diff options
| author |   Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-27 13:36:59 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-27 13:36:59 -0700 |
| commit | 23758867219c8d84c8363316e6dd2f9fd7ae3049 (patch) | |
| tree | 0c487804be739784f6a93e72a5bd1367bd7b5456 | |
| parent | Merge tag 'execve-v6.1-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux (diff) | |
| parent | net: enetc: survive memory pressure without crashing (diff) | |
| download | wireguard-linux-23758867219c8d84c8363316e6dd2f9fd7ae3049.tar.xz wireguard-linux-23758867219c8d84c8363316e6dd2f9fd7ae3049.zip | |
Merge tag 'net-6.1-rc3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from 802.15.4 (Zigbee et al).
Current release - regressions:
- ipa: fix bugs in the register conversion for IPA v3.1 and v3.5.1
Current release - new code bugs:
- mptcp: fix abba deadlock on fastopen
- eth: stmmac: rk3588: allow multiple gmac controllers in one system
Previous releases - regressions:
- ip: rework the fix for dflt addr selection for connected nexthop
- net: couple more fixes for misinterpreting bits in struct page
after the signature was added
Previous releases - always broken:
- ipv6: ensure sane device mtu in tunnels
- openvswitch: switch from WARN to pr_warn on a user-triggerable path
- ethtool: eeprom: fix null-deref on genl_info in dump
- ieee802154: more return code fixes for corner cases in
dgram_sendmsg
- mac802154: fix link-quality-indicator recording
- eth: mlx5: fixes for IPsec, PTP timestamps, OvS and conntrack
offload
- eth: fec: limit register access on i.MX6UL
- eth: bcm4908_enet: update TX stats after actual transmission
- can: rcar_canfd: improve IRQ handling for RZ/G2L
Misc:
- genetlink: piggy back on the newly added resv_op_start to enforce
more sanity checks on new commands"
* tag 'net-6.1-rc3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (57 commits)
net: enetc: survive memory pressure without crashing
kcm: do not sense pfmemalloc status in kcm_sendpage()
net: do not sense pfmemalloc status in skb_append_pagefrags()
net/mlx5e: Fix macsec sci endianness at rx sa update
net/mlx5e: Fix wrong bitwise comparison usage in macsec_fs_rx_add_rule function
net/mlx5e: Fix macsec rx security association (SA) update/delete
net/mlx5e: Fix macsec coverity issue at rx sa update
net/mlx5: Fix crash during sync firmware reset
net/mlx5: Update fw fatal reporter state on PCI handlers successful recover
net/mlx5e: TC, Fix cloned flow attr instance dests are not zeroed
net/mlx5e: TC, Reject forwarding from internal port to internal port
net/mlx5: Fix possible use-after-free in async command interface
net/mlx5: ASO, Create the ASO SQ with the correct timestamp format
net/mlx5e: Update restore chain id for slow path packets
net/mlx5e: Extend SKB room check to include PTP-SQ
net/mlx5: DR, Fix matcher disconnect error flow
net/mlx5: Wait for firmware to enable CRS before pci_restore_state
net/mlx5e: Do not increment ESN when updating IPsec ESN state
netdevsim: remove dir in nsim_dev_debugfs_init() when creating ports dir failed
netdevsim: fix memory leak in nsim_drv_probe() when nsim_dev_resources_register() failed
...
62 files changed, 1197 insertions, 347 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 3bb30c0d1cb4..10c1344b4473 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15436,6 +15436,7 @@ S: Maintained W: http://openvswitch.org F: include/uapi/linux/openvswitch.h F: net/openvswitch/ +F: tools/testing/selftests/net/openvswitch/ OPERATING PERFORMANCE POINTS (OPP) M: Viresh Kumar <vireshk@kernel.org> diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c index c469b2f3e57d..b0ed798ae70f 100644 --- a/drivers/net/can/mscan/mpc5xxx_can.c +++ b/drivers/net/can/mscan/mpc5xxx_can.c @@ -322,14 +322,14 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev) &mscan_clksrc); if (!priv->can.clock.freq) { dev_err(&ofdev->dev, "couldn't get MSCAN clock properties\n"); - goto exit_free_mscan; + goto exit_put_clock; } err = register_mscandev(dev, mscan_clksrc); if (err) { dev_err(&ofdev->dev, "registering %s failed (err=%d)\n", DRV_NAME, err); - goto exit_free_mscan; + goto exit_put_clock; } dev_info(&ofdev->dev, "MSCAN at 0x%p, irq %d, clock %d Hz\n", @@ -337,7 +337,9 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev) return 0; -exit_free_mscan: +exit_put_clock: + if (data->put_clock) + data->put_clock(ofdev); free_candev(dev); exit_dispose_irq: irq_dispose_mapping(irq); diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index 567620d215f8..198da643ee6d 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -1157,11 +1157,13 @@ static void rcar_canfd_handle_global_receive(struct rcar_canfd_global *gpriv, u3 { struct rcar_canfd_channel *priv = gpriv->ch[ch]; u32 ridx = ch + RCANFD_RFFIFO_IDX; - u32 sts; + u32 sts, cc; /* Handle Rx interrupts */ sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(gpriv, ridx)); - if (likely(sts & RCANFD_RFSTS_RFIF)) { + cc = rcar_canfd_read(priv->base, RCANFD_RFCC(gpriv, ridx)); + if (likely(sts & RCANFD_RFSTS_RFIF && + cc & RCANFD_RFCC_RFIE)) { if (napi_schedule_prep(&priv->napi)) { /* Disable Rx FIFO interrupts */ rcar_canfd_clear_bit(priv->base, @@ -1244,11 +1246,9 @@ static void rcar_canfd_handle_channel_tx(struct rcar_canfd_global *gpriv, u32 ch static irqreturn_t rcar_canfd_channel_tx_interrupt(int irq, void *dev_id) { - struct rcar_canfd_global *gpriv = dev_id; - u32 ch; + struct rcar_canfd_channel *priv = dev_id; - for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) - rcar_canfd_handle_channel_tx(gpriv, ch); + rcar_canfd_handle_channel_tx(priv->gpriv, priv->channel); return IRQ_HANDLED; } @@ -1276,11 +1276,9 @@ static void rcar_canfd_handle_channel_err(struct rcar_canfd_global *gpriv, u32 c static irqreturn_t rcar_canfd_channel_err_interrupt(int irq, void *dev_id) { - struct rcar_canfd_global *gpriv = dev_id; - u32 ch; + struct rcar_canfd_channel *priv = dev_id; - for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) - rcar_canfd_handle_channel_err(gpriv, ch); + rcar_canfd_handle_channel_err(priv->gpriv, priv->channel); return IRQ_HANDLED; } @@ -1721,6 +1719,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, priv->ndev = ndev; priv->base = gpriv->base; priv->channel = ch; + priv->gpriv = gpriv; priv->can.clock.freq = fcan_freq; dev_info(&pdev->dev, "can_clk rate is %u\n", priv->can.clock.freq); @@ -1749,7 +1748,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, } err = devm_request_irq(&pdev->dev, err_irq, rcar_canfd_channel_err_interrupt, 0, - irq_name, gpriv); + irq_name, priv); if (err) { dev_err(&pdev->dev, "devm_request_irq CH Err(%d) failed, error %d\n", err_irq, err); @@ -1763,7 +1762,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, } err = devm_request_irq(&pdev->dev, tx_irq, rcar_canfd_channel_tx_interrupt, 0, - irq_name, gpriv); + irq_name, priv); if (err) { dev_err(&pdev->dev, "devm_request_irq Tx (%d) failed, error %d\n", tx_irq, err); @@ -1789,7 +1788,6 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, priv->can.do_set_mode = rcar_canfd_do_set_mode; priv->can.do_get_berr_counter = rcar_canfd_get_berr_counter; - priv->gpriv = gpriv; SET_NETDEV_DEV(ndev, &pdev->dev); netif_napi_add_weight(ndev, &priv->napi, rcar_canfd_rx_poll, diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index c320de474f40..24883a65ca66 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -1415,11 +1415,14 @@ static int mcp251x_can_probe(struct spi_device *spi) ret = mcp251x_gpio_setup(priv); if (ret) - goto error_probe; + goto out_unregister_candev; netdev_info(net, "MCP%x successfully initialized.\n", priv->model); return 0; +out_unregister_candev: + unregister_candev(net); + error_probe: destroy_workqueue(priv->wq); priv->wq = NULL; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 7b52fda73d82..66f672ea631b 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -1875,7 +1875,7 @@ static int kvaser_usb_hydra_start_chip(struct kvaser_usb_net_priv *priv) { int err; - init_completion(&priv->start_comp); + reinit_completion(&priv->start_comp); err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_START_CHIP_REQ, priv->channel); @@ -1893,7 +1893,7 @@ static int kvaser_usb_hydra_stop_chip(struct kvaser_usb_net_priv *priv) { int err; - init_completion(&priv->stop_comp); + reinit_completion(&priv->stop_comp); /* Make sure we do not report invalid BUS_OFF from CMD_CHIP_STATE_EVENT * see comment in kvaser_usb_hydra_update_state() diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 50f2ac8319ff..19958037720f 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -1320,7 +1320,7 @@ static int kvaser_usb_leaf_start_chip(struct kvaser_usb_net_priv *priv) { int err; - init_completion(&priv->start_comp); + reinit_completion(&priv->start_comp); err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_START_CHIP, priv->channel); @@ -1338,7 +1338,7 @@ static int kvaser_usb_leaf_stop_chip(struct kvaser_usb_net_priv *priv) { int err; - init_completion(&priv->stop_comp); + reinit_completion(&priv->stop_comp); err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_STOP_CHIP, priv->channel); diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c index 93ccf549e2ed..a737b1913cf9 100644 --- a/drivers/net/ethernet/broadcom/bcm4908_enet.c +++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c @@ -561,8 +561,6 @@ static netdev_tx_t bcm4908_enet_start_xmit(struct sk_buff *skb, struct net_devic if (++ring->write_idx == ring->length - 1) ring->write_idx = 0; - enet->netdev->stats.tx_bytes += skb->len; - enet->netdev->stats.tx_packets++; return NETDEV_TX_OK; } @@ -635,6 +633,7 @@ static int bcm4908_enet_poll_tx(struct napi_struct *napi, int weight) struct bcm4908_enet_dma_ring_bd *buf_desc; struct bcm4908_enet_dma_ring_slot *slot; struct device *dev = enet->dev; + unsigned int bytes = 0; int handled = 0; while (handled < weight && tx_ring->read_idx != tx_ring->write_idx) { @@ -645,12 +644,17 @@ static int bcm4908_enet_poll_tx(struct napi_struct *napi, int weight) dma_unmap_single(dev, slot->dma_addr, slot->len, DMA_TO_DEVICE); dev_kfree_skb(slot->skb); - if (++tx_ring->read_idx == tx_ring->length) - tx_ring->read_idx = 0; handled++; + bytes += slot->len; + + if (++tx_ring->read_idx == tx_ring->length) + tx_ring->read_idx = 0; } + enet->netdev->stats.tx_packets += handled; + enet->netdev->stats.tx_bytes += bytes; + if (handled < weight) { napi_complete_done(napi, handled); bcm4908_enet_dma_ring_intrs_on(enet, tx_ring); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 867f14c30e09..425d6ccd5413 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1991,6 +1991,9 @@ static int bcm_sysport_open(struct net_device *dev) goto out_clk_disable; } + /* Indicate that the MAC is responsible for PHY PM */ + phydev->mac_managed_pm = true; + /* Reset house keeping link status */ priv->old_duplex = -1; priv->old_link = -1; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 54bc92fc6bf0..f8c06c3f9464 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2090,7 +2090,12 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) else enetc_rxbdr_wr(hw, idx, ENETC_RBBSR, ENETC_RXB_DMA_SIZE); + /* Also prepare the consumer index in case page allocation never + * succeeds. In that case, hardware will never advance producer index + * to match consumer index, and will drop all frames. + */ enetc_rxbdr_wr(hw, idx, ENETC_RBPIR, 0); + enetc_rxbdr_wr(hw, idx, ENETC_RBCIR, 1); /* enable Rx ints by setting pkt thr to 1 */ enetc_rxbdr_wr(hw, idx, ENETC_RBICR0, ENETC_RBICR0_ICEN | 0x1); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 98d5cd313fdd..28ef4d3c1878 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2432,6 +2432,31 @@ static u32 fec_enet_register_offset[] = { IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR, IEEE_R_FDXFC, IEEE_R_OCTETS_OK }; +/* for i.MX6ul */ +static u32 fec_enet_register_offset_6ul[] = { + FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0, + FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL, + FEC_X_CNTRL, FEC_ADDR_LOW, FEC_ADDR_HIGH, FEC_OPD, FEC_TXIC0, FEC_RXIC0, + FEC_HASH_TABLE_HIGH, FEC_HASH_TABLE_LOW, FEC_GRP_HASH_TABLE_HIGH, + FEC_GRP_HASH_TABLE_LOW, FEC_X_WMRK, FEC_R_DES_START_0, + FEC_X_DES_START_0, FEC_R_BUFF_SIZE_0, FEC_R_FIFO_RSFL, FEC_R_FIFO_RSEM, + FEC_R_FIFO_RAEM, FEC_R_FIFO_RAFL, FEC_RACC, + RMON_T_DROP, RMON_T_PACKETS, RMON_T_BC_PKT, RMON_T_MC_PKT, + RMON_T_CRC_ALIGN, RMON_T_UNDERSIZE, RMON_T_OVERSIZE, RMON_T_FRAG, + RMON_T_JAB, RMON_T_COL, RMON_T_P64, RMON_T_P65TO127, RMON_T_P128TO255, + RMON_T_P256TO511, RMON_T_P512TO1023, RMON_T_P1024TO2047, + RMON_T_P_GTE2048, RMON_T_OCTETS, + IEEE_T_DROP, IEEE_T_FRAME_OK, IEEE_T_1COL, IEEE_T_MCOL, IEEE_T_DEF, + IEEE_T_LCOL, IEEE_T_EXCOL, IEEE_T_MACERR, IEEE_T_CSERR, IEEE_T_SQE, + IEEE_T_FDXFC, IEEE_T_OCTETS_OK, + RMON_R_PACKETS, RMON_R_BC_PKT, RMON_R_MC_PKT, RMON_R_CRC_ALIGN, + RMON_R_UNDERSIZE, RMON_R_OVERSIZE, RMON_R_FRAG, RMON_R_JAB, + RMON_R_RESVD_O, RMON_R_P64, RMON_R_P65TO127, RMON_R_P128TO255, + RMON_R_P256TO511, RMON_R_P512TO1023, RMON_R_P1024TO2047, + RMON_R_P_GTE2048, RMON_R_OCTETS, + IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR, + IEEE_R_FDXFC, IEEE_R_OCTETS_OK +}; #else static __u32 fec_enet_register_version = 1; static u32 fec_enet_register_offset[] = { @@ -2456,7 +2481,24 @@ static void fec_enet_get_regs(struct net_device *ndev, u32 *buf = (u32 *)regbuf; u32 i, off; int ret; +#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ + defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ + defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST) + u32 *reg_list; + u32 reg_cnt; + if (!of_machine_is_compatible("fsl,imx6ul")) { + reg_list = fec_enet_register_offset; + reg_cnt = ARRAY_SIZE(fec_enet_register_offset); + } else { + reg_list = fec_enet_register_offset_6ul; + reg_cnt = ARRAY_SIZE(fec_enet_register_offset_6ul); + } +#else + /* coldfire */ + static u32 *reg_list = fec_enet_register_offset; + static const u32 reg_cnt = ARRAY_SIZE(fec_enet_register_offset); +#endif ret = pm_runtime_resume_and_get(dev); if (ret < 0) return; @@ -2465,8 +2507,8 @@ static void fec_enet_get_regs(struct net_device *ndev, memset(buf, 0, regs->len); - for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) { - off = fec_enet_register_offset[i]; + for (i = 0; i < reg_cnt; i++) { + off = reg_list[i]; if ((off == FEC_R_BOUND || off == FEC_R_FSTART) && !(fep->quirks & FEC_QUIRK_HAS_FRREG)) diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 294bdbbeacc3..b4aff59b3eb4 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -2900,6 +2900,7 @@ static struct device *ehea_register_port(struct ehea_port *port, ret = of_device_register(&port->ofdev); if (ret) { pr_err("failed to register device. ret=%d\n", ret); + put_device(&port->ofdev.dev); goto out; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 87f36d1ce800..4a6a6e48c615 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -3185,10 +3185,17 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd) if (cmd->flow_type == TCP_V4_FLOW || cmd->flow_type == UDP_V4_FLOW) { - if (i_set & I40E_L3_SRC_MASK) - cmd->data |= RXH_IP_SRC; - if (i_set & I40E_L3_DST_MASK) - cmd->data |= RXH_IP_DST; + if (hw->mac.type == I40E_MAC_X722) { + if (i_set & I40E_X722_L3_SRC_MASK) + cmd->data |= RXH_IP_SRC; + if (i_set & I40E_X722_L3_DST_MASK) + cmd->data |= RXH_IP_DST; + } else { + if (i_set & I40E_L3_SRC_MASK) + cmd->data |= RXH_IP_SRC; + if (i_set & I40E_L3_DST_MASK) + cmd->data |= RXH_IP_DST; + } } else if (cmd->flow_type == TCP_V6_FLOW || cmd->flow_type == UDP_V6_FLOW) { if (i_set & I40E_L3_V6_SRC_MASK) @@ -3546,12 +3553,15 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, /** * i40e_get_rss_hash_bits - Read RSS Hash bits from register + * @hw: hw structure * @nfc: pointer to user request * @i_setc: bits currently set * * Returns value of bits to be set per user request **/ -static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc) +static u64 i40e_get_rss_hash_bits(struct i40e_hw *hw, + struct ethtool_rxnfc *nfc, + u64 i_setc) { u64 i_set = i_setc; u64 src_l3 = 0, dst_l3 = 0; @@ -3570,8 +3580,13 @@ static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc) dst_l3 = I40E_L3_V6_DST_MASK; } else if (nfc->flow_type == TCP_V4_FLOW || nfc->flow_type == UDP_V4_FLOW) { - src_l3 = I40E_L3_SRC_MASK; - dst_l3 = I40E_L3_DST_MASK; + if (hw->mac.type == I40E_MAC_X722) { + src_l3 = I40E_X722_L3_SRC_MASK; + dst_l3 = I40E_X722_L3_DST_MASK; + } else { + src_l3 = I40E_L3_SRC_MASK; + dst_l3 = I40E_L3_DST_MASK; + } } else { /* Any other flow type are not supported here */ return i_set; @@ -3589,6 +3604,7 @@ static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc) return i_set; } +#define FLOW_PCTYPES_SIZE 64 /** * i40e_set_rss_hash_opt - Enable/Disable flow types for RSS hash * @pf: pointer to the physical function struct @@ -3601,9 +3617,11 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) struct i40e_hw *hw = &pf->hw; u64 hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) | ((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32); - u8 flow_pctype = 0; + DECLARE_BITMAP(flow_pctypes, FLOW_PCTYPES_SIZE); u64 i_set, i_setc; + bitmap_zero(flow_pctypes, FLOW_PCTYPES_SIZE); + if (pf->flags & I40E_FLAG_MFP_ENABLED) { dev_err(&pf->pdev->dev, "Change of RSS hash input set is not supported when MFP mode is enabled\n"); @@ -3619,36 +3637,35 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) switch (nfc->flow_type) { case TCP_V4_FLOW: - flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; + set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP, flow_pctypes); if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) - hena |= - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK); + set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK, + flow_pctypes); break; case TCP_V6_FLOW: - flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_TCP; - if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) - hena |= - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK); + set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP, flow_pctypes); if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) - hena |= - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK); + set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK, + flow_pctypes); break; case UDP_V4_FLOW: - flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP; - if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) - hena |= - BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | - BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP); - + set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_UDP, flow_pctypes); + if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) { + set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP, + flow_pctypes); + set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP, + flow_pctypes); + } hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4); break; case UDP_V6_FLOW: - flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_UDP; - if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) - hena |= - BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | - BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP); - + set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_UDP, flow_pctypes); + if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) { + set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP, + flow_pctypes); + set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP, + flow_pctypes); + } hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6); break; case AH_ESP_V4_FLOW: @@ -3681,17 +3698,20 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) return -EINVAL; } - if (flow_pctype) { - i_setc = (u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, - flow_pctype)) | - ((u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, - flow_pctype)) << 32); - i_set = i40e_get_rss_hash_bits(nfc, i_setc); - i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_pctype), - (u32)i_set); - i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_pctype), - (u32)(i_set >> 32)); - hena |= BIT_ULL(flow_pctype); + if (bitmap_weight(flow_pctypes, FLOW_PCTYPES_SIZE)) { + u8 flow_id; + + for_each_set_bit(flow_id, flow_pctypes, FLOW_PCTYPES_SIZE) { + i_setc = (u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_id)) | + ((u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_id)) << 32); + i_set = i40e_get_rss_hash_bits(&pf->hw, nfc, i_setc); + + i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_id), + (u32)i_set); + i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_id), + (u32)(i_set >> 32)); + hena |= BIT_ULL(flow_id); + } } i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), (u32)hena); diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 7b3f30beb757..388c3d36d96a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -1404,6 +1404,10 @@ struct i40e_lldp_variables { #define I40E_PFQF_CTL_0_HASHLUTSIZE_512 0x00010000 /* INPUT SET MASK for RSS, flow director, and flexible payload */ +#define I40E_X722_L3_SRC_SHIFT 49 +#define I40E_X722_L3_SRC_MASK (0x3ULL << I40E_X722_L3_SRC_SHIFT) +#define I40E_X722_L3_DST_SHIFT 41 +#define I40E_X722_L3_DST_MASK (0x3ULL << I40E_X722_L3_DST_SHIFT) #define I40E_L3_SRC_SHIFT 47 #define I40E_L3_SRC_MASK (0x3ULL << I40E_L3_SRC_SHIFT) #define I40E_L3_V6_SRC_SHIFT 43 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 7e9f6a69eb10..72ddcefc45b1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1536,10 +1536,12 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state)) return true; - /* If the VFs have been disabled, this means something else is - * resetting the VF, so we shouldn't continue. - */ - if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) + /* Bail out if VFs are disabled. */ + if (test_bit(__I40E_VF_DISABLE, pf->state)) + return true; + + /* If VF is being reset already we don't need to continue. */ + if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) return true; i40e_trigger_vf_reset(vf, flr); @@ -1576,7 +1578,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) i40e_cleanup_reset_vf(vf); i40e_flush(hw); - clear_bit(__I40E_VF_DISABLE, pf->state); + clear_bit(I40E_VF_STATE_RESETTING, &vf->vf_states); return true; } @@ -1609,8 +1611,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) return false; /* Begin reset on all VFs at once */ - for (v = 0; v < pf->num_alloc_vfs; v++) - i40e_trigger_vf_reset(&pf->vf[v], flr); + for (v = 0; v < pf->num_alloc_vfs; v++) { + vf = &pf->vf[v]; + /* If VF is being reset no need to trigger reset again */ + if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) + i40e_trigger_vf_reset(&pf->vf[v], flr); + } /* HW requires some time to make sure it can flush the FIFO for a VF * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in @@ -1626,9 +1632,11 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) */ while (v < pf->num_alloc_vfs) { vf = &pf->vf[v]; - reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); - if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) - break; + if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) { + reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); + if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK)) + break; + } /* If the current VF has finished resetting, move on * to the next VF in sequence. @@ -1656,6 +1664,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) if (pf->vf[v].lan_vsi_idx == 0) continue; + /* If VF is reset in another thread just continue */ + if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) + continue; + i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]); } @@ -1667,6 +1679,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) if (pf->vf[v].lan_vsi_idx == 0) continue; + /* If VF is reset in another thread just continue */ + if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) + continue; + i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]); } @@ -1676,8 +1692,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) mdelay(50); /* Finish the reset on each VF */ - for (v = 0; v < pf->num_alloc_vfs; v++) + for (v = 0; v < pf->num_alloc_vfs; v++) { + /* If VF is reset in another thread just continue */ + if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) + continue; + i40e_cleanup_reset_vf(&pf->vf[v]); + } i40e_flush(hw); clear_bit(__I40E_VF_DISABLE, pf->state); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index a554d0a0b09b..358bbdb58795 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -39,6 +39,7 @@ enum i40e_vf_states { I40E_VF_STATE_MC_PROMISC, I40E_VF_STATE_UC_PROMISC, I40E_VF_STATE_PRE_ENABLE, + I40E_VF_STATE_RESETTING }; /* VF capabilities */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 0377392848d9..46ba4c2faad2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -2004,7 +2004,7 @@ void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, ctx->dev = dev; /* Starts at 1 to avoid doing wake_up if we are not cleaning up */ atomic_set(&ctx->num_inflight, 1); - init_waitqueue_head(&ctx->wait); + init_completion(&ctx->inflight_done); } EXPORT_SYMBOL(mlx5_cmd_init_async_ctx); @@ -2018,8 +2018,8 @@ EXPORT_SYMBOL(mlx5_cmd_init_async_ctx); */ void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx) { - atomic_dec(&ctx->num_inflight); - wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0); + if (!atomic_dec_and_test(&ctx->num_inflight)) + wait_for_completion(&ctx->inflight_done); } EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx); @@ -2032,7 +2032,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work) status = cmd_status_err(ctx->dev, status, work->opcode, work->out); work->user_callback(status, work); if (atomic_dec_and_test(&ctx->num_inflight)) - wake_up(&ctx->wait); + complete(&ctx->inflight_done); } int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, @@ -2050,7 +2050,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, ret = cmd_exec(ctx->dev, in, in_size, out, out_size, mlx5_cmd_exec_cb_handler, work, false); if (ret && atomic_dec_and_test(&ctx->num_inflight)) - wake_up(&ctx->wait); + complete(&ctx->inflight_done); return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index 5bce554e131a..cc7efde88ac3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -6,6 +6,7 @@ #include "en.h" #include "en_stats.h" +#include "en/txrx.h" #include <linux/ptp_classify.h> #define MLX5E_PTP_CHANNEL_IX 0 @@ -68,6 +69,14 @@ static inline bool mlx5e_use_ptpsq(struct sk_buff *skb) fk.ports.dst == htons(PTP_EV_PORT)); } +static inline bool mlx5e_ptpsq_fifo_has_room(struct mlx5e_txqsq *sq) +{ + if (!sq->ptpsq) + return true; + + return mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo); +} + int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, u8 lag_port, struct mlx5e_ptp **cp); void mlx5e_ptp_close(struct mlx5e_ptp *c); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index 10c9a8a79d00..2e42d7c5451e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -96,6 +96,7 @@ struct mlx5e_tc_flow { struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS]; struct mlx5e_tc_flow *peer_flow; struct mlx5e_mod_hdr_handle *mh; /* attached mod header instance */ + struct mlx5e_mod_hdr_handle *slow_mh; /* attached mod header instance for slow path */ struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */ struct list_head hairpin; /* flows sharing the same hairpin */ struct list_head peer; /* flows with peer flow */ @@ -111,6 +112,7 @@ struct mlx5e_tc_flow { struct completion del_hw_done; struct mlx5_flow_attr *attr; struct list_head attrs; + u32 chain_mapping; }; struct mlx5_flow_handle * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 4456ad5cedf1..cb164b62f543 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -58,6 +58,12 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget); void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq); static inline bool +mlx5e_skb_fifo_has_room(struct mlx5e_skb_fifo *fifo) +{ + return (*fifo->pc - *fifo->cc) < fifo->mask; +} + +static inline bool mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n) { return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 2a8fd7020622..a715601865d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -101,7 +101,6 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) struct xfrm_replay_state_esn *replay_esn; u32 seq_bottom = 0; u8 overlap; - u32 *esn; if (!(sa_entry->x->props.flags & XFRM_STATE_ESN)) { sa_entry->esn_state.trigger = 0; @@ -116,11 +115,9 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) sa_entry->esn_state.esn = xfrm_replay_seqhi(sa_entry->x, htonl(seq_bottom)); - esn = &sa_entry->esn_state.esn; sa_entry->esn_state.trigger = 1; if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) { - ++(*esn); sa_entry->esn_state.overlap = 0; return true; } else if (unlikely(!overlap && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 4331235b21ee..2ef36cb9555a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -432,7 +432,7 @@ static int mlx5e_macsec_update_rx_sa(struct mlx5e_macsec *macsec, bool active) { struct mlx5_core_dev *mdev = macsec->mdev; - struct mlx5_macsec_obj_attrs attrs; + struct mlx5_macsec_obj_attrs attrs = {}; int err = 0; if (rx_sa->active != active) @@ -444,7 +444,7 @@ static int mlx5e_macsec_update_rx_sa(struct mlx5e_macsec *macsec, return 0; } - attrs.sci = rx_sa->sci; + attrs.sci = cpu_to_be64((__force u64)rx_sa->sci); attrs.enc_key_id = rx_sa->enc_key_id; err = mlx5e_macsec_create_object(mdev, &attrs, false, &rx_sa->macsec_obj_id); if (err) @@ -999,11 +999,11 @@ static int mlx5e_macsec_upd_rxsa(struct macsec_context *ctx) } rx_sa = rx_sc->rx_sa[assoc_num]; - if (rx_sa) { + if (!rx_sa) { netdev_err(ctx->netdev, - "MACsec offload rx_sc sci %lld rx_sa %d already exist\n", + "MACsec offload rx_sc sci %lld rx_sa %d doesn't exist\n", sci, assoc_num); - err = -EEXIST; + err = -EINVAL; goto out; } @@ -1055,11 +1055,11 @@ static int mlx5e_macsec_del_rxsa(struct macsec_context *ctx) } rx_sa = rx_sc->rx_sa[assoc_num]; - if (rx_sa) { + if (!rx_sa) { netdev_err(ctx->netdev, - "MACsec offload rx_sc sci %lld rx_sa %d already exist\n", + "MACsec offload rx_sc sci %lld rx_sa %d doesn't exist\n", sci, assoc_num); - err = -EEXIST; + err = -EINVAL; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c index 13dc628b988a..1ac0cf04e811 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c @@ -1180,7 +1180,7 @@ macsec_fs_rx_add_rule(struct mlx5e_macsec_fs *macsec_fs, rx_rule->rule[0] = rule; /* Rx crypto table without SCI rule */ - if (cpu_to_be64((__force u64)attrs->sci) & ntohs(MACSEC_PORT_ES)) { + if ((cpu_to_be64((__force u64)attrs->sci) & 0xFFFF) == ntohs(MACSEC_PORT_ES)) { memset(spec, 0, sizeof(struct mlx5_flow_spec)); memset(&dest, 0, sizeof(struct mlx5_flow_destination)); memset(&flow_act, 0, sizeof(flow_act)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 70a7a61f9708..dd6fea9e9a5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1405,8 +1405,13 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec) { + struct mlx5e_tc_mod_hdr_acts mod_acts = {}; + struct mlx5e_mod_hdr_handle *mh = NULL; struct mlx5_flow_attr *slow_attr; struct mlx5_flow_handle *rule; + bool fwd_and_modify_cap; + u32 chain_mapping = 0; + int err; slow_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB); if (!slow_attr) @@ -1417,13 +1422,56 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, slow_attr->esw_attr->split_count = 0; slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH; + fwd_and_modify_cap = MLX5_CAP_ESW_FLOWTABLE((esw)->dev, fdb_modify_header_fwd_to_table); + if (!fwd_and_modify_cap) + goto skip_restore; + + err = mlx5_chains_get_chain_mapping(esw_chains(esw), flow->attr->chain, &chain_mapping); + if (err) + goto err_get_chain; + + err = mlx5e_tc_match_to_reg_set(esw->dev, &mod_acts, MLX5_FLOW_NAMESPACE_FDB, + CHAIN_TO_REG, chain_mapping); + if (err) + goto err_reg_set; + + mh = mlx5e_mod_hdr_attach(esw->dev, get_mod_hdr_table(flow->priv, flow), + MLX5_FLOW_NAMESPACE_FDB, &mod_acts); + if (IS_ERR(mh)) { + err = PTR_ERR(mh); + goto err_attach; + } + + slow_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + slow_attr->modify_hdr = mlx5e_mod_hdr_get(mh); + +skip_restore: rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr); - if (!IS_ERR(rule)) - flow_flag_set(flow, SLOW); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + goto err_offload; + } + flow->slow_mh = mh; + flow->chain_mapping = chain_mapping; + flow_flag_set(flow, SLOW); + + mlx5e_mod_hdr_dealloc(&mod_acts); kfree(slow_attr); return rule; + +err_offload: + if (fwd_and_modify_cap) + mlx5e_mod_hdr_detach(esw->dev, get_mod_hdr_table(flow->priv, flow), mh); +err_attach: +err_reg_set: + if (fwd_and_modify_cap) + mlx5_chains_put_chain_mapping(esw_chains(esw), chain_mapping); +err_get_chain: + mlx5e_mod_hdr_dealloc(&mod_acts); + kfree(slow_attr); + return ERR_PTR(err); } void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, @@ -1441,7 +1489,17 @@ void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; slow_attr->esw_attr->split_count = 0; slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH; + if (flow->slow_mh) { + slow_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + slow_attr->modify_hdr = mlx5e_mod_hdr_get(flow->slow_mh); + } mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr); + if (flow->slow_mh) { + mlx5e_mod_hdr_detach(esw->dev, get_mod_hdr_table(flow->priv, flow), flow->slow_mh); + mlx5_chains_put_chain_mapping(esw_chains(esw), flow->chain_mapping); + flow->chain_mapping = 0; + flow->slow_mh = NULL; + } flow_flag_clear(flow, SLOW); kfree(slow_attr); } @@ -3575,6 +3633,10 @@ mlx5e_clone_flow_attr_for_post_act(struct mlx5_flow_attr *attr, attr2->action = 0; attr2->flags = 0; attr2->parse_attr = parse_attr; + attr2->esw_attr->out_count = 0; + attr2->esw_attr->split_count = 0; + attr2->dest_chain = 0; + attr2->dest_ft = NULL; return attr2; } @@ -4008,6 +4070,7 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; + struct net_device *filter_dev; int err; err = flow_action_supported(flow_action, extack); @@ -4016,6 +4079,7 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv, esw_attr = attr->esw_attr; parse_attr = attr->parse_attr; + filter_dev = parse_attr->filter_dev; parse_state = &parse_attr->parse_state; mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack); parse_state->ct_priv = get_ct_priv(priv); @@ -4025,13 +4089,21 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv, return err; /* Forward to/from internal port can only have 1 dest */ - if ((netif_is_ovs_master(parse_attr->filter_dev) || esw_attr->dest_int_port) && + if ((netif_is_ovs_master(filter_dev) || esw_attr->dest_int_port) && esw_attr->out_count > 1) { NL_SET_ERR_MSG_MOD(extack, "Rules with internal port can have only one destination"); return -EOPNOTSUPP; } + /* Forward from tunnel/internal port to internal port is not supported */ + if ((mlx5e_get_tc_tun(filter_dev) || netif_is_ovs_master(filter_dev)) && + esw_attr->dest_int_port) { + NL_SET_ERR_MSG_MOD(extack, + "Forwarding from tunnel/internal port to internal port is not supported"); + return -EOPNOTSUPP; + } + err = actions_prepare_mod_hdr_actions(priv, flow, attr, extack); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index bf2232a2a836..6adca01fbdc9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -392,6 +392,11 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, if (unlikely(sq->ptpsq)) { mlx5e_skb_cb_hwtstamp_init(skb); mlx5e_skb_fifo_push(&sq->ptpsq->skb_fifo, skb); + if (!netif_tx_queue_stopped(sq->txq) && + !mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo)) { + netif_tx_stop_queue(sq->txq); + sq->stats->stopped++; + } skb_get(skb); } @@ -868,6 +873,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) if (netif_tx_queue_stopped(sq->txq) && mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) && + mlx5e_ptpsq_fifo_has_room(sq) && !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { netif_tx_wake_queue(sq->txq); stats->wake++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index e8896f368362..07c583996c29 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -358,6 +358,23 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) err = -ETIMEDOUT; } + do { + err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, ®16); + if (err) + return err; + if (reg16 == dev_id) + break; + msleep(20); + } while (!time_after(jiffies, timeout)); + + if (reg16 == dev_id) { + mlx5_core_info(dev, "Firmware responds to PCI config cycles again\n"); + } else { + mlx5_core_err(dev, "Firmware is not responsive (0x%04x) after %llu ms\n", + reg16, mlx5_tout_ms(dev, PCI_TOGGLE)); + err = -ETIMEDOUT; + } + restore: list_for_each_entry(sdev, &bridge_bus->devices, bus_list) { pci_cfg_access_unlock(sdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c index baa8092f335e..c971ff04dd04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c @@ -3,6 +3,7 @@ #include <linux/mlx5/device.h> #include <linux/mlx5/transobj.h> +#include "clock.h" #include "aso.h" #include "wq.h" @@ -179,6 +180,7 @@ static int create_aso_sq(struct mlx5_core_dev *mdev, int pdn, { void *in, *sqc, *wq; int inlen, err; + u8 ts_format; inlen = MLX5_ST_SZ_BYTES(create_sq_in) + sizeof(u64) * sq->wq_ctrl.buf.npages; @@ -195,6 +197,11 @@ static int create_aso_sq(struct mlx5_core_dev *mdev, int pdn, MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST); MLX5_SET(sqc, sqc, flush_in_error_en, 1); + ts_format = mlx5_is_real_time_sq(mdev) ? + MLX5_TIMESTAMP_FORMAT_REAL_TIME : + MLX5_TIMESTAMP_FORMAT_FREE_RUNNING; + MLX5_SET(sqc, sqc, ts_format, ts_format); + MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); MLX5_SET(wq, wq, uar_page, mdev->mlx5e_res.hw_objs.bfreg.index); MLX5_SET(wq, wq, log_wq_pg_sz, sq->wq_ctrl.buf.page_shift - diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index 839a01da110f..8ff16318e32d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -122,7 +122,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) { struct mlx5_mpfs *mpfs = dev->priv.mpfs; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!mpfs) return; WARN_ON(!hlist_empty(mpfs->hash)); @@ -137,7 +137,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) int err = 0; u32 index; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!mpfs) return 0; mutex_lock(&mpfs->lock); @@ -185,7 +185,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) int err = 0; u32 index; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!mpfs) return 0; mutex_lock(&mpfs->lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 0b459d841c3a..283c4cc28944 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1872,6 +1872,10 @@ static void mlx5_pci_resume(struct pci_dev *pdev) err = mlx5_load_one(dev, false); + if (!err) + devlink_health_reporter_state_update(dev->priv.health.fw_fatal_reporter, + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); + mlx5_pci_trace(dev, "Done, err = %d, device %s\n", err, !err ? "recovered" : "Failed"); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index ddfaf7891188..91ff19f67695 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -1200,7 +1200,8 @@ free_rule: } remove_from_nic_tbl: - mlx5dr_matcher_remove_from_tbl_nic(dmn, nic_matcher); + if (!nic_matcher->rules) + mlx5dr_matcher_remove_from_tbl_nic(dmn, nic_matcher); free_hw_ste: mlx5dr_domain_nic_unlock(nic_dmn); diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index 468520079c65..e6acd1e7b263 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -6851,7 +6851,7 @@ static int pcidev_init(struct pci_dev *pdev, const struct pci_device_id *id) char banner[sizeof(version)]; struct ksz_switch *sw = NULL; - result = pci_enable_device(pdev); + result = pcim_enable_device(pdev); if (result) return result; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c index 7e4061c854f0..a42035cec611 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c @@ -309,6 +309,7 @@ static void lan966x_fdma_tx_disable(struct lan966x_tx *tx) lan966x, FDMA_CH_DB_DISCARD); tx->activated = false; + tx->last_in_use = -1; } static void lan966x_fdma_tx_reload(struct lan966x_tx *tx) @@ -687,17 +688,14 @@ static int lan966x_qsys_sw_status(struct lan966x *lan966x) static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) { - void *rx_dcbs, *tx_dcbs, *tx_dcbs_buf; - dma_addr_t rx_dma, tx_dma; + dma_addr_t rx_dma; + void *rx_dcbs; u32 size; int err; /* Store these for later to free them */ rx_dma = lan966x->rx.dma; - tx_dma = lan966x->tx.dma; rx_dcbs = lan966x->rx.dcbs; - tx_dcbs = lan966x->tx.dcbs; - tx_dcbs_buf = lan966x->tx.dcbs_buf; napi_synchronize(&lan966x->napi); napi_disable(&lan966x->napi); @@ -715,17 +713,6 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) size = ALIGN(size, PAGE_SIZE); dma_free_coherent(lan966x->dev, size, rx_dcbs, rx_dma); - lan966x_fdma_tx_disable(&lan966x->tx); - err = lan966x_fdma_tx_alloc(&lan966x->tx); - if (err) - goto restore_tx; - - size = sizeof(struct lan966x_tx_dcb) * FDMA_DCB_MAX; - size = ALIGN(size, PAGE_SIZE); - dma_free_coherent(lan966x->dev, size, tx_dcbs, tx_dma); - - kfree(tx_dcbs_buf); - lan966x_fdma_wakeup_netdev(lan966x); napi_enable(&lan966x->napi); @@ -735,11 +722,6 @@ restore: lan966x->rx.dcbs = rx_dcbs; lan966x_fdma_rx_start(&lan966x->rx); -restore_tx: - lan966x->tx.dma = tx_dma; - lan966x->tx.dcbs = tx_dcbs; - lan966x->tx.dcbs_buf = tx_dcbs_buf; - return err; } diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 1fa09b49ba7f..d2c6a5dfdc0e 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1229,6 +1229,8 @@ static int ave_init(struct net_device *ndev) phy_support_asym_pause(phydev); + phydev->mac_managed_pm = true; + phy_attached_info(phydev); return 0; @@ -1756,6 +1758,10 @@ static int ave_resume(struct device *dev) ave_global_reset(ndev); + ret = phy_init_hw(ndev->phydev); + if (ret) + return ret; + ave_ethtool_get_wol(ndev, &wol); wol.wolopts = priv->wolopts; __ave_ethtool_set_wol(ndev, &wol); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index f7269d79a385..6656d76b6766 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1243,6 +1243,12 @@ static const struct rk_gmac_ops rk3588_ops = { .set_rgmii_speed = rk3588_set_gmac_speed, .set_rmii_speed = rk3588_set_gmac_speed, .set_clock_selection = rk3588_set_clock_selection, + .regs_valid = true, + .regs = { + 0xfe1b0000, /* gmac0 */ + 0xfe1c0000, /* gmac1 */ + 0x0, /* sentinel */ + }, }; #define RV1108_GRF_GMAC_CON0 0X0900 diff --git a/drivers/net/ipa/data/ipa_data-v3.5.1.c b/drivers/net/ipa/data/ipa_data-v3.5.1.c index 383ef1890065..42f2c88a92d4 100644 --- a/drivers/net/ipa/data/ipa_data-v3.5.1.c +++ b/drivers/net/ipa/data/ipa_data-v3.5.1.c @@ -179,10 +179,10 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { static const struct ipa_resource ipa_resource_src[] = { [IPA_RESOURCE_TYPE_SRC_PKT_CONTEXTS] = { .limits[IPA_RSRC_GROUP_SRC_LWA_DL] = { - .min = 1, .max = 255, + .min = 1, .max = 63, }, .limits[IPA_RSRC_GROUP_SRC_UL_DL] = { - .min = 1, .max = 255, + .min = 1, .max = 63, }, .limits[IPA_RSRC_GROUP_SRC_UC_RX_Q] = { .min = 1, .max = 63, diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index 3461ad3029ab..49537fccf6ad 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -434,6 +434,9 @@ static void ipa_idle_indication_cfg(struct ipa *ipa, const struct ipa_reg *reg; u32 val; + if (ipa->version < IPA_VERSION_3_5_1) + return; + reg = ipa_reg(ipa, IDLE_INDICATION_CFG); val = ipa_reg_encode(reg, ENTER_IDLE_DEBOUNCE_THRESH, enter_idle_debounce_thresh); diff --git a/drivers/net/ipa/reg/ipa_reg-v3.1.c b/drivers/net/ipa/reg/ipa_reg-v3.1.c index 116b27717e3d..0d002c3c38a2 100644 --- a/drivers/net/ipa/reg/ipa_reg-v3.1.c +++ b/drivers/net/ipa/reg/ipa_reg-v3.1.c @@ -127,112 +127,80 @@ static const u32 ipa_reg_counter_cfg_fmask[] = { IPA_REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { - [X_MIN_LIM] = GENMASK(5, 0), - /* Bits 6-7 reserved */ - [X_MAX_LIM] = GENMASK(13, 8), - /* Bits 14-15 reserved */ - [Y_MIN_LIM] = GENMASK(21, 16), - /* Bits 22-23 reserved */ - [Y_MAX_LIM] = GENMASK(29, 24), - /* Bits 30-31 reserved */ + [X_MIN_LIM] = GENMASK(7, 0), + [X_MAX_LIM] = GENMASK(15, 8), + [Y_MIN_LIM] = GENMASK(23, 16), + [Y_MAX_LIM] = GENMASK(31, 24), }; IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, 0x00000400, 0x0020); static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { - [X_MIN_LIM] = GENMASK(5, 0), - /* Bits 6-7 reserved */ - [X_MAX_LIM] = GENMASK(13, 8), - /* Bits 14-15 reserved */ - [Y_MIN_LIM] = GENMASK(21, 16), - /* Bits 22-23 reserved */ - [Y_MAX_LIM] = GENMASK(29, 24), - /* Bits 30-31 reserved */ + [X_MIN_LIM] = GENMASK(7, 0), + [X_MAX_LIM] = GENMASK(15, 8), + [Y_MIN_LIM] = GENMASK(23, 16), + [Y_MAX_LIM] = GENMASK(31, 24), }; IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, 0x00000404, 0x0020); static const u32 ipa_reg_src_rsrc_grp_45_rsrc_type_fmask[] = { - [X_MIN_LIM] = GENMASK(5, 0), - /* Bits 6-7 reserved */ - [X_MAX_LIM] = GENMASK(13, 8), - /* Bits 14-15 reserved */ - [Y_MIN_LIM] = GENMASK(21, 16), - /* Bits 22-23 reserved */ - [Y_MAX_LIM] = GENMASK(29, 24), - /* Bits 30-31 reserved */ + [X_MIN_LIM] = GENMASK(7, 0), + [X_MAX_LIM] = GENMASK(15, 8), + [Y_MIN_LIM] = GENMASK(23, 16), + [Y_MAX_LIM] = GENMASK(31, 24), }; IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type, 0x00000408, 0x0020); static const u32 ipa_reg_src_rsrc_grp_67_rsrc_type_fmask[] = { - [X_MIN_LIM] = GENMASK(5, 0), - /* Bits 6-7 reserved */ - [X_MAX_LIM] = GENMASK(13, 8), - /* Bits 14-15 reserved */ - [Y_MIN_LIM] = GENMASK(21, 16), - /* Bits 22-23 reserved */ - [Y_MAX_LIM] = GENMASK(29, 24), - /* Bits 30-31 reserved */ + [X_MIN_LIM] = GENMASK(7, 0), + [X_MAX_LIM] = GENMASK(15, 8), + [Y_MIN_LIM] = GENMASK(23, 16), + [Y_MAX_LIM] = GENMASK(31, 24), }; IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_67_RSRC_TYPE, src_rsrc_grp_67_rsrc_type, 0x0000040c, 0x0020); static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { - [X_MIN_LIM] = GENMASK(5, 0), - /* Bits 6-7 reserved */ - [X_MAX_LIM] = GENMASK(13, 8), - /* Bits 14-15 reserved */ - [Y_MIN_LIM] = GENMASK(21, 16), - /* Bits 22-23 reserved */ - [Y_MAX_LIM] = GENMASK(29, 24), - /* Bits 30-31 reserved */ + [X_MIN_LIM] = GENMASK(7, 0), + [X_MAX_LIM] = GENMASK(15, 8), + [Y_MIN_LIM] = GENMASK(23, 16), + [Y_MAX_LIM] = GENMASK(31, 24), }; IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, 0x00000500, 0x0020); static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { - [X_MIN_LIM] = GENMASK(5, 0), - /* Bits 6-7 reserved */ - [X_MAX_LIM] = GENMASK(13, 8), - /* Bits 14-15 reserved */ - [Y_MIN_LIM] = GENMASK(21, 16), - /* Bits 22-23 reserved */ - [Y_MAX_LIM] = GENMASK(29, 24), - /* Bits 30-31 reserved */ + [X_MIN_LIM] = GENMASK(7, 0), + [X_MAX_LIM] = GENMASK(15, 8), + [Y_MIN_LIM] = GENMASK(23, 16), + [Y_MAX_LIM] = GENMASK(31, 24), }; IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, 0x00000504, 0x0020); static const u32 ipa_reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { - [X_MIN_LIM] = GENMASK(5, 0), - /* Bits 6-7 reserved */ - [X_MAX_LIM] = GENMASK(13, 8), - /* Bits 14-15 reserved */ - [Y_MIN_LIM] = GENMASK(21, 16), - /* Bits 22-23 reserved */ - [Y_MAX_LIM] = GENMASK(29, 24), - /* Bits 30-31 reserved */ + [X_MIN_LIM] = GENMASK(7, 0), + [X_MAX_LIM] = GENMASK(15, 8), + [Y_MIN_LIM] = GENMASK(23, 16), + [Y_MAX_LIM] = GENMASK(31, 24), }; IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type, 0x00000508, 0x0020); static const u32 ipa_reg_dst_rsrc_grp_67_rsrc_type_fmask[] = { - [X_MIN_LIM] = GENMASK(5, 0), - /* Bits 6-7 reserved */ - [X_MAX_LIM] = GENMASK(13, 8), - /* Bits 14-15 reserved */ - [Y_MIN_LIM] = GENMASK(21, 16), - /* Bits 22-23 reserved */ - [Y_MAX_LIM] = GENMASK(29, 24), - /* Bits 30-31 reserved */ + [X_MIN_LIM] = GENMASK(7, 0), + [X_MAX_LIM] = GENMASK(15, 8), + [Y_MIN_LIM] = GENMASK(23, 16), + [Y_MAX_LIM] = GENMASK(31, 24), }; IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_67_RSRC_TYPE, dst_rsrc_grp_67_rsrc_type, diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c index b5f4df1a07a3..0052968e881e 100644 --- a/drivers/net/netdevsim/bus.c +++ b/drivers/net/netdevsim/bus.c @@ -117,6 +117,10 @@ static const struct attribute_group *nsim_bus_dev_attr_groups[] = { static void nsim_bus_dev_release(struct device *dev) { + struct nsim_bus_dev *nsim_bus_dev; + + nsim_bus_dev = container_of(dev, struct nsim_bus_dev, dev); + kfree(nsim_bus_dev); } static struct device_type nsim_bus_dev_type = { @@ -291,6 +295,8 @@ nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queu err_nsim_bus_dev_id_free: ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id); + put_device(&nsim_bus_dev->dev); + nsim_bus_dev = NULL; err_nsim_bus_dev_free: kfree(nsim_bus_dev); return ERR_PTR(err); @@ -300,9 +306,8 @@ static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev) { /* Disallow using nsim_bus_dev */ smp_store_release(&nsim_bus_dev->init, false); - device_unregister(&nsim_bus_dev->dev); ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id); - kfree(nsim_bus_dev); + device_unregister(&nsim_bus_dev->dev); } static struct device_driver nsim_driver = { diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 794fc0cc73b8..a7880c7ce94c 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -309,8 +309,10 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) if (IS_ERR(nsim_dev->ddir)) return PTR_ERR(nsim_dev->ddir); nsim_dev->ports_ddir = debugfs_create_dir("ports", nsim_dev->ddir); - if (IS_ERR(nsim_dev->ports_ddir)) - return PTR_ERR(nsim_dev->ports_ddir); + if (IS_ERR(nsim_dev->ports_ddir)) { + err = PTR_ERR(nsim_dev->ports_ddir); + goto err_ddir; + } debugfs_create_bool("fw_update_status", 0600, nsim_dev->ddir, &nsim_dev->fw_update_status); debugfs_create_u32("fw_update_overwrite_mask", 0600, nsim_dev->ddir, @@ -346,7 +348,7 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) nsim_dev->nodes_ddir = debugfs_create_dir("rate_nodes", nsim_dev->ddir); if (IS_ERR(nsim_dev->nodes_ddir)) { err = PTR_ERR(nsim_dev->nodes_ddir); - goto err_out; + goto err_ports_ddir; } debugfs_create_bool("fail_trap_drop_counter_get", 0600, nsim_dev->ddir, @@ -354,8 +356,9 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) nsim_udp_tunnels_debugfs_create(nsim_dev); return 0; -err_out: +err_ports_ddir: debugfs_remove_recursive(nsim_dev->ports_ddir); +err_ddir: debugfs_remove_recursive(nsim_dev->ddir); return err; } @@ -442,7 +445,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) ¶ms); if (err) { pr_err("Failed to register IPv4 top resource\n"); - goto out; + goto err_out; } err = devl_resource_register(devlink, "fib", (u64)-1, @@ -450,7 +453,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) NSIM_RESOURCE_IPV4, ¶ms); if (err) { pr_err("Failed to register IPv4 FIB resource\n"); - return err; + goto err_out; } err = devl_resource_register(devlink, "fib-rules", (u64)-1, @@ -458,7 +461,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) NSIM_RESOURCE_IPV4, ¶ms); if (err) { pr_err("Failed to register IPv4 FIB rules resource\n"); - return err; + goto err_out; } /* Resources for IPv6 */ @@ -468,7 +471,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) ¶ms); if (err) { pr_err("Failed to register IPv6 top resource\n"); - goto out; + goto err_out; } err = devl_resource_register(devlink, "fib", (u64)-1, @@ -476,7 +479,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) NSIM_RESOURCE_IPV6, ¶ms); if (err) { pr_err("Failed to register IPv6 FIB resource\n"); - return err; + goto err_out; } err = devl_resource_register(devlink, "fib-rules", (u64)-1, @@ -484,7 +487,7 @@ static int nsim_dev_resources_register(struct devlink *devlink) NSIM_RESOURCE_IPV6, ¶ms); if (err) { pr_err("Failed to register IPv6 FIB rules resource\n"); - return err; + goto err_out; } /* Resources for nexthops */ @@ -492,8 +495,14 @@ static int nsim_dev_resources_register(struct devlink *devlink) NSIM_RESOURCE_NEXTHOPS, DEVLINK_RESOURCE_ID_PARENT_TOP, ¶ms); + if (err) { + pr_err("Failed to register NEXTHOPS resource\n"); + goto err_out; + } + return 0; -out: +err_out: + devl_resources_unregister(devlink); return err; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a12929bc31b2..af2ceb4160bc 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -970,7 +970,7 @@ void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode); struct mlx5_async_ctx { struct mlx5_core_dev *dev; atomic_t num_inflight; - struct wait_queue_head wait; + struct completion inflight_done; }; struct mlx5_async_work; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 3d08e67b3cfc..9f97f73615b6 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -41,13 +41,21 @@ struct genl_info; * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @resv_start_op: first operation for which reserved fields of the header - * can be validated, new families should leave this field at zero + * can be validated and policies are required (see below); + * new families should leave this field at zero * @mcgrp_offset: starting number of multicast group IDs in this family * (private) * @ops: the operations supported by this family * @n_ops: number of operations supported by this family * @small_ops: the small-struct operations supported by this family * @n_small_ops: number of small-struct operations supported by this family + * + * Attribute policies (the combination of @policy and @maxattr fields) + * can be attached at the family level or at the operation level. + * If both are present the per-operation policy takes precedence. + * For operations before @resv_start_op lack of policy means that the core + * will perform no attribute parsing or validation. For newer operations + * if policy is not provided core will reject all TLV attributes. */ struct genl_family { int id; /* private */ diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index b358a74ed7ed..f2ba5787055a 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -369,18 +369,10 @@ static int __init test_rhltable(unsigned int entries) pr_info("test %d random rhlist add/delete operations\n", entries); for (j = 0; j < entries; j++) { u32 i = prandom_u32_max(entries); - u32 prand = get_random_u32(); + u32 prand = prandom_u32_max(4); cond_resched(); - if (prand == 0) - prand = get_random_u32(); - - if (prand & 1) { - prand >>= 1; - continue; - } - err = rhltable_remove(&rhlt, &rhl_test_objects[i].list_node, test_rht_params); if (test_bit(i, obj_in_table)) { clear_bit(i, obj_in_table); @@ -393,35 +385,29 @@ static int __init test_rhltable(unsigned int entries) } if (prand & 1) { - prand >>= 1; - continue; - } - - err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node, test_rht_params); - if (err == 0) { - if (WARN(test_and_set_bit(i, obj_in_table), "succeeded to insert same object %d", i)) - continue; - } else { - if (WARN(!test_bit(i, obj_in_table), "failed to insert object %d", i)) - continue; - } - - if (prand & 1) { - prand >>= 1; - continue; + err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node, test_rht_params); + if (err == 0) { + if (WARN(test_and_set_bit(i, obj_in_table), "succeeded to insert same object %d", i)) + continue; + } else { + if (WARN(!test_bit(i, obj_in_table), "failed to insert object %d", i)) + continue; + } } - i = prandom_u32_max(entries); - if (test_bit(i, obj_in_table)) { - err = rhltable_remove(&rhlt, &rhl_test_objects[i].list_node, test_rht_params); - WARN(err, "cannot remove element at slot %d", i); - if (err == 0) - clear_bit(i, obj_in_table); - } else { - err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node, test_rht_params); - WARN(err, "failed to insert object %d", i); - if (err == 0) - set_bit(i, obj_in_table); + if (prand & 2) { + i = prandom_u32_max(entries); + if (test_bit(i, obj_in_table)) { + err = rhltable_remove(&rhlt, &rhl_test_objects[i].list_node, test_rht_params); + WARN(err, "cannot remove element at slot %d", i); + if (err == 0) + clear_bit(i, obj_in_table); + } else { + err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node, test_rht_params); + WARN(err, "failed to insert object %d", i); + if (err == 0) + set_bit(i, obj_in_table); + } } } diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index d7d86c944d76..55f29c9f9e08 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -342,10 +342,12 @@ static void j1939_session_skb_drop_old(struct j1939_session *session) __skb_unlink(do_skb, &session->skb_queue); /* drop ref taken in j1939_session_skb_queue() */ skb_unref(do_skb); + spin_unlock_irqrestore(&session->skb_queue.lock, flags); kfree_skb(do_skb); + } else { + spin_unlock_irqrestore(&session->skb_queue.lock, flags); } - spin_unlock_irqrestore(&session->skb_queue.lock, flags); } void j1939_session_skb_queue(struct j1939_session *session, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1d9719e72f9d..d1a3fa6f3f12 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3971,7 +3971,7 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, } else if (i < MAX_SKB_FRAGS) { skb_zcopy_downgrade_managed(skb); get_page(page); - skb_fill_page_desc(skb, i, page, offset, size); + skb_fill_page_desc_noacc(skb, i, page, offset, size); } else { return -EMSGSIZE; } diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c index 1c94bb8ea03f..49c0a2a77f02 100644 --- a/net/ethtool/eeprom.c +++ b/net/ethtool/eeprom.c @@ -124,7 +124,7 @@ static int eeprom_prepare_data(const struct ethnl_req_info *req_base, if (ret) goto err_free; - ret = get_module_eeprom_by_page(dev, &page_data, info->extack); + ret = get_module_eeprom_by_page(dev, &page_data, info ? info->extack : NULL); if (ret < 0) goto err_ops; diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 6e55fae4c686..1fa2fe041ec0 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -502,8 +502,10 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) if (err < 0) goto out; - if (addr->family != AF_IEEE802154) + if (addr->family != AF_IEEE802154) { + err = -EINVAL; goto out; + } ieee802154_addr_from_sa(&haddr, &addr->addr); dev = ieee802154_get_dev(sock_net(sk), &haddr); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 943edf4ad4db..f361d3d56be2 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -389,7 +389,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dev_match = dev_match || (res.type == RTN_LOCAL && dev == net->loopback_dev); if (dev_match) { - ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK; + ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) @@ -401,7 +401,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) - ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK; + ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index e9a7f70a54df..f721c308248b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1231,7 +1231,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh, nh->fib_nh_dev = in_dev->dev; netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); - nh->fib_nh_scope = RT_SCOPE_LINK; + nh->fib_nh_scope = RT_SCOPE_HOST; if (!netif_carrier_ok(nh->fib_nh_dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = 0; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 853a75a8fbaf..d8ef05347fd9 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2534,7 +2534,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, if (!err) { nh->nh_flags = fib_nh->fib_nh_flags; fib_info_update_nhc_saddr(net, &fib_nh->nh_common, - fib_nh->fib_nh_scope); + !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1); } else { fib_nh_release(net, fib_nh); } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 48b4ff0294f6..c035a96fba3a 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1175,14 +1175,16 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, dev->needed_headroom = dst_len; if (set_mtu) { - dev->mtu = rt->dst.dev->mtu - t_hlen; + int mtu = rt->dst.dev->mtu - t_hlen; + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - dev->mtu -= 8; + mtu -= 8; if (dev->type == ARPHRD_ETHER) - dev->mtu -= ETH_HLEN; + mtu -= ETH_HLEN; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } ip6_rt_put(rt); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index cc5d5e75b658..2fb4c6ad7243 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1450,8 +1450,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) struct net_device *tdev = NULL; struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; - unsigned int mtu; int t_hlen; + int mtu; __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); @@ -1498,12 +1498,13 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) dev->hard_header_len = tdev->hard_header_len + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); - dev->mtu = mtu - t_hlen; + mtu = mtu - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - dev->mtu -= 8; + mtu -= 8; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index d27683e3fc97..5703d3cbea9b 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1124,10 +1124,12 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); + int mtu; - dev->mtu = tdev->mtu - t_hlen; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + mtu = tdev->mtu - t_hlen; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 63e32f181f43..a5004228111d 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -839,7 +839,7 @@ static ssize_t kcm_sendpage(struct socket *sock, struct page *page, } get_page(page); - skb_fill_page_desc(skb, i, page, offset, size); + skb_fill_page_desc_noacc(skb, i, page, offset, size); skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; coalesced: diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index c439125ef2b9..726b47a4611b 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -132,7 +132,7 @@ static int ieee802154_parse_frame_start(struct sk_buff *skb, struct ieee802154_hdr *hdr) { int hlen; - struct ieee802154_mac_cb *cb = mac_cb_init(skb); + struct ieee802154_mac_cb *cb = mac_cb(skb); skb_reset_mac_header(skb); @@ -294,8 +294,9 @@ void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi) { struct ieee802154_local *local = hw_to_local(hw); + struct ieee802154_mac_cb *cb = mac_cb_init(skb); - mac_cb(skb)->lqi = lqi; + cb->lqi = lqi; skb->pkt_type = IEEE802154_RX_MSG; skb_queue_tail(&local->skb_queue, skb); tasklet_schedule(&local->tasklet); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f599ad44ed24..b6dc6e260334 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1673,6 +1673,37 @@ static void mptcp_set_nospace(struct sock *sk) set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags); } +static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg, + size_t len, int *copied_syn) +{ + unsigned int saved_flags = msg->msg_flags; + struct mptcp_sock *msk = mptcp_sk(sk); + int ret; + + lock_sock(ssk); + msg->msg_flags |= MSG_DONTWAIT; + msk->connect_flags = O_NONBLOCK; + msk->is_sendmsg = 1; + ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL); + msk->is_sendmsg = 0; + msg->msg_flags = saved_flags; + release_sock(ssk); + + /* do the blocking bits of inet_stream_connect outside the ssk socket lock */ + if (ret == -EINPROGRESS && !(msg->msg_flags & MSG_DONTWAIT)) { + ret = __inet_stream_connect(sk->sk_socket, msg->msg_name, + msg->msg_namelen, msg->msg_flags, 1); + + /* Keep the same behaviour of plain TCP: zero the copied bytes in + * case of any error, except timeout or signal + */ + if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR) + *copied_syn = 0; + } + + return ret; +} + static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1693,23 +1724,14 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ssock = __mptcp_nmpc_socket(msk); if (unlikely(ssock && inet_sk(ssock->sk)->defer_connect)) { - struct sock *ssk = ssock->sk; int copied_syn = 0; - lock_sock(ssk); - - ret = tcp_sendmsg_fastopen(ssk, msg, &copied_syn, len, NULL); + ret = mptcp_sendmsg_fastopen(sk, ssock->sk, msg, len, &copied_syn); copied += copied_syn; - if (ret == -EINPROGRESS && copied_syn > 0) { - /* reflect the new state on the MPTCP socket */ - inet_sk_state_store(sk, inet_sk_state_load(ssk)); - release_sock(ssk); + if (ret == -EINPROGRESS && copied_syn > 0) goto out; - } else if (ret) { - release_sock(ssk); + else if (ret) goto do_error; - } - release_sock(ssk); } timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); @@ -2952,7 +2974,7 @@ static void mptcp_close(struct sock *sk, long timeout) sock_put(sk); } -static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) +void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) const struct ipv6_pinfo *ssk6 = inet6_sk(ssk); @@ -3507,10 +3529,73 @@ static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg) return put_user(answ, (int __user *)arg); } +static void mptcp_subflow_early_fallback(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow) +{ + subflow->request_mptcp = 0; + __mptcp_do_fallback(msk); +} + +static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); + struct socket *ssock; + int err = -EINVAL; + + ssock = __mptcp_nmpc_socket(msk); + if (!ssock) + return -EINVAL; + + mptcp_token_destroy(msk); + inet_sk_state_store(sk, TCP_SYN_SENT); + subflow = mptcp_subflow_ctx(ssock->sk); +#ifdef CONFIG_TCP_MD5SIG + /* no MPTCP if MD5SIG is enabled on this socket or we may run out of + * TCP option space. + */ + if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info)) + mptcp_subflow_early_fallback(msk, subflow); +#endif + if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) { + MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT); + mptcp_subflow_early_fallback(msk, subflow); + } + if (likely(!__mptcp_check_fallback(msk))) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE); + + /* if reaching here via the fastopen/sendmsg path, the caller already + * acquired the subflow socket lock, too. + */ + if (msk->is_sendmsg) + err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1); + else + err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags); + inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect; + + /* on successful connect, the msk state will be moved to established by + * subflow_finish_connect() + */ + if (unlikely(err && err != -EINPROGRESS)) { + inet_sk_state_store(sk, inet_sk_state_load(ssock->sk)); + return err; + } + + mptcp_copy_inaddrs(sk, ssock->sk); + + /* unblocking connect, mptcp-level inet_stream_connect will error out + * without changing the socket state, update it here. + */ + if (err == -EINPROGRESS) + sk->sk_socket->state = ssock->state; + return err; +} + static struct proto mptcp_prot = { .name = "MPTCP", .owner = THIS_MODULE, .init = mptcp_init_sock, + .connect = mptcp_connect, .disconnect = mptcp_disconnect, .close = mptcp_close, .accept = mptcp_accept, @@ -3562,78 +3647,16 @@ unlock: return err; } -static void mptcp_subflow_early_fallback(struct mptcp_sock *msk, - struct mptcp_subflow_context *subflow) -{ - subflow->request_mptcp = 0; - __mptcp_do_fallback(msk); -} - static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { - struct mptcp_sock *msk = mptcp_sk(sock->sk); - struct mptcp_subflow_context *subflow; - struct socket *ssock; - int err = -EINVAL; + int ret; lock_sock(sock->sk); - if (uaddr) { - if (addr_len < sizeof(uaddr->sa_family)) - goto unlock; - - if (uaddr->sa_family == AF_UNSPEC) { - err = mptcp_disconnect(sock->sk, flags); - sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; - goto unlock; - } - } - - if (sock->state != SS_UNCONNECTED && msk->subflow) { - /* pending connection or invalid state, let existing subflow - * cope with that - */ - ssock = msk->subflow; - goto do_connect; - } - - ssock = __mptcp_nmpc_socket(msk); - if (!ssock) - goto unlock; - - mptcp_token_destroy(msk); - inet_sk_state_store(sock->sk, TCP_SYN_SENT); - subflow = mptcp_subflow_ctx(ssock->sk); -#ifdef CONFIG_TCP_MD5SIG - /* no MPTCP if MD5SIG is enabled on this socket or we may run out of - * TCP option space. - */ - if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info)) - mptcp_subflow_early_fallback(msk, subflow); -#endif - if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) { - MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT); - mptcp_subflow_early_fallback(msk, subflow); - } - if (likely(!__mptcp_check_fallback(msk))) - MPTCP_INC_STATS(sock_net(sock->sk), MPTCP_MIB_MPCAPABLEACTIVE); - -do_connect: - err = ssock->ops->connect(ssock, uaddr, addr_len, flags); - inet_sk(sock->sk)->defer_connect = inet_sk(ssock->sk)->defer_connect; - sock->state = ssock->state; - - /* on successful connect, the msk state will be moved to established by - * subflow_finish_connect() - */ - if (!err || err == -EINPROGRESS) - mptcp_copy_inaddrs(sock->sk, ssock->sk); - else - inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk)); - -unlock: + mptcp_sk(sock->sk)->connect_flags = flags; + ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0); release_sock(sock->sk); - return err; + return ret; } static int mptcp_listen(struct socket *sock, int backlog) @@ -3699,7 +3722,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (mptcp_is_fully_established(newsk)) mptcp_pm_fully_established(msk, msk->first, GFP_KERNEL); - mptcp_copy_inaddrs(newsk, msk->first); mptcp_rcv_space_init(msk, msk->first); mptcp_propagate_sndbuf(newsk, msk->first); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index c0b5b4628f65..6a09ab99a12d 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -285,7 +285,9 @@ struct mptcp_sock { u8 mpc_endpoint_id; u8 recvmsg_inq:1, cork:1, - nodelay:1; + nodelay:1, + is_sendmsg:1; + int connect_flags; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -599,6 +601,7 @@ int mptcp_is_checksum_enabled(const struct net *net); int mptcp_allow_join_id0(const struct net *net); unsigned int mptcp_stale_loss_cnt(const struct net *net); int mptcp_get_pm_type(const struct net *net); +void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 07dd23d0fe04..02a54d59697b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -723,6 +723,8 @@ create_child: goto dispose_child; } + if (new_msk) + mptcp_copy_inaddrs(new_msk, child); subflow_drop_ctx(child); goto out; } @@ -750,6 +752,11 @@ create_child: ctx->conn = new_msk; new_msk = NULL; + /* set msk addresses early to ensure mptcp_pm_get_local_id() + * uses the correct data + */ + mptcp_copy_inaddrs(ctx->conn, child); + /* with OoO packets we can reach here without ingress * mpc option */ diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 39b7c00e4cef..3e16527beb91 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -78,10 +78,29 @@ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) | static unsigned long *mc_groups = &mc_group_start; static unsigned long mc_groups_longs = 1; +/* We need the last attribute with non-zero ID therefore a 2-entry array */ +static struct nla_policy genl_policy_reject_all[] = { + { .type = NLA_REJECT }, + { .type = NLA_REJECT }, +}; + static int genl_ctrl_event(int event, const struct genl_family *family, const struct genl_multicast_group *grp, int grp_id); +static void +genl_op_fill_in_reject_policy(const struct genl_family *family, + struct genl_ops *op) +{ + BUILD_BUG_ON(ARRAY_SIZE(genl_policy_reject_all) - 1 != 1); + + if (op->policy || op->cmd < family->resv_start_op) + return; + + op->policy = genl_policy_reject_all; + op->maxattr = 1; +} + static const struct genl_family *genl_family_find_byid(unsigned int id) { return idr_find(&genl_fam_idr, id); @@ -113,6 +132,8 @@ static void genl_op_from_full(const struct genl_family *family, op->maxattr = family->maxattr; if (!op->policy) op->policy = family->policy; + + genl_op_fill_in_reject_policy(family, op); } static int genl_get_cmd_full(u32 cmd, const struct genl_family *family, @@ -142,6 +163,8 @@ static void genl_op_from_small(const struct genl_family *family, op->maxattr = family->maxattr; op->policy = family->policy; + + genl_op_fill_in_reject_policy(family, op); } static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, @@ -357,6 +380,8 @@ static int genl_validate_ops(const struct genl_family *family) genl_get_cmd_by_index(i, family, &op); if (op.dumpit == NULL && op.doit == NULL) return -EINVAL; + if (WARN_ON(op.cmd >= family->resv_start_op && op.validate)) + return -EINVAL; for (j = i + 1; j < genl_get_cmd_cnt(family); j++) { struct genl_ops op2; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index c8a9075ddd0a..155263e73512 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1616,7 +1616,8 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, if (IS_ERR(dp)) return; - WARN(dp->user_features, "Dropping previously announced user features\n"); + pr_warn("%s: Dropping previously announced user features\n", + ovs_dp_name(dp)); dp->user_features = 0; } diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 0464b2c6c1e4..f07aef7c592c 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -49,6 +49,7 @@ TARGETS += net TARGETS += net/af_unix TARGETS += net/forwarding TARGETS += net/mptcp +TARGETS += net/openvswitch TARGETS += netfilter TARGETS += nsfs TARGETS += pidfd diff --git a/tools/testing/selftests/net/openvswitch/Makefile b/tools/testing/selftests/net/openvswitch/Makefile new file mode 100644 index 000000000000..2f1508abc826 --- /dev/null +++ b/tools/testing/selftests/net/openvswitch/Makefile @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 + +top_srcdir = ../../../../.. + +CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) + +TEST_PROGS := openvswitch.sh + +TEST_FILES := ovs-dpctl.py + +EXTRA_CLEAN := test_netlink_checks + +include ../../lib.mk diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh new file mode 100755 index 000000000000..7ce46700a3ae --- /dev/null +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -0,0 +1,218 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# OVS kernel module self tests + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +PAUSE_ON_FAIL=no +VERBOSE=0 +TRACING=0 + +tests=" + netlink_checks ovsnl: validate netlink attrs and settings" + +info() { + [ $VERBOSE = 0 ] || echo $* +} + +ovs_base=`pwd` +sbxs= +sbx_add () { + info "adding sandbox '$1'" + + sbxs="$sbxs $1" + + NO_BIN=0 + + # Create sandbox. + local d="$ovs_base"/$1 + if [ -e $d ]; then + info "removing $d" + rm -rf "$d" + fi + mkdir "$d" || return 1 + ovs_setenv $1 +} + +ovs_exit_sig() { + [ -e ${ovs_dir}/cleanup ] && . "$ovs_dir/cleanup" +} + +on_exit() { + echo "$1" > ${ovs_dir}/cleanup.tmp + cat ${ovs_dir}/cleanup >> ${ovs_dir}/cleanup.tmp + mv ${ovs_dir}/cleanup.tmp ${ovs_dir}/cleanup +} + +ovs_setenv() { + sandbox=$1 + + ovs_dir=$ovs_base${1:+/$1}; export ovs_dir + + test -e ${ovs_dir}/cleanup || : > ${ovs_dir}/cleanup +} + +ovs_sbx() { + if test "X$2" != X; then + (ovs_setenv $1; shift; "$@" >> ${ovs_dir}/debug.log) + else + ovs_setenv $1 + fi +} + +ovs_add_dp () { + info "Adding DP/Bridge IF: sbx:$1 dp:$2 {$3, $4, $5}" + sbxname="$1" + shift + ovs_sbx "$sbxname" python3 $ovs_base/ovs-dpctl.py add-dp $* + on_exit "ovs_sbx $sbxname python3 $ovs_base/ovs-dpctl.py del-dp $1;" +} + +usage() { + echo + echo "$0 [OPTIONS] [TEST]..." + echo "If no TEST argument is given, all tests will be run." + echo + echo "Options" + echo " -t: capture traffic via tcpdump" + echo " -v: verbose" + echo " -p: pause on failure" + echo + echo "Available tests${tests}" + exit 1 +} + +# netlink_validation +# - Create a dp +# - check no warning with "old version" simulation +test_netlink_checks () { + sbx_add "test_netlink_checks" || return 1 + + info "setting up new DP" + ovs_add_dp "test_netlink_checks" nv0 || return 1 + # now try again + PRE_TEST=$(dmesg | grep -E "RIP: [0-9a-fA-Fx]+:ovs_dp_cmd_new\+") + ovs_add_dp "test_netlink_checks" nv0 -V 0 || return 1 + POST_TEST=$(dmesg | grep -E "RIP: [0-9a-fA-Fx]+:ovs_dp_cmd_new\+") + if [ "$PRE_TEST" != "$POST_TEST" ]; then + info "failed - gen warning" + return 1 + fi + + return 0 +} + +run_test() { + ( + tname="$1" + tdesc="$2" + + if ! lsmod | grep openvswitch >/dev/null 2>&1; then + stdbuf -o0 printf "TEST: %-60s [NOMOD]\n" "${tdesc}" + return $ksft_skip + fi + + if python3 ovs-dpctl.py -h 2>&1 | \ + grep "Need to install the python" >/dev/null 2>&1; then + stdbuf -o0 printf "TEST: %-60s [PYLIB]\n" "${tdesc}" + return $ksft_skip + fi + printf "TEST: %-60s [START]\n" "${tname}" + + unset IFS + + eval test_${tname} + ret=$? + + if [ $ret -eq 0 ]; then + printf "TEST: %-60s [ OK ]\n" "${tdesc}" + ovs_exit_sig + rm -rf "$ovs_dir" + elif [ $ret -eq 1 ]; then + printf "TEST: %-60s [FAIL]\n" "${tdesc}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "Pausing. Logs in $ovs_dir/. Hit enter to continue" + read a + fi + ovs_exit_sig + [ "${PAUSE_ON_FAIL}" = "yes" ] || rm -rf "$ovs_dir" + exit 1 + elif [ $ret -eq $ksft_skip ]; then + printf "TEST: %-60s [SKIP]\n" "${tdesc}" + elif [ $ret -eq 2 ]; then + rm -rf test_${tname} + run_test "$1" "$2" + fi + + return $ret + ) + ret=$? + case $ret in + 0) + [ $all_skipped = true ] && [ $exitcode=$ksft_skip ] && exitcode=0 + all_skipped=false + ;; + $ksft_skip) + [ $all_skipped = true ] && exitcode=$ksft_skip + ;; + *) + all_skipped=false + exitcode=1 + ;; + esac + + return $ret +} + + +exitcode=0 +desc=0 +all_skipped=true + +while getopts :pvt o +do + case $o in + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=1;; + t) if which tcpdump > /dev/null 2>&1; then + TRACING=1 + else + echo "=== tcpdump not available, tracing disabled" + fi + ;; + *) usage;; + esac +done +shift $(($OPTIND-1)) + +IFS=" +" + +for arg do + # Check first that all requested tests are available before running any + command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; } +done + +name="" +desc="" +for t in ${tests}; do + [ "${name}" = "" ] && name="${t}" && continue + [ "${desc}" = "" ] && desc="${t}" + + run_this=1 + for arg do + [ "${arg}" != "${arg#--*}" ] && continue + [ "${arg}" = "${name}" ] && run_this=1 && break + run_this=0 + done + if [ $run_this -eq 1 ]; then + run_test "${name}" "${desc}" + fi + name="" + desc="" +done + +exit ${exitcode} diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py new file mode 100644 index 000000000000..3243c90d449e --- /dev/null +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -0,0 +1,351 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +# Controls the openvswitch module. Part of the kselftest suite, but +# can be used for some diagnostic purpose as well. + +import argparse +import errno +import sys + +try: + from pyroute2 import NDB + + from pyroute2.netlink import NLM_F_ACK + from pyroute2.netlink import NLM_F_REQUEST + from pyroute2.netlink import genlmsg + from pyroute2.netlink import nla + from pyroute2.netlink.exceptions import NetlinkError + from pyroute2.netlink.generic import GenericNetlinkSocket +except ModuleNotFoundError: + print("Need to install the python pyroute2 package.") + sys.exit(0) + + +OVS_DATAPATH_FAMILY = "ovs_datapath" +OVS_VPORT_FAMILY = "ovs_vport" +OVS_FLOW_FAMILY = "ovs_flow" +OVS_PACKET_FAMILY = "ovs_packet" +OVS_METER_FAMILY = "ovs_meter" +OVS_CT_LIMIT_FAMILY = "ovs_ct_limit" + +OVS_DATAPATH_VERSION = 2 +OVS_DP_CMD_NEW = 1 +OVS_DP_CMD_DEL = 2 +OVS_DP_CMD_GET = 3 +OVS_DP_CMD_SET = 4 + +OVS_VPORT_CMD_NEW = 1 +OVS_VPORT_CMD_DEL = 2 +OVS_VPORT_CMD_GET = 3 +OVS_VPORT_CMD_SET = 4 + + +class ovs_dp_msg(genlmsg): + # include the OVS version + # We need a custom header rather than just being able to rely on + # genlmsg because fields ends up not expressing everything correctly + # if we use the canonical example of setting fields = (('customfield',),) + fields = genlmsg.fields + (("dpifindex", "I"),) + + +class OvsDatapath(GenericNetlinkSocket): + + OVS_DP_F_VPORT_PIDS = 1 << 1 + OVS_DP_F_DISPATCH_UPCALL_PER_CPU = 1 << 3 + + class dp_cmd_msg(ovs_dp_msg): + """ + Message class that will be used to communicate with the kernel module. + """ + + nla_map = ( + ("OVS_DP_ATTR_UNSPEC", "none"), + ("OVS_DP_ATTR_NAME", "asciiz"), + ("OVS_DP_ATTR_UPCALL_PID", "uint32"), + ("OVS_DP_ATTR_STATS", "dpstats"), + ("OVS_DP_ATTR_MEGAFLOW_STATS", "megaflowstats"), + ("OVS_DP_ATTR_USER_FEATURES", "uint32"), + ("OVS_DP_ATTR_PAD", "none"), + ("OVS_DP_ATTR_MASKS_CACHE_SIZE", "uint32"), + ("OVS_DP_ATTR_PER_CPU_PIDS", "array(uint32)"), + ) + + class dpstats(nla): + fields = ( + ("hit", "=Q"), + ("missed", "=Q"), + ("lost", "=Q"), + ("flows", "=Q"), + ) + + class megaflowstats(nla): + fields = ( + ("mask_hit", "=Q"), + ("masks", "=I"), + ("padding", "=I"), + ("cache_hits", "=Q"), + ("pad1", "=Q"), + ) + + def __init__(self): + GenericNetlinkSocket.__init__(self) + self.bind(OVS_DATAPATH_FAMILY, OvsDatapath.dp_cmd_msg) + + def info(self, dpname, ifindex=0): + msg = OvsDatapath.dp_cmd_msg() + msg["cmd"] = OVS_DP_CMD_GET + msg["version"] = OVS_DATAPATH_VERSION + msg["reserved"] = 0 + msg["dpifindex"] = ifindex + msg["attrs"].append(["OVS_DP_ATTR_NAME", dpname]) + + try: + reply = self.nlm_request( + msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST + ) + reply = reply[0] + except NetlinkError as ne: + if ne.code == errno.ENODEV: + reply = None + else: + raise ne + + return reply + + def create(self, dpname, shouldUpcall=False, versionStr=None): + msg = OvsDatapath.dp_cmd_msg() + msg["cmd"] = OVS_DP_CMD_NEW + if versionStr is None: + msg["version"] = OVS_DATAPATH_VERSION + else: + msg["version"] = int(versionStr.split(":")[0], 0) + msg["reserved"] = 0 + msg["dpifindex"] = 0 + msg["attrs"].append(["OVS_DP_ATTR_NAME", dpname]) + + dpfeatures = 0 + if versionStr is not None and versionStr.find(":") != -1: + dpfeatures = int(versionStr.split(":")[1], 0) + else: + dpfeatures = OvsDatapath.OVS_DP_F_VPORT_PIDS + + msg["attrs"].append(["OVS_DP_ATTR_USER_FEATURES", dpfeatures]) + if not shouldUpcall: + msg["attrs"].append(["OVS_DP_ATTR_UPCALL_PID", 0]) + + try: + reply = self.nlm_request( + msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST | NLM_F_ACK + ) + reply = reply[0] + except NetlinkError as ne: + if ne.code == errno.EEXIST: + reply = None + else: + raise ne + + return reply + + def destroy(self, dpname): + msg = OvsDatapath.dp_cmd_msg() + msg["cmd"] = OVS_DP_CMD_DEL + msg["version"] = OVS_DATAPATH_VERSION + msg["reserved"] = 0 + msg["dpifindex"] = 0 + msg["attrs"].append(["OVS_DP_ATTR_NAME", dpname]) + + try: + reply = self.nlm_request( + msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST | NLM_F_ACK + ) + reply = reply[0] + except NetlinkError as ne: + if ne.code == errno.ENODEV: + reply = None + else: + raise ne + + return reply + + +class OvsVport(GenericNetlinkSocket): + class ovs_vport_msg(ovs_dp_msg): + nla_map = ( + ("OVS_VPORT_ATTR_UNSPEC", "none"), + ("OVS_VPORT_ATTR_PORT_NO", "uint32"), + ("OVS_VPORT_ATTR_TYPE", "uint32"), + ("OVS_VPORT_ATTR_NAME", "asciiz"), + ("OVS_VPORT_ATTR_OPTIONS", "none"), + ("OVS_VPORT_ATTR_UPCALL_PID", "array(uint32)"), + ("OVS_VPORT_ATTR_STATS", "vportstats"), + ("OVS_VPORT_ATTR_PAD", "none"), + ("OVS_VPORT_ATTR_IFINDEX", "uint32"), + ("OVS_VPORT_ATTR_NETNSID", "uint32"), + ) + + class vportstats(nla): + fields = ( + ("rx_packets", "=Q"), + ("tx_packets", "=Q"), + ("rx_bytes", "=Q"), + ("tx_bytes", "=Q"), + ("rx_errors", "=Q"), + ("tx_errors", "=Q"), + ("rx_dropped", "=Q"), + ("tx_dropped", "=Q"), + ) + + def type_to_str(vport_type): + if vport_type == 1: + return "netdev" + elif vport_type == 2: + return "internal" + elif vport_type == 3: + return "gre" + elif vport_type == 4: + return "vxlan" + elif vport_type == 5: + return "geneve" + return "unknown:%d" % vport_type + + def __init__(self): + GenericNetlinkSocket.__init__(self) + self.bind(OVS_VPORT_FAMILY, OvsVport.ovs_vport_msg) + + def info(self, vport_name, dpifindex=0, portno=None): + msg = OvsVport.ovs_vport_msg() + + msg["cmd"] = OVS_VPORT_CMD_GET + msg["version"] = OVS_DATAPATH_VERSION + msg["reserved"] = 0 + msg["dpifindex"] = dpifindex + + if portno is None: + msg["attrs"].append(["OVS_VPORT_ATTR_NAME", vport_name]) + else: + msg["attrs"].append(["OVS_VPORT_ATTR_PORT_NO", portno]) + + try: + reply = self.nlm_request( + msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST + ) + reply = reply[0] + except NetlinkError as ne: + if ne.code == errno.ENODEV: + reply = None + else: + raise ne + return reply + + +def print_ovsdp_full(dp_lookup_rep, ifindex, ndb=NDB()): + dp_name = dp_lookup_rep.get_attr("OVS_DP_ATTR_NAME") + base_stats = dp_lookup_rep.get_attr("OVS_DP_ATTR_STATS") + megaflow_stats = dp_lookup_rep.get_attr("OVS_DP_ATTR_MEGAFLOW_STATS") + user_features = dp_lookup_rep.get_attr("OVS_DP_ATTR_USER_FEATURES") + masks_cache_size = dp_lookup_rep.get_attr("OVS_DP_ATTR_MASKS_CACHE_SIZE") + + print("%s:" % dp_name) + print( + " lookups: hit:%d missed:%d lost:%d" + % (base_stats["hit"], base_stats["missed"], base_stats["lost"]) + ) + print(" flows:%d" % base_stats["flows"]) + pkts = base_stats["hit"] + base_stats["missed"] + avg = (megaflow_stats["mask_hit"] / pkts) if pkts != 0 else 0.0 + print( + " masks: hit:%d total:%d hit/pkt:%f" + % (megaflow_stats["mask_hit"], megaflow_stats["masks"], avg) + ) + print(" caches:") + print(" masks-cache: size:%d" % masks_cache_size) + + if user_features is not None: + print(" features: 0x%X" % user_features) + + # port print out + vpl = OvsVport() + for iface in ndb.interfaces: + rep = vpl.info(iface.ifname, ifindex) + if rep is not None: + print( + " port %d: %s (%s)" + % ( + rep.get_attr("OVS_VPORT_ATTR_PORT_NO"), + rep.get_attr("OVS_VPORT_ATTR_NAME"), + OvsVport.type_to_str(rep.get_attr("OVS_VPORT_ATTR_TYPE")), + ) + ) + + +def main(argv): + parser = argparse.ArgumentParser() + parser.add_argument( + "-v", + "--verbose", + action="count", + help="Increment 'verbose' output counter.", + ) + subparsers = parser.add_subparsers() + + showdpcmd = subparsers.add_parser("show") + showdpcmd.add_argument( + "showdp", metavar="N", type=str, nargs="?", help="Datapath Name" + ) + + adddpcmd = subparsers.add_parser("add-dp") + adddpcmd.add_argument("adddp", help="Datapath Name") + adddpcmd.add_argument( + "-u", + "--upcall", + action="store_true", + help="Leave open a reader for upcalls", + ) + adddpcmd.add_argument( + "-V", + "--versioning", + required=False, + help="Specify a custom version / feature string", + ) + + deldpcmd = subparsers.add_parser("del-dp") + deldpcmd.add_argument("deldp", help="Datapath Name") + + args = parser.parse_args() + + ovsdp = OvsDatapath() + ndb = NDB() + + if hasattr(args, "showdp"): + found = False + for iface in ndb.interfaces: + rep = None + if args.showdp is None: + rep = ovsdp.info(iface.ifname, 0) + elif args.showdp == iface.ifname: + rep = ovsdp.info(iface.ifname, 0) + + if rep is not None: + found = True + print_ovsdp_full(rep, iface.index, ndb) + + if not found: + msg = "No DP found" + if args.showdp is not None: + msg += ":'%s'" % args.showdp + print(msg) + elif hasattr(args, "adddp"): + rep = ovsdp.create(args.adddp, args.upcall, args.versioning) + if rep is None: + print("DP '%s' already exists" % args.adddp) + else: + print("DP '%s' added" % args.adddp) + elif hasattr(args, "deldp"): + ovsdp.destroy(args.deldp) + + return 0 + + +if __name__ == "__main__": + sys.exit(main(sys.argv)) |