diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2025-07-30 17:14:01 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2025-07-30 17:14:01 -0700 |
| commit | 63eb28bb1402891b1ad2be02a530f29a9dd7f1cd (patch) | |
| tree | 982d9fa36c6e4f3e437c6fca10c151d165f7ddde /tools | |
| parent | Merge tag 'for-linus-6.17-rc1-tag' of git://git.kernel.org/pub/scm/linux/kern... (diff) | |
| parent | Merge tag 'kvm-s390-next-6.17-1' of https://git.kernel.org/pub/scm/linux/kern... (diff) | |
| download | linux-63eb28bb1402891b1ad2be02a530f29a9dd7f1cd.tar.gz linux-63eb28bb1402891b1ad2be02a530f29a9dd7f1cd.zip | |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"ARM:
- Host driver for GICv5, the next generation interrupt controller for
arm64, including support for interrupt routing, MSIs, interrupt
translation and wired interrupts
- Use FEAT_GCIE_LEGACY on GICv5 systems to virtualize GICv3 VMs on
GICv5 hardware, leveraging the legacy VGIC interface
- Userspace control of the 'nASSGIcap' GICv3 feature, allowing
userspace to disable support for SGIs w/o an active state on
hardware that previously advertised it unconditionally
- Map supporting endpoints with cacheable memory attributes on
systems with FEAT_S2FWB and DIC where KVM no longer needs to
perform cache maintenance on the address range
- Nested support for FEAT_RAS and FEAT_DoubleFault2, allowing the
guest hypervisor to inject external aborts into an L2 VM and take
traps of masked external aborts to the hypervisor
- Convert more system register sanitization to the config-driven
implementation
- Fixes to the visibility of EL2 registers, namely making VGICv3
system registers accessible through the VGIC device instead of the
ONE_REG vCPU ioctls
- Various cleanups and minor fixes
LoongArch:
- Add stat information for in-kernel irqchip
- Add tracepoints for CPUCFG and CSR emulation exits
- Enhance in-kernel irqchip emulation
- Various cleanups
RISC-V:
- Enable ring-based dirty memory tracking
- Improve perf kvm stat to report interrupt events
- Delegate illegal instruction trap to VS-mode
- MMU improvements related to upcoming nested virtualization
s390x
- Fixes
x86:
- Add CONFIG_KVM_IOAPIC for x86 to allow disabling support for I/O
APIC, PIC, and PIT emulation at compile time
- Share device posted IRQ code between SVM and VMX and harden it
against bugs and runtime errors
- Use vcpu_idx, not vcpu_id, for GA log tag/metadata, to make lookups
O(1) instead of O(n)
- For MMIO stale data mitigation, track whether or not a vCPU has
access to (host) MMIO based on whether the page tables have MMIO
pfns mapped; using VFIO is prone to false negatives
- Rework the MSR interception code so that the SVM and VMX APIs are
more or less identical
- Recalculate all MSR intercepts from scratch on MSR filter changes,
instead of maintaining shadow bitmaps
- Advertise support for LKGS (Load Kernel GS base), a new instruction
that's loosely related to FRED, but is supported and enumerated
independently
- Fix a user-triggerable WARN that syzkaller found by setting the
vCPU in INIT_RECEIVED state (aka wait-for-SIPI), and then putting
the vCPU into VMX Root Mode (post-VMXON). Trying to detect every
possible path leading to architecturally forbidden states is hard
and even risks breaking userspace (if it goes from valid to valid
state but passes through invalid states), so just wait until
KVM_RUN to detect that the vCPU state isn't allowed
- Add KVM_X86_DISABLE_EXITS_APERFMPERF to allow disabling
interception of APERF/MPERF reads, so that a "properly" configured
VM can access APERF/MPERF. This has many caveats (APERF/MPERF
cannot be zeroed on vCPU creation or saved/restored on suspend and
resume, or preserved over thread migration let alone VM migration)
but can be useful whenever you're interested in letting Linux
guests see the effective physical CPU frequency in /proc/cpuinfo
- Reject KVM_SET_TSC_KHZ for vm file descriptors if vCPUs have been
created, as there's no known use case for changing the default
frequency for other VM types and it goes counter to the very reason
why the ioctl was added to the vm file descriptor. And also, there
would be no way to make it work for confidential VMs with a
"secure" TSC, so kill two birds with one stone
- Dynamically allocation the shadow MMU's hashed page list, and defer
allocating the hashed list until it's actually needed (the TDP MMU
doesn't use the list)
- Extract many of KVM's helpers for accessing architectural local
APIC state to common x86 so that they can be shared by guest-side
code for Secure AVIC
- Various cleanups and fixes
x86 (Intel):
- Preserve the host's DEBUGCTL.FREEZE_IN_SMM when running the guest.
Failure to honor FREEZE_IN_SMM can leak host state into guests
- Explicitly check vmcs12.GUEST_DEBUGCTL on nested VM-Enter to
prevent L1 from running L2 with features that KVM doesn't support,
e.g. BTF
x86 (AMD):
- WARN and reject loading kvm-amd.ko instead of panicking the kernel
if the nested SVM MSRPM offsets tracker can't handle an MSR (which
is pretty much a static condition and therefore should never
happen, but still)
- Fix a variety of flaws and bugs in the AVIC device posted IRQ code
- Inhibit AVIC if a vCPU's ID is too big (relative to what hardware
supports) instead of rejecting vCPU creation
- Extend enable_ipiv module param support to SVM, by simply leaving
IsRunning clear in the vCPU's physical ID table entry
- Disable IPI virtualization, via enable_ipiv, if the CPU is affected
by erratum #1235, to allow (safely) enabling AVIC on such CPUs
- Request GA Log interrupts if and only if the target vCPU is
blocking, i.e. only if KVM needs a notification in order to wake
the vCPU
- Intercept SPEC_CTRL on AMD if the MSR shouldn't exist according to
the vCPU's CPUID model
- Accept any SNP policy that is accepted by the firmware with respect
to SMT and single-socket restrictions. An incompatible policy
doesn't put the kernel at risk in any way, so there's no reason for
KVM to care
- Drop a superfluous WBINVD (on all CPUs!) when destroying a VM and
use WBNOINVD instead of WBINVD when possible for SEV cache
maintenance
- When reclaiming memory from an SEV guest, only do cache flushes on
CPUs that have ever run a vCPU for the guest, i.e. don't flush the
caches for CPUs that can't possibly have cache lines with dirty,
encrypted data
Generic:
- Rework irqbypass to track/match producers and consumers via an
xarray instead of a linked list. Using a linked list leads to
O(n^2) insertion times, which is hugely problematic for use cases
that create large numbers of VMs. Such use cases typically don't
actually use irqbypass, but eliminating the pointless registration
is a future problem to solve as it likely requires new uAPI
- Track irqbypass's "token" as "struct eventfd_ctx *" instead of a
"void *", to avoid making a simple concept unnecessarily difficult
to understand
- Decouple device posted IRQs from VFIO device assignment, as binding
a VM to a VFIO group is not a requirement for enabling device
posted IRQs
- Clean up and document/comment the irqfd assignment code
- Disallow binding multiple irqfds to an eventfd with a priority
waiter, i.e. ensure an eventfd is bound to at most one irqfd
through the entire host, and add a selftest to verify eventfd:irqfd
bindings are globally unique
- Add a tracepoint for KVM_SET_MEMORY_ATTRIBUTES to help debug issues
related to private <=> shared memory conversions
- Drop guest_memfd's .getattr() implementation as the VFS layer will
call generic_fillattr() if inode_operations.getattr is NULL
- Fix issues with dirty ring harvesting where KVM doesn't bound the
processing of entries in any way, which allows userspace to keep
KVM in a tight loop indefinitely
- Kill off kvm_arch_{start,end}_assignment() and x86's associated
tracking, now that KVM no longer uses assigned_device_count as a
heuristic for either irqbypass usage or MDS mitigation
Selftests:
- Fix a comment typo
- Verify KVM is loaded when getting any KVM module param so that
attempting to run a selftest without kvm.ko loaded results in a
SKIP message about KVM not being loaded/enabled (versus some random
parameter not existing)
- Skip tests that hit EACCES when attempting to access a file, and
print a "Root required?" help message. In most cases, the test just
needs to be run with elevated permissions"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (340 commits)
Documentation: KVM: Use unordered list for pre-init VGIC registers
RISC-V: KVM: Avoid re-acquiring memslot in kvm_riscv_gstage_map()
RISC-V: KVM: Use find_vma_intersection() to search for intersecting VMAs
RISC-V: perf/kvm: Add reporting of interrupt events
RISC-V: KVM: Enable ring-based dirty memory tracking
RISC-V: KVM: Fix inclusion of Smnpm in the guest ISA bitmap
RISC-V: KVM: Delegate illegal instruction fault to VS mode
RISC-V: KVM: Pass VMID as parameter to kvm_riscv_hfence_xyz() APIs
RISC-V: KVM: Factor-out g-stage page table management
RISC-V: KVM: Add vmid field to struct kvm_riscv_hfence
RISC-V: KVM: Introduce struct kvm_gstage_mapping
RISC-V: KVM: Factor-out MMU related declarations into separate headers
RISC-V: KVM: Use ncsr_xyz() in kvm_riscv_vcpu_trap_redirect()
RISC-V: KVM: Implement kvm_arch_flush_remote_tlbs_range()
RISC-V: KVM: Don't flush TLB when PTE is unchanged
RISC-V: KVM: Replace KVM_REQ_HFENCE_GVMA_VMID_ALL with KVM_REQ_TLB_FLUSH
RISC-V: KVM: Rename and move kvm_riscv_local_tlb_sanitize()
RISC-V: KVM: Drop the return value of kvm_riscv_vcpu_aia_init()
RISC-V: KVM: Check kvm_riscv_vcpu_alloc_vector_context() return value
KVM: arm64: selftests: Add FEAT_RAS EL2 registers to get-reg-list
...
Diffstat (limited to 'tools')
27 files changed, 1333 insertions, 319 deletions
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index d00b85cb168c..7415a3863891 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -618,6 +618,7 @@ struct kvm_ioeventfd { #define KVM_X86_DISABLE_EXITS_HLT (1 << 1) #define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) #define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) +#define KVM_X86_DISABLE_EXITS_APERFMPERF (1 << 4) /* for KVM_ENABLE_CAP */ struct kvm_enable_cap { diff --git a/tools/perf/arch/riscv/util/kvm-stat.c b/tools/perf/arch/riscv/util/kvm-stat.c index 491aef449d1a..3ea7acb5e159 100644 --- a/tools/perf/arch/riscv/util/kvm-stat.c +++ b/tools/perf/arch/riscv/util/kvm-stat.c @@ -9,10 +9,10 @@ #include <memory.h> #include "../../../util/evsel.h" #include "../../../util/kvm-stat.h" -#include "riscv_exception_types.h" +#include "riscv_trap_types.h" #include "debug.h" -define_exit_reasons_table(riscv_exit_reasons, kvm_riscv_exception_class); +define_exit_reasons_table(riscv_exit_reasons, kvm_riscv_trap_class); const char *vcpu_id_str = "id"; const char *kvm_exit_reason = "scause"; @@ -30,7 +30,7 @@ static void event_get_key(struct evsel *evsel, struct event_key *key) { key->info = 0; - key->key = evsel__intval(evsel, sample, kvm_exit_reason); + key->key = evsel__intval(evsel, sample, kvm_exit_reason) & ~CAUSE_IRQ_FLAG; key->exit_reasons = riscv_exit_reasons; } diff --git a/tools/perf/arch/riscv/util/riscv_exception_types.h b/tools/perf/arch/riscv/util/riscv_exception_types.h deleted file mode 100644 index c49b8fa5e847..000000000000 --- a/tools/perf/arch/riscv/util/riscv_exception_types.h +++ /dev/null @@ -1,35 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#ifndef ARCH_PERF_RISCV_EXCEPTION_TYPES_H -#define ARCH_PERF_RISCV_EXCEPTION_TYPES_H - -#define EXC_INST_MISALIGNED 0 -#define EXC_INST_ACCESS 1 -#define EXC_INST_ILLEGAL 2 -#define EXC_BREAKPOINT 3 -#define EXC_LOAD_MISALIGNED 4 -#define EXC_LOAD_ACCESS 5 -#define EXC_STORE_MISALIGNED 6 -#define EXC_STORE_ACCESS 7 -#define EXC_SYSCALL 8 -#define EXC_HYPERVISOR_SYSCALL 9 -#define EXC_SUPERVISOR_SYSCALL 10 -#define EXC_INST_PAGE_FAULT 12 -#define EXC_LOAD_PAGE_FAULT 13 -#define EXC_STORE_PAGE_FAULT 15 -#define EXC_INST_GUEST_PAGE_FAULT 20 -#define EXC_LOAD_GUEST_PAGE_FAULT 21 -#define EXC_VIRTUAL_INST_FAULT 22 -#define EXC_STORE_GUEST_PAGE_FAULT 23 - -#define EXC(x) {EXC_##x, #x } - -#define kvm_riscv_exception_class \ - EXC(INST_MISALIGNED), EXC(INST_ACCESS), EXC(INST_ILLEGAL), \ - EXC(BREAKPOINT), EXC(LOAD_MISALIGNED), EXC(LOAD_ACCESS), \ - EXC(STORE_MISALIGNED), EXC(STORE_ACCESS), EXC(SYSCALL), \ - EXC(HYPERVISOR_SYSCALL), EXC(SUPERVISOR_SYSCALL), \ - EXC(INST_PAGE_FAULT), EXC(LOAD_PAGE_FAULT), EXC(STORE_PAGE_FAULT), \ - EXC(INST_GUEST_PAGE_FAULT), EXC(LOAD_GUEST_PAGE_FAULT), \ - EXC(VIRTUAL_INST_FAULT), EXC(STORE_GUEST_PAGE_FAULT) - -#endif /* ARCH_PERF_RISCV_EXCEPTION_TYPES_H */ diff --git a/tools/perf/arch/riscv/util/riscv_trap_types.h b/tools/perf/arch/riscv/util/riscv_trap_types.h new file mode 100644 index 000000000000..6cc71eb01fca --- /dev/null +++ b/tools/perf/arch/riscv/util/riscv_trap_types.h @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef ARCH_PERF_RISCV_TRAP_TYPES_H +#define ARCH_PERF_RISCV_TRAP_TYPES_H + +/* Exception cause high bit - is an interrupt if set */ +#define CAUSE_IRQ_FLAG (_AC(1, UL) << (__riscv_xlen - 1)) + +/* Interrupt causes (minus the high bit) */ +#define IRQ_S_SOFT 1 +#define IRQ_VS_SOFT 2 +#define IRQ_M_SOFT 3 +#define IRQ_S_TIMER 5 +#define IRQ_VS_TIMER 6 +#define IRQ_M_TIMER 7 +#define IRQ_S_EXT 9 +#define IRQ_VS_EXT 10 +#define IRQ_M_EXT 11 +#define IRQ_S_GEXT 12 +#define IRQ_PMU_OVF 13 + +/* Exception causes */ +#define EXC_INST_MISALIGNED 0 +#define EXC_INST_ACCESS 1 +#define EXC_INST_ILLEGAL 2 +#define EXC_BREAKPOINT 3 +#define EXC_LOAD_MISALIGNED 4 +#define EXC_LOAD_ACCESS 5 +#define EXC_STORE_MISALIGNED 6 +#define EXC_STORE_ACCESS 7 +#define EXC_SYSCALL 8 +#define EXC_HYPERVISOR_SYSCALL 9 +#define EXC_SUPERVISOR_SYSCALL 10 +#define EXC_INST_PAGE_FAULT 12 +#define EXC_LOAD_PAGE_FAULT 13 +#define EXC_STORE_PAGE_FAULT 15 +#define EXC_INST_GUEST_PAGE_FAULT 20 +#define EXC_LOAD_GUEST_PAGE_FAULT 21 +#define EXC_VIRTUAL_INST_FAULT 22 +#define EXC_STORE_GUEST_PAGE_FAULT 23 + +#define TRAP(x) { x, #x } + +#define kvm_riscv_trap_class \ + TRAP(IRQ_S_SOFT), TRAP(IRQ_VS_SOFT), TRAP(IRQ_M_SOFT), \ + TRAP(IRQ_S_TIMER), TRAP(IRQ_VS_TIMER), TRAP(IRQ_M_TIMER), \ + TRAP(IRQ_S_EXT), TRAP(IRQ_VS_EXT), TRAP(IRQ_M_EXT), \ + TRAP(IRQ_S_GEXT), TRAP(IRQ_PMU_OVF), \ + TRAP(EXC_INST_MISALIGNED), TRAP(EXC_INST_ACCESS), TRAP(EXC_INST_ILLEGAL), \ + TRAP(EXC_BREAKPOINT), TRAP(EXC_LOAD_MISALIGNED), TRAP(EXC_LOAD_ACCESS), \ + TRAP(EXC_STORE_MISALIGNED), TRAP(EXC_STORE_ACCESS), TRAP(EXC_SYSCALL), \ + TRAP(EXC_HYPERVISOR_SYSCALL), TRAP(EXC_SUPERVISOR_SYSCALL), \ + TRAP(EXC_INST_PAGE_FAULT), TRAP(EXC_LOAD_PAGE_FAULT), \ + TRAP(EXC_STORE_PAGE_FAULT), TRAP(EXC_INST_GUEST_PAGE_FAULT), \ + TRAP(EXC_LOAD_GUEST_PAGE_FAULT), TRAP(EXC_VIRTUAL_INST_FAULT), \ + TRAP(EXC_STORE_GUEST_PAGE_FAULT) + +#endif /* ARCH_PERF_RISCV_TRAP_TYPES_H */ diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 38b95998e1e6..f6fe7a07a0a2 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -59,6 +59,7 @@ TEST_PROGS_x86 += x86/nx_huge_pages_test.sh TEST_GEN_PROGS_COMMON = demand_paging_test TEST_GEN_PROGS_COMMON += dirty_log_test TEST_GEN_PROGS_COMMON += guest_print_test +TEST_GEN_PROGS_COMMON += irqfd_test TEST_GEN_PROGS_COMMON += kvm_binary_stats_test TEST_GEN_PROGS_COMMON += kvm_create_max_vcpus TEST_GEN_PROGS_COMMON += kvm_page_table_test @@ -134,6 +135,7 @@ TEST_GEN_PROGS_x86 += x86/amx_test TEST_GEN_PROGS_x86 += x86/max_vcpuid_cap_test TEST_GEN_PROGS_x86 += x86/triple_fault_event_test TEST_GEN_PROGS_x86 += x86/recalc_apic_map_test +TEST_GEN_PROGS_x86 += x86/aperfmperf_test TEST_GEN_PROGS_x86 += access_tracking_perf_test TEST_GEN_PROGS_x86 += coalesced_io_test TEST_GEN_PROGS_x86 += dirty_log_perf_test @@ -156,7 +158,7 @@ TEST_GEN_PROGS_arm64 += arm64/arch_timer_edge_cases TEST_GEN_PROGS_arm64 += arm64/debug-exceptions TEST_GEN_PROGS_arm64 += arm64/host_sve TEST_GEN_PROGS_arm64 += arm64/hypercalls -TEST_GEN_PROGS_arm64 += arm64/mmio_abort +TEST_GEN_PROGS_arm64 += arm64/external_aborts TEST_GEN_PROGS_arm64 += arm64/page_fault_test TEST_GEN_PROGS_arm64 += arm64/psci_test TEST_GEN_PROGS_arm64 += arm64/set_id_regs diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index da7196fd1b23..c9de66537ec3 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -596,11 +596,8 @@ int main(int argc, char *argv[]) if (ret) return ret; } else { - page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR); - __TEST_REQUIRE(page_idle_fd >= 0, - "Couldn't open /sys/kernel/mm/page_idle/bitmap. " - "Is CONFIG_IDLE_PAGE_TRACKING enabled?"); - + page_idle_fd = __open_path_or_exit("/sys/kernel/mm/page_idle/bitmap", O_RDWR, + "Is CONFIG_IDLE_PAGE_TRACKING enabled?"); close(page_idle_fd); puts("Using page_idle for aging"); diff --git a/tools/testing/selftests/kvm/arch_timer.c b/tools/testing/selftests/kvm/arch_timer.c index acb2cb596332..cf8fb67104f1 100644 --- a/tools/testing/selftests/kvm/arch_timer.c +++ b/tools/testing/selftests/kvm/arch_timer.c @@ -98,16 +98,11 @@ static uint32_t test_get_pcpu(void) static int test_migrate_vcpu(unsigned int vcpu_idx) { int ret; - cpu_set_t cpuset; uint32_t new_pcpu = test_get_pcpu(); - CPU_ZERO(&cpuset); - CPU_SET(new_pcpu, &cpuset); - pr_debug("Migrating vCPU: %u to pCPU: %u\n", vcpu_idx, new_pcpu); - ret = pthread_setaffinity_np(pt_vcpu_run[vcpu_idx], - sizeof(cpuset), &cpuset); + ret = __pin_task_to_cpu(pt_vcpu_run[vcpu_idx], new_pcpu); /* Allow the error where the vCPU thread is already finished */ TEST_ASSERT(ret == 0 || ret == ESRCH, diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c index 4e71740a098b..ce74d069cb7b 100644 --- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c @@ -862,25 +862,6 @@ static uint32_t next_pcpu(void) return next; } -static void migrate_self(uint32_t new_pcpu) -{ - int ret; - cpu_set_t cpuset; - pthread_t thread; - - thread = pthread_self(); - - CPU_ZERO(&cpuset); - CPU_SET(new_pcpu, &cpuset); - - pr_debug("Migrating from %u to %u\n", sched_getcpu(), new_pcpu); - - ret = pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset); - - TEST_ASSERT(ret == 0, "Failed to migrate to pCPU: %u; ret: %d\n", - new_pcpu, ret); -} - static void kvm_set_cntxct(struct kvm_vcpu *vcpu, uint64_t cnt, enum arch_timer timer) { @@ -907,7 +888,7 @@ static void handle_sync(struct kvm_vcpu *vcpu, struct ucall *uc) sched_yield(); break; case USERSPACE_MIGRATE_SELF: - migrate_self(next_pcpu()); + pin_self_to_cpu(next_pcpu()); break; default: break; @@ -919,7 +900,7 @@ static void test_run(struct kvm_vm *vm, struct kvm_vcpu *vcpu) struct ucall uc; /* Start on CPU 0 */ - migrate_self(0); + pin_self_to_cpu(0); while (true) { vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/arm64/external_aborts.c b/tools/testing/selftests/kvm/arm64/external_aborts.c new file mode 100644 index 000000000000..062bf84cced1 --- /dev/null +++ b/tools/testing/selftests/kvm/arm64/external_aborts.c @@ -0,0 +1,330 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * external_abort - Tests for userspace external abort injection + * + * Copyright (c) 2024 Google LLC + */ +#include "processor.h" +#include "test_util.h" + +#define MMIO_ADDR 0x8000000ULL +#define EXPECTED_SERROR_ISS (ESR_ELx_ISV | 0x1d1ed) + +static u64 expected_abort_pc; + +static void expect_sea_handler(struct ex_regs *regs) +{ + u64 esr = read_sysreg(esr_el1); + + GUEST_ASSERT_EQ(regs->pc, expected_abort_pc); + GUEST_ASSERT_EQ(ESR_ELx_EC(esr), ESR_ELx_EC_DABT_CUR); + GUEST_ASSERT_EQ(esr & ESR_ELx_FSC_TYPE, ESR_ELx_FSC_EXTABT); + + GUEST_DONE(); +} + +static void unexpected_dabt_handler(struct ex_regs *regs) +{ + GUEST_FAIL("Unexpected data abort at PC: %lx\n", regs->pc); +} + +static struct kvm_vm *vm_create_with_dabt_handler(struct kvm_vcpu **vcpu, void *guest_code, + handler_fn dabt_handler) +{ + struct kvm_vm *vm = vm_create_with_one_vcpu(vcpu, guest_code); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(*vcpu); + vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT, ESR_ELx_EC_DABT_CUR, dabt_handler); + + virt_map(vm, MMIO_ADDR, MMIO_ADDR, 1); + + return vm; +} + +static void vcpu_inject_sea(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_events events = {}; + + events.exception.ext_dabt_pending = true; + vcpu_events_set(vcpu, &events); +} + +static bool vcpu_has_ras(struct kvm_vcpu *vcpu) +{ + u64 pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); + + return SYS_FIELD_GET(ID_AA64PFR0_EL1, RAS, pfr0); +} + +static bool guest_has_ras(void) +{ + return SYS_FIELD_GET(ID_AA64PFR0_EL1, RAS, read_sysreg(id_aa64pfr0_el1)); +} + +static void vcpu_inject_serror(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_events events = {}; + + events.exception.serror_pending = true; + if (vcpu_has_ras(vcpu)) { + events.exception.serror_has_esr = true; + events.exception.serror_esr = EXPECTED_SERROR_ISS; + } + + vcpu_events_set(vcpu, &events); +} + +static void __vcpu_run_expect(struct kvm_vcpu *vcpu, unsigned int cmd) +{ + struct ucall uc; + + vcpu_run(vcpu); + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + break; + default: + if (uc.cmd == cmd) + return; + + TEST_FAIL("Unexpected ucall: %lu", uc.cmd); + } +} + +static void vcpu_run_expect_done(struct kvm_vcpu *vcpu) +{ + __vcpu_run_expect(vcpu, UCALL_DONE); +} + +static void vcpu_run_expect_sync(struct kvm_vcpu *vcpu) +{ + __vcpu_run_expect(vcpu, UCALL_SYNC); +} + +extern char test_mmio_abort_insn; + +static noinline void test_mmio_abort_guest(void) +{ + WRITE_ONCE(expected_abort_pc, (u64)&test_mmio_abort_insn); + + asm volatile("test_mmio_abort_insn:\n\t" + "ldr x0, [%0]\n\t" + : : "r" (MMIO_ADDR) : "x0", "memory"); + + GUEST_FAIL("MMIO instruction should not retire"); +} + +/* + * Test that KVM doesn't complete MMIO emulation when userspace has made an + * external abort pending for the instruction. + */ +static void test_mmio_abort(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_mmio_abort_guest, + expect_sea_handler); + struct kvm_run *run = vcpu->run; + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_MMIO); + TEST_ASSERT_EQ(run->mmio.phys_addr, MMIO_ADDR); + TEST_ASSERT_EQ(run->mmio.len, sizeof(unsigned long)); + TEST_ASSERT(!run->mmio.is_write, "Expected MMIO read"); + + vcpu_inject_sea(vcpu); + vcpu_run_expect_done(vcpu); + kvm_vm_free(vm); +} + +extern char test_mmio_nisv_insn; + +static void test_mmio_nisv_guest(void) +{ + WRITE_ONCE(expected_abort_pc, (u64)&test_mmio_nisv_insn); + + asm volatile("test_mmio_nisv_insn:\n\t" + "ldr x0, [%0], #8\n\t" + : : "r" (MMIO_ADDR) : "x0", "memory"); + + GUEST_FAIL("MMIO instruction should not retire"); +} + +/* + * Test that the KVM_RUN ioctl fails for ESR_EL2.ISV=0 MMIO aborts if userspace + * hasn't enabled KVM_CAP_ARM_NISV_TO_USER. + */ +static void test_mmio_nisv(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_mmio_nisv_guest, + unexpected_dabt_handler); + + TEST_ASSERT(_vcpu_run(vcpu), "Expected nonzero return code from KVM_RUN"); + TEST_ASSERT_EQ(errno, ENOSYS); + + kvm_vm_free(vm); +} + +/* + * Test that ESR_EL2.ISV=0 MMIO aborts reach userspace and that an injected SEA + * reaches the guest. + */ +static void test_mmio_nisv_abort(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_mmio_nisv_guest, + expect_sea_handler); + struct kvm_run *run = vcpu->run; + + vm_enable_cap(vm, KVM_CAP_ARM_NISV_TO_USER, 1); + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_ARM_NISV); + TEST_ASSERT_EQ(run->arm_nisv.fault_ipa, MMIO_ADDR); + + vcpu_inject_sea(vcpu); + vcpu_run_expect_done(vcpu); + kvm_vm_free(vm); +} + +static void unexpected_serror_handler(struct ex_regs *regs) +{ + GUEST_FAIL("Took unexpected SError exception"); +} + +static void test_serror_masked_guest(void) +{ + GUEST_ASSERT(read_sysreg(isr_el1) & ISR_EL1_A); + + isb(); + + GUEST_DONE(); +} + +static void test_serror_masked(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_serror_masked_guest, + unexpected_dabt_handler); + + vm_install_exception_handler(vm, VECTOR_ERROR_CURRENT, unexpected_serror_handler); + + vcpu_inject_serror(vcpu); + vcpu_run_expect_done(vcpu); + kvm_vm_free(vm); +} + +static void expect_serror_handler(struct ex_regs *regs) +{ + u64 esr = read_sysreg(esr_el1); + + GUEST_ASSERT_EQ(ESR_ELx_EC(esr), ESR_ELx_EC_SERROR); + if (guest_has_ras()) + GUEST_ASSERT_EQ(ESR_ELx_ISS(esr), EXPECTED_SERROR_ISS); + + GUEST_DONE(); +} + +static void test_serror_guest(void) +{ + GUEST_ASSERT(read_sysreg(isr_el1) & ISR_EL1_A); + + local_serror_enable(); + isb(); + local_serror_disable(); + + GUEST_FAIL("Should've taken pending SError exception"); +} + +static void test_serror(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_serror_guest, + unexpected_dabt_handler); + + vm_install_exception_handler(vm, VECTOR_ERROR_CURRENT, expect_serror_handler); + + vcpu_inject_serror(vcpu); + vcpu_run_expect_done(vcpu); + kvm_vm_free(vm); +} + +static void test_serror_emulated_guest(void) +{ + GUEST_ASSERT(!(read_sysreg(isr_el1) & ISR_EL1_A)); + + local_serror_enable(); + GUEST_SYNC(0); + local_serror_disable(); + + GUEST_FAIL("Should've taken unmasked SError exception"); +} + +static void test_serror_emulated(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_serror_emulated_guest, + unexpected_dabt_handler); + + vm_install_exception_handler(vm, VECTOR_ERROR_CURRENT, expect_serror_handler); + + vcpu_run_expect_sync(vcpu); + vcpu_inject_serror(vcpu); + vcpu_run_expect_done(vcpu); + kvm_vm_free(vm); +} + +static void test_mmio_ease_guest(void) +{ + sysreg_clear_set_s(SYS_SCTLR2_EL1, 0, SCTLR2_EL1_EASE); + isb(); + + test_mmio_abort_guest(); +} + +/* + * Test that KVM doesn't complete MMIO emulation when userspace has made an + * external abort pending for the instruction. + */ +static void test_mmio_ease(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_mmio_ease_guest, + unexpected_dabt_handler); + struct kvm_run *run = vcpu->run; + u64 pfr1; + + pfr1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); + if (!SYS_FIELD_GET(ID_AA64PFR1_EL1, DF2, pfr1)) { + pr_debug("Skipping %s\n", __func__); + return; + } + + /* + * SCTLR2_ELx.EASE changes the exception vector to the SError vector but + * doesn't further modify the exception context (e.g. ESR_ELx, FAR_ELx). + */ + vm_install_exception_handler(vm, VECTOR_ERROR_CURRENT, expect_sea_handler); + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_MMIO); + TEST_ASSERT_EQ(run->mmio.phys_addr, MMIO_ADDR); + TEST_ASSERT_EQ(run->mmio.len, sizeof(unsigned long)); + TEST_ASSERT(!run->mmio.is_write, "Expected MMIO read"); + + vcpu_inject_sea(vcpu); + vcpu_run_expect_done(vcpu); + kvm_vm_free(vm); +} + +int main(void) +{ + test_mmio_abort(); + test_mmio_nisv(); + test_mmio_nisv_abort(); + test_serror(); + test_serror_masked(); + test_serror_emulated(); + test_mmio_ease(); +} diff --git a/tools/testing/selftests/kvm/arm64/get-reg-list.c b/tools/testing/selftests/kvm/arm64/get-reg-list.c index d01798b6b3b4..011fad95dd02 100644 --- a/tools/testing/selftests/kvm/arm64/get-reg-list.c +++ b/tools/testing/selftests/kvm/arm64/get-reg-list.c @@ -15,6 +15,12 @@ #include "test_util.h" #include "processor.h" +#define SYS_REG(r) ARM64_SYS_REG(sys_reg_Op0(SYS_ ## r), \ + sys_reg_Op1(SYS_ ## r), \ + sys_reg_CRn(SYS_ ## r), \ + sys_reg_CRm(SYS_ ## r), \ + sys_reg_Op2(SYS_ ## r)) + struct feature_id_reg { __u64 reg; __u64 id_reg; @@ -22,37 +28,43 @@ struct feature_id_reg { __u64 feat_min; }; -static struct feature_id_reg feat_id_regs[] = { - { - ARM64_SYS_REG(3, 0, 2, 0, 3), /* TCR2_EL1 */ - ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 0, - 1 - }, - { - ARM64_SYS_REG(3, 0, 10, 2, 2), /* PIRE0_EL1 */ - ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 8, - 1 - }, - { - ARM64_SYS_REG(3, 0, 10, 2, 3), /* PIR_EL1 */ - ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 8, - 1 - }, - { - ARM64_SYS_REG(3, 0, 10, 2, 4), /* POR_EL1 */ - ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 16, - 1 - }, - { - ARM64_SYS_REG(3, 3, 10, 2, 4), /* POR_EL0 */ - ARM64_SYS_REG(3, 0, 0, 7, 3), /* ID_AA64MMFR3_EL1 */ - 16, - 1 +#define FEAT(id, f, v) \ + .id_reg = SYS_REG(id), \ + .feat_shift = id ## _ ## f ## _SHIFT, \ + .feat_min = id ## _ ## f ## _ ## v + +#define REG_FEAT(r, id, f, v) \ + { \ + .reg = SYS_REG(r), \ + FEAT(id, f, v) \ } + +static struct feature_id_reg feat_id_regs[] = { + REG_FEAT(TCR2_EL1, ID_AA64MMFR3_EL1, TCRX, IMP), + REG_FEAT(TCR2_EL2, ID_AA64MMFR3_EL1, TCRX, IMP), + REG_FEAT(PIRE0_EL1, ID_AA64MMFR3_EL1, S1PIE, IMP), + REG_FEAT(PIRE0_EL2, ID_AA64MMFR3_EL1, S1PIE, IMP), + REG_FEAT(PIR_EL1, ID_AA64MMFR3_EL1, S1PIE, IMP), + REG_FEAT(PIR_EL2, ID_AA64MMFR3_EL1, S1PIE, IMP), + REG_FEAT(POR_EL1, ID_AA64MMFR3_EL1, S1POE, IMP), + REG_FEAT(POR_EL0, ID_AA64MMFR3_EL1, S1POE, IMP), + REG_FEAT(POR_EL2, ID_AA64MMFR3_EL1, S1POE, IMP), + REG_FEAT(HCRX_EL2, ID_AA64MMFR1_EL1, HCX, IMP), + REG_FEAT(HFGRTR_EL2, ID_AA64MMFR0_EL1, FGT, IMP), + REG_FEAT(HFGWTR_EL2, ID_AA64MMFR0_EL1, FGT, IMP), + REG_FEAT(HFGITR_EL2, ID_AA64MMFR0_EL1, FGT, IMP), + REG_FEAT(HDFGRTR_EL2, ID_AA64MMFR0_EL1, FGT, IMP), + REG_FEAT(HDFGWTR_EL2, ID_AA64MMFR0_EL1, FGT, IMP), + REG_FEAT(HAFGRTR_EL2, ID_AA64MMFR0_EL1, FGT, IMP), + REG_FEAT(HFGRTR2_EL2, ID_AA64MMFR0_EL1, FGT, FGT2), + REG_FEAT(HFGWTR2_EL2, ID_AA64MMFR0_EL1, FGT, FGT2), + REG_FEAT(HFGITR2_EL2, ID_AA64MMFR0_EL1, FGT, FGT2), + REG_FEAT(HDFGRTR2_EL2, ID_AA64MMFR0_EL1, FGT, FGT2), + REG_FEAT(HDFGWTR2_EL2, ID_AA64MMFR0_EL1, FGT, FGT2), + REG_FEAT(ZCR_EL2, ID_AA64PFR0_EL1, SVE, IMP), + REG_FEAT(SCTLR2_EL1, ID_AA64MMFR3_EL1, SCTLRX, IMP), + REG_FEAT(VDISR_EL2, ID_AA64PFR0_EL1, RAS, IMP), + REG_FEAT(VSESR_EL2, ID_AA64PFR0_EL1, RAS, IMP), }; bool filter_reg(__u64 reg) @@ -469,6 +481,7 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 1, 0, 0), /* SCTLR_EL1 */ ARM64_SYS_REG(3, 0, 1, 0, 1), /* ACTLR_EL1 */ ARM64_SYS_REG(3, 0, 1, 0, 2), /* CPACR_EL1 */ + KVM_ARM64_SYS_REG(SYS_SCTLR2_EL1), ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ @@ -686,6 +699,62 @@ static __u64 pauth_generic_regs[] = { ARM64_SYS_REG(3, 0, 2, 3, 1), /* APGAKEYHI_EL1 */ }; +static __u64 el2_regs[] = { + SYS_REG(VPIDR_EL2), + SYS_REG(VMPIDR_EL2), + SYS_REG(SCTLR_EL2), + SYS_REG(ACTLR_EL2), + SYS_REG(HCR_EL2), + SYS_REG(MDCR_EL2), + SYS_REG(CPTR_EL2), + SYS_REG(HSTR_EL2), + SYS_REG(HFGRTR_EL2), + SYS_REG(HFGWTR_EL2), + SYS_REG(HFGITR_EL2), + SYS_REG(HACR_EL2), + SYS_REG(ZCR_EL2), + SYS_REG(HCRX_EL2), + SYS_REG(TTBR0_EL2), + SYS_REG(TTBR1_EL2), + SYS_REG(TCR_EL2), + SYS_REG(TCR2_EL2), + SYS_REG(VTTBR_EL2), + SYS_REG(VTCR_EL2), + SYS_REG(VNCR_EL2), + SYS_REG(HDFGRTR2_EL2), + SYS_REG(HDFGWTR2_EL2), + SYS_REG(HFGRTR2_EL2), + SYS_REG(HFGWTR2_EL2), + SYS_REG(HDFGRTR_EL2), + SYS_REG(HDFGWTR_EL2), + SYS_REG(HAFGRTR_EL2), + SYS_REG(HFGITR2_EL2), + SYS_REG(SPSR_EL2), + SYS_REG(ELR_EL2), + SYS_REG(AFSR0_EL2), + SYS_REG(AFSR1_EL2), + SYS_REG(ESR_EL2), + SYS_REG(FAR_EL2), + SYS_REG(HPFAR_EL2), + SYS_REG(MAIR_EL2), + SYS_REG(PIRE0_EL2), + SYS_REG(PIR_EL2), + SYS_REG(POR_EL2), + SYS_REG(AMAIR_EL2), + SYS_REG(VBAR_EL2), + SYS_REG(CONTEXTIDR_EL2), + SYS_REG(TPIDR_EL2), + SYS_REG(CNTVOFF_EL2), + SYS_REG(CNTHCTL_EL2), + SYS_REG(CNTHP_CTL_EL2), + SYS_REG(CNTHP_CVAL_EL2), + SYS_REG(CNTHV_CTL_EL2), + SYS_REG(CNTHV_CVAL_EL2), + SYS_REG(SP_EL2), + SYS_REG(VDISR_EL2), + SYS_REG(VSESR_EL2), +}; + #define BASE_SUBLIST \ { "base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), } #define VREGS_SUBLIST \ @@ -712,6 +781,14 @@ static __u64 pauth_generic_regs[] = { .regs = pauth_generic_regs, \ .regs_n = ARRAY_SIZE(pauth_generic_regs), \ } +#define EL2_SUBLIST \ + { \ + .name = "EL2", \ + .capability = KVM_CAP_ARM_EL2, \ + .feature = KVM_ARM_VCPU_HAS_EL2, \ + .regs = el2_regs, \ + .regs_n = ARRAY_SIZE(el2_regs), \ + } static struct vcpu_reg_list vregs_config = { .sublists = { @@ -761,6 +838,65 @@ static struct vcpu_reg_list pauth_pmu_config = { }, }; +static struct vcpu_reg_list el2_vregs_config = { + .sublists = { + BASE_SUBLIST, + EL2_SUBLIST, + VREGS_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list el2_vregs_pmu_config = { + .sublists = { + BASE_SUBLIST, + EL2_SUBLIST, + VREGS_SUBLIST, + PMU_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list el2_sve_config = { + .sublists = { + BASE_SUBLIST, + EL2_SUBLIST, + SVE_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list el2_sve_pmu_config = { + .sublists = { + BASE_SUBLIST, + EL2_SUBLIST, + SVE_SUBLIST, + PMU_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list el2_pauth_config = { + .sublists = { + BASE_SUBLIST, + EL2_SUBLIST, + VREGS_SUBLIST, + PAUTH_SUBLIST, + {0}, + }, +}; + +static struct vcpu_reg_list el2_pauth_pmu_config = { + .sublists = { + BASE_SUBLIST, + EL2_SUBLIST, + VREGS_SUBLIST, + PAUTH_SUBLIST, + PMU_SUBLIST, + {0}, + }, +}; + struct vcpu_reg_list *vcpu_configs[] = { &vregs_config, &vregs_pmu_config, @@ -768,5 +904,12 @@ struct vcpu_reg_list *vcpu_configs[] = { &sve_pmu_config, &pauth_config, &pauth_pmu_config, + + &el2_vregs_config, + &el2_vregs_pmu_config, + &el2_sve_config, + &el2_sve_pmu_config, + &el2_pauth_config, + &el2_pauth_pmu_config, }; int vcpu_configs_n = ARRAY_SIZE(vcpu_configs); diff --git a/tools/testing/selftests/kvm/arm64/mmio_abort.c b/tools/testing/selftests/kvm/arm64/mmio_abort.c deleted file mode 100644 index 8b7a80a51b1c..000000000000 --- a/tools/testing/selftests/kvm/arm64/mmio_abort.c +++ /dev/null @@ -1,159 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * mmio_abort - Tests for userspace MMIO abort injection - * - * Copyright (c) 2024 Google LLC - */ -#include "processor.h" -#include "test_util.h" - -#define MMIO_ADDR 0x8000000ULL - -static u64 expected_abort_pc; - -static void expect_sea_handler(struct ex_regs *regs) -{ - u64 esr = read_sysreg(esr_el1); - - GUEST_ASSERT_EQ(regs->pc, expected_abort_pc); - GUEST_ASSERT_EQ(ESR_ELx_EC(esr), ESR_ELx_EC_DABT_CUR); - GUEST_ASSERT_EQ(esr & ESR_ELx_FSC_TYPE, ESR_ELx_FSC_EXTABT); - - GUEST_DONE(); -} - -static void unexpected_dabt_handler(struct ex_regs *regs) -{ - GUEST_FAIL("Unexpected data abort at PC: %lx\n", regs->pc); -} - -static struct kvm_vm *vm_create_with_dabt_handler(struct kvm_vcpu **vcpu, void *guest_code, - handler_fn dabt_handler) -{ - struct kvm_vm *vm = vm_create_with_one_vcpu(vcpu, guest_code); - - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(*vcpu); - vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT, ESR_ELx_EC_DABT_CUR, dabt_handler); - - virt_map(vm, MMIO_ADDR, MMIO_ADDR, 1); - - return vm; -} - -static void vcpu_inject_extabt(struct kvm_vcpu *vcpu) -{ - struct kvm_vcpu_events events = {}; - - events.exception.ext_dabt_pending = true; - vcpu_events_set(vcpu, &events); -} - -static void vcpu_run_expect_done(struct kvm_vcpu *vcpu) -{ - struct ucall uc; - - vcpu_run(vcpu); - switch (get_ucall(vcpu, &uc)) { - case UCALL_ABORT: - REPORT_GUEST_ASSERT(uc); - break; - case UCALL_DONE: - break; - default: - TEST_FAIL("Unexpected ucall: %lu", uc.cmd); - } -} - -extern char test_mmio_abort_insn; - -static void test_mmio_abort_guest(void) -{ - WRITE_ONCE(expected_abort_pc, (u64)&test_mmio_abort_insn); - - asm volatile("test_mmio_abort_insn:\n\t" - "ldr x0, [%0]\n\t" - : : "r" (MMIO_ADDR) : "x0", "memory"); - - GUEST_FAIL("MMIO instruction should not retire"); -} - -/* - * Test that KVM doesn't complete MMIO emulation when userspace has made an - * external abort pending for the instruction. - */ -static void test_mmio_abort(void) -{ - struct kvm_vcpu *vcpu; - struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_mmio_abort_guest, - expect_sea_handler); - struct kvm_run *run = vcpu->run; - - vcpu_run(vcpu); - TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_MMIO); - TEST_ASSERT_EQ(run->mmio.phys_addr, MMIO_ADDR); - TEST_ASSERT_EQ(run->mmio.len, sizeof(unsigned long)); - TEST_ASSERT(!run->mmio.is_write, "Expected MMIO read"); - - vcpu_inject_extabt(vcpu); - vcpu_run_expect_done(vcpu); - kvm_vm_free(vm); -} - -extern char test_mmio_nisv_insn; - -static void test_mmio_nisv_guest(void) -{ - WRITE_ONCE(expected_abort_pc, (u64)&test_mmio_nisv_insn); - - asm volatile("test_mmio_nisv_insn:\n\t" - "ldr x0, [%0], #8\n\t" - : : "r" (MMIO_ADDR) : "x0", "memory"); - - GUEST_FAIL("MMIO instruction should not retire"); -} - -/* - * Test that the KVM_RUN ioctl fails for ESR_EL2.ISV=0 MMIO aborts if userspace - * hasn't enabled KVM_CAP_ARM_NISV_TO_USER. - */ -static void test_mmio_nisv(void) -{ - struct kvm_vcpu *vcpu; - struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_mmio_nisv_guest, - unexpected_dabt_handler); - - TEST_ASSERT(_vcpu_run(vcpu), "Expected nonzero return code from KVM_RUN"); - TEST_ASSERT_EQ(errno, ENOSYS); - - kvm_vm_free(vm); -} - -/* - * Test that ESR_EL2.ISV=0 MMIO aborts reach userspace and that an injected SEA - * reaches the guest. - */ -static void test_mmio_nisv_abort(void) -{ - struct kvm_vcpu *vcpu; - struct kvm_vm *vm = vm_create_with_dabt_handler(&vcpu, test_mmio_nisv_guest, - expect_sea_handler); - struct kvm_run *run = vcpu->run; - - vm_enable_cap(vm, KVM_CAP_ARM_NISV_TO_USER, 1); - - vcpu_run(vcpu); - TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_ARM_NISV); - TEST_ASSERT_EQ(run->arm_nisv.fault_ipa, MMIO_ADDR); - - vcpu_inject_extabt(vcpu); - vcpu_run_expect_done(vcpu); - kvm_vm_free(vm); -} - -int main(void) -{ - test_mmio_abort(); - test_mmio_nisv(); - test_mmio_nisv_abort(); -} diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index 8f422bfdfcb9..d3bf9204409c 100644 --- a/tools/testing/selftests/kvm/arm64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -139,6 +139,7 @@ static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = { }; static const struct reg_ftr_bits ftr_id_aa64pfr1_el1[] = { + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR1_EL1, DF2, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR1_EL1, CSV2_frac, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR1_EL1, SSBS, ID_AA64PFR1_EL1_SSBS_NI), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR1_EL1, BT, 0), @@ -187,6 +188,14 @@ static const struct reg_ftr_bits ftr_id_aa64mmfr2_el1[] = { REG_FTR_END, }; +static const struct reg_ftr_bits ftr_id_aa64mmfr3_el1[] = { + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR3_EL1, S1POE, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR3_EL1, S1PIE, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR3_EL1, SCTLRX, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR3_EL1, TCRX, 0), + REG_FTR_END, +}; + static const struct reg_ftr_bits ftr_id_aa64zfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, F64MM, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64ZFR0_EL1, F32MM, 0), @@ -217,6 +226,7 @@ static struct test_feature_reg test_regs[] = { TEST_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0_el1), TEST_REG(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1_el1), TEST_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2_el1), + TEST_REG(SYS_ID_AA64MMFR3_EL1, ftr_id_aa64mmfr3_el1), TEST_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0_el1), }; @@ -774,8 +784,8 @@ int main(void) ARRAY_SIZE(ftr_id_aa64isar2_el1) + ARRAY_SIZE(ftr_id_aa64pfr0_el1) + ARRAY_SIZE(ftr_id_aa64pfr1_el1) + ARRAY_SIZE(ftr_id_aa64mmfr0_el1) + ARRAY_SIZE(ftr_id_aa64mmfr1_el1) + ARRAY_SIZE(ftr_id_aa64mmfr2_el1) + - ARRAY_SIZE(ftr_id_aa64zfr0_el1) - ARRAY_SIZE(test_regs) + 3 + - MPAM_IDREG_TEST + MTE_IDREG_TEST; + ARRAY_SIZE(ftr_id_aa64mmfr3_el1) + ARRAY_SIZE(ftr_id_aa64zfr0_el1) - + ARRAY_SIZE(test_regs) + 3 + MPAM_IDREG_TEST + MTE_IDREG_TEST; ksft_set_plan(test_cnt); diff --git a/tools/testing/selftests/kvm/arm64/vgic_init.c b/tools/testing/selftests/kvm/arm64/vgic_init.c index b3b5fb0ff0a9..a8e0f46bc0ab 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_init.c +++ b/tools/testing/selftests/kvm/arm64/vgic_init.c @@ -9,17 +9,18 @@ #include <asm/kvm.h> #include <asm/kvm_para.h> +#include <arm64/gic_v3.h> + #include "test_util.h" #include "kvm_util.h" #include "processor.h" #include "vgic.h" +#include "gic_v3.h" #define NR_VCPUS 4 #define REG_OFFSET(vcpu, offset) (((uint64_t)vcpu << 32) | offset) -#define GICR_TYPER 0x8 - #define VGIC_DEV_IS_V2(_d) ((_d) == KVM_DEV_TYPE_ARM_VGIC_V2) #define VGIC_DEV_IS_V3(_d) ((_d) == KVM_DEV_TYPE_ARM_VGIC_V3) @@ -675,6 +676,44 @@ static void test_v3_its_region(void) vm_gic_destroy(&v); } +static void test_v3_nassgicap(void) +{ + struct kvm_vcpu *vcpus[NR_VCPUS]; + bool has_nassgicap; + struct vm_gic vm; + u32 typer2; + int ret; + + vm = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS, vcpus); + kvm_device_attr_get(vm.gic_fd, KVM_DEV_ARM_VGIC_GRP_DIST_REGS, + GICD_TYPER2, &typer2); + has_nassgicap = typer2 & GICD_TYPER2_nASSGIcap; + + typer2 |= GICD_TYPER2_nASSGIcap; + ret = __kvm_device_attr_set(vm.gic_fd, KVM_DEV_ARM_VGIC_GRP_DIST_REGS, + GICD_TYPER2, &typer2); + if (has_nassgicap) + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_DEVICE_ATTR_SET, ret)); + else + TEST_ASSERT(ret && errno == EINVAL, + "Enabled nASSGIcap even though it's unavailable"); + + typer2 &= ~GICD_TYPER2_nASSGIcap; + kvm_device_attr_set(vm.gic_fd, KVM_DEV_ARM_VGIC_GRP_DIST_REGS, + GICD_TYPER2, &typer2); + + kvm_device_attr_set(vm.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); + + typer2 ^= GICD_TYPER2_nASSGIcap; + ret = __kvm_device_attr_set(vm.gic_fd, KVM_DEV_ARM_VGIC_GRP_DIST_REGS, + GICD_TYPER2, &typer2); + TEST_ASSERT(ret && errno == EBUSY, + "Changed nASSGIcap after initializing the VGIC"); + + vm_gic_destroy(&vm); +} + /* * Returns 0 if it's possible to create GIC device of a given type (V2 or V3). */ @@ -715,6 +754,220 @@ int test_kvm_device(uint32_t gic_dev_type) return 0; } +struct sr_def { + const char *name; + u32 encoding; +}; + +#define PACK_SR(r) \ + ((sys_reg_Op0(r) << 14) | \ + (sys_reg_Op1(r) << 11) | \ + (sys_reg_CRn(r) << 7) | \ + (sys_reg_CRm(r) << 3) | \ + (sys_reg_Op2(r))) + +#define SR(r) \ + { \ + .name = #r, \ + .encoding = r, \ + } + +static const struct sr_def sysregs_el1[] = { + SR(SYS_ICC_PMR_EL1), + SR(SYS_ICC_BPR0_EL1), + SR(SYS_ICC_AP0R0_EL1), + SR(SYS_ICC_AP0R1_EL1), + SR(SYS_ICC_AP0R2_EL1), + SR(SYS_ICC_AP0R3_EL1), + SR(SYS_ICC_AP1R0_EL1), + SR(SYS_ICC_AP1R1_EL1), + SR(SYS_ICC_AP1R2_EL1), + SR(SYS_ICC_AP1R3_EL1), + SR(SYS_ICC_BPR1_EL1), + SR(SYS_ICC_CTLR_EL1), + SR(SYS_ICC_SRE_EL1), + SR(SYS_ICC_IGRPEN0_EL1), + SR(SYS_ICC_IGRPEN1_EL1), +}; + +static const struct sr_def sysregs_el2[] = { + SR(SYS_ICH_AP0R0_EL2), + SR(SYS_ICH_AP0R1_EL2), + SR(SYS_ICH_AP0R2_EL2), + SR(SYS_ICH_AP0R3_EL2), + SR(SYS_ICH_AP1R0_EL2), + SR(SYS_ICH_AP1R1_EL2), + SR(SYS_ICH_AP1R2_EL2), + SR(SYS_ICH_AP1R3_EL2), + SR(SYS_ICH_HCR_EL2), + SR(SYS_ICC_SRE_EL2), + SR(SYS_ICH_VTR_EL2), + SR(SYS_ICH_VMCR_EL2), + SR(SYS_ICH_LR0_EL2), + SR(SYS_ICH_LR1_EL2), + SR(SYS_ICH_LR2_EL2), + SR(SYS_ICH_LR3_EL2), + SR(SYS_ICH_LR4_EL2), + SR(SYS_ICH_LR5_EL2), + SR(SYS_ICH_LR6_EL2), + SR(SYS_ICH_LR7_EL2), + SR(SYS_ICH_LR8_EL2), + SR(SYS_ICH_LR9_EL2), + SR(SYS_ICH_LR10_EL2), + SR(SYS_ICH_LR11_EL2), + SR(SYS_ICH_LR12_EL2), + SR(SYS_ICH_LR13_EL2), + SR(SYS_ICH_LR14_EL2), + SR(SYS_ICH_LR15_EL2), +}; + +static void test_sysreg_array(int gic, const struct sr_def *sr, int nr, + int (*check)(int, const struct sr_def *, const char *)) +{ + for (int i = 0; i < nr; i++) { + u64 val; + u64 attr; + int ret; + + /* Assume MPIDR_EL1.Aff*=0 */ + attr = PACK_SR(sr[i].encoding); + + /* + * The API is braindead. A register can be advertised as + * available, and yet not be readable or writable. + * ICC_APnR{1,2,3}_EL1 are examples of such non-sense, and + * ICH_APnR{1,2,3}_EL2 do follow suit for consistency. + * + * On the bright side, no known HW is implementing more than + * 5 bits of priority, so we're safe. Sort of... + */ + ret = __kvm_has_device_attr(gic, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, + attr); + TEST_ASSERT(ret == 0, "%s unavailable", sr[i].name); + + /* Check that we can write back what we read */ + ret = __kvm_device_attr_get(gic, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, + attr, &val); + TEST_ASSERT(ret == 0 || !check(gic, &sr[i], "read"), "%s unreadable", sr[i].name); + ret = __kvm_device_attr_set(gic, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, + attr, &val); + TEST_ASSERT(ret == 0 || !check(gic, &sr[i], "write"), "%s unwritable", sr[i].name); + } +} + +static u8 get_ctlr_pribits(int gic) +{ + int ret; + u64 val; + u8 pri; + + ret = __kvm_device_attr_get(gic, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, + PACK_SR(SYS_ICC_CTLR_EL1), &val); + TEST_ASSERT(ret == 0, "ICC_CTLR_EL1 unreadable"); + + pri = FIELD_GET(ICC_CTLR_EL1_PRI_BITS_MASK, val) + 1; + TEST_ASSERT(pri >= 5 && pri <= 7, "Bad pribits %d", pri); + + return pri; +} + +static int check_unaccessible_el1_regs(int gic, const struct sr_def *sr, const char *what) +{ + switch (sr->encoding) { + case SYS_ICC_AP0R1_EL1: + case SYS_ICC_AP1R1_EL1: + if (get_ctlr_pribits(gic) >= 6) + return -EINVAL; + break; + case SYS_ICC_AP0R2_EL1: + case SYS_ICC_AP0R3_EL1: + case SYS_ICC_AP1R2_EL1: + case SYS_ICC_AP1R3_EL1: + if (get_ctlr_pribits(gic) == 7) + return 0; + break; + default: + return -EINVAL; + } + + pr_info("SKIP %s for %s\n", sr->name, what); + return 0; +} + +static u8 get_vtr_pribits(int gic) +{ + int ret; + u64 val; + u8 pri; + + ret = __kvm_device_attr_get(gic, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, + PACK_SR(SYS_ICH_VTR_EL2), &val); + TEST_ASSERT(ret == 0, "ICH_VTR_EL2 unreadable"); + + pri = FIELD_GET(ICH_VTR_EL2_PRIbits, val) + 1; + TEST_ASSERT(pri >= 5 && pri <= 7, "Bad pribits %d", pri); + + return pri; +} + +static int check_unaccessible_el2_regs(int gic, const struct sr_def *sr, const char *what) +{ + switch (sr->encoding) { + case SYS_ICH_AP0R1_EL2: + case SYS_ICH_AP1R1_EL2: + if (get_vtr_pribits(gic) >= 6) + return -EINVAL; + break; + case SYS_ICH_AP0R2_EL2: + case SYS_ICH_AP0R3_EL2: + case SYS_ICH_AP1R2_EL2: + case SYS_ICH_AP1R3_EL2: + if (get_vtr_pribits(gic) == 7) + return -EINVAL; + break; + default: + return -EINVAL; + } + + pr_info("SKIP %s for %s\n", sr->name, what); + return 0; +} + +static void test_v3_sysregs(void) +{ + struct kvm_vcpu_init init = {}; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + u32 feat = 0; + int gic; + + if (kvm_check_cap(KVM_CAP_ARM_EL2)) + feat |= BIT(KVM_ARM_VCPU_HAS_EL2); + + vm = vm_create(1); + + vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init); + init.features[0] |= feat; + + vcpu = aarch64_vcpu_add(vm, 0, &init, NULL); + TEST_ASSERT(vcpu, "Can't create a vcpu?"); + + gic = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3); + TEST_ASSERT(gic >= 0, "No GIC???"); + + kvm_device_attr_set(gic, KVM_DEV_ARM_VGIC_GRP_CTRL, + KVM_DEV_ARM_VGIC_CTRL_INIT, NULL); + + test_sysreg_array(gic, sysregs_el1, ARRAY_SIZE(sysregs_el1), check_unaccessible_el1_regs); + if (feat) + test_sysreg_array(gic, sysregs_el2, ARRAY_SIZE(sysregs_el2), check_unaccessible_el2_regs); + else + pr_info("SKIP EL2 registers, not available\n"); + + close(gic); + kvm_vm_free(vm); +} + void run_tests(uint32_t gic_dev_type) { test_vcpus_then_vgic(gic_dev_type); @@ -730,6 +983,8 @@ void run_tests(uint32_t gic_dev_type) test_v3_last_bit_single_rdist(); test_v3_redist_ipa_range_check_at_vcpu_run(); test_v3_its_region(); + test_v3_sysregs(); + test_v3_nassgicap(); } } diff --git a/tools/testing/selftests/kvm/arm64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c index f4ac28d53747..a09dd423c2d7 100644 --- a/tools/testing/selftests/kvm/arm64/vgic_irq.c +++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c @@ -620,18 +620,12 @@ static void kvm_routing_and_irqfd_check(struct kvm_vm *vm, * that no actual interrupt was injected for those cases. */ - for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { - fd[f] = eventfd(0, 0); - TEST_ASSERT(fd[f] != -1, __KVM_SYSCALL_ERROR("eventfd()", fd[f])); - } + for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) + fd[f] = kvm_new_eventfd(); for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { - struct kvm_irqfd irqfd = { - .fd = fd[f], - .gsi = i - MIN_SPI, - }; assert(i <= (uint64_t)UINT_MAX); - vm_ioctl(vm, KVM_IRQFD, &irqfd); + kvm_assign_irqfd(vm, i - MIN_SPI, fd[f]); } for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) { diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config index 8835fed09e9f..96d874b239eb 100644 --- a/tools/testing/selftests/kvm/config +++ b/tools/testing/selftests/kvm/config @@ -1,5 +1,6 @@ CONFIG_KVM=y CONFIG_KVM_INTEL=y CONFIG_KVM_AMD=y +CONFIG_EVENTFD=y CONFIG_USERFAULTFD=y CONFIG_IDLE_PAGE_TRACKING=y diff --git a/tools/testing/selftests/kvm/include/arm64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h index b0fc0f945766..255fed769a8a 100644 --- a/tools/testing/selftests/kvm/include/arm64/processor.h +++ b/tools/testing/selftests/kvm/include/arm64/processor.h @@ -254,6 +254,16 @@ static inline void local_irq_disable(void) asm volatile("msr daifset, #3" : : : "memory"); } +static inline void local_serror_enable(void) +{ + asm volatile("msr daifclr, #4" : : : "memory"); +} + +static inline void local_serror_disable(void) +{ + asm volatile("msr daifset, #4" : : : "memory"); +} + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index bee65ca08721..23a506d7eca3 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -18,8 +18,11 @@ #include <asm/atomic.h> #include <asm/kvm.h> +#include <sys/eventfd.h> #include <sys/ioctl.h> +#include <pthread.h> + #include "kvm_util_arch.h" #include "kvm_util_types.h" #include "sparsebit.h" @@ -253,6 +256,7 @@ struct vm_guest_mode_params { }; extern const struct vm_guest_mode_params vm_guest_mode_params[]; +int __open_path_or_exit(const char *path, int flags, const char *enoent_help); int open_path_or_exit(const char *path, int flags); int open_kvm_dev_path_or_exit(void); @@ -502,6 +506,45 @@ static inline int vm_get_stats_fd(struct kvm_vm *vm) return fd; } +static inline int __kvm_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd, + uint32_t flags) +{ + struct kvm_irqfd irqfd = { + .fd = eventfd, + .gsi = gsi, + .flags = flags, + .resamplefd = -1, + }; + + return __vm_ioctl(vm, KVM_IRQFD, &irqfd); +} + +static inline void kvm_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd, + uint32_t flags) +{ + int ret = __kvm_irqfd(vm, gsi, eventfd, flags); + + TEST_ASSERT_VM_VCPU_IOCTL(!ret, KVM_IRQFD, ret, vm); +} + +static inline void kvm_assign_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd) +{ + kvm_irqfd(vm, gsi, eventfd, 0); +} + +static inline void kvm_deassign_irqfd(struct kvm_vm *vm, uint32_t gsi, int eventfd) +{ + kvm_irqfd(vm, gsi, eventfd, KVM_IRQFD_FLAG_DEASSIGN); +} + +static inline int kvm_new_eventfd(void) +{ + int fd = eventfd(0, 0); + + TEST_ASSERT(fd >= 0, __KVM_SYSCALL_ERROR("eventfd()", fd)); + return fd; +} + static inline void read_stats_header(int stats_fd, struct kvm_stats_header *header) { ssize_t ret; @@ -1013,7 +1056,34 @@ struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); void kvm_set_files_rlimit(uint32_t nr_vcpus); -void kvm_pin_this_task_to_pcpu(uint32_t pcpu); +int __pin_task_to_cpu(pthread_t task, int cpu); + +static inline void pin_task_to_cpu(pthread_t task, int cpu) +{ + int r; + + r = __pin_task_to_cpu(task, cpu); + TEST_ASSERT(!r, "Failed to set thread affinity to pCPU '%u'", cpu); +} + +static inline int pin_task_to_any_cpu(pthread_t task) +{ + int cpu = sched_getcpu(); + + pin_task_to_cpu(task, cpu); + return cpu; +} + +static inline void pin_self_to_cpu(int cpu) +{ + pin_task_to_cpu(pthread_self(), cpu); +} + +static inline int pin_self_to_any_cpu(void) +{ + return pin_task_to_any_cpu(pthread_self()); +} + void kvm_print_vcpu_pinning_help(void); void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], int nr_vcpus); diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index b11b5a53ebd5..2efb05c2f2fb 100644 --- a/tools/testing/selftests/kvm/include/x86/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -1150,7 +1150,6 @@ do { \ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); void kvm_init_vm_address_properties(struct kvm_vm *vm); -bool vm_is_unrestricted_guest(struct kvm_vm *vm); struct ex_regs { uint64_t rax, rcx, rdx, rbx; @@ -1325,6 +1324,11 @@ static inline bool kvm_is_forced_emulation_enabled(void) return !!get_kvm_param_integer("force_emulation_prefix"); } +static inline bool kvm_is_unrestricted_guest_enabled(void) +{ + return get_kvm_intel_param_bool("unrestricted_guest"); +} + uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr, int *level); uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr); diff --git a/tools/testing/selftests/kvm/irqfd_test.c b/tools/testing/selftests/kvm/irqfd_test.c new file mode 100644 index 000000000000..7c301b4c7005 --- /dev/null +++ b/tools/testing/selftests/kvm/irqfd_test.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <errno.h> +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <signal.h> +#include <stdint.h> +#include <sys/sysinfo.h> + +#include "kvm_util.h" + +static struct kvm_vm *vm1; +static struct kvm_vm *vm2; +static int __eventfd; +static bool done; + +/* + * KVM de-assigns based on eventfd *and* GSI, but requires unique eventfds when + * assigning (the API isn't symmetrical). Abuse the oddity and use a per-task + * GSI base to avoid false failures due to cross-task de-assign, i.e. so that + * the secondary doesn't de-assign the primary's eventfd and cause assign to + * unexpectedly succeed on the primary. + */ +#define GSI_BASE_PRIMARY 0x20 +#define GSI_BASE_SECONDARY 0x30 + +static void juggle_eventfd_secondary(struct kvm_vm *vm, int eventfd) +{ + int r, i; + + /* + * The secondary task can encounter EBADF since the primary can close + * the eventfd at any time. And because the primary can recreate the + * eventfd, at the safe fd in the file table, the secondary can also + * encounter "unexpected" success, e.g. if the close+recreate happens + * between the first and second assignments. The secondary's role is + * mostly to antagonize KVM, not to detect bugs. + */ + for (i = 0; i < 2; i++) { + r = __kvm_irqfd(vm, GSI_BASE_SECONDARY, eventfd, 0); + TEST_ASSERT(!r || errno == EBUSY || errno == EBADF, + "Wanted success, EBUSY, or EBADF, r = %d, errno = %d", + r, errno); + + /* De-assign should succeed unless the eventfd was closed. */ + r = __kvm_irqfd(vm, GSI_BASE_SECONDARY + i, eventfd, KVM_IRQFD_FLAG_DEASSIGN); + TEST_ASSERT(!r || errno == EBADF, + "De-assign should succeed unless the fd was closed"); + } +} + +static void *secondary_irqfd_juggler(void *ign) +{ + while (!READ_ONCE(done)) { + juggle_eventfd_secondary(vm1, READ_ONCE(__eventfd)); + juggle_eventfd_secondary(vm2, READ_ONCE(__eventfd)); + } + + return NULL; +} + +static void juggle_eventfd_primary(struct kvm_vm *vm, int eventfd) +{ + int r1, r2; + + /* + * At least one of the assigns should fail. KVM disallows assigning a + * single eventfd to multiple GSIs (or VMs), so it's possible that both + * assignments can fail, too. + */ + r1 = __kvm_irqfd(vm, GSI_BASE_PRIMARY, eventfd, 0); + TEST_ASSERT(!r1 || errno == EBUSY, + "Wanted success or EBUSY, r = %d, errno = %d", r1, errno); + + r2 = __kvm_irqfd(vm, GSI_BASE_PRIMARY + 1, eventfd, 0); + TEST_ASSERT(r1 || (r2 && errno == EBUSY), + "Wanted failure (EBUSY), r1 = %d, r2 = %d, errno = %d", + r1, r2, errno); + + /* + * De-assign should always succeed, even if the corresponding assign + * failed. + */ + kvm_irqfd(vm, GSI_BASE_PRIMARY, eventfd, KVM_IRQFD_FLAG_DEASSIGN); + kvm_irqfd(vm, GSI_BASE_PRIMARY + 1, eventfd, KVM_IRQFD_FLAG_DEASSIGN); +} + +int main(int argc, char *argv[]) +{ + pthread_t racing_thread; + int r, i; + + /* Create "full" VMs, as KVM_IRQFD requires an in-kernel IRQ chip. */ + vm1 = vm_create(1); + vm2 = vm_create(1); + + WRITE_ONCE(__eventfd, kvm_new_eventfd()); + + kvm_irqfd(vm1, 10, __eventfd, 0); + + r = __kvm_irqfd(vm1, 11, __eventfd, 0); + TEST_ASSERT(r && errno == EBUSY, + "Wanted EBUSY, r = %d, errno = %d", r, errno); + + r = __kvm_irqfd(vm2, 12, __eventfd, 0); + TEST_ASSERT(r && errno == EBUSY, + "Wanted EBUSY, r = %d, errno = %d", r, errno); + + /* + * De-assign all eventfds, along with multiple eventfds that were never + * assigned. KVM's ABI is that de-assign is allowed so long as the + * eventfd itself is valid. + */ + kvm_irqfd(vm1, 11, READ_ONCE(__eventfd), KVM_IRQFD_FLAG_DEASSIGN); + kvm_irqfd(vm1, 12, READ_ONCE(__eventfd), KVM_IRQFD_FLAG_DEASSIGN); + kvm_irqfd(vm1, 13, READ_ONCE(__eventfd), KVM_IRQFD_FLAG_DEASSIGN); + kvm_irqfd(vm1, 14, READ_ONCE(__eventfd), KVM_IRQFD_FLAG_DEASSIGN); + kvm_irqfd(vm1, 10, READ_ONCE(__eventfd), KVM_IRQFD_FLAG_DEASSIGN); + + close(__eventfd); + + pthread_create(&racing_thread, NULL, secondary_irqfd_juggler, vm2); + + for (i = 0; i < 10000; i++) { + WRITE_ONCE(__eventfd, kvm_new_eventfd()); + + juggle_eventfd_primary(vm1, __eventfd); + juggle_eventfd_primary(vm2, __eventfd); + close(__eventfd); + } + + WRITE_ONCE(done, true); + pthread_join(racing_thread, NULL); +} diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index a055343a7bf7..c3f5142b0a54 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -26,15 +26,27 @@ static uint32_t last_guest_seed; static int vcpu_mmap_sz(void); -int open_path_or_exit(const char *path, int flags) +int __open_path_or_exit(const char *path, int flags, const char *enoent_help) { int fd; fd = open(path, flags); - __TEST_REQUIRE(fd >= 0 || errno != ENOENT, "Cannot open %s: %s", path, strerror(errno)); - TEST_ASSERT(fd >= 0, "Failed to open '%s'", path); + if (fd < 0) + goto error; return fd; + +error: + if (errno == EACCES || errno == ENOENT) + ksft_exit_skip("- Cannot open '%s': %s. %s\n", + path, strerror(errno), + errno == EACCES ? "Root required?" : enoent_help); + TEST_FAIL("Failed to open '%s'", path); +} + +int open_path_or_exit(const char *path, int flags) +{ + return __open_path_or_exit(path, flags, ""); } /* @@ -48,7 +60,7 @@ int open_path_or_exit(const char *path, int flags) */ static int _open_kvm_dev_path_or_exit(int flags) { - return open_path_or_exit(KVM_DEV_PATH, flags); + return __open_path_or_exit(KVM_DEV_PATH, flags, "Is KVM loaded and enabled?"); } int open_kvm_dev_path_or_exit(void) @@ -64,6 +76,9 @@ static ssize_t get_module_param(const char *module_name, const char *param, ssize_t bytes_read; int fd, r; + /* Verify KVM is loaded, to provide a more helpful SKIP message. */ + close(open_kvm_dev_path_or_exit()); + r = snprintf(path, path_size, "/sys/module/%s/parameters/%s", module_name, param); TEST_ASSERT(r < path_size, @@ -605,15 +620,14 @@ struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm) return vm_vcpu_recreate(vm, 0); } -void kvm_pin_this_task_to_pcpu(uint32_t pcpu) +int __pin_task_to_cpu(pthread_t task, int cpu) { - cpu_set_t mask; - int r; + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); - CPU_ZERO(&mask); - CPU_SET(pcpu, &mask); - r = sched_setaffinity(0, sizeof(mask), &mask); - TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.", pcpu); + return pthread_setaffinity_np(task, sizeof(cpuset), &cpuset); } static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask) @@ -667,7 +681,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], /* 2. Check if the main worker needs to be pinned. */ if (cpu) { - kvm_pin_this_task_to_pcpu(parse_pcpu(cpu, &allowed_mask)); + pin_self_to_cpu(parse_pcpu(cpu, &allowed_mask)); cpu = strtok(NULL, delim); } @@ -1716,7 +1730,18 @@ void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) /* Create an interrupt controller chip for the specified VM. */ void vm_create_irqchip(struct kvm_vm *vm) { - vm_ioctl(vm, KVM_CREATE_IRQCHIP, NULL); + int r; + + /* + * Allocate a fully in-kernel IRQ chip by default, but fall back to a + * split model (x86 only) if that fails (KVM x86 allows compiling out + * support for KVM_CREATE_IRQCHIP). + */ + r = __vm_ioctl(vm, KVM_CREATE_IRQCHIP, NULL); + if (r && errno == ENOTTY && kvm_has_cap(KVM_CAP_SPLIT_IRQCHIP)) + vm_enable_cap(vm, KVM_CAP_SPLIT_IRQCHIP, 24); + else + TEST_ASSERT_VM_VCPU_IOCTL(!r, KVM_CREATE_IRQCHIP, r, vm); vm->has_irqchip = true; } diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c index 313277486a1d..557c0a0a5658 100644 --- a/tools/testing/selftests/kvm/lib/memstress.c +++ b/tools/testing/selftests/kvm/lib/memstress.c @@ -265,7 +265,7 @@ static void *vcpu_thread_main(void *data) int vcpu_idx = vcpu->vcpu_idx; if (memstress_args.pin_vcpus) - kvm_pin_this_task_to_pcpu(memstress_args.vcpu_to_pcpu[vcpu_idx]); + pin_self_to_cpu(memstress_args.vcpu_to_pcpu[vcpu_idx]); WRITE_ONCE(vcpu->running, true); diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c index cfed9d26cc71..a99188f87a38 100644 --- a/tools/testing/selftests/kvm/lib/sparsebit.c +++ b/tools/testing/selftests/kvm/lib/sparsebit.c @@ -116,7 +116,7 @@ * * + A node with all mask bits set only occurs when the last bit * described by the previous node is not equal to this nodes - * starting index - 1. All such occurences of this condition are + * starting index - 1. All such occurrences of this condition are * avoided by moving the setting of the nodes mask bits into * the previous nodes num_after setting. * @@ -592,7 +592,7 @@ static struct node *node_split(struct sparsebit *s, sparsebit_idx_t idx) * * + A node with all mask bits set only occurs when the last bit * described by the previous node is not equal to this nodes - * starting index - 1. All such occurences of this condition are + * starting index - 1. All such occurrences of this condition are * avoided by moving the setting of the nodes mask bits into * the previous nodes num_after setting. */ diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c index a92dc1dad085..d4c19ac885a9 100644 --- a/tools/testing/selftests/kvm/lib/x86/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -1264,16 +1264,6 @@ done: return min(max_gfn, ht_gfn - 1); } -/* Returns true if kvm_intel was loaded with unrestricted_guest=1. */ -bool vm_is_unrestricted_guest(struct kvm_vm *vm) -{ - /* Ensure that a KVM vendor-specific module is loaded. */ - if (vm == NULL) - close(open_kvm_dev_path_or_exit()); - - return get_kvm_intel_param_bool("unrestricted_guest"); -} - void kvm_selftest_arch_init(void) { host_cpu_is_intel = this_cpu_is_intel(); diff --git a/tools/testing/selftests/kvm/x86/aperfmperf_test.c b/tools/testing/selftests/kvm/x86/aperfmperf_test.c new file mode 100644 index 000000000000..8b15a13df939 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/aperfmperf_test.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test for KVM_X86_DISABLE_EXITS_APERFMPERF + * + * Copyright (C) 2025, Google LLC. + * + * Test the ability to disable VM-exits for rdmsr of IA32_APERF and + * IA32_MPERF. When these VM-exits are disabled, reads of these MSRs + * return the host's values. + * + * Note: Requires read access to /dev/cpu/<lpu>/msr to read host MSRs. + */ + +#include <fcntl.h> +#include <limits.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <unistd.h> +#include <asm/msr-index.h> + +#include "kvm_util.h" +#include "processor.h" +#include "svm_util.h" +#include "test_util.h" +#include "vmx.h" + +#define NUM_ITERATIONS 10000 + +static int open_dev_msr(int cpu) +{ + char path[PATH_MAX]; + + snprintf(path, sizeof(path), "/dev/cpu/%d/msr", cpu); + return open_path_or_exit(path, O_RDONLY); +} + +static uint64_t read_dev_msr(int msr_fd, uint32_t msr) +{ + uint64_t data; + ssize_t rc; + + rc = pread(msr_fd, &data, sizeof(data), msr); + TEST_ASSERT(rc == sizeof(data), "Read of MSR 0x%x failed", msr); + + return data; +} + +static void guest_read_aperf_mperf(void) +{ + int i; + + for (i = 0; i < NUM_ITERATIONS; i++) + GUEST_SYNC2(rdmsr(MSR_IA32_APERF), rdmsr(MSR_IA32_MPERF)); +} + +#define L2_GUEST_STACK_SIZE 64 + +static void l2_guest_code(void) +{ + guest_read_aperf_mperf(); + GUEST_DONE(); +} + +static void l1_svm_code(struct svm_test_data *svm) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + struct vmcb *vmcb = svm->vmcb; + + generic_svm_setup(svm, l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + run_guest(vmcb, svm->vmcb_gpa); +} + +static void l1_vmx_code(struct vmx_pages *vmx) +{ + unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + + GUEST_ASSERT_EQ(prepare_for_vmx_operation(vmx), true); + GUEST_ASSERT_EQ(load_vmcs(vmx), true); + + prepare_vmcs(vmx, NULL, &l2_guest_stack[L2_GUEST_STACK_SIZE]); + + /* + * Enable MSR bitmaps (the bitmap itself is allocated, zeroed, and set + * in the VMCS by prepare_vmcs()), as MSR exiting mandatory on Intel. + */ + vmwrite(CPU_BASED_VM_EXEC_CONTROL, + vmreadz(CPU_BASED_VM_EXEC_CONTROL) | CPU_BASED_USE_MSR_BITMAPS); + + GUEST_ASSERT(!vmwrite(GUEST_RIP, (u64)l2_guest_code)); + GUEST_ASSERT(!vmlaunch()); +} + +static void guest_code(void *nested_test_data) +{ + guest_read_aperf_mperf(); + + if (this_cpu_has(X86_FEATURE_SVM)) + l1_svm_code(nested_test_data); + else if (this_cpu_has(X86_FEATURE_VMX)) + l1_vmx_code(nested_test_data); + else + GUEST_DONE(); + + TEST_FAIL("L2 should have signaled 'done'"); +} + +static void guest_no_aperfmperf(void) +{ + uint64_t msr_val; + uint8_t vector; + + vector = rdmsr_safe(MSR_IA32_APERF, &msr_val); + GUEST_ASSERT(vector == GP_VECTOR); + + vector = rdmsr_safe(MSR_IA32_APERF, &msr_val); + GUEST_ASSERT(vector == GP_VECTOR); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + const bool has_nested = kvm_cpu_has(X86_FEATURE_SVM) || kvm_cpu_has(X86_FEATURE_VMX); + uint64_t host_aperf_before, host_mperf_before; + vm_vaddr_t nested_test_data_gva; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int msr_fd, cpu, i; + + /* Sanity check that APERF/MPERF are unsupported by default. */ + vm = vm_create_with_one_vcpu(&vcpu, guest_no_aperfmperf); + vcpu_run(vcpu); + TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE); + kvm_vm_free(vm); + + cpu = pin_self_to_any_cpu(); + + msr_fd = open_dev_msr(cpu); + + /* + * This test requires a non-standard VM initialization, because + * KVM_ENABLE_CAP cannot be used on a VM file descriptor after + * a VCPU has been created. + */ + vm = vm_create(1); + + TEST_REQUIRE(vm_check_cap(vm, KVM_CAP_X86_DISABLE_EXITS) & + KVM_X86_DISABLE_EXITS_APERFMPERF); + + vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, + KVM_X86_DISABLE_EXITS_APERFMPERF); + + vcpu = vm_vcpu_add(vm, 0, guest_code); + + if (!has_nested) + nested_test_data_gva = NONCANONICAL; + else if (kvm_cpu_has(X86_FEATURE_SVM)) + vcpu_alloc_svm(vm, &nested_test_data_gva); + else + vcpu_alloc_vmx(vm, &nested_test_data_gva); + + vcpu_args_set(vcpu, 1, nested_test_data_gva); + + host_aperf_before = read_dev_msr(msr_fd, MSR_IA32_APERF); + host_mperf_before = read_dev_msr(msr_fd, MSR_IA32_MPERF); + + for (i = 0; i <= NUM_ITERATIONS * (1 + has_nested); i++) { + uint64_t host_aperf_after, host_mperf_after; + uint64_t guest_aperf, guest_mperf; + struct ucall uc; + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_DONE: + goto done; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_SYNC: + guest_aperf = uc.args[0]; + guest_mperf = uc.args[1]; + + host_aperf_after = read_dev_msr(msr_fd, MSR_IA32_APERF); + host_mperf_after = read_dev_msr(msr_fd, MSR_IA32_MPERF); + + TEST_ASSERT(host_aperf_before < guest_aperf, + "APERF: host_before (0x%" PRIx64 ") >= guest (0x%" PRIx64 ")", + host_aperf_before, guest_aperf); + TEST_ASSERT(guest_aperf < host_aperf_after, + "APERF: guest (0x%" PRIx64 ") >= host_after (0x%" PRIx64 ")", + guest_aperf, host_aperf_after); + TEST_ASSERT(host_mperf_before < guest_mperf, + "MPERF: host_before (0x%" PRIx64 ") >= guest (0x%" PRIx64 ")", + host_mperf_before, guest_mperf); + TEST_ASSERT(guest_mperf < host_mperf_after, + "MPERF: guest (0x%" PRIx64 ") >= host_after (0x%" PRIx64 ")", + guest_mperf, host_mperf_after); + + host_aperf_before = host_aperf_after; + host_mperf_before = host_mperf_after; + + break; + } + } + TEST_FAIL("Didn't receive UCALL_DONE\n"); +done: + kvm_vm_free(vm); + close(msr_fd); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c index 32b2794b78fe..8463a9956410 100644 --- a/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c @@ -343,6 +343,12 @@ static void guest_code_permission_bitmap(void) data = test_rdmsr(MSR_GS_BASE); GUEST_ASSERT(data == MSR_GS_BASE); + /* Access the MSRs again to ensure KVM has disabled interception.*/ + data = test_rdmsr(MSR_FS_BASE); + GUEST_ASSERT(data != MSR_FS_BASE); + data = test_rdmsr(MSR_GS_BASE); + GUEST_ASSERT(data != MSR_GS_BASE); + GUEST_DONE(); } @@ -682,6 +688,8 @@ KVM_ONE_VCPU_TEST(user_msr, msr_permission_bitmap, guest_code_permission_bitmap) "Expected ucall state to be UCALL_SYNC."); vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs); run_guest_then_process_rdmsr(vcpu, MSR_GS_BASE); + + vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_allow); run_guest_then_process_ucall_done(vcpu); } diff --git a/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c index 3fd6eceab46f..2cae86d9d5e2 100644 --- a/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c +++ b/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c @@ -110,7 +110,7 @@ int main(int argc, char *argv[]) struct kvm_vm *vm; TEST_REQUIRE(host_cpu_is_intel); - TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); + TEST_REQUIRE(!kvm_is_unrestricted_guest_enabled()); vm = vm_create_with_one_vcpu(&vcpu, guest_code); get_set_sigalrm_vcpu(vcpu); diff --git a/tools/testing/selftests/kvm/x86/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c index 287829f850f7..23909b501ac2 100644 --- a/tools/testing/selftests/kvm/x86/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c @@ -547,15 +547,9 @@ int main(int argc, char *argv[]) int irq_fd[2] = { -1, -1 }; if (do_eventfd_tests) { - irq_fd[0] = eventfd(0, 0); - irq_fd[1] = eventfd(0, 0); + irq_fd[0] = kvm_new_eventfd(); + irq_fd[1] = kvm_new_eventfd(); - /* Unexpected, but not a KVM failure */ - if (irq_fd[0] == -1 || irq_fd[1] == -1) - do_evtchn_tests = do_eventfd_tests = false; - } - - if (do_eventfd_tests) { irq_routes.info.nr = 2; irq_routes.entries[0].gsi = 32; @@ -572,15 +566,8 @@ int main(int argc, char *argv[]) vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes.info); - struct kvm_irqfd ifd = { }; - - ifd.fd = irq_fd[0]; - ifd.gsi = 32; - vm_ioctl(vm, KVM_IRQFD, &ifd); - - ifd.fd = irq_fd[1]; - ifd.gsi = 33; - vm_ioctl(vm, KVM_IRQFD, &ifd); + kvm_assign_irqfd(vm, 32, irq_fd[0]); + kvm_assign_irqfd(vm, 33, irq_fd[1]); struct sigaction sa = { }; sa.sa_handler = handle_alrm; |