[PATCH v4 2/6] PCI: handle Virtual Function ATS enabling

[Yu Zhao]

The SR-IOV spec requires the Smallest Translation Unit and the
Invalidate Queue Depth fields in the Virtual Function ATS capability
to be hardwired to 0. If a function is a Virtual Function, then and
set its Physical Function's STU before enabling the ATS.

Signed-off-by: Yu Zhao <yu.zhao@xxxxxxxxx>
---
 drivers/pci/iov.c |   66 +++++++++++++++++++++++++++++++++++++++++-----------
 drivers/pci/pci.h |    4 ++-
 2 files changed, 55 insertions(+), 15 deletions(-)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 8a9817c..0bf23fc 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -491,10 +491,10 @@ found:
 
 	if (pdev)
 		iov->dev = pci_dev_get(pdev);
-	else {
+	else
 		iov->dev = dev;
-		mutex_init(&iov->lock);
-	}
+
+	mutex_init(&iov->lock);
 
 	dev->sriov = iov;
 	dev->is_physfn = 1;
@@ -514,11 +514,11 @@ static void sriov_release(struct pci_dev *dev)
 {
 	BUG_ON(dev->sriov->nr_virtfn);
 
-	if (dev == dev->sriov->dev)
-		mutex_destroy(&dev->sriov->lock);
-	else
+	if (dev != dev->sriov->dev)
 		pci_dev_put(dev->sriov->dev);
 
+	mutex_destroy(&dev->sriov->lock);
+
 	kfree(dev->sriov);
 	dev->sriov = NULL;
 }
@@ -722,19 +722,40 @@ int pci_enable_ats(struct pci_dev *dev, int pgshift)
 	int rc;
 	u16 ctrl;
 
-	BUG_ON(dev->ats);
+	BUG_ON(dev->ats && dev->ats->is_enabled);
 
 	if (pgshift < PCI_ATS_MIN_STU)
 		return -EINVAL;
 
-	rc = ats_alloc_one(dev, pgshift);
-	if (rc)
-		return rc;
+	if (dev->is_physfn || dev->is_virtfn) {
+		struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn;
+
+		mutex_lock(&pdev->sriov->lock);
+		if (pdev->ats)
+			rc = pdev->ats->stu == pgshift ? 0 : -EINVAL;
+		else
+			rc = ats_alloc_one(pdev, pgshift);
+
+		if (!rc)
+			pdev->ats->ref_cnt++;
+		mutex_unlock(&pdev->sriov->lock);
+		if (rc)
+			return rc;
+	}
+
+	if (!dev->is_physfn) {
+		rc = ats_alloc_one(dev, pgshift);
+		if (rc)
+			return rc;
+	}
 
 	ctrl = PCI_ATS_CTRL_ENABLE;
-	ctrl |= PCI_ATS_CTRL_STU(pgshift - PCI_ATS_MIN_STU);
+	if (!dev->is_virtfn)
+		ctrl |= PCI_ATS_CTRL_STU(pgshift - PCI_ATS_MIN_STU);
 	pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
 
+	dev->ats->is_enabled = 1;
+
 	return 0;
 }
 
@@ -746,13 +767,26 @@ void pci_disable_ats(struct pci_dev *dev)
 {
 	u16 ctrl;
 
-	BUG_ON(!dev->ats);
+	BUG_ON(!dev->ats || !dev->ats->is_enabled);
 
 	pci_read_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, &ctrl);
 	ctrl &= ~PCI_ATS_CTRL_ENABLE;
 	pci_write_config_word(dev, dev->ats->pos + PCI_ATS_CTRL, ctrl);
 
-	ats_free_one(dev);
+	dev->ats->is_enabled = 0;
+
+	if (dev->is_physfn || dev->is_virtfn) {
+		struct pci_dev *pdev = dev->is_physfn ? dev : dev->physfn;
+
+		mutex_lock(&pdev->sriov->lock);
+		pdev->ats->ref_cnt--;
+		if (!pdev->ats->ref_cnt)
+			ats_free_one(pdev);
+		mutex_unlock(&pdev->sriov->lock);
+	}
+
+	if (!dev->is_physfn)
+		ats_free_one(dev);
 }
 
 /**
@@ -764,13 +798,17 @@ void pci_disable_ats(struct pci_dev *dev)
  * The ATS spec uses 0 in the Invalidate Queue Depth field to
  * indicate that the function can accept 32 Invalidate Request.
  * But here we use the `real' values (i.e. 1~32) for the Queue
- * Depth.
+ * Depth; and 0 indicates the function shares the Queue with
+ * other functions (doesn't exclusively own a Queue).
  */
 int pci_ats_queue_depth(struct pci_dev *dev)
 {
 	int pos;
 	u16 cap;
 
+	if (dev->is_virtfn)
+		return 0;
+
 	if (dev->ats)
 		return dev->ats->qdep;
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 9f0db6a..8ecd185 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -223,6 +223,8 @@ struct pci_ats {
 	int pos;	/* capability position */
 	int stu;	/* Smallest Translation Unit */
 	int qdep;	/* Invalidate Queue Depth */
+	int ref_cnt;	/* Physical Function reference count */
+	int is_enabled:1;	/* Enable bit is set */
 };
 
 #ifdef CONFIG_PCI_IOV
@@ -244,7 +246,7 @@ extern int pci_ats_queue_depth(struct pci_dev *dev);
  */
 static inline int pci_ats_enabled(struct pci_dev *dev)
 {
-	return !!dev->ats;
+	return dev->ats && dev->ats->is_enabled;
 }
 #else
 static inline int pci_iov_init(struct pci_dev *dev)
-- 
1.5.6.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/