ice: Split irq_tracker into sw_irq_tracker and hw_irq_tracker

For the PF driver, when mapping interrupts to queues, we need to request
IRQs from the kernel and we also have to allocate interrupts from
the device.

Similarly, when the VF driver (iavf.ko) initializes, it requests the kernel
IRQs that it needs but it can't directly allocate interrupts in the device.
Instead, it sends a mailbox message to the ice driver, which then allocates
interrupts in the device on the VF driver's behalf.

Currently both these cases end up having to reserve entries in
pf->irq_tracker but irq_tracker itself is sized based on how many vectors
the PF driver needs. Under the right circumstances, the VF driver can fail
to get entries in irq_tracker, which will result in the VF driver failing
probe.

To fix this, sw_irq_tracker and hw_irq_tracker are introduced. The
sw_irq_tracker tracks only the PF's IRQ request and doesn't play any
role in VF init. hw_irq_tracker represents the device's interrupt space.
When interrupts have to be allocated in the device for either PF or VF,
hw_irq_tracker will be looked up to see if the device has run out of
interrupts.

Signed-off-by: Preethi Banala <preethi.banala@intel.com>
Signed-off-by: Anirudh Venkataramanan <anirudh.venkataramanan@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

1 files changed, 81 insertions, 35 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index bb42ee643b77..d9f30d15ad65 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -95,7 +95,7 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf)
 				/* Trigger sw interrupt to revive the queue */
 				v_idx = tx_ring->q_vector->v_idx;
 				wr32(&vsi->back->hw,
-				     GLINT_DYN_CTL(vsi->base_vector + v_idx),
+				     GLINT_DYN_CTL(vsi->hw_base_vector + v_idx),
 				     (itr << GLINT_DYN_CTL_ITR_INDX_S) |
 				     GLINT_DYN_CTL_SWINT_TRIG_M |
 				     GLINT_DYN_CTL_INTENA_MSK_M);
@@ -1122,7 +1122,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 {
 	int q_vectors = vsi->num_q_vectors;
 	struct ice_pf *pf = vsi->back;
-	int base = vsi->base_vector;
+	int base = vsi->sw_base_vector;
 	int rx_int_idx = 0;
 	int tx_int_idx = 0;
 	int vector, err;
@@ -1203,7 +1203,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf)
 	wr32(hw, PFINT_OICR_ENA, val);
 
 	/* SW_ITR_IDX = 0, but don't change INTENA */
-	wr32(hw, GLINT_DYN_CTL(pf->oicr_idx),
+	wr32(hw, GLINT_DYN_CTL(pf->hw_oicr_idx),
 	     GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
 }
 
@@ -1321,12 +1321,15 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf)
 	ice_flush(&pf->hw);
 
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) {
-		synchronize_irq(pf->msix_entries[pf->oicr_idx].vector);
+		synchronize_irq(pf->msix_entries[pf->sw_oicr_idx].vector);
 		devm_free_irq(&pf->pdev->dev,
-			      pf->msix_entries[pf->oicr_idx].vector, pf);
+			      pf->msix_entries[pf->sw_oicr_idx].vector, pf);
 	}
 
-	ice_free_res(pf->irq_tracker, pf->oicr_idx, ICE_RES_MISC_VEC_ID);
+	pf->num_avail_sw_msix += 1;
+	ice_free_res(pf->sw_irq_tracker, pf->sw_oicr_idx, ICE_RES_MISC_VEC_ID);
+	pf->num_avail_hw_msix += 1;
+	ice_free_res(pf->hw_irq_tracker, pf->hw_oicr_idx, ICE_RES_MISC_VEC_ID);
 }
 
 /**
@@ -1356,39 +1359,53 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 	if (ice_is_reset_in_progress(pf->state))
 		goto skip_req_irq;
 
-	/* reserve one vector in irq_tracker for misc interrupts */
-	oicr_idx = ice_get_res(pf, pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+	/* reserve one vector in sw_irq_tracker for misc interrupts */
+	oicr_idx = ice_get_res(pf, pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID);
 	if (oicr_idx < 0)
 		return oicr_idx;
 
-	pf->oicr_idx = oicr_idx;
+	pf->num_avail_sw_msix -= 1;
+	pf->sw_oicr_idx = oicr_idx;
+
+	/* reserve one vector in hw_irq_tracker for misc interrupts */
+	oicr_idx = ice_get_res(pf, pf->hw_irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+	if (oicr_idx < 0) {
+		ice_free_res(pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+		pf->num_avail_sw_msix += 1;
+		return oicr_idx;
+	}
+	pf->num_avail_hw_msix -= 1;
+	pf->hw_oicr_idx = oicr_idx;
 
 	err = devm_request_irq(&pf->pdev->dev,
-			       pf->msix_entries[pf->oicr_idx].vector,
+			       pf->msix_entries[pf->sw_oicr_idx].vector,
 			       ice_misc_intr, 0, pf->int_name, pf);
 	if (err) {
 		dev_err(&pf->pdev->dev,
 			"devm_request_irq for %s failed: %d\n",
 			pf->int_name, err);
-		ice_free_res(pf->irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+		ice_free_res(pf->sw_irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+		pf->num_avail_sw_msix += 1;
+		ice_free_res(pf->hw_irq_tracker, 1, ICE_RES_MISC_VEC_ID);
+		pf->num_avail_hw_msix += 1;
 		return err;
 	}
 
 skip_req_irq:
 	ice_ena_misc_vector(pf);
 
-	val = ((pf->oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
+	val = ((pf->hw_oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
 	       PFINT_OICR_CTL_CAUSE_ENA_M);
 	wr32(hw, PFINT_OICR_CTL, val);
 
 	/* This enables Admin queue Interrupt causes */
-	val = ((pf->oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) |
+	val = ((pf->hw_oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) |
 	       PFINT_FW_CTL_CAUSE_ENA_M);
 	wr32(hw, PFINT_FW_CTL, val);
 
 	itr_gran = hw->itr_gran_200;
 
-	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_idx),
+	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->hw_oicr_idx),
 	     ITR_TO_REG(ICE_ITR_8K, itr_gran));
 
 	ice_flush(hw);
@@ -1797,6 +1814,7 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 	/* reserve vectors for LAN traffic */
 	pf->num_lan_msix = min_t(int, num_online_cpus(), v_left);
 	v_budget += pf->num_lan_msix;
+	v_left -= pf->num_lan_msix;
 
 	pf->msix_entries = devm_kcalloc(&pf->pdev->dev, v_budget,
 					sizeof(struct msix_entry), GFP_KERNEL);
@@ -1824,10 +1842,11 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 			 "not enough vectors. requested = %d, obtained = %d\n",
 			 v_budget, v_actual);
 		if (v_actual >= (pf->num_lan_msix + 1)) {
-			pf->num_avail_msix = v_actual - (pf->num_lan_msix + 1);
+			pf->num_avail_sw_msix = v_actual -
+						(pf->num_lan_msix + 1);
 		} else if (v_actual >= 2) {
 			pf->num_lan_msix = 1;
-			pf->num_avail_msix = v_actual - 2;
+			pf->num_avail_sw_msix = v_actual - 2;
 		} else {
 			pci_disable_msix(pf->pdev);
 			err = -ERANGE;
@@ -1860,12 +1879,32 @@ static void ice_dis_msix(struct ice_pf *pf)
 }
 
 /**
+ * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme
+ * @pf: board private structure
+ */
+static void ice_clear_interrupt_scheme(struct ice_pf *pf)
+{
+	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
+		ice_dis_msix(pf);
+
+	if (pf->sw_irq_tracker) {
+		devm_kfree(&pf->pdev->dev, pf->sw_irq_tracker);
+		pf->sw_irq_tracker = NULL;
+	}
+
+	if (pf->hw_irq_tracker) {
+		devm_kfree(&pf->pdev->dev, pf->hw_irq_tracker);
+		pf->hw_irq_tracker = NULL;
+	}
+}
+
+/**
  * ice_init_interrupt_scheme - Determine proper interrupt scheme
  * @pf: board private structure to initialize
  */
 static int ice_init_interrupt_scheme(struct ice_pf *pf)
 {
-	int vectors = 0;
+	int vectors = 0, hw_vectors = 0;
 	ssize_t size;
 
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
@@ -1879,30 +1918,31 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 	/* set up vector assignment tracking */
 	size = sizeof(struct ice_res_tracker) + (sizeof(u16) * vectors);
 
-	pf->irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
-	if (!pf->irq_tracker) {
+	pf->sw_irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
+	if (!pf->sw_irq_tracker) {
 		ice_dis_msix(pf);
 		return -ENOMEM;
 	}
 
-	pf->irq_tracker->num_entries = vectors;
+	/* populate SW interrupts pool with number of OS granted IRQs. */
+	pf->num_avail_sw_msix = vectors;
+	pf->sw_irq_tracker->num_entries = vectors;
 
-	return 0;
-}
+	/* set up HW vector assignment tracking */
+	hw_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
+	size = sizeof(struct ice_res_tracker) + (sizeof(u16) * hw_vectors);
 
-/**
- * ice_clear_interrupt_scheme - Undo things done by ice_init_interrupt_scheme
- * @pf: board private structure
- */
-static void ice_clear_interrupt_scheme(struct ice_pf *pf)
-{
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-		ice_dis_msix(pf);
-
-	if (pf->irq_tracker) {
-		devm_kfree(&pf->pdev->dev, pf->irq_tracker);
-		pf->irq_tracker = NULL;
+	pf->hw_irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
+	if (!pf->hw_irq_tracker) {
+		ice_clear_interrupt_scheme(pf);
+		return -ENOMEM;
 	}
+
+	/* populate HW interrupts pool with number of HW supported irqs. */
+	pf->num_avail_hw_msix = hw_vectors;
+	pf->hw_irq_tracker->num_entries = hw_vectors;
+
+	return 0;
 }
 
 /**
@@ -3213,6 +3253,12 @@ static void ice_rebuild(struct ice_pf *pf)
 	if (err)
 		goto err_sched_init_port;
 
+	/* reset search_hint of irq_trackers to 0 since interrupts are
+	 * reclaimed and could be allocated from beginning during VSI rebuild
+	 */
+	pf->sw_irq_tracker->search_hint = 0;
+	pf->hw_irq_tracker->search_hint = 0;
+
 	err = ice_vsi_rebuild_all(pf);
 	if (err) {
 		dev_err(dev, "ice_vsi_rebuild_all failed\n");
@@ -3610,7 +3656,7 @@ static void ice_tx_timeout(struct net_device *netdev)
 		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
 			val = rd32(&pf->hw,
 				   GLINT_DYN_CTL(tx_ring->q_vector->v_idx +
-						tx_ring->vsi->base_vector - 1));
+					tx_ring->vsi->hw_base_vector));
 
 		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n",
 			    vsi->vsi_num, hung_queue, tx_ring->next_to_clean,