At the moment we unconditionally avoid mapping MSIX data of a BAR and emulate MSIX table in QEMU. However it is 1) not always necessary as a platform may prodive a paravirt interface for MSIX configuration; 2) can affect the speed of MMIO access by emulating them in QEMU when frequently accessed registers share same system page with MSIX data, this is particularly a problem for systems with the page size bigger than 4KB.
A new capability - VFIO_REGION_INFO_CAP_MSIX_MAPPABLE - has been added to the kernel [1] which tells the userspace that mapping of the MSIX data is possible now. This makes use of it so from now on QEMU tries mapping the entire BAR as a whole and emulate MSIX on top of that. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=a32295c612c57990d17fb0f41e7134394b2f35f6 Signed-off-by: Alexey Kardashevskiy <[email protected]> --- Changes: v7: * test iova/llsize against pgmask in vfio_listener_region_add/del * s/vfio_is_cap_present/vfio_has_region_cap/ * added comments here and there * s/vdev->msix->table_bar/region-nr/ --- include/hw/vfio/vfio-common.h | 1 + hw/vfio/common.c | 15 +++++++++++++++ hw/vfio/pci.c | 9 +++++++++ 3 files changed, 25 insertions(+) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index f3a2ac9..42dd2b0 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_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type); #endif extern const MemoryListener vfio_prereg_listener; diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 736f271..b99ae77 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1464,6 +1464,21 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, return -ENODEV; } +bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type) +{ + 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 879510c..ae9098d 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -1294,6 +1294,15 @@ static void vfio_pci_fixup_msix_region(VFIOPCIDevice *vdev) VFIORegion *region = &vdev->bars[vdev->msix->table_bar].region; /* + * If the host driver allows mapping of a MSIX data, we are going to + * do map the entire BAR and emulate MSIX table on top of that. + */ + if (vfio_has_region_cap(&vdev->vbasedev, region->nr, + VFIO_REGION_INFO_CAP_MSIX_MAPPABLE)) { + return; + } + + /* * We expect to find a single mmap covering the whole BAR, anything else * means it's either unsupported or already setup. */ -- 2.11.0
