summaryrefslogtreecommitdiffstats
path: root/tools/testing/selftests/kvm/lib/x86_64
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-27 10:05:51 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-27 10:05:51 +0000
commit5d1646d90e1f2cceb9f0828f4b28318cd0ec7744 (patch)
treea94efe259b9009378be6d90eb30d2b019d95c194 /tools/testing/selftests/kvm/lib/x86_64
parentInitial commit. (diff)
downloadlinux-upstream/5.10.209.tar.xz
linux-upstream/5.10.209.zip
Adding upstream version 5.10.209.upstream/5.10.209upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'tools/testing/selftests/kvm/lib/x86_64')
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/handlers.S81
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c1258
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/svm.c177
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/ucall.c59
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/vmx.c553
5 files changed, 2128 insertions, 0 deletions
diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
new file mode 100644
index 000000000..aaf7bc7d2
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
@@ -0,0 +1,81 @@
+handle_exception:
+ push %r15
+ push %r14
+ push %r13
+ push %r12
+ push %r11
+ push %r10
+ push %r9
+ push %r8
+
+ push %rdi
+ push %rsi
+ push %rbp
+ push %rbx
+ push %rdx
+ push %rcx
+ push %rax
+ mov %rsp, %rdi
+
+ call route_exception
+
+ pop %rax
+ pop %rcx
+ pop %rdx
+ pop %rbx
+ pop %rbp
+ pop %rsi
+ pop %rdi
+ pop %r8
+ pop %r9
+ pop %r10
+ pop %r11
+ pop %r12
+ pop %r13
+ pop %r14
+ pop %r15
+
+ /* Discard vector and error code. */
+ add $16, %rsp
+ iretq
+
+/*
+ * Build the handle_exception wrappers which push the vector/error code on the
+ * stack and an array of pointers to those wrappers.
+ */
+.pushsection .rodata
+.globl idt_handlers
+idt_handlers:
+.popsection
+
+.macro HANDLERS has_error from to
+ vector = \from
+ .rept \to - \from + 1
+ .align 8
+
+ /* Fetch current address and append it to idt_handlers. */
+ current_handler = .
+.pushsection .rodata
+.quad current_handler
+.popsection
+
+ .if ! \has_error
+ pushq $0
+ .endif
+ pushq $vector
+ jmp handle_exception
+ vector = vector + 1
+ .endr
+.endm
+
+.global idt_handler_code
+idt_handler_code:
+ HANDLERS has_error=0 from=0 to=7
+ HANDLERS has_error=1 from=8 to=8
+ HANDLERS has_error=0 from=9 to=9
+ HANDLERS has_error=1 from=10 to=14
+ HANDLERS has_error=0 from=15 to=16
+ HANDLERS has_error=1 from=17 to=17
+ HANDLERS has_error=0 from=18 to=255
+
+.section .note.GNU-stack, "", %progbits
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
new file mode 100644
index 000000000..f5d2d27be
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -0,0 +1,1258 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * tools/testing/selftests/kvm/lib/x86_64/processor.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+
+#ifndef NUM_INTERRUPTS
+#define NUM_INTERRUPTS 256
+#endif
+
+#define DEFAULT_CODE_SELECTOR 0x8
+#define DEFAULT_DATA_SELECTOR 0x10
+
+/* Minimum physical address used for virtual translation tables. */
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+
+vm_vaddr_t exception_handlers;
+
+/* Virtual translation table structure declarations */
+struct pageMapL4Entry {
+ uint64_t present:1;
+ uint64_t writable:1;
+ uint64_t user:1;
+ uint64_t write_through:1;
+ uint64_t cache_disable:1;
+ uint64_t accessed:1;
+ uint64_t ignored_06:1;
+ uint64_t page_size:1;
+ uint64_t ignored_11_08:4;
+ uint64_t address:40;
+ uint64_t ignored_62_52:11;
+ uint64_t execute_disable:1;
+};
+
+struct pageDirectoryPointerEntry {
+ uint64_t present:1;
+ uint64_t writable:1;
+ uint64_t user:1;
+ uint64_t write_through:1;
+ uint64_t cache_disable:1;
+ uint64_t accessed:1;
+ uint64_t ignored_06:1;
+ uint64_t page_size:1;
+ uint64_t ignored_11_08:4;
+ uint64_t address:40;
+ uint64_t ignored_62_52:11;
+ uint64_t execute_disable:1;
+};
+
+struct pageDirectoryEntry {
+ uint64_t present:1;
+ uint64_t writable:1;
+ uint64_t user:1;
+ uint64_t write_through:1;
+ uint64_t cache_disable:1;
+ uint64_t accessed:1;
+ uint64_t ignored_06:1;
+ uint64_t page_size:1;
+ uint64_t ignored_11_08:4;
+ uint64_t address:40;
+ uint64_t ignored_62_52:11;
+ uint64_t execute_disable:1;
+};
+
+struct pageTableEntry {
+ uint64_t present:1;
+ uint64_t writable:1;
+ uint64_t user:1;
+ uint64_t write_through:1;
+ uint64_t cache_disable:1;
+ uint64_t accessed:1;
+ uint64_t dirty:1;
+ uint64_t reserved_07:1;
+ uint64_t global:1;
+ uint64_t ignored_11_09:3;
+ uint64_t address:40;
+ uint64_t ignored_62_52:11;
+ uint64_t execute_disable:1;
+};
+
+void regs_dump(FILE *stream, struct kvm_regs *regs,
+ uint8_t indent)
+{
+ fprintf(stream, "%*srax: 0x%.16llx rbx: 0x%.16llx "
+ "rcx: 0x%.16llx rdx: 0x%.16llx\n",
+ indent, "",
+ regs->rax, regs->rbx, regs->rcx, regs->rdx);
+ fprintf(stream, "%*srsi: 0x%.16llx rdi: 0x%.16llx "
+ "rsp: 0x%.16llx rbp: 0x%.16llx\n",
+ indent, "",
+ regs->rsi, regs->rdi, regs->rsp, regs->rbp);
+ fprintf(stream, "%*sr8: 0x%.16llx r9: 0x%.16llx "
+ "r10: 0x%.16llx r11: 0x%.16llx\n",
+ indent, "",
+ regs->r8, regs->r9, regs->r10, regs->r11);
+ fprintf(stream, "%*sr12: 0x%.16llx r13: 0x%.16llx "
+ "r14: 0x%.16llx r15: 0x%.16llx\n",
+ indent, "",
+ regs->r12, regs->r13, regs->r14, regs->r15);
+ fprintf(stream, "%*srip: 0x%.16llx rfl: 0x%.16llx\n",
+ indent, "",
+ regs->rip, regs->rflags);
+}
+
+/*
+ * Segment Dump
+ *
+ * Input Args:
+ * stream - Output FILE stream
+ * segment - KVM segment
+ * indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps the state of the KVM segment given by @segment, to the FILE stream
+ * given by @stream.
+ */
+static void segment_dump(FILE *stream, struct kvm_segment *segment,
+ uint8_t indent)
+{
+ fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.8x "
+ "selector: 0x%.4x type: 0x%.2x\n",
+ indent, "", segment->base, segment->limit,
+ segment->selector, segment->type);
+ fprintf(stream, "%*spresent: 0x%.2x dpl: 0x%.2x "
+ "db: 0x%.2x s: 0x%.2x l: 0x%.2x\n",
+ indent, "", segment->present, segment->dpl,
+ segment->db, segment->s, segment->l);
+ fprintf(stream, "%*sg: 0x%.2x avl: 0x%.2x "
+ "unusable: 0x%.2x padding: 0x%.2x\n",
+ indent, "", segment->g, segment->avl,
+ segment->unusable, segment->padding);
+}
+
+/*
+ * dtable Dump
+ *
+ * Input Args:
+ * stream - Output FILE stream
+ * dtable - KVM dtable
+ * indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps the state of the KVM dtable given by @dtable, to the FILE stream
+ * given by @stream.
+ */
+static void dtable_dump(FILE *stream, struct kvm_dtable *dtable,
+ uint8_t indent)
+{
+ fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.4x "
+ "padding: 0x%.4x 0x%.4x 0x%.4x\n",
+ indent, "", dtable->base, dtable->limit,
+ dtable->padding[0], dtable->padding[1], dtable->padding[2]);
+}
+
+void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
+ uint8_t indent)
+{
+ unsigned int i;
+
+ fprintf(stream, "%*scs:\n", indent, "");
+ segment_dump(stream, &sregs->cs, indent + 2);
+ fprintf(stream, "%*sds:\n", indent, "");
+ segment_dump(stream, &sregs->ds, indent + 2);
+ fprintf(stream, "%*ses:\n", indent, "");
+ segment_dump(stream, &sregs->es, indent + 2);
+ fprintf(stream, "%*sfs:\n", indent, "");
+ segment_dump(stream, &sregs->fs, indent + 2);
+ fprintf(stream, "%*sgs:\n", indent, "");
+ segment_dump(stream, &sregs->gs, indent + 2);
+ fprintf(stream, "%*sss:\n", indent, "");
+ segment_dump(stream, &sregs->ss, indent + 2);
+ fprintf(stream, "%*str:\n", indent, "");
+ segment_dump(stream, &sregs->tr, indent + 2);
+ fprintf(stream, "%*sldt:\n", indent, "");
+ segment_dump(stream, &sregs->ldt, indent + 2);
+
+ fprintf(stream, "%*sgdt:\n", indent, "");
+ dtable_dump(stream, &sregs->gdt, indent + 2);
+ fprintf(stream, "%*sidt:\n", indent, "");
+ dtable_dump(stream, &sregs->idt, indent + 2);
+
+ fprintf(stream, "%*scr0: 0x%.16llx cr2: 0x%.16llx "
+ "cr3: 0x%.16llx cr4: 0x%.16llx\n",
+ indent, "",
+ sregs->cr0, sregs->cr2, sregs->cr3, sregs->cr4);
+ fprintf(stream, "%*scr8: 0x%.16llx efer: 0x%.16llx "
+ "apic_base: 0x%.16llx\n",
+ indent, "",
+ sregs->cr8, sregs->efer, sregs->apic_base);
+
+ fprintf(stream, "%*sinterrupt_bitmap:\n", indent, "");
+ for (i = 0; i < (KVM_NR_INTERRUPTS + 63) / 64; i++) {
+ fprintf(stream, "%*s%.16llx\n", indent + 2, "",
+ sregs->interrupt_bitmap[i]);
+ }
+}
+
+void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
+{
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
+ "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+ /* If needed, create page map l4 table. */
+ if (!vm->pgd_created) {
+ vm_paddr_t paddr = vm_phy_page_alloc(vm,
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+ vm->pgd = paddr;
+ vm->pgd_created = true;
+ }
+}
+
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ uint32_t pgd_memslot)
+{
+ uint16_t index[4];
+ struct pageMapL4Entry *pml4e;
+
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
+ "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+ TEST_ASSERT((vaddr % vm->page_size) == 0,
+ "Virtual address not on page boundary,\n"
+ " vaddr: 0x%lx vm->page_size: 0x%x",
+ vaddr, vm->page_size);
+ TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+ (vaddr >> vm->page_shift)),
+ "Invalid virtual address, vaddr: 0x%lx",
+ vaddr);
+ TEST_ASSERT((paddr % vm->page_size) == 0,
+ "Physical address not on page boundary,\n"
+ " paddr: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->page_size);
+ TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+ "Physical address beyond beyond maximum supported,\n"
+ " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->max_gfn, vm->page_size);
+
+ index[0] = (vaddr >> 12) & 0x1ffu;
+ index[1] = (vaddr >> 21) & 0x1ffu;
+ index[2] = (vaddr >> 30) & 0x1ffu;
+ index[3] = (vaddr >> 39) & 0x1ffu;
+
+ /* Allocate page directory pointer table if not present. */
+ pml4e = addr_gpa2hva(vm, vm->pgd);
+ if (!pml4e[index[3]].present) {
+ pml4e[index[3]].address = vm_phy_page_alloc(vm,
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+ >> vm->page_shift;
+ pml4e[index[3]].writable = true;
+ pml4e[index[3]].present = true;
+ }
+
+ /* Allocate page directory table if not present. */
+ struct pageDirectoryPointerEntry *pdpe;
+ pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+ if (!pdpe[index[2]].present) {
+ pdpe[index[2]].address = vm_phy_page_alloc(vm,
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+ >> vm->page_shift;
+ pdpe[index[2]].writable = true;
+ pdpe[index[2]].present = true;
+ }
+
+ /* Allocate page table if not present. */
+ struct pageDirectoryEntry *pde;
+ pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+ if (!pde[index[1]].present) {
+ pde[index[1]].address = vm_phy_page_alloc(vm,
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+ >> vm->page_shift;
+ pde[index[1]].writable = true;
+ pde[index[1]].present = true;
+ }
+
+ /* Fill in page table entry. */
+ struct pageTableEntry *pte;
+ pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+ pte[index[0]].address = paddr >> vm->page_shift;
+ pte[index[0]].writable = true;
+ pte[index[0]].present = 1;
+}
+
+void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+ struct pageMapL4Entry *pml4e, *pml4e_start;
+ struct pageDirectoryPointerEntry *pdpe, *pdpe_start;
+ struct pageDirectoryEntry *pde, *pde_start;
+ struct pageTableEntry *pte, *pte_start;
+
+ if (!vm->pgd_created)
+ return;
+
+ fprintf(stream, "%*s "
+ " no\n", indent, "");
+ fprintf(stream, "%*s index hvaddr gpaddr "
+ "addr w exec dirty\n",
+ indent, "");
+ pml4e_start = (struct pageMapL4Entry *) addr_gpa2hva(vm,
+ vm->pgd);
+ for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) {
+ pml4e = &pml4e_start[n1];
+ if (!pml4e->present)
+ continue;
+ fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u "
+ " %u\n",
+ indent, "",
+ pml4e - pml4e_start, pml4e,
+ addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->address,
+ pml4e->writable, pml4e->execute_disable);
+
+ pdpe_start = addr_gpa2hva(vm, pml4e->address
+ * vm->page_size);
+ for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) {
+ pdpe = &pdpe_start[n2];
+ if (!pdpe->present)
+ continue;
+ fprintf(stream, "%*spdpe 0x%-3zx %p 0x%-12lx 0x%-10lx "
+ "%u %u\n",
+ indent, "",
+ pdpe - pdpe_start, pdpe,
+ addr_hva2gpa(vm, pdpe),
+ (uint64_t) pdpe->address, pdpe->writable,
+ pdpe->execute_disable);
+
+ pde_start = addr_gpa2hva(vm,
+ pdpe->address * vm->page_size);
+ for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) {
+ pde = &pde_start[n3];
+ if (!pde->present)
+ continue;
+ fprintf(stream, "%*spde 0x%-3zx %p "
+ "0x%-12lx 0x%-10lx %u %u\n",
+ indent, "", pde - pde_start, pde,
+ addr_hva2gpa(vm, pde),
+ (uint64_t) pde->address, pde->writable,
+ pde->execute_disable);
+
+ pte_start = addr_gpa2hva(vm,
+ pde->address * vm->page_size);
+ for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) {
+ pte = &pte_start[n4];
+ if (!pte->present)
+ continue;
+ fprintf(stream, "%*spte 0x%-3zx %p "
+ "0x%-12lx 0x%-10lx %u %u "
+ " %u 0x%-10lx\n",
+ indent, "",
+ pte - pte_start, pte,
+ addr_hva2gpa(vm, pte),
+ (uint64_t) pte->address,
+ pte->writable,
+ pte->execute_disable,
+ pte->dirty,
+ ((uint64_t) n1 << 27)
+ | ((uint64_t) n2 << 18)
+ | ((uint64_t) n3 << 9)
+ | ((uint64_t) n4));
+ }
+ }
+ }
+ }
+}
+
+/*
+ * Set Unusable Segment
+ *
+ * Input Args: None
+ *
+ * Output Args:
+ * segp - Pointer to segment register
+ *
+ * Return: None
+ *
+ * Sets the segment register pointed to by @segp to an unusable state.
+ */
+static void kvm_seg_set_unusable(struct kvm_segment *segp)
+{
+ memset(segp, 0, sizeof(*segp));
+ segp->unusable = true;
+}
+
+static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
+{
+ void *gdt = addr_gva2hva(vm, vm->gdt);
+ struct desc64 *desc = gdt + (segp->selector >> 3) * 8;
+
+ desc->limit0 = segp->limit & 0xFFFF;
+ desc->base0 = segp->base & 0xFFFF;
+ desc->base1 = segp->base >> 16;
+ desc->type = segp->type;
+ desc->s = segp->s;
+ desc->dpl = segp->dpl;
+ desc->p = segp->present;
+ desc->limit1 = segp->limit >> 16;
+ desc->avl = segp->avl;
+ desc->l = segp->l;
+ desc->db = segp->db;
+ desc->g = segp->g;
+ desc->base2 = segp->base >> 24;
+ if (!segp->s)
+ 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)
+{
+ memset(segp, 0, sizeof(*segp));
+ segp->selector = selector;
+ segp->limit = 0xFFFFFFFFu;
+ segp->s = 0x1; /* kTypeCodeData */
+ segp->type = 0x08 | 0x01 | 0x02; /* kFlagCode | kFlagCodeAccessed
+ * | kFlagCodeReadable
+ */
+ 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)
+{
+ memset(segp, 0, sizeof(*segp));
+ segp->selector = selector;
+ segp->limit = 0xFFFFFFFFu;
+ segp->s = 0x1; /* kTypeCodeData */
+ segp->type = 0x00 | 0x01 | 0x02; /* kFlagData | kFlagDataAccessed
+ * | kFlagDataWritable
+ */
+ segp->g = true;
+ segp->present = true;
+ if (vm)
+ kvm_seg_fill_gdt_64bit(vm, segp);
+}
+
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ uint16_t index[4];
+ struct pageMapL4Entry *pml4e;
+ struct pageDirectoryPointerEntry *pdpe;
+ struct pageDirectoryEntry *pde;
+ struct pageTableEntry *pte;
+
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
+ "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+ index[0] = (gva >> 12) & 0x1ffu;
+ index[1] = (gva >> 21) & 0x1ffu;
+ index[2] = (gva >> 30) & 0x1ffu;
+ index[3] = (gva >> 39) & 0x1ffu;
+
+ if (!vm->pgd_created)
+ goto unmapped_gva;
+ pml4e = addr_gpa2hva(vm, vm->pgd);
+ if (!pml4e[index[3]].present)
+ goto unmapped_gva;
+
+ pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+ if (!pdpe[index[2]].present)
+ goto unmapped_gva;
+
+ pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+ if (!pde[index[1]].present)
+ goto unmapped_gva;
+
+ pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+ if (!pte[index[0]].present)
+ goto unmapped_gva;
+
+ return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu);
+
+unmapped_gva:
+ TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
+ exit(EXIT_FAILURE);
+}
+
+static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt, int gdt_memslot,
+ int pgd_memslot)
+{
+ if (!vm->gdt)
+ vm->gdt = vm_vaddr_alloc(vm, getpagesize(),
+ KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
+
+ dt->base = vm->gdt;
+ dt->limit = getpagesize();
+}
+
+static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp,
+ int selector, int gdt_memslot,
+ int pgd_memslot)
+{
+ if (!vm->tss)
+ vm->tss = vm_vaddr_alloc(vm, getpagesize(),
+ KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
+
+ memset(segp, 0, sizeof(*segp));
+ segp->base = vm->tss;
+ segp->limit = 0x67;
+ segp->selector = selector;
+ segp->type = 0xb;
+ segp->present = 1;
+ kvm_seg_fill_gdt_64bit(vm, segp);
+}
+
+static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
+{
+ struct kvm_sregs sregs;
+
+ /* Set mode specific system register values. */
+ vcpu_sregs_get(vm, vcpuid, &sregs);
+
+ sregs.idt.limit = 0;
+
+ kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot);
+
+ 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(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, gdt_memslot, pgd_memslot);
+ break;
+
+ default:
+ TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
+ }
+
+ sregs.cr3 = vm->pgd;
+ vcpu_sregs_set(vm, vcpuid, &sregs);
+}
+
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
+{
+ struct kvm_mp_state mp_state;
+ struct kvm_regs regs;
+ vm_vaddr_t stack_vaddr;
+ stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
+ DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0);
+
+ /* Create VCPU */
+ vm_vcpu_add(vm, vcpuid);
+ vcpu_setup(vm, vcpuid, 0, 0);
+
+ /* Setup guest general purpose registers */
+ vcpu_regs_get(vm, vcpuid, &regs);
+ regs.rflags = regs.rflags | 0x2;
+ regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize());
+ regs.rip = (unsigned long) guest_code;
+ vcpu_regs_set(vm, vcpuid, &regs);
+
+ /* Setup the MP state */
+ mp_state.mp_state = 0;
+ vcpu_set_mp_state(vm, vcpuid, &mp_state);
+}
+
+/*
+ * Allocate an instance of struct kvm_cpuid2
+ *
+ * Input Args: None
+ *
+ * Output Args: None
+ *
+ * Return: A pointer to the allocated struct. The caller is responsible
+ * for freeing this struct.
+ *
+ * Since kvm_cpuid2 uses a 0-length array to allow a the size of the
+ * array to be decided at allocation time, allocation is slightly
+ * complicated. This function uses a reasonable default length for
+ * the array and performs the appropriate allocation.
+ */
+static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
+{
+ struct kvm_cpuid2 *cpuid;
+ int nent = 100;
+ size_t size;
+
+ size = sizeof(*cpuid);
+ size += nent * sizeof(struct kvm_cpuid_entry2);
+ cpuid = malloc(size);
+ if (!cpuid) {
+ perror("malloc");
+ abort();
+ }
+
+ cpuid->nent = nent;
+
+ return cpuid;
+}
+
+/*
+ * KVM Supported CPUID Get
+ *
+ * Input Args: None
+ *
+ * Output Args:
+ *
+ * Return: The supported KVM CPUID
+ *
+ * Get the guest CPUID supported by KVM.
+ */
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
+{
+ static struct kvm_cpuid2 *cpuid;
+ int ret;
+ int kvm_fd;
+
+ if (cpuid)
+ return cpuid;
+
+ cpuid = allocate_kvm_cpuid2();
+ kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
+
+ ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
+ TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
+ ret, errno);
+
+ close(kvm_fd);
+ return cpuid;
+}
+
+/*
+ * Locate a cpuid entry.
+ *
+ * Input Args:
+ * function: The function of the cpuid entry to find.
+ * index: The index of the cpuid entry.
+ *
+ * Output Args: None
+ *
+ * Return: A pointer to the cpuid entry. Never returns NULL.
+ */
+struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
+{
+ struct kvm_cpuid2 *cpuid;
+ struct kvm_cpuid_entry2 *entry = NULL;
+ int i;
+
+ cpuid = kvm_get_supported_cpuid();
+ for (i = 0; i < cpuid->nent; i++) {
+ if (cpuid->entries[i].function == function &&
+ cpuid->entries[i].index == index) {
+ entry = &cpuid->entries[i];
+ break;
+ }
+ }
+
+ TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).",
+ function, index);
+ return entry;
+}
+
+/*
+ * VM VCPU CPUID Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU id
+ * cpuid - The CPUID values to set.
+ *
+ * Output Args: None
+ *
+ * Return: void
+ *
+ * Set the VCPU's CPUID.
+ */
+void vcpu_set_cpuid(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_cpuid2 *cpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int rc;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ rc = ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
+ TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i",
+ rc, errno);
+
+}
+
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+ void *guest_code)
+{
+ struct kvm_vm *vm;
+ /*
+ * For x86 the maximum page table size for a memory region
+ * will be when only 4K pages are used. In that case the
+ * total extra size for page tables (for extra N pages) will
+ * be: N/512+N/512^2+N/512^3+... which is definitely smaller
+ * than N/512*2.
+ */
+ uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
+
+ /* Create VM */
+ vm = vm_create(VM_MODE_DEFAULT,
+ DEFAULT_GUEST_PHY_PAGES + extra_pg_pages,
+ O_RDWR);
+
+ /* Setup guest code */
+ kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+
+ /* Setup IRQ Chip */
+ vm_create_irqchip(vm);
+
+ /* Add the first vCPU. */
+ vm_vcpu_add_default(vm, vcpuid, guest_code);
+
+ return vm;
+}
+
+/*
+ * VCPU Get MSR
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * msr_index - Index of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, value of the MSR. On failure a TEST_ASSERT is produced.
+ *
+ * Get value of MSR for VCPU.
+ */
+uint64_t vcpu_get_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ struct {
+ struct kvm_msrs header;
+ struct kvm_msr_entry entry;
+ } buffer = {};
+ int r;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+ buffer.header.nmsrs = 1;
+ buffer.entry.index = msr_index;
+ r = ioctl(vcpu->fd, KVM_GET_MSRS, &buffer.header);
+ TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n"
+ " rc: %i errno: %i", r, errno);
+
+ return buffer.entry.data;
+}
+
+/*
+ * _VCPU Set MSR
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * msr_index - Index of MSR
+ * msr_value - New value of MSR
+ *
+ * Output Args: None
+ *
+ * Return: The result of KVM_SET_MSRS.
+ *
+ * Sets the value of an MSR for the given VCPU.
+ */
+int _vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+ uint64_t msr_value)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ struct {
+ struct kvm_msrs header;
+ struct kvm_msr_entry entry;
+ } buffer = {};
+ int r;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+ memset(&buffer, 0, sizeof(buffer));
+ buffer.header.nmsrs = 1;
+ buffer.entry.index = msr_index;
+ buffer.entry.data = msr_value;
+ r = ioctl(vcpu->fd, KVM_SET_MSRS, &buffer.header);
+ return r;
+}
+
+/*
+ * VCPU Set MSR
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * msr_index - Index of MSR
+ * msr_value - New value of MSR
+ *
+ * Output Args: None
+ *
+ * Return: On success, nothing. On failure a TEST_ASSERT is produced.
+ *
+ * Set value of MSR for VCPU.
+ */
+void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
+ uint64_t msr_value)
+{
+ int r;
+
+ r = _vcpu_set_msr(vm, vcpuid, msr_index, msr_value);
+ TEST_ASSERT(r == 1, "KVM_SET_MSRS IOCTL failed,\n"
+ " rc: %i errno: %i", r, errno);
+}
+
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+ va_list ap;
+ struct kvm_regs regs;
+
+ TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
+ " num: %u\n",
+ num);
+
+ va_start(ap, num);
+ vcpu_regs_get(vm, vcpuid, &regs);
+
+ if (num >= 1)
+ regs.rdi = va_arg(ap, uint64_t);
+
+ if (num >= 2)
+ regs.rsi = va_arg(ap, uint64_t);
+
+ if (num >= 3)
+ regs.rdx = va_arg(ap, uint64_t);
+
+ if (num >= 4)
+ regs.rcx = va_arg(ap, uint64_t);
+
+ if (num >= 5)
+ regs.r8 = va_arg(ap, uint64_t);
+
+ if (num >= 6)
+ regs.r9 = va_arg(ap, uint64_t);
+
+ vcpu_regs_set(vm, vcpuid, &regs);
+ va_end(ap);
+}
+
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
+{
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+
+ fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid);
+
+ fprintf(stream, "%*sregs:\n", indent + 2, "");
+ vcpu_regs_get(vm, vcpuid, &regs);
+ regs_dump(stream, &regs, indent + 4);
+
+ fprintf(stream, "%*ssregs:\n", indent + 2, "");
+ vcpu_sregs_get(vm, vcpuid, &sregs);
+ sregs_dump(stream, &sregs, indent + 4);
+}
+
+struct kvm_x86_state {
+ struct kvm_vcpu_events events;
+ struct kvm_mp_state mp_state;
+ struct kvm_regs regs;
+ struct kvm_xsave xsave;
+ struct kvm_xcrs xcrs;
+ struct kvm_sregs sregs;
+ struct kvm_debugregs debugregs;
+ union {
+ struct kvm_nested_state nested;
+ char nested_[16384];
+ };
+ struct kvm_msrs msrs;
+};
+
+static int kvm_get_num_msrs_fd(int kvm_fd)
+{
+ struct kvm_msr_list nmsrs;
+ int r;
+
+ nmsrs.nmsrs = 0;
+ r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, &nmsrs);
+ TEST_ASSERT(r == -1 && errno == E2BIG, "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i",
+ r);
+
+ return nmsrs.nmsrs;
+}
+
+static int kvm_get_num_msrs(struct kvm_vm *vm)
+{
+ return kvm_get_num_msrs_fd(vm->kvm_fd);
+}
+
+struct kvm_msr_list *kvm_get_msr_index_list(void)
+{
+ struct kvm_msr_list *list;
+ int nmsrs, r, kvm_fd;
+
+ kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
+
+ nmsrs = kvm_get_num_msrs_fd(kvm_fd);
+ list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+ list->nmsrs = nmsrs;
+ r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+ close(kvm_fd);
+
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
+ r);
+
+ return list;
+}
+
+struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ struct kvm_msr_list *list;
+ struct kvm_x86_state *state;
+ int nmsrs, r, i;
+ static int nested_size = -1;
+
+ if (nested_size == -1) {
+ nested_size = kvm_check_cap(KVM_CAP_NESTED_STATE);
+ TEST_ASSERT(nested_size <= sizeof(state->nested_),
+ "Nested state size too big, %i > %zi",
+ nested_size, sizeof(state->nested_));
+ }
+
+ /*
+ * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees
+ * guest state is consistent only after userspace re-enters the
+ * kernel with KVM_RUN. Complete IO prior to migrating state
+ * to a new VM.
+ */
+ vcpu_run_complete_io(vm, vcpuid);
+
+ nmsrs = kvm_get_num_msrs(vm);
+ list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+ list->nmsrs = nmsrs;
+ r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
+ r);
+
+ state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0]));
+ r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
+ r);
+
+ r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
+ r);
+
+ r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
+ r);
+
+ r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
+ r);
+
+ if (kvm_check_cap(KVM_CAP_XCRS)) {
+ r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i",
+ r);
+ }
+
+ r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
+ r);
+
+ if (nested_size) {
+ state->nested.size = sizeof(state->nested_);
+ r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i",
+ r);
+ TEST_ASSERT(state->nested.size <= nested_size,
+ "Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
+ state->nested.size, nested_size);
+ } else
+ state->nested.size = 0;
+
+ state->msrs.nmsrs = nmsrs;
+ for (i = 0; i < nmsrs; i++)
+ state->msrs.entries[i].index = list->indices[i];
+ r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs);
+ TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)",
+ r, r == nmsrs ? -1 : list->indices[r]);
+
+ r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
+ r);
+
+ free(list);
+ return state;
+}
+
+void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *state)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int r;
+
+ r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
+ r);
+
+ if (kvm_check_cap(KVM_CAP_XCRS)) {
+ r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i",
+ r);
+ }
+
+ r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
+ r);
+
+ r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs);
+ TEST_ASSERT(r == state->msrs.nmsrs, "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)",
+ r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index);
+
+ r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
+ r);
+
+ r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
+ r);
+
+ r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
+ r);
+
+ r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
+ r);
+
+ if (state->nested.size) {
+ r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
+ r);
+ }
+}
+
+bool is_intel_cpu(void)
+{
+ int eax, ebx, ecx, edx;
+ const uint32_t *chunk;
+ const int leaf = 0;
+
+ __asm__ __volatile__(
+ "cpuid"
+ : /* output */ "=a"(eax), "=b"(ebx),
+ "=c"(ecx), "=d"(edx)
+ : /* input */ "0"(leaf), "2"(0));
+
+ chunk = (const uint32_t *)("GenuineIntel");
+ return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]);
+}
+
+uint32_t kvm_get_cpuid_max_basic(void)
+{
+ return kvm_get_supported_cpuid_entry(0)->eax;
+}
+
+uint32_t kvm_get_cpuid_max_extended(void)
+{
+ return kvm_get_supported_cpuid_entry(0x80000000)->eax;
+}
+
+void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
+{
+ struct kvm_cpuid_entry2 *entry;
+ bool pae;
+
+ /* SDM 4.1.4 */
+ if (kvm_get_cpuid_max_extended() < 0x80000008) {
+ pae = kvm_get_supported_cpuid_entry(1)->edx & (1 << 6);
+ *pa_bits = pae ? 36 : 32;
+ *va_bits = 32;
+ } else {
+ entry = kvm_get_supported_cpuid_entry(0x80000008);
+ *pa_bits = entry->eax & 0xff;
+ *va_bits = (entry->eax >> 8) & 0xff;
+ }
+}
+
+struct idt_entry {
+ uint16_t offset0;
+ uint16_t selector;
+ uint16_t ist : 3;
+ uint16_t : 5;
+ uint16_t type : 4;
+ uint16_t : 1;
+ uint16_t dpl : 2;
+ uint16_t p : 1;
+ uint16_t offset1;
+ uint32_t offset2; uint32_t reserved;
+};
+
+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;
+}
+
+void kvm_exit_unexpected_vector(uint32_t value)
+{
+ outl(UNEXPECTED_VECTOR_PORT, value);
+}
+
+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;
+ }
+
+ kvm_exit_unexpected_vector(regs->vector);
+}
+
+void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+ extern void *idt_handlers;
+ int i;
+
+ vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0);
+ vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0);
+ /* 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_vm *vm, uint32_t vcpuid)
+{
+ struct kvm_sregs sregs;
+
+ vcpu_sregs_get(vm, vcpuid, &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(vm, vcpuid, &sregs);
+ *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+}
+
+void vm_handle_exception(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_vm *vm, uint32_t vcpuid)
+{
+ if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO
+ && vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT
+ && vcpu_state(vm, vcpuid)->io.size == 4) {
+ /* Grab pointer to io data */
+ uint32_t *data = (void *)vcpu_state(vm, vcpuid)
+ + vcpu_state(vm, vcpuid)->io.data_offset;
+
+ TEST_ASSERT(false,
+ "Unexpected vectored event in guest (vector:0x%x)",
+ *data);
+ }
+}
+
+bool set_cpuid(struct kvm_cpuid2 *cpuid,
+ struct kvm_cpuid_entry2 *ent)
+{
+ int i;
+
+ for (i = 0; i < cpuid->nent; i++) {
+ struct kvm_cpuid_entry2 *cur = &cpuid->entries[i];
+
+ if (cur->function != ent->function || cur->index != ent->index)
+ continue;
+
+ memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2));
+ return true;
+ }
+
+ return false;
+}
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+ uint64_t a3)
+{
+ uint64_t r;
+
+ asm volatile("vmcall"
+ : "=a"(r)
+ : "a"(nr), "b"(a0), "c"(a1), "d"(a2), "S"(a3));
+ return r;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c
new file mode 100644
index 000000000..a58507a7b
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * tools/testing/selftests/kvm/lib/x86_64/svm.c
+ * Helpers used for nested SVM testing
+ * Largely inspired from KVM unit test svm.c
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+#include "svm_util.h"
+
+struct gpr64_regs guest_regs;
+u64 rflags;
+
+/* Allocate memory regions for nested SVM tests.
+ *
+ * Input Args:
+ * vm - The VM to allocate guest-virtual addresses in.
+ *
+ * Output Args:
+ * p_svm_gva - The guest virtual address for the struct svm_test_data.
+ *
+ * Return:
+ * Pointer to structure with the addresses of the SVM areas.
+ */
+struct svm_test_data *
+vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva)
+{
+ vm_vaddr_t svm_gva = vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ struct svm_test_data *svm = addr_gva2hva(vm, svm_gva);
+
+ svm->vmcb = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ svm->vmcb_hva = addr_gva2hva(vm, (uintptr_t)svm->vmcb);
+ svm->vmcb_gpa = addr_gva2gpa(vm, (uintptr_t)svm->vmcb);
+
+ svm->save_area = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area);
+ svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area);
+
+ *p_svm_gva = svm_gva;
+ return svm;
+}
+
+static void vmcb_set_seg(struct vmcb_seg *seg, u16 selector,
+ u64 base, u32 limit, u32 attr)
+{
+ seg->selector = selector;
+ seg->attrib = attr;
+ seg->limit = limit;
+ seg->base = base;
+}
+
+/*
+ * Avoid using memset to clear the vmcb, since libc may not be
+ * available in L1 (and, even if it is, features that libc memset may
+ * want to use, like AVX, may not be enabled).
+ */
+static void clear_vmcb(struct vmcb *vmcb)
+{
+ int n = sizeof(*vmcb) / sizeof(u32);
+
+ asm volatile ("rep stosl" : "+c"(n), "+D"(vmcb) : "a"(0) : "memory");
+}
+
+void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp)
+{
+ struct vmcb *vmcb = svm->vmcb;
+ uint64_t vmcb_gpa = svm->vmcb_gpa;
+ struct vmcb_save_area *save = &vmcb->save;
+ struct vmcb_control_area *ctrl = &vmcb->control;
+ u32 data_seg_attr = 3 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK
+ | SVM_SELECTOR_DB_MASK | SVM_SELECTOR_G_MASK;
+ u32 code_seg_attr = 9 | SVM_SELECTOR_S_MASK | SVM_SELECTOR_P_MASK
+ | SVM_SELECTOR_L_MASK | SVM_SELECTOR_G_MASK;
+ uint64_t efer;
+
+ efer = rdmsr(MSR_EFER);
+ wrmsr(MSR_EFER, efer | EFER_SVME);
+ wrmsr(MSR_VM_HSAVE_PA, svm->save_area_gpa);
+
+ clear_vmcb(vmcb);
+ asm volatile ("vmsave %0\n\t" : : "a" (vmcb_gpa) : "memory");
+ vmcb_set_seg(&save->es, get_es(), 0, -1U, data_seg_attr);
+ vmcb_set_seg(&save->cs, get_cs(), 0, -1U, code_seg_attr);
+ vmcb_set_seg(&save->ss, get_ss(), 0, -1U, data_seg_attr);
+ vmcb_set_seg(&save->ds, get_ds(), 0, -1U, data_seg_attr);
+ vmcb_set_seg(&save->gdtr, 0, get_gdt().address, get_gdt().size, 0);
+ vmcb_set_seg(&save->idtr, 0, get_idt().address, get_idt().size, 0);
+
+ ctrl->asid = 1;
+ save->cpl = 0;
+ save->efer = rdmsr(MSR_EFER);
+ asm volatile ("mov %%cr4, %0" : "=r"(save->cr4) : : "memory");
+ asm volatile ("mov %%cr3, %0" : "=r"(save->cr3) : : "memory");
+ asm volatile ("mov %%cr0, %0" : "=r"(save->cr0) : : "memory");
+ asm volatile ("mov %%dr7, %0" : "=r"(save->dr7) : : "memory");
+ asm volatile ("mov %%dr6, %0" : "=r"(save->dr6) : : "memory");
+ asm volatile ("mov %%cr2, %0" : "=r"(save->cr2) : : "memory");
+ save->g_pat = rdmsr(MSR_IA32_CR_PAT);
+ save->dbgctl = rdmsr(MSR_IA32_DEBUGCTLMSR);
+ ctrl->intercept = (1ULL << INTERCEPT_VMRUN) |
+ (1ULL << INTERCEPT_VMMCALL);
+
+ vmcb->save.rip = (u64)guest_rip;
+ vmcb->save.rsp = (u64)guest_rsp;
+ guest_regs.rdi = (u64)svm;
+}
+
+/*
+ * save/restore 64-bit general registers except rax, rip, rsp
+ * which are directly handed through the VMCB guest processor state
+ */
+#define SAVE_GPR_C \
+ "xchg %%rbx, guest_regs+0x20\n\t" \
+ "xchg %%rcx, guest_regs+0x10\n\t" \
+ "xchg %%rdx, guest_regs+0x18\n\t" \
+ "xchg %%rbp, guest_regs+0x30\n\t" \
+ "xchg %%rsi, guest_regs+0x38\n\t" \
+ "xchg %%rdi, guest_regs+0x40\n\t" \
+ "xchg %%r8, guest_regs+0x48\n\t" \
+ "xchg %%r9, guest_regs+0x50\n\t" \
+ "xchg %%r10, guest_regs+0x58\n\t" \
+ "xchg %%r11, guest_regs+0x60\n\t" \
+ "xchg %%r12, guest_regs+0x68\n\t" \
+ "xchg %%r13, guest_regs+0x70\n\t" \
+ "xchg %%r14, guest_regs+0x78\n\t" \
+ "xchg %%r15, guest_regs+0x80\n\t"
+
+#define LOAD_GPR_C SAVE_GPR_C
+
+/*
+ * selftests do not use interrupts so we dropped clgi/sti/cli/stgi
+ * for now. registers involved in LOAD/SAVE_GPR_C are eventually
+ * unmodified so they do not need to be in the clobber list.
+ */
+void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa)
+{
+ asm volatile (
+ "vmload %[vmcb_gpa]\n\t"
+ "mov rflags, %%r15\n\t" // rflags
+ "mov %%r15, 0x170(%[vmcb])\n\t"
+ "mov guest_regs, %%r15\n\t" // rax
+ "mov %%r15, 0x1f8(%[vmcb])\n\t"
+ LOAD_GPR_C
+ "vmrun %[vmcb_gpa]\n\t"
+ SAVE_GPR_C
+ "mov 0x170(%[vmcb]), %%r15\n\t" // rflags
+ "mov %%r15, rflags\n\t"
+ "mov 0x1f8(%[vmcb]), %%r15\n\t" // rax
+ "mov %%r15, guest_regs\n\t"
+ "vmsave %[vmcb_gpa]\n\t"
+ : : [vmcb] "r" (vmcb), [vmcb_gpa] "a" (vmcb_gpa)
+ : "r15", "memory");
+}
+
+bool nested_svm_supported(void)
+{
+ struct kvm_cpuid_entry2 *entry =
+ kvm_get_supported_cpuid_entry(0x80000001);
+
+ return entry->ecx & CPUID_SVM;
+}
+
+void nested_svm_check_supported(void)
+{
+ if (!nested_svm_supported()) {
+ print_skip("nested SVM not enabled");
+ exit(KSFT_SKIP);
+ }
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
new file mode 100644
index 000000000..a3489973e
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ucall support. A ucall is a "hypercall to userspace".
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+#include "kvm_util.h"
+
+#define UCALL_PIO_PORT ((uint16_t)0x1000)
+
+void ucall_init(struct kvm_vm *vm, void *arg)
+{
+}
+
+void ucall_uninit(struct kvm_vm *vm)
+{
+}
+
+void ucall(uint64_t cmd, int nargs, ...)
+{
+ struct ucall uc = {
+ .cmd = cmd,
+ };
+ va_list va;
+ int i;
+
+ nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS;
+
+ va_start(va, nargs);
+ for (i = 0; i < nargs; ++i)
+ uc.args[i] = va_arg(va, uint64_t);
+ va_end(va);
+
+ asm volatile("in %[port], %%al"
+ : : [port] "d" (UCALL_PIO_PORT), "D" (&uc) : "rax", "memory");
+}
+
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
+{
+ struct kvm_run *run = vcpu_state(vm, vcpu_id);
+ struct ucall ucall = {};
+
+ if (uc)
+ memset(uc, 0, sizeof(*uc));
+
+ if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) {
+ struct kvm_regs regs;
+
+ vcpu_regs_get(vm, vcpu_id, &regs);
+ memcpy(&ucall, addr_gva2hva(vm, (vm_vaddr_t)regs.rdi),
+ sizeof(ucall));
+
+ vcpu_run_complete_io(vm, vcpu_id);
+ if (uc)
+ memcpy(uc, &ucall, sizeof(ucall));
+ }
+
+ return ucall.cmd;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
new file mode 100644
index 000000000..2448b30e8
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -0,0 +1,553 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * tools/testing/selftests/kvm/lib/x86_64/vmx.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+#include "vmx.h"
+
+#define PAGE_SHIFT_4K 12
+
+#define KVM_EPT_PAGE_TABLE_MIN_PADDR 0x1c0000
+
+bool enable_evmcs;
+
+struct hv_enlightened_vmcs *current_evmcs;
+struct hv_vp_assist_page *current_vp_assist;
+
+struct eptPageTableEntry {
+ uint64_t readable:1;
+ uint64_t writable:1;
+ uint64_t executable:1;
+ uint64_t memory_type:3;
+ uint64_t ignore_pat:1;
+ uint64_t page_size:1;
+ uint64_t accessed:1;
+ uint64_t dirty:1;
+ uint64_t ignored_11_10:2;
+ uint64_t address:40;
+ uint64_t ignored_62_52:11;
+ uint64_t suppress_ve:1;
+};
+
+struct eptPageTablePointer {
+ uint64_t memory_type:3;
+ uint64_t page_walk_length:3;
+ uint64_t ad_enabled:1;
+ uint64_t reserved_11_07:5;
+ uint64_t address:40;
+ uint64_t reserved_63_52:12;
+};
+int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id)
+{
+ uint16_t evmcs_ver;
+
+ struct kvm_enable_cap enable_evmcs_cap = {
+ .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
+ .args[0] = (unsigned long)&evmcs_ver
+ };
+
+ vcpu_ioctl(vm, vcpu_id, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+ /* KVM should return supported EVMCS version range */
+ TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) &&
+ (evmcs_ver & 0xff) > 0,
+ "Incorrect EVMCS version range: %x:%x\n",
+ evmcs_ver & 0xff, evmcs_ver >> 8);
+
+ return evmcs_ver;
+}
+
+/* Allocate memory regions for nested VMX tests.
+ *
+ * Input Args:
+ * vm - The VM to allocate guest-virtual addresses in.
+ *
+ * Output Args:
+ * p_vmx_gva - The guest virtual address for the struct vmx_pages.
+ *
+ * Return:
+ * Pointer to structure with the addresses of the VMX areas.
+ */
+struct vmx_pages *
+vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva)
+{
+ vm_vaddr_t vmx_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ struct vmx_pages *vmx = addr_gva2hva(vm, vmx_gva);
+
+ /* Setup of a region of guest memory for the vmxon region. */
+ vmx->vmxon = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ vmx->vmxon_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmxon);
+ vmx->vmxon_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmxon);
+
+ /* Setup of a region of guest memory for a vmcs. */
+ vmx->vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ vmx->vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmcs);
+ vmx->vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmcs);
+
+ /* Setup of a region of guest memory for the MSR bitmap. */
+ vmx->msr = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ vmx->msr_hva = addr_gva2hva(vm, (uintptr_t)vmx->msr);
+ vmx->msr_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->msr);
+ memset(vmx->msr_hva, 0, getpagesize());
+
+ /* Setup of a region of guest memory for the shadow VMCS. */
+ vmx->shadow_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ vmx->shadow_vmcs_hva = addr_gva2hva(vm, (uintptr_t)vmx->shadow_vmcs);
+ vmx->shadow_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->shadow_vmcs);
+
+ /* Setup of a region of guest memory for the VMREAD and VMWRITE bitmaps. */
+ vmx->vmread = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ vmx->vmread_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmread);
+ vmx->vmread_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmread);
+ memset(vmx->vmread_hva, 0, getpagesize());
+
+ vmx->vmwrite = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ vmx->vmwrite_hva = addr_gva2hva(vm, (uintptr_t)vmx->vmwrite);
+ vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite);
+ memset(vmx->vmwrite_hva, 0, getpagesize());
+
+ /* Setup of a region of guest memory for the VP Assist page. */
+ vmx->vp_assist = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ vmx->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)vmx->vp_assist);
+ vmx->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vp_assist);
+
+ /* Setup of a region of guest memory for the enlightened VMCS. */
+ vmx->enlightened_vmcs = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ vmx->enlightened_vmcs_hva =
+ addr_gva2hva(vm, (uintptr_t)vmx->enlightened_vmcs);
+ vmx->enlightened_vmcs_gpa =
+ addr_gva2gpa(vm, (uintptr_t)vmx->enlightened_vmcs);
+
+ *p_vmx_gva = vmx_gva;
+ return vmx;
+}
+
+bool prepare_for_vmx_operation(struct vmx_pages *vmx)
+{
+ uint64_t feature_control;
+ uint64_t required;
+ unsigned long cr0;
+ unsigned long cr4;
+
+ /*
+ * Ensure bits in CR0 and CR4 are valid in VMX operation:
+ * - Bit X is 1 in _FIXED0: bit X is fixed to 1 in CRx.
+ * - Bit X is 0 in _FIXED1: bit X is fixed to 0 in CRx.
+ */
+ __asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0) : : "memory");
+ cr0 &= rdmsr(MSR_IA32_VMX_CR0_FIXED1);
+ cr0 |= rdmsr(MSR_IA32_VMX_CR0_FIXED0);
+ __asm__ __volatile__("mov %0, %%cr0" : : "r"(cr0) : "memory");
+
+ __asm__ __volatile__("mov %%cr4, %0" : "=r"(cr4) : : "memory");
+ cr4 &= rdmsr(MSR_IA32_VMX_CR4_FIXED1);
+ cr4 |= rdmsr(MSR_IA32_VMX_CR4_FIXED0);
+ /* Enable VMX operation */
+ cr4 |= X86_CR4_VMXE;
+ __asm__ __volatile__("mov %0, %%cr4" : : "r"(cr4) : "memory");
+
+ /*
+ * Configure IA32_FEATURE_CONTROL MSR to allow VMXON:
+ * Bit 0: Lock bit. If clear, VMXON causes a #GP.
+ * Bit 2: Enables VMXON outside of SMX operation. If clear, VMXON
+ * outside of SMX causes a #GP.
+ */
+ required = FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX;
+ required |= FEAT_CTL_LOCKED;
+ feature_control = rdmsr(MSR_IA32_FEAT_CTL);
+ if ((feature_control & required) != required)
+ wrmsr(MSR_IA32_FEAT_CTL, feature_control | required);
+
+ /* Enter VMX root operation. */
+ *(uint32_t *)(vmx->vmxon) = vmcs_revision();
+ if (vmxon(vmx->vmxon_gpa))
+ return false;
+
+ return true;
+}
+
+bool load_vmcs(struct vmx_pages *vmx)
+{
+ if (!enable_evmcs) {
+ /* Load a VMCS. */
+ *(uint32_t *)(vmx->vmcs) = vmcs_revision();
+ if (vmclear(vmx->vmcs_gpa))
+ return false;
+
+ if (vmptrld(vmx->vmcs_gpa))
+ return false;
+
+ /* Setup shadow VMCS, do not load it yet. */
+ *(uint32_t *)(vmx->shadow_vmcs) =
+ vmcs_revision() | 0x80000000ul;
+ if (vmclear(vmx->shadow_vmcs_gpa))
+ return false;
+ } else {
+ if (evmcs_vmptrld(vmx->enlightened_vmcs_gpa,
+ vmx->enlightened_vmcs))
+ return false;
+ current_evmcs->revision_id = EVMCS_VERSION;
+ }
+
+ return true;
+}
+
+/*
+ * Initialize the control fields to the most basic settings possible.
+ */
+static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
+{
+ uint32_t sec_exec_ctl = 0;
+
+ vmwrite(VIRTUAL_PROCESSOR_ID, 0);
+ vmwrite(POSTED_INTR_NV, 0);
+
+ vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS));
+
+ if (vmx->eptp_gpa) {
+ uint64_t ept_paddr;
+ struct eptPageTablePointer eptp = {
+ .memory_type = VMX_BASIC_MEM_TYPE_WB,
+ .page_walk_length = 3, /* + 1 */
+ .ad_enabled = !!(rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & VMX_EPT_VPID_CAP_AD_BITS),
+ .address = vmx->eptp_gpa >> PAGE_SHIFT_4K,
+ };
+
+ memcpy(&ept_paddr, &eptp, sizeof(ept_paddr));
+ vmwrite(EPT_POINTER, ept_paddr);
+ sec_exec_ctl |= SECONDARY_EXEC_ENABLE_EPT;
+ }
+
+ if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, sec_exec_ctl))
+ vmwrite(CPU_BASED_VM_EXEC_CONTROL,
+ rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS);
+ else {
+ vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS));
+ GUEST_ASSERT(!sec_exec_ctl);
+ }
+
+ vmwrite(EXCEPTION_BITMAP, 0);
+ vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
+ vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
+ vmwrite(CR3_TARGET_COUNT, 0);
+ vmwrite(VM_EXIT_CONTROLS, rdmsr(MSR_IA32_VMX_EXIT_CTLS) |
+ VM_EXIT_HOST_ADDR_SPACE_SIZE); /* 64-bit host */
+ vmwrite(VM_EXIT_MSR_STORE_COUNT, 0);
+ vmwrite(VM_EXIT_MSR_LOAD_COUNT, 0);
+ vmwrite(VM_ENTRY_CONTROLS, rdmsr(MSR_IA32_VMX_ENTRY_CTLS) |
+ VM_ENTRY_IA32E_MODE); /* 64-bit guest */
+ vmwrite(VM_ENTRY_MSR_LOAD_COUNT, 0);
+ vmwrite(VM_ENTRY_INTR_INFO_FIELD, 0);
+ vmwrite(TPR_THRESHOLD, 0);
+
+ vmwrite(CR0_GUEST_HOST_MASK, 0);
+ vmwrite(CR4_GUEST_HOST_MASK, 0);
+ vmwrite(CR0_READ_SHADOW, get_cr0());
+ vmwrite(CR4_READ_SHADOW, get_cr4());
+
+ vmwrite(MSR_BITMAP, vmx->msr_gpa);
+ vmwrite(VMREAD_BITMAP, vmx->vmread_gpa);
+ vmwrite(VMWRITE_BITMAP, vmx->vmwrite_gpa);
+}
+
+/*
+ * Initialize the host state fields based on the current host state, with
+ * the exception of HOST_RSP and HOST_RIP, which should be set by vmlaunch
+ * or vmresume.
+ */
+static inline void init_vmcs_host_state(void)
+{
+ uint32_t exit_controls = vmreadz(VM_EXIT_CONTROLS);
+
+ vmwrite(HOST_ES_SELECTOR, get_es());
+ vmwrite(HOST_CS_SELECTOR, get_cs());
+ vmwrite(HOST_SS_SELECTOR, get_ss());
+ vmwrite(HOST_DS_SELECTOR, get_ds());
+ vmwrite(HOST_FS_SELECTOR, get_fs());
+ vmwrite(HOST_GS_SELECTOR, get_gs());
+ vmwrite(HOST_TR_SELECTOR, get_tr());
+
+ if (exit_controls & VM_EXIT_LOAD_IA32_PAT)
+ vmwrite(HOST_IA32_PAT, rdmsr(MSR_IA32_CR_PAT));
+ if (exit_controls & VM_EXIT_LOAD_IA32_EFER)
+ vmwrite(HOST_IA32_EFER, rdmsr(MSR_EFER));
+ if (exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+ vmwrite(HOST_IA32_PERF_GLOBAL_CTRL,
+ rdmsr(MSR_CORE_PERF_GLOBAL_CTRL));
+
+ vmwrite(HOST_IA32_SYSENTER_CS, rdmsr(MSR_IA32_SYSENTER_CS));
+
+ vmwrite(HOST_CR0, get_cr0());
+ vmwrite(HOST_CR3, get_cr3());
+ vmwrite(HOST_CR4, get_cr4());
+ vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
+ vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
+ vmwrite(HOST_TR_BASE,
+ get_desc64_base((struct desc64 *)(get_gdt().address + get_tr())));
+ vmwrite(HOST_GDTR_BASE, get_gdt().address);
+ vmwrite(HOST_IDTR_BASE, get_idt().address);
+ vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
+ vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
+}
+
+/*
+ * Initialize the guest state fields essentially as a clone of
+ * the host state fields. Some host state fields have fixed
+ * values, and we set the corresponding guest state fields accordingly.
+ */
+static inline void init_vmcs_guest_state(void *rip, void *rsp)
+{
+ vmwrite(GUEST_ES_SELECTOR, vmreadz(HOST_ES_SELECTOR));
+ vmwrite(GUEST_CS_SELECTOR, vmreadz(HOST_CS_SELECTOR));
+ vmwrite(GUEST_SS_SELECTOR, vmreadz(HOST_SS_SELECTOR));
+ vmwrite(GUEST_DS_SELECTOR, vmreadz(HOST_DS_SELECTOR));
+ vmwrite(GUEST_FS_SELECTOR, vmreadz(HOST_FS_SELECTOR));
+ vmwrite(GUEST_GS_SELECTOR, vmreadz(HOST_GS_SELECTOR));
+ vmwrite(GUEST_LDTR_SELECTOR, 0);
+ vmwrite(GUEST_TR_SELECTOR, vmreadz(HOST_TR_SELECTOR));
+ vmwrite(GUEST_INTR_STATUS, 0);
+ vmwrite(GUEST_PML_INDEX, 0);
+
+ vmwrite(VMCS_LINK_POINTER, -1ll);
+ vmwrite(GUEST_IA32_DEBUGCTL, 0);
+ vmwrite(GUEST_IA32_PAT, vmreadz(HOST_IA32_PAT));
+ vmwrite(GUEST_IA32_EFER, vmreadz(HOST_IA32_EFER));
+ vmwrite(GUEST_IA32_PERF_GLOBAL_CTRL,
+ vmreadz(HOST_IA32_PERF_GLOBAL_CTRL));
+
+ vmwrite(GUEST_ES_LIMIT, -1);
+ vmwrite(GUEST_CS_LIMIT, -1);
+ vmwrite(GUEST_SS_LIMIT, -1);
+ vmwrite(GUEST_DS_LIMIT, -1);
+ vmwrite(GUEST_FS_LIMIT, -1);
+ vmwrite(GUEST_GS_LIMIT, -1);
+ vmwrite(GUEST_LDTR_LIMIT, -1);
+ vmwrite(GUEST_TR_LIMIT, 0x67);
+ vmwrite(GUEST_GDTR_LIMIT, 0xffff);
+ vmwrite(GUEST_IDTR_LIMIT, 0xffff);
+ vmwrite(GUEST_ES_AR_BYTES,
+ vmreadz(GUEST_ES_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_CS_AR_BYTES, 0xa09b);
+ vmwrite(GUEST_SS_AR_BYTES, 0xc093);
+ vmwrite(GUEST_DS_AR_BYTES,
+ vmreadz(GUEST_DS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_FS_AR_BYTES,
+ vmreadz(GUEST_FS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_GS_AR_BYTES,
+ vmreadz(GUEST_GS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_LDTR_AR_BYTES, 0x10000);
+ vmwrite(GUEST_TR_AR_BYTES, 0x8b);
+ vmwrite(GUEST_INTERRUPTIBILITY_INFO, 0);
+ vmwrite(GUEST_ACTIVITY_STATE, 0);
+ vmwrite(GUEST_SYSENTER_CS, vmreadz(HOST_IA32_SYSENTER_CS));
+ vmwrite(VMX_PREEMPTION_TIMER_VALUE, 0);
+
+ vmwrite(GUEST_CR0, vmreadz(HOST_CR0));
+ vmwrite(GUEST_CR3, vmreadz(HOST_CR3));
+ vmwrite(GUEST_CR4, vmreadz(HOST_CR4));
+ vmwrite(GUEST_ES_BASE, 0);
+ vmwrite(GUEST_CS_BASE, 0);
+ vmwrite(GUEST_SS_BASE, 0);
+ vmwrite(GUEST_DS_BASE, 0);
+ vmwrite(GUEST_FS_BASE, vmreadz(HOST_FS_BASE));
+ vmwrite(GUEST_GS_BASE, vmreadz(HOST_GS_BASE));
+ vmwrite(GUEST_LDTR_BASE, 0);
+ vmwrite(GUEST_TR_BASE, vmreadz(HOST_TR_BASE));
+ vmwrite(GUEST_GDTR_BASE, vmreadz(HOST_GDTR_BASE));
+ vmwrite(GUEST_IDTR_BASE, vmreadz(HOST_IDTR_BASE));
+ vmwrite(GUEST_DR7, 0x400);
+ vmwrite(GUEST_RSP, (uint64_t)rsp);
+ vmwrite(GUEST_RIP, (uint64_t)rip);
+ vmwrite(GUEST_RFLAGS, 2);
+ vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+ vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP));
+ vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP));
+}
+
+void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp)
+{
+ init_vmcs_control_fields(vmx);
+ init_vmcs_host_state();
+ init_vmcs_guest_state(guest_rip, guest_rsp);
+}
+
+bool nested_vmx_supported(void)
+{
+ struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+ return entry->ecx & CPUID_VMX;
+}
+
+void nested_vmx_check_supported(void)
+{
+ if (!nested_vmx_supported()) {
+ print_skip("nested VMX not enabled");
+ exit(KSFT_SKIP);
+ }
+}
+
+void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot)
+{
+ uint16_t index[4];
+ struct eptPageTableEntry *pml4e;
+
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
+ "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+ TEST_ASSERT((nested_paddr % vm->page_size) == 0,
+ "Nested physical address not on page boundary,\n"
+ " nested_paddr: 0x%lx vm->page_size: 0x%x",
+ nested_paddr, vm->page_size);
+ TEST_ASSERT((nested_paddr >> vm->page_shift) <= vm->max_gfn,
+ "Physical address beyond beyond maximum supported,\n"
+ " nested_paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->max_gfn, vm->page_size);
+ TEST_ASSERT((paddr % vm->page_size) == 0,
+ "Physical address not on page boundary,\n"
+ " paddr: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->page_size);
+ TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+ "Physical address beyond beyond maximum supported,\n"
+ " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->max_gfn, vm->page_size);
+
+ index[0] = (nested_paddr >> 12) & 0x1ffu;
+ index[1] = (nested_paddr >> 21) & 0x1ffu;
+ index[2] = (nested_paddr >> 30) & 0x1ffu;
+ index[3] = (nested_paddr >> 39) & 0x1ffu;
+
+ /* Allocate page directory pointer table if not present. */
+ pml4e = vmx->eptp_hva;
+ if (!pml4e[index[3]].readable) {
+ pml4e[index[3]].address = vm_phy_page_alloc(vm,
+ KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot)
+ >> vm->page_shift;
+ pml4e[index[3]].writable = true;
+ pml4e[index[3]].readable = true;
+ pml4e[index[3]].executable = true;
+ }
+
+ /* Allocate page directory table if not present. */
+ struct eptPageTableEntry *pdpe;
+ pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+ if (!pdpe[index[2]].readable) {
+ pdpe[index[2]].address = vm_phy_page_alloc(vm,
+ KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot)
+ >> vm->page_shift;
+ pdpe[index[2]].writable = true;
+ pdpe[index[2]].readable = true;
+ pdpe[index[2]].executable = true;
+ }
+
+ /* Allocate page table if not present. */
+ struct eptPageTableEntry *pde;
+ pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+ if (!pde[index[1]].readable) {
+ pde[index[1]].address = vm_phy_page_alloc(vm,
+ KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot)
+ >> vm->page_shift;
+ pde[index[1]].writable = true;
+ pde[index[1]].readable = true;
+ pde[index[1]].executable = true;
+ }
+
+ /* Fill in page table entry. */
+ struct eptPageTableEntry *pte;
+ pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+ pte[index[0]].address = paddr >> vm->page_shift;
+ pte[index[0]].writable = true;
+ pte[index[0]].readable = true;
+ pte[index[0]].executable = true;
+
+ /*
+ * For now mark these as accessed and dirty because the only
+ * testcase we have needs that. Can be reconsidered later.
+ */
+ pte[index[0]].accessed = true;
+ pte[index[0]].dirty = true;
+}
+
+/*
+ * Map a range of EPT guest physical addresses to the VM's physical address
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * nested_paddr - Nested guest physical address to map
+ * paddr - VM Physical Address
+ * size - The size of the range to map
+ * eptp_memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within the VM given by vm, creates a nested guest translation for the
+ * page range starting at nested_paddr to the page range starting at paddr.
+ */
+void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint64_t nested_paddr, uint64_t paddr, uint64_t size,
+ uint32_t eptp_memslot)
+{
+ size_t page_size = vm->page_size;
+ size_t npages = size / page_size;
+
+ TEST_ASSERT(nested_paddr + size > nested_paddr, "Vaddr overflow");
+ TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
+
+ while (npages--) {
+ nested_pg_map(vmx, vm, nested_paddr, paddr, eptp_memslot);
+ nested_paddr += page_size;
+ paddr += page_size;
+ }
+}
+
+/* Prepare an identity extended page table that maps all the
+ * physical pages in VM.
+ */
+void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t memslot, uint32_t eptp_memslot)
+{
+ sparsebit_idx_t i, last;
+ struct userspace_mem_region *region =
+ memslot2region(vm, memslot);
+
+ i = (region->region.guest_phys_addr >> vm->page_shift) - 1;
+ last = i + (region->region.memory_size >> vm->page_shift);
+ for (;;) {
+ i = sparsebit_next_clear(region->unused_phy_pages, i);
+ if (i > last)
+ break;
+
+ nested_map(vmx, vm,
+ (uint64_t)i << vm->page_shift,
+ (uint64_t)i << vm->page_shift,
+ 1 << vm->page_shift,
+ eptp_memslot);
+ }
+}
+
+void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t eptp_memslot)
+{
+ vmx->eptp = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp);
+ vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp);
+}
+
+void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm,
+ uint32_t eptp_memslot)
+{
+ vmx->apic_access = (void *)vm_vaddr_alloc(vm, getpagesize(),
+ 0x10000, 0, 0);
+ vmx->apic_access_hva = addr_gva2hva(vm, (uintptr_t)vmx->apic_access);
+ vmx->apic_access_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->apic_access);
+}