Merge: ice: managing MSI-X in driver

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/522

JIRA: https://issues.redhat.com/browse/RHEL-80554

Patches are required for managing MSI-X in driver.

Signed-off-by: Petr Oros <poros@redhat.com>

Approved-by: Michal Schmidt <mschmidt@redhat.com>
Approved-by: Kamal Heib <kheib@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Julio Faracco <jfaracco@redhat.com>

Author: jcfaracco

Documentation/networking/devlink/ice.rst

@@ -69,6 +69,17 @@ Parameters
 
        To verify that value has been set:
        $ devlink dev param show pci/0000:16:00.0 name tx_scheduling_layers
+   * - ``msix_vec_per_pf_max``
+     - driverinit
+     - Set the max MSI-X that can be used by the PF, rest can be utilized for
+       SRIOV. The range is from min value set in msix_vec_per_pf_min to
+       2k/number of ports.
+   * - ``msix_vec_per_pf_min``
+     - driverinit
+     - Set the min MSI-X that will be used by the PF. This value inform how many
+       MSI-X will be allocated statically. The range is from 2 to value set
+       in msix_vec_per_pf_max.
+
 .. list-table:: Driver specific parameters implemented
     :widths: 5 5 90
 

drivers/infiniband/hw/irdma/hw.c

@@ -498,8 +498,6 @@ static int irdma_save_msix_info(struct irdma_pci_f *rf)
 	iw_qvlist->num_vectors = rf->msix_count;
 	if (rf->msix_count <= num_online_cpus())
 		rf->msix_shared = true;
-	else if (rf->msix_count > num_online_cpus() + 1)
-		rf->msix_count = num_online_cpus() + 1;
 
 	pmsix = rf->msix_entries;
 	for (i = 0, ceq_idx = 0; i < rf->msix_count; i++, iw_qvinfo++) {

drivers/infiniband/hw/irdma/main.c

@@ -206,6 +206,43 @@ static void irdma_lan_unregister_qset(struct irdma_sc_vsi *vsi,
 		ibdev_dbg(&iwdev->ibdev, "WS: LAN free_res for rdma qset failed.\n");
 }
 
+static int irdma_init_interrupts(struct irdma_pci_f *rf, struct ice_pf *pf)
+{
+	int i;
+
+	rf->msix_count = num_online_cpus() + IRDMA_NUM_AEQ_MSIX;
+	rf->msix_entries = kcalloc(rf->msix_count, sizeof(*rf->msix_entries),
+				   GFP_KERNEL);
+	if (!rf->msix_entries)
+		return -ENOMEM;
+
+	for (i = 0; i < rf->msix_count; i++)
+		if (ice_alloc_rdma_qvector(pf, &rf->msix_entries[i]))
+			break;
+
+	if (i < IRDMA_MIN_MSIX) {
+		for (; i > 0; i--)
+			ice_free_rdma_qvector(pf, &rf->msix_entries[i]);
+
+		kfree(rf->msix_entries);
+		return -ENOMEM;
+	}
+
+	rf->msix_count = i;
+
+	return 0;
+}
+
+static void irdma_deinit_interrupts(struct irdma_pci_f *rf, struct ice_pf *pf)
+{
+	int i;
+
+	for (i = 0; i < rf->msix_count; i++)
+		ice_free_rdma_qvector(pf, &rf->msix_entries[i]);
+
+	kfree(rf->msix_entries);
+}
+
 static void irdma_remove(struct auxiliary_device *aux_dev)
 {
 	struct iidc_auxiliary_dev *iidc_adev = container_of(aux_dev,
@@ -216,6 +253,7 @@ static void irdma_remove(struct auxiliary_device *aux_dev)
 
 	irdma_ib_unregister_device(iwdev);
 	ice_rdma_update_vsi_filter(pf, iwdev->vsi_num, false);
+	irdma_deinit_interrupts(iwdev->rf, pf);
 
 	pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(pf->pdev->devfn));
 }
@@ -230,9 +268,7 @@ static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf
 	rf->gen_ops.unregister_qset = irdma_lan_unregister_qset;
 	rf->hw.hw_addr = pf->hw.hw_addr;
 	rf->pcidev = pf->pdev;
-	rf->msix_count =  pf->num_rdma_msix;
 	rf->pf_id = pf->hw.pf_id;
-	rf->msix_entries = &pf->msix_entries[pf->rdma_base_vector];
 	rf->default_vsi.vsi_idx = vsi->vsi_num;
 	rf->protocol_used = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ?
 			    IRDMA_ROCE_PROTOCOL_ONLY : IRDMA_IWARP_PROTOCOL_ONLY;
@@ -281,6 +317,10 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_
 	irdma_fill_device_info(iwdev, pf, vsi);
 	rf = iwdev->rf;
 
+	err = irdma_init_interrupts(rf, pf);
+	if (err)
+		goto err_init_interrupts;
+
 	err = irdma_ctrl_init_hw(rf);
 	if (err)
 		goto err_ctrl_init;
@@ -311,6 +351,8 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_
 err_rt_init:
 	irdma_ctrl_deinit_hw(rf);
 err_ctrl_init:
+	irdma_deinit_interrupts(rf, pf);
+err_init_interrupts:
 	kfree(iwdev->rf);
 	ib_dealloc_device(&iwdev->ibdev);
 

drivers/infiniband/hw/irdma/main.h

@@ -117,6 +117,9 @@ extern struct auxiliary_driver i40iw_auxiliary_drv;
 
 #define IRDMA_IRQ_NAME_STR_LEN (64)
 
+#define IRDMA_NUM_AEQ_MSIX	1
+#define IRDMA_MIN_MSIX		2
+
 enum init_completion_state {
 	INVALID_STATE = 0,
 	INITIAL_STATE,

drivers/net/ethernet/intel/ice/devlink/devlink.c

@@ -1198,6 +1198,25 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate,
 	return status;
 }
 
+static void ice_set_min_max_msix(struct ice_pf *pf)
+{
+	struct devlink *devlink = priv_to_devlink(pf);
+	union devlink_param_value val;
+	int err;
+
+	err = devl_param_driverinit_value_get(devlink,
+					      DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+					      &val);
+	if (!err)
+		pf->msix.min = val.vu32;
+
+	err = devl_param_driverinit_value_get(devlink,
+					      DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
+					      &val);
+	if (!err)
+		pf->msix.max = val.vu32;
+}
+
 /**
  * ice_devlink_reinit_up - do reinit of the given PF
  * @pf: pointer to the PF struct
@@ -1207,9 +1226,18 @@ static int ice_devlink_reinit_up(struct ice_pf *pf)
 	struct ice_vsi *vsi = ice_get_main_vsi(pf);
 	int err;
 
+	err = ice_init_hw(&pf->hw);
+	if (err) {
+		dev_err(ice_pf_to_dev(pf), "ice_init_hw failed: %d\n", err);
+		return err;
+	}
+
+	/* load MSI-X values */
+	ice_set_min_max_msix(pf);
+
 	err = ice_init_dev(pf);
 	if (err)
-		return err;
+		goto unroll_hw_init;
 
 	vsi->flags = ICE_VSI_FLAG_INIT;
 
@@ -1232,6 +1260,8 @@ static int ice_devlink_reinit_up(struct ice_pf *pf)
 	rtnl_unlock();
 err_vsi_cfg:
 	ice_deinit_dev(pf);
+unroll_hw_init:
+	ice_deinit_hw(&pf->hw);
 	return err;
 }
 
@@ -1518,6 +1548,43 @@ static int ice_devlink_local_fwd_validate(struct devlink *devlink, u32 id,
 	return 0;
 }
 
+static int
+ice_devlink_msix_max_pf_validate(struct devlink *devlink, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+
+	if (val.vu32 > pf->hw.func_caps.common_cap.num_msix_vectors)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int
+ice_devlink_msix_min_pf_validate(struct devlink *devlink, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	if (val.vu32 < ICE_MIN_MSIX)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ice_devlink_enable_rdma_validate(struct devlink *devlink, u32 id,
+					    union devlink_param_value val,
+					    struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+	bool new_state = val.vbool;
+
+	if (new_state && !test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 enum ice_param_id {
 	ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
@@ -1533,6 +1600,17 @@ static const struct devlink_param ice_dvl_rdma_params[] = {
 			      ice_devlink_enable_iw_get,
 			      ice_devlink_enable_iw_set,
 			      ice_devlink_enable_iw_validate),
+	DEVLINK_PARAM_GENERIC(ENABLE_RDMA, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_enable_rdma_validate),
+};
+
+static const struct devlink_param ice_dvl_msix_params[] = {
+	DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MAX,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_msix_max_pf_validate),
+	DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MIN,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_msix_min_pf_validate),
 };
 
 static const struct devlink_param ice_dvl_sched_params[] = {
@@ -1636,6 +1714,7 @@ void ice_devlink_unregister(struct ice_pf *pf)
 int ice_devlink_register_params(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
+	union devlink_param_value value;
 	struct ice_hw *hw = &pf->hw;
 	int status;
 
@@ -1644,10 +1723,39 @@ int ice_devlink_register_params(struct ice_pf *pf)
 	if (status)
 		return status;
 
+	status = devl_params_register(devlink, ice_dvl_msix_params,
+				      ARRAY_SIZE(ice_dvl_msix_params));
+	if (status)
+		goto unregister_rdma_params;
+
 	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
 		status = devl_params_register(devlink, ice_dvl_sched_params,
 					      ARRAY_SIZE(ice_dvl_sched_params));
+	if (status)
+		goto unregister_msix_params;
+
+	value.vu32 = pf->msix.max;
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
+					value);
+	value.vu32 = pf->msix.min;
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+					value);
+
+	value.vbool = test_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
+					value);
+
+	return 0;
 
+unregister_msix_params:
+	devl_params_unregister(devlink, ice_dvl_msix_params,
+			       ARRAY_SIZE(ice_dvl_msix_params));
+unregister_rdma_params:
+	devl_params_unregister(devlink, ice_dvl_rdma_params,
+			       ARRAY_SIZE(ice_dvl_rdma_params));
 	return status;
 }
 
@@ -1658,6 +1766,8 @@ void ice_devlink_unregister_params(struct ice_pf *pf)
 
 	devl_params_unregister(devlink, ice_dvl_rdma_params,
 			       ARRAY_SIZE(ice_dvl_rdma_params));
+	devl_params_unregister(devlink, ice_dvl_msix_params,
+			       ARRAY_SIZE(ice_dvl_msix_params));
 
 	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
 		devl_params_unregister(devlink, ice_dvl_sched_params,

drivers/net/ethernet/intel/ice/ice.h

@@ -96,9 +96,6 @@
 #define ICE_MIN_LAN_OICR_MSIX	1
 #define ICE_MIN_MSIX		(ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX)
 #define ICE_FDIR_MSIX		2
-#define ICE_RDMA_NUM_AEQ_MSIX	4
-#define ICE_MIN_RDMA_MSIX	2
-#define ICE_ESWITCH_MSIX	1
 #define ICE_NO_VSI		0xffff
 #define ICE_VSI_MAP_CONTIG	0
 #define ICE_VSI_MAP_SCATTER	1
@@ -545,6 +542,14 @@ struct ice_agg_node {
 	u8 valid;
 };
 
+struct ice_pf_msix {
+	u32 cur;
+	u32 min;
+	u32 max;
+	u32 total;
+	u32 rest;
+};
+
 struct ice_pf {
 	struct pci_dev *pdev;
 	struct ice_adapter *adapter;
@@ -559,13 +564,7 @@ struct ice_pf {
 	/* OS reserved IRQ details */
 	struct msix_entry *msix_entries;
 	struct ice_irq_tracker irq_tracker;
-	/* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the
-	 * number of MSIX vectors needed for all SR-IOV VFs from the number of
-	 * 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 */
+	struct ice_virt_irq_tracker virt_irq_tracker;
 
 	u16 ctrl_vsi_idx;		/* control VSI index in pf->vsi array */
 
@@ -615,7 +614,7 @@ struct ice_pf {
 	struct msi_map ll_ts_irq;	/* LL_TS interrupt MSIX vector */
 	u16 max_pf_txqs;	/* Total Tx queues PF wide */
 	u16 max_pf_rxqs;	/* Total Rx queues PF wide */
-	u16 num_lan_msix;	/* Total MSIX vectors for base driver */
+	struct ice_pf_msix msix;
 	u16 num_lan_tx;		/* num LAN Tx queues setup */
 	u16 num_lan_rx;		/* num LAN Rx queues setup */
 	u16 next_vsi;		/* Next free slot in pf->vsi[] - 0-based! */

drivers/net/ethernet/intel/ice/ice_base.c

@@ -793,13 +793,11 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
 	return 0;
 
 err_out:
-	while (v_idx--)
-		ice_free_q_vector(vsi, v_idx);
 
-	dev_err(dev, "Failed to allocate %d q_vector for VSI %d, ret=%d\n",
-		vsi->num_q_vectors, vsi->vsi_num, err);
-	vsi->num_q_vectors = 0;
-	return err;
+	dev_info(dev, "Failed to allocate %d q_vectors for VSI %d, new value %d",
+		 vsi->num_q_vectors, vsi->vsi_num, v_idx);
+	vsi->num_q_vectors = v_idx;
+	return v_idx ? 0 : err;
 }
 
 /**