diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2024-05-02 14:28:10 +1000 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2024-05-02 14:28:10 +1000 |
commit | f7558582fe0a93e68096f59e3005c7e81992272c (patch) | |
tree | 8661232eae557fa41532b38c4b739b673f08a6d0 | |
parent | 171334a1eb7e24a08ab1ca1aff1132f900094099 (diff) | |
parent | 2489e6c9ebb57d6d0e98936479b5f586201379c7 (diff) | |
download | linux-next-f7558582fe0a93e68096f59e3005c7e81992272c.tar.gz |
Merge branch 'next' of https://github.com/kvm-x86/linux.git
Notice: this object is not reachable from any branch.
# Conflicts:
# tools/testing/selftests/kvm/aarch64/psci_test.c
Notice: this object is not reachable from any branch.
99 files changed, 1793 insertions, 648 deletions
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3cb7647ea2f20d..8307714cb2f6f9 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -994,9 +994,6 @@ struct kvm_vcpu_arch { u64 msr_kvm_poll_control; - /* set at EPT violation at this point */ - unsigned long exit_qualification; - /* pv related host specific info */ struct { bool pv_unhalted; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 1851b3870a9c05..f2f2be5d11415d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1232,9 +1232,22 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = 0; break; case 0x80000008: { - unsigned g_phys_as = (entry->eax >> 16) & 0xff; - unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); - unsigned phys_as = entry->eax & 0xff; + /* + * GuestPhysAddrSize (EAX[23:16]) is intended for software + * use. + * + * KVM's ABI is to report the effective MAXPHYADDR for the + * guest in PhysAddrSize (phys_as), and the maximum + * *addressable* GPA in GuestPhysAddrSize (g_phys_as). + * + * GuestPhysAddrSize is valid if and only if TDP is enabled, + * in which case the max GPA that can be addressed by KVM may + * be less than the max GPA that can be legally generated by + * the guest, e.g. if MAXPHYADDR>48 but the CPU doesn't + * support 5-level TDP. + */ + unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U); + unsigned int phys_as, g_phys_as; /* * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as @@ -1242,16 +1255,24 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * reductions in MAXPHYADDR for memory encryption affect shadow * paging, too. * - * If TDP is enabled but an explicit guest MAXPHYADDR is not - * provided, use the raw bare metal MAXPHYADDR as reductions to - * the HPAs do not affect GPAs. + * If TDP is enabled, use the raw bare metal MAXPHYADDR as + * reductions to the HPAs do not affect GPAs. The max + * addressable GPA is the same as the max effective GPA, except + * that it's capped at 48 bits if 5-level TDP isn't supported + * (hardware processes bits 51:48 only when walking the fifth + * level page table). */ - if (!tdp_enabled) - g_phys_as = boot_cpu_data.x86_phys_bits; - else if (!g_phys_as) + if (!tdp_enabled) { + phys_as = boot_cpu_data.x86_phys_bits; + g_phys_as = 0; + } else { + phys_as = entry->eax & 0xff; g_phys_as = phys_as; + if (kvm_mmu_get_max_tdp_level() < 5) + g_phys_as = min(g_phys_as, 48); + } - entry->eax = g_phys_as | (virt_as << 8); + entry->eax = phys_as | (virt_as << 8) | (g_phys_as << 16); entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 5382646162a387..29ea4313e1bb1e 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -26,6 +26,7 @@ struct x86_exception { bool nested_page_fault; u64 address; /* cr2 or nested page fault gpa */ u8 async_page_fault; + unsigned long exit_qualification; }; /* diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 60f21bb4c27b19..b410a227c6018d 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -100,6 +100,8 @@ static inline u8 kvm_get_shadow_phys_bits(void) return boot_cpu_data.x86_phys_bits; } +u8 kvm_mmu_get_max_tdp_level(void); + void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask); void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 69a872d151a9be..553d51cababa75 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5269,6 +5269,11 @@ static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) return max_tdp_level; } +u8 kvm_mmu_get_max_tdp_level(void) +{ + return tdp_root_level ? tdp_root_level : max_tdp_level; +} + static union kvm_mmu_page_role kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, union kvm_cpu_role cpu_role) diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index f6448284c18e3e..561c331fd6ecc7 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -41,7 +41,7 @@ bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) { - kvfree(slot->arch.gfn_write_track); + vfree(slot->arch.gfn_write_track); slot->arch.gfn_write_track = NULL; } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 4d4e98fe4f3548..7a87097cb45b52 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -497,21 +497,21 @@ error: * The other bits are set to 0. */ if (!(errcode & PFERR_RSVD_MASK)) { - vcpu->arch.exit_qualification &= (EPT_VIOLATION_GVA_IS_VALID | - EPT_VIOLATION_GVA_TRANSLATED); + walker->fault.exit_qualification = 0; + if (write_fault) - vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_WRITE; + walker->fault.exit_qualification |= EPT_VIOLATION_ACC_WRITE; if (user_fault) - vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_READ; + walker->fault.exit_qualification |= EPT_VIOLATION_ACC_READ; if (fetch_fault) - vcpu->arch.exit_qualification |= EPT_VIOLATION_ACC_INSTR; + walker->fault.exit_qualification |= EPT_VIOLATION_ACC_INSTR; /* * Note, pte_access holds the raw RWX bits from the EPTE, not * ACC_*_MASK flags! */ - vcpu->arch.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) << - EPT_VIOLATION_RWX_SHIFT; + walker->fault.exit_qualification |= (pte_access & VMX_EPT_RWX_MASK) << + EPT_VIOLATION_RWX_SHIFT; } #endif walker->fault.address = addr; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index af21703c848c16..c3dc18fac4f7cc 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -530,6 +530,31 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, kvm_set_pfn_accessed(spte_to_pfn(old_spte)); } +static inline int __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, u64 new_spte) +{ + u64 *sptep = rcu_dereference(iter->sptep); + + /* + * The caller is responsible for ensuring the old SPTE is not a REMOVED + * SPTE. KVM should never attempt to zap or manipulate a REMOVED SPTE, + * and pre-checking before inserting a new SPTE is advantageous as it + * avoids unnecessary work. + */ + WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte)); + + /* + * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and + * does not hold the mmu_lock. On failure, i.e. if a different logical + * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with + * the current value, so the caller operates on fresh data, e.g. if it + * retries tdp_mmu_set_spte_atomic() + */ + if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) + return -EBUSY; + + return 0; +} + /* * tdp_mmu_set_spte_atomic - Set a TDP MMU SPTE atomically * and handle the associated bookkeeping. Do not mark the page dirty @@ -551,27 +576,13 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte) { - u64 *sptep = rcu_dereference(iter->sptep); - - /* - * The caller is responsible for ensuring the old SPTE is not a REMOVED - * SPTE. KVM should never attempt to zap or manipulate a REMOVED SPTE, - * and pre-checking before inserting a new SPTE is advantageous as it - * avoids unnecessary work. - */ - WARN_ON_ONCE(iter->yielded || is_removed_spte(iter->old_spte)); + int ret; lockdep_assert_held_read(&kvm->mmu_lock); - /* - * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and - * does not hold the mmu_lock. On failure, i.e. if a different logical - * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with - * the current value, so the caller operates on fresh data, e.g. if it - * retries tdp_mmu_set_spte_atomic() - */ - if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) - return -EBUSY; + ret = __tdp_mmu_set_spte_atomic(iter, new_spte); + if (ret) + return ret; handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, new_spte, iter->level, true); @@ -584,13 +595,17 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, { int ret; + lockdep_assert_held_read(&kvm->mmu_lock); + /* - * Freeze the SPTE by setting it to a special, - * non-present value. This will stop other threads from - * immediately installing a present entry in its place - * before the TLBs are flushed. + * Freeze the SPTE by setting it to a special, non-present value. This + * will stop other threads from immediately installing a present entry + * in its place before the TLBs are flushed. + * + * Delay processing of the zapped SPTE until after TLBs are flushed and + * the REMOVED_SPTE is replaced (see below). */ - ret = tdp_mmu_set_spte_atomic(kvm, iter, REMOVED_SPTE); + ret = __tdp_mmu_set_spte_atomic(iter, REMOVED_SPTE); if (ret) return ret; @@ -599,12 +614,20 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, /* * No other thread can overwrite the removed SPTE as they must either * wait on the MMU lock or use tdp_mmu_set_spte_atomic() which will not - * overwrite the special removed SPTE value. No bookkeeping is needed - * here since the SPTE is going from non-present to non-present. Use - * the raw write helper to avoid an unnecessary check on volatile bits. + * overwrite the special removed SPTE value. Use the raw write helper to + * avoid an unnecessary check on volatile bits. */ __kvm_tdp_mmu_write_spte(iter->sptep, 0); + /* + * Process the zapped SPTE after flushing TLBs, and after replacing + * REMOVED_SPTE with 0. This minimizes the amount of time vCPUs are + * blocked by the REMOVED_SPTE and reduces contention on the child + * SPTEs. + */ + handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, + 0, iter->level, true); + return 0; } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d05ddf7514915c..d5b832126e3458 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -409,18 +409,40 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, { struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); + unsigned long exit_qualification; u32 vm_exit_reason; - unsigned long exit_qualification = vcpu->arch.exit_qualification; if (vmx->nested.pml_full) { vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; - exit_qualification &= INTR_INFO_UNBLOCK_NMI; + + /* + * It should be impossible to trigger a nested PML Full VM-Exit + * for anything other than an EPT Violation from L2. KVM *can* + * trigger nEPT page fault injection in response to an EPT + * Misconfig, e.g. if the MMIO SPTE was stale and L1's EPT + * tables also changed, but KVM should not treat EPT Misconfig + * VM-Exits as writes. + */ + WARN_ON_ONCE(vmx->exit_reason.basic != EXIT_REASON_EPT_VIOLATION); + + /* + * PML Full and EPT Violation VM-Exits both use bit 12 to report + * "NMI unblocking due to IRET", i.e. the bit can be propagated + * as-is from the original EXIT_QUALIFICATION. + */ + exit_qualification = vmx_get_exit_qual(vcpu) & INTR_INFO_UNBLOCK_NMI; } else { - if (fault->error_code & PFERR_RSVD_MASK) + if (fault->error_code & PFERR_RSVD_MASK) { vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; - else + exit_qualification = 0; + } else { + exit_qualification = fault->exit_qualification; + exit_qualification |= vmx_get_exit_qual(vcpu) & + (EPT_VIOLATION_GVA_IS_VALID | + EPT_VIOLATION_GVA_TRANSLATED); vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + } /* * Although the caller (kvm_inject_emulated_page_fault) would diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f7464fe029271d..3f77a065a5c370 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5766,8 +5766,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) != 0 ? PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK; - vcpu->arch.exit_qualification = exit_qualification; - /* * Check that the GPA doesn't exceed physical memory limits, as that is * a guest page fault. We have to emulate the instruction here, because diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2369956638deea..ae10da510f76b8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12798,7 +12798,7 @@ static void memslot_rmap_free(struct kvm_memory_slot *slot) int i; for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.rmap[i]); + vfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; } } @@ -12810,7 +12810,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) memslot_rmap_free(slot); for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.lpage_info[i - 1]); + vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } @@ -12902,7 +12902,7 @@ out_free: memslot_rmap_free(slot); for (i = 1; i < KVM_NR_PAGE_SIZES; ++i) { - kvfree(slot->arch.lpage_info[i - 1]); + vfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } return -ENOMEM; diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index a832e11944bf63..ac280dcba996df 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -231,8 +231,8 @@ LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include endif CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \ - -fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \ - -fno-builtin-strnlen \ + -D_GNU_SOURCE -fno-builtin-memcmp -fno-builtin-memcpy \ + -fno-builtin-memset -fno-builtin-strnlen \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ -I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \ diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 89be559cdb7ecf..eeba1cc87ff82b 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -5,13 +5,12 @@ * * Copyright (c) 2021, Google LLC. */ -#define _GNU_SOURCE - #include "arch_timer.h" #include "delay.h" #include "gic.h" #include "processor.h" #include "timer_test.h" +#include "ucall_common.h" #include "vgic.h" enum guest_stage { diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index 5972905275cfac..d29b08198b42e0 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -7,7 +7,6 @@ * hugetlbfs with a hole). It checks that the expected handling method is * called (e.g., uffd faults with the right address and write/read flag). */ -#define _GNU_SOURCE #include <linux/bitmap.h> #include <fcntl.h> #include <test_util.h> @@ -375,14 +374,14 @@ static void setup_uffd(struct kvm_vm *vm, struct test_params *p, *pt_uffd = uffd_setup_demand_paging(uffd_mode, 0, pt_args.hva, pt_args.paging_size, - test->uffd_pt_handler); + 1, test->uffd_pt_handler); *data_uffd = NULL; if (test->uffd_data_handler) *data_uffd = uffd_setup_demand_paging(uffd_mode, 0, data_args.hva, data_args.paging_size, - test->uffd_data_handler); + 1, test->uffd_data_handler); } static void free_uffd(struct test_desc *test, struct uffd_desc *pt_uffd, diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c index 9fa3578d47d530..fe77628d2d2619 100644 --- a/tools/testing/selftests/kvm/aarch64/psci_test.c +++ b/tools/testing/selftests/kvm/aarch64/psci_test.c @@ -10,9 +10,6 @@ * - A test for KVM's handling of PSCI SYSTEM_SUSPEND and the associated * KVM_SYSTEM_EVENT_SUSPEND UAPI. */ - -#define _GNU_SOURCE - #include <linux/kernel.h> #include <linux/psci.h> #include <asm/cputype.h> diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c index ca917c71ff602d..b3b5fb0ff0a9ae 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_init.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c @@ -4,7 +4,6 @@ * * Copyright (C) 2020, Red Hat, Inc. */ -#define _GNU_SOURCE #include <linux/kernel.h> #include <sys/syscall.h> #include <asm/kvm.h> diff --git a/tools/testing/selftests/kvm/arch_timer.c b/tools/testing/selftests/kvm/arch_timer.c index ae1f1a6d831234..acb2cb59633238 100644 --- a/tools/testing/selftests/kvm/arch_timer.c +++ b/tools/testing/selftests/kvm/arch_timer.c @@ -19,9 +19,6 @@ * * Copyright (c) 2021, Google LLC. */ - -#define _GNU_SOURCE - #include <stdlib.h> #include <pthread.h> #include <linux/sizes.h> @@ -29,6 +26,7 @@ #include <sys/sysinfo.h> #include "timer_test.h" +#include "ucall_common.h" struct test_args test_args = { .nr_vcpus = NR_VCPUS_DEF, diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index bf3609f718544f..0202b78f8680af 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -6,14 +6,10 @@ * Copyright (C) 2018, Red Hat, Inc. * Copyright (C) 2019, Google, Inc. */ - -#define _GNU_SOURCE /* for pipe2 */ - #include <inttypes.h> #include <stdio.h> #include <stdlib.h> #include <time.h> -#include <poll.h> #include <pthread.h> #include <linux/userfaultfd.h> #include <sys/syscall.h> @@ -22,6 +18,7 @@ #include "test_util.h" #include "memstress.h" #include "guest_modes.h" +#include "ucall_common.h" #include "userfaultfd_util.h" #ifdef __NR_userfaultfd @@ -77,8 +74,20 @@ static int handle_uffd_page_request(int uffd_mode, int uffd, copy.mode = 0; r = ioctl(uffd, UFFDIO_COPY, ©); - if (r == -1) { - pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d with errno: %d\n", + /* + * With multiple vCPU threads fault on a single page and there are + * multiple readers for the UFFD, at least one of the UFFDIO_COPYs + * will fail with EEXIST: handle that case without signaling an + * error. + * + * Note that this also suppress any EEXISTs occurring from, + * e.g., the first UFFDIO_COPY/CONTINUEs on a page. That never + * happens here, but a realistic VMM might potentially maintain + * some external state to correctly surface EEXISTs to userspace + * (or prevent duplicate COPY/CONTINUEs in the first place). + */ + if (r == -1 && errno != EEXIST) { + pr_info("Failed UFFDIO_COPY in 0x%lx from thread %d, errno = %d\n", addr, tid, errno); return r; } @@ -89,8 +98,20 @@ static int handle_uffd_page_request(int uffd_mode, int uffd, cont.range.len = demand_paging_size; r = ioctl(uffd, UFFDIO_CONTINUE, &cont); - if (r == -1) { - pr_info("Failed UFFDIO_CONTINUE in 0x%lx from thread %d with errno: %d\n", + /* + * With multiple vCPU threads fault on a single page and there are + * multiple readers for the UFFD, at least one of the UFFDIO_COPYs + * will fail with EEXIST: handle that case without signaling an + * error. + * + * Note that this also suppress any EEXISTs occurring from, + * e.g., the first UFFDIO_COPY/CONTINUEs on a page. That never + * happens here, but a realistic VMM might potentially maintain + * some external state to correctly surface EEXISTs to userspace + * (or prevent duplicate COPY/CONTINUEs in the first place). + */ + if (r == -1 && errno != EEXIST) { + pr_info("Failed UFFDIO_CONTINUE in 0x%lx, thread %d, errno = %d\n", addr, tid, errno); return r; } @@ -110,7 +131,9 @@ static int handle_uffd_page_request(int uffd_mode, int uffd, struct test_params { int uffd_mode; + bool single_uffd; useconds_t uffd_delay; + int readers_per_uffd; enum vm_mem_backing_src_type src_type; bool partition_vcpu_memory_access; }; @@ -131,10 +154,12 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct memstress_vcpu_args *vcpu_args; struct test_params *p = arg; struct uffd_desc **uffd_descs = NULL; + uint64_t uffd_region_size; struct timespec start; struct timespec ts_diff; + double vcpu_paging_rate; struct kvm_vm *vm; - int i; + int i, num_uffds = 0; vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, p->src_type, p->partition_vcpu_memory_access); @@ -147,7 +172,8 @@ static void run_test(enum vm_guest_mode mode, void *arg) memset(guest_data_prototype, 0xAB, demand_paging_size); if (p->uffd_mode == UFFDIO_REGISTER_MODE_MINOR) { - for (i = 0; i < nr_vcpus; i++) { + num_uffds = p->single_uffd ? 1 : nr_vcpus; + for (i = 0; i < num_uffds; i++) { vcpu_args = &memstress_args.vcpu_args[i]; prefault_mem(addr_gpa2alias(vm, vcpu_args->gpa), vcpu_args->pages * memstress_args.guest_page_size); @@ -155,9 +181,13 @@ static void run_test(enum vm_guest_mode mode, void *arg) } if (p->uffd_mode) { - uffd_descs = malloc(nr_vcpus * sizeof(struct uffd_desc *)); + num_uffds = p->single_uffd ? 1 : nr_vcpus; + uffd_region_size = nr_vcpus * guest_percpu_mem_size / num_uffds; + + uffd_descs = malloc(num_uffds * sizeof(struct uffd_desc *)); TEST_ASSERT(uffd_descs, "Memory allocation failed"); - for (i = 0; i < nr_vcpus; i++) { + for (i = 0; i < num_uffds; i++) { + struct memstress_vcpu_args *vcpu_args; void *vcpu_hva; vcpu_args = &memstress_args.vcpu_args[i]; @@ -170,7 +200,8 @@ static void run_test(enum vm_guest_mode mode, void *arg) */ uffd_descs[i] = uffd_setup_demand_paging( p->uffd_mode, p->uffd_delay, vcpu_hva, - vcpu_args->pages * memstress_args.guest_page_size, + uffd_region_size, + p->readers_per_uffd, &handle_uffd_page_request); } } @@ -187,15 +218,19 @@ static void run_test(enum vm_guest_mode mode, void *arg) if (p->uffd_mode) { /* Tell the user fault fd handler threads to quit */ - for (i = 0; i < nr_vcpus; i++) + for (i = 0; i < num_uffds; i++) uffd_stop_demand_paging(uffd_descs[i]); } - pr_info("Total guest execution time: %ld.%.9lds\n", + pr_info("Total guest execution time:\t%ld.%.9lds\n", ts_diff.tv_sec, ts_diff.tv_nsec); - pr_info("Overall demand paging rate: %f pgs/sec\n", - memstress_args.vcpu_args[0].pages * nr_vcpus / - ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / NSEC_PER_SEC)); + + vcpu_paging_rate = memstress_args.vcpu_args[0].pages / + ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / NSEC_PER_SEC); + pr_info("Per-vcpu demand paging rate:\t%f pgs/sec/vcpu\n", + vcpu_paging_rate); + pr_info("Overall demand paging rate:\t%f pgs/sec\n", + vcpu_paging_rate * nr_vcpus); memstress_destroy_vm(vm); @@ -207,15 +242,20 @@ static void run_test(enum vm_guest_mode mode, void *arg) static void help(char *name) { puts(""); - printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-d uffd_delay_usec]\n" - " [-b memory] [-s type] [-v vcpus] [-c cpu_list] [-o]\n", name); + printf("usage: %s [-h] [-m vm_mode] [-u uffd_mode] [-a]\n" + " [-d uffd_delay_usec] [-r readers_per_uffd] [-b memory]\n" + " [-s type] [-v vcpus] [-c cpu_list] [-o]\n", name); guest_modes_help(); printf(" -u: use userfaultfd to handle vCPU page faults. Mode is a\n" " UFFD registration mode: 'MISSING' or 'MINOR'.\n"); kvm_print_vcpu_pinning_help(); + printf(" -a: Use a single userfaultfd for all of guest memory, instead of\n" + " creating one for each region paged by a unique vCPU\n" + " Set implicitly with -o, and no effect without -u.\n"); printf(" -d: add a delay in usec to the User Fault\n" " FD handler to simulate demand paging\n" " overheads. Ignored without -u.\n"); + printf(" -r: Set the number of reader threads per uffd.\n"); printf(" -b: specify the size of the memory region which should be\n" " demand paged by each vCPU. e.g. 10M or 3G.\n" " Default: 1G\n"); @@ -234,12 +274,14 @@ int main(int argc, char *argv[]) struct test_params p = { .src_type = DEFAULT_VM_MEM_SRC, .partition_vcpu_memory_access = true, + .readers_per_uffd = 1, + .single_uffd = false, }; int opt; guest_modes_append_default(); - while ((opt = getopt(argc, argv, "hm:u:d:b:s:v:c:o")) != -1) { + while ((opt = getopt(argc, argv, "ahom:u:d:b:s:v:c:r:")) != -1) { switch (opt) { case 'm': guest_modes_cmdline(optarg); @@ -251,6 +293,9 @@ int main(int argc, char *argv[]) p.uffd_mode = UFFDIO_REGISTER_MODE_MINOR; TEST_ASSERT(p.uffd_mode, "UFFD mode must be 'MISSING' or 'MINOR'."); break; + case 'a': + p.single_uffd = true; + break; case 'd': p.uffd_delay = strtoul(optarg, NULL, 0); TEST_ASSERT(p.uffd_delay >= 0, "A negative UFFD delay is not supported."); @@ -271,6 +316,13 @@ int main(int argc, char *argv[]) break; case 'o': p.partition_vcpu_memory_access = false; + p.single_uffd = true; + break; + case 'r': + p.readers_per_uffd = atoi(optarg); + TEST_ASSERT(p.readers_per_uffd >= 1, + "Invalid number of readers per uffd %d: must be >=1", + p.readers_per_uffd); break; case 'h': default: diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 61535c4f340505..9f24303acb8cb2 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -18,6 +18,7 @@ #include "test_util.h" #include "memstress.h" #include "guest_modes.h" +#include "ucall_common.h" #ifdef __aarch64__ #include "aarch64/vgic.h" @@ -129,7 +130,6 @@ struct test_params { enum vm_mem_backing_src_type backing_src; int slots; uint32_t write_percent; - uint32_t random_seed; bool random_access; }; @@ -153,8 +153,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) p->slots, p->backing_src, p->partition_vcpu_memory_access); - pr_info("Random seed: %u\n", p->random_seed); - memstress_set_random_seed(vm, p->random_seed); memstress_set_write_percent(vm, p->write_percent); guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm->page_shift; @@ -343,11 +341,13 @@ int main(int argc, char *argv[]) .partition_vcpu_memory_access = true, .backing_src = DEFAULT_VM_MEM_SRC, .slots = 1, - .random_seed = 1, .write_percent = 100, }; int opt; + /* Override the seed to be deterministic by default. */ + guest_random_seed = 1; + dirty_log_manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | @@ -392,7 +392,7 @@ int main(int argc, char *argv[]) p.phys_offset = strtoull(optarg, NULL, 0); break; case 'r': - p.random_seed = atoi_positive("Random seed", optarg); + guest_random_seed = atoi_positive("Random seed", optarg); break; case 's': p.backing_src = parse_backing_src_type(optarg); diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index eaad5b20854ccf..aacf80f574391a 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -4,9 +4,6 @@ * * Copyright (C) 2018, Red Hat, Inc. */ - -#define _GNU_SOURCE /* for program_invocation_name */ - #include <stdio.h> #include <stdlib.h> #include <pthread.h> @@ -23,6 +20,7 @@ #include "test_util.h" #include "guest_modes.h" #include "processor.h" +#include "ucall_common.h" #define DIRTY_MEM_BITS 30 /* 1G */ #define PAGE_SHIFT_4K 12 @@ -76,7 +74,6 @@ static uint64_t host_page_size; static uint64_t guest_page_size; static uint64_t guest_num_pages; -static uint64_t random_array[TEST_PAGES_PER_LOOP]; static uint64_t iteration; /* @@ -109,19 +106,19 @@ static void guest_code(void) */ for (i = 0; i < guest_num_pages; i++) { addr = guest_test_virt_mem + i * guest_page_size; - *(uint64_t *)addr = READ_ONCE(iteration); + vcpu_arch_put_guest(*(uint64_t *)addr, READ_ONCE(iteration)); } while (true) { for (i = 0; i < TEST_PAGES_PER_LOOP; i++) { addr = guest_test_virt_mem; - addr += (READ_ONCE(random_array[i]) % guest_num_pages) + addr += (guest_random_u64(&guest_rng) % guest_num_pages) * guest_page_size; addr = align_down(addr, host_page_size); - *(uint64_t *)addr = READ_ONCE(iteration); + + vcpu_arch_put_guest(*(uint64_t *)addr, READ_ONCE(iteration)); } - /* Tell the host that we need more random numbers */ GUEST_SYNC(1); } } @@ -508,20 +505,10 @@ static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err) mode->after_vcpu_run(vcpu, ret, err); } -static void generate_random_array(uint64_t *guest_array, uint64_t size) -{ - uint64_t i; - - for (i = 0; i < size; i++) - guest_array[i] = random(); -} - static void *vcpu_worker(void *data) { int ret; struct kvm_vcpu *vcpu = data; - struct kvm_vm *vm = vcpu->vm; - uint64_t *guest_array; uint64_t pages_count = 0; struct kvm_signal_mask *sigmask = alloca(offsetof(struct kvm_signal_mask, sigset) + sizeof(sigset_t)); @@ -540,11 +527,8 @@ static void *vcpu_worker(void *data) sigemptyset(sigset); sigaddset(sigset, SIG_IPI); - guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array); - while (!READ_ONCE(host_quit)) { /* Clear any existing kick signals */ - generate_random_array(guest_array, TEST_PAGES_PER_LOOP); pages_count += TEST_PAGES_PER_LOOP; /* Let the guest dirty the random pages */ ret = __vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c index 92eae206baa62e..ba0c8e99603584 100644 --- a/tools/testing/selftests/kvm/guest_memfd_test.c +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -4,8 +4,6 @@ * * Author: Chao Peng <chao.p.peng@linux.intel.com> */ - -#define _GNU_SOURCE #include <stdlib.h> #include <string.h> #include <unistd.h> @@ -19,8 +17,8 @@ #include <sys/types.h> #include <sys/stat.h> +#include "kvm_util.h" #include "test_util.h" -#include "kvm_util_base.h" static void test_file_read_write(int fd) { diff --git a/tools/testing/selftests/kvm/guest_print_test.c b/tools/testing/selftests/kvm/guest_print_test.c index 3502caa3590c64..8092c2d0f5d688 100644 --- a/tools/testing/selftests/kvm/guest_print_test.c +++ b/tools/testing/selftests/kvm/guest_print_test.c @@ -13,6 +13,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "ucall_common.h" struct guest_vals { uint64_t a; diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index decc521fc7603b..bce73bcb973c8e 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -4,9 +4,6 @@ * kvm_arch_hardware_disable is called and it attempts to unregister the user * return notifiers. */ - -#define _GNU_SOURCE - #include <fcntl.h> #include <pthread.h> #include <semaphore.h> diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index 331ff6b2dbe2e4..9b20a355d81ade 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -8,6 +8,8 @@ #define SELFTEST_KVM_PROCESSOR_H #include "kvm_util.h" +#include "ucall_common.h" + #include <linux/stringify.h> #include <linux/types.h> #include <asm/sysreg.h> diff --git a/tools/testing/selftests/kvm/include/aarch64/ucall.h b/tools/testing/selftests/kvm/include/aarch64/ucall.h index 4b68f37efd368a..4ec801f37f00e7 100644 --- a/tools/testing/selftests/kvm/include/aarch64/ucall.h +++ b/tools/testing/selftests/kvm/include/aarch64/ucall.h @@ -2,7 +2,7 @@ #ifndef SELFTEST_KVM_UCALL_H #define SELFTEST_KVM_UCALL_H -#include "kvm_util_base.h" +#include "kvm_util.h" #define UCALL_EXIT_REASON KVM_EXIT_MMIO diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index c9286811a4cb88..63c2aaae51f30e 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -1,13 +1,1116 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/kvm_util.h - * * Copyright (C) 2018, Google LLC. */ #ifndef SELFTEST_KVM_UTIL_H #define SELFTEST_KVM_UTIL_H -#include "kvm_util_base.h" -#include "ucall_common.h" +#include "test_util.h" + +#include <linux/compiler.h> +#include "linux/hashtable.h" +#include "linux/list.h" +#include <linux/kernel.h> +#include <linux/kvm.h> +#include "linux/rbtree.h" +#include <linux/types.h> + +#include <asm/atomic.h> +#include <asm/kvm.h> + +#include <sys/ioctl.h> + +#include "kvm_util_arch.h" +#include "kvm_util_types.h" +#include "sparsebit.h" + +#define KVM_DEV_PATH "/dev/kvm" +#define KVM_MAX_VCPUS 512 + +#define NSEC_PER_SEC 1000000000L + +struct userspace_mem_region { + struct kvm_userspace_memory_region2 region; + struct sparsebit *unused_phy_pages; + struct sparsebit *protected_phy_pages; + int fd; + off_t offset; + enum vm_mem_backing_src_type backing_src_type; + void *host_mem; + void *host_alias; + void *mmap_start; + void *mmap_alias; + size_t mmap_size; + struct rb_node gpa_node; + struct rb_node hva_node; + struct hlist_node slot_node; +}; + +struct kvm_vcpu { + struct list_head list; + uint32_t id; + int fd; + struct kvm_vm *vm; + struct kvm_run *run; +#ifdef __x86_64__ + struct kvm_cpuid2 *cpuid; +#endif + struct kvm_dirty_gfn *dirty_gfns; + uint32_t fetch_index; + uint32_t dirty_gfns_count; +}; + +struct userspace_mem_regions { + struct rb_root gpa_tree; + struct rb_root hva_tree; + DECLARE_HASHTABLE(slot_hash, 9); +}; + +enum kvm_mem_region_type { + MEM_REGION_CODE, + MEM_REGION_DATA, + MEM_REGION_PT, + MEM_REGION_TEST_DATA, + NR_MEM_REGIONS, +}; + +struct kvm_vm { + int mode; + unsigned long type; + int kvm_fd; + int fd; + unsigned int pgtable_levels; + unsigned int page_size; + unsigned int page_shift; + unsigned int pa_bits; + unsigned int va_bits; + uint64_t max_gfn; + struct list_head vcpus; + struct userspace_mem_regions regions; + struct sparsebit *vpages_valid; + struct sparsebit *vpages_mapped; + bool has_irqchip; + bool pgd_created; + vm_paddr_t ucall_mmio_addr; + vm_paddr_t pgd; + vm_vaddr_t handlers; + uint32_t dirty_ring_size; + uint64_t gpa_tag_mask; + + struct kvm_vm_arch arch; + + /* Cache of information for binary stats interface */ + int stats_fd; + struct kvm_stats_header stats_header; + struct kvm_stats_desc *stats_desc; + + /* + * KVM region slots. These are the default memslots used by page + * allocators, e.g., lib/elf uses the memslots[MEM_REGION_CODE] + * memslot. + */ + uint32_t memslots[NR_MEM_REGIONS]; +}; + +struct vcpu_reg_sublist { + const char *name; + long capability; + int feature; + int feature_type; + bool finalize; + __u64 *regs; + __u64 regs_n; + __u64 *rejects_set; + __u64 rejects_set_n; + __u64 *skips_set; + __u64 skips_set_n; +}; + +struct vcpu_reg_list { + char *name; + struct vcpu_reg_sublist sublists[]; +}; + +#define for_each_sublist(c, s) \ + for ((s) = &(c)->sublists[0]; (s)->regs; ++(s)) + +#define kvm_for_each_vcpu(vm, i, vcpu) \ + for ((i) = 0; (i) <= (vm)->last_vcpu_id; (i)++) \ + if (!((vcpu) = vm->vcpus[i])) \ + continue; \ + else + +struct userspace_mem_region * +memslot2region(struct kvm_vm *vm, uint32_t memslot); + +static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm, + enum kvm_mem_region_type type) +{ + assert(type < NR_MEM_REGIONS); + return memslot2region(vm, vm->memslots[type]); +} + +/* Minimum allocated guest virtual and physical addresses */ +#define KVM_UTIL_MIN_VADDR 0x2000 +#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 + +#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000 +#define DEFAULT_STACK_PGS 5 + +enum vm_guest_mode { + VM_MODE_P52V48_4K, + VM_MODE_P52V48_16K, + VM_MODE_P52V48_64K, + VM_MODE_P48V48_4K, + VM_MODE_P48V48_16K, + VM_MODE_P48V48_64K, + VM_MODE_P40V48_4K, + VM_MODE_P40V48_16K, + VM_MODE_P40V48_64K, + VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */ + VM_MODE_P47V64_4K, + VM_MODE_P44V64_4K, + VM_MODE_P36V48_4K, + VM_MODE_P36V48_16K, + VM_MODE_P36V48_64K, + VM_MODE_P36V47_16K, + NUM_VM_MODES, +}; + +struct vm_shape { + uint32_t type; + uint8_t mode; + uint8_t pad0; + uint16_t pad1; +}; + +kvm_static_assert(sizeof(struct vm_shape) == sizeof(uint64_t)); + +#define VM_TYPE_DEFAULT 0 + +#define VM_SHAPE(__mode) \ +({ \ + struct vm_shape shape = { \ + .mode = (__mode), \ + .type = VM_TYPE_DEFAULT \ + }; \ + \ + shape; \ +}) + +#if defined(__aarch64__) + +extern enum vm_guest_mode vm_mode_default; + +#define VM_MODE_DEFAULT vm_mode_default +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__x86_64__) + +#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#elif defined(__s390x__) + +#define VM_MODE_DEFAULT VM_MODE_P44V64_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 16) + +#elif defined(__riscv) + +#if __riscv_xlen == 32 +#error "RISC-V 32-bit kvm selftests not supported" +#endif + +#define VM_MODE_DEFAULT VM_MODE_P40V48_4K +#define MIN_PAGE_SHIFT 12U +#define ptes_per_page(page_size) ((page_size) / 8) + +#endif + +#define VM_SHAPE_DEFAULT VM_SHAPE(VM_MODE_DEFAULT) + +#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) +#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) + +struct vm_guest_mode_params { + unsigned int pa_bits; + unsigned int va_bits; + unsigned int page_size; + unsigned int page_shift; +}; +extern const struct vm_guest_mode_params vm_guest_mode_params[]; + +int open_path_or_exit(const char *path, int flags); +int open_kvm_dev_path_or_exit(void); + +bool get_kvm_param_bool(const char *param); +bool get_kvm_intel_param_bool(const char *param); +bool get_kvm_amd_param_bool(const char *param); + +int get_kvm_param_integer(const char *param); +int get_kvm_intel_param_integer(const char *param); +int get_kvm_amd_param_integer(const char *param); + +unsigned int kvm_check_cap(long cap); + +static inline bool kvm_has_cap(long cap) +{ + return kvm_check_cap(cap); +} + +#define __KVM_SYSCALL_ERROR(_name, _ret) \ + "%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno) + +/* + * Use the "inner", double-underscore macro when reporting errors from within + * other macros so that the name of ioctl() and not its literal numeric value + * is printed on error. The "outer" macro is strongly preferred when reporting + * errors "directly", i.e. without an additional layer of macros, as it reduces + * the probability of passing in the wrong string. + */ +#define __KVM_IOCTL_ERROR(_name, _ret) __KVM_SYSCALL_ERROR(_name, _ret) +#define KVM_IOCTL_ERROR(_ioctl, _ret) __KVM_IOCTL_ERROR(#_ioctl, _ret) + +#define kvm_do_ioctl(fd, cmd, arg) \ +({ \ + kvm_static_assert(!_IOC_SIZE(cmd) || sizeof(*arg) == _IOC_SIZE(cmd)); \ + ioctl(fd, cmd, arg); \ +}) + +#define __kvm_ioctl(kvm_fd, cmd, arg) \ + kvm_do_ioctl(kvm_fd, cmd, arg) + +#define kvm_ioctl(kvm_fd, cmd, arg) \ +({ \ + int ret = __kvm_ioctl(kvm_fd, cmd, arg); \ + \ + TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret)); \ +}) + +static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { } + +#define __vm_ioctl(vm, cmd, arg) \ +({ \ + static_assert_is_vm(vm); \ + kvm_do_ioctl((vm)->fd, cmd, arg); \ +}) + +/* + * Assert that a VM or vCPU ioctl() succeeded, with extra magic to detect if + * the ioctl() failed because KVM killed/bugged the VM. To detect a dead VM, + * probe KVM_CAP_USER_MEMORY, which (a) has been supported by KVM since before + * selftests existed and (b) should never outright fail, i.e. is supposed to + * return 0 or 1. If KVM kills a VM, KVM returns -EIO for all ioctl()s for the + * VM and its vCPUs, including KVM_CHECK_EXTENSION. + */ +#define __TEST_ASSERT_VM_VCPU_IOCTL(cond, name, ret, vm) \ +do { \ + int __errno = errno; \ + \ + static_assert_is_vm(vm); \ + \ + if (cond) \ + break; \ + \ + if (errno == EIO && \ + __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)KVM_CAP_USER_MEMORY) < 0) { \ + TEST_ASSERT(errno == EIO, "KVM killed the VM, should return -EIO"); \ + TEST_FAIL("KVM killed/bugged the VM, check the kernel log for clues"); \ + } \ + errno = __errno; \ + TEST_ASSERT(cond, __KVM_IOCTL_ERROR(name, ret)); \ +} while (0) + +#define TEST_ASSERT_VM_VCPU_IOCTL(cond, cmd, ret, vm) \ + __TEST_ASSERT_VM_VCPU_IOCTL(cond, #cmd, ret, vm) + +#define vm_ioctl(vm, cmd, arg) \ +({ \ + int ret = __vm_ioctl(vm, cmd, arg); \ + \ + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm); \ +}) + +static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { } + +#define __vcpu_ioctl(vcpu, cmd, arg) \ +({ \ + static_assert_is_vcpu(vcpu); \ + kvm_do_ioctl((vcpu)->fd, cmd, arg); \ +}) + +#define vcpu_ioctl(vcpu, cmd, arg) \ +({ \ + int ret = __vcpu_ioctl(vcpu, cmd, arg); \ + \ + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, (vcpu)->vm); \ +}) + +/* + * Looks up and returns the value corresponding to the capability + * (KVM_CAP_*) given by cap. + */ +static inline int vm_check_cap(struct kvm_vm *vm, long cap) +{ + int ret = __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)cap); + + TEST_ASSERT_VM_VCPU_IOCTL(ret >= 0, KVM_CHECK_EXTENSION, ret, vm); + return ret; +} + +static inline int __vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) +{ + struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; + + return __vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); +} +static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) +{ + struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; + + vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); +} + +static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa, + uint64_t size, uint64_t attributes) +{ + struct kvm_memory_attributes attr = { + .attributes = attributes, + .address = gpa, + .size = size, + .flags = 0, + }; + + /* + * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes. These flows + * need significant enhancements to support multiple attributes. + */ + TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE, + "Update me to support multiple attributes!"); + + vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr); +} + + +static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE); +} + +static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_set_memory_attributes(vm, gpa, size, 0); +} + +void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size, + bool punch_hole); + +static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_guest_mem_fallocate(vm, gpa, size, true); +} + +static inline void vm_guest_mem_allocate(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_guest_mem_fallocate(vm, gpa, size, false); +} + +void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); +const char *vm_guest_mode_string(uint32_t i); + +void kvm_vm_free(struct kvm_vm *vmp); +void kvm_vm_restart(struct kvm_vm *vmp); +void kvm_vm_release(struct kvm_vm *vmp); +int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva, + size_t len); +void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename); +int kvm_memfd_alloc(size_t size, bool hugepages); + +void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); + +static inline void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) +{ + struct kvm_dirty_log args = { .dirty_bitmap = log, .slot = slot }; + + vm_ioctl(vm, KVM_GET_DIRTY_LOG, &args); +} + +static inline void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, + uint64_t first_page, uint32_t num_pages) +{ + struct kvm_clear_dirty_log args = { + .dirty_bitmap = log, + .slot = slot, + .first_page = first_page, + .num_pages = num_pages + }; + + vm_ioctl(vm, KVM_CLEAR_DIRTY_LOG, &args); +} + +static inline uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) +{ + return __vm_ioctl(vm, KVM_RESET_DIRTY_RINGS, NULL); +} + +static inline int vm_get_stats_fd(struct kvm_vm *vm) +{ + int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL); + + TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_GET_STATS_FD, fd, vm); + return fd; +} + +static inline void read_stats_header(int stats_fd, struct kvm_stats_header *header) +{ + ssize_t ret; + + ret = pread(stats_fd, header, sizeof(*header), 0); + TEST_ASSERT(ret == sizeof(*header), + "Failed to read '%lu' header bytes, ret = '%ld'", + sizeof(*header), ret); +} + +struct kvm_stats_desc *read_stats_descriptors(int stats_fd, + struct kvm_stats_header *header); + +static inline ssize_t get_stats_descriptor_size(struct kvm_stats_header *header) +{ + /* + * The base size of the descriptor is defined by KVM's ABI, but the + * size of the name field is variable, as far as KVM's ABI is + * concerned. For a given instance of KVM, the name field is the same + * size for all stats and is provided in the overall stats header. + */ + return sizeof(struct kvm_stats_desc) + header->name_size; +} + +static inline struct kvm_stats_desc *get_stats_descriptor(struct kvm_stats_desc *stats, + int index, + struct kvm_stats_header *header) +{ + /* + * Note, size_desc includes the size of the name field, which is + * variable. i.e. this is NOT equivalent to &stats_desc[i]. + */ + return (void *)stats + index * get_stats_descriptor_size(header); +} + +void read_stat_data(int stats_fd, struct kvm_stats_header *header, + struct kvm_stats_desc *desc, uint64_t *data, + size_t max_elements); + +void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data, + size_t max_elements); + +static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name) +{ + uint64_t data; + + __vm_get_stat(vm, stat_name, &data, 1); + return data; +} + +void vm_create_irqchip(struct kvm_vm *vm); + +static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, + uint64_t flags) +{ + struct kvm_create_guest_memfd guest_memfd = { + .size = size, + .flags = flags, + }; + + return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &guest_memfd); +} + +static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, + uint64_t flags) +{ + int fd = __vm_create_guest_memfd(vm, size, flags); + + TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_GUEST_MEMFD, fd)); + return fd; +} + +void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva); +int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva); +void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset); +int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset); + +void vm_userspace_mem_region_add(struct kvm_vm *vm, + enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, uint64_t npages, + uint32_t flags); +void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, uint64_t npages, + uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset); + +#ifndef vm_arch_has_protected_memory +static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) +{ + return false; +} +#endif + +void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); +void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); +void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot); +struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); +void vm_populate_vaddr_bitmap(struct kvm_vm *vm); +vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); +vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min); +vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type); +vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type); +vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages); +vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, + enum kvm_mem_region_type type); +vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm); + +void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, + unsigned int npages); +void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa); +void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); +vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); +void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); + +#ifndef vcpu_arch_put_guest +#define vcpu_arch_put_guest(mem, val) do { (mem) = (val); } while (0) +#endif + +static inline vm_paddr_t vm_untag_gpa(struct kvm_vm *vm, vm_paddr_t gpa) +{ + return gpa & ~vm->gpa_tag_mask; +} + +void vcpu_run(struct kvm_vcpu *vcpu); +int _vcpu_run(struct kvm_vcpu *vcpu); + +static inline int __vcpu_run(struct kvm_vcpu *vcpu) +{ + return __vcpu_ioctl(vcpu, KVM_RUN, NULL); +} + +void vcpu_run_complete_io(struct kvm_vcpu *vcpu); +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu); + +static inline void vcpu_enable_cap(struct kvm_vcpu *vcpu, uint32_t cap, + uint64_t arg0) +{ + struct kvm_enable_cap enable_cap = { .cap = cap, .args = { arg0 } }; + + vcpu_ioctl(vcpu, KVM_ENABLE_CAP, &enable_cap); +} + +static inline void vcpu_guest_debug_set(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *debug) +{ + vcpu_ioctl(vcpu, KVM_SET_GUEST_DEBUG, debug); +} + +static inline void vcpu_mp_state_get(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + vcpu_ioctl(vcpu, KVM_GET_MP_STATE, mp_state); +} +static inline void vcpu_mp_state_set(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + vcpu_ioctl(vcpu, KVM_SET_MP_STATE, mp_state); +} + +static inline void vcpu_regs_get(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu_ioctl(vcpu, KVM_GET_REGS, regs); +} + +static inline void vcpu_regs_set(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + vcpu_ioctl(vcpu, KVM_SET_REGS, regs); +} +static inline void vcpu_sregs_get(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + vcpu_ioctl(vcpu, KVM_GET_SREGS, sregs); + +} +static inline void vcpu_sregs_set(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + vcpu_ioctl(vcpu, KVM_SET_SREGS, sregs); +} +static inline int _vcpu_sregs_set(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + return __vcpu_ioctl(vcpu, KVM_SET_SREGS, sregs); +} +static inline void vcpu_fpu_get(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + vcpu_ioctl(vcpu, KVM_GET_FPU, fpu); +} +static inline void vcpu_fpu_set(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + vcpu_ioctl(vcpu, KVM_SET_FPU, fpu); +} + +static inline int __vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; + + return __vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); +} +static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + + return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); +} +static inline void vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; + + vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); +} +static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) +{ + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + + vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); +} + +#ifdef __KVM_HAVE_VCPU_EVENTS +static inline void vcpu_events_get(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + vcpu_ioctl(vcpu, KVM_GET_VCPU_EVENTS, events); +} +static inline void vcpu_events_set(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + vcpu_ioctl(vcpu, KVM_SET_VCPU_EVENTS, events); +} +#endif +#ifdef __x86_64__ +static inline void vcpu_nested_state_get(struct kvm_vcpu *vcpu, + struct kvm_nested_state *state) +{ + vcpu_ioctl(vcpu, KVM_GET_NESTED_STATE, state); +} +static inline int __vcpu_nested_state_set(struct kvm_vcpu *vcpu, + struct kvm_nested_state *state) +{ + return __vcpu_ioctl(vcpu, KVM_SET_NESTED_STATE, state); +} + +static inline void vcpu_nested_state_set(struct kvm_vcpu *vcpu, + struct kvm_nested_state *state) +{ + vcpu_ioctl(vcpu, KVM_SET_NESTED_STATE, state); +} +#endif +static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu) +{ + int fd = __vcpu_ioctl(vcpu, KVM_GET_STATS_FD, NULL); + + TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_CHECK_EXTENSION, fd, vcpu->vm); + return fd; +} + +int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr); + +static inline void kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr) +{ + int ret = __kvm_has_device_attr(dev_fd, group, attr); + + TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno); +} + +int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val); + +static inline void kvm_device_attr_get(int dev_fd, uint32_t group, + uint64_t attr, void *val) +{ + int ret = __kvm_device_attr_get(dev_fd, group, attr, val); + + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_GET_DEVICE_ATTR, ret)); +} + +int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val); + +static inline void kvm_device_attr_set(int dev_fd, uint32_t group, + uint64_t attr, void *val) +{ + int ret = __kvm_device_attr_set(dev_fd, group, attr, val); + + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_DEVICE_ATTR, ret)); +} + +static inline int __vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr) +{ + return __kvm_has_device_attr(vcpu->fd, group, attr); +} + +static inline void vcpu_has_device_attr(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr) +{ + kvm_has_device_attr(vcpu->fd, group, attr); +} + +static inline int __vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + return __kvm_device_attr_get(vcpu->fd, group, attr, val); +} + +static inline void vcpu_device_attr_get(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + kvm_device_attr_get(vcpu->fd, group, attr, val); +} + +static inline int __vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + return __kvm_device_attr_set(vcpu->fd, group, attr, val); +} + +static inline void vcpu_device_attr_set(struct kvm_vcpu *vcpu, uint32_t group, + uint64_t attr, void *val) +{ + kvm_device_attr_set(vcpu->fd, group, attr, val); +} + +int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type); +int __kvm_create_device(struct kvm_vm *vm, uint64_t type); + +static inline int kvm_create_device(struct kvm_vm *vm, uint64_t type) +{ + int fd = __kvm_create_device(vm, type); + + TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_DEVICE, fd)); + return fd; +} + +void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu); + +/* + * VM VCPU Args Set + * + * Input Args: + * vm - Virtual Machine + * num - number of arguments + * ... - arguments, each of type uint64_t + * + * Output Args: None + * + * Return: None + * + * Sets the first @num input parameters for the function at @vcpu's entry point, + * per the C calling convention of the architecture, to the values given as + * variable args. Each of the variable args is expected to be of type uint64_t. + * The maximum @num can be is specific to the architecture. + */ +void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...); + +void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); +int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); + +#define KVM_MAX_IRQ_ROUTES 4096 + +struct kvm_irq_routing *kvm_gsi_routing_create(void); +void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, + uint32_t gsi, uint32_t pin); +int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); +void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); + +const char *exit_reason_str(unsigned int exit_reason); + +vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, + uint32_t memslot); +vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot, + bool protected); +vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); + +static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot) +{ + /* + * By default, allocate memory as protected for VMs that support + * protected memory, as the majority of memory for such VMs is + * protected, i.e. using shared memory is effectively opt-in. + */ + return __vm_phy_pages_alloc(vm, num, paddr_min, memslot, + vm_arch_has_protected_memory(vm)); +} + +/* + * ____vm_create() does KVM_CREATE_VM and little else. __vm_create() also + * loads the test binary into guest memory and creates an IRQ chip (x86 only). + * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to + * calculate the amount of memory needed for per-vCPU data, e.g. stacks. + */ +struct kvm_vm *____vm_create(struct vm_shape shape); +struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, + uint64_t nr_extra_pages); + +static inline struct kvm_vm *vm_create_barebones(void) +{ + return ____vm_create(VM_SHAPE_DEFAULT); +} + +static inline struct kvm_vm *vm_create_barebones_type(unsigned long type) +{ + const struct vm_shape shape = { + .mode = VM_MODE_DEFAULT, + .type = type, + }; + + return ____vm_create(shape); +} + +static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus) +{ + return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0); +} + +struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, + uint64_t extra_mem_pages, + void *guest_code, struct kvm_vcpu *vcpus[]); + +static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus, + void *guest_code, + struct kvm_vcpu *vcpus[]) +{ + return __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus, 0, + guest_code, vcpus); +} + + +struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code); + +/* + * Create a VM with a single vCPU with reasonable defaults and @extra_mem_pages + * additional pages of guest memory. Returns the VM and vCPU (via out param). + */ +static inline struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code) +{ + return __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, vcpu, + extra_mem_pages, guest_code); +} + +static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + void *guest_code) +{ + return __vm_create_with_one_vcpu(vcpu, 0, guest_code); +} + +static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + void *guest_code) +{ + return __vm_create_shape_with_one_vcpu(shape, vcpu, 0, guest_code); +} + +struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); + +void kvm_pin_this_task_to_pcpu(uint32_t pcpu); +void kvm_print_vcpu_pinning_help(void); +void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], + int nr_vcpus); + +unsigned long vm_compute_max_gfn(struct kvm_vm *vm); +unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size); +unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages); +unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages); +static inline unsigned int +vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) +{ + unsigned int n; + n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages)); +#ifdef __s390x__ + /* s390 requires 1M aligned guest sizes */ + n = (n + 255) & ~255; +#endif + return n; +} + +#define sync_global_to_guest(vm, g) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + memcpy(_p, &(g), sizeof(g)); \ +}) + +#define sync_global_from_guest(vm, g) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + memcpy(&(g), _p, sizeof(g)); \ +}) + +/* + * Write a global value, but only in the VM's (guest's) domain. Primarily used + * for "globals" that hold per-VM values (VMs always duplicate code and global + * data into their own region of physical memory), but can be used anytime it's + * undesirable to change the host's copy of the global. + */ +#define write_guest_global(vm, g, val) ({ \ + typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ + typeof(g) _val = val; \ + \ + memcpy(_p, &(_val), sizeof(g)); \ +}) + +void assert_on_unhandled_exception(struct kvm_vcpu *vcpu); + +void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, + uint8_t indent); + +static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu, + uint8_t indent) +{ + vcpu_arch_dump(stream, vcpu, indent); +} + +/* + * Adds a vCPU with reasonable defaults (e.g. a stack) + * + * Input Args: + * vm - Virtual Machine + * vcpu_id - The id of the VCPU to add to the VM. + */ +struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id); +void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code); + +static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, + void *guest_code) +{ + struct kvm_vcpu *vcpu = vm_arch_vcpu_add(vm, vcpu_id); + + vcpu_arch_set_entry_point(vcpu, guest_code); + + return vcpu; +} + +/* Re-create a vCPU after restarting a VM, e.g. for state save/restore tests. */ +struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, uint32_t vcpu_id); + +static inline struct kvm_vcpu *vm_vcpu_recreate(struct kvm_vm *vm, + uint32_t vcpu_id) +{ + return vm_arch_vcpu_recreate(vm, vcpu_id); +} + +void vcpu_arch_free(struct kvm_vcpu *vcpu); + +void virt_arch_pgd_alloc(struct kvm_vm *vm); + +static inline void virt_pgd_alloc(struct kvm_vm *vm) +{ + virt_arch_pgd_alloc(vm); +} + +/* + * VM Virtual Page Map + * + * Input Args: + * vm - Virtual Machine + * vaddr - VM Virtual Address + * paddr - VM Physical Address + * memslot - Memory region slot for new virtual translation tables + * + * Output Args: None + * + * Return: None + * + * Within @vm, creates a virtual translation for the page starting + * at @vaddr to the page starting at @paddr. + */ +void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr); + +static inline void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr) +{ + virt_arch_pg_map(vm, vaddr, paddr); +} + + +/* + * Address Guest Virtual to Guest Physical + * + * Input Args: + * vm - Virtual Machine + * gva - VM virtual address + * + * Output Args: None + * + * Return: + * Equivalent VM physical address + * + * Returns the VM physical address of the translated VM virtual + * address given by @gva. + */ +vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva); + +static inline vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) +{ + return addr_arch_gva2gpa(vm, gva); +} + +/* + * Virtual Translation Tables Dump + * + * Input Args: + * stream - Output FILE stream + * vm - Virtual Machine + * indent - Left margin indent amount + * + * Output Args: None + * + * Return: None + * + * Dumps to the FILE stream given by @stream, the contents of all the + * virtual translation tables for the VM given by @vm. + */ +void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent); + +static inline void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) +{ + virt_arch_dump(stream, vm, indent); +} + + +static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm) +{ + return __vm_enable_cap(vm, KVM_CAP_VM_DISABLE_NX_HUGE_PAGES, 0); +} + +/* + * Arch hook that is invoked via a constructor, i.e. before exeucting main(), + * to allow for arch-specific setup that is common to all tests, e.g. computing + * the default guest "mode". + */ +void kvm_selftest_arch_init(void); + +void kvm_arch_vm_post_create(struct kvm_vm *vm); + +bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr); + +uint32_t guest_get_vcpuid(void); #endif /* SELFTEST_KVM_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 8acca823768700..e850269a321937 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -27,12 +27,12 @@ /* * Provide a version of static_assert() that is guaranteed to have an optional - * message param. If _ISOC11_SOURCE is defined, glibc (/usr/include/assert.h) - * #undefs and #defines static_assert() as a direct alias to _Static_assert(), - * i.e. effectively makes the message mandatory. Many KVM selftests #define - * _GNU_SOURCE for various reasons, and _GNU_SOURCE implies _ISOC11_SOURCE. As - * a result, static_assert() behavior is non-deterministic and may or may not - * require a message depending on #include order. + * message param. _GNU_SOURCE is defined for all KVM selftests, _GNU_SOURCE + * implies _ISOC11_SOURCE, and if _ISOC11_SOURCE is defined, glibc #undefs and + * #defines static_assert() as a direct alias to _Static_assert() (see + * usr/include/assert.h). Define a custom macro instead of redefining + * static_assert() to avoid creating non-deterministic behavior that is + * dependent on include order. */ #define __kvm_static_assert(expr, msg, ...) _Static_assert(expr, msg) #define kvm_static_assert(expr, ...) __kvm_static_assert(expr, ##__VA_ARGS__, #expr) @@ -609,6 +609,9 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva); vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva); void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa); +#ifndef vcpu_arch_put_guest +#define vcpu_arch_put_guest(mem, val) do { (mem) = (val); } while (0) +#endif static inline vm_paddr_t vm_untag_gpa(struct kvm_vm *vm, vm_paddr_t gpa) { diff --git a/tools/testing/selftests/kvm/include/kvm_util_types.h b/tools/testing/selftests/kvm/include/kvm_util_types.h new file mode 100644 index 00000000000000..ec787b97cf184e --- /dev/null +++ b/tools/testing/selftests/kvm/include/kvm_util_types.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTEST_KVM_UTIL_TYPES_H +#define SELFTEST_KVM_UTIL_TYPES_H + +/* + * Provide a version of static_assert() that is guaranteed to have an optional + * message param. _GNU_SOURCE is defined for all KVM selftests, _GNU_SOURCE + * implies _ISOC11_SOURCE, and if _ISOC11_SOURCE is defined, glibc #undefs and + * #defines static_assert() as a direct alias to _Static_assert() (see + * usr/include/assert.h). Define a custom macro instead of redefining + * static_assert() to avoid creating non-deterministic behavior that is + * dependent on include order. + */ +#define __kvm_static_assert(expr, msg, ...) _Static_assert(expr, msg) +#define kvm_static_assert(expr, ...) __kvm_static_assert(expr, ##__VA_ARGS__, #expr) + +typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ +typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ + +#endif /* SELFTEST_KVM_UTIL_TYPES_H */ diff --git a/tools/testing/selftests/kvm/include/memstress.h b/tools/testing/selftests/kvm/include/memstress.h index ce4e603050eaaa..9071eb6dea60a6 100644 --- a/tools/testing/selftests/kvm/include/memstress.h +++ b/tools/testing/selftests/kvm/include/memstress.h @@ -62,7 +62,6 @@ struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus, void memstress_destroy_vm(struct kvm_vm *vm); void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent); -void memstress_set_random_seed(struct kvm_vm *vm, uint32_t random_seed); void memstress_set_random_access(struct kvm_vm *vm, bool random_access); void memstress_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct memstress_vcpu_args *)); diff --git a/tools/testing/selftests/kvm/include/s390x/ucall.h b/tools/testing/selftests/kvm/include/s390x/ucall.h index b231bf2e49d620..8035a872a351bb 100644 --- a/tools/testing/selftests/kvm/include/s390x/ucall.h +++ b/tools/testing/selftests/kvm/include/s390x/ucall.h @@ -2,7 +2,7 @@ #ifndef SELFTEST_KVM_UCALL_H #define SELFTEST_KVM_UCALL_H -#include "kvm_util_base.h" +#include "kvm_util.h" #define UCALL_EXIT_REASON KVM_EXIT_S390_SIEIC diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 8a6e30612c8626..3e473058849ffa 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -91,9 +91,28 @@ struct guest_random_state { uint32_t seed; }; +extern uint32_t guest_random_seed; +extern struct guest_random_state guest_rng; + struct guest_random_state new_guest_random_state(uint32_t seed); uint32_t guest_random_u32(struct guest_random_state *state); +static inline bool __guest_random_bool(struct guest_random_state *state, + uint8_t percent) +{ + return (guest_random_u32(state) % 100) < percent; +} + +static inline bool guest_random_bool(struct guest_random_state *state) +{ + return __guest_random_bool(state, 50); +} + +static inline uint64_t guest_random_u64(struct guest_random_state *state) +{ + return ((uint64_t)guest_random_u32(state) << 32) | guest_random_u32(state); +} + enum vm_mem_backing_src_type { VM_MEM_SRC_ANONYMOUS, VM_MEM_SRC_ANONYMOUS_THP, diff --git a/tools/testing/selftests/kvm/include/userfaultfd_util.h b/tools/testing/selftests/kvm/include/userfaultfd_util.h index 877449c345928b..60f7f9d435dc2a 100644 --- a/tools/testing/selftests/kvm/include/userfaultfd_util.h +++ b/tools/testing/selftests/kvm/include/userfaultfd_util.h @@ -5,9 +5,6 @@ * Copyright (C) 2018, Red Hat, Inc. * Copyright (C) 2019-2022 Google LLC */ - -#define _GNU_SOURCE /* for pipe2 */ - #include <inttypes.h> #include <time.h> #include <pthread.h> @@ -17,17 +14,27 @@ typedef int (*uffd_handler_t)(int uffd_mode, int uffd, struct uffd_msg *msg); -struct uffd_desc { +struct uffd_reader_args { int uffd_mode; int uffd; - int pipefds[2]; useconds_t delay; uffd_handler_t handler; - pthread_t thread; + /* Holds the read end of the pipe for killing the reader. */ + int pipe; +}; + +struct uffd_desc { + int uffd; + uint64_t num_readers; + /* Holds the write ends of the pipes for killing the readers. */ + int *pipefds; + pthread_t *readers; + struct uffd_reader_args *reader_args; }; struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, void *hva, uint64_t len, + uint64_t num_readers, uffd_handler_t handler); void uffd_stop_demand_paging(struct uffd_desc *uffd); diff --git a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h index 9f1725192aa224..972bb1c4ab4c21 100644 --- a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h @@ -5,7 +5,16 @@ #include <stdbool.h> #include <stdint.h> +#include "kvm_util_types.h" +#include "test_util.h" + +extern bool is_forced_emulation_enabled; + struct kvm_vm_arch { + vm_vaddr_t gdt; + vm_vaddr_t tss; + vm_vaddr_t idt; + uint64_t c_bit; uint64_t s_bit; int sev_fd; @@ -20,4 +29,23 @@ static inline bool __vm_arch_has_protected_memory(struct kvm_vm_arch *arch) #define vm_arch_has_protected_memory(vm) \ __vm_arch_has_protected_memory(&(vm)->arch) +#define vcpu_arch_put_guest(mem, __val) \ +do { \ + const typeof(mem) val = (__val); \ + \ + if (!is_forced_emulation_enabled || guest_random_bool(&guest_rng)) { \ + (mem) = val; \ + } else if (guest_random_bool(&guest_rng)) { \ + __asm__ __volatile__(KVM_FEP "mov %1, %0" \ + : "+m" (mem) \ + : "r" (val) : "memory"); \ + } else { \ + uint64_t __old = READ_ONCE(mem); \ + \ + __asm__ __volatile__(KVM_FEP LOCK_PREFIX "cmpxchg %[new], %[ptr]" \ + : [ptr] "+m" (mem), [old] "+a" (__old) \ + : [new]"r" (val) : "memory", "cc"); \ + } \ +} while (0) + #endif // SELFTEST_KVM_UTIL_ARCH_H diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 74a59c7ce7edda..8eb57de0b5876d 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -18,7 +18,8 @@ #include <linux/kvm_para.h> #include <linux/stringify.h> -#include "../kvm_util.h" +#include "kvm_util.h" +#include "ucall_common.h" extern bool host_cpu_is_intel; extern bool host_cpu_is_amd; @@ -1133,8 +1134,6 @@ struct idt_entry { uint32_t offset2; uint32_t reserved; }; -void vm_init_descriptor_tables(struct kvm_vm *vm); -void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu); void vm_install_exception_handler(struct kvm_vm *vm, int vector, void (*handler)(struct ex_regs *)); diff --git a/tools/testing/selftests/kvm/include/x86_64/ucall.h b/tools/testing/selftests/kvm/include/x86_64/ucall.h index 06b244bd06eeb8..d3825dcc3cd935 100644 --- a/tools/testing/selftests/kvm/include/x86_64/ucall.h +++ b/tools/testing/selftests/kvm/include/x86_64/ucall.h @@ -2,7 +2,7 @@ #ifndef SELFTEST_KVM_UCALL_H #define SELFTEST_KVM_UCALL_H -#include "kvm_util_base.h" +#include "kvm_util.h" #define UCALL_EXIT_REASON KVM_EXIT_IO diff --git a/tools/testing/selftests/kvm/kvm_binary_stats_test.c b/tools/testing/selftests/kvm/kvm_binary_stats_test.c index 698c1cfa3111be..f02355c3c4c236 100644 --- a/tools/testing/selftests/kvm/kvm_binary_stats_test.c +++ b/tools/testing/selftests/kvm/kvm_binary_stats_test.c @@ -6,8 +6,6 @@ * * Test the fd-based interface for KVM statistics. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c index b9e23265e4b383..c78f34699f7301 100644 --- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c +++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c @@ -6,8 +6,6 @@ * * Test for KVM_CAP_MAX_VCPUS and KVM_CAP_MAX_VCPU_ID. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index e0ba97ac1c5611..dd8b12f626d3c0 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -8,9 +8,6 @@ * page size have been pre-allocated on your system, if you are planning to * use hugepages to back the guest memory for testing. */ - -#define _GNU_SOURCE /* for program_invocation_name */ - #include <stdio.h> #include <stdlib.h> #include <time.h> @@ -21,6 +18,7 @@ #include "kvm_util.h" #include "processor.h" #include "guest_modes.h" +#include "ucall_common.h" #define TEST_MEM_SLOT_INDEX 1 diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index a9eb17295be42f..0ac7cc89f38c1c 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -11,6 +11,8 @@ #include "guest_modes.h" #include "kvm_util.h" #include "processor.h" +#include "ucall_common.h" + #include <linux/bitfield.h> #include <linux/sizes.h> diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c index 2bd25b191d150c..b49690658c6061 100644 --- a/tools/testing/selftests/kvm/lib/assert.c +++ b/tools/testing/selftests/kvm/lib/assert.c @@ -4,9 +4,6 @@ * * Copyright (C) 2018, Google LLC. */ - -#define _GNU_SOURCE /* for getline(3) and strchrnul(3)*/ - #include "test_util.h" #include <execinfo.h> diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 9da388100f3a35..6b2158655baa10 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -4,11 +4,10 @@ * * Copyright (C) 2018, Google LLC. */ - -#define _GNU_SOURCE /* for program_invocation_name */ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "ucall_common.h" #include <assert.h> #include <sched.h> @@ -20,6 +19,9 @@ #define KVM_UTIL_MIN_PFN 2 +uint32_t guest_random_seed; +struct guest_random_state guest_rng; + static int vcpu_mmap_sz(void); int open_path_or_exit(const char *path, int flags) @@ -432,6 +434,10 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, slot0 = memslot2region(vm, 0); ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size); + pr_info("Random seed: 0x%x\n", guest_random_seed); + guest_rng = new_guest_random_state(guest_random_seed); + sync_global_to_guest(vm, guest_rng); + kvm_arch_vm_post_create(vm); return vm; @@ -2305,6 +2311,8 @@ void __attribute((constructor)) kvm_selftest_init(void) /* Tell stdout not to buffer its content. */ setbuf(stdout, NULL); + guest_random_seed = random(); + kvm_selftest_arch_init(); } diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c index cf2c739713080f..313277486a1dee 100644 --- a/tools/testing/selftests/kvm/lib/memstress.c +++ b/tools/testing/selftests/kvm/lib/memstress.c @@ -2,14 +2,13 @@ /* * Copyright (C) 2020, Google LLC. */ -#define _GNU_SOURCE - #include <inttypes.h> #include <linux/bitmap.h> #include "kvm_util.h" #include "memstress.h" #include "processor.h" +#include "ucall_common.h" struct memstress_args memstress_args; @@ -56,7 +55,7 @@ void memstress_guest_code(uint32_t vcpu_idx) uint64_t page; int i; - rand_state = new_guest_random_state(args->random_seed + vcpu_idx); + rand_state = new_guest_random_state(guest_random_seed + vcpu_idx); gva = vcpu_args->gva; pages = vcpu_args->pages; @@ -76,7 +75,7 @@ void memstress_guest_code(uint32_t vcpu_idx) addr = gva + (page * args->guest_page_size); - if (guest_random_u32(&rand_state) % 100 < args->write_percent) + if (__guest_random_bool(&rand_state, args->write_percent)) *(uint64_t *)addr = 0x0123456789ABCDEF; else READ_ONCE(*(uint64_t *)addr); @@ -243,12 +242,6 @@ void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent) sync_global_to_guest(vm, memstress_args.write_percent); } -void memstress_set_random_seed(struct kvm_vm *vm, uint32_t random_seed) -{ - memstress_args.random_seed = random_seed; - sync_global_to_guest(vm, memstress_args.random_seed); -} - void memstress_set_random_access(struct kvm_vm *vm, bool random_access) { memstress_args.random_access = random_access; diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index ccb35573749c3d..6ae47b3d6b25f4 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -10,6 +10,7 @@ #include "kvm_util.h" #include "processor.h" +#include "ucall_common.h" #define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000 diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 5a8f8becb12984..8ed0b74ae83733 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -4,8 +4,6 @@ * * Copyright (C) 2020, Google LLC. */ - -#define _GNU_SOURCE #include <stdio.h> #include <stdarg.h> #include <assert.h> diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c index f5af65a41c296e..42151e57195360 100644 --- a/tools/testing/selftests/kvm/lib/ucall_common.c +++ b/tools/testing/selftests/kvm/lib/ucall_common.c @@ -1,9 +1,12 @@ // SPDX-License-Identifier: GPL-2.0-only -#include "kvm_util.h" #include "linux/types.h" #include "linux/bitmap.h" #include "linux/atomic.h" +#include "kvm_util.h" +#include "ucall_common.h" + + #define GUEST_UCALL_FAILED -1 struct ucall_header { diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c index f4eef6eb2dc2cc..7c9de84144627e 100644 --- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c +++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c @@ -6,9 +6,6 @@ * Copyright (C) 2018, Red Hat, Inc. * Copyright (C) 2019-2022 Google LLC */ - -#define _GNU_SOURCE /* for pipe2 */ - #include <inttypes.h> #include <stdio.h> #include <stdlib.h> @@ -16,6 +13,7 @@ #include <poll.h> #include <pthread.h> #include <linux/userfaultfd.h> +#include <sys/epoll.h> #include <sys/syscall.h> #include "kvm_util.h" @@ -27,76 +25,69 @@ static void *uffd_handler_thread_fn(void *arg) { - struct uffd_desc *uffd_desc = (struct uffd_desc *)arg; - int uffd = uffd_desc->uffd; - int pipefd = uffd_desc->pipefds[0]; - useconds_t delay = uffd_desc->delay; + struct uffd_reader_args *reader_args = (struct uffd_reader_args *)arg; + int uffd = reader_args->uffd; int64_t pages = 0; struct timespec start; struct timespec ts_diff; + struct epoll_event evt; + int epollfd; + + epollfd = epoll_create(1); + TEST_ASSERT(epollfd >= 0, "Failed to create epollfd."); + + evt.events = EPOLLIN | EPOLLEXCLUSIVE; + evt.data.u32 = 0; + TEST_ASSERT(!epoll_ctl(epollfd, EPOLL_CTL_ADD, uffd, &evt), + "Failed to add uffd to epollfd"); + + evt.events = EPOLLIN; + evt.data.u32 = 1; + TEST_ASSERT(!epoll_ctl(epollfd, EPOLL_CTL_ADD, reader_args->pipe, &evt), + "Failed to add pipe to epollfd"); clock_gettime(CLOCK_MONOTONIC, &start); while (1) { struct uffd_msg msg; - struct pollfd pollfd[2]; - char tmp_chr; int r; - pollfd[0].fd = uffd; - pollfd[0].events = POLLIN; - pollfd[1].fd = pipefd; - pollfd[1].events = POLLIN; + r = epoll_wait(epollfd, &evt, 1, -1); + TEST_ASSERT(r == 1, + "Unexpected number of events (%d) from epoll, errno = %d", + r, errno); - r = poll(pollfd, 2, -1); - switch (r) { - case -1: - pr_info("poll err"); - continue; - case 0: - continue; - case 1: - break; - default: - pr_info("Polling uffd returned %d", r); - return NULL; - } - - if (pollfd[0].revents & POLLERR) { - pr_info("uffd revents has POLLERR"); - return NULL; - } + if (evt.data.u32 == 1) { + char tmp_chr; - if (pollfd[1].revents & POLLIN) { - r = read(pollfd[1].fd, &tmp_chr, 1); + TEST_ASSERT(!(evt.events & (EPOLLERR | EPOLLHUP)), + "Reader thread received EPOLLERR or EPOLLHUP on pipe."); + r = read(reader_args->pipe, &tmp_chr, 1); TEST_ASSERT(r == 1, - "Error reading pipefd in UFFD thread"); + "Error reading pipefd in uffd reader thread"); break; } - if (!(pollfd[0].revents & POLLIN)) - continue; + TEST_ASSERT(!(evt.events & (EPOLLERR | EPOLLHUP)), + "Reader thread received EPOLLERR or EPOLLHUP on uffd."); r = read(uffd, &msg, sizeof(msg)); if (r == -1) { - if (errno == EAGAIN) - continue; - pr_info("Read of uffd got errno %d\n", errno); - return NULL; + TEST_ASSERT(errno == EAGAIN, + "Error reading from UFFD: errno = %d", errno); + continue; } - if (r != sizeof(msg)) { - pr_info("Read on uffd returned unexpected size: %d bytes", r); - return NULL; - } + TEST_ASSERT(r == sizeof(msg), + "Read on uffd returned unexpected number of bytes (%d)", r); if (!(msg.event & UFFD_EVENT_PAGEFAULT)) continue; - if (delay) - usleep(delay); - r = uffd_desc->handler(uffd_desc->uffd_mode, uffd, &msg); - if (r < 0) - return NULL; + if (reader_args->delay) + usleep(reader_args->delay); + r = reader_args->handler(reader_args->uffd_mode, uffd, &msg); + TEST_ASSERT(r >= 0, + "Reader thread handler fn returned negative value %d", r); pages++; } @@ -110,6 +101,7 @@ static void *uffd_handler_thread_fn(void *arg) struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, void *hva, uint64_t len, + uint64_t num_readers, uffd_handler_t handler) { struct uffd_desc *uffd_desc; @@ -118,14 +110,25 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, struct uffdio_api uffdio_api; struct uffdio_register uffdio_register; uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY; - int ret; + int ret, i; PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n", is_minor ? "MINOR" : "MISSING", is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY"); uffd_desc = malloc(sizeof(struct uffd_desc)); - TEST_ASSERT(uffd_desc, "malloc failed"); + TEST_ASSERT(uffd_desc, "Failed to malloc uffd descriptor"); + + uffd_desc->pipefds = calloc(sizeof(int), num_readers); + TEST_ASSERT(uffd_desc->pipefds, "Failed to alloc pipes"); + + uffd_desc->readers = calloc(sizeof(pthread_t), num_readers); + TEST_ASSERT(uffd_desc->readers, "Failed to alloc reader threads"); + + uffd_desc->reader_args = calloc(sizeof(struct uffd_reader_args), num_readers); + TEST_ASSERT(uffd_desc->reader_args, "Failed to alloc reader_args"); + + uffd_desc->num_readers = num_readers; /* In order to get minor faults, prefault via the alias. */ if (is_minor) @@ -148,18 +151,28 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) == expected_ioctls, "missing userfaultfd ioctls"); - ret = pipe2(uffd_desc->pipefds, O_CLOEXEC | O_NONBLOCK); - TEST_ASSERT(!ret, "Failed to set up pipefd"); - - uffd_desc->uffd_mode = uffd_mode; uffd_desc->uffd = uffd; - uffd_desc->delay = delay; - uffd_desc->handler = handler; - pthread_create(&uffd_desc->thread, NULL, uffd_handler_thread_fn, - uffd_desc); + for (i = 0; i < uffd_desc->num_readers; ++i) { + int pipes[2]; - PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n", - hva, hva + len); + ret = pipe2((int *) &pipes, O_CLOEXEC | O_NONBLOCK); + TEST_ASSERT(!ret, "Failed to set up pipefd %i for uffd_desc %p", + i, uffd_desc); + + uffd_desc->pipefds[i] = pipes[1]; + + uffd_desc->reader_args[i].uffd_mode = uffd_mode; + uffd_desc->reader_args[i].uffd = uffd; + uffd_desc->reader_args[i].delay = delay; + uffd_desc->reader_args[i].handler = handler; + uffd_desc->reader_args[i].pipe = pipes[0]; + + pthread_create(&uffd_desc->readers[i], NULL, uffd_handler_thread_fn, + &uffd_desc->reader_args[i]); + + PER_VCPU_DEBUG("Created uffd thread %i for HVA range [%p, %p)\n", + i, hva, hva + len); + } return uffd_desc; } @@ -167,19 +180,26 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay, void uffd_stop_demand_paging(struct uffd_desc *uffd) { char c = 0; - int ret; + int i; - ret = write(uffd->pipefds[1], &c, 1); - TEST_ASSERT(ret == 1, "Unable to write to pipefd"); + for (i = 0; i < uffd->num_readers; ++i) + TEST_ASSERT(write(uffd->pipefds[i], &c, 1) == 1, + "Unable to write to pipefd %i for uffd_desc %p", i, uffd); - ret = pthread_join(uffd->thread, NULL); - TEST_ASSERT(ret == 0, "Pthread_join failed."); + for (i = 0; i < uffd->num_readers; ++i) + TEST_ASSERT(!pthread_join(uffd->readers[i], NULL), + "Pthread_join failed on reader %i for uffd_desc %p", i, uffd); close(uffd->uffd); - close(uffd->pipefds[1]); - close(uffd->pipefds[0]); + for (i = 0; i < uffd->num_readers; ++i) { + close(uffd->pipefds[i]); + close(uffd->reader_args[i].pipe); + } + free(uffd->pipefds); + free(uffd->readers); + free(uffd->reader_args); free(uffd); } diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 9f87ca8b7ab602..c664e446136bc6 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -15,14 +15,16 @@ #define NUM_INTERRUPTS 256 #endif -#define DEFAULT_CODE_SELECTOR 0x8 -#define DEFAULT_DATA_SELECTOR 0x10 +#define KERNEL_CS 0x8 +#define KERNEL_DS 0x10 +#define KERNEL_TSS 0x18 #define MAX_NR_CPUID_ENTRIES 100 vm_vaddr_t exception_handlers; bool host_cpu_is_amd; bool host_cpu_is_intel; +bool is_forced_emulation_enabled; static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { @@ -417,7 +419,7 @@ static void kvm_seg_set_unusable(struct kvm_segment *segp) static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) { - void *gdt = addr_gva2hva(vm, vm->gdt); + void *gdt = addr_gva2hva(vm, vm->arch.gdt); struct desc64 *desc = gdt + (segp->selector >> 3) * 8; desc->limit0 = segp->limit & 0xFFFF; @@ -437,27 +439,10 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) desc->base3 = segp->base >> 32; } - -/* - * Set Long Mode Flat Kernel Code Segment - * - * Input Args: - * vm - VM whose GDT is being filled, or NULL to only write segp - * selector - selector value - * - * Output Args: - * segp - Pointer to KVM segment - * - * Return: None - * - * Sets up the KVM segment pointed to by @segp, to be a code segment - * with the selector value given by @selector. - */ -static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector, - struct kvm_segment *segp) +static void kvm_seg_set_kernel_code_64bit(struct kvm_segment *segp) { memset(segp, 0, sizeof(*segp)); - segp->selector = selector; + segp->selector = KERNEL_CS; segp->limit = 0xFFFFFFFFu; segp->s = 0x1; /* kTypeCodeData */ segp->type = 0x08 | 0x01 | 0x02; /* kFlagCode | kFlagCodeAccessed @@ -466,30 +451,12 @@ static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector, segp->g = true; segp->l = true; segp->present = 1; - if (vm) - kvm_seg_fill_gdt_64bit(vm, segp); } -/* - * Set Long Mode Flat Kernel Data Segment - * - * Input Args: - * vm - VM whose GDT is being filled, or NULL to only write segp - * selector - selector value - * - * Output Args: - * segp - Pointer to KVM segment - * - * Return: None - * - * Sets up the KVM segment pointed to by @segp, to be a data segment - * with the selector value given by @selector. - */ -static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, - struct kvm_segment *segp) +static void kvm_seg_set_kernel_data_64bit(struct kvm_segment *segp) { memset(segp, 0, sizeof(*segp)); - segp->selector = selector; + segp->selector = KERNEL_DS; segp->limit = 0xFFFFFFFFu; segp->s = 0x1; /* kTypeCodeData */ segp->type = 0x00 | 0x01 | 0x02; /* kFlagData | kFlagDataAccessed @@ -497,8 +464,6 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector, */ segp->g = true; segp->present = true; - if (vm) - kvm_seg_fill_gdt_64bit(vm, segp); } vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) @@ -516,67 +481,147 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva) return vm_untag_gpa(vm, PTE_GET_PA(*pte)) | (gva & ~HUGEPAGE_MASK(level)); } -static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt) -{ - if (!vm->gdt) - vm->gdt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - - dt->base = vm->gdt; - dt->limit = getpagesize(); -} - -static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp, - int selector) +static void kvm_seg_set_tss_64bit(vm_vaddr_t base, struct kvm_segment *segp) { - if (!vm->tss) - vm->tss = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - memset(segp, 0, sizeof(*segp)); - segp->base = vm->tss; + segp->base = base; segp->limit = 0x67; - segp->selector = selector; + segp->selector = KERNEL_TSS; segp->type = 0xb; segp->present = 1; - kvm_seg_fill_gdt_64bit(vm, segp); } -static void vcpu_setup(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { struct kvm_sregs sregs; + TEST_ASSERT_EQ(vm->mode, VM_MODE_PXXV48_4K); + /* Set mode specific system register values. */ vcpu_sregs_get(vcpu, &sregs); - sregs.idt.limit = 0; + sregs.idt.base = vm->arch.idt; + sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1; + sregs.gdt.base = vm->arch.gdt; + sregs.gdt.limit = getpagesize() - 1; - kvm_setup_gdt(vm, &sregs.gdt); + sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG; + sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR; + sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX); - switch (vm->mode) { - case VM_MODE_PXXV48_4K: - sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG; - sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR; - sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX); + kvm_seg_set_unusable(&sregs.ldt); + kvm_seg_set_kernel_code_64bit(&sregs.cs); + kvm_seg_set_kernel_data_64bit(&sregs.ds); + kvm_seg_set_kernel_data_64bit(&sregs.es); + kvm_seg_set_kernel_data_64bit(&sregs.gs); + kvm_seg_set_tss_64bit(vm->arch.tss, &sregs.tr); - kvm_seg_set_unusable(&sregs.ldt); - kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs); - kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds); - kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es); - kvm_setup_tss_64bit(vm, &sregs.tr, 0x18); - break; + sregs.cr3 = vm->pgd; + vcpu_sregs_set(vcpu, &sregs); +} + +static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, + int dpl, unsigned short selector) +{ + struct idt_entry *base = + (struct idt_entry *)addr_gva2hva(vm, vm->arch.idt); + struct idt_entry *e = &base[vector]; + + memset(e, 0, sizeof(*e)); + e->offset0 = addr; + e->selector = selector; + e->ist = 0; + e->type = 14; + e->dpl = dpl; + e->p = 1; + e->offset1 = addr >> 16; + e->offset2 = addr >> 32; +} - default: - TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode); +static bool kvm_fixup_exception(struct ex_regs *regs) +{ + if (regs->r9 != KVM_EXCEPTION_MAGIC || regs->rip != regs->r10) + return false; + + if (regs->vector == DE_VECTOR) + return false; + + regs->rip = regs->r11; + regs->r9 = regs->vector; + regs->r10 = regs->error_code; + return true; +} + +void route_exception(struct ex_regs *regs) +{ + typedef void(*handler)(struct ex_regs *); + handler *handlers = (handler *)exception_handlers; + + if (handlers && handlers[regs->vector]) { + handlers[regs->vector](regs); + return; } - sregs.cr3 = vm->pgd; - vcpu_sregs_set(vcpu, &sregs); + if (kvm_fixup_exception(regs)) + return; + + ucall_assert(UCALL_UNHANDLED, + "Unhandled exception in guest", __FILE__, __LINE__, + "Unhandled exception '0x%lx' at guest RIP '0x%lx'", + regs->vector, regs->rip); +} + +static void vm_init_descriptor_tables(struct kvm_vm *vm) +{ + extern void *idt_handlers; + struct kvm_segment seg; + int i; + + vm->arch.gdt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); + vm->arch.idt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); + vm->handlers = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); + vm->arch.tss = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); + + /* Handlers have the same address in both address spaces.*/ + for (i = 0; i < NUM_INTERRUPTS; i++) + set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, KERNEL_CS); + + *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; + + kvm_seg_set_kernel_code_64bit(&seg); + kvm_seg_fill_gdt_64bit(vm, &seg); + + kvm_seg_set_kernel_data_64bit(&seg); + kvm_seg_fill_gdt_64bit(vm, &seg); + + kvm_seg_set_tss_64bit(vm->arch.tss, &seg); + kvm_seg_fill_gdt_64bit(vm, &seg); +} + +void vm_install_exception_handler(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)) +{ + vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers); + + handlers[vector] = (vm_vaddr_t)handler; +} + +void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) + REPORT_GUEST_ASSERT(uc); } void kvm_arch_vm_post_create(struct kvm_vm *vm) { vm_create_irqchip(vm); + vm_init_descriptor_tables(vm); + sync_global_to_guest(vm, host_cpu_is_intel); sync_global_to_guest(vm, host_cpu_is_amd); + sync_global_to_guest(vm, is_forced_emulation_enabled); if (vm->type == KVM_X86_SEV_VM || vm->type == KVM_X86_SEV_ES_VM) { struct kvm_sev_init init = { 0 }; @@ -622,7 +667,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) vcpu = __vm_vcpu_add(vm, vcpu_id); vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid()); - vcpu_setup(vm, vcpu); + vcpu_init_sregs(vm, vcpu); /* Setup guest general purpose registers */ vcpu_regs_get(vcpu, ®s); @@ -1091,102 +1136,6 @@ void kvm_init_vm_address_properties(struct kvm_vm *vm) } } -static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, - int dpl, unsigned short selector) -{ - struct idt_entry *base = - (struct idt_entry *)addr_gva2hva(vm, vm->idt); - struct idt_entry *e = &base[vector]; - - memset(e, 0, sizeof(*e)); - e->offset0 = addr; - e->selector = selector; - e->ist = 0; - e->type = 14; - e->dpl = dpl; - e->p = 1; - e->offset1 = addr >> 16; - e->offset2 = addr >> 32; -} - - -static bool kvm_fixup_exception(struct ex_regs *regs) -{ - if (regs->r9 != KVM_EXCEPTION_MAGIC || regs->rip != regs->r10) - return false; - - if (regs->vector == DE_VECTOR) - return false; - - regs->rip = regs->r11; - regs->r9 = regs->vector; - regs->r10 = regs->error_code; - return true; -} - -void route_exception(struct ex_regs *regs) -{ - typedef void(*handler)(struct ex_regs *); - handler *handlers = (handler *)exception_handlers; - - if (handlers && handlers[regs->vector]) { - handlers[regs->vector](regs); - return; - } - - if (kvm_fixup_exception(regs)) - return; - - ucall_assert(UCALL_UNHANDLED, - "Unhandled exception in guest", __FILE__, __LINE__, - "Unhandled exception '0x%lx' at guest RIP '0x%lx'", - regs->vector, regs->rip); -} - -void vm_init_descriptor_tables(struct kvm_vm *vm) -{ - extern void *idt_handlers; - int i; - - vm->idt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - vm->handlers = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA); - /* Handlers have the same address in both address spaces.*/ - for (i = 0; i < NUM_INTERRUPTS; i++) - set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, - DEFAULT_CODE_SELECTOR); -} - -void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu) -{ - struct kvm_vm *vm = vcpu->vm; - struct kvm_sregs sregs; - - vcpu_sregs_get(vcpu, &sregs); - sregs.idt.base = vm->idt; - sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1; - sregs.gdt.base = vm->gdt; - sregs.gdt.limit = getpagesize() - 1; - kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs); - vcpu_sregs_set(vcpu, &sregs); - *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; -} - -void vm_install_exception_handler(struct kvm_vm *vm, int vector, - void (*handler)(struct ex_regs *)) -{ - vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers); - - handlers[vector] = (vm_vaddr_t)handler; -} - -void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) -{ - struct ucall uc; - - if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) - REPORT_GUEST_ASSERT(uc); -} - const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid, uint32_t function, uint32_t index) { @@ -1348,6 +1297,7 @@ void kvm_selftest_arch_init(void) { host_cpu_is_intel = this_cpu_is_intel(); host_cpu_is_amd = this_cpu_is_amd(); + is_forced_emulation_enabled = kvm_is_forced_emulation_enabled(); } bool sys_clocksource_is_based_on_tsc(void) diff --git a/tools/testing/selftests/kvm/lib/x86_64/sev.c b/tools/testing/selftests/kvm/lib/x86_64/sev.c index d482029b600400..e9535ee20b7fcb 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/sev.c +++ b/tools/testing/selftests/kvm/lib/x86_64/sev.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0-only -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <stdint.h> #include <stdbool.h> diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c index 1a6da7389bf1f5..0b9678858b6d7d 100644 --- a/tools/testing/selftests/kvm/max_guest_memory_test.c +++ b/tools/testing/selftests/kvm/max_guest_memory_test.c @@ -1,6 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE - #include <stdio.h> #include <stdlib.h> #include <pthread.h> diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 1563619666123f..05fcf902e06710 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -6,9 +6,6 @@ * Copyright (C) 2018, Red Hat, Inc. * Copyright (C) 2020, Google, Inc. */ - -#define _GNU_SOURCE /* for program_invocation_name */ - #include <stdio.h> #include <stdlib.h> #include <sys/syscall.h> diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c index 735b7856902187..2c792228ac0bee 100644 --- a/tools/testing/selftests/kvm/riscv/arch_timer.c +++ b/tools/testing/selftests/kvm/riscv/arch_timer.c @@ -7,13 +7,11 @@ * * Copyright (c) 2024, Intel Corporation. */ - -#define _GNU_SOURCE - #include "arch_timer.h" #include "kvm_util.h" #include "processor.h" #include "timer_test.h" +#include "ucall_common.h" static int timer_irq = IRQ_S_TIMER; diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c index 28f97fb5204414..a44df60cf18936 100644 --- a/tools/testing/selftests/kvm/rseq_test.c +++ b/tools/testing/selftests/kvm/rseq_test.c @@ -1,5 +1,13 @@ // SPDX-License-Identifier: GPL-2.0-only -#define _GNU_SOURCE /* for program_invocation_short_name */ + +/* + * Include rseq.c without _GNU_SOURCE defined, before including any headers, so + * that rseq.c is compiled with its configuration, not KVM selftests' config. + */ +#undef _GNU_SOURCE +#include "../rseq/rseq.c" +#define _GNU_SOURCE + #include <errno.h> #include <fcntl.h> #include <pthread.h> @@ -19,8 +27,7 @@ #include "kvm_util.h" #include "processor.h" #include "test_util.h" - -#include "../rseq/rseq.c" +#include "ucall_common.h" /* * Any bug related to task migration is likely to be timing-dependent; perform diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c index 626a2b8a203724..b3903384475682 100644 --- a/tools/testing/selftests/kvm/s390x/cmma_test.c +++ b/tools/testing/selftests/kvm/s390x/cmma_test.c @@ -7,8 +7,6 @@ * Authors: * Nico Boehr <nrb@linux.ibm.com> */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> @@ -18,6 +16,7 @@ #include "test_util.h" #include "kvm_util.h" #include "kselftest.h" +#include "ucall_common.h" #define MAIN_PAGE_COUNT 512 diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index 48cb910e660de0..f2df7416be8474 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -15,6 +15,7 @@ #include "test_util.h" #include "kvm_util.h" #include "kselftest.h" +#include "ucall_common.h" enum mop_target { LOGICAL, diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c index 43fb25ddc3eca3..53def355ccba4c 100644 --- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c +++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c @@ -10,8 +10,6 @@ * * Test expected behavior of the KVM_CAP_SYNC_REGS functionality. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c index c73f948c9b6379..7a742a673b7c90 100644 --- a/tools/testing/selftests/kvm/s390x/tprot.c +++ b/tools/testing/selftests/kvm/s390x/tprot.c @@ -8,6 +8,7 @@ #include "test_util.h" #include "kvm_util.h" #include "kselftest.h" +#include "ucall_common.h" #define PAGE_SHIFT 12 #define PAGE_SIZE (1 << PAGE_SHIFT) diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 68c899d27561d8..bb8002084f52e9 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <pthread.h> #include <sched.h> @@ -221,8 +220,20 @@ static void test_move_memory_region(void) static void guest_code_delete_memory_region(void) { + struct desc_ptr idt; uint64_t val; + /* + * Clobber the IDT so that a #PF due to the memory region being deleted + * escalates to triple-fault shutdown. Because the memory region is + * deleted, there will be no valid mappings. As a result, KVM will + * repeatedly intercepts the state-2 page fault that occurs when trying + * to vector the guest's #PF. I.e. trying to actually handle the #PF + * in the guest will never succeed, and so isn't an option. + */ + memset(&idt, 0, sizeof(idt)); + __asm__ __volatile__("lidt %0" :: "m"(idt)); + GUEST_SYNC(0); /* Spin until the memory region is deleted. */ diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 2ff82c7fd92659..a8d3afa0b86b23 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -4,7 +4,6 @@ * * Copyright (C) 2020, Red Hat, Inc. */ -#define _GNU_SOURCE #include <stdio.h> #include <time.h> #include <sched.h> @@ -20,6 +19,7 @@ #include "test_util.h" #include "kvm_util.h" #include "processor.h" +#include "ucall_common.h" #define NR_VCPUS 4 #define ST_GPA_BASE (1 << 30) @@ -85,20 +85,18 @@ static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) { struct kvm_steal_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]); - int i; - pr_info("VCPU%d:\n", vcpu_idx); - pr_info(" steal: %lld\n", st->steal); - pr_info(" version: %d\n", st->version); - pr_info(" flags: %d\n", st->flags); - pr_info(" preempted: %d\n", st->preempted); - pr_info(" u8_pad: "); - for (i = 0; i < 3; ++i) - pr_info("%d", st->u8_pad[i]); - pr_info("\n pad: "); - for (i = 0; i < 11; ++i) - pr_info("%d", st->pad[i]); - pr_info("\n"); + ksft_print_msg("VCPU%d:\n", vcpu_idx); + ksft_print_msg(" steal: %lld\n", st->steal); + ksft_print_msg(" version: %d\n", st->version); + ksft_print_msg(" flags: %d\n", st->flags); + ksft_print_msg(" preempted: %d\n", st->preempted); + ksft_print_msg(" u8_pad: %d %d %d\n", + st->u8_pad[0], st->u8_pad[1], st->u8_pad[2]); + ksft_print_msg(" pad: %d %d %d %d %d %d %d %d %d %d %d\n", + st->pad[0], st->pad[1], st->pad[2], st->pad[3], + st->pad[4], st->pad[5], st->pad[6], st->pad[7], + st->pad[8], st->pad[9], st->pad[10]); } #elif defined(__aarch64__) @@ -201,10 +199,10 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) { struct st_time *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]); - pr_info("VCPU%d:\n", vcpu_idx); - pr_info(" rev: %d\n", st->rev); - pr_info(" attr: %d\n", st->attr); - pr_info(" st_time: %ld\n", st->st_time); + ksft_print_msg("VCPU%d:\n", vcpu_idx); + ksft_print_msg(" rev: %d\n", st->rev); + ksft_print_msg(" attr: %d\n", st->attr); + ksft_print_msg(" st_time: %ld\n", st->st_time); } #elif defined(__riscv) @@ -368,7 +366,9 @@ int main(int ac, char **av) vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0); virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, gpages); + ksft_print_header(); TEST_REQUIRE(is_steal_time_supported(vcpus[0])); + ksft_set_plan(NR_VCPUS); /* Run test on each VCPU */ for (i = 0; i < NR_VCPUS; ++i) { @@ -409,14 +409,15 @@ int main(int ac, char **av) run_delay, stolen_time); if (verbose) { - pr_info("VCPU%d: total-stolen-time=%ld test-stolen-time=%ld", i, - guest_stolen_time[i], stolen_time); - if (stolen_time == run_delay) - pr_info(" (BONUS: guest test-stolen-time even exactly matches test-run_delay)"); - pr_info("\n"); + ksft_print_msg("VCPU%d: total-stolen-time=%ld test-stolen-time=%ld%s\n", + i, guest_stolen_time[i], stolen_time, + stolen_time == run_delay ? + " (BONUS: guest test-stolen-time even exactly matches test-run_delay)" : ""); steal_time_dump(vm, i); } + ksft_test_result_pass("vcpu%d\n", i); } - return 0; + /* Print results and exit() accordingly */ + ksft_finished(); } diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index eae521f050e09f..903940c54d2dec 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -6,8 +6,6 @@ * * Tests for amx #NM exception and save/restore. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> @@ -246,8 +244,6 @@ int main(int argc, char *argv[]) vcpu_regs_get(vcpu, ®s1); /* Register #NM handler */ - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler); /* amx cfg for guest_code */ diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c index ee3b384b991c8b..2929c067c20782 100644 --- a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c +++ b/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c @@ -17,6 +17,7 @@ #include "test_util.h" #include "memstress.h" #include "guest_modes.h" +#include "ucall_common.h" #define VCPUS 2 #define SLOTS 2 diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c index 6c2e5e0ceb1f7d..81055476d39426 100644 --- a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c +++ b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c @@ -4,12 +4,9 @@ * * Test for KVM_CAP_EXIT_ON_EMULATION_FAILURE. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ - #include "flds_emulation.h" - #include "test_util.h" +#include "ucall_common.h" #define MMIO_GPA 0x700000000 #define MMIO_GVA MMIO_GPA diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c index f3c2239228b10e..762628f7d4ba38 100644 --- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c @@ -110,8 +110,6 @@ static void test_fix_hypercall(struct kvm_vcpu *vcpu, bool disable_quirk) { struct kvm_vm *vm = vcpu->vm; - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vcpu->vm, UD_VECTOR, guest_ud_handler); if (disable_quirk) diff --git a/tools/testing/selftests/kvm/x86_64/hwcr_msr_test.c b/tools/testing/selftests/kvm/x86_64/hwcr_msr_test.c index df351ae1702977..10b1b0ba374e66 100644 --- a/tools/testing/selftests/kvm/x86_64/hwcr_msr_test.c +++ b/tools/testing/selftests/kvm/x86_64/hwcr_msr_test.c @@ -2,8 +2,6 @@ /* * Copyright (C) 2023, Google LLC. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <sys/ioctl.h> #include "test_util.h" diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c index 5c27efbf405e1f..4f5881d4ef66d3 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c @@ -7,8 +7,6 @@ * This work is licensed under the terms of the GNU GPL, version 2. * */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c index 4c7257ecd2a68c..e192720bfe14b4 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c @@ -4,7 +4,6 @@ * * Tests for Enlightened VMCS, including nested guest state. */ -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> @@ -258,8 +257,6 @@ int main(int argc, char *argv[]) vcpu_args_set(vcpu, 3, vmx_pages_gva, hv_pages_gva, addr_gva2gpa(vm, hcall_page)); vcpu_set_msr(vcpu, HV_X64_MSR_VP_INDEX, vcpu->id); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); vm_install_exception_handler(vm, NMI_VECTOR, guest_nmi_handler); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index b923a285e96f94..068e9c69710d2e 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -156,9 +156,6 @@ static void guest_test_msrs_access(void) vcpu_init_cpuid(vcpu, prev_cpuid); } - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - /* TODO: Make this entire test easier to maintain. */ if (stage >= 21) vcpu_enable_cap(vcpu, KVM_CAP_HYPERV_SYNIC2, 0); @@ -532,9 +529,6 @@ static void guest_test_hcalls_access(void) while (true) { vm = vm_create_with_one_vcpu(&vcpu, guest_hcall); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - /* Hypercall input/output */ hcall_page = vm_vaddr_alloc_pages(vm, 2); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c index f1617762c22fec..22c0c124582fd8 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c @@ -5,8 +5,6 @@ * Copyright (C) 2022, Red Hat, Inc. * */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <pthread.h> #include <inttypes.h> @@ -256,16 +254,13 @@ int main(int argc, char *argv[]) hcall_page = vm_vaddr_alloc_pages(vm, 2); memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize()); - vm_init_descriptor_tables(vm); vcpu[1] = vm_vcpu_add(vm, RECEIVER_VCPU_ID_1, receiver_code); - vcpu_init_descriptor_tables(vcpu[1]); vcpu_args_set(vcpu[1], 2, hcall_page, addr_gva2gpa(vm, hcall_page)); vcpu_set_msr(vcpu[1], HV_X64_MSR_VP_INDEX, RECEIVER_VCPU_ID_1); vcpu_set_hv_cpuid(vcpu[1]); vcpu[2] = vm_vcpu_add(vm, RECEIVER_VCPU_ID_2, receiver_code); - vcpu_init_descriptor_tables(vcpu[2]); vcpu_args_set(vcpu[2], 2, hcall_page, addr_gva2gpa(vm, hcall_page)); vcpu_set_msr(vcpu[2], HV_X64_MSR_VP_INDEX, RECEIVER_VCPU_ID_2); vcpu_set_hv_cpuid(vcpu[2]); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c index c9b18707edc031..b987a3d7971537 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -4,7 +4,6 @@ * * Tests for Hyper-V extensions to SVM. */ -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c index 05b56095cf76f6..077cd0ec3040e9 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c @@ -5,8 +5,6 @@ * Copyright (C) 2022, Red Hat, Inc. * */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <asm/barrier.h> #include <pthread.h> #include <inttypes.h> diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c index 40cc59f4e65013..78878b3a272522 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -183,9 +183,6 @@ int main(void) vcpu_clear_cpuid_entry(vcpu, KVM_CPUID_FEATURES); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - enter_guest(vcpu); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c index 853802641e1eaf..2b550eff35f1b3 100644 --- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c @@ -75,14 +75,12 @@ int main(int argc, char *argv[]) struct ucall uc; int testcase; + TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_MWAIT); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - while (1) { vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c index 3670331adf21ad..3eb0313ffa397a 100644 --- a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c +++ b/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c @@ -1,6 +1,4 @@ // SPDX-License-Identifier: GPL-2.0-only -#define _GNU_SOURCE /* for program_invocation_short_name */ - #include "test_util.h" #include "kvm_util.h" #include "processor.h" diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c index 17bbb96fc4dfcb..e7efb2b35f8bdc 100644 --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c @@ -5,9 +5,6 @@ * * Copyright (C) 2022, Google LLC. */ - -#define _GNU_SOURCE - #include <fcntl.h> #include <stdint.h> #include <time.h> diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh index 7cbb409801eea7..caad084b8bfdb6 100755 --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh @@ -13,10 +13,21 @@ NX_HUGE_PAGES_RECOVERY_RATIO=$(cat /sys/module/kvm/parameters/nx_huge_pages_reco NX_HUGE_PAGES_RECOVERY_PERIOD=$(cat /sys/module/kvm/parameters/nx_huge_pages_recovery_period_ms) HUGE_PAGES=$(cat /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages) +# If we're already root, the host might not have sudo. +if [ $(whoami) == "root" ]; then + function do_sudo () { + "$@" + } +else + function do_sudo () { + sudo "$@" + } +fi + set +e function sudo_echo () { - echo "$1" | sudo tee -a "$2" > /dev/null + echo "$1" | do_sudo tee -a "$2" > /dev/null } NXECUTABLE="$(dirname $0)/nx_huge_pages_test" diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c index 87011965dc4166..eda88080c1868f 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c @@ -9,8 +9,6 @@ * Verifies expected behavior of controlling guest access to * MSR_PLATFORM_INFO. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> @@ -26,36 +24,18 @@ static void guest_code(void) { uint64_t msr_platform_info; + uint8_t vector; - for (;;) { - msr_platform_info = rdmsr(MSR_PLATFORM_INFO); - GUEST_SYNC(msr_platform_info); - asm volatile ("inc %r11"); - } -} - -static void test_msr_platform_info_enabled(struct kvm_vcpu *vcpu) -{ - struct ucall uc; - - vm_enable_cap(vcpu->vm, KVM_CAP_MSR_PLATFORM_INFO, true); - vcpu_run(vcpu); - TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + GUEST_SYNC(true); + msr_platform_info = rdmsr(MSR_PLATFORM_INFO); + GUEST_ASSERT_EQ(msr_platform_info & MSR_PLATFORM_INFO_MAX_TURBO_RATIO, + MSR_PLATFORM_INFO_MAX_TURBO_RATIO); - get_ucall(vcpu, &uc); - TEST_ASSERT(uc.cmd == UCALL_SYNC, - "Received ucall other than UCALL_SYNC: %lu", uc.cmd); - TEST_ASSERT((uc.args[1] & MSR_PLATFORM_INFO_MAX_TURBO_RATIO) == - MSR_PLATFORM_INFO_MAX_TURBO_RATIO, - "Expected MSR_PLATFORM_INFO to have max turbo ratio mask: %i.", - MSR_PLATFORM_INFO_MAX_TURBO_RATIO); -} + GUEST_SYNC(false); + vector = rdmsr_safe(MSR_PLATFORM_INFO, &msr_platform_info); + GUEST_ASSERT_EQ(vector, GP_VECTOR); -static void test_msr_platform_info_disabled(struct kvm_vcpu *vcpu) -{ - vm_enable_cap(vcpu->vm, KVM_CAP_MSR_PLATFORM_INFO, false); - vcpu_run(vcpu); - TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); + GUEST_DONE(); } int main(int argc, char *argv[]) @@ -63,6 +43,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; uint64_t msr_platform_info; + struct ucall uc; TEST_REQUIRE(kvm_has_cap(KVM_CAP_MSR_PLATFORM_INFO)); @@ -71,8 +52,26 @@ int main(int argc, char *argv[]) msr_platform_info = vcpu_get_msr(vcpu, MSR_PLATFORM_INFO); vcpu_set_msr(vcpu, MSR_PLATFORM_INFO, msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO); - test_msr_platform_info_enabled(vcpu); - test_msr_platform_info_disabled(vcpu); + + for (;;) { + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + vm_enable_cap(vm, KVM_CAP_MSR_PLATFORM_INFO, uc.args[1]); + break; + case UCALL_DONE: + goto done; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_FAIL("Unexpected ucall %lu", uc.cmd); + break; + } + } + +done: vcpu_set_msr(vcpu, MSR_PLATFORM_INFO, msr_platform_info); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c index 26c85815f7e983..96446134c00b7d 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c @@ -2,8 +2,6 @@ /* * Copyright (C) 2023, Tencent, Inc. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <x86intrin.h> #include "pmu.h" @@ -21,7 +19,6 @@ static uint8_t kvm_pmu_version; static bool kvm_has_perf_caps; -static bool is_forced_emulation_enabled; static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, void *guest_code, @@ -31,11 +28,7 @@ static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, struct kvm_vm *vm; vm = vm_create_with_one_vcpu(vcpu, guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(*vcpu); - sync_global_to_guest(vm, kvm_pmu_version); - sync_global_to_guest(vm, is_forced_emulation_enabled); /* * Set PERF_CAPABILITIES before PMU version as KVM disallows enabling @@ -630,7 +623,6 @@ int main(int argc, char *argv[]) kvm_pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION); kvm_has_perf_caps = kvm_cpu_has(X86_FEATURE_PDCM); - is_forced_emulation_enabled = kvm_is_forced_emulation_enabled(); test_intel_counters(); diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 3c85d1ae989366..26b3e7efe5ddc7 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -9,9 +9,6 @@ * Verifies the expected behavior of allow lists and deny lists for * virtual PMU events. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ - #include "kvm_util.h" #include "pmu.h" #include "processor.h" @@ -337,9 +334,6 @@ static void test_pmu_config_disable(void (*guest_code)(void)) vm_enable_cap(vm, KVM_CAP_PMU_CAPABILITY, KVM_PMU_CAP_DISABLE); vcpu = vm_vcpu_add(vm, 0, guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - TEST_ASSERT(!sanity_check_pmu(vcpu), "Guest should not be able to use disabled PMU."); @@ -876,9 +870,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - TEST_REQUIRE(sanity_check_pmu(vcpu)); if (use_amd_pmu()) diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c index e0f642d2a3c4b5..82a8d88b5338e3 100644 --- a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c +++ b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c @@ -2,7 +2,6 @@ /* * Copyright (C) 2022, Google LLC. */ -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <limits.h> #include <pthread.h> diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c index 366cf18600bc7e..d691d86e5bc33a 100644 --- a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c +++ b/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c @@ -4,7 +4,6 @@ * * Copyright (C) 2020, Red Hat, Inc. */ -#define _GNU_SOURCE /* for program_invocation_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c index 3610981d9162bb..c021c0795a9666 100644 --- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c @@ -10,7 +10,6 @@ * That bug allowed a user-mode program that called the KVM_SET_SREGS * ioctl to put a VCPU's local APIC into an invalid state. */ -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c index 416207c38a17ea..fabeeaddfb3acf 100644 --- a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c +++ b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c @@ -5,9 +5,6 @@ * Test that KVM emulates instructions in response to EPT violations when * allow_smaller_maxphyaddr is enabled and guest.MAXPHYADDR < host.MAXPHYADDR. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ - #include "flds_emulation.h" #include "test_util.h" @@ -60,9 +57,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); vcpu_args_set(vcpu, 1, kvm_is_tdp_enabled()); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vcpu_set_cpuid_property(vcpu, X86_PROPERTY_MAX_PHY_ADDR, MAXPHYADDR); rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE); diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index e18b86666e1fc2..55c88d664a9456 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -4,7 +4,6 @@ * * Tests for SMM. */ -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 88b58aab720773..1c756db329e575 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -6,7 +6,6 @@ * * Tests for vCPU state save/restore, including nested guest state. */ -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c index 32bef39bec2178..916e04248fbbdd 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -93,9 +93,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vm_install_exception_handler(vm, VINTR_IRQ_NUMBER, vintr_irq_handler); vm_install_exception_handler(vm, INTR_IRQ_NUMBER, intr_irq_handler); diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c index d6fcdcc3af3144..00135cbba35eac 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c @@ -48,12 +48,9 @@ int main(int argc, char *argv[]) TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vcpu_alloc_svm(vm, &svm_gva); - vcpu_args_set(vcpu, 2, svm_gva, vm->idt); + vcpu_args_set(vcpu, 2, svm_gva, vm->arch.idt); vcpu_run(vcpu); TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_SHUTDOWN); diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c index 0c7ce3d4e83a6f..7b6481d6c0d3db 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c @@ -152,9 +152,6 @@ static void run_test(bool is_nmi) vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vm_install_exception_handler(vm, NMI_VECTOR, guest_nmi_handler); vm_install_exception_handler(vm, BP_VECTOR, guest_bp_handler); vm_install_exception_handler(vm, INT_NR, guest_int_handler); @@ -166,7 +163,7 @@ static void run_test(bool is_nmi) idt_alt_vm = vm_vaddr_alloc_page(vm); idt_alt = addr_gva2hva(vm, idt_alt_vm); - idt = addr_gva2hva(vm, vm->idt); + idt = addr_gva2hva(vm, vm->arch.idt); memcpy(idt_alt, idt, getpagesize()); } else { idt_alt_vm = 0; diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c index adb5593daf483e..8fa3948b0170e1 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c @@ -8,8 +8,6 @@ * including requesting an invalid register set, updates to/from values * in kvm_run.s.regs when kvm_valid_regs and kvm_dirty_regs are toggled. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c index dcbb3c29fb8e9f..57f157c06b393c 100644 --- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c +++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c @@ -17,14 +17,11 @@ * delivered into the guest or not. * */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <pthread.h> #include <inttypes.h> #include <string.h> #include <time.h> -#include "kvm_util_base.h" #include "kvm_util.h" #include "mce.h" #include "processor.h" @@ -285,10 +282,6 @@ int main(int argc, char *argv[]) cmcidis_vcpu = create_vcpu_with_mce_cap(vm, 1, false, cmci_disabled_guest_code); cmci_vcpu = create_vcpu_with_mce_cap(vm, 2, true, cmci_enabled_guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(ucna_vcpu); - vcpu_init_descriptor_tables(cmcidis_vcpu); - vcpu_init_descriptor_tables(cmci_vcpu); vm_install_exception_handler(vm, CMCI_VECTOR, guest_cmci_handler); vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c index f4f61a2d2464c1..32b2794b78fece 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c @@ -4,8 +4,6 @@ * * Tests for exiting into userspace on registered MSRs */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <sys/ioctl.h> #include "kvm_test_harness.h" @@ -13,8 +11,6 @@ #include "kvm_util.h" #include "vmx.h" -static bool fep_available; - #define MSR_NON_EXISTENT 0x474f4f00 static u64 deny_bits = 0; @@ -258,7 +254,7 @@ static void guest_code_filter_allow(void) GUEST_ASSERT(data == 2); GUEST_ASSERT(guest_exception_count == 0); - if (fep_available) { + if (is_forced_emulation_enabled) { /* Let userspace know we aren't done. */ GUEST_SYNC(0); @@ -520,8 +516,6 @@ KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow) uint64_t cmd; int rc; - sync_global_to_guest(vm, fep_available); - rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR); TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available"); vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_FILTER); @@ -531,9 +525,6 @@ KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow) vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_allow); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler); /* Process guest code userspace exits. */ @@ -551,7 +542,7 @@ KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow) vcpu_run(vcpu); cmd = process_ucall(vcpu); - if (fep_available) { + if (is_forced_emulation_enabled) { TEST_ASSERT_EQ(cmd, UCALL_SYNC); vm_install_exception_handler(vm, GP_VECTOR, guest_fep_gp_handler); @@ -774,7 +765,5 @@ KVM_ONE_VCPU_TEST(user_msr, user_exit_msr_flags, NULL) int main(int argc, char *argv[]) { - fep_available = kvm_is_forced_emulation_enabled(); - return test_harness_run(argc, argv); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c index 977948fd52e6b8..fa512d033205fa 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c @@ -4,9 +4,6 @@ * * Copyright (C) 2018, Red Hat, Inc. */ - -#define _GNU_SOURCE /* for program_invocation_name */ - #include <stdio.h> #include <stdlib.h> #include <linux/bitmap.h> diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c index fad3634fd9eb62..3fd6eceab46f5d 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c @@ -115,9 +115,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); get_set_sigalrm_vcpu(vcpu); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler); /* diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index ea0cb3cae0f759..7c92536551cca1 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -10,7 +10,6 @@ * and check it can be retrieved with KVM_GET_MSR, also test * the invalid LBR formats are rejected. */ -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <sys/ioctl.h> #include <linux/bitmap.h> @@ -86,9 +85,6 @@ KVM_ONE_VCPU_TEST(vmx_pmu_caps, guest_wrmsr_perf_capabilities, guest_code) struct ucall uc; int r, i; - vm_init_descriptor_tables(vcpu->vm); - vcpu_init_descriptor_tables(vcpu); - vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities); vcpu_args_set(vcpu, 1, host_cap.capabilities); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c index affc3280015841..00dd2ac07a61e7 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c @@ -9,7 +9,6 @@ * value instead of partially decayed timer value * */ -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c index 725c206ba0b92b..a76078a08ff82f 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c @@ -19,8 +19,6 @@ * Migration is a command line option. When used on non-numa machines will * exit with error. Test is still usefull on non-numa for testing IPIs. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <getopt.h> #include <pthread.h> #include <inttypes.h> @@ -410,8 +408,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(¶ms[0].vcpu, halter_guest_code); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(params[0].vcpu); vm_install_exception_handler(vm, IPI_VECTOR, guest_ipi_handler); virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA); diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c index ab75b873a4ad8e..69849acd95b0af 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: GPL-2.0-only -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <fcntl.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c index 25a0b0db5c3c9d..95ce192d075309 100644 --- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c @@ -109,9 +109,6 @@ int main(int argc, char *argv[]) vm = vm_create_with_one_vcpu(&vcpu, guest_code); run = vcpu->run; - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); - while (1) { vcpu_run(vcpu); diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index d2ea0435f4f763..a59b3c799bb273 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -125,7 +125,7 @@ struct compat_vcpu_runstate_info { uint32_t state; uint64_t state_entry_time; uint64_t time[5]; -} __attribute__((__packed__));; +} __attribute__((__packed__)); struct arch_vcpu_info { unsigned long cr2; @@ -171,8 +171,9 @@ static volatile bool guest_saw_irq; static void evtchn_handler(struct ex_regs *regs) { struct vcpu_info *vi = (void *)VCPU_INFO_VADDR; - vi->evtchn_upcall_pending = 0; - vi->evtchn_pending_sel = 0; + + vcpu_arch_put_guest(vi->evtchn_upcall_pending, 0); + vcpu_arch_put_guest(vi->evtchn_pending_sel, 0); guest_saw_irq = true; GUEST_SYNC(TEST_GUEST_SAW_IRQ); @@ -380,20 +381,6 @@ wait_for_timer: GUEST_SYNC(TEST_DONE); } -static int cmp_timespec(struct timespec *a, struct timespec *b) -{ - if (a->tv_sec > b->tv_sec) - return 1; - else if (a->tv_sec < b->tv_sec) - return -1; - else if (a->tv_nsec > b->tv_nsec) - return 1; - else if (a->tv_nsec < b->tv_nsec) - return -1; - else - return 0; -} - static struct shared_info *shinfo; static struct vcpu_info *vinfo; static struct kvm_vcpu *vcpu; @@ -449,7 +436,6 @@ static void *juggle_shinfo_state(void *arg) int main(int argc, char *argv[]) { - struct timespec min_ts, max_ts, vm_ts; struct kvm_xen_hvm_attr evt_reset; struct kvm_vm *vm; pthread_t thread; @@ -468,8 +454,6 @@ int main(int argc, char *argv[]) bool do_evtchn_tests = do_eventfd_tests && !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_SEND); bool has_shinfo_hva = !!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA); - clock_gettime(CLOCK_REALTIME, &min_ts); - vm = vm_create_with_one_vcpu(&vcpu, guest_code); /* Map a region for the shared_info page */ @@ -553,8 +537,6 @@ int main(int argc, char *argv[]) }; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec); - vm_init_descriptor_tables(vm); - vcpu_init_descriptor_tables(vcpu); vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler); if (do_runstate_tests) { @@ -1010,7 +992,6 @@ int main(int argc, char *argv[]) vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset); alarm(0); - clock_gettime(CLOCK_REALTIME, &max_ts); /* * Just a *really* basic check that things are being put in the @@ -1019,6 +1000,8 @@ int main(int argc, char *argv[]) */ struct pvclock_wall_clock *wc; struct pvclock_vcpu_time_info *ti, *ti2; + struct kvm_clock_data kcdata; + long long delta; wc = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0xc00); ti = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20); @@ -1034,12 +1017,34 @@ int main(int argc, char *argv[]) ti2->tsc_shift, ti2->flags); } - vm_ts.tv_sec = wc->sec; - vm_ts.tv_nsec = wc->nsec; TEST_ASSERT(wc->version && !(wc->version & 1), "Bad wallclock version %x", wc->version); - TEST_ASSERT(cmp_timespec(&min_ts, &vm_ts) <= 0, "VM time too old"); - TEST_ASSERT(cmp_timespec(&max_ts, &vm_ts) >= 0, "VM time too new"); + + vm_ioctl(vm, KVM_GET_CLOCK, &kcdata); + + if (kcdata.flags & KVM_CLOCK_REALTIME) { + if (verbose) { + printf("KVM_GET_CLOCK clock: %lld.%09lld\n", + kcdata.clock / NSEC_PER_SEC, kcdata.clock % NSEC_PER_SEC); + printf("KVM_GET_CLOCK realtime: %lld.%09lld\n", + kcdata.realtime / NSEC_PER_SEC, kcdata.realtime % NSEC_PER_SEC); + } + + delta = (wc->sec * NSEC_PER_SEC + wc->nsec) - (kcdata.realtime - kcdata.clock); + + /* + * KVM_GET_CLOCK gives CLOCK_REALTIME which jumps on leap seconds updates but + * unfortunately KVM doesn't currently offer a CLOCK_TAI alternative. Accept 1s + * delta as testing clock accuracy is not the goal here. The test just needs to + * check that the value in shinfo is somewhat sane. + */ + TEST_ASSERT(llabs(delta) < NSEC_PER_SEC, + "Guest's epoch from shinfo %d.%09d differs from KVM_GET_CLOCK %lld.%lld", + wc->sec, wc->nsec, (kcdata.realtime - kcdata.clock) / NSEC_PER_SEC, + (kcdata.realtime - kcdata.clock) % NSEC_PER_SEC); + } else { + pr_info("Missing KVM_CLOCK_REALTIME, skipping shinfo epoch sanity check\n"); + } TEST_ASSERT(ti->version && !(ti->version & 1), "Bad time_info version %x", ti->version); diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c index 167c97abff1b81..f331a4e9bae3b4 100644 --- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c +++ b/tools/testing/selftests/kvm/x86_64/xss_msr_test.c @@ -4,8 +4,6 @@ * * Tests for the IA32_XSS MSR. */ - -#define _GNU_SOURCE /* for program_invocation_short_name */ #include <sys/ioctl.h> #include "test_util.h" diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ceab74b8ff5bf0..3508a9037d6435 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -971,7 +971,7 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) if (!memslot->dirty_bitmap) return; - kvfree(memslot->dirty_bitmap); + vfree(memslot->dirty_bitmap); memslot->dirty_bitmap = NULL; } @@ -2920,7 +2920,7 @@ out: /* * Pin guest page in memory and return its pfn. * @addr: host virtual address which maps memory to the guest - * @atomic: whether this function can sleep + * @atomic: whether this function is forbidden from sleeping * @interruptible: whether the process can be interrupted by non-fatal signals * @async: whether this function need to wait IO complete if the * host page is not in the memory @@ -2992,16 +2992,12 @@ kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, if (hva) *hva = addr; - if (addr == KVM_HVA_ERR_RO_BAD) { - if (writable) - *writable = false; - return KVM_PFN_ERR_RO_FAULT; - } - if (kvm_is_error_hva(addr)) { if (writable) *writable = false; - return KVM_PFN_NOSLOT; + + return addr == KVM_HVA_ERR_RO_BAD ? KVM_PFN_ERR_RO_FAULT : + KVM_PFN_NOSLOT; } /* Do not map writable pfn in the readonly memslot. */ @@ -3265,6 +3261,7 @@ static int next_segment(unsigned long len, int offset) return len; } +/* Copy @len bytes from guest memory at '(@gfn * PAGE_SIZE) + @offset' to @data */ static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn, void *data, int offset, int len) { @@ -3366,6 +3363,7 @@ int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic); +/* Copy @len bytes from @data into guest memory at '(@gfn * PAGE_SIZE) + @offset' */ static int __kvm_write_guest_page(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn, const void *data, int offset, int len) |