selftests: kvm: Allows userspace to handle emulation errors.

This test exercises the feature KVM_CAP_EXIT_ON_EMULATION_FAILURE.  When
enabled, errors in the in-kernel instruction emulator are forwarded to
userspace with the instruction bytes stored in the exit struct for
KVM_EXIT_INTERNAL_ERROR.  So, when the guest attempts to emulate an
'flds' instruction, which isn't able to be emulated in KVM, instead
of failing, KVM sends the instruction to userspace to handle.

For this test to work properly the module parameter
'allow_smaller_maxphyaddr' has to be set.

Signed-off-by: Aaron Lewis <aaronlewis@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Message-Id: <20210510144834.658457-3-aaronlewis@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 92 insertions, 0 deletions

diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 5e0e3a131dad..3114b18454d5 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -282,6 +282,98 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 	__virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K);
 }
 
+static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
+						       uint64_t vaddr)
+{
+	uint16_t index[4];
+	struct pageUpperEntry *pml4e, *pdpe, *pde;
+	struct pageTableEntry *pte;
+	struct kvm_cpuid_entry2 *entry;
+	struct kvm_sregs sregs;
+	int max_phy_addr;
+	/* Set the bottom 52 bits. */
+	uint64_t rsvd_mask = 0x000fffffffffffff;
+
+	entry = kvm_get_supported_cpuid_index(0x80000008, 0);
+	max_phy_addr = entry->eax & 0x000000ff;
+	/* Clear the bottom bits of the reserved mask. */
+	rsvd_mask = (rsvd_mask >> max_phy_addr) << max_phy_addr;
+
+	/*
+	 * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries
+	 * with 4-Level Paging and 5-Level Paging".
+	 * If IA32_EFER.NXE = 0 and the P flag of a paging-structure entry is 1,
+	 * the XD flag (bit 63) is reserved.
+	 */
+	vcpu_sregs_get(vm, vcpuid, &sregs);
+	if ((sregs.efer & EFER_NX) == 0) {
+		rsvd_mask |= (1ull << 63);
+	}
+
+	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
+		"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+	TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+		(vaddr >> vm->page_shift)),
+		"Invalid virtual address, vaddr: 0x%lx",
+		vaddr);
+	/*
+	 * Based on the mode check above there are 48 bits in the vaddr, so
+	 * shift 16 to sign extend the last bit (bit-47),
+	 */
+	TEST_ASSERT(vaddr == (((int64_t)vaddr << 16) >> 16),
+		"Canonical check failed.  The virtual address is invalid.");
+
+	index[0] = (vaddr >> 12) & 0x1ffu;
+	index[1] = (vaddr >> 21) & 0x1ffu;
+	index[2] = (vaddr >> 30) & 0x1ffu;
+	index[3] = (vaddr >> 39) & 0x1ffu;
+
+	pml4e = addr_gpa2hva(vm, vm->pgd);
+	TEST_ASSERT(pml4e[index[3]].present,
+		"Expected pml4e to be present for gva: 0x%08lx", vaddr);
+	TEST_ASSERT((*(uint64_t*)(&pml4e[index[3]]) &
+		(rsvd_mask | (1ull << 7))) == 0,
+		"Unexpected reserved bits set.");
+
+	pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size);
+	TEST_ASSERT(pdpe[index[2]].present,
+		"Expected pdpe to be present for gva: 0x%08lx", vaddr);
+	TEST_ASSERT(pdpe[index[2]].page_size == 0,
+		"Expected pdpe to map a pde not a 1-GByte page.");
+	TEST_ASSERT((*(uint64_t*)(&pdpe[index[2]]) & rsvd_mask) == 0,
+		"Unexpected reserved bits set.");
+
+	pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size);
+	TEST_ASSERT(pde[index[1]].present,
+		"Expected pde to be present for gva: 0x%08lx", vaddr);
+	TEST_ASSERT(pde[index[1]].page_size == 0,
+		"Expected pde to map a pte not a 2-MByte page.");
+	TEST_ASSERT((*(uint64_t*)(&pde[index[1]]) & rsvd_mask) == 0,
+		"Unexpected reserved bits set.");
+
+	pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size);
+	TEST_ASSERT(pte[index[0]].present,
+		"Expected pte to be present for gva: 0x%08lx", vaddr);
+
+	return &pte[index[0]];
+}
+
+uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr)
+{
+	struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr);
+
+	return *(uint64_t *)pte;
+}
+
+void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr,
+			     uint64_t pte)
+{
+	struct pageTableEntry *new_pte = _vm_get_page_table_entry(vm, vcpuid,
+								  vaddr);
+
+	*(uint64_t *)new_pte = pte;
+}
+
 void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 {
 	struct pageUpperEntry *pml4e, *pml4e_start;