dmaengine: idxd: change MSIX allocation based on per wq activation

Change the driver where WQ interrupt is requested only when wq is being
enabled. This new scheme set things up so that request_threaded_irq() is
only called when a kernel wq type is being enabled. This also sets up for
future interrupt request where different interrupt handler such as wq
occupancy interrupt can be setup instead of the wq completion interrupt.

Not calling request_irq() until the WQ actually needs an irq also prevents
wasting of CPU irq vectors on x86 systems, which is a limited resource.

idxd_flush_pending_descs() is moved to device.c since descriptor flushing
is now part of wq disable rather than shutdown().
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/163942149487.2412839.6691222855803875848.stgit@djiang5-desk3.ch.intel.comSigned-off-by: Vinod Koul <vkoul@kernel.org>

drivers/dma/idxd/device.c

@@ -19,36 +19,6 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd);
 static void idxd_wq_disable_cleanup(struct idxd_wq *wq);
 
 /* Interrupt control bits */
-void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id)
-{
-	struct idxd_irq_entry *ie;
-	struct irq_data *data;
-
-	ie = idxd_get_ie(idxd, vec_id);
-	data = irq_get_irq_data(ie->vector);
-	pci_msi_mask_irq(data);
-}
-
-void idxd_mask_msix_vectors(struct idxd_device *idxd)
-{
-	struct pci_dev *pdev = idxd->pdev;
-	int msixcnt = pci_msix_vec_count(pdev);
-	int i;
-
-	for (i = 0; i < msixcnt; i++)
-		idxd_mask_msix_vector(idxd, i);
-}
-
-void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id)
-{
-	struct idxd_irq_entry *ie;
-	struct irq_data *data;
-
-	ie = idxd_get_ie(idxd, vec_id);
-	data = irq_get_irq_data(ie->vector);
-	pci_msi_unmask_irq(data);
-}
-
 void idxd_unmask_error_interrupts(struct idxd_device *idxd)
 {
 	union genctrl_reg genctrl;
@@ -593,7 +563,6 @@ void idxd_device_reset(struct idxd_device *idxd)
 	idxd_device_clear_state(idxd);
 	idxd->state = IDXD_DEV_DISABLED;
 	idxd_unmask_error_interrupts(idxd);
-	idxd_msix_perm_setup(idxd);
 	spin_unlock(&idxd->dev_lock);
 }
 
@@ -732,36 +701,6 @@ void idxd_device_clear_state(struct idxd_device *idxd)
 	idxd_device_wqs_clear_state(idxd);
 }
 
-void idxd_msix_perm_setup(struct idxd_device *idxd)
-{
-	union msix_perm mperm;
-	int i, msixcnt;
-
-	msixcnt = pci_msix_vec_count(idxd->pdev);
-	if (msixcnt < 0)
-		return;
-
-	mperm.bits = 0;
-	mperm.pasid = idxd->pasid;
-	mperm.pasid_en = device_pasid_enabled(idxd);
-	for (i = 1; i < msixcnt; i++)
-		iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
-}
-
-void idxd_msix_perm_clear(struct idxd_device *idxd)
-{
-	union msix_perm mperm;
-	int i, msixcnt;
-
-	msixcnt = pci_msix_vec_count(idxd->pdev);
-	if (msixcnt < 0)
-		return;
-
-	mperm.bits = 0;
-	for (i = 1; i < msixcnt; i++)
-		iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
-}
-
 static void idxd_group_config_write(struct idxd_group *group)
 {
 	struct idxd_device *idxd = group->idxd;
@@ -1158,6 +1097,106 @@ int idxd_device_load_config(struct idxd_device *idxd)
 	return 0;
 }
 
+static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)
+{
+	struct idxd_desc *desc, *itr;
+	struct llist_node *head;
+	LIST_HEAD(flist);
+	enum idxd_complete_type ctype;
+
+	spin_lock(&ie->list_lock);
+	head = llist_del_all(&ie->pending_llist);
+	if (head) {
+		llist_for_each_entry_safe(desc, itr, head, llnode)
+			list_add_tail(&desc->list, &ie->work_list);
+	}
+
+	list_for_each_entry_safe(desc, itr, &ie->work_list, list)
+		list_move_tail(&desc->list, &flist);
+	spin_unlock(&ie->list_lock);
+
+	list_for_each_entry_safe(desc, itr, &flist, list) {
+		list_del(&desc->list);
+		ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT;
+		idxd_dma_complete_txd(desc, ctype, true);
+	}
+}
+
+static void idxd_device_set_perm_entry(struct idxd_device *idxd,
+				       struct idxd_irq_entry *ie)
+{
+	union msix_perm mperm;
+
+	if (ie->pasid == INVALID_IOASID)
+		return;
+
+	mperm.bits = 0;
+	mperm.pasid = ie->pasid;
+	mperm.pasid_en = 1;
+	iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + ie->id * 8);
+}
+
+static void idxd_device_clear_perm_entry(struct idxd_device *idxd,
+					 struct idxd_irq_entry *ie)
+{
+	iowrite32(0, idxd->reg_base + idxd->msix_perm_offset + ie->id * 8);
+}
+
+void idxd_wq_free_irq(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct idxd_irq_entry *ie = &wq->ie;
+
+	synchronize_irq(ie->vector);
+	free_irq(ie->vector, ie);
+	idxd_flush_pending_descs(ie);
+	if (idxd->request_int_handles)
+		idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
+	idxd_device_clear_perm_entry(idxd, ie);
+	ie->vector = -1;
+	ie->int_handle = INVALID_INT_HANDLE;
+	ie->pasid = INVALID_IOASID;
+}
+
+int idxd_wq_request_irq(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct pci_dev *pdev = idxd->pdev;
+	struct device *dev = &pdev->dev;
+	struct idxd_irq_entry *ie;
+	int rc;
+
+	ie = &wq->ie;
+	ie->vector = pci_irq_vector(pdev, ie->id);
+	ie->pasid = device_pasid_enabled(idxd) ? idxd->pasid : INVALID_IOASID;
+	idxd_device_set_perm_entry(idxd, ie);
+
+	rc = request_threaded_irq(ie->vector, NULL, idxd_wq_thread, 0, "idxd-portal", ie);
+	if (rc < 0) {
+		dev_err(dev, "Failed to request irq %d.\n", ie->vector);
+		goto err_irq;
+	}
+
+	if (idxd->request_int_handles) {
+		rc = idxd_device_request_int_handle(idxd, ie->id, &ie->int_handle,
+						    IDXD_IRQ_MSIX);
+		if (rc < 0)
+			goto err_int_handle;
+	} else {
+		ie->int_handle = ie->id;
+	}
+
+	return 0;
+
+err_int_handle:
+	ie->int_handle = INVALID_INT_HANDLE;
+	free_irq(ie->vector, ie);
+err_irq:
+	idxd_device_clear_perm_entry(idxd, ie);
+	ie->pasid = INVALID_IOASID;
+	return rc;
+}
+
 int __drv_enable_wq(struct idxd_wq *wq)
 {
 	struct idxd_device *idxd = wq->idxd;

drivers/dma/idxd/dma.c

@@ -289,6 +289,14 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 
 	mutex_lock(&wq->wq_lock);
 	wq->type = IDXD_WQT_KERNEL;
+
+	rc = idxd_wq_request_irq(wq);
+	if (rc < 0) {
+		idxd->cmd_status = IDXD_SCMD_WQ_IRQ_ERR;
+		dev_dbg(dev, "WQ %d irq setup failed: %d\n", wq->id, rc);
+		goto err_irq;
+	}
+
 	rc = __drv_enable_wq(wq);
 	if (rc < 0) {
 		dev_dbg(dev, "Enable wq %d failed: %d\n", wq->id, rc);
@@ -329,6 +337,8 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 err_res_alloc:
 	__drv_disable_wq(wq);
 err:
+	idxd_wq_free_irq(wq);
+err_irq:
 	wq->type = IDXD_WQT_NONE;
 	mutex_unlock(&wq->wq_lock);
 	return rc;
@@ -344,6 +354,8 @@ static void idxd_dmaengine_drv_remove(struct idxd_dev *idxd_dev)
 	idxd_wq_free_resources(wq);
 	__drv_disable_wq(wq);
 	percpu_ref_exit(&wq->wq_active);
+	idxd_wq_free_irq(wq);
+	wq->type = IDXD_WQT_NONE;
 	mutex_unlock(&wq->wq_lock);
 }
 

drivers/dma/idxd/idxd.h

@@ -548,15 +548,10 @@ void idxd_wqs_quiesce(struct idxd_device *idxd);
 bool idxd_queue_int_handle_resubmit(struct idxd_desc *desc);
 
 /* device interrupt control */
-void idxd_msix_perm_setup(struct idxd_device *idxd);
-void idxd_msix_perm_clear(struct idxd_device *idxd);
 irqreturn_t idxd_misc_thread(int vec, void *data);
 irqreturn_t idxd_wq_thread(int irq, void *data);
 void idxd_mask_error_interrupts(struct idxd_device *idxd);
 void idxd_unmask_error_interrupts(struct idxd_device *idxd);
-void idxd_mask_msix_vectors(struct idxd_device *idxd);
-void idxd_mask_msix_vector(struct idxd_device *idxd, int vec_id);
-void idxd_unmask_msix_vector(struct idxd_device *idxd, int vec_id);
 
 /* device control */
 int idxd_register_idxd_drv(void);
@@ -595,6 +590,8 @@ int idxd_wq_disable_pasid(struct idxd_wq *wq);
 void __idxd_wq_quiesce(struct idxd_wq *wq);
 void idxd_wq_quiesce(struct idxd_wq *wq);
 int idxd_wq_init_percpu_ref(struct idxd_wq *wq);
+void idxd_wq_free_irq(struct idxd_wq *wq);
+int idxd_wq_request_irq(struct idxd_wq *wq);
 
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);

drivers/dma/idxd/init.c

@@ -90,7 +90,6 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 	}
 	dev_dbg(dev, "Enabled %d msix vectors\n", msixcnt);
 
-	idxd_msix_perm_setup(idxd);
 
 	ie = idxd_get_ie(idxd, 0);
 	ie->vector = pci_irq_vector(pdev, 0);
@@ -99,65 +98,26 @@ static int idxd_setup_interrupts(struct idxd_device *idxd)
 		dev_err(dev, "Failed to allocate misc interrupt.\n");
 		goto err_misc_irq;
 	}
-
-	dev_dbg(dev, "Allocated idxd-misc handler on msix vector %d\n", ie->vector);
+	dev_dbg(dev, "Requested idxd-misc handler on msix vector %d\n", ie->vector);
 
 	for (i = 0; i < idxd->max_wqs; i++) {
 		int msix_idx = i + 1;
 
 		ie = idxd_get_ie(idxd, msix_idx);
-
-		/* MSIX vector 0 special, wq irq entry starts at 1 */
 		ie->id = msix_idx;
-		ie->vector = pci_irq_vector(pdev, msix_idx);
 		ie->int_handle = INVALID_INT_HANDLE;
-		if (device_pasid_enabled(idxd) && i > 0)
-			ie->pasid = idxd->pasid;
-		else
-			ie->pasid = INVALID_IOASID;
+		ie->pasid = INVALID_IOASID;
+
 		spin_lock_init(&ie->list_lock);
 		init_llist_head(&ie->pending_llist);
 		INIT_LIST_HEAD(&ie->work_list);
-
-		rc = request_threaded_irq(ie->vector, NULL, idxd_wq_thread, 0, "idxd-portal", ie);
-		if (rc < 0) {
-			dev_err(dev, "Failed to allocate irq %d.\n", ie->vector);
-			goto err_wq_irqs;
-		}
-
-		dev_dbg(dev, "Allocated idxd-msix %d for vector %d\n", i, ie->vector);
-		if (idxd->request_int_handles) {
-			rc = idxd_device_request_int_handle(idxd, i, &ie->int_handle,
-							    IDXD_IRQ_MSIX);
-			if (rc < 0) {
-				free_irq(ie->vector, ie);
-				goto err_wq_irqs;
-			}
-			dev_dbg(dev, "int handle requested: %u\n", ie->int_handle);
-		} else {
-			ie->int_handle = msix_idx;
-		}
-
 	}
 
 	idxd_unmask_error_interrupts(idxd);
 	return 0;
 
- err_wq_irqs:
-	while (--i >= 0) {
-		ie = &idxd->wqs[i]->ie;
-		free_irq(ie->vector, ie);
-		if (ie->int_handle != INVALID_INT_HANDLE) {
-			idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
-			ie->int_handle = INVALID_INT_HANDLE;
-			ie->pasid = INVALID_IOASID;
-		}
-		ie->vector = -1;
-	}
  err_misc_irq:
-	/* Disable error interrupt generation */
 	idxd_mask_error_interrupts(idxd);
-	idxd_msix_perm_clear(idxd);
 	pci_free_irq_vectors(pdev);
 	dev_err(dev, "No usable interrupts\n");
 	return rc;
@@ -167,20 +127,15 @@ static void idxd_cleanup_interrupts(struct idxd_device *idxd)
 {
 	struct pci_dev *pdev = idxd->pdev;
 	struct idxd_irq_entry *ie;
-	int i;
+	int msixcnt;
 
-	for (i = 0; i < idxd->irq_cnt; i++) {
-		ie = idxd_get_ie(idxd, i);
-		if (ie->int_handle != INVALID_INT_HANDLE) {
-			idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
-			ie->int_handle = INVALID_INT_HANDLE;
-			ie->pasid = INVALID_IOASID;
-		}
-		free_irq(ie->vector, ie);
-		ie->vector = -1;
-	}
+	msixcnt = pci_msix_vec_count(pdev);
+	if (msixcnt <= 0)
+		return;
 
+	ie = idxd_get_ie(idxd, 0);
 	idxd_mask_error_interrupts(idxd);
+	free_irq(ie->vector, ie);
 	pci_free_irq_vectors(pdev);
 }
 
@@ -592,8 +547,6 @@ static int idxd_probe(struct idxd_device *idxd)
 	if (rc)
 		goto err_config;
 
-	dev_dbg(dev, "IDXD interrupt setup complete.\n");
-
 	idxd->major = idxd_cdev_get_major(idxd);
 
 	rc = perfmon_pmu_init(idxd);
@@ -689,31 +642,6 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	return rc;
 }
 
-static void idxd_flush_pending_descs(struct idxd_irq_entry *ie)
-{
-	struct idxd_desc *desc, *itr;
-	struct llist_node *head;
-	LIST_HEAD(flist);
-	enum idxd_complete_type ctype;
-
-	spin_lock(&ie->list_lock);
-	head = llist_del_all(&ie->pending_llist);
-	if (head) {
-		llist_for_each_entry_safe(desc, itr, head, llnode)
-			list_add_tail(&desc->list, &ie->work_list);
-	}
-
-	list_for_each_entry_safe(desc, itr, &ie->work_list, list)
-		list_move_tail(&desc->list, &flist);
-	spin_unlock(&ie->list_lock);
-
-	list_for_each_entry_safe(desc, itr, &flist, list) {
-		list_del(&desc->list);
-		ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT;
-		idxd_dma_complete_txd(desc, ctype, true);
-	}
-}
-
 void idxd_wqs_quiesce(struct idxd_device *idxd)
 {
 	struct idxd_wq *wq;
@@ -726,46 +654,19 @@ void idxd_wqs_quiesce(struct idxd_device *idxd)
 	}
 }
 
-static void idxd_release_int_handles(struct idxd_device *idxd)
-{
-	struct device *dev = &idxd->pdev->dev;
-	int i, rc;
-
-	for (i = 1; i < idxd->irq_cnt; i++) {
-		struct idxd_irq_entry *ie = idxd_get_ie(idxd, i);
-
-		if (ie->int_handle != INVALID_INT_HANDLE) {
-			rc = idxd_device_release_int_handle(idxd, ie->int_handle, IDXD_IRQ_MSIX);
-			if (rc < 0)
-				dev_warn(dev, "irq handle %d release failed\n", ie->int_handle);
-			else
-				dev_dbg(dev, "int handle released: %u\n", ie->int_handle);
-		}
-	}
-}
-
 static void idxd_shutdown(struct pci_dev *pdev)
 {
 	struct idxd_device *idxd = pci_get_drvdata(pdev);
-	int rc, i;
 	struct idxd_irq_entry *irq_entry;
-	int msixcnt = pci_msix_vec_count(pdev);
+	int rc;
 
 	rc = idxd_device_disable(idxd);
 	if (rc)
 		dev_err(&pdev->dev, "Disabling device failed\n");
 
-	dev_dbg(&pdev->dev, "%s called\n", __func__);
-	idxd_mask_msix_vectors(idxd);
+	irq_entry = &idxd->ie;
+	synchronize_irq(irq_entry->vector);
 	idxd_mask_error_interrupts(idxd);
-
-	for (i = 0; i < msixcnt; i++) {
-		irq_entry = idxd_get_ie(idxd, i);
-		synchronize_irq(irq_entry->vector);
-		if (i == 0)
-			continue;
-		idxd_flush_pending_descs(irq_entry);
-	}
 	flush_workqueue(idxd->wq);
 }
 
@@ -773,8 +674,6 @@ static void idxd_remove(struct pci_dev *pdev)
 {
 	struct idxd_device *idxd = pci_get_drvdata(pdev);
 	struct idxd_irq_entry *irq_entry;
-	int msixcnt = pci_msix_vec_count(pdev);
-	int i;
 
 	idxd_unregister_devices(idxd);
 	/*
@@ -790,12 +689,8 @@ static void idxd_remove(struct pci_dev *pdev)
 	if (device_pasid_enabled(idxd))
 		idxd_disable_system_pasid(idxd);
 
-	for (i = 0; i < msixcnt; i++) {
-		irq_entry = idxd_get_ie(idxd, i);
-		free_irq(irq_entry->vector, irq_entry);
-	}
-	idxd_msix_perm_clear(idxd);
-	idxd_release_int_handles(idxd);
+	irq_entry = idxd_get_ie(idxd, 0);
+	free_irq(irq_entry->vector, irq_entry);
 	pci_free_irq_vectors(pdev);
 	pci_iounmap(pdev, idxd->reg_base);
 	iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);

drivers/dma/idxd/irq.c

@@ -158,6 +158,9 @@ static void idxd_int_handle_revoke(struct work_struct *work)
 		struct idxd_irq_entry *ie = idxd_get_ie(idxd, i);
 		struct idxd_wq *wq = ie_to_wq(ie);
 
+		if (ie->int_handle == INVALID_INT_HANDLE)
+			continue;
+
 		rc = idxd_device_request_int_handle(idxd, i, &new_handle, IDXD_IRQ_MSIX);
 		if (rc < 0) {
 			dev_warn(dev, "get int handle %d failed: %d\n", i, rc);

include/uapi/linux/idxd.h

@@ -28,6 +28,7 @@ enum idxd_scmd_stat {
 	IDXD_SCMD_WQ_NONE_CONFIGURED = 0x800d0000,
 	IDXD_SCMD_WQ_NO_SIZE = 0x800e0000,
 	IDXD_SCMD_WQ_NO_PRIV = 0x800f0000,
+	IDXD_SCMD_WQ_IRQ_ERR = 0x80100000,
 };
 
 #define IDXD_SCMD_SOFTERR_MASK	0x80000000