[RFC v6 08/10] PCI: Set PCI_BUS_FLAGS_MSI_REMAP if MSI controller supports IRQ remapping

[RFC v6 08/10] PCI: Set PCI_BUS_FLAGS_MSI_REMAP if MSI controller supports IRQ remapping

[Yongji Xie]

On ARM HW the capability of IRQ remapping is abstracted on
MSI controller side. MSI_FLAG_IRQ_REMAPPING is used to advertise
this [1].

To have a universal flag to test this capability for different
archs on PCI side, we set PCI_BUS_FLAGS_MSI_REMAP for PCI buses
when MSI_FLAG_IRQ_REMAPPING is set.

[1] http://www.spinics.net/lists/kvm/msg130256.html

Signed-off-by: Yongji Xie <xyjxie@linux.vnet.ibm.com>
---
 drivers/pci/msi.c   |   12 ++++++++++++
 drivers/pci/probe.c |    3 +++
 include/linux/msi.h |    6 +++++-
 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index a080f44..1661cdf 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1134,6 +1134,18 @@ void *msi_desc_to_pci_sysdata(struct msi_desc *desc)
 }
 EXPORT_SYMBOL_GPL(msi_desc_to_pci_sysdata);
 
+void pci_bus_check_msi_remapping(struct pci_bus *bus,
+				 struct irq_domain *domain)
+{
+#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
+	struct msi_domain_info *info;
+
+	info = msi_get_domain_info(domain);
+	if (info->flags & MSI_FLAG_IRQ_REMAPPING)
+		bus->bus_flags |= PCI_BUS_FLAGS_MSI_REMAP;
+#endif
+}
+
 #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
 /**
  * pci_msi_domain_write_msg - Helper to write MSI message to PCI config space
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 6d7ab9b..25cf1b1 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -696,6 +696,9 @@ static void pci_set_bus_msi_domain(struct pci_bus *bus)
 	if (!d)
 		d = pci_host_bridge_msi_domain(b);
 
+	if (d && b == bus)
+		pci_bus_check_msi_remapping(bus, d);
+
 	dev_set_msi_domain(&bus->dev, d);
 }
 
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 03eda72..b4c649e 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -15,6 +15,8 @@ extern int pci_msi_ignore_mask;
 struct irq_data;
 struct msi_desc;
 struct pci_dev;
+struct pci_bus;
+struct irq_domain;
 struct platform_msi_priv_data;
 void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
@@ -155,6 +157,9 @@ void arch_restore_msi_irqs(struct pci_dev *dev);
 void default_teardown_msi_irqs(struct pci_dev *dev);
 void default_restore_msi_irqs(struct pci_dev *dev);
 
+void pci_bus_check_msi_remapping(struct pci_bus *bus,
+				 struct irq_domain *domain);
+
 struct msi_controller {
 	struct module *owner;
 	struct device *dev;
@@ -173,7 +178,6 @@ struct msi_controller {
 #include <linux/irqhandler.h>
 #include <asm/msi.h>
 
-struct irq_domain;
 struct irq_domain_ops;
 struct irq_chip;
 struct device_node;
-- 
1.7.9.5

[RFC v6 09/10] pci-ioda: Set PCI_BUS_FLAGS_MSI_REMAP for IODA host bridge

[Yongji Xie]

Any IODA host bridge have the capability of IRQ remapping.
So we set PCI_BUS_FLAGS_MSI_REMAP when this kind of host birdge
is detected.

Signed-off-by: Yongji Xie <xyjxie@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/pci-ioda.c |    8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index f90dc04..9557638 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -3080,6 +3080,12 @@ static void pnv_pci_ioda_fixup(void)
 	pnv_npu_ioda_fixup();
 }
 
+int pnv_pci_ioda_root_bridge_prepare(struct pci_host_bridge *bridge)
+{
+	bridge->bus->bus_flags |= PCI_BUS_FLAGS_MSI_REMAP;
+	return 0;
+}
+
 /*
  * Returns the alignment for I/O or memory windows for P2P
  * bridges. That actually depends on how PEs are segmented.
@@ -3364,6 +3370,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	 */
 	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
 
+	ppc_md.pcibios_root_bridge_prepare = pnv_pci_ioda_root_bridge_prepare;
+
 	if (phb->type == PNV_PHB_NPU)
 		hose->controller_ops = pnv_npu_ioda_controller_ops;
 	else
-- 
1.7.9.5

[RFC v6 10/10] vfio-pci: Allow to mmap MSI-X table if interrupt remapping is supported

[Yongji Xie]

This patch enables mmapping MSI-X tables if hardware supports
interrupt remapping which can ensure that a given pci device
can only shoot the MSIs assigned for it.

With MSI-X table mmapped, we also need to expose the
read/write interface which will be used to access MSI-X table.

Signed-off-by: Yongji Xie <xyjxie@linux.vnet.ibm.com>
---
 drivers/vfio/pci/vfio_pci.c      |    7 +++++--
 drivers/vfio/pci/vfio_pci_rdwr.c |    3 ++-
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index dc1779c..b08abe0 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -635,7 +635,9 @@ static long vfio_pci_ioctl(void *device_data,
 				     VFIO_REGION_INFO_FLAG_WRITE;
 			if (vdev->bar_mmap_supported[info.index]) {
 				info.flags |= VFIO_REGION_INFO_FLAG_MMAP;
-				if (info.index == vdev->msix_bar) {
+				if (info.index == vdev->msix_bar &&
+					!(pdev->bus->bus_flags &
+					PCI_BUS_FLAGS_MSI_REMAP)) {
 					ret = msix_sparse_mmap_cap(vdev, &caps);
 					if (ret)
 						return ret;
@@ -1067,7 +1069,8 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 	if (req_start + req_len > phys_len)
 		return -EINVAL;
 
-	if (index == vdev->msix_bar) {
+	if (index == vdev->msix_bar &&
+		!(pdev->bus->bus_flags & PCI_BUS_FLAGS_MSI_REMAP)) {
 		/*
 		 * Disallow mmaps overlapping the MSI-X table; users don't
 		 * get to touch this directly.  We could find somewhere
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 5ffd1d9..dbf9cd0 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -164,7 +164,8 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
 	} else
 		io = vdev->barmap[bar];
 
-	if (bar == vdev->msix_bar) {
+	if (bar == vdev->msix_bar &&
+		!(pdev->bus->bus_flags & PCI_BUS_FLAGS_MSI_REMAP)) {
 		x_start = vdev->msix_offset;
 		x_end = vdev->msix_offset + vdev->msix_size;
 	}
-- 
1.7.9.5