[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [RFC v4 20/27] hw/vfio/common: Setup nested stage mappings
From: |
Eric Auger |
Subject: |
[Qemu-devel] [RFC v4 20/27] hw/vfio/common: Setup nested stage mappings |
Date: |
Mon, 27 May 2019 13:41:56 +0200 |
In nested mode, legacy vfio_iommu_map_notify cannot be used as
there is no "caching" mode and we do not trap on map.
On Intel, vfio_iommu_map_notify was used to DMA map the RAM
through the host single stage.
With nested mode, we need to setup the stage 2 and the stage 1
separately. This patch introduces a prereg_lsitener to setup
the stage 2 mapping.
The stage 1 mapping, owned by the guest, is passed to the host
when the guest invalidates the stage 1 configuration, through
a dedicated config IOMMU notifier. Guest IOTLB invalidations
are cascaded downto the host through another IOMMU MR UNMAP
notifier.
Signed-off-by: Eric Auger <address@hidden>
---
v3 -> v4:
- use iommu_inv_pasid_info for ASID invalidation
v2 -> v3:
- use VFIO_IOMMU_ATTACH_PASID_TABLE
- new user API
- handle leaf
v1 -> v2:
- adapt to uapi changes
- pass the asid
- pass IOMMU_NOTIFIER_S1_CFG when initializing the config notifier
---
hw/vfio/common.c | 151 +++++++++++++++++++++++++++++++++++++++----
hw/vfio/trace-events | 2 +
2 files changed, 142 insertions(+), 11 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 26bc2ab19f..084e3f30e6 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -445,6 +445,71 @@ static bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void
**vaddr,
return true;
}
+/* Pass the guest stage 1 config to the host */
+static void vfio_iommu_nested_notify(IOMMUNotifier *n, IOMMUConfig *cfg)
+{
+ VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
+ VFIOContainer *container = giommu->container;
+ struct vfio_iommu_type1_attach_pasid_table info;
+ int ret;
+
+ info.argsz = sizeof(info);
+ info.flags = 0;
+ memcpy(&info.config, &cfg->pasid_cfg, sizeof(cfg->pasid_cfg));
+
+ ret = ioctl(container->fd, VFIO_IOMMU_ATTACH_PASID_TABLE, &info);
+ if (ret) {
+ error_report("%p: failed to pass S1 config to the host (%d)",
+ container, ret);
+ }
+}
+
+/* Propagate a guest IOTLB invalidation to the host (nested mode) */
+static void vfio_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
+{
+ VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
+ hwaddr start = iotlb->iova + giommu->iommu_offset;
+
+ VFIOContainer *container = giommu->container;
+ struct vfio_iommu_type1_cache_invalidate ustruct;
+ size_t size = iotlb->addr_mask + 1;
+ int ret;
+
+ assert(iotlb->perm == IOMMU_NONE);
+
+ ustruct.argsz = sizeof(ustruct);
+ ustruct.flags = 0;
+ ustruct.info.version = IOMMU_CACHE_INVALIDATE_INFO_VERSION_1;
+
+ if (size <= 0x10000) {
+ ustruct.info.cache = IOMMU_CACHE_INV_TYPE_IOTLB;
+ ustruct.info.granularity = IOMMU_INV_GRANU_ADDR;
+ ustruct.info.addr_info.flags = IOMMU_INV_ADDR_FLAGS_ARCHID;
+ if (iotlb->leaf) {
+ ustruct.info.addr_info.flags |= IOMMU_INV_ADDR_FLAGS_LEAF;
+ }
+ ustruct.info.addr_info.archid = iotlb->arch_id;
+ ustruct.info.addr_info.addr = start;
+ ustruct.info.addr_info.granule_size = size;
+ ustruct.info.addr_info.nb_granules = 1;
+ trace_vfio_iommu_addr_inv_iotlb(iotlb->arch_id, start, size, 1,
+ iotlb->leaf);
+ } else {
+ ustruct.info.cache = IOMMU_CACHE_INV_TYPE_IOTLB;
+ ustruct.info.granularity = IOMMU_INV_GRANU_PASID;
+ ustruct.info.pasid_info.archid = iotlb->arch_id;
+ ustruct.info.pasid_info.flags = IOMMU_INV_PASID_FLAGS_ARCHID;
+ trace_vfio_iommu_asid_inv_iotlb(iotlb->arch_id);
+ }
+
+ ret = ioctl(container->fd, VFIO_IOMMU_CACHE_INVALIDATE, &ustruct);
+ if (ret) {
+ error_report("%p: failed to invalidate CACHE for 0x%"PRIx64
+ " mask=0x%"PRIx64" (%d)",
+ container, start, iotlb->addr_mask, ret);
+ }
+}
+
static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
{
VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
@@ -628,6 +693,32 @@ static void vfio_dma_unmap_ram_section(VFIOContainer
*container,
}
}
+static void vfio_prereg_listener_region_add(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+ VFIOContainer *container =
+ container_of(listener, VFIOContainer, prereg_listener);
+
+ if (!memory_region_is_ram(section->mr)) {
+ return;
+ }
+
+ vfio_dma_map_ram_section(container, section);
+
+}
+static void vfio_prereg_listener_region_del(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+ VFIOContainer *container =
+ container_of(listener, VFIOContainer, prereg_listener);
+
+ if (!memory_region_is_ram(section->mr)) {
+ return;
+ }
+
+ vfio_dma_unmap_ram_section(container, section);
+}
+
static void vfio_listener_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
@@ -739,21 +830,40 @@ static void vfio_listener_region_add(MemoryListener
*listener,
offset = section->offset_within_address_space -
section->offset_within_region;
- giommu = vfio_alloc_guest_iommu(container, iommu_mr, offset);
-
llend = int128_add(int128_make64(section->offset_within_region),
section->size);
llend = int128_sub(llend, int128_one());
iommu_idx = memory_region_iommu_attrs_to_index(iommu_mr,
MEMTXATTRS_UNSPECIFIED);
- iommu_iotlb_notifier_init(&giommu->n, vfio_iommu_map_notify,
- IOMMU_NOTIFIER_IOTLB_ALL,
- section->offset_within_region,
- int128_get64(llend),
- iommu_idx);
- QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
- memory_region_register_iommu_notifier(section->mr, &giommu->n);
+ if (container->iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
+ /* Config notifier to propagate guest stage 1 config changes */
+ giommu = vfio_alloc_guest_iommu(container, iommu_mr, offset);
+ iommu_config_notifier_init(&giommu->n, vfio_iommu_nested_notify,
+ IOMMU_NOTIFIER_CONFIG_PASID, iommu_idx);
+ QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
+ memory_region_register_iommu_notifier(section->mr, &giommu->n);
+
+ /* IOTLB unmap notifier to propagate guest IOTLB invalidations */
+ giommu = vfio_alloc_guest_iommu(container, iommu_mr, offset);
+ iommu_iotlb_notifier_init(&giommu->n, vfio_iommu_unmap_notify,
+ IOMMU_NOTIFIER_IOTLB_UNMAP,
+ section->offset_within_region,
+ int128_get64(llend),
+ iommu_idx);
+ QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
+ memory_region_register_iommu_notifier(section->mr, &giommu->n);
+ } else {
+ /* MAP/UNMAP IOTLB notifier */
+ giommu = vfio_alloc_guest_iommu(container, iommu_mr, offset);
+ iommu_iotlb_notifier_init(&giommu->n, vfio_iommu_map_notify,
+ IOMMU_NOTIFIER_IOTLB_ALL,
+ section->offset_within_region,
+ int128_get64(llend),
+ iommu_idx);
+ QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
+ memory_region_register_iommu_notifier(section->mr, &giommu->n);
+ }
memory_region_iommu_replay(giommu->iommu, &giommu->n);
return;
@@ -850,15 +960,21 @@ static void vfio_listener_region_del(MemoryListener
*listener,
}
}
-static const MemoryListener vfio_memory_listener = {
+static MemoryListener vfio_memory_listener = {
.region_add = vfio_listener_region_add,
.region_del = vfio_listener_region_del,
};
+static MemoryListener vfio_memory_prereg_listener = {
+ .region_add = vfio_prereg_listener_region_add,
+ .region_del = vfio_prereg_listener_region_del,
+};
+
static void vfio_listener_release(VFIOContainer *container)
{
memory_listener_unregister(&container->listener);
- if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
+ if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU ||
+ container->iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
memory_listener_unregister(&container->prereg_listener);
}
}
@@ -1354,6 +1470,19 @@ static int vfio_connect_container(VFIOGroup *group,
AddressSpace *as,
}
vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes);
container->pgsizes = info.iova_pgsizes;
+
+ if (container->iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
+ container->prereg_listener = vfio_memory_prereg_listener;
+ memory_listener_register(&container->prereg_listener,
+ &address_space_memory);
+ if (container->error) {
+ memory_listener_unregister(&container->prereg_listener);
+ ret = container->error;
+ error_setg(errp, "RAM memory listener initialization failed "
+ " for container");
+ goto free_container_exit;
+ }
+ }
break;
}
case VFIO_SPAPR_TCE_v2_IOMMU:
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 410801de6e..9f1868af2d 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -115,6 +115,8 @@ vfio_region_sparse_mmap_header(const char *name, int index,
int nr_areas) "Devic
vfio_region_sparse_mmap_entry(int i, unsigned long start, unsigned long end)
"sparse entry %d [0x%lx - 0x%lx]"
vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t
subtype) "%s index %d, %08x/%0x8"
vfio_dma_unmap_overflow_workaround(void) ""
+vfio_iommu_addr_inv_iotlb(int asid, uint64_t addr, uint64_t size, uint64_t
nb_granules, bool leaf) "nested IOTLB invalidate asid=%d, addr=0x%"PRIx64"
granule_size=0x%"PRIx64" nb_granules=0x%"PRIx64" leaf=%d"
+vfio_iommu_asid_inv_iotlb(int asid) "nested IOTLB invalidate asid=%d"
# platform.c
vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group
#%d"
--
2.20.1
- [Qemu-devel] [RFC v4 10/27] memory: Add IOMMUConfigNotifier, (continued)
- [Qemu-devel] [RFC v4 10/27] memory: Add IOMMUConfigNotifier, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 11/27] memory: Add arch_id and leaf fields in IOTLBEntry, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 12/27] hw/arm/smmuv3: Store the PASID table GPA in the translation config, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 13/27] hw/arm/smmuv3: Implement dummy replay, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 14/27] hw/arm/smmuv3: Fill the IOTLBEntry arch_id on NH_VA invalidation, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 15/27] hw/arm/smmuv3: Fill the IOTLBEntry leaf field on NH_VA invalidation, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 16/27] hw/arm/smmuv3: Notify on config changes, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 17/27] hw/vfio/common: Introduce vfio_alloc_guest_iommu helper, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 18/27] hw/vfio/common: Introduce hostwin_from_range helper, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 19/27] hw/vfio/common: Introduce helpers to DMA map/unmap a RAM section, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 20/27] hw/vfio/common: Setup nested stage mappings,
Eric Auger <=
- [Qemu-devel] [RFC v4 21/27] hw/vfio/common: Register a MAP notifier for MSI binding, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 22/27] vfio-pci: Expose MSI stage 1 bindings to the host, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 23/27] memory: Introduce IOMMU Memory Region inject_faults API, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 26/27] vfio-pci: Set up fault regions, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 27/27] vfio-pci: Implement the DMA fault handler, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 25/27] vfio-pci: register handler for iommu fault, Eric Auger, 2019/05/27
- [Qemu-devel] [RFC v4 24/27] hw/arm/smmuv3: Implement fault injection, Eric Auger, 2019/05/27
- Re: [Qemu-devel] [RFC v4 00/27] vSMMUv3/pSMMUv3 2 stage VFIO integration, no-reply, 2019/05/27