diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-10-21 15:36:50 -1000 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-10-21 15:36:50 -1000 |
| commit | 6c2c712767ee1d74b2234c9caaf1920808333be6 (patch) | |
| tree | 44e4c0a6277d2d6633eff71c5f1d8aec9bebd512 | |
| parent | 0a3221b65874b5089f1742de59ef89f032b9f2ea (diff) | |
| parent | 397430b50a363d8b7bdda00522123f82df6adc5e (diff) | |
| download | linux-6c2c712767ee1d74b2234c9caaf1920808333be6.tar.bz2 | |
Merge tag 'net-5.15-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from netfilter, and can.
We'll have one more fix for a socket accounting regression, it's still
getting polished. Otherwise things look fine.
Current release - regressions:
- revert "vrf: reset skb conntrack connection on VRF rcv", there are
valid uses for previous behavior
- can: m_can: fix iomap_read_fifo() and iomap_write_fifo()
Current release - new code bugs:
- mlx5: e-switch, return correct error code on group creation failure
Previous releases - regressions:
- sctp: fix transport encap_port update in sctp_vtag_verify
- stmmac: fix E2E delay mechanism (in PTP timestamping)
Previous releases - always broken:
- netfilter: ip6t_rt: fix out-of-bounds read of ipv6_rt_hdr
- netfilter: xt_IDLETIMER: fix out-of-bound read caused by lack of
init
- netfilter: ipvs: make global sysctl read-only in non-init netns
- tcp: md5: fix selection between vrf and non-vrf keys
- ipv6: count rx stats on the orig netdev when forwarding
- bridge: mcast: use multicast_membership_interval for IGMPv3
- can:
- j1939: fix UAF for rx_kref of j1939_priv abort sessions on
receiving bad messages
- isotp: fix TX buffer concurrent access in isotp_sendmsg() fix
return error on FC timeout on TX path
- ice: fix re-init of RDMA Tx queues and crash if RDMA was not inited
- hns3: schedule the polling again when allocation fails, prevent
stalls
- drivers: add missing of_node_put() when aborting
for_each_available_child_of_node()
- ptp: fix possible memory leak and UAF in ptp_clock_register()
- e1000e: fix packet loss in burst mode on Tiger Lake and later
- mlx5e: ipsec: fix more checksum offload issues"
* tag 'net-5.15-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (75 commits)
usbnet: sanity check for maxpacket
net: enetc: make sure all traffic classes can send large frames
net: enetc: fix ethtool counter name for PM0_TERR
ptp: free 'vclock_index' in ptp_clock_release()
sfc: Don't use netif_info before net_device setup
sfc: Export fibre-specific supported link modes
net/mlx5e: IPsec: Fix work queue entry ethernet segment checksum flags
net/mlx5e: IPsec: Fix a misuse of the software parser's fields
net/mlx5e: Fix vlan data lost during suspend flow
net/mlx5: E-switch, Return correct error code on group creation failure
net/mlx5: Lag, change multipath and bonding to be mutually exclusive
ice: Add missing E810 device ids
igc: Update I226_K device ID
e1000e: Fix packet loss on Tiger Lake and later
e1000e: Separate TGP board type from SPT
ptp: Fix possible memory leak in ptp_clock_register()
net: stmmac: Fix E2E delay mechanism
nfc: st95hf: Make spi remove() callback return zero
net: hns3: disable sriov before unload hclge layer
net: hns3: fix vf reset workqueue cannot exit
...
92 files changed, 913 insertions, 301 deletions
diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index a432dc419fa4..5d97cee9457b 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -30,10 +30,11 @@ The ``ice`` driver reports the following versions PHY, link, etc. * - ``fw.mgmt.api`` - running - - 1.5 - - 2-digit version number of the API exported over the AdminQ by the - management firmware. Used by the driver to identify what commands - are supported. + - 1.5.1 + - 3-digit version number (major.minor.patch) of the API exported over + the AdminQ by the management firmware. Used by the driver to + identify what commands are supported. Historical versions of the + kernel only displayed a 2-digit version number (major.minor). * - ``fw.mgmt.build`` - running - 0x305d955f diff --git a/Documentation/networking/mctp.rst b/Documentation/networking/mctp.rst index 6100cdc220f6..fa7730dbf7b9 100644 --- a/Documentation/networking/mctp.rst +++ b/Documentation/networking/mctp.rst @@ -59,11 +59,11 @@ specified with a ``sockaddr`` type, with a single-byte endpoint address: }; struct sockaddr_mctp { - unsigned short int smctp_family; - int smctp_network; - struct mctp_addr smctp_addr; - __u8 smctp_type; - __u8 smctp_tag; + __kernel_sa_family_t smctp_family; + unsigned int smctp_network; + struct mctp_addr smctp_addr; + __u8 smctp_type; + __u8 smctp_tag; }; #define MCTP_NET_ANY 0x0 diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index e501cb03f211..bd087cca1c1d 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -1994,14 +1994,14 @@ setup_hw(struct hfc_pci *hc) pci_set_master(hc->pdev); if (!hc->irq) { printk(KERN_WARNING "HFC-PCI: No IRQ for PCI card found\n"); - return 1; + return -EINVAL; } hc->hw.pci_io = (char __iomem *)(unsigned long)hc->pdev->resource[1].start; if (!hc->hw.pci_io) { printk(KERN_WARNING "HFC-PCI: No IO-Mem for PCI card found\n"); - return 1; + return -ENOMEM; } /* Allocate memory for FIFOS */ /* the memory needs to be on a 32k boundary within the first 4G */ @@ -2012,7 +2012,7 @@ setup_hw(struct hfc_pci *hc) if (!buffer) { printk(KERN_WARNING "HFC-PCI: Error allocating memory for FIFO!\n"); - return 1; + return -ENOMEM; } hc->hw.fifos = buffer; pci_write_config_dword(hc->pdev, 0x80, hc->hw.dmahandle); @@ -2022,7 +2022,7 @@ setup_hw(struct hfc_pci *hc) "HFC-PCI: Error in ioremap for PCI!\n"); dma_free_coherent(&hc->pdev->dev, 0x8000, hc->hw.fifos, hc->hw.dmahandle); - return 1; + return -ENOMEM; } printk(KERN_INFO diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c index 308d4f2fff00..eee47bad0592 100644 --- a/drivers/net/can/m_can/m_can_platform.c +++ b/drivers/net/can/m_can/m_can_platform.c @@ -32,8 +32,13 @@ static u32 iomap_read_reg(struct m_can_classdev *cdev, int reg) static int iomap_read_fifo(struct m_can_classdev *cdev, int offset, void *val, size_t val_count) { struct m_can_plat_priv *priv = cdev_to_priv(cdev); + void __iomem *src = priv->mram_base + offset; - ioread32_rep(priv->mram_base + offset, val, val_count); + while (val_count--) { + *(unsigned int *)val = ioread32(src); + val += 4; + src += 4; + } return 0; } @@ -51,8 +56,13 @@ static int iomap_write_fifo(struct m_can_classdev *cdev, int offset, const void *val, size_t val_count) { struct m_can_plat_priv *priv = cdev_to_priv(cdev); + void __iomem *dst = priv->mram_base + offset; - iowrite32_rep(priv->base + offset, val, val_count); + while (val_count--) { + iowrite32(*(unsigned int *)val, dst); + val += 4; + dst += 4; + } return 0; } diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index 00e4533c8bdd..8999ec9455ec 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -846,10 +846,12 @@ static int __maybe_unused rcar_can_suspend(struct device *dev) struct rcar_can_priv *priv = netdev_priv(ndev); u16 ctlr; - if (netif_running(ndev)) { - netif_stop_queue(ndev); - netif_device_detach(ndev); - } + if (!netif_running(ndev)) + return 0; + + netif_stop_queue(ndev); + netif_device_detach(ndev); + ctlr = readw(&priv->regs->ctlr); ctlr |= RCAR_CAN_CTLR_CANM_HALT; writew(ctlr, &priv->regs->ctlr); @@ -868,6 +870,9 @@ static int __maybe_unused rcar_can_resume(struct device *dev) u16 ctlr; int err; + if (!netif_running(ndev)) + return 0; + err = clk_enable(priv->clk); if (err) { netdev_err(ndev, "clk_enable() failed, error %d\n", err); @@ -881,10 +886,9 @@ static int __maybe_unused rcar_can_resume(struct device *dev) writew(ctlr, &priv->regs->ctlr); priv->can.state = CAN_STATE_ERROR_ACTIVE; - if (netif_running(ndev)) { - netif_device_attach(ndev); - netif_start_queue(ndev); - } + netif_device_attach(ndev); + netif_start_queue(ndev); + return 0; } diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c index 6db90dc4bc9d..84f34020aafb 100644 --- a/drivers/net/can/sja1000/peak_pci.c +++ b/drivers/net/can/sja1000/peak_pci.c @@ -752,16 +752,15 @@ static void peak_pci_remove(struct pci_dev *pdev) struct net_device *prev_dev = chan->prev_dev; dev_info(&pdev->dev, "removing device %s\n", dev->name); + /* do that only for first channel */ + if (!prev_dev && chan->pciec_card) + peak_pciec_remove(chan->pciec_card); unregister_sja1000dev(dev); free_sja1000dev(dev); dev = prev_dev; - if (!dev) { - /* do that only for first channel */ - if (chan->pciec_card) - peak_pciec_remove(chan->pciec_card); + if (!dev) break; - } priv = netdev_priv(dev); chan = priv->priv; } diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index b11eabad575b..09029a3bad1a 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -551,11 +551,10 @@ static int pcan_usb_fd_decode_status(struct pcan_usb_fd_if *usb_if, } else if (sm->channel_p_w_b & PUCAN_BUS_WARNING) { new_state = CAN_STATE_ERROR_WARNING; } else { - /* no error bit (so, no error skb, back to active state) */ - dev->can.state = CAN_STATE_ERROR_ACTIVE; + /* back to (or still in) ERROR_ACTIVE state */ + new_state = CAN_STATE_ERROR_ACTIVE; pdev->bec.txerr = 0; pdev->bec.rxerr = 0; - return 0; } /* state hasn't changed */ @@ -568,8 +567,7 @@ static int pcan_usb_fd_decode_status(struct pcan_usb_fd_if *usb_if, /* allocate an skb to store the error frame */ skb = alloc_can_err_skb(netdev, &cf); - if (skb) - can_change_state(netdev, cf, tx_state, rx_state); + can_change_state(netdev, cf, tx_state, rx_state); /* things must be done even in case of OOM */ if (new_state == CAN_STATE_BUS_OFF) diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 3ff4b7e177f3..dbd4486a173f 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -230,7 +230,7 @@ #define GSWIP_SDMA_PCTRLp(p) (0xBC0 + ((p) * 0x6)) #define GSWIP_SDMA_PCTRL_EN BIT(0) /* SDMA Port Enable */ #define GSWIP_SDMA_PCTRL_FCEN BIT(1) /* Flow Control Enable */ -#define GSWIP_SDMA_PCTRL_PAUFWD BIT(1) /* Pause Frame Forwarding */ +#define GSWIP_SDMA_PCTRL_PAUFWD BIT(3) /* Pause Frame Forwarding */ #define GSWIP_TABLE_ACTIVE_VLAN 0x01 #define GSWIP_TABLE_VLAN_MAPPING 0x02 diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 094737e5084a..9890672a206d 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1035,9 +1035,6 @@ mt7530_port_enable(struct dsa_switch *ds, int port, { struct mt7530_priv *priv = ds->priv; - if (!dsa_is_user_port(ds, port)) - return 0; - mutex_lock(&priv->reg_mutex); /* Allow the user port gets connected to the cpu port and also @@ -1060,9 +1057,6 @@ mt7530_port_disable(struct dsa_switch *ds, int port) { struct mt7530_priv *priv = ds->priv; - if (!dsa_is_user_port(ds, port)) - return; - mutex_lock(&priv->reg_mutex); /* Clear up all port matrix which could be restored in the next @@ -3211,7 +3205,7 @@ mt7530_probe(struct mdio_device *mdiodev) return -ENOMEM; priv->ds->dev = &mdiodev->dev; - priv->ds->num_ports = DSA_MAX_PORTS; + priv->ds->num_ports = MT7530_NUM_PORTS; /* Use medatek,mcm property to distinguish hardware type that would * casues a little bit differences on power-on sequence. diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 691e1475d55e..0fbecd093fa1 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -1193,7 +1193,7 @@ static int nic_register_interrupts(struct nicpf *nic) dev_err(&nic->pdev->dev, "Request for #%d msix vectors failed, returned %d\n", nic->num_vec, ret); - return 1; + return ret; } /* Register mailbox interrupt handler */ diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index d1667b759522..a27227aeae88 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1224,7 +1224,7 @@ static int nicvf_register_misc_interrupt(struct nicvf *nic) if (ret < 0) { netdev_err(nic->netdev, "Req for #%d msix vectors failed\n", nic->num_vec); - return 1; + return ret; } sprintf(nic->irq_name[irq], "%s Mbox", "NICVF"); @@ -1243,7 +1243,7 @@ static int nicvf_register_misc_interrupt(struct nicvf *nic) if (!nicvf_check_pf_ready(nic)) { nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0); nicvf_unregister_interrupts(nic); - return 1; + return -EIO; } return 0; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index 9690e36e9e85..910b9f722504 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -157,7 +157,7 @@ static const struct { { ENETC_PM0_TFRM, "MAC tx frames" }, { ENETC_PM0_TFCS, "MAC tx fcs errors" }, { ENETC_PM0_TVLAN, "MAC tx VLAN frames" }, - { ENETC_PM0_TERR, "MAC tx frames" }, + { ENETC_PM0_TERR, "MAC tx frame errors" }, { ENETC_PM0_TUCA, "MAC tx unicast frames" }, { ENETC_PM0_TMCA, "MAC tx multicast frames" }, { ENETC_PM0_TBCA, "MAC tx broadcast frames" }, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 4c977dfc44f0..d522bd5c90b4 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -517,10 +517,13 @@ static void enetc_port_si_configure(struct enetc_si *si) static void enetc_configure_port_mac(struct enetc_hw *hw) { + int tc; + enetc_port_wr(hw, ENETC_PM0_MAXFRM, ENETC_SET_MAXFRM(ENETC_RX_MAXFRM_SIZE)); - enetc_port_wr(hw, ENETC_PTCMSDUR(0), ENETC_MAC_MAXFRM_SIZE); + for (tc = 0; tc < 8; tc++) + enetc_port_wr(hw, ENETC_PTCMSDUR(tc), ENETC_MAC_MAXFRM_SIZE); enetc_port_wr(hw, ENETC_PM0_CMD_CFG, ENETC_PM0_CMD_PHY_TX_EN | ENETC_PM0_CMD_TXP | ENETC_PM0_PROMISC); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index eef1b2764d34..67b0bf310daa 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -10,6 +10,27 @@ static LIST_HEAD(hnae3_ae_algo_list); static LIST_HEAD(hnae3_client_list); static LIST_HEAD(hnae3_ae_dev_list); +void hnae3_unregister_ae_algo_prepare(struct hnae3_ae_algo *ae_algo) +{ + const struct pci_device_id *pci_id; + struct hnae3_ae_dev *ae_dev; + + if (!ae_algo) + return; + + list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) { + if (!hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B)) + continue; + + pci_id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev); + if (!pci_id) + continue; + if (IS_ENABLED(CONFIG_PCI_IOV)) + pci_disable_sriov(ae_dev->pdev); + } +} +EXPORT_SYMBOL(hnae3_unregister_ae_algo_prepare); + /* we are keeping things simple and using single lock for all the * list. This is a non-critical code so other updations, if happen * in parallel, can wait. diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 8ba21d6dc220..d701451596c8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -853,6 +853,7 @@ struct hnae3_handle { int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev); void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev); +void hnae3_unregister_ae_algo_prepare(struct hnae3_ae_algo *ae_algo); void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo); void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 468b8f07bf47..4b886a13e079 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1847,7 +1847,6 @@ void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size) static int hns3_skb_linearize(struct hns3_enet_ring *ring, struct sk_buff *skb, - u8 max_non_tso_bd_num, unsigned int bd_num) { /* 'bd_num == UINT_MAX' means the skb' fraglist has a @@ -1864,8 +1863,7 @@ static int hns3_skb_linearize(struct hns3_enet_ring *ring, * will not help. */ if (skb->len > HNS3_MAX_TSO_SIZE || - (!skb_is_gso(skb) && skb->len > - HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num))) { + (!skb_is_gso(skb) && skb->len > HNS3_MAX_NON_TSO_SIZE)) { u64_stats_update_begin(&ring->syncp); ring->stats.hw_limitation++; u64_stats_update_end(&ring->syncp); @@ -1900,8 +1898,7 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring, goto out; } - if (hns3_skb_linearize(ring, skb, max_non_tso_bd_num, - bd_num)) + if (hns3_skb_linearize(ring, skb, bd_num)) return -ENOMEM; bd_num = hns3_tx_bd_count(skb->len); @@ -3258,6 +3255,7 @@ static void hns3_buffer_detach(struct hns3_enet_ring *ring, int i) { hns3_unmap_buffer(ring, &ring->desc_cb[i]); ring->desc[i].addr = 0; + ring->desc_cb[i].refill = 0; } static void hns3_free_buffer_detach(struct hns3_enet_ring *ring, int i, @@ -3336,6 +3334,7 @@ static int hns3_alloc_and_attach_buffer(struct hns3_enet_ring *ring, int i) ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma + ring->desc_cb[i].page_offset); + ring->desc_cb[i].refill = 1; return 0; } @@ -3365,6 +3364,7 @@ static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i, { hns3_unmap_buffer(ring, &ring->desc_cb[i]); ring->desc_cb[i] = *res_cb; + ring->desc_cb[i].refill = 1; ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma + ring->desc_cb[i].page_offset); ring->desc[i].rx.bd_base_info = 0; @@ -3373,6 +3373,7 @@ static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i, static void hns3_reuse_buffer(struct hns3_enet_ring *ring, int i) { ring->desc_cb[i].reuse_flag = 0; + ring->desc_cb[i].refill = 1; ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma + ring->desc_cb[i].page_offset); ring->desc[i].rx.bd_base_info = 0; @@ -3479,10 +3480,14 @@ static int hns3_desc_unused(struct hns3_enet_ring *ring) int ntc = ring->next_to_clean; int ntu = ring->next_to_use; + if (unlikely(ntc == ntu && !ring->desc_cb[ntc].refill)) + return ring->desc_num; + return ((ntc >= ntu) ? 0 : ring->desc_num) + ntc - ntu; } -static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, +/* Return true if there is any allocation failure */ +static bool hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, int cleand_count) { struct hns3_desc_cb *desc_cb; @@ -3507,7 +3512,10 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, hns3_rl_err(ring_to_netdev(ring), "alloc rx buffer failed: %d\n", ret); - break; + + writel(i, ring->tqp->io_base + + HNS3_RING_RX_RING_HEAD_REG); + return true; } hns3_replace_buffer(ring, ring->next_to_use, &res_cbs); @@ -3520,6 +3528,7 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, } writel(i, ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG); + return false; } static bool hns3_can_reuse_page(struct hns3_desc_cb *cb) @@ -3824,6 +3833,7 @@ static void hns3_rx_ring_move_fw(struct hns3_enet_ring *ring) { ring->desc[ring->next_to_clean].rx.bd_base_info &= cpu_to_le32(~BIT(HNS3_RXD_VLD_B)); + ring->desc_cb[ring->next_to_clean].refill = 0; ring->next_to_clean += 1; if (unlikely(ring->next_to_clean == ring->desc_num)) @@ -4170,6 +4180,7 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, { #define RCB_NOF_ALLOC_RX_BUFF_ONCE 16 int unused_count = hns3_desc_unused(ring); + bool failure = false; int recv_pkts = 0; int err; @@ -4178,9 +4189,9 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, while (recv_pkts < budget) { /* Reuse or realloc buffers */ if (unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) { - hns3_nic_alloc_rx_buffers(ring, unused_count); - unused_count = hns3_desc_unused(ring) - - ring->pending_buf; + failure = failure || + hns3_nic_alloc_rx_buffers(ring, unused_count); + unused_count = 0; } /* Poll one pkt */ @@ -4199,11 +4210,7 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, } out: - /* Make all data has been write before submit */ - if (unused_count > 0) - hns3_nic_alloc_rx_buffers(ring, unused_count); - - return recv_pkts; + return failure ? budget : recv_pkts; } static void hns3_update_rx_int_coalesce(struct hns3_enet_tqp_vector *tqp_vector) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 6162d9f88e37..f09a61d9c626 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -186,11 +186,9 @@ enum hns3_nic_state { #define HNS3_MAX_BD_SIZE 65535 #define HNS3_MAX_TSO_BD_NUM 63U -#define HNS3_MAX_TSO_SIZE \ - (HNS3_MAX_BD_SIZE * HNS3_MAX_TSO_BD_NUM) +#define HNS3_MAX_TSO_SIZE 1048576U +#define HNS3_MAX_NON_TSO_SIZE 9728U -#define HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num) \ - (HNS3_MAX_BD_SIZE * (max_non_tso_bd_num)) #define HNS3_VECTOR_GL0_OFFSET 0x100 #define HNS3_VECTOR_GL1_OFFSET 0x200 @@ -332,6 +330,7 @@ struct hns3_desc_cb { u32 length; /* length of the buffer */ u16 reuse_flag; + u16 refill; /* desc type, used by the ring user to mark the type of the priv data */ u16 type; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 307c9e830510..91cb578f56b8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -137,6 +137,15 @@ static int hclge_ets_sch_mode_validate(struct hclge_dev *hdev, *changed = true; break; case IEEE_8021QAZ_TSA_ETS: + /* The hardware will switch to sp mode if bandwidth is + * 0, so limit ets bandwidth must be greater than 0. + */ + if (!ets->tc_tx_bw[i]) { + dev_err(&hdev->pdev->dev, + "tc%u ets bw cannot be 0\n", i); + return -EINVAL; + } + if (hdev->tm_info.tc_info[i].tc_sch_mode != HCLGE_SCH_MODE_DWRR) *changed = true; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index bb9b026ae88e..93aa7f2bdc13 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -1560,8 +1560,11 @@ static int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en) /* configure TM QCN hw errors */ hclge_cmd_setup_basic_desc(&desc, HCLGE_TM_QCN_MEM_INT_CFG, false); - if (en) + desc.data[0] = cpu_to_le32(HCLGE_TM_QCN_ERR_INT_TYPE); + if (en) { + desc.data[0] |= cpu_to_le32(HCLGE_TM_QCN_FIFO_INT_EN); desc.data[1] = cpu_to_le32(HCLGE_TM_QCN_MEM_ERR_INT_EN); + } ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h index 07987fb8332e..d811eeefe2c0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h @@ -50,6 +50,8 @@ #define HCLGE_PPP_MPF_ECC_ERR_INT3_EN 0x003F #define HCLGE_PPP_MPF_ECC_ERR_INT3_EN_MASK 0x003F #define HCLGE_TM_SCH_ECC_ERR_INT_EN 0x3 +#define HCLGE_TM_QCN_ERR_INT_TYPE 0x29 +#define HCLGE_TM_QCN_FIFO_INT_EN 0xFFFF00 #define HCLGE_TM_QCN_MEM_ERR_INT_EN 0xFFFFFF #define HCLGE_NCSI_ERR_INT_EN 0x3 #define HCLGE_NCSI_ERR_INT_TYPE 0x9 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index f5b8d1fee0f1..dcd40cc73082 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -13065,6 +13065,7 @@ static int hclge_init(void) static void hclge_exit(void) { + hnae3_unregister_ae_algo_prepare(&ae_algo); hnae3_unregister_ae_algo(&ae_algo); destroy_workqueue(hclge_wq); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index f314dbd3ce11..95074e91a846 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -752,6 +752,8 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev) hdev->tm_info.pg_info[i].tc_bit_map = hdev->hw_tc_map; for (k = 0; k < hdev->tm_info.num_tc; k++) hdev->tm_info.pg_info[i].tc_dwrr[k] = BW_PERCENT; + for (; k < HNAE3_MAX_TC; k++) + hdev->tm_info.pg_info[i].tc_dwrr[k] = 0; } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 5fdac8685f95..bef6b98e2f50 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2273,9 +2273,9 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev) hdev->reset_attempts = 0; hdev->last_reset_time = jiffies; - while ((hdev->reset_type = - hclgevf_get_reset_level(hdev, &hdev->reset_pending)) - != HNAE3_NONE_RESET) + hdev->reset_type = + hclgevf_get_reset_level(hdev, &hdev->reset_pending); + if (hdev->reset_type != HNAE3_NONE_RESET) hclgevf_reset(hdev); } else if (test_and_clear_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state)) { diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 5b2143f4b1f8..3178efd98006 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -113,7 +113,8 @@ enum e1000_boards { board_pch2lan, board_pch_lpt, board_pch_spt, - board_pch_cnp + board_pch_cnp, + board_pch_tgp }; struct e1000_ps_page { @@ -499,6 +500,7 @@ extern const struct e1000_info e1000_pch2_info; extern const struct e1000_info e1000_pch_lpt_info; extern const struct e1000_info e1000_pch_spt_info; extern const struct e1000_info e1000_pch_cnp_info; +extern const struct e1000_info e1000_pch_tgp_info; extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 60c582a16821..5e4fc9b4e2ad 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -4813,7 +4813,7 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw) static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw) { struct e1000_mac_info *mac = &hw->mac; - u32 ctrl_ext, txdctl, snoop; + u32 ctrl_ext, txdctl, snoop, fflt_dbg; s32 ret_val; u16 i; @@ -4872,6 +4872,15 @@ static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw) snoop = (u32)~(PCIE_NO_SNOOP_ALL); e1000e_set_pcie_no_snoop(hw, snoop); + /* Enable workaround for packet loss issue on TGP PCH + * Do not gate DMA clock from the modPHY block + */ + if (mac->type >= e1000_pch_tgp) { + fflt_dbg = er32(FFLT_DBG); + fflt_dbg |= E1000_FFLT_DBG_DONT_GATE_WAKE_DMA_CLK; + ew32(FFLT_DBG, fflt_dbg); + } + ctrl_ext = er32(CTRL_EXT); ctrl_ext |= E1000_CTRL_EXT_RO_DIS; ew32(CTRL_EXT, ctrl_ext); @@ -5992,3 +6001,23 @@ const struct e1000_info e1000_pch_cnp_info = { .phy_ops = &ich8_phy_ops, .nvm_ops = &spt_nvm_ops, }; + +const struct e1000_info e1000_pch_tgp_info = { + .mac = e1000_pch_tgp, + .flags = FLAG_IS_ICH + | FLAG_HAS_WOL + | FLAG_HAS_HW_TIMESTAMP + | FLAG_HAS_CTRLEXT_ON_LOAD + | FLAG_HAS_AMT + | FLAG_HAS_FLASH + | FLAG_HAS_JUMBO_FRAMES + | FLAG_APME_IN_WUC, + .flags2 = FLAG2_HAS_PHY_STATS + | FLAG2_HAS_EEE, + .pba = 26, + .max_hw_frame_size = 9022, + .get_variants = e1000_get_variants_ich8lan, + .mac_ops = &ich8_mac_ops, + .phy_ops = &ich8_phy_ops, + .nvm_ops = &spt_nvm_ops, +}; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index d6a092e5ee74..2504b11c3169 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -289,6 +289,9 @@ /* Proprietary Latency Tolerance Reporting PCI Capability */ #define E1000_PCI_LTR_CAP_LPT 0xA8 +/* Don't gate wake DMA clock */ +#define E1000_FFLT_DBG_DONT_GATE_WAKE_DMA_CLK 0x1000 + void e1000e_write_protect_nvm_ich8lan(struct e1000_hw *hw); void e1000e_set_kmrn_lock_loss_workaround_ich8lan(struct e1000_hw *hw, bool state); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 900b3ab998bd..ebcb2a30add0 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -51,6 +51,7 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pch_lpt] = &e1000_pch_lpt_info, [board_pch_spt] = &e1000_pch_spt_info, [board_pch_cnp] = &e1000_pch_cnp_info, + [board_pch_tgp] = &e1000_pch_tgp_info, }; struct e1000_reg_info { @@ -7896,28 +7897,28 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_V11), board_pch_cnp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_LM12), board_pch_spt }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_V12), board_pch_spt }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM13), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V13), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM14), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_cnp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM13), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V13), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM14), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_tgp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 2fb81e359cdf..df5ad4de1f00 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -25,6 +25,8 @@ static enum ice_status ice_set_mac_type(struct ice_hw *hw) case ICE_DEV_ID_E810C_BACKPLANE: case ICE_DEV_ID_E810C_QSFP: case ICE_DEV_ID_E810C_SFP: + case ICE_DEV_ID_E810_XXV_BACKPLANE: + case ICE_DEV_ID_E810_XXV_QSFP: case ICE_DEV_ID_E810_XXV_SFP: hw->mac_type = ICE_MAC_E810; break; diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index 9d8194671f6a..ef4392e6e244 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -21,6 +21,10 @@ #define ICE_DEV_ID_E810C_QSFP 0x1592 /* Intel(R) Ethernet Controller E810-C for SFP */ #define ICE_DEV_ID_E810C_SFP 0x1593 +/* Intel(R) Ethernet Controller E810-XXV for backplane */ +#define ICE_DEV_ID_E810_XXV_BACKPLANE 0x1599 +/* Intel(R) Ethernet Controller E810-XXV for QSFP */ +#define ICE_DEV_ID_E810_XXV_QSFP 0x159A /* Intel(R) Ethernet Controller E810-XXV for SFP */ #define ICE_DEV_ID_E810_XXV_SFP 0x159B /* Intel(R) Ethernet Connection E823-C for backplane */ diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 14afce82ef63..da7288bdc9a3 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -63,7 +63,8 @@ static int ice_info_fw_api(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_hw *hw = &pf->hw; - snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u", hw->api_maj_ver, hw->api_min_ver); + snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", hw->api_maj_ver, + hw->api_min_ver, hw->api_patch); return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 06ac9badee77..1ac96dc66d0d 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -1668,7 +1668,7 @@ static u16 ice_tunnel_idx_to_entry(struct ice_hw *hw, enum ice_tunnel_type type, for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++) if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].type == type && - idx--) + idx-- == 0) return i; WARN_ON_ONCE(1); @@ -1828,7 +1828,7 @@ int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, u16 index; tnl_type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? TNL_VXLAN : TNL_GENEVE; - index = ice_tunnel_idx_to_entry(&pf->hw, idx, tnl_type); + index = ice_tunnel_idx_to_entry(&pf->hw, tnl_type, idx); status = ice_create_tunnel(&pf->hw, index, tnl_type, ntohs(ti->port)); if (status) { diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index dde9802c6c72..b718e196af2a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2841,6 +2841,7 @@ void ice_napi_del(struct ice_vsi *vsi) */ int ice_vsi_release(struct ice_vsi *vsi) { + enum ice_status err; struct ice_pf *pf; if (!vsi->back) @@ -2912,6 +2913,10 @@ int ice_vsi_release(struct ice_vsi *vsi) ice_fltr_remove_all(vsi); ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); + err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); + if (err) + dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", + vsi->vsi_num, err); ice_vsi_delete(vsi); ice_vsi_free_q_vectors(vsi); @@ -3092,6 +3097,10 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce); ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); + ret = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); + if (ret) + dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", + vsi->vsi_num, ret); ice_vsi_free_q_vectors(vsi); /* SR-IOV determines needed MSIX resources all at once instead of per diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 0d6c143f6653..06fa93e597fb 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4224,6 +4224,9 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) if (!pf) return -ENOMEM; + /* initialize Auxiliary index to invalid value */ + pf->aux_idx = -1; + /* set up for high or low DMA */ err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); if (err) @@ -4615,7 +4618,8 @@ static void ice_remove(struct pci_dev *pdev) ice_aq_cancel_waiting_tasks(pf); ice_unplug_aux_dev(pf); - ida_free(&ice_aux_ida, pf->aux_idx); + if (pf->aux_idx >= 0) + ida_free(&ice_aux_ida, pf->aux_idx); set_bit(ICE_DOWN, pf->state); mutex_destroy(&(&pf->hw)->fdir_fltr_lock); @@ -5016,6 +5020,8 @@ static const struct pci_device_id ice_pci_tbl[] = { { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_BACKPLANE), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_QSFP), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP), 0 }, diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 9f07b6641705..2d9b10277186 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -2071,6 +2071,19 @@ enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle) } /** + * ice_rm_vsi_rdma_cfg - remove VSI and its RDMA children nodes + * @pi: port information structure + * @vsi_handle: software VSI handle + * + * This function clears the VSI and its RDMA children nodes from scheduler tree + * for all TCs. + */ +enum ice_status ice_rm_vsi_rdma_cfg(struct ice_port_info *pi, u16 vsi_handle) +{ + return ice_sched_rm_vsi_cfg(pi, vsi_handle, ICE_SCHED_NODE_OWNER_RDMA); +} + +/** * ice_get_agg_info - get the aggregator ID * @hw: pointer to the hardware structure * @agg_id: aggregator ID diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index 9beef8f0ec76..fdf7a5882f07 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -89,6 +89,7 @@ enum ice_status ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, u8 owner, bool enable); enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle); +enum ice_status ice_rm_vsi_rdma_cfg(struct ice_port_info *pi, u16 vsi_handle); /* Tx scheduler rate limiter functions */ enum ice_status diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h index 4461f8b9a864..4e0203336c6b 100644 --- a/drivers/net/ethernet/intel/igc/igc_hw.h +++ b/drivers/net/ethernet/intel/igc/igc_hw.h @@ -22,8 +22,8 @@ #define IGC_DEV_ID_I220_V 0x15F7 #define IGC_DEV_ID_I225_K 0x3100 #define IGC_DEV_ID_I225_K2 0x3101 +#define IGC_DEV_ID_I226_K 0x3102 #define IGC_DEV_ID_I225_LMVP 0x5502 -#define IGC_DEV_ID_I226_K 0x5504 #define IGC_DEV_ID_I225_IT 0x0D9F #define IGC_DEV_ID_I226_LM 0x125B #define IGC_DEV_ID_I226_V 0x125C diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 41684a6c44e9..a88a1a48229f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -199,6 +199,9 @@ void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); int mlx5e_create_flow_steering(struct mlx5e_priv *priv); void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv); +int mlx5e_fs_init(struct mlx5e_priv *priv); +void mlx5e_fs_cleanup(struct mlx5e_priv *priv); + int mlx5e_add_vlan_trap(struct mlx5e_priv *priv, int trap_id, int tir_num); void mlx5e_remove_vlan_trap(struct mlx5e_priv *priv); int mlx5e_add_mac_trap(struct mlx5e_priv *priv, int trap_id, int tir_num); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index b4e986818794..4a13ef561587 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -10,6 +10,8 @@ #include "en_tc.h" #include "rep/tc.h" #include "rep/neigh.h" +#include "lag.h" +#include "lag_mp.h" struct mlx5e_tc_tun_route_attr { struct net_device *out_dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 33de8f0092a6..fb5397324aa4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -141,8 +141,7 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, * Pkt: MAC IP ESP IP L4 * * Transport Mode: - * SWP: OutL3 InL4 - * InL3 + * SWP: OutL3 OutL4 * Pkt: MAC IP ESP L4 * * Tunnel(VXLAN TCP/UDP) over Transport Mode @@ -171,31 +170,35 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, return; if (!xo->inner_ipproto) { - eseg->swp_inner_l3_offset = skb_network_offset(skb) / 2; - eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; - if (skb->protocol == htons(ETH_P_IPV6)) - eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; - if (xo->proto == IPPROTO_UDP) + switch (xo->proto) { + case IPPROTO_UDP: + eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L4_UDP; + fallthrough; + case IPPROTO_TCP: + /* IP | ESP | TCP */ + eseg->swp_outer_l4_offset = skb_inner_transport_offset(skb) / 2; + break; + default: + break; + } + } else { + /* Tunnel(VXLAN TCP/UDP) over Transport Mode */ + switch (xo->inner_ipproto) { + case IPPROTO_UDP: eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; - return; - } - - /* Tunnel(VXLAN TCP/UDP) over Transport Mode */ - switch (xo->inner_ipproto) { - case IPPROTO_UDP: - eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; - fallthrough; - case IPPROTO_TCP: - eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; - eseg->swp_inner_l4_offset = (skb->csum_start + skb->head - skb->data) / 2; - if (skb->protocol == htons(ETH_P_IPV6)) - eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; - break; - default: - break; + fallthrough; + case IPPROTO_TCP: + eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; + eseg->swp_inner_l4_offset = + (skb->csum_start + skb->head - skb->data) / 2; + if (skb->protocol == htons(ETH_P_IPV6)) + eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; + break; + default: + break; + } } - return; } void mlx5e_ipsec_set_iv_esn(struct sk_buff *skb, struct xfrm_state *x, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index c06b4b938ae7..d226cc5ab1d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -1186,10 +1186,6 @@ static int mlx5e_create_vlan_table(struct mlx5e_priv *priv) struct mlx5e_flow_table *ft; int err; - priv->fs.vlan = kvzalloc(sizeof(*priv->fs.vlan), GFP_KERNEL); - if (!priv->fs.vlan) - return -ENOMEM; - ft = &priv->fs.vlan->ft; ft->num_groups = 0; @@ -1198,10 +1194,8 @@ static int mlx5e_create_vlan_table(struct mlx5e_priv *priv) ft_attr.prio = MLX5E_NIC_PRIO; ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr); - if (IS_ERR(ft->t)) { - err = PTR_ERR(ft->t); - goto err_free_t; - } + if (IS_ERR(ft->t)) + return PTR_ERR(ft->t); ft->g = kcalloc(MLX5E_NUM_VLAN_GROUPS, sizeof(*ft->g), GFP_KERNEL); if (!ft->g) { @@ -1221,9 +1215,6 @@ err_free_g: kfree(ft->g); err_destroy_vlan_table: mlx5_destroy_flow_table(ft->t); -err_free_t: - kvfree(priv->fs.vlan); - priv->fs.vlan = NULL; return err; } @@ -1232,7 +1223,6 @@ static void mlx5e_destroy_vlan_table(struct mlx5e_priv *priv) { mlx5e_del_vlan_rules(priv); mlx5e_destroy_flow_table(&priv->fs.vlan->ft); - kvfree(priv->fs.vlan); } static void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv) @@ -1351,3 +1341,17 @@ void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv) mlx5e_arfs_destroy_tables(priv); mlx5e_ethtool_cleanup_steering(priv); } + +int mlx5e_fs_init(struct mlx5e_priv *priv) +{ + priv->fs.vlan = kvzalloc(sizeof(*priv->fs.vlan), GFP_KERNEL); + if (!priv->fs.vlan) + return -ENOMEM; + return 0; +} + +void mlx5e_fs_cleanup(struct mlx5e_priv *priv) +{ + kvfree(priv->fs.vlan); + priv->fs.vlan = NULL; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 09c8b71b186c..41ef6eb70a58 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4578,6 +4578,12 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5e_timestamp_init(priv); + err = mlx5e_fs_init(priv); + if (err) { + mlx5_core_err(mdev, "FS initialization failed, %d\n", err); + return err; + } + err = mlx5e_ipsec_init(priv); if (err) mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err); @@ -4595,6 +4601,7 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) mlx5e_health_destroy_reporters(priv); mlx5e_tls_cleanup(priv); mlx5e_ipsec_cleanup(priv); + mlx5e_fs_cleanup(priv); } static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ba8164792016..129ff7e0d65c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -67,6 +67,8 @@ #include "lib/fs_chains.h" #include "diag/en_tc_tracepoint.h" #include <asm/div64.h> +#include "lag.h" +#include "lag_mp.h" #define nic_chains(priv) ((priv)->fs.tc.chains) #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index c63d78eda606..188994d091c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -213,19 +213,18 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz); } -/* If packet is not IP's CHECKSUM_PARTIAL (e.g. icmd packet), - * need to set L3 checksum flag for IPsec - */ static void ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) { + struct xfrm_offload *xo = xfrm_offload(skb); + eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; - if (skb->encapsulation) { - eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM; + if (xo->inner_ipproto) { + eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM | MLX5_ETH_WQE_L3_INNER_CSUM; + } else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { + eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial_inner++; - } else { - sq->stats->csum_partial++; } } @@ -234,6 +233,11 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5e_accel_tx_state *accel, struct mlx5_wqe_eth_seg *eseg) { + if (unlikely(mlx5e_ipsec_eseg_meta(eseg))) { + ipsec_txwqe_build_eseg_csum(sq, skb, eseg); + return; + } + if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; if (skb->encapsulation) { @@ -249,8 +253,6 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial++; #endif - } else if (unlikely(mlx5e_ipsec_eseg_meta(eseg))) { - ipsec_txwqe_build_eseg_csum(sq, skb, eseg); } else sq->stats->csum_none++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 985e305179d1..c6cc67cb4f6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -473,10 +473,9 @@ esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta err_min_rate: list_del(&group->list); - err = mlx5_destroy_scheduling_element_cmd(esw->dev, - SCHEDULING_HIERARCHY_E_SWITCH, - group->tsar_ix); - if (err) + if (mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + group->tsar_ix)) NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR for group failed"); err_sched_elem: kfree(group); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index ca5690b0a7ab..d2105c1635c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -442,6 +442,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) if (!mlx5_lag_is_ready(ldev)) { do_bond = false; } else { + /* VF LAG is in multipath mode, ignore bond change requests */ + if (mlx5_lag_is_multipath(dev0)) + return; + tracker = ldev->tracker; do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index f239b352a58a..21fdaf708f1f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -9,20 +9,23 @@ #include "eswitch.h" #include "lib/mlx5.h" +static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev) +{ + return !!(ldev->flags & MLX5_LAG_FLAG_MULTIPATH); +} + static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) { if (!mlx5_lag_is_ready(ldev)) return false; + if (__mlx5_lag_is_active(ldev) && !__mlx5_lag_is_multipath(ldev)) + return false; + return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev, ldev->pf[MLX5_LAG_P2].dev); } -static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev) -{ - return !!(ldev->flags & MLX5_LAG_FLAG_MULTIPATH); -} - bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h index 729c839397a8..dea199e79bed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h @@ -24,12 +24,14 @@ struct lag_mp { void mlx5_lag_mp_reset(struct mlx5_lag *ldev); int mlx5_lag_mp_init(struct mlx5_lag *ldev); void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev); +bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ static inline void mlx5_lag_mp_reset(struct mlx5_lag *ldev) {}; static inline int mlx5_lag_mp_init(struct mlx5_lag *ldev) { return 0; } static inline void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) {} +bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) { return false; } #endif /* CONFIG_MLX5_ESWITCH */ #endif /* __MLX5_LAG_MP_H__ */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index cbece6e9bff2..5030dfca3879 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -758,6 +758,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev) err = dev_err_probe(sparx5->dev, PTR_ERR(serdes), "port %u: missing serdes\n", portno); + of_node_put(portnp); goto cleanup_config; } config->portno = portno; diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 291ae6817c26..d51f799e4e86 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -969,6 +969,7 @@ static int mscc_ocelot_init_ports(struct platform_device *pdev, target = ocelot_regmap_init(ocelot, res); if (IS_ERR(target)) { err = PTR_ERR(target); + of_node_put(portnp); goto out_teardown; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c index 2643ea5948f4..154399c5453f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_asm.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c @@ -196,7 +196,7 @@ int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg, } reg->dst_lmextn = swreg_lmextn(dst); - reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg); + reg->src_lmextn = swreg_lmextn(lreg) || swreg_lmextn(rreg); return 0; } @@ -277,7 +277,7 @@ int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg, } reg->dst_lmextn = swreg_lmextn(dst); - reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg); + reg->src_lmextn = swreg_lmextn(lreg) || swreg_lmextn(rreg); return 0; } diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.c b/drivers/net/ethernet/sfc/mcdi_port_common.c index 4bd3ef8f3384..c4fe3c48ac46 100644 --- a/drivers/net/ethernet/sfc/mcdi_port_common.c +++ b/drivers/net/ethernet/sfc/mcdi_port_common.c @@ -132,16 +132,27 @@ void mcdi_to_ethtool_linkset(u32 media, u32 cap, unsigned long *linkset) case MC_CMD_MEDIA_SFP_PLUS: case MC_CMD_MEDIA_QSFP_PLUS: SET_BIT(FIBRE); - if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN)) + if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN)) { SET_BIT(1000baseT_Full); - if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN)) - SET_BIT(10000baseT_Full); - if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN)) + SET_BIT(1000baseX_Full); + } + if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN)) { + SET_BIT(10000baseCR_Full); + SET_BIT(10000baseLR_Full); + SET_BIT(10000baseSR_Full); + } + if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN)) { SET_BIT(40000baseCR4_Full); - if (cap & (1 << MC_CMD_PHY_CAP_100000FDX_LBN)) + SET_BIT(40000baseSR4_Full); + } + if (cap & (1 << MC_CMD_PHY_CAP_100000FDX_LBN)) { SET_BIT(100000baseCR4_Full); - if (cap & (1 << MC_CMD_PHY_CAP_25000FDX_LBN)) + SET_BIT(100000baseSR4_Full); + } + if (cap & (1 << MC_CMD_PHY_CAP_25000FDX_LBN)) { SET_BIT(25000baseCR_Full); + SET_BIT(25000baseSR_Full); + } if (cap & (1 << MC_CMD_PHY_CAP_50000FDX_LBN)) SET_BIT(50000baseCR2_Full); break; @@ -192,15 +203,19 @@ u32 ethtool_linkset_to_mcdi_cap(const unsigned long *linkset) result |= (1 << MC_CMD_PHY_CAP_100FDX_LBN); if (TEST_BIT(1000baseT_Half)) result |= (1 << MC_CMD_PHY_CAP_1000HDX_LBN); - if (TEST_BIT(1000baseT_Full) || TEST_BIT(1000baseKX_Full)) + if (TEST_BIT(1000baseT_Full) || TEST_BIT(1000baseKX_Full) || + TEST_BIT(1000baseX_Full)) result |= (1 << MC_CMD_PHY_CAP_1000FDX_LBN); - if (TEST_BIT(10000baseT_Full) || TEST_BIT(10000baseKX4_Full)) + if (TEST_BIT(10000baseT_Full) || TEST_BIT(10000baseKX4_Full) || + TEST_BIT(10000baseCR_Full) || TEST_BIT(10000baseLR_Full) || + TEST_BIT(10000baseSR_Full)) result |= (1 << MC_CMD_PHY_CAP_10000FDX_LBN); - if (TEST_BIT(40000baseCR4_Full) || TEST_BIT(40000baseKR4_Full)) + if (TEST_BIT(40000baseCR4_Full) || TEST_BIT(40000baseKR4_Full) || + TEST_BIT(40000baseSR4_Full)) result |= (1 << MC_CMD_PHY_CAP_40000FDX_LBN); - if (TEST_BIT(100000baseCR4_Full)) + if (TEST_BIT(100000baseCR4_Full) || TEST_BIT(100000baseSR4_Full)) result |= (1 << MC_CMD_PHY_CAP_100000FDX_LBN); - if (TEST_BIT(25000baseCR_Full)) + if (TEST_BIT(25000baseCR_Full) || TEST_BIT(25000baseSR_Full)) result |= (1 << MC_CMD_PHY_CAP_25000FDX_LBN); if (TEST_BIT(50000baseCR2_Full)) result |= (1 << MC_CMD_PHY_CAP_50000FDX_LBN); diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index a39c5143b386..797e51802ccb 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -648,7 +648,7 @@ static int efx_ptp_get_attributes(struct efx_nic *efx) } else if (rc == -EINVAL) { fmt = MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS; } else if (rc == -EPERM) { - netif_info(efx, probe, efx->net_dev, "no PTP support\n"); + pci_info(efx->pci_dev, "no PTP support\n"); return rc; } else { efx_mcdi_display_error(efx, MC_CMD_PTP, sizeof(inbuf), @@ -824,7 +824,7 @@ static int efx_ptp_disable(struct efx_nic *efx) * should only have been called during probe. */ if (rc == -ENOSYS || rc == -EPERM) - netif_info(efx, probe, efx->net_dev, "no PTP support\n"); + pci_info(efx->pci_dev, "no PTP support\n"); else if (rc) efx_mcdi_display_error(efx, MC_CMD_PTP, MC_CMD_PTP_IN_DISABLE_LEN, diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c index 83dcfcae3d4b..441e7f3e5375 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.c +++ b/drivers/net/ethernet/sfc/siena_sriov.c @@ -1057,7 +1057,7 @@ void efx_siena_sriov_probe(struct efx_nic *efx) return; if (efx_siena_sriov_cmd(efx, false, &efx->vi_scale, &count)) { - netif_info(efx, probe, efx->net_dev, "no SR-IOV VFs probed\n"); + pci_info(efx->pci_dev, "no SR-IOV VFs probed\n"); return; } if (count > 0 && count > max_vfs) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index eb3b7bf771d7..3d67d1fa3690 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -736,7 +736,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; ptp_v2 = PTP_TCR_TSVER2ENA; snap_type_sel = PTP_TCR_SNAPTYPSEL_1; - if (priv->synopsys_id != DWMAC_CORE_5_10) + if (priv->synopsys_id < DWMAC_CORE_4_10) ts_event_en = PTP_TCR_TSEVNTENA; ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA; ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA; diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 775dcf4ebde5..6b6f28d5b8d5 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -623,16 +623,16 @@ static int receive(struct net_device *dev, int cnt) /* --------------------------------------------------------------------- */ -#ifdef __i386__ +#if defined(__i386__) && !defined(CONFIG_UML) #include <asm/msr.h> #define GETTICK(x) \ ({ \ if (boot_cpu_has(X86_FEATURE_TSC)) \ x = (unsigned int)rdtsc(); \ }) -#else /* __i386__ */ +#else /* __i386__ && !CONFIG_UML */ #define GETTICK(x) -#endif /* __i386__ */ +#endif /* __i386__ && !CONFIG_UML */ static void epp_bh(struct work_struct *work) { diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index f87f17503373..b554054a7560 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -117,6 +117,7 @@ config USB_LAN78XX select PHYLIB select MICROCHIP_PHY select FIXED_PHY + select CRC32 help This option adds support for Microchip LAN78XX based USB 2 & USB 3 10/100/1000 Ethernet adapters. diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 840c1c2ab16a..80432ee0ce69 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1788,6 +1788,10 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) if (!dev->rx_urb_size) dev->rx_urb_size = dev->hard_mtu; dev->maxpacket = usb_maxpacket (dev->udev, dev->out, 1); + if (dev->maxpacket == 0) { + /* that is a broken device */ + goto out4; + } /* let userspace know we have a random address */ if (ether_addr_equal(net->dev_addr, node_id)) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index bf2fac913942..662e26117353 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1360,8 +1360,6 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); bool is_ndisc = ipv6_ndisc_frame(skb); - nf_reset_ct(skb); - /* loopback, multicast & non-ND link-local traffic; do not push through * packet taps again. Reset pkt_type for upper layers to process skb. * For strict packets with a source LLA, determine the dst using the @@ -1424,8 +1422,6 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, skb->skb_iif = vrf_dev->ifindex; IPCB(skb)->flags |= IPSKB_L3SLAVE; - nf_reset_ct(skb); - if (ipv4_is_multicast(ip_hdr(skb)->daddr)) goto out; diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c index d16cf3ff644e..b23f47936473 100644 --- a/drivers/nfc/st95hf/core.c +++ b/drivers/nfc/st95hf/core.c @@ -1226,11 +1226,9 @@ static int st95hf_remove(struct spi_device *nfc_spi_dev) &reset_cmd, ST95HF_RESET_CMD_LEN, ASYNC); - if (result) { + if (result) dev_err(&spictx->spidev->dev, "ST95HF reset failed in remove() err = %d\n", result); - return result; - } /* wait for 3 ms to complete the controller reset process */ usleep_range(3000, 4000); @@ -1239,7 +1237,7 @@ static int st95hf_remove(struct spi_device *nfc_spi_dev) if (stcontext->st95hf_supply) regulator_disable(stcontext->st95hf_supply); - return result; + return 0; } /* Register as SPI protocol driver */ diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 4dfc52e06704..f9b2d66b0443 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -170,6 +170,7 @@ static void ptp_clock_release(struct device *dev) struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev); ptp_cleanup_pin_groups(ptp); + kfree(ptp->vclock_index); mutex_destroy(&ptp->tsevq_mux); mutex_destroy(&ptp->pincfg_mux); mutex_destroy(&ptp->n_vclocks_mux); @@ -283,15 +284,20 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, /* Create a posix clock and link it to the device. */ err = posix_clock_register(&ptp->clock, &ptp->dev); if (err) { + if (ptp->pps_source) + pps_unregister_source(ptp->pps_source); + + if (ptp->kworker) + kthread_destroy_worker(ptp->kworker); + + put_device(&ptp->dev); + pr_err("failed to create posix clock\n"); - goto no_clock; + return ERR_PTR(err); } return ptp; -no_clock: - if (ptp->pps_source) - pps_unregister_source(ptp->pps_source); no_pps: ptp_cleanup_pin_groups(ptp); no_pin_groups: @@ -321,8 +327,6 @@ int ptp_clock_unregister(struct ptp_clock *ptp) ptp->defunct = 1; wake_up_interruptible(&ptp->tsev_wq); - kfree(ptp->vclock_index); - if (ptp->kworker) { kthread_cancel_delayed_work_sync(&ptp->aux_work); kthread_destroy_worker(ptp->kworker); diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c index d0096cd7096a..4991054a2135 100644 --- a/drivers/ptp/ptp_kvm_x86.c +++ b/drivers/ptp/ptp_kvm_x86.c @@ -31,10 +31,10 @@ int kvm_arch_ptp_init(void) ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa, KVM_CLOCK_PAIRING_WALLCLOCK); - if (ret == -KVM_ENOSYS || ret == -KVM_EOPNOTSUPP) + if (ret == -KVM_ENOSYS) return -ENODEV; - return 0; + return ret; } int kvm_arch_ptp_get_clock(struct timespec64 *ts) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e23417424373..f17d2101af7a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1138,7 +1138,6 @@ int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev); int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev); bool mlx5_lag_is_roce(struct mlx5_core_dev *dev); bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev); -bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); bool mlx5_lag_is_master(struct mlx5_core_dev *dev); bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev); diff --git a/include/net/mctp.h b/include/net/mctp.h index a824d47c3c6d..ffd2c23bd76d 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -54,7 +54,7 @@ struct mctp_sock { struct sock sk; /* bind() params */ - int bind_net; + unsigned int bind_net; mctp_eid_t bind_addr; __u8 bind_type; diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 2eb6d7c2c931..f37c7a558d6d 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -384,11 +384,11 @@ sctp_vtag_verify(const struct sctp_chunk *chunk, * Verification Tag value does not match the receiver's own * tag value, the receiver shall silently discard the packet... */ - if (ntohl(chunk->sctp_hdr->vtag) == asoc->c.my_vtag) - return 1; + if (ntohl(chunk->sctp_hdr->vtag) != asoc->c.my_vtag) + return 0; chunk->transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; - return 0; + return 1; } /* Check VTAG of the packet matches the sender's own tag and the T bit is diff --git a/include/net/tcp.h b/include/net/tcp.h index 3166dc15d7d6..60c384569e9c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1576,6 +1576,7 @@ struct tcp_md5sig_key { u8 keylen; u8 family; /* AF_INET or AF_INET6 */ u8 prefixlen; + u8 flags; union tcp_md5_addr addr; int l3index; /* set if key added with L3 scope */ u8 key[TCP_MD5SIG_MAXKEYLEN]; @@ -1621,10 +1622,10 @@ struct tcp_md5sig_pool { int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, int l3index, + int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, int l3index); + int family, u8 prefixlen, int l3index, u8 flags); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 52b54d13f385..6acd4ccafbf7 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -10,6 +10,7 @@ #define __UAPI_MCTP_H #include <linux/types.h> +#include <linux/socket.h> typedef __u8 mctp_eid_t; @@ -18,11 +19,13 @@ struct mctp_addr { }; struct sockaddr_mctp { - unsigned short int smctp_family; - int smctp_network; + __kernel_sa_family_t smctp_family; + __u16 __smctp_pad0; + unsigned int smctp_network; struct mctp_addr smctp_addr; __u8 smctp_type; __u8 smctp_tag; + __u8 __smctp_pad1; }; #define MCTP_NET_ANY 0x0 diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e8136db44462..37ca76406f1e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1125,9 +1125,7 @@ static inline unsigned long br_multicast_lmqt(const struct net_bridge_mcast *brm static inline unsigned long br_multicast_gmi(const struct net_bridge_mcast *brmctx) { - /* use the RFC default of 2 for QRV */ - return 2 * brmctx->multicast_query_interval + - brmctx->multicast_query_response_interval; + return brmctx->multicast_membership_interval; } static inline bool diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 83d1798dfbb4..ba045f35114d 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -926,7 +926,9 @@ static int translate_table(struct net *net, const char *name, return -ENOMEM; for_each_possible_cpu(i) { newinfo->chainstack[i] = - vmalloc(array_size(udc_cnt, sizeof(*(newinfo->chainstack[0])))); + vmalloc_node(array_size(udc_cnt, + sizeof(*(newinfo->chainstack[0]))), + cpu_to_node(i)); if (!newinfo->chainstack[i]) { while (i) vfree(newinfo->chainstack[--i]); diff --git a/net/can/isotp.c b/net/can/isotp.c index caaa532ece94..df6968b28bf4 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -121,7 +121,7 @@ enum { struct tpcon { int idx; int len; - u8 state; + u32 state; u8 bs; u8 sn; u8 ll_dl; @@ -848,6 +848,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); + u32 old_state = so->tx.state; struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf; @@ -860,45 +861,55 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) return -EADDRNOTAVAIL; /* we do not support multiple buffers - for now */ - if (so->tx.state != ISOTP_IDLE || wq_has_sleeper(&so->wait)) { - if (msg->msg_flags & MSG_DONTWAIT) - return -EAGAIN; + if (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE || + wq_has_sleeper(&so->wait)) { + if (msg->msg_flags & MSG_DONTWAIT) { + err = -EAGAIN; + goto err_out; + } /* wait for complete transmission of current pdu */ - wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + if (err) + goto err_out; } - if (!size || size > MAX_MSG_LENGTH) - return -EINVAL; + if (!size || size > MAX_MSG_LENGTH) { + err = -EINVAL; + goto err_out; + } /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; /* does the given data fit into a single frame for SF_BROADCAST? */ if ((so->opt.flags & CAN_ISOTP_SF_BROADCAST) && - (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off)) - return -EINVAL; + (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off)) { + err = -EINVAL; + goto err_out; + } err = memcpy_from_msg(so->tx.buf, msg, size); if (err < 0) - return err; + goto err_out; dev = dev_get_by_index(sock_net(sk), so->ifindex); - if (!dev) - return -ENXIO; + if (!dev) { + err = -ENXIO; + goto err_out; + } skb = sock_alloc_send_skb(sk, so->ll.mtu + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) { dev_put(dev); - return err; + goto err_out; } can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; - so->tx.state = ISOTP_SENDING; so->tx.len = size; so->tx.idx = 0; @@ -954,15 +965,25 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); - return err; + goto err_out; } if (wait_tx_done) { /* wait for complete transmission of current pdu */ wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + + if (sk->sk_err) + return -sk->sk_err; } return size; + +err_out: + so->tx.state = old_state; + if (so->tx.state == ISOTP_IDLE) + wake_up_interruptible(&so->wait); + + return err; } static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index f6df20808f5e..16af1a7f80f6 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -330,6 +330,7 @@ int j1939_session_activate(struct j1939_session *session); void j1939_tp_schedule_txtimer(struct j1939_session *session, int msec); void j1939_session_timers_cancel(struct j1939_session *session); +#define J1939_MIN_TP_PACKET_SIZE 9 #define J1939_MAX_TP_PACKET_SIZE (7 * 0xff) #define J1939_MAX_ETP_PACKET_SIZE (7 * 0x00ffffff) diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 08c8606cfd9c..9bc55ecb37f9 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -249,11 +249,14 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) struct j1939_priv *priv, *priv_new; int ret; - priv = j1939_priv_get_by_ndev(ndev); + spin_lock(&j1939_netdev_lock); + priv = j1939_priv_get_by_ndev_locked(ndev); if (priv) { kref_get(&priv->rx_kref); + spin_unlock(&j1939_netdev_lock); return priv; } + spin_unlock(&j1939_netdev_lock); priv = j1939_priv_create(ndev); if (!priv) @@ -269,10 +272,10 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev) /* Someone was faster than us, use their priv and roll * back our's. */ + kref_get(&priv_new->rx_kref); spin_unlock(&j1939_netdev_lock); dev_put(ndev); kfree(priv); - kref_get(&priv_new->rx_kref); return priv_new; } j1939_priv_set(ndev, priv); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index bb5c4b8979be..6c0a0ebdd024 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1237,12 +1237,11 @@ static enum hrtimer_restart j1939_tp_rxtimer(struct hrtimer *hrtimer) session->err = -ETIME; j1939_session_deactivate(session); } else { - netdev_alert(priv->ndev, "%s: 0x%p: rx timeout, send abort\n", - __func__, session); - j1939_session_list_lock(session->priv); if (session->state >= J1939_SESSION_ACTIVE && session->state < J1939_SESSION_ACTIVE_MAX) { + netdev_alert(priv->ndev, "%s: 0x%p: rx timeout, send abort\n", + __func__, session); j1939_session_get(session); hrtimer_start(&session->rxtimer, ms_to_ktime(J1939_XTP_ABORT_TIMEOUT_MS), @@ -1609,6 +1608,8 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv, abort = J1939_XTP_ABORT_FAULT; else if (len > priv->tp_max_packet_size) abort = J1939_XTP_ABORT_RESOURCE; + else if (len < J1939_MIN_TP_PACKET_SIZE) + abort = J1939_XTP_ABORT_FAULT; } if (abort != J1939_XTP_NO_ABORT) { @@ -1789,6 +1790,7 @@ static void j1939_xtp_rx_dpo(struct j1939_priv *priv, struct sk_buff *skb, static void j1939_xtp_rx_dat_one(struct j1939_session *session, struct sk_buff *skb) { + enum j1939_xtp_abort abort = J1939_XTP_ABORT_FAULT; struct j1939_priv *priv = session->priv; struct j1939_sk_buff_cb *skcb, *se_skcb; struct sk_buff *se_skb = NULL; @@ -1803,9 +1805,11 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, skcb = j1939_skb_to_cb(skb); dat = skb->data; - if (skb->len <= 1) + if (skb->len != 8) { /* makes no sense */ + abort = J1939_XTP_ABORT_UNEXPECTED_DATA; goto out_session_cancel; + } switch (session->last_cmd) { case 0xff: @@ -1904,7 +1908,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, out_session_cancel: kfree_skb(se_skb); j1939_session_timers_cancel(session); - j1939_session_cancel(session, J1939_XTP_ABORT_FAULT); + j1939_session_cancel(session, abort); j1939_session_put(session); } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index da18094b5a04..e9911b18bdbf 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1374,12 +1374,15 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds, for_each_available_child_of_node(ports, port) { err = of_property_read_u32(port, "reg", ®); - if (err) + if (err) { + of_node_put(port); goto out_put_node; + } if (reg >= ds->num_ports) { dev_err(ds->dev, "port %pOF index %u exceeds num_ports (%zu)\n", port, reg, ds->num_ports); + of_node_put(port); err = -EINVAL; goto out_put_node; } @@ -1387,8 +1390,10 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds, dp = dsa_to_port(ds, reg); err = dsa_port_parse_of(dp, port); - if (err) + if (err) { + of_node_put(port); goto out_put_node; + } } out_put_node: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2e62e0d6373a..5b8ce65dfc06 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1037,6 +1037,20 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) DEFINE_STATIC_KEY_FALSE(tcp_md5_needed); EXPORT_SYMBOL(tcp_md5_needed); +static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new) +{ + if (!old) + return true; + + /* l3index always overrides non-l3index */ + if (old->l3index && new->l3index == 0) + return false; + if (old->l3index == 0 && new->l3index) + return true; + + return old->prefixlen < new->prefixlen; +} + /* Find the Key structure for an address. */ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, @@ -1059,7 +1073,7 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, lockdep_sock_is_held(sk)) { if (key->family != family) continue; - if (key->l3index && key->l3index != l3index) + if (key->flags & TCP_MD5SIG_FLAG_IFINDEX && key->l3index != l3index) continue; if (family == AF_INET) { mask = inet_make_mask(key->prefixlen); @@ -1074,8 +1088,7 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, match = false; } - if (match && (!best_match || - key->prefixlen > best_match->prefixlen)) + if (match && better_md5_match(best_match, key)) best_match = key; } return best_match; @@ -1085,7 +1098,7 @@ EXPORT_SYMBOL(__tcp_md5_do_lookup); static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, - int l3index) + int l3index, u8 flags) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; @@ -1105,7 +1118,9 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, lockdep_sock_is_held(sk)) { if (key->family != family) continue; - if (key->l3index && key->l3index != l3index) + if ((key->flags & TCP_MD5SIG_FLAG_IFINDEX) != (flags & TCP_MD5SIG_FLAG_IFINDEX)) + continue; + if (key->l3index != l3index) continue; if (!memcmp(&key->addr, addr, size) && key->prefixlen == prefixlen) @@ -1129,7 +1144,7 @@ EXPORT_SYMBOL(tcp_v4_md5_lookup); /* This can be called on a newly created socket, from other files */ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, int l3index, + int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ @@ -1137,7 +1152,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; - key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags); if (key) { /* Pre-existing entry - just update that one. * Note that the key might be used concurrently. @@ -1182,6 +1197,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key->family = family; key->prefixlen = prefixlen; key->l3index = l3index; + key->flags = flags; memcpy(&key->addr, addr, (family == AF_INET6) ? sizeof(struct in6_addr) : sizeof(struct in_addr)); @@ -1191,11 +1207,11 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, EXPORT_SYMBOL(tcp_md5_do_add); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, - u8 prefixlen, int l3index) + u8 prefixlen, int l3index, u8 flags) { struct tcp_md5sig_key *key; - key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags); if (!key) return -ENOENT; hlist_del_rcu(&key->node); @@ -1229,6 +1245,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, const union tcp_md5_addr *addr; u8 prefixlen = 32; int l3index = 0; + u8 flags; if (optlen < sizeof(cmd)) return -EINVAL; @@ -1239,6 +1256,8 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, if (sin->sin_family != AF_INET) return -EINVAL; + flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; + if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { prefixlen = cmd.tcpm_prefixlen; @@ -1246,7 +1265,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, return -EINVAL; } - if (optname == TCP_MD5SIG_EXT && + if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex && cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { struct net_device *dev; @@ -1267,12 +1286,12 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, addr = (union tcp_md5_addr *)&sin->sin_addr.s_addr; if (!cmd.tcpm_keylen) - return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index); + return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index, flags); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; - return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, + return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } @@ -1596,7 +1615,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, * memory, then we end up not copying the key * across. Shucks. */ - tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, + tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, key->flags, key->key, key->keylen, GFP_ATOMIC); sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 12f985f43bcc..2f044a49afa8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -464,13 +464,14 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) int ip6_forward(struct sk_buff *skb) { - struct inet6_dev *idev = __in6_dev_get_safely(skb->dev); struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); + struct inet6_dev *idev; u32 mtu; + idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); if (net->ipv6.devconf_all->forwarding == 0) goto error; diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index 733c83d38b30..4ad8b2032f1f 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -25,12 +25,7 @@ MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>"); static inline bool segsleft_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert) { - bool r; - pr_debug("segsleft_match:%c 0x%x <= 0x%x <= 0x%x\n", - invert ? '!' : ' ', min, id, max); - r = (id >= min && id <= max) ^ invert; - pr_debug(" result %s\n", r ? "PASS" : "FAILED"); - return r; + return (id >= min && id <= max) ^ invert; } static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) @@ -65,30 +60,6 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) return false; } - pr_debug("IPv6 RT LEN %u %u ", hdrlen, rh->hdrlen); - pr_debug("TYPE %04X ", rh->type); - pr_debug("SGS_LEFT %u %02X\n", rh->segments_left, rh->segments_left); - - pr_debug("IPv6 RT segsleft %02X ", - segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], - rh->segments_left, - !!(rtinfo->invflags & IP6T_RT_INV_SGS))); - pr_debug("type %02X %02X %02X ", - rtinfo->rt_type, rh->type, - (!(rtinfo->flags & IP6T_RT_TYP) || - ((rtinfo->rt_type == rh->type) ^ - !!(rtinfo->invflags & IP6T_RT_INV_TYP)))); - pr_debug("len %02X %04X %02X ", - rtinfo->hdrlen, hdrlen, - !(rtinfo->flags & IP6T_RT_LEN) || - ((rtinfo->hdrlen == hdrlen) ^ - !!(rtinfo->invflags & IP6T_RT_INV_LEN))); - pr_debug("res %02X %02X %02X ", - rtinfo->flags & IP6T_RT_RES, - ((const struct rt0_hdr *)rh)->reserved, - !((rtinfo->flags & IP6T_RT_RES) && - (((const struct rt0_hdr *)rh)->reserved))); - ret = (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], rh->segments_left, !!(rtinfo->invflags & IP6T_RT_INV_SGS))) && @@ -107,22 +78,22 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) reserved), sizeof(_reserved), &_reserved); + if (!rp) { + par->hotdrop = true; + return false; + } ret = (*rp == 0); } - pr_debug("#%d ", rtinfo->addrnr); if (!(rtinfo->flags & IP6T_RT_FST)) { return ret; } else if (rtinfo->flags & IP6T_RT_FST_NSTRICT) { - pr_debug("Not strict "); if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) { - pr_debug("There isn't enough space\n"); return false; } else { unsigned int i = 0; - pr_debug("#%d ", rtinfo->addrnr); for (temp = 0; temp < (unsigned int)((hdrlen - 8) / 16); temp++) { @@ -138,26 +109,20 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) return false; } - if (ipv6_addr_equal(ap, &rtinfo->addrs[i])) { - pr_debug("i=%d temp=%d;\n", i, temp); + if (ipv6_addr_equal(ap, &rtinfo->addrs[i])) i++; - } if (i == rtinfo->addrnr) break; } - pr_debug("i=%d #%d\n", i, rtinfo->addrnr); if (i == rtinfo->addrnr) return ret; else return false; } } else { - pr_debug("Strict "); if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) { - pr_debug("There isn't enough space\n"); return false; } else { - pr_debug("#%d ", rtinfo->addrnr); for (temp = 0; temp < rtinfo->addrnr; temp++) { ap = skb_header_pointer(skb, ptr @@ -173,7 +138,6 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) if (!ipv6_addr_equal(ap, &rtinfo->addrs[temp])) break; } - pr_debug("temp=%d #%d\n", temp, rtinfo->addrnr); if (temp == rtinfo->addrnr && temp == (unsigned int)((hdrlen - 8) / 16)) return ret; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0ce52d46e4f8..b03dd02c9f13 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -599,6 +599,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; int l3index = 0; u8 prefixlen; + u8 flags; if (optlen < sizeof(cmd)) return -EINVAL; @@ -609,6 +610,8 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, if (sin6->sin6_family != AF_INET6) return -EINVAL; + flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; + if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { prefixlen = cmd.tcpm_prefixlen; @@ -619,7 +622,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128; } - if (optname == TCP_MD5SIG_EXT && + if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex && cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { struct net_device *dev; @@ -640,9 +643,9 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], AF_INET, prefixlen, - l3index); + l3index, flags); return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6, prefixlen, l3index); + AF_INET6, prefixlen, l3index, flags); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) @@ -650,12 +653,12 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], - AF_INET, prefixlen, l3index, + AF_INET, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, - AF_INET6, prefixlen, l3index, + AF_INET6, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } @@ -1404,7 +1407,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, - AF_INET6, 128, l3index, key->key, key->keylen, + AF_INET6, 128, l3index, key->flags, key->key, key->keylen, sk_gfp_mask(sk, GFP_ATOMIC)); } #endif diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 54395266339d..92a747896f80 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -109,7 +109,7 @@ config NF_CONNTRACK_MARK config NF_CONNTRACK_SECMARK bool 'Connection tracking security mark support' depends on NETWORK_SECMARK - default m if NETFILTER_ADVANCED=n + default y if NETFILTER_ADVANCED=n help This option enables security markings to be applied to connections. Typically they are copied to connections from diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c25097092a06..29ec3ef63edc 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -4090,6 +4090,11 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; tbl[idx++].data = &ipvs->sysctl_schedule_icmp; tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; +#ifdef CONFIG_IP_VS_DEBUG + /* Global sysctls must be ro in non-init netns */ + if (!net_eq(net, &init_net)) + tbl[idx++].mode = 0444; +#endif ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); if (ipvs->sysctl_hdr == NULL) { diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 5b02408a920b..3ced0eb6b7c3 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -342,12 +342,6 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, return; } - /* UNREGISTER events are also happening on netns exit. - * - * Although nf_tables core releases all tables/chains, only this event - * handler provides guarantee that hook->ops.dev is still accessible, - * so we cannot skip exiting net namespaces. - */ __nft_release_basechain(ctx); } @@ -366,6 +360,9 @@ static int nf_tables_netdev_event(struct notifier_block *this, event != NETDEV_CHANGENAME) return NOTIFY_DONE; + if (!check_net(ctx.net)) + return NOTIFY_DONE; + nft_net = nft_pernet(ctx.net); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 7b2f359bfce4..2f7cf5ecebf4 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -137,7 +137,7 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) { int ret; - info->timer = kmalloc(sizeof(*info->timer), GFP_KERNEL); + info->timer = kzalloc(sizeof(*info->timer), GFP_KERNEL); if (!info->timer) { ret = -ENOMEM; goto out; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index ad9df0cb4b98..90866ae45573 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -960,6 +960,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, tmpl = p->tmpl; tcf_lastuse_update(&c->tcf_tm); + tcf_action_update_bstats(&c->common, skb); if (clear) { qdisc_skb_cb(skb)->post_ct = false; @@ -1049,7 +1050,6 @@ out_push: qdisc_skb_cb(skb)->post_ct = true; out_clear: - tcf_action_update_bstats(&c->common, skb); if (defrag) qdisc_skb_cb(skb)->pkt_len = skb->len; return retval; diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 21b646d10b88..86ab429fe7f3 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -43,3 +43,4 @@ CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_MIRRED=m CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y +CONFIG_CRYPTO_SM4=y diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 13350cd5c8ac..8e67a252b672 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -289,6 +289,12 @@ set_sysctl() run_cmd sysctl -q -w $* } +# get sysctl values in NS-A +get_sysctl() +{ + ${NSA_CMD} sysctl -n $* +} + ################################################################################ # Setup for tests @@ -1003,6 +1009,60 @@ ipv4_tcp_md5() run_cmd nettest -s -I ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET} log_test $? 1 "MD5: VRF: Device must be a VRF - prefix" + test_ipv4_md5_vrf__vrf_server__no_bind_ifindex + test_ipv4_md5_vrf__global_server__bind_ifindex0 +} + +test_ipv4_md5_vrf__vrf_server__no_bind_ifindex() +{ + log_start + show_hint "Simulates applications using VRF without TCP_MD5SIG_FLAG_IFINDEX" + run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: VRF-bound server, unbound key accepts connection" + + log_start + show_hint "Binding both the socket and the key is not required but it works" + run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: VRF-bound server, bound key accepts connection" +} + +test_ipv4_md5_vrf__global_server__bind_ifindex0() +{ + # This particular test needs tcp_l3mdev_accept=1 for Global server to accept VRF connections + local old_tcp_l3mdev_accept + old_tcp_l3mdev_accept=$(get_sysctl net.ipv4.tcp_l3mdev_accept) + set_sysctl net.ipv4.tcp_l3mdev_accept=1 + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 2 "MD5: VRF: Global server, Key bound to ifindex=0 rejects VRF connection" + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key bound to ifindex=0 accepts non-VRF connection" + log_start + + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts VRF connection" + + log_start + run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex & + sleep 1 + run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW} + log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts non-VRF connection" + + # restore value + set_sysctl net.ipv4.tcp_l3mdev_accept="$old_tcp_l3mdev_accept" } ipv4_tcp_novrf() diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index d97bd6889446..72ee644d47bf 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -9,6 +9,7 @@ TEST_PROGS = bridge_igmp.sh \ gre_inner_v4_multipath.sh \ gre_inner_v6_multipath.sh \ gre_multipath.sh \ + ip6_forward_instats_vrf.sh \ ip6gre_inner_v4_multipath.sh \ ip6gre_inner_v6_multipath.sh \ ipip_flat_gre_key.sh \ diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index b802c14d2950..e5e2fbeca22e 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -39,3 +39,5 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# IPv6 traceroute utility name. +TROUTE6=traceroute6 diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh new file mode 100755 index 000000000000..9f5b3e2e5e95 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -0,0 +1,172 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Test ipv6 stats on the incoming if when forwarding with VRF + +ALL_TESTS=" + ipv6_ping + ipv6_in_too_big_err + ipv6_in_hdr_err + ipv6_in_addr_err + ipv6_in_discard +" + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 2001:1:1::2/64 + ip -6 route add vrf v$h1 2001:1:2::/64 via 2001:1:1::1 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 2001:1:2::/64 via 2001:1:1::1 + simple_if_fini $h1 2001:1:1::2/64 +} + +router_create() +{ + vrf_create router + __simple_if_init $rtr1 router 2001:1:1::1/64 + __simple_if_init $rtr2 router 2001:1:2::1/64 + mtu_set $rtr2 1280 +} + +router_destroy() +{ + mtu_restore $rtr2 + __simple_if_fini $rtr2 2001:1:2::1/64 + __simple_if_fini $rtr1 2001:1:1::1/64 + vrf_destroy router +} + +h2_create() +{ + simple_if_init $h2 2001:1:2::2/64 + ip -6 route add vrf v$h2 2001:1:1::/64 via 2001:1:2::1 + mtu_set $h2 1280 +} + +h2_destroy() +{ + mtu_restore $h2 + ip -6 route del vrf v$h2 2001:1:1::/64 via 2001:1:2::1 + simple_if_fini $h2 2001:1:2::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rtr1=${NETIFS[p2]} + + rtr2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + h1_create + router_create + h2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + h2_destroy + router_destroy + h1_destroy + vrf_cleanup +} + +ipv6_in_too_big_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors) + local vrf_name=$(master_name_get $h1) + + # Send too big packets + ip vrf exec $vrf_name \ + $PING6 -s 1300 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + + local t1=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InTooBigErrors" +} + +ipv6_in_hdr_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InHdrErrors) + local vrf_name=$(master_name_get $h1) + + # Send packets with hop limit 1, easiest with traceroute6 as some ping6 + # doesn't allow hop limit to be specified + ip vrf exec $vrf_name \ + $TROUTE6 2001:1:2::2 &> /dev/null + + local t1=$(ipv6_stats_get $rtr1 Ip6InHdrErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InHdrErrors" +} + +ipv6_in_addr_err() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InAddrErrors) + local vrf_name=$(master_name_get $h1) + + # Disable forwarding temporary while sending the packet + sysctl -qw net.ipv6.conf.all.forwarding=0 + ip vrf exec $vrf_name \ + $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + sysctl -qw net.ipv6.conf.all.forwarding=1 + + local t1=$(ipv6_stats_get $rtr1 Ip6InAddrErrors) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InAddrErrors" +} + +ipv6_in_discard() +{ + RET=0 + + local t0=$(ipv6_stats_get $rtr1 Ip6InDiscards) + local vrf_name=$(master_name_get $h1) + + # Add a policy to discard + ip xfrm policy add dst 2001:1:2::2/128 dir fwd action block + ip vrf exec $vrf_name \ + $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null + ip xfrm policy del dst 2001:1:2::2/128 dir fwd + + local t1=$(ipv6_stats_get $rtr1 Ip6InDiscards) + test "$((t1 - t0))" -ne 0 + check_err $? + log_test "Ip6InDiscards" +} +ipv6_ping() +{ + RET=0 + + ping6_test $h1 2001:1:2::2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index e7fc5c35b569..92087d423bcf 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -751,6 +751,14 @@ qdisc_parent_stats_get() | jq '.[] | select(.parent == "'"$parent"'") | '"$selector" } +ipv6_stats_get() +{ + local dev=$1; shift + local stat=$1; shift + + cat /proc/net/dev_snmp6/$dev | grep "^$stat" | cut -f2 +} + humanize() { local speed=$1; shift diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c index bd6288302094..b599003eb5ba 100644 --- a/tools/testing/selftests/net/nettest.c +++ b/tools/testing/selftests/net/nettest.c @@ -28,6 +28,7 @@ #include <unistd.h> #include <time.h> #include <errno.h> +#include <getopt.h> #include <linux/xfrm.h> #include <linux/ipsec.h> @@ -101,6 +102,8 @@ struct sock_args { struct sockaddr_in6 v6; } md5_prefix; unsigned int prefix_len; + /* 0: default, -1: force off, +1: force on */ + int bind_key_ifindex; /* expected addresses and device index for connection */ const char *expected_dev; @@ -271,11 +274,14 @@ static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args } memcpy(&md5sig.tcpm_addr, addr, alen); - if (args->ifindex) { + if ((args->ifindex && args->bind_key_ifindex >= 0) || args->bind_key_ifindex >= 1) { opt = TCP_MD5SIG_EXT; md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_IFINDEX; md5sig.tcpm_ifindex = args->ifindex; + log_msg("TCP_MD5SIG_FLAG_IFINDEX set tcpm_ifindex=%d\n", md5sig.tcpm_ifindex); + } else { + log_msg("TCP_MD5SIG_FLAG_IFINDEX off\n", md5sig.tcpm_ifindex); } rc = setsockopt(sd, IPPROTO_TCP, opt, &md5sig, sizeof(md5sig)); @@ -1822,6 +1828,14 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args) } #define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq" +#define OPT_FORCE_BIND_KEY_IFINDEX 1001 +#define OPT_NO_BIND_KEY_IFINDEX 1002 + +static struct option long_opts[] = { + {"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX}, + {"no-bind-key-ifindex", 0, 0, OPT_NO_BIND_KEY_IFINDEX}, + {0, 0, 0, 0} +}; static void print_usage(char *prog) { @@ -1858,6 +1872,10 @@ static void print_usage(char *prog) " -M password use MD5 sum protection\n" " -X password MD5 password for client mode\n" " -m prefix/len prefix and length to use for MD5 key\n" + " --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n" + " --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n" + " (default: only if -I is passed)\n" + "\n" " -g grp multicast group (e.g., 239.1.1.1)\n" " -i interactive mode (default is echo and terminate)\n" "\n" @@ -1893,7 +1911,7 @@ int main(int argc, char *argv[]) * process input args */ - while ((rc = getopt(argc, argv, GETOPT_STR)) != -1) { + while ((rc = getopt_long(argc, argv, GETOPT_STR, long_opts, NULL)) != -1) { switch (rc) { case 'B': both_mode = 1; @@ -1966,6 +1984,12 @@ int main(int argc, char *argv[]) case 'M': args.password = optarg; break; + case OPT_FORCE_BIND_KEY_IFINDEX: + args.bind_key_ifindex = 1; + break; + case OPT_NO_BIND_KEY_IFINDEX: + args.bind_key_ifindex = -1; + break; case 'X': args.client_pw = optarg; break; diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index 427d94816f2d..d4ffebb989f8 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -199,7 +199,6 @@ fi # test basic connectivity if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then echo "ERROR: ns1 cannot reach ns2" 1>&2 - bash exit 1 fi diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index d7e07f4c3d7f..da1c1e4b6c86 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -741,6 +741,149 @@ EOF return $lret } +# test port shadowing. +# create two listening services, one on router (ns0), one +# on client (ns2), which is masqueraded from ns1 point of view. +# ns2 sends udp packet coming from service port to ns1, on a highport. +# Later, if n1 uses same highport to connect to ns0:service, packet +# might be port-forwarded to ns2 instead. + +# second argument tells if we expect the 'fake-entry' to take effect +# (CLIENT) or not (ROUTER). +test_port_shadow() +{ + local test=$1 + local expect=$2 + local daddrc="10.0.1.99" + local daddrs="10.0.1.1" + local result="" + local logmsg="" + + echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & + nc_r=$! + + echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & + nc_c=$! + + # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. + echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + + # ns1 tries to connect to ns0:1405. With default settings this should connect + # to client, it matches the conntrack entry created above. + + result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405) + + if [ "$result" = "$expect" ] ;then + echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}" + else + echo "ERROR: portshadow test $test: got reply from \"$result\", not $expect as intended" + ret=1 + fi + + kill $nc_r $nc_c 2>/dev/null + + # flush udp entries for next test round, if any + ip netns exec "$ns0" conntrack -F >/dev/null 2>&1 +} + +# This prevents port shadow of router service via packet filter, +# packets claiming to originate from service port from internal +# network are dropped. +test_port_shadow_filter() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family filter { + chain forward { + type filter hook forward priority 0; policy accept; + meta iif veth1 udp sport 1405 drop + } +} +EOF + test_port_shadow "port-filter" "ROUTER" + + ip netns exec "$ns0" nft delete table $family filter +} + +# This prevents port shadow of router service via notrack. +test_port_shadow_notrack() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family raw { + chain prerouting { + type filter hook prerouting priority -300; policy accept; + meta iif veth0 udp dport 1405 notrack + udp dport 1405 notrack + } + chain output { + type filter hook output priority -300; policy accept; + udp sport 1405 notrack + } +} +EOF + test_port_shadow "port-notrack" "ROUTER" + + ip netns exec "$ns0" nft delete table $family raw +} + +# This prevents port shadow of router service via sport remap. +test_port_shadow_pat() +{ + local family=$1 + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family pat { + chain postrouting { + type nat hook postrouting priority -1; policy accept; + meta iif veth1 udp sport <= 1405 masquerade to : 1406-65535 random + } +} +EOF + test_port_shadow "pat" "ROUTER" + + ip netns exec "$ns0" nft delete table $family pat +} + +test_port_shadowing() +{ + local family="ip" + + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table $family nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + meta oif veth0 masquerade + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add add $family masquerade hook" + return $ksft_skip + fi + + # test default behaviour. Packet from ns1 to ns0 is redirected to ns2. + test_port_shadow "default" "CLIENT" + + # test packet filter based mitigation: prevent forwarding of + # packets claiming to come from the service port. + test_port_shadow_filter "$family" + + # test conntrack based mitigation: connections going or coming + # from router:service bypass connection tracking. + test_port_shadow_notrack "$family" + + # test nat based mitigation: fowarded packets coming from service port + # are masqueraded with random highport. + test_port_shadow_pat "$family" + + ip netns exec "$ns0" nft delete table $family nat +} # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do @@ -861,6 +1004,8 @@ reset_counters $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet +test_port_shadowing + if [ $ret -ne 0 ];then echo -n "FAIL: " nft --version diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c index cec6f5a738e1..fa927ad16f8a 100644 --- a/tools/testing/vsock/vsock_diag_test.c +++ b/tools/testing/vsock/vsock_diag_test.c @@ -332,8 +332,6 @@ static void test_no_sockets(const struct test_opts *opts) read_vsock_stat(&sockets); check_no_sockets(&sockets); - - free_sock_stat(&sockets); } static void test_listen_socket_server(const struct test_opts *opts) |