summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/testing/selftests/bpf/verifier/value_ptr_arith.c229
-rw-r--r--tools/testing/selftests/kvm/.gitignore1
-rw-r--r--tools/testing/selftests/kvm/Makefile1
-rw-r--r--tools/testing/selftests/kvm/aarch64/get-reg-list.c3
-rw-r--r--tools/testing/selftests/kvm/access_tracking_perf_test.c429
-rw-r--r--tools/testing/selftests/kvm/dirty_log_perf_test.c1
-rw-r--r--tools/testing/selftests/kvm/steal_time.c2
-rw-r--r--tools/testing/selftests/vm/userfaultfd.c6
8 files changed, 668 insertions, 4 deletions
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index a3e593ddfafc..2debba4e8a3a 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -1,4 +1,233 @@
{
+ "map access: known scalar += value_ptr unknown vs const",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs unknown",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs const (ne)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs const (eq)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (eq)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (lt)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (gt)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
"map access: known scalar += value_ptr from different maps",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 06a351b4f93b..0709af0144c8 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -38,6 +38,7 @@
/x86_64/xen_vmcall_test
/x86_64/xss_msr_test
/x86_64/vmx_pmu_msrs_test
+/access_tracking_perf_test
/demand_paging_test
/dirty_log_test
/dirty_log_perf_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index b853be2ae3c6..5832f510a16c 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -71,6 +71,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
+TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
TEST_GEN_PROGS_x86_64 += demand_paging_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index a16c8f05366c..cc898181faab 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -1019,7 +1019,8 @@ static __u64 sve_rejects_set[] = {
#define VREGS_SUBLIST \
{ "vregs", .regs = vregs, .regs_n = ARRAY_SIZE(vregs), }
#define PMU_SUBLIST \
- { "pmu", .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), }
+ { "pmu", .capability = KVM_CAP_ARM_PMU_V3, .feature = KVM_ARM_VCPU_PMU_V3, \
+ .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), }
#define SVE_SUBLIST \
{ "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \
.regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \
diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
new file mode 100644
index 000000000000..e2baa187a21e
--- /dev/null
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -0,0 +1,429 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * access_tracking_perf_test
+ *
+ * Copyright (C) 2021, Google, Inc.
+ *
+ * This test measures the performance effects of KVM's access tracking.
+ * Access tracking is driven by the MMU notifiers test_young, clear_young, and
+ * clear_flush_young. These notifiers do not have a direct userspace API,
+ * however the clear_young notifier can be triggered by marking a pages as idle
+ * in /sys/kernel/mm/page_idle/bitmap. This test leverages that mechanism to
+ * enable access tracking on guest memory.
+ *
+ * To measure performance this test runs a VM with a configurable number of
+ * vCPUs that each touch every page in disjoint regions of memory. Performance
+ * is measured in the time it takes all vCPUs to finish touching their
+ * predefined region.
+ *
+ * Note that a deterministic correctness test of access tracking is not possible
+ * by using page_idle as it exists today. This is for a few reasons:
+ *
+ * 1. page_idle only issues clear_young notifiers, which lack a TLB flush. This
+ * means subsequent guest accesses are not guaranteed to see page table
+ * updates made by KVM until some time in the future.
+ *
+ * 2. page_idle only operates on LRU pages. Newly allocated pages are not
+ * immediately allocated to LRU lists. Instead they are held in a "pagevec",
+ * which is drained to LRU lists some time in the future. There is no
+ * userspace API to force this drain to occur.
+ *
+ * These limitations are worked around in this test by using a large enough
+ * region of memory for each vCPU such that the number of translations cached in
+ * the TLB and the number of pages held in pagevecs are a small fraction of the
+ * overall workload. And if either of those conditions are not true this test
+ * will fail rather than silently passing.
+ */
+#include <inttypes.h>
+#include <limits.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include "kvm_util.h"
+#include "test_util.h"
+#include "perf_test_util.h"
+#include "guest_modes.h"
+
+/* Global variable used to synchronize all of the vCPU threads. */
+static int iteration = -1;
+
+/* Defines what vCPU threads should do during a given iteration. */
+static enum {
+ /* Run the vCPU to access all its memory. */
+ ITERATION_ACCESS_MEMORY,
+ /* Mark the vCPU's memory idle in page_idle. */
+ ITERATION_MARK_IDLE,
+} iteration_work;
+
+/* Set to true when vCPU threads should exit. */
+static bool done;
+
+/* The iteration that was last completed by each vCPU. */
+static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
+
+/* Whether to overlap the regions of memory vCPUs access. */
+static bool overlap_memory_access;
+
+struct test_params {
+ /* The backing source for the region of memory. */
+ enum vm_mem_backing_src_type backing_src;
+
+ /* The amount of memory to allocate for each vCPU. */
+ uint64_t vcpu_memory_bytes;
+
+ /* The number of vCPUs to create in the VM. */
+ int vcpus;
+};
+
+static uint64_t pread_uint64(int fd, const char *filename, uint64_t index)
+{
+ uint64_t value;
+ off_t offset = index * sizeof(value);
+
+ TEST_ASSERT(pread(fd, &value, sizeof(value), offset) == sizeof(value),
+ "pread from %s offset 0x%" PRIx64 " failed!",
+ filename, offset);
+
+ return value;
+
+}
+
+#define PAGEMAP_PRESENT (1ULL << 63)
+#define PAGEMAP_PFN_MASK ((1ULL << 55) - 1)
+
+static uint64_t lookup_pfn(int pagemap_fd, struct kvm_vm *vm, uint64_t gva)
+{
+ uint64_t hva = (uint64_t) addr_gva2hva(vm, gva);
+ uint64_t entry;
+ uint64_t pfn;
+
+ entry = pread_uint64(pagemap_fd, "pagemap", hva / getpagesize());
+ if (!(entry & PAGEMAP_PRESENT))
+ return 0;
+
+ pfn = entry & PAGEMAP_PFN_MASK;
+ if (!pfn) {
+ print_skip("Looking up PFNs requires CAP_SYS_ADMIN");
+ exit(KSFT_SKIP);
+ }
+
+ return pfn;
+}
+
+static bool is_page_idle(int page_idle_fd, uint64_t pfn)
+{
+ uint64_t bits = pread_uint64(page_idle_fd, "page_idle", pfn / 64);
+
+ return !!((bits >> (pfn % 64)) & 1);
+}
+
+static void mark_page_idle(int page_idle_fd, uint64_t pfn)
+{
+ uint64_t bits = 1ULL << (pfn % 64);
+
+ TEST_ASSERT(pwrite(page_idle_fd, &bits, 8, 8 * (pfn / 64)) == 8,
+ "Set page_idle bits for PFN 0x%" PRIx64, pfn);
+}
+
+static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id)
+{
+ uint64_t base_gva = perf_test_args.vcpu_args[vcpu_id].gva;
+ uint64_t pages = perf_test_args.vcpu_args[vcpu_id].pages;
+ uint64_t page;
+ uint64_t still_idle = 0;
+ uint64_t no_pfn = 0;
+ int page_idle_fd;
+ int pagemap_fd;
+
+ /* If vCPUs are using an overlapping region, let vCPU 0 mark it idle. */
+ if (overlap_memory_access && vcpu_id)
+ return;
+
+ page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
+ TEST_ASSERT(page_idle_fd > 0, "Failed to open page_idle.");
+
+ pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+ TEST_ASSERT(pagemap_fd > 0, "Failed to open pagemap.");
+
+ for (page = 0; page < pages; page++) {
+ uint64_t gva = base_gva + page * perf_test_args.guest_page_size;
+ uint64_t pfn = lookup_pfn(pagemap_fd, vm, gva);
+
+ if (!pfn) {
+ no_pfn++;
+ continue;
+ }
+
+ if (is_page_idle(page_idle_fd, pfn)) {
+ still_idle++;
+ continue;
+ }
+
+ mark_page_idle(page_idle_fd, pfn);
+ }
+
+ /*
+ * Assumption: Less than 1% of pages are going to be swapped out from
+ * under us during this test.
+ */
+ TEST_ASSERT(no_pfn < pages / 100,
+ "vCPU %d: No PFN for %" PRIu64 " out of %" PRIu64 " pages.",
+ vcpu_id, no_pfn, pages);
+
+ /*
+ * Test that at least 90% of memory has been marked idle (the rest might
+ * not be marked idle because the pages have not yet made it to an LRU
+ * list or the translations are still cached in the TLB). 90% is
+ * arbitrary; high enough that we ensure most memory access went through
+ * access tracking but low enough as to not make the test too brittle
+ * over time and across architectures.
+ */
+ TEST_ASSERT(still_idle < pages / 10,
+ "vCPU%d: Too many pages still idle (%"PRIu64 " out of %"
+ PRIu64 ").\n",
+ vcpu_id, still_idle, pages);
+
+ close(page_idle_fd);
+ close(pagemap_fd);
+}
+
+static void assert_ucall(struct kvm_vm *vm, uint32_t vcpu_id,
+ uint64_t expected_ucall)
+{
+ struct ucall uc;
+ uint64_t actual_ucall = get_ucall(vm, vcpu_id, &uc);
+
+ TEST_ASSERT(expected_ucall == actual_ucall,
+ "Guest exited unexpectedly (expected ucall %" PRIu64
+ ", got %" PRIu64 ")",
+ expected_ucall, actual_ucall);
+}
+
+static bool spin_wait_for_next_iteration(int *current_iteration)
+{
+ int last_iteration = *current_iteration;
+
+ do {
+ if (READ_ONCE(done))
+ return false;
+
+ *current_iteration = READ_ONCE(iteration);
+ } while (last_iteration == *current_iteration);
+
+ return true;
+}
+
+static void *vcpu_thread_main(void *arg)
+{
+ struct perf_test_vcpu_args *vcpu_args = arg;
+ struct kvm_vm *vm = perf_test_args.vm;
+ int vcpu_id = vcpu_args->vcpu_id;
+ int current_iteration = -1;
+
+ vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
+ while (spin_wait_for_next_iteration(&current_iteration)) {
+ switch (READ_ONCE(iteration_work)) {
+ case ITERATION_ACCESS_MEMORY:
+ vcpu_run(vm, vcpu_id);
+ assert_ucall(vm, vcpu_id, UCALL_SYNC);
+ break;
+ case ITERATION_MARK_IDLE:
+ mark_vcpu_memory_idle(vm, vcpu_id);
+ break;
+ };
+
+ vcpu_last_completed_iteration[vcpu_id] = current_iteration;
+ }
+
+ return NULL;
+}
+
+static void spin_wait_for_vcpu(int vcpu_id, int target_iteration)
+{
+ while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) !=
+ target_iteration) {
+ continue;
+ }
+}
+
+/* The type of memory accesses to perform in the VM. */
+enum access_type {
+ ACCESS_READ,
+ ACCESS_WRITE,
+};
+
+static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description)
+{
+ struct timespec ts_start;
+ struct timespec ts_elapsed;
+ int next_iteration;
+ int vcpu_id;
+
+ /* Kick off the vCPUs by incrementing iteration. */
+ next_iteration = ++iteration;
+
+ clock_gettime(CLOCK_MONOTONIC, &ts_start);
+
+ /* Wait for all vCPUs to finish the iteration. */
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++)
+ spin_wait_for_vcpu(vcpu_id, next_iteration);
+
+ ts_elapsed = timespec_elapsed(ts_start);
+ pr_info("%-30s: %ld.%09lds\n",
+ description, ts_elapsed.tv_sec, ts_elapsed.tv_nsec);
+}
+
+static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access,
+ const char *description)
+{
+ perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1;
+ sync_global_to_guest(vm, perf_test_args);
+ iteration_work = ITERATION_ACCESS_MEMORY;
+ run_iteration(vm, vcpus, description);
+}
+
+static void mark_memory_idle(struct kvm_vm *vm, int vcpus)
+{
+ /*
+ * Even though this parallelizes the work across vCPUs, this is still a
+ * very slow operation because page_idle forces the test to mark one pfn
+ * at a time and the clear_young notifier serializes on the KVM MMU
+ * lock.
+ */
+ pr_debug("Marking VM memory idle (slow)...\n");
+ iteration_work = ITERATION_MARK_IDLE;
+ run_iteration(vm, vcpus, "Mark memory idle");
+}
+
+static pthread_t *create_vcpu_threads(int vcpus)
+{
+ pthread_t *vcpu_threads;
+ int i;
+
+ vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
+ TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
+
+ for (i = 0; i < vcpus; i++) {
+ vcpu_last_completed_iteration[i] = iteration;
+ pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
+ &perf_test_args.vcpu_args[i]);
+ }
+
+ return vcpu_threads;
+}
+
+static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus)
+{
+ int i;
+
+ /* Set done to signal the vCPU threads to exit */
+ done = true;
+
+ for (i = 0; i < vcpus; i++)
+ pthread_join(vcpu_threads[i], NULL);
+}
+
+static void run_test(enum vm_guest_mode mode, void *arg)
+{
+ struct test_params *params = arg;
+ struct kvm_vm *vm;
+ pthread_t *vcpu_threads;
+ int vcpus = params->vcpus;
+
+ vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes,
+ params->backing_src);
+
+ perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
+ !overlap_memory_access);
+
+ vcpu_threads = create_vcpu_threads(vcpus);
+
+ pr_info("\n");
+ access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory");
+
+ /* As a control, read and write to the populated memory first. */
+ access_memory(vm, vcpus, ACCESS_WRITE, "Writing to populated memory");
+ access_memory(vm, vcpus, ACCESS_READ, "Reading from populated memory");
+
+ /* Repeat on memory that has been marked as idle. */
+ mark_memory_idle(vm, vcpus);
+ access_memory(vm, vcpus, ACCESS_WRITE, "Writing to idle memory");
+ mark_memory_idle(vm, vcpus);
+ access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory");
+
+ terminate_vcpu_threads(vcpu_threads, vcpus);
+ free(vcpu_threads);
+ perf_test_destroy_vm(vm);
+}
+
+static void help(char *name)
+{
+ puts("");
+ printf("usage: %s [-h] [-m mode] [-b vcpu_bytes] [-v vcpus] [-o] [-s mem_type]\n",
+ name);
+ puts("");
+ printf(" -h: Display this help message.");
+ guest_modes_help();
+ printf(" -b: specify the size of the memory region which should be\n"
+ " dirtied by each vCPU. e.g. 10M or 3G.\n"
+ " (default: 1G)\n");
+ printf(" -v: specify the number of vCPUs to run.\n");
+ printf(" -o: Overlap guest memory accesses instead of partitioning\n"
+ " them into a separate region of memory for each vCPU.\n");
+ printf(" -s: specify the type of memory that should be used to\n"
+ " back the guest data region.\n\n");
+ backing_src_help();
+ puts("");
+ exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+ struct test_params params = {
+ .backing_src = VM_MEM_SRC_ANONYMOUS,
+ .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE,
+ .vcpus = 1,
+ };
+ int page_idle_fd;
+ int opt;
+
+ guest_modes_append_default();
+
+ while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) {
+ switch (opt) {
+ case 'm':
+ guest_modes_cmdline(optarg);
+ break;
+ case 'b':
+ params.vcpu_memory_bytes = parse_size(optarg);
+ break;
+ case 'v':
+ params.vcpus = atoi(optarg);
+ break;
+ case 'o':
+ overlap_memory_access = true;
+ break;
+ case 's':
+ params.backing_src = parse_backing_src_type(optarg);
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
+
+ page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
+ if (page_idle_fd < 0) {
+ print_skip("CONFIG_IDLE_PAGE_TRACKING is not enabled");
+ exit(KSFT_SKIP);
+ }
+ close(page_idle_fd);
+
+ for_each_guest_mode(run_test, &params);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 04a2641261be..80cbd3a748c0 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -312,6 +312,7 @@ int main(int argc, char *argv[])
break;
case 'o':
p.partition_vcpu_memory_access = false;
+ break;
case 's':
p.backing_src = parse_backing_src_type(optarg);
break;
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index b0031f2d38fd..ecec30865a74 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -320,7 +320,7 @@ int main(int ac, char **av)
run_delay = get_run_delay();
pthread_create(&thread, &attr, do_steal_time, NULL);
do
- pthread_yield();
+ sched_yield();
while (get_run_delay() - run_delay < MIN_RUN_DELAY_NS);
pthread_join(thread, NULL);
run_delay = get_run_delay() - run_delay;
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index e363bdaff59d..2ea438e6b8b1 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -210,8 +210,10 @@ static void anon_release_pages(char *rel_area)
static void anon_allocate_area(void **alloc_area)
{
- if (posix_memalign(alloc_area, page_size, nr_pages * page_size))
- err("posix_memalign() failed");
+ *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (*alloc_area == MAP_FAILED)
+ err("mmap of anonymous memory failed");
}
static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)