Merge remote-tracking branch 'torvalds/master' into perf/core

To pick up fixes that went thru perf/urgent.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

11 files changed, 77 insertions, 63 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index a9fa701aaa95..bea1d1e39fa2 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,
@@ -484,6 +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 */
 };
 
@@ -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_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)
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_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.
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 17a9bb461dc3..493942e910be 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);
 			}
 		}
 	}
@@ -2253,9 +2255,30 @@ 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;
+
+		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);
@@ -3021,7 +3044,7 @@ 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 */
@@ -6820,7 +6843,6 @@ 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;
 
@@ -6855,14 +6877,6 @@ 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 */
@@ -6870,21 +6884,18 @@ 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;
 }
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_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);
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);
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;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index 39b80124d282..1be3cd4b2bef 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);
 }
 
 /**
@@ -2170,24 +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) {
@@ -4625,10 +4619,6 @@ 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;
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;