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 the new capability is present, this puts MSIX IO memory region under mapped memory region. If the capability is not there, it falls back to the old behaviour with the sparse capability. In 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 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 <a...@ozlabs.ru> --- This is mtree and flatview BEFORE this patch: "info mtree": memory-region: p...@800000020000000.mmio 0000000000000000-ffffffffffffffff (prio 0, i/o): p...@800000020000000.mmio 0000210000000000-000021000000ffff (prio 1, i/o): 0001:03:00.0 BAR 1 000021000000e000-000021000000e5ff (prio 0, i/o): msix-table 000021000000f000-000021000000f00f (prio 0, i/o): msix-pba [disabled] 0000210000040000-000021000007ffff (prio 1, i/o): 0001:03:00.0 BAR 3 0000210000040000-000021000007ffff (prio 0, ramd): 0001:03:00.0 BAR 3 mmaps[0] "info mtree -f": FlatView #0 AS "memory", root: system AS "cpu-memory", root: system Root memory region: system 0000000000000000-000000007fffffff (prio 0, ram): ppc_spapr.ram 0000210000000000-000021000000dfff (prio 1, i/o): 0001:03:00.0 BAR 1 000021000000e000-000021000000e5ff (prio 0, i/o): msix-table 000021000000e600-000021000000ffff (prio 1, i/o): 0001:03:00.0 BAR 1 @000000000000e600 0000210000040000-000021000007ffff (prio 0, ramd): 0001:03:00.0 BAR 3 mmaps[0] This is AFTER this patch applied: "info mtree": memory-region: p...@800000020000000.mmio 0000000000000000-ffffffffffffffff (prio 0, i/o): p...@800000020000000.mmio 0000210000000000-000021000000ffff (prio 1, i/o): 0001:03:00.0 BAR 1 0000210000000000-000021000000ffff (prio 0, ramd): 0001:03:00.0 BAR 1 mmaps[0] 000021000000e000-000021000000e5ff (prio 0, i/o): msix-table [disabled] 000021000000f000-000021000000f00f (prio 0, i/o): msix-pba [disabled] 0000210000040000-000021000007ffff (prio 1, i/o): 0001:03:00.0 BAR 3 0000210000040000-000021000007ffff (prio 0, ramd): 0001:03:00.0 BAR 3 mmaps[0] "info mtree -f": FlatView #2 AS "memory", root: system AS "cpu-memory", root: system Root memory region: system 0000000000000000-000000007fffffff (prio 0, ram): ppc_spapr.ram 0000210000000000-000021000000ffff (prio 0, ramd): 0001:03:00.0 BAR 1 mmaps[0] 0000210000040000-000021000007ffff (prio 0, ramd): 0001:03:00.0 BAR 3 mmaps[0] This is AFTER this patch applied AND spapr_get_msix_emulation() patched to enable emulation: "info mtree": memory-region: p...@800000020000000.mmio 0000000000000000-ffffffffffffffff (prio 0, i/o): p...@800000020000000.mmio 0000210000000000-000021000000ffff (prio 1, i/o): 0001:03:00.0 BAR 1 0000210000000000-000021000000ffff (prio 0, ramd): 0001:03:00.0 BAR 1 mmaps[0] 000021000000e000-000021000000e5ff (prio 0, i/o): msix-table 000021000000f000-000021000000f00f (prio 0, i/o): msix-pba [disabled] 0000210000040000-000021000007ffff (prio 1, i/o): 0001:03:00.0 BAR 3 0000210000040000-000021000007ffff (prio 0, ramd): 0001:03:00.0 BAR 3 mmaps[0] "info mtree -f": FlatView #1 AS "memory", root: system AS "cpu-memory", root: system Root memory region: system 0000000000000000-000000007fffffff (prio 0, ram): ppc_spapr.ram 0000210000000000-000021000000dfff (prio 0, ramd): 0001:03:00.0 BAR 1 mmaps[0] 000021000000e000-000021000000e5ff (prio 0, i/o): msix-table 000021000000e600-000021000000ffff (prio 0, ramd): 0001:03:00.0 BAR 1 mmaps[0] @000000000000e600 0000210000040000-000021000007ffff (prio 0, ramd): 0001:03:00.0 BAR 3 mmaps[0] --- include/hw/vfio/vfio-common.h | 1 + linux-headers/linux/vfio.h | 5 +++++ hw/ppc/spapr.c | 8 ++++++++ hw/vfio/common.c | 15 +++++++++++++++ hw/vfio/pci.c | 23 +++++++++++++++++++++-- 5 files changed, 50 insertions(+), 2 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 9de63f0..693394a 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -2772,6 +2772,11 @@ 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); @@ -2853,6 +2858,8 @@ static void spapr_machine_initfn(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) @@ -3742,6 +3749,7 @@ static const TypeInfo spapr_machine_info = { /* * pseries-2.11 */ + static void spapr_machine_2_11_instance_options(MachineState *machine) { } diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 1fb8a8e..da5f182 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1411,6 +1411,21 @@ 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 c977ee3..27a3706 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. @@ -1432,6 +1437,15 @@ static void vfio_msix_early_setup(VFIOPCIDevice *vdev, Error **errp) vfio_pci_fixup_msix_region(vdev); } +static MemoryRegion *vfio_msix_parent(VFIORegion *region) +{ + if (region->nr_mmaps == 1 && region->mmaps[0].size == region->size) { + return ®ion->mmaps[0].mem; + } + + return region->mem; +} + static int vfio_msix_setup(VFIOPCIDevice *vdev, int pos, Error **errp) { int ret; @@ -1440,9 +1454,9 @@ static int vfio_msix_setup(VFIOPCIDevice *vdev, int pos, Error **errp) vdev->msix->pending = g_malloc0(BITS_TO_LONGS(vdev->msix->entries) * sizeof(unsigned long)); ret = msix_init(&vdev->pdev, vdev->msix->entries, - vdev->bars[vdev->msix->table_bar].region.mem, + vfio_msix_parent(&vdev->bars[vdev->msix->table_bar].region), vdev->msix->table_bar, vdev->msix->table_offset, - vdev->bars[vdev->msix->pba_bar].region.mem, + vfio_msix_parent(&vdev->bars[vdev->msix->pba_bar].region), vdev->msix->pba_bar, vdev->msix->pba_offset, pos, &err); if (ret < 0) { @@ -1473,6 +1487,11 @@ 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; } -- 2.11.0