Until now, the members of struct guest_fault are always accessed while holding the required locks, and thus the ptep and crstep pointers can be dereferenced safely. There will be some new cases where callers of kvm_s390_faultin_gfn() need to know the size of the page used to solve the fault, at which point no locks are held anymore, and dereferencing the crstep field is not possible. Introduce a new crste_region3 flag for struct guest_fault to indicate whether the crstep used to solve the fault was a region 3 entry with FC=1 (large pud). This allows to disambiguate all three possible scenarios: * If ptep is not NULL, the fault was solved with a pte. * If ptep is NULL and crste_region3 is 0, a segment entry with FC=1 (large pmd) was used. * If ptep is NULL and crste_region3 is 1, a region 3 entry with FC=1 (large pud) was used. Signed-off-by: Claudio Imbrenda --- arch/s390/kvm/dat.h | 1 + arch/s390/kvm/gmap.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h index 8f8278c44879..5d848e74e382 100644 --- a/arch/s390/kvm/dat.h +++ b/arch/s390/kvm/dat.h @@ -500,6 +500,7 @@ struct guest_fault { bool write_attempt; /* Write access attempted */ bool attempt_pfault; /* Attempt a pfault first */ bool valid; /* This entry contains valid data */ + bool crste_region3; /* Whether crstep refers to a region3 entry */ void (*callback)(struct guest_fault *f); void *priv; }; diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c index 3c26e35af0ef..fe138d17caaf 100644 --- a/arch/s390/kvm/gmap.c +++ b/arch/s390/kvm/gmap.c @@ -531,6 +531,7 @@ static int gmap_handle_minor_crste_fault(struct gmap *gmap, struct guest_fault * f->pfn = PHYS_PFN(large_crste_to_phys(oldcrste, f->gfn)); f->writable = oldcrste.s.fc1.w; + f->crste_region3 = is_pud(oldcrste); /* Appropriate permissions already (race with another handler), nothing to do. */ if (!oldcrste.h.i && !(f->write_attempt && oldcrste.h.p)) return 0; @@ -690,6 +691,7 @@ static int _gmap_link(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, int leve if (oldval.val != _CRSTE_EMPTY(oldval.h.tt).val && crste_origin_large(oldval) != crste_origin_large(newval)) return -EAGAIN; + f->crste_region3 = is_pud(newval); } while (!gmap_crstep_xchg_atomic(gmap, f->crstep, oldval, newval, f->gfn)); if (f->callback) f->callback(f); -- 2.54.0 Implement and enable the KVM_PRE_FAULT_MEMORY ioctl for s390. Faulted-in pages will be marked as accessed, unlike x86, otherwise they will trigger a minor fault when accessed. Avoiding such faults is one of the points of KVM_PRE_FAULT_MEMORY. Signed-off-by: Claudio Imbrenda --- arch/s390/kvm/Kconfig | 1 + arch/s390/kvm/kvm-s390.c | 45 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+) diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 5b835bc6a194..8d3ee17a1bcb 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -30,6 +30,7 @@ config KVM select KVM_VFIO select VIRT_XFER_TO_GUEST_WORK select KVM_MMU_LOCKLESS_AGING + select KVM_GENERIC_PRE_FAULT_MEMORY help Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index e09960c2e6ed..f6521f16532a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -630,6 +630,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_USER_OPEREXEC: case KVM_CAP_S390_KEYOP: case KVM_CAP_S390_VSIE_ESAMODE: + case KVM_CAP_PRE_FAULT_MEMORY: r = 1; break; case KVM_CAP_SET_GUEST_DEBUG2: @@ -5736,6 +5737,50 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, return; } +/** + * kvm_arch_vcpu_pre_fault_memory() -- pre-fault and link gmap dat tables + * @vcpu: the vcpu that shall appear to have generated the fault-in. + * @range: the range that needs to be faulted in. + * + * The first page of the given range is faulted in and the corresponding gmap + * page tables are created, as if the given vCPU had performed a read + * operation. + * If the range starts outside any memslots, an error is returned. An error is + * also returned for UCONTROL VMs, which should instead use the + * KVM_S390_VCPU_FAULT ioctl. + * + * Return: + * * %-ENOENT if the range lies outside of a memslot. + * * %-EINVAL in case of invalid state (for example if the VM is UCONTROL). + * * %-EIO if errors happen while faulting-in the page (will trigger a warning + * in the caller). + * * other error codes < 0 in case of other errors. + * * otherwise a number > 0 of bytes that have been faulted in successfully. + */ +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, struct kvm_pre_fault_memory *range) +{ + struct guest_fault f = { .gfn = gpa_to_gfn(range->gpa), }; + gpa_t end; + int rc; + + if (kvm_is_ucontrol(vcpu->kvm)) + return -EINVAL; + + rc = kvm_s390_faultin_gfn(vcpu, NULL, &f); + if (rc == PGM_ADDRESSING) + return -ENOENT; + if (rc > 0) + return -EIO; + if (rc < 0) + return rc; + + if (f.ptep) + return PAGE_SIZE; + + end = ALIGN(range->gpa + PAGE_SIZE, f.crste_region3 ? _REGION3_SIZE : HPAGE_SIZE); + return min(range->size, end - range->gpa); +} + /** * kvm_test_age_gfn() - test young * @kvm: the kvm instance -- 2.54.0 Update the API documentation for KVM_PRE_FAULT_MEMORY to account for its s390 implementation. Signed-off-by: Claudio Imbrenda --- Documentation/virt/kvm/api.rst | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 52bbbb553ce1..e7998feaa940 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6471,7 +6471,8 @@ Errors: ========== =============================================================== EINVAL The specified `gpa` and `size` were invalid (e.g. not - page aligned, causes an overflow, or size is zero). + page aligned, causes an overflow, or size is zero), or the VM + is UCONTROL (s390). ENOENT The specified `gpa` is outside defined memslots. EINTR An unmasked signal is pending and no page was processed. EFAULT The parameter address was invalid. @@ -6494,7 +6495,7 @@ Errors: KVM_PRE_FAULT_MEMORY populates KVM's stage-2 page tables used to map memory for the current vCPU state. KVM maps memory as if the vCPU generated a stage-2 read page fault, e.g. faults in memory as needed, but doesn't break -CoW. However, KVM does not mark any newly created stage-2 PTE as Accessed. +CoW. On x86, KVM does not mark any newly created stage-2 PTE as Accessed. In the case of confidential VM types where there is an initial set up of private guest memory before the guest is 'finalized'/measured, this ioctl -- 2.54.0 Add a missing #include which is needed and otherwise not included on s390. Remove the assertion vcpu->run->exit_reason == KVM_EXIT_IO since it is x86-specific and redundant anyway. Signed-off-by: Claudio Imbrenda Acked-by: Sean Christopherson --- tools/testing/selftests/kvm/pre_fault_memory_test.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/tools/testing/selftests/kvm/pre_fault_memory_test.c b/tools/testing/selftests/kvm/pre_fault_memory_test.c index fcb57fd034e6..a0fcae3cb7a8 100644 --- a/tools/testing/selftests/kvm/pre_fault_memory_test.c +++ b/tools/testing/selftests/kvm/pre_fault_memory_test.c @@ -11,6 +11,7 @@ #include #include #include +#include /* Arbitrarily chosen values */ #define TEST_SIZE (SZ_2M + PAGE_SIZE) @@ -167,7 +168,6 @@ static void __test_pre_fault_memory(unsigned long vm_type, bool private) .type = vm_type, }; struct kvm_vcpu *vcpu; - struct kvm_run *run; struct kvm_vm *vm; struct ucall uc; @@ -193,11 +193,6 @@ static void __test_pre_fault_memory(unsigned long vm_type, bool private) vcpu_args_set(vcpu, 1, gva); vcpu_run(vcpu); - run = vcpu->run; - TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, - "Wanted KVM_EXIT_IO, got exit reason: %u (%s)", - run->exit_reason, exit_reason_str(run->exit_reason)); - switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: REPORT_GUEST_ASSERT(uc); -- 2.54.0 Enable the pre_fault_memory_test to run on s390. Signed-off-by: Claudio Imbrenda --- tools/testing/selftests/kvm/Makefile.kvm | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 9118a5a51b89..fff939db89cd 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -210,6 +210,7 @@ TEST_GEN_PROGS_s390 += s390/keyop TEST_GEN_PROGS_s390 += rseq_test TEST_GEN_PROGS_s390 += s390/irq_routing TEST_GEN_PROGS_s390 += mmu_stress_test +TEST_GEN_PROGS_s390 += pre_fault_memory_test TEST_GEN_PROGS_riscv = $(TEST_GEN_PROGS_COMMON) TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test -- 2.54.0