diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt index 41b3f3f864e8..5d88f37480b6 100644 --- a/Documentation/devicetree/bindings/net/ethernet.txt +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -25,7 +25,11 @@ The following properties are common to the Ethernet controllers: flow control thresholds. - tx-fifo-depth: the size of the controller's transmit fifo in bytes. This is used for components that can have configurable fifo sizes. +- managed: string, specifies the PHY management type. Supported values are: + "auto", "in-band-status". "auto" is the default, it usess MDIO for + management if fixed-link is not specified. Child nodes of the Ethernet controller are typically the individual PHY devices connected via the MDIO bus (sometimes the MDIO bus controller is separate). They are described in the phy.txt file in this same directory. +For non-MDIO PHY management see fixed-link.txt. diff --git a/Makefile b/Makefile index e071176b2ce6..d02f16b510dc 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 1 -SUBLEVEL = 9 +SUBLEVEL = 10 EXTRAVERSION = NAME = Series 4800 diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index f1ff39a3d1c1..54d946a9eee6 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -325,12 +325,14 @@ void zcomp_destroy(struct zcomp *comp) * allocate new zcomp and initialize it. return compressing * backend pointer or ERR_PTR if things went bad. ERR_PTR(-EINVAL) * if requested algorithm is not supported, ERR_PTR(-ENOMEM) in - * case of allocation error. + * case of allocation error, or any other error potentially + * returned by functions zcomp_strm_{multi,single}_create. */ struct zcomp *zcomp_create(const char *compress, int max_strm) { struct zcomp *comp; struct zcomp_backend *backend; + int error; backend = find_backend(compress); if (!backend) @@ -342,12 +344,12 @@ struct zcomp *zcomp_create(const char *compress, int max_strm) comp->backend = backend; if (max_strm > 1) - zcomp_strm_multi_create(comp, max_strm); + error = zcomp_strm_multi_create(comp, max_strm); else - zcomp_strm_single_create(comp); - if (!comp->stream) { + error = zcomp_strm_single_create(comp); + if (error) { kfree(comp); - return ERR_PTR(-ENOMEM); + return ERR_PTR(error); } return comp; } diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index cedb572bf25a..db9ebbc1a732 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -417,7 +417,7 @@ static int bcm_sf2_sw_fast_age_port(struct dsa_switch *ds, int port) core_writel(priv, port, CORE_FAST_AGE_PORT); reg = core_readl(priv, CORE_FAST_AGE_CTRL); - reg |= EN_AGE_PORT | FAST_AGE_STR_DONE; + reg |= EN_AGE_PORT | EN_AGE_DYNAMIC | FAST_AGE_STR_DONE; core_writel(priv, reg, CORE_FAST_AGE_CTRL); do { @@ -431,6 +431,8 @@ static int bcm_sf2_sw_fast_age_port(struct dsa_switch *ds, int port) if (!timeout) return -ETIMEDOUT; + core_writel(priv, 0, CORE_FAST_AGE_CTRL); + return 0; } @@ -506,7 +508,7 @@ static int bcm_sf2_sw_br_set_stp_state(struct dsa_switch *ds, int port, u32 reg; reg = core_readl(priv, CORE_G_PCTL_PORT(port)); - cur_hw_state = reg >> G_MISTP_STATE_SHIFT; + cur_hw_state = reg & (G_MISTP_STATE_MASK << G_MISTP_STATE_SHIFT); switch (state) { case BR_STATE_DISABLED: @@ -530,10 +532,12 @@ static int bcm_sf2_sw_br_set_stp_state(struct dsa_switch *ds, int port, } /* Fast-age ARL entries if we are moving a port from Learning or - * Forwarding state to Disabled, Blocking or Listening state + * Forwarding (cur_hw_state) state to Disabled, Blocking or Listening + * state (hw_state) */ if (cur_hw_state != hw_state) { - if (cur_hw_state & 4 && !(hw_state & 4)) { + if (cur_hw_state >= G_MISTP_LEARN_STATE && + hw_state <= G_MISTP_LISTEN_STATE) { ret = bcm_sf2_sw_fast_age_port(ds, port); if (ret) { pr_err("%s: fast-ageing failed\n", __func__); @@ -889,15 +893,11 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, struct fixed_phy_status *status) { struct bcm_sf2_priv *priv = ds_to_priv(ds); - u32 duplex, pause, speed; + u32 duplex, pause; u32 reg; duplex = core_readl(priv, CORE_DUPSTS); pause = core_readl(priv, CORE_PAUSESTS); - speed = core_readl(priv, CORE_SPDSTS); - - speed >>= (port * SPDSTS_SHIFT); - speed &= SPDSTS_MASK; status->link = 0; @@ -925,18 +925,6 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, reg &= ~LINK_STS; core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(port)); - switch (speed) { - case SPDSTS_10: - status->speed = SPEED_10; - break; - case SPDSTS_100: - status->speed = SPEED_100; - break; - case SPDSTS_1000: - status->speed = SPEED_1000; - break; - } - if ((pause & (1 << port)) && (pause & (1 << (port + PAUSESTS_TX_PAUSE_SHIFT)))) { status->asym_pause = 1; diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h index 22e2ebf31333..789d7b7737da 100644 --- a/drivers/net/dsa/bcm_sf2.h +++ b/drivers/net/dsa/bcm_sf2.h @@ -112,8 +112,8 @@ static inline u64 name##_readq(struct bcm_sf2_priv *priv, u32 off) \ spin_unlock(&priv->indir_lock); \ return (u64)indir << 32 | dir; \ } \ -static inline void name##_writeq(struct bcm_sf2_priv *priv, u32 off, \ - u64 val) \ +static inline void name##_writeq(struct bcm_sf2_priv *priv, u64 val, \ + u32 off) \ { \ spin_lock(&priv->indir_lock); \ reg_writel(priv, upper_32_bits(val), REG_DIR_DATA_WRITE); \ diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index da48e66377b5..8207877d6237 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -511,8 +511,7 @@ static int tse_poll(struct napi_struct *napi, int budget) if (rxcomplete < budget) { - napi_gro_flush(napi, false); - __napi_complete(napi); + napi_complete(napi); netdev_dbg(priv->dev, "NAPI Complete, did %d packets with budget %d\n", diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 66d47e448e4d..570390b5cd42 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1396,6 +1396,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) if ((status & BD_ENET_RX_LAST) == 0) netdev_err(ndev, "rcv is not +last\n"); + writel(FEC_ENET_RXF, fep->hwp + FEC_IEVENT); /* Check for errors. */ if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_NO | diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 74d0389bf233..4d608f0117cd 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3029,8 +3029,8 @@ static int mvneta_probe(struct platform_device *pdev) const char *dt_mac_addr; char hw_mac_addr[ETH_ALEN]; const char *mac_from; + const char *managed; int phy_mode; - int fixed_phy = 0; int err; /* Our multiqueue support is not complete, so for now, only @@ -3064,7 +3064,6 @@ static int mvneta_probe(struct platform_device *pdev) dev_err(&pdev->dev, "cannot register fixed PHY\n"); goto err_free_irq; } - fixed_phy = 1; /* In the case of a fixed PHY, the DT node associated * to the PHY is the Ethernet MAC DT node. @@ -3088,8 +3087,10 @@ static int mvneta_probe(struct platform_device *pdev) pp = netdev_priv(dev); pp->phy_node = phy_node; pp->phy_interface = phy_mode; - pp->use_inband_status = (phy_mode == PHY_INTERFACE_MODE_SGMII) && - fixed_phy; + + err = of_property_read_string(dn, "managed", &managed); + pp->use_inband_status = (err == 0 && + strcmp(managed, "in-band-status") == 0); pp->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(pp->clk)) { diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index eab4e080ebd2..80aac20104de 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -1256,8 +1256,6 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv) rss_context->hash_fn = MLX4_RSS_HASH_TOP; memcpy(rss_context->rss_key, priv->rss_key, MLX4_EN_RSS_KEY_SIZE); - netdev_rss_key_fill(rss_context->rss_key, - MLX4_EN_RSS_KEY_SIZE); } else { en_err(priv, "Unknown RSS hash function requested\n"); err = -EINVAL; diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 8c350c5d54ad..58858c5589db 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -1054,10 +1054,10 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, return 0; case TUNSETSNDBUF: - if (get_user(u, up)) + if (get_user(s, sp)) return -EFAULT; - q->sk.sk_sndbuf = u; + q->sk.sk_sndbuf = s; return 0; case TUNGETVNETHDRSZ: diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 1960b46add65..479b93f9581c 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -52,6 +52,10 @@ static int fixed_phy_update_regs(struct fixed_phy *fp) u16 lpagb = 0; u16 lpa = 0; + if (!fp->status.link) + goto done; + bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE; + if (fp->status.duplex) { bmcr |= BMCR_FULLDPLX; @@ -96,15 +100,13 @@ static int fixed_phy_update_regs(struct fixed_phy *fp) } } - if (fp->status.link) - bmsr |= BMSR_LSTATUS | BMSR_ANEGCOMPLETE; - if (fp->status.pause) lpa |= LPA_PAUSE_CAP; if (fp->status.asym_pause) lpa |= LPA_PAUSE_ASYM; +done: fp->regs[MII_PHYSID1] = 0; fp->regs[MII_PHYSID2] = 0; diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 3c86b107275a..e0498571ae26 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -778,7 +778,7 @@ int usbnet_stop (struct net_device *net) { struct usbnet *dev = netdev_priv(net); struct driver_info *info = dev->driver_info; - int retval, pm; + int retval, pm, mpn; clear_bit(EVENT_DEV_OPEN, &dev->flags); netif_stop_queue (net); @@ -809,6 +809,8 @@ int usbnet_stop (struct net_device *net) usbnet_purge_paused_rxq(dev); + mpn = !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags); + /* deferred work (task, timer, softirq) must also stop. * can't flush_scheduled_work() until we drop rtnl (later), * else workers could deadlock; so make workers a NOP. @@ -819,8 +821,7 @@ int usbnet_stop (struct net_device *net) if (!pm) usb_autopm_put_interface(dev->intf); - if (info->manage_power && - !test_and_clear_bit(EVENT_NO_RUNTIME_PM, &dev->flags)) + if (info->manage_power && mpn) info->manage_power(dev, 0); else usb_autopm_put_interface(dev->intf); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 21a0fbf1ed94..0085b8df83e2 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2212,6 +2212,8 @@ static int vxlan_open(struct net_device *dev) if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) { ret = vxlan_igmp_join(vxlan); + if (ret == -EADDRINUSE) + ret = 0; if (ret) { vxlan_sock_release(vs); return ret; diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 0c064485d1c2..bec8ec2b31f6 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -263,7 +263,8 @@ EXPORT_SYMBOL(of_phy_attach); bool of_phy_is_fixed_link(struct device_node *np) { struct device_node *dn; - int len; + int len, err; + const char *managed; /* New binding */ dn = of_get_child_by_name(np, "fixed-link"); @@ -272,6 +273,10 @@ bool of_phy_is_fixed_link(struct device_node *np) return true; } + err = of_property_read_string(np, "managed", &managed); + if (err == 0 && strcmp(managed, "auto") != 0) + return true; + /* Old binding */ if (of_get_property(np, "fixed-link", &len) && len == (5 * sizeof(__be32))) @@ -286,8 +291,18 @@ int of_phy_register_fixed_link(struct device_node *np) struct fixed_phy_status status = {}; struct device_node *fixed_link_node; const __be32 *fixed_link_prop; - int len; + int len, err; struct phy_device *phy; + const char *managed; + + err = of_property_read_string(np, "managed", &managed); + if (err == 0) { + if (strcmp(managed, "in-band-status") == 0) { + /* status is zeroed, namely its .link member */ + phy = fixed_phy_register(PHY_POLL, &status, np); + return IS_ERR(phy) ? PTR_ERR(phy) : 0; + } + } /* New binding */ fixed_link_node = of_get_child_by_name(np, "fixed-link"); diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 06697315a088..fb4dd7b3ee71 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -54,8 +54,9 @@ MODULE_ALIAS("wmi:5FB7F034-2C63-45e9-BE91-3D44E2C707E4"); #define HPWMI_HARDWARE_QUERY 0x4 #define HPWMI_WIRELESS_QUERY 0x5 #define HPWMI_BIOS_QUERY 0x9 +#define HPWMI_FEATURE_QUERY 0xb #define HPWMI_HOTKEY_QUERY 0xc -#define HPWMI_FEATURE_QUERY 0xd +#define HPWMI_FEATURE2_QUERY 0xd #define HPWMI_WIRELESS2_QUERY 0x1b #define HPWMI_POSTCODEERROR_QUERY 0x2a @@ -295,25 +296,33 @@ static int hp_wmi_tablet_state(void) return (state & 0x4) ? 1 : 0; } -static int __init hp_wmi_bios_2009_later(void) +static int __init hp_wmi_bios_2008_later(void) { int state = 0; int ret = hp_wmi_perform_query(HPWMI_FEATURE_QUERY, 0, &state, sizeof(state), sizeof(state)); - if (ret) - return ret; + if (!ret) + return 1; - return (state & 0x10) ? 1 : 0; + return (ret == HPWMI_RET_UNKNOWN_CMDTYPE) ? 0 : -ENXIO; } -static int hp_wmi_enable_hotkeys(void) +static int __init hp_wmi_bios_2009_later(void) { - int ret; - int query = 0x6e; + int state = 0; + int ret = hp_wmi_perform_query(HPWMI_FEATURE2_QUERY, 0, &state, + sizeof(state), sizeof(state)); + if (!ret) + return 1; - ret = hp_wmi_perform_query(HPWMI_BIOS_QUERY, 1, &query, sizeof(query), - 0); + return (ret == HPWMI_RET_UNKNOWN_CMDTYPE) ? 0 : -ENXIO; +} +static int __init hp_wmi_enable_hotkeys(void) +{ + int value = 0x6e; + int ret = hp_wmi_perform_query(HPWMI_BIOS_QUERY, 1, &value, + sizeof(value), 0); if (ret) return -EINVAL; return 0; @@ -663,7 +672,7 @@ static int __init hp_wmi_input_setup(void) hp_wmi_tablet_state()); input_sync(hp_wmi_input_dev); - if (hp_wmi_bios_2009_later() == 4) + if (!hp_wmi_bios_2009_later() && hp_wmi_bios_2008_later()) hp_wmi_enable_hotkeys(); status = wmi_install_notify_handler(HPWMI_EVENT_GUID, hp_wmi_notify, NULL); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index ff667e18b2d6..9ba383f5b0c4 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -980,7 +980,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); - len = sizeof(*ih); + len = skb_transport_offset(skb) + sizeof(*ih); for (i = 0; i < num; i++) { len += sizeof(*grec); @@ -1035,7 +1035,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, icmp6h = icmp6_hdr(skb); num = ntohs(icmp6h->icmp6_dataun.un_data16[1]); - len = sizeof(*icmp6h); + len = skb_transport_offset(skb) + sizeof(*icmp6h); for (i = 0; i < num; i++) { __be16 *nsrcs, _nsrcs; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 9a12668f7d62..0ad144fb0c79 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -615,15 +615,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, { int idx = 0; struct fib_rule *rule; + int err = 0; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; - if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWRULE, - NLM_F_MULTI, ops) < 0) + err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWRULE, + NLM_F_MULTI, ops); + if (err) break; skip: idx++; @@ -632,7 +634,7 @@ skip: cb->args[1] = idx; rules_ops_put(ops); - return skb->len; + return err; } static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) @@ -648,7 +650,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) if (ops == NULL) return -EAFNOSUPPORT; - return dump_rules(skb, cb, ops); + dump_rules(skb, cb, ops); + + return skb->len; } rcu_read_lock(); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 74dddf84adcd..556ecf96a385 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -86,6 +86,9 @@ int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, goto out; fprog = filter->prog->orig_prog; + if (!fprog) + goto out; + flen = bpf_classic_proglen(fprog); attr = nla_reserve(skb, attrtype, flen); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a369e8a70b2c..986440b24978 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2893,6 +2893,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); + skb_mstamp_get(&skb->skb_mstamp); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); diff --git a/net/ipv6/exthdrs_offload.c b/net/ipv6/exthdrs_offload.c index 447a7fbd1bb6..f5e2ba1c18bf 100644 --- a/net/ipv6/exthdrs_offload.c +++ b/net/ipv6/exthdrs_offload.c @@ -36,6 +36,6 @@ out: return ret; out_rt: - inet_del_offload(&rthdr_offload, IPPROTO_ROUTING); + inet6_del_offload(&rthdr_offload, IPPROTO_ROUTING); goto out; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a38d3ac0f18f..69f4f689f06a 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -361,6 +361,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); ip6gre_tunnel_unlink(ign, t); + ip6_tnl_dst_reset(t); dev_put(dev); } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 74ceb73c1c9a..5f36266b1f5e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -550,7 +550,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) if (it->cache == &mrt->mfc6_unres_queue) spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == mrt->mfc6_cache_array) + else if (it->cache == &mrt->mfc6_cache_array[it->ct]) read_unlock(&mrt_lock); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c73ae5039e46..f371fefa7fdc 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1515,7 +1515,7 @@ static int ip6_convert_metrics(struct mx6_config *mxc, return -EINVAL; } -int ip6_route_add(struct fib6_config *cfg) +int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret) { int err; struct net *net = cfg->fc_nlinfo.nl_net; @@ -1523,7 +1523,6 @@ int ip6_route_add(struct fib6_config *cfg) struct net_device *dev = NULL; struct inet6_dev *idev = NULL; struct fib6_table *table; - struct mx6_config mxc = { .mx = NULL, }; int addr_type; if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) @@ -1719,6 +1718,32 @@ install_route: cfg->fc_nlinfo.nl_net = dev_net(dev); + *rt_ret = rt; + + return 0; +out: + if (dev) + dev_put(dev); + if (idev) + in6_dev_put(idev); + if (rt) + dst_free(&rt->dst); + + *rt_ret = NULL; + + return err; +} + +int ip6_route_add(struct fib6_config *cfg) +{ + struct mx6_config mxc = { .mx = NULL, }; + struct rt6_info *rt = NULL; + int err; + + err = ip6_route_info_create(cfg, &rt); + if (err) + goto out; + err = ip6_convert_metrics(&mxc, cfg); if (err) goto out; @@ -1726,14 +1751,12 @@ install_route: err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc); kfree(mxc.mx); + return err; out: - if (dev) - dev_put(dev); - if (idev) - in6_dev_put(idev); if (rt) dst_free(&rt->dst); + return err; } @@ -2496,19 +2519,78 @@ errout: return err; } -static int ip6_route_multipath(struct fib6_config *cfg, int add) +struct rt6_nh { + struct rt6_info *rt6_info; + struct fib6_config r_cfg; + struct mx6_config mxc; + struct list_head next; +}; + +static void ip6_print_replace_route_err(struct list_head *rt6_nh_list) +{ + struct rt6_nh *nh; + + list_for_each_entry(nh, rt6_nh_list, next) { + pr_warn("IPV6: multipath route replace failed (check consistency of installed routes): %pI6 nexthop %pI6 ifi %d\n", + &nh->r_cfg.fc_dst, &nh->r_cfg.fc_gateway, + nh->r_cfg.fc_ifindex); + } +} + +static int ip6_route_info_append(struct list_head *rt6_nh_list, + struct rt6_info *rt, struct fib6_config *r_cfg) +{ + struct rt6_nh *nh; + struct rt6_info *rtnh; + int err = -EEXIST; + + list_for_each_entry(nh, rt6_nh_list, next) { + /* check if rt6_info already exists */ + rtnh = nh->rt6_info; + + if (rtnh->dst.dev == rt->dst.dev && + rtnh->rt6i_idev == rt->rt6i_idev && + ipv6_addr_equal(&rtnh->rt6i_gateway, + &rt->rt6i_gateway)) + return err; + } + + nh = kzalloc(sizeof(*nh), GFP_KERNEL); + if (!nh) + return -ENOMEM; + nh->rt6_info = rt; + err = ip6_convert_metrics(&nh->mxc, r_cfg); + if (err) { + kfree(nh); + return err; + } + memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg)); + list_add_tail(&nh->next, rt6_nh_list); + + return 0; +} + +static int ip6_route_multipath_add(struct fib6_config *cfg) { struct fib6_config r_cfg; struct rtnexthop *rtnh; + struct rt6_info *rt; + struct rt6_nh *err_nh; + struct rt6_nh *nh, *nh_safe; int remaining; int attrlen; - int err = 0, last_err = 0; + int err = 1; + int nhn = 0; + int replace = (cfg->fc_nlinfo.nlh && + (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE)); + LIST_HEAD(rt6_nh_list); remaining = cfg->fc_mp_len; -beginning: rtnh = (struct rtnexthop *)cfg->fc_mp; - /* Parse a Multipath Entry */ + /* Parse a Multipath Entry and build a list (rt6_nh_list) of + * rt6_info structs per nexthop + */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) @@ -2524,22 +2606,32 @@ beginning: r_cfg.fc_flags |= RTF_GATEWAY; } } - err = add ? ip6_route_add(&r_cfg) : ip6_route_del(&r_cfg); + + err = ip6_route_info_create(&r_cfg, &rt); + if (err) + goto cleanup; + + err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); if (err) { - last_err = err; - /* If we are trying to remove a route, do not stop the - * loop when ip6_route_del() fails (because next hop is - * already gone), we should try to remove all next hops. - */ - if (add) { - /* If add fails, we should try to delete all - * next hops that have been already added. - */ - add = 0; - remaining = cfg->fc_mp_len - remaining; - goto beginning; - } + dst_free(&rt->dst); + goto cleanup; + } + + rtnh = rtnh_next(rtnh, &remaining); + } + + err_nh = NULL; + list_for_each_entry(nh, &rt6_nh_list, next) { + err = __ip6_ins_rt(nh->rt6_info, &cfg->fc_nlinfo, &nh->mxc); + /* nh->rt6_info is used or freed at this point, reset to NULL*/ + nh->rt6_info = NULL; + if (err) { + if (replace && nhn) + ip6_print_replace_route_err(&rt6_nh_list); + err_nh = nh; + goto add_errout; } + /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, * we have already failed to add the first nexthop: @@ -2549,6 +2641,63 @@ beginning: */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + nhn++; + } + + goto cleanup; + +add_errout: + /* Delete routes that were already added */ + list_for_each_entry(nh, &rt6_nh_list, next) { + if (err_nh == nh) + break; + ip6_route_del(&nh->r_cfg); + } + +cleanup: + list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { + if (nh->rt6_info) + dst_free(&nh->rt6_info->dst); + if (nh->mxc.mx) + kfree(nh->mxc.mx); + list_del(&nh->next); + kfree(nh); + } + + return err; +} + +static int ip6_route_multipath_del(struct fib6_config *cfg) +{ + struct fib6_config r_cfg; + struct rtnexthop *rtnh; + int remaining; + int attrlen; + int err = 1, last_err = 0; + + remaining = cfg->fc_mp_len; + rtnh = (struct rtnexthop *)cfg->fc_mp; + + /* Parse a Multipath Entry */ + while (rtnh_ok(rtnh, remaining)) { + memcpy(&r_cfg, cfg, sizeof(*cfg)); + if (rtnh->rtnh_ifindex) + r_cfg.fc_ifindex = rtnh->rtnh_ifindex; + + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + struct nlattr *nla, *attrs = rtnh_attrs(rtnh); + + nla = nla_find(attrs, attrlen, RTA_GATEWAY); + if (nla) { + nla_memcpy(&r_cfg.fc_gateway, nla, 16); + r_cfg.fc_flags |= RTF_GATEWAY; + } + } + err = ip6_route_del(&r_cfg); + if (err) + last_err = err; + rtnh = rtnh_next(rtnh, &remaining); } @@ -2565,7 +2714,7 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) return err; if (cfg.fc_mp) - return ip6_route_multipath(&cfg, 0); + return ip6_route_multipath_del(&cfg); else return ip6_route_del(&cfg); } @@ -2580,7 +2729,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) return err; if (cfg.fc_mp) - return ip6_route_multipath(&cfg, 1); + return ip6_route_multipath_add(&cfg); else return ip6_route_add(&cfg); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4856d975492d..980121e75d2e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -123,6 +123,24 @@ static inline u32 netlink_group_mask(u32 group) return group ? 1 << (group - 1) : 0; } +static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, + gfp_t gfp_mask) +{ + unsigned int len = skb_end_offset(skb); + struct sk_buff *new; + + new = alloc_skb(len, gfp_mask); + if (new == NULL) + return NULL; + + NETLINK_CB(new).portid = NETLINK_CB(skb).portid; + NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group; + NETLINK_CB(new).creds = NETLINK_CB(skb).creds; + + memcpy(skb_put(new, len), skb->data, len); + return new; +} + int netlink_add_tap(struct netlink_tap *nt) { if (unlikely(nt->dev->type != ARPHRD_NETLINK)) @@ -204,7 +222,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb, int ret = -ENOMEM; dev_hold(dev); - nskb = skb_clone(skb, GFP_ATOMIC); + + if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head)) + nskb = netlink_to_full_skb(skb, GFP_ATOMIC); + else + nskb = skb_clone(skb, GFP_ATOMIC); if (nskb) { nskb->dev = dev; nskb->protocol = htons((u16) sk->sk_protocol); @@ -276,11 +298,6 @@ static void netlink_rcv_wake(struct sock *sk) } #ifdef CONFIG_NETLINK_MMAP -static bool netlink_skb_is_mmaped(const struct sk_buff *skb) -{ - return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED; -} - static bool netlink_rx_is_mmaped(struct sock *sk) { return nlk_sk(sk)->rx_ring.pg_vec != NULL; @@ -832,7 +849,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb) } #else /* CONFIG_NETLINK_MMAP */ -#define netlink_skb_is_mmaped(skb) false #define netlink_rx_is_mmaped(sk) false #define netlink_tx_is_mmaped(sk) false #define netlink_mmap sock_no_mmap @@ -1080,8 +1096,8 @@ static int netlink_insert(struct sock *sk, u32 portid) lock_sock(sk); - err = -EBUSY; - if (nlk_sk(sk)->portid) + err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY; + if (nlk_sk(sk)->bound) goto err; err = -ENOMEM; @@ -1101,10 +1117,13 @@ static int netlink_insert(struct sock *sk, u32 portid) err = -EOVERFLOW; if (err == -EEXIST) err = -EADDRINUSE; - nlk_sk(sk)->portid = 0; sock_put(sk); } + /* We need to ensure that the socket is hashed and visible. */ + smp_wmb(); + nlk_sk(sk)->bound = portid; + err: release_sock(sk); return err; @@ -1484,6 +1503,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err; long unsigned int groups = nladdr->nl_groups; + bool bound; if (addr_len < sizeof(struct sockaddr_nl)) return -EINVAL; @@ -1500,9 +1520,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } - if (nlk->portid) + bound = nlk->bound; + if (bound) { + /* Ensure nlk->portid is up-to-date. */ + smp_rmb(); + if (nladdr->nl_pid != nlk->portid) return -EINVAL; + } if (nlk->netlink_bind && groups) { int group; @@ -1518,7 +1543,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, } } - if (!nlk->portid) { + /* No need for barriers here as we return to user-space without + * using any of the bound attributes. + */ + if (!bound) { err = nladdr->nl_pid ? netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); @@ -1566,7 +1594,10 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; - if (!nlk->portid) + /* No need for barriers here as we return to user-space without + * using any of the bound attributes. + */ + if (!nlk->bound) err = netlink_autobind(sock); if (err == 0) { @@ -2323,10 +2354,13 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) dst_group = nlk->dst_group; } - if (!nlk->portid) { + if (!nlk->bound) { err = netlink_autobind(sock); if (err) goto out; + } else { + /* Ensure nlk is hashed and visible. */ + smp_rmb(); } /* It's a really convoluted way for userland to ask for mmaped diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 89008405d6b4..14437d9b1965 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -35,6 +35,7 @@ struct netlink_sock { unsigned long state; size_t max_recvmsg_len; wait_queue_head_t wait; + bool bound; bool cb_running; struct netlink_callback cb; struct mutex *cb_mutex; @@ -59,6 +60,15 @@ static inline struct netlink_sock *nlk_sk(struct sock *sk) return container_of(sk, struct netlink_sock, sk); } +static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb) +{ +#ifdef CONFIG_NETLINK_MMAP + return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED; +#else + return false; +#endif /* CONFIG_NETLINK_MMAP */ +} + struct netlink_table { struct rhashtable hash; struct hlist_head mc_list; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 096c6276e6b9..27e14962b504 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -906,7 +906,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) if (error) goto err_kfree_flow; - ovs_flow_mask_key(&new_flow->key, &key, &mask); + ovs_flow_mask_key(&new_flow->key, &key, true, &mask); /* Extract flow identifier. */ error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], @@ -1033,7 +1033,7 @@ static struct sw_flow_actions *get_flow_actions(const struct nlattr *a, struct sw_flow_key masked_key; int error; - ovs_flow_mask_key(&masked_key, key, mask); + ovs_flow_mask_key(&masked_key, key, true, mask); error = ovs_nla_copy_actions(a, &masked_key, &acts, log); if (error) { OVS_NLERR(log, diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 4613df8c8290..aa349514e4cb 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -56,20 +56,21 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range) } void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, - const struct sw_flow_mask *mask) + bool full, const struct sw_flow_mask *mask) { - const long *m = (const long *)((const u8 *)&mask->key + - mask->range.start); - const long *s = (const long *)((const u8 *)src + - mask->range.start); - long *d = (long *)((u8 *)dst + mask->range.start); + int start = full ? 0 : mask->range.start; + int len = full ? sizeof *dst : range_n_bytes(&mask->range); + const long *m = (const long *)((const u8 *)&mask->key + start); + const long *s = (const long *)((const u8 *)src + start); + long *d = (long *)((u8 *)dst + start); int i; - /* The memory outside of the 'mask->range' are not set since - * further operations on 'dst' only uses contents within - * 'mask->range'. + /* If 'full' is true then all of 'dst' is fully initialized. Otherwise, + * if 'full' is false the memory outside of the 'mask->range' is left + * uninitialized. This can be used as an optimization when further + * operations on 'dst' only use contents within 'mask->range'. */ - for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long)) + for (i = 0; i < len; i += sizeof(long)) *d++ = *s++ & *m++; } @@ -473,7 +474,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, u32 hash; struct sw_flow_key masked_key; - ovs_flow_mask_key(&masked_key, unmasked, mask); + ovs_flow_mask_key(&masked_key, unmasked, false, mask); hash = flow_hash(&masked_key, &mask->range); head = find_bucket(ti, hash); hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) { diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index 616eda10d955..2dd9900f533d 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -86,5 +86,5 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *, bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *); void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, - const struct sw_flow_mask *mask); + bool full, const struct sw_flow_mask *mask); #endif /* flow_table.h */ diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 715e01e5910a..f23a3b68bba6 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -33,7 +33,6 @@ struct fw_head { u32 mask; - bool mask_set; struct fw_filter __rcu *ht[HTSIZE]; struct rcu_head rcu; }; @@ -84,7 +83,7 @@ static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, } } } else { - /* old method */ + /* Old method: classify the packet using its skb mark. */ if (id && (TC_H_MAJ(id) == 0 || !(TC_H_MAJ(id ^ tp->q->handle)))) { res->classid = id; @@ -114,14 +113,9 @@ static unsigned long fw_get(struct tcf_proto *tp, u32 handle) static int fw_init(struct tcf_proto *tp) { - struct fw_head *head; - - head = kzalloc(sizeof(struct fw_head), GFP_KERNEL); - if (head == NULL) - return -ENOBUFS; - - head->mask_set = false; - rcu_assign_pointer(tp->root, head); + /* We don't allocate fw_head here, because in the old method + * we don't need it at all. + */ return 0; } @@ -252,7 +246,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, int err; if (!opt) - return handle ? -EINVAL : 0; + return handle ? -EINVAL : 0; /* Succeed if it is old method. */ err = nla_parse_nested(tb, TCA_FW_MAX, opt, fw_policy); if (err < 0) @@ -302,11 +296,17 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, if (!handle) return -EINVAL; - if (!head->mask_set) { - head->mask = 0xFFFFFFFF; + if (!head) { + u32 mask = 0xFFFFFFFF; if (tb[TCA_FW_MASK]) - head->mask = nla_get_u32(tb[TCA_FW_MASK]); - head->mask_set = true; + mask = nla_get_u32(tb[TCA_FW_MASK]); + + head = kzalloc(sizeof(*head), GFP_KERNEL); + if (!head) + return -ENOBUFS; + head->mask = mask; + + rcu_assign_pointer(tp->root, head); } f = kzalloc(sizeof(struct fw_filter), GFP_KERNEL); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index cab9e9b43967..4fbb67430ce4 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -490,6 +490,19 @@ static bool u32_destroy(struct tcf_proto *tp, bool force) return false; } } + + if (tp_c->refcnt > 1) + return false; + + if (tp_c->refcnt == 1) { + struct tc_u_hnode *ht; + + for (ht = rtnl_dereference(tp_c->hlist); + ht; + ht = rtnl_dereference(ht->next)) + if (!ht_empty(ht)) + return false; + } } if (root_ht && --root_ht->refcnt == 0) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 53b7acde9aa3..e13c3c3ea4ac 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1166,7 +1166,7 @@ static void sctp_v4_del_protocol(void) unregister_inetaddr_notifier(&sctp_inetaddr_notifier); } -static int __net_init sctp_net_init(struct net *net) +static int __net_init sctp_defaults_init(struct net *net) { int status; @@ -1259,12 +1259,6 @@ static int __net_init sctp_net_init(struct net *net) sctp_dbg_objcnt_init(net); - /* Initialize the control inode/socket for handling OOTB packets. */ - if ((status = sctp_ctl_sock_init(net))) { - pr_err("Failed to initialize the SCTP control sock\n"); - goto err_ctl_sock_init; - } - /* Initialize the local address list. */ INIT_LIST_HEAD(&net->sctp.local_addr_list); spin_lock_init(&net->sctp.local_addr_lock); @@ -1280,9 +1274,6 @@ static int __net_init sctp_net_init(struct net *net) return 0; -err_ctl_sock_init: - sctp_dbg_objcnt_exit(net); - sctp_proc_exit(net); err_init_proc: cleanup_sctp_mibs(net); err_init_mibs: @@ -1291,15 +1282,12 @@ err_sysctl_register: return status; } -static void __net_exit sctp_net_exit(struct net *net) +static void __net_exit sctp_defaults_exit(struct net *net) { /* Free the local address list */ sctp_free_addr_wq(net); sctp_free_local_addr_list(net); - /* Free the control endpoint. */ - inet_ctl_sock_destroy(net->sctp.ctl_sock); - sctp_dbg_objcnt_exit(net); sctp_proc_exit(net); @@ -1307,9 +1295,32 @@ static void __net_exit sctp_net_exit(struct net *net) sctp_sysctl_net_unregister(net); } -static struct pernet_operations sctp_net_ops = { - .init = sctp_net_init, - .exit = sctp_net_exit, +static struct pernet_operations sctp_defaults_ops = { + .init = sctp_defaults_init, + .exit = sctp_defaults_exit, +}; + +static int __net_init sctp_ctrlsock_init(struct net *net) +{ + int status; + + /* Initialize the control inode/socket for handling OOTB packets. */ + status = sctp_ctl_sock_init(net); + if (status) + pr_err("Failed to initialize the SCTP control sock\n"); + + return status; +} + +static void __net_init sctp_ctrlsock_exit(struct net *net) +{ + /* Free the control endpoint. */ + inet_ctl_sock_destroy(net->sctp.ctl_sock); +} + +static struct pernet_operations sctp_ctrlsock_ops = { + .init = sctp_ctrlsock_init, + .exit = sctp_ctrlsock_exit, }; /* Initialize the universe into something sensible. */ @@ -1442,8 +1453,11 @@ static __init int sctp_init(void) sctp_v4_pf_init(); sctp_v6_pf_init(); - status = sctp_v4_protosw_init(); + status = register_pernet_subsys(&sctp_defaults_ops); + if (status) + goto err_register_defaults; + status = sctp_v4_protosw_init(); if (status) goto err_protosw_init; @@ -1451,9 +1465,9 @@ static __init int sctp_init(void) if (status) goto err_v6_protosw_init; - status = register_pernet_subsys(&sctp_net_ops); + status = register_pernet_subsys(&sctp_ctrlsock_ops); if (status) - goto err_register_pernet_subsys; + goto err_register_ctrlsock; status = sctp_v4_add_protocol(); if (status) @@ -1469,12 +1483,14 @@ out: err_v6_add_protocol: sctp_v4_del_protocol(); err_add_protocol: - unregister_pernet_subsys(&sctp_net_ops); -err_register_pernet_subsys: + unregister_pernet_subsys(&sctp_ctrlsock_ops); +err_register_ctrlsock: sctp_v6_protosw_exit(); err_v6_protosw_init: sctp_v4_protosw_exit(); err_protosw_init: + unregister_pernet_subsys(&sctp_defaults_ops); +err_register_defaults: sctp_v4_pf_exit(); sctp_v6_pf_exit(); sctp_sysctl_unregister(); @@ -1507,12 +1523,14 @@ static __exit void sctp_exit(void) sctp_v6_del_protocol(); sctp_v4_del_protocol(); - unregister_pernet_subsys(&sctp_net_ops); + unregister_pernet_subsys(&sctp_ctrlsock_ops); /* Free protosw registrations */ sctp_v6_protosw_exit(); sctp_v4_protosw_exit(); + unregister_pernet_subsys(&sctp_defaults_ops); + /* Unregister with socket layer. */ sctp_v6_pf_exit(); sctp_v4_pf_exit(); -- To unsubscribe from this list: send the line "unsubscribe stable" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html