diff options
45 files changed, 630 insertions, 144 deletions
@@ -691,9 +691,10 @@ Serge Hallyn <sergeh@kernel.org> <serge.hallyn@canonical.com> Serge Hallyn <sergeh@kernel.org> <serue@us.ibm.com> Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com> Shakeel Butt <shakeel.butt@linux.dev> <shakeelb@google.com> -Shannon Nelson <shannon.nelson@amd.com> <snelson@pensando.io> -Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@intel.com> -Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@oracle.com> +Shannon Nelson <sln@onemain.com> <shannon.nelson@amd.com> +Shannon Nelson <sln@onemain.com> <snelson@pensando.io> +Shannon Nelson <sln@onemain.com> <shannon.nelson@intel.com> +Shannon Nelson <sln@onemain.com> <shannon.nelson@oracle.com> Sharath Chandra Vurukala <quic_sharathv@quicinc.com> <sharathv@codeaurora.org> Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com> Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com> diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 9f98715a6512..72a076b0e1b5 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -7,6 +7,9 @@ protocol: genetlink-legacy doc: Partial family for Ethtool Netlink. uapi-header: linux/ethtool_netlink_generated.h +c-family-name: ethtool-genl-name +c-version-name: ethtool-genl-version + definitions: - name: udp-tunnel-type diff --git a/MAINTAINERS b/MAINTAINERS index 99fbde007792..437381aeaa71 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1157,7 +1157,6 @@ F: arch/x86/include/asm/amd/node.h F: arch/x86/kernel/amd_node.c AMD PDS CORE DRIVER -M: Shannon Nelson <shannon.nelson@amd.com> M: Brett Creeley <brett.creeley@amd.com> L: netdev@vger.kernel.org S: Maintained @@ -9941,7 +9940,6 @@ F: drivers/fwctl/mlx5/ FWCTL PDS DRIVER M: Brett Creeley <brett.creeley@amd.com> -R: Shannon Nelson <shannon.nelson@amd.com> L: linux-kernel@vger.kernel.org S: Maintained F: drivers/fwctl/pds/ @@ -19377,7 +19375,7 @@ F: crypto/pcrypt.c F: include/crypto/pcrypt.h PDS DSC VIRTIO DATA PATH ACCELERATOR -R: Shannon Nelson <shannon.nelson@amd.com> +R: Brett Creeley <brett.creeley@amd.com> F: drivers/vdpa/pds/ PECI HARDWARE MONITORING DRIVERS @@ -19399,7 +19397,6 @@ F: include/linux/peci-cpu.h F: include/linux/peci.h PENSANDO ETHERNET DRIVERS -M: Shannon Nelson <shannon.nelson@amd.com> M: Brett Creeley <brett.creeley@amd.com> L: netdev@vger.kernel.org S: Maintained diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c index d4aa0f353b6c..eeae160c898d 100644 --- a/drivers/atm/atmtcp.c +++ b/drivers/atm/atmtcp.c @@ -288,7 +288,9 @@ static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb) struct sk_buff *new_skb; int result = 0; - if (!skb->len) return 0; + if (skb->len < sizeof(struct atmtcp_hdr)) + goto done; + dev = vcc->dev_data; hdr = (struct atmtcp_hdr *) skb->data; if (hdr->length == ATMTCP_HDR_MAGIC) { diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c index e5c162f8c589..8edaa339d590 100644 --- a/drivers/net/can/m_can/tcan4x5x-core.c +++ b/drivers/net/can/m_can/tcan4x5x-core.c @@ -411,10 +411,11 @@ static int tcan4x5x_can_probe(struct spi_device *spi) priv = cdev_to_priv(mcan_class); priv->power = devm_regulator_get_optional(&spi->dev, "vsup"); - if (PTR_ERR(priv->power) == -EPROBE_DEFER) { - ret = -EPROBE_DEFER; - goto out_m_can_class_free_dev; - } else { + if (IS_ERR(priv->power)) { + if (PTR_ERR(priv->power) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto out_m_can_class_free_dev; + } priv->power = NULL; } diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 9067d2fc7706..0e217acfc5ef 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -809,8 +809,10 @@ airoha_ppe_foe_flow_l2_entry_update(struct airoha_ppe *ppe, int idle; hwe = airoha_ppe_foe_get_entry(ppe, iter->hash); - ib1 = READ_ONCE(hwe->ib1); + if (!hwe) + continue; + ib1 = READ_ONCE(hwe->ib1); state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, ib1); if (state != AIROHA_FOE_STATE_BIND) { iter->hash = 0xffff; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 869580b6f70d..2cb3185c442c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10780,6 +10780,72 @@ void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx, bp->num_rss_ctx--; } +static bool bnxt_vnic_has_rx_ring(struct bnxt *bp, struct bnxt_vnic_info *vnic, + int rxr_id) +{ + u16 tbl_size = bnxt_get_rxfh_indir_size(bp->dev); + int i, vnic_rx; + + /* Ntuple VNIC always has all the rx rings. Any change of ring id + * must be updated because a future filter may use it. + */ + if (vnic->flags & BNXT_VNIC_NTUPLE_FLAG) + return true; + + for (i = 0; i < tbl_size; i++) { + if (vnic->flags & BNXT_VNIC_RSSCTX_FLAG) + vnic_rx = ethtool_rxfh_context_indir(vnic->rss_ctx)[i]; + else + vnic_rx = bp->rss_indir_tbl[i]; + + if (rxr_id == vnic_rx) + return true; + } + + return false; +} + +static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic, + u16 mru, int rxr_id) +{ + int rc; + + if (!bnxt_vnic_has_rx_ring(bp, vnic, rxr_id)) + return 0; + + if (mru) { + rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true); + if (rc) { + netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n", + vnic->vnic_id, rc); + return rc; + } + } + vnic->mru = mru; + bnxt_hwrm_vnic_update(bp, vnic, + VNIC_UPDATE_REQ_ENABLES_MRU_VALID); + + return 0; +} + +static int bnxt_set_rss_ctx_vnic_mru(struct bnxt *bp, u16 mru, int rxr_id) +{ + struct ethtool_rxfh_context *ctx; + unsigned long context; + int rc; + + xa_for_each(&bp->dev->ethtool->rss_ctx, context, ctx) { + struct bnxt_rss_ctx *rss_ctx = ethtool_rxfh_context_priv(ctx); + struct bnxt_vnic_info *vnic = &rss_ctx->vnic; + + rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, rxr_id); + if (rc) + return rc; + } + + return 0; +} + static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp) { bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA); @@ -15927,6 +15993,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) struct bnxt_vnic_info *vnic; struct bnxt_napi *bnapi; int i, rc; + u16 mru; rxr = &bp->rx_ring[idx]; clone = qmem; @@ -15977,21 +16044,15 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) napi_enable_locked(&bnapi->napi); bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); + mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN; for (i = 0; i < bp->nr_vnics; i++) { vnic = &bp->vnic_info[i]; - rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true); - if (rc) { - netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n", - vnic->vnic_id, rc); + rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, idx); + if (rc) return rc; - } - vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN; - bnxt_hwrm_vnic_update(bp, vnic, - VNIC_UPDATE_REQ_ENABLES_MRU_VALID); } - - return 0; + return bnxt_set_rss_ctx_vnic_mru(bp, mru, idx); err_reset: netdev_err(bp->dev, "Unexpected HWRM error during queue start rc: %d\n", @@ -16013,10 +16074,10 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) for (i = 0; i < bp->nr_vnics; i++) { vnic = &bp->vnic_info[i]; - vnic->mru = 0; - bnxt_hwrm_vnic_update(bp, vnic, - VNIC_UPDATE_REQ_ENABLES_MRU_VALID); + + bnxt_set_vnic_mru_p5(bp, vnic, 0, idx); } + bnxt_set_rss_ctx_vnic_mru(bp, 0, idx); /* Make sure NAPI sees that the VNIC is disabled */ synchronize_net(); rxr = &bp->rx_ring[idx]; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 84c4812414fd..2450a369b792 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -231,10 +231,9 @@ void bnxt_ulp_stop(struct bnxt *bp) return; mutex_lock(&edev->en_dev_lock); - if (!bnxt_ulp_registered(edev)) { - mutex_unlock(&edev->en_dev_lock); - return; - } + if (!bnxt_ulp_registered(edev) || + (edev->flags & BNXT_EN_FLAG_ULP_STOPPED)) + goto ulp_stop_exit; edev->flags |= BNXT_EN_FLAG_ULP_STOPPED; if (aux_priv) { @@ -250,6 +249,7 @@ void bnxt_ulp_stop(struct bnxt *bp) adrv->suspend(adev, pm); } } +ulp_stop_exit: mutex_unlock(&edev->en_dev_lock); } @@ -258,19 +258,13 @@ void bnxt_ulp_start(struct bnxt *bp, int err) struct bnxt_aux_priv *aux_priv = bp->aux_priv; struct bnxt_en_dev *edev = bp->edev; - if (!edev) - return; - - edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED; - - if (err) + if (!edev || err) return; mutex_lock(&edev->en_dev_lock); - if (!bnxt_ulp_registered(edev)) { - mutex_unlock(&edev->en_dev_lock); - return; - } + if (!bnxt_ulp_registered(edev) || + !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED)) + goto ulp_start_exit; if (edev->ulp_tbl->msix_requested) bnxt_fill_msix_vecs(bp, edev->msix_entries); @@ -287,6 +281,8 @@ void bnxt_ulp_start(struct bnxt *bp, int err) adrv->resume(adev); } } +ulp_start_exit: + edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED; mutex_unlock(&edev->en_dev_lock); } diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig index c699bd6bcbb9..474073c7f94d 100644 --- a/drivers/net/ethernet/faraday/Kconfig +++ b/drivers/net/ethernet/faraday/Kconfig @@ -31,6 +31,7 @@ config FTGMAC100 depends on ARM || COMPILE_TEST depends on !64BIT || BROKEN select PHYLIB + select FIXED_PHY select MDIO_ASPEED if MACH_ASPEED_G6 select CRC32 help diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index a96f4cfa6e17..7719e15813ee 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3534,9 +3534,6 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) case e1000_pch_cnp: case e1000_pch_tgp: case e1000_pch_adp: - case e1000_pch_mtp: - case e1000_pch_lnp: - case e1000_pch_ptp: case e1000_pch_nvp: if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { /* Stable 24MHz frequency */ @@ -3552,6 +3549,17 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) adapter->cc.shift = shift; } break; + case e1000_pch_mtp: + case e1000_pch_lnp: + case e1000_pch_ptp: + /* System firmware can misreport this value, so set it to a + * stable 38400KHz frequency. + */ + incperiod = INCPERIOD_38400KHZ; + incvalue = INCVALUE_38400KHZ; + shift = INCVALUE_SHIFT_38400KHZ; + adapter->cc.shift = shift; + break; case e1000_82574: case e1000_82583: /* Stable 25MHz frequency */ diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 89d57dd911dc..ea3c3eb2ef20 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -295,15 +295,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) case e1000_pch_cnp: case e1000_pch_tgp: case e1000_pch_adp: - case e1000_pch_mtp: - case e1000_pch_lnp: - case e1000_pch_ptp: case e1000_pch_nvp: if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ; else adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ; break; + case e1000_pch_mtp: + case e1000_pch_lnp: + case e1000_pch_ptp: + adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ; + break; case e1000_82574: case e1000_82583: adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ; diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 2bc5c7f59844..1f7834c03550 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -378,6 +378,50 @@ ice_arfs_is_perfect_flow_set(struct ice_hw *hw, __be16 l3_proto, u8 l4_proto) } /** + * ice_arfs_cmp - Check if aRFS filter matches this flow. + * @fltr_info: filter info of the saved ARFS entry. + * @fk: flow dissector keys. + * @n_proto: One of htons(ETH_P_IP) or htons(ETH_P_IPV6). + * @ip_proto: One of IPPROTO_TCP or IPPROTO_UDP. + * + * Since this function assumes limited values for n_proto and ip_proto, it + * is meant to be called only from ice_rx_flow_steer(). + * + * Return: + * * true - fltr_info refers to the same flow as fk. + * * false - fltr_info and fk refer to different flows. + */ +static bool +ice_arfs_cmp(const struct ice_fdir_fltr *fltr_info, const struct flow_keys *fk, + __be16 n_proto, u8 ip_proto) +{ + /* Determine if the filter is for IPv4 or IPv6 based on flow_type, + * which is one of ICE_FLTR_PTYPE_NONF_IPV{4,6}_{TCP,UDP}. + */ + bool is_v4 = fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP || + fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP; + + /* Following checks are arranged in the quickest and most discriminative + * fields first for early failure. + */ + if (is_v4) + return n_proto == htons(ETH_P_IP) && + fltr_info->ip.v4.src_port == fk->ports.src && + fltr_info->ip.v4.dst_port == fk->ports.dst && + fltr_info->ip.v4.src_ip == fk->addrs.v4addrs.src && + fltr_info->ip.v4.dst_ip == fk->addrs.v4addrs.dst && + fltr_info->ip.v4.proto == ip_proto; + + return fltr_info->ip.v6.src_port == fk->ports.src && + fltr_info->ip.v6.dst_port == fk->ports.dst && + fltr_info->ip.v6.proto == ip_proto && + !memcmp(&fltr_info->ip.v6.src_ip, &fk->addrs.v6addrs.src, + sizeof(struct in6_addr)) && + !memcmp(&fltr_info->ip.v6.dst_ip, &fk->addrs.v6addrs.dst, + sizeof(struct in6_addr)); +} + +/** * ice_rx_flow_steer - steer the Rx flow to where application is being run * @netdev: ptr to the netdev being adjusted * @skb: buffer with required header information @@ -448,6 +492,10 @@ ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb, continue; fltr_info = &arfs_entry->fltr_info; + + if (!ice_arfs_cmp(fltr_info, &fk, n_proto, ip_proto)) + continue; + ret = fltr_info->fltr_id; if (fltr_info->q_index == rxq_idx || diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 6aae03771746..2e4f0969035f 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -508,10 +508,14 @@ err_create_repr: */ int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf) { - struct ice_repr *repr = ice_repr_create_vf(vf); struct devlink *devlink = priv_to_devlink(pf); + struct ice_repr *repr; int err; + if (!ice_is_eswitch_mode_switchdev(pf)) + return 0; + + repr = ice_repr_create_vf(vf); if (IS_ERR(repr)) return PTR_ERR(repr); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 6f572589f1e5..6b5c9536d26d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1822,7 +1822,7 @@ int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable) req->chan_cnt = IEEE_8021QAZ_MAX_TCS; req->bpid_per_chan = 1; } else { - req->chan_cnt = 1; + req->chan_cnt = pfvf->hw.rx_chan_cnt; req->bpid_per_chan = 0; } @@ -1847,7 +1847,7 @@ int otx2_nix_cpt_config_bp(struct otx2_nic *pfvf, bool enable) req->chan_cnt = IEEE_8021QAZ_MAX_TCS; req->bpid_per_chan = 1; } else { - req->chan_cnt = 1; + req->chan_cnt = pfvf->hw.rx_chan_cnt; req->bpid_per_chan = 0; } diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index fb2e5b844c15..d76d7a945899 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -447,8 +447,10 @@ static int mlxbf_gige_probe(struct platform_device *pdev) priv->llu_plu_irq = platform_get_irq(pdev, MLXBF_GIGE_LLU_PLU_INTR_IDX); phy_irq = acpi_dev_gpio_irq_get_by(ACPI_COMPANION(&pdev->dev), "phy", 0); - if (phy_irq < 0) { - dev_err(&pdev->dev, "Error getting PHY irq. Use polling instead"); + if (phy_irq == -EPROBE_DEFER) { + err = -EPROBE_DEFER; + goto out; + } else if (phy_irq < 0) { phy_irq = PHY_POLL; } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c index e2368075ab8c..4521d0483d18 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c @@ -127,11 +127,8 @@ static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx, return -EBUSY; addr = dma_map_single(fbd->dev, msg, PAGE_SIZE, direction); - if (dma_mapping_error(fbd->dev, addr)) { - free_page((unsigned long)msg); - + if (dma_mapping_error(fbd->dev, addr)) return -ENOSPC; - } mbx->buf_info[tail].msg = msg; mbx->buf_info[tail].addr = addr; diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.h b/drivers/net/ethernet/microchip/lan743x_ptp.h index e8d073bfa2ca..f33dc83c5700 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.h +++ b/drivers/net/ethernet/microchip/lan743x_ptp.h @@ -18,9 +18,9 @@ */ #define LAN743X_PTP_N_EVENT_CHAN 2 #define LAN743X_PTP_N_PEROUT LAN743X_PTP_N_EVENT_CHAN -#define LAN743X_PTP_N_EXTTS 4 -#define LAN743X_PTP_N_PPS 0 #define PCI11X1X_PTP_IO_MAX_CHANNELS 8 +#define LAN743X_PTP_N_EXTTS PCI11X1X_PTP_IO_MAX_CHANNELS +#define LAN743X_PTP_N_PPS 0 #define PTP_CMD_CTL_TIMEOUT_CNT 50 struct lan743x_adapter; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index daf1e82cb76b..0e60a6bef99a 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -516,9 +516,9 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds, unsigned long start_time; unsigned long max_wait; unsigned long duration; - int done = 0; bool fw_up; int opcode; + bool done; int err; /* Wait for dev cmd to complete, retrying if we get EAGAIN, @@ -526,6 +526,7 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds, */ max_wait = jiffies + (max_seconds * HZ); try_again: + done = false; opcode = idev->opcode; start_time = jiffies; for (fw_up = ionic_is_fw_running(idev); diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index 5b8fdb882172..12f25cec6255 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -98,20 +98,11 @@ void prueth_xmit_free(struct prueth_tx_chn *tx_chn, { struct cppi5_host_desc_t *first_desc, *next_desc; dma_addr_t buf_dma, next_desc_dma; - struct prueth_swdata *swdata; - struct page *page; u32 buf_dma_len; first_desc = desc; next_desc = first_desc; - swdata = cppi5_hdesc_get_swdata(desc); - if (swdata->type == PRUETH_SWDATA_PAGE) { - page = swdata->data.page; - page_pool_recycle_direct(page->pp, swdata->data.page); - goto free_desc; - } - cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len); k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma); @@ -135,7 +126,6 @@ void prueth_xmit_free(struct prueth_tx_chn *tx_chn, k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc); } -free_desc: k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc); } EXPORT_SYMBOL_GPL(prueth_xmit_free); @@ -612,13 +602,8 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac, k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma); cppi5_hdesc_attach_buf(first_desc, buf_dma, xdpf->len, buf_dma, xdpf->len); swdata = cppi5_hdesc_get_swdata(first_desc); - if (page) { - swdata->type = PRUETH_SWDATA_PAGE; - swdata->data.page = page; - } else { - swdata->type = PRUETH_SWDATA_XDPF; - swdata->data.xdpf = xdpf; - } + swdata->type = PRUETH_SWDATA_XDPF; + swdata->data.xdpf = xdpf; /* Report BQL before sending the packet */ netif_txq = netdev_get_tx_queue(ndev, tx_chn->id); diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 35a5994bf64f..36f57d7b4a66 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -121,7 +121,8 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx) struct ptp_clock_info *ops; int err = -EOPNOTSUPP; - if (ptp_clock_freerun(ptp)) { + if (tx->modes & (ADJ_SETOFFSET | ADJ_FREQUENCY | ADJ_OFFSET) && + ptp_clock_freerun(ptp)) { pr_err("ptp: physical clock is free running\n"); return -EBUSY; } diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 528d86a33f37..a6aad743c282 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -98,7 +98,27 @@ static inline int queue_cnt(const struct timestamp_event_queue *q) /* Check if ptp virtual clock is in use */ static inline bool ptp_vclock_in_use(struct ptp_clock *ptp) { - return !ptp->is_virtual_clock; + bool in_use = false; + + /* Virtual clocks can't be stacked on top of virtual clocks. + * Avoid acquiring the n_vclocks_mux on virtual clocks, to allow this + * function to be called from code paths where the n_vclocks_mux of the + * parent physical clock is already held. Functionally that's not an + * issue, but lockdep would complain, because they have the same lock + * class. + */ + if (ptp->is_virtual_clock) + return false; + + if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) + return true; + + if (ptp->n_vclocks) + in_use = true; + + mutex_unlock(&ptp->n_vclocks_mux); + + return in_use; } /* Check if ptp clock shall be free running */ diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h index 9b02961d65ee..45f2f278b50a 100644 --- a/include/linux/atmdev.h +++ b/include/linux/atmdev.h @@ -249,6 +249,12 @@ static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb) ATM_SKB(skb)->atm_options = vcc->atm_options; } +static inline void atm_return_tx(struct atm_vcc *vcc, struct sk_buff *skb) +{ + WARN_ON_ONCE(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, + &sk_atm(vcc)->sk_wmem_alloc)); +} + static inline void atm_force_charge(struct atm_vcc *vcc,int truesize) { atomic_add(truesize, &sk_atm(vcc)->sk_rmem_alloc); diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 9ff72cfb2e98..09a75bdb6560 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -208,10 +208,6 @@ enum { ETHTOOL_A_STATS_PHY_MAX = (__ETHTOOL_A_STATS_PHY_CNT - 1) }; -/* generic netlink info */ -#define ETHTOOL_GENL_NAME "ethtool" -#define ETHTOOL_GENL_VERSION 1 - #define ETHTOOL_MCGRP_MONITOR_NAME "monitor" #endif /* _UAPI_LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index 9a02f579de22..aa8ab5227c1e 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -6,8 +6,8 @@ #ifndef _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H #define _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H -#define ETHTOOL_FAMILY_NAME "ethtool" -#define ETHTOOL_FAMILY_VERSION 1 +#define ETHTOOL_GENL_NAME "ethtool" +#define ETHTOOL_GENL_VERSION 1 enum { ETHTOOL_UDP_TUNNEL_TYPE_VXLAN, diff --git a/lib/Kconfig b/lib/Kconfig index 6c1b8f184267..37db228f70a9 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -716,6 +716,7 @@ config GENERIC_LIB_DEVMEM_IS_ALLOWED config PLDMFW bool + select CRC32 default n config ASN1_ENCODER diff --git a/net/atm/common.c b/net/atm/common.c index 9b75699992ff..d7f7976ea13a 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -635,6 +635,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) skb->dev = NULL; /* for paths shared with net_device interfaces */ if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) { + atm_return_tx(vcc, skb); kfree_skb(skb); error = -EFAULT; goto out; diff --git a/net/atm/lec.c b/net/atm/lec.c index acef984f3367..afb8d3eb2185 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -124,6 +124,7 @@ static unsigned char bus_mac[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; /* Device structures */ static struct net_device *dev_lec[MAX_LEC_ITF]; +static DEFINE_MUTEX(lec_mutex); #if IS_ENABLED(CONFIG_BRIDGE) static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) @@ -685,6 +686,7 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) int bytes_left; struct atmlec_ioc ioc_data; + lockdep_assert_held(&lec_mutex); /* Lecd must be up in this case */ bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc)); if (bytes_left != 0) @@ -710,6 +712,7 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) static int lec_mcast_attach(struct atm_vcc *vcc, int arg) { + lockdep_assert_held(&lec_mutex); if (arg < 0 || arg >= MAX_LEC_ITF) return -EINVAL; arg = array_index_nospec(arg, MAX_LEC_ITF); @@ -725,6 +728,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) int i; struct lec_priv *priv; + lockdep_assert_held(&lec_mutex); if (arg < 0) arg = 0; if (arg >= MAX_LEC_ITF) @@ -742,6 +746,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) snprintf(dev_lec[i]->name, IFNAMSIZ, "lec%d", i); if (register_netdev(dev_lec[i])) { free_netdev(dev_lec[i]); + dev_lec[i] = NULL; return -EINVAL; } @@ -904,7 +909,6 @@ static void *lec_itf_walk(struct lec_state *state, loff_t *l) v = (dev && netdev_priv(dev)) ? lec_priv_walk(state, l, netdev_priv(dev)) : NULL; if (!v && dev) { - dev_put(dev); /* Partial state reset for the next time we get called */ dev = NULL; } @@ -928,6 +932,7 @@ static void *lec_seq_start(struct seq_file *seq, loff_t *pos) { struct lec_state *state = seq->private; + mutex_lock(&lec_mutex); state->itf = 0; state->dev = NULL; state->locked = NULL; @@ -945,8 +950,9 @@ static void lec_seq_stop(struct seq_file *seq, void *v) if (state->dev) { spin_unlock_irqrestore(&state->locked->lec_arp_lock, state->flags); - dev_put(state->dev); + state->dev = NULL; } + mutex_unlock(&lec_mutex); } static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos) @@ -1003,6 +1009,7 @@ static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return -ENOIOCTLCMD; } + mutex_lock(&lec_mutex); switch (cmd) { case ATMLEC_CTRL: err = lecd_attach(vcc, (int)arg); @@ -1017,6 +1024,7 @@ static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } + mutex_unlock(&lec_mutex); return err; } diff --git a/net/atm/raw.c b/net/atm/raw.c index 2b5f78a7ec3e..1e6511ec842c 100644 --- a/net/atm/raw.c +++ b/net/atm/raw.c @@ -36,7 +36,7 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb) pr_debug("(%d) %d -= %d\n", vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize); - WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc)); + atm_return_tx(vcc, skb); dev_kfree_skb_any(skb); sk->sk_write_space(sk); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 85fc82f72d26..d6420b74ea9c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6261,9 +6261,6 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) if (!pskb_may_pull(skb, write_len)) return -ENOMEM; - if (!skb_frags_readable(skb)) - return -EFAULT; - if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 9b83d639b5ac..5107121c5e37 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -3,6 +3,7 @@ #include <linux/tcp.h> #include <linux/rcupdate.h> #include <net/tcp.h> +#include <net/busy_poll.h> void tcp_fastopen_init_key_once(struct net *net) { @@ -279,6 +280,8 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, refcount_set(&req->rsk_refcnt, 2); + sk_mark_napi_id_set(child, skb); + /* Now finish processing the fastopen child socket. */ tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8ec92dec321a..12c2e6fc85c6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2479,20 +2479,33 @@ static inline bool tcp_packet_delayed(const struct tcp_sock *tp) { const struct sock *sk = (const struct sock *)tp; - if (tp->retrans_stamp && - tcp_tsopt_ecr_before(tp, tp->retrans_stamp)) - return true; /* got echoed TS before first retransmission */ - - /* Check if nothing was retransmitted (retrans_stamp==0), which may - * happen in fast recovery due to TSQ. But we ignore zero retrans_stamp - * in TCP_SYN_SENT, since when we set FLAG_SYN_ACKED we also clear - * retrans_stamp even if we had retransmitted the SYN. + /* Received an echoed timestamp before the first retransmission? */ + if (tp->retrans_stamp) + return tcp_tsopt_ecr_before(tp, tp->retrans_stamp); + + /* We set tp->retrans_stamp upon the first retransmission of a loss + * recovery episode, so normally if tp->retrans_stamp is 0 then no + * retransmission has happened yet (likely due to TSQ, which can cause + * fast retransmits to be delayed). So if snd_una advanced while + * (tp->retrans_stamp is 0 then apparently a packet was merely delayed, + * not lost. But there are exceptions where we retransmit but then + * clear tp->retrans_stamp, so we check for those exceptions. */ - if (!tp->retrans_stamp && /* no record of a retransmit/SYN? */ - sk->sk_state != TCP_SYN_SENT) /* not the FLAG_SYN_ACKED case? */ - return true; /* nothing was retransmitted */ - return false; + /* (1) For non-SACK connections, tcp_is_non_sack_preventing_reopen() + * clears tp->retrans_stamp when snd_una == high_seq. + */ + if (!tcp_is_sack(tp) && !before(tp->snd_una, tp->high_seq)) + return false; + + /* (2) In TCP_SYN_SENT tcp_clean_rtx_queue() clears tp->retrans_stamp + * when setting FLAG_SYN_ACKED is set, even if the SYN was + * retransmitted. + */ + if (sk->sk_state == TCP_SYN_SENT) + return false; + + return true; /* tp->retrans_stamp is zero; no retransmit yet */ } /* Undo procedures. */ diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 62618a058b8f..a247bb93908b 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1207,6 +1207,10 @@ static int calipso_req_setattr(struct request_sock *req, struct ipv6_opt_hdr *old, *new; struct sock *sk = sk_to_full_sk(req_to_sk(req)); + /* sk is NULL for SYN+ACK w/ SYN Cookie */ + if (!sk) + return -ENOMEM; + if (req_inet->ipv6_opt && req_inet->ipv6_opt->hopopt) old = req_inet->ipv6_opt->hopopt; else @@ -1247,6 +1251,10 @@ static void calipso_req_delattr(struct request_sock *req) struct ipv6_txoptions *txopts; struct sock *sk = sk_to_full_sk(req_to_sk(req)); + /* sk is NULL for SYN+ACK w/ SYN Cookie */ + if (!sk) + return; + if (!req_inet->ipv6_opt || !req_inet->ipv6_opt->hopopt) return; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index d536c97144e9..47d7dfd9ad09 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -81,8 +81,8 @@ static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index) if (index < net->mpls.platform_labels) { struct mpls_route __rcu **platform_label = - rcu_dereference(net->mpls.platform_label); - rt = rcu_dereference(platform_label[index]); + rcu_dereference_rtnl(net->mpls.platform_label); + rt = rcu_dereference_rtnl(platform_label[index]); } return rt; } diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index ed1508a9e093..aab107727f18 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -119,22 +119,22 @@ static int nci_uart_set_driver(struct tty_struct *tty, unsigned int driver) memcpy(nu, nci_uart_drivers[driver], sizeof(struct nci_uart)); nu->tty = tty; - tty->disc_data = nu; skb_queue_head_init(&nu->tx_q); INIT_WORK(&nu->write_work, nci_uart_write_work); spin_lock_init(&nu->rx_lock); ret = nu->ops.open(nu); if (ret) { - tty->disc_data = NULL; kfree(nu); + return ret; } else if (!try_module_get(nu->owner)) { nu->ops.close(nu); - tty->disc_data = NULL; kfree(nu); return -ENOENT; } - return ret; + tty->disc_data = nu; + + return 0; } /* ------ LDISC part ------ */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index e7269a3eec79..3add108340bf 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -39,16 +39,14 @@ #include "flow_netlink.h" #include "openvswitch_trace.h" -DEFINE_PER_CPU(struct ovs_pcpu_storage, ovs_pcpu_storage) = { - .bh_lock = INIT_LOCAL_LOCK(bh_lock), -}; +struct ovs_pcpu_storage __percpu *ovs_pcpu_storage; /* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys' * space. Return NULL if out of key spaces. */ static struct sw_flow_key *clone_key(const struct sw_flow_key *key_) { - struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(&ovs_pcpu_storage); + struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage); struct action_flow_keys *keys = &ovs_pcpu->flow_keys; int level = ovs_pcpu->exec_level; struct sw_flow_key *key = NULL; @@ -94,7 +92,7 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb, const struct nlattr *actions, const int actions_len) { - struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage.action_fifos); + struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos); struct deferred_action *da; da = action_fifo_put(fifo); @@ -755,7 +753,7 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage.frag_data); + struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage->frag_data); struct vport *vport = data->vport; if (skb_cow_head(skb, data->l2_len) < 0) { @@ -807,7 +805,7 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb, unsigned int hlen = skb_network_offset(skb); struct ovs_frag_data *data; - data = this_cpu_ptr(&ovs_pcpu_storage.frag_data); + data = this_cpu_ptr(&ovs_pcpu_storage->frag_data); data->dst = skb->_skb_refdst; data->vport = vport; data->cb = *OVS_CB(skb); @@ -1566,16 +1564,15 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb, clone = clone_flow_key ? clone_key(key) : key; if (clone) { int err = 0; - if (actions) { /* Sample action */ if (clone_flow_key) - __this_cpu_inc(ovs_pcpu_storage.exec_level); + __this_cpu_inc(ovs_pcpu_storage->exec_level); err = do_execute_actions(dp, skb, clone, actions, len); if (clone_flow_key) - __this_cpu_dec(ovs_pcpu_storage.exec_level); + __this_cpu_dec(ovs_pcpu_storage->exec_level); } else { /* Recirc action */ clone->recirc_id = recirc_id; ovs_dp_process_packet(skb, clone); @@ -1611,7 +1608,7 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb, static void process_deferred_actions(struct datapath *dp) { - struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage.action_fifos); + struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos); /* Do not touch the FIFO in case there is no deferred actions. */ if (action_fifo_is_empty(fifo)) @@ -1642,7 +1639,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, { int err, level; - level = __this_cpu_inc_return(ovs_pcpu_storage.exec_level); + level = __this_cpu_inc_return(ovs_pcpu_storage->exec_level); if (unlikely(level > OVS_RECURSION_LIMIT)) { net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n", ovs_dp_name(dp)); @@ -1659,6 +1656,6 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, process_deferred_actions(dp); out: - __this_cpu_dec(ovs_pcpu_storage.exec_level); + __this_cpu_dec(ovs_pcpu_storage->exec_level); return err; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 6a304ae2d959..b990dc83504f 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -244,7 +244,7 @@ void ovs_dp_detach_port(struct vport *p) /* Must be called with rcu_read_lock. */ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) { - struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(&ovs_pcpu_storage); + struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage); const struct vport *p = OVS_CB(skb)->input_vport; struct datapath *dp = p->dp; struct sw_flow *flow; @@ -299,7 +299,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) * avoided. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && ovs_pcpu->owner != current) { - local_lock_nested_bh(&ovs_pcpu_storage.bh_lock); + local_lock_nested_bh(&ovs_pcpu_storage->bh_lock); ovs_pcpu->owner = current; ovs_pcpu_locked = true; } @@ -310,7 +310,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) ovs_dp_name(dp), error); if (ovs_pcpu_locked) { ovs_pcpu->owner = NULL; - local_unlock_nested_bh(&ovs_pcpu_storage.bh_lock); + local_unlock_nested_bh(&ovs_pcpu_storage->bh_lock); } stats_counter = &stats->n_hit; @@ -689,13 +689,13 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) sf_acts = rcu_dereference(flow->sf_acts); local_bh_disable(); - local_lock_nested_bh(&ovs_pcpu_storage.bh_lock); + local_lock_nested_bh(&ovs_pcpu_storage->bh_lock); if (IS_ENABLED(CONFIG_PREEMPT_RT)) - this_cpu_write(ovs_pcpu_storage.owner, current); + this_cpu_write(ovs_pcpu_storage->owner, current); err = ovs_execute_actions(dp, packet, sf_acts, &flow->key); if (IS_ENABLED(CONFIG_PREEMPT_RT)) - this_cpu_write(ovs_pcpu_storage.owner, NULL); - local_unlock_nested_bh(&ovs_pcpu_storage.bh_lock); + this_cpu_write(ovs_pcpu_storage->owner, NULL); + local_unlock_nested_bh(&ovs_pcpu_storage->bh_lock); local_bh_enable(); rcu_read_unlock(); @@ -2744,6 +2744,28 @@ static struct drop_reason_list drop_reason_list_ovs = { .n_reasons = ARRAY_SIZE(ovs_drop_reasons), }; +static int __init ovs_alloc_percpu_storage(void) +{ + unsigned int cpu; + + ovs_pcpu_storage = alloc_percpu(*ovs_pcpu_storage); + if (!ovs_pcpu_storage) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + struct ovs_pcpu_storage *ovs_pcpu; + + ovs_pcpu = per_cpu_ptr(ovs_pcpu_storage, cpu); + local_lock_init(&ovs_pcpu->bh_lock); + } + return 0; +} + +static void ovs_free_percpu_storage(void) +{ + free_percpu(ovs_pcpu_storage); +} + static int __init dp_init(void) { int err; @@ -2753,6 +2775,10 @@ static int __init dp_init(void) pr_info("Open vSwitch switching datapath\n"); + err = ovs_alloc_percpu_storage(); + if (err) + goto error; + err = ovs_internal_dev_rtnl_link_register(); if (err) goto error; @@ -2799,6 +2825,7 @@ error_flow_exit: error_unreg_rtnl_link: ovs_internal_dev_rtnl_link_unregister(); error: + ovs_free_percpu_storage(); return err; } @@ -2813,6 +2840,7 @@ static void dp_cleanup(void) ovs_vport_exit(); ovs_flow_exit(); ovs_internal_dev_rtnl_link_unregister(); + ovs_free_percpu_storage(); } module_init(dp_init); diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 1b5348b0f559..cfeb817a1889 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -220,7 +220,8 @@ struct ovs_pcpu_storage { struct task_struct *owner; local_lock_t bh_lock; }; -DECLARE_PER_CPU(struct ovs_pcpu_storage, ovs_pcpu_storage); + +extern struct ovs_pcpu_storage __percpu *ovs_pcpu_storage; /** * enum ovs_pkt_hash_types - hash info to include with a packet diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 14021b812329..2b14c81a87e5 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1328,13 +1328,15 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, stab = rtnl_dereference(q->root->stab); - oper = rtnl_dereference(q->oper_sched); + rcu_read_lock(); + oper = rcu_dereference(q->oper_sched); if (oper) taprio_update_queue_max_sdu(q, oper, stab); - admin = rtnl_dereference(q->admin_sched); + admin = rcu_dereference(q->admin_sched); if (admin) taprio_update_queue_max_sdu(q, admin, stab); + rcu_read_unlock(); break; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 108a4cc2e001..258d6aa4f21a 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -489,7 +489,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); b = tipc_bearer_find(net, bname); - if (!b) { + if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) { rtnl_unlock(); return -EINVAL; } @@ -500,7 +500,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); b = rtnl_dereference(tn->bearer_list[bid]); - if (!b) { + if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) { rtnl_unlock(); return -EINVAL; } diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index 55b59f6c79b8..61deb5923067 100644 --- a/tools/net/ynl/pyynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -231,14 +231,7 @@ class NlMsg: self.extack['unknown'].append(extack) if attr_space: - # We don't have the ability to parse nests yet, so only do global - if 'miss-type' in self.extack and 'miss-nest' not in self.extack: - miss_type = self.extack['miss-type'] - if miss_type in attr_space.attrs_by_val: - spec = attr_space.attrs_by_val[miss_type] - self.extack['miss-type'] = spec['name'] - if 'doc' in spec: - self.extack['miss-type-doc'] = spec['doc'] + self.annotate_extack(attr_space) def _decode_policy(self, raw): policy = {} @@ -264,6 +257,18 @@ class NlMsg: policy['mask'] = attr.as_scalar('u64') return policy + def annotate_extack(self, attr_space): + """ Make extack more human friendly with attribute information """ + + # We don't have the ability to parse nests yet, so only do global + if 'miss-type' in self.extack and 'miss-nest' not in self.extack: + miss_type = self.extack['miss-type'] + if miss_type in attr_space.attrs_by_val: + spec = attr_space.attrs_by_val[miss_type] + self.extack['miss-type'] = spec['name'] + if 'doc' in spec: + self.extack['miss-type-doc'] = spec['doc'] + def cmd(self): return self.nl_type @@ -277,12 +282,12 @@ class NlMsg: class NlMsgs: - def __init__(self, data, attr_space=None): + def __init__(self, data): self.msgs = [] offset = 0 while offset < len(data): - msg = NlMsg(data, offset, attr_space=attr_space) + msg = NlMsg(data, offset) offset += msg.nl_len self.msgs.append(msg) @@ -1034,12 +1039,13 @@ class YnlFamily(SpecFamily): op_rsp = [] while not done: reply = self.sock.recv(self._recv_size) - nms = NlMsgs(reply, attr_space=op.attr_set) + nms = NlMsgs(reply) self._recv_dbg_print(reply, nms) for nl_msg in nms: if nl_msg.nl_seq in reqs_by_seq: (op, vals, req_msg, req_flags) = reqs_by_seq[nl_msg.nl_seq] if nl_msg.extack: + nl_msg.annotate_extack(op.attr_set) self._decode_extack(req_msg, op, nl_msg.extack, vals) else: op = None diff --git a/tools/testing/selftests/drivers/net/netdevsim/peer.sh b/tools/testing/selftests/drivers/net/netdevsim/peer.sh index 1bb46ec435d4..7f32b5600925 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/peer.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/peer.sh @@ -1,7 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0-only -source ../../../net/lib.sh +lib_dir=$(dirname $0)/../../../net +source $lib_dir/lib.sh NSIM_DEV_1_ID=$((256 + RANDOM % 256)) NSIM_DEV_1_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_DEV_1_ID diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 532bb732bc6d..c6dd2a335cf4 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -50,6 +50,7 @@ tap tcp_fastopen_backup_key tcp_inq tcp_mmap +tfo timestamping tls toeplitz diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index ab996bd22a5f..332f387615d7 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -110,6 +110,8 @@ TEST_GEN_PROGS += proc_net_pktgen TEST_PROGS += lwt_dst_cache_ref_loop.sh TEST_PROGS += skf_net_off.sh TEST_GEN_FILES += skf_net_off +TEST_GEN_FILES += tfo +TEST_PROGS += tfo_passive.sh # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := busy_poller netlink-dumps diff --git a/tools/testing/selftests/net/tfo.c b/tools/testing/selftests/net/tfo.c new file mode 100644 index 000000000000..eb3cac5e583c --- /dev/null +++ b/tools/testing/selftests/net/tfo.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <error.h> +#include <fcntl.h> +#include <limits.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <arpa/inet.h> +#include <sys/socket.h> +#include <netinet/tcp.h> +#include <errno.h> + +static int cfg_server; +static int cfg_client; +static int cfg_port = 8000; +static struct sockaddr_in6 cfg_addr; +static char *cfg_outfile; + +static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6) +{ + int ret; + + sin6->sin6_family = AF_INET6; + sin6->sin6_port = htons(port); + + ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr); + if (ret != 1) { + /* fallback to plain IPv4 */ + ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]); + if (ret != 1) + return -1; + + /* add ::ffff prefix */ + sin6->sin6_addr.s6_addr32[0] = 0; + sin6->sin6_addr.s6_addr32[1] = 0; + sin6->sin6_addr.s6_addr16[4] = 0; + sin6->sin6_addr.s6_addr16[5] = 0xffff; + } + + return 0; +} + +static void run_server(void) +{ + unsigned long qlen = 32; + int fd, opt, connfd; + socklen_t len; + char buf[64]; + FILE *outfile; + + outfile = fopen(cfg_outfile, "w"); + if (!outfile) + error(1, errno, "fopen() outfile"); + + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (fd == -1) + error(1, errno, "socket()"); + + opt = 1; + if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt)) < 0) + error(1, errno, "setsockopt(SO_REUSEADDR)"); + + if (setsockopt(fd, SOL_TCP, TCP_FASTOPEN, &qlen, sizeof(qlen)) < 0) + error(1, errno, "setsockopt(TCP_FASTOPEN)"); + + if (bind(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr)) < 0) + error(1, errno, "bind()"); + + if (listen(fd, 5) < 0) + error(1, errno, "listen()"); + + len = sizeof(cfg_addr); + connfd = accept(fd, (struct sockaddr *)&cfg_addr, &len); + if (connfd < 0) + error(1, errno, "accept()"); + + len = sizeof(opt); + if (getsockopt(connfd, SOL_SOCKET, SO_INCOMING_NAPI_ID, &opt, &len) < 0) + error(1, errno, "getsockopt(SO_INCOMING_NAPI_ID)"); + + read(connfd, buf, 64); + fprintf(outfile, "%d\n", opt); + + fclose(outfile); + close(connfd); + close(fd); +} + +static void run_client(void) +{ + int fd; + char *msg = "Hello, world!"; + + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (fd == -1) + error(1, errno, "socket()"); + + sendto(fd, msg, strlen(msg), MSG_FASTOPEN, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr)); + + close(fd); +} + +static void usage(const char *filepath) +{ + error(1, 0, "Usage: %s (-s|-c) -h<server_ip> -p<port> -o<outfile> ", filepath); +} + +static void parse_opts(int argc, char **argv) +{ + struct sockaddr_in6 *addr6 = (void *) &cfg_addr; + char *addr = NULL; + int ret; + int c; + + if (argc <= 1) + usage(argv[0]); + + while ((c = getopt(argc, argv, "sch:p:o:")) != -1) { + switch (c) { + case 's': + if (cfg_client) + error(1, 0, "Pass one of -s or -c"); + cfg_server = 1; + break; + case 'c': + if (cfg_server) + error(1, 0, "Pass one of -s or -c"); + cfg_client = 1; + break; + case 'h': + addr = optarg; + break; + case 'p': + cfg_port = strtoul(optarg, NULL, 0); + break; + case 'o': + cfg_outfile = strdup(optarg); + if (!cfg_outfile) + error(1, 0, "outfile invalid"); + break; + } + } + + if (cfg_server && addr) + error(1, 0, "Server cannot have -h specified"); + + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(cfg_port); + addr6->sin6_addr = in6addr_any; + if (addr) { + ret = parse_address(addr, cfg_port, addr6); + if (ret) + error(1, 0, "Client address parse error: %s", addr); + } +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + + if (cfg_server) + run_server(); + else if (cfg_client) + run_client(); + + return 0; +} diff --git a/tools/testing/selftests/net/tfo_passive.sh b/tools/testing/selftests/net/tfo_passive.sh new file mode 100755 index 000000000000..80bf11fdc046 --- /dev/null +++ b/tools/testing/selftests/net/tfo_passive.sh @@ -0,0 +1,112 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +source lib.sh + +NSIM_SV_ID=$((256 + RANDOM % 256)) +NSIM_SV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_SV_ID +NSIM_CL_ID=$((512 + RANDOM % 256)) +NSIM_CL_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_CL_ID + +NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device +NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device +NSIM_DEV_SYS_LINK=/sys/bus/netdevsim/link_device +NSIM_DEV_SYS_UNLINK=/sys/bus/netdevsim/unlink_device + +SERVER_IP=192.168.1.1 +CLIENT_IP=192.168.1.2 +SERVER_PORT=48675 + +setup_ns() +{ + set -e + ip netns add nssv + ip netns add nscl + + NSIM_SV_NAME=$(find $NSIM_SV_SYS/net -maxdepth 1 -type d ! \ + -path $NSIM_SV_SYS/net -exec basename {} \;) + NSIM_CL_NAME=$(find $NSIM_CL_SYS/net -maxdepth 1 -type d ! \ + -path $NSIM_CL_SYS/net -exec basename {} \;) + + ip link set $NSIM_SV_NAME netns nssv + ip link set $NSIM_CL_NAME netns nscl + + ip netns exec nssv ip addr add "${SERVER_IP}/24" dev $NSIM_SV_NAME + ip netns exec nscl ip addr add "${CLIENT_IP}/24" dev $NSIM_CL_NAME + + ip netns exec nssv ip link set dev $NSIM_SV_NAME up + ip netns exec nscl ip link set dev $NSIM_CL_NAME up + + # Enable passive TFO + ip netns exec nssv sysctl -w net.ipv4.tcp_fastopen=519 > /dev/null + + set +e +} + +cleanup_ns() +{ + ip netns del nscl + ip netns del nssv +} + +### +### Code start +### + +modprobe netdevsim + +# linking + +echo $NSIM_SV_ID > $NSIM_DEV_SYS_NEW +echo $NSIM_CL_ID > $NSIM_DEV_SYS_NEW +udevadm settle + +setup_ns + +NSIM_SV_FD=$((256 + RANDOM % 256)) +exec {NSIM_SV_FD}</var/run/netns/nssv +NSIM_SV_IFIDX=$(ip netns exec nssv cat /sys/class/net/$NSIM_SV_NAME/ifindex) + +NSIM_CL_FD=$((256 + RANDOM % 256)) +exec {NSIM_CL_FD}</var/run/netns/nscl +NSIM_CL_IFIDX=$(ip netns exec nscl cat /sys/class/net/$NSIM_CL_NAME/ifindex) + +echo "$NSIM_SV_FD:$NSIM_SV_IFIDX $NSIM_CL_FD:$NSIM_CL_IFIDX" > \ + $NSIM_DEV_SYS_LINK + +if [ $? -ne 0 ]; then + echo "linking netdevsim1 with netdevsim2 should succeed" + cleanup_ns + exit 1 +fi + +out_file=$(mktemp) + +timeout -k 1s 30s ip netns exec nssv ./tfo \ + -s \ + -p ${SERVER_PORT} \ + -o ${out_file}& + +wait_local_port_listen nssv ${SERVER_PORT} tcp + +ip netns exec nscl ./tfo -c -h ${SERVER_IP} -p ${SERVER_PORT} + +wait + +res=$(cat $out_file) +rm $out_file + +if [ $res -eq 0 ]; then + echo "got invalid NAPI ID from passive TFO socket" + cleanup_ns + exit 1 +fi + +echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK + +echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL + +cleanup_ns + +modprobe -r netdevsim + +exit 0 |