vfio-pci: add MSI-X support

Add virtual MSI-X tables for PCI devices, and create IRQFD routes to let
the kernel inject MSIs from a physical device directly into the guest.

It would be tempting to create the MSI routes at init time before starting
vCPUs, when we can afford to exit gracefully. But some of it must be
initialized when the guest requests it.

* On the KVM side, MSIs must be enabled after devices allocate their IRQ
  lines and irqchips are operational, which can happen until late_init.

* On the VFIO side, hardware state of devices may be updated when setting
  up MSIs. For example, when passing a virtio-pci-legacy device to the
  guest:

  (1) The device-specific configuration layout (in BAR0) depends on
      whether MSIs are enabled or not in the device. If they are enabled,
      the device-specific configuration starts at offset 24, otherwise it
      starts at offset 20.
  (2) Linux guest assumes that MSIs are initially disabled (doesn't
      actually check the capability). So it reads the device config at
      offset 20.
  (3) Had we enabled MSIs early, host would have enabled the MSI-X
      capability and device would return the config at offset 24.
  (4) The guest would read junk and explode.

Therefore we have to create MSI-X routes when the guest requests MSIs, and
enable/disable them in VFIO when the guest pokes the MSI-X capability. We
have to follow both physical and virtual state of the capability, which
makes the state machine a bit complex, but I think it works.

An important missing feature is the absence of pending MSI handling. When
a vector or the function is masked, we should rewire the IRQFD to a
special thread that keeps note of pending interrupts (or just poll the
IRQFD before recreating the route?). And when the vector is unmasked, one
MSI should be injected if it was pending. At the moment no MSI is
injected, we simply disconnect the IRQFD and all messages are lost.

Reviewed-by: Punit Agrawal <punit.agrawal@arm.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

1 files changed, 52 insertions, 0 deletions

diff --git a/include/kvm/vfio.h b/include/kvm/vfio.h
index c434703a..483ba7e4 100644
--- a/include/kvm/vfio.h
+++ b/include/kvm/vfio.h
@@ -1,6 +1,7 @@
 #ifndef KVM__VFIO_H
 #define KVM__VFIO_H
 
+#include "kvm/mutex.h"
 #include "kvm/parse-options.h"
 #include "kvm/pci.h"
 
@@ -24,8 +25,59 @@ enum vfio_device_type {
 	VFIO_DEVICE_PCI,
 };
 
+/* MSI/MSI-X capability enabled */
+#define VFIO_PCI_MSI_STATE_ENABLED	(1 << 0)
+/* MSI/MSI-X capability or individual vector masked */
+#define VFIO_PCI_MSI_STATE_MASKED	(1 << 1)
+/* MSI-X capability has no vector enabled yet */
+#define VFIO_PCI_MSI_STATE_EMPTY	(1 << 2)
+
+struct vfio_pci_msi_entry {
+	struct msix_table		config;
+	int				gsi;
+	int				eventfd;
+	u8				phys_state;
+	u8				virt_state;
+};
+
+struct vfio_pci_msix_table {
+	size_t				size;
+	unsigned int			bar;
+	u32				guest_phys_addr;
+};
+
+struct vfio_pci_msix_pba {
+	size_t				size;
+	off_t				offset; /* in VFIO device fd */
+	unsigned int			bar;
+	u32				guest_phys_addr;
+};
+
+/* Common data for MSI and MSI-X */
+struct vfio_pci_msi_common {
+	off_t				pos;
+	u8				virt_state;
+	u8				phys_state;
+	struct mutex			mutex;
+	struct vfio_irq_info		info;
+	struct vfio_irq_set		*irq_set;
+	size_t				nr_entries;
+	struct vfio_pci_msi_entry	*entries;
+};
+
+#define VFIO_PCI_IRQ_MODE_INTX		(1 << 0)
+#define VFIO_PCI_IRQ_MODE_MSI		(1 << 1)
+#define VFIO_PCI_IRQ_MODE_MSIX		(1 << 2)
+
 struct vfio_pci_device {
 	struct pci_device_header	hdr;
+
+	unsigned long			irq_modes;
+	int				intx_fd;
+	unsigned int			intx_gsi;
+	struct vfio_pci_msi_common	msix;
+	struct vfio_pci_msix_table	msix_table;
+	struct vfio_pci_msix_pba	msix_pba;
 };
 
 struct vfio_region {