aboutsummaryrefslogtreecommitdiff
path: root/tools/testing/selftests/kvm/lib
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/kvm/lib')
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/handlers.S126
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/processor.c131
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/ucall.c2
-rw-r--r--tools/testing/selftests/kvm/lib/elf.c6
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c404
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util_internal.h17
-rw-r--r--tools/testing/selftests/kvm/lib/perf_test_util.c8
-rw-r--r--tools/testing/selftests/kvm/lib/rbtree.c1
-rw-r--r--tools/testing/selftests/kvm/lib/s390x/processor.c17
-rw-r--r--tools/testing/selftests/kvm/lib/test_util.c51
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/apic.c45
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/handlers.S4
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c368
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/svm.c9
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/vmx.c52
15 files changed, 914 insertions, 327 deletions
diff --git a/tools/testing/selftests/kvm/lib/aarch64/handlers.S b/tools/testing/selftests/kvm/lib/aarch64/handlers.S
new file mode 100644
index 000000000000..0e443eadfac6
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/handlers.S
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+.macro save_registers
+ add sp, sp, #-16 * 17
+
+ stp x0, x1, [sp, #16 * 0]
+ stp x2, x3, [sp, #16 * 1]
+ stp x4, x5, [sp, #16 * 2]
+ stp x6, x7, [sp, #16 * 3]
+ stp x8, x9, [sp, #16 * 4]
+ stp x10, x11, [sp, #16 * 5]
+ stp x12, x13, [sp, #16 * 6]
+ stp x14, x15, [sp, #16 * 7]
+ stp x16, x17, [sp, #16 * 8]
+ stp x18, x19, [sp, #16 * 9]
+ stp x20, x21, [sp, #16 * 10]
+ stp x22, x23, [sp, #16 * 11]
+ stp x24, x25, [sp, #16 * 12]
+ stp x26, x27, [sp, #16 * 13]
+ stp x28, x29, [sp, #16 * 14]
+
+ /*
+ * This stores sp_el1 into ex_regs.sp so exception handlers can "look"
+ * at it. It will _not_ be used to restore the sp on return from the
+ * exception so handlers can not update it.
+ */
+ add x1, sp, #16 * 17
+ stp x30, x1, [sp, #16 * 15] /* x30, SP */
+
+ mrs x1, elr_el1
+ mrs x2, spsr_el1
+ stp x1, x2, [sp, #16 * 16] /* PC, PSTATE */
+.endm
+
+.macro restore_registers
+ ldp x1, x2, [sp, #16 * 16] /* PC, PSTATE */
+ msr elr_el1, x1
+ msr spsr_el1, x2
+
+ /* sp is not restored */
+ ldp x30, xzr, [sp, #16 * 15] /* x30, SP */
+
+ ldp x28, x29, [sp, #16 * 14]
+ ldp x26, x27, [sp, #16 * 13]
+ ldp x24, x25, [sp, #16 * 12]
+ ldp x22, x23, [sp, #16 * 11]
+ ldp x20, x21, [sp, #16 * 10]
+ ldp x18, x19, [sp, #16 * 9]
+ ldp x16, x17, [sp, #16 * 8]
+ ldp x14, x15, [sp, #16 * 7]
+ ldp x12, x13, [sp, #16 * 6]
+ ldp x10, x11, [sp, #16 * 5]
+ ldp x8, x9, [sp, #16 * 4]
+ ldp x6, x7, [sp, #16 * 3]
+ ldp x4, x5, [sp, #16 * 2]
+ ldp x2, x3, [sp, #16 * 1]
+ ldp x0, x1, [sp, #16 * 0]
+
+ add sp, sp, #16 * 17
+
+ eret
+.endm
+
+.pushsection ".entry.text", "ax"
+.balign 0x800
+.global vectors
+vectors:
+.popsection
+
+.set vector, 0
+
+/*
+ * Build an exception handler for vector and append a jump to it into
+ * vectors (while making sure that it's 0x80 aligned).
+ */
+.macro HANDLER, label
+handler_\label:
+ save_registers
+ mov x0, sp
+ mov x1, #vector
+ bl route_exception
+ restore_registers
+
+.pushsection ".entry.text", "ax"
+.balign 0x80
+ b handler_\label
+.popsection
+
+.set vector, vector + 1
+.endm
+
+.macro HANDLER_INVALID
+.pushsection ".entry.text", "ax"
+.balign 0x80
+/* This will abort so no need to save and restore registers. */
+ mov x0, #vector
+ mov x1, #0 /* ec */
+ mov x2, #0 /* valid_ec */
+ b kvm_exit_unexpected_exception
+.popsection
+
+.set vector, vector + 1
+.endm
+
+/*
+ * Caution: be sure to not add anything between the declaration of vectors
+ * above and these macro calls that will build the vectors table below it.
+ */
+ HANDLER_INVALID // Synchronous EL1t
+ HANDLER_INVALID // IRQ EL1t
+ HANDLER_INVALID // FIQ EL1t
+ HANDLER_INVALID // Error EL1t
+
+ HANDLER el1h_sync // Synchronous EL1h
+ HANDLER el1h_irq // IRQ EL1h
+ HANDLER el1h_fiq // FIQ EL1h
+ HANDLER el1h_error // Error EL1h
+
+ HANDLER el0_sync_64 // Synchronous 64-bit EL0
+ HANDLER el0_irq_64 // IRQ 64-bit EL0
+ HANDLER el0_fiq_64 // FIQ 64-bit EL0
+ HANDLER el0_error_64 // Error 64-bit EL0
+
+ HANDLER el0_sync_32 // Synchronous 32-bit EL0
+ HANDLER el0_irq_32 // IRQ 32-bit EL0
+ HANDLER el0_fiq_32 // FIQ 32-bit EL0
+ HANDLER el0_error_32 // Error 32-bit EL0
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index cee92d477dc0..9f49f6caafe5 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -6,14 +6,16 @@
*/
#include <linux/compiler.h>
+#include <assert.h>
#include "kvm_util.h"
#include "../kvm_util_internal.h"
#include "processor.h"
-#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
#define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN 0xac0000
+static vm_vaddr_t exception_handlers;
+
static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
{
return (v + vm->page_size) & ~(vm->page_size - 1);
@@ -72,19 +74,19 @@ static uint64_t __maybe_unused ptrs_per_pte(struct kvm_vm *vm)
return 1 << (vm->page_shift - 3);
}
-void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
+void virt_pgd_alloc(struct kvm_vm *vm)
{
if (!vm->pgd_created) {
vm_paddr_t paddr = vm_phy_pages_alloc(vm,
page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size,
- KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
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, uint64_t flags)
+static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ uint64_t flags)
{
uint8_t attr_idx = flags & 7;
uint64_t *ptep;
@@ -104,25 +106,19 @@ void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
paddr, vm->max_gfn, vm->page_size);
ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8;
- if (!*ptep) {
- *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
- *ptep |= 3;
- }
+ if (!*ptep)
+ *ptep = vm_alloc_page_table(vm) | 3;
switch (vm->pgtable_levels) {
case 4:
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8;
- if (!*ptep) {
- *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
- *ptep |= 3;
- }
+ if (!*ptep)
+ *ptep = vm_alloc_page_table(vm) | 3;
/* fall through */
case 3:
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8;
- if (!*ptep) {
- *ptep = vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
- *ptep |= 3;
- }
+ if (!*ptep)
+ *ptep = vm_alloc_page_table(vm) | 3;
/* fall through */
case 2:
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
@@ -135,12 +131,11 @@ void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
*ptep |= (attr_idx << 2) | (1 << 10) /* Access Flag */;
}
-void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- uint32_t pgd_memslot)
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
{
uint64_t attr_idx = 4; /* NORMAL (See DEFAULT_MAIR_EL1) */
- _virt_pg_map(vm, vaddr, paddr, pgd_memslot, attr_idx);
+ _virt_pg_map(vm, vaddr, paddr, attr_idx);
}
vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
@@ -302,7 +297,7 @@ void aarch64_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid,
DEFAULT_STACK_PGS * vm->page_size :
vm->page_size;
uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size,
- DEFAULT_ARM64_GUEST_STACK_VADDR_MIN, 0, 0);
+ DEFAULT_ARM64_GUEST_STACK_VADDR_MIN);
vm_vcpu_add(vm, vcpuid);
aarch64_vcpu_setup(vm, vcpuid, init);
@@ -334,6 +329,100 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
va_end(ap);
}
+void kvm_exit_unexpected_exception(int vector, uint64_t ec, bool valid_ec)
+{
+ ucall(UCALL_UNHANDLED, 3, vector, ec, valid_ec);
+ while (1)
+ ;
+}
+
void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
{
+ struct ucall uc;
+
+ if (get_ucall(vm, vcpuid, &uc) != UCALL_UNHANDLED)
+ return;
+
+ if (uc.args[2]) /* valid_ec */ {
+ assert(VECTOR_IS_SYNC(uc.args[0]));
+ TEST_FAIL("Unexpected exception (vector:0x%lx, ec:0x%lx)",
+ uc.args[0], uc.args[1]);
+ } else {
+ assert(!VECTOR_IS_SYNC(uc.args[0]));
+ TEST_FAIL("Unexpected exception (vector:0x%lx)",
+ uc.args[0]);
+ }
+}
+
+struct handlers {
+ handler_fn exception_handlers[VECTOR_NUM][ESR_EC_NUM];
+};
+
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ extern char vectors;
+
+ set_reg(vm, vcpuid, ARM64_SYS_REG(VBAR_EL1), (uint64_t)&vectors);
+}
+
+void route_exception(struct ex_regs *regs, int vector)
+{
+ struct handlers *handlers = (struct handlers *)exception_handlers;
+ bool valid_ec;
+ int ec = 0;
+
+ switch (vector) {
+ case VECTOR_SYNC_CURRENT:
+ case VECTOR_SYNC_LOWER_64:
+ ec = (read_sysreg(esr_el1) >> ESR_EC_SHIFT) & ESR_EC_MASK;
+ valid_ec = true;
+ break;
+ case VECTOR_IRQ_CURRENT:
+ case VECTOR_IRQ_LOWER_64:
+ case VECTOR_FIQ_CURRENT:
+ case VECTOR_FIQ_LOWER_64:
+ case VECTOR_ERROR_CURRENT:
+ case VECTOR_ERROR_LOWER_64:
+ ec = 0;
+ valid_ec = false;
+ break;
+ default:
+ valid_ec = false;
+ goto unexpected_exception;
+ }
+
+ if (handlers && handlers->exception_handlers[vector][ec])
+ return handlers->exception_handlers[vector][ec](regs);
+
+unexpected_exception:
+ kvm_exit_unexpected_exception(vector, ec, valid_ec);
+}
+
+void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+ vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers),
+ vm->page_size, 0, 0);
+
+ *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+}
+
+void vm_install_sync_handler(struct kvm_vm *vm, int vector, int ec,
+ void (*handler)(struct ex_regs *))
+{
+ struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
+
+ assert(VECTOR_IS_SYNC(vector));
+ assert(vector < VECTOR_NUM);
+ assert(ec < ESR_EC_NUM);
+ handlers->exception_handlers[vector][ec] = handler;
+}
+
+void vm_install_exception_handler(struct kvm_vm *vm, int vector,
+ void (*handler)(struct ex_regs *))
+{
+ struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
+
+ assert(!VECTOR_IS_SYNC(vector));
+ assert(vector < VECTOR_NUM);
+ handlers->exception_handlers[vector][0] = handler;
}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index 2f37b90ee1a9..e0b0164e9af8 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -14,7 +14,7 @@ static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa)
if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1))
return false;
- virt_pg_map(vm, gpa, gpa, 0);
+ virt_pg_map(vm, gpa, gpa);
ucall_exit_mmio_addr = (vm_vaddr_t *)gpa;
sync_global_to_guest(vm, ucall_exit_mmio_addr);
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index bc75a91e00a6..eac44f5d0db0 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -111,8 +111,7 @@ static void elfhdr_get(const char *filename, Elf64_Ehdr *hdrp)
* by the image and it needs to have sufficient available physical pages, to
* back the virtual pages used to load the image.
*/
-void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename,
- uint32_t data_memslot, uint32_t pgd_memslot)
+void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
{
off_t offset, offset_rv;
Elf64_Ehdr hdr;
@@ -164,8 +163,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename,
seg_vend |= vm->page_size - 1;
size_t seg_size = seg_vend - seg_vstart + 1;
- vm_vaddr_t vaddr = vm_vaddr_alloc(vm, seg_size, seg_vstart,
- data_memslot, pgd_memslot);
+ vm_vaddr_t vaddr = vm_vaddr_alloc(vm, seg_size, seg_vstart);
TEST_ASSERT(vaddr == seg_vstart, "Unable to allocate "
"virtual memory for segment at requested min addr,\n"
" segment idx: %u\n"
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index fc83f6c5902d..5b56b57b3c20 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -32,6 +32,34 @@ static void *align(void *x, size_t size)
}
/*
+ * Open KVM_DEV_PATH if available, otherwise exit the entire program.
+ *
+ * Input Args:
+ * flags - The flags to pass when opening KVM_DEV_PATH.
+ *
+ * Return:
+ * The opened file descriptor of /dev/kvm.
+ */
+static int _open_kvm_dev_path_or_exit(int flags)
+{
+ int fd;
+
+ fd = open(KVM_DEV_PATH, flags);
+ if (fd < 0) {
+ print_skip("%s not available, is KVM loaded? (errno: %d)",
+ KVM_DEV_PATH, errno);
+ exit(KSFT_SKIP);
+ }
+
+ return fd;
+}
+
+int open_kvm_dev_path_or_exit(void)
+{
+ return _open_kvm_dev_path_or_exit(O_RDONLY);
+}
+
+/*
* Capability
*
* Input Args:
@@ -52,12 +80,9 @@ int kvm_check_cap(long cap)
int ret;
int kvm_fd;
- kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
- if (kvm_fd < 0)
- exit(KSFT_SKIP);
-
+ kvm_fd = open_kvm_dev_path_or_exit();
ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap);
- TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n"
+ TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n"
" rc: %i errno: %i", ret, errno);
close(kvm_fd);
@@ -128,9 +153,7 @@ void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size)
static void vm_open(struct kvm_vm *vm, int perm)
{
- vm->kvm_fd = open(KVM_DEV_PATH, perm);
- if (vm->kvm_fd < 0)
- exit(KSFT_SKIP);
+ vm->kvm_fd = _open_kvm_dev_path_or_exit(perm);
if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
print_skip("immediate_exit not available");
@@ -152,6 +175,7 @@ const char *vm_guest_mode_string(uint32_t i)
[VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages",
[VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
[VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
+ [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
};
_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
@@ -169,6 +193,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
{ 40, 48, 0x1000, 12 },
{ 40, 48, 0x10000, 16 },
{ 0, 0, 0x1000, 12 },
+ { 47, 64, 0x1000, 12 },
};
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
"Missing new mode params?");
@@ -203,7 +228,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
TEST_ASSERT(vm != NULL, "Insufficient Memory");
INIT_LIST_HEAD(&vm->vcpus);
- INIT_LIST_HEAD(&vm->userspace_mem_regions);
+ vm->regions.gpa_tree = RB_ROOT;
+ vm->regions.hva_tree = RB_ROOT;
+ hash_init(vm->regions.slot_hash);
vm->mode = mode;
vm->type = 0;
@@ -252,6 +279,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms");
#endif
break;
+ case VM_MODE_P47V64_4K:
+ vm->pgtable_levels = 5;
+ break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
}
@@ -283,21 +313,50 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
return vm;
}
+/*
+ * VM Create with customized parameters
+ *
+ * Input Args:
+ * mode - VM Mode (e.g. VM_MODE_P52V48_4K)
+ * nr_vcpus - VCPU count
+ * slot0_mem_pages - Slot0 physical memory size
+ * extra_mem_pages - Non-slot0 physical memory total size
+ * num_percpu_pages - Per-cpu physical memory pages
+ * guest_code - Guest entry point
+ * vcpuids - VCPU IDs
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to opaque structure that describes the created VM.
+ *
+ * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K),
+ * with customized slot0 memory size, at least 512 pages currently.
+ * extra_mem_pages is only used to calculate the maximum page table size,
+ * no real memory allocation for non-slot0 memory in this function.
+ */
struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
- uint64_t extra_mem_pages, uint32_t num_percpu_pages,
- void *guest_code, uint32_t vcpuids[])
+ uint64_t slot0_mem_pages, uint64_t extra_mem_pages,
+ uint32_t num_percpu_pages, void *guest_code,
+ uint32_t vcpuids[])
{
+ uint64_t vcpu_pages, extra_pg_pages, pages;
+ struct kvm_vm *vm;
+ int i;
+
+ /* Force slot0 memory size not small than DEFAULT_GUEST_PHY_PAGES */
+ if (slot0_mem_pages < DEFAULT_GUEST_PHY_PAGES)
+ slot0_mem_pages = DEFAULT_GUEST_PHY_PAGES;
+
/* The maximum page table size for a memory region will be when the
* smallest pages are used. Considering each page contains x page
* table descriptors, the total extra size for page tables (for extra
* N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller
* than N/x*2.
*/
- uint64_t vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus;
- uint64_t extra_pg_pages = (extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2;
- uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
- struct kvm_vm *vm;
- int i;
+ vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus;
+ extra_pg_pages = (slot0_mem_pages + extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2;
+ pages = slot0_mem_pages + vcpu_pages + extra_pg_pages;
TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS),
"nr_vcpus = %d too large for host, max-vcpus = %d",
@@ -306,7 +365,7 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
pages = vm_adjust_num_guest_pages(mode, pages);
vm = vm_create(mode, pages, O_RDWR);
- kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+ kvm_vm_elf_load(vm, program_invocation_name);
#ifdef __x86_64__
vm_create_irqchip(vm);
@@ -316,10 +375,6 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
uint32_t vcpuid = vcpuids ? vcpuids[i] : i;
vm_vcpu_add_default(vm, vcpuid, guest_code);
-
-#ifdef __x86_64__
- vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
-#endif
}
return vm;
@@ -329,8 +384,8 @@ struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_me
uint32_t num_percpu_pages, void *guest_code,
uint32_t vcpuids[])
{
- return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, extra_mem_pages,
- num_percpu_pages, guest_code, vcpuids);
+ return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, DEFAULT_GUEST_PHY_PAGES,
+ extra_mem_pages, num_percpu_pages, guest_code, vcpuids);
}
struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
@@ -355,13 +410,14 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
*/
void kvm_vm_restart(struct kvm_vm *vmp, int perm)
{
+ int ctr;
struct userspace_mem_region *region;
vm_open(vmp, perm);
if (vmp->has_irqchip)
vm_create_irqchip(vmp);
- list_for_each_entry(region, &vmp->userspace_mem_regions, list) {
+ hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) {
int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
" rc: %i errno: %i\n"
@@ -424,14 +480,21 @@ uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm)
static struct userspace_mem_region *
userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
{
- struct userspace_mem_region *region;
+ struct rb_node *node;
- list_for_each_entry(region, &vm->userspace_mem_regions, list) {
+ for (node = vm->regions.gpa_tree.rb_node; node; ) {
+ struct userspace_mem_region *region =
+ container_of(node, struct userspace_mem_region, gpa_node);
uint64_t existing_start = region->region.guest_phys_addr;
uint64_t existing_end = region->region.guest_phys_addr
+ region->region.memory_size - 1;
if (start <= existing_end && end >= existing_start)
return region;
+
+ if (start < existing_start)
+ node = node->rb_left;
+ else
+ node = node->rb_right;
}
return NULL;
@@ -546,11 +609,16 @@ void kvm_vm_release(struct kvm_vm *vmp)
}
static void __vm_mem_region_delete(struct kvm_vm *vm,
- struct userspace_mem_region *region)
+ struct userspace_mem_region *region,
+ bool unlink)
{
int ret;
- list_del(&region->list);
+ if (unlink) {
+ rb_erase(&region->gpa_node, &vm->regions.gpa_tree);
+ rb_erase(&region->hva_node, &vm->regions.hva_tree);
+ hash_del(&region->slot_node);
+ }
region->region.memory_size = 0;
ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
@@ -569,14 +637,16 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
*/
void kvm_vm_free(struct kvm_vm *vmp)
{
- struct userspace_mem_region *region, *tmp;
+ int ctr;
+ struct hlist_node *node;
+ struct userspace_mem_region *region;
if (vmp == NULL)
return;
/* Free userspace_mem_regions. */
- list_for_each_entry_safe(region, tmp, &vmp->userspace_mem_regions, list)
- __vm_mem_region_delete(vmp, region);
+ hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node)
+ __vm_mem_region_delete(vmp, region, false);
/* Free sparsebit arrays. */
sparsebit_free(&vmp->vpages_valid);
@@ -658,13 +728,64 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
return 0;
}
+static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree,
+ struct userspace_mem_region *region)
+{
+ struct rb_node **cur, *parent;
+
+ for (cur = &gpa_tree->rb_node, parent = NULL; *cur; ) {
+ struct userspace_mem_region *cregion;
+
+ cregion = container_of(*cur, typeof(*cregion), gpa_node);
+ parent = *cur;
+ if (region->region.guest_phys_addr <
+ cregion->region.guest_phys_addr)
+ cur = &(*cur)->rb_left;
+ else {
+ TEST_ASSERT(region->region.guest_phys_addr !=
+ cregion->region.guest_phys_addr,
+ "Duplicate GPA in region tree");
+
+ cur = &(*cur)->rb_right;
+ }
+ }
+
+ rb_link_node(&region->gpa_node, parent, cur);
+ rb_insert_color(&region->gpa_node, gpa_tree);
+}
+
+static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree,
+ struct userspace_mem_region *region)
+{
+ struct rb_node **cur, *parent;
+
+ for (cur = &hva_tree->rb_node, parent = NULL; *cur; ) {
+ struct userspace_mem_region *cregion;
+
+ cregion = container_of(*cur, typeof(*cregion), hva_node);
+ parent = *cur;
+ if (region->host_mem < cregion->host_mem)
+ cur = &(*cur)->rb_left;
+ else {
+ TEST_ASSERT(region->host_mem !=
+ cregion->host_mem,
+ "Duplicate HVA in region tree");
+
+ cur = &(*cur)->rb_right;
+ }
+ }
+
+ rb_link_node(&region->hva_node, parent, cur);
+ rb_insert_color(&region->hva_node, hva_tree);
+}
+
/*
* VM Userspace Memory Region Add
*
* Input Args:
* vm - Virtual Machine
- * backing_src - Storage source for this region.
- * NULL to use anonymous memory.
+ * src_type - Storage source for this region.
+ * NULL to use anonymous memory.
* guest_paddr - Starting guest physical address
* slot - KVM region slot
* npages - Number of physical pages
@@ -722,7 +843,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
(uint64_t) region->region.memory_size);
/* Confirm no region with the requested slot already exists. */
- list_for_each_entry(region, &vm->userspace_mem_regions, list) {
+ hash_for_each_possible(vm->regions.slot_hash, region, slot_node,
+ slot) {
if (region->region.slot != slot)
continue;
@@ -755,11 +877,30 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
if (alignment > 1)
region->mmap_size += alignment;
+ region->fd = -1;
+ if (backing_src_is_shared(src_type)) {
+ int memfd_flags = MFD_CLOEXEC;
+
+ if (src_type == VM_MEM_SRC_SHARED_HUGETLB)
+ memfd_flags |= MFD_HUGETLB;
+
+ region->fd = memfd_create("kvm_selftest", memfd_flags);
+ TEST_ASSERT(region->fd != -1,
+ "memfd_create failed, errno: %i", errno);
+
+ ret = ftruncate(region->fd, region->mmap_size);
+ TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno);
+
+ ret = fallocate(region->fd,
+ FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0,
+ region->mmap_size);
+ TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno);
+ }
+
region->mmap_start = mmap(NULL, region->mmap_size,
PROT_READ | PROT_WRITE,
- MAP_PRIVATE | MAP_ANONYMOUS
- | vm_mem_backing_src_alias(src_type)->flag,
- -1, 0);
+ vm_mem_backing_src_alias(src_type)->flag,
+ region->fd, 0);
TEST_ASSERT(region->mmap_start != MAP_FAILED,
"test_malloc failed, mmap_start: %p errno: %i",
region->mmap_start, errno);
@@ -793,8 +934,23 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
ret, errno, slot, flags,
guest_paddr, (uint64_t) region->region.memory_size);
- /* Add to linked-list of memory regions. */
- list_add(&region->list, &vm->userspace_mem_regions);
+ /* Add to quick lookup data structures */
+ vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region);
+ vm_userspace_mem_region_hva_insert(&vm->regions.hva_tree, region);
+ hash_add(vm->regions.slot_hash, &region->slot_node, slot);
+
+ /* If shared memory, create an alias. */
+ if (region->fd >= 0) {
+ region->mmap_alias = mmap(NULL, region->mmap_size,
+ PROT_READ | PROT_WRITE,
+ vm_mem_backing_src_alias(src_type)->flag,
+ region->fd, 0);
+ TEST_ASSERT(region->mmap_alias != MAP_FAILED,
+ "mmap of alias failed, errno: %i", errno);
+
+ /* Align host alias address */
+ region->host_alias = align(region->mmap_alias, alignment);
+ }
}
/*
@@ -817,10 +973,10 @@ memslot2region(struct kvm_vm *vm, uint32_t memslot)
{
struct userspace_mem_region *region;
- list_for_each_entry(region, &vm->userspace_mem_regions, list) {
+ hash_for_each_possible(vm->regions.slot_hash, region, slot_node,
+ memslot)
if (region->region.slot == memslot)
return region;
- }
fprintf(stderr, "No mem region with the requested slot found,\n"
" requested slot: %u\n", memslot);
@@ -905,7 +1061,7 @@ 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)
{
- __vm_mem_region_delete(vm, memslot2region(vm, slot));
+ __vm_mem_region_delete(vm, memslot2region(vm, slot), true);
}
/*
@@ -925,9 +1081,7 @@ static int vcpu_mmap_sz(void)
{
int dev_fd, ret;
- dev_fd = open(KVM_DEV_PATH, O_RDONLY);
- if (dev_fd < 0)
- exit(KSFT_SKIP);
+ dev_fd = open_kvm_dev_path_or_exit();
ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
TEST_ASSERT(ret >= sizeof(struct kvm_run),
@@ -1093,12 +1247,13 @@ va_found:
* a unique set of pages, with the minimum real allocation being at least
* a page.
*/
-vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
- uint32_t data_memslot, uint32_t pgd_memslot)
+vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min)
{
uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);
- virt_pgd_alloc(vm, pgd_memslot);
+ virt_pgd_alloc(vm);
+ vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages,
+ KVM_UTIL_MIN_PFN * vm->page_size, 0);
/*
* Find an unused range of virtual page addresses of at least
@@ -1108,13 +1263,9 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
/* Map the virtual pages. */
for (vm_vaddr_t vaddr = vaddr_start; pages > 0;
- pages--, vaddr += vm->page_size) {
- vm_paddr_t paddr;
-
- paddr = vm_phy_page_alloc(vm,
- KVM_UTIL_MIN_PFN * vm->page_size, data_memslot);
+ pages--, vaddr += vm->page_size, paddr += vm->page_size) {
- virt_pg_map(vm, vaddr, paddr, pgd_memslot);
+ virt_pg_map(vm, vaddr, paddr);
sparsebit_set(vm->vpages_mapped,
vaddr >> vm->page_shift);
@@ -1124,6 +1275,44 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
}
/*
+ * VM Virtual Address Allocate Pages
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Starting guest virtual address
+ *
+ * Allocates at least N system pages worth of bytes within the virtual address
+ * space of the vm.
+ */
+vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages)
+{
+ return vm_vaddr_alloc(vm, nr_pages * getpagesize(), KVM_UTIL_MIN_VADDR);
+}
+
+/*
+ * VM Virtual Address Allocate Page
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Starting guest virtual address
+ *
+ * Allocates at least one system page worth of bytes within the virtual address
+ * space of the vm.
+ */
+vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm)
+{
+ return vm_vaddr_alloc_pages(vm, 1);
+}
+
+/*
* Map a range of VM virtual address to the VM's physical address
*
* Input Args:
@@ -1141,7 +1330,7 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
* @npages starting at @vaddr to the page range starting at @paddr.
*/
void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- unsigned int npages, uint32_t pgd_memslot)
+ unsigned int npages)
{
size_t page_size = vm->page_size;
size_t size = npages * page_size;
@@ -1150,7 +1339,7 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
while (npages--) {
- virt_pg_map(vm, vaddr, paddr, pgd_memslot);
+ virt_pg_map(vm, vaddr, paddr);
vaddr += page_size;
paddr += page_size;
}
@@ -1177,16 +1366,14 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
{
struct userspace_mem_region *region;
- list_for_each_entry(region, &vm->userspace_mem_regions, list) {
- if ((gpa >= region->region.guest_phys_addr)
- && (gpa <= (region->region.guest_phys_addr
- + region->region.memory_size - 1)))
- return (void *) ((uintptr_t) region->host_mem
- + (gpa - region->region.guest_phys_addr));
+ region = userspace_mem_region_find(vm, gpa, gpa);
+ if (!region) {
+ TEST_FAIL("No vm physical memory at 0x%lx", gpa);
+ return NULL;
}
- TEST_FAIL("No vm physical memory at 0x%lx", gpa);
- return NULL;
+ return (void *)((uintptr_t)region->host_mem
+ + (gpa - region->region.guest_phys_addr));
}
/*
@@ -1208,15 +1395,22 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
*/
vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
{
- struct userspace_mem_region *region;
+ struct rb_node *node;
+
+ for (node = vm->regions.hva_tree.rb_node; node; ) {
+ struct userspace_mem_region *region =
+ container_of(node, struct userspace_mem_region, hva_node);
- list_for_each_entry(region, &vm->userspace_mem_regions, list) {
- if ((hva >= region->host_mem)
- && (hva <= (region->host_mem
- + region->region.memory_size - 1)))
- return (vm_paddr_t) ((uintptr_t)
- region->region.guest_phys_addr
- + (hva - (uintptr_t) region->host_mem));
+ if (hva >= region->host_mem) {
+ if (hva <= (region->host_mem
+ + region->region.memory_size - 1))
+ return (vm_paddr_t)((uintptr_t)
+ region->region.guest_phys_addr
+ + (hva - (uintptr_t)region->host_mem));
+
+ node = node->rb_right;
+ } else
+ node = node->rb_left;
}
TEST_FAIL("No mapping to a guest physical address, hva: %p", hva);
@@ -1224,6 +1418,42 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
}
/*
+ * Address VM physical to Host Virtual *alias*.
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * gpa - VM physical address
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Equivalent address within the host virtual *alias* area, or NULL
+ * (without failing the test) if the guest memory is not shared (so
+ * no alias exists).
+ *
+ * When vm_create() and related functions are called with a shared memory
+ * src_type, we also create a writable, shared alias mapping of the
+ * underlying guest memory. This allows the host to manipulate guest memory
+ * without mapping that memory in the guest's address space. And, for
+ * userfaultfd-based demand paging, we can do so without triggering userfaults.
+ */
+void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa)
+{
+ struct userspace_mem_region *region;
+ uintptr_t offset;
+
+ region = userspace_mem_region_find(vm, gpa, gpa);
+ if (!region)
+ return NULL;
+
+ if (!region->host_alias)
+ return NULL;
+
+ offset = gpa - region->region.guest_phys_addr;
+ return (void *) ((uintptr_t) region->host_alias + offset);
+}
+
+/*
* VM Create IRQ Chip
*
* Input Args:
@@ -1822,6 +2052,7 @@ int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
*/
void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
{
+ int ctr;
struct userspace_mem_region *region;
struct vcpu *vcpu;
@@ -1829,7 +2060,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd);
fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size);
fprintf(stream, "%*sMem Regions:\n", indent, "");
- list_for_each_entry(region, &vm->userspace_mem_regions, list) {
+ hash_for_each(vm->regions.slot_hash, ctr, region, slot_node) {
fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx "
"host_virt: %p\n", indent + 2, "",
(uint64_t) region->region.guest_phys_addr,
@@ -1978,6 +2209,14 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
return vm_phy_pages_alloc(vm, 1, paddr_min, memslot);
}
+/* Arbitrary minimum physical address used for virtual translation tables. */
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+
+vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm)
+{
+ return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+}
+
/*
* Address Guest Virtual to Host Virtual
*
@@ -2015,10 +2254,7 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm)
if (vm == NULL) {
/* Ensure that the KVM vendor-specific module is loaded. */
- f = fopen(KVM_DEV_PATH, "r");
- TEST_ASSERT(f != NULL, "Error in opening KVM dev file: %d",
- errno);
- fclose(f);
+ close(open_kvm_dev_path_or_exit());
}
f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r");
@@ -2041,7 +2277,7 @@ unsigned int vm_get_page_shift(struct kvm_vm *vm)
return vm->page_shift;
}
-unsigned int vm_get_max_gfn(struct kvm_vm *vm)
+uint64_t vm_get_max_gfn(struct kvm_vm *vm)
{
return vm->max_gfn;
}
@@ -2090,3 +2326,15 @@ unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size)
n = DIV_ROUND_UP(size, vm_guest_mode_params[mode].page_size);
return vm_adjust_num_guest_pages(mode, n);
}
+
+int vm_get_stats_fd(struct kvm_vm *vm)
+{
+ return ioctl(vm->fd, KVM_GET_STATS_FD, NULL);
+}
+
+int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+ return ioctl(vcpu->fd, KVM_GET_STATS_FD, NULL);
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index 91ce1b5d480b..a03febc24ba6 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -8,6 +8,9 @@
#ifndef SELFTEST_KVM_UTIL_INTERNAL_H
#define SELFTEST_KVM_UTIL_INTERNAL_H
+#include "linux/hashtable.h"
+#include "linux/rbtree.h"
+
#include "sparsebit.h"
struct userspace_mem_region {
@@ -16,9 +19,13 @@ struct userspace_mem_region {
int fd;
off_t offset;
void *host_mem;
+ void *host_alias;
void *mmap_start;
+ void *mmap_alias;
size_t mmap_size;
- struct list_head list;
+ struct rb_node gpa_node;
+ struct rb_node hva_node;
+ struct hlist_node slot_node;
};
struct vcpu {
@@ -31,6 +38,12 @@ struct vcpu {
uint32_t dirty_gfns_count;
};
+struct userspace_mem_regions {
+ struct rb_root gpa_tree;
+ struct rb_root hva_tree;
+ DECLARE_HASHTABLE(slot_hash, 9);
+};
+
struct kvm_vm {
int mode;
unsigned long type;
@@ -43,7 +56,7 @@ struct kvm_vm {
unsigned int va_bits;
uint64_t max_gfn;
struct list_head vcpus;
- struct list_head userspace_mem_regions;
+ struct userspace_mem_regions regions;
struct sparsebit *vpages_valid;
struct sparsebit *vpages_mapped;
bool has_irqchip;
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 81490b9b4e32..b488f4aefea8 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -2,6 +2,7 @@
/*
* Copyright (C) 2020, Google LLC.
*/
+#include <inttypes.h>
#include "kvm_util.h"
#include "perf_test_util.h"
@@ -68,7 +69,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
"Guest memory size is not guest page size aligned.");
- vm = vm_create_with_vcpus(mode, vcpus,
+ vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
(vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
0, guest_code, NULL);
@@ -80,7 +81,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
*/
TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
"Requested more guest memory than address space allows.\n"
- " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+ " guest pages: %" PRIx64 " max gfn: %" PRIx64
+ " vcpus: %d wss: %" PRIx64 "]\n",
guest_num_pages, vm_get_max_gfn(vm), vcpus,
vcpu_memory_bytes);
@@ -99,7 +101,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
guest_num_pages, 0);
/* Do mapping for the demand paging memory slot */
- virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+ virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages);
ucall_init(vm, NULL);
diff --git a/tools/testing/selftests/kvm/lib/rbtree.c b/tools/testing/selftests/kvm/lib/rbtree.c
new file mode 100644
index 000000000000..a703f0194ea3
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/rbtree.c
@@ -0,0 +1 @@
+#include "../../../../lib/rbtree.c"
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 0152f356c099..f87c7137598e 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -9,11 +9,9 @@
#include "kvm_util.h"
#include "../kvm_util_internal.h"
-#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
-
#define PAGES_PER_REGION 4
-void virt_pgd_alloc(struct kvm_vm *vm, uint32_t memslot)
+void virt_pgd_alloc(struct kvm_vm *vm)
{
vm_paddr_t paddr;
@@ -24,7 +22,7 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t memslot)
return;
paddr = vm_phy_pages_alloc(vm, PAGES_PER_REGION,
- KVM_GUEST_PAGE_TABLE_MIN_PADDR, memslot);
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
memset(addr_gpa2hva(vm, paddr), 0xff, PAGES_PER_REGION * vm->page_size);
vm->pgd = paddr;
@@ -36,12 +34,12 @@ void virt_pgd_alloc(struct kvm_vm *vm, uint32_t memslot)
* a page table (ri == 4). Returns a suitable region/segment table entry
* which points to the freshly allocated pages.
*/
-static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri, uint32_t memslot)
+static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri)
{
uint64_t taddr;
taddr = vm_phy_pages_alloc(vm, ri < 4 ? PAGES_PER_REGION : 1,
- KVM_GUEST_PAGE_TABLE_MIN_PADDR, memslot);
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
memset(addr_gpa2hva(vm, taddr), 0xff, PAGES_PER_REGION * vm->page_size);
return (taddr & REGION_ENTRY_ORIGIN)
@@ -49,8 +47,7 @@ static uint64_t virt_alloc_region(struct kvm_vm *vm, int ri, uint32_t memslot)
| ((ri < 4 ? (PAGES_PER_REGION - 1) : 0) & REGION_ENTRY_LENGTH);
}
-void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa,
- uint32_t memslot)
+void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa)
{
int ri, idx;
uint64_t *entry;
@@ -77,7 +74,7 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t gva, uint64_t gpa,
for (ri = 1; ri <= 4; ri++) {
idx = (gva >> (64 - 11 * ri)) & 0x7ffu;
if (entry[idx] & REGION_ENTRY_INVALID)
- entry[idx] = virt_alloc_region(vm, ri, memslot);
+ entry[idx] = virt_alloc_region(vm, ri);
entry = addr_gpa2hva(vm, entry[idx] & REGION_ENTRY_ORIGIN);
}
@@ -170,7 +167,7 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
vm->page_size);
stack_vaddr = vm_vaddr_alloc(vm, stack_size,
- DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0);
+ DEFAULT_GUEST_STACK_VADDR_MIN);
vm_vcpu_add(vm, vcpuid);
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 63d2bc7d757b..af1031fed97f 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -166,72 +166,89 @@ size_t get_def_hugetlb_pagesz(void)
return 0;
}
+#define ANON_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS)
+#define ANON_HUGE_FLAGS (ANON_FLAGS | MAP_HUGETLB)
+
const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i)
{
static const struct vm_mem_backing_src_alias aliases[] = {
[VM_MEM_SRC_ANONYMOUS] = {
.name = "anonymous",
- .flag = 0,
+ .flag = ANON_FLAGS,
},
[VM_MEM_SRC_ANONYMOUS_THP] = {
.name = "anonymous_thp",
- .flag = 0,
+ .flag = ANON_FLAGS,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB] = {
.name = "anonymous_hugetlb",
- .flag = MAP_HUGETLB,
+ .flag = ANON_HUGE_FLAGS,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_16KB] = {
.name = "anonymous_hugetlb_16kb",
- .flag = MAP_HUGETLB | MAP_HUGE_16KB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_16KB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_64KB] = {
.name = "anonymous_hugetlb_64kb",
- .flag = MAP_HUGETLB | MAP_HUGE_64KB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_64KB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_512KB] = {
.name = "anonymous_hugetlb_512kb",
- .flag = MAP_HUGETLB | MAP_HUGE_512KB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_512KB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_1MB] = {
.name = "anonymous_hugetlb_1mb",
- .flag = MAP_HUGETLB | MAP_HUGE_1MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_1MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_2MB] = {
.name = "anonymous_hugetlb_2mb",
- .flag = MAP_HUGETLB | MAP_HUGE_2MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_2MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_8MB] = {
.name = "anonymous_hugetlb_8mb",
- .flag = MAP_HUGETLB | MAP_HUGE_8MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_8MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_16MB] = {
.name = "anonymous_hugetlb_16mb",
- .flag = MAP_HUGETLB | MAP_HUGE_16MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_16MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_32MB] = {
.name = "anonymous_hugetlb_32mb",
- .flag = MAP_HUGETLB | MAP_HUGE_32MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_32MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_256MB] = {
.name = "anonymous_hugetlb_256mb",
- .flag = MAP_HUGETLB | MAP_HUGE_256MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_256MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_512MB] = {
.name = "anonymous_hugetlb_512mb",
- .flag = MAP_HUGETLB | MAP_HUGE_512MB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_512MB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_1GB] = {
.name = "anonymous_hugetlb_1gb",
- .flag = MAP_HUGETLB | MAP_HUGE_1GB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_1GB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_2GB] = {
.name = "anonymous_hugetlb_2gb",
- .flag = MAP_HUGETLB | MAP_HUGE_2GB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_2GB,
},
[VM_MEM_SRC_ANONYMOUS_HUGETLB_16GB] = {
.name = "anonymous_hugetlb_16gb",
- .flag = MAP_HUGETLB | MAP_HUGE_16GB,
+ .flag = ANON_HUGE_FLAGS | MAP_HUGE_16GB,
+ },
+ [VM_MEM_SRC_SHMEM] = {
+ .name = "shmem",
+ .flag = MAP_SHARED,
+ },
+ [VM_MEM_SRC_SHARED_HUGETLB] = {
+ .name = "shared_hugetlb",
+ /*
+ * No MAP_HUGETLB, we use MFD_HUGETLB instead. Since
+ * we're using "file backed" memory, we need to specify
+ * this when the FD is created, not when the area is
+ * mapped.
+ */
+ .flag = MAP_SHARED,
},
};
_Static_assert(ARRAY_SIZE(aliases) == NUM_SRC_TYPES,
@@ -250,10 +267,12 @@ size_t get_backing_src_pagesz(uint32_t i)
switch (i) {
case VM_MEM_SRC_ANONYMOUS:
+ case VM_MEM_SRC_SHMEM:
return getpagesize();
case VM_MEM_SRC_ANONYMOUS_THP:
return get_trans_hugepagesz();
case VM_MEM_SRC_ANONYMOUS_HUGETLB:
+ case VM_MEM_SRC_SHARED_HUGETLB:
return get_def_hugetlb_pagesz();
default:
return MAP_HUGE_PAGE_SIZE(flag);
diff --git a/tools/testing/selftests/kvm/lib/x86_64/apic.c b/tools/testing/selftests/kvm/lib/x86_64/apic.c
new file mode 100644
index 000000000000..7168e25c194e
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/apic.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * tools/testing/selftests/kvm/lib/x86_64/processor.c
+ *
+ * Copyright (C) 2021, Google LLC.
+ */
+
+#include "apic.h"
+
+void apic_disable(void)
+{
+ wrmsr(MSR_IA32_APICBASE,
+ rdmsr(MSR_IA32_APICBASE) &
+ ~(MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD));
+}
+
+void xapic_enable(void)
+{
+ uint64_t val = rdmsr(MSR_IA32_APICBASE);
+
+ /* Per SDM: to enable xAPIC when in x2APIC must first disable APIC */
+ if (val & MSR_IA32_APICBASE_EXTD) {
+ apic_disable();
+ wrmsr(MSR_IA32_APICBASE,
+ rdmsr(MSR_IA32_APICBASE) | MSR_IA32_APICBASE_ENABLE);
+ } else if (!(val & MSR_IA32_APICBASE_ENABLE)) {
+ wrmsr(MSR_IA32_APICBASE, val | MSR_IA32_APICBASE_ENABLE);
+ }
+
+ /*
+ * Per SDM: reset value of spurious interrupt vector register has the
+ * APIC software enabled bit=0. It must be enabled in addition to the
+ * enable bit in the MSR.
+ */
+ val = xapic_read_reg(APIC_SPIV) | APIC_SPIV_APIC_ENABLED;
+ xapic_write_reg(APIC_SPIV, val);
+}
+
+void x2apic_enable(void)
+{
+ wrmsr(MSR_IA32_APICBASE, rdmsr(MSR_IA32_APICBASE) |
+ MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD);
+ x2apic_write_reg(APIC_SPIV,
+ x2apic_read_reg(APIC_SPIV) | APIC_SPIV_APIC_ENABLED);
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
index aaf7bc7d2ce1..7629819734af 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/handlers.S
+++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S
@@ -54,9 +54,9 @@ idt_handlers:
.align 8
/* Fetch current address and append it to idt_handlers. */
- current_handler = .
+666 :
.pushsection .rodata
-.quad current_handler
+ .quad 666b
.popsection
.if ! \has_error
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index a8906e60a108..28cb881f440d 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -17,13 +17,10 @@
#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 {
+struct pageUpperEntry {
uint64_t present:1;
uint64_t writable:1;
uint64_t user:1;
@@ -33,37 +30,7 @@ struct pageMapL4Entry {
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 pfn:40;
uint64_t ignored_62_52:11;
uint64_t execute_disable:1;
};
@@ -79,7 +46,7 @@ struct pageTableEntry {
uint64_t reserved_07:1;
uint64_t global:1;
uint64_t ignored_11_09:3;
- uint64_t address:40;
+ uint64_t pfn:40;
uint64_t ignored_62_52:11;
uint64_t execute_disable:1;
};
@@ -207,96 +174,211 @@ void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
}
}
-void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
+void virt_pgd_alloc(struct kvm_vm *vm)
{
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 = vm_alloc_page_table(vm);
vm->pgd_created = true;
}
}
-void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- uint32_t pgd_memslot)
+static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr,
+ int level)
+{
+ uint64_t *page_table = addr_gpa2hva(vm, pt_pfn << vm->page_shift);
+ int index = vaddr >> (vm->page_shift + level * 9) & 0x1ffu;
+
+ return &page_table[index];
+}
+
+static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
+ uint64_t pt_pfn,
+ uint64_t vaddr,
+ uint64_t paddr,
+ int level,
+ enum x86_page_size page_size)
+{
+ struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
+
+ if (!pte->present) {
+ pte->writable = true;
+ pte->present = true;
+ pte->page_size = (level == page_size);
+ if (pte->page_size)
+ pte->pfn = paddr >> vm->page_shift;
+ else
+ pte->pfn = vm_alloc_page_table(vm) >> vm->page_shift;
+ } else {
+ /*
+ * Entry already present. Assert that the caller doesn't want
+ * a hugepage at this level, and that there isn't a hugepage at
+ * this level.
+ */
+ TEST_ASSERT(level != page_size,
+ "Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
+ page_size, vaddr);
+ TEST_ASSERT(!pte->page_size,
+ "Cannot create page table at level: %u, vaddr: 0x%lx\n",
+ level, vaddr);
+ }
+ return pte;
+}
+
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ enum x86_page_size page_size)
+{
+ const uint64_t pg_size = 1ull << ((page_size * 9) + 12);
+ struct pageUpperEntry *pml4e, *pdpe, *pde;
+ struct pageTableEntry *pte;
+
+ TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K,
+ "Unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+ TEST_ASSERT((vaddr % pg_size) == 0,
+ "Virtual address not aligned,\n"
+ "vaddr: 0x%lx page size: 0x%lx", vaddr, pg_size);
+ TEST_ASSERT(sparsebit_is_set(vm->vpages_valid, (vaddr >> vm->page_shift)),
+ "Invalid virtual address, vaddr: 0x%lx", vaddr);
+ TEST_ASSERT((paddr % pg_size) == 0,
+ "Physical address not aligned,\n"
+ " paddr: 0x%lx page size: 0x%lx", paddr, pg_size);
+ TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+ "Physical address beyond maximum supported,\n"
+ " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->max_gfn, vm->page_size);
+
+ /*
+ * Allocate upper level page tables, if not already present. Return
+ * early if a hugepage was created.
+ */
+ pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift,
+ vaddr, paddr, 3, page_size);
+ if (pml4e->page_size)
+ return;
+
+ pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, 2, page_size);
+ if (pdpe->page_size)
+ return;
+
+ pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, 1, page_size);
+ if (pde->page_size)
+ return;
+
+ /* Fill in page table entry. */
+ pte = virt_get_pte(vm, pde->pfn, vaddr, 0);
+ TEST_ASSERT(!pte->present,
+ "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
+ pte->pfn = paddr >> vm->page_shift;
+ pte->writable = true;
+ pte->present = 1;
+}
+
+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 pageMapL4Entry *pml4e;
+ 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((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);
+ /*
+ * 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;
- /* 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;
- }
+ 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]];
+}
- /* 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;
- }
+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);
- /* 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;
- }
+ return *(uint64_t *)pte;
+}
- /* 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 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 pageMapL4Entry *pml4e, *pml4e_start;
- struct pageDirectoryPointerEntry *pdpe, *pdpe_start;
- struct pageDirectoryEntry *pde, *pde_start;
+ struct pageUpperEntry *pml4e, *pml4e_start;
+ struct pageUpperEntry *pdpe, *pdpe_start;
+ struct pageUpperEntry *pde, *pde_start;
struct pageTableEntry *pte, *pte_start;
if (!vm->pgd_created)
@@ -307,8 +389,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
fprintf(stream, "%*s index hvaddr gpaddr "
"addr w exec dirty\n",
indent, "");
- pml4e_start = (struct pageMapL4Entry *) addr_gpa2hva(vm,
- vm->pgd);
+ pml4e_start = (struct pageUpperEntry *) addr_gpa2hva(vm, vm->pgd);
for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) {
pml4e = &pml4e_start[n1];
if (!pml4e->present)
@@ -317,11 +398,10 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
" %u\n",
indent, "",
pml4e - pml4e_start, pml4e,
- addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->address,
+ addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->pfn,
pml4e->writable, pml4e->execute_disable);
- pdpe_start = addr_gpa2hva(vm, pml4e->address
- * vm->page_size);
+ pdpe_start = addr_gpa2hva(vm, pml4e->pfn * vm->page_size);
for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) {
pdpe = &pdpe_start[n2];
if (!pdpe->present)
@@ -331,11 +411,10 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
indent, "",
pdpe - pdpe_start, pdpe,
addr_hva2gpa(vm, pdpe),
- (uint64_t) pdpe->address, pdpe->writable,
+ (uint64_t) pdpe->pfn, pdpe->writable,
pdpe->execute_disable);
- pde_start = addr_gpa2hva(vm,
- pdpe->address * vm->page_size);
+ pde_start = addr_gpa2hva(vm, pdpe->pfn * vm->page_size);
for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) {
pde = &pde_start[n3];
if (!pde->present)
@@ -344,11 +423,10 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
"0x%-12lx 0x%-10lx %u %u\n",
indent, "", pde - pde_start, pde,
addr_hva2gpa(vm, pde),
- (uint64_t) pde->address, pde->writable,
+ (uint64_t) pde->pfn, pde->writable,
pde->execute_disable);
- pte_start = addr_gpa2hva(vm,
- pde->address * vm->page_size);
+ pte_start = addr_gpa2hva(vm, pde->pfn * vm->page_size);
for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) {
pte = &pte_start[n4];
if (!pte->present)
@@ -359,7 +437,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
indent, "",
pte - pte_start, pte,
addr_hva2gpa(vm, pte),
- (uint64_t) pte->address,
+ (uint64_t) pte->pfn,
pte->writable,
pte->execute_disable,
pte->dirty,
@@ -480,9 +558,7 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
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 pageUpperEntry *pml4e, *pdpe, *pde;
struct pageTableEntry *pte;
TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
@@ -499,43 +575,39 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
if (!pml4e[index[3]].present)
goto unmapped_gva;
- pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+ pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size);
if (!pdpe[index[2]].present)
goto unmapped_gva;
- pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+ pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size);
if (!pde[index[1]].present)
goto unmapped_gva;
- pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+ pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size);
if (!pte[index[0]].present)
goto unmapped_gva;
- return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu);
+ return (pte[index[0]].pfn * 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)
+static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt)
{
if (!vm->gdt)
- vm->gdt = vm_vaddr_alloc(vm, getpagesize(),
- KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
+ vm->gdt = vm_vaddr_alloc_page(vm);
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)
+ int selector)
{
if (!vm->tss)
- vm->tss = vm_vaddr_alloc(vm, getpagesize(),
- KVM_UTIL_MIN_VADDR, gdt_memslot, pgd_memslot);
+ vm->tss = vm_vaddr_alloc_page(vm);
memset(segp, 0, sizeof(*segp));
segp->base = vm->tss;
@@ -546,7 +618,7 @@ static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp,
kvm_seg_fill_gdt_64bit(vm, segp);
}
-static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_memslot)
+static void vcpu_setup(struct kvm_vm *vm, int vcpuid)
{
struct kvm_sregs sregs;
@@ -555,7 +627,7 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m
sregs.idt.limit = 0;
- kvm_setup_gdt(vm, &sregs.gdt, gdt_memslot, pgd_memslot);
+ kvm_setup_gdt(vm, &sregs.gdt);
switch (vm->mode) {
case VM_MODE_PXXV48_4K:
@@ -567,7 +639,7 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m
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);
+ kvm_setup_tss_64bit(vm, &sregs.tr, 0x18);
break;
default:
@@ -584,11 +656,11 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
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);
+ DEFAULT_GUEST_STACK_VADDR_MIN);
/* Create VCPU */
vm_vcpu_add(vm, vcpuid);
- vcpu_setup(vm, vcpuid, 0, 0);
+ vcpu_setup(vm, vcpuid);
/* Setup guest general purpose registers */
vcpu_regs_get(vm, vcpuid, &regs);
@@ -600,6 +672,9 @@ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
/* Setup the MP state */
mp_state.mp_state = 0;
vcpu_set_mp_state(vm, vcpuid, &mp_state);
+
+ /* Setup supported CPUIDs */
+ vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
}
/*
@@ -657,9 +732,7 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
return cpuid;
cpuid = allocate_kvm_cpuid2();
- kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
- if (kvm_fd < 0)
- exit(KSFT_SKIP);
+ kvm_fd = open_kvm_dev_path_or_exit();
ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
@@ -691,9 +764,7 @@ uint64_t kvm_get_feature_msr(uint64_t msr_index)
buffer.header.nmsrs = 1;
buffer.entry.index = msr_index;
- kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
- if (kvm_fd < 0)
- exit(KSFT_SKIP);
+ kvm_fd = open_kvm_dev_path_or_exit();
r = ioctl(kvm_fd, KVM_GET_MSRS, &buffer.header);
TEST_ASSERT(r == 1, "KVM_GET_MSRS IOCTL failed,\n"
@@ -986,9 +1057,7 @@ 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);
+ kvm_fd = open_kvm_dev_path_or_exit();
nmsrs = kvm_get_num_msrs_fd(kvm_fd);
list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
@@ -1207,7 +1276,7 @@ static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
void kvm_exit_unexpected_vector(uint32_t value)
{
- outl(UNEXPECTED_VECTOR_PORT, value);
+ ucall(UCALL_UNHANDLED, 1, value);
}
void route_exception(struct ex_regs *regs)
@@ -1228,8 +1297,8 @@ 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);
+ vm->idt = vm_vaddr_alloc_page(vm);
+ vm->handlers = vm_vaddr_alloc_page(vm);
/* 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,
@@ -1250,8 +1319,8 @@ void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid)
*(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 *))
+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);
@@ -1260,16 +1329,13 @@ void vm_handle_exception(struct kvm_vm *vm, int vector,
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);
+ struct ucall uc;
+
+ if (get_ucall(vm, vcpuid, &uc) == UCALL_UNHANDLED) {
+ uint64_t vector = uc.args[0];
+
+ TEST_FAIL("Unexpected vectored event in guest (vector:0x%lx)",
+ vector);
}
}
@@ -1312,9 +1378,7 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void)
return cpuid;
cpuid = allocate_kvm_cpuid2();
- kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
- if (kvm_fd < 0)
- exit(KSFT_SKIP);
+ kvm_fd = open_kvm_dev_path_or_exit();
ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_HV_CPUID, cpuid);
TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_HV_CPUID failed %d %d\n",
diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c
index 827fe6028dd4..2ac98d70d02b 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/svm.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c
@@ -30,17 +30,14 @@ u64 rflags;
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);
+ vm_vaddr_t svm_gva = vm_vaddr_alloc_page(vm);
struct svm_test_data *svm = addr_gva2hva(vm, svm_gva);
- svm->vmcb = (void *)vm_vaddr_alloc(vm, getpagesize(),
- 0x10000, 0, 0);
+ svm->vmcb = (void *)vm_vaddr_alloc_page(vm);
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 = (void *)vm_vaddr_alloc_page(vm);
svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area);
svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area);
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 2448b30e8efa..d089d8b850b5 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -77,50 +77,48 @@ int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id)
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);
+ vm_vaddr_t vmx_gva = vm_vaddr_alloc_page(vm);
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 = (void *)vm_vaddr_alloc_page(vm);
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 = (void *)vm_vaddr_alloc_page(vm);
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 = (void *)vm_vaddr_alloc_page(vm);
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 = (void *)vm_vaddr_alloc_page(vm);
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 = (void *)vm_vaddr_alloc_page(vm);
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 = (void *)vm_vaddr_alloc_page(vm);
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 = (void *)vm_vaddr_alloc_page(vm);
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 = (void *)vm_vaddr_alloc_page(vm);
vmx->enlightened_vmcs_hva =
addr_gva2hva(vm, (uintptr_t)vmx->enlightened_vmcs);
vmx->enlightened_vmcs_gpa =
@@ -395,7 +393,7 @@ void nested_vmx_check_supported(void)
}
void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
- uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot)
+ uint64_t nested_paddr, uint64_t paddr)
{
uint16_t index[4];
struct eptPageTableEntry *pml4e;
@@ -428,9 +426,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
/* 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]].address = vm_alloc_page_table(vm) >> vm->page_shift;
pml4e[index[3]].writable = true;
pml4e[index[3]].readable = true;
pml4e[index[3]].executable = true;
@@ -440,9 +436,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
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]].address = vm_alloc_page_table(vm) >> vm->page_shift;
pdpe[index[2]].writable = true;
pdpe[index[2]].readable = true;
pdpe[index[2]].executable = true;
@@ -452,9 +446,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
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]].address = vm_alloc_page_table(vm) >> vm->page_shift;
pde[index[1]].writable = true;
pde[index[1]].readable = true;
pde[index[1]].executable = true;
@@ -494,8 +486,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
* 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)
+ uint64_t nested_paddr, uint64_t paddr, uint64_t size)
{
size_t page_size = vm->page_size;
size_t npages = size / page_size;
@@ -504,7 +495,7 @@ void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
while (npages--) {
- nested_pg_map(vmx, vm, nested_paddr, paddr, eptp_memslot);
+ nested_pg_map(vmx, vm, nested_paddr, paddr);
nested_paddr += page_size;
paddr += page_size;
}
@@ -514,7 +505,7 @@ void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
* physical pages in VM.
*/
void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
- uint32_t memslot, uint32_t eptp_memslot)
+ uint32_t memslot)
{
sparsebit_idx_t i, last;
struct userspace_mem_region *region =
@@ -530,24 +521,21 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
nested_map(vmx, vm,
(uint64_t)i << vm->page_shift,
(uint64_t)i << vm->page_shift,
- 1 << vm->page_shift,
- eptp_memslot);
+ 1 << vm->page_shift);
}
}
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 = (void *)vm_vaddr_alloc_page(vm);
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)
+void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm)
{
- vmx->apic_access = (void *)vm_vaddr_alloc(vm, getpagesize(),
- 0x10000, 0, 0);
+ vmx->apic_access = (void *)vm_vaddr_alloc_page(vm);
vmx->apic_access_hva = addr_gva2hva(vm, (uintptr_t)vmx->apic_access);
vmx->apic_access_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->apic_access);
}
Powered by cgit, Gruvboxed by Blaster4385.