qemu/vfio-container-Move-pgsizes-and-dma_max_mappings-to-.patch

235 lines
10 KiB
Diff
Raw Normal View History

QEMU update to version 8.2.0-30: - 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)
2025-04-22 14:34:58 +08:00
From 961614f6c997caf632ce37ead96b301ec47b1847 Mon Sep 17 00:00:00 2001
From: Eric Auger <eric.auger@redhat.com>
Date: Sat, 11 Jan 2025 10:52:27 +0800
Subject: [PATCH] vfio/container: Move pgsizes and dma_max_mappings to base
container
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
No functional change intended.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Yi Sun <yi.y.sun@linux.intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Signed-off-by: Zhou Wang <wangzhou1@hisilicon.com>
---
hw/vfio/common.c | 17 +++++++++--------
hw/vfio/container-base.c | 1 +
hw/vfio/container.c | 11 +++++------
hw/vfio/spapr.c | 10 ++++++----
include/hw/vfio/vfio-common.h | 2 --
include/hw/vfio/vfio-container-base.h | 2 ++
6 files changed, 23 insertions(+), 20 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index b663d0bcc0..fd6249c290 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -401,6 +401,7 @@ static int vfio_ram_discard_notify_populate(RamDiscardListener *rdl,
static void vfio_register_ram_discard_listener(VFIOContainer *container,
MemoryRegionSection *section)
{
+ VFIOContainerBase *bcontainer = &container->bcontainer;
RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr);
VFIORamDiscardListener *vrdl;
@@ -419,8 +420,8 @@ static void vfio_register_ram_discard_listener(VFIOContainer *container,
section->mr);
g_assert(vrdl->granularity && is_power_of_2(vrdl->granularity));
- g_assert(container->pgsizes &&
- vrdl->granularity >= 1ULL << ctz64(container->pgsizes));
+ g_assert(bcontainer->pgsizes &&
+ vrdl->granularity >= 1ULL << ctz64(bcontainer->pgsizes));
ram_discard_listener_init(&vrdl->listener,
vfio_ram_discard_notify_populate,
@@ -441,7 +442,7 @@ static void vfio_register_ram_discard_listener(VFIOContainer *container,
* number of sections in the address space we could have over time,
* also consuming DMA mappings.
*/
- if (container->dma_max_mappings) {
+ if (bcontainer->dma_max_mappings) {
unsigned int vrdl_count = 0, vrdl_mappings = 0, max_memslots = 512;
#ifdef CONFIG_KVM
@@ -462,11 +463,11 @@ static void vfio_register_ram_discard_listener(VFIOContainer *container,
}
if (vrdl_mappings + max_memslots - vrdl_count >
- container->dma_max_mappings) {
+ bcontainer->dma_max_mappings) {
warn_report("%s: possibly running out of DMA mappings. E.g., try"
" increasing the 'block-size' of virtio-mem devies."
" Maximum possible DMA mappings: %d, Maximum possible"
- " memslots: %d", __func__, container->dma_max_mappings,
+ " memslots: %d", __func__, bcontainer->dma_max_mappings,
max_memslots);
}
}
@@ -626,7 +627,7 @@ static void vfio_listener_region_add(MemoryListener *listener,
iommu_idx);
ret = memory_region_iommu_set_page_size_mask(giommu->iommu_mr,
- container->pgsizes,
+ bcontainer->pgsizes,
&err);
if (ret) {
g_free(giommu);
@@ -675,7 +676,7 @@ static void vfio_listener_region_add(MemoryListener *listener,
llsize = int128_sub(llend, int128_make64(iova));
if (memory_region_is_ram_device(section->mr)) {
- hwaddr pgmask = (1ULL << ctz64(container->pgsizes)) - 1;
+ hwaddr pgmask = (1ULL << ctz64(bcontainer->pgsizes)) - 1;
if ((iova & pgmask) || (int128_get64(llsize) & pgmask)) {
trace_vfio_listener_region_add_no_dma_map(
@@ -777,7 +778,7 @@ static void vfio_listener_region_del(MemoryListener *listener,
if (memory_region_is_ram_device(section->mr)) {
hwaddr pgmask;
- pgmask = (1ULL << ctz64(container->pgsizes)) - 1;
+ pgmask = (1ULL << ctz64(bcontainer->pgsizes)) - 1;
try_unmap = !((iova & pgmask) || (int128_get64(llsize) & pgmask));
} else if (memory_region_has_ram_discard_manager(section->mr)) {
vfio_unregister_ram_discard_listener(container, section);
diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c
index 5d654ae172..dcce111349 100644
--- a/hw/vfio/container-base.c
+++ b/hw/vfio/container-base.c
@@ -52,6 +52,7 @@ void vfio_container_init(VFIOContainerBase *bcontainer, VFIOAddressSpace *space,
bcontainer->ops = ops;
bcontainer->space = space;
bcontainer->dirty_pages_supported = false;
+ bcontainer->dma_max_mappings = 0;
QLIST_INIT(&bcontainer->giommu_list);
}
diff --git a/hw/vfio/container.c b/hw/vfio/container.c
index 9a542368ab..116a9e1e73 100644
--- a/hw/vfio/container.c
+++ b/hw/vfio/container.c
@@ -196,7 +196,7 @@ static int vfio_legacy_dma_unmap(VFIOContainerBase *bcontainer, hwaddr iova,
if (errno == EINVAL && unmap.size && !(unmap.iova + unmap.size) &&
container->iommu_type == VFIO_TYPE1v2_IOMMU) {
trace_vfio_legacy_dma_unmap_overflow_workaround();
- unmap.size -= 1ULL << ctz64(container->pgsizes);
+ unmap.size -= 1ULL << ctz64(bcontainer->pgsizes);
continue;
}
error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno));
@@ -652,7 +652,6 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
container = g_malloc0(sizeof(*container));
container->fd = fd;
container->error = NULL;
- container->dma_max_mappings = 0;
container->iova_ranges = NULL;
QLIST_INIT(&container->vrdl_list);
QLIST_INIT(&container->dma_list);
@@ -684,13 +683,13 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
}
if (info->flags & VFIO_IOMMU_INFO_PGSIZES) {
- container->pgsizes = info->iova_pgsizes;
+ bcontainer->pgsizes = info->iova_pgsizes;
} else {
- container->pgsizes = qemu_real_host_page_size();
+ bcontainer->pgsizes = qemu_real_host_page_size();
}
- if (!vfio_get_info_dma_avail(info, &container->dma_max_mappings)) {
- container->dma_max_mappings = 65535;
+ if (!vfio_get_info_dma_avail(info, &bcontainer->dma_max_mappings)) {
+ bcontainer->dma_max_mappings = 65535;
}
vfio_get_info_iova_range(info, container);
diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c
index 83da2f7ec2..4f76bdd3ca 100644
--- a/hw/vfio/spapr.c
+++ b/hw/vfio/spapr.c
@@ -226,6 +226,7 @@ static int vfio_spapr_create_window(VFIOContainer *container,
hwaddr *pgsize)
{
int ret = 0;
+ VFIOContainerBase *bcontainer = &container->bcontainer;
IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr);
uint64_t pagesize = memory_region_iommu_get_min_page_size(iommu_mr), pgmask;
unsigned entries, bits_total, bits_per_level, max_levels;
@@ -239,13 +240,13 @@ static int vfio_spapr_create_window(VFIOContainer *container,
if (pagesize > rampagesize) {
pagesize = rampagesize;
}
- pgmask = container->pgsizes & (pagesize | (pagesize - 1));
+ pgmask = bcontainer->pgsizes & (pagesize | (pagesize - 1));
pagesize = pgmask ? (1ULL << (63 - clz64(pgmask))) : 0;
if (!pagesize) {
error_report("Host doesn't support page size 0x%"PRIx64
", the supported mask is 0x%lx",
memory_region_iommu_get_min_page_size(iommu_mr),
- container->pgsizes);
+ bcontainer->pgsizes);
return -EINVAL;
}
@@ -421,6 +422,7 @@ void vfio_container_del_section_window(VFIOContainer *container,
int vfio_spapr_container_init(VFIOContainer *container, Error **errp)
{
+ VFIOContainerBase *bcontainer = &container->bcontainer;
struct vfio_iommu_spapr_tce_info info;
bool v2 = container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU;
int ret, fd = container->fd;
@@ -461,7 +463,7 @@ int vfio_spapr_container_init(VFIOContainer *container, Error **errp)
}
if (v2) {
- container->pgsizes = info.ddw.pgsizes;
+ bcontainer->pgsizes = info.ddw.pgsizes;
/*
* There is a default window in just created container.
* To make region_add/del simpler, we better remove this
@@ -476,7 +478,7 @@ int vfio_spapr_container_init(VFIOContainer *container, Error **errp)
}
} else {
/* The default table uses 4K pages */
- container->pgsizes = 0x1000;
+ bcontainer->pgsizes = 0x1000;
vfio_host_win_add(container, info.dma32_window_start,
info.dma32_window_start +
info.dma32_window_size - 1,
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 0295ede7ba..3046287070 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -94,8 +94,6 @@ typedef struct VFIOContainer {
bool dirty_log_manual_clear;
uint64_t dirty_pgsizes;
uint64_t max_dirty_bitmap_size;
- unsigned long pgsizes;
- unsigned int dma_max_mappings;
QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list;
QLIST_HEAD(, VFIOGroup) group_list;
QLIST_HEAD(, VFIORamDiscardListener) vrdl_list;
diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h
index 7090962496..85ec7e1a56 100644
--- a/include/hw/vfio/vfio-container-base.h
+++ b/include/hw/vfio/vfio-container-base.h
@@ -36,6 +36,8 @@ typedef struct VFIOAddressSpace {
typedef struct VFIOContainerBase {
const VFIOIOMMUOps *ops;
VFIOAddressSpace *space;
+ unsigned long pgsizes;
+ unsigned int dma_max_mappings;
bool dirty_pages_supported;
QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
QLIST_ENTRY(VFIOContainerBase) next;
--
2.41.0.windows.1