- Revert "linux-user: Print tid not pid with strace" - gpex-acpi: Remove duplicate DSM #5 - smmuv3: Use default bus for arm-smmuv3-accel - smmuv3: Change arm-smmuv3-nested name to arm-smmuv3-accel - smmu-common: Return sysmem address space only for vfio-pci - smmuv3: realize get_pasid_cap and set ssidsize with pasid - vfio: Synthesize vPASID capability to VM - backend/iommufd: Report PASID capability - pci: Get pasid capability from vIOMMU - smmuv3: Add support for page fault handling - kvm: Translate MSI doorbell address only if it is valid - hw/arm/smmuv3: Enable sva/stall IDR features - iommufd.h: Updated to openeuler olk-6.6 kernel - tests/data/acpi/virt: Update IORT acpi table - hw/arm/virt-acpi-build: Add IORT RMR regions to handle MSI nested binding - tests/qtest: Allow IORT acpi table to change - hw/arm/virt-acpi-build: Build IORT with multiple SMMU nodes - hw/arm/smmuv3: Associate a pci bus with a SMMUv3 Nested device - hw/arm/smmuv3: Add initial support for SMMUv3 Nested device - hw/arm/virt: Add an SMMU_IO_LEN macro - hw/pci-host/gpex: [needs kernel fix] Allow to generate preserve boot config DSM #5 - tests/data/acpi: Update DSDT acpi tables - acpi/gpex: Fix PCI Express Slot Information function 0 returned value - tests/qtest: Allow DSDT acpi tables to change - hw/arm/smmuv3: Forward cache invalidate commands via iommufd - hw/arm/smmu-common: Replace smmu_iommu_mr with smmu_find_sdev - hw/arm/smmuv3: Add missing STE invalidation - hw/arm/smmuv3: Add smmu_dev_install_nested_ste() for CFGI_STE - hw/arm/smmuv3: Check idr registers for STE_S1CDMAX and STE_S1STALLD - hw/arm/smmuv3: Read host SMMU device info - hw/arm/smmuv3: Ignore IOMMU_NOTIFIER_MAP for nested-smmuv3 - hw/arm/smmu-common: Return sysmem if stage-1 is bypassed - hw/arm/smmu-common: Add iommufd helpers - hw/arm/smmu-common: Add set/unset_iommu_device callback - hw/arm/smmu-common: Extract smmu_get_sbus and smmu_get_sdev helpers - hw/arm/smmu-common: Bypass emulated IOTLB for a nested SMMU - hw/arm/smmu-common: Add a nested flag to SMMUState - backends/iommufd: Introduce iommufd_viommu_invalidate_cache - backends/iommufd: Introduce iommufd_vdev_alloc - backends/iommufd: Introduce iommufd_backend_alloc_viommu - vfio/iommufd: Implement [at|de]tach_hwpt handlers - vfio/iommufd: Implement HostIOMMUDeviceClass::realize_late() handler - HostIOMMUDevice: Introduce realize_late callback - vfio/iommufd: Add properties and handlers to TYPE_HOST_IOMMU_DEVICE_IOMMUFD - backends/iommufd: Add helpers for invalidating user-managed HWPT - Update iommufd.h header for vSVA - vfio/common: Allow disabling device dirty page tracking - vfio/migration: Don't block migration device dirty tracking is unsupported - vfio/iommufd: Implement VFIOIOMMUClass::query_dirty_bitmap support - vfio/iommufd: Implement VFIOIOMMUClass::set_dirty_tracking support - vfio/iommufd: Probe and request hwpt dirty tracking capability - vfio/{iommufd, container}: Invoke HostIOMMUDevice::realize() during attach_device() - vfio/iommufd: Add hw_caps field to HostIOMMUDeviceCaps - vfio/{iommufd,container}: Remove caps::aw_bits - HostIOMMUDevice: Store the VFIO/VDPA agent - vfio/iommufd: Introduce auto domain creation - vfio/ccw: Don't initialize HOST_IOMMU_DEVICE with mdev - vfio/ap: Don't initialize HOST_IOMMU_DEVICE with mdev - vfio/iommufd: Return errno in iommufd_cdev_attach_ioas_hwpt() - backends/iommufd: Extend iommufd_backend_get_device_info() to fetch HW capabilities - vfio/iommufd: Don't initialize nor set a HOST_IOMMU_DEVICE with mdev - vfio/pci: Extract mdev check into an helper - intel_iommu: Check compatibility with host IOMMU capabilities - intel_iommu: Implement [set|unset]_iommu_device() callbacks - intel_iommu: Extract out vtd_cap_init() to initialize cap/ecap - vfio/pci: Pass HostIOMMUDevice to vIOMMU - hw/pci: Introduce pci_device_[set|unset]_iommu_device() - hw/pci: Introduce helper function pci_device_get_iommu_bus_devfn() - vfio: Create host IOMMU device instance - backends/iommufd: Implement HostIOMMUDeviceClass::get_cap() handler - vfio/container: Implement HostIOMMUDeviceClass::get_cap() handler - vfio/iommufd: Implement HostIOMMUDeviceClass::realize() handler - backends/iommufd: Introduce helper function iommufd_backend_get_device_info() - vfio/container: Implement HostIOMMUDeviceClass::realize() handler - range: Introduce range_get_last_bit() - backends/iommufd: Introduce TYPE_HOST_IOMMU_DEVICE_IOMMUFD[_VFIO] devices - vfio/container: Introduce TYPE_HOST_IOMMU_DEVICE_LEGACY_VFIO device - backends/host_iommu_device: Introduce HostIOMMUDeviceCaps - backends: Introduce HostIOMMUDevice abstract - vfio/iommufd: Remove CONFIG_IOMMUFD usage - vfio/spapr: Extend VFIOIOMMUOps with a release handler - vfio/spapr: Only compile sPAPR IOMMU support when needed - vfio/iommufd: Introduce a VFIOIOMMU iommufd QOM interface - vfio/spapr: Introduce a sPAPR VFIOIOMMU QOM interface - vfio/container: Intoduce a new VFIOIOMMUClass::setup handler - vfio/container: Introduce a VFIOIOMMU legacy QOM interface - vfio/container: Introduce a VFIOIOMMU QOM interface - vfio/container: Initialize VFIOIOMMUOps under vfio_init_container() - vfio/container: Introduce vfio_legacy_setup() for further cleanups - docs/devel: Add VFIO iommufd backend documentation - vfio: Introduce a helper function to initialize VFIODevice - vfio/ccw: Move VFIODevice initializations in vfio_ccw_instance_init - vfio/ap: Move VFIODevice initializations in vfio_ap_instance_init - vfio/platform: Move VFIODevice initializations in vfio_platform_instance_init - vfio/pci: Move VFIODevice initializations in vfio_instance_init - hw/i386: Activate IOMMUFD for q35 machines - kconfig: Activate IOMMUFD for s390x machines - hw/arm: Activate IOMMUFD for virt machines - vfio: Make VFIOContainerBase poiner parameter const in VFIOIOMMUOps callbacks - vfio/ccw: Make vfio cdev pre-openable by passing a file handle - vfio/ccw: Allow the selection of a given iommu backend - vfio/ap: Make vfio cdev pre-openable by passing a file handle - vfio/ap: Allow the selection of a given iommu backend - vfio/platform: Make vfio cdev pre-openable by passing a file handle - vfio/platform: Allow the selection of a given iommu backend - vfio/pci: Make vfio cdev pre-openable by passing a file handle - vfio/pci: Allow the selection of a given iommu backend - vfio/iommufd: Enable pci hot reset through iommufd cdev interface - vfio/pci: Introduce a vfio pci hot reset interface - vfio/pci: Extract out a helper vfio_pci_get_pci_hot_reset_info - vfio/iommufd: Add support for iova_ranges and pgsizes - vfio/iommufd: Relax assert check for iommufd backend - vfio/iommufd: Implement the iommufd backend - vfio/common: return early if space isn't empty - util/char_dev: Add open_cdev() - backends/iommufd: Introduce the iommufd object - vfio/spapr: Move hostwin_list into spapr container - vfio/spapr: Move prereg_listener into spapr container - vfio/spapr: switch to spapr IOMMU BE add/del_section_window - vfio/spapr: Introduce spapr backend and target interface - vfio/container: Implement attach/detach_device - vfio/container: Move iova_ranges to base container - vfio/container: Move dirty_pgsizes and max_dirty_bitmap_size to base container - vfio/container: Move listener to base container - vfio/container: Move vrdl_list to base container - vfio/container: Move pgsizes and dma_max_mappings to base container - vfio/container: Convert functions to base container - vfio/container: Move per container device list in base container - vfio/container: Switch to IOMMU BE set_dirty_page_tracking/query_dirty_bitmap API - vfio/container: Move space field to base container - vfio/common: Move giommu_list in base container - vfio/common: Introduce vfio_container_init/destroy helper - vfio/container: Switch to dma_map|unmap API - vfio/container: Introduce a empty VFIOIOMMUOps - vfio: Introduce base object for VFIOContainer and targeted interface - cryptodev: Fix error handling in cryptodev_lkcf_execute_task() - hw/xen: Fix xen_bus_realize() error handling - hw/misc/aspeed_hace: Fix buffer overflow in has_padding function - target/s390x: Fix a typo in s390_cpu_class_init() - hw/sd/sdhci: free irq on exit - hw/ufs: free irq on exit - hw/pci-host/designware: Fix ATU_UPPER_TARGET register access - target/i386: Make invtsc migratable when user sets tsc-khz explicitly - target/i386: Construct CPUID 2 as stateful iff times > 1 - target/i386: Enable fdp-excptn-only and zero-fcs-fds - target/i386: Don't construct a all-zero entry for CPUID[0xD 0x3f] - i386/cpuid: Remove subleaf constraint on CPUID leaf 1F - target/i386: pass X86CPU to x86_cpu_get_supported_feature_word - target/i386: Raise the highest index value used for any VMCS encoding - target/i386: Add VMX control bits for nested FRED support - target/i386: Delete duplicated macro definition CR4_FRED_MASK - target/i386: Add get/set/migrate support for FRED MSRs - target/i386: enumerate VMX nested-exception support - vmxcap: add support for VMX FRED controls - target/i386: mark CR4.FRED not reserved - target/i386: add support for FRED in CPUID enumeration - target/i386: fix feature dependency for WAITPKG - target/i386: Add more features enumerated by CPUID.7.2.EDX - net: fix build when libbpf is disabled, but libxdp is enabled - hw/nvme: fix invalid endian conversion - hw/nvme: fix invalid check on mcl - backends/cryptodev: Do not ignore throttle/backends Errors - backends/cryptodev: Do not abort for invalid session ID - virtcca: add kvm isolation when get tmi version. - qga: Don't daemonize before channel is initialized - qga: Add log to guest-fsfreeze-thaw command - backends: VirtCCA: cvm_gpa_start supports both 1GB and 3GB - BUGFIX: Enforce isolation for virtcca_shared_hugepage - arm: VirtCCA: qemu CoDA support UEFI boot - arm: VirtCCA: Compatibility with older versions of TMM and the kernel - arm: VirtCCA: qemu uefi boot support kae - arm: VirtCCA: CVM support UEFI boot Signed-off-by: Jiabo Feng <fengjiabo1@huawei.com> (cherry picked from commit 85fd7a435d8203dde56fedc4c8f500e41faf132c)
188 lines
7.8 KiB
Diff
188 lines
7.8 KiB
Diff
From 1746ba1aee671b9552540e36a629988b00846a82 Mon Sep 17 00:00:00 2001
|
|
From: Eric Auger <eric.auger@redhat.com>
|
|
Date: Tue, 5 Oct 2021 10:53:13 +0200
|
|
Subject: [PATCH] hw/arm/virt-acpi-build: Add IORT RMR regions to handle MSI
|
|
nested binding
|
|
|
|
To handle SMMUv3 nested stage support it is practical to
|
|
expose the guest with reserved memory regions (RMRs)
|
|
covering the IOVAs used by the host kernel to map
|
|
physical MSI doorbells.
|
|
|
|
Those IOVAs belong to [0x8000000, 0x8100000] matching
|
|
MSI_IOVA_BASE and MSI_IOVA_LENGTH definitions in kernel
|
|
arm-smmu-v3 driver. This is the window used to allocate
|
|
IOVAs matching physical MSI doorbells.
|
|
|
|
With those RMRs, the guest is forced to use a flat mapping
|
|
for this range. Hence the assigned device is programmed
|
|
with one IOVA from this range. Stage 1, owned by the guest
|
|
has a flat mapping for this IOVA. Stage2, owned by the VMM
|
|
then enforces a mapping from this IOVA to the physical
|
|
MSI doorbell.
|
|
|
|
The creation of those RMR nodes only is relevant if nested
|
|
stage SMMU is in use, along with VFIO. As VFIO devices can be
|
|
hotplugged, all RMRs need to be created in advance. Hence
|
|
the patch introduces a new arm virt "nested-smmuv3" iommu type.
|
|
|
|
ARM DEN 0049E.b IORT specification also mandates that when
|
|
RMRs are present, the OS must preserve PCIe configuration
|
|
performed by the boot FW. So along with the RMR IORT nodes,
|
|
a _DSM function #5, as defined by PCI FIRMWARE SPECIFICATION
|
|
EVISION 3.3, chapter 4.6.5 is added to PCIe host bridge
|
|
and PCIe expander bridge objects.
|
|
|
|
Signed-off-by: Eric Auger <eric.auger@redhat.com>
|
|
Suggested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
|
|
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
|
|
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
|
|
---
|
|
hw/arm/virt-acpi-build.c | 71 +++++++++++++++++++++++++++++++++++-----
|
|
1 file changed, 63 insertions(+), 8 deletions(-)
|
|
|
|
diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
|
|
index 1d7839e4a0..ad0f79e03d 100644
|
|
--- a/hw/arm/virt-acpi-build.c
|
|
+++ b/hw/arm/virt-acpi-build.c
|
|
@@ -417,6 +417,14 @@ static void acpi_dsdt_add_pci(Aml *scope, const MemMapEntry *memmap,
|
|
.bus = vms->bus,
|
|
};
|
|
|
|
+ /*
|
|
+ * Nested SMMU requires RMRs for MSI 1-1 mapping, which
|
|
+ * require _DSM for PreservingPCI Boot Configurations
|
|
+ */
|
|
+ if (vms->iommu == VIRT_IOMMU_SMMUV3_NESTED) {
|
|
+ cfg.preserve_config = true;
|
|
+ }
|
|
+
|
|
if (vms->highmem_mmio) {
|
|
cfg.mmio64 = memmap[VIRT_HIGH_PCIE_MMIO];
|
|
}
|
|
@@ -495,7 +503,7 @@ static void acpi_dsdt_add_tpm(Aml *scope, VirtMachineState *vms)
|
|
#define IORT_NODE_OFFSET 48
|
|
|
|
static void build_iort_id_mapping(GArray *table_data, uint32_t input_base,
|
|
- uint32_t id_count, uint32_t out_ref)
|
|
+ uint32_t id_count, uint32_t out_ref, uint32_t flags)
|
|
{
|
|
/* Table 4 ID mapping format */
|
|
build_append_int_noprefix(table_data, input_base, 4); /* Input base */
|
|
@@ -503,7 +511,7 @@ static void build_iort_id_mapping(GArray *table_data, uint32_t input_base,
|
|
build_append_int_noprefix(table_data, input_base, 4); /* Output base */
|
|
build_append_int_noprefix(table_data, out_ref, 4); /* Output Reference */
|
|
/* Flags */
|
|
- build_append_int_noprefix(table_data, 0 /* Single mapping (disabled) */, 4);
|
|
+ build_append_int_noprefix(table_data, flags, 4); /* Flags */
|
|
}
|
|
|
|
struct AcpiIortIdMapping {
|
|
@@ -545,6 +553,50 @@ static int iort_idmap_compare(gconstpointer a, gconstpointer b)
|
|
return idmap_a->input_base - idmap_b->input_base;
|
|
}
|
|
|
|
+static void
|
|
+build_iort_rmr_nodes(GArray *table_data, GArray *smmu_idmaps,
|
|
+ size_t *smmu_offset, uint32_t *id)
|
|
+{
|
|
+ AcpiIortIdMapping *range;
|
|
+ int i;
|
|
+
|
|
+ for (i = 0; i < smmu_idmaps->len; i++) {
|
|
+ range = &g_array_index(smmu_idmaps, AcpiIortIdMapping, i);
|
|
+ int bdf = range->input_base;
|
|
+
|
|
+ /* Table 18 Reserved Memory Range Node */
|
|
+
|
|
+ build_append_int_noprefix(table_data, 6 /* RMR */, 1); /* Type */
|
|
+ /* Length */
|
|
+ build_append_int_noprefix(table_data, 28 + ID_MAPPING_ENTRY_SIZE + 20, 2);
|
|
+ build_append_int_noprefix(table_data, 3, 1); /* Revision */
|
|
+ build_append_int_noprefix(table_data, *id, 4); /* Identifier */
|
|
+ /* Number of ID mappings */
|
|
+ build_append_int_noprefix(table_data, 1, 4);
|
|
+ /* Reference to ID Array */
|
|
+ build_append_int_noprefix(table_data, 28, 4);
|
|
+
|
|
+ /* RMR specific data */
|
|
+
|
|
+ /* Flags */
|
|
+ build_append_int_noprefix(table_data, 0 /* Disallow remapping */, 4);
|
|
+ /* Number of Memory Range Descriptors */
|
|
+ build_append_int_noprefix(table_data, 1 , 4);
|
|
+ /* Reference to Memory Range Descriptors */
|
|
+ build_append_int_noprefix(table_data, 28 + ID_MAPPING_ENTRY_SIZE, 4);
|
|
+ build_iort_id_mapping(table_data, bdf, range->id_count, smmu_offset[i], 1);
|
|
+
|
|
+ /* Table 19 Memory Range Descriptor */
|
|
+
|
|
+ /* Physical Range offset */
|
|
+ build_append_int_noprefix(table_data, 0x8000000, 8);
|
|
+ /* Physical Range length */
|
|
+ build_append_int_noprefix(table_data, 0x100000, 8);
|
|
+ build_append_int_noprefix(table_data, 0, 4); /* Reserved */
|
|
+ *id += 1;
|
|
+ }
|
|
+}
|
|
+
|
|
/*
|
|
* Input Output Remapping Table (IORT)
|
|
* Conforms to "IO Remapping Table System Software on ARM Platforms",
|
|
@@ -554,7 +606,6 @@ static void
|
|
build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
|
|
{
|
|
int i, nb_nodes, rc_mapping_count;
|
|
- const uint32_t iort_node_offset = IORT_NODE_OFFSET;
|
|
size_t node_size, *smmu_offset;
|
|
AcpiIortIdMapping *idmap;
|
|
hwaddr base;
|
|
@@ -563,7 +614,7 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
|
|
GArray *smmu_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping));
|
|
GArray *its_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping));
|
|
|
|
- AcpiTable table = { .sig = "IORT", .rev = 3, .oem_id = vms->oem_id,
|
|
+ AcpiTable table = { .sig = "IORT", .rev = 5, .oem_id = vms->oem_id,
|
|
.oem_table_id = vms->oem_table_id };
|
|
/* Table 2 The IORT */
|
|
acpi_table_begin(&table, table_data);
|
|
@@ -668,7 +719,7 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
|
|
build_append_int_noprefix(table_data, 0, 4);
|
|
|
|
/* output IORT node is the ITS group node (the first node) */
|
|
- build_iort_id_mapping(table_data, 0, 0x10000, IORT_NODE_OFFSET);
|
|
+ build_iort_id_mapping(table_data, 0, 0x10000, IORT_NODE_OFFSET, 0);
|
|
}
|
|
|
|
/* Table 17 Root Complex Node */
|
|
@@ -709,7 +760,7 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
|
|
range = &g_array_index(smmu_idmaps, AcpiIortIdMapping, i);
|
|
/* output IORT node is the smmuv3 node */
|
|
build_iort_id_mapping(table_data, range->input_base,
|
|
- range->id_count, smmu_offset[i]);
|
|
+ range->id_count, smmu_offset[i], 0);
|
|
}
|
|
|
|
/* bypassed RIDs connect to ITS group node directly: RC -> ITS */
|
|
@@ -717,11 +768,15 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms)
|
|
range = &g_array_index(its_idmaps, AcpiIortIdMapping, i);
|
|
/* output IORT node is the ITS group node (the first node) */
|
|
build_iort_id_mapping(table_data, range->input_base,
|
|
- range->id_count, iort_node_offset);
|
|
+ range->id_count, IORT_NODE_OFFSET, 0);
|
|
}
|
|
} else {
|
|
/* output IORT node is the ITS group node (the first node) */
|
|
- build_iort_id_mapping(table_data, 0, 0xFFFF, IORT_NODE_OFFSET);
|
|
+ build_iort_id_mapping(table_data, 0, 0x10000, IORT_NODE_OFFSET, 0);
|
|
+ }
|
|
+
|
|
+ if (vms->iommu == VIRT_IOMMU_SMMUV3_NESTED) {
|
|
+ build_iort_rmr_nodes(table_data, smmu_idmaps, smmu_offset, &id);
|
|
}
|
|
|
|
acpi_table_end(linker, &table);
|
|
--
|
|
2.41.0.windows.1
|
|
|