diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-02-05 09:39:26 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-02-05 09:39:26 -0800 |
| commit | 8fdb05de0e2db89d8f56144c60ab784812e8c3b7 (patch) | |
| tree | 89d2d6564d3e401fc43217a574e08ba7ed1e7b8d | |
| parent | b20624608f350c5dadd74577629e90715d351e2c (diff) | |
| parent | bbf4a17ad9ffc4e3d7ec13d73ecd59dea149ed25 (diff) | |
| download | linux-master.tar.gz | |
Pull networking fixes from Jakub Kicinski:
"Including fixes from wireless and Netfilter.
Previous releases - regressions:
- eth: stmmac: fix stm32 (and potentially others) resume regression
- nf_tables: fix inverted genmask check in nft_map_catchall_activate()
- usb: r8152: fix resume reset deadlock
- fix reporting RXH_XFRM_NO_CHANGE as input_xfrm for RSS contexts
Previous releases - always broken:
- sched: cls_u32: use skb_header_pointer_careful() to avoid OOB reads
with malicious u32 rules
- eth: ice: timestamping related fixes"
* tag 'net-6.19-rc9' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (38 commits)
ipv6: Fix ECMP sibling count mismatch when clearing RTF_ADDRCONF
netfilter: nf_tables: fix inverted genmask check in nft_map_catchall_activate()
net: cpsw: Execute ndo_set_rx_mode callback in a work queue
net: cpsw_new: Execute ndo_set_rx_mode callback in a work queue
gve: Correct ethtool rx_dropped calculation
gve: Fix stats report corruption on queue count change
selftest: net: add a test-case for encap segmentation after GRO
net: gro: fix outer network offset
net: add proper RCU protection to /proc/net/ptype
net: ethernet: adi: adin1110: Check return value of devm_gpiod_get_optional() in adin1110_check_spi()
wifi: iwlwifi: mvm: pause TCM on fast resume
wifi: iwlwifi: mld: cancel mlo_scan_start_wk
net: spacemit: k1-emac: fix jumbo frame support
net: enetc: Convert 16-bit register reads to 32-bit for ENETC v4
net: enetc: Convert 16-bit register writes to 32-bit for ENETC v4
net: enetc: Remove CBDR cacheability AXI settings for ENETC v4
net: enetc: Remove SI/BDR cacheability AXI settings for ENETC v4
tipc: use kfree_sensitive() for session key material
net: stmmac: fix stm32 (and potentially others) resume regression
net: rss: fix reporting RXH_XFRM_NO_CHANGE as input_xfrm for contexts
...
38 files changed, 513 insertions, 234 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 36abe938f960df..e0876732376362 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -20978,6 +20978,18 @@ F: Documentation/devicetree/bindings/net/pse-pd/ F: drivers/net/pse-pd/ F: net/ethtool/pse-pd.c +PSP SECURITY PROTOCOL +M: Daniel Zahka <daniel.zahka@gmail.com> +M: Jakub Kicinski <kuba@kernel.org> +M: Willem de Bruijn <willemdebruijn.kernel@gmail.com> +F: Documentation/netlink/specs/psp.yaml +F: Documentation/networking/psp.rst +F: include/net/psp/ +F: include/net/psp.h +F: include/uapi/linux/psp.h +F: net/psp/ +K: struct\ psp(_assoc|_dev|hdr)\b + PSTORE FILESYSTEM M: Kees Cook <kees@kernel.org> R: Tony Luck <tony.luck@intel.com> diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index 30f9d271e59531..71a2397edf2bbf 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -1089,6 +1089,9 @@ static int adin1110_check_spi(struct adin1110_priv *priv) reset_gpio = devm_gpiod_get_optional(&priv->spidev->dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(reset_gpio)) + return dev_err_probe(&priv->spidev->dev, PTR_ERR(reset_gpio), + "failed to get reset gpio\n"); if (reset_gpio) { /* MISO pin is used for internal configuration, can't have * anyone else disturbing the SDO line. diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 0732440eeacd62..c1a3df22525492 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3505,6 +3505,23 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) */ netdev->netdev_ops = &lionetdevops; + lio = GET_LIO(netdev); + + memset(lio, 0, sizeof(struct lio)); + + lio->ifidx = ifidx_or_pfnum; + + props = &octeon_dev->props[i]; + props->gmxport = resp->cfg_info.linfo.gmxport; + props->netdev = netdev; + + /* Point to the properties for octeon device to which this + * interface belongs. + */ + lio->oct_dev = octeon_dev; + lio->octprops = props; + lio->netdev = netdev; + retval = netif_set_real_num_rx_queues(netdev, num_oqueues); if (retval) { dev_err(&octeon_dev->pci_dev->dev, @@ -3521,16 +3538,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) goto setup_nic_dev_free; } - lio = GET_LIO(netdev); - - memset(lio, 0, sizeof(struct lio)); - - lio->ifidx = ifidx_or_pfnum; - - props = &octeon_dev->props[i]; - props->gmxport = resp->cfg_info.linfo.gmxport; - props->netdev = netdev; - lio->linfo.num_rxpciq = num_oqueues; lio->linfo.num_txpciq = num_iqueues; for (j = 0; j < num_oqueues; j++) { @@ -3596,13 +3603,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) netdev->min_mtu = LIO_MIN_MTU_SIZE; netdev->max_mtu = LIO_MAX_MTU_SIZE; - /* Point to the properties for octeon device to which this - * interface belongs. - */ - lio->oct_dev = octeon_dev; - lio->octprops = props; - lio->netdev = netdev; - dev_dbg(&octeon_dev->pci_dev->dev, "if%d gmx: %d hw_addr: 0x%llx\n", i, lio->linfo.gmxport, CVM_CAST64(lio->linfo.hw_addr)); @@ -3750,6 +3750,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) if (!devlink) { device_unlock(&octeon_dev->pci_dev->dev); dev_err(&octeon_dev->pci_dev->dev, "devlink alloc failed\n"); + i--; goto setup_nic_dev_free; } @@ -3765,11 +3766,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) setup_nic_dev_free: - while (i--) { + do { dev_err(&octeon_dev->pci_dev->dev, "NIC ifidx:%d Setup failed\n", i); liquidio_destroy_nic_device(octeon_dev, i); - } + } while (i--); setup_nic_dev_done: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index e02942dbbcce53..43c595f3b84e45 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -2212,11 +2212,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) setup_nic_dev_free: - while (i--) { + do { dev_err(&octeon_dev->pci_dev->dev, "NIC ifidx:%d Setup failed\n", i); liquidio_destroy_nic_device(octeon_dev, i); - } + } while (i--); setup_nic_dev_done: diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index b1e1ad9e4b48e6..66240c340492ce 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1531,6 +1531,10 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) } if_id = (status & 0xFFFF0000) >> 16; + if (if_id >= ethsw->sw_attr.num_ifs) { + dev_err(dev, "Invalid if_id %d in IRQ status\n", if_id); + goto out; + } port_priv = ethsw->ports[if_id]; if (status & DPSW_IRQ_EVENT_LINK_CHANGED) @@ -3024,6 +3028,12 @@ static int dpaa2_switch_init(struct fsl_mc_device *sw_dev) goto err_close; } + if (!ethsw->sw_attr.num_ifs) { + dev_err(dev, "DPSW device has no interfaces\n"); + err = -ENODEV; + goto err_close; + } + err = dpsw_get_api_version(ethsw->mc_io, 0, ðsw->major, ðsw->minor); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 53b26cece16a80..e380a4f3985560 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2512,10 +2512,13 @@ int enetc_configure_si(struct enetc_ndev_priv *priv) struct enetc_hw *hw = &si->hw; int err; - /* set SI cache attributes */ - enetc_wr(hw, ENETC_SICAR0, - ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT); - enetc_wr(hw, ENETC_SICAR1, ENETC_SICAR_MSI); + if (is_enetc_rev1(si)) { + /* set SI cache attributes */ + enetc_wr(hw, ENETC_SICAR0, + ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT); + enetc_wr(hw, ENETC_SICAR1, ENETC_SICAR_MSI); + } + /* enable SI */ enetc_wr(hw, ENETC_SIMR, ENETC_SIMR_EN); diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c index 498346dd996aa9..5850540634b0cd 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -59,10 +59,10 @@ static void enetc4_pf_set_si_primary_mac(struct enetc_hw *hw, int si, if (si != 0) { __raw_writel(upper, hw->port + ENETC4_PSIPMAR0(si)); - __raw_writew(lower, hw->port + ENETC4_PSIPMAR1(si)); + __raw_writel(lower, hw->port + ENETC4_PSIPMAR1(si)); } else { __raw_writel(upper, hw->port + ENETC4_PMAR0); - __raw_writew(lower, hw->port + ENETC4_PMAR1); + __raw_writel(lower, hw->port + ENETC4_PMAR1); } } @@ -73,7 +73,7 @@ static void enetc4_pf_get_si_primary_mac(struct enetc_hw *hw, int si, u16 lower; upper = __raw_readl(hw->port + ENETC4_PSIPMAR0(si)); - lower = __raw_readw(hw->port + ENETC4_PSIPMAR1(si)); + lower = __raw_readl(hw->port + ENETC4_PSIPMAR1(si)); put_unaligned_le32(upper, addr); put_unaligned_le16(lower, addr + 4); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c index 3d5f31879d5c64..a635bfdc30afc2 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c @@ -74,10 +74,6 @@ int enetc4_setup_cbdr(struct enetc_si *si) if (!user->ring) return -ENOMEM; - /* set CBDR cache attributes */ - enetc_wr(hw, ENETC_SICAR2, - ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT); - regs.pir = hw->reg + ENETC_SICBDRPIR; regs.cir = hw->reg + ENETC_SICBDRCIR; regs.mr = hw->reg + ENETC_SICBDRMR; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 7b882b8921fe94..662e4fbafb74c7 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -708,13 +708,24 @@ struct enetc_cmd_rfse { #define ENETC_RFSE_EN BIT(15) #define ENETC_RFSE_MODE_BD 2 +static inline void enetc_get_primary_mac_addr(struct enetc_hw *hw, u8 *addr) +{ + u32 upper; + u16 lower; + + upper = __raw_readl(hw->reg + ENETC_SIPMAR0); + lower = __raw_readl(hw->reg + ENETC_SIPMAR1); + + put_unaligned_le32(upper, addr); + put_unaligned_le16(lower, addr + 4); +} + static inline void enetc_load_primary_mac_addr(struct enetc_hw *hw, struct net_device *ndev) { - u8 addr[ETH_ALEN] __aligned(4); + u8 addr[ETH_ALEN]; - *(u32 *)addr = __raw_readl(hw->reg + ENETC_SIPMAR0); - *(u16 *)(addr + 4) = __raw_readw(hw->reg + ENETC_SIPMAR1); + enetc_get_primary_mac_addr(hw, addr); eth_hw_addr_set(ndev, addr); } diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 311b106160b20a..66ddc4413f8dff 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -152,11 +152,13 @@ gve_get_ethtool_stats(struct net_device *netdev, u64 tmp_rx_pkts, tmp_rx_hsplit_pkt, tmp_rx_bytes, tmp_rx_hsplit_bytes, tmp_rx_skb_alloc_fail, tmp_rx_buf_alloc_fail, tmp_rx_desc_err_dropped_pkt, tmp_rx_hsplit_unsplit_pkt, - tmp_tx_pkts, tmp_tx_bytes; + tmp_tx_pkts, tmp_tx_bytes, + tmp_xdp_tx_errors, tmp_xdp_redirect_errors; u64 rx_buf_alloc_fail, rx_desc_err_dropped_pkt, rx_hsplit_unsplit_pkt, rx_pkts, rx_hsplit_pkt, rx_skb_alloc_fail, rx_bytes, tx_pkts, tx_bytes, - tx_dropped; - int stats_idx, base_stats_idx, max_stats_idx; + tx_dropped, xdp_tx_errors, xdp_redirect_errors; + int rx_base_stats_idx, max_rx_stats_idx, max_tx_stats_idx; + int stats_idx, stats_region_len, nic_stats_len; struct stats *report_stats; int *rx_qid_to_stats_idx; int *tx_qid_to_stats_idx; @@ -198,6 +200,7 @@ gve_get_ethtool_stats(struct net_device *netdev, for (rx_pkts = 0, rx_bytes = 0, rx_hsplit_pkt = 0, rx_skb_alloc_fail = 0, rx_buf_alloc_fail = 0, rx_desc_err_dropped_pkt = 0, rx_hsplit_unsplit_pkt = 0, + xdp_tx_errors = 0, xdp_redirect_errors = 0, ring = 0; ring < priv->rx_cfg.num_queues; ring++) { if (priv->rx) { @@ -215,6 +218,9 @@ gve_get_ethtool_stats(struct net_device *netdev, rx->rx_desc_err_dropped_pkt; tmp_rx_hsplit_unsplit_pkt = rx->rx_hsplit_unsplit_pkt; + tmp_xdp_tx_errors = rx->xdp_tx_errors; + tmp_xdp_redirect_errors = + rx->xdp_redirect_errors; } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); rx_pkts += tmp_rx_pkts; @@ -224,6 +230,8 @@ gve_get_ethtool_stats(struct net_device *netdev, rx_buf_alloc_fail += tmp_rx_buf_alloc_fail; rx_desc_err_dropped_pkt += tmp_rx_desc_err_dropped_pkt; rx_hsplit_unsplit_pkt += tmp_rx_hsplit_unsplit_pkt; + xdp_tx_errors += tmp_xdp_tx_errors; + xdp_redirect_errors += tmp_xdp_redirect_errors; } } for (tx_pkts = 0, tx_bytes = 0, tx_dropped = 0, ring = 0; @@ -249,8 +257,8 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = rx_bytes; data[i++] = tx_bytes; /* total rx dropped packets */ - data[i++] = rx_skb_alloc_fail + rx_buf_alloc_fail + - rx_desc_err_dropped_pkt; + data[i++] = rx_skb_alloc_fail + rx_desc_err_dropped_pkt + + xdp_tx_errors + xdp_redirect_errors; data[i++] = tx_dropped; data[i++] = priv->tx_timeo_cnt; data[i++] = rx_skb_alloc_fail; @@ -265,20 +273,38 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = priv->stats_report_trigger_cnt; i = GVE_MAIN_STATS_LEN; - /* For rx cross-reporting stats, start from nic rx stats in report */ - base_stats_idx = GVE_TX_STATS_REPORT_NUM * num_tx_queues + - GVE_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues; - /* The boundary between driver stats and NIC stats shifts if there are - * stopped queues. - */ - base_stats_idx += NIC_RX_STATS_REPORT_NUM * num_stopped_rxqs + - NIC_TX_STATS_REPORT_NUM * num_stopped_txqs; - max_stats_idx = NIC_RX_STATS_REPORT_NUM * - (priv->rx_cfg.num_queues - num_stopped_rxqs) + - base_stats_idx; + rx_base_stats_idx = 0; + max_rx_stats_idx = 0; + max_tx_stats_idx = 0; + stats_region_len = priv->stats_report_len - + sizeof(struct gve_stats_report); + nic_stats_len = (NIC_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues + + NIC_TX_STATS_REPORT_NUM * num_tx_queues) * sizeof(struct stats); + if (unlikely((stats_region_len - + nic_stats_len) % sizeof(struct stats))) { + net_err_ratelimited("Starting index of NIC stats should be multiple of stats size"); + } else { + /* For rx cross-reporting stats, + * start from nic rx stats in report + */ + rx_base_stats_idx = (stats_region_len - nic_stats_len) / + sizeof(struct stats); + /* The boundary between driver stats and NIC stats + * shifts if there are stopped queues + */ + rx_base_stats_idx += NIC_RX_STATS_REPORT_NUM * + num_stopped_rxqs + NIC_TX_STATS_REPORT_NUM * + num_stopped_txqs; + max_rx_stats_idx = NIC_RX_STATS_REPORT_NUM * + (priv->rx_cfg.num_queues - num_stopped_rxqs) + + rx_base_stats_idx; + max_tx_stats_idx = NIC_TX_STATS_REPORT_NUM * + (num_tx_queues - num_stopped_txqs) + + max_rx_stats_idx; + } /* Preprocess the stats report for rx, map queue id to start index */ skip_nic_stats = false; - for (stats_idx = base_stats_idx; stats_idx < max_stats_idx; + for (stats_idx = rx_base_stats_idx; stats_idx < max_rx_stats_idx; stats_idx += NIC_RX_STATS_REPORT_NUM) { u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name); u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id); @@ -311,6 +337,9 @@ gve_get_ethtool_stats(struct net_device *netdev, tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; tmp_rx_desc_err_dropped_pkt = rx->rx_desc_err_dropped_pkt; + tmp_xdp_tx_errors = rx->xdp_tx_errors; + tmp_xdp_redirect_errors = + rx->xdp_redirect_errors; } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); data[i++] = tmp_rx_bytes; @@ -321,8 +350,9 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = rx->rx_frag_alloc_cnt; /* rx dropped packets */ data[i++] = tmp_rx_skb_alloc_fail + - tmp_rx_buf_alloc_fail + - tmp_rx_desc_err_dropped_pkt; + tmp_rx_desc_err_dropped_pkt + + tmp_xdp_tx_errors + + tmp_xdp_redirect_errors; data[i++] = rx->rx_copybreak_pkt; data[i++] = rx->rx_copied_pkt; /* stats from NIC */ @@ -354,14 +384,9 @@ gve_get_ethtool_stats(struct net_device *netdev, i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS; } - /* For tx cross-reporting stats, start from nic tx stats in report */ - base_stats_idx = max_stats_idx; - max_stats_idx = NIC_TX_STATS_REPORT_NUM * - (num_tx_queues - num_stopped_txqs) + - max_stats_idx; - /* Preprocess the stats report for tx, map queue id to start index */ skip_nic_stats = false; - for (stats_idx = base_stats_idx; stats_idx < max_stats_idx; + /* NIC TX stats start right after NIC RX stats */ + for (stats_idx = max_rx_stats_idx; stats_idx < max_tx_stats_idx; stats_idx += NIC_TX_STATS_REPORT_NUM) { u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name); u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 52c5e4942cd489..dbc84de39b7078 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -283,9 +283,9 @@ static int gve_alloc_stats_report(struct gve_priv *priv) int tx_stats_num, rx_stats_num; tx_stats_num = (GVE_TX_STATS_REPORT_NUM + NIC_TX_STATS_REPORT_NUM) * - gve_num_tx_queues(priv); + priv->tx_cfg.max_queues; rx_stats_num = (GVE_RX_STATS_REPORT_NUM + NIC_RX_STATS_REPORT_NUM) * - priv->rx_cfg.num_queues; + priv->rx_cfg.max_queues; priv->stats_report_len = struct_size(priv->stats_report, stats, size_add(tx_stats_num, rx_stats_num)); priv->stats_report = diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 0b1cc0481027ab..d3bc3207054f90 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9030,7 +9030,6 @@ int i40e_open(struct net_device *netdev) TCP_FLAG_FIN | TCP_FLAG_CWR) >> 16); wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16); - udp_tunnel_get_rx_info(netdev); return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 71c6d53b461e9f..d04605d3e61af1 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3314,18 +3314,20 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data) if (ice_is_reset_in_progress(pf->state)) goto skip_irq; - if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) { - /* Process outstanding Tx timestamps. If there is more work, - * re-arm the interrupt to trigger again. - */ - if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) { - wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); - ice_flush(hw); - } - } + if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) + ice_ptp_process_ts(pf); skip_irq: ice_irq_dynamic_ena(hw, NULL, NULL); + ice_flush(hw); + + if (ice_ptp_tx_tstamps_pending(pf)) { + /* If any new Tx timestamps happened while in interrupt, + * re-arm the interrupt to trigger it again. + */ + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); + } return IRQ_HANDLED; } @@ -7807,6 +7809,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) /* Restore timestamp mode settings after VSI rebuild */ ice_ptp_restore_timestamp_mode(pf); + + /* Start PTP periodic work after VSI is fully rebuilt */ + ice_ptp_queue_work(pf); return; err_vsi_rebuild: @@ -9657,9 +9662,6 @@ int ice_open_internal(struct net_device *netdev) netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n", vsi->vsi_num, vsi->vsw->sw_id); - /* Update existing tunnels information */ - udp_tunnel_get_rx_info(netdev); - return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 4c8d20f2d2c0a4..27268300147625 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -573,6 +573,9 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) pf = ptp_port_to_pf(ptp_port); hw = &pf->hw; + if (!tx->init) + return; + /* Read the Tx ready status first */ if (tx->has_ready_bitmap) { err = ice_get_phy_tx_tstamp_ready(hw, tx->block, &tstamp_ready); @@ -674,14 +677,9 @@ skip_ts_read: pf->ptp.tx_hwtstamp_good += tstamp_good; } -/** - * ice_ptp_tx_tstamp_owner - Process Tx timestamps for all ports on the device - * @pf: Board private structure - */ -static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) +static void ice_ptp_tx_tstamp_owner(struct ice_pf *pf) { struct ice_ptp_port *port; - unsigned int i; mutex_lock(&pf->adapter->ports.lock); list_for_each_entry(port, &pf->adapter->ports.ports, list_node) { @@ -693,49 +691,6 @@ static enum ice_tx_tstamp_work ice_ptp_tx_tstamp_owner(struct ice_pf *pf) ice_ptp_process_tx_tstamp(tx); } mutex_unlock(&pf->adapter->ports.lock); - - for (i = 0; i < ICE_GET_QUAD_NUM(pf->hw.ptp.num_lports); i++) { - u64 tstamp_ready; - int err; - - /* Read the Tx ready status first */ - err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); - if (err) - break; - else if (tstamp_ready) - return ICE_TX_TSTAMP_WORK_PENDING; - } - - return ICE_TX_TSTAMP_WORK_DONE; -} - -/** - * ice_ptp_tx_tstamp - Process Tx timestamps for this function. - * @tx: Tx tracking structure to initialize - * - * Returns: ICE_TX_TSTAMP_WORK_PENDING if there are any outstanding incomplete - * Tx timestamps, or ICE_TX_TSTAMP_WORK_DONE otherwise. - */ -static enum ice_tx_tstamp_work ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) -{ - bool more_timestamps; - unsigned long flags; - - if (!tx->init) - return ICE_TX_TSTAMP_WORK_DONE; - - /* Process the Tx timestamp tracker */ - ice_ptp_process_tx_tstamp(tx); - - /* Check if there are outstanding Tx timestamps */ - spin_lock_irqsave(&tx->lock, flags); - more_timestamps = tx->init && !bitmap_empty(tx->in_use, tx->len); - spin_unlock_irqrestore(&tx->lock, flags); - - if (more_timestamps) - return ICE_TX_TSTAMP_WORK_PENDING; - - return ICE_TX_TSTAMP_WORK_DONE; } /** @@ -1347,9 +1302,12 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup) /* Do not reconfigure E810 or E830 PHY */ return; case ICE_MAC_GENERIC: - case ICE_MAC_GENERIC_3K_E825: ice_ptp_port_phy_restart(ptp_port); return; + case ICE_MAC_GENERIC_3K_E825: + if (linkup) + ice_ptp_port_phy_restart(ptp_port); + return; default: dev_warn(ice_pf_to_dev(pf), "%s: Unknown PHY type\n", __func__); } @@ -2663,30 +2621,92 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) return idx + tx->offset; } -/** - * ice_ptp_process_ts - Process the PTP Tx timestamps - * @pf: Board private structure - * - * Returns: ICE_TX_TSTAMP_WORK_PENDING if there are any outstanding Tx - * timestamps that need processing, and ICE_TX_TSTAMP_WORK_DONE otherwise. - */ -enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf) +void ice_ptp_process_ts(struct ice_pf *pf) { switch (pf->ptp.tx_interrupt_mode) { case ICE_PTP_TX_INTERRUPT_NONE: /* This device has the clock owner handle timestamps for it */ - return ICE_TX_TSTAMP_WORK_DONE; + return; case ICE_PTP_TX_INTERRUPT_SELF: /* This device handles its own timestamps */ - return ice_ptp_tx_tstamp(&pf->ptp.port.tx); + ice_ptp_process_tx_tstamp(&pf->ptp.port.tx); + return; case ICE_PTP_TX_INTERRUPT_ALL: /* This device handles timestamps for all ports */ - return ice_ptp_tx_tstamp_owner(pf); + ice_ptp_tx_tstamp_owner(pf); + return; + default: + WARN_ONCE(1, "Unexpected Tx timestamp interrupt mode %u\n", + pf->ptp.tx_interrupt_mode); + return; + } +} + +static bool ice_port_has_timestamps(struct ice_ptp_tx *tx) +{ + bool more_timestamps; + + scoped_guard(spinlock_irqsave, &tx->lock) { + if (!tx->init) + return false; + + more_timestamps = !bitmap_empty(tx->in_use, tx->len); + } + + return more_timestamps; +} + +static bool ice_any_port_has_timestamps(struct ice_pf *pf) +{ + struct ice_ptp_port *port; + + scoped_guard(mutex, &pf->adapter->ports.lock) { + list_for_each_entry(port, &pf->adapter->ports.ports, + list_node) { + struct ice_ptp_tx *tx = &port->tx; + + if (ice_port_has_timestamps(tx)) + return true; + } + } + + return false; +} + +bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + unsigned int i; + + /* Check software indicator */ + switch (pf->ptp.tx_interrupt_mode) { + case ICE_PTP_TX_INTERRUPT_NONE: + return false; + case ICE_PTP_TX_INTERRUPT_SELF: + if (ice_port_has_timestamps(&pf->ptp.port.tx)) + return true; + break; + case ICE_PTP_TX_INTERRUPT_ALL: + if (ice_any_port_has_timestamps(pf)) + return true; + break; default: WARN_ONCE(1, "Unexpected Tx timestamp interrupt mode %u\n", pf->ptp.tx_interrupt_mode); - return ICE_TX_TSTAMP_WORK_DONE; + break; + } + + /* Check hardware indicator */ + for (i = 0; i < ICE_GET_QUAD_NUM(hw->ptp.num_lports); i++) { + u64 tstamp_ready = 0; + int err; + + err = ice_get_phy_tx_tstamp_ready(&pf->hw, i, &tstamp_ready); + if (err || tstamp_ready) + return true; } + + return false; } /** @@ -2738,7 +2758,9 @@ irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) return IRQ_WAKE_THREAD; case ICE_MAC_E830: /* E830 can read timestamps in the top half using rd32() */ - if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) { + ice_ptp_process_ts(pf); + + if (ice_ptp_tx_tstamps_pending(pf)) { /* Process outstanding Tx timestamps. If there * is more work, re-arm the interrupt to trigger again. */ @@ -2818,6 +2840,20 @@ static void ice_ptp_periodic_work(struct kthread_work *work) } /** + * ice_ptp_queue_work - Queue PTP periodic work for a PF + * @pf: Board private structure + * + * Helper function to queue PTP periodic work after VSI rebuild completes. + * This ensures that PTP work only runs when VSI structures are ready. + */ +void ice_ptp_queue_work(struct ice_pf *pf) +{ + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags) && + pf->ptp.state == ICE_PTP_READY) + kthread_queue_delayed_work(pf->ptp.kworker, &pf->ptp.work, 0); +} + +/** * ice_ptp_prepare_rebuild_sec - Prepare second NAC for PTP reset or rebuild * @pf: Board private structure * @rebuild: rebuild if true, prepare if false @@ -2835,10 +2871,15 @@ static void ice_ptp_prepare_rebuild_sec(struct ice_pf *pf, bool rebuild, struct ice_pf *peer_pf = ptp_port_to_pf(port); if (!ice_is_primary(&peer_pf->hw)) { - if (rebuild) + if (rebuild) { + /* TODO: When implementing rebuild=true: + * 1. Ensure secondary PFs' VSIs are rebuilt + * 2. Call ice_ptp_queue_work(peer_pf) after VSI rebuild + */ ice_ptp_rebuild(peer_pf, reset_type); - else + } else { ice_ptp_prepare_for_reset(peer_pf, reset_type); + } } } } @@ -2984,9 +3025,6 @@ void ice_ptp_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ptp->state = ICE_PTP_READY; - /* Start periodic work going */ - kthread_queue_delayed_work(ptp->kworker, &ptp->work, 0); - dev_info(ice_pf_to_dev(pf), "PTP reset successful\n"); return; @@ -3191,8 +3229,9 @@ static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) { switch (pf->hw.mac_type) { case ICE_MAC_GENERIC: - /* E822 based PHY has the clock owner process the interrupt - * for all ports. + case ICE_MAC_GENERIC_3K_E825: + /* E82x hardware has the clock owner process timestamps for + * all ports. */ if (ice_pf_src_tmr_owned(pf)) pf->ptp.tx_interrupt_mode = ICE_PTP_TX_INTERRUPT_ALL; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 27016aac4f1e8a..8c44bd758a4fe3 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -304,8 +304,9 @@ void ice_ptp_extts_event(struct ice_pf *pf); s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx); void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx); -enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf); +void ice_ptp_process_ts(struct ice_pf *pf); irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf); +bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf); u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts); @@ -317,6 +318,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, void ice_ptp_init(struct ice_pf *pf); void ice_ptp_release(struct ice_pf *pf); void ice_ptp_link_change(struct ice_pf *pf, bool linkup); +void ice_ptp_queue_work(struct ice_pf *pf); #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ static inline int ice_ptp_hwtstamp_get(struct net_device *netdev, @@ -345,16 +347,18 @@ static inline void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) static inline void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) { } -static inline bool ice_ptp_process_ts(struct ice_pf *pf) -{ - return true; -} +static inline void ice_ptp_process_ts(struct ice_pf *pf) { } static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) { return IRQ_HANDLED; } +static inline bool ice_ptp_tx_tstamps_pending(struct ice_pf *pf) +{ + return false; +} + static inline u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) { @@ -383,6 +387,10 @@ static inline void ice_ptp_link_change(struct ice_pf *pf, bool linkup) { } +static inline void ice_ptp_queue_work(struct ice_pf *pf) +{ +} + static inline int ice_ptp_clock_index(struct ice_pf *pf) { return -1; diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c index 88e9424d2d51aa..b49c4708bf9eb1 100644 --- a/drivers/net/ethernet/spacemit/k1_emac.c +++ b/drivers/net/ethernet/spacemit/k1_emac.c @@ -12,6 +12,7 @@ #include <linux/dma-mapping.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> +#include <linux/if_vlan.h> #include <linux/interrupt.h> #include <linux/io.h> #include <linux/iopoll.h> @@ -38,7 +39,7 @@ #define EMAC_DEFAULT_BUFSIZE 1536 #define EMAC_RX_BUF_2K 2048 -#define EMAC_RX_BUF_4K 4096 +#define EMAC_RX_BUF_MAX FIELD_MAX(RX_DESC_1_BUFFER_SIZE_1_MASK) /* Tuning parameters from SpacemiT */ #define EMAC_TX_FRAMES 64 @@ -202,8 +203,7 @@ static void emac_init_hw(struct emac_priv *priv) { /* Destination address for 802.3x Ethernet flow control */ u8 fc_dest_addr[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x01 }; - - u32 rxirq = 0, dma = 0; + u32 rxirq = 0, dma = 0, frame_sz; regmap_set_bits(priv->regmap_apmu, priv->regmap_apmu_offset + APMU_EMAC_CTRL_REG, @@ -228,6 +228,15 @@ static void emac_init_hw(struct emac_priv *priv) DEFAULT_TX_THRESHOLD); emac_wr(priv, MAC_RECEIVE_PACKET_START_THRESHOLD, DEFAULT_RX_THRESHOLD); + /* Set maximum frame size and jabber size based on configured MTU, + * accounting for Ethernet header, double VLAN tags, and FCS. + */ + frame_sz = priv->ndev->mtu + ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN; + + emac_wr(priv, MAC_MAXIMUM_FRAME_SIZE, frame_sz); + emac_wr(priv, MAC_TRANSMIT_JABBER_SIZE, frame_sz); + emac_wr(priv, MAC_RECEIVE_JABBER_SIZE, frame_sz); + /* Configure flow control (enabled in emac_adjust_link() later) */ emac_set_mac_addr_reg(priv, fc_dest_addr, MAC_FC_SOURCE_ADDRESS_HIGH); emac_wr(priv, MAC_FC_PAUSE_HIGH_THRESHOLD, DEFAULT_FC_FIFO_HIGH); @@ -924,14 +933,14 @@ static int emac_change_mtu(struct net_device *ndev, int mtu) return -EBUSY; } - frame_len = mtu + ETH_HLEN + ETH_FCS_LEN; + frame_len = mtu + ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN; if (frame_len <= EMAC_DEFAULT_BUFSIZE) priv->dma_buf_sz = EMAC_DEFAULT_BUFSIZE; else if (frame_len <= EMAC_RX_BUF_2K) priv->dma_buf_sz = EMAC_RX_BUF_2K; else - priv->dma_buf_sz = EMAC_RX_BUF_4K; + priv->dma_buf_sz = EMAC_RX_BUF_MAX; ndev->mtu = mtu; @@ -2025,7 +2034,7 @@ static int emac_probe(struct platform_device *pdev) ndev->hw_features = NETIF_F_SG; ndev->features |= ndev->hw_features; - ndev->max_mtu = EMAC_RX_BUF_4K - (ETH_HLEN + ETH_FCS_LEN); + ndev->max_mtu = EMAC_RX_BUF_MAX - (ETH_HLEN + 2 * VLAN_HLEN + ETH_FCS_LEN); ndev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; priv = netdev_priv(ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3f42843cd9ed01..a379221b96a348 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -8042,7 +8042,7 @@ int stmmac_suspend(struct device *dev) u32 chan; if (!ndev || !netif_running(ndev)) - return 0; + goto suspend_bsp; mutex_lock(&priv->lock); @@ -8082,6 +8082,7 @@ int stmmac_suspend(struct device *dev) if (stmmac_fpe_supported(priv)) ethtool_mmsv_stop(&priv->fpe_cfg.mmsv); +suspend_bsp: if (priv->plat->suspend) return priv->plat->suspend(dev, priv->plat->bsp_priv); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 54c24cd3d3be63..b0e18bdc2c8510 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -305,12 +305,19 @@ static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num) return 0; } -static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +static void cpsw_ndo_set_rx_mode_work(struct work_struct *work) { - struct cpsw_priv *priv = netdev_priv(ndev); + struct cpsw_priv *priv = container_of(work, struct cpsw_priv, rx_mode_work); struct cpsw_common *cpsw = priv->cpsw; + struct net_device *ndev = priv->ndev; int slave_port = -1; + rtnl_lock(); + if (!netif_running(ndev)) + goto unlock_rtnl; + + netif_addr_lock_bh(ndev); + if (cpsw->data.dual_emac) slave_port = priv->emac_port + 1; @@ -318,7 +325,7 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) /* Enable promiscuous mode */ cpsw_set_promiscious(ndev, true); cpsw_ale_set_allmulti(cpsw->ale, IFF_ALLMULTI, slave_port); - return; + goto unlock_addr; } else { /* Disable promiscuous mode */ cpsw_set_promiscious(ndev, false); @@ -331,6 +338,18 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) /* add/remove mcast address either for real netdev or for vlan */ __hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr, cpsw_del_mc_addr); + +unlock_addr: + netif_addr_unlock_bh(ndev); +unlock_rtnl: + rtnl_unlock(); +} + +static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + + schedule_work(&priv->rx_mode_work); } static unsigned int cpsw_rxbuf_total_len(unsigned int len) @@ -1472,6 +1491,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv) priv_sl2->ndev = ndev; priv_sl2->dev = &ndev->dev; priv_sl2->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); + INIT_WORK(&priv_sl2->rx_mode_work, cpsw_ndo_set_rx_mode_work); if (is_valid_ether_addr(data->slave_data[1].mac_addr)) { memcpy(priv_sl2->mac_addr, data->slave_data[1].mac_addr, @@ -1653,6 +1673,7 @@ static int cpsw_probe(struct platform_device *pdev) priv->dev = dev; priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); priv->emac_port = 0; + INIT_WORK(&priv->rx_mode_work, cpsw_ndo_set_rx_mode_work); if (is_valid_ether_addr(data->slave_data[0].mac_addr)) { memcpy(priv->mac_addr, data->slave_data[0].mac_addr, ETH_ALEN); @@ -1758,6 +1779,8 @@ clean_runtime_disable_ret: static void cpsw_remove(struct platform_device *pdev) { struct cpsw_common *cpsw = platform_get_drvdata(pdev); + struct net_device *ndev; + struct cpsw_priv *priv; int i, ret; ret = pm_runtime_resume_and_get(&pdev->dev); @@ -1770,9 +1793,15 @@ static void cpsw_remove(struct platform_device *pdev) return; } - for (i = 0; i < cpsw->data.slaves; i++) - if (cpsw->slaves[i].ndev) - unregister_netdev(cpsw->slaves[i].ndev); + for (i = 0; i < cpsw->data.slaves; i++) { + ndev = cpsw->slaves[i].ndev; + if (!ndev) + continue; + + priv = netdev_priv(ndev); + unregister_netdev(ndev); + disable_work_sync(&priv->rx_mode_work); + } cpts_release(cpsw->cpts); cpdma_ctlr_destroy(cpsw->dma); diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index ab88d4c02cbde7..21af0a10626aaf 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -248,16 +248,22 @@ static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num) return 0; } -static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +static void cpsw_ndo_set_rx_mode_work(struct work_struct *work) { - struct cpsw_priv *priv = netdev_priv(ndev); + struct cpsw_priv *priv = container_of(work, struct cpsw_priv, rx_mode_work); struct cpsw_common *cpsw = priv->cpsw; + struct net_device *ndev = priv->ndev; + rtnl_lock(); + if (!netif_running(ndev)) + goto unlock_rtnl; + + netif_addr_lock_bh(ndev); if (ndev->flags & IFF_PROMISC) { /* Enable promiscuous mode */ cpsw_set_promiscious(ndev, true); cpsw_ale_set_allmulti(cpsw->ale, IFF_ALLMULTI, priv->emac_port); - return; + goto unlock_addr; } /* Disable promiscuous mode */ @@ -270,6 +276,18 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) /* add/remove mcast address either for real netdev or for vlan */ __hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr, cpsw_del_mc_addr); + +unlock_addr: + netif_addr_unlock_bh(ndev); +unlock_rtnl: + rtnl_unlock(); +} + +static void cpsw_ndo_set_rx_mode(struct net_device *ndev) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + + schedule_work(&priv->rx_mode_work); } static unsigned int cpsw_rxbuf_total_len(unsigned int len) @@ -1398,6 +1416,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) priv->msg_enable = netif_msg_init(debug_level, CPSW_DEBUG); priv->emac_port = i + 1; priv->tx_packet_min = CPSW_MIN_PACKET_SIZE; + INIT_WORK(&priv->rx_mode_work, cpsw_ndo_set_rx_mode_work); if (is_valid_ether_addr(slave_data->mac_addr)) { ether_addr_copy(priv->mac_addr, slave_data->mac_addr); @@ -1447,13 +1466,18 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) static void cpsw_unregister_ports(struct cpsw_common *cpsw) { + struct net_device *ndev; + struct cpsw_priv *priv; int i = 0; for (i = 0; i < cpsw->data.slaves; i++) { - if (!cpsw->slaves[i].ndev) + ndev = cpsw->slaves[i].ndev; + if (!ndev) continue; - unregister_netdev(cpsw->slaves[i].ndev); + priv = netdev_priv(ndev); + unregister_netdev(ndev); + disable_work_sync(&priv->rx_mode_work); } } diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index 91add8925e235c..acb6181c5c9e1b 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -391,6 +391,7 @@ struct cpsw_priv { u32 tx_packet_min; struct cpsw_ale_ratelimit ale_bc_ratelimit; struct cpsw_ale_ratelimit ale_mc_ratelimit; + struct work_struct rx_mode_work; }; #define ndev_to_cpsw(ndev) (((struct cpsw_priv *)netdev_priv(ndev))->cpsw) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index b4df7e184791d0..c509228be84d1b 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1567,9 +1567,10 @@ destroy_macvlan_port: /* the macvlan port may be freed by macvlan_uninit when fail to register. * so we destroy the macvlan port only when it's valid. */ - if (create && macvlan_port_get_rtnl(lowerdev)) { + if (macvlan_port_get_rtnl(lowerdev)) { macvlan_flush_sources(port, vlan); - macvlan_port_destroy(port->dev); + if (create) + macvlan_port_destroy(port->dev); } return err; } diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 47f095bd91ceab..3e023723887c4b 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -479,6 +479,8 @@ static void sfp_quirk_ubnt_uf_instant(const struct sfp_eeprom_id *id, linkmode_zero(caps->link_modes); linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, caps->link_modes); + phy_interface_zero(caps->interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, caps->interfaces); } #define SFP_QUIRK(_v, _p, _s, _f) \ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index fa519258386070..2f3baa5f6e9c94 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -8535,19 +8535,6 @@ static int rtl8152_system_resume(struct r8152 *tp) usb_submit_urb(tp->intr_urb, GFP_NOIO); } - /* If the device is RTL8152_INACCESSIBLE here then we should do a - * reset. This is important because the usb_lock_device_for_reset() - * that happens as a result of usb_queue_reset_device() will silently - * fail if the device was suspended or if too much time passed. - * - * NOTE: The device is locked here so we can directly do the reset. - * We don't need usb_lock_device_for_reset() because that's just a - * wrapper over device_lock() and device_resume() (which calls us) - * does that for us. - */ - if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) - usb_reset_device(tp->udev); - return 0; } @@ -8658,19 +8645,33 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) static int rtl8152_resume(struct usb_interface *intf) { struct r8152 *tp = usb_get_intfdata(intf); + bool runtime_resume = test_bit(SELECTIVE_SUSPEND, &tp->flags); int ret; mutex_lock(&tp->control); rtl_reset_ocp_base(tp); - if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) + if (runtime_resume) ret = rtl8152_runtime_resume(tp); else ret = rtl8152_system_resume(tp); mutex_unlock(&tp->control); + /* If the device is RTL8152_INACCESSIBLE here then we should do a + * reset. This is important because the usb_lock_device_for_reset() + * that happens as a result of usb_queue_reset_device() will silently + * fail if the device was suspended or if too much time passed. + * + * NOTE: The device is locked here so we can directly do the reset. + * We don't need usb_lock_device_for_reset() because that's just a + * wrapper over device_lock() and device_resume() (which calls us) + * does that for us. + */ + if (!runtime_resume && test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + usb_reset_device(tp->udev); + return ret; } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.c b/drivers/net/wireless/intel/iwlwifi/mld/iface.c index a5ececfc13e449..f15d1f5d1bf593 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/iface.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.c @@ -55,8 +55,6 @@ void iwl_mld_cleanup_vif(void *data, u8 *mac, struct ieee80211_vif *vif) ieee80211_iter_keys(mld->hw, vif, iwl_mld_cleanup_keys_iter, NULL); - wiphy_delayed_work_cancel(mld->wiphy, &mld_vif->mlo_scan_start_wk); - CLEANUP_STRUCT(mld_vif); } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c index 55b484c162807f..cd0dce8de85690 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c @@ -1759,6 +1759,8 @@ static int iwl_mld_move_sta_state_down(struct iwl_mld *mld, wiphy_work_cancel(mld->wiphy, &mld_vif->emlsr.unblock_tpt_wk); wiphy_delayed_work_cancel(mld->wiphy, &mld_vif->emlsr.check_tpt_wk); + wiphy_delayed_work_cancel(mld->wiphy, + &mld_vif->mlo_scan_start_wk); iwl_mld_reset_cca_40mhz_workaround(mld, vif); iwl_mld_smps_workaround(mld, vif, true); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 07f1a84c274efe..af1a45845999bb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2026 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -3239,6 +3239,8 @@ void iwl_mvm_fast_suspend(struct iwl_mvm *mvm) IWL_DEBUG_WOWLAN(mvm, "Starting fast suspend flow\n"); + iwl_mvm_pause_tcm(mvm, true); + mvm->fast_resume = true; set_bit(IWL_MVM_STATUS_IN_D3, &mvm->status); @@ -3295,6 +3297,8 @@ int iwl_mvm_fast_resume(struct iwl_mvm *mvm) mvm->trans->state = IWL_TRANS_NO_FW; } + iwl_mvm_resume_tcm(mvm); + out: clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status); mvm->fast_resume = false; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 86737076101d4a..112e48970338fa 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4301,6 +4301,18 @@ skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) skb_headlen(skb), buffer); } +/* Variant of skb_header_pointer() where @offset is user-controlled + * and potentially negative. + */ +static inline void * __must_check +skb_header_pointer_careful(const struct sk_buff *skb, int offset, + int len, void *buffer) +{ + if (unlikely(offset < 0 && -offset > skb_headroom(skb))) + return NULL; + return skb_header_pointer(skb, offset, len, buffer); +} + static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { diff --git a/net/core/filter.c b/net/core/filter.c index bcd73d9bd76491..029e560e32ce3e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2289,12 +2289,12 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); out_xmit: return ret; @@ -2396,12 +2396,12 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - DEV_STATS_INC(dev, tx_errors); + dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); out_xmit: return ret; diff --git a/net/core/gro.c b/net/core/gro.c index 76f9c371242210..482fa7d7f5981a 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -265,6 +265,8 @@ static void gro_complete(struct gro_node *gro, struct sk_buff *skb) goto out; } + /* NICs can feed encapsulated packets into GRO */ + skb->encapsulation = 0; rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { if (ptype->type != type || !ptype->callbacks.gro_complete) diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 212cde35affa7b..25c455c10a01cf 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -185,10 +185,6 @@ static void linkwatch_do_dev(struct net_device *dev) netif_state_change(dev); } - /* Note: our callers are responsible for calling netdev_tracker_free(). - * This is the reason we use __dev_put() instead of dev_put(). - */ - __dev_put(dev); } static void __linkwatch_run_queue(int urgent_only) @@ -243,6 +239,11 @@ static void __linkwatch_run_queue(int urgent_only) netdev_lock_ops(dev); linkwatch_do_dev(dev); netdev_unlock_ops(dev); + /* Use __dev_put() because netdev_tracker_free() was already + * called above. Must be after netdev_unlock_ops() to prevent + * netdev_run_todo() from freeing the device while still in use. + */ + __dev_put(dev); do_dev--; spin_lock_irq(&lweventlist_lock); } @@ -278,8 +279,13 @@ void __linkwatch_sync_dev(struct net_device *dev) { netdev_ops_assert_locked(dev); - if (linkwatch_clean_dev(dev)) + if (linkwatch_clean_dev(dev)) { linkwatch_do_dev(dev); + /* Use __dev_put() because netdev_tracker_free() was already + * called inside linkwatch_clean_dev(). + */ + __dev_put(dev); + } } void linkwatch_sync_dev(struct net_device *dev) @@ -288,6 +294,10 @@ void linkwatch_sync_dev(struct net_device *dev) netdev_lock_ops(dev); linkwatch_do_dev(dev); netdev_unlock_ops(dev); + /* Use __dev_put() because netdev_tracker_free() was already + * called inside linkwatch_clean_dev(). + */ + __dev_put(dev); } } diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 70e0e9a3b650c0..7dbfa6109f0b87 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -170,8 +170,14 @@ static const struct seq_operations softnet_seq_ops = { .show = softnet_seq_show, }; +struct ptype_iter_state { + struct seq_net_private p; + struct net_device *dev; +}; + static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { + struct ptype_iter_state *iter = seq->private; struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; struct net_device *dev; @@ -181,12 +187,16 @@ static void *ptype_get_idx(struct seq_file *seq, loff_t pos) for_each_netdev_rcu(seq_file_net(seq), dev) { ptype_list = &dev->ptype_all; list_for_each_entry_rcu(pt, ptype_list, list) { - if (i == pos) + if (i == pos) { + iter->dev = dev; return pt; + } ++i; } } + iter->dev = NULL; + list_for_each_entry_rcu(pt, &seq_file_net(seq)->ptype_all, list) { if (i == pos) return pt; @@ -218,6 +228,7 @@ static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + struct ptype_iter_state *iter = seq->private; struct net *net = seq_file_net(seq); struct net_device *dev; struct packet_type *pt; @@ -229,19 +240,21 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) return ptype_get_idx(seq, 0); pt = v; - nxt = pt->list.next; - if (pt->dev) { - if (nxt != &pt->dev->ptype_all) + nxt = READ_ONCE(pt->list.next); + dev = iter->dev; + if (dev) { + if (nxt != &dev->ptype_all) goto found; - dev = pt->dev; for_each_netdev_continue_rcu(seq_file_net(seq), dev) { - if (!list_empty(&dev->ptype_all)) { - nxt = dev->ptype_all.next; + nxt = READ_ONCE(dev->ptype_all.next); + if (nxt != &dev->ptype_all) { + iter->dev = dev; goto found; } } - nxt = net->ptype_all.next; + iter->dev = NULL; + nxt = READ_ONCE(net->ptype_all.next); goto net_ptype_all; } @@ -252,20 +265,20 @@ net_ptype_all: if (nxt == &net->ptype_all) { /* continue with ->ptype_specific if it's not empty */ - nxt = net->ptype_specific.next; + nxt = READ_ONCE(net->ptype_specific.next); if (nxt != &net->ptype_specific) goto found; } hash = 0; - nxt = ptype_base[0].next; + nxt = READ_ONCE(ptype_base[0].next); } else hash = ntohs(pt->type) & PTYPE_HASH_MASK; while (nxt == &ptype_base[hash]) { if (++hash >= PTYPE_HASH_SIZE) return NULL; - nxt = ptype_base[hash].next; + nxt = READ_ONCE(ptype_base[hash].next); } found: return list_entry(nxt, struct packet_type, list); @@ -279,19 +292,24 @@ static void ptype_seq_stop(struct seq_file *seq, void *v) static int ptype_seq_show(struct seq_file *seq, void *v) { + struct ptype_iter_state *iter = seq->private; struct packet_type *pt = v; + struct net_device *dev; - if (v == SEQ_START_TOKEN) + if (v == SEQ_START_TOKEN) { seq_puts(seq, "Type Device Function\n"); - else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && - (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) { + return 0; + } + dev = iter->dev; + if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && + (!dev || net_eq(dev_net(dev), seq_file_net(seq)))) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else seq_printf(seq, "%04x", ntohs(pt->type)); seq_printf(seq, " %-8s %ps\n", - pt->dev ? pt->dev->name : "", pt->func); + dev ? dev->name : "", pt->func); } return 0; @@ -315,7 +333,7 @@ static int __net_init dev_proc_net_init(struct net *net) &softnet_seq_ops)) goto out_dev; if (!proc_create_net("ptype", 0444, net->proc_net, &ptype_seq_ops, - sizeof(struct seq_net_private))) + sizeof(struct ptype_iter_state))) goto out_softnet; if (wext_proc_init(net)) diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 369c05cf8163c1..d47a279eb8b999 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -862,9 +862,6 @@ ethtool_rxfh_ctx_alloc(const struct ethtool_ops *ops, ctx->key_off = key_off; ctx->priv_size = ops->rxfh_priv_size; - ctx->hfunc = ETH_RSS_HASH_NO_CHANGE; - ctx->input_xfrm = RXH_XFRM_NO_CHANGE; - return ctx; } diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 4dced53be4b3bb..da5934cceb0757 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -824,8 +824,8 @@ rss_set_ctx_update(struct ethtool_rxfh_context *ctx, struct nlattr **tb, static int ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) { - bool indir_reset = false, indir_mod, xfrm_sym = false; struct rss_req_info *request = RSS_REQINFO(req_info); + bool indir_reset = false, indir_mod, xfrm_sym; struct ethtool_rxfh_context *ctx = NULL; struct net_device *dev = req_info->dev; bool mod = false, fields_mod = false; @@ -860,12 +860,7 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) rxfh.input_xfrm = data.input_xfrm; ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod); - /* For drivers which don't support input_xfrm it will be set to 0xff - * in the RSS context info. In all other case input_xfrm != 0 means - * symmetric hashing is requested. - */ - if (!request->rss_context || ops->rxfh_per_ctx_key) - xfrm_sym = rxfh.input_xfrm || data.input_xfrm; + xfrm_sym = rxfh.input_xfrm || data.input_xfrm; if (rxfh.input_xfrm == data.input_xfrm) rxfh.input_xfrm = RXH_XFRM_NO_CHANGE; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 2111af022d946d..c6439e30e892af 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1138,7 +1138,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); } - if (!(rt->fib6_flags & (RTF_ADDRCONF | RTF_PREFIX_RT))) { + if (!(rt->fib6_flags & (RTF_ADDRCONF | RTF_PREFIX_RT)) && + !iter->fib6_nh->fib_nh_gw_family) { iter->fib6_flags &= ~RTF_ADDRCONF; iter->fib6_flags &= ~RTF_PREFIX_RT; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 729a92781a1a47..be92750e2af3ad 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5914,7 +5914,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask)) + if (nft_set_elem_active(ext, genmask)) continue; nft_clear(ctx->net, ext); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 2a1c00048fd6f4..58e849c0acf412 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -161,10 +161,8 @@ next_knode: int toff = off + key->off + (off2 & key->offmask); __be32 *data, hdata; - if (skb_headroom(skb) + toff > INT_MAX) - goto out; - - data = skb_header_pointer(skb, toff, 4, &hdata); + data = skb_header_pointer_careful(skb, toff, 4, + &hdata); if (!data) goto out; if ((*data ^ key->val) & key->mask) { @@ -214,8 +212,9 @@ check_terminal: if (ht->divisor) { __be32 *data, hdata; - data = skb_header_pointer(skb, off + n->sel.hoff, 4, - &hdata); + data = skb_header_pointer_careful(skb, + off + n->sel.hoff, + 4, &hdata); if (!data) goto out; sel = ht->divisor & u32_hash_fold(*data, &n->sel, @@ -229,7 +228,7 @@ check_terminal: if (n->sel.flags & TC_U32_VAROFFSET) { __be16 *data, hdata; - data = skb_header_pointer(skb, + data = skb_header_pointer_careful(skb, off + n->sel.offoff, 2, &hdata); if (!data) diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 751904f10aab00..970db62bd029b2 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1219,7 +1219,7 @@ void tipc_crypto_key_flush(struct tipc_crypto *c) rx = c; tx = tipc_net(rx->net)->crypto_tx; if (cancel_delayed_work(&rx->work)) { - kfree(rx->skey); + kfree_sensitive(rx->skey); rx->skey = NULL; atomic_xchg(&rx->key_distr, 0); tipc_node_put(rx->node); @@ -2394,7 +2394,7 @@ static void tipc_crypto_work_rx(struct work_struct *work) break; default: synchronize_rcu(); - kfree(rx->skey); + kfree_sensitive(rx->skey); rx->skey = NULL; break; } diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh index a39fdc4aa2ffb3..9b722c1e4b0fe9 100755 --- a/tools/testing/selftests/net/udpgro_fwd.sh +++ b/tools/testing/selftests/net/udpgro_fwd.sh @@ -162,6 +162,39 @@ run_test() { echo " ok" } +run_test_csum() { + local -r msg="$1" + local -r dst="$2" + local csum_error_filter=UdpInCsumErrors + local csum_errors + + printf "%-40s" "$msg" + + is_ipv6 "$dst" && csum_error_filter=Udp6InCsumErrors + + ip netns exec "$NS_DST" iperf3 -s -1 >/dev/null & + wait_local_port_listen "$NS_DST" 5201 tcp + local spid="$!" + ip netns exec "$NS_SRC" iperf3 -c "$dst" -t 2 >/dev/null + local retc="$?" + wait "$spid" + local rets="$?" + if [ "$rets" -ne 0 ] || [ "$retc" -ne 0 ]; then + echo " fail client exit code $retc, server $rets" + ret=1 + return + fi + + csum_errors=$(ip netns exec "$NS_DST" nstat -as "$csum_error_filter" | + grep "$csum_error_filter" | awk '{print $2}') + if [ -n "$csum_errors" ] && [ "$csum_errors" -gt 0 ]; then + echo " fail - csum error on receive $csum_errors, expected 0" + ret=1 + return + fi + echo " ok" +} + run_bench() { local -r msg=$1 local -r dst=$2 @@ -260,6 +293,37 @@ for family in 4 6; do ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 10 10 $OL_NET$DST cleanup + + # force segmentation and re-aggregation + create_vxlan_pair + ip netns exec "$NS_DST" ethtool -K veth"$DST" generic-receive-offload on + ip netns exec "$NS_SRC" ethtool -K veth"$SRC" tso off + ip -n "$NS_SRC" link set dev veth"$SRC" mtu 1430 + + # forward to a 2nd veth pair + ip -n "$NS_DST" link add br0 type bridge + ip -n "$NS_DST" link set dev veth"$DST" master br0 + + # segment the aggregated TSO packet, without csum offload + ip -n "$NS_DST" link add veth_segment type veth peer veth_rx + for FEATURE in tso tx-udp-segmentation tx-checksumming; do + ip netns exec "$NS_DST" ethtool -K veth_segment "$FEATURE" off + done + ip -n "$NS_DST" link set dev veth_segment master br0 up + ip -n "$NS_DST" link set dev br0 up + ip -n "$NS_DST" link set dev veth_rx up + + # move the lower layer IP in the last added veth + for ADDR in "$BM_NET_V4$DST/24" "$BM_NET_V6$DST/64"; do + # the dad argument will let iproute emit a unharmful warning + # with ipv4 addresses + ip -n "$NS_DST" addr del dev veth"$DST" "$ADDR" + ip -n "$NS_DST" addr add dev veth_rx "$ADDR" \ + nodad 2>/dev/null + done + + run_test_csum "GSO after GRO" "$OL_NET$DST" + cleanup done exit $ret |
