powerpc/powernv: Reserve a hole which appears after enabling IOV

In order to make generic IOV code work, the physical function IOV BAR
should start from offset of the first VF. Since M64 segments share
PE number space across PHB, and some PEs may be in use at the time
when IOV is enabled, the existing code shifts the IOV BAR to the index
of the first PE/VF. This creates a hole in IOMEM space which can be
potentially taken by some other device.

This reserves a temporary hole on a parent and releases it when IOV is
disabled; the temporary resources are stored in pci_dn to avoid
kmalloc/free.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 0b8aa1fe2d5f5dbc7b7dc96dfda5ab20c9de9971..62ed83db04ae96def6417e404fd3f099e1ab81ec 100644 (file)
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -218,6 +218,7 @@ struct pci_dn {
 #endif
        struct list_head child_list;
        struct list_head list;
+       struct resource holes[PCI_SRIOV_NUM_BARS];
 };
 
 /* Get the pointer to a device_node's pci_dn */

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index fb5cd75111893906f1b78240d29483f2c77f90e0..7e87867984e72b9463c815a9dfb96d584716c95c 100644 (file)
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1002,9 +1002,12 @@ static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset)
        }
 
        /*
-        * After doing so, there would be a "hole" in the /proc/iomem when
-        * offset is a positive value. It looks like the device return some
-        * mmio back to the system, which actually no one could use it.
+        * Since M64 BAR shares segments among all possible 256 PEs,
+        * we have to shift the beginning of PF IOV BAR to make it start from
+        * the segment which belongs to the PE number assigned to the first VF.
+        * This creates a "hole" in the /proc/iomem which could be used for
+        * allocating other resources so we reserve this area below and
+        * release when IOV is released.
         */
        for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
                res = &dev->resource[i + PCI_IOV_RESOURCES];
@@ -1018,7 +1021,22 @@ static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset)
                dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (%sabling %d VFs shifted by %d)\n",
                         i, &res2, res, (offset > 0) ? "En" : "Dis",
                         num_vfs, offset);
+
+               if (offset < 0) {
+                       devm_release_resource(&dev->dev, &pdn->holes[i]);
+                       memset(&pdn->holes[i], 0, sizeof(pdn->holes[i]));
+               }
+
                pci_update_resource(dev, i + PCI_IOV_RESOURCES);
+
+               if (offset > 0) {
+                       pdn->holes[i].start = res2.start;
+                       pdn->holes[i].end = res2.start + size * offset - 1;
+                       pdn->holes[i].flags = IORESOURCE_BUS;
+                       pdn->holes[i].name = "pnv_iov_reserved";
+                       devm_request_resource(&dev->dev, res->parent,
+                                       &pdn->holes[i]);
+               }
        }
        return 0;
 }