if (!(sacked & TCPCB_SACKED_ACKED)) reord = min(pkts_acked, reord); + if (!after(scb->end_seq, tp->high_seq)) + flag |= FLAG_ORIG_SACK_ACKED; }

if (sacked & TCPCB_SACKED_ACKED) @@@ -3247,6 -3403,150 +3248,6 @@@ static int tcp_ack_update_window(struc return flag; }

-/* A very conservative spurious RTO response algorithm: reduce cwnd and - * continue in congestion avoidance. - */ -static void tcp_conservative_spur_to_response(struct tcp_sock *tp) -{ - tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); - tp->snd_cwnd_cnt = 0; - TCP_ECN_queue_cwr(tp); - tcp_moderate_cwnd(tp); -} - -/* A conservative spurious RTO response algorithm: reduce cwnd using - * PRR and continue in congestion avoidance. - */ -static void tcp_cwr_spur_to_response(struct sock *sk) -{ - tcp_enter_cwr(sk, 0); -} - -static void tcp_undo_spur_to_response(struct sock *sk, int flag) -{ - if (flag & FLAG_ECE) - tcp_cwr_spur_to_response(sk); - else - tcp_undo_cwr(sk, true); -} - -/* F-RTO spurious RTO detection algorithm (RFC4138) - * - * F-RTO affects during two new ACKs following RTO (well, almost, see inline - * comments). State (ACK number) is kept in frto_counter. When ACK advances - * window (but not to or beyond highest sequence sent before RTO): - * On First ACK, send two new segments out. - * On Second ACK, RTO was likely spurious. Do spurious response (response - * algorithm is not part of the F-RTO detection algorithm - * given in RFC4138 but can be selected separately). - * Otherwise (basically on duplicate ACK), RTO was (likely) caused by a loss - * and TCP falls back to conventional RTO recovery. F-RTO allows overriding - * of Nagle, this is done using frto_counter states 2 and 3, when a new data - * segment of any size sent during F-RTO, state 2 is upgraded to 3. - * - * Rationale: if the RTO was spurious, new ACKs should arrive from the - * original window even after we transmit two new data segments. - * - * SACK version: - * on first step, wait until first cumulative ACK arrives, then move to - * the second step. In second step, the next ACK decides. - * - * F-RTO is implemented (mainly) in four functions: - * - tcp_use_frto() is used to determine if TCP is can use F-RTO - * - tcp_enter_frto() prepares TCP state on RTO if F-RTO is used, it is - * called when tcp_use_frto() showed green light - * - tcp_process_frto() handles incoming ACKs during F-RTO algorithm - * - tcp_enter_frto_loss() is called if there is not enough evidence - * to prove that the RTO is indeed spurious. It transfers the control - * from F-RTO to the conventional RTO recovery - */ -static bool tcp_process_frto(struct sock *sk, int flag) -{ - struct tcp_sock *tp = tcp_sk(sk); - - tcp_verify_left_out(tp); - - /* Duplicate the behavior from Loss state (fastretrans_alert) */ - if (flag & FLAG_DATA_ACKED) - inet_csk(sk)->icsk_retransmits = 0; - - if ((flag & FLAG_NONHEAD_RETRANS_ACKED) || - ((tp->frto_counter >= 2) && (flag & FLAG_RETRANS_DATA_ACKED))) - tp->undo_marker = 0; - - if (!before(tp->snd_una, tp->frto_highmark)) { - tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag); - return true; - } - - if (!tcp_is_sackfrto(tp)) { - /* RFC4138 shortcoming in step 2; should also have case c): - * ACK isn't duplicate nor advances window, e.g., opposite dir - * data, winupdate - */ - if (!(flag & FLAG_ANY_PROGRESS) && (flag & FLAG_NOT_DUP)) - return true; - - if (!(flag & FLAG_DATA_ACKED)) { - tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 0 : 3), - flag); - return true; - } - } else { - if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) { - if (!tcp_packets_in_flight(tp)) { - tcp_enter_frto_loss(sk, 2, flag); - return true; - } - - /* Prevent sending of new data. */ - tp->snd_cwnd = min(tp->snd_cwnd, - tcp_packets_in_flight(tp)); - return true; - } - - if ((tp->frto_counter >= 2) && - (!(flag & FLAG_FORWARD_PROGRESS) || - ((flag & FLAG_DATA_SACKED) && - !(flag & FLAG_ONLY_ORIG_SACKED)))) { - /* RFC4138 shortcoming (see comment above) */ - if (!(flag & FLAG_FORWARD_PROGRESS) && - (flag & FLAG_NOT_DUP)) - return true; - - tcp_enter_frto_loss(sk, 3, flag); - return true; - } - } - - if (tp->frto_counter == 1) { - /* tcp_may_send_now needs to see updated state */ - tp->snd_cwnd = tcp_packets_in_flight(tp) + 2; - tp->frto_counter = 2; - - if (!tcp_may_send_now(sk)) - tcp_enter_frto_loss(sk, 2, flag); - - return true; - } else { - switch (sysctl_tcp_frto_response) { - case 2: - tcp_undo_spur_to_response(sk, flag); - break; - case 1: - tcp_conservative_spur_to_response(tp); - break; - default: - tcp_cwr_spur_to_response(sk); - break; - } - tp->frto_counter = 0; - tp->undo_marker = 0; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); - } - return false; -} - /* RFC 5961 7 [ACK Throttling] */ static void tcp_send_challenge_ack(struct sock *sk) { @@@ -3265,38 -3565,27 +3266,59 @@@ } }

+ static void tcp_store_ts_recent(struct tcp_sock *tp) + { + tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; + tp->rx_opt.ts_recent_stamp = get_seconds(); + } + + static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) + { + if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { + /* PAWS bug workaround wrt. ACK frames, the PAWS discard + * extra check below makes sure this can only happen + * for pure ACK frames. -DaveM + * + * Not only, also it occurs for expired timestamps. + */ + + if (tcp_paws_check(&tp->rx_opt, 0)) + tcp_store_ts_recent(tp); + } + } + +/* This routine deals with acks during a TLP episode. + * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe. + */ +static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + bool is_tlp_dupack = (ack == tp->tlp_high_seq) && + !(flag & (FLAG_SND_UNA_ADVANCED | + FLAG_NOT_DUP | FLAG_DATA_SACKED)); + + /* Mark the end of TLP episode on receiving TLP dupack or when + * ack is after tlp_high_seq. + */ + if (is_tlp_dupack) { + tp->tlp_high_seq = 0; + return; + } + + if (after(ack, tp->tlp_high_seq)) { + tp->tlp_high_seq = 0; + /* Don't reduce cwnd if DSACK arrives for TLP retrans. */ + if (!(flag & FLAG_DSACKING_ACK)) { + tcp_init_cwnd_reduction(sk, true); + tcp_set_ca_state(sk, TCP_CA_CWR); + tcp_end_cwnd_reduction(sk); + tcp_set_ca_state(sk, TCP_CA_Open); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPLOSSPROBERECOVERY); + } + } +} + /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { @@@ -3311,6 -3600,7 +3333,6 @@@ int prior_packets; int prior_sacked = tp->sacked_out; int pkts_acked = 0; - bool frto_cwnd = false;

/* If the ack is older than previous acks * then we can probably ignore it. @@@ -3330,8 -3620,7 +3352,8 @@@ if (after(ack, tp->snd_nxt)) goto invalid_ack;

- if (tp->early_retrans_delayed) + if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk);

if (after(ack, prior_snd_una)) @@@ -3340,6 -3629,12 +3362,12 @@@ prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp);

+ /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + if (flag & FLAG_UPDATE_TS_RECENT) + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) { /* Window is constant, pure forward advance. * No more checks are required. @@@ -3384,29 -3679,30 +3412,29 @@@

pkts_acked = prior_packets - tp->packets_out;

- if (tp->frto_counter) - frto_cwnd = tcp_process_frto(sk, flag); - /* Guarantee sacktag reordering detection against wrap-arounds */ - if (before(tp->frto_highmark, tp->snd_una)) - tp->frto_highmark = 0; - if (tcp_ack_is_dubious(sk, flag)) { /* Advance CWND, if state allows this. */ - if ((flag & FLAG_DATA_ACKED) && !frto_cwnd && - tcp_may_raise_cwnd(sk, flag)) + if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, pkts_acked, prior_sacked, is_dupack, flag); } else { - if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) + if (flag & FLAG_DATA_ACKED) tcp_cong_avoid(sk, ack, prior_in_flight); }

+ if (tp->tlp_high_seq) + tcp_process_tlp_ack(sk, ack, flag); + if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) { struct dst_entry *dst = __sk_dst_get(sk); if (dst) dst_confirm(dst); } + + if (icsk->icsk_pending == ICSK_TIME_RETRANS) + tcp_schedule_loss_probe(sk); return 1;

no_queue: @@@ -3420,9 -3716,6 +3448,9 @@@ */ if (tcp_send_head(sk)) tcp_ack_probe(sk); + + if (tp->tlp_high_seq) + tcp_process_tlp_ack(sk, ack, flag); return 1;

invalid_ack: @@@ -3447,8 -3740,8 +3475,8 @@@ old_ack * But, this can also be called on packets in the established flow when * the fast version below fails. */ -void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx, - const u8 **hvpp, int estab, +void tcp_parse_options(const struct sk_buff *skb, + struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc) { const unsigned char *ptr; @@@ -3532,6 -3825,31 +3560,6 @@@ */ break; #endif - case TCPOPT_COOKIE: - /* This option is variable length. - */ - switch (opsize) { - case TCPOLEN_COOKIE_BASE: - /* not yet implemented */ - break; - case TCPOLEN_COOKIE_PAIR: - /* not yet implemented */ - break; - case TCPOLEN_COOKIE_MIN+0: - case TCPOLEN_COOKIE_MIN+2: - case TCPOLEN_COOKIE_MIN+4: - case TCPOLEN_COOKIE_MIN+6: - case TCPOLEN_COOKIE_MAX: - /* 16-bit multiple */ - opt_rx->cookie_plus = opsize; - *hvpp = ptr; - break; - default: - /* ignore option */ - break; - } - break; - case TCPOPT_EXP: /* Fast Open option shares code 254 using a * 16 bits magic number. It's valid only in @@@ -3577,7 -3895,8 +3605,7 @@@ static bool tcp_parse_aligned_timestamp * If it is wrong it falls back on tcp_parse_options(). */ static bool tcp_fast_parse_options(const struct sk_buff *skb, - const struct tcphdr *th, - struct tcp_sock *tp, const u8 **hvpp) + const struct tcphdr *th, struct tcp_sock *tp) { /* In the spirit of fast parsing, compare doff directly to constant * values. Because equality is used, short doff can be ignored here. @@@ -3591,7 -3910,7 +3619,7 @@@ return true; }

- tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); + tcp_parse_options(skb, &tp->rx_opt, 1, NULL); if (tp->rx_opt.saw_tstamp) tp->rx_opt.rcv_tsecr -= tp->tsoffset;

@@@ -3636,27 -3955,6 +3664,6 @@@ const u8 *tcp_parse_md5sig_option(cons EXPORT_SYMBOL(tcp_parse_md5sig_option); #endif

- static inline void tcp_store_ts_recent(struct tcp_sock *tp) - { - tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; - tp->rx_opt.ts_recent_stamp = get_seconds(); - } - - static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) - { - if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { - /* PAWS bug workaround wrt. ACK frames, the PAWS discard - * extra check below makes sure this can only happen - * for pure ACK frames. -DaveM - * - * Not only, also it occurs for expired timestamps. - */ - - if (tcp_paws_check(&tp->rx_opt, 0)) - tcp_store_ts_recent(tp); - } - } - /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM * * It is not fatal. If this ACK does _not_ change critical state (seqs, window) @@@ -4972,10 -5270,12 +4979,10 @@@ out static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, int syn_inerr) { struct tcp_sock *tp = tcp_sk(sk);

/* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(skb, th, tp, &hash_location) && - tp->rx_opt.saw_tstamp && + if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); @@@ -5250,14 -5550,9 +5257,9 @@@ slow_path return 0;

step5: - if (tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) + if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0) goto discard;

- /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - tcp_rcv_rtt_measure_ts(sk, skb);

/* Process urgent data. */ @@@ -5329,11 -5624,12 +5331,11 @@@ static bool tcp_rcv_fastopen_synack(str

if (mss == tp->rx_opt.user_mss) { struct tcp_options_received opt; - const u8 *hash_location;

/* Get original SYNACK MSS value if user MSS sets mss_clamp */ tcp_clear_options(&opt); opt.user_mss = opt.mss_clamp = 0; - tcp_parse_options(synack, &opt, &hash_location, 0, NULL); + tcp_parse_options(synack, &opt, 0, NULL); mss = opt.mss_clamp; }

@@@ -5364,12 -5660,14 +5366,12 @@@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len) { - const u8 *hash_location; struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_cookie foc = { .len = -1 }; int saved_clamp = tp->rx_opt.mss_clamp;

- tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc); + tcp_parse_options(skb, &tp->rx_opt, 0, &foc); if (tp->rx_opt.saw_tstamp) tp->rx_opt.rcv_tsecr -= tp->tsoffset;

@@@ -5466,6 -5764,30 +5468,6 @@@ * is initialized. */ tp->copied_seq = tp->rcv_nxt;

- if (cvp != NULL && - cvp->cookie_pair_size > 0 && - tp->rx_opt.cookie_plus > 0) { - int cookie_size = tp->rx_opt.cookie_plus - - TCPOLEN_COOKIE_BASE; - int cookie_pair_size = cookie_size - + cvp->cookie_desired; - - /* A cookie extension option was sent and returned. - * Note that each incoming SYNACK replaces the - * Responder cookie. The initial exchange is most - * fragile, as protection against spoofing relies - * entirely upon the sequence and timestamp (above). - * This replacement strategy allows the correct pair to - * pass through, while any others will be filtered via - * Responder verification later. - */ - if (sizeof(cvp->cookie_pair) >= cookie_pair_size) { - memcpy(&cvp->cookie_pair[cvp->cookie_desired], - hash_location, cookie_size); - cvp->cookie_pair_size = cookie_pair_size; - } - } - smp_mb();

tcp_finish_connect(sk, skb); @@@ -5666,7 -5988,8 +5668,8 @@@ int tcp_rcv_state_process(struct sock *

/* step 5: check the ACK field */ if (true) { - int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0; + int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | + FLAG_UPDATE_TS_RECENT) > 0;

switch (sk->sk_state) { case TCP_SYN_RECV: @@@ -5817,11 -6140,6 +5820,6 @@@ } }

- /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - /* step 6: check the URG bit */ tcp_urg(sk, skb, th);

diff --combined net/ipv4/tcp_output.c index 5f28131,509912a..b735c23 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@@ -65,22 -65,27 +65,22 @@@ int sysctl_tcp_base_mss __read_mostly /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1;

-int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */ -EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size); - static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp);

/* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) { + struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out;

tcp_advance_send_head(sk, skb); tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;

- /* Don't override Nagle indefinitely with F-RTO */ - if (tp->frto_counter == 2) - tp->frto_counter = 3; - tp->packets_out += tcp_skb_pcount(skb); - if (!prior_packets || tp->early_retrans_delayed) + if (!prior_packets || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); }

@@@ -379,6 -384,7 +379,6 @@@ static inline bool tcp_urg_mode(const s #define OPTION_TS (1 << 1) #define OPTION_MD5 (1 << 2) #define OPTION_WSCALE (1 << 3) -#define OPTION_COOKIE_EXTENSION (1 << 4) #define OPTION_FAST_OPEN_COOKIE (1 << 8)

struct tcp_out_options { @@@ -392,6 -398,36 +392,6 @@@ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ };

-/* The sysctl int routines are generic, so check consistency here. - */ -static u8 tcp_cookie_size_check(u8 desired) -{ - int cookie_size; - - if (desired > 0) - /* previously specified */ - return desired; - - cookie_size = ACCESS_ONCE(sysctl_tcp_cookie_size); - if (cookie_size <= 0) - /* no default specified */ - return 0; - - if (cookie_size <= TCP_COOKIE_MIN) - /* value too small, specify minimum */ - return TCP_COOKIE_MIN; - - if (cookie_size >= TCP_COOKIE_MAX) - /* value too large, specify maximum */ - return TCP_COOKIE_MAX; - - if (cookie_size & 1) - /* 8-bit multiple, illegal, fix it */ - cookie_size++; - - return (u8)cookie_size; -} - /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@@ -410,9 -446,27 +410,9 @@@ static void tcp_options_write(__be32 *p { u16 options = opts->options; /* mungable copy */

- /* Having both authentication and cookies for security is redundant, - * and there's certainly not enough room. Instead, the cookie-less - * extension variant is proposed. - * - * Consider the pessimal case with authentication. The options - * could look like: - * COOKIE|MD5(20) + MSS(4) + SACK|TS(12) + WSCALE(4) == 40 - */ if (unlikely(OPTION_MD5 & options)) { - if (unlikely(OPTION_COOKIE_EXTENSION & options)) { - *ptr++ = htonl((TCPOPT_COOKIE << 24) | - (TCPOLEN_COOKIE_BASE << 16) | - (TCPOPT_MD5SIG << 8) | - TCPOLEN_MD5SIG); - } else { - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | - (TCPOPT_MD5SIG << 8) | - TCPOLEN_MD5SIG); - } - options &= ~OPTION_COOKIE_EXTENSION; + *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | + (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* overload cookie hash location */ opts->hash_location = (__u8 *)ptr; ptr += 4; @@@ -441,6 -495,44 +441,6 @@@ *ptr++ = htonl(opts->tsecr); }

- /* Specification requires after timestamp, so do it now. - * - * Consider the pessimal case without authentication. The options - * could look like: - * MSS(4) + SACK|TS(12) + COOKIE(20) + WSCALE(4) == 40 - */ - if (unlikely(OPTION_COOKIE_EXTENSION & options)) { - __u8 *cookie_copy = opts->hash_location; - u8 cookie_size = opts->hash_size; - - /* 8-bit multiple handled in tcp_cookie_size_check() above, - * and elsewhere. - */ - if (0x2 & cookie_size) { - __u8 *p = (__u8 *)ptr; - - /* 16-bit multiple */ - *p++ = TCPOPT_COOKIE; - *p++ = TCPOLEN_COOKIE_BASE + cookie_size; - *p++ = *cookie_copy++; - *p++ = *cookie_copy++; - ptr++; - cookie_size -= 2; - } else { - /* 32-bit multiple */ - *ptr++ = htonl(((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | - (TCPOPT_COOKIE << 8) | - TCPOLEN_COOKIE_BASE) + - cookie_size); - } - - if (cookie_size > 0) { - memcpy(ptr, cookie_copy, cookie_size); - ptr += (cookie_size / 4); - } - } - if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@@ -499,7 -591,11 +499,7 @@@ static unsigned int tcp_syn_options(str struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); - struct tcp_cookie_values *cvp = tp->cookie_values; unsigned int remaining = MAX_TCP_OPTION_SPACE; - u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ? - tcp_cookie_size_check(cvp->cookie_desired) : - 0; struct tcp_fastopen_request *fastopen = tp->fastopen_req;

#ifdef CONFIG_TCP_MD5SIG @@@ -551,7 -647,52 +551,7 @@@ tp->syn_fastopen = 1; } } - /* Note that timestamps are required by the specification. - * - * Odd numbers of bytes are prohibited by the specification, ensuring - * that the cookie is 16-bit aligned, and the resulting cookie pair is - * 32-bit aligned. - */ - if (*md5 == NULL && - (OPTION_TS & opts->options) && - cookie_size > 0) { - int need = TCPOLEN_COOKIE_BASE + cookie_size; - - if (0x2 & need) { - /* 32-bit multiple */ - need += 2; /* NOPs */ - - if (need > remaining) { - /* try shrinking cookie to fit */ - cookie_size -= 2; - need -= 4; - } - } - while (need > remaining && TCP_COOKIE_MIN <= cookie_size) { - cookie_size -= 4; - need -= 4; - } - if (TCP_COOKIE_MIN <= cookie_size) { - opts->options |= OPTION_COOKIE_EXTENSION; - opts->hash_location = (__u8 *)&cvp->cookie_pair[0]; - opts->hash_size = cookie_size; - - /* Remember for future incarnations. */ - cvp->cookie_desired = cookie_size; - - if (cvp->cookie_desired != cvp->cookie_pair_size) { - /* Currently use random bytes as a nonce, - * assuming these are completely unpredictable - * by hostile users of the same system. - */ - get_random_bytes(&cvp->cookie_pair[0], - cookie_size); - cvp->cookie_pair_size = cookie_size; - }

- remaining -= need; - } - } return MAX_TCP_OPTION_SPACE - remaining; }

@@@ -561,10 -702,14 +561,10 @@@ static unsigned int tcp_synack_options( unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5, - struct tcp_extend_values *xvp, struct tcp_fastopen_cookie *foc) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; - u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ? - xvp->cookie_plus : - 0;

#ifdef CONFIG_TCP_MD5SIG *md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req); @@@ -612,7 -757,28 +612,7 @@@ remaining -= need; } } - /* Similar rationale to tcp_syn_options() applies here, too. - * If the <SYN> options fit, the same options should fit now! - */ - if (*md5 == NULL && - ireq->tstamp_ok && - cookie_plus > TCPOLEN_COOKIE_BASE) { - int need = cookie_plus; /* has TCPOLEN_COOKIE_BASE */ - - if (0x2 & need) { - /* 32-bit multiple */ - need += 2; /* NOPs */ - } - if (need <= remaining) { - opts->options |= OPTION_COOKIE_EXTENSION; - opts->hash_size = cookie_plus - TCPOLEN_COOKIE_BASE; - remaining -= need; - } else { - /* There's no error return, so flag it. */ - xvp->cookie_out_never = 1; /* true */ - opts->hash_size = 0; - } - } + return MAX_TCP_OPTION_SPACE - remaining; }

@@@ -787,7 -953,7 +787,7 @@@ void __init tcp_tasklet_init(void * We cant xmit new skbs from this context, as we might already * hold qdisc lock. */ -static void tcp_wfree(struct sk_buff *skb) +void tcp_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); @@@ -846,13 -1012,6 +846,13 @@@ static int tcp_transmit_skb(struct soc __net_timestamp(skb);

if (likely(clone_it)) { + const struct sk_buff *fclone = skb + 1; + + if (unlikely(skb->fclone == SKB_FCLONE_ORIG && + fclone->fclone == SKB_FCLONE_CLONE)) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); else @@@ -1473,8 -1632,11 +1473,8 @@@ static inline bool tcp_nagle_test(cons if (nonagle & TCP_NAGLE_PUSH) return true;

- /* Don't use the nagle rule for urgent data (or for the final FIN). - * Nagle can be ignored during F-RTO too (see RFC4138). - */ - if (tcp_urg_mode(tp) || (tp->frto_counter == 2) || - (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) + /* Don't use the nagle rule for urgent data (or for the final FIN). */ + if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) return true;

if (!tcp_nagle_check(tp, skb, cur_mss, nonagle)) @@@ -1799,9 -1961,6 +1799,9 @@@ static int tcp_mtu_probe(struct sock *s * snd_up-64k-mss .. snd_up cannot be large. However, taking into * account rare use of URG, this is not a big flaw. * + * Send at most one packet when push_one > 0. Temporarily ignore + * cwnd limit to force at most one packet out when push_one == 2. + * Returns true, if no segments are in flight and we have queued segments, * but cannot send anything now because of SWS or another problem. */ @@@ -1837,13 -1996,8 +1837,13 @@@ static bool tcp_write_xmit(struct sock goto repair; /* Skip network transmission */

cwnd_quota = tcp_cwnd_test(tp, skb); - if (!cwnd_quota) - break; + if (!cwnd_quota) { + if (push_one == 2) + /* Force out a loss probe pkt. */ + cwnd_quota = 1; + else + break; + }

if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) break; @@@ -1897,129 -2051,10 +1897,129 @@@ repair if (likely(sent_pkts)) { if (tcp_in_cwnd_reduction(sk)) tp->prr_out += sent_pkts; + + /* Send one loss probe per tail loss episode. */ + if (push_one != 2) + tcp_schedule_loss_probe(sk); tcp_cwnd_validate(sk); return false; } - return !tp->packets_out && tcp_send_head(sk); + return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk)); +} + +bool tcp_schedule_loss_probe(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + u32 timeout, tlp_time_stamp, rto_time_stamp; + u32 rtt = tp->srtt >> 3; + + if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS)) + return false; + /* No consecutive loss probes. */ + if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) { + tcp_rearm_rto(sk); + return false; + } + /* Don't do any loss probe on a Fast Open connection before 3WHS + * finishes. + */ + if (sk->sk_state == TCP_SYN_RECV) + return false; + + /* TLP is only scheduled when next timer event is RTO. */ + if (icsk->icsk_pending != ICSK_TIME_RETRANS) + return false; + + /* Schedule a loss probe in 2*RTT for SACK capable connections + * in Open state, that are either limited by cwnd or application. + */ + if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out || + !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open) + return false; + + if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) && + tcp_send_head(sk)) + return false; + + /* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account + * for delayed ack when there's one outstanding packet. + */ + timeout = rtt << 1; + if (tp->packets_out == 1) + timeout = max_t(u32, timeout, + (rtt + (rtt >> 1) + TCP_DELACK_MAX)); + timeout = max_t(u32, timeout, msecs_to_jiffies(10)); + + /* If RTO is shorter, just schedule TLP in its place. */ + tlp_time_stamp = tcp_time_stamp + timeout; + rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout; + if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) { + s32 delta = rto_time_stamp - tcp_time_stamp; + if (delta > 0) + timeout = delta; + } + + inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, + TCP_RTO_MAX); + return true; +} + +/* When probe timeout (PTO) fires, send a new segment if one exists, else + * retransmit the last segment. + */ +void tcp_send_loss_probe(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + int pcount; + int mss = tcp_current_mss(sk); + int err = -1; + + if (tcp_send_head(sk) != NULL) { + err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); + goto rearm_timer; + } + + /* At most one outstanding TLP retransmission. */ + if (tp->tlp_high_seq) + goto rearm_timer; + + /* Retransmit last segment. */ + skb = tcp_write_queue_tail(sk); + if (WARN_ON(!skb)) + goto rearm_timer; + + pcount = tcp_skb_pcount(skb); + if (WARN_ON(!pcount)) + goto rearm_timer; + + if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { + if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss))) + goto rearm_timer; + skb = tcp_write_queue_tail(sk); + } + + if (WARN_ON(!skb || !tcp_skb_pcount(skb))) + goto rearm_timer; + + /* Probe with zero data doesn't trigger fast recovery. */ + if (skb->len > 0) + err = __tcp_retransmit_skb(sk, skb); + + /* Record snd_nxt for loss detection. */ + if (likely(!err)) + tp->tlp_high_seq = tp->snd_nxt; + +rearm_timer: + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + inet_csk(sk)->icsk_rto, + TCP_RTO_MAX); + + if (likely(!err)) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPLOSSPROBES); + return; }

/* Push out any pending frames which were held back due to @@@ -2353,8 -2388,12 +2353,12 @@@ int __tcp_retransmit_skb(struct sock *s */ TCP_SKB_CB(skb)->when = tcp_time_stamp;

- /* make sure skb->data is aligned on arches that require it */ - if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) { + /* make sure skb->data is aligned on arches that require it + * and check if ack-trimming & collapsing extended the headroom + * beyond what csum_start can cover. + */ + if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || + skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : @@@ -2640,24 -2679,32 +2644,24 @@@ int tcp_send_synack(struct sock *sk * sk: listener socket * dst: dst entry attached to the SYNACK * req: request_sock pointer - * rvp: request_values pointer * * Allocate one skb and build a SYNACK packet. * @dst is consumed : Caller should not use it again. */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc) { struct tcp_out_options opts; - struct tcp_extend_values *xvp = tcp_xv(rvp); struct inet_request_sock *ireq = inet_rsk(req); struct tcp_sock *tp = tcp_sk(sk); - const struct tcp_cookie_values *cvp = tp->cookie_values; struct tcphdr *th; struct sk_buff *skb; struct tcp_md5sig_key *md5; int tcp_header_size; int mss; - int s_data_desired = 0;

- if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired) - s_data_desired = cvp->s_data_desired; - skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired, - sk_gfp_atomic(sk, GFP_ATOMIC)); + skb = alloc_skb(MAX_TCP_HEADER + 15, sk_gfp_atomic(sk, GFP_ATOMIC)); if (unlikely(!skb)) { dst_release(dst); return NULL; @@@ -2666,6 -2713,7 +2670,7 @@@ skb_reserve(skb, MAX_TCP_HEADER);

skb_dst_set(skb, dst); + security_skb_owned_by(skb, sk);

mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) @@@ -2699,8 -2747,9 +2704,8 @@@ else #endif TCP_SKB_CB(skb)->when = tcp_time_stamp; - tcp_header_size = tcp_synack_options(sk, req, mss, - skb, &opts, &md5, xvp, foc) - + sizeof(*th); + tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5, + foc) + sizeof(*th);

skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@@ -2718,6 -2767,40 +2723,6 @@@ tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn, TCPHDR_SYN | TCPHDR_ACK);

- if (OPTION_COOKIE_EXTENSION & opts.options) { - if (s_data_desired) { - u8 *buf = skb_put(skb, s_data_desired); - - /* copy data directly from the listening socket. */ - memcpy(buf, cvp->s_data_payload, s_data_desired); - TCP_SKB_CB(skb)->end_seq += s_data_desired; - } - - if (opts.hash_size > 0) { - __u32 workspace[SHA_WORKSPACE_WORDS]; - u32 *mess = &xvp->cookie_bakery[COOKIE_DIGEST_WORDS]; - u32 *tail = &mess[COOKIE_MESSAGE_WORDS-1]; - - /* Secret recipe depends on the Timestamp, (future) - * Sequence and Acknowledgment Numbers, Initiator - * Cookie, and others handled by IP variant caller. - */ - *tail-- ^= opts.tsval; - *tail-- ^= tcp_rsk(req)->rcv_isn + 1; - *tail-- ^= TCP_SKB_CB(skb)->seq + 1; - - /* recommended */ - *tail-- ^= (((__force u32)th->dest << 16) | (__force u32)th->source); - *tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */ - - sha_transform((__u32 *)&xvp->cookie_bakery[0], - (char *)mess, - &workspace[0]); - opts.hash_location = - (__u8 *)&xvp->cookie_bakery[0]; - } - } - th->seq = htonl(TCP_SKB_CB(skb)->seq); /* XXX data is queued and acked as is. No buffer/window check */ th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); diff --combined net/ipv6/addrconf.c index 28b61e8,dae802c..d1ab6ab --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@@ -70,7 -70,6 +70,7 @@@ #include <net/snmp.h>

#include <net/af_ieee802154.h> +#include <net/firewire.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/ndisc.h> @@@ -169,8 -168,6 +169,6 @@@ static void inet6_prefix_notify(int eve static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev);

- static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); - static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, @@@ -422,7 -419,6 +420,7 @@@ static struct inet6_dev *ipv6_add_dev(s ipv6_regen_rndid((unsigned long) ndev); } #endif + ndev->token = in6addr_any;

if (netif_running(dev) && addrconf_qdisc_ok(dev)) ndev->if_flags |= IF_READY; @@@ -546,7 -542,8 +544,7 @@@ static const struct nla_policy devconf_ };

static int inet6_netconf_get_devconf(struct sk_buff *in_skb, - struct nlmsghdr *nlh, - void *arg) + struct nlmsghdr *nlh) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX+1]; @@@ -606,77 -603,6 +604,77 @@@ errout return err; }

+static int inet6_netconf_dump_devconf(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + int h, s_h; + int idx, s_idx; + struct net_device *dev; + struct inet6_dev *idev; + struct hlist_head *head; + + s_h = cb->args[0]; + s_idx = idx = cb->args[1]; + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + rcu_read_lock(); + cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ + net->dev_base_seq; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + idev = __in6_dev_get(dev); + if (!idev) + goto cont; + + if (inet6_netconf_fill_devconf(skb, dev->ifindex, + &idev->cnf, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNETCONF, + NLM_F_MULTI, + -1) <= 0) { + rcu_read_unlock(); + goto done; + } + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); +cont: + idx++; + } + rcu_read_unlock(); + } + if (h == NETDEV_HASHENTRIES) { + if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + -1) <= 0) + goto done; + else + h++; + } + if (h == NETDEV_HASHENTRIES + 1) { + if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWNETCONF, NLM_F_MULTI, + -1) <= 0) + goto done; + else + h++; + } +done: + cb->args[0] = h; + cb->args[1] = idx; + + return skb->len; +} + #ifdef CONFIG_SYSCTL static void dev_forward_change(struct inet6_dev *idev) { @@@ -878,7 -804,6 +876,7 @@@ ipv6_add_addr(struct inet6_dev *idev, c ifa->prefix_len = pfxlen; ifa->flags = flags | IFA_F_TENTATIVE; ifa->cstamp = ifa->tstamp = jiffies; + ifa->tokenized = false;

ifa->rt = rt;

@@@ -910,7 -835,7 +908,7 @@@ out2 rcu_read_unlock_bh();

if (likely(err == 0)) - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa); + inet6addr_notifier_call_chain(NETDEV_UP, ifa); else { kfree(ifa); ifa = ERR_PTR(err); @@@ -1000,7 -925,7 +998,7 @@@ static void ipv6_del_addr(struct inet6_

ipv6_ifa_notify(RTM_DELADDR, ifp);

- atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifp); + inet6addr_notifier_call_chain(NETDEV_DOWN, ifp);

/* * Purge or update corresponding prefix @@@ -1741,20 -1666,6 +1739,20 @@@ static int addrconf_ifid_eui64(u8 *eui return 0; }

+static int addrconf_ifid_ieee1394(u8 *eui, struct net_device *dev) +{ + union fwnet_hwaddr *ha; + + if (dev->addr_len != FWNET_ALEN) + return -1; + + ha = (union fwnet_hwaddr *)dev->dev_addr; + + memcpy(eui, &ha->uc.uniq_id, sizeof(ha->uc.uniq_id)); + eui[0] ^= 2; + return 0; +} + static int addrconf_ifid_arcnet(u8 *eui, struct net_device *dev) { /* XXX: inherit EUI-64 from other interface -- yoshfuji */ @@@ -1819,8 -1730,6 +1817,8 @@@ static int ipv6_generate_eui64(u8 *eui return addrconf_ifid_gre(eui, dev); case ARPHRD_IEEE802154: return addrconf_ifid_eui64(eui, dev); + case ARPHRD_IEEE1394: + return addrconf_ifid_ieee1394(eui, dev); } return -1; } @@@ -2135,19 -2044,11 +2133,19 @@@ void addrconf_prefix_rcv(struct net_dev struct inet6_ifaddr *ifp; struct in6_addr addr; int create = 0, update_lft = 0; + bool tokenized = false;

if (pinfo->prefix_len == 64) { memcpy(&addr, &pinfo->prefix, 8); - if (ipv6_generate_eui64(addr.s6_addr + 8, dev) && - ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) { + + if (!ipv6_addr_any(&in6_dev->token)) { + read_lock_bh(&in6_dev->lock); + memcpy(addr.s6_addr + 8, + in6_dev->token.s6_addr + 8, 8); + read_unlock_bh(&in6_dev->lock); + tokenized = true; + } else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) && + ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) { in6_dev_put(in6_dev); return; } @@@ -2188,7 -2089,6 +2186,7 @@@ ok

update_lft = create = 1; ifp->cstamp = jiffies; + ifp->tokenized = tokenized; addrconf_dad_start(ifp); }

@@@ -2698,8 -2598,7 +2696,8 @@@ static void addrconf_dev_config(struct (dev->type != ARPHRD_FDDI) && (dev->type != ARPHRD_ARCNET) && (dev->type != ARPHRD_INFINIBAND) && - (dev->type != ARPHRD_IEEE802154)) { + (dev->type != ARPHRD_IEEE802154) && + (dev->type != ARPHRD_IEEE1394)) { /* Alas, we support only Ethernet autoconfiguration. */ return; } @@@ -3087,7 -2986,7 +3085,7 @@@ static int addrconf_ifdown(struct net_d

if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); + inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } in6_ifa_put(ifa);

@@@ -3636,7 -3535,7 +3634,7 @@@ static const struct nla_policy ifa_ipv6 };

static int -inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; @@@ -3702,7 -3601,7 +3700,7 @@@ static int inet6_addr_modify(struct ine }

static int -inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; @@@ -3933,7 -3832,6 +3931,7 @@@ static int in6_dump_addrs(struct inet6_ NLM_F_MULTI); if (err <= 0) break; + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); } break; } @@@ -3991,7 -3889,6 +3989,7 @@@ static int inet6_dump_addr(struct sk_bu s_ip_idx = ip_idx = cb->args[2];

rcu_read_lock(); + cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ net->dev_base_seq; for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; @@@ -4043,7 -3940,8 +4041,7 @@@ static int inet6_dump_ifacaddr(struct s return inet6_dump_addr(skb, cb, type); }

-static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, - void *arg) +static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh) { struct net *net = sock_net(in_skb->sk); struct ifaddrmsg *ifm; @@@ -4176,8 -4074,7 +4174,8 @@@ static inline size_t inet6_ifla6_size(v + nla_total_size(sizeof(struct ifla_cacheinfo)) + nla_total_size(DEVCONF_MAX * 4) /* IFLA_INET6_CONF */ + nla_total_size(IPSTATS_MIB_MAX * 8) /* IFLA_INET6_STATS */ - + nla_total_size(ICMP6_MIB_MAX * 8); /* IFLA_INET6_ICMP6STATS */ + + nla_total_size(ICMP6_MIB_MAX * 8) /* IFLA_INET6_ICMP6STATS */ + + nla_total_size(sizeof(struct in6_addr)); /* IFLA_INET6_TOKEN */ }

static inline size_t inet6_if_nlmsg_size(void) @@@ -4264,13 -4161,6 +4262,13 @@@ static int inet6_fill_ifla6_attrs(struc goto nla_put_failure; snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));

+ nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr)); + if (nla == NULL) + goto nla_put_failure; + read_lock_bh(&idev->lock); + memcpy(nla_data(nla), idev->token.s6_addr, nla_len(nla)); + read_unlock_bh(&idev->lock); + return 0;

nla_put_failure: @@@ -4298,80 -4188,6 +4296,80 @@@ static int inet6_fill_link_af(struct sk return 0; }

+static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) +{ + struct inet6_ifaddr *ifp; + struct net_device *dev = idev->dev; + bool update_rs = false; + + if (token == NULL) + return -EINVAL; + if (ipv6_addr_any(token)) + return -EINVAL; + if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) + return -EINVAL; + if (!ipv6_accept_ra(idev)) + return -EINVAL; + if (idev->cnf.rtr_solicits <= 0) + return -EINVAL; + + write_lock_bh(&idev->lock); + + BUILD_BUG_ON(sizeof(token->s6_addr) != 16); + memcpy(idev->token.s6_addr + 8, token->s6_addr + 8, 8); + + write_unlock_bh(&idev->lock); + + if (!idev->dead && (idev->if_flags & IF_READY)) { + struct in6_addr ll_addr; + + ipv6_get_lladdr(dev, &ll_addr, IFA_F_TENTATIVE | + IFA_F_OPTIMISTIC); + + /* If we're not ready, then normal ifup will take care + * of this. Otherwise, we need to request our rs here. + */ + ndisc_send_rs(dev, &ll_addr, &in6addr_linklocal_allrouters); + update_rs = true; + } + + write_lock_bh(&idev->lock); + + if (update_rs) + idev->if_flags |= IF_RS_SENT; + + /* Well, that's kinda nasty ... */ + list_for_each_entry(ifp, &idev->addr_list, if_list) { + spin_lock(&ifp->lock); + if (ifp->tokenized) { + ifp->valid_lft = 0; + ifp->prefered_lft = 0; + } + spin_unlock(&ifp->lock); + } + + write_unlock_bh(&idev->lock); + return 0; +} + +static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) +{ + int err = -EINVAL; + struct inet6_dev *idev = __in6_dev_get(dev); + struct nlattr *tb[IFLA_INET6_MAX + 1]; + + if (!idev) + return -EAFNOSUPPORT; + + if (nla_parse_nested(tb, IFLA_INET6_MAX, nla, NULL) < 0) + BUG(); + + if (tb[IFLA_INET6_TOKEN]) + err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN])); + + return err; +} + static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, u32 portid, u32 seq, int event, unsigned int flags) { @@@ -4550,8 -4366,6 +4548,8 @@@ errout

static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { + struct net *net = dev_net(ifp->idev->dev); + inet6_ifa_notify(event ? : RTM_NEWADDR, ifp);

switch (event) { @@@ -4577,7 -4391,6 +4575,7 @@@ dst_free(&ifp->rt->dst); break; } + atomic_inc(&net->ipv6.dev_addr_genid); }

static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) @@@ -5054,27 -4867,10 +5052,11 @@@ static struct pernet_operations addrcon .exit = addrconf_exit_net, };

- /* - * Device notifier - */ - - int register_inet6addr_notifier(struct notifier_block *nb) - { - return atomic_notifier_chain_register(&inet6addr_chain, nb); - } - EXPORT_SYMBOL(register_inet6addr_notifier); - - int unregister_inet6addr_notifier(struct notifier_block *nb) - { - return atomic_notifier_chain_unregister(&inet6addr_chain, nb); - } - EXPORT_SYMBOL(unregister_inet6addr_notifier); - static struct rtnl_af_ops inet6_ops = { .family = AF_INET6, .fill_link_af = inet6_fill_link_af, .get_link_af_size = inet6_get_link_af_size, + .set_link_af = inet6_set_link_af, };

/* @@@ -5147,7 -4943,7 +5129,7 @@@ int __init addrconf_init(void __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr, NULL); __rtnl_register(PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, - NULL, NULL); + inet6_netconf_dump_devconf, NULL);

ipv6_addr_label_rtnl_register();

diff --combined net/ipv6/reassembly.c index e6e44ce,0ba10e5..790d9f4 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@@ -58,7 -58,6 +58,7 @@@ #include <net/ndisc.h> #include <net/addrconf.h> #include <net/inet_frag.h> +#include <net/inet_ecn.h>

struct ip6frag_skb_cb { @@@ -68,10 -67,6 +68,10 @@@

#define FRAG6_CB(skb) ((struct ip6frag_skb_cb*)((skb)->cb))

+static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) +{ + return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); +}

static struct inet_frags ip6_frags;

@@@ -124,7 -119,6 +124,7 @@@ void ip6_frag_init(struct inet_frag_que fq->user = arg->user; fq->saddr = *arg->src; fq->daddr = *arg->dst; + fq->ecn = arg->ecn; } EXPORT_SYMBOL(ip6_frag_init);

@@@ -179,8 -173,7 +179,8 @@@ static void ip6_frag_expire(unsigned lo }

static __inline__ struct frag_queue * -fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6_addr *dst) +fq_find(struct net *net, __be32 id, const struct in6_addr *src, + const struct in6_addr *dst, u8 ecn) { struct inet_frag_queue *q; struct ip6_create_arg arg; @@@ -190,7 -183,6 +190,7 @@@ arg.user = IP6_DEFRAG_LOCAL_DELIVER; arg.src = src; arg.dst = dst; + arg.ecn = ecn;

read_lock(&ip6_frags.lock); hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd); @@@ -210,7 -202,6 +210,7 @@@ static int ip6_frag_queue(struct frag_q struct net_device *dev; int offset, end; struct net *net = dev_net(skb_dst(skb)->dev); + u8 ecn;

if (fq->q.last_in & INET_FRAG_COMPLETE) goto err; @@@ -228,8 -219,6 +228,8 @@@ return -1; }

+ ecn = ip6_frag_ecn(ipv6_hdr(skb)); + if (skb->ip_summed == CHECKSUM_COMPLETE) { const unsigned char *nh = skb_network_header(skb); skb->csum = csum_sub(skb->csum, @@@ -330,7 -319,6 +330,7 @@@ found } fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; + fq->ecn |= ecn; add_frag_mem_limit(&fq->q, skb->truesize);

/* The first fragment. @@@ -342,9 -330,17 +342,17 @@@ }

if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len) - return ip6_frag_reasm(fq, prev, dev); + fq->q.meat == fq->q.len) { + int res; + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + res = ip6_frag_reasm(fq, prev, dev); + skb->_skb_refdst = orefdst; + return res; + }

+ skb_dst_drop(skb); inet_frag_lru_move(&fq->q); return -1;

@@@ -374,14 -370,9 +382,14 @@@ static int ip6_frag_reasm(struct frag_q int payload_len; unsigned int nhoff; int sum_truesize; + u8 ecn;

inet_frag_kill(&fq->q, &ip6_frags);

+ ecn = ip_frag_ecn_table[fq->ecn]; + if (unlikely(ecn == 0xff)) + goto out_fail; + /* Make the one we just received the head. */ if (prev) { head = prev->next; @@@ -480,7 -471,6 +488,7 @@@ head->dev = dev; head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); IP6CB(head)->nhoff = nhoff;

/* Yes, and fold redundant checksum back. 8) */ @@@ -544,8 -534,7 +552,8 @@@ static int ipv6_frag_rcv(struct sk_buf IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS, evicted);

- fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr); + fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, + ip6_frag_ecn(hdr)); if (fq != NULL) { int ret;

diff --combined net/iucv/af_iucv.c index e165e8d,206ce6d..ae69165 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@@ -49,12 -49,6 +49,6 @@@ static const u8 iprm_shutdown[8]

#define TRGCLS_SIZE (sizeof(((struct iucv_message *)0)->class))

- /* macros to set/get socket control buffer at correct offset */ - #define CB_TAG(skb) ((skb)->cb) /* iucv message tag */ - #define CB_TAG_LEN (sizeof(((struct iucv_message *) 0)->tag)) - #define CB_TRGCLS(skb) ((skb)->cb + CB_TAG_LEN) /* iucv msg target class */ - #define CB_TRGCLS_LEN (TRGCLS_SIZE) - #define __iucv_sock_wait(sk, condition, timeo, ret) \ do { \ DEFINE_WAIT(__wait); \ @@@ -1141,7 -1135,7 +1135,7 @@@ static int iucv_sock_sendmsg(struct kio

/* increment and save iucv message tag for msg_completion cbk */ txmsg.tag = iucv->send_tag++; - memcpy(CB_TAG(skb), &txmsg.tag, CB_TAG_LEN); + IUCV_SKB_CB(skb)->tag = txmsg.tag;

if (iucv->transport == AF_IUCV_TRANS_HIPER) { atomic_inc(&iucv->msg_sent); @@@ -1224,7 -1218,7 +1218,7 @@@ static int iucv_fragment_skb(struct soc return -ENOMEM;

/* copy target class to control buffer of new skb */ - memcpy(CB_TRGCLS(nskb), CB_TRGCLS(skb), CB_TRGCLS_LEN); + IUCV_SKB_CB(nskb)->class = IUCV_SKB_CB(skb)->class;

/* copy data fragment */ memcpy(nskb->data, skb->data + copied, size); @@@ -1256,7 -1250,7 +1250,7 @@@ static void iucv_process_message(struc

/* store msg target class in the second 4 bytes of skb ctrl buffer */ /* Note: the first 4 bytes are reserved for msg tag */ - memcpy(CB_TRGCLS(skb), &msg->class, CB_TRGCLS_LEN); + IUCV_SKB_CB(skb)->class = msg->class;

/* check for special IPRM messages (e.g. iucv_sock_shutdown) */ if ((msg->flags & IUCV_IPRMDATA) && len > 7) { @@@ -1292,6 -1286,7 +1286,7 @@@ } }

+ IUCV_SKB_CB(skb)->offset = 0; if (sock_queue_rcv_skb(sk, skb)) skb_queue_head(&iucv_sk(sk)->backlog_skb_q, skb); } @@@ -1327,6 -1322,7 +1322,7 @@@ static int iucv_sock_recvmsg(struct kio unsigned int copied, rlen; struct sk_buff *skb, *rskb, *cskb; int err = 0; + u32 offset;

msg->msg_namelen = 0;

@@@ -1348,13 -1344,14 +1344,14 @@@ return err; }

- rlen = skb->len; /* real length of skb */ + offset = IUCV_SKB_CB(skb)->offset; + rlen = skb->len - offset; /* real length of skb */ copied = min_t(unsigned int, rlen, len); if (!rlen) sk->sk_shutdown = sk->sk_shutdown | RCV_SHUTDOWN;

cskb = skb; - if (skb_copy_datagram_iovec(cskb, 0, msg->msg_iov, copied)) { + if (skb_copy_datagram_iovec(cskb, offset, msg->msg_iov, copied)) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); return -EFAULT; @@@ -1372,7 -1369,8 +1369,8 @@@ * get the trgcls from the control buffer of the skb due to * fragmentation of original iucv message. */ err = put_cmsg(msg, SOL_IUCV, SCM_IUCV_TRGCLS, - CB_TRGCLS_LEN, CB_TRGCLS(skb)); + sizeof(IUCV_SKB_CB(skb)->class), + (void *)&IUCV_SKB_CB(skb)->class); if (err) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); @@@ -1384,9 -1382,8 +1382,8 @@@

/* SOCK_STREAM: re-queue skb if it contains unreceived data */ if (sk->sk_type == SOCK_STREAM) { - skb_pull(skb, copied); - if (skb->len) { - skb_queue_head(&sk->sk_receive_queue, skb); + if (copied < rlen) { + IUCV_SKB_CB(skb)->offset = offset + copied; goto done; } } @@@ -1405,6 -1402,7 +1402,7 @@@ spin_lock_bh(&iucv->message_q.lock); rskb = skb_dequeue(&iucv->backlog_skb_q); while (rskb) { + IUCV_SKB_CB(rskb)->offset = 0; if (sock_queue_rcv_skb(sk, rskb)) { skb_queue_head(&iucv->backlog_skb_q, rskb); @@@ -1463,8 -1461,7 +1461,8 @@@ unsigned int iucv_sock_poll(struct fil return iucv_accept_poll(sk);

if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR; + mask |= POLLERR | + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);

if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLRDHUP; @@@ -1833,7 -1830,7 +1831,7 @@@ static void iucv_callback_txdone(struc spin_lock_irqsave(&list->lock, flags);

while (list_skb != (struct sk_buff *)list) { - if (!memcmp(&msg->tag, CB_TAG(list_skb), CB_TAG_LEN)) { + if (msg->tag != IUCV_SKB_CB(list_skb)->tag) { this = list_skb; break; } @@@ -2094,6 -2091,7 +2092,7 @@@ static int afiucv_hs_callback_rx(struc skb_pull(skb, sizeof(struct af_iucv_trans_hdr)); skb_reset_transport_header(skb); skb_reset_network_header(skb); + IUCV_SKB_CB(skb)->offset = 0; spin_lock(&iucv->message_q.lock); if (skb_queue_empty(&iucv->backlog_skb_q)) { if (sock_queue_rcv_skb(sk, skb)) { @@@ -2198,8 -2196,7 +2197,7 @@@ static int afiucv_hs_rcv(struct sk_buf /* fall through and receive zero length data */ case 0: /* plain data frame */ - memcpy(CB_TRGCLS(skb), &trans_hdr->iucv_hdr.class, - CB_TRGCLS_LEN); + IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class; err = afiucv_hs_callback_rx(sk, skb); break; default: diff --combined net/mac80211/iface.c index 69aaba7,9ed49ad..e8a260f --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@@ -78,7 -78,7 +78,7 @@@ void ieee80211_recalc_txpower(struct ie ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_TXPOWER); }

- u32 ieee80211_idle_off(struct ieee80211_local *local) + static u32 __ieee80211_idle_off(struct ieee80211_local *local) { if (!(local->hw.conf.flags & IEEE80211_CONF_IDLE)) return 0; @@@ -87,27 -87,29 +87,29 @@@ return IEEE80211_CONF_CHANGE_IDLE; }

- static u32 ieee80211_idle_on(struct ieee80211_local *local) + static u32 __ieee80211_idle_on(struct ieee80211_local *local) { if (local->hw.conf.flags & IEEE80211_CONF_IDLE) return 0;

- drv_flush(local, false); + ieee80211_flush_queues(local, NULL);

local->hw.conf.flags |= IEEE80211_CONF_IDLE; return IEEE80211_CONF_CHANGE_IDLE; }

- void ieee80211_recalc_idle(struct ieee80211_local *local) + static u32 __ieee80211_recalc_idle(struct ieee80211_local *local, + bool force_active) { bool working = false, scanning, active; unsigned int led_trig_start = 0, led_trig_stop = 0; struct ieee80211_roc_work *roc;

lockdep_assert_held(&local->mtx);

- active = !list_empty(&local->chanctx_list) || local->monitors; + active = force_active || + !list_empty(&local->chanctx_list) || + local->monitors;

if (!local->ops->remain_on_channel) { list_for_each_entry(roc, &local->roc_list, list) { @@@ -132,9 -134,18 +134,18 @@@ ieee80211_mod_tpt_led_trig(local, led_trig_start, led_trig_stop);

if (working || scanning || active) - change = ieee80211_idle_off(local); - else - change = ieee80211_idle_on(local); + return __ieee80211_idle_off(local); + return __ieee80211_idle_on(local); + } + + u32 ieee80211_idle_off(struct ieee80211_local *local) + { + return __ieee80211_recalc_idle(local, true); + } + + void ieee80211_recalc_idle(struct ieee80211_local *local) + { + u32 change = __ieee80211_recalc_idle(local, false); if (change) ieee80211_hw_config(local, change); } @@@ -488,6 -499,8 +499,6 @@@ int ieee80211_do_open(struct wireless_d res = drv_start(local); if (res) goto err_del_bss; - if (local->ops->napi_poll) - napi_enable(&local->napi); /* we're brought up, everything changes */ hw_reconf_flags = ~0; ieee80211_led_radio(local, true); @@@ -560,6 -573,8 +571,6 @@@ goto err_del_interface; }

- drv_add_interface_debugfs(local, sdata); - if (sdata->vif.type == NL80211_IFTYPE_AP) { local->fif_pspoll++; local->fif_probe_req++; @@@ -837,15 -852,15 +848,15 @@@ static void ieee80211_do_stop(struct ie rcu_barrier(); sta_info_flush_cleanup(sdata);

- skb_queue_purge(&sdata->skb_queue); - /* * Free all remaining keys, there shouldn't be any, - * except maybe group keys in AP more or WDS? + * except maybe in WDS mode? */ ieee80211_free_keys(sdata);

- drv_remove_interface_debugfs(local, sdata); + /* fall through */ + case NL80211_IFTYPE_AP: + skb_queue_purge(&sdata->skb_queue);

if (going_down) drv_remove_interface(local, sdata); @@@ -856,6 -871,8 +867,6 @@@ ieee80211_recalc_ps(local, -1);

if (local->open_count == 0) { - if (local->ops->napi_poll) - napi_disable(&local->napi); ieee80211_clear_tx_pending(local); ieee80211_stop_device(local);

@@@ -918,17 -935,6 +929,17 @@@ static void ieee80211_set_multicast_lis atomic_dec(&local->iff_promiscs); sdata->flags ^= IEEE80211_SDATA_PROMISC; } + + /* + * TODO: If somebody needs this on AP interfaces, + * it can be enabled easily but multicast + * addresses from VLANs need to be synced. + */ + if (sdata->vif.type != NL80211_IFTYPE_MONITOR && + sdata->vif.type != NL80211_IFTYPE_AP_VLAN && + sdata->vif.type != NL80211_IFTYPE_AP) + drv_set_multicast_list(local, sdata, &dev->mc); + spin_lock_bh(&local->filter_lock); __hw_addr_sync(&local->mc_list, &dev->mc, dev->addr_len); spin_unlock_bh(&local->filter_lock); @@@ -1555,8 -1561,6 +1566,8 @@@ int ieee80211_if_add(struct ieee80211_l INIT_WORK(&sdata->cleanup_stations_wk, ieee80211_cleanup_sdata_stas_wk); INIT_DELAYED_WORK(&sdata->dfs_cac_timer_work, ieee80211_dfs_cac_timer_work); + INIT_DELAYED_WORK(&sdata->dec_tailroom_needed_wk, + ieee80211_delayed_tailroom_dec);

for (i = 0; i < IEEE80211_NUM_BANDS; i++) { struct ieee80211_supported_band *sband; diff --combined net/mac80211/mlme.c index e06dbbf,346ad4c..dec42ab --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@@ -87,6 -87,9 +87,6 @@@ MODULE_PARM_DESC(probe_wait_ms */ #define IEEE80211_SIGNAL_AVE_MIN_COUNT 4

-#define TMR_RUNNING_TIMER 0 -#define TMR_RUNNING_CHANSW 1 - /* * All cfg80211 functions have to be called outside a locked * section so that they can acquire a lock themselves... This @@@ -606,7 -609,6 +606,7 @@@ static void ieee80211_add_vht_ie(struc BUILD_BUG_ON(sizeof(vht_cap) != sizeof(sband->vht_cap));

memcpy(&vht_cap, &sband->vht_cap, sizeof(vht_cap)); + ieee80211_apply_vhtcap_overrides(sdata, &vht_cap);

/* determine capability flags */ cap = vht_cap.cap; @@@ -1009,7 -1011,6 +1009,7 @@@ static void ieee80211_chswitch_work(str

/* XXX: wait for a beacon first? */ ieee80211_wake_queues_by_reason(&sdata->local->hw, + IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA); out: ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED; @@@ -1037,8 -1038,14 +1037,8 @@@ static void ieee80211_chswitch_timer(un { struct ieee80211_sub_if_data *sdata = (struct ieee80211_sub_if_data *) data; - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - - if (sdata->local->quiescing) { - set_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running); - return; - }

- ieee80211_queue_work(&sdata->local->hw, &ifmgd->chswitch_work); + ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.chswitch_work); }

void @@@ -1109,7 -1116,6 +1109,7 @@@ ieee80211_sta_process_chanswitch(struc

if (sw_elem->mode) ieee80211_stop_queues_by_reason(&sdata->local->hw, + IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA);

if (sdata->local->ops->channel_switch) { @@@ -1377,7 -1383,6 +1377,7 @@@ void ieee80211_dynamic_ps_disable_work( }

ieee80211_wake_queues_by_reason(&local->hw, + IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_PS); }

@@@ -1439,7 -1444,7 +1439,7 @@@ void ieee80211_dynamic_ps_enable_work(s else { ieee80211_send_nullfunc(local, sdata, 1); /* Flush to get the tx status of nullfunc frame */ - drv_flush(local, false); + ieee80211_flush_queues(local, sdata); } }

@@@ -1770,7 -1775,7 +1770,7 @@@ static void ieee80211_set_disassoc(stru

/* flush out any pending frame (e.g. DELBA) before deauth/disassoc */ if (tx) - drv_flush(local, false); + ieee80211_flush_queues(local, sdata);

/* deauthenticate/disassociate now */ if (tx || frame_buf) @@@ -1779,7 -1784,7 +1779,7 @@@

/* flush out frame */ if (tx) - drv_flush(local, false); + ieee80211_flush_queues(local, sdata);

/* clear bssid only after building the needed mgmt frames */ memset(ifmgd->bssid, 0, ETH_ALEN); @@@ -1797,11 -1802,9 +1797,11 @@@ sdata->vif.bss_conf.p2p_ctwindow = 0; sdata->vif.bss_conf.p2p_oppps = false;

- /* on the next assoc, re-program HT parameters */ + /* on the next assoc, re-program HT/VHT parameters */ memset(&ifmgd->ht_capa, 0, sizeof(ifmgd->ht_capa)); memset(&ifmgd->ht_capa_mask, 0, sizeof(ifmgd->ht_capa_mask)); + memset(&ifmgd->vht_capa, 0, sizeof(ifmgd->vht_capa)); + memset(&ifmgd->vht_capa_mask, 0, sizeof(ifmgd->vht_capa_mask));

sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL;

@@@ -1827,6 -1830,8 +1827,6 @@@ del_timer_sync(&sdata->u.mgd.timer); del_timer_sync(&sdata->u.mgd.chswitch_timer);

- sdata->u.mgd.timers_running = 0; - sdata->vif.bss_conf.dtim_period = 0;

ifmgd->flags = 0; @@@ -1951,7 -1956,7 +1951,7 @@@ static void ieee80211_mgd_probe_ap_send ifmgd->probe_timeout = jiffies + msecs_to_jiffies(probe_wait_ms); run_again(ifmgd, ifmgd->probe_timeout); if (sdata->local->hw.flags & IEEE80211_HW_REPORTS_TX_ACK_STATUS) - drv_flush(sdata->local, false); + ieee80211_flush_queues(sdata->local, sdata); }

static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, @@@ -2074,7 -2079,6 +2074,7 @@@ static void __ieee80211_disconnect(stru true, frame_buf); ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED; ieee80211_wake_queues_by_reason(&sdata->local->hw, + IEEE80211_MAX_QUEUE_MAP, IEEE80211_QUEUE_STOP_REASON_CSA); mutex_unlock(&ifmgd->mtx);

@@@ -3136,8 -3140,15 +3136,8 @@@ static void ieee80211_sta_timer(unsigne { struct ieee80211_sub_if_data *sdata = (struct ieee80211_sub_if_data *) data; - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_local *local = sdata->local; - - if (local->quiescing) { - set_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running); - return; - }

- ieee80211_queue_work(&local->hw, &sdata->work); + ieee80211_queue_work(&sdata->local->hw, &sdata->work); }

static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata, @@@ -3489,6 -3500,72 +3489,6 @@@ static void ieee80211_restart_sta_timer } }

-#ifdef CONFIG_PM -void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - - /* - * Stop timers before deleting work items, as timers - * could race and re-add the work-items. They will be - * re-established on connection. - */ - del_timer_sync(&ifmgd->conn_mon_timer); - del_timer_sync(&ifmgd->bcn_mon_timer); - - /* - * we need to use atomic bitops for the running bits - * only because both timers might fire at the same - * time -- the code here is properly synchronised. - */ - - cancel_work_sync(&ifmgd->request_smps_work); - - cancel_work_sync(&ifmgd->monitor_work); - cancel_work_sync(&ifmgd->beacon_connection_loss_work); - cancel_work_sync(&ifmgd->csa_connection_drop_work); - if (del_timer_sync(&ifmgd->timer)) - set_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running); - - if (del_timer_sync(&ifmgd->chswitch_timer)) - set_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running); - cancel_work_sync(&ifmgd->chswitch_work); -} - -void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) -{ - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - - mutex_lock(&ifmgd->mtx); - if (!ifmgd->associated) { - mutex_unlock(&ifmgd->mtx); - return; - } - - if (sdata->flags & IEEE80211_SDATA_DISCONNECT_RESUME) { - sdata->flags &= ~IEEE80211_SDATA_DISCONNECT_RESUME; - mlme_dbg(sdata, "driver requested disconnect after resume\n"); - ieee80211_sta_connection_lost(sdata, - ifmgd->associated->bssid, - WLAN_REASON_UNSPECIFIED, - true); - mutex_unlock(&ifmgd->mtx); - return; - } - mutex_unlock(&ifmgd->mtx); - - if (test_and_clear_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running)) - add_timer(&ifmgd->timer); - if (test_and_clear_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running)) - add_timer(&ifmgd->chswitch_timer); - ieee80211_sta_reset_beacon_monitor(sdata); - - mutex_lock(&sdata->local->mtx); - ieee80211_restart_sta_timer(sdata); - mutex_unlock(&sdata->local->mtx); -} -#endif - /* interface setup */ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) { @@@ -3887,8 -3964,16 +3887,16 @@@ int ieee80211_mgd_auth(struct ieee80211 /* prep auth_data so we don't go into idle on disassoc */ ifmgd->auth_data = auth_data;

- if (ifmgd->associated) - ieee80211_set_disassoc(sdata, 0, 0, false, NULL); + if (ifmgd->associated) { + u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + + ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, + WLAN_REASON_UNSPECIFIED, + false, frame_buf); + + __cfg80211_send_deauth(sdata->dev, frame_buf, + sizeof(frame_buf)); + }

sdata_info(sdata, "authenticate with %pM\n", req->bss->bssid);

@@@ -3948,8 -4033,16 +3956,16 @@@ int ieee80211_mgd_assoc(struct ieee8021

mutex_lock(&ifmgd->mtx);

- if (ifmgd->associated) - ieee80211_set_disassoc(sdata, 0, 0, false, NULL); + if (ifmgd->associated) { + u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + + ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, + WLAN_REASON_UNSPECIFIED, + false, frame_buf); + + __cfg80211_send_deauth(sdata->dev, frame_buf, + sizeof(frame_buf)); + }

if (ifmgd->auth_data && !ifmgd->auth_data->done) { err = -EBUSY; @@@ -3996,9 -4089,6 +4012,9 @@@ ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; }

+ if (req->flags & ASSOC_REQ_DISABLE_VHT) + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + /* Also disable HT if we don't support it or the AP doesn't use WMM */ sband = local->hw.wiphy->bands[req->bss->channel->band]; if (!sband->ht_cap.ht_supported || @@@ -4022,10 -4112,6 +4038,10 @@@ memcpy(&ifmgd->ht_capa_mask, &req->ht_capa_mask, sizeof(ifmgd->ht_capa_mask));

+ memcpy(&ifmgd->vht_capa, &req->vht_capa, sizeof(ifmgd->vht_capa)); + memcpy(&ifmgd->vht_capa_mask, &req->vht_capa_mask, + sizeof(ifmgd->vht_capa_mask)); + if (req->ie && req->ie_len) { memcpy(assoc_data->ie, req->ie, req->ie_len); assoc_data->ie_len = req->ie_len; diff --combined net/netfilter/nf_nat_core.c index 346f871,ad24be0..2e469ca --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@@ -87,10 -87,9 +87,10 @@@ int nf_xfrm_me_harder(struct sk_buff *s struct flowi fl; unsigned int hh_len; struct dst_entry *dst; + int err;

- if (xfrm_decode_session(skb, &fl, family) < 0) - return -1; + err = xfrm_decode_session(skb, &fl, family); + return err;

dst = skb_dst(skb); if (dst->xfrm) @@@ -99,7 -98,7 +99,7 @@@

dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0); if (IS_ERR(dst)) - return -1; + return PTR_ERR(dst);

skb_dst_drop(skb); skb_dst_set(skb, dst); @@@ -108,7 -107,7 +108,7 @@@ hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) - return -1; + return -ENOMEM; return 0; } EXPORT_SYMBOL(nf_xfrm_me_harder); @@@ -468,33 -467,22 +468,22 @@@ EXPORT_SYMBOL_GPL(nf_nat_packet) struct nf_nat_proto_clean { u8 l3proto; u8 l4proto; - bool hash; };

- /* Clear NAT section of all conntracks, in case we're loaded again. */ - static int nf_nat_proto_clean(struct nf_conn *i, void *data) + /* kill conntracks with affected NAT section */ + static int nf_nat_proto_remove(struct nf_conn *i, void *data) { const struct nf_nat_proto_clean *clean = data; struct nf_conn_nat *nat = nfct_nat(i);

if (!nat) return 0; - if (!(i->status & IPS_SRC_NAT_DONE)) - return 0; + if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) || (clean->l4proto && nf_ct_protonum(i) != clean->l4proto)) return 0;

- if (clean->hash) { - spin_lock_bh(&nf_nat_lock); - hlist_del_rcu(&nat->bysource); - spin_unlock_bh(&nf_nat_lock); - } else { - memset(nat, 0, sizeof(*nat)); - i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | - IPS_SEQ_ADJUST); - } - return 0; + return i->status & IPS_NAT_MASK ? 1 : 0; }

static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) @@@ -506,16 -494,8 +495,8 @@@ struct net *net;

rtnl_lock(); - /* Step 1 - remove from bysource hash */ - clean.hash = true; for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); - synchronize_rcu(); - - /* Step 2 - clean NAT section */ - clean.hash = false; - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); rtnl_unlock(); }

@@@ -527,16 -507,9 +508,9 @@@ static void nf_nat_l3proto_clean(u8 l3p struct net *net;

rtnl_lock(); - /* Step 1 - remove from bysource hash */ - clean.hash = true; - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); - synchronize_rcu();

- /* Step 2 - clean NAT section */ - clean.hash = false; for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); rtnl_unlock(); }

@@@ -774,7 -747,7 +748,7 @@@ static void __net_exit nf_nat_net_exit( { struct nf_nat_proto_clean clean = {};

- nf_ct_iterate_cleanup(net, &nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean); synchronize_rcu(); nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); } diff --combined net/openvswitch/datapath.c index 7bb5d4f,6980c3e..d2f9f2e --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@@ -44,7 -44,6 +44,7 @@@ #include <linux/netfilter_ipv4.h> #include <linux/inetdevice.h> #include <linux/list.h> +#include <linux/lockdep.h> #include <linux/openvswitch.h> #include <linux/rculist.h> #include <linux/dmi.h> @@@ -57,59 -56,38 +57,59 @@@ #include "flow.h" #include "vport-internal_dev.h"

-/** - * struct ovs_net - Per net-namespace data for ovs. - * @dps: List of datapaths to enable dumping them all out. - * Protected by genl_mutex. - */ -struct ovs_net { - struct list_head dps; -}; - -static int ovs_net_id __read_mostly;

#define REHASH_FLOW_INTERVAL (10 * 60 * HZ) static void rehash_flow_table(struct work_struct *work); static DECLARE_DELAYED_WORK(rehash_flow_wq, rehash_flow_table);

+int ovs_net_id __read_mostly; + +static void ovs_notify(struct sk_buff *skb, struct genl_info *info, + struct genl_multicast_group *grp) +{ + genl_notify(skb, genl_info_net(info), info->snd_portid, + grp->id, info->nlhdr, GFP_KERNEL); +} + /** * DOC: Locking: * - * Writes to device state (add/remove datapath, port, set operations on vports, - * etc.) are protected by RTNL. - * - * Writes to other state (flow table modifications, set miscellaneous datapath - * parameters, etc.) are protected by genl_mutex. The RTNL lock nests inside - * genl_mutex. + * All writes e.g. Writes to device state (add/remove datapath, port, set + * operations on vports, etc.), Writes to other state (flow table + * modifications, set miscellaneous datapath parameters, etc.) are protected + * by ovs_lock. * * Reads are protected by RCU. * * There are a few special cases (mostly stats) that have their own * synchronization but they nest under all of above and don't interact with * each other. + * + * The RTNL lock nests inside ovs_mutex. */

+static DEFINE_MUTEX(ovs_mutex); + +void ovs_lock(void) +{ + mutex_lock(&ovs_mutex); +} + +void ovs_unlock(void) +{ + mutex_unlock(&ovs_mutex); +} + +#ifdef CONFIG_LOCKDEP +int lockdep_ovsl_is_held(void) +{ + if (debug_locks) + return lockdep_is_held(&ovs_mutex); + else + return 1; +} +#endif + static struct vport *new_vport(const struct vport_parms *); static int queue_gso_packets(struct net *, int dp_ifindex, struct sk_buff *, const struct dp_upcall_info *); @@@ -117,7 -95,7 +117,7 @@@ static int queue_userspace_packet(struc struct sk_buff *, const struct dp_upcall_info *);

-/* Must be called with rcu_read_lock, genl_mutex, or RTNL lock. */ +/* Must be called with rcu_read_lock or ovs_mutex. */ static struct datapath *get_dp(struct net *net, int dp_ifindex) { struct datapath *dp = NULL; @@@ -135,10 -113,10 +135,10 @@@ return dp; }

-/* Must be called with rcu_read_lock or RTNL lock. */ +/* Must be called with rcu_read_lock or ovs_mutex. */ const char *ovs_dp_name(const struct datapath *dp) { - struct vport *vport = ovs_vport_rtnl_rcu(dp, OVSP_LOCAL); + struct vport *vport = ovs_vport_ovsl_rcu(dp, OVSP_LOCAL); return vport->ops->get_name(vport); }

@@@ -190,7 -168,7 +190,7 @@@ struct vport *ovs_lookup_vport(const st return NULL; }

-/* Called with RTNL lock and genl_lock. */ +/* Called with ovs_mutex. */ static struct vport *new_vport(const struct vport_parms *parms) { struct vport *vport; @@@ -202,12 -180,14 +202,12 @@@

hlist_add_head_rcu(&vport->dp_hash_node, head); } return vport; }

-/* Called with RTNL lock. */ void ovs_dp_detach_port(struct vport *p) { - ASSERT_RTNL(); + ASSERT_OVSL();

/* First drop references to device. */ hlist_del_rcu(&p->dp_hash_node); @@@ -357,35 -337,6 +357,35 @@@ static int queue_gso_packets(struct ne return err; }

+static size_t key_attr_size(void) +{ + return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + + nla_total_size(4) /* OVS_KEY_ATTR_IN_PORT */ + + nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */ + + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + + nla_total_size(4) /* OVS_KEY_ATTR_8021Q */ + + nla_total_size(0) /* OVS_KEY_ATTR_ENCAP */ + + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + + nla_total_size(40) /* OVS_KEY_ATTR_IPV6 */ + + nla_total_size(2) /* OVS_KEY_ATTR_ICMPV6 */ + + nla_total_size(28); /* OVS_KEY_ATTR_ND */ +} + +static size_t upcall_msg_size(const struct sk_buff *skb, + const struct nlattr *userdata) +{ + size_t size = NLMSG_ALIGN(sizeof(struct ovs_header)) + + nla_total_size(skb->len) /* OVS_PACKET_ATTR_PACKET */ + + nla_total_size(key_attr_size()); /* OVS_PACKET_ATTR_KEY */ + + /* OVS_PACKET_ATTR_USERDATA */ + if (userdata) + size += NLA_ALIGN(userdata->nla_len); + + return size; +} + static int queue_userspace_packet(struct net *net, int dp_ifindex, struct sk_buff *skb, const struct dp_upcall_info *upcall_info) @@@ -394,6 -345,7 +394,6 @@@ struct sk_buff *nskb = NULL; struct sk_buff *user_skb; /* to be queued to userspace */ struct nlattr *nla; - unsigned int len; int err;

if (vlan_tx_tag_present(skb)) { @@@ -401,7 -353,7 +401,7 @@@ if (!nskb) return -ENOMEM;

- nskb = __vlan_put_tag(nskb, vlan_tx_tag_get(nskb)); + nskb = __vlan_put_tag(nskb, nskb->vlan_proto, vlan_tx_tag_get(nskb)); if (!nskb) return -ENOMEM;

@@@ -414,7 -366,13 +414,7 @@@ goto out; }

- len = sizeof(struct ovs_header); - len += nla_total_size(skb->len); - len += nla_total_size(FLOW_BUFSIZE); - if (upcall_info->cmd == OVS_PACKET_CMD_ACTION) - len += nla_total_size(8); - - user_skb = genlmsg_new(len, GFP_ATOMIC); + user_skb = genlmsg_new(upcall_msg_size(skb, upcall_info->userdata), GFP_ATOMIC); if (!user_skb) { err = -ENOMEM; goto out; @@@ -429,9 -387,8 +429,9 @@@ nla_nest_end(user_skb, nla);

if (upcall_info->userdata) - nla_put_u64(user_skb, OVS_PACKET_ATTR_USERDATA, - nla_get_u64(upcall_info->userdata)); + __nla_put(user_skb, OVS_PACKET_ATTR_USERDATA, + nla_len(upcall_info->userdata), + nla_data(upcall_info->userdata));

nla = __nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, skb->len);

@@@ -445,13 -402,13 +445,13 @@@ out return err; }

-/* Called with genl_mutex. */ +/* Called with ovs_mutex. */ static int flush_flows(struct datapath *dp) { struct flow_table *old_table; struct flow_table *new_table;

- old_table = genl_dereference(dp->table); + old_table = ovsl_dereference(dp->table); new_table = ovs_flow_tbl_alloc(TBL_MIN_BUCKETS); if (!new_table) return -ENOMEM; @@@ -587,7 -544,7 +587,7 @@@ static int validate_userspace(const str { static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = { [OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 }, - [OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_U64 }, + [OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_UNSPEC }, }; struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1]; int error; @@@ -704,7 -661,8 +704,7 @@@ static int ovs_packet_cmd_execute(struc

err = -EINVAL; if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] || - !a[OVS_PACKET_ATTR_ACTIONS] || - nla_len(a[OVS_PACKET_ATTR_PACKET]) < ETH_HLEN) + !a[OVS_PACKET_ATTR_ACTIONS]) goto err;

len = nla_len(a[OVS_PACKET_ATTR_PACKET]); @@@ -714,7 -672,7 +714,7 @@@ goto err; skb_reserve(packet, NET_IP_ALIGN);

- memcpy(__skb_put(packet, len), nla_data(a[OVS_PACKET_ATTR_PACKET]), len); + nla_memcpy(__skb_put(packet, len), a[OVS_PACKET_ATTR_PACKET], len);

skb_reset_mac_header(packet); eth = eth_hdr(packet); @@@ -722,7 -680,7 +722,7 @@@ /* Normally, setting the skb 'protocol' field would be handled by a * call to eth_type_trans(), but it assumes there's a sending * device, which we may not have. */ - if (ntohs(eth->h_proto) >= 1536) + if (ntohs(eth->h_proto) >= ETH_P_802_3_MIN) packet->protocol = eth->h_proto; else packet->protocol = htons(ETH_P_802_2); @@@ -785,7 -743,7 +785,7 @@@ err }

static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = { - [OVS_PACKET_ATTR_PACKET] = { .type = NLA_UNSPEC }, + [OVS_PACKET_ATTR_PACKET] = { .len = ETH_HLEN }, [OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED }, [OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED }, }; @@@ -801,7 -759,7 +801,7 @@@ static struct genl_ops dp_packet_genl_o static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats) { int i; - struct flow_table *table = genl_dereference(dp->table); + struct flow_table *table = ovsl_dereference(dp->table);

stats->n_flows = ovs_flow_tbl_count(table);

@@@ -843,17 -801,7 +843,17 @@@ static struct genl_multicast_group ovs_ .name = OVS_FLOW_MCGROUP };

-/* Called with genl_lock. */ +static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts) +{ + return NLMSG_ALIGN(sizeof(struct ovs_header)) + + nla_total_size(key_attr_size()) /* OVS_FLOW_ATTR_KEY */ + + nla_total_size(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */ + + nla_total_size(1) /* OVS_FLOW_ATTR_TCP_FLAGS */ + + nla_total_size(8) /* OVS_FLOW_ATTR_USED */ + + nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */ +} + +/* Called with ovs_mutex. */ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) @@@ -867,7 -815,8 +867,7 @@@ u8 tcp_flags; int err;

- sf_acts = rcu_dereference_protected(flow->sf_acts, - lockdep_genl_is_held()); + sf_acts = ovsl_dereference(flow->sf_acts);

ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd); if (!ovs_header) @@@ -930,10 -879,25 +930,10 @@@ error static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow) { const struct sw_flow_actions *sf_acts; - int len;

- sf_acts = rcu_dereference_protected(flow->sf_acts, - lockdep_genl_is_held()); + sf_acts = ovsl_dereference(flow->sf_acts);

- /* OVS_FLOW_ATTR_KEY */ - len = nla_total_size(FLOW_BUFSIZE); - /* OVS_FLOW_ATTR_ACTIONS */ - len += nla_total_size(sf_acts->actions_len); - /* OVS_FLOW_ATTR_STATS */ - len += nla_total_size(sizeof(struct ovs_flow_stats)); - /* OVS_FLOW_ATTR_TCP_FLAGS */ - len += nla_total_size(1); - /* OVS_FLOW_ATTR_USED */ - len += nla_total_size(8); - - len += NLMSG_ALIGN(sizeof(struct ovs_header)); - - return genlmsg_new(len, GFP_KERNEL); + return genlmsg_new(ovs_flow_cmd_msg_size(sf_acts), GFP_KERNEL); }

static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow, @@@ -982,13 -946,12 +982,13 @@@ static int ovs_flow_cmd_new_or_set(stru goto error; }

+ ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); error = -ENODEV; if (!dp) - goto error; + goto err_unlock_ovs;

- table = genl_dereference(dp->table); + table = ovsl_dereference(dp->table); flow = ovs_flow_tbl_lookup(table, &key, key_len); if (!flow) { struct sw_flow_actions *acts; @@@ -996,7 -959,7 +996,7 @@@ /* Bail out if we're not allowed to create a new flow. */ error = -ENOENT; if (info->genlhdr->cmd == OVS_FLOW_CMD_SET) - goto error; + goto err_unlock_ovs;

/* Expand table, if necessary, to make room. */ if (ovs_flow_tbl_need_to_expand(table)) { @@@ -1006,7 -969,7 +1006,7 @@@ if (!IS_ERR(new_table)) { rcu_assign_pointer(dp->table, new_table); ovs_flow_tbl_deferred_destroy(table); - table = genl_dereference(dp->table); + table = ovsl_dereference(dp->table); } }

@@@ -1014,7 -977,7 +1014,7 @@@ flow = ovs_flow_alloc(); if (IS_ERR(flow)) { error = PTR_ERR(flow); - goto error; + goto err_unlock_ovs; } flow->key = key; clear_stats(flow); @@@ -1047,10 -1010,11 +1047,10 @@@ error = -EEXIST; if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW && info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) - goto error; + goto err_unlock_ovs;

/* Update actions. */ - old_acts = rcu_dereference_protected(flow->sf_acts, - lockdep_genl_is_held()); + old_acts = ovsl_dereference(flow->sf_acts); acts_attrs = a[OVS_FLOW_ATTR_ACTIONS]; if (acts_attrs && (old_acts->actions_len != nla_len(acts_attrs) || @@@ -1061,7 -1025,7 +1061,7 @@@ new_acts = ovs_flow_actions_alloc(acts_attrs); error = PTR_ERR(new_acts); if (IS_ERR(new_acts)) - goto error; + goto err_unlock_ovs;

rcu_assign_pointer(flow->sf_acts, new_acts); ovs_flow_deferred_free_acts(old_acts); @@@ -1077,10 -1041,11 +1077,10 @@@ spin_unlock_bh(&flow->lock); } } + ovs_unlock();

if (!IS_ERR(reply)) - genl_notify(reply, genl_info_net(info), info->snd_portid, - ovs_dp_flow_multicast_group.id, info->nlhdr, - GFP_KERNEL); + ovs_notify(reply, info, &ovs_dp_flow_multicast_group); else netlink_set_err(sock_net(skb->sk)->genl_sock, 0, ovs_dp_flow_multicast_group.id, PTR_ERR(reply)); @@@ -1088,8 -1053,6 +1088,8 @@@

error_free_flow: ovs_flow_free(flow); +err_unlock_ovs: + ovs_unlock(); error: return error; } @@@ -1112,32 -1075,21 +1112,32 @@@ static int ovs_flow_cmd_get(struct sk_b if (err) return err;

+ ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); - if (!dp) - return -ENODEV; + if (!dp) { + err = -ENODEV; + goto unlock; + }

- table = genl_dereference(dp->table); + table = ovsl_dereference(dp->table); flow = ovs_flow_tbl_lookup(table, &key, key_len); - if (!flow) - return -ENOENT; + if (!flow) { + err = -ENOENT; + goto unlock; + }

reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid, info->snd_seq, OVS_FLOW_CMD_NEW); - if (IS_ERR(reply)) - return PTR_ERR(reply); + if (IS_ERR(reply)) { + err = PTR_ERR(reply); + goto unlock; + }

+ ovs_unlock(); return genlmsg_reply(reply, info); +unlock: + ovs_unlock(); + return err; }

static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) @@@ -1152,33 -1104,25 +1152,33 @@@ int err; int key_len;

+ ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); - if (!dp) - return -ENODEV; - - if (!a[OVS_FLOW_ATTR_KEY]) - return flush_flows(dp); + if (!dp) { + err = -ENODEV; + goto unlock; + }

+ if (!a[OVS_FLOW_ATTR_KEY]) { + err = flush_flows(dp); + goto unlock; + } err = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]); if (err) - return err; + goto unlock;

- table = genl_dereference(dp->table); + table = ovsl_dereference(dp->table); flow = ovs_flow_tbl_lookup(table, &key, key_len); - if (!flow) - return -ENOENT; + if (!flow) { + err = -ENOENT; + goto unlock; + }

reply = ovs_flow_cmd_alloc_info(flow); - if (!reply) - return -ENOMEM; + if (!reply) { + err = -ENOMEM; + goto unlock; + }

ovs_flow_tbl_remove(table, flow);

@@@ -1187,13 -1131,10 +1187,13 @@@ BUG_ON(err < 0);

ovs_flow_deferred_free(flow); + ovs_unlock();

- genl_notify(reply, genl_info_net(info), info->snd_portid, - ovs_dp_flow_multicast_group.id, info->nlhdr, GFP_KERNEL); + ovs_notify(reply, info, &ovs_dp_flow_multicast_group); return 0; +unlock: + ovs_unlock(); + return err; }

static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) @@@ -1202,14 -1143,11 +1202,14 @@@ struct datapath *dp; struct flow_table *table;

+ ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); - if (!dp) + if (!dp) { + ovs_unlock(); return -ENODEV; + }

- table = genl_dereference(dp->table); + table = ovsl_dereference(dp->table);

for (;;) { struct sw_flow *flow; @@@ -1230,7 -1168,6 +1230,7 @@@ cb->args[0] = bucket; cb->args[1] = obj; } + ovs_unlock(); return skb->len; }

@@@ -1276,16 -1213,6 +1276,16 @@@ static struct genl_multicast_group ovs_ .name = OVS_DATAPATH_MCGROUP };

+static size_t ovs_dp_cmd_msg_size(void) +{ + size_t msgsize = NLMSG_ALIGN(sizeof(struct ovs_header)); + + msgsize += nla_total_size(IFNAMSIZ); + msgsize += nla_total_size(sizeof(struct ovs_dp_stats)); + + return msgsize; +} + static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) { @@@ -1324,7 -1251,7 +1324,7 @@@ static struct sk_buff *ovs_dp_cmd_build struct sk_buff *skb; int retval;

- skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + skb = genlmsg_new(ovs_dp_cmd_msg_size(), GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM);

@@@ -1336,7 -1263,7 +1336,7 @@@ return skb; }

-/* Called with genl_mutex and optionally with RTNL lock also. */ +/* Called with ovs_mutex. */ static struct datapath *lookup_datapath(struct net *net, struct ovs_header *ovs_header, struct nlattr *a[OVS_DP_ATTR_MAX + 1]) @@@ -1370,12 -1297,12 +1370,12 @@@ static int ovs_dp_cmd_new(struct sk_buf if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID]) goto err;

- rtnl_lock(); + ovs_lock();

err = -ENOMEM; dp = kzalloc(sizeof(*dp), GFP_KERNEL); if (dp == NULL) - goto err_unlock_rtnl; + goto err_unlock_ovs;

ovs_dp_set_net(dp, hold_net(sock_net(skb->sk)));

@@@ -1426,34 -1353,37 +1426,34 @@@

ovs_net = net_generic(ovs_dp_get_net(dp), ovs_net_id); list_add_tail(&dp->list_node, &ovs_net->dps); - rtnl_unlock();

- genl_notify(reply, genl_info_net(info), info->snd_portid, - ovs_dp_datapath_multicast_group.id, info->nlhdr, - GFP_KERNEL); + ovs_unlock(); + + ovs_notify(reply, info, &ovs_dp_datapath_multicast_group); return 0;

err_destroy_local_port: - ovs_dp_detach_port(ovs_vport_rtnl(dp, OVSP_LOCAL)); + ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL)); err_destroy_ports_array: kfree(dp->ports); err_destroy_percpu: free_percpu(dp->stats_percpu); err_destroy_table: - ovs_flow_tbl_destroy(genl_dereference(dp->table)); + ovs_flow_tbl_destroy(ovsl_dereference(dp->table)); err_free_dp: release_net(ovs_dp_get_net(dp)); kfree(dp); -err_unlock_rtnl: - rtnl_unlock(); +err_unlock_ovs: + ovs_unlock(); err: return err; }

-/* Called with genl_mutex. */ +/* Called with ovs_mutex. */ static void __dp_destroy(struct datapath *dp) { int i;

- rtnl_lock(); - for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; struct hlist_node *n; @@@ -1464,11 -1394,14 +1464,11 @@@ }

list_del(&dp->list_node); - ovs_dp_detach_port(ovs_vport_rtnl(dp, OVSP_LOCAL));

- /* rtnl_unlock() will wait until all the references to devices that - * are pending unregistration have been dropped. We do it here to - * ensure that any internal devices (which contain DP pointers) are - * fully destroyed before freeing the datapath. + /* OVSP_LOCAL is datapath internal port. We need to make sure that + * all port in datapath are destroyed first before freeing datapath. */ - rtnl_unlock(); + ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));

call_rcu(&dp->rcu, destroy_dp_rcu); } @@@ -1479,27 -1412,24 +1479,27 @@@ static int ovs_dp_cmd_del(struct sk_buf struct datapath *dp; int err;

+ ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) - return err; + goto unlock;

reply = ovs_dp_cmd_build_info(dp, info->snd_portid, info->snd_seq, OVS_DP_CMD_DEL); err = PTR_ERR(reply); if (IS_ERR(reply)) - return err; + goto unlock;

__dp_destroy(dp); + ovs_unlock();

- genl_notify(reply, genl_info_net(info), info->snd_portid, - ovs_dp_datapath_multicast_group.id, info->nlhdr, - GFP_KERNEL); + ovs_notify(reply, info, &ovs_dp_datapath_multicast_group);

return 0; +unlock: + ovs_unlock(); + return err; }

static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) @@@ -1508,11 -1438,9 +1508,11 @@@ struct datapath *dp; int err;

+ ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); + err = PTR_ERR(dp); if (IS_ERR(dp)) - return PTR_ERR(dp); + goto unlock;

reply = ovs_dp_cmd_build_info(dp, info->snd_portid, info->snd_seq, OVS_DP_CMD_NEW); @@@ -1520,45 -1448,31 +1520,45 @@@ err = PTR_ERR(reply); netlink_set_err(sock_net(skb->sk)->genl_sock, 0, ovs_dp_datapath_multicast_group.id, err); - return 0; + err = 0; + goto unlock; }

- genl_notify(reply, genl_info_net(info), info->snd_portid, - ovs_dp_datapath_multicast_group.id, info->nlhdr, - GFP_KERNEL); + ovs_unlock(); + ovs_notify(reply, info, &ovs_dp_datapath_multicast_group);

return 0; +unlock: + ovs_unlock(); + return err; }

static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *reply; struct datapath *dp; + int err;

+ ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); - if (IS_ERR(dp)) - return PTR_ERR(dp); + if (IS_ERR(dp)) { + err = PTR_ERR(dp); + goto unlock; + }

reply = ovs_dp_cmd_build_info(dp, info->snd_portid, info->snd_seq, OVS_DP_CMD_NEW); - if (IS_ERR(reply)) - return PTR_ERR(reply); + if (IS_ERR(reply)) { + err = PTR_ERR(reply); + goto unlock; + }

+ ovs_unlock(); return genlmsg_reply(reply, info); + +unlock: + ovs_unlock(); + return err; }

static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) @@@ -1568,7 -1482,6 +1568,7 @@@ int skip = cb->args[0]; int i = 0;

+ ovs_lock(); list_for_each_entry(dp, &ovs_net->dps, list_node) { if (i >= skip && ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).portid, @@@ -1577,7 -1490,6 +1577,7 @@@ break; i++; } + ovs_unlock();

cb->args[0] = i;

@@@ -1630,7 -1542,7 +1630,7 @@@ struct genl_multicast_group ovs_dp_vpor .name = OVS_VPORT_MCGROUP };

-/* Called with RTNL lock or RCU read lock. */ +/* Called with ovs_mutex or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) { @@@ -1669,7 -1581,7 +1669,7 @@@ error return err; }

-/* Called with RTNL lock or RCU read lock. */ +/* Called with ovs_mutex or RCU read lock. */ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, u32 seq, u8 cmd) { @@@ -1681,14 -1593,12 +1681,12 @@@ return ERR_PTR(-ENOMEM);

retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd); - if (retval < 0) { - kfree_skb(skb); - return ERR_PTR(retval); - } + BUG_ON(retval < 0); + return skb; }

-/* Called with RTNL lock or RCU read lock. */ +/* Called with ovs_mutex or RCU read lock. */ static struct vport *lookup_vport(struct net *net, struct ovs_header *ovs_header, struct nlattr *a[OVS_VPORT_ATTR_MAX + 1]) @@@ -1714,9 -1624,9 +1712,9 @@@ if (!dp) return ERR_PTR(-ENODEV);

- vport = ovs_vport_rtnl_rcu(dp, port_no); + vport = ovs_vport_ovsl_rcu(dp, port_no); if (!vport) - return ERR_PTR(-ENOENT); + return ERR_PTR(-ENODEV); return vport; } else return ERR_PTR(-EINVAL); @@@ -1738,7 -1648,7 +1736,7 @@@ static int ovs_vport_cmd_new(struct sk_ !a[OVS_VPORT_ATTR_UPCALL_PID]) goto exit;

- rtnl_lock(); + ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); err = -ENODEV; if (!dp) @@@ -1751,7 -1661,7 +1749,7 @@@ if (port_no >= DP_MAX_PORTS) goto exit_unlock;

- vport = ovs_vport_rtnl_rcu(dp, port_no); + vport = ovs_vport_ovsl(dp, port_no); err = -EBUSY; if (vport) goto exit_unlock; @@@ -1761,7 -1671,7 +1759,7 @@@ err = -EFBIG; goto exit_unlock; } - vport = ovs_vport_rtnl(dp, port_no); + vport = ovs_vport_ovsl(dp, port_no); if (!vport) break; } @@@ -1787,11 -1697,11 +1785,11 @@@ ovs_dp_detach_port(vport); goto exit_unlock; } - genl_notify(reply, genl_info_net(info), info->snd_portid, - ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL); + + ovs_notify(reply, info, &ovs_dp_vport_multicast_group);

exit_unlock: - rtnl_unlock(); + ovs_unlock(); exit: return err; } @@@ -1803,7 -1713,7 +1801,7 @@@ static int ovs_vport_cmd_set(struct sk_ struct vport *vport; int err;

- rtnl_lock(); + ovs_lock(); vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); err = PTR_ERR(vport); if (IS_ERR(vport)) @@@ -1814,27 -1724,34 +1812,35 @@@ nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type) err = -EINVAL;

+ reply = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!reply) { + err = -ENOMEM; + goto exit_unlock; + } + if (!err && a[OVS_VPORT_ATTR_OPTIONS]) err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]); if (err) - goto exit_unlock; + goto exit_free; + if (a[OVS_VPORT_ATTR_UPCALL_PID]) vport->upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]);

- reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, - OVS_VPORT_CMD_NEW); - if (IS_ERR(reply)) { - netlink_set_err(sock_net(skb->sk)->genl_sock, 0, - ovs_dp_vport_multicast_group.id, PTR_ERR(reply)); - goto exit_unlock; - } + err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, + info->snd_seq, 0, OVS_VPORT_CMD_NEW); + BUG_ON(err < 0);

- genl_notify(reply, genl_info_net(info), info->snd_portid, - ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL); + ovs_unlock(); + ovs_notify(reply, info, &ovs_dp_vport_multicast_group); + return 0;

+ rtnl_unlock(); + return 0; + + exit_free: + kfree_skb(reply); exit_unlock: - rtnl_unlock(); + ovs_unlock(); return err; }

@@@ -1845,7 -1762,7 +1851,7 @@@ static int ovs_vport_cmd_del(struct sk_ struct vport *vport; int err;

- rtnl_lock(); + ovs_lock(); vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); err = PTR_ERR(vport); if (IS_ERR(vport)) @@@ -1865,10 -1782,11 +1871,10 @@@ err = 0; ovs_dp_detach_port(vport);

- genl_notify(reply, genl_info_net(info), info->snd_portid, - ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL); + ovs_notify(reply, info, &ovs_dp_vport_multicast_group);

exit_unlock: - rtnl_unlock(); + ovs_unlock(); return err; }

@@@ -2028,13 -1946,13 +2034,13 @@@ static void rehash_flow_table(struct wo struct datapath *dp; struct net *net;

- genl_lock(); + ovs_lock(); rtnl_lock(); for_each_net(net) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id);

list_for_each_entry(dp, &ovs_net->dps, list_node) { - struct flow_table *old_table = genl_dereference(dp->table); + struct flow_table *old_table = ovsl_dereference(dp->table); struct flow_table *new_table;

new_table = ovs_flow_tbl_rehash(old_table); @@@ -2045,7 -1963,8 +2051,7 @@@ } } rtnl_unlock(); - genl_unlock(); - + ovs_unlock(); schedule_delayed_work(&rehash_flow_wq, REHASH_FLOW_INTERVAL); }

@@@ -2054,21 -1973,18 +2060,21 @@@ static int __net_init ovs_init_net(stru struct ovs_net *ovs_net = net_generic(net, ovs_net_id);

INIT_LIST_HEAD(&ovs_net->dps); + INIT_WORK(&ovs_net->dp_notify_work, ovs_dp_notify_wq); return 0; }

static void __net_exit ovs_exit_net(struct net *net) { - struct ovs_net *ovs_net = net_generic(net, ovs_net_id); struct datapath *dp, *dp_next; + struct ovs_net *ovs_net = net_generic(net, ovs_net_id);

- genl_lock(); + ovs_lock(); list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node) __dp_destroy(dp); - genl_unlock(); + ovs_unlock(); + + cancel_work_sync(&ovs_net->dp_notify_work); }

static struct pernet_operations ovs_net_ops = { diff --combined net/openvswitch/flow.c index cf9328b,67a2b78..b15321a --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@@ -211,7 -211,7 +211,7 @@@ struct sw_flow_actions *ovs_flow_action return ERR_PTR(-ENOMEM);

sfa->actions_len = actions_len; - memcpy(sfa->actions, nla_data(actions), actions_len); + nla_memcpy(sfa->actions, actions, actions_len); return sfa; }

@@@ -466,7 -466,7 +466,7 @@@ static __be16 parse_ethertype(struct sk proto = *(__be16 *) skb->data; __skb_pull(skb, sizeof(__be16));

- if (ntohs(proto) >= 1536) + if (ntohs(proto) >= ETH_P_802_3_MIN) return proto;

if (skb->len < sizeof(struct llc_snap_hdr)) @@@ -483,7 -483,7 +483,7 @@@

__skb_pull(skb, sizeof(struct llc_snap_hdr));

- if (ntohs(llc->ethertype) >= 1536) + if (ntohs(llc->ethertype) >= ETH_P_802_3_MIN) return llc->ethertype;

return htons(ETH_P_802_2); @@@ -795,9 -795,9 +795,9 @@@ void ovs_flow_tbl_insert(struct flow_ta

void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) { + BUG_ON(table->count == 0); hlist_del_rcu(&flow->hash_node[table->node_ver]); table->count--; - BUG_ON(table->count < 0); }

/* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ @@@ -1038,7 -1038,7 +1038,7 @@@ int ovs_flow_from_nlattrs(struct sw_flo

if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) { swkey->eth.type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]); - if (ntohs(swkey->eth.type) < 1536) + if (ntohs(swkey->eth.type) < ETH_P_802_3_MIN) return -EINVAL; attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); } else { diff --combined net/unix/af_unix.c index 5ca1631,2db702d..9efe011 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@@ -1340,6 -1340,7 +1340,6 @@@ static void unix_destruct_scm(struct sk struct scm_cookie scm; memset(&scm, 0, sizeof(scm)); scm.pid = UNIXCB(skb).pid; - scm.cred = UNIXCB(skb).cred; if (UNIXCB(skb).fp) unix_detach_fds(&scm, skb);

@@@ -1390,8 -1391,8 +1390,8 @@@ static int unix_scm_to_skb(struct scm_c int err = 0;

UNIXCB(skb).pid = get_pid(scm->pid); - if (scm->cred) - UNIXCB(skb).cred = get_cred(scm->cred); + UNIXCB(skb).uid = scm->creds.uid; + UNIXCB(skb).gid = scm->creds.gid; UNIXCB(skb).fp = NULL; if (scm->fp && send_fds) err = unix_attach_fds(scm, skb); @@@ -1408,13 -1409,13 +1408,13 @@@ static void maybe_add_creds(struct sk_buff *skb, const struct socket *sock, const struct sock *other) { - if (UNIXCB(skb).cred) + if (UNIXCB(skb).pid) return; if (test_bit(SOCK_PASSCRED, &sock->flags) || !other->sk_socket || test_bit(SOCK_PASSCRED, &other->sk_socket->flags)) { UNIXCB(skb).pid = get_pid(task_tgid(current)); - current_euid_egid(&UNIXCB(skb).uid, &UNIXCB(skb).gid); - UNIXCB(skb).cred = get_current_cred(); ++ current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid); } }

@@@ -1818,7 -1819,7 +1818,7 @@@ static int unix_dgram_recvmsg(struct ki siocb->scm = &tmp_scm; memset(&tmp_scm, 0, sizeof(tmp_scm)); } - scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred); + scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); unix_set_secdata(siocb->scm, skb);

if (!(flags & MSG_PEEK)) { @@@ -1990,12 -1991,11 +1990,12 @@@ again if (check_creds) { /* Never glue messages from different writers */ if ((UNIXCB(skb).pid != siocb->scm->pid) || - (UNIXCB(skb).cred != siocb->scm->cred)) + !uid_eq(UNIXCB(skb).uid, siocb->scm->creds.uid) || + !gid_eq(UNIXCB(skb).gid, siocb->scm->creds.gid)) break; } else if (test_bit(SOCK_PASSCRED, &sock->flags)) { /* Copy credentials */ - scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred); + scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); check_creds = 1; }

@@@ -2196,9 -2196,7 +2196,9 @@@ static unsigned int unix_dgram_poll(str

/* exceptional events? */ if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) - mask |= POLLERR; + mask |= POLLERR | + (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0); + if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) diff --combined security/selinux/hooks.c index 0a0609f,7171a95..bf889ee --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@@ -51,6 -51,7 +51,7 @@@ #include <linux/tty.h> #include <net/icmp.h> #include <net/ip.h> /* for local_port_range[] */ + #include <net/sock.h> #include <net/tcp.h> /* struct or_callable used in sock_rcv_skb */ #include <net/net_namespace.h> #include <net/netlabel.h> @@@ -60,7 -61,7 +61,7 @@@ #include <linux/bitops.h> #include <linux/interrupt.h> #include <linux/netdevice.h> /* for network interface checks */ -#include <linux/netlink.h> +#include <net/netlink.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/dccp.h> @@@ -4363,6 -4364,11 +4364,11 @@@ static void selinux_inet_conn_establish selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); }

+ static void selinux_skb_owned_by(struct sk_buff *skb, struct sock *sk) + { + skb_set_owner_w(skb, sk); + } + static int selinux_secmark_relabel_packet(u32 sid) { const struct task_security_struct *__tsec; @@@ -4475,7 -4481,7 +4481,7 @@@ static int selinux_nlmsg_perm(struct so struct nlmsghdr *nlh; struct sk_security_struct *sksec = sk->sk_security;

- if (skb->len < NLMSG_SPACE(0)) { + if (skb->len < NLMSG_HDRLEN) { err = -EINVAL; goto out; } @@@ -5664,6 -5670,7 +5670,7 @@@ static struct security_operations selin .tun_dev_attach_queue = selinux_tun_dev_attach_queue, .tun_dev_attach = selinux_tun_dev_attach, .tun_dev_open = selinux_tun_dev_open, + .skb_owned_by = selinux_skb_owned_by,

#ifdef CONFIG_SECURITY_NETWORK_XFRM .xfrm_policy_alloc_security = selinux_xfrm_policy_alloc,