Merge branch 'ice-vf-resource-tracking'

Jacob Keller says:

====================
Intel Wired LAN Driver Updates 2023-10-19 (ice, igb, ixgbe)

This series contains improvements to the ice driver related to VF MSI-X
resource tracking, as well as other minor cleanups.

Dan fixes code in igb and ixgbe where the conversion to list_for_each_entry
failed to account for logic which assumed a NULL pointer after iteration.

Jacob makes ice_get_pf_c827_idx static, and refactors ice_find_netlist_node
based on feedback that got missed before the function merged.

Michal adds a switch rule to drop all traffic received by an inactive LAG
port. He also implements ops to allow individual control of MSI-X vectors
for SR-IOV VFs.

Przemek removes some unused fields in struct ice_flow_entry, and modifies
the ice driver to cache the VF PCI device inside struct ice_vf rather than
performing lookup at run time.
====================

Signed-off-by: David S. Miller <[email protected]>

18 files changed, 398 insertions, 108 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 988b177d9388..351e0d36df44 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -554,6 +554,8 @@ struct ice_pf {
 	 * MSIX vectors allowed on this PF.
 	 */
 	u16 sriov_base_vector;
+	unsigned long *sriov_irq_bm;	/* bitmap to track irq usage */
+	u16 sriov_irq_size;		/* size of the irq_bm bitmap */
 
 	u16 ctrl_vsi_idx;		/* control VSI index in pf->vsi array */
 
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 8cbe63401378..377fae41bbae 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -473,41 +473,41 @@ ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd,
  * @node_part_number: node part number to look for
  * @node_handle: output parameter if node found - optional
  *
- * Find and return the node handle for a given node type and part number in the
- * netlist. When found ICE_SUCCESS is returned, ICE_ERR_DOES_NOT_EXIST
- * otherwise. If node_handle provided, it would be set to found node handle.
+ * Scan the netlist for a node handle of the given node type and part number.
+ *
+ * If node_handle is non-NULL it will be modified on function exit. It is only
+ * valid if the function returns zero, and should be ignored on any non-zero
+ * return value.
+ *
+ * Returns: 0 if the node is found, -ENOENT if no handle was found, and
+ * a negative error code on failure to access the AQ.
  */
 static int ice_find_netlist_node(struct ice_hw *hw, u8 node_type_ctx,
 				 u8 node_part_number, u16 *node_handle)
 {
-	struct ice_aqc_get_link_topo cmd;
-	u8 rec_node_part_number;
-	u16 rec_node_handle;
 	u8 idx;
 
 	for (idx = 0; idx < ICE_MAX_NETLIST_SIZE; idx++) {
+		struct ice_aqc_get_link_topo cmd = {};
+		u8 rec_node_part_number;
 		int status;
 
-		memset(&cmd, 0, sizeof(cmd));
-
 		cmd.addr.topo_params.node_type_ctx =
-			(node_type_ctx << ICE_AQC_LINK_TOPO_NODE_TYPE_S);
+			FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M,
+				   node_type_ctx);
 		cmd.addr.topo_params.index = idx;
 
 		status = ice_aq_get_netlist_node(hw, &cmd,
 						 &rec_node_part_number,
-						 &rec_node_handle);
+						 node_handle);
 		if (status)
 			return status;
 
-		if (rec_node_part_number == node_part_number) {
-			if (node_handle)
-				*node_handle = rec_node_handle;
+		if (rec_node_part_number == node_part_number)
 			return 0;
-		}
 	}
 
-	return -ENOTBLK;
+	return -ENOENT;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
index 67bfd1f61cdd..6ae0269bdf73 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c
@@ -73,7 +73,7 @@ ice_eswitch_br_ingress_rule_setup(struct ice_adv_rule_info *rule_info,
 	rule_info->sw_act.vsi_handle = vf_vsi_idx;
 	rule_info->sw_act.flag |= ICE_FLTR_RX;
 	rule_info->sw_act.src = pf_id;
-	rule_info->priority = 5;
+	rule_info->priority = 2;
 }
 
 static void
@@ -84,7 +84,7 @@ ice_eswitch_br_egress_rule_setup(struct ice_adv_rule_info *rule_info,
 	rule_info->sw_act.flag |= ICE_FLTR_TX;
 	rule_info->flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE;
 	rule_info->flags_info.act_valid = true;
-	rule_info->priority = 5;
+	rule_info->priority = 2;
 }
 
 static int
@@ -207,7 +207,7 @@ ice_eswitch_br_guard_rule_create(struct ice_hw *hw, u16 vsi_idx,
 	rule_info.allow_pass_l2 = true;
 	rule_info.sw_act.vsi_handle = vsi_idx;
 	rule_info.sw_act.fltr_act = ICE_NOP;
-	rule_info.priority = 5;
+	rule_info.priority = 2;
 
 	err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule);
 	if (err)
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
index 85cca572c22a..fb8b925aaf8b 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.c
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -1318,7 +1318,6 @@ ice_flow_rem_entry_sync(struct ice_hw *hw, enum ice_block __always_unused blk,
 
 	list_del(&entry->l_entry);
 
-	devm_kfree(ice_hw_to_dev(hw), entry->entry);
 	devm_kfree(ice_hw_to_dev(hw), entry);
 
 	return 0;
@@ -1645,10 +1644,8 @@ ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id,
 	*entry_h = ICE_FLOW_ENTRY_HNDL(e);
 
 out:
-	if (status && e) {
-		devm_kfree(ice_hw_to_dev(hw), e->entry);
+	if (status)
 		devm_kfree(ice_hw_to_dev(hw), e);
-	}
 
 	return status;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index b465d27d9b80..96923ef0a5a8 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -350,11 +350,8 @@ struct ice_flow_entry {
 
 	u64 id;
 	struct ice_flow_prof *prof;
-	/* Flow entry's content */
-	void *entry;
 	enum ice_flow_priority priority;
 	u16 vsi_handle;
-	u16 entry_sz;
 };
 
 #define ICE_FLOW_ENTRY_HNDL(e)	((u64)(uintptr_t)e)
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 165a9d512ce2..b980f89dc892 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -19,8 +19,11 @@ static const u8 lacp_train_pkt[LACP_TRAIN_PKT_LEN] = { 0, 0, 0, 0, 0, 0,
 static const u8 ice_dflt_vsi_rcp[ICE_RECIPE_LEN] = {
 	0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 	0x85, 0, 0x01, 0, 0, 0, 0xff, 0xff, 0x08, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0x30, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
+	0, 0, 0, 0, 0, 0, 0x30 };
+static const u8 ice_lport_rcp[ICE_RECIPE_LEN] = {
+	0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	0x85, 0, 0x16, 0, 0, 0, 0xff, 0xff, 0x07, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0x30 };
 
 /**
  * ice_lag_set_primary - set PF LAG state as Primary
@@ -173,18 +176,22 @@ static struct ice_lag *ice_lag_find_primary(struct ice_lag *lag)
 }
 
 /**
- * ice_lag_cfg_dflt_fltr - Add/Remove default VSI rule for LAG
+ * ice_lag_cfg_fltr - Add/Remove rule for LAG
  * @lag: lag struct for local interface
+ * @act: rule action
+ * @recipe_id: recipe id for the new rule
+ * @rule_idx: pointer to rule index
  * @add: boolean on whether we are adding filters
  */
 static int
-ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add)
+ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx,
+		 bool add)
 {
 	struct ice_sw_rule_lkup_rx_tx *s_rule;
 	u16 s_rule_sz, vsi_num;
 	struct ice_hw *hw;
-	u32 act, opc;
 	u8 *eth_hdr;
+	u32 opc;
 	int err;
 
 	hw = &lag->pf->hw;
@@ -193,7 +200,7 @@ ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add)
 	s_rule_sz = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule);
 	s_rule = kzalloc(s_rule_sz, GFP_KERNEL);
 	if (!s_rule) {
-		dev_err(ice_pf_to_dev(lag->pf), "error allocating rule for LAG default VSI\n");
+		dev_err(ice_pf_to_dev(lag->pf), "error allocating rule for LAG\n");
 		return -ENOMEM;
 	}
 
@@ -201,19 +208,17 @@ ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add)
 		eth_hdr = s_rule->hdr_data;
 		ice_fill_eth_hdr(eth_hdr);
 
-		act = (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) &
+		act |= (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) &
 			ICE_SINGLE_ACT_VSI_ID_M;
-		act |= ICE_SINGLE_ACT_VSI_FORWARDING |
-			ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE;
 
 		s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX);
-		s_rule->recipe_id = cpu_to_le16(lag->pf_recipe);
+		s_rule->recipe_id = cpu_to_le16(recipe_id);
 		s_rule->src = cpu_to_le16(hw->port_info->lport);
 		s_rule->act = cpu_to_le32(act);
 		s_rule->hdr_len = cpu_to_le16(DUMMY_ETH_HDR_LEN);
 		opc = ice_aqc_opc_add_sw_rules;
 	} else {
-		s_rule->index = cpu_to_le16(lag->pf_rule_id);
+		s_rule->index = cpu_to_le16(*rule_idx);
 		opc = ice_aqc_opc_remove_sw_rules;
 	}
 
@@ -222,9 +227,9 @@ ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add)
 		goto dflt_fltr_free;
 
 	if (add)
-		lag->pf_rule_id = le16_to_cpu(s_rule->index);
+		*rule_idx = le16_to_cpu(s_rule->index);
 	else
-		lag->pf_rule_id = 0;
+		*rule_idx = 0;
 
 dflt_fltr_free:
 	kfree(s_rule);
@@ -232,6 +237,37 @@ dflt_fltr_free:
 }
 
 /**
+ * ice_lag_cfg_dflt_fltr - Add/Remove default VSI rule for LAG
+ * @lag: lag struct for local interface
+ * @add: boolean on whether to add filter
+ */
+static int
+ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add)
+{
+	u32 act = ICE_SINGLE_ACT_VSI_FORWARDING |
+		ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE;
+
+	return ice_lag_cfg_fltr(lag, act, lag->pf_recipe,
+				&lag->pf_rule_id, add);
+}
+
+/**
+ * ice_lag_cfg_drop_fltr - Add/Remove lport drop rule
+ * @lag: lag struct for local interface
+ * @add: boolean on whether to add filter
+ */
+static int
+ice_lag_cfg_drop_fltr(struct ice_lag *lag, bool add)
+{
+	u32 act = ICE_SINGLE_ACT_VSI_FORWARDING |
+		  ICE_SINGLE_ACT_VALID_BIT |
+		  ICE_SINGLE_ACT_DROP;
+
+	return ice_lag_cfg_fltr(lag, act, lag->lport_recipe,
+				&lag->lport_rule_idx, add);
+}
+
+/**
  * ice_lag_cfg_pf_fltrs - set filters up for new active port
  * @lag: local interfaces lag struct
  * @ptr: opaque data containing notifier event
@@ -257,13 +293,18 @@ ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr)
 	if (bonding_info->slave.state && lag->pf_rule_id) {
 		if (ice_lag_cfg_dflt_fltr(lag, false))
 			dev_err(dev, "Error removing old default VSI filter\n");
+		if (ice_lag_cfg_drop_fltr(lag, true))
+			dev_err(dev, "Error adding new drop filter\n");
 		return;
 	}
 
 	/* interface becoming active - add new default VSI rule */
-	if (!bonding_info->slave.state && !lag->pf_rule_id)
+	if (!bonding_info->slave.state && !lag->pf_rule_id) {
 		if (ice_lag_cfg_dflt_fltr(lag, true))
 			dev_err(dev, "Error adding new default VSI filter\n");
+		if (lag->lport_rule_idx && ice_lag_cfg_drop_fltr(lag, false))
+			dev_err(dev, "Error removing old drop filter\n");
+	}
 }
 
 /**
@@ -1179,6 +1220,7 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr)
 			swid = primary_lag->pf->hw.port_info->sw_id;
 			ice_lag_set_swid(swid, lag, true);
 			ice_lag_add_prune_list(primary_lag, lag->pf);
+			ice_lag_cfg_drop_fltr(lag, true);
 		}
 		/* add filter for primary control packets */
 		ice_lag_cfg_cp_fltr(lag, true);
@@ -1929,11 +1971,16 @@ int ice_init_lag(struct ice_pf *pf)
 		goto lag_error;
 	}
 
-	err = ice_create_lag_recipe(&pf->hw, &lag->pf_recipe, ice_dflt_vsi_rcp,
-				    1);
+	err = ice_create_lag_recipe(&pf->hw, &lag->pf_recipe,
+				    ice_dflt_vsi_rcp, 1);
 	if (err)
 		goto lag_error;
 
+	err = ice_create_lag_recipe(&pf->hw, &lag->lport_recipe,
+				    ice_lport_rcp, 3);
+	if (err)
+		goto free_rcp_res;
+
 	/* associate recipes to profiles */
 	for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) {
 		err = ice_aq_get_recipe_to_profile(&pf->hw, n,
@@ -1942,7 +1989,8 @@ int ice_init_lag(struct ice_pf *pf)
 			continue;
 
 		if (recipe_bits & BIT(ICE_SW_LKUP_DFLT)) {
-			recipe_bits |= BIT(lag->pf_recipe);
+			recipe_bits |= BIT(lag->pf_recipe) |
+				       BIT(lag->lport_recipe);
 			ice_aq_map_recipe_to_profile(&pf->hw, n,
 						     (u8 *)&recipe_bits, NULL);
 		}
@@ -1953,6 +2001,9 @@ int ice_init_lag(struct ice_pf *pf)
 	dev_dbg(dev, "INIT LAG complete\n");
 	return 0;
 
+free_rcp_res:
+	ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1,
+			&pf->lag->pf_recipe);
 lag_error:
 	kfree(lag);
 	pf->lag = NULL;
@@ -1982,6 +2033,8 @@ void ice_deinit_lag(struct ice_pf *pf)
 
 	ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1,
 			&pf->lag->pf_recipe);
+	ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1,
+			&pf->lag->lport_recipe);
 
 	kfree(lag);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h
index facb6c894b6d..9557e8605a07 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.h
+++ b/drivers/net/ethernet/intel/ice/ice_lag.h
@@ -39,8 +39,10 @@ struct ice_lag {
 	u8 bonded:1; /* currently bonded */
 	u8 primary:1; /* this is primary */
 	u16 pf_recipe;
+	u16 lport_recipe;
 	u16 pf_rule_id;
 	u16 cp_rule_idx;
+	u16 lport_rule_idx;
 	u8 role;
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index f61002273c30..4b1e56396293 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -229,7 +229,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 		 * of queues vectors, subtract 1 (ICE_NONQ_VECS_VF) from the
 		 * original vector count
 		 */
-		vsi->num_q_vectors = pf->vfs.num_msix_per - ICE_NONQ_VECS_VF;
+		vsi->num_q_vectors = vf->num_msix - ICE_NONQ_VECS_VF;
 		break;
 	case ICE_VSI_CTRL:
 		vsi->alloc_txq = 1;
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c528675d4c82..b67c806a5a4d 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5541,7 +5541,7 @@ static void ice_pci_err_resume(struct pci_dev *pdev)
 		return;
 	}
 
-	ice_restore_all_vfs_msi_state(pdev);
+	ice_restore_all_vfs_msi_state(pf);
 
 	ice_do_reset(pf, ICE_RESET_PFR);
 	ice_service_task_restart(pf);
@@ -5635,6 +5635,8 @@ static struct pci_driver ice_driver = {
 #endif /* CONFIG_PM */
 	.shutdown = ice_shutdown,
 	.sriov_configure = ice_sriov_configure,
+	.sriov_get_vf_total_msix = ice_sriov_get_vf_total_msix,
+	.sriov_set_msix_vec_count = ice_sriov_set_msix_vec_count,
 	.err_handler = &ice_pci_err_handler
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index de16cf14c4b2..6d573908de7a 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -3564,7 +3564,7 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx)
  * * 0 - success
  * * negative - failure
  */
-int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx)
+static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx)
 {
 	struct ice_aqc_get_link_topo cmd;
 	u8 node_part_number;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 18a993134826..36aeeef99ec0 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -271,7 +271,6 @@ int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data);
 int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data);
 int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data);
 bool ice_is_pca9575_present(struct ice_hw *hw);
-int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx);
 enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input);
 struct dpll_pin_frequency *
 ice_cgu_get_pin_freq_supp(struct ice_hw *hw, u8 pin, bool input, u8 *num);
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index 31314e7540f8..2a5e6616cc0a 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -64,7 +64,7 @@ static void ice_free_vf_res(struct ice_vf *vf)
 		vf->num_mac = 0;
 	}
 
-	last_vector_idx = vf->first_vector_idx + pf->vfs.num_msix_per - 1;
+	last_vector_idx = vf->first_vector_idx + vf->num_msix - 1;
 
 	/* clear VF MDD event information */
 	memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events));
@@ -102,7 +102,7 @@ static void ice_dis_vf_mappings(struct ice_vf *vf)
 	wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0);
 
 	first = vf->first_vector_idx;
-	last = first + pf->vfs.num_msix_per - 1;
+	last = first + vf->num_msix - 1;
 	for (v = first; v <= last; v++) {
 		u32 reg;
 
@@ -138,6 +138,8 @@ static int ice_sriov_free_msix_res(struct ice_pf *pf)
 	if (!pf)
 		return -EINVAL;
 
+	bitmap_free(pf->sriov_irq_bm);
+	pf->sriov_irq_size = 0;
 	pf->sriov_base_vector = 0;
 
 	return 0;
@@ -244,22 +246,6 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf)
 	return vsi;
 }
 
-/**
- * ice_calc_vf_first_vector_idx - Calculate MSIX vector index in the PF space
- * @pf: pointer to PF structure
- * @vf: pointer to VF that the first MSIX vector index is being calculated for
- *
- * This returns the first MSIX vector index in PF space that is used by this VF.
- * This index is used when accessing PF relative registers such as
- * GLINT_VECT2FUNC and GLINT_DYN_CTL.
- * This will always be the OICR index in the AVF driver so any functionality
- * using vf->first_vector_idx for queue configuration will have to increment by
- * 1 to avoid meddling with the OICR index.
- */
-static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf)
-{
-	return pf->sriov_base_vector + vf->vf_id * pf->vfs.num_msix_per;
-}
 
 /**
  * ice_ena_vf_msix_mappings - enable VF MSIX mappings in hardware
@@ -280,12 +266,12 @@ static void ice_ena_vf_msix_mappings(struct ice_vf *vf)
 
 	hw = &pf->hw;
 	pf_based_first_msix = vf->first_vector_idx;
-	pf_based_last_msix = (pf_based_first_msix + pf->vfs.num_msix_per) - 1;
+	pf_based_last_msix = (pf_based_first_msix + vf->num_msix) - 1;
 
 	device_based_first_msix = pf_based_first_msix +
 		pf->hw.func_caps.common_cap.msix_vector_first_id;
 	device_based_last_msix =
-		(device_based_first_msix + pf->vfs.num_msix_per) - 1;
+		(device_based_first_msix + vf->num_msix) - 1;
 	device_based_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
 
 	reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) &
@@ -527,6 +513,52 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 }
 
 /**
+ * ice_sriov_get_irqs - get irqs for SR-IOV usacase
+ * @pf: pointer to PF structure
+ * @needed: number of irqs to get
+ *
+ * This returns the first MSI-X vector index in PF space that is used by this
+ * VF. This index is used when accessing PF relative registers such as
+ * GLINT_VECT2FUNC and GLINT_DYN_CTL.
+ * This will always be the OICR index in the AVF driver so any functionality
+ * using vf->first_vector_idx for queue configuration_id: id of VF which will
+ * use this irqs
+ *
+ * Only SRIOV specific vectors are tracked in sriov_irq_bm. SRIOV vectors are
+ * allocated from the end of global irq index. First bit in sriov_irq_bm means
+ * last irq index etc. It simplifies extension of SRIOV vectors.
+ * They will be always located from sriov_base_vector to the last irq
+ * index. While increasing/decreasing sriov_base_vector can be moved.
+ */
+static int ice_sriov_get_irqs(struct ice_pf *pf, u16 needed)
+{
+	int res = bitmap_find_next_zero_area(pf->sriov_irq_bm,
+					     pf->sriov_irq_size, 0, needed, 0);
+	/* conversion from number in bitmap to global irq index */
+	int index = pf->sriov_irq_size - res - needed;
+
+	if (res >= pf->sriov_irq_size || index < pf->sriov_base_vector)
+		return -ENOENT;
+
+	bitmap_set(pf->sriov_irq_bm, res, needed);
+	return index;
+}
+
+/**
+ * ice_sriov_free_irqs - free irqs used by the VF
+ * @pf: pointer to PF structure
+ * @vf: pointer to VF structure
+ */
+static void ice_sriov_free_irqs(struct ice_pf *pf, struct ice_vf *vf)
+{
+	/* Move back from first vector index to first index in bitmap */
+	int bm_i = pf->sriov_irq_size - vf->first_vector_idx - vf->num_msix;
+
+	bitmap_clear(pf->sriov_irq_bm, bm_i, vf->num_msix);
+	vf->first_vector_idx = 0;
+}
+
+/**
  * ice_init_vf_vsi_res - initialize/setup VF VSI resources
  * @vf: VF to initialize/setup the VSI for
  *
@@ -539,7 +571,9 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf)
 	struct ice_vsi *vsi;
 	int err;
 
-	vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf);
+	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+	if (vf->first_vector_idx < 0)
+		return -ENOMEM;
 
 	vsi = ice_vf_vsi_setup(vf);
 	if (!vsi)
@@ -789,14 +823,19 @@ static const struct ice_vf_ops ice_sriov_vf_ops = {
  */
 static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs)
 {
+	struct pci_dev *pdev = pf->pdev;
 	struct ice_vfs *vfs = &pf->vfs;
+	struct pci_dev *vfdev = NULL;
 	struct ice_vf *vf;
-	u16 vf_id;
-	int err;
+	u16 vf_pdev_id;
+	int err, pos;
 
 	lockdep_assert_held(&vfs->table_lock);
 
-	for (vf_id = 0; vf_id < num_vfs; vf_id++) {
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
+	pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_pdev_id);
+
+	for (u16 vf_id = 0; vf_id < num_vfs; vf_id++) {
 		vf = kzalloc(sizeof(*vf), GFP_KERNEL);
 		if (!vf) {
 			err = -ENOMEM;
@@ -812,11 +851,28 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs)
 
 		ice_initialize_vf_entry(vf);
 
+		do {
+			vfdev = pci_get_device(pdev->vendor, vf_pdev_id, vfdev);
+		} while (vfdev && vfdev->physfn != pdev);
+		vf->vfdev = vfdev;
 		vf->vf_sw_id = pf->first_sw;
 
+		pci_dev_get(vfdev);
+
+		/* set default number of MSI-X */
+		vf->num_msix = pf->vfs.num_msix_per;
+		vf->num_vf_qs = pf->vfs.num_qps_per;
+		ice_vc_set_default_allowlist(vf);
+
 		hash_add_rcu(vfs->table, &vf->entry, vf_id);
 	}
 
+	/* Decrement of refcount done by pci_get_device() inside the loop does
+	 * not touch the last iteration's vfdev, so it has to be done manually
+	 * to balance pci_dev_get() added within the loop.
+	 */
+	pci_dev_put(vfdev);
+
 	return 0;
 
 err_free_entries:
@@ -831,10 +887,16 @@ err_free_entries:
  */
 static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
 {
+	int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	int ret;
 
+	pf->sriov_irq_bm = bitmap_zalloc(total_vectors, GFP_KERNEL);
+	if (!pf->sriov_irq_bm)
+		return -ENOMEM;
+	pf->sriov_irq_size = total_vectors;
+
 	/* Disable global interrupt 0 so we don't try to handle the VFLR. */
 	wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index),
 	     ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S);
@@ -893,6 +955,7 @@ err_unroll_intr:
 	/* rearm interrupts here */
 	ice_irq_dynamic_ena(hw, NULL, NULL);
 	clear_bit(ICE_OICR_INTR_DIS, pf->state);
+	bitmap_free(pf->sriov_irq_bm);
 	return ret;
 }
 
@@ -957,6 +1020,175 @@ static int ice_check_sriov_allowed(struct ice_pf *pf)
 }
 
 /**
+ * ice_sriov_get_vf_total_msix - return number of MSI-X used by VFs
+ * @pdev: pointer to pci_dev struct
+ *
+ * The function is called via sysfs ops
+ */
+u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev)
+{
+	struct ice_pf *pf = pci_get_drvdata(pdev);
+
+	return pf->sriov_irq_size - ice_get_max_used_msix_vector(pf);
+}
+
+static int ice_sriov_move_base_vector(struct ice_pf *pf, int move)
+{
+	if (pf->sriov_base_vector - move < ice_get_max_used_msix_vector(pf))
+		return -ENOMEM;
+
+	pf->sriov_base_vector -= move;
+	return 0;
+}
+
+static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id)
+{
+	u16 vf_ids[ICE_MAX_SRIOV_VFS];
+	struct ice_vf *tmp_vf;
+	int to_remap = 0, bkt;
+
+	/* For better irqs usage try to remap irqs of VFs
+	 * that aren't running yet
+	 */
+	ice_for_each_vf(pf, bkt, tmp_vf) {
+		/* skip VF which is changing the number of MSI-X */
+		if (restricted_id == tmp_vf->vf_id ||
+		    test_bit(ICE_VF_STATE_ACTIVE, tmp_vf->vf_states))
+			continue;
+
+		ice_dis_vf_mappings(tmp_vf);
+		ice_sriov_free_irqs(pf, tmp_vf);
+
+		vf_ids[to_remap] = tmp_vf->vf_id;
+		to_remap += 1;
+	}
+
+	for (int i = 0; i < to_remap; i++) {
+		tmp_vf = ice_get_vf_by_id(pf, vf_ids[i]);
+		if (!tmp_vf)
+			continue;
+
+		tmp_vf->first_vector_idx =
+			ice_sriov_get_irqs(pf, tmp_vf->num_msix);
+		/* there is no need to rebuild VSI as we are only changing the
+		 * vector indexes not amount of MSI-X or queues
+		 */
+		ice_ena_vf_mappings(tmp_vf);
+		ice_put_vf(tmp_vf);
+	}
+}
+
+/**
+ * ice_sriov_set_msix_vec_count
+ * @vf_dev: pointer to pci_dev struct of VF device
+ * @msix_vec_count: new value for MSI-X amount on this VF
+ *
+ * Set requested MSI-X, queues and registers for @vf_dev.
+ *
+ * First do some sanity checks like if there are any VFs, if the new value
+ * is correct etc. Then disable old mapping (MSI-X and queues registers), change
+ * MSI-X and queues, rebuild VSI and enable new mapping.
+ *
+ * If it is possible (driver not binded to VF) try to remap also other VFs to
+ * linearize irqs register usage.
+ */
+int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
+{
+	struct pci_dev *pdev = pci_physfn(vf_dev);
+	struct ice_pf *pf = pci_get_drvdata(pdev);
+	u16 prev_msix, prev_queues, queues;
+	bool needs_rebuild = false;
+	struct ice_vf *vf;
+	int id;
+
+	if (!ice_get_num_vfs(pf))
+		return -ENOENT;
+
+	if (!msix_vec_count)
+		return 0;
+
+	queues = msix_vec_count;
+	/* add 1 MSI-X for OICR */
+	msix_vec_count += 1;
+
+	if (queues > min(ice_get_avail_txq_count(pf),
+			 ice_get_avail_rxq_count(pf)))
+		return -EINVAL;
+
+	if (msix_vec_count < ICE_MIN_INTR_PER_VF)
+		return -EINVAL;
+
+	/* Transition of PCI VF function number to function_id */
+	for (id = 0; id < pci_num_vf(pdev); id++) {
+		if (vf_dev->devfn == pci_iov_virtfn_devfn(pdev, id))
+			break;
+	}
+
+	if (id == pci_num_vf(pdev))
+		return -ENOENT;
+
+	vf = ice_get_vf_by_id(pf, id);
+
+	if (!vf)
+		return -ENOENT;
+
+	prev_msix = vf->num_msix;
+	prev_queues = vf->num_vf_qs;
+
+	if (ice_sriov_move_base_vector(pf, msix_vec_count - prev_msix)) {
+		ice_put_vf(vf);
+		return -ENOSPC;
+	}
+
+	ice_dis_vf_mappings(vf);
+	ice_sriov_free_irqs(pf, vf);
+
+	/* Remap all VFs beside the one is now configured */
+	ice_sriov_remap_vectors(pf, vf->vf_id);
+
+	vf->num_msix = msix_vec_count;
+	vf->num_vf_qs = queues;
+	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+	if (vf->first_vector_idx < 0)
+		goto unroll;
+
+	ice_vf_vsi_release(vf);
+	if (vf->vf_ops->create_vsi(vf)) {
+		/* Try to rebuild with previous values */
+		needs_rebuild = true;
+		goto unroll;
+	}
+
+	dev_info(ice_pf_to_dev(pf),
+		 "Changing VF %d resources to %d vectors and %d queues\n",
+		 vf->vf_id, vf->num_msix, vf->num_vf_qs);
+
+	ice_ena_vf_mappings(vf);
+	ice_put_vf(vf);
+
+	return 0;
+
+unroll:
+	dev_info(ice_pf_to_dev(pf),
+		 "Can't set %d vectors on VF %d, falling back to %d\n",
+		 vf->num_msix, vf->vf_id, prev_msix);
+
+	vf->num_msix = prev_msix;
+	vf->num_vf_qs = prev_queues;
+	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+	if (vf->first_vector_idx < 0)
+		return -EINVAL;
+
+	if (needs_rebuild)
+		vf->vf_ops->create_vsi(vf);
+
+	ice_ena_vf_mappings(vf);
+	ice_put_vf(vf);
+
+	return -EINVAL;
+}
+
+/**
  * ice_sriov_configure - Enable or change number of VFs via sysfs
  * @pdev: pointer to a pci_dev structure
  * @num_vfs: number of VFs to allocate or 0 to free VFs
@@ -1709,31 +1941,16 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf)
 
 /**
  * ice_restore_all_vfs_msi_state - restore VF MSI state after PF FLR
- * @pdev: pointer to a pci_dev structure
+ * @pf: pointer to the PF structure
  *
  * Called when recovering from a PF FLR to restore interrupt capability to
  * the VFs.
  */
-void ice_restore_all_vfs_msi_state(struct pci_dev *pdev)
+void ice_restore_all_vfs_msi_state(struct ice_pf *pf)
 {
-	u16 vf_id;
-	int pos;
-
-	if (!pci_num_vf(pdev))
-		return;
+	struct ice_vf *vf;
+	u32 bkt;
 
-	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV);
-	if (pos) {
-		struct pci_dev *vfdev;
-
-		pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID,
-				     &vf_id);
-		vfdev = pci_get_device(pdev->vendor, vf_id, NULL);
-		while (vfdev) {
-			if (vfdev->is_virtfn && vfdev->physfn == pdev)
-				pci_restore_msi_state(vfdev);
-			vfdev = pci_get_device(pdev->vendor, vf_id,
-					       vfdev);
-		}
-	}
+	ice_for_each_vf(pf, bkt, vf)
+		pci_restore_msi_state(vf->vfdev);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h
index 346cb2666f3a..8488df38b586 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.h
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.h
@@ -33,7 +33,7 @@ int
 ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi);
 
 void ice_free_vfs(struct ice_pf *pf);
-void ice_restore_all_vfs_msi_state(struct pci_dev *pdev);
+void ice_restore_all_vfs_msi_state(struct ice_pf *pf);
 
 int
 ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos,
@@ -60,6 +60,8 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf);
 void ice_print_vf_rx_mdd_event(struct ice_vf *vf);
 bool
 ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto);
+u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev);
+int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count);
 #else /* CONFIG_PCI_IOV */
 static inline void ice_process_vflr_event(struct ice_pf *pf) { }
 static inline void ice_free_vfs(struct ice_pf *pf) { }
@@ -67,7 +69,7 @@ static inline
 void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { }
 static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { }
 static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { }
-static inline void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { }
+static inline void ice_restore_all_vfs_msi_state(struct ice_pf *pf) { }
 
 static inline int
 ice_sriov_configure(struct pci_dev __always_unused *pdev,
@@ -142,5 +144,16 @@ ice_get_vf_stats(struct net_device __always_unused *netdev,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev)
+{
+	return 0;
+}
+
+static inline int
+ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_PCI_IOV */
 #endif /* _ICE_SRIOV_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 24e4f4d897b6..aca1f2ea5034 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -56,6 +56,8 @@ static void ice_release_vf(struct kref *ref)
 {
 	struct ice_vf *vf = container_of(ref, struct ice_vf, refcnt);
 
+	pci_dev_put(vf->vfdev);
+
 	vf->vf_ops->free(vf);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
index 31a082e8a827..93c774f2f437 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
@@ -72,7 +72,7 @@ struct ice_vfs {
 	struct mutex table_lock;	/* Lock for protecting the hash table */
 	u16 num_supported;		/* max supported VFs on this PF */
 	u16 num_qps_per;		/* number of queue pairs per VF */
-	u16 num_msix_per;		/* number of MSI-X vectors per VF */
+	u16 num_msix_per;		/* default MSI-X vectors per VF */
 	unsigned long last_printed_mdd_jiffies;	/* MDD message rate limit */
 };
 
@@ -82,7 +82,7 @@ struct ice_vf {
 	struct rcu_head rcu;
 	struct kref refcnt;
 	struct ice_pf *pf;
-
+	struct pci_dev *vfdev;
 	/* Used during virtchnl message handling and NDO ops against the VF
 	 * that will trigger a VFR
 	 */
@@ -136,6 +136,8 @@ struct ice_vf {
 
 	/* devlink port data */
 	struct devlink_port devlink_port;
+
+	u16 num_msix;			/* num of MSI-X configured on this VF */
 };
 
 /* Flags for controlling behavior of ice_reset_vf */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 01e88b6e43a1..cdf17b1e2f25 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -501,7 +501,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	vfres->num_vsis = 1;
 	/* Tx and Rx queue are equal for VF */
 	vfres->num_queue_pairs = vsi->num_txq;
-	vfres->max_vectors = vf->pf->vfs.num_msix_per;
+	vfres->max_vectors = vf->num_msix;
 	vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE;
 	vfres->rss_lut_size = ICE_LUT_VSI_SIZE;
 	vfres->max_mtu = ice_vc_get_max_frame_size(vf);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index db54453e1946..b2295caa2f0a 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -7856,7 +7856,8 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf,
 {
 	struct pci_dev *pdev = adapter->pdev;
 	struct vf_data_storage *vf_data = &adapter->vf_data[vf];
-	struct vf_mac_filter *entry = NULL;
+	struct vf_mac_filter *entry;
+	bool found = false;
 	int ret = 0;
 
 	if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) &&
@@ -7887,11 +7888,13 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf,
 	case E1000_VF_MAC_FILTER_ADD:
 		/* try to find empty slot in the list */
 		list_for_each_entry(entry, &adapter->vf_macs.l, l) {
-			if (entry->free)
+			if (entry->free) {
+				found = true;
 				break;
+			}
 		}
 
-		if (entry && entry->free) {
+		if (found) {
 			entry->free = false;
 			entry->vf = vf;
 			ether_addr_copy(entry->vf_mac, addr);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index cd593f5719e1..9cfdfa8a4355 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -640,6 +640,7 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter,
 				int vf, int index, unsigned char *mac_addr)
 {
 	struct vf_macvlans *entry;
+	bool found = false;
 	int retval = 0;
 
 	if (index <= 1) {
@@ -661,22 +662,22 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter,
 	if (!index)
 		return 0;
 
-	entry = NULL;
-
 	list_for_each_entry(entry, &adapter->vf_mvs.l, l) {
-		if (entry->free)
+		if (entry->free) {
+			found = true;
 			break;
+		}
 	}
 
 	/*
 	 * If we traversed the entire list and didn't find a free entry
-	 * then we're out of space on the RAR table.  Also entry may
-	 * be NULL because the original memory allocation for the list
-	 * failed, which is not fatal but does mean we can't support
-	 * VF requests for MACVLAN because we couldn't allocate
-	 * memory for the list management required.
+	 * then we're out of space on the RAR table.  It's also possible
+	 * for the &adapter->vf_mvs.l list to be empty because the original
+	 * memory allocation for the list failed, which is not fatal but does
+	 * mean we can't support VF requests for MACVLAN because we couldn't
+	 * allocate memory for the list management required.
 	 */
-	if (!entry || !entry->free)
+	if (!found)
 		return -ENOSPC;
 
 	retval = ixgbe_add_mac_filter(adapter, mac_addr, vf);