From 3647bc35bd427610a70eb83c58c5e834262badfa Mon Sep 17 00:00:00 2001 From: Rabin Vincent Date: Tue, 2 Feb 2016 09:39:02 +0100 Subject: dwc_eth_qos: Reset hardware before PHY start The hardware reset is currently done after phy_start() is called, leading to a race where we can lose the link status if the phy state machine calls dwceqos_adjust_link() before we reset the MAC registers. Acked-by: Lars Persson Signed-off-by: Rabin Vincent Signed-off-by: David S. Miller --- drivers/net/ethernet/synopsys/dwc_eth_qos.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 70814b7386b3..fc8bbff2d7e3 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -1880,9 +1880,9 @@ static int dwceqos_open(struct net_device *ndev) } netdev_reset_queue(ndev); + dwceqos_init_hw(lp); napi_enable(&lp->napi); phy_start(lp->phy_dev); - dwceqos_init_hw(lp); netif_start_queue(ndev); tasklet_enable(&lp->tx_bdreclaim_tasklet); -- cgit v1.2.3 From b7d987295c74500b733a0ba07f9a9bcc4074fa83 Mon Sep 17 00:00:00 2001 From: Siva Reddy Kallam Date: Wed, 3 Feb 2016 14:09:38 +0530 Subject: tg3: Fix for tg3 transmit queue 0 timed out when too many gso_segs tg3_tso_bug() can hit a condition where the entire tx ring is not big enough to segment the GSO packet. For example, if MSS is very small, gso_segs can exceed the tx ring size. When we hit the condition, it will cause tx timeout. tg3_tso_bug() is called to handle TSO and DMA hardware bugs. For TSO bugs, if tg3_tso_bug() cannot succeed, we have to drop the packet. For DMA bugs, we can still fall back to linearize the SKB and let the hardware transmit the TSO packet. This patch adds a function tg3_tso_bug_gso_check() to check if there are enough tx descriptors for GSO before calling tg3_tso_bug(). The caller will then handle the error appropriately - drop or lineraize the SKB. v2: Corrected patch description to avoid confusion. Signed-off-by: Siva Reddy Kallam Signed-off-by: Michael Chan Acked-by: Prashant Sreedharan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 49eea8981332..3010080cfeee 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -7831,6 +7831,14 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, return ret; } +static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb) +{ + /* Check if we will never have enough descriptors, + * as gso_segs can be more than current ring size + */ + return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3; +} + static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *); /* Use GSO to workaround all TSO packets that meet HW bug conditions @@ -7934,14 +7942,19 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) * vlan encapsulated. */ if (skb->protocol == htons(ETH_P_8021Q) || - skb->protocol == htons(ETH_P_8021AD)) - return tg3_tso_bug(tp, tnapi, txq, skb); + skb->protocol == htons(ETH_P_8021AD)) { + if (tg3_tso_bug_gso_check(tnapi, skb)) + return tg3_tso_bug(tp, tnapi, txq, skb); + goto drop; + } if (!skb_is_gso_v6(skb)) { if (unlikely((ETH_HLEN + hdr_len) > 80) && - tg3_flag(tp, TSO_BUG)) - return tg3_tso_bug(tp, tnapi, txq, skb); - + tg3_flag(tp, TSO_BUG)) { + if (tg3_tso_bug_gso_check(tnapi, skb)) + return tg3_tso_bug(tp, tnapi, txq, skb); + goto drop; + } ip_csum = iph->check; ip_tot_len = iph->tot_len; iph->check = 0; @@ -8073,7 +8086,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) if (would_hit_hwbug) { tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, i); - if (mss) { + if (mss && tg3_tso_bug_gso_check(tnapi, skb)) { /* If it's a TSO packet, do GSO instead of * allocating and copying to a large linear SKB */ -- cgit v1.2.3 From ca7f41a4957b872577807169bd7464b36aae9b9c Mon Sep 17 00:00:00 2001 From: Sandeep Pillai Date: Wed, 3 Feb 2016 14:40:44 +0530 Subject: enic: increment devcmd2 result ring in case of timeout Firmware posts the devcmd result in result ring. In case of timeout, driver does not increment the current result pointer and firmware could post the result after timeout has occurred. During next devcmd, driver would be reading the result of previous devcmd. Fix this by incrementing result even in case of timeout. Fixes: 373fb0873d43 ("enic: add devcmd2") Signed-off-by: Sandeep Pillai Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com> Signed-off-by: David S. Miller --- drivers/net/ethernet/cisco/enic/enic.h | 2 +- drivers/net/ethernet/cisco/enic/vnic_dev.c | 19 ++++++++++++------- 2 files changed, 13 insertions(+), 8 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index 1671fa3332c2..7ba6d530b0c0 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -33,7 +33,7 @@ #define DRV_NAME "enic" #define DRV_DESCRIPTION "Cisco VIC Ethernet NIC Driver" -#define DRV_VERSION "2.3.0.12" +#define DRV_VERSION "2.3.0.20" #define DRV_COPYRIGHT "Copyright 2008-2013 Cisco Systems, Inc" #define ENIC_BARS_MAX 6 diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c index 1ffd1050860b..1fdf5fe12a95 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_dev.c +++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c @@ -298,7 +298,8 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, int wait) { struct devcmd2_controller *dc2c = vdev->devcmd2; - struct devcmd2_result *result = dc2c->result + dc2c->next_result; + struct devcmd2_result *result; + u8 color; unsigned int i; int delay, err; u32 fetch_index, new_posted; @@ -336,13 +337,17 @@ static int _vnic_dev_cmd2(struct vnic_dev *vdev, enum vnic_devcmd_cmd cmd, if (dc2c->cmd_ring[posted].flags & DEVCMD2_FNORESULT) return 0; + result = dc2c->result + dc2c->next_result; + color = dc2c->color; + + dc2c->next_result++; + if (dc2c->next_result == dc2c->result_size) { + dc2c->next_result = 0; + dc2c->color = dc2c->color ? 0 : 1; + } + for (delay = 0; delay < wait; delay++) { - if (result->color == dc2c->color) { - dc2c->next_result++; - if (dc2c->next_result == dc2c->result_size) { - dc2c->next_result = 0; - dc2c->color = dc2c->color ? 0 : 1; - } + if (result->color == color) { if (result->error) { err = result->error; if (err != ERR_ECMDUNKNOWN || -- cgit v1.2.3 From f5a952c08e842cb06eb5c65947ced9b5128a62ee Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Wed, 3 Feb 2016 21:35:29 +0200 Subject: of: of_mdio: Add marvell, 88e1145 to whitelist of PHY compatibilities. Commit ae461131960b ("of: of_mdio: Add a whitelist of PHY compatibilities.") missed one compatible string used in in-tree DTBs: in OCTEON, for selected boards, the kernel DTB pruning code will overwrite the DTB compatible string with "marvell,88e1145", which is missing from the whitelist. Add it. The patch fixes broken networking on EdgeRouter Lite. Fixes: ae461131960b ("of: of_mdio: Add a whitelist of PHY compatibilities.") Signed-off-by: Aaro Koskinen Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/of/of_mdio.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers') diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 5648317d355f..39c4be41ef83 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -154,6 +154,7 @@ static const struct of_device_id whitelist_phys[] = { { .compatible = "marvell,88E1111", }, { .compatible = "marvell,88e1116", }, { .compatible = "marvell,88e1118", }, + { .compatible = "marvell,88e1145", }, { .compatible = "marvell,88e1149r", }, { .compatible = "marvell,88e1310", }, { .compatible = "marvell,88E1510", }, -- cgit v1.2.3 From 72564b59ffc438ea103b0727a921aaddce766728 Mon Sep 17 00:00:00 2001 From: David Wragg Date: Wed, 10 Feb 2016 00:05:55 +0000 Subject: vxlan: Relax MTU constraints Allow the MTU of vxlan devices without an underlying device to be set to larger values (up to a maximum based on IP packet limits and vxlan overhead). Previously, their MTUs could not be set to higher than the conventional ethernet value of 1500. This is a very arbitrary value in the context of vxlan, and prevented vxlan devices from being able to take advantage of jumbo frames etc. The default MTU remains 1500, for compatibility. Signed-off-by: David Wragg Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 36 +++++++++++++++++++++++++----------- 1 file changed, 25 insertions(+), 11 deletions(-) (limited to 'drivers') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 65439188c582..e992c6a05f86 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2367,29 +2367,43 @@ static void vxlan_set_multicast_list(struct net_device *dev) { } -static int vxlan_change_mtu(struct net_device *dev, int new_mtu) +static int __vxlan_change_mtu(struct net_device *dev, + struct net_device *lowerdev, + struct vxlan_rdst *dst, int new_mtu, bool strict) { - struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_rdst *dst = &vxlan->default_dst; - struct net_device *lowerdev; - int max_mtu; + int max_mtu = IP_MAX_MTU; - lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); - if (lowerdev == NULL) - return eth_change_mtu(dev, new_mtu); + if (lowerdev) + max_mtu = lowerdev->mtu; if (dst->remote_ip.sa.sa_family == AF_INET6) - max_mtu = lowerdev->mtu - VXLAN6_HEADROOM; + max_mtu -= VXLAN6_HEADROOM; else - max_mtu = lowerdev->mtu - VXLAN_HEADROOM; + max_mtu -= VXLAN_HEADROOM; - if (new_mtu < 68 || new_mtu > max_mtu) + if (new_mtu < 68) return -EINVAL; + if (new_mtu > max_mtu) { + if (strict) + return -EINVAL; + + new_mtu = max_mtu; + } + dev->mtu = new_mtu; return 0; } +static int vxlan_change_mtu(struct net_device *dev, int new_mtu) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_rdst *dst = &vxlan->default_dst; + struct net_device *lowerdev = __dev_get_by_index(vxlan->net, + dst->remote_ifindex); + return __vxlan_change_mtu(dev, lowerdev, dst, new_mtu, true); +} + static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb, struct ip_tunnel_info *info, __be16 sport, __be16 dport) -- cgit v1.2.3 From 55e5bfb53cff286c1c1ff49f51325dc15c7fea63 Mon Sep 17 00:00:00 2001 From: David Wragg Date: Wed, 10 Feb 2016 00:05:57 +0000 Subject: geneve: Relax MTU constraints Allow the MTU of geneve devices to be set to large values, in order to exploit underlying networks with larger frame sizes. GENEVE does not have a fixed encapsulation overhead (an openvswitch rule can add variable length options), so there is no relevant maximum MTU to enforce. A maximum of IP_MAX_MTU is used instead. Encapsulated packets that are too big for the underlying network will get dropped on the floor. Signed-off-by: David Wragg Signed-off-by: David S. Miller --- drivers/net/geneve.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 0b14ac3b8d11..d2031ce8baea 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1039,6 +1039,17 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) return geneve_xmit_skb(skb, dev, info); } +static int geneve_change_mtu(struct net_device *dev, int new_mtu) +{ + /* GENEVE overhead is not fixed, so we can't enforce a more + * precise max MTU. + */ + if (new_mtu < 68 || new_mtu > IP_MAX_MTU) + return -EINVAL; + dev->mtu = new_mtu; + return 0; +} + static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); @@ -1083,7 +1094,7 @@ static const struct net_device_ops geneve_netdev_ops = { .ndo_stop = geneve_stop, .ndo_start_xmit = geneve_xmit, .ndo_get_stats64 = ip_tunnel_get_stats64, - .ndo_change_mtu = eth_change_mtu, + .ndo_change_mtu = geneve_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fill_metadata_dst = geneve_fill_metadata_dst, -- cgit v1.2.3 From 7e059158d57b79159eaf1f504825d19866ef2c42 Mon Sep 17 00:00:00 2001 From: David Wragg Date: Wed, 10 Feb 2016 00:05:58 +0000 Subject: vxlan, gre, geneve: Set a large MTU on ovs-created tunnel devices Prior to 4.3, openvswitch tunnel vports (vxlan, gre and geneve) could transmit vxlan packets of any size, constrained only by the ability to send out the resulting packets. 4.3 introduced netdevs corresponding to tunnel vports. These netdevs have an MTU, which limits the size of a packet that can be successfully encapsulated. The default MTU values are low (1500 or less), which is awkwardly small in the context of physical networks supporting jumbo frames, and leads to a conspicuous change in behaviour for userspace. Instead, set the MTU on openvswitch-created netdevs to be the relevant maximum (i.e. the maximum IP packet size minus any relevant overhead), effectively restoring the behaviour prior to 4.3. Signed-off-by: David Wragg Signed-off-by: David S. Miller --- drivers/net/geneve.c | 18 ++++++++++++++---- drivers/net/vxlan.c | 11 ++++++++--- 2 files changed, 22 insertions(+), 7 deletions(-) (limited to 'drivers') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index d2031ce8baea..028e3873c310 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1453,11 +1453,21 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, err = geneve_configure(net, dev, &geneve_remote_unspec, 0, 0, 0, htons(dst_port), true, 0); - if (err) { - free_netdev(dev); - return ERR_PTR(err); - } + if (err) + goto err; + + /* openvswitch users expect packet sizes to be unrestricted, + * so set the largest MTU we can. + */ + err = geneve_change_mtu(dev, IP_MAX_MTU); + if (err) + goto err; + return dev; + + err: + free_netdev(dev); + return ERR_PTR(err); } EXPORT_SYMBOL_GPL(geneve_dev_create_fb); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index e992c6a05f86..a31cd954b308 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2779,6 +2779,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, int err; bool use_ipv6 = false; __be16 default_port = vxlan->cfg.dst_port; + struct net_device *lowerdev = NULL; vxlan->net = src_net; @@ -2799,9 +2800,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, } if (conf->remote_ifindex) { - struct net_device *lowerdev - = __dev_get_by_index(src_net, conf->remote_ifindex); - + lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex); dst->remote_ifindex = conf->remote_ifindex; if (!lowerdev) { @@ -2825,6 +2824,12 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, needed_headroom = lowerdev->hard_header_len; } + if (conf->mtu) { + err = __vxlan_change_mtu(dev, lowerdev, dst, conf->mtu, false); + if (err) + return err; + } + if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA) needed_headroom += VXLAN6_HEADROOM; else -- cgit v1.2.3