This patch series makes the selftest work with NV enabled. The guest code
is run in vEL2 instead of EL1. We add a command line option to enable
testing of NV. The NV tests are disabled by default.
Modified around 12 selftests in this series.
Changes since v1:
- Updated NV helper functions as per comments [1].
- Modified existing testscases to run guest code in vEL2.
[1] https://lkml.iu.edu/hypermail/linux/kernel/2502.0/07001.html
Ganapatrao Kulkarni (9):
KVM: arm64: nv: selftests: Add support to run guest code in vEL2.
KVM: arm64: nv: selftests: Add simple test to run guest code in vEL2
KVM: arm64: nv: selftests: Enable hypervisor timer tests to run in
vEL2
KVM: arm64: nv: selftests: enable aarch32_id_regs test to run in vEL2
KVM: arm64: nv: selftests: Enable vgic tests to run in vEL2
KVM: arm64: nv: selftests: Enable set_id_regs test to run in vEL2
KVM: arm64: nv: selftests: Enable test to run in vEL2
KVM: selftests: arm64: Extend kvm_page_table_test to run guest code in
vEL2
KVM: arm64: nv: selftests: Enable page_fault_test test to run in vEL2
tools/testing/selftests/kvm/Makefile.kvm | 2 +
tools/testing/selftests/kvm/arch_timer.c | 8 +-
.../selftests/kvm/arm64/aarch32_id_regs.c | 34 ++++-
.../testing/selftests/kvm/arm64/arch_timer.c | 118 +++++++++++++++---
.../selftests/kvm/arm64/nv_guest_hypervisor.c | 68 ++++++++++
.../selftests/kvm/arm64/page_fault_test.c | 35 +++++-
.../testing/selftests/kvm/arm64/set_id_regs.c | 57 ++++++++-
tools/testing/selftests/kvm/arm64/vgic_init.c | 54 +++++++-
tools/testing/selftests/kvm/arm64/vgic_irq.c | 27 ++--
.../selftests/kvm/arm64/vgic_lpi_stress.c | 19 ++-
.../testing/selftests/kvm/guest_print_test.c | 32 +++++
.../selftests/kvm/include/arm64/arch_timer.h | 16 +++
.../kvm/include/arm64/kvm_util_arch.h | 3 +
.../selftests/kvm/include/arm64/nv_util.h | 45 +++++++
.../selftests/kvm/include/arm64/vgic.h | 1 +
.../testing/selftests/kvm/include/kvm_util.h | 3 +
.../selftests/kvm/include/timer_test.h | 1 +
.../selftests/kvm/kvm_page_table_test.c | 30 ++++-
tools/testing/selftests/kvm/lib/arm64/nv.c | 46 +++++++
.../selftests/kvm/lib/arm64/processor.c | 61 ++++++---
tools/testing/selftests/kvm/lib/arm64/vgic.c | 8 ++
21 files changed, 604 insertions(+), 64 deletions(-)
create mode 100644 tools/testing/selftests/kvm/arm64/nv_guest_hypervisor.c
create mode 100644 tools/testing/selftests/kvm/include/arm64/nv_util.h
create mode 100644 tools/testing/selftests/kvm/lib/arm64/nv.c
--
2.48.1
This is the second version of a series that lets us run VMware
Workstation on Linux on top of KVM.
The most significant change in this series is the introduction of
CONFIG_KVM_VMWARE which is, in general, a nice cleanup for various
bits of VMware compatibility code that have been scattered around KVM.
(first patch)
The rest of the series builds upon the VMware platform to implement
features that are needed to run VMware guests without any
modifications on top of KVM:
- ability to turn on the VMware backdoor at runtime on a per-vm basis
(used to be a kernel boot argument only)
- support for VMware hypercalls - VMware products have a huge
collection of hypercalls, all of which are handled in userspace,
- support for handling legacy VMware backdoor in L0 in nested configs
- in cases where we have WS running a Windows VBS guest, the L0 would
be KVM, L1 Hyper-V so by default VMware Tools backdoor calls endup in
Hyper-V which can not handle them, so introduce a cap to let L0 handle
those.
The final change in the series is a kselftest of the VMware hypercall
functionality.
Cc: Paolo Bonzini <pbonzini(a)redhat.com>
Cc: Jonathan Corbet <corbet(a)lwn.net>
Cc: Sean Christopherson <seanjc(a)google.com>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: Ingo Molnar <mingo(a)redhat.com>
Cc: Borislav Petkov <bp(a)alien8.de>
Cc: Dave Hansen <dave.hansen(a)linux.intel.com>
Cc: x86(a)kernel.org
Cc: "H. Peter Anvin" <hpa(a)zytor.com>
Cc: Zack Rusin <zack.rusin(a)broadcom.com>
Cc: Doug Covelli <doug.covelli(a)broadcom.com>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: Namhyung Kim <namhyung(a)kernel.org>
Cc: Arnaldo Carvalho de Melo <acme(a)redhat.com>
Cc: Michael Ellerman <mpe(a)ellerman.id.au>
Cc: Joel Stanley <joel(a)jms.id.au>
Cc: Isaku Yamahata <isaku.yamahata(a)intel.com>
Cc: kvm(a)vger.kernel.org
Cc: linux-doc(a)vger.kernel.org
Cc: linux-kernel(a)vger.kernel.org
Cc: linux-kselftest(a)vger.kernel.org
Zack Rusin (5):
KVM: x86: Centralize KVM's VMware code
KVM: x86: Allow enabling of the vmware backdoor via a cap
KVM: x86: Add support for VMware guest specific hypercalls
KVM: x86: Add support for legacy VMware backdoors in nested setups
KVM: selftests: x86: Add a test for KVM_CAP_X86_VMWARE_HYPERCALL
Documentation/virt/kvm/api.rst | 86 +++++++-
MAINTAINERS | 9 +
arch/x86/include/asm/kvm_host.h | 13 ++
arch/x86/kvm/Kconfig | 16 ++
arch/x86/kvm/Makefile | 1 +
arch/x86/kvm/emulate.c | 11 +-
arch/x86/kvm/kvm_vmware.c | 85 ++++++++
arch/x86/kvm/kvm_vmware.h | 189 ++++++++++++++++++
arch/x86/kvm/pmu.c | 39 +---
arch/x86/kvm/pmu.h | 4 -
arch/x86/kvm/svm/nested.c | 6 +
arch/x86/kvm/svm/svm.c | 10 +-
arch/x86/kvm/vmx/nested.c | 6 +
arch/x86/kvm/vmx/vmx.c | 5 +-
arch/x86/kvm/x86.c | 74 +++----
arch/x86/kvm/x86.h | 2 -
include/uapi/linux/kvm.h | 27 +++
tools/include/uapi/linux/kvm.h | 3 +
tools/testing/selftests/kvm/Makefile.kvm | 1 +
.../selftests/kvm/x86/vmware_hypercall_test.c | 121 +++++++++++
20 files changed, 614 insertions(+), 94 deletions(-)
create mode 100644 arch/x86/kvm/kvm_vmware.c
create mode 100644 arch/x86/kvm/kvm_vmware.h
create mode 100644 tools/testing/selftests/kvm/x86/vmware_hypercall_test.c
--
2.48.1
I'd like to cut down the memory usage of parsing vmlinux BTF in ebpf-go.
With some upcoming changes the library is sitting at 5MiB for a parse.
Most of that memory is simply copying the BTF blob into user space.
By allowing vmlinux BTF to be mmapped read-only into user space I can
cut memory usage by about 75%.
Signed-off-by: Lorenz Bauer <lmb(a)isovalent.com>
---
Changes in v5:
- Fix error return of btf_parse_raw_mmap (Andrii)
- Link to v4: https://lore.kernel.org/r/20250510-vmlinux-mmap-v4-0-69e424b2a672@isovalent…
Changes in v4:
- Go back to remap_pfn_range for aarch64 compat
- Dropped btf_new_no_copy (Andrii)
- Fixed nits in selftests (Andrii)
- Clearer error handling in the mmap handler (Andrii)
- Fixed build on s390
- Link to v3: https://lore.kernel.org/r/20250505-vmlinux-mmap-v3-0-5d53afa060e8@isovalent…
Changes in v3:
- Remove slightly confusing calculation of trailing (Alexei)
- Use vm_insert_page (Alexei)
- Simplified libbpf code
- Link to v2: https://lore.kernel.org/r/20250502-vmlinux-mmap-v2-0-95c271434519@isovalent…
Changes in v2:
- Use btf__new in selftest
- Avoid vm_iomap_memory in btf_vmlinux_mmap
- Add VM_DONTDUMP
- Add support to libbpf
- Link to v1: https://lore.kernel.org/r/20250501-vmlinux-mmap-v1-0-aa2724572598@isovalent…
---
Lorenz Bauer (3):
btf: allow mmap of vmlinux btf
selftests: bpf: add a test for mmapable vmlinux BTF
libbpf: Use mmap to parse vmlinux BTF from sysfs
include/asm-generic/vmlinux.lds.h | 3 +-
kernel/bpf/sysfs_btf.c | 32 ++++++++
tools/lib/bpf/btf.c | 89 +++++++++++++++++-----
tools/testing/selftests/bpf/prog_tests/btf_sysfs.c | 81 ++++++++++++++++++++
4 files changed, 186 insertions(+), 19 deletions(-)
---
base-commit: 7220eabff8cb4af3b93cd021aa853b9f5df2923f
change-id: 20250501-vmlinux-mmap-2ec5563c3ef1
Best regards,
--
Lorenz Bauer <lmb(a)isovalent.com>
NOTE: I'm leaving Daynix Computing Ltd., for which I worked on this
patch series, by the end of this month.
While net-next is closed, this is the last chance for me to send another
version so let me send the local changes now.
Please contact Yuri Benditovich, who is CCed on this email, for anything
about this series.
virtio-net have two usage of hashes: one is RSS and another is hash
reporting. Conventionally the hash calculation was done by the VMM.
However, computing the hash after the queue was chosen defeats the
purpose of RSS.
Another approach is to use eBPF steering program. This approach has
another downside: it cannot report the calculated hash due to the
restrictive nature of eBPF.
Introduce the code to compute hashes to the kernel in order to overcome
thse challenges.
An alternative solution is to extend the eBPF steering program so that it
will be able to report to the userspace, but it is based on context
rewrites, which is in feature freeze. We can adopt kfuncs, but they will
not be UAPIs. We opt to ioctl to align with other relevant UAPIs (KVM
and vhost_net).
The patches for QEMU to use this new feature was submitted as RFC and
is available at:
https://patchew.org/QEMU/20250530-hash-v5-0-343d7d7a8200@daynix.com/
This work was presented at LPC 2024:
https://lpc.events/event/18/contributions/1963/
V1 -> V2:
Changed to introduce a new BPF program type.
Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com>
---
Changes in v12:
- Updated tools/testing/selftests/net/config.
- Split TUNSETVNETHASH.
- Link to v11: https://lore.kernel.org/r/20250317-rss-v11-0-4cacca92f31f@daynix.com
Changes in v11:
- Added the missing code to free vnet_hash in patch
"tap: Introduce virtio-net hash feature".
- Link to v10: https://lore.kernel.org/r/20250313-rss-v10-0-3185d73a9af0@daynix.com
Changes in v10:
- Split common code and TUN/TAP-specific code into separate patches.
- Reverted a spurious style change in patch "tun: Introduce virtio-net
hash feature".
- Added a comment explaining disable_ipv6 in tests.
- Used AF_PACKET for patch "selftest: tun: Add tests for
virtio-net hashing". I also added the usage of FIXTURE_VARIANT() as
the testing function now needs access to more variant-specific
variables.
- Corrected the message of patch "selftest: tun: Add tests for
virtio-net hashing"; it mentioned validation of configuration but
it is not scope of this patch.
- Expanded the description of patch "selftest: tun: Add tests for
virtio-net hashing".
- Added patch "tun: Allow steering eBPF program to fall back".
- Changed to handle TUNGETVNETHASHCAP before taking the rtnl lock.
- Removed redundant tests for tun_vnet_ioctl().
- Added patch "selftest: tap: Add tests for virtio-net ioctls".
- Added a design explanation of ioctls for extensibility and migration.
- Removed a few branches in patch
"vhost/net: Support VIRTIO_NET_F_HASH_REPORT".
- Link to v9: https://lore.kernel.org/r/20250307-rss-v9-0-df76624025eb@daynix.com
Changes in v9:
- Added a missing return statement in patch
"tun: Introduce virtio-net hash feature".
- Link to v8: https://lore.kernel.org/r/20250306-rss-v8-0-7ab4f56ff423@daynix.com
Changes in v8:
- Disabled IPv6 to eliminate noises in tests.
- Added a branch in tap to avoid unnecessary dissection when hash
reporting is disabled.
- Removed unnecessary rtnl_lock().
- Extracted code to handle new ioctls into separate functions to avoid
adding extra NULL checks to the code handling other ioctls.
- Introduced variable named "fd" to __tun_chr_ioctl().
- s/-/=/g in a patch message to avoid confusing Git.
- Link to v7: https://lore.kernel.org/r/20250228-rss-v7-0-844205cbbdd6@daynix.com
Changes in v7:
- Ensured to set hash_report to VIRTIO_NET_HASH_REPORT_NONE for
VHOST_NET_F_VIRTIO_NET_HDR.
- s/4/sizeof(u32)/ in patch "virtio_net: Add functions for hashing".
- Added tap_skb_cb type.
- Rebased.
- Link to v6: https://lore.kernel.org/r/20250109-rss-v6-0-b1c90ad708f6@daynix.com
Changes in v6:
- Extracted changes to fill vnet header holes into another series.
- Squashed patches "skbuff: Introduce SKB_EXT_TUN_VNET_HASH", "tun:
Introduce virtio-net hash reporting feature", and "tun: Introduce
virtio-net RSS" into patch "tun: Introduce virtio-net hash feature".
- Dropped the RFC tag.
- Link to v5: https://lore.kernel.org/r/20241008-rss-v5-0-f3cf68df005d@daynix.com
Changes in v5:
- Fixed a compilation error with CONFIG_TUN_VNET_CROSS_LE.
- Optimized the calculation of the hash value according to:
https://git.dpdk.org/dpdk/commit/?id=3fb1ea032bd6ff8317af5dac9af901f1f324ca…
- Added patch "tun: Unify vnet implementation".
- Dropped patch "tap: Pad virtio header with zero".
- Added patch "selftest: tun: Test vnet ioctls without device".
- Reworked selftests to skip for older kernels.
- Documented the case when the underlying device is deleted and packets
have queue_mapping set by TC.
- Reordered test harness arguments.
- Added code to handle fragmented packets.
- Link to v4: https://lore.kernel.org/r/20240924-rss-v4-0-84e932ec0e6c@daynix.com
Changes in v4:
- Moved tun_vnet_hash_ext to if_tun.h.
- Renamed virtio_net_toeplitz() to virtio_net_toeplitz_calc().
- Replaced htons() with cpu_to_be16().
- Changed virtio_net_hash_rss() to return void.
- Reordered variable declarations in virtio_net_hash_rss().
- Removed virtio_net_hdr_v1_hash_from_skb().
- Updated messages of "tap: Pad virtio header with zero" and
"tun: Pad virtio header with zero".
- Fixed vnet_hash allocation size.
- Ensured to free vnet_hash when destructing tun_struct.
- Link to v3: https://lore.kernel.org/r/20240915-rss-v3-0-c630015db082@daynix.com
Changes in v3:
- Reverted back to add ioctl.
- Split patch "tun: Introduce virtio-net hashing feature" into
"tun: Introduce virtio-net hash reporting feature" and
"tun: Introduce virtio-net RSS".
- Changed to reuse hash values computed for automq instead of performing
RSS hashing when hash reporting is requested but RSS is not.
- Extracted relevant data from struct tun_struct to keep it minimal.
- Added kernel-doc.
- Changed to allow calling TUNGETVNETHASHCAP before TUNSETIFF.
- Initialized num_buffers with 1.
- Added a test case for unclassified packets.
- Fixed error handling in tests.
- Changed tests to verify that the queue index will not overflow.
- Rebased.
- Link to v2: https://lore.kernel.org/r/20231015141644.260646-1-akihiko.odaki@daynix.com
---
Akihiko Odaki (10):
virtio_net: Add functions for hashing
net: flow_dissector: Export flow_keys_dissector_symmetric
tun: Allow steering eBPF program to fall back
tun: Add common virtio-net hash feature code
tun: Introduce virtio-net hash feature
tap: Introduce virtio-net hash feature
selftest: tun: Test vnet ioctls without device
selftest: tun: Add tests for virtio-net hashing
selftest: tap: Add tests for virtio-net ioctls
vhost/net: Support VIRTIO_NET_F_HASH_REPORT
Documentation/networking/tuntap.rst | 7 +
drivers/net/Kconfig | 1 +
drivers/net/ipvlan/ipvtap.c | 2 +-
drivers/net/macvtap.c | 2 +-
drivers/net/tap.c | 80 +++++-
drivers/net/tun.c | 92 +++++--
drivers/net/tun_vnet.h | 165 +++++++++++-
drivers/vhost/net.c | 68 ++---
include/linux/if_tap.h | 4 +-
include/linux/skbuff.h | 3 +
include/linux/virtio_net.h | 188 ++++++++++++++
include/net/flow_dissector.h | 1 +
include/uapi/linux/if_tun.h | 80 ++++++
net/core/flow_dissector.c | 3 +-
net/core/skbuff.c | 4 +
tools/testing/selftests/net/Makefile | 2 +-
tools/testing/selftests/net/config | 1 +
tools/testing/selftests/net/tap.c | 131 +++++++++-
tools/testing/selftests/net/tun.c | 485 ++++++++++++++++++++++++++++++++++-
19 files changed, 1234 insertions(+), 85 deletions(-)
---
base-commit: 5cb8274d66c611b7889565c418a8158517810f9b
change-id: 20240403-rss-e737d89efa77
Best regards,
--
Akihiko Odaki <akihiko.odaki(a)daynix.com>
This patchset refactors non-composite global variables into a common
struct that can be initialized and passed around per-test instead of
relying on the presence of global variables.
This allows:
- Better encapsulation
- Debugging becomes easier -- local variable state can be viewed per
stack frame, and we can more easily reason about the variable
mutations
Patch 1 needs to be applied first and can be followed by any of the
other patches.
I've ensured that the tests are passing locally (or atleast have the
same output as the code on master).
Ujwal Kundur (4):
selftests/mm/uffd: Refactor non-composite global vars into struct
selftests/mm/uffd: Swap global vars with global test options
selftests/mm/uffd: Swap global variables with global test opts
selftests/mm/uffd: Swap global variables with global test opts
tools/testing/selftests/mm/uffd-common.c | 269 +++++-----
tools/testing/selftests/mm/uffd-common.h | 78 +--
tools/testing/selftests/mm/uffd-stress.c | 226 ++++----
tools/testing/selftests/mm/uffd-unit-tests.c | 523 ++++++++++---------
tools/testing/selftests/mm/uffd-wp-mremap.c | 23 +-
5 files changed, 591 insertions(+), 528 deletions(-)
--
2.20.1
With joint effort from the upstream KVM community, we come up with the
4th version of mediated vPMU for x86. We have made the following changes
on top of the previous RFC v3.
v3 -> v4
- Rebase whole patchset on 6.14-rc3 base.
- Address Peter's comments on Perf part.
- Address Sean's comments on KVM part.
* Change key word "passthrough" to "mediated" in all patches
* Change static enabling to user space dynamic enabling via KVM_CAP_PMU_CAPABILITY.
* Only support GLOBAL_CTRL save/restore with VMCS exec_ctrl, drop the MSR
save/retore list support for GLOBAL_CTRL, thus the support of mediated
vPMU is constrained to SapphireRapids and later CPUs on Intel side.
* Merge some small changes into a single patch.
- Address Sandipan's comment on invalid pmu pointer.
- Add back "eventsel_hw" and "fixed_ctr_ctrl_hw" to avoid to directly
manipulate pmc->eventsel and pmu->fixed_ctr_ctrl.
Testing (Intel side):
- Perf-based legacy vPMU (force emulation on/off)
* Kselftests pmu_counters_test, pmu_event_filter_test and
vmx_pmu_caps_test pass.
* KUT PMU tests pmu, pmu_lbr, pmu_pebs pass.
* Basic perf counting/sampling tests in 3 scenarios, guest-only,
host-only and host-guest coexistence all pass.
- Mediated vPMU (force emulation on/off)
* Kselftests pmu_counters_test, pmu_event_filter_test and
vmx_pmu_caps_test pass.
* KUT PMU tests pmu, pmu_lbr, pmu_pebs pass.
* Basic perf counting/sampling tests in 3 scenarios, guest-only,
host-only and host-guest coexistence all pass.
- Failures. All above tests passed on Intel Granite Rapids as well
except a failure on KUT/pmu_pebs.
* GP counter 0 (0xfffffffffffe): PEBS record (written seq 0)
is verified (including size, counters and cfg).
* The pebs_data_cfg (0xb500000000) doesn't match with the
effective MSR_PEBS_DATA_CFG (0x0).
* This failure has nothing to do with this mediated vPMU patch set. The
failure is caused by Granite Rapids supported timed PEBS which needs
extra support on Qemu and KUT/pmu_pebs. These extra support would be
sent in separate patches later.
Testing (AMD side):
- Kselftests pmu_counters_test, pmu_event_filter_test and
vmx_pmu_caps_test all pass
- legacy guest with KUT/pmu:
* qmeu option: -cpu host, -perfctr-core
* when set force_emulation_prefix=1, passes
* when set force_emulation_prefix=0, passes
- perfmon-v1 guest with KUT/pmu:
* qmeu option: -cpu host, -perfmon-v2
* when set force_emulation_prefix=1, passes
* when set force_emulation_prefix=0, passes
- perfmon-v2 guest with KUT/pmu:
* qmeu option: -cpu host
* when set force_emulation_prefix=1, passes
* when set force_emulation_prefix=0, passes
- perf_fuzzer (perfmon-v2):
* fails with soft lockup in guest in current version.
* culprit could be between 6.13 ~ 6.14-rc3 within KVM
* Series tested on 6.12 and 6.13 without issue.
Note: a QEMU series is needed to run mediated vPMU v4:
- https://lore.kernel.org/all/20250324123712.34096-1-dapeng1.mi@linux.intel.c…
History:
- RFC v3: https://lore.kernel.org/all/20240801045907.4010984-1-mizhang@google.com/
- RFC v2: https://lore.kernel.org/all/20240506053020.3911940-1-mizhang@google.com/
- RFC v1: https://lore.kernel.org/all/20240126085444.324918-1-xiong.y.zhang@linux.int…
Dapeng Mi (18):
KVM: x86/pmu: Introduce enable_mediated_pmu global parameter
KVM: x86/pmu: Check PMU cpuid configuration from user space
KVM: x86: Rename vmx_vmentry/vmexit_ctrl() helpers
KVM: x86/pmu: Add perf_capabilities field in struct kvm_host_values{}
KVM: x86/pmu: Move PMU_CAP_{FW_WRITES,LBR_FMT} into msr-index.h header
KVM: VMX: Add macros to wrap around
{secondary,tertiary}_exec_controls_changebit()
KVM: x86/pmu: Check if mediated vPMU can intercept rdpmc
KVM: x86/pmu/vmx: Save/load guest IA32_PERF_GLOBAL_CTRL with
vm_exit/entry_ctrl
KVM: x86/pmu: Optimize intel/amd_pmu_refresh() helpers
KVM: x86/pmu: Setup PMU MSRs' interception mode
KVM: x86/pmu: Handle PMU MSRs interception and event filtering
KVM: x86/pmu: Switch host/guest PMU context at vm-exit/vm-entry
KVM: x86/pmu: Handle emulated instruction for mediated vPMU
KVM: nVMX: Add macros to simplify nested MSR interception setting
KVM: selftests: Add mediated vPMU supported for pmu tests
KVM: Selftests: Support mediated vPMU for vmx_pmu_caps_test
KVM: Selftests: Fix pmu_counters_test error for mediated vPMU
KVM: x86/pmu: Expose enable_mediated_pmu parameter to user space
Kan Liang (8):
perf: Support get/put mediated PMU interfaces
perf: Skip pmu_ctx based on event_type
perf: Clean up perf ctx time
perf: Add a EVENT_GUEST flag
perf: Add generic exclude_guest support
perf: Add switch_guest_ctx() interface
perf/x86: Support switch_guest_ctx interface
perf/x86/intel: Support PERF_PMU_CAP_MEDIATED_VPMU
Mingwei Zhang (5):
perf/x86: Forbid PMI handler when guest own PMU
perf/x86/core: Plumb mediated PMU capability from x86_pmu to
x86_pmu_cap
KVM: x86/pmu: Exclude PMU MSRs in vmx_get_passthrough_msr_slot()
KVM: x86/pmu: introduce eventsel_hw to prepare for pmu event filtering
KVM: nVMX: Add nested virtualization support for mediated PMU
Sandipan Das (4):
perf/x86/core: Do not set bit width for unavailable counters
KVM: x86/pmu: Add AMD PMU registers to direct access list
KVM: x86/pmu/svm: Set GuestOnly bit and clear HostOnly bit when guest
write to event selectors
perf/x86/amd: Support PERF_PMU_CAP_MEDIATED_VPMU for AMD host
Xiong Zhang (3):
x86/irq: Factor out common code for installing kvm irq handler
perf: core/x86: Register a new vector for KVM GUEST PMI
KVM: x86/pmu: Register KVM_GUEST_PMI_VECTOR handler
arch/x86/events/amd/core.c | 2 +
arch/x86/events/core.c | 40 +-
arch/x86/events/intel/core.c | 5 +
arch/x86/include/asm/hardirq.h | 1 +
arch/x86/include/asm/idtentry.h | 1 +
arch/x86/include/asm/irq.h | 2 +-
arch/x86/include/asm/irq_vectors.h | 5 +-
arch/x86/include/asm/kvm-x86-pmu-ops.h | 2 +
arch/x86/include/asm/kvm_host.h | 10 +
arch/x86/include/asm/msr-index.h | 18 +-
arch/x86/include/asm/perf_event.h | 1 +
arch/x86/include/asm/vmx.h | 1 +
arch/x86/kernel/idt.c | 1 +
arch/x86/kernel/irq.c | 39 +-
arch/x86/kvm/cpuid.c | 15 +
arch/x86/kvm/pmu.c | 254 ++++++++-
arch/x86/kvm/pmu.h | 45 ++
arch/x86/kvm/svm/pmu.c | 148 ++++-
arch/x86/kvm/svm/svm.c | 26 +
arch/x86/kvm/svm/svm.h | 2 +-
arch/x86/kvm/vmx/capabilities.h | 11 +-
arch/x86/kvm/vmx/nested.c | 68 ++-
arch/x86/kvm/vmx/pmu_intel.c | 224 ++++++--
arch/x86/kvm/vmx/vmx.c | 89 +--
arch/x86/kvm/vmx/vmx.h | 11 +-
arch/x86/kvm/x86.c | 63 ++-
arch/x86/kvm/x86.h | 2 +
include/linux/perf_event.h | 47 +-
kernel/events/core.c | 519 ++++++++++++++----
.../beauty/arch/x86/include/asm/irq_vectors.h | 5 +-
.../selftests/kvm/include/kvm_test_harness.h | 13 +
.../testing/selftests/kvm/include/kvm_util.h | 3 +
.../selftests/kvm/include/x86/processor.h | 8 +
tools/testing/selftests/kvm/lib/kvm_util.c | 23 +
.../selftests/kvm/x86/pmu_counters_test.c | 24 +-
.../selftests/kvm/x86/pmu_event_filter_test.c | 8 +-
.../selftests/kvm/x86/vmx_pmu_caps_test.c | 2 +-
37 files changed, 1480 insertions(+), 258 deletions(-)
base-commit: 0ad2507d5d93f39619fc42372c347d6006b64319
--
2.49.0.395.g12beb8f557-goog
This series introduces VFIO selftests, located in
tools/testing/selftests/vfio/.
VFIO selftests aim to enable kernel developers to write and run tests
that take the form of userspace programs that interact with VFIO and
IOMMUFD uAPIs. VFIO selftests can be used to write functional tests for
new features, regression tests for bugs, and performance tests for
optimizations.
These tests are designed to interact with real PCI devices, i.e. they do
not rely on mocking out or faking any behavior in the kernel. This
allows the tests to exercise not only VFIO but also IOMMUFD, the IOMMU
driver, interrupt remapping, IRQ handling, etc.
We chose selftests to host these tests primarily to enable integration
with the existing KVM selftests. As explained in the next section,
enabling KVM developers to test the interaction between VFIO and KVM is
one of the motivators of this series.
Motivation
-----------------------------------------------------------------------
The main motivation for this series is upcoming development in the
kernel to support Hypervisor Live Updates [1][2]. Live Update is a
specialized reboot process where selected devices are kept operational
and their kernel state is preserved and recreated across a kexec. For
devices, DMA and interrupts may continue during the reboot. VFIO-bound
devices are the main target, since the first usecase of Live Updates is
to enable host kernel upgrades in a Cloud Computing environment without
disrupting running customer VMs.
To prepare for upcoming support for Live Updates in VFIO, IOMMUFD, IOMMU
drivers, the PCI layer, etc., we'd like to first lay the ground work for
exercising and testing VFIO from kernel selftests. This way when we
eventually upstream support for Live Updates, we can also upstream tests
for those changes, rather than purely relying on Live Update integration
tests which would be hard to share and reproduce upstream.
But even without Live Updates, VFIO and IOMMUFD are becoming an
increasingly critical component of running KVM-based VMs in cloud
environments. Virtualized networking and storage are increasingly being
offloaded to smart NICs/cards, and demand for high performance
networking, storage, and AI are also leading to NICs, SSDs, and GPUs
being directly attached to VMs via VFIO.
VFIO selftests increases our ability to test in several ways.
- It enables developers sending VFIO, IOMMUFD, etc. commits upstream to
test their changes against all existing VFIO selftests, reducing the
probability of regressions.
- It enables developers sending VFIO, IOMMUFD, etc. commits upstream to
include tests alongside their changes, increasing the quality of the
code that is merged.
- It enables testing the interaction between VFIO and KVM. There are
some paths in KVM that are only exercised through VFIO, such as IRQ
bypass. VFIO selftests provides a helper library to enable KVM
developers to write KVM selftests to test those interactions [3].
Design
-----------------------------------------------------------------------
VFIO selftests are designed around interacting with with VFIO-managed PCI
devices. As such, the core data struture is struct vfio_pci_device, which
represents a single PCI device.
struct vfio_pci_device *device;
device = vfio_pci_device_init("0000:6a:01.0", iommu_mode);
...
vfio_pci_device_cleanup(device);
vfio_pci_device_init() sets up a container or iommufd, depending on the
iommu_mode argument, to manage DMA mappings, fetches information about
the device and what interrupts it supports from VFIO and caches it, and
mmap()s all mappable BARs for the test to use.
There are helper methods that operate on struct vfio_pci_device to do
things like read and write to PCI config space, enable/disable IRQs, and
map memory for DMA,
struct vfio_pci_device and its methods do not care about what device
they are actually interacting with. It can be a GPU, a NIC, an SSD, etc.
To keep things simple initially, VFIO selftests only support a single
device per group and per container/iommufd. But it should be possible to
relax those restrictions in the future, e.g. to enable testing with
multiple devices in the same container/iommufd.
Driver Framework
-----------------------------------------------------------------------
In order to support VFIO selftests where a device is generating DMA and
interrupts on command, the VFIO selftests supports a driver framework.
This framework abstracts away device-specific details allowing VFIO
selftests to be written in a generic way, and then run against different
devices depending on what hardware developers have access to.
The framework also aims to support carrying drivers out-of-tree, e.g.
so that companies can run VFIO selftests with custom/test hardware.
Drivers must implement the following methods:
- probe(): Check if the driver supports a given device.
- init(): Initialize the driver.
- remove(): Deinitialize the driver and reset the device.
- memcpy_start(): Kick off a series of repeated memcpys (DMA reads and
DMA writes).
- memcpy_wait(): Wait for a memcpy operation to complete.
- send_msi(): Make the device send an MSI interrupt.
memcpy_start/wait() are for generating DMA. We separate the operation
into 2 steps so that tests can trigger a long-running DMA operation. We
expect to use this to stress test Live Updates by kicking off a
long-running mempcy operation and then performing a Live Update. These
methods are required to not generate any interrupts.
send_msi() is used for testing MSI and MSI-x interrupts. The driver
tells the test which MSI it will be using via device->driver.msi.
It's the responsibility of the test to set up a region of memory
and map it into the device for use by the driver, e.g. for in-memory
descriptors, before calling init().
A demo of the driver framework can be found in
tools/testing/selftests/vfio/vfio_pci_driver_test.c.
In addition, this series introduces a new KVM selftest to demonstrate
delivering a device MSI directly into a guest, which can be found in
tools/testing/selftests/kvm/vfio_pci_device_irq_test.c.
Tests
-----------------------------------------------------------------------
There are 5 tests in this series, mostly to demonstrate as a
proof-of-concept:
- tools/testing/selftests/vfio/vfio_pci_device_test.c
- tools/testing/selftests/vfio/vfio_pci_driver_test.c
- tools/testing/selftests/vfio/vfio_iommufd_setup_test.c
- tools/testing/selftests/vfio/vfio_dma_mapping_test.c
- tools/testing/selftests/kvm/vfio_pci_device_irq_test.c
Integrating with KVM selftests
-----------------------------------------------------------------------
To support testing the interactions between VFIO and KVM, the VFIO
selftests support sharing its library with the KVM selftest. The patches
at the end of this series demonstrate how that works.
Essentially, we allow the KVM selftests to build their own copy of
tools/testing/selftests/vfio/lib/ and link it into KVM selftests
binaries. This requires minimal changes to the KVM selftests Makefile.
Future Areas of Development
-----------------------------------------------------------------------
Library:
- Driver support for devices that can be used on AMD, ARM, and other
platforms.
- Driver support for a device available in QEMU VMs.
- Support for tests that use multiple devices.
- Support for IOMMU groups with multiple devices.
- Support for multiple devices sharing the same container/iommufd.
- Sharing TEST_ASSERT() macros and other common code between KVM
and VFIO selftests.
Tests:
- DMA mapping performance tests for BARs/HugeTLB/etc.
- Live Update selftests.
- Porting Sean's KVM selftest for posted interrupts to use the VFIO
selftests library [3]
This series can also be found on GitHub:
https://github.com/dmatlack/linux/tree/vfio/selftests/rfc
Cc: Alex Williamson <alex.williamson(a)redhat.com>
Cc: Jason Gunthorpe <jgg(a)nvidia.com>
Cc: Kevin Tian <kevin.tian(a)intel.com>
Cc: Paolo Bonzini <pbonzini(a)redhat.com>
Cc: Sean Christopherson <seanjc(a)google.com>
Cc: Vipin Sharma <vipinsh(a)google.com>
Cc: Josh Hilke <jrhilke(a)google.com>
Cc: Pasha Tatashin <pasha.tatashin(a)soleen.com>
Cc: Saeed Mahameed <saeedm(a)nvidia.com>
Cc: Saeed Mahameed <saeedm(a)nvidia.com>
Cc: Adithya Jayachandran <ajayachandra(a)nvidia.com>
Cc: Parav Pandit <parav(a)nvidia.com>
Cc: Leon Romanovsky <leonro(a)nvidia.com>
Cc: Vinicius Costa Gomes <vinicius.gomes(a)intel.com>
Cc: Dave Jiang <dave.jiang(a)intel.com>
Cc: Dan Williams <dan.j.williams(a)intel.com>
[1] https://lore.kernel.org/all/f35359d5-63e1-8390-619f-67961443bfe1@google.com/
[2] https://lore.kernel.org/all/20250515182322.117840-1-pasha.tatashin@soleen.c…
[3] https://lore.kernel.org/kvm/20250404193923.1413163-68-seanjc@google.com/
David Matlack (28):
selftests: Create tools/testing/selftests/vfio
vfio: selftests: Add a helper library for VFIO selftests
vfio: selftests: Introduce vfio_pci_device_test
tools headers: Add stub definition for __iomem
tools headers: Import asm-generic MMIO helpers
tools headers: Import x86 MMIO helper overrides
tools headers: Import iosubmit_cmds512()
tools headers: Import drivers/dma/ioat/{hw.h,registers.h}
tools headers: Import drivers/dma/idxd/registers.h
tools headers: Import linux/pci_ids.h
vfio: selftests: Keep track of DMA regions mapped into the device
vfio: selftests: Enable asserting MSI eventfds not firing
vfio: selftests: Add a helper for matching vendor+device IDs
vfio: selftests: Add driver framework
vfio: sefltests: Add vfio_pci_driver_test
vfio: selftests: Add driver for Intel CBDMA
vfio: selftests: Add driver for Intel DSA
vfio: selftests: Move helper to get cdev path to libvfio
vfio: selftests: Encapsulate IOMMU mode
vfio: selftests: Add [-i iommu_mode] option to all tests
vfio: selftests: Add vfio_type1v2_mode
vfio: selftests: Add iommufd_compat_type1{,v2} modes
vfio: selftests: Add iommufd mode
vfio: selftests: Make iommufd the default iommu_mode
vfio: selftests: Add a script to help with running VFIO selftests
KVM: selftests: Build and link sefltests/vfio/lib into KVM selftests
KVM: selftests: Test sending a vfio-pci device IRQ to a VM
KVM: selftests: Use real device MSIs in vfio_pci_device_irq_test
Josh Hilke (5):
vfio: selftests: Test basic VFIO and IOMMUFD integration
vfio: selftests: Move vfio dma mapping test to their own file
vfio: selftests: Add test to reset vfio device.
vfio: selftests: Use command line to set hugepage size for DMA mapping
test
vfio: selftests: Validate 2M/1G HugeTLB are mapped as 2M/1G in IOMMU
MAINTAINERS | 7 +
tools/arch/x86/include/asm/io.h | 101 +
tools/arch/x86/include/asm/special_insns.h | 27 +
tools/include/asm-generic/io.h | 482 +++
tools/include/asm/io.h | 11 +
tools/include/drivers/dma/idxd/registers.h | 601 +++
tools/include/drivers/dma/ioat/hw.h | 270 ++
tools/include/drivers/dma/ioat/registers.h | 251 ++
tools/include/linux/compiler.h | 4 +
tools/include/linux/io.h | 4 +-
tools/include/linux/pci_ids.h | 3212 +++++++++++++++++
tools/testing/selftests/Makefile | 1 +
tools/testing/selftests/kvm/Makefile.kvm | 6 +-
.../testing/selftests/kvm/include/kvm_util.h | 4 +
tools/testing/selftests/kvm/lib/kvm_util.c | 21 +
.../selftests/kvm/vfio_pci_device_irq_test.c | 173 +
tools/testing/selftests/vfio/.gitignore | 7 +
tools/testing/selftests/vfio/Makefile | 20 +
.../testing/selftests/vfio/lib/drivers/dsa.c | 416 +++
.../testing/selftests/vfio/lib/drivers/ioat.c | 235 ++
.../selftests/vfio/lib/include/vfio_util.h | 271 ++
tools/testing/selftests/vfio/lib/libvfio.mk | 26 +
.../selftests/vfio/lib/vfio_pci_device.c | 573 +++
.../selftests/vfio/lib/vfio_pci_driver.c | 126 +
tools/testing/selftests/vfio/run.sh | 110 +
.../selftests/vfio/vfio_dma_mapping_test.c | 239 ++
.../selftests/vfio/vfio_iommufd_setup_test.c | 133 +
.../selftests/vfio/vfio_pci_device_test.c | 195 +
.../selftests/vfio/vfio_pci_driver_test.c | 256 ++
29 files changed, 7780 insertions(+), 2 deletions(-)
create mode 100644 tools/arch/x86/include/asm/io.h
create mode 100644 tools/arch/x86/include/asm/special_insns.h
create mode 100644 tools/include/asm-generic/io.h
create mode 100644 tools/include/asm/io.h
create mode 100644 tools/include/drivers/dma/idxd/registers.h
create mode 100644 tools/include/drivers/dma/ioat/hw.h
create mode 100644 tools/include/drivers/dma/ioat/registers.h
create mode 100644 tools/include/linux/pci_ids.h
create mode 100644 tools/testing/selftests/kvm/vfio_pci_device_irq_test.c
create mode 100644 tools/testing/selftests/vfio/.gitignore
create mode 100644 tools/testing/selftests/vfio/Makefile
create mode 100644 tools/testing/selftests/vfio/lib/drivers/dsa.c
create mode 100644 tools/testing/selftests/vfio/lib/drivers/ioat.c
create mode 100644 tools/testing/selftests/vfio/lib/include/vfio_util.h
create mode 100644 tools/testing/selftests/vfio/lib/libvfio.mk
create mode 100644 tools/testing/selftests/vfio/lib/vfio_pci_device.c
create mode 100644 tools/testing/selftests/vfio/lib/vfio_pci_driver.c
create mode 100755 tools/testing/selftests/vfio/run.sh
create mode 100644 tools/testing/selftests/vfio/vfio_dma_mapping_test.c
create mode 100644 tools/testing/selftests/vfio/vfio_iommufd_setup_test.c
create mode 100644 tools/testing/selftests/vfio/vfio_pci_device_test.c
create mode 100644 tools/testing/selftests/vfio/vfio_pci_driver_test.c
base-commit: a11a72229881d8ac1d52ea727101bc9c744189c1
prerequisite-patch-id: 3bae97c9e1093148763235f47a84fa040b512d04
--
2.49.0.1151.ga128411c76-goog