diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-10-31 11:52:20 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-10-31 11:52:20 -0700 |
commit | c94eee8a3befe480a1193f2633f16988108393bc (patch) | |
tree | 124e15138ceb070a19464a6c2d5b4e0b771b68e8 | |
parent | 38dab9ac1c017e96dc98e978111e365134d41d13 (diff) | |
parent | 89bc7848a91bc99532f5c21b2885472ba710f249 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
1) Fix two regressions in ipv6 route lookups, particularly wrt output
interface specifications in the lookup key. From David Ahern.
2) Fix checks in ipv6 IPSEC tunnel pre-encap fragmentation, from
Herbert Xu.
3) Fix mis-advertisement of 1000BASE-T on bcm63xx_enet, from Simon
Arlott.
4) Some smsc phys misbehave with energy detect mode enabled, so add a
DT property and disable it on such switches. From Heiko Schocher.
5) Fix TSO corruption on TX in mv643xx_eth, from Philipp Kirchhofer.
6) Fix regression added by removal of openvswitch vport stats, from
James Morse.
7) Vendor Kconfig options should be bool, not tristate, from Andreas
Schwab.
8) Use non-_BH() net stats bump in tcp_xmit_probe_skb(), otherwise we
barf during TCP REPAIR operations.
9) Fix various bugs in openvswitch conntrack support, from Joe
Stringer.
10) Fix NETLINK_LIST_MEMBERSHIPS locking, from David Herrmann.
11) Don't have VSOCK do sock_put() in interrupt context, from Jorgen
Hansen.
12) Fix skb_realloc_headroom() failures properly in ISDN, from Karsten
Keil.
13) Add some device IDs to qmi_wwan, from Bjorn Mork.
14) Fix ovs egress tunnel information when using lwtunnel devices, from
Pravin B Shelar.
15) Add missing NETIF_F_FRAGLIST to macvtab feature list, from Jason
Wang.
16) Fix incorrect handling of throw routes when the result of the throw
cannot find a match, from Xin Long.
17) Protect ipv6 MTU calculations from wrap-around, from Hannes Frederic
Sowa.
18) Fix failed autonegotiation on KSZ9031 micrel PHYs, from Nathan
Sullivan.
19) Add missing memory barries in descriptor accesses or xgbe driver,
from Thomas Lendacky.
20) Fix release conditon test in pppoe_release(), from Guillaume Nault.
21) Fix gianfar bugs wrt filter configuration, from Claudiu Manoil.
22) Fix violations of RX buffer alignment in sh_eth driver, from Sergei
Shtylyov.
23) Fixing missing of_node_put() calls in various places around the
networking, from Julia Lawall.
24) Fix incorrect leaf now walking in ipv4 routing tree, from Alexander
Duyck.
25) RDS doesn't check pskb_pull()/pskb_trim() return values, from
Sowmini Varadhan.
26) Fix VLAN configuration in mlx4 driver, from Jack Morgenstein.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (79 commits)
ipv6: protect mtu calculation of wrap-around and infinite loop by rounding issues
Revert "Merge branch 'ipv6-overflow-arith'"
net/mlx4: Copy/set only sizeof struct mlx4_eqe bytes
net/mlx4_en: Explicitly set no vlan tags in WQE ctrl segment when no vlan is present
vhost: fix performance on LE hosts
bpf: sample: define aarch64 specific registers
amd-xgbe: Fix race between access of desc and desc index
RDS-TCP: Recover correctly from pskb_pull()/pksb_trim() failure in rds_tcp_data_recv
forcedeth: fix unilateral interrupt disabling in netpoll path
openvswitch: Fix skb leak using IPv6 defrag
ipv6: Export nf_ct_frag6_consume_orig()
openvswitch: Fix double-free on ip_defrag() errors
fib_trie: leaf_walk_rcu should not compute key if key is less than pn->key
net: mv643xx_eth: add missing of_node_put
ath6kl: add missing of_node_put
net: phy: mdio: add missing of_node_put
netdev/phy: add missing of_node_put
net: netcp: add missing of_node_put
net: thunderx: add missing of_node_put
ipv6: gre: support SIT encapsulation
...
89 files changed, 894 insertions, 477 deletions
diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index a9df21aaa154..a2cae4eb4a60 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -39,6 +39,7 @@ Required properties: Optional properties: - dual_emac_res_vlan : Specifies VID to be used to segregate the ports - mac-address : See ethernet.txt file in the same directory +- phy-handle : See ethernet.txt file in the same directory Note: "ti,hwmods" field is used to fetch the base address and irq resources from TI, omap hwmod data base during device registration. diff --git a/Documentation/devicetree/bindings/net/smsc-lan87xx.txt b/Documentation/devicetree/bindings/net/smsc-lan87xx.txt new file mode 100644 index 000000000000..974edd5c85cc --- /dev/null +++ b/Documentation/devicetree/bindings/net/smsc-lan87xx.txt @@ -0,0 +1,24 @@ +SMSC LAN87xx Ethernet PHY + +Some boards require special tuning values. Configure them +through an Ethernet OF device node. + +Optional properties: + +- smsc,disable-energy-detect: + If set, do not enable energy detect mode for the SMSC phy. + default: enable energy detect mode + +Examples: +smsc phy with disabled energy detect mode on an am335x based board. +&davinci_mdio { + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&davinci_mdio_default>; + pinctrl-1 = <&davinci_mdio_sleep>; + status = "okay"; + + ethernetphy0: ethernet-phy@0 { + reg = <0>; + smsc,disable-energy-detect; + }; +}; diff --git a/MAINTAINERS b/MAINTAINERS index 9de185da5f5b..747c65316167 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4428,6 +4428,14 @@ L: linuxppc-dev@lists.ozlabs.org S: Maintained F: drivers/net/ethernet/freescale/ucc_geth* +FREESCALE eTSEC ETHERNET DRIVER (GIANFAR) +M: Claudiu Manoil <claudiu.manoil@freescale.com> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/freescale/gianfar* +X: drivers/net/ethernet/freescale/gianfar_ptp.c +F: Documentation/devicetree/bindings/net/fsl-tsec-phy.txt + FREESCALE QUICC ENGINE UCC UART DRIVER M: Timur Tabi <timur@tabi.org> L: linuxppc-dev@lists.ozlabs.org diff --git a/drivers/isdn/hisax/isdnl2.c b/drivers/isdn/hisax/isdnl2.c index 18accb0a79cc..c53a53f6efb6 100644 --- a/drivers/isdn/hisax/isdnl2.c +++ b/drivers/isdn/hisax/isdnl2.c @@ -1247,7 +1247,7 @@ static void l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) { struct PStack *st = fi->userdata; - struct sk_buff *skb; + struct sk_buff *skb, *nskb; struct Layer2 *l2 = &st->l2; u_char header[MAX_HEADER_LEN]; int i, hdr_space_needed; @@ -1262,14 +1262,10 @@ l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) return; hdr_space_needed = l2headersize(l2, 0); - if (hdr_space_needed > skb_headroom(skb)) { - struct sk_buff *orig_skb = skb; - - skb = skb_realloc_headroom(skb, hdr_space_needed); - if (!skb) { - dev_kfree_skb(orig_skb); - return; - } + nskb = skb_realloc_headroom(skb, hdr_space_needed); + if (!nskb) { + skb_queue_head(&l2->i_queue, skb); + return; } spin_lock_irqsave(&l2->lock, flags); if (test_bit(FLG_MOD128, &l2->flag)) @@ -1282,7 +1278,7 @@ l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) p1); dev_kfree_skb(l2->windowar[p1]); } - l2->windowar[p1] = skb_clone(skb, GFP_ATOMIC); + l2->windowar[p1] = skb; i = sethdraddr(&st->l2, header, CMD); @@ -1295,8 +1291,8 @@ l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) l2->vs = (l2->vs + 1) % 8; } spin_unlock_irqrestore(&l2->lock, flags); - memcpy(skb_push(skb, i), header, i); - st->l2.l2l1(st, PH_PULL | INDICATION, skb); + memcpy(skb_push(nskb, i), header, i); + st->l2.l2l1(st, PH_PULL | INDICATION, nskb); test_and_clear_bit(FLG_ACK_PEND, &st->l2.flag); if (!test_and_set_bit(FLG_T200_RUN, &st->l2.flag)) { FsmDelTimer(&st->l2.t203, 13); diff --git a/drivers/isdn/mISDN/layer2.c b/drivers/isdn/mISDN/layer2.c index 949cabb88f1c..5eb380a25903 100644 --- a/drivers/isdn/mISDN/layer2.c +++ b/drivers/isdn/mISDN/layer2.c @@ -1476,7 +1476,7 @@ static void l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) { struct layer2 *l2 = fi->userdata; - struct sk_buff *skb, *nskb, *oskb; + struct sk_buff *skb, *nskb; u_char header[MAX_L2HEADER_LEN]; u_int i, p1; @@ -1486,48 +1486,34 @@ l2_pull_iqueue(struct FsmInst *fi, int event, void *arg) skb = skb_dequeue(&l2->i_queue); if (!skb) return; - - if (test_bit(FLG_MOD128, &l2->flag)) - p1 = (l2->vs - l2->va) % 128; - else - p1 = (l2->vs - l2->va) % 8; - p1 = (p1 + l2->sow) % l2->window; - if (l2->windowar[p1]) { - printk(KERN_WARNING "%s: l2 try overwrite ack queue entry %d\n", - mISDNDevName4ch(&l2->ch), p1); - dev_kfree_skb(l2->windowar[p1]); - } - l2->windowar[p1] = skb; i = sethdraddr(l2, header, CMD); if (test_bit(FLG_MOD128, &l2->flag)) { header[i++] = l2->vs << 1; header[i++] = l2->vr << 1; + } else + header[i++] = (l2->vr << 5) | (l2->vs << 1); + nskb = skb_realloc_headroom(skb, i); + if (!nskb) { + printk(KERN_WARNING "%s: no headroom(%d) copy for IFrame\n", + mISDNDevName4ch(&l2->ch), i); + skb_queue_head(&l2->i_queue, skb); + return; + } + if (test_bit(FLG_MOD128, &l2->flag)) { + p1 = (l2->vs - l2->va) % 128; l2->vs = (l2->vs + 1) % 128; } else { - header[i++] = (l2->vr << 5) | (l2->vs << 1); + p1 = (l2->vs - l2->va) % 8; l2->vs = (l2->vs + 1) % 8; } - - nskb = skb_clone(skb, GFP_ATOMIC); - p1 = skb_headroom(nskb); - if (p1 >= i) - memcpy(skb_push(nskb, i), header, i); - else { - printk(KERN_WARNING - "%s: L2 pull_iqueue skb header(%d/%d) too short\n", - mISDNDevName4ch(&l2->ch), i, p1); - oskb = nskb; - nskb = mI_alloc_skb(oskb->len + i, GFP_ATOMIC); - if (!nskb) { - dev_kfree_skb(oskb); - printk(KERN_WARNING "%s: no skb mem in %s\n", - mISDNDevName4ch(&l2->ch), __func__); - return; - } - memcpy(skb_put(nskb, i), header, i); - memcpy(skb_put(nskb, oskb->len), oskb->data, oskb->len); - dev_kfree_skb(oskb); + p1 = (p1 + l2->sow) % l2->window; + if (l2->windowar[p1]) { + printk(KERN_WARNING "%s: l2 try overwrite ack queue entry %d\n", + mISDNDevName4ch(&l2->ch), p1); + dev_kfree_skb(l2->windowar[p1]); } + l2->windowar[p1] = skb; + memcpy(skb_push(nskb, i), header, i); l2down(l2, PH_DATA_REQ, l2_newid(l2), nskb); test_and_clear_bit(FLG_ACK_PEND, &l2->flag); if (!test_and_set_bit(FLG_T200_RUN, &l2->flag)) { diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 48ce83e443c2..8d50314ac3eb 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -847,21 +847,25 @@ static int emac_probe(struct platform_device *pdev) if (ndev->irq == -ENXIO) { netdev_err(ndev, "No irq resource\n"); ret = ndev->irq; - goto out; + goto out_iounmap; } db->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(db->clk)) { ret = PTR_ERR(db->clk); - goto out; + goto out_iounmap; } - clk_prepare_enable(db->clk); + ret = clk_prepare_enable(db->clk); + if (ret) { + dev_err(&pdev->dev, "Error couldn't enable clock (%d)\n", ret); + goto out_iounmap; + } ret = sunxi_sram_claim(&pdev->dev); if (ret) { dev_err(&pdev->dev, "Error couldn't map SRAM to device\n"); - goto out; + goto out_clk_disable_unprepare; } db->phy_node = of_parse_phandle(np, "phy", 0); @@ -910,6 +914,10 @@ static int emac_probe(struct platform_device *pdev) out_release_sram: sunxi_sram_release(&pdev->dev); +out_clk_disable_unprepare: + clk_disable_unprepare(db->clk); +out_iounmap: + iounmap(db->membase); out: dev_err(db->dev, "not found (%d).\n", ret); @@ -921,8 +929,12 @@ out: static int emac_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); + struct emac_board_info *db = netdev_priv(ndev); unregister_netdev(ndev); + sunxi_sram_release(&pdev->dev); + clk_disable_unprepare(db->clk); + iounmap(db->membase); free_netdev(ndev); dev_dbg(&pdev->dev, "released and freed device\n"); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index a4473d8ff4fa..f672dba345f7 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1595,7 +1595,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) packet->rdesc_count, 1); /* Make sure ownership is written to the descriptor */ - dma_wmb(); + smp_wmb(); ring->cur = cur_index + 1; if (!packet->skb->xmit_more || diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index aae9d5ecd182..dde0486667e0 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1807,6 +1807,7 @@ static int xgbe_tx_poll(struct xgbe_channel *channel) struct netdev_queue *txq; int processed = 0; unsigned int tx_packets = 0, tx_bytes = 0; + unsigned int cur; DBGPR("-->xgbe_tx_poll\n"); @@ -1814,10 +1815,15 @@ static int xgbe_tx_poll(struct xgbe_channel *channel) if (!ring) return 0; + cur = ring->cur; + + /* Be sure we get ring->cur before accessing descriptor data */ + smp_rmb(); + txq = netdev_get_tx_queue(netdev, channel->queue_index); while ((processed < XGBE_TX_DESC_MAX_PROC) && - (ring->dirty != ring->cur)) { + (ring->dirty != cur)) { rdata = XGBE_GET_DESC_DATA(ring, ring->dirty); rdesc = rdata->rdesc; diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index a7f2cc3e485e..4183c2abeeeb 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -2049,7 +2049,7 @@ static void swphy_poll_timer(unsigned long data) for (i = 0; i < priv->num_ports; i++) { struct bcm63xx_enetsw_port *port; - int val, j, up, advertise, lpa, lpa2, speed, duplex, media; + int val, j, up, advertise, lpa, speed, duplex, media; int external_phy = bcm_enet_port_is_rgmii(i); u8 override; @@ -2092,22 +2092,27 @@ static void swphy_poll_timer(unsigned long data) lpa = bcmenet_sw_mdio_read(priv, external_phy, port->phy_id, MII_LPA); - lpa2 = bcmenet_sw_mdio_read(priv, external_phy, port->phy_id, - MII_STAT1000); - /* figure out media and duplex from advertise and LPA values */ media = mii_nway_result(lpa & advertise); duplex = (media & ADVERTISE_FULL) ? 1 : 0; - if (lpa2 & LPA_1000FULL) - duplex = 1; - - if (lpa2 & (LPA_1000FULL | LPA_1000HALF)) - speed = 1000; - else { - if (media & (ADVERTISE_100FULL | ADVERTISE_100HALF)) - speed = 100; - else - speed = 10; + + if (media & (ADVERTISE_100FULL | ADVERTISE_100HALF)) + speed = 100; + else + speed = 10; + + if (val & BMSR_ESTATEN) { + advertise = bcmenet_sw_mdio_read(priv, external_phy, + port->phy_id, MII_CTRL1000); + + lpa = bcmenet_sw_mdio_read(priv, external_phy, + port->phy_id, MII_STAT1000); + + if (advertise & (ADVERTISE_1000FULL | ADVERTISE_1000HALF) + && lpa & (LPA_1000FULL | LPA_1000HALF)) { + speed = 1000; + duplex = (lpa & LPA_1000FULL); + } } dev_info(&priv->pdev->dev, diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 9b35d142f47a..8fb84e69c30e 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -3,7 +3,7 @@ # config NET_VENDOR_CAVIUM - tristate "Cavium ethernet drivers" + bool "Cavium ethernet drivers" depends on PCI default y ---help--- diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index b3a5947a2cc0..c561fdcb79a7 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -22,7 +22,6 @@ struct nicpf { struct pci_dev *pdev; - u8 rev_id; u8 node; unsigned int flags; u8 num_vf_en; /* No of VF enabled */ @@ -44,6 +43,7 @@ struct nicpf { u8 duplex[MAX_LMAC]; u32 speed[MAX_LMAC]; u16 cpi_base[MAX_NUM_VFS_SUPPORTED]; + u16 rssi_base[MAX_NUM_VFS_SUPPORTED]; u16 rss_ind_tbl_size; bool mbx_lock[MAX_NUM_VFS_SUPPORTED]; @@ -54,6 +54,11 @@ struct nicpf { bool irq_allocated[NIC_PF_MSIX_VECTORS]; }; +static inline bool pass1_silicon(struct nicpf *nic) +{ + return nic->pdev->revision < 8; +} + /* Supported devices */ static const struct pci_device_id nic_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_NIC_PF) }, @@ -117,7 +122,7 @@ static void nic_send_msg_to_vf(struct nicpf *nic, int vf, union nic_mbx *mbx) * when PF writes to MBOX(1), in next revisions when * PF writes to MBOX(0) */ - if (nic->rev_id == 0) { + if (pass1_silicon(nic)) { /* see the comment for nic_reg_write()/nic_reg_read() * functions above */ @@ -305,9 +310,6 @@ static void nic_init_hw(struct nicpf *nic) { int i; - /* Reset NIC, in case the driver is repeatedly inserted and removed */ - nic_reg_write(nic, NIC_PF_SOFT_RESET, 1); - /* Enable NIC HW block */ nic_reg_write(nic, NIC_PF_CFG, 0x3); @@ -395,8 +397,18 @@ static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg) padd = cpi % 8; /* 3 bits CS out of 6bits DSCP */ /* Leave RSS_SIZE as '0' to disable RSS */ - nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3), - (vnic << 24) | (padd << 16) | (rssi_base + rssi)); + if (pass1_silicon(nic)) { + nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3), + (vnic << 24) | (padd << 16) | + (rssi_base + rssi)); + } else { + /* Set MPI_ALG to '0' to disable MCAM parsing */ + nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi << 3), + (padd << 16)); + /* MPI index is same as CPI if MPI_ALG is not enabled */ + nic_reg_write(nic, NIC_PF_MPI_0_2047_CFG | (cpi << 3), + (vnic << 24) | (rssi_base + rssi)); + } if ((rssi + 1) >= cfg->rq_cnt) continue; @@ -409,6 +421,7 @@ static void nic_config_cpi(struct nicpf *nic, struct cpi_cfg_msg *cfg) rssi = ((cpi - cpi_base) & 0x38) >> 3; } nic->cpi_base[cfg->vf_id] = cpi_base; + nic->rssi_base[cfg->vf_id] = rssi_base; } /* Responsds to VF with its RSS indirection table size */ @@ -434,10 +447,9 @@ static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg) { u8 qset, idx = 0; u64 cpi_cfg, cpi_base, rssi_base, rssi; + u64 idx_addr; - cpi_base = nic->cpi_base[cfg->vf_id]; - cpi_cfg = nic_reg_read(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3)); - rssi_base = (cpi_cfg & 0x0FFF) + cfg->tbl_offset; + rssi_base = nic->rssi_base[cfg->vf_id] + cfg->tbl_offset; rssi = rssi_base; qset = cfg->vf_id; @@ -454,9 +466,15 @@ static void nic_config_rss(struct nicpf *nic, struct rss_cfg_msg *cfg) idx++; } + cpi_base = nic->cpi_base[cfg->vf_id]; + if (pass1_silicon(nic)) + idx_addr = NIC_PF_CPI_0_2047_CFG; + else + idx_addr = NIC_PF_MPI_0_2047_CFG; + cpi_cfg = nic_reg_read(nic, idx_addr | (cpi_base << 3)); cpi_cfg &= ~(0xFULL << 20); cpi_cfg |= (cfg->hash_bits << 20); - nic_reg_write(nic, NIC_PF_CPI_0_2047_CFG | (cpi_base << 3), cpi_cfg); + nic_reg_write(nic, idx_addr | (cpi_base << 3), cpi_cfg); } /* 4 level transmit side scheduler configutation @@ -1001,8 +1019,6 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_release_regions; } - pci_read_config_byte(pdev, PCI_REVISION_ID, &nic->rev_id); - nic->node = nic_get_node_id(pdev); nic_set_lmac_vf_mapping(nic); diff --git a/drivers/net/ethernet/cavium/thunder/nic_reg.h b/drivers/net/ethernet/cavium/thunder/nic_reg.h index 58197bb2f805..dd536be20193 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_reg.h +++ b/drivers/net/ethernet/cavium/thunder/nic_reg.h @@ -85,7 +85,11 @@ #define NIC_PF_ECC3_DBE_INT_W1S (0x2708) #define NIC_PF_ECC3_DBE_ENA_W1C (0x2710) #define NIC_PF_ECC3_DBE_ENA_W1S (0x2718) +#define NIC_PF_MCAM_0_191_ENA (0x100000) +#define NIC_PF_MCAM_0_191_M_0_5_DATA (0x110000) +#define NIC_PF_MCAM_CTRL (0x120000) #define NIC_PF_CPI_0_2047_CFG (0x200000) +#define NIC_PF_MPI_0_2047_CFG (0x210000) #define NIC_PF_RSSI_0_4097_RQ (0x220000) #define NIC_PF_LMAC_0_7_CFG (0x240000) #define NIC_PF_LMAC_0_7_SW_XOFF (0x242000) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index b63e579aeb12..a9377727c11c 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -29,7 +29,7 @@ static const struct pci_device_id nicvf_id_table[] = { { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_NIC_VF, - PCI_VENDOR_ID_CAVIUM, 0xA11E) }, + PCI_VENDOR_ID_CAVIUM, 0xA134) }, { PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_PASS1_NIC_VF, PCI_VENDOR_ID_CAVIUM, 0xA11E) }, diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 574c49278900..180aa9fabf48 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -977,8 +977,10 @@ static int bgx_init_of_phy(struct bgx *bgx) SET_NETDEV_DEV(&bgx->lmac[lmac].netdev, &bgx->pdev->dev); bgx->lmac[lmac].lmacid = lmac; lmac++; - if (lmac == MAX_LMAC_PER_BGX) + if (lmac == MAX_LMAC_PER_BGX) { + of_node_put(np_child); break; + } } return 0; } diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 710715fcb23d..ce38d266f931 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -341,7 +341,7 @@ static void gfar_rx_offload_en(struct gfar_private *priv) if (priv->ndev->features & (NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_RX)) priv->uses_rxfcb = 1; - if (priv->hwts_rx_en) + if (priv->hwts_rx_en || priv->rx_filer_enable) priv->uses_rxfcb = 1; } @@ -351,7 +351,7 @@ static void gfar_mac_rx_config(struct gfar_private *priv) u32 rctrl = 0; if (priv->rx_filer_enable) { - rctrl |= RCTRL_FILREN; + rctrl |= RCTRL_FILREN | RCTRL_PRSDEP_INIT; /* Program the RIR0 reg with the required distribution */ if (priv->poll_mode == GFAR_SQ_POLLING) gfar_write(®s->rir0, DEFAULT_2RXQ_RIR0); @@ -3462,11 +3462,9 @@ static irqreturn_t gfar_error(int irq, void *grp_id) netif_dbg(priv, tx_err, dev, "Transmit Error\n"); } if (events & IEVENT_BSY) { - dev->stats.rx_errors++; + dev->stats.rx_over_errors++; atomic64_inc(&priv->extra_stats.rx_bsy); - gfar_receive(irq, grp_id); - netif_dbg(priv, rx_err, dev, "busy error (rstat: %x)\n", gfar_read(®s->rstat)); } diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 6bdc89179b72..a33e4a829601 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -676,14 +676,14 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow) u32 fcr = 0x0, fpr = FPR_FILER_MASK; if (ethflow & RXH_L2DA) { - fcr = RQFCR_PID_DAH |RQFCR_CMP_NOMATCH | + fcr = RQFCR_PID_DAH | RQFCR_CMP_NOMATCH | RQFCR_HASH | RQFCR_AND | RQFCR_HASHTBL_0; priv->ftp_rqfpr[priv->cur_filer_idx] = fpr; priv->ftp_rqfcr[priv->cur_filer_idx] = fcr; gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr); priv->cur_filer_idx = priv->cur_filer_idx - 1; - fcr = RQFCR_PID_DAL | RQFCR_AND | RQFCR_CMP_NOMATCH | + fcr = RQFCR_PID_DAL | RQFCR_CMP_NOMATCH | RQFCR_HASH | RQFCR_AND | RQFCR_HASHTBL_0; priv->ftp_rqfpr[priv->cur_filer_idx] = fpr; priv->ftp_rqfcr[priv->cur_filer_idx] = fcr; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index e972b5ecbf0b..13a5d4cf494b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1344,6 +1344,12 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, data[i++] = (i40e_gstrings_veb_stats[j].sizeof_stat == sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } + for (j = 0; j < I40E_MAX_TRAFFIC_CLASS; j++) { + data[i++] = veb->tc_stats.tc_tx_packets[j]; + data[i++] = veb->tc_stats.tc_tx_bytes[j]; + data[i++] = veb->tc_stats.tc_rx_packets[j]; + data[i++] = veb->tc_stats.tc_rx_bytes[j]; + } } for (j = 0; j < I40E_GLOBAL_STATS_LEN; j++) { p = (char *)pf + i40e_gstrings_stats[j].stat_offset; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index dd44fafd8798..3dd26cdd0bf2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7911,6 +7911,7 @@ static int i40e_sw_init(struct i40e_pf *pf) if (pf->hw.func_caps.vmdq) { pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI; pf->flags |= I40E_FLAG_VMDQ_ENABLED; + pf->num_vmdq_qps = i40e_default_queues_per_vmdq(pf); } #ifdef I40E_FCOE diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 960169efe636..dfb6d5f79a10 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -759,11 +759,23 @@ txq_put_data_tso(struct net_device *dev, struct tx_queue *txq, desc->l4i_chk = 0; desc->byte_cnt = length; - desc->buf_ptr = dma_map_single(dev->dev.parent, data, - length, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev->dev.parent, desc->buf_ptr))) { - WARN(1, "dma_map_single failed!\n"); - return -ENOMEM; + + if (length <= 8 && (uintptr_t)data & 0x7) { + /* Copy unaligned small data fragment to TSO header data area */ + memcpy(txq->tso_hdrs + txq->tx_curr_desc * TSO_HEADER_SIZE, + data, length); + desc->buf_ptr = txq->tso_hdrs_dma + + txq->tx_curr_desc * TSO_HEADER_SIZE; + } else { + /* Alignment is okay, map buffer and hand off to hardware */ + txq->tx_desc_mapping[tx_index] = DESC_DMA_MAP_SINGLE; + desc->buf_ptr = dma_map_single(dev->dev.parent, data, + length, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev->dev.parent, + desc->buf_ptr))) { + WARN(1, "dma_map_single failed!\n"); + return -ENOMEM; + } } cmd_sts = BUFFER_OWNED_BY_DMA; @@ -779,7 +791,8 @@ txq_put_data_tso(struct net_device *dev, struct tx_queue *txq, } static inline void -txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length) +txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length, + u32 *first_cmd_sts, bool first_desc) { struct mv643xx_eth_private *mp = txq_to_mp(txq); int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); @@ -788,6 +801,7 @@ txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length) int ret; u32 cmd_csum = 0; u16 l4i_chk = 0; + u32 cmd_sts; tx_index = txq->tx_curr_desc; desc = &txq->tx_desc_area[tx_index]; @@ -803,9 +817,17 @@ txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length) desc->byte_cnt = hdr_len; desc->buf_ptr = txq->tso_hdrs_dma + txq->tx_curr_desc * TSO_HEADER_SIZE; - desc->cmd_sts = cmd_csum | BUFFER_OWNED_BY_DMA | TX_FIRST_DESC | + cmd_sts = cmd_csum | BUFFER_OWNED_BY_DMA | TX_FIRST_DESC | GEN_CRC; + /* Defer updating the first command descriptor until all + * following descriptors have been written. + */ + if (first_desc) + *first_cmd_sts = cmd_sts; + else + desc->cmd_sts = cmd_sts; + txq->tx_curr_desc++; if (txq->tx_curr_desc == txq->tx_ring_size) txq->tx_curr_desc = 0; @@ -819,6 +841,8 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb, int desc_count = 0; struct tso_t tso; int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + struct tx_desc *first_tx_desc; + u32 first_cmd_sts = 0; /* Count needed descriptors */ if ((txq->tx_desc_count + tso_count_descs(skb)) >= txq->tx_ring_size) { @@ -826,11 +850,14 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb, return -EBUSY; } + first_tx_desc = &txq->tx_desc_area[txq->tx_curr_desc]; + /* Initialize the TSO handler, and prepare the first payload */ tso_start(skb, &tso); total_len = skb->len - hdr_len; while (total_len > 0) { + bool first_desc = (desc_count == 0); char *hdr; data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len); @@ -840,7 +867,8 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb, /* prepare packet headers: MAC + IP + TCP */ hdr = txq->tso_hdrs + txq->tx_curr_desc * TSO_HEADER_SIZE; tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0); - txq_put_hdr_tso(skb, txq, data_left); + txq_put_hdr_tso(skb, txq, data_left, &first_cmd_sts, + first_desc); while (data_left > 0) { int size; @@ -860,6 +888,10 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb, __skb_queue_tail(&txq->tx_skb, skb); skb_tx_timestamp(skb); + /* ensure all other descriptors are written before first cmd_sts */ + wmb(); + first_tx_desc->cmd_sts = first_cmd_sts; + /* clear TX_END status */ mp->work_tx_end &= ~(1 << txq->index); @@ -2785,8 +2817,10 @@ static int mv643xx_eth_shared_of_probe(struct platform_device *pdev) for_each_available_child_of_node(np, pnp) { ret = mv643xx_eth_shared_of_add_port(pdev, pnp); - if (ret) + if (ret) { + of_node_put(pnp); return ret; + } } return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 0a3202047569..2177e56ed0be 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2398,7 +2398,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) } } - memset(&priv->mfunc.master.cmd_eqe, 0, dev->caps.eqe_size); + memset(&priv->mfunc.master.cmd_eqe, 0, sizeof(struct mlx4_eqe)); priv->mfunc.master.cmd_eqe.type = MLX4_EVENT_TYPE_CMD; INIT_WORK(&priv->mfunc.master.comm_work, mlx4_master_comm_channel); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 494e7762fdb1..4421bf5463f6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -964,6 +964,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_SVLAN; else if (vlan_proto == ETH_P_8021Q) tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_CVLAN; + else + tx_desc->ctrl.ins_vlan = 0; tx_desc->ctrl.fence_size = real_size; diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index c34488479365..603d1c3d3b2e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -196,7 +196,7 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe) return; } - memcpy(s_eqe, eqe, dev->caps.eqe_size - 1); + memcpy(s_eqe, eqe, sizeof(struct mlx4_eqe) - 1); s_eqe->slave_id = slave; /* ensure all information is written before setting the ownersip bit */ dma_wmb(); diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index a41bb5e6b954..75e88f4c1531 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -4076,6 +4076,8 @@ static void nv_do_nic_poll(unsigned long data) struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); u32 mask = 0; + unsigned long flags; + unsigned int irq = 0; /* * First disable irq(s) and then @@ -4085,25 +4087,27 @@ static void nv_do_nic_poll(unsigned long data) if (!using_multi_irqs(dev)) { if (np->msi_flags & NV_MSI_X_ENABLED) - disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector); + irq = np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector; else - disable_irq_lockdep(np->pci_dev->irq); + irq = np->pci_dev->irq; mask = np->irqmask; } else { if (np->nic_poll_irq & NVREG_IRQ_RX_ALL) { - disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector); + irq = np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector; mask |= NVREG_IRQ_RX_ALL; } if (np->nic_poll_irq & NVREG_IRQ_TX_ALL) { - disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector); + irq = np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector; mask |= NVREG_IRQ_TX_ALL; } if (np->nic_poll_irq & NVREG_IRQ_OTHER) { - disable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector); + irq = np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector; mask |= NVREG_IRQ_OTHER; } } - /* disable_irq() contains synchronize_irq, thus no irq handler can run now */ + + disable_irq_nosync_lockdep_irqsave(irq, &flags); + synchronize_irq(irq); if (np->recover_error) { np->recover_error = 0; @@ -4156,28 +4160,22 @@ static void nv_do_nic_poll(unsigned long data) nv_nic_irq_optimized(0, dev); else nv_nic_irq(0, dev); - if (np->msi_flags & NV_MSI_X_ENABLED) - enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector); - else - enable_irq_lockdep(np->pci_dev->irq); } else { if (np->nic_poll_irq & NVREG_IRQ_RX_ALL) { np->nic_poll_irq &= ~NVREG_IRQ_RX_ALL; nv_nic_irq_rx(0, dev); - enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector); } if (np->nic_poll_irq & NVREG_IRQ_TX_ALL) { np->nic_poll_irq &= ~NVREG_IRQ_TX_ALL; nv_nic_irq_tx(0, dev); - enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector); } if (np->nic_poll_irq & NVREG_IRQ_OTHER) { np->nic_poll_irq &= ~NVREG_IRQ_OTHER; nv_nic_irq_other(0, dev); - enable_irq_lockdep(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector); } } + enable_irq_lockdep_irqrestore(irq, &flags); } #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 257ea713b4c1..a484d8beb855 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1127,7 +1127,7 @@ static void sh_eth_ring_format(struct net_device *ndev) struct sh_eth_txdesc *txdesc = NULL; int rx_ringsize = sizeof(*rxdesc) * mdp->num_rx_ring; int tx_ringsize = sizeof(*txdesc) * mdp->num_tx_ring; - int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1; + int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN + 32 - 1; dma_addr_t dma_addr; mdp->cur_rx = 0; @@ -1148,8 +1148,8 @@ static void sh_eth_ring_format(struct net_device *ndev) /* RX descriptor */ rxdesc = &mdp->rx_ring[i]; - /* The size of the buffer is a multiple of 16 bytes. */ - rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16); + /* The size of the buffer is a multiple of 32 bytes. */ + rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32); dma_addr = dma_map_single(&ndev->dev, skb->data, rxdesc->buffer_length, DMA_FROM_DEVICE); @@ -1450,7 +1450,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) struct sk_buff *skb; u16 pkt_len = 0; u32 desc_status; - int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN - 1; + int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN + 32 - 1; dma_addr_t dma_addr; boguscnt = min(boguscnt, *quota); @@ -1506,7 +1506,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) if (mdp->cd->rpadir) skb_reserve(skb, NET_IP_ALIGN); dma_unmap_single(&ndev->dev, rxdesc->addr, - ALIGN(mdp->rx_buf_sz, 16), + ALIGN(mdp->rx_buf_sz, 32), DMA_FROM_DEVICE); skb_put(skb, pkt_len); skb->protocol = eth_type_trans(skb, ndev); @@ -1524,8 +1524,8 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) for (; mdp->cur_rx - mdp->dirty_rx > 0; mdp->dirty_rx++) { entry = mdp->dirty_rx % mdp->num_rx_ring; rxdesc = &mdp->rx_ring[entry]; - /* The size of the buffer is 16 byte boundary. */ - rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 16); + /* The size of the buffer is 32 byte boundary. */ + rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32); if (mdp->rx_skbuff[entry] == NULL) { skb = netdev_alloc_skb(ndev, skbuff_size); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 8fc90f1c872c..874fb297e96c 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -30,6 +30,7 @@ #include <linux/delay.h> #include <linux/pm_runtime.h> #include <linux/of.h> +#include <linux/of_mdio.h> #include <linux/of_net.h> #include <linux/of_device.h> #include <linux/if_vlan.h> @@ -365,6 +366,7 @@ struct cpsw_priv { spinlock_t lock; struct platform_device *pdev; struct net_device *ndev; + struct device_node *phy_node; struct napi_struct napi_rx; struct napi_struct napi_tx; struct device *dev; @@ -1145,7 +1147,11 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) cpsw_ale_add_mcast(priv->ale, priv->ndev->broadcast, 1 << slave_port, 0, 0, ALE_MCAST_FWD_2); - slave->phy = phy_connect(priv->ndev, slave->data->phy_id, + if (priv->phy_node) + slave->phy = of_phy_connect(priv->ndev, priv->phy_node, + &cpsw_adjust_link, 0, slave->data->phy_if); + else + slave->phy = phy_connect(priv->ndev, slave->data->phy_id, &cpsw_adjust_link, slave->data->phy_if); if (IS_ERR(slave->phy)) { dev_err(priv->dev, "phy %s not found on slave %d\n", @@ -1934,11 +1940,12 @@ static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv, slave->port_vlan = data->dual_emac_res_vlan; } -static int cpsw_probe_dt(struct cpsw_platform_data *data, +static int cpsw_probe_dt(struct cpsw_priv *priv, struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; struct device_node *slave_node; + struct cpsw_platform_data *data = &priv->data; int i = 0, ret; u32 prop; @@ -2029,6 +2036,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, if (strcmp(slave_node->name, "slave")) continue; + priv->phy_node = of_parse_phandle(slave_node, "phy-handle", 0); parp = of_get_property(slave_node, "phy_id", &lenp); if ((parp == NULL) || (lenp != (sizeof(void *) * 2))) { dev_err(&pdev->dev, "Missing slave[%d] phy_id property\n", i); @@ -2044,7 +2052,6 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, } snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), PHY_ID_FMT, mdio->name, phyid); - slave_data->phy_if = of_get_phy_mode(slave_node); if (slave_data->phy_if < 0) { dev_err(&pdev->dev, "Missing or malformed slave[%d] phy-mode property\n", @@ -2240,7 +2247,7 @@ static int cpsw_probe(struct platform_device *pdev) /* Select default pin state */ pinctrl_pm_select_default_state(&pdev->dev); - if (cpsw_probe_dt(&priv->data, pdev)) { + if (cpsw_probe_dt(priv, pdev)) { dev_err(&pdev->dev, "cpsw: platform data missing\n"); ret = -ENODEV; goto clean_runtime_disable_ret; diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 6bff8d82ceab..4e70e7586a09 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2637,8 +2637,10 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev, mac_phy_link = true; slave->open = true; - if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) + if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) { + of_node_put(port); break; + } } /* of_phy_connect() is needed only for MAC-PHY interface */ @@ -3137,8 +3139,10 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, continue; } gbe_dev->num_slaves++; - if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) + if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves) { + of_node_put(interface); break; + } } of_node_put(interfaces); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index cde29f8a37bf..445071c163cb 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -594,14 +594,12 @@ static struct rtable *geneve_get_rt(struct sk_buff *skb, rt = ip_route_output_key(geneve->net, fl4); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", &fl4->daddr); - dev->stats.tx_carrier_errors++; - return rt; + return ERR_PTR(-ENETUNREACH); } if (rt->dst.dev == dev) { /* is this necessary? */ netdev_dbg(dev, "circular route to %pI4\n", &fl4->daddr); - dev->stats.collisions++; ip_rt_put(rt); - return ERR_PTR(-EINVAL); + return ERR_PTR(-ELOOP); } return rt; } @@ -627,12 +625,12 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) struct ip_tunnel_info *info = NULL; struct rtable *rt = NULL; const struct iphdr *iip; /* interior IP header */ + int err = -EINVAL; struct flowi4 fl4; __u8 tos, ttl; __be16 sport; bool udp_csum; __be16 df; - int err; if (geneve->collect_md) { info = skb_tunnel_info(skb); @@ -647,7 +645,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) rt = geneve_get_rt(skb, dev, &fl4, info); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); - dev->stats.tx_carrier_errors++; + err = PTR_ERR(rt); goto tx_error; } @@ -699,10 +697,37 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) tx_error: dev_kfree_skb(skb); err: - dev->stats.tx_errors++; + if (err == -ELOOP) + dev->stats.collisions++; + else if (err == -ENETUNREACH) + dev->stats.tx_carrier_errors++; + else + dev->stats.tx_errors++; return NETDEV_TX_OK; } +static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct ip_tunnel_info *info = skb_tunnel_info(skb); + struct geneve_dev *geneve = netdev_priv(dev); + struct rtable *rt; + struct flowi4 fl4; + + if (ip_tunnel_info_af(info) != AF_INET) + return -EINVAL; + + rt = geneve_get_rt(skb, dev, &fl4, info); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + ip_rt_put(rt); + info->key.u.ipv4.src = fl4.saddr; + info->key.tp_src = udp_flow_src_port(geneve->net, skb, + 1, USHRT_MAX, true); + info->key.tp_dst = geneve->dst_port; + return 0; +} + static const struct net_device_ops geneve_netdev_ops = { .ndo_init = geneve_init, .ndo_uninit = geneve_uninit, @@ -713,6 +738,7 @@ static const struct net_device_ops geneve_netdev_ops = { .ndo_change_mtu = eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, + .ndo_fill_metadata_dst = geneve_fill_metadata_dst, }; static void geneve_get_drvinfo(struct net_device *dev, diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 248478c6f6e4..197c93937c2d 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -137,7 +137,7 @@ static const struct proto_ops macvtap_socket_ops; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6 | NETIF_F_UFO) #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO) -#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG) +#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG | NETIF_F_FRAGLIST) static struct macvlan_dev *macvtap_get_vlan_rcu(const struct net_device *dev) { diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 11e3975485c1..436972b2a746 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -122,6 +122,11 @@ config MICREL_PHY ---help--- Supports the KSZ9021, VSC8201, KS8001 PHYs. +config DP83848_PHY + tristate "Driver for Texas Instruments DP83848 PHY" + ---help--- + Supports the DP83848 PHY. + config DP83867_PHY tristate "Drivers for Texas Instruments DP83867 Gigabit PHY" ---help--- diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 87f079c4b2c7..b74822463930 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_MDIO_BITBANG) += mdio-bitbang.o obj-$(CONFIG_MDIO_GPIO) += mdio-gpio.o obj-$(CONFIG_NATIONAL_PHY) += national.o obj-$(CONFIG_DP83640_PHY) += dp83640.o +obj-$(CONFIG_DP83848_PHY) += dp83848.o obj-$(CONFIG_DP83867_PHY) += dp83867.o obj-$(CONFIG_STE10XP) += ste10Xp.o obj-$(CONFIG_MICREL_PHY) += micrel.o diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c new file mode 100644 index 000000000000..5ce9bef54468 --- /dev/null +++ b/drivers/net/phy/dp83848.c @@ -0,0 +1,99 @@ +/* + * Driver for the Texas Instruments DP83848 PHY + * + * Copyright (C) 2015 Texas Instruments Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/module.h> +#include <linux/phy.h> + +#define DP83848_PHY_ID 0x20005c90 + +/* Registers */ +#define DP83848_MICR 0x11 +#define DP83848_MISR 0x12 + +/* MICR Register Fields */ +#define DP83848_MICR_INT_OE BIT(0) /* Interrupt Output Enable */ +#define DP83848_MICR_INTEN BIT(1) /* Interrupt Enable */ + +/* MISR Register Fields */ +#define DP83848_MISR_RHF_INT_EN BIT(0) /* Receive Error Counter */ +#define DP83848_MISR_FHF_INT_EN BIT(1) /* False Carrier Counter */ +#define DP83848_MISR_ANC_INT_EN BIT(2) /* Auto-negotiation complete */ +#define DP83848_MISR_DUP_INT_EN BIT(3) /* Duplex Status */ +#define DP83848_MISR_SPD_INT_EN BIT(4) /* Speed status */ +#define DP83848_MISR_LINK_INT_EN BIT(5) /* Link status */ +#define DP83848_MISR_ED_INT_EN BIT(6) /* Energy detect */ +#define DP83848_MISR_LQM_INT_EN BIT(7) /* Link Quality Monitor */ + +static int dp83848_ack_interrupt(struct phy_device *phydev) +{ + int err = phy_read(phydev, DP83848_MISR); + + return err < 0 ? err : 0; +} + +static int dp83848_config_intr(struct phy_device *phydev) +{ + int err; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = phy_write(phydev, DP83848_MICR, + DP83848_MICR_INT_OE | + DP83848_MICR_INTEN); + if (err < 0) + return err; + + return phy_write(phydev, DP83848_MISR, + DP83848_MISR_ANC_INT_EN | + DP83848_MISR_DUP_INT_EN | + DP83848_MISR_SPD_INT_EN | + DP83848_MISR_LINK_INT_EN); + } + + return phy_write(phydev, DP83848_MICR, 0x0); +} + +static struct mdio_device_id __maybe_unused dp83848_tbl[] = { + { DP83848_PHY_ID, 0xfffffff0 }, + { } +}; +MODULE_DEVICE_TABLE(mdio, dp83848_tbl); + +static struct phy_driver dp83848_driver[] = { + { + .phy_id = DP83848_PHY_ID, + .phy_id_mask = 0xfffffff0, + .name = "TI DP83848", + .features = PHY_BASIC_FEATURES, + .flags = PHY_HAS_INTERRUPT, + + .soft_reset = genphy_soft_reset, + .config_init = genphy_config_init, + .suspend = genphy_suspend, + .resume = genphy_resume, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + + /* IRQ related */ + .ack_interrupt = dp83848_ack_interrupt, + .config_intr = dp83848_config_intr, + + .driver = { .owner = THIS_MODULE, }, + }, +}; +module_phy_driver(dp83848_driver); + +MODULE_DESCRIPTION("Texas Instruments DP83848 PHY driver"); +MODULE_AUTHOR("Andrew F. Davis <afd@ti.com"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/mdio-mux-mmioreg.c b/drivers/net/phy/mdio-mux-mmioreg.c index 2377c1341172..7fde454fbc4f 100644 --- a/drivers/net/phy/mdio-mux-mmioreg.c +++ b/drivers/net/phy/mdio-mux-mmioreg.c @@ -113,12 +113,14 @@ static int mdio_mux_mmioreg_probe(struct platform_device *pdev) if (!iprop || len != sizeof(uint32_t)) { dev_err(&pdev->dev, "mdio-mux child node %s is " "missing a 'reg' property\n", np2->full_name); + of_node_put(np2); return -ENODEV; } if (be32_to_cpup(iprop) & ~s->mask) { dev_err(&pdev->dev, "mdio-mux child node %s has " "a 'reg' value with unmasked bits\n", np2->full_name); + of_node_put(np2); return -ENODEV; } } diff --git a/drivers/net/phy/mdio-mux.c b/drivers/net/phy/mdio-mux.c index 280c7c311f72..908e8d486342 100644 --- a/drivers/net/phy/mdio-mux.c +++ b/drivers/net/phy/mdio-mux.c @@ -144,6 +144,7 @@ int mdio_mux_init(struct device *dev, dev_err(dev, "Error: Failed to allocate memory for child\n"); ret_val = -ENOMEM; + of_node_put(child_bus_node); break; } cb->bus_number = v; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 499185eaf413..cf6312fafea5 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -514,6 +514,27 @@ static int ksz8873mll_read_status(struct phy_device *phydev) return 0; } +static int ksz9031_read_status(struct phy_device *phydev) +{ + int err; + int regval; + + err = genphy_read_status(phydev); + if (err) + return err; + + /* Make sure the PHY is not broken. Read idle error count, + * and reset the PHY if it is maxed out. + */ + regval = phy_read(phydev, MII_STAT1000); + if ((regval & 0xFF) == 0xFF) { + phy_init_hw(phydev); + phydev->link = 0; + } + + return 0; +} + static int ksz8873mll_config_aneg(struct phy_device *phydev) { return 0; @@ -772,7 +793,7 @@ static struct phy_driver ksphy_driver[] = { .driver_data = &ksz9021_type, .config_init = ksz9031_config_init, .config_aneg = genphy_config_aneg, - .read_status = genphy_read_status, + .read_status = ksz9031_read_status, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, .suspend = genphy_suspend, diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 70b08958763a..dc2da8770918 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -43,16 +43,25 @@ static int smsc_phy_ack_interrupt(struct phy_device *phydev) static int smsc_phy_config_init(struct phy_device *phydev) { + int __maybe_unused len; + struct device *dev __maybe_unused = &phydev->dev; + struct device_node *of_node __maybe_unused = dev->of_node; int rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS); + int enable_energy = 1; if (rc < 0) return rc; - /* Enable energy detect mode for this SMSC Transceivers */ - rc = phy_write(phydev, MII_LAN83C185_CTRL_STATUS, - rc | MII_LAN83C185_EDPWRDOWN); - if (rc < 0) - return rc; + if (of_find_property(of_node, "smsc,disable-energy-detect", &len)) + enable_energy = 0; + + if (enable_energy) { + /* Enable energy detect mode for this SMSC Transceivers */ + rc = phy_write(phydev, MII_LAN83C185_CTRL_STATUS, + rc | MII_LAN83C185_EDPWRDOWN); + if (rc < 0) + return rc; + } return smsc_phy_ack_interrupt(phydev); } diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 2ed75060da50..5e0b43283bce 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -589,7 +589,7 @@ static int pppoe_release(struct socket *sock) po = pppox_sk(sk); - if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND | PPPOX_ZOMBIE)) { + if (po->pppoe_dev) { dev_put(po->pppoe_dev); po->pppoe_dev = NULL; } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 355842b85ee9..2a7c1be23c4f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -765,6 +765,10 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9056, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9057, 8)}, {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ + {QMI_FIXED_INTF(0x1199, 0x9070, 8)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9070, 10)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx/EM74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx/EM74xx */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index afdc65fd5bc5..c1587ece28cf 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2337,6 +2337,46 @@ static int vxlan_change_mtu(struct net_device *dev, int new_mtu) return 0; } +static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb, + struct ip_tunnel_info *info, + __be16 sport, __be16 dport) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct rtable *rt; + struct flowi4 fl4; + + memset(&fl4, 0, sizeof(fl4)); + fl4.flowi4_tos = RT_TOS(info->key.tos); + fl4.flowi4_mark = skb->mark; + fl4.flowi4_proto = IPPROTO_UDP; + fl4.daddr = info->key.u.ipv4.dst; + + rt = ip_route_output_key(vxlan->net, &fl4); + if (IS_ERR(rt)) + return PTR_ERR(rt); + ip_rt_put(rt); + + info->key.u.ipv4.src = fl4.saddr; + info->key.tp_src = sport; + info->key.tp_dst = dport; + return 0; +} + +static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct vxlan_dev *vxlan = netdev_priv(dev); + struct ip_tunnel_info *info = skb_tunnel_info(skb); + __be16 sport, dport; + + sport = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, + vxlan->cfg.port_max, true); + dport = info->key.tp_dst ? : vxlan->cfg.dst_port; + + if (ip_tunnel_info_af(info) == AF_INET) + return egress_ipv4_tun_info(dev, skb, info, sport, dport); + return -EINVAL; +} + static const struct net_device_ops vxlan_netdev_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, @@ -2351,6 +2391,7 @@ static const struct net_device_ops vxlan_netdev_ops = { .ndo_fdb_add = vxlan_fdb_add, .ndo_fdb_del = vxlan_fdb_delete, .ndo_fdb_dump = vxlan_fdb_dump, + .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; /* Info for udev, that this is a virtual tunnel endpoint */ diff --git a/drivers/net/wireless/ath/ath6kl/init.c b/drivers/net/wireless/ath/ath6kl/init.c index 6e473fa4b13c..12241b1c57cd 100644 --- a/drivers/net/wireless/ath/ath6kl/init.c +++ b/drivers/net/wireless/ath/ath6kl/init.c @@ -715,6 +715,7 @@ static bool check_device_tree(struct ath6kl *ar) board_filename, ret); continue; } + of_node_put(node); return true; } return false; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index f821a97d7827..6febc053a37f 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1706,19 +1706,19 @@ static void xennet_destroy_queues(struct netfront_info *info) } static int xennet_create_queues(struct netfront_info *info, - unsigned int num_queues) + unsigned int *num_queues) { unsigned int i; int ret; - info->queues = kcalloc(num_queues, sizeof(struct netfront_queue), + info->queues = kcalloc(*num_queues, sizeof(struct netfront_queue), GFP_KERNEL); if (!info->queues) return -ENOMEM; rtnl_lock(); - for (i = 0; i < num_queues; i++) { + for (i = 0; i < *num_queues; i++) { struct netfront_queue *queue = &info->queues[i]; queue->id = i; @@ -1728,7 +1728,7 @@ static int xennet_create_queues(struct netfront_info *info, if (ret < 0) { dev_warn(&info->netdev->dev, "only created %d queues\n", i); - num_queues = i; + *num_queues = i; break; } @@ -1738,11 +1738,11 @@ static int xennet_create_queues(struct netfront_info *info, napi_enable(&queue->napi); } - netif_set_real_num_tx_queues(info->netdev, num_queues); + netif_set_real_num_tx_queues(info->netdev, *num_queues); rtnl_unlock(); - if (num_queues == 0) { + if (*num_queues == 0) { dev_err(&info->netdev->dev, "no queues\n"); return -EINVAL; } @@ -1788,7 +1788,7 @@ static int talk_to_netback(struct xenbus_device *dev, if (info->queues) xennet_destroy_queues(info); - err = xennet_create_queues(info, num_queues); + err = xennet_create_queues(info, &num_queues); if (err < 0) goto destroy_ring; diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 4772862b71a7..d3f767448a72 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -183,10 +183,17 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit) return vq->acked_features & (1ULL << bit); } +#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq) { return vq->is_le; } +#else +static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq) +{ + return virtio_legacy_is_little_endian() || vq->is_le; +} +#endif /* Memory accessors */ static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2d15e3831440..210d11a75e4f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1054,6 +1054,10 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * This function is used to pass protocol port error state information * to the switch driver. The switch driver can react to the proto_down * by doing a phys down on the associated switch port. + * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); + * This function is used to get egress tunnel information for given skb. + * This is useful for retrieving outer tunnel header parameters while + * sampling packet. * */ struct net_device_ops { @@ -1227,6 +1231,8 @@ struct net_device_ops { int (*ndo_get_iflink)(const struct net_device *dev); int (*ndo_change_proto_down)(struct net_device *dev, bool proto_down); + int (*ndo_fill_metadata_dst)(struct net_device *dev, + struct sk_buff *skb); }; /** @@ -2203,6 +2209,7 @@ void dev_add_offload(struct packet_offload *po); void dev_remove_offload(struct packet_offload *po); int dev_get_iflink(const struct net_device *dev); +int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb); struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, unsigned short mask); struct net_device *dev_get_by_name(struct net *net, const char *name); diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index af9d5382f6cb..ce009710120c 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -60,6 +60,38 @@ static inline struct metadata_dst *tun_rx_dst(int md_size) return tun_dst; } +static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) +{ + struct metadata_dst *md_dst = skb_metadata_dst(skb); + int md_size = md_dst->u.tun_info.options_len; + struct metadata_dst *new_md; + + if (!md_dst) + return ERR_PTR(-EINVAL); + + new_md = metadata_dst_alloc(md_size, GFP_ATOMIC); + if (!new_md) + return ERR_PTR(-ENOMEM); + + memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, + sizeof(struct ip_tunnel_info) + md_size); + skb_dst_drop(skb); + dst_hold(&new_md->dst); + skb_dst_set(skb, &new_md->dst); + return new_md; +} + +static inline struct ip_tunnel_info *skb_tunnel_info_unclone(struct sk_buff *skb) +{ + struct metadata_dst *dst; + + dst = tun_dst_unclone(skb); + if (IS_ERR(dst)) + return NULL; + + return &dst->u.tun_info; +} + static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, __be16 flags, __be64 tunnel_id, diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 036f73bc54cd..e663627a8ef3 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -620,7 +620,8 @@ struct ovs_action_hash { * enum ovs_ct_attr - Attributes for %OVS_ACTION_ATTR_CT action. * @OVS_CT_ATTR_COMMIT: If present, commits the connection to the conntrack * table. This allows future packets for the same connection to be identified - * as 'established' or 'related'. + * as 'established' or 'related'. The flow key for the current packet will + * retain the pre-commit connection state. * @OVS_CT_ATTR_ZONE: u16 connection tracking zone. * @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the * mask, the corresponding bit in the value is copied to the connection diff --git a/net/core/dev.c b/net/core/dev.c index 6bb6470f5b7b..c14748d051e7 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -99,6 +99,7 @@ #include <linux/rtnetlink.h> #include <linux/stat.h> #include <net/dst.h> +#include <net/dst_metadata.h> #include <net/pkt_sched.h> #include <net/checksum.h> #include <net/xfrm.h> @@ -682,6 +683,32 @@ int dev_get_iflink(const struct net_device *dev) EXPORT_SYMBOL(dev_get_iflink); /** + * dev_fill_metadata_dst - Retrieve tunnel egress information. + * @dev: targeted interface + * @skb: The packet. + * + * For better visibility of tunnel traffic OVS needs to retrieve + * egress tunnel information for a packet. Following API allows + * user to get this info. + */ +int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct ip_tunnel_info *info; + + if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst) + return -EINVAL; + + info = skb_tunnel_info_unclone(skb); + if (!info) + return -ENOMEM; + if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX))) + return -EINVAL; + + return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb); +} +EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); + +/** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 6c2af797f2f9..744e5936c10d 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1569,7 +1569,7 @@ static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key) do { /* record parent and next child index */ pn = n; - cindex = key ? get_index(key, pn) : 0; + cindex = (key > pn->key) ? get_index(key, pn) : 0; if (cindex >> pn->bits) break; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 5aa46d4b44ef..5a8ee3282550 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -36,7 +36,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, SKB_GSO_TCP_ECN | SKB_GSO_GRE | SKB_GSO_GRE_CSUM | - SKB_GSO_IPIP))) + SKB_GSO_IPIP | + SKB_GSO_SIT))) goto out; if (!skb->encapsulation) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index bd0679d90519..614521437e30 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -498,10 +498,26 @@ static struct sk_buff *gre_handle_offloads(struct sk_buff *skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } +static struct rtable *gre_get_rt(struct sk_buff *skb, + struct net_device *dev, + struct flowi4 *fl, + const struct ip_tunnel_key *key) +{ + struct net *net = dev_net(dev); + + memset(fl, 0, sizeof(*fl)); + fl->daddr = key->u.ipv4.dst; + fl->saddr = key->u.ipv4.src; + fl->flowi4_tos = RT_TOS(key->tos); + fl->flowi4_mark = skb->mark; + fl->flowi4_proto = IPPROTO_GRE; + + return ip_route_output_key(net, fl); +} + static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel_info *tun_info; - struct net *net = dev_net(dev); const struct ip_tunnel_key *key; struct flowi4 fl; struct rtable *rt; @@ -516,14 +532,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; key = &tun_info->key; - memset(&fl, 0, sizeof(fl)); - fl.daddr = key->u.ipv4.dst; - fl.saddr = key->u.ipv4.src; - fl.flowi4_tos = RT_TOS(key->tos); - fl.flowi4_mark = skb->mark; - fl.flowi4_proto = IPPROTO_GRE; - - rt = ip_route_output_key(net, &fl); + rt = gre_get_rt(skb, dev, &fl, key); if (IS_ERR(rt)) goto err_free_skb; @@ -566,6 +575,24 @@ err_free_skb: dev->stats.tx_dropped++; } +static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) +{ + struct ip_tunnel_info *info = skb_tunnel_info(skb); + struct rtable *rt; + struct flowi4 fl4; + + if (ip_tunnel_info_af(info) != AF_INET) + return -EINVAL; + + rt = gre_get_rt(skb, dev, &fl4, &info->key); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + ip_rt_put(rt); + info->key.u.ipv4.src = fl4.saddr; + return 0; +} + static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -1023,6 +1050,7 @@ static const struct net_device_ops gre_tap_netdev_ops = { .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip_tunnel_get_iflink, + .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static void ipgre_tap_setup(struct net_device *dev) diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 690d27d3f2f9..a35584176535 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -75,6 +75,7 @@ endif # NF_TABLES config NF_DUP_IPV4 tristate "Netfilter IPv4 packet duplication to alternate destination" + depends on !NF_CONNTRACK || NF_CONNTRACK help This option enables the nf_dup_ipv4 core, which duplicates an IPv4 packet to be rerouted to another destination. diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 8618fd150c96..c4ffc9de1654 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -61,9 +61,7 @@ static bool rpfilter_lookup_reverse(struct flowi4 *fl4, if (FIB_RES_DEV(res) == dev) dev_match = true; #endif - if (dev_match || flags & XT_RPFILTER_LOOSE) - return FIB_RES_NH(res).nh_scope <= RT_SCOPE_HOST; - return dev_match; + return dev_match || flags & XT_RPFILTER_LOOSE; } static bool rpfilter_is_local(const struct sk_buff *skb) diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 7092a61c4dc8..7e538f71f5fb 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -209,7 +209,7 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags) /* alpha = (1 - g) * alpha + g * F */ - alpha -= alpha >> dctcp_shift_g; + alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); if (bytes_ecn) { /* If dctcp_shift_g == 1, a 32bit value would overflow * after 8 Mbytes. diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1100ffe4a722..3dbee0d83b15 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3405,7 +3405,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); skb_mstamp_get(&skb->skb_mstamp); - NET_INC_STATS_BH(sock_net(sk), mib); + NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC); } diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 2878dbfffeb7..41a261355662 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -30,6 +30,8 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) mtu = dst_mtu(skb_dst(skb)); if (skb->len > mtu) { + skb->protocol = htons(ETH_P_IP); + if (skb->sk) xfrm_local_error(skb, mtu); else diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 9f777ec59a59..ed33abf57abd 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -32,6 +32,7 @@ struct fib6_rule { struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { + struct rt6_info *rt; struct fib_lookup_arg arg = { .lookup_ptr = lookup, .flags = FIB_LOOKUP_NOREF, @@ -40,11 +41,21 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, fib_rules_lookup(net->ipv6.fib6_rules_ops, flowi6_to_flowi(fl6), flags, &arg); - if (arg.result) - return arg.result; + rt = arg.result; - dst_hold(&net->ipv6.ip6_null_entry->dst); - return &net->ipv6.ip6_null_entry->dst; + if (!rt) { + dst_hold(&net->ipv6.ip6_null_entry->dst); + return &net->ipv6.ip6_null_entry->dst; + } + + if (rt->rt6i_flags & RTF_REJECT && + rt->dst.error == -EAGAIN) { + ip6_rt_put(rt); + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } + + return &rt->dst; } static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7d2e0023c72d..6cedc62b2abb 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -285,7 +285,17 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, int flags, pol_lookup_t lookup) { - return (struct dst_entry *) lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + struct rt6_info *rt; + + rt = lookup(net, net->ipv6.fib6_main_tbl, fl6, flags); + if (rt->rt6i_flags & RTF_REJECT && + rt->dst.error == -EAGAIN) { + ip6_rt_put(rt); + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } + + return &rt->dst; } static void __net_init fib6_tables_init(struct net *net) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 61d403ee1031..f84ec4e9b2de 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -584,6 +584,8 @@ int ip6_fragment(struct sock *sk, struct sk_buff *skb, if (np->frag_size) mtu = np->frag_size; } + if (mtu < hlen + sizeof(struct frag_hdr) + 8) + goto fail_toobig; mtu -= hlen + sizeof(struct frag_hdr); frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, @@ -877,7 +879,8 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, #ifdef CONFIG_IPV6_SUBTREES ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || #endif - (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { + (!(fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) && + (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex))) { dst_release(dst); dst = NULL; } diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 96833e4b3193..f6a024e141e5 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -58,6 +58,7 @@ endif # NF_TABLES config NF_DUP_IPV6 tristate "Netfilter IPv6 packet duplication to alternate destination" + depends on !NF_CONNTRACK || NF_CONNTRACK help This option enables the nf_dup_ipv6 core, which duplicates an IPv6 packet to be rerouted to another destination. diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 701cd2bae0a9..c7196ad1d69f 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -646,6 +646,7 @@ void nf_ct_frag6_consume_orig(struct sk_buff *skb) s = s2; } } +EXPORT_SYMBOL_GPL(nf_ct_frag6_consume_orig); static int nf_ct_net_init(struct net *net) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 968f31c01f89..946880ad48ac 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1068,6 +1068,9 @@ static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; + if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) + oif = 0; + redo_rt6_select: rt = rt6_select(fn, oif, strict); if (rt->rt6i_nsiblings) @@ -1190,14 +1193,16 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, struct flowi6 *fl6) { int flags = 0; + bool any_src; fl6->flowi6_iif = LOOPBACK_IFINDEX; + any_src = ipv6_addr_any(&fl6->saddr); if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || - fl6->flowi6_oif) + (fl6->flowi6_oif && any_src)) flags |= RT6_LOOKUP_F_IFACE; - if (!ipv6_addr_any(&fl6->saddr)) + if (!any_src) flags |= RT6_LOOKUP_F_HAS_SADDR; else if (sk) flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 09c76a7b474d..e15feb7b413d 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -79,6 +79,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) if (!skb->ignore_df && skb->len > mtu) { skb->dev = dst->dev; + skb->protocol = htons(ETH_P_IPV6); if (xfrm6_local_dontfrag(skb)) xfrm6_local_rxpmtu(skb, mtu); @@ -136,6 +137,7 @@ static int __xfrm6_output(struct sock *sk, struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; int mtu; + bool toobig; #ifdef CONFIG_NETFILTER if (!x) { @@ -144,25 +146,29 @@ static int __xfrm6_output(struct sock *sk, struct sk_buff *skb) } #endif + if (x->props.mode != XFRM_MODE_TUNNEL) + goto skip_frag; + if (skb->protocol == htons(ETH_P_IPV6)) mtu = ip6_skb_dst_mtu(skb); else mtu = dst_mtu(skb_dst(skb)); - if (skb->len > mtu && xfrm6_local_dontfrag(skb)) { + toobig = skb->len > mtu && !skb_is_gso(skb); + + if (toobig && xfrm6_local_dontfrag(skb)) { xfrm6_local_rxpmtu(skb, mtu); return -EMSGSIZE; - } else if (!skb->ignore_df && skb->len > mtu && skb->sk) { + } else if (!skb->ignore_df && toobig && skb->sk) { xfrm_local_error(skb, mtu); return -EMSGSIZE; } - if (x->props.mode == XFRM_MODE_TUNNEL && - ((skb->len > mtu && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb)))) { + if (toobig || dst_allfrag(skb_dst(skb))) return ip6_fragment(sk, skb, x->outer_mode->afinfo->output_finish); - } + +skip_frag: return x->outer_mode->afinfo->output_finish(sk, skb); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 5cedfda4b241..da55e0c85bb8 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -179,7 +179,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) return; case IPPROTO_ICMPV6: - if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) { + if (!onlyproto && (nh + offset + 2 < skb->data || + pskb_may_pull(skb, nh + offset + 2 - skb->data))) { u8 *icmp; nh = skb_network_header(skb); @@ -193,7 +194,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: offset += ipv6_optlen(exthdr); - if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) { + if (!onlyproto && (nh + offset + 3 < skb->data || + pskb_may_pull(skb, nh + offset + 3 - skb->data))) { struct ip6_mh *mh; nh = skb_network_header(skb); diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c index a26c401ef4a4..43964594aa12 100644 --- a/net/irda/irlmp.c +++ b/net/irda/irlmp.c @@ -1839,7 +1839,7 @@ static void *irlmp_seq_hb_idx(struct irlmp_iter_state *iter, loff_t *off) for (element = hashbin_get_first(iter->hashbin); element != NULL; element = hashbin_get_next(iter->hashbin)) { - if (!off || *off-- == 0) { + if (!off || (*off)-- == 0) { /* NB: hashbin left locked */ return element; } diff --git a/net/key/af_key.c b/net/key/af_key.c index 83a70688784b..f9c9ecb0cdd3 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -261,7 +261,7 @@ static int pfkey_broadcast(struct sk_buff *skb, err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); - /* Error is cleare after succecful sending to at least one + /* Error is cleared after successful sending to at least one * registered KM */ if ((broadcast_flags & BROADCAST_REGISTERED) && err) err = err2; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 8e47f8113495..21a085686dc1 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -152,6 +152,8 @@ void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) #endif synchronize_net(); nf_queue_nf_hook_drop(net, &entry->ops); + /* other cpu might still process nfqueue verdict that used reg */ + synchronize_net(); kfree(entry); } EXPORT_SYMBOL(nf_unregister_net_hook); diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index a1fe5377a2b3..5a30ce6e8c90 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -297,7 +297,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, ip_set_timeout_expired(ext_timeout(n, set)))) n = NULL; - e = kzalloc(set->dsize, GFP_KERNEL); + e = kzalloc(set->dsize, GFP_ATOMIC); if (!e) return -ENOMEM; e->id = d->id; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 0a49a8c7c564..fafe33bdb619 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2371,7 +2371,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, int pos, idx, shift; err = 0; - netlink_table_grab(); + netlink_lock_table(); for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { if (len - pos < sizeof(u32)) break; @@ -2386,7 +2386,7 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, } if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen)) err = -EFAULT; - netlink_table_ungrab(); + netlink_unlock_table(); break; } case NETLINK_CAP_ACK: diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index c6a39bf2c3b9..dba635d086b2 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -768,7 +768,6 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, const struct nlattr *actions, int actions_len) { - struct ip_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; @@ -796,11 +795,9 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, if (vport) { int err; - upcall.egress_tun_info = &info; - err = ovs_vport_get_egress_tun_info(vport, skb, - &upcall); - if (err) - upcall.egress_tun_info = NULL; + err = dev_fill_metadata_dst(vport->dev, skb); + if (!err) + upcall.egress_tun_info = skb_tunnel_info(skb); } break; @@ -1112,8 +1109,8 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, nla_data(a)); /* Hide stolen IP fragments from user space. */ - if (err == -EINPROGRESS) - return 0; + if (err) + return err == -EINPROGRESS ? 0 : err; break; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 80bf702715bb..50095820edb7 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -151,6 +151,8 @@ static void ovs_ct_update_key(const struct sk_buff *skb, ct = nf_ct_get(skb, &ctinfo); if (ct) { state = ovs_ct_get_state(ctinfo); + if (!nf_ct_is_confirmed(ct)) + state |= OVS_CS_F_NEW; if (ct->master) state |= OVS_CS_F_RELATED; zone = nf_ct_zone(ct); @@ -222,9 +224,6 @@ static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key, struct nf_conn *ct; int err; - if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) - return -ENOTSUPP; - /* The connection could be invalid, in which case set_label is no-op.*/ ct = nf_ct_get(skb, &ctinfo); if (!ct) @@ -294,6 +293,9 @@ static int ovs_ct_helper(struct sk_buff *skb, u16 proto) return helper->help(skb, protoff, ct, ctinfo); } +/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero + * value if 'skb' is freed. + */ static int handle_fragments(struct net *net, struct sw_flow_key *key, u16 zone, struct sk_buff *skb) { @@ -309,8 +311,8 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, return err; ovs_cb.mru = IPCB(skb)->frag_max_size; - } else if (key->eth.type == htons(ETH_P_IPV6)) { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + } else if (key->eth.type == htons(ETH_P_IPV6)) { enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; struct sk_buff *reasm; @@ -319,17 +321,25 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, if (!reasm) return -EINPROGRESS; - if (skb == reasm) + if (skb == reasm) { + kfree_skb(skb); return -EINVAL; + } + + /* Don't free 'skb' even though it is one of the original + * fragments, as we're going to morph it into the head. + */ + skb_get(skb); + nf_ct_frag6_consume_orig(reasm); key->ip.proto = ipv6_hdr(reasm)->nexthdr; skb_morph(skb, reasm); + skb->next = reasm->next; consume_skb(reasm); ovs_cb.mru = IP6CB(skb)->frag_max_size; -#else - return -EPFNOSUPPORT; #endif } else { + kfree_skb(skb); return -EPFNOSUPPORT; } @@ -377,7 +387,7 @@ static bool skb_nfct_cached(const struct net *net, const struct sk_buff *skb, return true; } -static int __ovs_ct_lookup(struct net *net, const struct sw_flow_key *key, +static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb) { @@ -408,6 +418,8 @@ static int __ovs_ct_lookup(struct net *net, const struct sw_flow_key *key, } } + ovs_ct_update_key(skb, key, true); + return 0; } @@ -430,8 +442,6 @@ static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key, err = __ovs_ct_lookup(net, key, info, skb); if (err) return err; - - ovs_ct_update_key(skb, key, true); } return 0; @@ -460,8 +470,6 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, if (nf_conntrack_confirm(skb) != NF_ACCEPT) return -EINVAL; - ovs_ct_update_key(skb, key, true); - return 0; } @@ -476,6 +484,9 @@ static bool labels_nonzero(const struct ovs_key_ct_labels *labels) return false; } +/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero + * value if 'skb' is freed. + */ int ovs_ct_execute(struct net *net, struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_conntrack_info *info) @@ -511,6 +522,8 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, &info->labels.mask); err: skb_push(skb, nh_ofs); + if (err) + kfree_skb(skb); return err; } @@ -587,6 +600,10 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, case OVS_CT_ATTR_MARK: { struct md_mark *mark = nla_data(a); + if (!mark->mask) { + OVS_NLERR(log, "ct_mark mask cannot be 0"); + return -EINVAL; + } info->mark = *mark; break; } @@ -595,6 +612,10 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, case OVS_CT_ATTR_LABELS: { struct md_labels *labels = nla_data(a); + if (!labels_nonzero(&labels->mask)) { + OVS_NLERR(log, "ct_labels mask cannot be 0"); + return -EINVAL; + } info->labels = *labels; break; } @@ -705,11 +726,12 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) return -EMSGSIZE; - if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && + if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && ct_info->mark.mask && nla_put(skb, OVS_CT_ATTR_MARK, sizeof(ct_info->mark), &ct_info->mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + labels_nonzero(&ct_info->labels.mask) && nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels), &ct_info->labels)) return -EMSGSIZE; diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index da8714942c95..a7544f405c16 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -35,12 +35,9 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb); void ovs_ct_free_action(const struct nlattr *a); -static inline bool ovs_ct_state_supported(u32 state) -{ - return !(state & ~(OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | - OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | - OVS_CS_F_INVALID | OVS_CS_F_TRACKED)); -} +#define CT_SUPPORTED_MASK (OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | \ + OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | \ + OVS_CS_F_INVALID | OVS_CS_F_TRACKED) #else #include <linux/errno.h> @@ -53,11 +50,6 @@ static inline bool ovs_ct_verify(struct net *net, int attr) return false; } -static inline bool ovs_ct_state_supported(u32 state) -{ - return false; -} - static inline int ovs_ct_copy_action(struct net *net, const struct nlattr *nla, const struct sw_flow_key *key, struct sw_flow_actions **acts, bool log) @@ -75,6 +67,7 @@ static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_conntrack_info *info) { + kfree_skb(skb); return -ENOTSUPP; } @@ -94,5 +87,7 @@ static inline int ovs_ct_put_key(const struct sw_flow_key *key, } static inline void ovs_ct_free_action(const struct nlattr *a) { } + +#define CT_SUPPORTED_MASK 0 #endif /* CONFIG_NF_CONNTRACK */ #endif /* ovs_conntrack.h */ diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index b816ff871528..c5d08ee37730 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -490,9 +490,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, if (upcall_info->egress_tun_info) { nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY); - err = ovs_nla_put_egress_tunnel_key(user_skb, - upcall_info->egress_tun_info, - upcall_info->egress_tun_opts); + err = ovs_nla_put_tunnel_info(user_skb, + upcall_info->egress_tun_info); BUG_ON(err); nla_nest_end(user_skb, nla); } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index f88038a99f44..67bdecd9fdc1 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -117,7 +117,6 @@ struct ovs_skb_cb { */ struct dp_upcall_info { struct ip_tunnel_info *egress_tun_info; - const void *egress_tun_opts; const struct nlattr *userdata; const struct nlattr *actions; int actions_len; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 171a691f1c32..38536c137c54 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -717,7 +717,7 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, if ((output->tun_flags & TUNNEL_OAM) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; - if (tun_opts) { + if (swkey_tun_opts_len) { if (output->tun_flags & TUNNEL_GENEVE_OPT && nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, swkey_tun_opts_len, tun_opts)) @@ -749,13 +749,12 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, return 0; } -int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb, - const struct ip_tunnel_info *egress_tun_info, - const void *egress_tun_opts) +int ovs_nla_put_tunnel_info(struct sk_buff *skb, + struct ip_tunnel_info *tun_info) { - return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key, - egress_tun_opts, - egress_tun_info->options_len); + return __ipv4_tun_to_nlattr(skb, &tun_info->key, + ip_tunnel_info_opts(tun_info), + tun_info->options_len); } static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, @@ -816,7 +815,7 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) { u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]); - if (!is_mask && !ovs_ct_state_supported(ct_state)) { + if (ct_state & ~CT_SUPPORTED_MASK) { OVS_NLERR(log, "ct_state flags %08x unsupported", ct_state); return -EINVAL; @@ -1099,6 +1098,9 @@ static void nlattr_set(struct nlattr *attr, u8 val, } else { memset(nla_data(nla), val, nla_len(nla)); } + + if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE) + *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK; } } @@ -2380,10 +2382,7 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) if (!start) return -EMSGSIZE; - err = ipv4_tun_to_nlattr(skb, &tun_info->key, - tun_info->options_len ? - ip_tunnel_info_opts(tun_info) : NULL, - tun_info->options_len); + err = ovs_nla_put_tunnel_info(skb, tun_info); if (err) return err; nla_nest_end(skb, start); diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 6ca3f0baf449..47dd142eca1c 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -55,9 +55,9 @@ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_get_match(struct net *, struct sw_flow_match *, const struct nlattr *key, const struct nlattr *mask, bool log); -int ovs_nla_put_egress_tunnel_key(struct sk_buff *, - const struct ip_tunnel_info *, - const void *egress_tun_opts); + +int ovs_nla_put_tunnel_info(struct sk_buff *skb, + struct ip_tunnel_info *tun_info); bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log); int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid, diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 2735e9c4a3b8..5f8aaaaa0785 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -52,18 +52,6 @@ static int geneve_get_options(const struct vport *vport, return 0; } -static int geneve_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - struct geneve_port *geneve_port = geneve_vport(vport); - struct net *net = ovs_dp_get_net(vport->dp); - __be16 dport = htons(geneve_port->port_no); - __be16 sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true); - - return ovs_tunnel_get_egress_info(upcall, ovs_dp_get_net(vport->dp), - skb, IPPROTO_UDP, sport, dport); -} - static struct vport *geneve_tnl_create(const struct vport_parms *parms) { struct net *net = ovs_dp_get_net(parms->dp); @@ -130,7 +118,6 @@ static struct vport_ops ovs_geneve_vport_ops = { .get_options = geneve_get_options, .send = ovs_netdev_send, .owner = THIS_MODULE, - .get_egress_tun_info = geneve_get_egress_tun_info, }; static int __init ovs_geneve_tnl_init(void) diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 4d24481669c9..64225bf5eb40 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -84,18 +84,10 @@ static struct vport *gre_create(const struct vport_parms *parms) return ovs_netdev_link(vport, parms->name); } -static int gre_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - return ovs_tunnel_get_egress_info(upcall, ovs_dp_get_net(vport->dp), - skb, IPPROTO_GRE, 0, 0); -} - static struct vport_ops ovs_gre_vport_ops = { .type = OVS_VPORT_TYPE_GRE, .create = gre_create, .send = ovs_netdev_send, - .get_egress_tun_info = gre_get_egress_tun_info, .destroy = ovs_netdev_tunnel_destroy, .owner = THIS_MODULE, }; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 388b8a6bf112..b3934126daa8 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -106,12 +106,45 @@ static void internal_dev_destructor(struct net_device *dev) free_netdev(dev); } +static struct rtnl_link_stats64 * +internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) +{ + int i; + + memset(stats, 0, sizeof(*stats)); + stats->rx_errors = dev->stats.rx_errors; + stats->tx_errors = dev->stats.tx_errors; + stats->tx_dropped = dev->stats.tx_dropped; + stats->rx_dropped = dev->stats.rx_dropped; + + for_each_possible_cpu(i) { + const struct pcpu_sw_netstats *percpu_stats; + struct pcpu_sw_netstats local_stats; + unsigned int start; + + percpu_stats = per_cpu_ptr(dev->tstats, i); + + do { + start = u64_stats_fetch_begin_irq(&percpu_stats->syncp); + local_stats = *percpu_stats; + } while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start)); + + stats->rx_bytes += local_stats.rx_bytes; + stats->rx_packets += local_stats.rx_packets; + stats->tx_bytes += local_stats.tx_bytes; + stats->tx_packets += local_stats.tx_packets; + } + + return stats; +} + static const struct net_device_ops internal_dev_netdev_ops = { .ndo_open = internal_dev_open, .ndo_stop = internal_dev_stop, .ndo_start_xmit = internal_dev_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = internal_dev_change_mtu, + .ndo_get_stats64 = internal_get_stats, }; static struct rtnl_link_ops internal_dev_link_ops __read_mostly = { @@ -161,6 +194,11 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) err = -ENOMEM; goto error_free_vport; } + vport->dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!vport->dev->tstats) { + err = -ENOMEM; + goto error_free_netdev; + } dev_net_set(vport->dev, ovs_dp_get_net(vport->dp)); internal_dev = internal_dev_priv(vport->dev); @@ -173,7 +211,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) rtnl_lock(); err = register_netdevice(vport->dev); if (err) - goto error_free_netdev; + goto error_unlock; dev_set_promiscuity(vport->dev, 1); rtnl_unlock(); @@ -181,8 +219,10 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) return vport; -error_free_netdev: +error_unlock: rtnl_unlock(); + free_percpu(vport->dev->tstats); +error_free_netdev: free_netdev(vport->dev); error_free_vport: ovs_vport_free(vport); @@ -198,7 +238,7 @@ static void internal_dev_destroy(struct vport *vport) /* unregister_netdevice() waits for an RCU grace period. */ unregister_netdevice(vport->dev); - + free_percpu(vport->dev->tstats); rtnl_unlock(); } diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index c11413d5075f..e1c9c0888037 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -146,31 +146,12 @@ static struct vport *vxlan_create(const struct vport_parms *parms) return ovs_netdev_link(vport, parms->name); } -static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - struct vxlan_dev *vxlan = netdev_priv(vport->dev); - struct net *net = ovs_dp_get_net(vport->dp); - __be16 dst_port = vxlan_dev_dst_port(vxlan); - __be16 src_port; - int port_min; - int port_max; - - inet_get_local_port_range(net, &port_min, &port_max); - src_port = udp_flow_src_port(net, skb, 0, 0, true); - - return ovs_tunnel_get_egress_info(upcall, net, - skb, IPPROTO_UDP, - src_port, dst_port); -} - static struct vport_ops ovs_vxlan_netdev_vport_ops = { .type = OVS_VPORT_TYPE_VXLAN, .create = vxlan_create, .destroy = ovs_netdev_tunnel_destroy, .get_options = vxlan_get_options, .send = ovs_netdev_send, - .get_egress_tun_info = vxlan_get_egress_tun_info, }; static int __init ovs_vxlan_tnl_init(void) diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 12a36ac21eda..320c765ce44a 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -479,61 +479,3 @@ void ovs_vport_deferred_free(struct vport *vport) call_rcu(&vport->rcu, free_vport_rcu); } EXPORT_SYMBOL_GPL(ovs_vport_deferred_free); - -int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall, - struct net *net, - struct sk_buff *skb, - u8 ipproto, - __be16 tp_src, - __be16 tp_dst) -{ - struct ip_tunnel_info *egress_tun_info = upcall->egress_tun_info; - const struct ip_tunnel_info *tun_info = skb_tunnel_info(skb); - const struct ip_tunnel_key *tun_key; - u32 skb_mark = skb->mark; - struct rtable *rt; - struct flowi4 fl; - - if (unlikely(!tun_info)) - return -EINVAL; - if (ip_tunnel_info_af(tun_info) != AF_INET) - return -EINVAL; - - tun_key = &tun_info->key; - - /* Route lookup to get srouce IP address. - * The process may need to be changed if the corresponding process - * in vports ops changed. - */ - rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto); - if (IS_ERR(rt)) - return PTR_ERR(rt); - - ip_rt_put(rt); - - /* Generate egress_tun_info based on tun_info, - * saddr, tp_src and tp_dst - */ - ip_tunnel_key_init(&egress_tun_info->key, - fl.saddr, tun_key->u.ipv4.dst, - tun_key->tos, - tun_key->ttl, - tp_src, tp_dst, - tun_key->tun_id, - tun_key->tun_flags); - egress_tun_info->options_len = tun_info->options_len; - egress_tun_info->mode = tun_info->mode; - upcall->egress_tun_opts = ip_tunnel_info_opts(egress_tun_info); - return 0; -} -EXPORT_SYMBOL_GPL(ovs_tunnel_get_egress_info); - -int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall) -{ - /* get_egress_tun_info() is only implemented on tunnel ports. */ - if (unlikely(!vport->ops->get_egress_tun_info)) - return -EINVAL; - - return vport->ops->get_egress_tun_info(vport, skb, upcall); -} diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index a413f3ae6a7b..d341ad6f3afe 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -27,7 +27,6 @@ #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/u64_stats_sync.h> -#include <net/route.h> #include "datapath.h" @@ -53,16 +52,6 @@ int ovs_vport_set_upcall_portids(struct vport *, const struct nlattr *pids); int ovs_vport_get_upcall_portids(const struct vport *, struct sk_buff *); u32 ovs_vport_find_upcall_portid(const struct vport *, struct sk_buff *); -int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall, - struct net *net, - struct sk_buff *, - u8 ipproto, - __be16 tp_src, - __be16 tp_dst); - -int ovs_vport_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, - struct dp_upcall_info *upcall); - /** * struct vport_portids - array of netlink portids of a vport. * must be protected by rcu. @@ -140,8 +129,6 @@ struct vport_parms { * have any configuration. * @send: Send a packet on the device. * zero for dropped packets or negative for error. - * @get_egress_tun_info: Get the egress tunnel 5-tuple and other info for - * a packet. */ struct vport_ops { enum ovs_vport_type type; @@ -154,9 +141,6 @@ struct vport_ops { int (*get_options)(const struct vport *, struct sk_buff *); void (*send)(struct vport *, struct sk_buff *); - int (*get_egress_tun_info)(struct vport *, struct sk_buff *, - struct dp_upcall_info *upcall); - struct module *owner; struct list_head list; }; @@ -215,25 +199,6 @@ static inline const char *ovs_vport_name(struct vport *vport) int ovs_vport_ops_register(struct vport_ops *ops); void ovs_vport_ops_unregister(struct vport_ops *ops); -static inline struct rtable *ovs_tunnel_route_lookup(struct net *net, - const struct ip_tunnel_key *key, - u32 mark, - struct flowi4 *fl, - u8 protocol) -{ - struct rtable *rt; - - memset(fl, 0, sizeof(*fl)); - fl->daddr = key->u.ipv4.dst; - fl->saddr = key->u.ipv4.src; - fl->flowi4_tos = RT_TOS(key->tos); - fl->flowi4_mark = mark; - fl->flowi4_proto = protocol; - - rt = ip_route_output_key(net, fl); - return rt; -} - static inline void ovs_vport_send(struct vport *vport, struct sk_buff *skb) { vport->ops->send(vport, skb); diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index fbc5ef88bc0e..27a992154804 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -214,8 +214,15 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb, } to_copy = min(tc->t_tinc_data_rem, left); - pskb_pull(clone, offset); - pskb_trim(clone, to_copy); + if (!pskb_pull(clone, offset) || + pskb_trim(clone, to_copy)) { + pr_warn("rds_tcp_data_recv: pull/trim failed " + "left %zu data_rem %zu skb_len %d\n", + left, tc->t_tinc_data_rem, skb->len); + kfree_skb(clone); + desc->error = -ENOMEM; + goto out; + } skb_queue_tail(&tinc->ti_skb_list, clone); rdsdebug("skb %p data %p len %d off %u to_copy %zu -> " diff --git a/net/sysctl_net.c b/net/sysctl_net.c index e7000be321b0..ed98c1fc3de1 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -94,10 +94,14 @@ __init int net_sysctl_init(void) goto out; ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) - goto out; + goto out1; register_sysctl_root(&net_sysctl_root); out: return ret; +out1: + unregister_sysctl_table(net_header); + net_header = NULL; + goto out; } struct ctl_table_header *register_net_sysctl(struct net *net, diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 41042de3ae9b..eadba62afa85 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -42,7 +42,8 @@ #include "core.h" #define MAX_PKT_DEFAULT_MCAST 1500 /* bcast link max packet size (fixed) */ -#define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */ +#define BCLINK_WIN_DEFAULT 50 /* bcast link window size (default) */ +#define BCLINK_WIN_MIN 32 /* bcast minimum link window size */ const char tipc_bclink_name[] = "broadcast-link"; @@ -908,9 +909,10 @@ int tipc_bclink_set_queue_limits(struct net *net, u32 limit) if (!bcl) return -ENOPROTOOPT; - if ((limit < TIPC_MIN_LINK_WIN) || (limit > TIPC_MAX_LINK_WIN)) + if (limit < BCLINK_WIN_MIN) + limit = BCLINK_WIN_MIN; + if (limit > TIPC_MAX_LINK_WIN) return -EINVAL; - tipc_bclink_lock(net); tipc_link_set_queue_limits(bcl, limit); tipc_bclink_unlock(net); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index c5ac436235e0..5f73450159df 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -121,7 +121,7 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) { struct sk_buff *head = *headbuf; struct sk_buff *frag = *buf; - struct sk_buff *tail; + struct sk_buff *tail = NULL; struct tipc_msg *msg; u32 fragid; int delta; @@ -141,9 +141,15 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (unlikely(skb_unclone(frag, GFP_ATOMIC))) goto err; head = *headbuf = frag; - skb_frag_list_init(head); - TIPC_SKB_CB(head)->tail = NULL; *buf = NULL; + TIPC_SKB_CB(head)->tail = NULL; + if (skb_is_nonlinear(head)) { + skb_walk_frags(head, tail) { + TIPC_SKB_CB(head)->tail = tail; + } + } else { + skb_frag_list_init(head); + } return 0; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index c170d3138953..6e648d90297a 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -52,6 +52,8 @@ /* IANA assigned UDP port */ #define UDP_PORT_DEFAULT 6118 +#define UDP_MIN_HEADROOM 28 + static const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = { [TIPC_NLA_UDP_UNSPEC] = {.type = NLA_UNSPEC}, [TIPC_NLA_UDP_LOCAL] = {.type = NLA_BINARY, @@ -156,6 +158,9 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb, struct sk_buff *clone; struct rtable *rt; + if (skb_headroom(skb) < UDP_MIN_HEADROOM) + pskb_expand_head(skb, UDP_MIN_HEADROOM, 0, GFP_ATOMIC); + clone = skb_clone(skb, GFP_ATOMIC); skb_set_inner_protocol(clone, htons(ETH_P_TIPC)); ub = rcu_dereference_rtnl(b->media_ptr); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index df5fc6b340f1..00e8a349aabc 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1948,13 +1948,13 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner) err = misc_register(&vsock_device); if (err) { pr_err("Failed to register misc device\n"); - return -ENOENT; + goto err_reset_transport; } err = proto_register(&vsock_proto, 1); /* we want our slab */ if (err) { pr_err("Cannot register vsock protocol\n"); - goto err_misc_deregister; + goto err_deregister_misc; } err = sock_register(&vsock_family_ops); @@ -1969,8 +1969,9 @@ int __vsock_core_init(const struct vsock_transport *t, struct module *owner) err_unregister_proto: proto_unregister(&vsock_proto); -err_misc_deregister: +err_deregister_misc: misc_deregister(&vsock_device); +err_reset_transport: transport = NULL; err_busy: mutex_unlock(&vsock_register_mutex); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 1f63daff3965..7555cad83a75 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -40,13 +40,11 @@ static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg); static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg); -static void vmci_transport_peer_attach_cb(u32 sub_id, - const struct vmci_event_data *ed, - void *client_data); static void vmci_transport_peer_detach_cb(u32 sub_id, const struct vmci_event_data *ed, void *client_data); static void vmci_transport_recv_pkt_work(struct work_struct *work); +static void vmci_transport_cleanup(struct work_struct *work); static int vmci_transport_recv_listen(struct sock *sk, struct vmci_transport_packet *pkt); static int vmci_transport_recv_connecting_server( @@ -75,6 +73,10 @@ struct vmci_transport_recv_pkt_info { struct vmci_transport_packet pkt; }; +static LIST_HEAD(vmci_transport_cleanup_list); +static DEFINE_SPINLOCK(vmci_transport_cleanup_lock); +static DECLARE_WORK(vmci_transport_cleanup_work, vmci_transport_cleanup); + static struct vmci_handle vmci_transport_stream_handle = { VMCI_INVALID_ID, VMCI_INVALID_ID }; static u32 vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID; @@ -791,44 +793,6 @@ out: return err; } -static void vmci_transport_peer_attach_cb(u32 sub_id, - const struct vmci_event_data *e_data, - void *client_data) -{ - struct sock *sk = client_data; - const struct vmci_event_payload_qp *e_payload; - struct vsock_sock *vsk; - - e_payload = vmci_event_data_const_payload(e_data); - - vsk = vsock_sk(sk); - - /* We don't ask for delayed CBs when we subscribe to this event (we - * pass 0 as flags to vmci_event_subscribe()). VMCI makes no - * guarantees in that case about what context we might be running in, - * so it could be BH or process, blockable or non-blockable. So we - * need to account for all possible contexts here. - */ - local_bh_disable(); - bh_lock_sock(sk); - - /* XXX This is lame, we should provide a way to lookup sockets by - * qp_handle. - */ - if (vmci_handle_is_equal(vmci_trans(vsk)->qp_handle, - e_payload->handle)) { - /* XXX This doesn't do anything, but in the future we may want - * to set a flag here to verify the attach really did occur and - * we weren't just sent a datagram claiming it was. - */ - goto out; - } - -out: - bh_unlock_sock(sk); - local_bh_enable(); -} - static void vmci_transport_handle_detach(struct sock *sk) { struct vsock_sock *vsk; @@ -871,28 +835,38 @@ static void vmci_transport_peer_detach_cb(u32 sub_id, const struct vmci_event_data *e_data, void *client_data) { - struct sock *sk = client_data; + struct vmci_transport *trans = client_data; const struct vmci_event_payload_qp *e_payload; - struct vsock_sock *vsk; e_payload = vmci_event_data_const_payload(e_data); - vsk = vsock_sk(sk); - if (vmci_handle_is_invalid(e_payload->handle)) - return; - - /* Same rules for locking as for peer_attach_cb(). */ - local_bh_disable(); - bh_lock_sock(sk); /* XXX This is lame, we should provide a way to lookup sockets by * qp_handle. */ - if (vmci_handle_is_equal(vmci_trans(vsk)->qp_handle, - e_payload->handle)) - vmci_transport_handle_detach(sk); + if (vmci_handle_is_invalid(e_payload->handle) || + vmci_handle_is_equal(trans->qp_handle, e_payload->handle)) + return; - bh_unlock_sock(sk); - local_bh_enable(); + /* We don't ask for delayed CBs when we subscribe to this event (we + * pass 0 as flags to vmci_event_subscribe()). VMCI makes no + * guarantees in that case about what context we might be running in, + * so it could be BH or process, blockable or non-blockable. So we + * need to account for all possible contexts here. + */ + spin_lock_bh(&trans->lock); + if (!trans->sk) + goto out; + + /* Apart from here, trans->lock is only grabbed as part of sk destruct, + * where trans->sk isn't locked. + */ + bh_lock_sock(trans->sk); + + vmci_transport_handle_detach(trans->sk); + + bh_unlock_sock(trans->sk); + out: + spin_unlock_bh(&trans->lock); } static void vmci_transport_qp_resumed_cb(u32 sub_id, @@ -1181,7 +1155,7 @@ vmci_transport_recv_connecting_server(struct sock *listener, */ err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH, vmci_transport_peer_detach_cb, - pending, &detach_sub_id); + vmci_trans(vpending), &detach_sub_id); if (err < VMCI_SUCCESS) { vmci_transport_send_reset(pending, pkt); err = vmci_transport_error_to_vsock_error(err); @@ -1321,7 +1295,6 @@ vmci_transport_recv_connecting_client(struct sock *sk, || vmci_trans(vsk)->qpair || vmci_trans(vsk)->produce_size != 0 || vmci_trans(vsk)->consume_size != 0 - || vmci_trans(vsk)->attach_sub_id != VMCI_INVALID_ID || vmci_trans(vsk)->detach_sub_id != VMCI_INVALID_ID) { skerr = EPROTO; err = -EINVAL; @@ -1389,7 +1362,6 @@ static int vmci_transport_recv_connecting_client_negotiate( struct vsock_sock *vsk; struct vmci_handle handle; struct vmci_qp *qpair; - u32 attach_sub_id; u32 detach_sub_id; bool is_local; u32 flags; @@ -1399,7 +1371,6 @@ static int vmci_transport_recv_connecting_client_negotiate( vsk = vsock_sk(sk); handle = VMCI_INVALID_HANDLE; - attach_sub_id = VMCI_INVALID_ID; detach_sub_id = VMCI_INVALID_ID; /* If we have gotten here then we should be past the point where old @@ -1444,23 +1415,15 @@ static int vmci_transport_recv_connecting_client_negotiate( goto destroy; } - /* Subscribe to attach and detach events first. + /* Subscribe to detach events first. * * XXX We attach once for each queue pair created for now so it is easy * to find the socket (it's provided), but later we should only * subscribe once and add a way to lookup sockets by queue pair handle. */ - err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_ATTACH, - vmci_transport_peer_attach_cb, - sk, &attach_sub_id); - if (err < VMCI_SUCCESS) { - err = vmci_transport_error_to_vsock_error(err); - goto destroy; - } - err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH, vmci_transport_peer_detach_cb, - sk, &detach_sub_id); + vmci_trans(vsk), &detach_sub_id); if (err < VMCI_SUCCESS) { err = vmci_transport_error_to_vsock_error(err); goto destroy; @@ -1496,7 +1459,6 @@ static int vmci_transport_recv_connecting_client_negotiate( vmci_trans(vsk)->produce_size = vmci_trans(vsk)->consume_size = pkt->u.size; - vmci_trans(vsk)->attach_sub_id = attach_sub_id; vmci_trans(vsk)->detach_sub_id = detach_sub_id; vmci_trans(vsk)->notify_ops->process_negotiate(sk); @@ -1504,9 +1466,6 @@ static int vmci_transport_recv_connecting_client_negotiate( return 0; destroy: - if (attach_sub_id != VMCI_INVALID_ID) - vmci_event_unsubscribe(attach_sub_id); - if (detach_sub_id != VMCI_INVALID_ID) vmci_event_unsubscribe(detach_sub_id); @@ -1607,9 +1566,11 @@ static int vmci_transport_socket_init(struct vsock_sock *vsk, vmci_trans(vsk)->qp_handle = VMCI_INVALID_HANDLE; vmci_trans(vsk)->qpair = NULL; vmci_trans(vsk)->produce_size = vmci_trans(vsk)->consume_size = 0; - vmci_trans(vsk)->attach_sub_id = vmci_trans(vsk)->detach_sub_id = - VMCI_INVALID_ID; + vmci_trans(vsk)->detach_sub_id = VMCI_INVALID_ID; vmci_trans(vsk)->notify_ops = NULL; + INIT_LIST_HEAD(&vmci_trans(vsk)->elem); + vmci_trans(vsk)->sk = &vsk->sk; + spin_lock_init(&vmci_trans(vsk)->lock); if (psk) { vmci_trans(vsk)->queue_pair_size = vmci_trans(psk)->queue_pair_size; @@ -1629,29 +1590,57 @@ static int vmci_transport_socket_init(struct vsock_sock *vsk, return 0; } -static void vmci_transport_destruct(struct vsock_sock *vsk) +static void vmci_transport_free_resources(struct list_head *transport_list) { - if (vmci_trans(vsk)->attach_sub_id != VMCI_INVALID_ID) { - vmci_event_unsubscribe(vmci_trans(vsk)->attach_sub_id); - vmci_trans(vsk)->attach_sub_id = VMCI_INVALID_ID; - } + while (!list_empty(transport_list)) { + struct vmci_transport *transport = + list_first_entry(transport_list, struct vmci_transport, + elem); + list_del(&transport->elem); - if (vmci_trans(vsk)->detach_sub_id != VMCI_INVALID_ID) { - vmci_event_unsubscribe(vmci_trans(vsk)->detach_sub_id); - vmci_trans(vsk)->detach_sub_id = VMCI_INVALID_ID; - } + if (transport->detach_sub_id != VMCI_INVALID_ID) { + vmci_event_unsubscribe(transport->detach_sub_id); + transport->detach_sub_id = VMCI_INVALID_ID; + } - if (!vmci_handle_is_invalid(vmci_trans(vsk)->qp_handle)) { - vmci_qpair_detach(&vmci_trans(vsk)->qpair); - vmci_trans(vsk)->qp_handle = VMCI_INVALID_HANDLE; - vmci_trans(vsk)->produce_size = 0; - vmci_trans(vsk)->consume_size = 0; + if (!vmci_handle_is_invalid(transport->qp_handle)) { + vmci_qpair_detach(&transport->qpair); + transport->qp_handle = VMCI_INVALID_HANDLE; + transport->produce_size = 0; + transport->consume_size = 0; + } + + kfree(transport); } +} + +static void vmci_transport_cleanup(struct work_struct *work) +{ + LIST_HEAD(pending); + + spin_lock_bh(&vmci_transport_cleanup_lock); + list_replace_init(&vmci_transport_cleanup_list, &pending); + spin_unlock_bh(&vmci_transport_cleanup_lock); + vmci_transport_free_resources(&pending); +} + +static void vmci_transport_destruct(struct vsock_sock *vsk) +{ + /* Ensure that the detach callback doesn't use the sk/vsk + * we are about to destruct. + */ + spin_lock_bh(&vmci_trans(vsk)->lock); + vmci_trans(vsk)->sk = NULL; + spin_unlock_bh(&vmci_trans(vsk)->lock); if (vmci_trans(vsk)->notify_ops) vmci_trans(vsk)->notify_ops->socket_destruct(vsk); - kfree(vsk->trans); + spin_lock_bh(&vmci_transport_cleanup_lock); + list_add(&vmci_trans(vsk)->elem, &vmci_transport_cleanup_list); + spin_unlock_bh(&vmci_transport_cleanup_lock); + schedule_work(&vmci_transport_cleanup_work); + vsk->trans = NULL; } @@ -2146,6 +2135,9 @@ module_init(vmci_transport_init); static void __exit vmci_transport_exit(void) { + cancel_work_sync(&vmci_transport_cleanup_work); + vmci_transport_free_resources(&vmci_transport_cleanup_list); + if (!vmci_handle_is_invalid(vmci_transport_stream_handle)) { if (vmci_datagram_destroy_handle( vmci_transport_stream_handle) != VMCI_SUCCESS) @@ -2164,6 +2156,7 @@ module_exit(vmci_transport_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMCI transport for Virtual Sockets"); +MODULE_VERSION("1.0.2.0-k"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("vmware_vsock"); MODULE_ALIAS_NETPROTO(PF_VSOCK); diff --git a/net/vmw_vsock/vmci_transport.h b/net/vmw_vsock/vmci_transport.h index ce6c9623d5f0..2ad46f39649f 100644 --- a/net/vmw_vsock/vmci_transport.h +++ b/net/vmw_vsock/vmci_transport.h @@ -119,10 +119,12 @@ struct vmci_transport { u64 queue_pair_size; u64 queue_pair_min_size; u64 queue_pair_max_size; - u32 attach_sub_id; u32 detach_sub_id; union vmci_transport_notify notify; struct vmci_transport_notify_ops *notify_ops; + struct list_head elem; + struct sock *sk; + spinlock_t lock; /* protects sk. */ }; int vmci_transport_register(void); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index a8de9e300200..24e06a2377f6 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1928,8 +1928,10 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr *rp = attrs[XFRMA_REPLAY_VAL]; struct nlattr *re = attrs[XFRMA_REPLAY_ESN_VAL]; struct nlattr *lt = attrs[XFRMA_LTIME_VAL]; + struct nlattr *et = attrs[XFRMA_ETIMER_THRESH]; + struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; - if (!lt && !rp && !re) + if (!lt && !rp && !re && !et && !rt) return err; /* pedantic mode - thou shalt sayeth replaceth */ diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 3a44d3a272af..af44e564d6dd 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -86,5 +86,17 @@ static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flag #define PT_REGS_RC(x) ((x)->gprs[2]) #define PT_REGS_SP(x) ((x)->gprs[15]) +#elif defined(__aarch64__) + +#define PT_REGS_PARM1(x) ((x)->regs[0]) +#define PT_REGS_PARM2(x) ((x)->regs[1]) +#define PT_REGS_PARM3(x) ((x)->regs[2]) +#define PT_REGS_PARM4(x) ((x)->regs[3]) +#define PT_REGS_PARM5(x) ((x)->regs[4]) +#define PT_REGS_RET(x) ((x)->regs[30]) +#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_RC(x) ((x)->regs[0]) +#define PT_REGS_SP(x) ((x)->sp) + #endif #endif |