[RFC PATCH V3 11/17] ppc/pnv: Expand VF resources according to the number of total_pe

[Wei Yang]

On PHB3, VF resources will be covered by M64 BAR to have better PE isolation.
Mostly the total_pe number is different from the total_VFs, which will lead to
a conflict between MMIO space and the PE number.

This patch expands the VF resource size to reserve total_pe number of VFs'
resource, which prevents the conflict.

Signed-off-by: Wei Yang <weiyang at linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/machdep.h        |    6 +++
 arch/powerpc/include/asm/pci-bridge.h     |    3 ++
 arch/powerpc/kernel/pci-common.c          |   15 ++++++
 arch/powerpc/platforms/powernv/pci-ioda.c |   83 +++++++++++++++++++++++++++++
 4 files changed, 107 insertions(+)

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index ad3025d..2f2e770 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -234,9 +234,15 @@ struct machdep_calls {
 
 	/* Called after scan and before resource survey */
 	void (*pcibios_fixup_phb)(struct pci_controller *hose);
+#ifdef CONFIG_PCI_IOV
+	void (*pcibios_fixup_sriov)(struct pci_bus *bus);
+#endif /* CONFIG_PCI_IOV */
 
 	/* Called during PCI resource reassignment */
 	resource_size_t (*pcibios_window_alignment)(struct pci_bus *, unsigned long type);
+#ifdef CONFIG_PCI_IOV
+	resource_size_t (*__pci_sriov_resource_size)(struct pci_dev *, int resno);
+#endif /* CONFIG_PCI_IOV */
 
 	/* Called to shutdown machine specific hardware not already controlled
 	 * by other drivers.
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 4ca90a3..8c849d8 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -168,6 +168,9 @@ struct pci_dn {
 #define IODA_INVALID_PE		(-1)
 #ifdef CONFIG_PPC_POWERNV
 	int	pe_number;
+#ifdef CONFIG_PCI_IOV
+	u16     vfs;
+#endif /* CONFIG_PCI_IOV */
 #endif
 };
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index c449a26..c4e2e92 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -120,6 +120,16 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 	return 1;
 }
 
+#ifdef CONFIG_PCI_IOV
+resource_size_t pcibios_sriov_resource_size(struct pci_dev *pdev, int resno)
+{
+	if (ppc_md.__pci_sriov_resource_size)
+		return ppc_md.__pci_sriov_resource_size(pdev, resno);
+
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
@@ -1675,6 +1685,11 @@ void pcibios_scan_phb(struct pci_controller *hose)
 	if (ppc_md.pcibios_fixup_phb)
 		ppc_md.pcibios_fixup_phb(hose);
 
+#ifdef CONFIG_PCI_IOV
+	if (ppc_md.pcibios_fixup_sriov)
+		ppc_md.pcibios_fixup_sriov(bus);
+#endif /* CONFIG_PCI_IOV */
+
 	/* Configure PCI Express settings */
 	if (bus && !pci_has_flag(PCI_PROBE_ONLY)) {
 		struct pci_bus *child;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 87cb3089..7dfad6a 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1298,6 +1298,67 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb)
 static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { }
 #endif /* CONFIG_PCI_MSI */
 
+#ifdef CONFIG_PCI_IOV
+static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb;
+	struct resource *res;
+	int i;
+	resource_size_t size;
+	struct pci_dn *pdn;
+
+	if (!pdev->is_physfn || pdev->is_added)
+		return;
+
+	hose = pci_bus_to_host(pdev->bus);
+	if (!hose) {
+		dev_err(&pdev->dev, "%s: NULL pci_controller\n", __func__);
+		return;
+	}
+
+	phb = hose->private_data;
+	if (!phb) {
+		dev_err(&pdev->dev, "%s: NULL PHB\n", __func__);
+		return;
+	}
+
+	pdn = pci_get_pdn(pdev);
+	pdn->vfs = 0;
+
+	for (i = PCI_IOV_RESOURCES; i <= PCI_IOV_RESOURCE_END; i++) {
+		res = &pdev->resource[i];
+		if (!res->flags || res->parent)
+			continue;
+
+		if (!is_mem_pref_64_type(res->flags))
+			continue;
+
+		dev_info(&pdev->dev, "PowerNV: Fixing VF BAR[%d] %pR to\n",
+				i, res);
+		size = pci_sriov_resource_size(pdev, i);
+		res->end = res->start + size * phb->ioda.total_pe - 1;
+		dev_info(&pdev->dev, "                       %pR\n", res);
+	}
+	pdn->vfs = phb->ioda.total_pe;
+}
+
+static void pnv_pci_ioda_fixup_sriov(struct pci_bus *bus)
+{
+	struct pci_dev *pdev;
+	struct pci_bus *b;
+
+	list_for_each_entry(pdev, &bus->devices, bus_list) {
+		b = pdev->subordinate;
+
+		if (b)
+			pnv_pci_ioda_fixup_sriov(b);
+
+		pnv_pci_ioda_fixup_iov_resources(pdev);
+	}
+}
+#endif /* CONFIG_PCI_IOV */
+
 /*
  * This function is supposed to be called on basis of PE from top
  * to bottom style. So the the I/O or MMIO segment assigned to
@@ -1498,6 +1559,22 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
 	return phb->ioda.io_segsize;
 }
 
+#ifdef CONFIG_PCI_IOV
+static resource_size_t __pnv_pci_sriov_resource_size(struct pci_dev *pdev, int resno)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	u64 size = 0;
+
+	if (!pdn->vfs)
+		return size;
+
+	size = resource_size(pdev->resource + resno);
+	do_div(size, pdn->vfs);
+
+	return size;
+}
+#endif /* CONFIG_PCI_IOV */
+
 /* Prevent enabling devices for which we couldn't properly
  * assign a PE
  */
@@ -1692,9 +1769,15 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	 * for the P2P bridge bars so that each PCI bus (excluding
 	 * the child P2P bridges) can form individual PE.
 	 */
+#ifdef CONFIG_PCI_IOV
+	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_sriov;
+#endif /* CONFIG_PCI_IOV */
 	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
 	ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
 	ppc_md.pcibios_window_alignment = pnv_pci_window_alignment;
+#ifdef CONFIG_PCI_IOV
+	ppc_md.__pci_sriov_resource_size = __pnv_pci_sriov_resource_size;
+#endif /* CONFIG_PCI_IOV */
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 
 	/* Reset IODA tables to a clean state */
-- 
1.7.9.5