[Qemu-devel] [PATCH qemu v4] RFC: vfio-pci: Allow mmap of MSIX BAR

[Alexey Kardashevskiy <aik@ozlabs.ru>]

This makes use of a new VFIO_REGION_INFO_CAP_MSIX_MAPPABLE capability
which tells that a region with MSIX data can be mapped entirely, i.e.
the VFIO PCI driver won't prevent MSIX vectors area from being mapped.

With this change, all BARs are mapped in a single chunk and MSIX vectors
are emulated on top unless the machine requests not to by defining and
enabling a new "vfio-no-msix-emulation" property. At the moment only
sPAPR machine does so - it prohibits MSIX emulation and does not allow
enabling it as it does not define the "set" callback for the new property;
the new property also does not appear in "-machine pseries,help".

If MSIX vectors section is not aligned to the page size, the KVM memory
listener does not register it with the KVM as a memory slot and MSIX is
emulated by QEMU as before. This may create MMIO RAM memory sections with
an address or/and a size not aligned which will make vfio_dma_map() fail;
to address this, this treats such failures as non-fatal and does not print
an error. This adds a return value from vfio_dma_map() to the tracepoint
and moves the latter further down to let the user have a clue why P2P
might not work.

This requires the kernel change - "vfio-pci: Allow mapping MSIX BAR" -
for the new capability: https://www.spinics.net/lists/kvm/msg160282.html

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Changes:
v4:
* silenced dma map errors if unaligned mapping is attempted - they are going
to fail anyway

v3:
* vfio_listener_region_add() won't make qemu exit if failed on MMIO MR
---
 include/hw/vfio/vfio-common.h |  1 +
 linux-headers/linux/vfio.h    |  5 +++++
 hw/ppc/spapr.c                |  7 +++++++
 hw/vfio/common.c              | 27 +++++++++++++++++++++++++--
 hw/vfio/pci.c                 | 10 ++++++++++
 hw/vfio/trace-events          |  2 +-
 6 files changed, 49 insertions(+), 3 deletions(-)

diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index f3a2ac9..927d600 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -171,6 +171,7 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index,
                          struct vfio_region_info **info);
 int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
                              uint32_t subtype, struct vfio_region_info **info);
+bool vfio_is_cap_present(VFIODevice *vbasedev, uint16_t cap_type, int region);
 #endif
 extern const MemoryListener vfio_prereg_listener;
 
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index 4312e96..b45182e 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -301,6 +301,11 @@ struct vfio_region_info_cap_type {
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_HOST_CFG	(2)
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG	(3)
 
+/*
+ * The MSIX mappable capability informs that MSIX data of a BAR can be mmapped.
+ */
+#define VFIO_REGION_INFO_CAP_MSIX_MAPPABLE	3
+
 /**
  * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9,
  *				    struct vfio_irq_info)
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index d1acfe8..5ff43ce 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -2789,6 +2789,11 @@ static void spapr_set_modern_hotplug_events(Object *obj, bool value,
     spapr->use_hotplug_event_source = value;
 }
 
+static bool spapr_get_msix_emulation(Object *obj, Error **errp)
+{
+    return true;
+}
+
 static char *spapr_get_resize_hpt(Object *obj, Error **errp)
 {
     sPAPRMachineState *spapr = SPAPR_MACHINE(obj);
@@ -2870,6 +2875,8 @@ static void spapr_instance_init(Object *obj)
     object_property_set_description(obj, "vsmt",
                                     "Virtual SMT: KVM behaves as if this were"
                                     " the host's SMT mode", &error_abort);
+    object_property_add_bool(obj, "vfio-no-msix-emulation",
+                             spapr_get_msix_emulation, NULL, NULL);
 }
 
 static void spapr_machine_finalizefn(Object *obj)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 3d652c8..04a8280 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -513,13 +513,21 @@ static void vfio_listener_region_add(MemoryListener *listener,
             section->offset_within_region +
             (iova - section->offset_within_address_space);
 
-    trace_vfio_listener_region_add_ram(iova, end, vaddr);
-
     llsize = int128_sub(llend, int128_make64(iova));
 
     ret = vfio_dma_map(container, iova, int128_get64(llsize),
                        vaddr, section->readonly);
+    trace_vfio_listener_region_add_ram(iova, end, vaddr, ret);
+
     if (ret) {
+        hwaddr pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1;
+
+        if (memory_region_is_ram_device(section->mr) &&
+            ((section->offset_within_region & pgmask) ||
+             (int128_getlo(section->size) & pgmask))) {
+            return;
+        }
+
         error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", "
                      "0x%"HWADDR_PRIx", %p) = %d (%m)",
                      container, iova, int128_get64(llsize), vaddr, ret);
@@ -1386,6 +1394,21 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type,
     return -ENODEV;
 }
 
+bool vfio_is_cap_present(VFIODevice *vbasedev, uint16_t cap_type, int region)
+{
+    struct vfio_region_info *info = NULL;
+    bool ret = false;
+
+    if (!vfio_get_region_info(vbasedev, region, &info)) {
+        if (vfio_get_region_info_cap(info, cap_type)) {
+            ret = true;
+        }
+        g_free(info);
+    }
+
+    return ret;
+}
+
 /*
  * Interfaces for IBM EEH (Enhanced Error Handling)
  */
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 359a8f1..a96ece6 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -1289,6 +1289,11 @@ static void vfio_pci_fixup_msix_region(VFIOPCIDevice *vdev)
     off_t start, end;
     VFIORegion *region = &vdev->bars[vdev->msix->table_bar].region;
 
+    if (vfio_is_cap_present(&vdev->vbasedev, VFIO_REGION_INFO_CAP_MSIX_MAPPABLE,
+                            vdev->msix->table_bar)) {
+        return;
+    }
+
     /*
      * We expect to find a single mmap covering the whole BAR, anything else
      * means it's either unsupported or already setup.
@@ -1569,6 +1574,11 @@ static int vfio_msix_setup(VFIOPCIDevice *vdev, int pos, Error **errp)
      */
     memory_region_set_enabled(&vdev->pdev.msix_pba_mmio, false);
 
+    if (object_property_get_bool(OBJECT(qdev_get_machine()),
+                                 "vfio-no-msix-emulation", NULL)) {
+        memory_region_set_enabled(&vdev->pdev.msix_table_mmio, false);
+    }
+
     return 0;
 }
 
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 437ccdd..d747c11 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -89,7 +89,7 @@ vfio_region_read(char *name, int index, uint64_t addr, unsigned size, uint64_t d
 vfio_iommu_map_notify(const char *op, uint64_t iova_start, uint64_t iova_end) "iommu %s @ 0x%"PRIx64" - 0x%"PRIx64
 vfio_listener_region_add_skip(uint64_t start, uint64_t end) "SKIPPING region_add 0x%"PRIx64" - 0x%"PRIx64
 vfio_listener_region_add_iommu(uint64_t start, uint64_t end) "region_add [iommu] 0x%"PRIx64" - 0x%"PRIx64
-vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr) "region_add [ram] 0x%"PRIx64" - 0x%"PRIx64" [%p]"
+vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr, int ret) "region_add [ram] 0x%"PRIx64" - 0x%"PRIx64" [%p] ret=%d"
 vfio_listener_region_del_skip(uint64_t start, uint64_t end) "SKIPPING region_del 0x%"PRIx64" - 0x%"PRIx64
 vfio_listener_region_del(uint64_t start, uint64_t end) "region_del 0x%"PRIx64" - 0x%"PRIx64
 vfio_disconnect_container(int fd) "close container->fd=%d"
-- 
2.11.0