packages/qemu
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

vfio: Set up nested stage mappings

Browse Source 
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_listener 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 PCIPASIDOps callback. Guest IOTLB invalidations
are cascaded downto the host through another IOMMU MR UNMAP
notifier.

Signed-off-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Kunkun Jiang <jiangkunkun@huawei.com>
Signed-off-by: imxcc <xingchaochao@huawei.com>
(cherry picked from commit 0b8a30af7d1c4e85b6e00dbf2569dc9e0a2e254f)
This commit is contained in:
Chen Qun 2018-08-29 18:10:12 +02:00 committed by yezengruan
parent cc885c623f
commit 5ddcc899dd
1 changed files with 281 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

281
vfio-Set-up-nested-stage-mappings.patch Normal file
View File

@ -0,0 +1,281 @@
From 96581a5ee46e89dbc9e1ebe247b00adefb1c7a41 Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Wed, 29 Aug 2018 18:10:12 +0200
Subject: [PATCH] vfio: Set up nested stage mappings
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_listener 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 PCIPASIDOps callback. Guest IOTLB invalidations
are cascaded downto the host through another IOMMU MR UNMAP
notifier.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Kunkun Jiang <jiangkunkun@huawei.com>
---
hw/vfio/common.c | 139 +++++++++++++++++++++++++++++++++++++++++--
hw/vfio/pci.c | 21 +++++++
hw/vfio/trace-events | 2 +
3 files changed, 157 insertions(+), 5 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index b3dc090840..58f8a43a43 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -707,6 +707,73 @@ static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
return true;
}
+/* 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);
+ struct vfio_iommu_type1_cache_invalidate ustruct = {};
+ VFIOContainer *container = giommu->container;
+ int ret;
+
+ assert(iotlb->perm == IOMMU_NONE);
+
+ ustruct.argsz = sizeof(ustruct);
+ ustruct.flags = 0;
+ ustruct.info.argsz = sizeof(struct iommu_cache_invalidate_info);
+ ustruct.info.version = IOMMU_CACHE_INVALIDATE_INFO_VERSION_1;
+ ustruct.info.cache = IOMMU_CACHE_INV_TYPE_IOTLB;
+
+ switch (iotlb->granularity) {
+ case IOMMU_INV_GRAN_DOMAIN:
+ ustruct.info.granularity = IOMMU_INV_GRANU_DOMAIN;
+ break;
+ case IOMMU_INV_GRAN_PASID:
+ {
+ struct iommu_inv_pasid_info *pasid_info;
+ int archid = -1;
+
+ pasid_info = &ustruct.info.granu.pasid_info;
+ ustruct.info.granularity = IOMMU_INV_GRANU_PASID;
+ if (iotlb->flags & IOMMU_INV_FLAGS_ARCHID) {
+ pasid_info->flags |= IOMMU_INV_ADDR_FLAGS_ARCHID;
+ archid = iotlb->arch_id;
+ }
+ pasid_info->archid = archid;
+ trace_vfio_iommu_asid_inv_iotlb(archid);
+ break;
+ }
+ case IOMMU_INV_GRAN_ADDR:
+ {
+ hwaddr start = iotlb->iova + giommu->iommu_offset;
+ struct iommu_inv_addr_info *addr_info;
+ size_t size = iotlb->addr_mask + 1;
+ int archid = -1;
+
+ addr_info = &ustruct.info.granu.addr_info;
+ ustruct.info.granularity = IOMMU_INV_GRANU_ADDR;
+ if (iotlb->leaf) {
+ addr_info->flags |= IOMMU_INV_ADDR_FLAGS_LEAF;
+ }
+ if (iotlb->flags & IOMMU_INV_FLAGS_ARCHID) {
+ addr_info->flags |= IOMMU_INV_ADDR_FLAGS_ARCHID;
+ archid = iotlb->arch_id;
+ }
+ addr_info->archid = archid;
+ addr_info->addr = start;
+ addr_info->granule_size = size;
+ addr_info->nb_granules = 1;
+ trace_vfio_iommu_addr_inv_iotlb(archid, start, size,
+ 1, iotlb->leaf);
+ break;
+ }
+ }
+
+ ret = ioctl(container->fd, VFIO_IOMMU_CACHE_INVALIDATE, &ustruct);
+ if (ret) {
+ error_report("%p: failed to invalidate CACHE (%d)", container, ret);
+ }
+}
+
static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
{
VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
@@ -1040,6 +1107,35 @@ 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);
+ Error *err = NULL;
+
+ if (!memory_region_is_ram(section->mr)) {
+ return;
+ }
+
+ vfio_dma_map_ram_section(container, section, &err);
+ if (err) {
+ error_report_err(err);
+ }
+}
+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)
{
@@ -1150,9 +1246,10 @@ static void vfio_listener_region_add(MemoryListener *listener,
memory_region_ref(section->mr);
if (memory_region_is_iommu(section->mr)) {
+ IOMMUNotify notify;
VFIOGuestIOMMU *giommu;
IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr);
- int iommu_idx;
+ int iommu_idx, flags;
trace_vfio_listener_region_add_iommu(iova, end);
/*
@@ -1171,8 +1268,18 @@ static void vfio_listener_region_add(MemoryListener *listener,
llend = int128_sub(llend, int128_one());
iommu_idx = memory_region_iommu_attrs_to_index(iommu_mr,
MEMTXATTRS_UNSPECIFIED);
- iommu_notifier_init(&giommu->n, vfio_iommu_map_notify,
- IOMMU_NOTIFIER_IOTLB_EVENTS,
+
+ if (container->iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
+ /* IOTLB unmap notifier to propagate guest IOTLB invalidations */
+ flags = IOMMU_NOTIFIER_UNMAP;
+ notify = vfio_iommu_unmap_notify;
+ } else {
+ /* MAP/UNMAP IOTLB notifier */
+ flags = IOMMU_NOTIFIER_IOTLB_EVENTS;
+ notify = vfio_iommu_map_notify;
+ }
+
+ iommu_notifier_init(&giommu->n, notify, flags,
section->offset_within_region,
int128_get64(llend),
iommu_idx);
@@ -1192,7 +1299,9 @@ static void vfio_listener_region_add(MemoryListener *listener,
goto fail;
}
QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
- memory_region_iommu_replay(giommu->iommu, &giommu->n);
+ if (flags & IOMMU_NOTIFIER_MAP) {
+ memory_region_iommu_replay(giommu->iommu, &giommu->n);
+ }
return;
}
@@ -1672,10 +1781,16 @@ static const MemoryListener vfio_memory_listener = {
.log_clear = vfio_listener_log_clear,
};
+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);
}
}
@@ -2351,6 +2466,20 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
vfio_get_iommu_info_migration(container, info);
}
g_free(info);
+
+ 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 = -1;
+ error_propagate_prepend(errp, container->error,
+ "RAM memory listener initialization failed "
+ "for container");
+ goto free_container_exit;
+ }
+ }
break;
}
case VFIO_SPAPR_TCE_v2_IOMMU:
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 7b45353ce2..ae5e014e5d 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2797,6 +2797,25 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev)
vdev->req_enabled = false;
}
+static int vfio_iommu_set_pasid_table(PCIBus *bus, int32_t devfn,
+ IOMMUConfig *config)
+{
+ PCIDevice *pdev = bus->devices[devfn];
+ VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev);
+ VFIOContainer *container = vdev->vbasedev.group->container;
+ struct vfio_iommu_type1_set_pasid_table info;
+
+ info.argsz = sizeof(info);
+ info.flags = VFIO_PASID_TABLE_FLAG_SET;
+ memcpy(&info.config, &config->pasid_cfg, sizeof(config->pasid_cfg));
+
+ return ioctl(container->fd, VFIO_IOMMU_SET_PASID_TABLE, &info);
+}
+
+static PCIPASIDOps vfio_pci_pasid_ops = {
+ .set_pasid_table = vfio_iommu_set_pasid_table,
+};
+
static void vfio_realize(PCIDevice *pdev, Error **errp)
{
VFIOPCIDevice *vdev = VFIO_PCI(pdev);
@@ -3108,6 +3127,8 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
vfio_register_req_notifier(vdev);
vfio_setup_resetfn_quirk(vdev);
+ pci_setup_pasid_ops(pdev, &vfio_pci_pasid_ops);
+
return;
out_deregister:
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index a37563a315..20069935f5 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -118,6 +118,8 @@ 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"
--
2.27.0