From b70bc066d77b460a63a8c3fb2ea0d811ce862a83 Mon Sep 17 00:00:00 2001 From: Wojciech Drewek Date: Fri, 17 Dec 2021 12:36:25 +0100 Subject: ice: Match on all profiles in slow-path In switchdev mode, slow-path rules need to match all protocols, in order to correctly redirect unfiltered or missed packets to the uplink. To set this up for the virtual function to uplink flow, the rule that redirects packets to the control VSI must have the tunnel type set to ICE_SW_TUN_AND_NON_TUN. As a result of that new tunnel type being set, ice_get_compat_fv_bitmap will select ICE_PROF_ALL. At that point all profiles would be selected for this rule, resulting in the desired behavior. Without this change slow-path would not work with tunnel protocols. Fixes: 8b032a55c1bd ("ice: low level support for tunnels") Signed-off-by: Wojciech Drewek Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_eswitch.c | 1 + drivers/net/ethernet/intel/ice/ice_protocol_type.h | 1 + drivers/net/ethernet/intel/ice/ice_switch.c | 4 +++- 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet/intel/ice') diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 864692b157b6..73edc24d81d5 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -44,6 +44,7 @@ ice_eswitch_add_vf_mac_rule(struct ice_pf *pf, struct ice_vf *vf, const u8 *mac) ctrl_vsi->rxq_map[vf->vf_id]; rule_info.flags_info.act |= ICE_SINGLE_ACT_LB_ENABLE; rule_info.flags_info.act_valid = true; + rule_info.tun_type = ICE_SW_TUN_AND_NON_TUN; err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, vf->repr->mac_rule); diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index dc1b0e9e6df5..695b6dd61dc2 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -47,6 +47,7 @@ enum ice_protocol_type { enum ice_sw_tunnel_type { ICE_NON_TUN = 0, + ICE_SW_TUN_AND_NON_TUN, ICE_SW_TUN_VXLAN, ICE_SW_TUN_GENEVE, ICE_SW_TUN_NVGRE, diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 11ae0bee3590..475ec2afa210 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -4537,6 +4537,7 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, case ICE_SW_TUN_NVGRE: prof_type = ICE_PROF_TUN_GRE; break; + case ICE_SW_TUN_AND_NON_TUN: default: prof_type = ICE_PROF_ALL; break; @@ -5305,7 +5306,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (status) goto err_ice_add_adv_rule; - if (rinfo->tun_type != ICE_NON_TUN) { + if (rinfo->tun_type != ICE_NON_TUN && + rinfo->tun_type != ICE_SW_TUN_AND_NON_TUN) { status = ice_fill_adv_packet_tun(hw, rinfo->tun_type, s_rule->pdata.lkup_tx_rx.hdr, pkt_offsets); -- cgit v1.2.3 From 932645c298c41aad64ef13016ff4c2034eef5aed Mon Sep 17 00:00:00 2001 From: Michal Swiatkowski Date: Mon, 3 Jan 2022 07:41:21 +0100 Subject: ice: fix setting l4 port flag when adding filter Accidentally filter flag for none encapsulated l4 port field is always set. Even if user wants to add encapsulated l4 port field. Remove this unnecessary flag setting. Fixes: 9e300987d4a81 ("ice: VXLAN and Geneve TC support") Signed-off-by: Michal Swiatkowski Tested-by: Sandeep Penigalapati Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_tc_lib.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/intel/ice') diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index e8aab664270a..65cf32eb4046 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -709,7 +709,7 @@ ice_tc_set_port(struct flow_match_ports match, fltr->flags |= ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT; else fltr->flags |= ICE_TC_FLWR_FIELD_DEST_L4_PORT; - fltr->flags |= ICE_TC_FLWR_FIELD_DEST_L4_PORT; + headers->l4_key.dst_port = match.key->dst; headers->l4_mask.dst_port = match.mask->dst; } @@ -718,7 +718,7 @@ ice_tc_set_port(struct flow_match_ports match, fltr->flags |= ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT; else fltr->flags |= ICE_TC_FLWR_FIELD_SRC_L4_PORT; - fltr->flags |= ICE_TC_FLWR_FIELD_SRC_L4_PORT; + headers->l4_key.src_port = match.key->src; headers->l4_mask.src_port = match.mask->src; } -- cgit v1.2.3 From fadead80fe4c033b5e514fcbadd20b55c4494112 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 7 Feb 2022 10:23:29 -0800 Subject: ice: fix concurrent reset and removal of VFs Commit c503e63200c6 ("ice: Stop processing VF messages during teardown") introduced a driver state flag, ICE_VF_DEINIT_IN_PROGRESS, which is intended to prevent some issues with concurrently handling messages from VFs while tearing down the VFs. This change was motivated by crashes caused while tearing down and bringing up VFs in rapid succession. It turns out that the fix actually introduces issues with the VF driver caused because the PF no longer responds to any messages sent by the VF during its .remove routine. This results in the VF potentially removing its DMA memory before the PF has shut down the device queues. Additionally, the fix doesn't actually resolve concurrency issues within the ice driver. It is possible for a VF to initiate a reset just prior to the ice driver removing VFs. This can result in the remove task concurrently operating while the VF is being reset. This results in similar memory corruption and panics purportedly fixed by that commit. Fix this concurrency at its root by protecting both the reset and removal flows using the existing VF cfg_lock. This ensures that we cannot remove the VF while any outstanding critical tasks such as a virtchnl message or a reset are occurring. This locking change also fixes the root cause originally fixed by commit c503e63200c6 ("ice: Stop processing VF messages during teardown"), so we can simply revert it. Note that I kept these two changes together because simply reverting the original commit alone would leave the driver vulnerable to worse race conditions. Fixes: c503e63200c6 ("ice: Stop processing VF messages during teardown") Signed-off-by: Jacob Keller Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice.h | 1 - drivers/net/ethernet/intel/ice/ice_main.c | 2 ++ drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 42 ++++++++++++++---------- 3 files changed, 27 insertions(+), 18 deletions(-) (limited to 'drivers/net/ethernet/intel/ice') diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index a9fa701aaa95..473b1f6be9de 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -280,7 +280,6 @@ enum ice_pf_state { ICE_VFLR_EVENT_PENDING, ICE_FLTR_OVERFLOW_PROMISC, ICE_VF_DIS, - ICE_VF_DEINIT_IN_PROGRESS, ICE_CFG_BUSY, ICE_SERVICE_SCHED, ICE_SERVICE_DIS, diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 17a9bb461dc3..f3c346e13b7a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1799,7 +1799,9 @@ static void ice_handle_mdd_event(struct ice_pf *pf) * reset, so print the event prior to reset. */ ice_print_vf_rx_mdd_event(vf); + mutex_lock(&pf->vf[i].cfg_lock); ice_reset_vf(&pf->vf[i], false); + mutex_unlock(&pf->vf[i].cfg_lock); } } } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 39b80124d282..408f78e3eb13 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -500,8 +500,6 @@ void ice_free_vfs(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; unsigned int tmp, i; - set_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); - if (!pf->vf) return; @@ -519,22 +517,26 @@ void ice_free_vfs(struct ice_pf *pf) else dev_warn(dev, "VFs are assigned - not disabling SR-IOV\n"); - /* Avoid wait time by stopping all VFs at the same time */ - ice_for_each_vf(pf, i) - ice_dis_vf_qs(&pf->vf[i]); - tmp = pf->num_alloc_vfs; pf->num_qps_per_vf = 0; pf->num_alloc_vfs = 0; for (i = 0; i < tmp; i++) { - if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { + struct ice_vf *vf = &pf->vf[i]; + + mutex_lock(&vf->cfg_lock); + + ice_dis_vf_qs(vf); + + if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { /* disable VF qp mappings and set VF disable state */ - ice_dis_vf_mappings(&pf->vf[i]); - set_bit(ICE_VF_STATE_DIS, pf->vf[i].vf_states); - ice_free_vf_res(&pf->vf[i]); + ice_dis_vf_mappings(vf); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + ice_free_vf_res(vf); } - mutex_destroy(&pf->vf[i].cfg_lock); + mutex_unlock(&vf->cfg_lock); + + mutex_destroy(&vf->cfg_lock); } if (ice_sriov_free_msix_res(pf)) @@ -570,7 +572,6 @@ void ice_free_vfs(struct ice_pf *pf) i); clear_bit(ICE_VF_DIS, pf->state); - clear_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); } @@ -1498,6 +1499,8 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) ice_for_each_vf(pf, v) { vf = &pf->vf[v]; + mutex_lock(&vf->cfg_lock); + vf->driver_caps = 0; ice_vc_set_default_allowlist(vf); @@ -1512,6 +1515,8 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) ice_vf_pre_vsi_rebuild(vf); ice_vf_rebuild_vsi(vf); ice_vf_post_vsi_rebuild(vf); + + mutex_unlock(&vf->cfg_lock); } if (ice_is_eswitch_mode_switchdev(pf)) @@ -1562,6 +1567,8 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) u32 reg; int i; + lockdep_assert_held(&vf->cfg_lock); + dev = ice_pf_to_dev(pf); if (test_bit(ICE_VF_RESETS_DISABLED, pf->state)) { @@ -2061,9 +2068,12 @@ void ice_process_vflr_event(struct ice_pf *pf) bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; /* read GLGEN_VFLRSTAT register to find out the flr VFs */ reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx)); - if (reg & BIT(bit_idx)) + if (reg & BIT(bit_idx)) { /* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */ + mutex_lock(&vf->cfg_lock); ice_reset_vf(vf, true); + mutex_unlock(&vf->cfg_lock); + } } } @@ -2140,7 +2150,9 @@ ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) if (!vf) return; + mutex_lock(&vf->cfg_lock); ice_vc_reset_vf(vf); + mutex_unlock(&vf->cfg_lock); } /** @@ -4625,10 +4637,6 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) struct device *dev; int err = 0; - /* if de-init is underway, don't process messages from VF */ - if (test_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state)) - return; - dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) { err = -EINVAL; -- cgit v1.2.3 From ed22d9c8d128293fc7b0b086c7d3654bcb99a8dd Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 14 Feb 2022 06:33:27 -0800 Subject: ice: check the return of ice_ptp_gettimex64 Clang static analysis reports this issue time64.h:69:50: warning: The left operand of '+' is a garbage value set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, ~~~~~~~~~~ ^ In ice_ptp_adjtime_nonatomic(), the timespec64 variable 'now' is set by ice_ptp_gettimex64(). This function can fail with -EBUSY, so 'now' can have a gargbage value. So check the return. Fixes: 06c16d89d2cb ("ice: register 1588 PTP clock device object for E810 devices") Signed-off-by: Tom Rix Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ptp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet/intel/ice') diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index ae291d442539..000c39d163a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1533,9 +1533,12 @@ exit: static int ice_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta) { struct timespec64 now, then; + int ret; then = ns_to_timespec64(delta); - ice_ptp_gettimex64(info, &now, NULL); + ret = ice_ptp_gettimex64(info, &now, NULL); + if (ret) + return ret; now = timespec64_add(now, then); return ice_ptp_settime64(info, (const struct timespec64 *)&now); -- cgit v1.2.3 From 5950bdc88dd1d158f2845fdff8fb1de86476806c Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Mon, 14 Feb 2022 07:40:43 -0800 Subject: ice: initialize local variable 'tlv' Clang static analysis reports this issues ice_common.c:5008:21: warning: The left expression of the compound assignment is an uninitialized value. The computed value will also be garbage ldo->phy_type_low |= ((u64)buf << (i * 16)); ~~~~~~~~~~~~~~~~~ ^ When called from ice_cfg_phy_fec() ldo is the uninitialized local variable tlv. So initialize. Fixes: ea78ce4dab05 ("ice: add link lenient and default override support") Signed-off-by: Tom Rix Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/intel/ice') diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index a6d7d3eff186..e2af99a763ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -3340,7 +3340,7 @@ ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, if (fec == ICE_FEC_AUTO && ice_fw_supports_link_override(hw) && !ice_fw_supports_report_dflt_cfg(hw)) { - struct ice_link_default_override_tlv tlv; + struct ice_link_default_override_tlv tlv = { 0 }; status = ice_get_link_default_override(&tlv, pi); if (status) -- cgit v1.2.3 From 79498d5af8e458102242d1667cf44df1f1564e63 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Wed, 16 Feb 2022 16:51:36 -0800 Subject: ice: stop disabling VFs due to PF error responses The ice_vc_send_msg_to_vf function has logic to detect "failure" responses being sent to a VF. If a VF is sent more than ICE_DFLT_NUM_INVAL_MSGS_ALLOWED then the VF is marked as disabled. Almost identical logic also existed in the i40e driver. This logic was added to the ice driver in commit 1071a8358a28 ("ice: Implement virtchnl commands for AVF support") which itself copied from the i40e implementation in commit 5c3c48ac6bf5 ("i40e: implement virtual device interface"). Neither commit provides a proper explanation or justification of the check. In fact, later commits to i40e changed the logic to allow bypassing the check in some specific instances. The "logic" for this seems to be that error responses somehow indicate a malicious VF. This is not really true. The PF might be sending an error for any number of reasons such as lack of resources, etc. Additionally, this causes the PF to log an info message for every failed VF response which may confuse users, and can spam the kernel log. This behavior is not documented as part of any requirement for our products and other operating system drivers such as the FreeBSD implementation of our drivers do not include this type of check. In fact, the change from dev_err to dev_info in i40e commit 18b7af57d9c1 ("i40e: Lower some message levels") explains that these messages typically don't actually indicate a real issue. It is quite likely that a user who hits this in practice will be very confused as the VF will be disabled without an obvious way to recover. We already have robust malicious driver detection logic using actual hardware detection mechanisms that detect and prevent invalid device usage. Remove the logic since its not a documented requirement and the behavior is not intuitive. Fixes: 1071a8358a28 ("ice: Implement virtchnl commands for AVF support") Signed-off-by: Jacob Keller Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 18 ------------------ drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h | 3 --- 2 files changed, 21 deletions(-) (limited to 'drivers/net/ethernet/intel/ice') diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 408f78e3eb13..1be3cd4b2bef 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -2182,24 +2182,6 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, dev = ice_pf_to_dev(pf); - /* single place to detect unsuccessful return values */ - if (v_retval) { - vf->num_inval_msgs++; - dev_info(dev, "VF %d failed opcode %d, retval: %d\n", vf->vf_id, - v_opcode, v_retval); - if (vf->num_inval_msgs > ICE_DFLT_NUM_INVAL_MSGS_ALLOWED) { - dev_err(dev, "Number of invalid messages exceeded for VF %d\n", - vf->vf_id); - dev_err(dev, "Use PF Control I/F to enable the VF\n"); - set_bit(ICE_VF_STATE_DIS, vf->vf_states); - return -EIO; - } - } else { - vf->num_valid_msgs++; - /* reset the invalid counter, if a valid message is received. */ - vf->num_inval_msgs = 0; - } - aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, msg, msglen, NULL); if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) { diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 752487a1bdd6..8f27255cc0cc 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -14,7 +14,6 @@ #define ICE_MAX_MACADDR_PER_VF 18 /* Malicious Driver Detection */ -#define ICE_DFLT_NUM_INVAL_MSGS_ALLOWED 10 #define ICE_MDD_EVENTS_THRESHOLD 30 /* Static VF transaction/status register def */ @@ -134,8 +133,6 @@ struct ice_vf { unsigned int max_tx_rate; /* Maximum Tx bandwidth limit in Mbps */ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ - u64 num_inval_msgs; /* number of continuous invalid msgs */ - u64 num_valid_msgs; /* number of valid msgs detected */ unsigned long vf_caps; /* VF's adv. capabilities */ u8 num_req_qs; /* num of queue pairs requested by VF */ u16 num_mac; -- cgit v1.2.3 From 97b0129146b1544bbb0773585327896da3bb4e0a Mon Sep 17 00:00:00 2001 From: Dave Ertman Date: Fri, 18 Feb 2022 12:39:25 -0800 Subject: ice: Fix error with handling of bonding MTU When a bonded interface is destroyed, .ndo_change_mtu can be called during the tear-down process while the RTNL lock is held. This is a problem since the auxiliary driver linked to the LAN driver needs to be notified of the MTU change, and this requires grabbing a device_lock on the auxiliary_device's dev. Currently this is being attempted in the same execution context as the call to .ndo_change_mtu which is causing a dead-lock. Move the notification of the changed MTU to a separate execution context (watchdog service task) and eliminate the "before" notification. Fixes: 348048e724a0e ("ice: Implement iidc operations") Signed-off-by: Dave Ertman Tested-by: Jonathan Toppins Tested-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice.h | 1 + drivers/net/ethernet/intel/ice/ice_main.c | 29 ++++++++++++++--------------- 2 files changed, 15 insertions(+), 15 deletions(-) (limited to 'drivers/net/ethernet/intel/ice') diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 473b1f6be9de..3121f9b04f59 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -483,6 +483,7 @@ enum ice_pf_flags { ICE_FLAG_MDD_AUTO_RESET_VF, ICE_FLAG_LINK_LENIENT_MODE_ENA, ICE_FLAG_PLUG_AUX_DEV, + ICE_FLAG_MTU_CHANGED, ICE_PF_FLAGS_NBITS /* must be last */ }; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f3c346e13b7a..6fc6514eb007 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2258,6 +2258,17 @@ static void ice_service_task(struct work_struct *work) if (test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) ice_plug_aux_dev(pf); + if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) { + struct iidc_event *event; + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (event) { + set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + } + } + ice_clean_adminq_subtask(pf); ice_check_media_subtask(pf); ice_check_for_hang_subtask(pf); @@ -6822,7 +6833,6 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; - struct iidc_event *event; u8 count = 0; int err = 0; @@ -6857,14 +6867,6 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return -EBUSY; } - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (!event) - return -ENOMEM; - - set_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - clear_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); - netdev->mtu = (unsigned int)new_mtu; /* if VSI is up, bring it down and then back up */ @@ -6872,21 +6874,18 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) err = ice_down(vsi); if (err) { netdev_err(netdev, "change MTU if_down err %d\n", err); - goto event_after; + return err; } err = ice_up(vsi); if (err) { netdev_err(netdev, "change MTU if_up err %d\n", err); - goto event_after; + return err; } } netdev_dbg(netdev, "changed MTU to %d\n", new_mtu); -event_after: - set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - kfree(event); + set_bit(ICE_FLAG_MTU_CHANGED, pf->flags); return err; } -- cgit v1.2.3 From 3d97f1afd8d831e0c0dc1157418f94b8faa97b54 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 16 Jan 2022 19:46:20 +0100 Subject: ice: Don't use GFP_KERNEL in atomic context ice_misc_intr() is an irq handler. It should not sleep. Use GFP_ATOMIC instead of GFP_KERNEL when allocating some memory. Fixes: 348048e724a0 ("ice: Implement iidc operations") Signed-off-by: Christophe JAILLET Tested-by: Leszek Kaliszczuk Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/intel/ice') diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 6fc6514eb007..83e3e8aae6cf 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3034,7 +3034,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) struct iidc_event *event; ena_mask &= ~ICE_AUX_CRIT_ERR; - event = kzalloc(sizeof(*event), GFP_KERNEL); + event = kzalloc(sizeof(*event), GFP_ATOMIC); if (event) { set_bit(IIDC_EVENT_CRIT_ERR, event->type); /* report the entire OICR value to AUX driver */ -- cgit v1.2.3 From ad35ffa252af67d4cc7c744b9377a2b577748e3f Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Tue, 22 Feb 2022 11:43:04 +0000 Subject: ice: Fix curr_link_speed advertised speed Change curr_link_speed advertised speed, due to link_info.link_speed is not equal phy.curr_user_speed_req. Without this patch it is impossible to set advertised speed to same as link_speed. Testing Hints: Try to set advertised speed to 25G only with 25G default link (use ethtool -s 0x80000000) Fixes: 48cb27f2fd18 ("ice: Implement handlers for ethtool PHY/link operations") Signed-off-by: Grzegorz Siwik Signed-off-by: Jedrzej Jagielski Tested-by: Gurucharan (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ethernet/intel/ice') diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index e2e3ef7fba7f..a5dc9824e255 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2298,7 +2298,7 @@ ice_set_link_ksettings(struct net_device *netdev, if (err) goto done; - curr_link_speed = pi->phy.link_info.link_speed; + curr_link_speed = pi->phy.curr_user_speed_req; adv_link_speed = ice_ksettings_find_adv_link_speed(ks); /* If speed didn't get set, set it to what it currently is. -- cgit v1.2.3 From 5cb1ebdbc4342b1c2ce89516e19808d64417bdbc Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Thu, 10 Mar 2022 18:16:41 +0100 Subject: ice: Fix race condition during interface enslave Commit 5dbbbd01cbba83 ("ice: Avoid RTNL lock when re-creating auxiliary device") changes a process of re-creation of aux device so ice_plug_aux_dev() is called from ice_service_task() context. This unfortunately opens a race window that can result in dead-lock when interface has left LAG and immediately enters LAG again. Reproducer: ``` #!/bin/sh ip link add lag0 type bond mode 1 miimon 100 ip link set lag0 for n in {1..10}; do echo Cycle: $n ip link set ens7f0 master lag0 sleep 1 ip link set ens7f0 nomaster done ``` This results in: [20976.208697] Workqueue: ice ice_service_task [ice] [20976.213422] Call Trace: [20976.215871] __schedule+0x2d1/0x830 [20976.219364] schedule+0x35/0xa0 [20976.222510] schedule_preempt_disabled+0xa/0x10 [20976.227043] __mutex_lock.isra.7+0x310/0x420 [20976.235071] enum_all_gids_of_dev_cb+0x1c/0x100 [ib_core] [20976.251215] ib_enum_roce_netdev+0xa4/0xe0 [ib_core] [20976.256192] ib_cache_setup_one+0x33/0xa0 [ib_core] [20976.261079] ib_register_device+0x40d/0x580 [ib_core] [20976.266139] irdma_ib_register_device+0x129/0x250 [irdma] [20976.281409] irdma_probe+0x2c1/0x360 [irdma] [20976.285691] auxiliary_bus_probe+0x45/0x70 [20976.289790] really_probe+0x1f2/0x480 [20976.298509] driver_probe_device+0x49/0xc0 [20976.302609] bus_for_each_drv+0x79/0xc0 [20976.306448] __device_attach+0xdc/0x160 [20976.310286] bus_probe_device+0x9d/0xb0 [20976.314128] device_add+0x43c/0x890 [20976.321287] __auxiliary_device_add+0x43/0x60 [20976.325644] ice_plug_aux_dev+0xb2/0x100 [ice] [20976.330109] ice_service_task+0xd0c/0xed0 [ice] [20976.342591] process_one_work+0x1a7/0x360 [20976.350536] worker_thread+0x30/0x390 [20976.358128] kthread+0x10a/0x120 [20976.365547] ret_from_fork+0x1f/0x40 ... [20976.438030] task:ip state:D stack: 0 pid:213658 ppid:213627 flags:0x00004084 [20976.446469] Call Trace: [20976.448921] __schedule+0x2d1/0x830 [20976.452414] schedule+0x35/0xa0 [20976.455559] schedule_preempt_disabled+0xa/0x10 [20976.460090] __mutex_lock.isra.7+0x310/0x420 [20976.464364] device_del+0x36/0x3c0 [20976.467772] ice_unplug_aux_dev+0x1a/0x40 [ice] [20976.472313] ice_lag_event_handler+0x2a2/0x520 [ice] [20976.477288] notifier_call_chain+0x47/0x70 [20976.481386] __netdev_upper_dev_link+0x18b/0x280 [20976.489845] bond_enslave+0xe05/0x1790 [bonding] [20976.494475] do_setlink+0x336/0xf50 [20976.502517] __rtnl_newlink+0x529/0x8b0 [20976.543441] rtnl_newlink+0x43/0x60 [20976.546934] rtnetlink_rcv_msg+0x2b1/0x360 [20976.559238] netlink_rcv_skb+0x4c/0x120 [20976.563079] netlink_unicast+0x196/0x230 [20976.567005] netlink_sendmsg+0x204/0x3d0 [20976.570930] sock_sendmsg+0x4c/0x50 [20976.574423] ____sys_sendmsg+0x1eb/0x250 [20976.586807] ___sys_sendmsg+0x7c/0xc0 [20976.606353] __sys_sendmsg+0x57/0xa0 [20976.609930] do_syscall_64+0x5b/0x1a0 [20976.613598] entry_SYSCALL_64_after_hwframe+0x65/0xca 1. Command 'ip link ... set nomaster' causes that ice_plug_aux_dev() is called from ice_service_task() context, aux device is created and associated device->lock is taken. 2. Command 'ip link ... set master...' calls ice's notifier under RTNL lock and that notifier calls ice_unplug_aux_dev(). That function tries to take aux device->lock but this is already taken by ice_plug_aux_dev() in step 1 3. Later ice_plug_aux_dev() tries to take RTNL lock but this is already taken in step 2 4. Dead-lock The patch fixes this issue by following changes: - Bit ICE_FLAG_PLUG_AUX_DEV is kept to be set during ice_plug_aux_dev() call in ice_service_task() - The bit is checked in ice_clear_rdma_cap() and only if it is not set then ice_unplug_aux_dev() is called. If it is set (in other words plugging of aux device was requested and ice_plug_aux_dev() is potentially running) then the function only clears the bit - Once ice_plug_aux_dev() call (in ice_service_task) is finished the bit ICE_FLAG_PLUG_AUX_DEV is cleared but it is also checked whether it was already cleared by ice_clear_rdma_cap(). If so then aux device is unplugged. Signed-off-by: Ivan Vecera Co-developed-by: Petr Oros Signed-off-by: Petr Oros Reviewed-by: Dave Ertman Link: https://lore.kernel.org/r/20220310171641.3863659-1-ivecera@redhat.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ice/ice.h | 11 ++++++++++- drivers/net/ethernet/intel/ice/ice_main.c | 12 +++++++++++- 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/intel/ice') diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 3121f9b04f59..bea1d1e39fa2 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -898,7 +898,16 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf) */ static inline void ice_clear_rdma_cap(struct ice_pf *pf) { - ice_unplug_aux_dev(pf); + /* We can directly unplug aux device here only if the flag bit + * ICE_FLAG_PLUG_AUX_DEV is not set because ice_unplug_aux_dev() + * could race with ice_plug_aux_dev() called from + * ice_service_task(). In this case we only clear that bit now and + * aux device will be unplugged later once ice_plug_aux_device() + * called from ice_service_task() finishes (see ice_service_task()). + */ + if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_unplug_aux_dev(pf); + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); clear_bit(ICE_FLAG_AUX_ENA, pf->flags); } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 83e3e8aae6cf..493942e910be 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2255,9 +2255,19 @@ static void ice_service_task(struct work_struct *work) return; } - if (test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + if (test_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) { + /* Plug aux device per request */ ice_plug_aux_dev(pf); + /* Mark plugging as done but check whether unplug was + * requested during ice_plug_aux_dev() call + * (e.g. from ice_clear_rdma_cap()) and if so then + * plug aux device. + */ + if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_unplug_aux_dev(pf); + } + if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) { struct iidc_event *event; -- cgit v1.2.3