From f870c1ff65a6d1f3a083f277280802ee09a5b44d Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Thu, 14 Dec 2017 20:20:00 +0300 Subject: vxlan: restore dev->mtu setting based on lower device Stefano Brivio says: Commit a985343ba906 ("vxlan: refactor verification and application of configuration") introduced a change in the behaviour of initial MTU setting: earlier, the MTU for a link created on top of a given lower device, without an initial MTU specification, was set to the MTU of the lower device minus headroom as a result of this path in vxlan_dev_configure(): if (!conf->mtu) dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); which is now gone. Now, the initial MTU, in absence of a configured value, is simply set by ether_setup() to ETH_DATA_LEN (1500 bytes). This breaks userspace expectations in case the MTU of the lower device is higher than 1500 bytes minus headroom. This patch restores the previous behaviour on newlink operation. Since max_mtu can be negative and we update dev->mtu directly, also check it for valid minimum. Reported-by: Junhan Yan Fixes: a985343ba906 ("vxlan: refactor verification and application of configuration") Signed-off-by: Alexey Kodanev Acked-by: Stefano Brivio Signed-off-by: Stefano Brivio Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 19b9cc51079e..1000b0e4ee01 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3103,6 +3103,11 @@ static void vxlan_config_apply(struct net_device *dev, max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); + if (max_mtu < ETH_MIN_MTU) + max_mtu = ETH_MIN_MTU; + + if (!changelink && !conf->mtu) + dev->mtu = max_mtu; } if (dev->mtu > max_mtu) -- cgit v1.2.3-59-g8ed1b From c505873eaece2b4aefd07d339dc7e1400e0235ac Mon Sep 17 00:00:00 2001 From: Zhao Qiang Date: Mon, 18 Dec 2017 10:26:43 +0800 Subject: net: phy: marvell: Limit 88m1101 autoneg errata to 88E1145 as well. 88E1145 also need this autoneg errata. Fixes: f2899788353c ("net: phy: marvell: Limit errata to 88m1101") Signed-off-by: Zhao Qiang Signed-off-by: David S. Miller --- drivers/net/phy/marvell.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index b5a8f750e433..26c9a11220ca 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -2073,7 +2073,7 @@ static struct phy_driver marvell_drivers[] = { .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, .config_init = &m88e1145_config_init, - .config_aneg = &marvell_config_aneg, + .config_aneg = &m88e1101_config_aneg, .read_status = &genphy_read_status, .ack_interrupt = &marvell_ack_interrupt, .config_intr = &marvell_config_intr, -- cgit v1.2.3-59-g8ed1b From ac3241d5c81bf6e85095481435f29a4627ff820e Mon Sep 17 00:00:00 2001 From: Hemanth Puranik Date: Mon, 18 Dec 2017 11:27:47 +0530 Subject: net: qcom/emac: Change the order of mac up and sgmii open This patch fixes the order of mac_up and sgmii_open for the reasons noted below: - If open takes more time(if the SGMII block is not responding or if we want to do some delay based task) in this situation we will hit NETDEV watchdog - The main reason : We should signal to upper layers that we are ready to receive packets "only" when the entire path is initialized not the other way around, this is followed in the reset path where we do mac_down, sgmii_reset and mac_up. This also makes the driver uniform across the reset and open paths. - In the future there may be need for delay based tasks to be done in sgmii open which will result in NETDEV watchdog - As per the documentation the order of init should be sgmii, mac, rings and DMA Signed-off-by: Hemanth Puranik Acked-by: Timur Tabi Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 70c92b649b29..38c924bdd32e 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -253,18 +253,18 @@ static int emac_open(struct net_device *netdev) return ret; } - ret = emac_mac_up(adpt); + ret = adpt->phy.open(adpt); if (ret) { emac_mac_rx_tx_rings_free_all(adpt); free_irq(irq->irq, irq); return ret; } - ret = adpt->phy.open(adpt); + ret = emac_mac_up(adpt); if (ret) { - emac_mac_down(adpt); emac_mac_rx_tx_rings_free_all(adpt); free_irq(irq->irq, irq); + adpt->phy.close(adpt); return ret; } -- cgit v1.2.3-59-g8ed1b From 6623c0fba10ef45b64ca213ad5dec926f37fa9a0 Mon Sep 17 00:00:00 2001 From: Russell King Date: Fri, 15 Dec 2017 16:10:20 +0000 Subject: net: phy: marvell: avoid pause mode on SGMII-to-Copper for 88e151x Observed on the 88e1512 in SGMII-to-Copper mode, negotiating pause is unreliable. While the pause bits can be set in the advertisment register, they clear shortly after negotiation with a link partner commences irrespective of the cause of the negotiation. While these bits may be correctly conveyed to the link partner on the first negotiation, a subsequent negotiation (eg, due to negotiation restart by the link partner, or reconnection of the cable) will result in the link partner seeing these bits as zero, while the kernel believes that it has advertised pause modes. This leads to the local kernel evaluating (eg) symmetric pause mode, while the remote end evaluates that we have no pause mode capability. Since we can't guarantee the advertisment, disable pause mode support with this PHY when used in SGMII-to-Copper mode. The 88e1510 in RGMII-to-Copper mode appears to behave correctly. Reviewed-by: Andrew Lunn Signed-off-by: Russell King Signed-off-by: David S. Miller --- drivers/net/phy/marvell.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 26c9a11220ca..82104edca393 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -879,6 +879,8 @@ static int m88e1510_config_init(struct phy_device *phydev) /* SGMII-to-Copper mode initialization */ if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { + u32 pause; + /* Select page 18 */ err = marvell_set_page(phydev, 18); if (err < 0) @@ -902,6 +904,16 @@ static int m88e1510_config_init(struct phy_device *phydev) err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE); if (err < 0) return err; + + /* There appears to be a bug in the 88e1512 when used in + * SGMII to copper mode, where the AN advertisment register + * clears the pause bits each time a negotiation occurs. + * This means we can never be truely sure what was advertised, + * so disable Pause support. + */ + pause = SUPPORTED_Pause | SUPPORTED_Asym_Pause; + phydev->supported &= ~pause; + phydev->advertising &= ~pause; } return m88e1121_config_init(phydev); -- cgit v1.2.3-59-g8ed1b From ab14436065c8066c265540312742390d6d07ddd2 Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Sat, 16 Dec 2017 00:52:39 +0300 Subject: net: phy: xgene: disable clk on error paths There are several error paths in xgene_mdio_probe(), where clk is left undisabled. The patch fixes them. Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Alexey Khoroshilov Signed-off-by: David S. Miller --- drivers/net/phy/mdio-xgene.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/phy/mdio-xgene.c index bfd3090fb055..07c6048200c6 100644 --- a/drivers/net/phy/mdio-xgene.c +++ b/drivers/net/phy/mdio-xgene.c @@ -194,8 +194,11 @@ static int xgene_mdio_reset(struct xgene_mdio_pdata *pdata) } ret = xgene_enet_ecc_init(pdata); - if (ret) + if (ret) { + if (pdata->dev->of_node) + clk_disable_unprepare(pdata->clk); return ret; + } xgene_gmac_reset(pdata); return 0; @@ -388,8 +391,10 @@ static int xgene_mdio_probe(struct platform_device *pdev) return ret; mdio_bus = mdiobus_alloc(); - if (!mdio_bus) - return -ENOMEM; + if (!mdio_bus) { + ret = -ENOMEM; + goto out_clk; + } mdio_bus->name = "APM X-Gene MDIO bus"; @@ -418,7 +423,7 @@ static int xgene_mdio_probe(struct platform_device *pdev) mdio_bus->phy_mask = ~0; ret = mdiobus_register(mdio_bus); if (ret) - goto out; + goto out_mdiobus; acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_HANDLE(dev), 1, acpi_register_phy, NULL, mdio_bus, NULL); @@ -426,16 +431,20 @@ static int xgene_mdio_probe(struct platform_device *pdev) } if (ret) - goto out; + goto out_mdiobus; pdata->mdio_bus = mdio_bus; xgene_mdio_status = true; return 0; -out: +out_mdiobus: mdiobus_free(mdio_bus); +out_clk: + if (dev->of_node) + clk_disable_unprepare(pdata->clk); + return ret; } -- cgit v1.2.3-59-g8ed1b From b65c7b8aeac818eb8f80ce825073c12ad081b177 Mon Sep 17 00:00:00 2001 From: Adiel Aloni Date: Mon, 18 Dec 2017 12:14:04 +0200 Subject: mac80211_hwsim: enable TODS BIT in null data frame Same as in ieee80211_nullfunc_get, enable the TODS bit, otherwise the nullfunc packet will not be handled in ap rx path. (will be dropped in ieee80211_accept_frame()). Signed-off-by: Adiel Aloni Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/mac80211_hwsim.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/net') diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 10b075a46b26..59b0cedcdf7b 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -684,6 +684,7 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, hdr = skb_put(skb, sizeof(*hdr) - ETH_ALEN); hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC | + IEEE80211_FCTL_TODS | (ps ? IEEE80211_FCTL_PM : 0)); hdr->duration_id = cpu_to_le16(0); memcpy(hdr->addr1, vp->bssid, ETH_ALEN); -- cgit v1.2.3-59-g8ed1b From 162bd5e5fd921785077b5862d8f2ffabe2fe11e5 Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Tue, 12 Dec 2017 17:26:36 +0800 Subject: mac80211_hwsim: Fix a possible sleep-in-atomic bug in hwsim_get_radio_nl The driver may sleep under a spinlock. The function call path is: hwsim_get_radio_nl (acquire the spinlock) nlmsg_new(GFP_KERNEL) --> may sleep To fix it, GFP_KERNEL is replaced with GFP_ATOMIC. This bug is found by my static analysis tool(DSAC) and checked by my code review. Signed-off-by: Jia-Ju Bai Signed-off-by: Johannes Berg --- drivers/net/wireless/mac80211_hwsim.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 59b0cedcdf7b..e8189c07b41f 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3216,7 +3216,7 @@ static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info) if (!net_eq(wiphy_net(data->hw->wiphy), genl_info_net(info))) continue; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) { res = -ENOMEM; goto out_err; -- cgit v1.2.3-59-g8ed1b From 748a240c589824e9121befb1cba5341c319885bc Mon Sep 17 00:00:00 2001 From: Brian King Date: Fri, 15 Dec 2017 15:21:50 -0600 Subject: tg3: Fix rx hang on MTU change with 5717/5719 This fixes a hang issue seen when changing the MTU size from 1500 MTU to 9000 MTU on both 5717 and 5719 chips. In discussion with Broadcom, they've indicated that these chipsets have the same phy as the 57766 chipset, so the same workarounds apply. This has been tested by IBM on both Power 8 and Power 9 systems as well as by Broadcom on x86 hardware and has been confirmed to resolve the hang issue. Signed-off-by: Brian King Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/tg3.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index de51c2177d03..d09c5a9c53b5 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -14225,7 +14225,9 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu) /* Reset PHY, otherwise the read DMA engine will be in a mode that * breaks all requests to 256 bytes. */ - if (tg3_asic_rev(tp) == ASIC_REV_57766) + if (tg3_asic_rev(tp) == ASIC_REV_57766 || + tg3_asic_rev(tp) == ASIC_REV_5717 || + tg3_asic_rev(tp) == ASIC_REV_5719) reset_phy = true; err = tg3_restart_hw(tp, reset_phy); -- cgit v1.2.3-59-g8ed1b From 8ba6b30ef700e16f3bc668e6f4f8375da9229e4d Mon Sep 17 00:00:00 2001 From: Petr Machata Date: Sun, 17 Dec 2017 17:16:43 +0100 Subject: mlxsw: spectrum_router: Remove batch neighbour deletion causing FW bug This reverts commit 63dd00fa3e524c27cc0509190084ab147ecc8ae2. RAUHT DELETE_ALL seems to trigger a bug in FW. That manifests by later calls to RAUHT ADD of an IPv6 neighbor to fail with "bad parameter" error code. Signed-off-by: Petr Machata Fixes: 63dd00fa3e52 ("mlxsw: spectrum_router: Add batch neighbour deletion") Reviewed-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 72ef4f8025f0..be657b8533f0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2436,25 +2436,16 @@ static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp) rhashtable_destroy(&mlxsw_sp->router->neigh_ht); } -static int mlxsw_sp_neigh_rif_flush(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_rif *rif) -{ - char rauht_pl[MLXSW_REG_RAUHT_LEN]; - - mlxsw_reg_rauht_pack(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL, - rif->rif_index, rif->addr); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); -} - static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif) { struct mlxsw_sp_neigh_entry *neigh_entry, *tmp; - mlxsw_sp_neigh_rif_flush(mlxsw_sp, rif); list_for_each_entry_safe(neigh_entry, tmp, &rif->neigh_list, - rif_list_node) + rif_list_node) { + mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, false); mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); + } } enum mlxsw_sp_nexthop_type { -- cgit v1.2.3-59-g8ed1b From 7352e252b5bf40d59342494a70354a2d436fd0cd Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Mon, 18 Dec 2017 17:00:17 +0800 Subject: net: mediatek: setup proper state for disabled GMAC on the default The current solution would setup fixed and force link of 1Gbps to the both GMAC on the default. However, The GMAC should always be put to link down state when the GMAC is disabled on certain target boards. Otherwise, the driver possibly receives unexpected data from the floating hardware connection through the unused GMAC. Although the driver had been added certain protection in RX path to get rid of such kind of unexpected data sent to the upper stack. Signed-off-by: Sean Wang Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 54adfd967858..fc67e35b253e 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1961,11 +1961,12 @@ static int mtk_hw_init(struct mtk_eth *eth) /* set GE2 TUNE */ regmap_write(eth->pctl, GPIO_BIAS_CTRL, 0x0); - /* GE1, Force 1000M/FD, FC ON */ - mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(0)); - - /* GE2, Force 1000M/FD, FC ON */ - mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(1)); + /* Set linkdown as the default for each GMAC. Its own MCR would be set + * up with the more appropriate value when mtk_phy_link_adjust call is + * being invoked. + */ + for (i = 0; i < MTK_MAC_COUNT; i++) + mtk_w32(eth, 0, MTK_MAC_MCR(i)); /* Indicates CDM to parse the MTK special tag from CPU * which also is working out for untag packets. -- cgit v1.2.3-59-g8ed1b From e688822d035b494071ecbadcccbd6f3325fb0f59 Mon Sep 17 00:00:00 2001 From: Alexander Kochetkov Date: Fri, 15 Dec 2017 20:20:06 +0300 Subject: net: arc_emac: fix arc_emac_rx() error paths arc_emac_rx() has some issues found by code review. In case netdev_alloc_skb_ip_align() or dma_map_single() failure rx fifo entry will not be returned to EMAC. In case dma_map_single() failure previously allocated skb became lost to driver. At the same time address of newly allocated skb will not be provided to EMAC. Signed-off-by: Alexander Kochetkov Signed-off-by: David S. Miller --- drivers/net/ethernet/arc/emac_main.c | 53 +++++++++++++++++++++--------------- 1 file changed, 31 insertions(+), 22 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 3241af1ce718..5b422be56165 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -210,39 +210,48 @@ static int arc_emac_rx(struct net_device *ndev, int budget) continue; } - pktlen = info & LEN_MASK; - stats->rx_packets++; - stats->rx_bytes += pktlen; - skb = rx_buff->skb; - skb_put(skb, pktlen); - skb->dev = ndev; - skb->protocol = eth_type_trans(skb, ndev); - - dma_unmap_single(&ndev->dev, dma_unmap_addr(rx_buff, addr), - dma_unmap_len(rx_buff, len), DMA_FROM_DEVICE); - - /* Prepare the BD for next cycle */ - rx_buff->skb = netdev_alloc_skb_ip_align(ndev, - EMAC_BUFFER_SIZE); - if (unlikely(!rx_buff->skb)) { + /* Prepare the BD for next cycle. netif_receive_skb() + * only if new skb was allocated and mapped to avoid holes + * in the RX fifo. + */ + skb = netdev_alloc_skb_ip_align(ndev, EMAC_BUFFER_SIZE); + if (unlikely(!skb)) { + if (net_ratelimit()) + netdev_err(ndev, "cannot allocate skb\n"); + /* Return ownership to EMAC */ + rxbd->info = cpu_to_le32(FOR_EMAC | EMAC_BUFFER_SIZE); stats->rx_errors++; - /* Because receive_skb is below, increment rx_dropped */ stats->rx_dropped++; continue; } - /* receive_skb only if new skb was allocated to avoid holes */ - netif_receive_skb(skb); - - addr = dma_map_single(&ndev->dev, (void *)rx_buff->skb->data, + addr = dma_map_single(&ndev->dev, (void *)skb->data, EMAC_BUFFER_SIZE, DMA_FROM_DEVICE); if (dma_mapping_error(&ndev->dev, addr)) { if (net_ratelimit()) - netdev_err(ndev, "cannot dma map\n"); - dev_kfree_skb(rx_buff->skb); + netdev_err(ndev, "cannot map dma buffer\n"); + dev_kfree_skb(skb); + /* Return ownership to EMAC */ + rxbd->info = cpu_to_le32(FOR_EMAC | EMAC_BUFFER_SIZE); stats->rx_errors++; + stats->rx_dropped++; continue; } + + /* unmap previosly mapped skb */ + dma_unmap_single(&ndev->dev, dma_unmap_addr(rx_buff, addr), + dma_unmap_len(rx_buff, len), DMA_FROM_DEVICE); + + pktlen = info & LEN_MASK; + stats->rx_packets++; + stats->rx_bytes += pktlen; + skb_put(rx_buff->skb, pktlen); + rx_buff->skb->dev = ndev; + rx_buff->skb->protocol = eth_type_trans(rx_buff->skb, ndev); + + netif_receive_skb(rx_buff->skb); + + rx_buff->skb = skb; dma_unmap_addr_set(rx_buff, addr, addr); dma_unmap_len_set(rx_buff, len, EMAC_BUFFER_SIZE); -- cgit v1.2.3-59-g8ed1b From 78aa09754d69ba19a55c59f490788ec1c85f41f0 Mon Sep 17 00:00:00 2001 From: Alexander Kochetkov Date: Tue, 19 Dec 2017 14:03:57 +0300 Subject: net: arc_emac: restart stalled EMAC Under certain conditions EMAC stop reception of incoming packets and continuously increment R_MISS register instead of saving data into provided buffer. The commit implement workaround for such situation. Then the stall detected EMAC will be restarted. On device the stall looks like the device lost it's dynamic IP address. ifconfig shows that interface error counter rapidly increments. At the same time on the DHCP server we can see continues DHCP-requests from device. In real network stalls happen really rarely. To make them frequent the broadcast storm[1] should be simulated. For simulation it is necessary to make following connections: 1. connect radxarock to 1st port of switch 2. connect some PC to 2nd port of switch 3. connect two other free ports together using standard ethernet cable, in order to make a switching loop. After that, is necessary to make a broadcast storm. For example, running on PC 'ping' to some IP address triggers ARP-request storm. After some time (~10sec), EMAC on rk3188 will stall. Observed and tested on rk3188 radxarock. [1] https://en.wikipedia.org/wiki/Broadcast_radiation Signed-off-by: Alexander Kochetkov Signed-off-by: David S. Miller --- drivers/net/ethernet/arc/emac.h | 2 + drivers/net/ethernet/arc/emac_main.c | 111 +++++++++++++++++++++++++++++++++++ 2 files changed, 113 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/arc/emac.h b/drivers/net/ethernet/arc/emac.h index 3c63b16d485f..d9efbc8d783b 100644 --- a/drivers/net/ethernet/arc/emac.h +++ b/drivers/net/ethernet/arc/emac.h @@ -159,6 +159,8 @@ struct arc_emac_priv { unsigned int link; unsigned int duplex; unsigned int speed; + + unsigned int rx_missed_errors; }; /** diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 5b422be56165..bd277b0dc615 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -26,6 +26,8 @@ #include "emac.h" +static void arc_emac_restart(struct net_device *ndev); + /** * arc_emac_tx_avail - Return the number of available slots in the tx ring. * @priv: Pointer to ARC EMAC private data structure. @@ -267,6 +269,53 @@ static int arc_emac_rx(struct net_device *ndev, int budget) return work_done; } +/** + * arc_emac_rx_miss_handle - handle R_MISS register + * @ndev: Pointer to the net_device structure. + */ +static void arc_emac_rx_miss_handle(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct net_device_stats *stats = &ndev->stats; + unsigned int miss; + + miss = arc_reg_get(priv, R_MISS); + if (miss) { + stats->rx_errors += miss; + stats->rx_missed_errors += miss; + priv->rx_missed_errors += miss; + } +} + +/** + * arc_emac_rx_stall_check - check RX stall + * @ndev: Pointer to the net_device structure. + * @budget: How many BDs requested to process on 1 call. + * @work_done: How many BDs processed + * + * Under certain conditions EMAC stop reception of incoming packets and + * continuously increment R_MISS register instead of saving data into + * provided buffer. This function detect that condition and restart + * EMAC. + */ +static void arc_emac_rx_stall_check(struct net_device *ndev, + int budget, unsigned int work_done) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct arc_emac_bd *rxbd; + + if (work_done) + priv->rx_missed_errors = 0; + + if (priv->rx_missed_errors && budget) { + rxbd = &priv->rxbd[priv->last_rx_bd]; + if (le32_to_cpu(rxbd->info) & FOR_EMAC) { + arc_emac_restart(ndev); + priv->rx_missed_errors = 0; + } + } +} + /** * arc_emac_poll - NAPI poll handler. * @napi: Pointer to napi_struct structure. @@ -281,6 +330,7 @@ static int arc_emac_poll(struct napi_struct *napi, int budget) unsigned int work_done; arc_emac_tx_clean(ndev); + arc_emac_rx_miss_handle(ndev); work_done = arc_emac_rx(ndev, budget); if (work_done < budget) { @@ -288,6 +338,8 @@ static int arc_emac_poll(struct napi_struct *napi, int budget) arc_reg_or(priv, R_ENABLE, RXINT_MASK | TXINT_MASK); } + arc_emac_rx_stall_check(ndev, budget, work_done); + return work_done; } @@ -329,6 +381,8 @@ static irqreturn_t arc_emac_intr(int irq, void *dev_instance) if (status & MSER_MASK) { stats->rx_missed_errors += 0x100; stats->rx_errors += 0x100; + priv->rx_missed_errors += 0x100; + napi_schedule(&priv->napi); } if (status & RXCR_MASK) { @@ -741,6 +795,63 @@ static int arc_emac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } +/** + * arc_emac_restart - Restart EMAC + * @ndev: Pointer to net_device structure. + * + * This function do hardware reset of EMAC in order to restore + * network packets reception. + */ +static void arc_emac_restart(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct net_device_stats *stats = &ndev->stats; + int i; + + if (net_ratelimit()) + netdev_warn(ndev, "restarting stalled EMAC\n"); + + netif_stop_queue(ndev); + + /* Disable interrupts */ + arc_reg_clr(priv, R_ENABLE, RXINT_MASK | TXINT_MASK | ERR_MASK); + + /* Disable EMAC */ + arc_reg_clr(priv, R_CTRL, EN_MASK); + + /* Return the sk_buff to system */ + arc_free_tx_queue(ndev); + + /* Clean Tx BD's */ + priv->txbd_curr = 0; + priv->txbd_dirty = 0; + memset(priv->txbd, 0, TX_RING_SZ); + + for (i = 0; i < RX_BD_NUM; i++) { + struct arc_emac_bd *rxbd = &priv->rxbd[i]; + unsigned int info = le32_to_cpu(rxbd->info); + + if (!(info & FOR_EMAC)) { + stats->rx_errors++; + stats->rx_dropped++; + } + /* Return ownership to EMAC */ + rxbd->info = cpu_to_le32(FOR_EMAC | EMAC_BUFFER_SIZE); + } + priv->last_rx_bd = 0; + + /* Make sure info is visible to EMAC before enable */ + wmb(); + + /* Enable interrupts */ + arc_reg_set(priv, R_ENABLE, RXINT_MASK | TXINT_MASK | ERR_MASK); + + /* Enable EMAC */ + arc_reg_or(priv, R_CTRL, EN_MASK); + + netif_start_queue(ndev); +} + static const struct net_device_ops arc_emac_netdev_ops = { .ndo_open = arc_emac_open, .ndo_stop = arc_emac_stop, -- cgit v1.2.3-59-g8ed1b From a93bf0ff449064e6b7f44e58522e940f88c0d966 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 18 Dec 2017 14:20:56 +0800 Subject: vxlan: update skb dst pmtu on tx path Unlike ip tunnels, now vxlan doesn't do any pmtu update for upper dst pmtu, even if it doesn't match the lower dst pmtu any more. The problem can be reproduced when reducing the vxlan lower dev's pmtu when running netperf. In jianlin's testing, the performance went to 1/7 of the previous. This patch is to update the upper dst pmtu to match the lower dst pmtu on tx path so that packets can be sent out even when lower dev's pmtu has been changed. It also works for metadata dst. Note that this patch doesn't process any pmtu icmp packet. But even in the future, the support for pmtu icmp packets process of udp tunnels will also needs this. The same thing will be done for geneve in another patch. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 1000b0e4ee01..31f4b7911ef8 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2155,6 +2155,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } ndst = &rt->dst; + if (skb_dst(skb)) { + int mtu = dst_mtu(ndst) - VXLAN_HEADROOM; + + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, + skb, mtu); + } + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), @@ -2190,6 +2197,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto out_unlock; } + if (skb_dst(skb)) { + int mtu = dst_mtu(ndst) - VXLAN6_HEADROOM; + + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, + skb, mtu); + } + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); -- cgit v1.2.3-59-g8ed1b From 200922c93f008e03ddc804c6dacdf26ca1ba86d7 Mon Sep 17 00:00:00 2001 From: Fredrik Hallenberg Date: Mon, 18 Dec 2017 23:33:59 +0100 Subject: net: stmmac: Fix TX timestamp calculation When using GMAC4 the value written in PTP_SSIR should be shifted however the shifted value is also used in subsequent calculations which results in a bad timestamp value. Signed-off-by: Fredrik Hallenberg Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 721b61655261..08c19ebd5306 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -34,6 +34,7 @@ static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr, { u32 value = readl(ioaddr + PTP_TCR); unsigned long data; + u32 reg_value; /* For GMAC3.x, 4.x versions, convert the ptp_clock to nano second * formula = (1/ptp_clock) * 1000000000 @@ -50,10 +51,11 @@ static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr, data &= PTP_SSIR_SSINC_MASK; + reg_value = data; if (gmac4) - data = data << GMAC4_PTP_SSIR_SSINC_SHIFT; + reg_value <<= GMAC4_PTP_SSIR_SSINC_SHIFT; - writel(data, ioaddr + PTP_SSIR); + writel(reg_value, ioaddr + PTP_SSIR); return data; } -- cgit v1.2.3-59-g8ed1b From a1762456993893795030d911106a7650481db0ef Mon Sep 17 00:00:00 2001 From: Fredrik Hallenberg Date: Mon, 18 Dec 2017 23:34:00 +0100 Subject: net: stmmac: Fix bad RX timestamp extraction As noted in dwmac4_wrback_get_rx_timestamp_status the timestamp is found in the context descriptor following the current descriptor. However the current code looks for the context descriptor in the current descriptor, which will always fail. Signed-off-by: Fredrik Hallenberg Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c | 5 +++-- drivers/net/ethernet/stmicro/stmmac/enh_desc.c | 3 ++- drivers/net/ethernet/stmicro/stmmac/norm_desc.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- 5 files changed, 8 insertions(+), 6 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index e1e5ac053760..ce2ea2d491ac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -409,7 +409,7 @@ struct stmmac_desc_ops { /* get timestamp value */ u64(*get_timestamp) (void *desc, u32 ats); /* get rx timestamp status */ - int (*get_rx_timestamp_status) (void *desc, u32 ats); + int (*get_rx_timestamp_status)(void *desc, void *next_desc, u32 ats); /* Display ring */ void (*display_ring)(void *head, unsigned int size, bool rx); /* set MSS via context descriptor */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 4b286e27c4ca..7e089bf906b4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -258,7 +258,8 @@ static int dwmac4_rx_check_timestamp(void *desc) return ret; } -static int dwmac4_wrback_get_rx_timestamp_status(void *desc, u32 ats) +static int dwmac4_wrback_get_rx_timestamp_status(void *desc, void *next_desc, + u32 ats) { struct dma_desc *p = (struct dma_desc *)desc; int ret = -EINVAL; @@ -270,7 +271,7 @@ static int dwmac4_wrback_get_rx_timestamp_status(void *desc, u32 ats) /* Check if timestamp is OK from context descriptor */ do { - ret = dwmac4_rx_check_timestamp(desc); + ret = dwmac4_rx_check_timestamp(next_desc); if (ret < 0) goto exit; i++; diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 7546b3664113..2a828a312814 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -400,7 +400,8 @@ static u64 enh_desc_get_timestamp(void *desc, u32 ats) return ns; } -static int enh_desc_get_rx_timestamp_status(void *desc, u32 ats) +static int enh_desc_get_rx_timestamp_status(void *desc, void *next_desc, + u32 ats) { if (ats) { struct dma_extended_desc *p = (struct dma_extended_desc *)desc; diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c index f817f8f36569..db4cee57bb24 100644 --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c @@ -265,7 +265,7 @@ static u64 ndesc_get_timestamp(void *desc, u32 ats) return ns; } -static int ndesc_get_rx_timestamp_status(void *desc, u32 ats) +static int ndesc_get_rx_timestamp_status(void *desc, void *next_desc, u32 ats) { struct dma_desc *p = (struct dma_desc *)desc; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d7250539d0bd..337d53d12e94 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -482,7 +482,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, desc = np; /* Check if timestamp is available */ - if (priv->hw->desc->get_rx_timestamp_status(desc, priv->adv_ts)) { + if (priv->hw->desc->get_rx_timestamp_status(p, np, priv->adv_ts)) { ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts); netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns); shhwtstamp = skb_hwtstamps(skb); -- cgit v1.2.3-59-g8ed1b From bae115a2bb479142605726e6aa130f43f50e801a Mon Sep 17 00:00:00 2001 From: Kamal Heib Date: Sun, 29 Oct 2017 04:03:37 +0200 Subject: net/mlx5: FPGA, return -EINVAL if size is zero Currently, if a size of zero is passed to mlx5_fpga_mem_{read|write}_i2c() the "err" return value will not be initialized, which triggers gcc warnings: [..]/mlx5/core/fpga/sdk.c:87 mlx5_fpga_mem_read_i2c() error: uninitialized symbol 'err'. [..]/mlx5/core/fpga/sdk.c:115 mlx5_fpga_mem_write_i2c() error: uninitialized symbol 'err'. fix that. Fixes: a9956d35d199 ('net/mlx5: FPGA, Add SBU infrastructure') Signed-off-by: Kamal Heib Reviewed-by: Yevgeny Kliteynik Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c index 3c11d6e2160a..14962969c5ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c @@ -66,6 +66,9 @@ static int mlx5_fpga_mem_read_i2c(struct mlx5_fpga_device *fdev, size_t size, u8 actual_size; int err; + if (!size) + return -EINVAL; + if (!fdev->mdev) return -ENOTCONN; @@ -95,6 +98,9 @@ static int mlx5_fpga_mem_write_i2c(struct mlx5_fpga_device *fdev, size_t size, u8 actual_size; int err; + if (!size) + return -EINVAL; + if (!fdev->mdev) return -ENOTCONN; -- cgit v1.2.3-59-g8ed1b From 231243c82793428467524227ae02ca451e6a98e7 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 10 Nov 2017 15:59:52 +0900 Subject: Revert "mlx5: move affinity hints assignments to generic code" Before the offending commit, mlx5 core did the IRQ affinity itself, and it seems that the new generic code have some drawbacks and one of them is the lack for user ability to modify irq affinity after the initial affinity values got assigned. The issue is still being discussed and a solution in the new generic code is required, until then we need to revert this patch. This fixes the following issue: echo > /proc/irq//smp_affinity fails with -EIO This reverts commit a435393acafbf0ecff4deb3e3cb554b34f0d0664. Note: kept mlx5_get_vector_affinity in include/linux/mlx5/driver.h since it is used in mlx5_ib driver. Fixes: a435393acafb ("mlx5: move affinity hints assignments to generic code") Cc: Sagi Grimberg Cc: Thomas Gleixner Cc: Jes Sorensen Reported-by: Jes Sorensen Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 45 +++++++------- drivers/net/ethernet/mellanox/mlx5/core/main.c | 75 +++++++++++++++++++++-- include/linux/mlx5/driver.h | 1 + 4 files changed, 93 insertions(+), 29 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index c0872b3284cb..43f9054830e5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -590,6 +590,7 @@ struct mlx5e_channel { struct mlx5_core_dev *mdev; struct hwtstamp_config *tstamp; int ix; + int cpu; }; struct mlx5e_channels { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d2b057a3e512..cbec66bc82f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -71,11 +71,6 @@ struct mlx5e_channel_param { struct mlx5e_cq_param icosq_cq; }; -static int mlx5e_get_node(struct mlx5e_priv *priv, int ix) -{ - return pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix); -} - static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) { return MLX5_CAP_GEN(mdev, striding_rq) && @@ -444,17 +439,16 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int wq_sz = mlx5_wq_ll_get_size(&rq->wq); int mtt_sz = mlx5e_get_wqe_mtt_sz(); int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1; - int node = mlx5e_get_node(c->priv, c->ix); int i; rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info), - GFP_KERNEL, node); + GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->mpwqe.info) goto err_out; /* We allocate more than mtt_sz as we will align the pointer */ - rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, - GFP_KERNEL, node); + rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL, + cpu_to_node(c->cpu)); if (unlikely(!rq->mpwqe.mtt_no_align)) goto err_free_wqe_info; @@ -562,7 +556,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, int err; int i; - rqp->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + rqp->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq, &rq->wq_ctrl); @@ -629,8 +623,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, default: /* MLX5_WQ_TYPE_LINKED_LIST */ rq->wqe.frag_info = kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info), - GFP_KERNEL, - mlx5e_get_node(c->priv, c->ix)); + GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->wqe.frag_info) { err = -ENOMEM; goto err_rq_wq_destroy; @@ -1000,13 +993,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_xdpsq_db(sq, mlx5e_get_node(c->priv, c->ix)); + err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; @@ -1053,13 +1046,13 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, sq->channel = c; sq->uar_map = mdev->mlx5e_res.bfreg.map; - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_icosq_db(sq, mlx5e_get_node(c->priv, c->ix)); + err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; @@ -1126,13 +1119,13 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_txqsq_db(sq, mlx5e_get_node(c->priv, c->ix)); + err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; @@ -1504,8 +1497,8 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c, struct mlx5_core_dev *mdev = c->priv->mdev; int err; - param->wq.buf_numa_node = mlx5e_get_node(c->priv, c->ix); - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.buf_numa_node = cpu_to_node(c->cpu); + param->wq.db_numa_node = cpu_to_node(c->cpu); param->eq_ix = c->ix; err = mlx5e_alloc_cq_common(mdev, param, cq); @@ -1604,6 +1597,11 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq) mlx5e_free_cq(cq); } +static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix) +{ + return cpumask_first(priv->mdev->priv.irq_info[ix].mask); +} + static int mlx5e_open_tx_cqs(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) @@ -1752,12 +1750,13 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, { struct mlx5e_cq_moder icocq_moder = {0, 0}; struct net_device *netdev = priv->netdev; + int cpu = mlx5e_get_cpu(priv, ix); struct mlx5e_channel *c; unsigned int irq; int err; int eqn; - c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix)); + c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu)); if (!c) return -ENOMEM; @@ -1765,6 +1764,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->mdev = priv->mdev; c->tstamp = &priv->tstamp; c->ix = ix; + c->cpu = cpu; c->pdev = &priv->mdev->pdev->dev; c->netdev = priv->netdev; c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key); @@ -1853,8 +1853,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) for (tc = 0; tc < c->num_tc; tc++) mlx5e_activate_txqsq(&c->sq[tc]); mlx5e_activate_rq(&c->rq); - netif_set_xps_queue(c->netdev, - mlx5_get_vector_affinity(c->priv->mdev, c->ix), c->ix); + netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix); } static void mlx5e_deactivate_channel(struct mlx5e_channel *c) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 5f323442cc5a..8a89c7e8cd63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -317,9 +317,6 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; struct mlx5_eq_table *table = &priv->eq_table; - struct irq_affinity irqdesc = { - .pre_vectors = MLX5_EQ_VEC_COMP_BASE, - }; int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq); int nvec; @@ -333,10 +330,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) if (!priv->irq_info) goto err_free_msix; - nvec = pci_alloc_irq_vectors_affinity(dev->pdev, + nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1, nvec, - PCI_IRQ_MSIX | PCI_IRQ_AFFINITY, - &irqdesc); + PCI_IRQ_MSIX); if (nvec < 0) return nvec; @@ -622,6 +618,63 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev) return (u64)timer_l | (u64)timer_h1 << 32; } +static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i) +{ + struct mlx5_priv *priv = &mdev->priv; + int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i); + + if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) { + mlx5_core_warn(mdev, "zalloc_cpumask_var failed"); + return -ENOMEM; + } + + cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node), + priv->irq_info[i].mask); + + if (IS_ENABLED(CONFIG_SMP) && + irq_set_affinity_hint(irq, priv->irq_info[i].mask)) + mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq); + + return 0; +} + +static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i) +{ + struct mlx5_priv *priv = &mdev->priv; + int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i); + + irq_set_affinity_hint(irq, NULL); + free_cpumask_var(priv->irq_info[i].mask); +} + +static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev) +{ + int err; + int i; + + for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) { + err = mlx5_irq_set_affinity_hint(mdev, i); + if (err) + goto err_out; + } + + return 0; + +err_out: + for (i--; i >= 0; i--) + mlx5_irq_clear_affinity_hint(mdev, i); + + return err; +} + +static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev) +{ + int i; + + for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) + mlx5_irq_clear_affinity_hint(mdev, i); +} + int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, unsigned int *irqn) { @@ -1097,6 +1150,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_stop_eqs; } + err = mlx5_irq_set_affinity_hints(dev); + if (err) { + dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n"); + goto err_affinity_hints; + } + err = mlx5_init_fs(dev); if (err) { dev_err(&pdev->dev, "Failed to init flow steering\n"); @@ -1154,6 +1213,9 @@ err_sriov: mlx5_cleanup_fs(dev); err_fs: + mlx5_irq_clear_affinity_hints(dev); + +err_affinity_hints: free_comp_eqs(dev); err_stop_eqs: @@ -1222,6 +1284,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_sriov_detach(dev); mlx5_cleanup_fs(dev); + mlx5_irq_clear_affinity_hints(dev); free_comp_eqs(dev); mlx5_stop_eqs(dev); mlx5_put_uars_page(dev, priv->uar); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a886b51511ab..40a6f33c4cde 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -556,6 +556,7 @@ struct mlx5_core_sriov { }; struct mlx5_irq_info { + cpumask_var_t mask; char name[MLX5_MAX_IRQ_NAME]; }; -- cgit v1.2.3-59-g8ed1b From 37e92a9d4fe38dc3e7308913575983a6a088c8d4 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 13 Nov 2017 10:11:27 +0200 Subject: net/mlx5: Fix rate limit packet pacing naming and struct In mlx5_ifc, struct size was not complete, and thus driver was sending garbage after the last defined field. Fixed it by adding reserved field to complete the struct size. In addition, rename all set_rate_limit to set_pp_rate_limit to be compliant with the Firmware <-> Driver definition. Fixes: 7486216b3a0b ("{net,IB}/mlx5: mlx5_ifc updates") Fixes: 1466cc5b23d1 ("net/mlx5: Rate limit tables support") Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/rl.c | 22 +++++++++++----------- include/linux/mlx5/mlx5_ifc.h | 8 +++++--- 3 files changed, 18 insertions(+), 16 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1fffdebbc9e8..e9a1fbcc4adf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -362,7 +362,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_QUERY_VPORT_COUNTER: case MLX5_CMD_OP_ALLOC_Q_COUNTER: case MLX5_CMD_OP_QUERY_Q_COUNTER: - case MLX5_CMD_OP_SET_RATE_LIMIT: + case MLX5_CMD_OP_SET_PP_RATE_LIMIT: case MLX5_CMD_OP_QUERY_RATE_LIMIT: case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT: case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT: @@ -505,7 +505,7 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER); MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER); MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER); - MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT); + MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT); MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT); MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT); MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c index e651e4c02867..d3c33e9eea72 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c @@ -125,16 +125,16 @@ static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table, return ret_entry; } -static int mlx5_set_rate_limit_cmd(struct mlx5_core_dev *dev, +static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev, u32 rate, u16 index) { - u32 in[MLX5_ST_SZ_DW(set_rate_limit_in)] = {0}; - u32 out[MLX5_ST_SZ_DW(set_rate_limit_out)] = {0}; + u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(set_pp_rate_limit_out)] = {0}; - MLX5_SET(set_rate_limit_in, in, opcode, - MLX5_CMD_OP_SET_RATE_LIMIT); - MLX5_SET(set_rate_limit_in, in, rate_limit_index, index); - MLX5_SET(set_rate_limit_in, in, rate_limit, rate); + MLX5_SET(set_pp_rate_limit_in, in, opcode, + MLX5_CMD_OP_SET_PP_RATE_LIMIT); + MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, index); + MLX5_SET(set_pp_rate_limit_in, in, rate_limit, rate); return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } @@ -173,7 +173,7 @@ int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index) entry->refcount++; } else { /* new rate limit */ - err = mlx5_set_rate_limit_cmd(dev, rate, entry->index); + err = mlx5_set_pp_rate_limit_cmd(dev, rate, entry->index); if (err) { mlx5_core_err(dev, "Failed configuring rate: %u (%d)\n", rate, err); @@ -209,7 +209,7 @@ void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate) entry->refcount--; if (!entry->refcount) { /* need to remove rate */ - mlx5_set_rate_limit_cmd(dev, 0, entry->index); + mlx5_set_pp_rate_limit_cmd(dev, 0, entry->index); entry->rate = 0; } @@ -262,8 +262,8 @@ void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev) /* Clear all configured rates */ for (i = 0; i < table->max_size; i++) if (table->rl_entry[i].rate) - mlx5_set_rate_limit_cmd(dev, 0, - table->rl_entry[i].index); + mlx5_set_pp_rate_limit_cmd(dev, 0, + table->rl_entry[i].index); kfree(dev->priv.rl_table.rl_entry); } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 38a7577a9ce7..d44ec5f41d4a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -147,7 +147,7 @@ enum { MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771, MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772, MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773, - MLX5_CMD_OP_SET_RATE_LIMIT = 0x780, + MLX5_CMD_OP_SET_PP_RATE_LIMIT = 0x780, MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781, MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT = 0x782, MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT = 0x783, @@ -7239,7 +7239,7 @@ struct mlx5_ifc_add_vxlan_udp_dport_in_bits { u8 vxlan_udp_port[0x10]; }; -struct mlx5_ifc_set_rate_limit_out_bits { +struct mlx5_ifc_set_pp_rate_limit_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -7248,7 +7248,7 @@ struct mlx5_ifc_set_rate_limit_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_set_rate_limit_in_bits { +struct mlx5_ifc_set_pp_rate_limit_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -7261,6 +7261,8 @@ struct mlx5_ifc_set_rate_limit_in_bits { u8 reserved_at_60[0x20]; u8 rate_limit[0x20]; + + u8 reserved_at_a0[0x160]; }; struct mlx5_ifc_access_register_out_bits { -- cgit v1.2.3-59-g8ed1b From ff0891915cd7b24ab27eee9b360c0452853bf9f6 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Thu, 26 Oct 2017 09:56:34 -0500 Subject: net/mlx5e: Fix ETS BW check Fix bug that allows ets bw sum to be 0% when ets tc type exists. Fixes: 08fb1dacdd76 ('net/mlx5e: Support DCBNL IEEE ETS') Signed-off-by: Moshe Shemesh Reviewed-by: Huy Nguyen Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index c6d90b6dd80e..9bcf38f4123b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -274,6 +274,7 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, struct ieee_ets *ets) { + bool have_ets_tc = false; int bw_sum = 0; int i; @@ -288,11 +289,14 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, } /* Validate Bandwidth Sum */ - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { + have_ets_tc = true; bw_sum += ets->tc_tx_bw[i]; + } + } - if (bw_sum != 0 && bw_sum != 100) { + if (have_ets_tc && bw_sum != 100) { netdev_err(netdev, "Failed to validate ETS: BW sum is illegal\n"); return -EINVAL; -- cgit v1.2.3-59-g8ed1b From 2989ad1ec03021ee6d2193c35414f1d970a243de Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Tue, 21 Nov 2017 17:49:36 +0200 Subject: net/mlx5e: Fix features check of IPv6 traffic The assumption that the next header field contains the transport protocol is wrong for IPv6 packets with extension headers. Instead, we should look the inner-most next header field in the buffer. This will fix TSO offload for tunnels over IPv6 with extension headers. Performance testing: 19.25x improvement, cool! Measuring bandwidth of 16 threads TCP traffic over IPv6 GRE tap. CPU: Intel(R) Xeon(R) CPU E5-2660 v2 @ 2.20GHz NIC: Mellanox Technologies MT28800 Family [ConnectX-5 Ex] TSO: Enabled Before: 4,926.24 Mbps Now : 94,827.91 Mbps Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling") Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index cbec66bc82f1..c535a44ab8ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3678,6 +3678,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, struct sk_buff *skb, netdev_features_t features) { + unsigned int offset = 0; struct udphdr *udph; u8 proto; u16 port; @@ -3687,7 +3688,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, proto = ip_hdr(skb)->protocol; break; case htons(ETH_P_IPV6): - proto = ipv6_hdr(skb)->nexthdr; + proto = ipv6_find_hdr(skb, &offset, -1, NULL, NULL); break; default: goto out; -- cgit v1.2.3-59-g8ed1b From 696a97cf9f5c551fca257e0d4aa07b5cbde6084a Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Tue, 14 Nov 2017 09:44:55 +0200 Subject: net/mlx5e: Fix defaulting RX ring size when not needed Fixes the bug when turning on/off CQE compression mechanism resets the RX rings size to default value when it is not needed. Fixes: 2fc4bfb7250d ("net/mlx5e: Dynamic RQ type infrastructure") Signed-off-by: Eugenia Emantayev Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 8 ++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 10 ++++++++-- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 +++++++-------- drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 2 +- 4 files changed, 22 insertions(+), 13 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 43f9054830e5..543060c305a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -82,6 +82,9 @@ max_t(u32, MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev), req) #define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev) MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 6) #define MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 8) +#define MLX5E_MPWQE_STRIDE_SZ(mdev, cqe_cmprs) \ + (cqe_cmprs ? MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) : \ + MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev)) #define MLX5_MPWRQ_LOG_WQE_SZ 18 #define MLX5_MPWRQ_WQE_PAGE_ORDER (MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT > 0 ? \ @@ -936,8 +939,9 @@ void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode); void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode); -void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, - struct mlx5e_params *params, u8 rq_type); +void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + u8 rq_type); static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 23425f028405..8f05efa5c829 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1523,8 +1523,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val new_channels.params = priv->channels.params; MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val); - mlx5e_set_rq_type_params(priv->mdev, &new_channels.params, - new_channels.params.rq_wq_type); + new_channels.params.mpwqe_log_stride_sz = + MLX5E_MPWQE_STRIDE_SZ(priv->mdev, new_val); + new_channels.params.mpwqe_log_num_strides = + MLX5_MPWRQ_LOG_WQE_SZ - new_channels.params.mpwqe_log_stride_sz; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; @@ -1536,6 +1538,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val return err; mlx5e_switch_priv_channels(priv, &new_channels, NULL); + mlx5e_dbg(DRV, priv, "MLX5E: RxCqeCmprss was turned %s\n", + MLX5E_GET_PFLAG(&priv->channels.params, + MLX5E_PFLAG_RX_CQE_COMPRESS) ? "ON" : "OFF"); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index c535a44ab8ac..d9d8227f195f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -78,8 +78,8 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) MLX5_CAP_ETH(mdev, reg_umr_sq); } -void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, - struct mlx5e_params *params, u8 rq_type) +void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, u8 rq_type) { params->rq_wq_type = rq_type; params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; @@ -88,10 +88,8 @@ void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, params->log_rq_size = is_kdump_kernel() ? MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW : MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW; - params->mpwqe_log_stride_sz = - MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS) ? - MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) : - MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev); + params->mpwqe_log_stride_sz = MLX5E_MPWQE_STRIDE_SZ(mdev, + MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); params->mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - params->mpwqe_log_stride_sz; break; @@ -115,13 +113,14 @@ void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); } -static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params) +static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params) { u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(mdev) && !params->xdp_prog && !MLX5_IPSEC_DEV(mdev) ? MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ : MLX5_WQ_TYPE_LINKED_LIST; - mlx5e_set_rq_type_params(mdev, params, rq_type); + mlx5e_init_rq_type_params(mdev, params, rq_type); } static void mlx5e_update_carrier(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index d2a66dc4adc6..8812d7208e8f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -57,7 +57,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { /* Override RQ params as IPoIB supports only LINKED LIST RQ for now */ - mlx5e_set_rq_type_params(mdev, params, MLX5_WQ_TYPE_LINKED_LIST); + mlx5e_init_rq_type_params(mdev, params, MLX5_WQ_TYPE_LINKED_LIST); /* RQ size in ipoib by default is 512 */ params->log_rq_size = is_kdump_kernel() ? -- cgit v1.2.3-59-g8ed1b From 777ec2b2a3f2760505db395de1a9fa4115d74548 Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Thu, 16 Nov 2017 14:57:48 +0200 Subject: net/mlx5: Fix misspelling in the error message and comment Fix misspelling in word syndrome. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Eugenia Emantayev Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/health.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 60771865c99c..0308a2b4823c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -466,7 +466,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) break; case MLX5_EVENT_TYPE_CQ_ERROR: cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff; - mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrom 0x%x\n", + mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrome 0x%x\n", cqn, eqe->data.cq_err.syndrome); mlx5_cq_event(dev, cqn, eqe->type); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 1a0e797ad001..21d29f7936f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -241,7 +241,7 @@ static void print_health_info(struct mlx5_core_dev *dev) u32 fw; int i; - /* If the syndrom is 0, the device is OK and no need to print buffer */ + /* If the syndrome is 0, the device is OK and no need to print buffer */ if (!ioread8(&h->synd)) return; -- cgit v1.2.3-59-g8ed1b From dbff26e44dc3ec4de6578733b054a0114652a764 Mon Sep 17 00:00:00 2001 From: Moni Shoua Date: Mon, 4 Dec 2017 08:59:25 +0200 Subject: net/mlx5: Fix error flow in CREATE_QP command In error flow, when DESTROY_QP command should be executed, the wrong mailbox was set with data, not the one that is written to hardware, Fix that. Fixes: 09a7d9eca1a6 '{net,IB}/mlx5: QP/XRCD commands via mlx5 ifc' Signed-off-by: Moni Shoua Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index db9e665ab104..889130edb715 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -213,8 +213,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev, err_cmd: memset(din, 0, sizeof(din)); memset(dout, 0, sizeof(dout)); - MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP); - MLX5_SET(destroy_qp_in, in, qpn, qp->qpn); + MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP); + MLX5_SET(destroy_qp_in, din, qpn, qp->qpn); mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout)); return err; } -- cgit v1.2.3-59-g8ed1b From 6323514116404cc651df1b7fffa1311ddf8ce647 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 23 Nov 2017 13:52:28 +0200 Subject: net/mlx5e: Fix possible deadlock of VXLAN lock mlx5e_vxlan_lookup_port is called both from mlx5e_add_vxlan_port (user context) and mlx5e_features_check (softirq), but the lock acquired does not disable bottom half and might result in deadlock. Fix it by simply replacing spin_lock() with spin_lock_bh(). While at it, replace all unnecessary spin_lock_irq() to spin_lock_bh(). lockdep's WARNING: inconsistent lock state [ 654.028136] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 654.028229] swapper/5/0 [HC0[0]:SC1[9]:HE1:SE0] takes: [ 654.028321] (&(&vxlan_db->lock)->rlock){+.?.}, at: [] mlx5e_vxlan_lookup_port+0x1e/0x50 [mlx5_core] [ 654.028528] {SOFTIRQ-ON-W} state was registered at: [ 654.028607] _raw_spin_lock+0x3c/0x70 [ 654.028689] mlx5e_vxlan_lookup_port+0x1e/0x50 [mlx5_core] [ 654.028794] mlx5e_vxlan_add_port+0x2e/0x120 [mlx5_core] [ 654.028878] process_one_work+0x1e9/0x640 [ 654.028942] worker_thread+0x4a/0x3f0 [ 654.029002] kthread+0x141/0x180 [ 654.029056] ret_from_fork+0x24/0x30 [ 654.029114] irq event stamp: 579088 [ 654.029174] hardirqs last enabled at (579088): [] ip6_finish_output2+0x49a/0x8c0 [ 654.029309] hardirqs last disabled at (579087): [] ip6_finish_output2+0x44e/0x8c0 [ 654.029446] softirqs last enabled at (579030): [] irq_enter+0x6d/0x80 [ 654.029567] softirqs last disabled at (579031): [] irq_exit+0xb5/0xc0 [ 654.029684] other info that might help us debug this: [ 654.029781] Possible unsafe locking scenario: [ 654.029868] CPU0 [ 654.029908] ---- [ 654.029947] lock(&(&vxlan_db->lock)->rlock); [ 654.030045] [ 654.030090] lock(&(&vxlan_db->lock)->rlock); [ 654.030162] *** DEADLOCK *** Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling") Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c index 07a9ba6cfc70..f8238275759f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -71,9 +71,9 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port) struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; struct mlx5e_vxlan *vxlan; - spin_lock(&vxlan_db->lock); + spin_lock_bh(&vxlan_db->lock); vxlan = radix_tree_lookup(&vxlan_db->tree, port); - spin_unlock(&vxlan_db->lock); + spin_unlock_bh(&vxlan_db->lock); return vxlan; } @@ -100,9 +100,9 @@ static void mlx5e_vxlan_add_port(struct work_struct *work) vxlan->udp_port = port; - spin_lock_irq(&vxlan_db->lock); + spin_lock_bh(&vxlan_db->lock); err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan); - spin_unlock_irq(&vxlan_db->lock); + spin_unlock_bh(&vxlan_db->lock); if (err) goto err_free; @@ -121,9 +121,9 @@ static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port) struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; struct mlx5e_vxlan *vxlan; - spin_lock_irq(&vxlan_db->lock); + spin_lock_bh(&vxlan_db->lock); vxlan = radix_tree_delete(&vxlan_db->tree, port); - spin_unlock_irq(&vxlan_db->lock); + spin_unlock_bh(&vxlan_db->lock); if (!vxlan) return; @@ -171,12 +171,12 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv) struct mlx5e_vxlan *vxlan; unsigned int port = 0; - spin_lock_irq(&vxlan_db->lock); + spin_lock_bh(&vxlan_db->lock); while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) { port = vxlan->udp_port; - spin_unlock_irq(&vxlan_db->lock); + spin_unlock_bh(&vxlan_db->lock); __mlx5e_vxlan_core_del_port(priv, (u16)port); - spin_lock_irq(&vxlan_db->lock); + spin_lock_bh(&vxlan_db->lock); } - spin_unlock_irq(&vxlan_db->lock); + spin_unlock_bh(&vxlan_db->lock); } -- cgit v1.2.3-59-g8ed1b From 23f4cc2cd9ed92570647220aca60d0197d8c1fa9 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sun, 3 Dec 2017 13:58:50 +0200 Subject: net/mlx5e: Add refcount to VXLAN structure A refcount mechanism must be implemented in order to prevent unwanted scenarios such as: - Open an IPv4 VXLAN interface - Open an IPv6 VXLAN interface (different socket) - Remove one of the interfaces With current implementation, the UDP port will be removed from our VXLAN database and turn off the offloads for the other interface, which is still active. The reference count mechanism will only allow UDP port removals once all consumers are gone. Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling") Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 50 +++++++++++++------------ drivers/net/ethernet/mellanox/mlx5/core/vxlan.h | 1 + 2 files changed, 28 insertions(+), 23 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c index f8238275759f..25f782344667 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -88,8 +88,11 @@ static void mlx5e_vxlan_add_port(struct work_struct *work) struct mlx5e_vxlan *vxlan; int err; - if (mlx5e_vxlan_lookup_port(priv, port)) + vxlan = mlx5e_vxlan_lookup_port(priv, port); + if (vxlan) { + atomic_inc(&vxlan->refcount); goto free_work; + } if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port)) goto free_work; @@ -99,6 +102,7 @@ static void mlx5e_vxlan_add_port(struct work_struct *work) goto err_delete_port; vxlan->udp_port = port; + atomic_set(&vxlan->refcount, 1); spin_lock_bh(&vxlan_db->lock); err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan); @@ -116,32 +120,33 @@ free_work: kfree(vxlan_work); } -static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port) +static void mlx5e_vxlan_del_port(struct work_struct *work) { + struct mlx5e_vxlan_work *vxlan_work = + container_of(work, struct mlx5e_vxlan_work, work); + struct mlx5e_priv *priv = vxlan_work->priv; struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; + u16 port = vxlan_work->port; struct mlx5e_vxlan *vxlan; + bool remove = false; spin_lock_bh(&vxlan_db->lock); - vxlan = radix_tree_delete(&vxlan_db->tree, port); - spin_unlock_bh(&vxlan_db->lock); - + vxlan = radix_tree_lookup(&vxlan_db->tree, port); if (!vxlan) - return; - - mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port); - - kfree(vxlan); -} + goto out_unlock; -static void mlx5e_vxlan_del_port(struct work_struct *work) -{ - struct mlx5e_vxlan_work *vxlan_work = - container_of(work, struct mlx5e_vxlan_work, work); - struct mlx5e_priv *priv = vxlan_work->priv; - u16 port = vxlan_work->port; + if (atomic_dec_and_test(&vxlan->refcount)) { + radix_tree_delete(&vxlan_db->tree, port); + remove = true; + } - __mlx5e_vxlan_core_del_port(priv, port); +out_unlock: + spin_unlock_bh(&vxlan_db->lock); + if (remove) { + mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); + kfree(vxlan); + } kfree(vxlan_work); } @@ -171,12 +176,11 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv) struct mlx5e_vxlan *vxlan; unsigned int port = 0; - spin_lock_bh(&vxlan_db->lock); + /* Lockless since we are the only radix-tree consumers, wq is disabled */ while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) { port = vxlan->udp_port; - spin_unlock_bh(&vxlan_db->lock); - __mlx5e_vxlan_core_del_port(priv, (u16)port); - spin_lock_bh(&vxlan_db->lock); + radix_tree_delete(&vxlan_db->tree, port); + mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); + kfree(vxlan); } - spin_unlock_bh(&vxlan_db->lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h index 5def12c048e3..5ef6ae7d568a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h @@ -36,6 +36,7 @@ #include "en.h" struct mlx5e_vxlan { + atomic_t refcount; u16 udp_port; }; -- cgit v1.2.3-59-g8ed1b From 0c1cc8b2215f5122ca614b5adca60346018758c3 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 4 Dec 2017 09:57:43 +0200 Subject: net/mlx5e: Prevent possible races in VXLAN control flow When calling add/remove VXLAN port, a lock must be held in order to prevent race scenarios when more than one add/remove happens at the same time. Fix by holding our state_lock (mutex) as done by all other parts of the driver. Note that the spinlock protecting the radix-tree is still needed in order to synchronize radix-tree access from softirq context. Fixes: b3f63c3d5e2c ("net/mlx5e: Add netdev support for VXLAN tunneling") Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c index 25f782344667..2f74953e4561 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -88,6 +88,7 @@ static void mlx5e_vxlan_add_port(struct work_struct *work) struct mlx5e_vxlan *vxlan; int err; + mutex_lock(&priv->state_lock); vxlan = mlx5e_vxlan_lookup_port(priv, port); if (vxlan) { atomic_inc(&vxlan->refcount); @@ -117,6 +118,7 @@ err_free: err_delete_port: mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); free_work: + mutex_unlock(&priv->state_lock); kfree(vxlan_work); } @@ -130,6 +132,7 @@ static void mlx5e_vxlan_del_port(struct work_struct *work) struct mlx5e_vxlan *vxlan; bool remove = false; + mutex_lock(&priv->state_lock); spin_lock_bh(&vxlan_db->lock); vxlan = radix_tree_lookup(&vxlan_db->tree, port); if (!vxlan) @@ -147,6 +150,7 @@ out_unlock: mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); kfree(vxlan); } + mutex_unlock(&priv->state_lock); kfree(vxlan_work); } -- cgit v1.2.3-59-g8ed1b From 139ed6c6c46aa3d8970a086b8e0cf1f3522f5d4a Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 5 Dec 2017 13:45:21 +0200 Subject: net/mlx5: Fix steering memory leak Flow steering priority and namespace are software only objects that didn't have the proper destructors and were not freed during steering cleanup. Fix it by adding destructor functions for these objects. Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel") Signed-off-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index c70fd663a633..dfaad9ecb2b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -174,6 +174,8 @@ static void del_hw_fte(struct fs_node *node); static void del_sw_flow_table(struct fs_node *node); static void del_sw_flow_group(struct fs_node *node); static void del_sw_fte(struct fs_node *node); +static void del_sw_prio(struct fs_node *node); +static void del_sw_ns(struct fs_node *node); /* Delete rule (destination) is special case that * requires to lock the FTE for all the deletion process. */ @@ -408,6 +410,16 @@ static inline struct mlx5_core_dev *get_dev(struct fs_node *node) return NULL; } +static void del_sw_ns(struct fs_node *node) +{ + kfree(node); +} + +static void del_sw_prio(struct fs_node *node) +{ + kfree(node); +} + static void del_hw_flow_table(struct fs_node *node) { struct mlx5_flow_table *ft; @@ -2064,7 +2076,7 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, return ERR_PTR(-ENOMEM); fs_prio->node.type = FS_TYPE_PRIO; - tree_init_node(&fs_prio->node, NULL, NULL); + tree_init_node(&fs_prio->node, NULL, del_sw_prio); tree_add_node(&fs_prio->node, &ns->node); fs_prio->num_levels = num_levels; fs_prio->prio = prio; @@ -2090,7 +2102,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) return ERR_PTR(-ENOMEM); fs_init_namespace(ns); - tree_init_node(&ns->node, NULL, NULL); + tree_init_node(&ns->node, NULL, del_sw_ns); tree_add_node(&ns->node, &prio->node); list_add_tail(&ns->node.list, &prio->node.children); -- cgit v1.2.3-59-g8ed1b From d6b2785cd55ee72e9608762650b3ef299f801b1b Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Tue, 21 Nov 2017 15:15:51 +0200 Subject: net/mlx5: Cleanup IRQs in case of unload failure When mlx5_stop_eqs fails to destroy any of the eqs it returns with an error. In such failure flow the function will return without releasing all EQs irqs and then pci_free_irq_vectors will fail. Fix by only warn on destroy EQ failure and continue to release other EQs and their irqs. It fixes the following kernel trace: kernel: kernel BUG at drivers/pci/msi.c:352! ... ... kernel: Call Trace: kernel: pci_disable_msix+0xd3/0x100 kernel: pci_free_irq_vectors+0xe/0x20 kernel: mlx5_load_one.isra.17+0x9f5/0xec0 [mlx5_core] Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 20 +++++++++++++------- include/linux/mlx5/driver.h | 2 +- 2 files changed, 14 insertions(+), 8 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 0308a2b4823c..ab4d1465b7e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -775,7 +775,7 @@ err1: return err; } -int mlx5_stop_eqs(struct mlx5_core_dev *dev) +void mlx5_stop_eqs(struct mlx5_core_dev *dev) { struct mlx5_eq_table *table = &dev->priv.eq_table; int err; @@ -784,22 +784,28 @@ int mlx5_stop_eqs(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, pg)) { err = mlx5_destroy_unmap_eq(dev, &table->pfault_eq); if (err) - return err; + mlx5_core_err(dev, "failed to destroy page fault eq, err(%d)\n", + err); } #endif err = mlx5_destroy_unmap_eq(dev, &table->pages_eq); if (err) - return err; + mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n", + err); - mlx5_destroy_unmap_eq(dev, &table->async_eq); + err = mlx5_destroy_unmap_eq(dev, &table->async_eq); + if (err) + mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n", + err); mlx5_cmd_use_polling(dev); err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq); - if (err) + if (err) { + mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n", + err); mlx5_cmd_use_events(dev); - - return err; + } } int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 40a6f33c4cde..57b109c6e422 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1049,7 +1049,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, enum mlx5_eq_type type); int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_start_eqs(struct mlx5_core_dev *dev); -int mlx5_stop_eqs(struct mlx5_core_dev *dev); +void mlx5_stop_eqs(struct mlx5_core_dev *dev); int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, unsigned int *irqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); -- cgit v1.2.3-59-g8ed1b From a2fba188fd5eadd6061bef4f2f2577a43231ebf3 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Mon, 4 Dec 2017 15:23:51 +0200 Subject: net/mlx5: Stay in polling mode when command EQ destroy fails During unload, on mlx5_stop_eqs we move command interface from events mode to polling mode, but if command interface EQ destroy fail we move back to events mode. That's wrong since even if we fail to destroy command interface EQ, we do release its irq, so no interrupts will be received. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index ab4d1465b7e4..e7e7cef2bde4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -801,11 +801,9 @@ void mlx5_stop_eqs(struct mlx5_core_dev *dev) mlx5_cmd_use_polling(dev); err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq); - if (err) { + if (err) mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n", err); - mlx5_cmd_use_events(dev); - } } int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, -- cgit v1.2.3-59-g8ed1b From 4423c18e466afdfb02a36ee8b9f901d144b3c607 Mon Sep 17 00:00:00 2001 From: Yelena Krivosheev Date: Tue, 19 Dec 2017 17:59:45 +0100 Subject: net: mvneta: clear interface link status on port disable When port connect to PHY in polling mode (with poll interval 1 sec), port and phy link status must be synchronize in order don't loss link change event. [gregory.clement@free-electrons.com: add fixes tag] Cc: Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP network unit") Signed-off-by: Yelena Krivosheev Tested-by: Dmitri Epshtein Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index bc93b69cfd1e..16b2bfb2cf51 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1214,6 +1214,10 @@ static void mvneta_port_disable(struct mvneta_port *pp) val &= ~MVNETA_GMAC0_PORT_ENABLE; mvreg_write(pp, MVNETA_GMAC_CTRL_0, val); + pp->link = 0; + pp->duplex = -1; + pp->speed = 0; + udelay(200); } -- cgit v1.2.3-59-g8ed1b From ca5902a6547f662419689ca28b3c29a772446caa Mon Sep 17 00:00:00 2001 From: Yelena Krivosheev Date: Tue, 19 Dec 2017 17:59:46 +0100 Subject: net: mvneta: use proper rxq_number in loop on rx queues When adding the RX queue association with each CPU, a typo was made in the mvneta_cleanup_rxqs() function. This patch fixes it. [gregory.clement@free-electrons.com: add commit log and fixes tag] Cc: stable@vger.kernel.org Fixes: 2dcf75e2793c ("net: mvneta: Associate RX queues with each CPU") Signed-off-by: Yelena Krivosheev Tested-by: Dmitri Epshtein Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 16b2bfb2cf51..1e0835655c93 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3015,7 +3015,7 @@ static void mvneta_cleanup_rxqs(struct mvneta_port *pp) { int queue; - for (queue = 0; queue < txq_number; queue++) + for (queue = 0; queue < rxq_number; queue++) mvneta_rxq_deinit(pp, &pp->rxqs[queue]); } -- cgit v1.2.3-59-g8ed1b From 2eecb2e04abb62ef8ea7b43e1a46bdb5b99d1bf8 Mon Sep 17 00:00:00 2001 From: Yelena Krivosheev Date: Tue, 19 Dec 2017 17:59:47 +0100 Subject: net: mvneta: eliminate wrong call to handle rx descriptor error There are few reasons in mvneta_rx_swbm() function when received packet is dropped. mvneta_rx_error() should be called only if error bit [16] is set in rx descriptor. [gregory.clement@free-electrons.com: add fixes tag] Cc: stable@vger.kernel.org Fixes: dc35a10f68d3 ("net: mvneta: bm: add support for hardware buffer management") Signed-off-by: Yelena Krivosheev Tested-by: Dmitri Epshtein Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 1e0835655c93..a539263cd79c 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1962,9 +1962,9 @@ static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo, if (!mvneta_rxq_desc_is_first_last(rx_status) || (rx_status & MVNETA_RXD_ERR_SUMMARY)) { + mvneta_rx_error(pp, rx_desc); err_drop_frame: dev->stats.rx_errors++; - mvneta_rx_error(pp, rx_desc); /* leave the descriptor untouched */ continue; } -- cgit v1.2.3-59-g8ed1b From 102740bd9436a3a6ba129af3a48271d794009fa5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 19 Dec 2017 13:32:13 -0800 Subject: cls_bpf: fix offload assumptions after callback conversion cls_bpf used to take care of tracking what offload state a filter is in, i.e. it would track if offload request succeeded or not. This information would then be used to issue correct requests to the driver, e.g. requests for statistics only on offloaded filters, removing only filters which were offloaded, using add instead of replace if previous filter was not added etc. This tracking of offload state no longer functions with the new callback infrastructure. There could be multiple entities trying to offload the same filter. Throw out all the tracking and corresponding commands and simply pass to the drivers both old and new bpf program. Drivers will have to deal with offload state tracking by themselves. Fixes: 3f7889c4c79b ("net: sched: cls_bpf: call block callbacks for offload") Signed-off-by: Jakub Kicinski Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/main.c | 12 +--- include/net/pkt_cls.h | 5 +- net/sched/cls_bpf.c | 93 +++++++++++---------------- 3 files changed, 43 insertions(+), 67 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index e379b78e86ef..a4cf62ba4604 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -110,16 +110,10 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, return -EOPNOTSUPP; } - switch (cls_bpf->command) { - case TC_CLSBPF_REPLACE: - return nfp_net_bpf_offload(nn, cls_bpf->prog, true); - case TC_CLSBPF_ADD: - return nfp_net_bpf_offload(nn, cls_bpf->prog, false); - case TC_CLSBPF_DESTROY: - return nfp_net_bpf_offload(nn, NULL, true); - default: + if (cls_bpf->command != TC_CLSBPF_OFFLOAD) return -EOPNOTSUPP; - } + + return nfp_net_bpf_offload(nn, cls_bpf->prog, cls_bpf->oldprog); } static int nfp_bpf_setup_tc_block(struct net_device *netdev, diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 0105445cab83..8e08b6da72f3 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -694,9 +694,7 @@ struct tc_cls_matchall_offload { }; enum tc_clsbpf_command { - TC_CLSBPF_ADD, - TC_CLSBPF_REPLACE, - TC_CLSBPF_DESTROY, + TC_CLSBPF_OFFLOAD, TC_CLSBPF_STATS, }; @@ -705,6 +703,7 @@ struct tc_cls_bpf_offload { enum tc_clsbpf_command command; struct tcf_exts *exts; struct bpf_prog *prog; + struct bpf_prog *oldprog; const char *name; bool exts_integrated; u32 gen_flags; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 6fe798c2df1a..8d78e7f4ecc3 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -42,7 +42,6 @@ struct cls_bpf_prog { struct list_head link; struct tcf_result res; bool exts_integrated; - bool offloaded; u32 gen_flags; struct tcf_exts exts; u32 handle; @@ -148,33 +147,37 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) } static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, - enum tc_clsbpf_command cmd) + struct cls_bpf_prog *oldprog) { - bool addorrep = cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE; struct tcf_block *block = tp->chain->block; - bool skip_sw = tc_skip_sw(prog->gen_flags); struct tc_cls_bpf_offload cls_bpf = {}; + struct cls_bpf_prog *obj; + bool skip_sw; int err; + skip_sw = prog && tc_skip_sw(prog->gen_flags); + obj = prog ?: oldprog; + tc_cls_common_offload_init(&cls_bpf.common, tp); - cls_bpf.command = cmd; - cls_bpf.exts = &prog->exts; - cls_bpf.prog = prog->filter; - cls_bpf.name = prog->bpf_name; - cls_bpf.exts_integrated = prog->exts_integrated; - cls_bpf.gen_flags = prog->gen_flags; + cls_bpf.command = TC_CLSBPF_OFFLOAD; + cls_bpf.exts = &obj->exts; + cls_bpf.prog = prog ? prog->filter : NULL; + cls_bpf.oldprog = oldprog ? oldprog->filter : NULL; + cls_bpf.name = obj->bpf_name; + cls_bpf.exts_integrated = obj->exts_integrated; + cls_bpf.gen_flags = obj->gen_flags; err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, skip_sw); - if (addorrep) { + if (prog) { if (err < 0) { - cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); + cls_bpf_offload_cmd(tp, oldprog, prog); return err; } else if (err > 0) { prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; } } - if (addorrep && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW)) + if (prog && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW)) return -EINVAL; return 0; @@ -183,38 +186,17 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, struct cls_bpf_prog *oldprog) { - struct cls_bpf_prog *obj = prog; - enum tc_clsbpf_command cmd; - bool skip_sw; - int ret; - - skip_sw = tc_skip_sw(prog->gen_flags) || - (oldprog && tc_skip_sw(oldprog->gen_flags)); - - if (oldprog && oldprog->offloaded) { - if (!tc_skip_hw(prog->gen_flags)) { - cmd = TC_CLSBPF_REPLACE; - } else if (!tc_skip_sw(prog->gen_flags)) { - obj = oldprog; - cmd = TC_CLSBPF_DESTROY; - } else { - return -EINVAL; - } - } else { - if (tc_skip_hw(prog->gen_flags)) - return skip_sw ? -EINVAL : 0; - cmd = TC_CLSBPF_ADD; - } - - ret = cls_bpf_offload_cmd(tp, obj, cmd); - if (ret) - return ret; + if (prog && oldprog && prog->gen_flags != oldprog->gen_flags) + return -EINVAL; - obj->offloaded = true; - if (oldprog) - oldprog->offloaded = false; + if (prog && tc_skip_hw(prog->gen_flags)) + prog = NULL; + if (oldprog && tc_skip_hw(oldprog->gen_flags)) + oldprog = NULL; + if (!prog && !oldprog) + return 0; - return 0; + return cls_bpf_offload_cmd(tp, prog, oldprog); } static void cls_bpf_stop_offload(struct tcf_proto *tp, @@ -222,25 +204,26 @@ static void cls_bpf_stop_offload(struct tcf_proto *tp, { int err; - if (!prog->offloaded) - return; - - err = cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); - if (err) { + err = cls_bpf_offload_cmd(tp, NULL, prog); + if (err) pr_err("Stopping hardware offload failed: %d\n", err); - return; - } - - prog->offloaded = false; } static void cls_bpf_offload_update_stats(struct tcf_proto *tp, struct cls_bpf_prog *prog) { - if (!prog->offloaded) - return; + struct tcf_block *block = tp->chain->block; + struct tc_cls_bpf_offload cls_bpf = {}; + + tc_cls_common_offload_init(&cls_bpf.common, tp); + cls_bpf.command = TC_CLSBPF_STATS; + cls_bpf.exts = &prog->exts; + cls_bpf.prog = prog->filter; + cls_bpf.name = prog->bpf_name; + cls_bpf.exts_integrated = prog->exts_integrated; + cls_bpf.gen_flags = prog->gen_flags; - cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_STATS); + tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, false); } static int cls_bpf_init(struct tcf_proto *tp) -- cgit v1.2.3-59-g8ed1b From d3f89b98e391475419ae2d8834813d3ecbb48f67 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 19 Dec 2017 13:32:14 -0800 Subject: nfp: bpf: keep track of the offloaded program After TC offloads were converted to callbacks we have no choice but keep track of the offloaded filter in the driver. The check for nn->dp.bpf_offload_xdp was a stop gap solution to make sure failed TC offload won't disable XDP, it's no longer necessary. nfp_net_bpf_offload() will return -EBUSY on TC vs XDP conflicts. Fixes: 3f7889c4c79b ("net: sched: cls_bpf: call block callbacks for offload") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/bpf/main.c | 47 ++++++++++++++++++++++++--- drivers/net/ethernet/netronome/nfp/bpf/main.h | 8 +++++ 2 files changed, 51 insertions(+), 4 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index a4cf62ba4604..13190aa09faf 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -82,10 +82,33 @@ static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn) return nfp_net_ebpf_capable(nn) ? "BPF" : ""; } +static int +nfp_bpf_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) +{ + int err; + + nn->app_priv = kzalloc(sizeof(struct nfp_bpf_vnic), GFP_KERNEL); + if (!nn->app_priv) + return -ENOMEM; + + err = nfp_app_nic_vnic_alloc(app, nn, id); + if (err) + goto err_free_priv; + + return 0; +err_free_priv: + kfree(nn->app_priv); + return err; +} + static void nfp_bpf_vnic_free(struct nfp_app *app, struct nfp_net *nn) { + struct nfp_bpf_vnic *bv = nn->app_priv; + if (nn->dp.bpf_offload_xdp) nfp_bpf_xdp_offload(app, nn, NULL); + WARN_ON(bv->tc_prog); + kfree(bv); } static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, @@ -93,6 +116,9 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, { struct tc_cls_bpf_offload *cls_bpf = type_data; struct nfp_net *nn = cb_priv; + struct bpf_prog *oldprog; + struct nfp_bpf_vnic *bv; + int err; if (type != TC_SETUP_CLSBPF || !tc_can_offload(nn->dp.netdev) || @@ -100,8 +126,6 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, cls_bpf->common.protocol != htons(ETH_P_ALL) || cls_bpf->common.chain_index) return -EOPNOTSUPP; - if (nn->dp.bpf_offload_xdp) - return -EBUSY; /* Only support TC direct action */ if (!cls_bpf->exts_integrated || @@ -113,7 +137,22 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, if (cls_bpf->command != TC_CLSBPF_OFFLOAD) return -EOPNOTSUPP; - return nfp_net_bpf_offload(nn, cls_bpf->prog, cls_bpf->oldprog); + bv = nn->app_priv; + oldprog = cls_bpf->oldprog; + + /* Don't remove if oldprog doesn't match driver's state */ + if (bv->tc_prog != oldprog) { + oldprog = NULL; + if (!cls_bpf->prog) + return 0; + } + + err = nfp_net_bpf_offload(nn, cls_bpf->prog, oldprog); + if (err) + return err; + + bv->tc_prog = cls_bpf->prog; + return 0; } static int nfp_bpf_setup_tc_block(struct net_device *netdev, @@ -161,7 +200,7 @@ const struct nfp_app_type app_bpf = { .extra_cap = nfp_bpf_extra_cap, - .vnic_alloc = nfp_app_nic_vnic_alloc, + .vnic_alloc = nfp_bpf_vnic_alloc, .vnic_free = nfp_bpf_vnic_free, .setup_tc = nfp_bpf_setup_tc, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 082a15f6dfb5..57b6043177a3 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -172,6 +172,14 @@ struct nfp_prog { struct list_head insns; }; +/** + * struct nfp_bpf_vnic - per-vNIC BPF priv structure + * @tc_prog: currently loaded cls_bpf program + */ +struct nfp_bpf_vnic { + struct bpf_prog *tc_prog; +}; + int nfp_bpf_jit(struct nfp_prog *prog); extern const struct bpf_ext_analyzer_ops nfp_bpf_analyzer_ops; -- cgit v1.2.3-59-g8ed1b