From 29e71f41e7d2f7069c12c686ca4d222e8be2a2ee Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Thu, 6 May 2021 08:40:02 -0700 Subject: ice: Remove boolean vlan_promisc flag from function Currently, the vlan_promisc flag is used exclusively by VF VSI to determine whether or not to toggle VLAN pruning along with trusted/true-promiscuous mode. This is not needed for a couple of reasons. First, trusted/true-promiscuous mode is only supposed to allow all MAC filters within VLANs that a VF has added filters for, so VLAN pruning should not be disabled. Second, the boolean argument makes the function confusing and unintuitive. Remove this flag. Signed-off-by: Brett Creeley Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 7 ++----- drivers/net/ethernet/intel/ice/ice_lib.h | 2 +- drivers/net/ethernet/intel/ice/ice_main.c | 12 ++++++------ drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 9 ++++++--- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 159c52b9b9d4..40562600a8cf 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2284,11 +2284,10 @@ bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI * @vsi: VSI to enable or disable VLAN pruning on * @ena: set to true to enable VLAN pruning and false to disable it - * @vlan_promisc: enable valid security flags if not in VLAN promiscuous mode * * returns 0 if VSI is updated, negative otherwise */ -int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc) +int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) { struct ice_vsi_ctx *ctxt; struct ice_pf *pf; @@ -2316,9 +2315,7 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc) else ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - if (!vlan_promisc) - ctxt->info.valid_sections = - cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); status = ice_update_vsi(&pf->hw, vsi->idx, ctxt, NULL); if (status) { diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index e7f4ecbb8549..6c803407b67d 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -45,7 +45,7 @@ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi); -int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc); +int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena); void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 66112addfb9a..f099797f35e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -396,7 +396,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) ~IFF_PROMISC; goto out_promisc; } - ice_cfg_vlan_pruning(vsi, false, false); + ice_cfg_vlan_pruning(vsi, false); } } else { /* Clear Rx filter to remove traffic from wire */ @@ -410,7 +410,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) goto out_promisc; } if (vsi->num_vlan > 1) - ice_cfg_vlan_pruning(vsi, true, false); + ice_cfg_vlan_pruning(vsi, true); } } } @@ -3387,7 +3387,7 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto, /* Enable VLAN pruning when a VLAN other than 0 is added */ if (!ice_vsi_is_vlan_pruning_ena(vsi)) { - ret = ice_cfg_vlan_pruning(vsi, true, false); + ret = ice_cfg_vlan_pruning(vsi, true); if (ret) return ret; } @@ -3431,7 +3431,7 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto, /* Disable pruning when VLAN 0 is the only VLAN rule */ if (vsi->num_vlan == 1 && ice_vsi_is_vlan_pruning_ena(vsi)) - ret = ice_cfg_vlan_pruning(vsi, false, false); + ret = ice_cfg_vlan_pruning(vsi, false); set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); return ret; @@ -5616,10 +5616,10 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) && !(netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) - ret = ice_cfg_vlan_pruning(vsi, true, false); + ret = ice_cfg_vlan_pruning(vsi, true); else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) && (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) - ret = ice_cfg_vlan_pruning(vsi, false, false); + ret = ice_cfg_vlan_pruning(vsi, false); if ((features & NETIF_F_NTUPLE) && !(netdev->features & NETIF_F_NTUPLE)) { diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 6a74344a3c21..2ac21484b876 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -3072,7 +3072,10 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) v_ret = VIRTCHNL_STATUS_ERR_PARAM; } - ret = ice_cfg_vlan_pruning(vsi, true, !rm_promisc); + if (rm_promisc) + ret = ice_cfg_vlan_pruning(vsi, true); + else + ret = ice_cfg_vlan_pruning(vsi, false); if (ret) { dev_err(dev, "Failed to configure VLAN pruning in promiscuous mode\n"); v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -4277,7 +4280,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) /* Enable VLAN pruning when non-zero VLAN is added */ if (!vlan_promisc && vid && !ice_vsi_is_vlan_pruning_ena(vsi)) { - status = ice_cfg_vlan_pruning(vsi, true, false); + status = ice_cfg_vlan_pruning(vsi, true); if (status) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; dev_err(dev, "Enable VLAN pruning on VLAN ID: %d failed error-%d\n", @@ -4331,7 +4334,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) /* Disable VLAN pruning when only VLAN 0 is left */ if (vsi->num_vlan == 1 && ice_vsi_is_vlan_pruning_ena(vsi)) - ice_cfg_vlan_pruning(vsi, false, false); + ice_cfg_vlan_pruning(vsi, false); /* Disable Unicast/Multicast VLAN promiscuous mode */ if (vlan_promisc) { -- cgit v1.2.3 From c79bb28e19cca322b70a912ec17dd6482d24c7e9 Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Tue, 26 Oct 2021 17:46:28 +0200 Subject: ice: Clear synchronized addrs when adding VFs in switchdev mode When spawning VFs in switchdev mode, internal filter list of VSIs is cleared, which includes MAC rules. However MAC entries stay on netdev's multicast list, which causes error message when bringing link up after spawning VFs ("Failed to delete MAC filters"). __dev_mc_sync() is called and tries to unsync addresses that were already removed internally when adding VFs. This can be reproduced with: 1) Load ice driver 2) Change PF to switchdev mode 3) Bring PF link up 4) Bring PF link down 5) Create a VF on PF 6) Bring PF link up Added clearing of netdev's multicast (and also unicast) list when spawning VFs in switchdev mode, so the state of internal rule list and netdev's MAC list is consistent. Fixes: 1a1c40df2e80 ("ice: set and release switchdev environment") Signed-off-by: Marcin Szycik Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_eswitch.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 6cb50653b18d..d1d7389b0bff 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -19,6 +19,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) { struct ice_vsi *uplink_vsi = pf->switchdev.uplink_vsi; + struct net_device *uplink_netdev = uplink_vsi->netdev; struct ice_vsi *ctrl_vsi = pf->switchdev.control_vsi; struct ice_port_info *pi = pf->hw.port_info; bool rule_added = false; @@ -27,6 +28,11 @@ static int ice_eswitch_setup_env(struct ice_pf *pf) ice_remove_vsi_fltr(&pf->hw, uplink_vsi->idx); + netif_addr_lock_bh(uplink_netdev); + __dev_uc_unsync(uplink_netdev, NULL); + __dev_mc_unsync(uplink_netdev, NULL); + netif_addr_unlock_bh(uplink_netdev); + if (ice_vsi_add_vlan(uplink_vsi, 0, ICE_FWD_TO_VSI)) goto err_def_rx; -- cgit v1.2.3 From bfaaba99e680bf82bf2cbf69866c3f37434ff766 Mon Sep 17 00:00:00 2001 From: Marcin Szycik Date: Tue, 26 Oct 2021 17:56:24 +0200 Subject: ice: Hide bus-info in ethtool for PRs in switchdev mode Disable showing bus-info information for port representors in switchdev mode. This fixes a bug that caused displaying wrong netdev descriptions in lshw tool - one port representor displayed PF branding string, and in turn one PF displayed a "generic" description. The bug occurs when many devices show the same bus-info in ethtool, which was the case in switchdev mode (PF and its port representors displayed the same bus-info). The bug occurs only if a port representor netdev appears before PF netdev in /proc/net/dev. In the examples below: ens6fX is PF ens6fXvY is VF ethX is port representor One irrelevant column was removed from output Before: $ sudo lshw -c net -businfo Bus info Device Description ========================================= pci@0000:02:00.0 eth102 Ethernet Controller E810-XXV for SFP pci@0000:02:00.1 ens6f1 Ethernet Controller E810-XXV for SFP pci@0000:02:01.0 ens6f0v0 Ethernet Adaptive Virtual Function pci@0000:02:01.1 ens6f0v1 Ethernet Adaptive Virtual Function pci@0000:02:01.2 ens6f0v2 Ethernet Adaptive Virtual Function pci@0000:02:00.0 ens6f0 Ethernet interface Notice that eth102 and ens6f0 have the same bus-info and their descriptions are swapped. After: $ sudo lshw -c net -businfo Bus info Device Description ========================================= pci@0000:02:00.0 ens6f0 Ethernet Controller E810-XXV for SFP pci@0000:02:00.1 ens6f1 Ethernet Controller E810-XXV for SFP pci@0000:02:01.0 ens6f0v0 Ethernet Adaptive Virtual Function pci@0000:02:01.1 ens6f0v1 Ethernet Adaptive Virtual Function pci@0000:02:01.2 ens6f0v2 Ethernet Adaptive Virtual Function Fixes: 7aae80cef7ba ("ice: add port representor ethtool ops and stats") Signed-off-by: Marcin Szycik Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ethtool.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index cfe96a127ed4..572519e402f4 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -189,18 +189,19 @@ __ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo, snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%x.%02x 0x%x %d.%d.%d", nvm->major, nvm->minor, nvm->eetrack, orom->major, orom->build, orom->patch); - - strscpy(drvinfo->bus_info, pci_name(pf->pdev), - sizeof(drvinfo->bus_info)); } static void ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; __ice_get_drvinfo(netdev, drvinfo, np->vsi); + strscpy(drvinfo->bus_info, pci_name(pf->pdev), + sizeof(drvinfo->bus_info)); + drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE; } -- cgit v1.2.3 From 5bf84b29938579a9350a4a9c2c4f8b5da2aa6992 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Fri, 7 May 2021 15:09:10 -0700 Subject: virtchnl: Remove unused VIRTCHNL_VF_OFFLOAD_RSVD define Remove unused define that is currently marked as reserved. This will open up space for a new feature if/when it's introduced. Also, there is no reason to keep unused defines around. Suggested-by: Tony Nguyen Signed-off-by: Brett Creeley Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index db0e099c2399..2e1e1379b569 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -240,7 +240,6 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); */ #define VIRTCHNL_VF_OFFLOAD_L2 0x00000001 #define VIRTCHNL_VF_OFFLOAD_IWARP 0x00000002 -#define VIRTCHNL_VF_OFFLOAD_RSVD 0x00000004 #define VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 #define VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 #define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 -- cgit v1.2.3 From 4a15022f82ee0f2e14a7f953b7bbc0f5c983b663 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Fri, 7 May 2021 15:09:11 -0700 Subject: virtchnl: Use the BIT() macro for capability/offload flags Currently raw hex values are used to define specific bits for each capability/offload in virtchnl.h. Using raw hex values makes it unclear which bits are used/available. Fix this by using the BIT() macro so it's immediately obvious which bits are used/available. Also, move the VIRTCHNL_VF_CAP_ADV_LINK_SPEED define in the correct place to line up with the other bit values and add a comment for its purpose. Signed-off-by: Brett Creeley Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 2e1e1379b569..b30a1bc74fc7 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -238,26 +238,26 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); * VIRTCHNL_VF_OFFLOAD_L2 flag is inclusive of base mode L2 offloads including * TX/RX Checksum offloading and TSO for non-tunnelled packets. */ -#define VIRTCHNL_VF_OFFLOAD_L2 0x00000001 -#define VIRTCHNL_VF_OFFLOAD_IWARP 0x00000002 -#define VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 -#define VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 -#define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 -#define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES 0x00000040 -#define VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 -#define VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 -#define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 -#define VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000 -#define VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000 -#define VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000 -#define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000 -#define VIRTCHNL_VF_OFFLOAD_ADQ 0X00800000 -#define VIRTCHNL_VF_OFFLOAD_USO 0X02000000 -#define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF 0X08000000 -#define VIRTCHNL_VF_OFFLOAD_FDIR_PF 0X10000000 - -/* Define below the capability flags that are not offloads */ -#define VIRTCHNL_VF_CAP_ADV_LINK_SPEED 0x00000080 +#define VIRTCHNL_VF_OFFLOAD_L2 BIT(0) +#define VIRTCHNL_VF_OFFLOAD_IWARP BIT(1) +#define VIRTCHNL_VF_OFFLOAD_RSS_AQ BIT(3) +#define VIRTCHNL_VF_OFFLOAD_RSS_REG BIT(4) +#define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR BIT(5) +#define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES BIT(6) +/* used to negotiate communicating link speeds in Mbps */ +#define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) +#define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) +#define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) +#define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 BIT(18) +#define VIRTCHNL_VF_OFFLOAD_RSS_PF BIT(19) +#define VIRTCHNL_VF_OFFLOAD_ENCAP BIT(20) +#define VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM BIT(21) +#define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM BIT(22) +#define VIRTCHNL_VF_OFFLOAD_ADQ BIT(23) +#define VIRTCHNL_VF_OFFLOAD_USO BIT(25) +#define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF BIT(27) +#define VIRTCHNL_VF_OFFLOAD_FDIR_PF BIT(28) + #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ VIRTCHNL_VF_OFFLOAD_RSS_PF) -- cgit v1.2.3 From 247aa001b72b6c8a89df9d108a2ec6f274a6b64d Mon Sep 17 00:00:00 2001 From: Karen Sornek Date: Wed, 15 Sep 2021 08:41:23 +0200 Subject: iavf: Add helper function to go from pci_dev to adapter Add helper function to go from pci_dev to adapter to make work simple - to go from a pci_dev to the adapter structure and make netdev assignment instead of having to go to the net_device then the adapter. Signed-off-by: Brett Creeley Signed-off-by: Karen Sornek Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 56956e449c97..469160346438 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -51,6 +51,15 @@ MODULE_LICENSE("GPL v2"); static const struct net_device_ops iavf_netdev_ops; struct workqueue_struct *iavf_wq; +/** + * iavf_pdev_to_adapter - go from pci_dev to adapter + * @pdev: pci_dev pointer + */ +static struct iavf_adapter *iavf_pdev_to_adapter(struct pci_dev *pdev) +{ + return netdev_priv(pci_get_drvdata(pdev)); +} + /** * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure @@ -3681,8 +3690,8 @@ int iavf_process_config(struct iavf_adapter *adapter) **/ static void iavf_shutdown(struct pci_dev *pdev) { - struct net_device *netdev = pci_get_drvdata(pdev); - struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); + struct net_device *netdev = adapter->netdev; netif_device_detach(netdev); @@ -3866,10 +3875,11 @@ static int __maybe_unused iavf_suspend(struct device *dev_d) static int __maybe_unused iavf_resume(struct device *dev_d) { struct pci_dev *pdev = to_pci_dev(dev_d); - struct net_device *netdev = pci_get_drvdata(pdev); - struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter; u32 err; + adapter = iavf_pdev_to_adapter(pdev); + pci_set_master(pdev); rtnl_lock(); @@ -3888,7 +3898,7 @@ static int __maybe_unused iavf_resume(struct device *dev_d) queue_work(iavf_wq, &adapter->reset_task); - netif_device_attach(netdev); + netif_device_attach(adapter->netdev); return err; } @@ -3904,8 +3914,8 @@ static int __maybe_unused iavf_resume(struct device *dev_d) **/ static void iavf_remove(struct pci_dev *pdev) { - struct net_device *netdev = pci_get_drvdata(pdev); - struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); + struct net_device *netdev = adapter->netdev; struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; struct iavf_adv_rss *rss, *rsstmp; -- cgit v1.2.3 From 605ca7c5c670762e36ccb475cfa089d7ad0698e0 Mon Sep 17 00:00:00 2001 From: Przemyslaw Patynowski Date: Fri, 22 Oct 2021 10:30:14 +0200 Subject: iavf: Fix kernel BUG in free_msi_irqs Fix driver not freeing VF's traffic irqs, prior to calling pci_disable_msix in iavf_remove. There were possible 2 erroneous states in which, iavf_close would not be called. One erroneous state is fixed by allowing netdev to register, when state is already running. It was possible for VF adapter to enter state loop from running to resetting, where iavf_open would subsequently fail. If user would then unload driver/remove VF pci, iavf_close would not be called, as the netdev was not registered, leaving traffic pcis still allocated. Fixed this by breaking loop, allowing netdev to open device when adapter state is __IAVF_RUNNING and it is not explicitily downed. Other possiblity is entering to iavf_remove from __IAVF_RESETTING state, where iavf_close would not free irqs, but just return 0. Fixed this by checking for last adapter state and then removing irqs. Kernel panic: [ 2773.628585] kernel BUG at drivers/pci/msi.c:375! ... [ 2773.631567] RIP: 0010:free_msi_irqs+0x180/0x1b0 ... [ 2773.640939] Call Trace: [ 2773.641572] pci_disable_msix+0xf7/0x120 [ 2773.642224] iavf_reset_interrupt_capability.part.41+0x15/0x30 [iavf] [ 2773.642897] iavf_remove+0x12e/0x500 [iavf] [ 2773.643578] pci_device_remove+0x3b/0xc0 [ 2773.644266] device_release_driver_internal+0x103/0x1f0 [ 2773.644948] pci_stop_bus_device+0x69/0x90 [ 2773.645576] pci_stop_and_remove_bus_device+0xe/0x20 [ 2773.646215] pci_iov_remove_virtfn+0xba/0x120 [ 2773.646862] sriov_disable+0x2f/0xe0 [ 2773.647531] ice_free_vfs+0x2f8/0x350 [ice] [ 2773.648207] ice_sriov_configure+0x94/0x960 [ice] [ 2773.648883] ? _kstrtoull+0x3b/0x90 [ 2773.649560] sriov_numvfs_store+0x10a/0x190 [ 2773.650249] kernfs_fop_write+0x116/0x190 [ 2773.650948] vfs_write+0xa5/0x1a0 [ 2773.651651] ksys_write+0x4f/0xb0 [ 2773.652358] do_syscall_64+0x5b/0x1a0 [ 2773.653075] entry_SYSCALL_64_after_hwframe+0x65/0xca Fixes: 22ead37f8af8 ("i40evf: Add longer wait after remove module") Signed-off-by: Przemyslaw Patynowski Signed-off-by: Mateusz Palczewski Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf.h | 36 +++++++++++++++++++++++++++++ drivers/net/ethernet/intel/iavf/iavf_main.c | 20 ++++++++++++++++ 2 files changed, 56 insertions(+) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index e0b88ff76466..e6e7c1da47fb 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -394,6 +394,38 @@ struct iavf_device { extern char iavf_driver_name[]; extern struct workqueue_struct *iavf_wq; +static inline const char *iavf_state_str(enum iavf_state_t state) +{ + switch (state) { + case __IAVF_STARTUP: + return "__IAVF_STARTUP"; + case __IAVF_REMOVE: + return "__IAVF_REMOVE"; + case __IAVF_INIT_VERSION_CHECK: + return "__IAVF_INIT_VERSION_CHECK"; + case __IAVF_INIT_GET_RESOURCES: + return "__IAVF_INIT_GET_RESOURCES"; + case __IAVF_INIT_SW: + return "__IAVF_INIT_SW"; + case __IAVF_INIT_FAILED: + return "__IAVF_INIT_FAILED"; + case __IAVF_RESETTING: + return "__IAVF_RESETTING"; + case __IAVF_COMM_FAILED: + return "__IAVF_COMM_FAILED"; + case __IAVF_DOWN: + return "__IAVF_DOWN"; + case __IAVF_DOWN_PENDING: + return "__IAVF_DOWN_PENDING"; + case __IAVF_TESTING: + return "__IAVF_TESTING"; + case __IAVF_RUNNING: + return "__IAVF_RUNNING"; + default: + return "__IAVF_UNKNOWN_STATE"; + } +} + static inline void iavf_change_state(struct iavf_adapter *adapter, enum iavf_state_t state) { @@ -401,6 +433,10 @@ static inline void iavf_change_state(struct iavf_adapter *adapter, adapter->last_state = adapter->state; adapter->state = state; } + dev_dbg(&adapter->pdev->dev, + "state transition from:%s to:%s\n", + iavf_state_str(adapter->last_state), + iavf_state_str(adapter->state)); } int iavf_up(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 469160346438..847d67e32a54 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3280,6 +3280,13 @@ static int iavf_open(struct net_device *netdev) goto err_unlock; } + if (adapter->state == __IAVF_RUNNING && + !test_bit(__IAVF_VSI_DOWN, adapter->vsi.state)) { + dev_dbg(&adapter->pdev->dev, "VF is already open.\n"); + err = 0; + goto err_unlock; + } + /* allocate transmit descriptors */ err = iavf_setup_all_tx_resources(adapter); if (err) @@ -3915,6 +3922,7 @@ static int __maybe_unused iavf_resume(struct device *dev_d) static void iavf_remove(struct pci_dev *pdev) { struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); + enum iavf_state_t prev_state = adapter->last_state; struct net_device *netdev = adapter->netdev; struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; @@ -3953,10 +3961,22 @@ static void iavf_remove(struct pci_dev *pdev) iavf_change_state(adapter, __IAVF_REMOVE); adapter->aq_required = 0; adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + iavf_free_all_tx_resources(adapter); iavf_free_all_rx_resources(adapter); iavf_misc_irq_disable(adapter); iavf_free_misc_irq(adapter); + + /* In case we enter iavf_remove from erroneous state, free traffic irqs + * here, so as to not cause a kernel crash, when calling + * iavf_reset_interrupt_capability. + */ + if ((adapter->last_state == __IAVF_RESETTING && + prev_state != __IAVF_DOWN) || + (adapter->last_state == __IAVF_RUNNING && + !(netdev->flags & IFF_UP))) + iavf_free_traffic_irqs(adapter); + iavf_reset_interrupt_capability(adapter); iavf_free_q_vectors(adapter); -- cgit v1.2.3