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@xxxxxxxxxxxxxxxxxx>
---
arch/powerpc/include/asm/machdep.h | 4 ++
arch/powerpc/include/asm/pci-bridge.h | 3 +
arch/powerpc/kernel/pci-common.c | 5 ++
arch/powerpc/platforms/powernv/pci-ioda.c | 91 +++++++++++++++++++++++++++++
arch/powerpc/platforms/powernv/pci.h | 3 +
5 files changed, 106 insertions(+)
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 3909d1b..fabb8016 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -252,6 +252,10 @@ struct machdep_calls {
/* Reset the secondary bus of bridge */
void (*pcibios_reset_secondary_bus)(struct pci_dev *dev);
+#ifdef CONFIG_PCI_IOV
+ void (*pcibios_fixup_sriov)(struct pci_bus *bus);
+#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 757d7bb..3cb95af 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -173,6 +173,9 @@ struct pci_dn {
#define IODA_INVALID_PE (-1)
#ifdef CONFIG_PPC_POWERNV
int pe_number;
+#ifdef CONFIG_PCI_IOV
+ u16 vfs; /* number of VFs IOV BAR expended */
+#endif /* CONFIG_PCI_IOV */
#endif
struct list_head child_list;
struct list_head list;
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index d38a330..c2b7930 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1651,6 +1651,11 @@ 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 8318b07..6fd2377 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1505,6 +1505,60 @@ 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);
+ phb = hose->private_data;
+
+ 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 (!pnv_pci_is_mem_pref_64(res->flags)) {
+ dev_warn(&pdev->dev, " non M64 IOV BAR %pR on %s\n",
+ res, pci_name(pdev));
+ continue;
+ }
+
+ dev_dbg(&pdev->dev, "PowerNV: Fixing VF BAR[%d] %pR to\n",
+ i, res);
+ size = pnv_pci_sriov_resource_size(pdev, i);
+ res->end = res->start + size * phb->ioda.total_pe - 1;
+ dev_dbg(&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
@@ -1681,6 +1735,40 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
return phb->ioda.io_segsize;
}
+/*
+ * Allocate firmware data for VF, which doesn't have corresponding
+ * device node. So we have to extend device's archdata.
+ */
+#ifdef CONFIG_PCI_IOV
+static resource_size_t pnv_pcibios_sriov_resource_size(struct pci_dev *pdev, int resno)
+{
+ struct pci_dn *pdn = pci_get_pdn(pdev);
+ resource_size_t size = 0;
+
+ if (!pdn->vfs)
+ return size;
+
+ size = resource_size(pdev->resource + resno);
+ do_div(size, pdn->vfs);
+
+ return size;
+}
+
+resource_size_t pnv_pci_sriov_resource_size(struct pci_dev *pdev, int resno)
+{
+ resource_size_t size;
+
+ size = pnv_pcibios_sriov_resource_size(pdev, resno);
+ if (size != 0)
+ return size;
+
+ size = resource_size(pdev->resource + resno);
+ do_div(size, pci_sriov_get_totalvfs(pdev));
+
+ return size;
+}
+#endif /* CONFIG_PCI_IOV */
+
/* Prevent enabling devices for which we couldn't properly
* assign a PE
*/
@@ -1886,6 +1974,9 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
ppc_md.pcibios_window_alignment = pnv_pci_window_alignment;
ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus;
+#ifdef CONFIG_PCI_IOV
+ ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_sriov;
+#endif /* CONFIG_PCI_IOV */
pci_add_flags(PCI_REASSIGN_ALL_RSRC);
/* Reset IODA tables to a clean state */
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 0d616f0..e55772f 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -229,5 +229,8 @@ extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
__be64 *startp, __be64 *endp, bool rm);
extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
extern int ioda_eeh_phb_reset(struct pci_controller *hose, int option);
+#ifdef CONFIG_PCI_IOV
+resource_size_t pnv_pci_sriov_resource_size(struct pci_dev *pdev, int resno);
+#endif
#endif /* __POWERNV_PCI_H */
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
