PCI: Add x86_msi.msi_mask_irq() and msix_mask_irq()

Certain platforms do not allow writes in the MSI-X BARs to setup or tear
down vector values.  To combat against the generic code trying to write to
that and either silently being ignored or crashing due to the pagetables
being marked R/O this patch introduces a platform override.

Note that we keep two separate, non-weak, functions default_mask_msi_irqs()
and default_mask_msix_irqs() for the behavior of the arch_mask_msi_irqs()
and arch_mask_msix_irqs(), as the default behavior is needed by x86 PCI
code.

For Xen, which does not allow the guest to write to MSI-X tables - as the
hypervisor is solely responsible for setting the vector values - we
implement two nops.

This fixes a Xen guest crash when passing a PCI device with MSI-X to the
guest.  See the bugzilla for more details.

[bhelgaas: add bugzilla info]
Reference: https://bugzilla.kernel.org/show_bug.cgi?id=64581
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com>
CC: Zhenzhong Duan <zhenzhong.duan@oracle.com>

1 files changed, 16 insertions, 6 deletions

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 604265c40853..5e63645a7abe 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -185,7 +185,7 @@ static inline __attribute_const__ u32 msi_enabled_mask(u16 control)
  * reliably as devices without an INTx disable bit will then generate a
  * level IRQ which will never be cleared.
  */
-static u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 {
 	u32 mask_bits = desc->masked;
 
@@ -199,9 +199,14 @@ static u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 	return mask_bits;
 }
 
+__weak u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
+{
+	return default_msi_mask_irq(desc, mask, flag);
+}
+
 static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
 {
-	desc->masked = __msi_mask_irq(desc, mask, flag);
+	desc->masked = arch_msi_mask_irq(desc, mask, flag);
 }
 
 /*
@@ -211,7 +216,7 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
  * file.  This saves a few milliseconds when initialising devices with lots
  * of MSI-X interrupts.
  */
-static u32 __msix_mask_irq(struct msi_desc *desc, u32 flag)
+u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag)
 {
 	u32 mask_bits = desc->masked;
 	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
@@ -224,9 +229,14 @@ static u32 __msix_mask_irq(struct msi_desc *desc, u32 flag)
 	return mask_bits;
 }
 
+__weak u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag)
+{
+	return default_msix_mask_irq(desc, flag);
+}
+
 static void msix_mask_irq(struct msi_desc *desc, u32 flag)
 {
-	desc->masked = __msix_mask_irq(desc, flag);
+	desc->masked = arch_msix_mask_irq(desc, flag);
 }
 
 static void msi_set_mask_bit(struct irq_data *data, u32 flag)
@@ -902,7 +912,7 @@ void pci_msi_shutdown(struct pci_dev *dev)
 	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &ctrl);
 	mask = msi_capable_mask(ctrl);
 	/* Keep cached state to be restored */
-	__msi_mask_irq(desc, mask, ~mask);
+	arch_msi_mask_irq(desc, mask, ~mask);
 
 	/* Restore dev->irq to its default pin-assertion irq */
 	dev->irq = desc->msi_attrib.default_irq;
@@ -998,7 +1008,7 @@ void pci_msix_shutdown(struct pci_dev *dev)
 	/* Return the device with MSI-X masked as initial states */
 	list_for_each_entry(entry, &dev->msi_list, list) {
 		/* Keep cached states to be restored */
-		__msix_mask_irq(entry, 1);
+		arch_msix_mask_irq(entry, 1);
 	}
 
 	msix_set_enable(dev, 0);