powerpc/pci: Create pci_dn for VFs

pci_dn is the extension of PCI device node and is created from device node.
Unfortunately, VFs are enabled dynamically by PF's driver and they don't
have corresponding device nodes and pci_dn, which is required to access
VFs' config spaces.

The patch creates pci_dn for VFs in pcibios_sriov_enable() on their PF,
and removes pci_dn for VFs in pcibios_sriov_disable() on their PF. When
VF's pci_dn is created, it's put to the child list of the pci_dn of PF's
upstream bridge. The pci_dn is linked to pci_dev during early fixup time
to setup the fast path.

[bhelgaas: add ifdef around add_one_dev_pci_info(), use dev_printk()]
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

3 files changed, 135 insertions, 0 deletions

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 2c6dc2a3d14a..ece30f589398 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -156,6 +156,7 @@ struct iommu_table;
 
 struct pci_dn {
 	int     flags;
+#define PCI_DN_FLAG_IOV_VF	0x01
 
 	int	busno;			/* pci bus number */
 	int	devfn;			/* pci device and function number */
@@ -188,6 +189,8 @@ struct pci_dn {
 extern struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
 					   int devfn);
 extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev);
+extern struct pci_dn *add_dev_pci_data(struct pci_dev *pdev);
+extern void remove_dev_pci_data(struct pci_dev *pdev);
 extern void *update_dn_pci_info(struct device_node *dn, void *data);
 
 static inline int pci_device_from_OF_node(struct device_node *np,
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 65b98367005c..e5f1d78ef7cf 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -136,6 +136,122 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 	return NULL;
 }
 
+#ifdef CONFIG_PCI_IOV
+static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
+					   struct pci_dev *pdev,
+					   int busno, int devfn)
+{
+	struct pci_dn *pdn;
+
+	/* Except PHB, we always have the parent */
+	if (!parent)
+		return NULL;
+
+	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
+	if (!pdn) {
+		dev_warn(&pdev->dev, "%s: Out of memory!\n", __func__);
+		return NULL;
+	}
+
+	pdn->phb = parent->phb;
+	pdn->parent = parent;
+	pdn->busno = busno;
+	pdn->devfn = devfn;
+#ifdef CONFIG_PPC_POWERNV
+	pdn->pe_number = IODA_INVALID_PE;
+#endif
+	INIT_LIST_HEAD(&pdn->child_list);
+	INIT_LIST_HEAD(&pdn->list);
+	list_add_tail(&pdn->list, &parent->child_list);
+
+	/*
+	 * If we already have PCI device instance, lets
+	 * bind them.
+	 */
+	if (pdev)
+		pdev->dev.archdata.pci_data = pdn;
+
+	return pdn;
+}
+#endif
+
+struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dn *parent, *pdn;
+	int i;
+
+	/* Only support IOV for now */
+	if (!pdev->is_physfn)
+		return pci_get_pdn(pdev);
+
+	/* Check if VFs have been populated */
+	pdn = pci_get_pdn(pdev);
+	if (!pdn || (pdn->flags & PCI_DN_FLAG_IOV_VF))
+		return NULL;
+
+	pdn->flags |= PCI_DN_FLAG_IOV_VF;
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return NULL;
+
+	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		pdn = add_one_dev_pci_data(parent, NULL,
+					   pci_iov_virtfn_bus(pdev, i),
+					   pci_iov_virtfn_devfn(pdev, i));
+		if (!pdn) {
+			dev_warn(&pdev->dev, "%s: Cannot create firmware data for VF#%d\n",
+				 __func__, i);
+			return NULL;
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+
+	return pci_get_pdn(pdev);
+}
+
+void remove_dev_pci_data(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dn *parent;
+	struct pci_dn *pdn, *tmp;
+	int i;
+
+	/* Only support IOV PF for now */
+	if (!pdev->is_physfn)
+		return;
+
+	/* Check if VFs have been populated */
+	pdn = pci_get_pdn(pdev);
+	if (!pdn || !(pdn->flags & PCI_DN_FLAG_IOV_VF))
+		return;
+
+	pdn->flags &= ~PCI_DN_FLAG_IOV_VF;
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return;
+
+	/*
+	 * We might introduce flag to pci_dn in future
+	 * so that we can release VF's firmware data in
+	 * a batch mode.
+	 */
+	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		list_for_each_entry_safe(pdn, tmp,
+			&parent->child_list, list) {
+			if (pdn->busno != pci_iov_virtfn_bus(pdev, i) ||
+			    pdn->devfn != pci_iov_virtfn_devfn(pdev, i))
+				continue;
+
+			if (!list_empty(&pdn->list))
+				list_del(&pdn->list);
+
+			kfree(pdn);
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+}
+
 /*
  * Traverse_func that inits the PCI fields of the device node.
  * NOTE: this *must* be done before read/write config to the device.
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 26fe09936935..7f58f199f2c1 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -974,6 +974,22 @@ static void pnv_pci_ioda_setup_PEs(void)
 	}
 }
 
+#ifdef CONFIG_PCI_IOV
+int pcibios_sriov_disable(struct pci_dev *pdev)
+{
+	/* Release PCI data */
+	remove_dev_pci_data(pdev);
+	return 0;
+}
+
+int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+{
+	/* Allocate PCI data */
+	add_dev_pci_data(pdev);
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
 {
 	struct pci_dn *pdn = pci_get_pdn(pdev);