aboutsummaryrefslogtreecommitdiff
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rw-r--r--tools/testing/cxl/Kbuild3
-rw-r--r--tools/testing/cxl/test/cxl.c68
-rw-r--r--tools/testing/cxl/test/mem.c99
-rw-r--r--tools/testing/cxl/test/mock.c30
-rw-r--r--tools/testing/cxl/test/mock.h6
-rw-r--r--tools/testing/kunit/kunit_kernel.py1
-rwxr-xr-xtools/testing/kunit/run_checks.py2
-rw-r--r--tools/testing/nvdimm/Kbuild8
-rw-r--r--tools/testing/nvdimm/dax_pmem_compat_test.c8
-rw-r--r--tools/testing/nvdimm/dax_pmem_core_test.c8
-rw-r--r--tools/testing/nvdimm/test/iomap.c43
-rw-r--r--tools/testing/nvdimm/test/ndtest.c4
-rw-r--r--tools/testing/nvdimm/test/nfit.c4
-rw-r--r--tools/testing/scatterlist/linux/mm.h3
-rw-r--r--tools/testing/selftests/Makefile3
-rw-r--r--tools/testing/selftests/alsa/.gitignore1
-rw-r--r--tools/testing/selftests/alsa/Makefile9
-rw-r--r--tools/testing/selftests/alsa/mixer-test.c705
-rw-r--r--tools/testing/selftests/arm64/abi/syscall-abi.c1
-rw-r--r--tools/testing/selftests/arm64/fp/sve-ptrace.c15
-rw-r--r--tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c11
-rw-r--r--tools/testing/selftests/arm64/mte/check_user_mem.c193
-rw-r--r--tools/testing/selftests/arm64/signal/test_signals.h1
-rw-r--r--tools/testing/selftests/arm64/signal/test_signals_utils.c34
-rw-r--r--tools/testing/selftests/arm64/signal/test_signals_utils.h2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/d_path.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/timer_crash.c32
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_link.c61
-rw-r--r--tools/testing/selftests/bpf/progs/test_d_path_check_types.c32
-rw-r--r--tools/testing/selftests/bpf/progs/test_sockmap_kern.h26
-rw-r--r--tools/testing/selftests/bpf/progs/test_stacktrace_map.c6
-rw-r--r--tools/testing/selftests/bpf/progs/test_tracepoint.c6
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_link.c6
-rw-r--r--tools/testing/selftests/bpf/progs/timer_crash.c54
-rw-r--r--tools/testing/selftests/bpf/test_lirc_mode2_user.c1
-rw-r--r--tools/testing/selftests/bpf/verifier/ringbuf.c95
-rw-r--r--tools/testing/selftests/bpf/verifier/spill_fill.c2
-rw-r--r--tools/testing/selftests/cgroup/cgroup_util.c15
-rw-r--r--tools/testing/selftests/cgroup/cgroup_util.h1
-rw-r--r--tools/testing/selftests/cgroup/test_memcontrol.c78
-rw-r--r--tools/testing/selftests/clone3/clone3.c2
-rwxr-xr-xtools/testing/selftests/cpufreq/main.sh2
-rw-r--r--tools/testing/selftests/damon/Makefile1
-rw-r--r--tools/testing/selftests/damon/sysfs.sh306
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh2
-rw-r--r--tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh3
-rw-r--r--tools/testing/selftests/exec/Makefile7
-rw-r--r--tools/testing/selftests/exec/null-argv.c78
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc2
-rw-r--r--tools/testing/selftests/futex/Makefile4
-rw-r--r--tools/testing/selftests/ir/ir_loopback.c10
-rw-r--r--tools/testing/selftests/kselftest_harness.h4
-rw-r--r--tools/testing/selftests/kvm/.gitignore6
-rw-r--r--tools/testing/selftests/kvm/Makefile24
-rw-r--r--tools/testing/selftests/kvm/aarch64/arch_timer.c7
-rw-r--r--tools/testing/selftests/kvm/aarch64/get-reg-list.c50
-rw-r--r--tools/testing/selftests/kvm/aarch64/vgic_irq.c857
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/gic.h26
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/gic_v3.h (renamed from tools/testing/selftests/kvm/lib/aarch64/gic_v3.h)12
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/processor.h3
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/vgic.h18
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h409
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util_base.h398
-rw-r--r--tools/testing/selftests/kvm/include/riscv/processor.h135
-rw-r--r--tools/testing/selftests/kvm/include/ucall_common.h59
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h52
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic.c66
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic_private.h11
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic_v3.c206
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/processor.c82
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/vgic.c107
-rw-r--r--tools/testing/selftests/kvm/lib/guest_modes.c59
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c129
-rw-r--r--tools/testing/selftests/kvm/lib/riscv/processor.c362
-rw-r--r--tools/testing/selftests/kvm/lib/riscv/ucall.c87
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c244
-rw-r--r--tools/testing/selftests/kvm/x86_64/amx_test.c450
-rw-r--r--tools/testing/selftests/kvm/x86_64/cpuid_test.c (renamed from tools/testing/selftests/kvm/x86_64/get_cpuid_test.c)30
-rw-r--r--tools/testing/selftests/kvm/x86_64/evmcs_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c434
-rw-r--r--tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c59
-rw-r--r--tools/testing/selftests/kvm/x86_64/smm_test.c3
-rw-r--r--tools/testing/selftests/kvm/x86_64/state_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c139
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c218
-rwxr-xr-xtools/testing/selftests/lkdtm/stack-entropy.sh16
-rw-r--r--tools/testing/selftests/memfd/memfd_test.c1
-rw-r--r--tools/testing/selftests/mincore/mincore_selftest.c20
-rw-r--r--tools/testing/selftests/mount_setattr/mount_setattr_test.c4
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh3
-rw-r--r--tools/testing/selftests/net/ioam6_parser.c5
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh44
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect.sh4
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh38
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh21
-rw-r--r--tools/testing/selftests/net/settings2
-rw-r--r--tools/testing/selftests/netfilter/.gitignore1
-rw-r--r--tools/testing/selftests/netfilter/Makefile4
-rw-r--r--tools/testing/selftests/netfilter/connect_close.c136
-rwxr-xr-xtools/testing/selftests/netfilter/nft_concat_range.sh74
-rwxr-xr-xtools/testing/selftests/netfilter/nft_fib.sh1
-rwxr-xr-xtools/testing/selftests/netfilter/nft_nat.sh157
-rwxr-xr-xtools/testing/selftests/netfilter/nft_queue.sh19
-rwxr-xr-xtools/testing/selftests/netfilter/nft_synproxy.sh117
-rwxr-xr-xtools/testing/selftests/netfilter/nft_zones_many.sh12
-rw-r--r--tools/testing/selftests/openat2/Makefile2
-rw-r--r--tools/testing/selftests/openat2/helpers.h12
-rw-r--r--tools/testing/selftests/openat2/openat2_test.c12
-rw-r--r--tools/testing/selftests/perf_events/sigtrap_threads.c17
-rw-r--r--tools/testing/selftests/pidfd/pidfd.h13
-rw-r--r--tools/testing/selftests/pidfd/pidfd_fdinfo_test.c22
-rw-r--r--tools/testing/selftests/pidfd/pidfd_test.c6
-rw-r--r--tools/testing/selftests/pidfd/pidfd_wait.c5
-rwxr-xr-xtools/testing/selftests/powerpc/security/mitigation-patching.sh5
-rw-r--r--tools/testing/selftests/powerpc/security/spectre_v2.c2
-rw-r--r--tools/testing/selftests/powerpc/signal/.gitignore2
-rw-r--r--tools/testing/selftests/powerpc/signal/Makefile2
-rw-r--r--tools/testing/selftests/powerpc/signal/sigreturn_kernel.c132
-rw-r--r--tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c43
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/console-badness.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-again.sh4
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-check-branches.sh4
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh4
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-find-errors.sh6
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-remote.sh25
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh16
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-console.sh10
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/torture.sh38
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/RUDE012
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot2
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE012
-rw-r--r--tools/testing/selftests/rseq/Makefile2
-rw-r--r--tools/testing/selftests/rseq/basic_percpu_ops_test.c2
-rw-r--r--tools/testing/selftests/rseq/compiler.h30
-rw-r--r--tools/testing/selftests/rseq/param_test.c8
-rw-r--r--tools/testing/selftests/rseq/rseq-abi.h151
-rw-r--r--tools/testing/selftests/rseq/rseq-arm.h110
-rw-r--r--tools/testing/selftests/rseq/rseq-arm64.h79
-rw-r--r--tools/testing/selftests/rseq/rseq-generic-thread-pointer.h25
-rw-r--r--tools/testing/selftests/rseq/rseq-mips.h71
-rw-r--r--tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h30
-rw-r--r--tools/testing/selftests/rseq/rseq-ppc.h128
-rw-r--r--tools/testing/selftests/rseq/rseq-s390.h55
-rw-r--r--tools/testing/selftests/rseq/rseq-skip.h2
-rw-r--r--tools/testing/selftests/rseq/rseq-thread-pointer.h19
-rw-r--r--tools/testing/selftests/rseq/rseq-x86-thread-pointer.h40
-rw-r--r--tools/testing/selftests/rseq/rseq-x86.h200
-rw-r--r--tools/testing/selftests/rseq/rseq.c164
-rw-r--r--tools/testing/selftests/rseq/rseq.h30
-rw-r--r--tools/testing/selftests/rtc/settings2
-rw-r--r--tools/testing/selftests/seccomp/Makefile2
-rw-r--r--tools/testing/selftests/sgx/Makefile2
-rw-r--r--tools/testing/selftests/sgx/load.c9
-rw-r--r--tools/testing/selftests/sgx/main.c9
-rw-r--r--tools/testing/selftests/tpm2/tpm2.py31
-rw-r--r--tools/testing/selftests/tpm2/tpm2_tests.py45
-rw-r--r--tools/testing/selftests/user_events/Makefile9
-rw-r--r--tools/testing/selftests/user_events/dyn_test.c130
-rw-r--r--tools/testing/selftests/user_events/ftrace_test.c452
-rw-r--r--tools/testing/selftests/user_events/perf_test.c168
-rw-r--r--tools/testing/selftests/user_events/settings1
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_abi.c135
-rw-r--r--tools/testing/selftests/vm/.gitignore1
-rw-r--r--tools/testing/selftests/vm/Makefile13
-rw-r--r--tools/testing/selftests/vm/charge_reserved_hugetlb.sh34
-rw-r--r--tools/testing/selftests/vm/hmm-tests.c42
-rw-r--r--tools/testing/selftests/vm/hugepage-mremap.c60
-rw-r--r--tools/testing/selftests/vm/hugepage-vmemmap.c144
-rw-r--r--tools/testing/selftests/vm/hugetlb_reparenting_test.sh21
-rw-r--r--tools/testing/selftests/vm/map_fixed_noreplace.c49
-rwxr-xr-xtools/testing/selftests/vm/run_vmtests.sh14
-rw-r--r--tools/testing/selftests/vm/transhuge-stress.c35
-rw-r--r--tools/testing/selftests/vm/userfaultfd.c25
-rw-r--r--tools/testing/selftests/vm/write_hugetlb_memory.sh2
-rw-r--r--tools/testing/selftests/x86/Makefile6
-rwxr-xr-xtools/testing/selftests/x86/check_cc.sh2
-rwxr-xr-xtools/testing/selftests/zram/zram.sh15
-rwxr-xr-xtools/testing/selftests/zram/zram01.sh33
-rwxr-xr-xtools/testing/selftests/zram/zram02.sh1
-rwxr-xr-xtools/testing/selftests/zram/zram_lib.sh134
185 files changed, 9139 insertions, 1573 deletions
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index 86deba8308a1..1acdf2fc31c5 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
+ldflags-y += --wrap=acpi_table_parse_cedt
ldflags-y += --wrap=is_acpi_device_node
-ldflags-y += --wrap=acpi_get_table
-ldflags-y += --wrap=acpi_put_table
ldflags-y += --wrap=acpi_evaluate_integer
ldflags-y += --wrap=acpi_pci_find_root
ldflags-y += --wrap=pci_walk_bus
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index cb32f9e27d5d..736d99006fb7 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -182,6 +182,13 @@ static struct {
},
};
+struct acpi_cedt_cfmws *mock_cfmws[4] = {
+ [0] = &mock_cedt.cfmws0.cfmws,
+ [1] = &mock_cedt.cfmws1.cfmws,
+ [2] = &mock_cedt.cfmws2.cfmws,
+ [3] = &mock_cedt.cfmws3.cfmws,
+};
+
struct cxl_mock_res {
struct list_head list;
struct range range;
@@ -232,12 +239,6 @@ static struct cxl_mock_res *alloc_mock_res(resource_size_t size)
static int populate_cedt(void)
{
- struct acpi_cedt_cfmws *cfmws[4] = {
- [0] = &mock_cedt.cfmws0.cfmws,
- [1] = &mock_cedt.cfmws1.cfmws,
- [2] = &mock_cedt.cfmws2.cfmws,
- [3] = &mock_cedt.cfmws3.cfmws,
- };
struct cxl_mock_res *res;
int i;
@@ -257,8 +258,8 @@ static int populate_cedt(void)
chbs->length = size;
}
- for (i = 0; i < ARRAY_SIZE(cfmws); i++) {
- struct acpi_cedt_cfmws *window = cfmws[i];
+ for (i = 0; i < ARRAY_SIZE(mock_cfmws); i++) {
+ struct acpi_cedt_cfmws *window = mock_cfmws[i];
res = alloc_mock_res(window->window_size);
if (!res)
@@ -269,21 +270,44 @@ static int populate_cedt(void)
return 0;
}
-static acpi_status mock_acpi_get_table(char *signature, u32 instance,
- struct acpi_table_header **out_table)
+/*
+ * WARNING, this hack assumes the format of 'struct
+ * cxl_cfmws_context' and 'struct cxl_chbs_context' share the property that
+ * the first struct member is the device being probed by the cxl_acpi
+ * driver.
+ */
+struct cxl_cedt_context {
+ struct device *dev;
+};
+
+static int mock_acpi_table_parse_cedt(enum acpi_cedt_type id,
+ acpi_tbl_entry_handler_arg handler_arg,
+ void *arg)
{
- if (instance < U32_MAX || strcmp(signature, ACPI_SIG_CEDT) != 0)
- return acpi_get_table(signature, instance, out_table);
+ struct cxl_cedt_context *ctx = arg;
+ struct device *dev = ctx->dev;
+ union acpi_subtable_headers *h;
+ unsigned long end;
+ int i;
- *out_table = (struct acpi_table_header *) &mock_cedt;
- return AE_OK;
-}
+ if (dev != &cxl_acpi->dev)
+ return acpi_table_parse_cedt(id, handler_arg, arg);
-static void mock_acpi_put_table(struct acpi_table_header *table)
-{
- if (table == (struct acpi_table_header *) &mock_cedt)
- return;
- acpi_put_table(table);
+ if (id == ACPI_CEDT_TYPE_CHBS)
+ for (i = 0; i < ARRAY_SIZE(mock_cedt.chbs); i++) {
+ h = (union acpi_subtable_headers *)&mock_cedt.chbs[i];
+ end = (unsigned long)&mock_cedt.chbs[i + 1];
+ handler_arg(h, arg, end);
+ }
+
+ if (id == ACPI_CEDT_TYPE_CFMWS)
+ for (i = 0; i < ARRAY_SIZE(mock_cfmws); i++) {
+ h = (union acpi_subtable_headers *) mock_cfmws[i];
+ end = (unsigned long) h + mock_cfmws[i]->header.length;
+ handler_arg(h, arg, end);
+ }
+
+ return 0;
}
static bool is_mock_bridge(struct device *dev)
@@ -388,8 +412,7 @@ static struct cxl_mock_ops cxl_mock_ops = {
.is_mock_port = is_mock_port,
.is_mock_dev = is_mock_dev,
.mock_port = mock_cxl_root_port,
- .acpi_get_table = mock_acpi_get_table,
- .acpi_put_table = mock_acpi_put_table,
+ .acpi_table_parse_cedt = mock_acpi_table_parse_cedt,
.acpi_evaluate_integer = mock_acpi_evaluate_integer,
.acpi_pci_find_root = mock_acpi_pci_find_root,
.list = LIST_HEAD_INIT(cxl_mock_ops.list),
@@ -574,3 +597,4 @@ static __exit void cxl_test_exit(void)
module_init(cxl_test_init);
module_exit(cxl_test_exit);
MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(ACPI);
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 12a8437a9ca0..8c2086c4caef 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -28,8 +28,24 @@ static struct cxl_cel_entry mock_cel[] = {
.opcode = cpu_to_le16(CXL_MBOX_OP_SET_LSA),
.effect = cpu_to_le16(EFFECT(1) | EFFECT(2)),
},
+ {
+ .opcode = cpu_to_le16(CXL_MBOX_OP_GET_HEALTH_INFO),
+ .effect = cpu_to_le16(0),
+ },
};
+/* See CXL 2.0 Table 181 Get Health Info Output Payload */
+struct cxl_mbox_health_info {
+ u8 health_status;
+ u8 media_status;
+ u8 ext_status;
+ u8 life_used;
+ __le16 temperature;
+ __le32 dirty_shutdowns;
+ __le32 volatile_errors;
+ __le32 pmem_errors;
+} __packed;
+
static struct {
struct cxl_mbox_get_supported_logs gsl;
struct cxl_gsl_entry entry;
@@ -54,7 +70,7 @@ static int mock_gsl(struct cxl_mbox_cmd *cmd)
return 0;
}
-static int mock_get_log(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
+static int mock_get_log(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
{
struct cxl_mbox_get_log *gl = cmd->payload_in;
u32 offset = le32_to_cpu(gl->offset);
@@ -64,7 +80,7 @@ static int mock_get_log(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
if (cmd->size_in < sizeof(*gl))
return -EINVAL;
- if (length > cxlm->payload_size)
+ if (length > cxlds->payload_size)
return -EINVAL;
if (offset + length > sizeof(mock_cel))
return -EINVAL;
@@ -78,9 +94,9 @@ static int mock_get_log(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
return 0;
}
-static int mock_id(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
+static int mock_id(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
{
- struct platform_device *pdev = to_platform_device(cxlm->dev);
+ struct platform_device *pdev = to_platform_device(cxlds->dev);
struct cxl_mbox_identify id = {
.fw_revision = { "mock fw v1 " },
.lsa_size = cpu_to_le32(LSA_SIZE),
@@ -120,10 +136,10 @@ static int mock_id(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
return 0;
}
-static int mock_get_lsa(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
+static int mock_get_lsa(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
{
struct cxl_mbox_get_lsa *get_lsa = cmd->payload_in;
- void *lsa = dev_get_drvdata(cxlm->dev);
+ void *lsa = dev_get_drvdata(cxlds->dev);
u32 offset, length;
if (sizeof(*get_lsa) > cmd->size_in)
@@ -139,10 +155,10 @@ static int mock_get_lsa(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
return 0;
}
-static int mock_set_lsa(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
+static int mock_set_lsa(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
{
struct cxl_mbox_set_lsa *set_lsa = cmd->payload_in;
- void *lsa = dev_get_drvdata(cxlm->dev);
+ void *lsa = dev_get_drvdata(cxlds->dev);
u32 offset, length;
if (sizeof(*set_lsa) > cmd->size_in)
@@ -156,9 +172,39 @@ static int mock_set_lsa(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
return 0;
}
-static int cxl_mock_mbox_send(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
+static int mock_health_info(struct cxl_dev_state *cxlds,
+ struct cxl_mbox_cmd *cmd)
{
- struct device *dev = cxlm->dev;
+ struct cxl_mbox_health_info health_info = {
+ /* set flags for maint needed, perf degraded, hw replacement */
+ .health_status = 0x7,
+ /* set media status to "All Data Lost" */
+ .media_status = 0x3,
+ /*
+ * set ext_status flags for:
+ * ext_life_used: normal,
+ * ext_temperature: critical,
+ * ext_corrected_volatile: warning,
+ * ext_corrected_persistent: normal,
+ */
+ .ext_status = 0x18,
+ .life_used = 15,
+ .temperature = cpu_to_le16(25),
+ .dirty_shutdowns = cpu_to_le32(10),
+ .volatile_errors = cpu_to_le32(20),
+ .pmem_errors = cpu_to_le32(30),
+ };
+
+ if (cmd->size_out < sizeof(health_info))
+ return -EINVAL;
+
+ memcpy(cmd->payload_out, &health_info, sizeof(health_info));
+ return 0;
+}
+
+static int cxl_mock_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
+{
+ struct device *dev = cxlds->dev;
int rc = -EIO;
switch (cmd->opcode) {
@@ -166,16 +212,19 @@ static int cxl_mock_mbox_send(struct cxl_mem *cxlm, struct cxl_mbox_cmd *cmd)
rc = mock_gsl(cmd);
break;
case CXL_MBOX_OP_GET_LOG:
- rc = mock_get_log(cxlm, cmd);
+ rc = mock_get_log(cxlds, cmd);
break;
case CXL_MBOX_OP_IDENTIFY:
- rc = mock_id(cxlm, cmd);
+ rc = mock_id(cxlds, cmd);
break;
case CXL_MBOX_OP_GET_LSA:
- rc = mock_get_lsa(cxlm, cmd);
+ rc = mock_get_lsa(cxlds, cmd);
break;
case CXL_MBOX_OP_SET_LSA:
- rc = mock_set_lsa(cxlm, cmd);
+ rc = mock_set_lsa(cxlds, cmd);
+ break;
+ case CXL_MBOX_OP_GET_HEALTH_INFO:
+ rc = mock_health_info(cxlds, cmd);
break;
default:
break;
@@ -196,7 +245,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
struct cxl_memdev *cxlmd;
- struct cxl_mem *cxlm;
+ struct cxl_dev_state *cxlds;
void *lsa;
int rc;
@@ -208,30 +257,30 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
return rc;
dev_set_drvdata(dev, lsa);
- cxlm = cxl_mem_create(dev);
- if (IS_ERR(cxlm))
- return PTR_ERR(cxlm);
+ cxlds = cxl_dev_state_create(dev);
+ if (IS_ERR(cxlds))
+ return PTR_ERR(cxlds);
- cxlm->mbox_send = cxl_mock_mbox_send;
- cxlm->payload_size = SZ_4K;
+ cxlds->mbox_send = cxl_mock_mbox_send;
+ cxlds->payload_size = SZ_4K;
- rc = cxl_mem_enumerate_cmds(cxlm);
+ rc = cxl_enumerate_cmds(cxlds);
if (rc)
return rc;
- rc = cxl_mem_identify(cxlm);
+ rc = cxl_dev_state_identify(cxlds);
if (rc)
return rc;
- rc = cxl_mem_create_range_info(cxlm);
+ rc = cxl_mem_create_range_info(cxlds);
if (rc)
return rc;
- cxlmd = devm_cxl_add_memdev(cxlm);
+ cxlmd = devm_cxl_add_memdev(cxlds);
if (IS_ERR(cxlmd))
return PTR_ERR(cxlmd);
- if (range_len(&cxlm->pmem_range) && IS_ENABLED(CONFIG_CXL_PMEM))
+ if (range_len(&cxlds->pmem_range) && IS_ENABLED(CONFIG_CXL_PMEM))
rc = devm_cxl_add_nvdimm(dev, cxlmd);
return 0;
diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c
index b8c108abcf07..17408f892df4 100644
--- a/tools/testing/cxl/test/mock.c
+++ b/tools/testing/cxl/test/mock.c
@@ -58,36 +58,23 @@ bool __wrap_is_acpi_device_node(const struct fwnode_handle *fwnode)
}
EXPORT_SYMBOL(__wrap_is_acpi_device_node);
-acpi_status __wrap_acpi_get_table(char *signature, u32 instance,
- struct acpi_table_header **out_table)
+int __wrap_acpi_table_parse_cedt(enum acpi_cedt_type id,
+ acpi_tbl_entry_handler_arg handler_arg,
+ void *arg)
{
- int index;
+ int index, rc;
struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
- acpi_status status;
if (ops)
- status = ops->acpi_get_table(signature, instance, out_table);
+ rc = ops->acpi_table_parse_cedt(id, handler_arg, arg);
else
- status = acpi_get_table(signature, instance, out_table);
+ rc = acpi_table_parse_cedt(id, handler_arg, arg);
put_cxl_mock_ops(index);
- return status;
-}
-EXPORT_SYMBOL(__wrap_acpi_get_table);
-
-void __wrap_acpi_put_table(struct acpi_table_header *table)
-{
- int index;
- struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
-
- if (ops)
- ops->acpi_put_table(table);
- else
- acpi_put_table(table);
- put_cxl_mock_ops(index);
+ return rc;
}
-EXPORT_SYMBOL(__wrap_acpi_put_table);
+EXPORT_SYMBOL_NS_GPL(__wrap_acpi_table_parse_cedt, ACPI);
acpi_status __wrap_acpi_evaluate_integer(acpi_handle handle,
acpi_string pathname,
@@ -169,3 +156,4 @@ __wrap_nvdimm_bus_register(struct device *dev,
EXPORT_SYMBOL_GPL(__wrap_nvdimm_bus_register);
MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS(ACPI);
diff --git a/tools/testing/cxl/test/mock.h b/tools/testing/cxl/test/mock.h
index 805a94cb3fbe..15ed0fd877e4 100644
--- a/tools/testing/cxl/test/mock.h
+++ b/tools/testing/cxl/test/mock.h
@@ -6,9 +6,9 @@
struct cxl_mock_ops {
struct list_head list;
bool (*is_mock_adev)(struct acpi_device *dev);
- acpi_status (*acpi_get_table)(char *signature, u32 instance,
- struct acpi_table_header **out_table);
- void (*acpi_put_table)(struct acpi_table_header *table);
+ int (*acpi_table_parse_cedt)(enum acpi_cedt_type id,
+ acpi_tbl_entry_handler_arg handler_arg,
+ void *arg);
bool (*is_mock_bridge)(struct device *dev);
acpi_status (*acpi_evaluate_integer)(acpi_handle handle,
acpi_string pathname,
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 44bbe54f25f1..3c4196cef3ed 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -6,6 +6,7 @@
# Author: Felix Guo <[email protected]>
# Author: Brendan Higgins <[email protected]>
+import importlib.abc
import importlib.util
import logging
import subprocess
diff --git a/tools/testing/kunit/run_checks.py b/tools/testing/kunit/run_checks.py
index 4f32133ed77c..13d854afca9d 100755
--- a/tools/testing/kunit/run_checks.py
+++ b/tools/testing/kunit/run_checks.py
@@ -61,7 +61,7 @@ def main(argv: Sequence[str]) -> None:
elif isinstance(ex, subprocess.CalledProcessError):
print(f'{name}: FAILED')
else:
- print('{name}: unexpected exception: {ex}')
+ print(f'{name}: unexpected exception: {ex}')
continue
output = ex.output
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index 47f9cc9dcd94..c57d9e9d4480 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -35,8 +35,6 @@ obj-$(CONFIG_DAX) += dax.o
endif
obj-$(CONFIG_DEV_DAX) += device_dax.o
obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
-obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem_core.o
-obj-$(CONFIG_DEV_DAX_PMEM_COMPAT) += dax_pmem_compat.o
nfit-y := $(ACPI_SRC)/core.o
nfit-y += $(ACPI_SRC)/intel.o
@@ -67,12 +65,8 @@ device_dax-y += dax-dev.o
device_dax-y += device_dax_test.o
device_dax-y += config_check.o
-dax_pmem-y := $(DAX_SRC)/pmem/pmem.o
+dax_pmem-y := $(DAX_SRC)/pmem.o
dax_pmem-y += dax_pmem_test.o
-dax_pmem_core-y := $(DAX_SRC)/pmem/core.o
-dax_pmem_core-y += dax_pmem_core_test.o
-dax_pmem_compat-y := $(DAX_SRC)/pmem/compat.o
-dax_pmem_compat-y += dax_pmem_compat_test.o
dax_pmem-y += config_check.o
libnvdimm-y := $(NVDIMM_SRC)/core.o
diff --git a/tools/testing/nvdimm/dax_pmem_compat_test.c b/tools/testing/nvdimm/dax_pmem_compat_test.c
deleted file mode 100644
index 7cd1877f3765..000000000000
--- a/tools/testing/nvdimm/dax_pmem_compat_test.c
+++ /dev/null
@@ -1,8 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright(c) 2019 Intel Corporation. All rights reserved.
-
-#include <linux/module.h>
-#include <linux/printk.h>
-#include "watermark.h"
-
-nfit_test_watermark(dax_pmem_compat);
diff --git a/tools/testing/nvdimm/dax_pmem_core_test.c b/tools/testing/nvdimm/dax_pmem_core_test.c
deleted file mode 100644
index a4249cdbeec1..000000000000
--- a/tools/testing/nvdimm/dax_pmem_core_test.c
+++ /dev/null
@@ -1,8 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright(c) 2019 Intel Corporation. All rights reserved.
-
-#include <linux/module.h>
-#include <linux/printk.h>
-#include "watermark.h"
-
-nfit_test_watermark(dax_pmem_core);
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index ed563bdd88f3..b752ce47ead3 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -100,25 +100,17 @@ static void nfit_test_kill(void *_pgmap)
{
struct dev_pagemap *pgmap = _pgmap;
- WARN_ON(!pgmap || !pgmap->ref);
-
- if (pgmap->ops && pgmap->ops->kill)
- pgmap->ops->kill(pgmap);
- else
- percpu_ref_kill(pgmap->ref);
-
- if (pgmap->ops && pgmap->ops->cleanup) {
- pgmap->ops->cleanup(pgmap);
- } else {
- wait_for_completion(&pgmap->done);
- percpu_ref_exit(pgmap->ref);
- }
+ WARN_ON(!pgmap);
+
+ percpu_ref_kill(&pgmap->ref);
+
+ wait_for_completion(&pgmap->done);
+ percpu_ref_exit(&pgmap->ref);
}
static void dev_pagemap_percpu_release(struct percpu_ref *ref)
{
- struct dev_pagemap *pgmap =
- container_of(ref, struct dev_pagemap, internal_ref);
+ struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref);
complete(&pgmap->done);
}
@@ -132,22 +124,11 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
if (!nfit_res)
return devm_memremap_pages(dev, pgmap);
- if (!pgmap->ref) {
- if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
- return ERR_PTR(-EINVAL);
-
- init_completion(&pgmap->done);
- error = percpu_ref_init(&pgmap->internal_ref,
- dev_pagemap_percpu_release, 0, GFP_KERNEL);
- if (error)
- return ERR_PTR(error);
- pgmap->ref = &pgmap->internal_ref;
- } else {
- if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
- WARN(1, "Missing reference count teardown definition\n");
- return ERR_PTR(-EINVAL);
- }
- }
+ init_completion(&pgmap->done);
+ error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0,
+ GFP_KERNEL);
+ if (error)
+ return ERR_PTR(error);
error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
if (error)
diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c
index 6862915f1fb0..3ca7c32e9362 100644
--- a/tools/testing/nvdimm/test/ndtest.c
+++ b/tools/testing/nvdimm/test/ndtest.c
@@ -1054,10 +1054,6 @@ static __init int ndtest_init(void)
libnvdimm_test();
device_dax_test();
dax_pmem_test();
- dax_pmem_core_test();
-#ifdef CONFIG_DEV_DAX_PMEM_COMPAT
- dax_pmem_compat_test();
-#endif
nfit_test_setup(ndtest_resource_lookup, NULL);
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index b1bff5fb0f65..0bc91ffee257 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -3300,10 +3300,6 @@ static __init int nfit_test_init(void)
acpi_nfit_test();
device_dax_test();
dax_pmem_test();
- dax_pmem_core_test();
-#ifdef CONFIG_DEV_DAX_PMEM_COMPAT
- dax_pmem_compat_test();
-#endif
nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm);
diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h
index 16ec895bbe5f..5bd9e6e80625 100644
--- a/tools/testing/scatterlist/linux/mm.h
+++ b/tools/testing/scatterlist/linux/mm.h
@@ -74,7 +74,7 @@ static inline unsigned long page_to_phys(struct page *page)
__UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \
x, y)
-#define preemptible() (1)
+#define pagefault_disabled() (0)
static inline void *kmap(struct page *page)
{
@@ -127,6 +127,7 @@ kmalloc_array(unsigned int n, unsigned int size, unsigned int flags)
#define kmemleak_free(a)
#define PageSlab(p) (0)
+#define flush_dcache_page(p)
#define MAX_ERRNO 4095
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index c852eb40c4f7..d08fe4cfe811 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
-TARGETS = arm64
+TARGETS += alsa
+TARGETS += arm64
TARGETS += bpf
TARGETS += breakpoints
TARGETS += capabilities
diff --git a/tools/testing/selftests/alsa/.gitignore b/tools/testing/selftests/alsa/.gitignore
new file mode 100644
index 000000000000..3bb7c41266a8
--- /dev/null
+++ b/tools/testing/selftests/alsa/.gitignore
@@ -0,0 +1 @@
+mixer-test
diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile
new file mode 100644
index 000000000000..f64d9090426d
--- /dev/null
+++ b/tools/testing/selftests/alsa/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+
+CFLAGS += $(shell pkg-config --cflags alsa)
+LDLIBS += $(shell pkg-config --libs alsa)
+
+TEST_GEN_PROGS := mixer-test
+
+include ../lib.mk
diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c
new file mode 100644
index 000000000000..17f158d7a767
--- /dev/null
+++ b/tools/testing/selftests/alsa/mixer-test.c
@@ -0,0 +1,705 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// kselftest for the ALSA mixer API
+//
+// Original author: Mark Brown <[email protected]>
+// Copyright (c) 2021 Arm Limited
+
+// This test will iterate over all cards detected in the system, exercising
+// every mixer control it can find. This may conflict with other system
+// software if there is audio activity so is best run on a system with a
+// minimal active userspace.
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <getopt.h>
+#include <stdarg.h>
+#include <ctype.h>
+#include <math.h>
+#include <errno.h>
+#include <assert.h>
+#include <alsa/asoundlib.h>
+#include <poll.h>
+#include <stdint.h>
+
+#include "../kselftest.h"
+
+#define TESTS_PER_CONTROL 3
+
+struct card_data {
+ snd_ctl_t *handle;
+ int card;
+ int num_ctls;
+ snd_ctl_elem_list_t *ctls;
+ struct card_data *next;
+};
+
+struct ctl_data {
+ const char *name;
+ snd_ctl_elem_id_t *id;
+ snd_ctl_elem_info_t *info;
+ snd_ctl_elem_value_t *def_val;
+ int elem;
+ struct card_data *card;
+ struct ctl_data *next;
+};
+
+static const char *alsa_config =
+"ctl.hw {\n"
+" @args [ CARD ]\n"
+" @args.CARD.type string\n"
+" type hw\n"
+" card $CARD\n"
+"}\n"
+;
+
+int num_cards = 0;
+int num_controls = 0;
+struct card_data *card_list = NULL;
+struct ctl_data *ctl_list = NULL;
+
+#ifdef SND_LIB_VER
+#if SND_LIB_VERSION >= SND_LIB_VER(1, 2, 6)
+#define LIB_HAS_LOAD_STRING
+#endif
+#endif
+
+#ifndef LIB_HAS_LOAD_STRING
+int snd_config_load_string(snd_config_t **config, const char *s, size_t size)
+{
+ snd_input_t *input;
+ snd_config_t *dst;
+ int err;
+
+ assert(config && s);
+ if (size == 0)
+ size = strlen(s);
+ err = snd_input_buffer_open(&input, s, size);
+ if (err < 0)
+ return err;
+ err = snd_config_top(&dst);
+ if (err < 0) {
+ snd_input_close(input);
+ return err;
+ }
+ err = snd_config_load(dst, input);
+ snd_input_close(input);
+ if (err < 0) {
+ snd_config_delete(dst);
+ return err;
+ }
+ *config = dst;
+ return 0;
+}
+#endif
+
+void find_controls(void)
+{
+ char name[32];
+ int card, ctl, err;
+ struct card_data *card_data;
+ struct ctl_data *ctl_data;
+ snd_config_t *config;
+
+ card = -1;
+ if (snd_card_next(&card) < 0 || card < 0)
+ return;
+
+ err = snd_config_load_string(&config, alsa_config, strlen(alsa_config));
+ if (err < 0) {
+ ksft_print_msg("Unable to parse custom alsa-lib configuration: %s\n",
+ snd_strerror(err));
+ ksft_exit_fail();
+ }
+
+ while (card >= 0) {
+ sprintf(name, "hw:%d", card);
+
+ card_data = malloc(sizeof(*card_data));
+ if (!card_data)
+ ksft_exit_fail_msg("Out of memory\n");
+
+ err = snd_ctl_open_lconf(&card_data->handle, name, 0, config);
+ if (err < 0) {
+ ksft_print_msg("Failed to get hctl for card %d: %s\n",
+ card, snd_strerror(err));
+ goto next_card;
+ }
+
+ /* Count controls */
+ snd_ctl_elem_list_malloc(&card_data->ctls);
+ snd_ctl_elem_list(card_data->handle, card_data->ctls);
+ card_data->num_ctls = snd_ctl_elem_list_get_count(card_data->ctls);
+
+ /* Enumerate control information */
+ snd_ctl_elem_list_alloc_space(card_data->ctls, card_data->num_ctls);
+ snd_ctl_elem_list(card_data->handle, card_data->ctls);
+
+ card_data->card = num_cards++;
+ card_data->next = card_list;
+ card_list = card_data;
+
+ num_controls += card_data->num_ctls;
+
+ for (ctl = 0; ctl < card_data->num_ctls; ctl++) {
+ ctl_data = malloc(sizeof(*ctl_data));
+ if (!ctl_data)
+ ksft_exit_fail_msg("Out of memory\n");
+
+ ctl_data->card = card_data;
+ ctl_data->elem = ctl;
+ ctl_data->name = snd_ctl_elem_list_get_name(card_data->ctls,
+ ctl);
+
+ err = snd_ctl_elem_id_malloc(&ctl_data->id);
+ if (err < 0)
+ ksft_exit_fail_msg("Out of memory\n");
+
+ err = snd_ctl_elem_info_malloc(&ctl_data->info);
+ if (err < 0)
+ ksft_exit_fail_msg("Out of memory\n");
+
+ err = snd_ctl_elem_value_malloc(&ctl_data->def_val);
+ if (err < 0)
+ ksft_exit_fail_msg("Out of memory\n");
+
+ snd_ctl_elem_list_get_id(card_data->ctls, ctl,
+ ctl_data->id);
+ snd_ctl_elem_info_set_id(ctl_data->info, ctl_data->id);
+ err = snd_ctl_elem_info(card_data->handle,
+ ctl_data->info);
+ if (err < 0) {
+ ksft_print_msg("%s getting info for %d\n",
+ snd_strerror(err),
+ ctl_data->name);
+ }
+
+ snd_ctl_elem_value_set_id(ctl_data->def_val,
+ ctl_data->id);
+
+ ctl_data->next = ctl_list;
+ ctl_list = ctl_data;
+ }
+
+ next_card:
+ if (snd_card_next(&card) < 0) {
+ ksft_print_msg("snd_card_next");
+ break;
+ }
+ }
+
+ snd_config_delete(config);
+}
+
+bool ctl_value_index_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val,
+ int index)
+{
+ long int_val;
+ long long int64_val;
+
+ switch (snd_ctl_elem_info_get_type(ctl->info)) {
+ case SND_CTL_ELEM_TYPE_NONE:
+ ksft_print_msg("%s.%d Invalid control type NONE\n",
+ ctl->name, index);
+ return false;
+
+ case SND_CTL_ELEM_TYPE_BOOLEAN:
+ int_val = snd_ctl_elem_value_get_boolean(val, index);
+ switch (int_val) {
+ case 0:
+ case 1:
+ break;
+ default:
+ ksft_print_msg("%s.%d Invalid boolean value %ld\n",
+ ctl->name, index, int_val);
+ return false;
+ }
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER:
+ int_val = snd_ctl_elem_value_get_integer(val, index);
+
+ if (int_val < snd_ctl_elem_info_get_min(ctl->info)) {
+ ksft_print_msg("%s.%d value %ld less than minimum %ld\n",
+ ctl->name, index, int_val,
+ snd_ctl_elem_info_get_min(ctl->info));
+ return false;
+ }
+
+ if (int_val > snd_ctl_elem_info_get_max(ctl->info)) {
+ ksft_print_msg("%s.%d value %ld more than maximum %ld\n",
+ ctl->name, index, int_val,
+ snd_ctl_elem_info_get_max(ctl->info));
+ return false;
+ }
+
+ /* Only check step size if there is one and we're in bounds */
+ if (snd_ctl_elem_info_get_step(ctl->info) &&
+ (int_val - snd_ctl_elem_info_get_min(ctl->info) %
+ snd_ctl_elem_info_get_step(ctl->info))) {
+ ksft_print_msg("%s.%d value %ld invalid for step %ld minimum %ld\n",
+ ctl->name, index, int_val,
+ snd_ctl_elem_info_get_step(ctl->info),
+ snd_ctl_elem_info_get_min(ctl->info));
+ return false;
+ }
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER64:
+ int64_val = snd_ctl_elem_value_get_integer64(val, index);
+
+ if (int64_val < snd_ctl_elem_info_get_min64(ctl->info)) {
+ ksft_print_msg("%s.%d value %lld less than minimum %lld\n",
+ ctl->name, index, int64_val,
+ snd_ctl_elem_info_get_min64(ctl->info));
+ return false;
+ }
+
+ if (int64_val > snd_ctl_elem_info_get_max64(ctl->info)) {
+ ksft_print_msg("%s.%d value %lld more than maximum %lld\n",
+ ctl->name, index, int64_val,
+ snd_ctl_elem_info_get_max(ctl->info));
+ return false;
+ }
+
+ /* Only check step size if there is one and we're in bounds */
+ if (snd_ctl_elem_info_get_step64(ctl->info) &&
+ (int64_val - snd_ctl_elem_info_get_min64(ctl->info)) %
+ snd_ctl_elem_info_get_step64(ctl->info)) {
+ ksft_print_msg("%s.%d value %lld invalid for step %lld minimum %lld\n",
+ ctl->name, index, int64_val,
+ snd_ctl_elem_info_get_step64(ctl->info),
+ snd_ctl_elem_info_get_min64(ctl->info));
+ return false;
+ }
+ break;
+
+ case SND_CTL_ELEM_TYPE_ENUMERATED:
+ int_val = snd_ctl_elem_value_get_enumerated(val, index);
+
+ if (int_val < 0) {
+ ksft_print_msg("%s.%d negative value %ld for enumeration\n",
+ ctl->name, index, int_val);
+ return false;
+ }
+
+ if (int_val >= snd_ctl_elem_info_get_items(ctl->info)) {
+ ksft_print_msg("%s.%d value %ld more than item count %ld\n",
+ ctl->name, index, int_val,
+ snd_ctl_elem_info_get_items(ctl->info));
+ return false;
+ }
+ break;
+
+ default:
+ /* No tests for other types */
+ break;
+ }
+
+ return true;
+}
+
+/*
+ * Check that the provided value meets the constraints for the
+ * provided control.
+ */
+bool ctl_value_valid(struct ctl_data *ctl, snd_ctl_elem_value_t *val)
+{
+ int i;
+ bool valid = true;
+
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++)
+ if (!ctl_value_index_valid(ctl, val, i))
+ valid = false;
+
+ return valid;
+}
+
+/*
+ * Check that we can read the default value and it is valid. Write
+ * tests use the read value to restore the default.
+ */
+void test_ctl_get_value(struct ctl_data *ctl)
+{
+ int err;
+
+ /* If the control is turned off let's be polite */
+ if (snd_ctl_elem_info_is_inactive(ctl->info)) {
+ ksft_print_msg("%s is inactive\n", ctl->name);
+ ksft_test_result_skip("get_value.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ /* Can't test reading on an unreadable control */
+ if (!snd_ctl_elem_info_is_readable(ctl->info)) {
+ ksft_print_msg("%s is not readable\n", ctl->name);
+ ksft_test_result_skip("get_value.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ err = snd_ctl_elem_read(ctl->card->handle, ctl->def_val);
+ if (err < 0) {
+ ksft_print_msg("snd_ctl_elem_read() failed: %s\n",
+ snd_strerror(err));
+ goto out;
+ }
+
+ if (!ctl_value_valid(ctl, ctl->def_val))
+ err = -EINVAL;
+
+out:
+ ksft_test_result(err >= 0, "get_value.%d.%d\n",
+ ctl->card->card, ctl->elem);
+}
+
+bool show_mismatch(struct ctl_data *ctl, int index,
+ snd_ctl_elem_value_t *read_val,
+ snd_ctl_elem_value_t *expected_val)
+{
+ long long expected_int, read_int;
+
+ /*
+ * We factor out the code to compare values representable as
+ * integers, ensure that check doesn't log otherwise.
+ */
+ expected_int = 0;
+ read_int = 0;
+
+ switch (snd_ctl_elem_info_get_type(ctl->info)) {
+ case SND_CTL_ELEM_TYPE_BOOLEAN:
+ expected_int = snd_ctl_elem_value_get_boolean(expected_val,
+ index);
+ read_int = snd_ctl_elem_value_get_boolean(read_val, index);
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER:
+ expected_int = snd_ctl_elem_value_get_integer(expected_val,
+ index);
+ read_int = snd_ctl_elem_value_get_integer(read_val, index);
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER64:
+ expected_int = snd_ctl_elem_value_get_integer64(expected_val,
+ index);
+ read_int = snd_ctl_elem_value_get_integer64(read_val,
+ index);
+ break;
+
+ case SND_CTL_ELEM_TYPE_ENUMERATED:
+ expected_int = snd_ctl_elem_value_get_enumerated(expected_val,
+ index);
+ read_int = snd_ctl_elem_value_get_enumerated(read_val,
+ index);
+ break;
+
+ default:
+ break;
+ }
+
+ if (expected_int != read_int) {
+ /*
+ * NOTE: The volatile attribute means that the hardware
+ * can voluntarily change the state of control element
+ * independent of any operation by software.
+ */
+ bool is_volatile = snd_ctl_elem_info_is_volatile(ctl->info);
+ ksft_print_msg("%s.%d expected %lld but read %lld, is_volatile %d\n",
+ ctl->name, index, expected_int, read_int, is_volatile);
+ return !is_volatile;
+ } else {
+ return false;
+ }
+}
+
+/*
+ * Write a value then if possible verify that we get the expected
+ * result. An optional expected value can be provided if we expect
+ * the write to fail, for verifying that invalid writes don't corrupt
+ * anything.
+ */
+int write_and_verify(struct ctl_data *ctl,
+ snd_ctl_elem_value_t *write_val,
+ snd_ctl_elem_value_t *expected_val)
+{
+ int err, i;
+ bool error_expected, mismatch_shown;
+ snd_ctl_elem_value_t *read_val, *w_val;
+ snd_ctl_elem_value_alloca(&read_val);
+ snd_ctl_elem_value_alloca(&w_val);
+
+ /*
+ * We need to copy the write value since writing can modify
+ * the value which causes surprises, and allocate an expected
+ * value if we expect to read back what we wrote.
+ */
+ snd_ctl_elem_value_copy(w_val, write_val);
+ if (expected_val) {
+ error_expected = true;
+ } else {
+ error_expected = false;
+ snd_ctl_elem_value_alloca(&expected_val);
+ snd_ctl_elem_value_copy(expected_val, write_val);
+ }
+
+ /*
+ * Do the write, if we have an expected value ignore the error
+ * and carry on to validate the expected value.
+ */
+ err = snd_ctl_elem_write(ctl->card->handle, w_val);
+ if (err < 0 && !error_expected) {
+ ksft_print_msg("snd_ctl_elem_write() failed: %s\n",
+ snd_strerror(err));
+ return err;
+ }
+
+ /* Can we do the verification part? */
+ if (!snd_ctl_elem_info_is_readable(ctl->info))
+ return err;
+
+ snd_ctl_elem_value_set_id(read_val, ctl->id);
+
+ err = snd_ctl_elem_read(ctl->card->handle, read_val);
+ if (err < 0) {
+ ksft_print_msg("snd_ctl_elem_read() failed: %s\n",
+ snd_strerror(err));
+ return err;
+ }
+
+ /*
+ * Use the libray to compare values, if there's a mismatch
+ * carry on and try to provide a more useful diagnostic than
+ * just "mismatch".
+ */
+ if (!snd_ctl_elem_value_compare(expected_val, read_val))
+ return 0;
+
+ mismatch_shown = false;
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++)
+ if (show_mismatch(ctl, i, read_val, expected_val))
+ mismatch_shown = true;
+
+ if (!mismatch_shown)
+ ksft_print_msg("%s read and written values differ\n",
+ ctl->name);
+
+ return -1;
+}
+
+/*
+ * Make sure we can write the default value back to the control, this
+ * should validate that at least some write works.
+ */
+void test_ctl_write_default(struct ctl_data *ctl)
+{
+ int err;
+
+ /* If the control is turned off let's be polite */
+ if (snd_ctl_elem_info_is_inactive(ctl->info)) {
+ ksft_print_msg("%s is inactive\n", ctl->name);
+ ksft_test_result_skip("write_default.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ if (!snd_ctl_elem_info_is_writable(ctl->info)) {
+ ksft_print_msg("%s is not writeable\n", ctl->name);
+ ksft_test_result_skip("write_default.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ /* No idea what the default was for unreadable controls */
+ if (!snd_ctl_elem_info_is_readable(ctl->info)) {
+ ksft_print_msg("%s couldn't read default\n", ctl->name);
+ ksft_test_result_skip("write_default.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ err = write_and_verify(ctl, ctl->def_val, NULL);
+
+ ksft_test_result(err >= 0, "write_default.%d.%d\n",
+ ctl->card->card, ctl->elem);
+}
+
+bool test_ctl_write_valid_boolean(struct ctl_data *ctl)
+{
+ int err, i, j;
+ bool fail = false;
+ snd_ctl_elem_value_t *val;
+ snd_ctl_elem_value_alloca(&val);
+
+ snd_ctl_elem_value_set_id(val, ctl->id);
+
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) {
+ for (j = 0; j < 2; j++) {
+ snd_ctl_elem_value_set_boolean(val, i, j);
+ err = write_and_verify(ctl, val, NULL);
+ if (err != 0)
+ fail = true;
+ }
+ }
+
+ return !fail;
+}
+
+bool test_ctl_write_valid_integer(struct ctl_data *ctl)
+{
+ int err;
+ int i;
+ long j, step;
+ bool fail = false;
+ snd_ctl_elem_value_t *val;
+ snd_ctl_elem_value_alloca(&val);
+
+ snd_ctl_elem_value_set_id(val, ctl->id);
+
+ step = snd_ctl_elem_info_get_step(ctl->info);
+ if (!step)
+ step = 1;
+
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) {
+ for (j = snd_ctl_elem_info_get_min(ctl->info);
+ j <= snd_ctl_elem_info_get_max(ctl->info); j += step) {
+
+ snd_ctl_elem_value_set_integer(val, i, j);
+ err = write_and_verify(ctl, val, NULL);
+ if (err != 0)
+ fail = true;
+ }
+ }
+
+
+ return !fail;
+}
+
+bool test_ctl_write_valid_integer64(struct ctl_data *ctl)
+{
+ int err, i;
+ long long j, step;
+ bool fail = false;
+ snd_ctl_elem_value_t *val;
+ snd_ctl_elem_value_alloca(&val);
+
+ snd_ctl_elem_value_set_id(val, ctl->id);
+
+ step = snd_ctl_elem_info_get_step64(ctl->info);
+ if (!step)
+ step = 1;
+
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) {
+ for (j = snd_ctl_elem_info_get_min64(ctl->info);
+ j <= snd_ctl_elem_info_get_max64(ctl->info); j += step) {
+
+ snd_ctl_elem_value_set_integer64(val, i, j);
+ err = write_and_verify(ctl, val, NULL);
+ if (err != 0)
+ fail = true;
+ }
+ }
+
+ return !fail;
+}
+
+bool test_ctl_write_valid_enumerated(struct ctl_data *ctl)
+{
+ int err, i, j;
+ bool fail = false;
+ snd_ctl_elem_value_t *val;
+ snd_ctl_elem_value_alloca(&val);
+
+ snd_ctl_elem_value_set_id(val, ctl->id);
+
+ for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) {
+ for (j = 0; j < snd_ctl_elem_info_get_items(ctl->info); j++) {
+ snd_ctl_elem_value_set_enumerated(val, i, j);
+ err = write_and_verify(ctl, val, NULL);
+ if (err != 0)
+ fail = true;
+ }
+ }
+
+ return !fail;
+}
+
+void test_ctl_write_valid(struct ctl_data *ctl)
+{
+ bool pass;
+ int err;
+
+ /* If the control is turned off let's be polite */
+ if (snd_ctl_elem_info_is_inactive(ctl->info)) {
+ ksft_print_msg("%s is inactive\n", ctl->name);
+ ksft_test_result_skip("write_valid.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ if (!snd_ctl_elem_info_is_writable(ctl->info)) {
+ ksft_print_msg("%s is not writeable\n", ctl->name);
+ ksft_test_result_skip("write_valid.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ switch (snd_ctl_elem_info_get_type(ctl->info)) {
+ case SND_CTL_ELEM_TYPE_BOOLEAN:
+ pass = test_ctl_write_valid_boolean(ctl);
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER:
+ pass = test_ctl_write_valid_integer(ctl);
+ break;
+
+ case SND_CTL_ELEM_TYPE_INTEGER64:
+ pass = test_ctl_write_valid_integer64(ctl);
+ break;
+
+ case SND_CTL_ELEM_TYPE_ENUMERATED:
+ pass = test_ctl_write_valid_enumerated(ctl);
+ break;
+
+ default:
+ /* No tests for this yet */
+ ksft_test_result_skip("write_valid.%d.%d\n",
+ ctl->card->card, ctl->elem);
+ return;
+ }
+
+ /* Restore the default value to minimise disruption */
+ err = write_and_verify(ctl, ctl->def_val, NULL);
+ if (err < 0)
+ pass = false;
+
+ ksft_test_result(pass, "write_valid.%d.%d\n",
+ ctl->card->card, ctl->elem);
+}
+
+int main(void)
+{
+ struct ctl_data *ctl;
+
+ ksft_print_header();
+
+ find_controls();
+
+ ksft_set_plan(num_controls * TESTS_PER_CONTROL);
+
+ for (ctl = ctl_list; ctl != NULL; ctl = ctl->next) {
+ /*
+ * Must test get_value() before we write anything, the
+ * test stores the default value for later cleanup.
+ */
+ test_ctl_get_value(ctl);
+ test_ctl_write_default(ctl);
+ test_ctl_write_valid(ctl);
+ }
+
+ ksft_exit_pass();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c
index d8eeeafb50dc..1e13b7523918 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi.c
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.c
@@ -18,7 +18,6 @@
#include "../../kselftest.h"
-#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0]))
#define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1)
extern void do_syscall(int sve_vl);
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index af798b9d232c..4c418b2021e0 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -21,8 +21,6 @@
#include "../../kselftest.h"
-#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0]))
-
/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
#ifndef NT_ARM_SVE
#define NT_ARM_SVE 0x405
@@ -261,7 +259,7 @@ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
}
ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD,
- "Set FPSIMD registers via %s\n", type->name);
+ "Got FPSIMD registers via %s\n", type->name);
if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD)
goto out;
@@ -489,6 +487,8 @@ static int do_parent(pid_t child)
unsigned int vq, vl;
bool vl_supported;
+ ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
+
/* Attach to the child */
while (1) {
int sig;
@@ -557,7 +557,14 @@ static int do_parent(pid_t child)
}
/* prctl() flags */
- ptrace_set_get_inherit(child, &vec_types[i]);
+ if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) {
+ ptrace_set_get_inherit(child, &vec_types[i]);
+ } else {
+ ksft_test_result_skip("%s SVE_PT_VL_INHERIT set\n",
+ vec_types[i].name);
+ ksft_test_result_skip("%s SVE_PT_VL_INHERIT cleared\n",
+ vec_types[i].name);
+ }
/* Step through every possible VQ */
for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
diff --git a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c
index a876db1f096a..325bca0de0f6 100644
--- a/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c
+++ b/tools/testing/selftests/arm64/mte/check_gcr_el1_cswitch.c
@@ -19,17 +19,6 @@
#include "kselftest.h"
#include "mte_common_util.h"
-#define PR_SET_TAGGED_ADDR_CTRL 55
-#define PR_GET_TAGGED_ADDR_CTRL 56
-# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
-# define PR_MTE_TCF_SHIFT 1
-# define PR_MTE_TCF_NONE (0UL << PR_MTE_TCF_SHIFT)
-# define PR_MTE_TCF_SYNC (1UL << PR_MTE_TCF_SHIFT)
-# define PR_MTE_TCF_ASYNC (2UL << PR_MTE_TCF_SHIFT)
-# define PR_MTE_TCF_MASK (3UL << PR_MTE_TCF_SHIFT)
-# define PR_MTE_TAG_SHIFT 3
-# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT)
-
#include "mte_def.h"
#define NUM_ITERATIONS 1024
diff --git a/tools/testing/selftests/arm64/mte/check_user_mem.c b/tools/testing/selftests/arm64/mte/check_user_mem.c
index 1de7a0abd0ae..f4ae5f87a3b7 100644
--- a/tools/testing/selftests/arm64/mte/check_user_mem.c
+++ b/tools/testing/selftests/arm64/mte/check_user_mem.c
@@ -3,6 +3,7 @@
#define _GNU_SOURCE
+#include <assert.h>
#include <errno.h>
#include <fcntl.h>
#include <signal.h>
@@ -11,6 +12,7 @@
#include <string.h>
#include <ucontext.h>
#include <unistd.h>
+#include <sys/uio.h>
#include <sys/mman.h>
#include "kselftest.h"
@@ -19,14 +21,28 @@
static size_t page_sz;
-static int check_usermem_access_fault(int mem_type, int mode, int mapping)
+#define TEST_NAME_MAX 100
+
+enum test_type {
+ READ_TEST,
+ WRITE_TEST,
+ READV_TEST,
+ WRITEV_TEST,
+ LAST_TEST,
+};
+
+static int check_usermem_access_fault(int mem_type, int mode, int mapping,
+ int tag_offset, int tag_len,
+ enum test_type test_type)
{
int fd, i, err;
char val = 'A';
- size_t len, read_len;
+ ssize_t len, syscall_len;
void *ptr, *ptr_next;
+ int fileoff, ptroff, size;
+ int sizes[] = {1, 2, 3, 8, 16, 32, 4096, page_sz};
- err = KSFT_FAIL;
+ err = KSFT_PASS;
len = 2 * page_sz;
mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
fd = create_temp_file();
@@ -43,9 +59,9 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping)
}
mte_initialize_current_context(mode, (uintptr_t)ptr, len);
/* Copy from file into buffer with valid tag */
- read_len = read(fd, ptr, len);
+ syscall_len = read(fd, ptr, len);
mte_wait_after_trig();
- if (cur_mte_cxt.fault_valid || read_len < len)
+ if (cur_mte_cxt.fault_valid || syscall_len < len)
goto usermem_acc_err;
/* Verify same pattern is read */
for (i = 0; i < len; i++)
@@ -54,36 +70,136 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping)
if (i < len)
goto usermem_acc_err;
- /* Tag the next half of memory with different value */
- ptr_next = (void *)((unsigned long)ptr + page_sz);
+ if (!tag_len)
+ tag_len = len - tag_offset;
+ /* Tag a part of memory with different value */
+ ptr_next = (void *)((unsigned long)ptr + tag_offset);
ptr_next = mte_insert_new_tag(ptr_next);
- mte_set_tag_address_range(ptr_next, page_sz);
+ mte_set_tag_address_range(ptr_next, tag_len);
- lseek(fd, 0, 0);
- /* Copy from file into buffer with invalid tag */
- read_len = read(fd, ptr, len);
- mte_wait_after_trig();
- /*
- * Accessing user memory in kernel with invalid tag should fail in sync
- * mode without fault but may not fail in async mode as per the
- * implemented MTE userspace support in Arm64 kernel.
- */
- if (mode == MTE_SYNC_ERR &&
- !cur_mte_cxt.fault_valid && read_len < len) {
- err = KSFT_PASS;
- } else if (mode == MTE_ASYNC_ERR &&
- !cur_mte_cxt.fault_valid && read_len == len) {
- err = KSFT_PASS;
+ for (fileoff = 0; fileoff < 16; fileoff++) {
+ for (ptroff = 0; ptroff < 16; ptroff++) {
+ for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+ size = sizes[i];
+ lseek(fd, 0, 0);
+
+ /* perform file operation on buffer with invalid tag */
+ switch (test_type) {
+ case READ_TEST:
+ syscall_len = read(fd, ptr + ptroff, size);
+ break;
+ case WRITE_TEST:
+ syscall_len = write(fd, ptr + ptroff, size);
+ break;
+ case READV_TEST: {
+ struct iovec iov[1];
+ iov[0].iov_base = ptr + ptroff;
+ iov[0].iov_len = size;
+ syscall_len = readv(fd, iov, 1);
+ break;
+ }
+ case WRITEV_TEST: {
+ struct iovec iov[1];
+ iov[0].iov_base = ptr + ptroff;
+ iov[0].iov_len = size;
+ syscall_len = writev(fd, iov, 1);
+ break;
+ }
+ case LAST_TEST:
+ goto usermem_acc_err;
+ }
+
+ mte_wait_after_trig();
+ /*
+ * Accessing user memory in kernel with invalid tag should fail in sync
+ * mode without fault but may not fail in async mode as per the
+ * implemented MTE userspace support in Arm64 kernel.
+ */
+ if (cur_mte_cxt.fault_valid) {
+ goto usermem_acc_err;
+ }
+ if (mode == MTE_SYNC_ERR && syscall_len < len) {
+ /* test passed */
+ } else if (mode == MTE_ASYNC_ERR && syscall_len == size) {
+ /* test passed */
+ } else {
+ goto usermem_acc_err;
+ }
+ }
+ }
}
+
+ goto exit;
+
usermem_acc_err:
+ err = KSFT_FAIL;
+exit:
mte_free_memory((void *)ptr, len, mem_type, true);
close(fd);
return err;
}
+void format_test_name(char* name, int name_len, int type, int sync, int map, int len, int offset) {
+ const char* test_type;
+ const char* mte_type;
+ const char* map_type;
+
+ switch (type) {
+ case READ_TEST:
+ test_type = "read";
+ break;
+ case WRITE_TEST:
+ test_type = "write";
+ break;
+ case READV_TEST:
+ test_type = "readv";
+ break;
+ case WRITEV_TEST:
+ test_type = "writev";
+ break;
+ default:
+ assert(0);
+ break;
+ }
+
+ switch (sync) {
+ case MTE_SYNC_ERR:
+ mte_type = "MTE_SYNC_ERR";
+ break;
+ case MTE_ASYNC_ERR:
+ mte_type = "MTE_ASYNC_ERR";
+ break;
+ default:
+ assert(0);
+ break;
+ }
+
+ switch (map) {
+ case MAP_SHARED:
+ map_type = "MAP_SHARED";
+ break;
+ case MAP_PRIVATE:
+ map_type = "MAP_PRIVATE";
+ break;
+ default:
+ assert(0);
+ break;
+ }
+
+ snprintf(name, name_len,
+ "test type: %s, %s, %s, tag len: %d, tag offset: %d\n",
+ test_type, mte_type, map_type, len, offset);
+}
+
int main(int argc, char *argv[])
{
int err;
+ int t, s, m, l, o;
+ int mte_sync[] = {MTE_SYNC_ERR, MTE_ASYNC_ERR};
+ int maps[] = {MAP_SHARED, MAP_PRIVATE};
+ int tag_lens[] = {0, MT_GRANULE_SIZE};
+ int tag_offsets[] = {page_sz, MT_GRANULE_SIZE};
+ char test_name[TEST_NAME_MAX];
page_sz = getpagesize();
if (!page_sz) {
@@ -98,17 +214,28 @@ int main(int argc, char *argv[])
mte_register_signal(SIGSEGV, mte_default_handler);
/* Set test plan */
- ksft_set_plan(4);
+ ksft_set_plan(64);
- evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE),
- "Check memory access from kernel in sync mode, private mapping and mmap memory\n");
- evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED),
- "Check memory access from kernel in sync mode, shared mapping and mmap memory\n");
-
- evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE),
- "Check memory access from kernel in async mode, private mapping and mmap memory\n");
- evaluate_test(check_usermem_access_fault(USE_MMAP, MTE_ASYNC_ERR, MAP_SHARED),
- "Check memory access from kernel in async mode, shared mapping and mmap memory\n");
+ for (t = 0; t < LAST_TEST; t++) {
+ for (s = 0; s < ARRAY_SIZE(mte_sync); s++) {
+ for (m = 0; m < ARRAY_SIZE(maps); m++) {
+ for (l = 0; l < ARRAY_SIZE(tag_lens); l++) {
+ for (o = 0; o < ARRAY_SIZE(tag_offsets); o++) {
+ int sync = mte_sync[s];
+ int map = maps[m];
+ int offset = tag_offsets[o];
+ int tag_len = tag_lens[l];
+ int res = check_usermem_access_fault(USE_MMAP, sync,
+ map, offset,
+ tag_len, t);
+ format_test_name(test_name, TEST_NAME_MAX,
+ t, sync, map, tag_len, offset);
+ evaluate_test(res, test_name);
+ }
+ }
+ }
+ }
+ }
mte_restore_setup();
ksft_print_cnts();
diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h
index ebe8694dbef0..f909b70d9e98 100644
--- a/tools/testing/selftests/arm64/signal/test_signals.h
+++ b/tools/testing/selftests/arm64/signal/test_signals.h
@@ -53,6 +53,7 @@ struct tdescr {
char *name;
char *descr;
unsigned long feats_required;
+ unsigned long feats_incompatible;
/* bitmask of effectively supported feats: populated at run-time */
unsigned long feats_supported;
bool initialized;
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c
index 2f8c23af3b5e..5743897984b0 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.c
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c
@@ -36,6 +36,8 @@ static inline char *feats_to_string(unsigned long feats)
{
size_t flen = MAX_FEATS_SZ - 1;
+ feats_string[0] = '\0';
+
for (int i = 0; i < FMAX_END; i++) {
if (feats & (1UL << i)) {
size_t tlen = strlen(feats_names[i]);
@@ -256,7 +258,7 @@ int test_init(struct tdescr *td)
td->minsigstksz = MINSIGSTKSZ;
fprintf(stderr, "Detected MINSTKSIGSZ:%d\n", td->minsigstksz);
- if (td->feats_required) {
+ if (td->feats_required || td->feats_incompatible) {
td->feats_supported = 0;
/*
* Checking for CPU required features using both the
@@ -267,15 +269,29 @@ int test_init(struct tdescr *td)
if (getauxval(AT_HWCAP) & HWCAP_SVE)
td->feats_supported |= FEAT_SVE;
if (feats_ok(td)) {
- fprintf(stderr,
- "Required Features: [%s] supported\n",
- feats_to_string(td->feats_required &
- td->feats_supported));
+ if (td->feats_required & td->feats_supported)
+ fprintf(stderr,
+ "Required Features: [%s] supported\n",
+ feats_to_string(td->feats_required &
+ td->feats_supported));
+ if (!(td->feats_incompatible & td->feats_supported))
+ fprintf(stderr,
+ "Incompatible Features: [%s] absent\n",
+ feats_to_string(td->feats_incompatible));
} else {
- fprintf(stderr,
- "Required Features: [%s] NOT supported\n",
- feats_to_string(td->feats_required &
- ~td->feats_supported));
+ if ((td->feats_required & td->feats_supported) !=
+ td->feats_supported)
+ fprintf(stderr,
+ "Required Features: [%s] NOT supported\n",
+ feats_to_string(td->feats_required &
+ ~td->feats_supported));
+ if (td->feats_incompatible & td->feats_supported)
+ fprintf(stderr,
+ "Incompatible Features: [%s] supported\n",
+ feats_to_string(td->feats_incompatible &
+ ~td->feats_supported));
+
+
td->result = KSFT_SKIP;
return 0;
}
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h
index 6772b5c8d274..f3aa99ba67bb 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.h
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h
@@ -18,6 +18,8 @@ void test_result(struct tdescr *td);
static inline bool feats_ok(struct tdescr *td)
{
+ if (td->feats_incompatible & td->feats_supported)
+ return false;
return (td->feats_required & td->feats_supported) == td->feats_required;
}
diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c
index 32fc5b3b5cf6..911345c526e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/d_path.c
+++ b/tools/testing/selftests/bpf/prog_tests/d_path.c
@@ -10,6 +10,7 @@
#include "test_d_path.skel.h"
#include "test_d_path_check_rdonly_mem.skel.h"
+#include "test_d_path_check_types.skel.h"
static int duration;
@@ -167,6 +168,16 @@ static void test_d_path_check_rdonly_mem(void)
test_d_path_check_rdonly_mem__destroy(skel);
}
+static void test_d_path_check_types(void)
+{
+ struct test_d_path_check_types *skel;
+
+ skel = test_d_path_check_types__open_and_load();
+ ASSERT_ERR_PTR(skel, "unexpected_load_passing_wrong_type");
+
+ test_d_path_check_types__destroy(skel);
+}
+
void test_d_path(void)
{
if (test__start_subtest("basic"))
@@ -174,4 +185,7 @@ void test_d_path(void)
if (test__start_subtest("check_rdonly_mem"))
test_d_path_check_rdonly_mem();
+
+ if (test__start_subtest("check_alloc_mem"))
+ test_d_path_check_types();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
new file mode 100644
index 000000000000..f74b82305da8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "timer_crash.skel.h"
+
+enum {
+ MODE_ARRAY,
+ MODE_HASH,
+};
+
+static void test_timer_crash_mode(int mode)
+{
+ struct timer_crash *skel;
+
+ skel = timer_crash__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load"))
+ return;
+ skel->bss->pid = getpid();
+ skel->bss->crash_map = mode;
+ if (!ASSERT_OK(timer_crash__attach(skel), "timer_crash__attach"))
+ goto end;
+ usleep(1);
+end:
+ timer_crash__destroy(skel);
+}
+
+void test_timer_crash(void)
+{
+ if (test__start_subtest("array"))
+ test_timer_crash_mode(MODE_ARRAY);
+ if (test__start_subtest("hash"))
+ test_timer_crash_mode(MODE_HASH);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
index 983ab0b47d30..b2b357f8c74c 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
@@ -8,46 +8,47 @@
void serial_test_xdp_link(void)
{
- __u32 duration = 0, id1, id2, id0 = 0, prog_fd1, prog_fd2, err;
DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1);
struct test_xdp_link *skel1 = NULL, *skel2 = NULL;
+ __u32 id1, id2, id0 = 0, prog_fd1, prog_fd2;
struct bpf_link_info link_info;
struct bpf_prog_info prog_info;
struct bpf_link *link;
+ int err;
__u32 link_info_len = sizeof(link_info);
__u32 prog_info_len = sizeof(prog_info);
skel1 = test_xdp_link__open_and_load();
- if (CHECK(!skel1, "skel_load", "skeleton open and load failed\n"))
+ if (!ASSERT_OK_PTR(skel1, "skel_load"))
goto cleanup;
prog_fd1 = bpf_program__fd(skel1->progs.xdp_handler);
skel2 = test_xdp_link__open_and_load();
- if (CHECK(!skel2, "skel_load", "skeleton open and load failed\n"))
+ if (!ASSERT_OK_PTR(skel2, "skel_load"))
goto cleanup;
prog_fd2 = bpf_program__fd(skel2->progs.xdp_handler);
memset(&prog_info, 0, sizeof(prog_info));
err = bpf_obj_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len);
- if (CHECK(err, "fd_info1", "failed %d\n", -errno))
+ if (!ASSERT_OK(err, "fd_info1"))
goto cleanup;
id1 = prog_info.id;
memset(&prog_info, 0, sizeof(prog_info));
err = bpf_obj_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len);
- if (CHECK(err, "fd_info2", "failed %d\n", -errno))
+ if (!ASSERT_OK(err, "fd_info2"))
goto cleanup;
id2 = prog_info.id;
/* set initial prog attachment */
err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts);
- if (CHECK(err, "fd_attach", "initial prog attach failed: %d\n", err))
+ if (!ASSERT_OK(err, "fd_attach"))
goto cleanup;
/* validate prog ID */
err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
- CHECK(err || id0 != id1, "id1_check",
- "loaded prog id %u != id1 %u, err %d", id0, id1, err);
+ if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val"))
+ goto cleanup;
/* BPF link is not allowed to replace prog attachment */
link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO);
@@ -62,7 +63,7 @@ void serial_test_xdp_link(void)
/* detach BPF program */
opts.old_fd = prog_fd1;
err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts);
- if (CHECK(err, "prog_detach", "failed %d\n", err))
+ if (!ASSERT_OK(err, "prog_detach"))
goto cleanup;
/* now BPF link should attach successfully */
@@ -73,24 +74,23 @@ void serial_test_xdp_link(void)
/* validate prog ID */
err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
- if (CHECK(err || id0 != id1, "id1_check",
- "loaded prog id %u != id1 %u, err %d", id0, id1, err))
+ if (!ASSERT_OK(err, "id1_check_err") || !ASSERT_EQ(id0, id1, "id1_check_val"))
goto cleanup;
/* BPF prog attach is not allowed to replace BPF link */
opts.old_fd = prog_fd1;
err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts);
- if (CHECK(!err, "prog_attach_fail", "unexpected success\n"))
+ if (!ASSERT_ERR(err, "prog_attach_fail"))
goto cleanup;
/* Can't force-update when BPF link is active */
err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd2, 0);
- if (CHECK(!err, "prog_update_fail", "unexpected success\n"))
+ if (!ASSERT_ERR(err, "prog_update_fail"))
goto cleanup;
/* Can't force-detach when BPF link is active */
err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0);
- if (CHECK(!err, "prog_detach_fail", "unexpected success\n"))
+ if (!ASSERT_ERR(err, "prog_detach_fail"))
goto cleanup;
/* BPF link is not allowed to replace another BPF link */
@@ -110,40 +110,39 @@ void serial_test_xdp_link(void)
skel2->links.xdp_handler = link;
err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
- if (CHECK(err || id0 != id2, "id2_check",
- "loaded prog id %u != id2 %u, err %d", id0, id1, err))
+ if (!ASSERT_OK(err, "id2_check_err") || !ASSERT_EQ(id0, id2, "id2_check_val"))
goto cleanup;
/* updating program under active BPF link works as expected */
err = bpf_link__update_program(link, skel1->progs.xdp_handler);
- if (CHECK(err, "link_upd", "failed: %d\n", err))
+ if (!ASSERT_OK(err, "link_upd"))
goto cleanup;
memset(&link_info, 0, sizeof(link_info));
err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
- if (CHECK(err, "link_info", "failed: %d\n", err))
+ if (!ASSERT_OK(err, "link_info"))
goto cleanup;
- CHECK(link_info.type != BPF_LINK_TYPE_XDP, "link_type",
- "got %u != exp %u\n", link_info.type, BPF_LINK_TYPE_XDP);
- CHECK(link_info.prog_id != id1, "link_prog_id",
- "got %u != exp %u\n", link_info.prog_id, id1);
- CHECK(link_info.xdp.ifindex != IFINDEX_LO, "link_ifindex",
- "got %u != exp %u\n", link_info.xdp.ifindex, IFINDEX_LO);
+ ASSERT_EQ(link_info.type, BPF_LINK_TYPE_XDP, "link_type");
+ ASSERT_EQ(link_info.prog_id, id1, "link_prog_id");
+ ASSERT_EQ(link_info.xdp.ifindex, IFINDEX_LO, "link_ifindex");
+
+ /* updating program under active BPF link with different type fails */
+ err = bpf_link__update_program(link, skel1->progs.tc_handler);
+ if (!ASSERT_ERR(err, "link_upd_invalid"))
+ goto cleanup;
err = bpf_link__detach(link);
- if (CHECK(err, "link_detach", "failed %d\n", err))
+ if (!ASSERT_OK(err, "link_detach"))
goto cleanup;
memset(&link_info, 0, sizeof(link_info));
err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
- if (CHECK(err, "link_info", "failed: %d\n", err))
- goto cleanup;
- CHECK(link_info.prog_id != id1, "link_prog_id",
- "got %u != exp %u\n", link_info.prog_id, id1);
+
+ ASSERT_OK(err, "link_info");
+ ASSERT_EQ(link_info.prog_id, id1, "link_prog_id");
/* ifindex should be zeroed out */
- CHECK(link_info.xdp.ifindex != 0, "link_ifindex",
- "got %u != exp %u\n", link_info.xdp.ifindex, 0);
+ ASSERT_EQ(link_info.xdp.ifindex, 0, "link_ifindex");
cleanup:
test_xdp_link__destroy(skel1);
diff --git a/tools/testing/selftests/bpf/progs/test_d_path_check_types.c b/tools/testing/selftests/bpf/progs/test_d_path_check_types.c
new file mode 100644
index 000000000000..7e02b7361307
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_d_path_check_types.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+extern const int bpf_prog_active __ksym;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_RINGBUF);
+ __uint(max_entries, 1 << 12);
+} ringbuf SEC(".maps");
+
+SEC("fentry/security_inode_getattr")
+int BPF_PROG(d_path_check_rdonly_mem, struct path *path, struct kstat *stat,
+ __u32 request_mask, unsigned int query_flags)
+{
+ void *active;
+ u32 cpu;
+
+ cpu = bpf_get_smp_processor_id();
+ active = (void *)bpf_per_cpu_ptr(&bpf_prog_active, cpu);
+ if (active) {
+ /* FAIL here! 'active' points to 'regular' memory. It
+ * cannot be submitted to ring buffer.
+ */
+ bpf_ringbuf_submit(active, 0);
+ }
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
index 2966564b8497..6c85b00f27b2 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
@@ -235,7 +235,7 @@ SEC("sk_msg1")
int bpf_prog4(struct sk_msg_md *msg)
{
int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
- int *start, *end, *start_push, *end_push, *start_pop, *pop;
+ int *start, *end, *start_push, *end_push, *start_pop, *pop, err = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
@@ -249,8 +249,11 @@ int bpf_prog4(struct sk_msg_md *msg)
bpf_msg_pull_data(msg, *start, *end, 0);
start_push = bpf_map_lookup_elem(&sock_bytes, &two);
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push)
- bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (start_push && end_push) {
+ err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (err)
+ return SK_DROP;
+ }
start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
pop = bpf_map_lookup_elem(&sock_bytes, &five);
if (start_pop && pop)
@@ -263,6 +266,7 @@ int bpf_prog6(struct sk_msg_md *msg)
{
int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0;
int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f;
+ int err = 0;
__u64 flags = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
@@ -279,8 +283,11 @@ int bpf_prog6(struct sk_msg_md *msg)
start_push = bpf_map_lookup_elem(&sock_bytes, &two);
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push)
- bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (start_push && end_push) {
+ err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (err)
+ return SK_DROP;
+ }
start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
pop = bpf_map_lookup_elem(&sock_bytes, &five);
@@ -338,7 +345,7 @@ SEC("sk_msg5")
int bpf_prog10(struct sk_msg_md *msg)
{
int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop;
- int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
+ int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, err = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
@@ -352,8 +359,11 @@ int bpf_prog10(struct sk_msg_md *msg)
bpf_msg_pull_data(msg, *start, *end, 0);
start_push = bpf_map_lookup_elem(&sock_bytes, &two);
end_push = bpf_map_lookup_elem(&sock_bytes, &three);
- if (start_push && end_push)
- bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (start_push && end_push) {
+ err = bpf_msg_push_data(msg, *start_push, *end_push, 0);
+ if (err)
+ return SK_PASS;
+ }
start_pop = bpf_map_lookup_elem(&sock_bytes, &four);
pop = bpf_map_lookup_elem(&sock_bytes, &five);
if (start_pop && pop)
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index a8233e7f173b..728dbd39eff0 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
-#include <linux/bpf.h>
+#include <vmlinux.h>
#include <bpf/bpf_helpers.h>
#ifndef PERF_MAX_STACK_DEPTH
@@ -41,11 +41,11 @@ struct {
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
unsigned long long pad;
- char prev_comm[16];
+ char prev_comm[TASK_COMM_LEN];
int prev_pid;
int prev_prio;
long long prev_state;
- char next_comm[16];
+ char next_comm[TASK_COMM_LEN];
int next_pid;
int next_prio;
};
diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c
index ce6974016f53..43bd7a20cc50 100644
--- a/tools/testing/selftests/bpf/progs/test_tracepoint.c
+++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c
@@ -1,17 +1,17 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2017 Facebook
-#include <linux/bpf.h>
+#include <vmlinux.h>
#include <bpf/bpf_helpers.h>
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
unsigned long long pad;
- char prev_comm[16];
+ char prev_comm[TASK_COMM_LEN];
int prev_pid;
int prev_prio;
long long prev_state;
- char next_comm[16];
+ char next_comm[TASK_COMM_LEN];
int next_pid;
int next_prio;
};
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c
index ee7d6ac0f615..64ff32eaae92 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_link.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c
@@ -10,3 +10,9 @@ int xdp_handler(struct xdp_md *xdp)
{
return 0;
}
+
+SEC("tc")
+int tc_handler(struct __sk_buff *skb)
+{
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_crash.c b/tools/testing/selftests/bpf/progs/timer_crash.c
new file mode 100644
index 000000000000..f8f7944e70da
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_crash.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+struct map_elem {
+ struct bpf_timer timer;
+ struct bpf_spin_lock lock;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct map_elem);
+} amap SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct map_elem);
+} hmap SEC(".maps");
+
+int pid = 0;
+int crash_map = 0; /* 0 for amap, 1 for hmap */
+
+SEC("fentry/do_nanosleep")
+int sys_enter(void *ctx)
+{
+ struct map_elem *e, value = {};
+ void *map = crash_map ? (void *)&hmap : (void *)&amap;
+
+ if (bpf_get_current_task_btf()->tgid != pid)
+ return 0;
+
+ *(void **)&value = (void *)0xdeadcaf3;
+
+ bpf_map_update_elem(map, &(int){0}, &value, 0);
+ /* For array map, doing bpf_map_update_elem will do a
+ * check_and_free_timer_in_array, which will trigger the crash if timer
+ * pointer was overwritten, for hmap we need to use bpf_timer_cancel.
+ */
+ if (crash_map == 1) {
+ e = bpf_map_lookup_elem(map, &(int){0});
+ if (!e)
+ return 0;
+ bpf_timer_cancel(&e->timer);
+ }
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
index ebf68dce5504..2893e9f2f1e0 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
@@ -28,7 +28,6 @@
// 5. We can read keycode from same /dev/lirc device
#include <linux/bpf.h>
-#include <linux/lirc.h>
#include <linux/input.h>
#include <errno.h>
#include <stdio.h>
diff --git a/tools/testing/selftests/bpf/verifier/ringbuf.c b/tools/testing/selftests/bpf/verifier/ringbuf.c
new file mode 100644
index 000000000000..b64d33e4833c
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/ringbuf.c
@@ -0,0 +1,95 @@
+{
+ "ringbuf: invalid reservation offset 1",
+ .insns = {
+ /* reserve 8 byte ringbuf memory */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+ /* store a pointer to the reserved memory in R6 */
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ /* check whether the reservation was successful */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ /* spill R6(mem) into the stack */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+ /* fill it back in R7 */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
+ /* should be able to access *(R7) = 0 */
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
+ /* submit the reserved ringbuf memory */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ /* add invalid offset to reserved ringbuf memory */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xcafe),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_ringbuf = { 1 },
+ .result = REJECT,
+ .errstr = "dereference of modified alloc_mem ptr R1",
+},
+{
+ "ringbuf: invalid reservation offset 2",
+ .insns = {
+ /* reserve 8 byte ringbuf memory */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+ /* store a pointer to the reserved memory in R6 */
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ /* check whether the reservation was successful */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ /* spill R6(mem) into the stack */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
+ /* fill it back in R7 */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
+ /* add invalid offset to reserved ringbuf memory */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 0xcafe),
+ /* should be able to access *(R7) = 0 */
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
+ /* submit the reserved ringbuf memory */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_ringbuf = { 1 },
+ .result = REJECT,
+ .errstr = "R7 min value is outside of the allowed memory range",
+},
+{
+ "ringbuf: check passing rb mem to helpers",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ /* reserve 8 byte ringbuf memory */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_2, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ /* check whether the reservation was successful */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ /* pass allocated ring buffer memory to fib lookup */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_fib_lookup),
+ /* submit the ringbuf memory */
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_ringbuf = { 2 },
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c
index 1a8eb9672bd1..8cfc5349d2a8 100644
--- a/tools/testing/selftests/bpf/verifier/spill_fill.c
+++ b/tools/testing/selftests/bpf/verifier/spill_fill.c
@@ -84,7 +84,7 @@
},
.fixup_map_ringbuf = { 1 },
.result = REJECT,
- .errstr = "R0 pointer arithmetic on mem_or_null prohibited",
+ .errstr = "R0 pointer arithmetic on alloc_mem_or_null prohibited",
},
{
"check corrupted spill/fill",
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 0cf7e90c0052..dbaa7aabbb4a 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -583,7 +583,7 @@ int clone_into_cgroup_run_wait(const char *cgroup)
return 0;
}
-int cg_prepare_for_wait(const char *cgroup)
+static int __prepare_for_wait(const char *cgroup, const char *filename)
{
int fd, ret = -1;
@@ -591,8 +591,7 @@ int cg_prepare_for_wait(const char *cgroup)
if (fd == -1)
return fd;
- ret = inotify_add_watch(fd, cg_control(cgroup, "cgroup.events"),
- IN_MODIFY);
+ ret = inotify_add_watch(fd, cg_control(cgroup, filename), IN_MODIFY);
if (ret == -1) {
close(fd);
fd = -1;
@@ -601,6 +600,16 @@ int cg_prepare_for_wait(const char *cgroup)
return fd;
}
+int cg_prepare_for_wait(const char *cgroup)
+{
+ return __prepare_for_wait(cgroup, "cgroup.events");
+}
+
+int memcg_prepare_for_wait(const char *cgroup)
+{
+ return __prepare_for_wait(cgroup, "memory.events");
+}
+
int cg_wait_for(int fd)
{
int ret = -1;
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
index 4f66d10626d2..628738532ac9 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -55,4 +55,5 @@ extern int clone_reap(pid_t pid, int options);
extern int clone_into_cgroup_run_wait(const char *cgroup);
extern int dirfd_open_opath(const char *dir);
extern int cg_prepare_for_wait(const char *cgroup);
+extern int memcg_prepare_for_wait(const char *cgroup);
extern int cg_wait_for(int fd);
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index c19a97dd02d4..36ccf2322e21 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -16,6 +16,7 @@
#include <netinet/in.h>
#include <netdb.h>
#include <errno.h>
+#include <sys/mman.h>
#include "../kselftest.h"
#include "cgroup_util.h"
@@ -628,6 +629,82 @@ cleanup:
return ret;
}
+static int alloc_anon_mlock(const char *cgroup, void *arg)
+{
+ size_t size = (size_t)arg;
+ void *buf;
+
+ buf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON,
+ 0, 0);
+ if (buf == MAP_FAILED)
+ return -1;
+
+ mlock(buf, size);
+ munmap(buf, size);
+ return 0;
+}
+
+/*
+ * This test checks that memory.high is able to throttle big single shot
+ * allocation i.e. large allocation within one kernel entry.
+ */
+static int test_memcg_high_sync(const char *root)
+{
+ int ret = KSFT_FAIL, pid, fd = -1;
+ char *memcg;
+ long pre_high, pre_max;
+ long post_high, post_max;
+
+ memcg = cg_name(root, "memcg_test");
+ if (!memcg)
+ goto cleanup;
+
+ if (cg_create(memcg))
+ goto cleanup;
+
+ pre_high = cg_read_key_long(memcg, "memory.events", "high ");
+ pre_max = cg_read_key_long(memcg, "memory.events", "max ");
+ if (pre_high < 0 || pre_max < 0)
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.swap.max", "0"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.high", "30M"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.max", "140M"))
+ goto cleanup;
+
+ fd = memcg_prepare_for_wait(memcg);
+ if (fd < 0)
+ goto cleanup;
+
+ pid = cg_run_nowait(memcg, alloc_anon_mlock, (void *)MB(200));
+ if (pid < 0)
+ goto cleanup;
+
+ cg_wait_for(fd);
+
+ post_high = cg_read_key_long(memcg, "memory.events", "high ");
+ post_max = cg_read_key_long(memcg, "memory.events", "max ");
+ if (post_high < 0 || post_max < 0)
+ goto cleanup;
+
+ if (pre_high == post_high || pre_max != post_max)
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ if (fd >= 0)
+ close(fd);
+ cg_destroy(memcg);
+ free(memcg);
+
+ return ret;
+}
+
/*
* This test checks that memory.max limits the amount of
* memory which can be consumed by either anonymous memory
@@ -1180,6 +1257,7 @@ struct memcg_test {
T(test_memcg_min),
T(test_memcg_low),
T(test_memcg_high),
+ T(test_memcg_high_sync),
T(test_memcg_max),
T(test_memcg_oom_events),
T(test_memcg_swap_max),
diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c
index 076cf4325f78..cd4582129c7d 100644
--- a/tools/testing/selftests/clone3/clone3.c
+++ b/tools/testing/selftests/clone3/clone3.c
@@ -126,8 +126,6 @@ static void test_clone3(uint64_t flags, size_t size, int expected,
int main(int argc, char *argv[])
{
- pid_t pid;
-
uid_t uid = getuid();
ksft_print_header();
diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh
index 31f8c9a76c5f..60ce18ed0666 100755
--- a/tools/testing/selftests/cpufreq/main.sh
+++ b/tools/testing/selftests/cpufreq/main.sh
@@ -194,5 +194,5 @@ prerequisite
# Run requested functions
clear_dumps $OUTFILE
-do_test >> $OUTFILE.txt
+do_test | tee -a $OUTFILE.txt
dmesg_dumps $OUTFILE
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 937d36ae9a69..0470c5f3e690 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -6,5 +6,6 @@ TEST_GEN_FILES += huge_count_read_write
TEST_FILES = _chk_dependency.sh _debugfs_common.sh
TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh
TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh
+TEST_PROGS += sysfs.sh
include ../lib.mk
diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh
new file mode 100644
index 000000000000..2e3ae77cb6db
--- /dev/null
+++ b/tools/testing/selftests/damon/sysfs.sh
@@ -0,0 +1,306 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest frmework requirement - SKIP code is 4.
+ksft_skip=4
+
+ensure_write_succ()
+{
+ file=$1
+ content=$2
+ reason=$3
+
+ if ! echo "$content" > "$file"
+ then
+ echo "writing $content to $file failed"
+ echo "expected success because $reason"
+ exit 1
+ fi
+}
+
+ensure_write_fail()
+{
+ file=$1
+ content=$2
+ reason=$3
+
+ if echo "$content" > "$file"
+ then
+ echo "writing $content to $file succeed ($fail_reason)"
+ echo "expected failure because $reason"
+ exit 1
+ fi
+}
+
+ensure_dir()
+{
+ dir=$1
+ to_ensure=$2
+ if [ "$to_ensure" = "exist" ] && [ ! -d "$dir" ]
+ then
+ echo "$dir dir is expected but not found"
+ exit 1
+ elif [ "$to_ensure" = "not_exist" ] && [ -d "$dir" ]
+ then
+ echo "$dir dir is not expected but found"
+ exit 1
+ fi
+}
+
+ensure_file()
+{
+ file=$1
+ to_ensure=$2
+ permission=$3
+ if [ "$to_ensure" = "exist" ]
+ then
+ if [ ! -f "$file" ]
+ then
+ echo "$file is expected but not found"
+ exit 1
+ fi
+ perm=$(stat -c "%a" "$file")
+ if [ ! "$perm" = "$permission" ]
+ then
+ echo "$file permission: expected $permission but $perm"
+ exit 1
+ fi
+ elif [ "$to_ensure" = "not_exist" ] && [ -f "$dir" ]
+ then
+ echo "$file is not expected but found"
+ exit 1
+ fi
+}
+
+test_range()
+{
+ range_dir=$1
+ ensure_dir "$range_dir" "exist"
+ ensure_file "$range_dir/min" "exist" 600
+ ensure_file "$range_dir/max" "exist" 600
+}
+
+test_stats()
+{
+ stats_dir=$1
+ ensure_dir "$stats_dir" "exist"
+ for f in nr_tried sz_tried nr_applied sz_applied qt_exceeds
+ do
+ ensure_file "$stats_dir/$f" "exist" "400"
+ done
+}
+
+test_watermarks()
+{
+ watermarks_dir=$1
+ ensure_dir "$watermarks_dir" "exist"
+ ensure_file "$watermarks_dir/metric" "exist" "600"
+ ensure_file "$watermarks_dir/interval_us" "exist" "600"
+ ensure_file "$watermarks_dir/high" "exist" "600"
+ ensure_file "$watermarks_dir/mid" "exist" "600"
+ ensure_file "$watermarks_dir/low" "exist" "600"
+}
+
+test_weights()
+{
+ weights_dir=$1
+ ensure_dir "$weights_dir" "exist"
+ ensure_file "$weights_dir/sz_permil" "exist" "600"
+ ensure_file "$weights_dir/nr_accesses_permil" "exist" "600"
+ ensure_file "$weights_dir/age_permil" "exist" "600"
+}
+
+test_quotas()
+{
+ quotas_dir=$1
+ ensure_dir "$quotas_dir" "exist"
+ ensure_file "$quotas_dir/ms" "exist" 600
+ ensure_file "$quotas_dir/bytes" "exist" 600
+ ensure_file "$quotas_dir/reset_interval_ms" "exist" 600
+ test_weights "$quotas_dir/weights"
+}
+
+test_access_pattern()
+{
+ access_pattern_dir=$1
+ ensure_dir "$access_pattern_dir" "exist"
+ test_range "$access_pattern_dir/age"
+ test_range "$access_pattern_dir/nr_accesses"
+ test_range "$access_pattern_dir/sz"
+}
+
+test_scheme()
+{
+ scheme_dir=$1
+ ensure_dir "$scheme_dir" "exist"
+ ensure_file "$scheme_dir/action" "exist" "600"
+ test_access_pattern "$scheme_dir/access_pattern"
+ test_quotas "$scheme_dir/quotas"
+ test_watermarks "$scheme_dir/watermarks"
+ test_stats "$scheme_dir/stats"
+}
+
+test_schemes()
+{
+ schemes_dir=$1
+ ensure_dir "$schemes_dir" "exist"
+ ensure_file "$schemes_dir/nr_schemes" "exist" 600
+
+ ensure_write_succ "$schemes_dir/nr_schemes" "1" "valid input"
+ test_scheme "$schemes_dir/0"
+
+ ensure_write_succ "$schemes_dir/nr_schemes" "2" "valid input"
+ test_scheme "$schemes_dir/0"
+ test_scheme "$schemes_dir/1"
+
+ ensure_write_succ "$schemes_dir/nr_schemes" "0" "valid input"
+ ensure_dir "$schemes_dir/0" "not_exist"
+ ensure_dir "$schemes_dir/1" "not_exist"
+}
+
+test_region()
+{
+ region_dir=$1
+ ensure_dir "$region_dir" "exist"
+ ensure_file "$region_dir/start" "exist" 600
+ ensure_file "$region_dir/end" "exist" 600
+}
+
+test_regions()
+{
+ regions_dir=$1
+ ensure_dir "$regions_dir" "exist"
+ ensure_file "$regions_dir/nr_regions" "exist" 600
+
+ ensure_write_succ "$regions_dir/nr_regions" "1" "valid input"
+ test_region "$regions_dir/0"
+
+ ensure_write_succ "$regions_dir/nr_regions" "2" "valid input"
+ test_region "$regions_dir/0"
+ test_region "$regions_dir/1"
+
+ ensure_write_succ "$regions_dir/nr_regions" "0" "valid input"
+ ensure_dir "$regions_dir/0" "not_exist"
+ ensure_dir "$regions_dir/1" "not_exist"
+}
+
+test_target()
+{
+ target_dir=$1
+ ensure_dir "$target_dir" "exist"
+ ensure_file "$target_dir/pid_target" "exist" "600"
+ test_regions "$target_dir/regions"
+}
+
+test_targets()
+{
+ targets_dir=$1
+ ensure_dir "$targets_dir" "exist"
+ ensure_file "$targets_dir/nr_targets" "exist" 600
+
+ ensure_write_succ "$targets_dir/nr_targets" "1" "valid input"
+ test_target "$targets_dir/0"
+
+ ensure_write_succ "$targets_dir/nr_targets" "2" "valid input"
+ test_target "$targets_dir/0"
+ test_target "$targets_dir/1"
+
+ ensure_write_succ "$targets_dir/nr_targets" "0" "valid input"
+ ensure_dir "$targets_dir/0" "not_exist"
+ ensure_dir "$targets_dir/1" "not_exist"
+}
+
+test_intervals()
+{
+ intervals_dir=$1
+ ensure_dir "$intervals_dir" "exist"
+ ensure_file "$intervals_dir/aggr_us" "exist" "600"
+ ensure_file "$intervals_dir/sample_us" "exist" "600"
+ ensure_file "$intervals_dir/update_us" "exist" "600"
+}
+
+test_monitoring_attrs()
+{
+ monitoring_attrs_dir=$1
+ ensure_dir "$monitoring_attrs_dir" "exist"
+ test_intervals "$monitoring_attrs_dir/intervals"
+ test_range "$monitoring_attrs_dir/nr_regions"
+}
+
+test_context()
+{
+ context_dir=$1
+ ensure_dir "$context_dir" "exist"
+ ensure_file "$context_dir/operations" "exist" 600
+ test_monitoring_attrs "$context_dir/monitoring_attrs"
+ test_targets "$context_dir/targets"
+ test_schemes "$context_dir/schemes"
+}
+
+test_contexts()
+{
+ contexts_dir=$1
+ ensure_dir "$contexts_dir" "exist"
+ ensure_file "$contexts_dir/nr_contexts" "exist" 600
+
+ ensure_write_succ "$contexts_dir/nr_contexts" "1" "valid input"
+ test_context "$contexts_dir/0"
+
+ ensure_write_fail "$contexts_dir/nr_contexts" "2" "only 0/1 are supported"
+ test_context "$contexts_dir/0"
+
+ ensure_write_succ "$contexts_dir/nr_contexts" "0" "valid input"
+ ensure_dir "$contexts_dir/0" "not_exist"
+}
+
+test_kdamond()
+{
+ kdamond_dir=$1
+ ensure_dir "$kdamond_dir" "exist"
+ ensure_file "$kdamond_dir/state" "exist" "600"
+ ensure_file "$kdamond_dir/pid" "exist" 400
+ test_contexts "$kdamond_dir/contexts"
+}
+
+test_kdamonds()
+{
+ kdamonds_dir=$1
+ ensure_dir "$kdamonds_dir" "exist"
+
+ ensure_file "$kdamonds_dir/nr_kdamonds" "exist" "600"
+
+ ensure_write_succ "$kdamonds_dir/nr_kdamonds" "1" "valid input"
+ test_kdamond "$kdamonds_dir/0"
+
+ ensure_write_succ "$kdamonds_dir/nr_kdamonds" "2" "valid input"
+ test_kdamond "$kdamonds_dir/0"
+ test_kdamond "$kdamonds_dir/1"
+
+ ensure_write_succ "$kdamonds_dir/nr_kdamonds" "0" "valid input"
+ ensure_dir "$kdamonds_dir/0" "not_exist"
+ ensure_dir "$kdamonds_dir/1" "not_exist"
+}
+
+test_damon_sysfs()
+{
+ damon_sysfs=$1
+ if [ ! -d "$damon_sysfs" ]
+ then
+ echo "$damon_sysfs not found"
+ exit $ksft_skip
+ fi
+
+ test_kdamonds "$damon_sysfs/kdamonds"
+}
+
+check_dependencies()
+{
+ if [ $EUID -ne 0 ]
+ then
+ echo "Run as root"
+ exit $ksft_skip
+ fi
+}
+
+check_dependencies
+test_damon_sysfs "/sys/kernel/mm/damon/admin"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index bcb110e830ce..dea33dc93790 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -50,8 +50,8 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
else
log_test "'$current_test' [$profile] overflow $target"
fi
+ RET_FIN=$(( RET_FIN || RET ))
done
- RET_FIN=$(( RET_FIN || RET ))
done
done
current_test=""
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
index 3e3e06ea5703..86e787895f78 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh
@@ -60,7 +60,8 @@ __tc_police_test()
tc_police_rules_create $count $should_fail
- offload_count=$(tc filter show dev $swp1 ingress | grep in_hw | wc -l)
+ offload_count=$(tc -j filter show dev $swp1 ingress |
+ jq "[.[] | select(.options.in_hw == true)] | length")
((offload_count == count))
check_err_fail $should_fail $? "tc police offload count"
}
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index dd61118df66e..a89ba6de7987 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -3,13 +3,14 @@ CFLAGS = -Wall
CFLAGS += -Wno-nonnull
CFLAGS += -D_GNU_SOURCE
-TEST_PROGS := binfmt_script non-regular
-TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216
-TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir pipe
+TEST_PROGS := binfmt_script
+TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 non-regular
+TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir
# Makefile is a run-time dependency, since it's accessed by the execveat test
TEST_FILES := Makefile
TEST_GEN_PROGS += recursion-depth
+TEST_GEN_PROGS += null-argv
EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx* \
$(OUTPUT)/S_I*.test
diff --git a/tools/testing/selftests/exec/null-argv.c b/tools/testing/selftests/exec/null-argv.c
new file mode 100644
index 000000000000..c19726e710d1
--- /dev/null
+++ b/tools/testing/selftests/exec/null-argv.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Test that empty argvs are swapped out for a single empty string. */
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include "../kselftest.h"
+
+#define FORK(exec) \
+do { \
+ pid = fork(); \
+ if (pid == 0) { \
+ /* Child */ \
+ exec; /* Some kind of exec */ \
+ perror("# " #exec); \
+ return 1; \
+ } \
+ check_result(pid, #exec); \
+} while (0)
+
+void check_result(pid_t pid, const char *msg)
+{
+ int wstatus;
+
+ if (pid == (pid_t)-1) {
+ perror("# fork");
+ ksft_test_result_fail("fork failed: %s\n", msg);
+ return;
+ }
+ if (waitpid(pid, &wstatus, 0) < 0) {
+ perror("# waitpid");
+ ksft_test_result_fail("waitpid failed: %s\n", msg);
+ return;
+ }
+ if (!WIFEXITED(wstatus)) {
+ ksft_test_result_fail("child did not exit: %s\n", msg);
+ return;
+ }
+ if (WEXITSTATUS(wstatus) != 0) {
+ ksft_test_result_fail("non-zero exit: %s\n", msg);
+ return;
+ }
+ ksft_test_result_pass("%s\n", msg);
+}
+
+int main(int argc, char *argv[], char *envp[])
+{
+ pid_t pid;
+ static char * const args[] = { NULL };
+ static char * const str[] = { "", NULL };
+
+ /* argc counting checks */
+ if (argc < 1) {
+ fprintf(stderr, "# FAIL: saw argc == 0 (old kernel?)\n");
+ return 1;
+ }
+ if (argc != 1) {
+ fprintf(stderr, "# FAIL: unknown argc (%d)\n", argc);
+ return 1;
+ }
+ if (argv[0][0] == '\0') {
+ /* Good, we found a NULL terminated string at argv[0]! */
+ return 0;
+ }
+
+ /* Test runner. */
+ ksft_print_header();
+ ksft_set_plan(5);
+
+ FORK(execve(argv[0], str, NULL));
+ FORK(execve(argv[0], NULL, NULL));
+ FORK(execve(argv[0], NULL, envp));
+ FORK(execve(argv[0], args, NULL));
+ FORK(execve(argv[0], args, envp));
+
+ ksft_exit(ksft_cnt.ksft_pass == ksft_plan);
+}
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
index e96e279e0533..25432b8cd5bd 100644
--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
@@ -19,7 +19,7 @@ fail() { # mesg
FILTER=set_ftrace_filter
FUNC1="schedule"
-FUNC2="do_softirq"
+FUNC2="scheduler_tick"
ALL_FUNCS="#### all functions enabled ####"
diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index 12631f0076a1..11e157d7533b 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -11,7 +11,7 @@ all:
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
- make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
if [ -e $$DIR/$(TEST_PROGS) ]; then \
rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \
fi \
@@ -32,6 +32,6 @@ override define CLEAN
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
- make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
done
endef
diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c
index 06256c96df12..f4a15cbdd5ea 100644
--- a/tools/testing/selftests/ir/ir_loopback.c
+++ b/tools/testing/selftests/ir/ir_loopback.c
@@ -29,6 +29,16 @@
#define SYSFS_PATH_MAX 256
#define DNAME_PATH_MAX 256
+/*
+ * Support ancient lirc.h which does not have these values. Can be removed
+ * once RHEL 8 is no longer a relevant testing platform.
+ */
+#if RC_PROTO_MAX < 26
+#define RC_PROTO_RCMM12 24
+#define RC_PROTO_RCMM24 25
+#define RC_PROTO_RCMM32 26
+#endif
+
static const struct {
enum rc_proto proto;
const char *name;
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 471eaa7b3a3f..11779405dc80 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -877,7 +877,8 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext)
}
t->timed_out = true;
- kill(t->pid, SIGKILL);
+ // signal process group
+ kill(-(t->pid), SIGKILL);
}
void __wait_for_test(struct __test_metadata *t)
@@ -987,6 +988,7 @@ void __run_test(struct __fixture_metadata *f,
ksft_print_msg("ERROR SPAWNING TEST CHILD\n");
t->passed = 0;
} else if (t->pid == 0) {
+ setpgrp();
t->fn(t, variant);
if (t->skip)
_exit(255);
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 3cb5ac5da087..dce7de7755e6 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -4,14 +4,16 @@
/aarch64/get-reg-list
/aarch64/psci_cpu_on_test
/aarch64/vgic_init
+/aarch64/vgic_irq
/s390x/memop
/s390x/resets
/s390x/sync_regs_test
+/x86_64/amx_test
+/x86_64/cpuid_test
/x86_64/cr4_cpuid_sync_test
/x86_64/debug_regs
/x86_64/evmcs_test
/x86_64/emulator_error_test
-/x86_64/get_cpuid_test
/x86_64/get_msr_index_features
/x86_64/kvm_clock_test
/x86_64/kvm_pv_test
@@ -21,6 +23,7 @@
/x86_64/mmio_warning_test
/x86_64/mmu_role_test
/x86_64/platform_info_test
+/x86_64/pmu_event_filter_test
/x86_64/set_boot_cpu_id
/x86_64/set_sregs_test
/x86_64/sev_migrate_tests
@@ -35,6 +38,7 @@
/x86_64/vmx_apic_access_test
/x86_64/vmx_close_while_nested_test
/x86_64/vmx_dirty_log_test
+/x86_64/vmx_exception_with_invalid_guest_state
/x86_64/vmx_invalid_nested_guest_state
/x86_64/vmx_preemption_timer_test
/x86_64/vmx_set_nested_state_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 17342b575e85..17c3f0749f05 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -32,17 +32,22 @@ endif
ifeq ($(ARCH),s390)
UNAME_M := s390x
endif
+# Set UNAME_M riscv compile/install to work
+ifeq ($(ARCH),riscv)
+ UNAME_M := riscv
+endif
LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c
LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
+LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c
-TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
+TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test
-TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features
@@ -51,6 +56,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
TEST_GEN_PROGS_x86_64 += x86_64/mmu_role_test
TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test
TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
TEST_GEN_PROGS_x86_64 += x86_64/smm_test
@@ -64,6 +70,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_exception_with_invalid_guest_state
TEST_GEN_PROGS_x86_64 += x86_64/vmx_invalid_nested_guest_state
TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
@@ -75,8 +82,9 @@ 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 += x86_64/vmx_pi_mmio_test
TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests
+TEST_GEN_PROGS_x86_64 += x86_64/amx_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
@@ -96,6 +104,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
+TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
TEST_GEN_PROGS_aarch64 += demand_paging_test
TEST_GEN_PROGS_aarch64 += dirty_log_test
TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
@@ -119,6 +128,13 @@ TEST_GEN_PROGS_s390x += rseq_test
TEST_GEN_PROGS_s390x += set_memory_region_test
TEST_GEN_PROGS_s390x += kvm_binary_stats_test
+TEST_GEN_PROGS_riscv += demand_paging_test
+TEST_GEN_PROGS_riscv += dirty_log_test
+TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
+TEST_GEN_PROGS_riscv += kvm_page_table_test
+TEST_GEN_PROGS_riscv += set_memory_region_test
+TEST_GEN_PROGS_riscv += kvm_binary_stats_test
+
TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
LIBKVM += $(LIBKVM_$(UNAME_M))
@@ -133,7 +149,7 @@ endif
CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
- -I$(<D) -Iinclude/$(UNAME_M) -I..
+ -I$(<D) -Iinclude/$(UNAME_M) -I.. $(EXTRA_CFLAGS)
no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
$(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie)
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index bf6a45b0b8dc..b08d30bf71c5 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -366,6 +366,7 @@ static struct kvm_vm *test_vm_create(void)
{
struct kvm_vm *vm;
unsigned int i;
+ int ret;
int nr_vcpus = test_args.nr_vcpus;
vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
@@ -382,7 +383,11 @@ static struct kvm_vm *test_vm_create(void)
ucall_init(vm, NULL);
test_init_timer_irq(vm);
- vgic_v3_setup(vm, nr_vcpus, GICD_BASE_GPA, GICR_BASE_GPA);
+ ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+ if (ret < 0) {
+ print_skip("Failed to create vgic-v3");
+ exit(KSFT_SKIP);
+ }
/* Make all the test's cmdline args visible to the guest */
sync_global_to_guest(vm, test_args);
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index cc898181faab..f769fc6cd927 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -1014,6 +1014,22 @@ static __u64 sve_rejects_set[] = {
KVM_REG_ARM64_SVE_VLS,
};
+static __u64 pauth_addr_regs[] = {
+ ARM64_SYS_REG(3, 0, 2, 1, 0), /* APIAKEYLO_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 1, 1), /* APIAKEYHI_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 1, 2), /* APIBKEYLO_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 1, 3), /* APIBKEYHI_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 2, 0), /* APDAKEYLO_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 2, 1), /* APDAKEYHI_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 2, 2), /* APDBKEYLO_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 2, 3) /* APDBKEYHI_EL1 */
+};
+
+static __u64 pauth_generic_regs[] = {
+ ARM64_SYS_REG(3, 0, 2, 3, 0), /* APGAKEYLO_EL1 */
+ ARM64_SYS_REG(3, 0, 2, 3, 1), /* APGAKEYHI_EL1 */
+};
+
#define BASE_SUBLIST \
{ "base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), }
#define VREGS_SUBLIST \
@@ -1025,6 +1041,21 @@ static __u64 sve_rejects_set[] = {
{ "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \
.regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \
.rejects_set = sve_rejects_set, .rejects_set_n = ARRAY_SIZE(sve_rejects_set), }
+#define PAUTH_SUBLIST \
+ { \
+ .name = "pauth_address", \
+ .capability = KVM_CAP_ARM_PTRAUTH_ADDRESS, \
+ .feature = KVM_ARM_VCPU_PTRAUTH_ADDRESS, \
+ .regs = pauth_addr_regs, \
+ .regs_n = ARRAY_SIZE(pauth_addr_regs), \
+ }, \
+ { \
+ .name = "pauth_generic", \
+ .capability = KVM_CAP_ARM_PTRAUTH_GENERIC, \
+ .feature = KVM_ARM_VCPU_PTRAUTH_GENERIC, \
+ .regs = pauth_generic_regs, \
+ .regs_n = ARRAY_SIZE(pauth_generic_regs), \
+ }
static struct vcpu_config vregs_config = {
.sublists = {
@@ -1056,11 +1087,30 @@ static struct vcpu_config sve_pmu_config = {
{0},
},
};
+static struct vcpu_config pauth_config = {
+ .sublists = {
+ BASE_SUBLIST,
+ VREGS_SUBLIST,
+ PAUTH_SUBLIST,
+ {0},
+ },
+};
+static struct vcpu_config pauth_pmu_config = {
+ .sublists = {
+ BASE_SUBLIST,
+ VREGS_SUBLIST,
+ PAUTH_SUBLIST,
+ PMU_SUBLIST,
+ {0},
+ },
+};
static struct vcpu_config *vcpu_configs[] = {
&vregs_config,
&vregs_pmu_config,
&sve_config,
&sve_pmu_config,
+ &pauth_config,
+ &pauth_pmu_config,
};
static int vcpu_configs_n = ARRAY_SIZE(vcpu_configs);
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
new file mode 100644
index 000000000000..7eca97799917
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
@@ -0,0 +1,857 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * vgic_irq.c - Test userspace injection of IRQs
+ *
+ * This test validates the injection of IRQs from userspace using various
+ * methods (e.g., KVM_IRQ_LINE) and modes (e.g., EOI). The guest "asks" the
+ * host to inject a specific intid via a GUEST_SYNC call, and then checks that
+ * it received it.
+ */
+
+#include <asm/kvm.h>
+#include <asm/kvm_para.h>
+#include <sys/eventfd.h>
+#include <linux/sizes.h>
+
+#include "processor.h"
+#include "test_util.h"
+#include "kvm_util.h"
+#include "gic.h"
+#include "gic_v3.h"
+#include "vgic.h"
+
+#define GICD_BASE_GPA 0x08000000ULL
+#define GICR_BASE_GPA 0x080A0000ULL
+#define VCPU_ID 0
+
+/*
+ * Stores the user specified args; it's passed to the guest and to every test
+ * function.
+ */
+struct test_args {
+ uint32_t nr_irqs; /* number of KVM supported IRQs. */
+ bool eoi_split; /* 1 is eoir+dir, 0 is eoir only */
+ bool level_sensitive; /* 1 is level, 0 is edge */
+ int kvm_max_routes; /* output of KVM_CAP_IRQ_ROUTING */
+ bool kvm_supports_irqfd; /* output of KVM_CAP_IRQFD */
+};
+
+/*
+ * KVM implements 32 priority levels:
+ * 0x00 (highest priority) - 0xF8 (lowest priority), in steps of 8
+ *
+ * Note that these macros will still be correct in the case that KVM implements
+ * more priority levels. Also note that 32 is the minimum for GICv3 and GICv2.
+ */
+#define KVM_NUM_PRIOS 32
+#define KVM_PRIO_SHIFT 3 /* steps of 8 = 1 << 3 */
+#define KVM_PRIO_STEPS (1 << KVM_PRIO_SHIFT) /* 8 */
+#define LOWEST_PRIO (KVM_NUM_PRIOS - 1)
+#define CPU_PRIO_MASK (LOWEST_PRIO << KVM_PRIO_SHIFT) /* 0xf8 */
+#define IRQ_DEFAULT_PRIO (LOWEST_PRIO - 1)
+#define IRQ_DEFAULT_PRIO_REG (IRQ_DEFAULT_PRIO << KVM_PRIO_SHIFT) /* 0xf0 */
+
+static void *dist = (void *)GICD_BASE_GPA;
+static void *redist = (void *)GICR_BASE_GPA;
+
+/*
+ * The kvm_inject_* utilities are used by the guest to ask the host to inject
+ * interrupts (e.g., using the KVM_IRQ_LINE ioctl).
+ */
+
+typedef enum {
+ KVM_INJECT_EDGE_IRQ_LINE = 1,
+ KVM_SET_IRQ_LINE,
+ KVM_SET_IRQ_LINE_HIGH,
+ KVM_SET_LEVEL_INFO_HIGH,
+ KVM_INJECT_IRQFD,
+ KVM_WRITE_ISPENDR,
+ KVM_WRITE_ISACTIVER,
+} kvm_inject_cmd;
+
+struct kvm_inject_args {
+ kvm_inject_cmd cmd;
+ uint32_t first_intid;
+ uint32_t num;
+ int level;
+ bool expect_failure;
+};
+
+/* Used on the guest side to perform the hypercall. */
+static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid,
+ uint32_t num, int level, bool expect_failure);
+
+/* Used on the host side to get the hypercall info. */
+static void kvm_inject_get_call(struct kvm_vm *vm, struct ucall *uc,
+ struct kvm_inject_args *args);
+
+#define _KVM_INJECT_MULTI(cmd, intid, num, expect_failure) \
+ kvm_inject_call(cmd, intid, num, -1 /* not used */, expect_failure)
+
+#define KVM_INJECT_MULTI(cmd, intid, num) \
+ _KVM_INJECT_MULTI(cmd, intid, num, false)
+
+#define _KVM_INJECT(cmd, intid, expect_failure) \
+ _KVM_INJECT_MULTI(cmd, intid, 1, expect_failure)
+
+#define KVM_INJECT(cmd, intid) \
+ _KVM_INJECT_MULTI(cmd, intid, 1, false)
+
+#define KVM_ACTIVATE(cmd, intid) \
+ kvm_inject_call(cmd, intid, 1, 1, false);
+
+struct kvm_inject_desc {
+ kvm_inject_cmd cmd;
+ /* can inject PPIs, PPIs, and/or SPIs. */
+ bool sgi, ppi, spi;
+};
+
+static struct kvm_inject_desc inject_edge_fns[] = {
+ /* sgi ppi spi */
+ { KVM_INJECT_EDGE_IRQ_LINE, false, false, true },
+ { KVM_INJECT_IRQFD, false, false, true },
+ { KVM_WRITE_ISPENDR, true, false, true },
+ { 0, },
+};
+
+static struct kvm_inject_desc inject_level_fns[] = {
+ /* sgi ppi spi */
+ { KVM_SET_IRQ_LINE_HIGH, false, true, true },
+ { KVM_SET_LEVEL_INFO_HIGH, false, true, true },
+ { KVM_INJECT_IRQFD, false, false, true },
+ { KVM_WRITE_ISPENDR, false, true, true },
+ { 0, },
+};
+
+static struct kvm_inject_desc set_active_fns[] = {
+ /* sgi ppi spi */
+ { KVM_WRITE_ISACTIVER, true, true, true },
+ { 0, },
+};
+
+#define for_each_inject_fn(t, f) \
+ for ((f) = (t); (f)->cmd; (f)++)
+
+#define for_each_supported_inject_fn(args, t, f) \
+ for_each_inject_fn(t, f) \
+ if ((args)->kvm_supports_irqfd || (f)->cmd != KVM_INJECT_IRQFD)
+
+#define for_each_supported_activate_fn(args, t, f) \
+ for_each_supported_inject_fn((args), (t), (f))
+
+/* Shared between the guest main thread and the IRQ handlers. */
+volatile uint64_t irq_handled;
+volatile uint32_t irqnr_received[MAX_SPI + 1];
+
+static void reset_stats(void)
+{
+ int i;
+
+ irq_handled = 0;
+ for (i = 0; i <= MAX_SPI; i++)
+ irqnr_received[i] = 0;
+}
+
+static uint64_t gic_read_ap1r0(void)
+{
+ uint64_t reg = read_sysreg_s(SYS_ICV_AP1R0_EL1);
+
+ dsb(sy);
+ return reg;
+}
+
+static void gic_write_ap1r0(uint64_t val)
+{
+ write_sysreg_s(val, SYS_ICV_AP1R0_EL1);
+ isb();
+}
+
+static void guest_set_irq_line(uint32_t intid, uint32_t level);
+
+static void guest_irq_generic_handler(bool eoi_split, bool level_sensitive)
+{
+ uint32_t intid = gic_get_and_ack_irq();
+
+ if (intid == IAR_SPURIOUS)
+ return;
+
+ GUEST_ASSERT(gic_irq_get_active(intid));
+
+ if (!level_sensitive)
+ GUEST_ASSERT(!gic_irq_get_pending(intid));
+
+ if (level_sensitive)
+ guest_set_irq_line(intid, 0);
+
+ GUEST_ASSERT(intid < MAX_SPI);
+ irqnr_received[intid] += 1;
+ irq_handled += 1;
+
+ gic_set_eoi(intid);
+ GUEST_ASSERT_EQ(gic_read_ap1r0(), 0);
+ if (eoi_split)
+ gic_set_dir(intid);
+
+ GUEST_ASSERT(!gic_irq_get_active(intid));
+ GUEST_ASSERT(!gic_irq_get_pending(intid));
+}
+
+static void kvm_inject_call(kvm_inject_cmd cmd, uint32_t first_intid,
+ uint32_t num, int level, bool expect_failure)
+{
+ struct kvm_inject_args args = {
+ .cmd = cmd,
+ .first_intid = first_intid,
+ .num = num,
+ .level = level,
+ .expect_failure = expect_failure,
+ };
+ GUEST_SYNC(&args);
+}
+
+#define GUEST_ASSERT_IAR_EMPTY() \
+do { \
+ uint32_t _intid; \
+ _intid = gic_get_and_ack_irq(); \
+ GUEST_ASSERT(_intid == 0 || _intid == IAR_SPURIOUS); \
+} while (0)
+
+#define CAT_HELPER(a, b) a ## b
+#define CAT(a, b) CAT_HELPER(a, b)
+#define PREFIX guest_irq_handler_
+#define GUEST_IRQ_HANDLER_NAME(split, lev) CAT(PREFIX, CAT(split, lev))
+#define GENERATE_GUEST_IRQ_HANDLER(split, lev) \
+static void CAT(PREFIX, CAT(split, lev))(struct ex_regs *regs) \
+{ \
+ guest_irq_generic_handler(split, lev); \
+}
+
+GENERATE_GUEST_IRQ_HANDLER(0, 0);
+GENERATE_GUEST_IRQ_HANDLER(0, 1);
+GENERATE_GUEST_IRQ_HANDLER(1, 0);
+GENERATE_GUEST_IRQ_HANDLER(1, 1);
+
+static void (*guest_irq_handlers[2][2])(struct ex_regs *) = {
+ {GUEST_IRQ_HANDLER_NAME(0, 0), GUEST_IRQ_HANDLER_NAME(0, 1),},
+ {GUEST_IRQ_HANDLER_NAME(1, 0), GUEST_IRQ_HANDLER_NAME(1, 1),},
+};
+
+static void reset_priorities(struct test_args *args)
+{
+ int i;
+
+ for (i = 0; i < args->nr_irqs; i++)
+ gic_set_priority(i, IRQ_DEFAULT_PRIO_REG);
+}
+
+static void guest_set_irq_line(uint32_t intid, uint32_t level)
+{
+ kvm_inject_call(KVM_SET_IRQ_LINE, intid, 1, level, false);
+}
+
+static void test_inject_fail(struct test_args *args,
+ uint32_t intid, kvm_inject_cmd cmd)
+{
+ reset_stats();
+
+ _KVM_INJECT(cmd, intid, true);
+ /* no IRQ to handle on entry */
+
+ GUEST_ASSERT_EQ(irq_handled, 0);
+ GUEST_ASSERT_IAR_EMPTY();
+}
+
+static void guest_inject(struct test_args *args,
+ uint32_t first_intid, uint32_t num,
+ kvm_inject_cmd cmd)
+{
+ uint32_t i;
+
+ reset_stats();
+
+ /* Cycle over all priorities to make things more interesting. */
+ for (i = first_intid; i < num + first_intid; i++)
+ gic_set_priority(i, (i % (KVM_NUM_PRIOS - 1)) << 3);
+
+ asm volatile("msr daifset, #2" : : : "memory");
+ KVM_INJECT_MULTI(cmd, first_intid, num);
+
+ while (irq_handled < num) {
+ asm volatile("wfi\n"
+ "msr daifclr, #2\n"
+ /* handle IRQ */
+ "msr daifset, #2\n"
+ : : : "memory");
+ }
+ asm volatile("msr daifclr, #2" : : : "memory");
+
+ GUEST_ASSERT_EQ(irq_handled, num);
+ for (i = first_intid; i < num + first_intid; i++)
+ GUEST_ASSERT_EQ(irqnr_received[i], 1);
+ GUEST_ASSERT_IAR_EMPTY();
+
+ reset_priorities(args);
+}
+
+/*
+ * Restore the active state of multiple concurrent IRQs (given by
+ * concurrent_irqs). This does what a live-migration would do on the
+ * destination side assuming there are some active IRQs that were not
+ * deactivated yet.
+ */
+static void guest_restore_active(struct test_args *args,
+ uint32_t first_intid, uint32_t num,
+ kvm_inject_cmd cmd)
+{
+ uint32_t prio, intid, ap1r;
+ int i;
+
+ /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs
+ * in descending order, so intid+1 can preempt intid.
+ */
+ for (i = 0, prio = (num - 1) * 8; i < num; i++, prio -= 8) {
+ GUEST_ASSERT(prio >= 0);
+ intid = i + first_intid;
+ gic_set_priority(intid, prio);
+ }
+
+ /* In a real migration, KVM would restore all GIC state before running
+ * guest code.
+ */
+ for (i = 0; i < num; i++) {
+ intid = i + first_intid;
+ KVM_ACTIVATE(cmd, intid);
+ ap1r = gic_read_ap1r0();
+ ap1r |= 1U << i;
+ gic_write_ap1r0(ap1r);
+ }
+
+ /* This is where the "migration" would occur. */
+
+ /* finish handling the IRQs starting with the highest priority one. */
+ for (i = 0; i < num; i++) {
+ intid = num - i - 1 + first_intid;
+ gic_set_eoi(intid);
+ if (args->eoi_split)
+ gic_set_dir(intid);
+ }
+
+ for (i = 0; i < num; i++)
+ GUEST_ASSERT(!gic_irq_get_active(i + first_intid));
+ GUEST_ASSERT_EQ(gic_read_ap1r0(), 0);
+ GUEST_ASSERT_IAR_EMPTY();
+}
+
+/*
+ * Polls the IAR until it's not a spurious interrupt.
+ *
+ * This function should only be used in test_inject_preemption (with IRQs
+ * masked).
+ */
+static uint32_t wait_for_and_activate_irq(void)
+{
+ uint32_t intid;
+
+ do {
+ asm volatile("wfi" : : : "memory");
+ intid = gic_get_and_ack_irq();
+ } while (intid == IAR_SPURIOUS);
+
+ return intid;
+}
+
+/*
+ * Inject multiple concurrent IRQs (num IRQs starting at first_intid) and
+ * handle them without handling the actual exceptions. This is done by masking
+ * interrupts for the whole test.
+ */
+static void test_inject_preemption(struct test_args *args,
+ uint32_t first_intid, int num,
+ kvm_inject_cmd cmd)
+{
+ uint32_t intid, prio, step = KVM_PRIO_STEPS;
+ int i;
+
+ /* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs
+ * in descending order, so intid+1 can preempt intid.
+ */
+ for (i = 0, prio = (num - 1) * step; i < num; i++, prio -= step) {
+ GUEST_ASSERT(prio >= 0);
+ intid = i + first_intid;
+ gic_set_priority(intid, prio);
+ }
+
+ local_irq_disable();
+
+ for (i = 0; i < num; i++) {
+ uint32_t tmp;
+ intid = i + first_intid;
+ KVM_INJECT(cmd, intid);
+ /* Each successive IRQ will preempt the previous one. */
+ tmp = wait_for_and_activate_irq();
+ GUEST_ASSERT_EQ(tmp, intid);
+ if (args->level_sensitive)
+ guest_set_irq_line(intid, 0);
+ }
+
+ /* finish handling the IRQs starting with the highest priority one. */
+ for (i = 0; i < num; i++) {
+ intid = num - i - 1 + first_intid;
+ gic_set_eoi(intid);
+ if (args->eoi_split)
+ gic_set_dir(intid);
+ }
+
+ local_irq_enable();
+
+ for (i = 0; i < num; i++)
+ GUEST_ASSERT(!gic_irq_get_active(i + first_intid));
+ GUEST_ASSERT_EQ(gic_read_ap1r0(), 0);
+ GUEST_ASSERT_IAR_EMPTY();
+
+ reset_priorities(args);
+}
+
+static void test_injection(struct test_args *args, struct kvm_inject_desc *f)
+{
+ uint32_t nr_irqs = args->nr_irqs;
+
+ if (f->sgi) {
+ guest_inject(args, MIN_SGI, 1, f->cmd);
+ guest_inject(args, 0, 16, f->cmd);
+ }
+
+ if (f->ppi)
+ guest_inject(args, MIN_PPI, 1, f->cmd);
+
+ if (f->spi) {
+ guest_inject(args, MIN_SPI, 1, f->cmd);
+ guest_inject(args, nr_irqs - 1, 1, f->cmd);
+ guest_inject(args, MIN_SPI, nr_irqs - MIN_SPI, f->cmd);
+ }
+}
+
+static void test_injection_failure(struct test_args *args,
+ struct kvm_inject_desc *f)
+{
+ uint32_t bad_intid[] = { args->nr_irqs, 1020, 1024, 1120, 5120, ~0U, };
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(bad_intid); i++)
+ test_inject_fail(args, bad_intid[i], f->cmd);
+}
+
+static void test_preemption(struct test_args *args, struct kvm_inject_desc *f)
+{
+ /*
+ * Test up to 4 levels of preemption. The reason is that KVM doesn't
+ * currently implement the ability to have more than the number-of-LRs
+ * number of concurrently active IRQs. The number of LRs implemented is
+ * IMPLEMENTATION DEFINED, however, it seems that most implement 4.
+ */
+ if (f->sgi)
+ test_inject_preemption(args, MIN_SGI, 4, f->cmd);
+
+ if (f->ppi)
+ test_inject_preemption(args, MIN_PPI, 4, f->cmd);
+
+ if (f->spi)
+ test_inject_preemption(args, MIN_SPI, 4, f->cmd);
+}
+
+static void test_restore_active(struct test_args *args, struct kvm_inject_desc *f)
+{
+ /* Test up to 4 active IRQs. Same reason as in test_preemption. */
+ if (f->sgi)
+ guest_restore_active(args, MIN_SGI, 4, f->cmd);
+
+ if (f->ppi)
+ guest_restore_active(args, MIN_PPI, 4, f->cmd);
+
+ if (f->spi)
+ guest_restore_active(args, MIN_SPI, 4, f->cmd);
+}
+
+static void guest_code(struct test_args args)
+{
+ uint32_t i, nr_irqs = args.nr_irqs;
+ bool level_sensitive = args.level_sensitive;
+ struct kvm_inject_desc *f, *inject_fns;
+
+ gic_init(GIC_V3, 1, dist, redist);
+
+ for (i = 0; i < nr_irqs; i++)
+ gic_irq_enable(i);
+
+ for (i = MIN_SPI; i < nr_irqs; i++)
+ gic_irq_set_config(i, !args.level_sensitive);
+
+ gic_set_eoi_split(args.eoi_split);
+
+ reset_priorities(&args);
+ gic_set_priority_mask(CPU_PRIO_MASK);
+
+ inject_fns = level_sensitive ? inject_level_fns
+ : inject_edge_fns;
+
+ local_irq_enable();
+
+ /* Start the tests. */
+ for_each_supported_inject_fn(&args, inject_fns, f) {
+ test_injection(&args, f);
+ test_preemption(&args, f);
+ test_injection_failure(&args, f);
+ }
+
+ /* Restore the active state of IRQs. This would happen when live
+ * migrating IRQs in the middle of being handled.
+ */
+ for_each_supported_activate_fn(&args, set_active_fns, f)
+ test_restore_active(&args, f);
+
+ GUEST_DONE();
+}
+
+static void kvm_irq_line_check(struct kvm_vm *vm, uint32_t intid, int level,
+ struct test_args *test_args, bool expect_failure)
+{
+ int ret;
+
+ if (!expect_failure) {
+ kvm_arm_irq_line(vm, intid, level);
+ } else {
+ /* The interface doesn't allow larger intid's. */
+ if (intid > KVM_ARM_IRQ_NUM_MASK)
+ return;
+
+ ret = _kvm_arm_irq_line(vm, intid, level);
+ TEST_ASSERT(ret != 0 && errno == EINVAL,
+ "Bad intid %i did not cause KVM_IRQ_LINE "
+ "error: rc: %i errno: %i", intid, ret, errno);
+ }
+}
+
+void kvm_irq_set_level_info_check(int gic_fd, uint32_t intid, int level,
+ bool expect_failure)
+{
+ if (!expect_failure) {
+ kvm_irq_set_level_info(gic_fd, intid, level);
+ } else {
+ int ret = _kvm_irq_set_level_info(gic_fd, intid, level);
+ /*
+ * The kernel silently fails for invalid SPIs and SGIs (which
+ * are not level-sensitive). It only checks for intid to not
+ * spill over 1U << 10 (the max reserved SPI). Also, callers
+ * are supposed to mask the intid with 0x3ff (1023).
+ */
+ if (intid > VGIC_MAX_RESERVED)
+ TEST_ASSERT(ret != 0 && errno == EINVAL,
+ "Bad intid %i did not cause VGIC_GRP_LEVEL_INFO "
+ "error: rc: %i errno: %i", intid, ret, errno);
+ else
+ TEST_ASSERT(!ret, "KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO "
+ "for intid %i failed, rc: %i errno: %i",
+ intid, ret, errno);
+ }
+}
+
+static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm,
+ uint32_t intid, uint32_t num, uint32_t kvm_max_routes,
+ bool expect_failure)
+{
+ struct kvm_irq_routing *routing;
+ int ret;
+ uint64_t i;
+
+ assert(num <= kvm_max_routes && kvm_max_routes <= KVM_MAX_IRQ_ROUTES);
+
+ routing = kvm_gsi_routing_create();
+ for (i = intid; i < (uint64_t)intid + num; i++)
+ kvm_gsi_routing_irqchip_add(routing, i - MIN_SPI, i - MIN_SPI);
+
+ if (!expect_failure) {
+ kvm_gsi_routing_write(vm, routing);
+ } else {
+ ret = _kvm_gsi_routing_write(vm, routing);
+ /* The kernel only checks for KVM_IRQCHIP_NUM_PINS. */
+ if (intid >= KVM_IRQCHIP_NUM_PINS)
+ TEST_ASSERT(ret != 0 && errno == EINVAL,
+ "Bad intid %u did not cause KVM_SET_GSI_ROUTING "
+ "error: rc: %i errno: %i", intid, ret, errno);
+ else
+ TEST_ASSERT(ret == 0, "KVM_SET_GSI_ROUTING "
+ "for intid %i failed, rc: %i errno: %i",
+ intid, ret, errno);
+ }
+}
+
+static void kvm_irq_write_ispendr_check(int gic_fd, uint32_t intid,
+ uint32_t vcpu, bool expect_failure)
+{
+ /*
+ * Ignore this when expecting failure as invalid intids will lead to
+ * either trying to inject SGIs when we configured the test to be
+ * level_sensitive (or the reverse), or inject large intids which
+ * will lead to writing above the ISPENDR register space (and we
+ * don't want to do that either).
+ */
+ if (!expect_failure)
+ kvm_irq_write_ispendr(gic_fd, intid, vcpu);
+}
+
+static void kvm_routing_and_irqfd_check(struct kvm_vm *vm,
+ uint32_t intid, uint32_t num, uint32_t kvm_max_routes,
+ bool expect_failure)
+{
+ int fd[MAX_SPI];
+ uint64_t val;
+ int ret, f;
+ uint64_t i;
+
+ /*
+ * There is no way to try injecting an SGI or PPI as the interface
+ * starts counting from the first SPI (above the private ones), so just
+ * exit.
+ */
+ if (INTID_IS_SGI(intid) || INTID_IS_PPI(intid))
+ return;
+
+ kvm_set_gsi_routing_irqchip_check(vm, intid, num,
+ kvm_max_routes, expect_failure);
+
+ /*
+ * If expect_failure, then just to inject anyway. These
+ * will silently fail. And in any case, the guest will check
+ * that no actual interrupt was injected for those cases.
+ */
+
+ for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) {
+ fd[f] = eventfd(0, 0);
+ TEST_ASSERT(fd[f] != -1,
+ "eventfd failed, errno: %i\n", errno);
+ }
+
+ for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) {
+ struct kvm_irqfd irqfd = {
+ .fd = fd[f],
+ .gsi = i - MIN_SPI,
+ };
+ assert(i <= (uint64_t)UINT_MAX);
+ vm_ioctl(vm, KVM_IRQFD, &irqfd);
+ }
+
+ for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++) {
+ val = 1;
+ ret = write(fd[f], &val, sizeof(uint64_t));
+ TEST_ASSERT(ret == sizeof(uint64_t),
+ "Write to KVM_IRQFD failed with ret: %d\n", ret);
+ }
+
+ for (f = 0, i = intid; i < (uint64_t)intid + num; i++, f++)
+ close(fd[f]);
+}
+
+/* handles the valid case: intid=0xffffffff num=1 */
+#define for_each_intid(first, num, tmp, i) \
+ for ((tmp) = (i) = (first); \
+ (tmp) < (uint64_t)(first) + (uint64_t)(num); \
+ (tmp)++, (i)++)
+
+static void run_guest_cmd(struct kvm_vm *vm, int gic_fd,
+ struct kvm_inject_args *inject_args,
+ struct test_args *test_args)
+{
+ kvm_inject_cmd cmd = inject_args->cmd;
+ uint32_t intid = inject_args->first_intid;
+ uint32_t num = inject_args->num;
+ int level = inject_args->level;
+ bool expect_failure = inject_args->expect_failure;
+ uint64_t tmp;
+ uint32_t i;
+
+ /* handles the valid case: intid=0xffffffff num=1 */
+ assert(intid < UINT_MAX - num || num == 1);
+
+ switch (cmd) {
+ case KVM_INJECT_EDGE_IRQ_LINE:
+ for_each_intid(intid, num, tmp, i)
+ kvm_irq_line_check(vm, i, 1, test_args,
+ expect_failure);
+ for_each_intid(intid, num, tmp, i)
+ kvm_irq_line_check(vm, i, 0, test_args,
+ expect_failure);
+ break;
+ case KVM_SET_IRQ_LINE:
+ for_each_intid(intid, num, tmp, i)
+ kvm_irq_line_check(vm, i, level, test_args,
+ expect_failure);
+ break;
+ case KVM_SET_IRQ_LINE_HIGH:
+ for_each_intid(intid, num, tmp, i)
+ kvm_irq_line_check(vm, i, 1, test_args,
+ expect_failure);
+ break;
+ case KVM_SET_LEVEL_INFO_HIGH:
+ for_each_intid(intid, num, tmp, i)
+ kvm_irq_set_level_info_check(gic_fd, i, 1,
+ expect_failure);
+ break;
+ case KVM_INJECT_IRQFD:
+ kvm_routing_and_irqfd_check(vm, intid, num,
+ test_args->kvm_max_routes,
+ expect_failure);
+ break;
+ case KVM_WRITE_ISPENDR:
+ for (i = intid; i < intid + num; i++)
+ kvm_irq_write_ispendr_check(gic_fd, i,
+ VCPU_ID, expect_failure);
+ break;
+ case KVM_WRITE_ISACTIVER:
+ for (i = intid; i < intid + num; i++)
+ kvm_irq_write_isactiver(gic_fd, i, VCPU_ID);
+ break;
+ default:
+ break;
+ }
+}
+
+static void kvm_inject_get_call(struct kvm_vm *vm, struct ucall *uc,
+ struct kvm_inject_args *args)
+{
+ struct kvm_inject_args *kvm_args_hva;
+ vm_vaddr_t kvm_args_gva;
+
+ kvm_args_gva = uc->args[1];
+ kvm_args_hva = (struct kvm_inject_args *)addr_gva2hva(vm, kvm_args_gva);
+ memcpy(args, kvm_args_hva, sizeof(struct kvm_inject_args));
+}
+
+static void print_args(struct test_args *args)
+{
+ printf("nr-irqs=%d level-sensitive=%d eoi-split=%d\n",
+ args->nr_irqs, args->level_sensitive,
+ args->eoi_split);
+}
+
+static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
+{
+ struct ucall uc;
+ int gic_fd;
+ struct kvm_vm *vm;
+ struct kvm_inject_args inject_args;
+
+ struct test_args args = {
+ .nr_irqs = nr_irqs,
+ .level_sensitive = level_sensitive,
+ .eoi_split = eoi_split,
+ .kvm_max_routes = kvm_check_cap(KVM_CAP_IRQ_ROUTING),
+ .kvm_supports_irqfd = kvm_check_cap(KVM_CAP_IRQFD),
+ };
+
+ print_args(&args);
+
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+ ucall_init(vm, NULL);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+ /* Setup the guest args page (so it gets the args). */
+ vcpu_args_set(vm, 0, 1, args);
+
+ gic_fd = vgic_v3_setup(vm, 1, nr_irqs,
+ GICD_BASE_GPA, GICR_BASE_GPA);
+ if (gic_fd < 0) {
+ print_skip("Failed to create vgic-v3, skipping");
+ exit(KSFT_SKIP);
+ }
+
+ vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT,
+ guest_irq_handlers[args.eoi_split][args.level_sensitive]);
+
+ while (1) {
+ vcpu_run(vm, VCPU_ID);
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_SYNC:
+ kvm_inject_get_call(vm, &uc, &inject_args);
+ run_guest_cmd(vm, gic_fd, &inject_args, &args);
+ break;
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld\n\tvalues: %#lx, %#lx",
+ (const char *)uc.args[0],
+ __FILE__, uc.args[1], uc.args[2], uc.args[3]);
+ break;
+ case UCALL_DONE:
+ goto done;
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ }
+ }
+
+done:
+ close(gic_fd);
+ kvm_vm_free(vm);
+}
+
+static void help(const char *name)
+{
+ printf(
+ "\n"
+ "usage: %s [-n num_irqs] [-e eoi_split] [-l level_sensitive]\n", name);
+ printf(" -n: specify number of IRQs to setup the vgic with. "
+ "It has to be a multiple of 32 and between 64 and 1024.\n");
+ printf(" -e: if 1 then EOI is split into a write to DIR on top "
+ "of writing EOI.\n");
+ printf(" -l: specify whether the IRQs are level-sensitive (1) or not (0).");
+ puts("");
+ exit(1);
+}
+
+int main(int argc, char **argv)
+{
+ uint32_t nr_irqs = 64;
+ bool default_args = true;
+ bool level_sensitive = false;
+ int opt;
+ bool eoi_split = false;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ while ((opt = getopt(argc, argv, "hn:e:l:")) != -1) {
+ switch (opt) {
+ case 'n':
+ nr_irqs = atoi(optarg);
+ if (nr_irqs > 1024 || nr_irqs % 32)
+ help(argv[0]);
+ break;
+ case 'e':
+ eoi_split = (bool)atoi(optarg);
+ default_args = false;
+ break;
+ case 'l':
+ level_sensitive = (bool)atoi(optarg);
+ default_args = false;
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
+
+ /* If the user just specified nr_irqs and/or gic_version, then run all
+ * combinations.
+ */
+ if (default_args) {
+ test_vgic(nr_irqs, false /* level */, false /* eoi_split */);
+ test_vgic(nr_irqs, false /* level */, true /* eoi_split */);
+ test_vgic(nr_irqs, true /* level */, false /* eoi_split */);
+ test_vgic(nr_irqs, true /* level */, true /* eoi_split */);
+ } else {
+ test_vgic(nr_irqs, level_sensitive, eoi_split);
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic.h b/tools/testing/selftests/kvm/include/aarch64/gic.h
index 85dd1e53048e..b217ea17cac5 100644
--- a/tools/testing/selftests/kvm/include/aarch64/gic.h
+++ b/tools/testing/selftests/kvm/include/aarch64/gic.h
@@ -11,11 +11,37 @@ enum gic_type {
GIC_TYPE_MAX,
};
+#define MIN_SGI 0
+#define MIN_PPI 16
+#define MIN_SPI 32
+#define MAX_SPI 1019
+#define IAR_SPURIOUS 1023
+
+#define INTID_IS_SGI(intid) (0 <= (intid) && (intid) < MIN_PPI)
+#define INTID_IS_PPI(intid) (MIN_PPI <= (intid) && (intid) < MIN_SPI)
+#define INTID_IS_SPI(intid) (MIN_SPI <= (intid) && (intid) <= MAX_SPI)
+
void gic_init(enum gic_type type, unsigned int nr_cpus,
void *dist_base, void *redist_base);
void gic_irq_enable(unsigned int intid);
void gic_irq_disable(unsigned int intid);
unsigned int gic_get_and_ack_irq(void);
void gic_set_eoi(unsigned int intid);
+void gic_set_dir(unsigned int intid);
+
+/*
+ * Sets the EOI mode. When split is false, EOI just drops the priority. When
+ * split is true, EOI drops the priority and deactivates the interrupt.
+ */
+void gic_set_eoi_split(bool split);
+void gic_set_priority_mask(uint64_t mask);
+void gic_set_priority(uint32_t intid, uint32_t prio);
+void gic_irq_set_active(unsigned int intid);
+void gic_irq_clear_active(unsigned int intid);
+bool gic_irq_get_active(unsigned int intid);
+void gic_irq_set_pending(unsigned int intid);
+void gic_irq_clear_pending(unsigned int intid);
+bool gic_irq_get_pending(unsigned int intid);
+void gic_irq_set_config(unsigned int intid, bool is_edge);
#endif /* SELFTEST_KVM_GIC_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h
index b51536d469a6..ba0886e8a2bb 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h
+++ b/tools/testing/selftests/kvm/include/aarch64/gic_v3.h
@@ -16,8 +16,12 @@
#define GICD_IGROUPR 0x0080
#define GICD_ISENABLER 0x0100
#define GICD_ICENABLER 0x0180
+#define GICD_ISPENDR 0x0200
+#define GICD_ICPENDR 0x0280
#define GICD_ICACTIVER 0x0380
+#define GICD_ISACTIVER 0x0300
#define GICD_IPRIORITYR 0x0400
+#define GICD_ICFGR 0x0C00
/*
* The assumption is that the guest runs in a non-secure mode.
@@ -49,16 +53,24 @@
#define GICR_IGROUPR0 GICD_IGROUPR
#define GICR_ISENABLER0 GICD_ISENABLER
#define GICR_ICENABLER0 GICD_ICENABLER
+#define GICR_ISPENDR0 GICD_ISPENDR
+#define GICR_ISACTIVER0 GICD_ISACTIVER
#define GICR_ICACTIVER0 GICD_ICACTIVER
+#define GICR_ICENABLER GICD_ICENABLER
+#define GICR_ICACTIVER GICD_ICACTIVER
#define GICR_IPRIORITYR0 GICD_IPRIORITYR
/* CPU interface registers */
#define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0)
#define SYS_ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0)
#define SYS_ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1)
+#define SYS_ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1)
+#define SYS_ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4)
#define SYS_ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
#define SYS_ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
+#define SYS_ICV_AP1R0_EL1 sys_reg(3, 0, 12, 9, 0)
+
#define ICC_PMR_DEF_PRIO 0xf0
#define ICC_SRE_EL1_SRE (1U << 0)
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index 27d8e1bb5b36..8f9f46979a00 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -113,6 +113,9 @@ enum {
#define ESR_EC_WP_CURRENT 0x35
#define ESR_EC_BRK_INS 0x3c
+void aarch64_get_supported_page_sizes(uint32_t ipa,
+ bool *ps4k, bool *ps16k, bool *ps64k);
+
void vm_init_descriptor_tables(struct kvm_vm *vm);
void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/aarch64/vgic.h
index 0ecfb253893c..4442081221a0 100644
--- a/tools/testing/selftests/kvm/include/aarch64/vgic.h
+++ b/tools/testing/selftests/kvm/include/aarch64/vgic.h
@@ -14,7 +14,21 @@
((uint64_t)(flags) << 12) | \
index)
-int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus,
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
uint64_t gicd_base_gpa, uint64_t gicr_base_gpa);
-#endif /* SELFTEST_KVM_VGIC_H */
+#define VGIC_MAX_RESERVED 1023
+
+void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level);
+int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level);
+
+void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level);
+int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level);
+
+/* The vcpu arg only applies to private interrupts. */
+void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, uint32_t vcpu);
+void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, uint32_t vcpu);
+
+#define KVM_IRQCHIP_NUM_PINS (1020 - 32)
+
+#endif // SELFTEST_KVM_VGIC_H
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 2d62edc49d67..c9286811a4cb 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -7,412 +7,7 @@
#ifndef SELFTEST_KVM_UTIL_H
#define SELFTEST_KVM_UTIL_H
-#include "test_util.h"
-
-#include "asm/kvm.h"
-#include "linux/list.h"
-#include "linux/kvm.h"
-#include <sys/ioctl.h>
-
-#include "sparsebit.h"
-
-#define KVM_DEV_PATH "/dev/kvm"
-#define KVM_MAX_VCPUS 512
-
-#define NSEC_PER_SEC 1000000000L
-
-/*
- * Callers of kvm_util only have an incomplete/opaque description of the
- * structure kvm_util is using to maintain the state of a VM.
- */
-struct kvm_vm;
-
-typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
-typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
-
-/* Minimum allocated guest virtual and physical addresses */
-#define KVM_UTIL_MIN_VADDR 0x2000
-#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
-
-#define DEFAULT_GUEST_PHY_PAGES 512
-#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000
-#define DEFAULT_STACK_PGS 5
-
-enum vm_guest_mode {
- VM_MODE_P52V48_4K,
- VM_MODE_P52V48_64K,
- VM_MODE_P48V48_4K,
- VM_MODE_P48V48_64K,
- VM_MODE_P40V48_4K,
- VM_MODE_P40V48_64K,
- VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
- VM_MODE_P47V64_4K,
- VM_MODE_P44V64_4K,
- NUM_VM_MODES,
-};
-
-#if defined(__aarch64__)
-
-#define VM_MODE_DEFAULT VM_MODE_P40V48_4K
-#define MIN_PAGE_SHIFT 12U
-#define ptes_per_page(page_size) ((page_size) / 8)
-
-#elif defined(__x86_64__)
-
-#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K
-#define MIN_PAGE_SHIFT 12U
-#define ptes_per_page(page_size) ((page_size) / 8)
-
-#elif defined(__s390x__)
-
-#define VM_MODE_DEFAULT VM_MODE_P44V64_4K
-#define MIN_PAGE_SHIFT 12U
-#define ptes_per_page(page_size) ((page_size) / 16)
-
-#endif
-
-#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT)
-#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE)
-
-struct vm_guest_mode_params {
- unsigned int pa_bits;
- unsigned int va_bits;
- unsigned int page_size;
- unsigned int page_shift;
-};
-extern const struct vm_guest_mode_params vm_guest_mode_params[];
-
-int open_path_or_exit(const char *path, int flags);
-int open_kvm_dev_path_or_exit(void);
-int kvm_check_cap(long cap);
-int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
-int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
- struct kvm_enable_cap *cap);
-void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
-const char *vm_guest_mode_string(uint32_t i);
-
-struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
-void kvm_vm_free(struct kvm_vm *vmp);
-void kvm_vm_restart(struct kvm_vm *vmp, int perm);
-void kvm_vm_release(struct kvm_vm *vmp);
-void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
-void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
- uint64_t first_page, uint32_t num_pages);
-uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm);
-
-int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
- size_t len);
-
-void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename);
-
-void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
-
-/*
- * VM VCPU Dump
- *
- * Input Args:
- * stream - Output FILE stream
- * vm - Virtual Machine
- * vcpuid - VCPU ID
- * indent - Left margin indent amount
- *
- * Output Args: None
- *
- * Return: None
- *
- * Dumps the current state of the VCPU specified by @vcpuid, within the VM
- * given by @vm, to the FILE stream given by @stream.
- */
-void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid,
- uint8_t indent);
-
-void vm_create_irqchip(struct kvm_vm *vm);
-
-void vm_userspace_mem_region_add(struct kvm_vm *vm,
- enum vm_mem_backing_src_type src_type,
- uint64_t guest_paddr, uint32_t slot, uint64_t npages,
- uint32_t flags);
-
-void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
- void *arg);
-int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
- void *arg);
-void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
-int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg);
-void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
-int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
-void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
-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);
-void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid);
-vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
-vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages);
-vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm);
-
-void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
- unsigned int npages);
-void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
-void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
-vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
-void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa);
-
-/*
- * Address Guest Virtual to Guest Physical
- *
- * Input Args:
- * vm - Virtual Machine
- * gva - VM virtual address
- *
- * Output Args: None
- *
- * Return:
- * Equivalent VM physical address
- *
- * Returns the VM physical address of the translated VM virtual
- * address given by @gva.
- */
-vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
-
-struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
-int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
-int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_guest_debug *debug);
-void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_mp_state *mp_state);
-struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid);
-void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
-void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
-
-/*
- * VM VCPU Args Set
- *
- * Input Args:
- * vm - Virtual Machine
- * vcpuid - VCPU ID
- * num - number of arguments
- * ... - arguments, each of type uint64_t
- *
- * Output Args: None
- *
- * Return: None
- *
- * Sets the first @num function input registers of the VCPU with @vcpuid,
- * per the C calling convention of the architecture, to the values given
- * as variable args. Each of the variable args is expected to be of type
- * uint64_t. The maximum @num can be is specific to the architecture.
- */
-void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...);
-
-void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_sregs *sregs);
-void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_sregs *sregs);
-int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_sregs *sregs);
-void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_fpu *fpu);
-void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_fpu *fpu);
-void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg);
-void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg);
-#ifdef __KVM_HAVE_VCPU_EVENTS
-void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_vcpu_events *events);
-void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_vcpu_events *events);
-#endif
-#ifdef __x86_64__
-void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_nested_state *state);
-int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
- struct kvm_nested_state *state, bool ignore_error);
-#endif
-void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid);
-
-int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr);
-int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr);
-int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd);
-int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test);
-int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
- void *val, bool write);
-int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
- void *val, bool write);
-
-int _vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
- uint64_t attr);
-int vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
- uint64_t attr);
-int _vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
- uint64_t attr, void *val, bool write);
-int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
- uint64_t attr, void *val, bool write);
-
-const char *exit_reason_str(unsigned int exit_reason);
-
-void virt_pgd_alloc(struct kvm_vm *vm);
-
-/*
- * VM Virtual Page Map
- *
- * Input Args:
- * vm - Virtual Machine
- * vaddr - VM Virtual Address
- * paddr - VM Physical Address
- * memslot - Memory region slot for new virtual translation tables
- *
- * Output Args: None
- *
- * Return: None
- *
- * Within @vm, creates a virtual translation for the page starting
- * at @vaddr to the page starting at @paddr.
- */
-void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr);
-
-vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
- uint32_t memslot);
-vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
- vm_paddr_t paddr_min, uint32_t memslot);
-vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
-
-/*
- * Create a VM with reasonable defaults
- *
- * Input Args:
- * vcpuid - The id of the single VCPU to add to the VM.
- * extra_mem_pages - The number of extra pages to add (this will
- * decide how much extra space we will need to
- * setup the page tables using memslot 0)
- * guest_code - The vCPU's entry point
- *
- * Output Args: None
- *
- * Return:
- * Pointer to opaque structure that describes the created VM.
- */
-struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
- void *guest_code);
-
-/* Same as vm_create_default, but can be used for more than one vcpu */
-struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages,
- uint32_t num_percpu_pages, void *guest_code,
- uint32_t vcpuids[]);
-
-/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */
-struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
- uint64_t slot0_mem_pages, uint64_t extra_mem_pages,
- uint32_t num_percpu_pages, void *guest_code,
- uint32_t vcpuids[]);
-
-/*
- * Adds a vCPU with reasonable defaults (e.g. a stack)
- *
- * Input Args:
- * vm - Virtual Machine
- * vcpuid - The id of the VCPU to add to the VM.
- * guest_code - The vCPU's entry point
- */
-void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
-
-bool vm_is_unrestricted_guest(struct kvm_vm *vm);
-
-unsigned int vm_get_page_size(struct kvm_vm *vm);
-unsigned int vm_get_page_shift(struct kvm_vm *vm);
-unsigned long vm_compute_max_gfn(struct kvm_vm *vm);
-uint64_t vm_get_max_gfn(struct kvm_vm *vm);
-int vm_get_fd(struct kvm_vm *vm);
-
-unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size);
-unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages);
-unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages);
-static inline unsigned int
-vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
-{
- unsigned int n;
- n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages));
-#ifdef __s390x__
- /* s390 requires 1M aligned guest sizes */
- n = (n + 255) & ~255;
-#endif
- return n;
-}
-
-struct kvm_userspace_memory_region *
-kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
- uint64_t end);
-
-struct kvm_dirty_log *
-allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region);
-
-int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
-
-#define sync_global_to_guest(vm, g) ({ \
- typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
- memcpy(_p, &(g), sizeof(g)); \
-})
-
-#define sync_global_from_guest(vm, g) ({ \
- typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
- memcpy(&(g), _p, sizeof(g)); \
-})
-
-void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid);
-
-/* Common ucalls */
-enum {
- UCALL_NONE,
- UCALL_SYNC,
- UCALL_ABORT,
- UCALL_DONE,
- UCALL_UNHANDLED,
-};
-
-#define UCALL_MAX_ARGS 6
-
-struct ucall {
- uint64_t cmd;
- uint64_t args[UCALL_MAX_ARGS];
-};
-
-void ucall_init(struct kvm_vm *vm, void *arg);
-void ucall_uninit(struct kvm_vm *vm);
-void ucall(uint64_t cmd, int nargs, ...);
-uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc);
-
-#define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \
- ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
-#define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage)
-#define GUEST_DONE() ucall(UCALL_DONE, 0)
-#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) do { \
- if (!(_condition)) \
- ucall(UCALL_ABORT, 2 + _nargs, \
- "Failed guest assert: " \
- _condstr, __LINE__, _args); \
-} while (0)
-
-#define GUEST_ASSERT(_condition) \
- __GUEST_ASSERT(_condition, #_condition, 0, 0)
-
-#define GUEST_ASSERT_1(_condition, arg1) \
- __GUEST_ASSERT(_condition, #_condition, 1, (arg1))
-
-#define GUEST_ASSERT_2(_condition, arg1, arg2) \
- __GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2))
-
-#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \
- __GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3))
-
-#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \
- __GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4))
-
-#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b)
-
-int vm_get_stats_fd(struct kvm_vm *vm);
-int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid);
-
-uint32_t guest_get_vcpuid(void);
+#include "kvm_util_base.h"
+#include "ucall_common.h"
#endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
new file mode 100644
index 000000000000..4ed6aa049a91
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -0,0 +1,398 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/kvm_util_base.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+#ifndef SELFTEST_KVM_UTIL_BASE_H
+#define SELFTEST_KVM_UTIL_BASE_H
+
+#include "test_util.h"
+
+#include "asm/kvm.h"
+#include "linux/list.h"
+#include "linux/kvm.h"
+#include <sys/ioctl.h>
+
+#include "sparsebit.h"
+
+#define KVM_DEV_PATH "/dev/kvm"
+#define KVM_MAX_VCPUS 512
+
+#define NSEC_PER_SEC 1000000000L
+
+/*
+ * Callers of kvm_util only have an incomplete/opaque description of the
+ * structure kvm_util is using to maintain the state of a VM.
+ */
+struct kvm_vm;
+
+typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
+typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
+
+/* Minimum allocated guest virtual and physical addresses */
+#define KVM_UTIL_MIN_VADDR 0x2000
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+
+#define DEFAULT_GUEST_PHY_PAGES 512
+#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000
+#define DEFAULT_STACK_PGS 5
+
+enum vm_guest_mode {
+ VM_MODE_P52V48_4K,
+ VM_MODE_P52V48_64K,
+ VM_MODE_P48V48_4K,
+ VM_MODE_P48V48_16K,
+ VM_MODE_P48V48_64K,
+ VM_MODE_P40V48_4K,
+ VM_MODE_P40V48_16K,
+ VM_MODE_P40V48_64K,
+ VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
+ VM_MODE_P47V64_4K,
+ VM_MODE_P44V64_4K,
+ VM_MODE_P36V48_4K,
+ VM_MODE_P36V48_16K,
+ VM_MODE_P36V48_64K,
+ VM_MODE_P36V47_16K,
+ NUM_VM_MODES,
+};
+
+#if defined(__aarch64__)
+
+extern enum vm_guest_mode vm_mode_default;
+
+#define VM_MODE_DEFAULT vm_mode_default
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 8)
+
+#elif defined(__x86_64__)
+
+#define VM_MODE_DEFAULT VM_MODE_PXXV48_4K
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 8)
+
+#elif defined(__s390x__)
+
+#define VM_MODE_DEFAULT VM_MODE_P44V64_4K
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 16)
+
+#elif defined(__riscv)
+
+#if __riscv_xlen == 32
+#error "RISC-V 32-bit kvm selftests not supported"
+#endif
+
+#define VM_MODE_DEFAULT VM_MODE_P40V48_4K
+#define MIN_PAGE_SHIFT 12U
+#define ptes_per_page(page_size) ((page_size) / 8)
+
+#endif
+
+#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT)
+#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE)
+
+struct vm_guest_mode_params {
+ unsigned int pa_bits;
+ unsigned int va_bits;
+ unsigned int page_size;
+ unsigned int page_shift;
+};
+extern const struct vm_guest_mode_params vm_guest_mode_params[];
+
+int open_path_or_exit(const char *path, int flags);
+int open_kvm_dev_path_or_exit(void);
+int kvm_check_cap(long cap);
+int vm_check_cap(struct kvm_vm *vm, long cap);
+int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+ struct kvm_enable_cap *cap);
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
+const char *vm_guest_mode_string(uint32_t i);
+
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
+void kvm_vm_free(struct kvm_vm *vmp);
+void kvm_vm_restart(struct kvm_vm *vmp, int perm);
+void kvm_vm_release(struct kvm_vm *vmp);
+void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
+void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
+ uint64_t first_page, uint32_t num_pages);
+uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm);
+
+int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
+ size_t len);
+
+void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename);
+
+void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
+
+/*
+ * VM VCPU Dump
+ *
+ * Input Args:
+ * stream - Output FILE stream
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * indent - Left margin indent amount
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Dumps the current state of the VCPU specified by @vcpuid, within the VM
+ * given by @vm, to the FILE stream given by @stream.
+ */
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid,
+ uint8_t indent);
+
+void vm_create_irqchip(struct kvm_vm *vm);
+
+void vm_userspace_mem_region_add(struct kvm_vm *vm,
+ enum vm_mem_backing_src_type src_type,
+ uint64_t guest_paddr, uint32_t slot, uint64_t npages,
+ uint32_t flags);
+
+void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
+ void *arg);
+int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
+ void *arg);
+void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg);
+void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
+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);
+void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid);
+vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
+vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages);
+vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm);
+
+void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ unsigned int npages);
+void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
+void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
+vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
+void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa);
+
+/*
+ * Address Guest Virtual to Guest Physical
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * gva - VM virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Equivalent VM physical address
+ *
+ * Returns the VM physical address of the translated VM virtual
+ * address given by @gva.
+ */
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
+
+struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_guest_debug *debug);
+void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_mp_state *mp_state);
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
+void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
+
+/*
+ * VM VCPU Args Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * num - number of arguments
+ * ... - arguments, each of type uint64_t
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the first @num function input registers of the VCPU with @vcpuid,
+ * per the C calling convention of the architecture, to the values given
+ * as variable args. Each of the variable args is expected to be of type
+ * uint64_t. The maximum @num can be is specific to the architecture.
+ */
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...);
+
+void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_sregs *sregs);
+void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_sregs *sregs);
+int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_sregs *sregs);
+void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_fpu *fpu);
+void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_fpu *fpu);
+void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg);
+void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg);
+#ifdef __KVM_HAVE_VCPU_EVENTS
+void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_vcpu_events *events);
+void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_vcpu_events *events);
+#endif
+#ifdef __x86_64__
+void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_nested_state *state);
+int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_nested_state *state, bool ignore_error);
+#endif
+void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid);
+
+int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr);
+int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr);
+int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd);
+int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test);
+int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
+ void *val, bool write);
+int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr,
+ void *val, bool write);
+void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level);
+int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level);
+
+int _vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
+ uint64_t attr);
+int vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
+ uint64_t attr);
+int _vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
+ uint64_t attr, void *val, bool write);
+int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
+ uint64_t attr, void *val, bool write);
+
+#define KVM_MAX_IRQ_ROUTES 4096
+
+struct kvm_irq_routing *kvm_gsi_routing_create(void);
+void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing,
+ uint32_t gsi, uint32_t pin);
+int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing);
+void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing);
+
+const char *exit_reason_str(unsigned int exit_reason);
+
+void virt_pgd_alloc(struct kvm_vm *vm);
+
+/*
+ * VM Virtual Page Map
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vaddr - VM Virtual Address
+ * paddr - VM Physical Address
+ * memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within @vm, creates a virtual translation for the page starting
+ * at @vaddr to the page starting at @paddr.
+ */
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr);
+
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
+ uint32_t memslot);
+vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+ vm_paddr_t paddr_min, uint32_t memslot);
+vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
+
+/*
+ * Create a VM with reasonable defaults
+ *
+ * Input Args:
+ * vcpuid - The id of the single VCPU to add to the VM.
+ * extra_mem_pages - The number of extra pages to add (this will
+ * decide how much extra space we will need to
+ * setup the page tables using memslot 0)
+ * guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages,
+ void *guest_code);
+
+/* Same as vm_create_default, but can be used for more than one vcpu */
+struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages,
+ uint32_t num_percpu_pages, void *guest_code,
+ uint32_t vcpuids[]);
+
+/* Like vm_create_default_with_vcpus, but accepts mode and slot0 memory as a parameter */
+struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+ uint64_t slot0_mem_pages, uint64_t extra_mem_pages,
+ uint32_t num_percpu_pages, void *guest_code,
+ uint32_t vcpuids[]);
+
+/*
+ * Adds a vCPU with reasonable defaults (e.g. a stack)
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - The id of the VCPU to add to the VM.
+ * guest_code - The vCPU's entry point
+ */
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
+
+bool vm_is_unrestricted_guest(struct kvm_vm *vm);
+
+unsigned int vm_get_page_size(struct kvm_vm *vm);
+unsigned int vm_get_page_shift(struct kvm_vm *vm);
+unsigned long vm_compute_max_gfn(struct kvm_vm *vm);
+uint64_t vm_get_max_gfn(struct kvm_vm *vm);
+int vm_get_fd(struct kvm_vm *vm);
+
+unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size);
+unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages);
+unsigned int vm_num_guest_pages(enum vm_guest_mode mode, unsigned int num_host_pages);
+static inline unsigned int
+vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages)
+{
+ unsigned int n;
+ n = vm_num_guest_pages(mode, vm_num_host_pages(mode, num_guest_pages));
+#ifdef __s390x__
+ /* s390 requires 1M aligned guest sizes */
+ n = (n + 255) & ~255;
+#endif
+ return n;
+}
+
+struct kvm_userspace_memory_region *
+kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
+ uint64_t end);
+
+struct kvm_dirty_log *
+allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region);
+
+int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
+
+#define sync_global_to_guest(vm, g) ({ \
+ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
+ memcpy(_p, &(g), sizeof(g)); \
+})
+
+#define sync_global_from_guest(vm, g) ({ \
+ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
+ memcpy(&(g), _p, sizeof(g)); \
+})
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid);
+
+int vm_get_stats_fd(struct kvm_vm *vm);
+int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid);
+
+uint32_t guest_get_vcpuid(void);
+
+#endif /* SELFTEST_KVM_UTIL_BASE_H */
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
new file mode 100644
index 000000000000..dc284c6bdbc3
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * RISC-V processor specific defines
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include "kvm_util.h"
+#include <linux/stringify.h>
+
+static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx,
+ uint64_t size)
+{
+ return KVM_REG_RISCV | type | idx | size;
+}
+
+#if __riscv_xlen == 64
+#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U64
+#else
+#define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U32
+#endif
+
+#define RISCV_CONFIG_REG(name) __kvm_reg_id(KVM_REG_RISCV_CONFIG, \
+ KVM_REG_RISCV_CONFIG_REG(name), \
+ KVM_REG_SIZE_ULONG)
+
+#define RISCV_CORE_REG(name) __kvm_reg_id(KVM_REG_RISCV_CORE, \
+ KVM_REG_RISCV_CORE_REG(name), \
+ KVM_REG_SIZE_ULONG)
+
+#define RISCV_CSR_REG(name) __kvm_reg_id(KVM_REG_RISCV_CSR, \
+ KVM_REG_RISCV_CSR_REG(name), \
+ KVM_REG_SIZE_ULONG)
+
+#define RISCV_TIMER_REG(name) __kvm_reg_id(KVM_REG_RISCV_TIMER, \
+ KVM_REG_RISCV_TIMER_REG(name), \
+ KVM_REG_SIZE_U64)
+
+static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id,
+ unsigned long *addr)
+{
+ struct kvm_one_reg reg;
+
+ reg.id = id;
+ reg.addr = (unsigned long)addr;
+ vcpu_get_reg(vm, vcpuid, &reg);
+}
+
+static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id,
+ unsigned long val)
+{
+ struct kvm_one_reg reg;
+
+ reg.id = id;
+ reg.addr = (unsigned long)&val;
+ vcpu_set_reg(vm, vcpuid, &reg);
+}
+
+/* L3 index Bit[47:39] */
+#define PGTBL_L3_INDEX_MASK 0x0000FF8000000000ULL
+#define PGTBL_L3_INDEX_SHIFT 39
+#define PGTBL_L3_BLOCK_SHIFT 39
+#define PGTBL_L3_BLOCK_SIZE 0x0000008000000000ULL
+#define PGTBL_L3_MAP_MASK (~(PGTBL_L3_BLOCK_SIZE - 1))
+/* L2 index Bit[38:30] */
+#define PGTBL_L2_INDEX_MASK 0x0000007FC0000000ULL
+#define PGTBL_L2_INDEX_SHIFT 30
+#define PGTBL_L2_BLOCK_SHIFT 30
+#define PGTBL_L2_BLOCK_SIZE 0x0000000040000000ULL
+#define PGTBL_L2_MAP_MASK (~(PGTBL_L2_BLOCK_SIZE - 1))
+/* L1 index Bit[29:21] */
+#define PGTBL_L1_INDEX_MASK 0x000000003FE00000ULL
+#define PGTBL_L1_INDEX_SHIFT 21
+#define PGTBL_L1_BLOCK_SHIFT 21
+#define PGTBL_L1_BLOCK_SIZE 0x0000000000200000ULL
+#define PGTBL_L1_MAP_MASK (~(PGTBL_L1_BLOCK_SIZE - 1))
+/* L0 index Bit[20:12] */
+#define PGTBL_L0_INDEX_MASK 0x00000000001FF000ULL
+#define PGTBL_L0_INDEX_SHIFT 12
+#define PGTBL_L0_BLOCK_SHIFT 12
+#define PGTBL_L0_BLOCK_SIZE 0x0000000000001000ULL
+#define PGTBL_L0_MAP_MASK (~(PGTBL_L0_BLOCK_SIZE - 1))
+
+#define PGTBL_PTE_ADDR_MASK 0x003FFFFFFFFFFC00ULL
+#define PGTBL_PTE_ADDR_SHIFT 10
+#define PGTBL_PTE_RSW_MASK 0x0000000000000300ULL
+#define PGTBL_PTE_RSW_SHIFT 8
+#define PGTBL_PTE_DIRTY_MASK 0x0000000000000080ULL
+#define PGTBL_PTE_DIRTY_SHIFT 7
+#define PGTBL_PTE_ACCESSED_MASK 0x0000000000000040ULL
+#define PGTBL_PTE_ACCESSED_SHIFT 6
+#define PGTBL_PTE_GLOBAL_MASK 0x0000000000000020ULL
+#define PGTBL_PTE_GLOBAL_SHIFT 5
+#define PGTBL_PTE_USER_MASK 0x0000000000000010ULL
+#define PGTBL_PTE_USER_SHIFT 4
+#define PGTBL_PTE_EXECUTE_MASK 0x0000000000000008ULL
+#define PGTBL_PTE_EXECUTE_SHIFT 3
+#define PGTBL_PTE_WRITE_MASK 0x0000000000000004ULL
+#define PGTBL_PTE_WRITE_SHIFT 2
+#define PGTBL_PTE_READ_MASK 0x0000000000000002ULL
+#define PGTBL_PTE_READ_SHIFT 1
+#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_EXECUTE_MASK | \
+ PGTBL_PTE_WRITE_MASK | \
+ PGTBL_PTE_READ_MASK)
+#define PGTBL_PTE_VALID_MASK 0x0000000000000001ULL
+#define PGTBL_PTE_VALID_SHIFT 0
+
+#define PGTBL_PAGE_SIZE PGTBL_L0_BLOCK_SIZE
+#define PGTBL_PAGE_SIZE_SHIFT PGTBL_L0_BLOCK_SHIFT
+
+#define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL)
+#define SATP_MODE_39 _AC(0x8000000000000000, UL)
+#define SATP_MODE_48 _AC(0x9000000000000000, UL)
+#define SATP_ASID_BITS 16
+#define SATP_ASID_SHIFT 44
+#define SATP_ASID_MASK _AC(0xFFFF, UL)
+
+#define SBI_EXT_EXPERIMENTAL_START 0x08000000
+#define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF
+
+#define KVM_RISCV_SELFTESTS_SBI_EXT SBI_EXT_EXPERIMENTAL_END
+
+struct sbiret {
+ long error;
+ long value;
+};
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+ unsigned long arg1, unsigned long arg2,
+ unsigned long arg3, unsigned long arg4,
+ unsigned long arg5);
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
new file mode 100644
index 000000000000..9eecc9d40b79
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * tools/testing/selftests/kvm/include/kvm_util.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ */
+#ifndef SELFTEST_KVM_UCALL_COMMON_H
+#define SELFTEST_KVM_UCALL_COMMON_H
+
+/* Common ucalls */
+enum {
+ UCALL_NONE,
+ UCALL_SYNC,
+ UCALL_ABORT,
+ UCALL_DONE,
+ UCALL_UNHANDLED,
+};
+
+#define UCALL_MAX_ARGS 6
+
+struct ucall {
+ uint64_t cmd;
+ uint64_t args[UCALL_MAX_ARGS];
+};
+
+void ucall_init(struct kvm_vm *vm, void *arg);
+void ucall_uninit(struct kvm_vm *vm);
+void ucall(uint64_t cmd, int nargs, ...);
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc);
+
+#define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \
+ ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
+#define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage)
+#define GUEST_DONE() ucall(UCALL_DONE, 0)
+#define __GUEST_ASSERT(_condition, _condstr, _nargs, _args...) do { \
+ if (!(_condition)) \
+ ucall(UCALL_ABORT, 2 + _nargs, \
+ "Failed guest assert: " \
+ _condstr, __LINE__, _args); \
+} while (0)
+
+#define GUEST_ASSERT(_condition) \
+ __GUEST_ASSERT(_condition, #_condition, 0, 0)
+
+#define GUEST_ASSERT_1(_condition, arg1) \
+ __GUEST_ASSERT(_condition, #_condition, 1, (arg1))
+
+#define GUEST_ASSERT_2(_condition, arg1, arg2) \
+ __GUEST_ASSERT(_condition, #_condition, 2, (arg1), (arg2))
+
+#define GUEST_ASSERT_3(_condition, arg1, arg2, arg3) \
+ __GUEST_ASSERT(_condition, #_condition, 3, (arg1), (arg2), (arg3))
+
+#define GUEST_ASSERT_4(_condition, arg1, arg2, arg3, arg4) \
+ __GUEST_ASSERT(_condition, #_condition, 4, (arg1), (arg2), (arg3), (arg4))
+
+#define GUEST_ASSERT_EQ(a, b) __GUEST_ASSERT((a) == (b), #a " == " #b, 2, a, b)
+
+#endif /* SELFTEST_KVM_UCALL_COMMON_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 05e65ca1c30c..8a470da7b71a 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -10,8 +10,10 @@
#include <assert.h>
#include <stdint.h>
+#include <syscall.h>
#include <asm/msr-index.h>
+#include <asm/prctl.h>
#include "../kvm_util.h"
@@ -92,6 +94,21 @@ struct desc_ptr {
uint64_t address;
} __attribute__((packed));
+struct kvm_x86_state {
+ struct kvm_xsave *xsave;
+ struct kvm_vcpu_events events;
+ struct kvm_mp_state mp_state;
+ struct kvm_regs regs;
+ struct kvm_xcrs xcrs;
+ struct kvm_sregs sregs;
+ struct kvm_debugregs debugregs;
+ union {
+ struct kvm_nested_state nested;
+ char nested_[16384];
+ };
+ struct kvm_msrs msrs;
+};
+
static inline uint64_t get_desc64_base(const struct desc64 *desc)
{
return ((uint64_t)desc->base3 << 32) |
@@ -347,17 +364,37 @@ static inline unsigned long get_xmm(int n)
}
bool is_intel_cpu(void);
+bool is_amd_cpu(void);
+
+static inline unsigned int x86_family(unsigned int eax)
+{
+ unsigned int x86;
+
+ x86 = (eax >> 8) & 0xf;
+
+ if (x86 == 0xf)
+ x86 += (eax >> 20) & 0xff;
+
+ return x86;
+}
+
+static inline unsigned int x86_model(unsigned int eax)
+{
+ return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f);
+}
-struct kvm_x86_state;
struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid);
void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_x86_state *state);
+void kvm_x86_state_cleanup(struct kvm_x86_state *state);
struct kvm_msr_list *kvm_get_msr_index_list(void);
uint64_t kvm_get_feature_msr(uint64_t msr_index);
struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
struct kvm_cpuid2 *vcpu_get_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
+int __vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_cpuid2 *cpuid);
void vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_cpuid2 *cpuid);
@@ -402,6 +439,11 @@ void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr,
uint64_t pte);
/*
+ * get_cpuid() - find matching CPUID entry and return pointer to it.
+ */
+struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function,
+ uint32_t index);
+/*
* set_cpuid() - overwrites a matching cpuid entry with the provided value.
* matches based on ent->function && ent->index. returns true
* if a match was found and successfully overwritten.
@@ -416,6 +458,7 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void);
void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
+void vm_xsave_req_perm(int bit);
enum x86_page_size {
X86_PAGE_SIZE_4K = 0,
@@ -443,4 +486,11 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
/* VMX_EPT_VPID_CAP bits */
#define VMX_EPT_VPID_CAP_AD_BITS (1ULL << 21)
+#define XSTATE_XTILE_CFG_BIT 17
+#define XSTATE_XTILE_DATA_BIT 18
+
+#define XSTATE_XTILE_CFG_MASK (1ULL << XSTATE_XTILE_CFG_BIT)
+#define XSTATE_XTILE_DATA_MASK (1ULL << XSTATE_XTILE_DATA_BIT)
+#define XFEATURE_XTILE_MASK (XSTATE_XTILE_CFG_MASK | \
+ XSTATE_XTILE_DATA_MASK)
#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/aarch64/gic.c
index fff4fc27504d..55668631d546 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic.c
@@ -93,3 +93,69 @@ void gic_set_eoi(unsigned int intid)
GUEST_ASSERT(gic_common_ops);
gic_common_ops->gic_write_eoir(intid);
}
+
+void gic_set_dir(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_write_dir(intid);
+}
+
+void gic_set_eoi_split(bool split)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_set_eoi_split(split);
+}
+
+void gic_set_priority_mask(uint64_t pmr)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_set_priority_mask(pmr);
+}
+
+void gic_set_priority(unsigned int intid, unsigned int prio)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_set_priority(intid, prio);
+}
+
+void gic_irq_set_active(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_set_active(intid);
+}
+
+void gic_irq_clear_active(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_clear_active(intid);
+}
+
+bool gic_irq_get_active(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ return gic_common_ops->gic_irq_get_active(intid);
+}
+
+void gic_irq_set_pending(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_set_pending(intid);
+}
+
+void gic_irq_clear_pending(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_clear_pending(intid);
+}
+
+bool gic_irq_get_pending(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ return gic_common_ops->gic_irq_get_pending(intid);
+}
+
+void gic_irq_set_config(unsigned int intid, bool is_edge)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_set_config(intid, is_edge);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
index d81d739433dc..75d07313c893 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
@@ -14,6 +14,17 @@ struct gic_common_ops {
void (*gic_irq_disable)(unsigned int intid);
uint64_t (*gic_read_iar)(void);
void (*gic_write_eoir)(uint32_t irq);
+ void (*gic_write_dir)(uint32_t irq);
+ void (*gic_set_eoi_split)(bool split);
+ void (*gic_set_priority_mask)(uint64_t mask);
+ void (*gic_set_priority)(uint32_t intid, uint32_t prio);
+ void (*gic_irq_set_active)(uint32_t intid);
+ void (*gic_irq_clear_active)(uint32_t intid);
+ bool (*gic_irq_get_active)(uint32_t intid);
+ void (*gic_irq_set_pending)(uint32_t intid);
+ void (*gic_irq_clear_pending)(uint32_t intid);
+ bool (*gic_irq_get_pending)(uint32_t intid);
+ void (*gic_irq_set_config)(uint32_t intid, bool is_edge);
};
extern const struct gic_common_ops gicv3_ops;
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
index 2dbf3339b62e..00f613c0583c 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
@@ -19,7 +19,8 @@ struct gicv3_data {
unsigned int nr_spis;
};
-#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K)
+#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K)
+#define DIST_BIT (1U << 31)
enum gicv3_intid_range {
SGI_RANGE,
@@ -50,6 +51,14 @@ static void gicv3_gicr_wait_for_rwp(void *redist_base)
}
}
+static void gicv3_wait_for_rwp(uint32_t cpu_or_dist)
+{
+ if (cpu_or_dist & DIST_BIT)
+ gicv3_gicd_wait_for_rwp();
+ else
+ gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu_or_dist]);
+}
+
static enum gicv3_intid_range get_intid_range(unsigned int intid)
{
switch (intid) {
@@ -81,39 +90,175 @@ static void gicv3_write_eoir(uint32_t irq)
isb();
}
-static void
-gicv3_config_irq(unsigned int intid, unsigned int offset)
+static void gicv3_write_dir(uint32_t irq)
+{
+ write_sysreg_s(irq, SYS_ICC_DIR_EL1);
+ isb();
+}
+
+static void gicv3_set_priority_mask(uint64_t mask)
+{
+ write_sysreg_s(mask, SYS_ICC_PMR_EL1);
+}
+
+static void gicv3_set_eoi_split(bool split)
+{
+ uint32_t val;
+
+ /* All other fields are read-only, so no need to read CTLR first. In
+ * fact, the kernel does the same.
+ */
+ val = split ? (1U << 1) : 0;
+ write_sysreg_s(val, SYS_ICC_CTLR_EL1);
+ isb();
+}
+
+uint32_t gicv3_reg_readl(uint32_t cpu_or_dist, uint64_t offset)
+{
+ void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base
+ : sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]);
+ return readl(base + offset);
+}
+
+void gicv3_reg_writel(uint32_t cpu_or_dist, uint64_t offset, uint32_t reg_val)
+{
+ void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base
+ : sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]);
+ writel(reg_val, base + offset);
+}
+
+uint32_t gicv3_getl_fields(uint32_t cpu_or_dist, uint64_t offset, uint32_t mask)
+{
+ return gicv3_reg_readl(cpu_or_dist, offset) & mask;
+}
+
+void gicv3_setl_fields(uint32_t cpu_or_dist, uint64_t offset,
+ uint32_t mask, uint32_t reg_val)
+{
+ uint32_t tmp = gicv3_reg_readl(cpu_or_dist, offset) & ~mask;
+
+ tmp |= (reg_val & mask);
+ gicv3_reg_writel(cpu_or_dist, offset, tmp);
+}
+
+/*
+ * We use a single offset for the distributor and redistributor maps as they
+ * have the same value in both. The only exceptions are registers that only
+ * exist in one and not the other, like GICR_WAKER that doesn't exist in the
+ * distributor map. Such registers are conveniently marked as reserved in the
+ * map that doesn't implement it; like GICR_WAKER's offset of 0x0014 being
+ * marked as "Reserved" in the Distributor map.
+ */
+static void gicv3_access_reg(uint32_t intid, uint64_t offset,
+ uint32_t reg_bits, uint32_t bits_per_field,
+ bool write, uint32_t *val)
{
uint32_t cpu = guest_get_vcpuid();
- uint32_t mask = 1 << (intid % 32);
enum gicv3_intid_range intid_range = get_intid_range(intid);
- void *reg;
-
- /* We care about 'cpu' only for SGIs or PPIs */
- if (intid_range == SGI_RANGE || intid_range == PPI_RANGE) {
- GUEST_ASSERT(cpu < gicv3_data.nr_cpus);
-
- reg = sgi_base_from_redist(gicv3_data.redist_base[cpu]) +
- offset;
- writel(mask, reg);
- gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu]);
- } else if (intid_range == SPI_RANGE) {
- reg = gicv3_data.dist_base + offset + (intid / 32) * 4;
- writel(mask, reg);
- gicv3_gicd_wait_for_rwp();
- } else {
- GUEST_ASSERT(0);
- }
+ uint32_t fields_per_reg, index, mask, shift;
+ uint32_t cpu_or_dist;
+
+ GUEST_ASSERT(bits_per_field <= reg_bits);
+ GUEST_ASSERT(*val < (1U << bits_per_field));
+ /* Some registers like IROUTER are 64 bit long. Those are currently not
+ * supported by readl nor writel, so just asserting here until then.
+ */
+ GUEST_ASSERT(reg_bits == 32);
+
+ fields_per_reg = reg_bits / bits_per_field;
+ index = intid % fields_per_reg;
+ shift = index * bits_per_field;
+ mask = ((1U << bits_per_field) - 1) << shift;
+
+ /* Set offset to the actual register holding intid's config. */
+ offset += (intid / fields_per_reg) * (reg_bits / 8);
+
+ cpu_or_dist = (intid_range == SPI_RANGE) ? DIST_BIT : cpu;
+
+ if (write)
+ gicv3_setl_fields(cpu_or_dist, offset, mask, *val << shift);
+ *val = gicv3_getl_fields(cpu_or_dist, offset, mask) >> shift;
+}
+
+static void gicv3_write_reg(uint32_t intid, uint64_t offset,
+ uint32_t reg_bits, uint32_t bits_per_field, uint32_t val)
+{
+ gicv3_access_reg(intid, offset, reg_bits,
+ bits_per_field, true, &val);
+}
+
+static uint32_t gicv3_read_reg(uint32_t intid, uint64_t offset,
+ uint32_t reg_bits, uint32_t bits_per_field)
+{
+ uint32_t val;
+
+ gicv3_access_reg(intid, offset, reg_bits,
+ bits_per_field, false, &val);
+ return val;
+}
+
+static void gicv3_set_priority(uint32_t intid, uint32_t prio)
+{
+ gicv3_write_reg(intid, GICD_IPRIORITYR, 32, 8, prio);
+}
+
+/* Sets the intid to be level-sensitive or edge-triggered. */
+static void gicv3_irq_set_config(uint32_t intid, bool is_edge)
+{
+ uint32_t val;
+
+ /* N/A for private interrupts. */
+ GUEST_ASSERT(get_intid_range(intid) == SPI_RANGE);
+ val = is_edge ? 2 : 0;
+ gicv3_write_reg(intid, GICD_ICFGR, 32, 2, val);
+}
+
+static void gicv3_irq_enable(uint32_t intid)
+{
+ bool is_spi = get_intid_range(intid) == SPI_RANGE;
+ uint32_t cpu = guest_get_vcpuid();
+
+ gicv3_write_reg(intid, GICD_ISENABLER, 32, 1, 1);
+ gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu);
+}
+
+static void gicv3_irq_disable(uint32_t intid)
+{
+ bool is_spi = get_intid_range(intid) == SPI_RANGE;
+ uint32_t cpu = guest_get_vcpuid();
+
+ gicv3_write_reg(intid, GICD_ICENABLER, 32, 1, 1);
+ gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu);
+}
+
+static void gicv3_irq_set_active(uint32_t intid)
+{
+ gicv3_write_reg(intid, GICD_ISACTIVER, 32, 1, 1);
+}
+
+static void gicv3_irq_clear_active(uint32_t intid)
+{
+ gicv3_write_reg(intid, GICD_ICACTIVER, 32, 1, 1);
+}
+
+static bool gicv3_irq_get_active(uint32_t intid)
+{
+ return gicv3_read_reg(intid, GICD_ISACTIVER, 32, 1);
+}
+
+static void gicv3_irq_set_pending(uint32_t intid)
+{
+ gicv3_write_reg(intid, GICD_ISPENDR, 32, 1, 1);
}
-static void gicv3_irq_enable(unsigned int intid)
+static void gicv3_irq_clear_pending(uint32_t intid)
{
- gicv3_config_irq(intid, GICD_ISENABLER);
+ gicv3_write_reg(intid, GICD_ICPENDR, 32, 1, 1);
}
-static void gicv3_irq_disable(unsigned int intid)
+static bool gicv3_irq_get_pending(uint32_t intid)
{
- gicv3_config_irq(intid, GICD_ICENABLER);
+ return gicv3_read_reg(intid, GICD_ISPENDR, 32, 1);
}
static void gicv3_enable_redist(void *redist_base)
@@ -237,4 +382,15 @@ const struct gic_common_ops gicv3_ops = {
.gic_irq_disable = gicv3_irq_disable,
.gic_read_iar = gicv3_read_iar,
.gic_write_eoir = gicv3_write_eoir,
+ .gic_write_dir = gicv3_write_dir,
+ .gic_set_priority_mask = gicv3_set_priority_mask,
+ .gic_set_eoi_split = gicv3_set_eoi_split,
+ .gic_set_priority = gicv3_set_priority,
+ .gic_irq_set_active = gicv3_irq_set_active,
+ .gic_irq_clear_active = gicv3_irq_clear_active,
+ .gic_irq_get_active = gicv3_irq_get_active,
+ .gic_irq_set_pending = gicv3_irq_set_pending,
+ .gic_irq_clear_pending = gicv3_irq_clear_pending,
+ .gic_irq_get_pending = gicv3_irq_get_pending,
+ .gic_irq_set_config = gicv3_irq_set_config,
};
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index b4eeeafd2a70..9343d82519b4 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -8,6 +8,7 @@
#include <linux/compiler.h>
#include <assert.h>
+#include "guest_modes.h"
#include "kvm_util.h"
#include "../kvm_util_internal.h"
#include "processor.h"
@@ -237,6 +238,7 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init
get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1);
get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1);
+ /* Configure base granule size */
switch (vm->mode) {
case VM_MODE_P52V48_4K:
TEST_FAIL("AArch64 does not support 4K sized pages "
@@ -245,25 +247,47 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init
TEST_FAIL("AArch64 does not support 4K sized pages "
"with ANY-bit physical address ranges");
case VM_MODE_P52V48_64K:
+ case VM_MODE_P48V48_64K:
+ case VM_MODE_P40V48_64K:
+ case VM_MODE_P36V48_64K:
tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
- tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+ break;
+ case VM_MODE_P48V48_16K:
+ case VM_MODE_P40V48_16K:
+ case VM_MODE_P36V48_16K:
+ case VM_MODE_P36V47_16K:
+ tcr_el1 |= 2ul << 14; /* TG0 = 16KB */
break;
case VM_MODE_P48V48_4K:
+ case VM_MODE_P40V48_4K:
+ case VM_MODE_P36V48_4K:
tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
- tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
break;
+ default:
+ TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
+ }
+
+ /* Configure output size */
+ switch (vm->mode) {
+ case VM_MODE_P52V48_64K:
+ tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+ break;
+ case VM_MODE_P48V48_4K:
+ case VM_MODE_P48V48_16K:
case VM_MODE_P48V48_64K:
- tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
break;
case VM_MODE_P40V48_4K:
- tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
- tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
- break;
+ case VM_MODE_P40V48_16K:
case VM_MODE_P40V48_64K:
- tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
break;
+ case VM_MODE_P36V48_4K:
+ case VM_MODE_P36V48_16K:
+ case VM_MODE_P36V48_64K:
+ case VM_MODE_P36V47_16K:
+ tcr_el1 |= 1ul << 32; /* IPS = 36 bits */
+ break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
}
@@ -432,3 +456,47 @@ uint32_t guest_get_vcpuid(void)
{
return read_sysreg(tpidr_el1);
}
+
+void aarch64_get_supported_page_sizes(uint32_t ipa,
+ bool *ps4k, bool *ps16k, bool *ps64k)
+{
+ struct kvm_vcpu_init preferred_init;
+ int kvm_fd, vm_fd, vcpu_fd, err;
+ uint64_t val;
+ struct kvm_one_reg reg = {
+ .id = KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1),
+ .addr = (uint64_t)&val,
+ };
+
+ kvm_fd = open_kvm_dev_path_or_exit();
+ vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, ipa);
+ TEST_ASSERT(vm_fd >= 0, "Can't create VM");
+
+ vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0);
+ TEST_ASSERT(vcpu_fd >= 0, "Can't create vcpu");
+
+ err = ioctl(vm_fd, KVM_ARM_PREFERRED_TARGET, &preferred_init);
+ TEST_ASSERT(err == 0, "Can't get target");
+ err = ioctl(vcpu_fd, KVM_ARM_VCPU_INIT, &preferred_init);
+ TEST_ASSERT(err == 0, "Can't get init vcpu");
+
+ err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
+ TEST_ASSERT(err == 0, "Can't get MMFR0");
+
+ *ps4k = ((val >> 28) & 0xf) != 0xf;
+ *ps64k = ((val >> 24) & 0xf) == 0;
+ *ps16k = ((val >> 20) & 0xf) != 0;
+
+ close(vcpu_fd);
+ close(vm_fd);
+ close(kvm_fd);
+}
+
+/*
+ * arm64 doesn't have a true default mode, so start by computing the
+ * available IPA space and page sizes early.
+ */
+void __attribute__((constructor)) init_guest_modes(void)
+{
+ guest_modes_append_default();
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
index b9b271ff520d..f5cd0c536d85 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -5,11 +5,14 @@
#include <linux/kvm.h>
#include <linux/sizes.h>
+#include <asm/kvm_para.h>
#include <asm/kvm.h>
#include "kvm_util.h"
#include "../kvm_util_internal.h"
#include "vgic.h"
+#include "gic.h"
+#include "gic_v3.h"
/*
* vGIC-v3 default host setup
@@ -28,7 +31,7 @@
* redistributor regions of the guest. Since it depends on the number of
* vCPUs for the VM, it must be called after all the vCPUs have been created.
*/
-int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus,
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
uint64_t gicd_base_gpa, uint64_t gicr_base_gpa)
{
int gic_fd;
@@ -49,7 +52,16 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus,
nr_vcpus, nr_vcpus_created);
/* Distributor setup */
- gic_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+ if (_kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3,
+ false, &gic_fd) != 0)
+ return -1;
+
+ kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS,
+ 0, &nr_irqs, true);
+
+ kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+ KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
+
kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
KVM_VGIC_V3_ADDR_TYPE_DIST, &gicd_base_gpa, true);
nr_gic_pages = vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_DIST_SIZE);
@@ -68,3 +80,94 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus,
return gic_fd;
}
+
+/* should only work for level sensitive interrupts */
+int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level)
+{
+ uint64_t attr = 32 * (intid / 32);
+ uint64_t index = intid % 32;
+ uint64_t val;
+ int ret;
+
+ ret = _kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO,
+ attr, &val, false);
+ if (ret != 0)
+ return ret;
+
+ val |= 1U << index;
+ ret = _kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO,
+ attr, &val, true);
+ return ret;
+}
+
+void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level)
+{
+ int ret = _kvm_irq_set_level_info(gic_fd, intid, level);
+
+ TEST_ASSERT(ret == 0, "KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO failed, "
+ "rc: %i errno: %i", ret, errno);
+}
+
+int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level)
+{
+ uint32_t irq = intid & KVM_ARM_IRQ_NUM_MASK;
+
+ TEST_ASSERT(!INTID_IS_SGI(intid), "KVM_IRQ_LINE's interface itself "
+ "doesn't allow injecting SGIs. There's no mask for it.");
+
+ if (INTID_IS_PPI(intid))
+ irq |= KVM_ARM_IRQ_TYPE_PPI << KVM_ARM_IRQ_TYPE_SHIFT;
+ else
+ irq |= KVM_ARM_IRQ_TYPE_SPI << KVM_ARM_IRQ_TYPE_SHIFT;
+
+ return _kvm_irq_line(vm, irq, level);
+}
+
+void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level)
+{
+ int ret = _kvm_arm_irq_line(vm, intid, level);
+
+ TEST_ASSERT(ret == 0, "KVM_IRQ_LINE failed, rc: %i errno: %i",
+ ret, errno);
+}
+
+static void vgic_poke_irq(int gic_fd, uint32_t intid,
+ uint32_t vcpu, uint64_t reg_off)
+{
+ uint64_t reg = intid / 32;
+ uint64_t index = intid % 32;
+ uint64_t attr = reg_off + reg * 4;
+ uint64_t val;
+ bool intid_is_private = INTID_IS_SGI(intid) || INTID_IS_PPI(intid);
+
+ /* Check that the addr part of the attr is within 32 bits. */
+ assert(attr <= KVM_DEV_ARM_VGIC_OFFSET_MASK);
+
+ uint32_t group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
+ : KVM_DEV_ARM_VGIC_GRP_DIST_REGS;
+
+ if (intid_is_private) {
+ /* TODO: only vcpu 0 implemented for now. */
+ assert(vcpu == 0);
+ attr += SZ_64K;
+ }
+
+ /* All calls will succeed, even with invalid intid's, as long as the
+ * addr part of the attr is within 32 bits (checked above). An invalid
+ * intid will just make the read/writes point to above the intended
+ * register space (i.e., ICPENDR after ISPENDR).
+ */
+ kvm_device_access(gic_fd, group, attr, &val, false);
+ val |= 1ULL << index;
+ kvm_device_access(gic_fd, group, attr, &val, true);
+}
+
+void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, uint32_t vcpu)
+{
+ vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISPENDR);
+}
+
+void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, uint32_t vcpu)
+{
+ vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISACTIVER);
+}
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
index c330f414ef96..8784013b747c 100644
--- a/tools/testing/selftests/kvm/lib/guest_modes.c
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -4,22 +4,59 @@
*/
#include "guest_modes.h"
+#ifdef __aarch64__
+#include "processor.h"
+enum vm_guest_mode vm_mode_default;
+#endif
+
struct guest_mode guest_modes[NUM_VM_MODES];
void guest_modes_append_default(void)
{
+#ifndef __aarch64__
guest_mode_append(VM_MODE_DEFAULT, true, true);
-
-#ifdef __aarch64__
- guest_mode_append(VM_MODE_P40V48_64K, true, true);
+#else
{
unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+ bool ps4k, ps16k, ps64k;
+ int i;
+
+ aarch64_get_supported_page_sizes(limit, &ps4k, &ps16k, &ps64k);
+
+ vm_mode_default = NUM_VM_MODES;
+
if (limit >= 52)
- guest_mode_append(VM_MODE_P52V48_64K, true, true);
+ guest_mode_append(VM_MODE_P52V48_64K, ps64k, ps64k);
if (limit >= 48) {
- guest_mode_append(VM_MODE_P48V48_4K, true, true);
- guest_mode_append(VM_MODE_P48V48_64K, true, true);
+ guest_mode_append(VM_MODE_P48V48_4K, ps4k, ps4k);
+ guest_mode_append(VM_MODE_P48V48_16K, ps16k, ps16k);
+ guest_mode_append(VM_MODE_P48V48_64K, ps64k, ps64k);
+ }
+ if (limit >= 40) {
+ guest_mode_append(VM_MODE_P40V48_4K, ps4k, ps4k);
+ guest_mode_append(VM_MODE_P40V48_16K, ps16k, ps16k);
+ guest_mode_append(VM_MODE_P40V48_64K, ps64k, ps64k);
+ if (ps4k)
+ vm_mode_default = VM_MODE_P40V48_4K;
}
+ if (limit >= 36) {
+ guest_mode_append(VM_MODE_P36V48_4K, ps4k, ps4k);
+ guest_mode_append(VM_MODE_P36V48_16K, ps16k, ps16k);
+ guest_mode_append(VM_MODE_P36V48_64K, ps64k, ps64k);
+ guest_mode_append(VM_MODE_P36V47_16K, ps16k, ps16k);
+ }
+
+ /*
+ * Pick the first supported IPA size if the default
+ * isn't available.
+ */
+ for (i = 0; vm_mode_default == NUM_VM_MODES && i < NUM_VM_MODES; i++) {
+ if (guest_modes[i].supported && guest_modes[i].enabled)
+ vm_mode_default = i;
+ }
+
+ TEST_ASSERT(vm_mode_default != NUM_VM_MODES,
+ "No supported mode!");
}
#endif
#ifdef __s390x__
@@ -38,6 +75,16 @@ void guest_modes_append_default(void)
guest_mode_append(VM_MODE_P47V64_4K, true, true);
}
#endif
+#ifdef __riscv
+ {
+ unsigned int sz = kvm_check_cap(KVM_CAP_VM_GPA_BITS);
+
+ if (sz >= 52)
+ guest_mode_append(VM_MODE_P52V48_4K, true, true);
+ if (sz >= 48)
+ guest_mode_append(VM_MODE_P48V48_4K, true, true);
+ }
+#endif
}
void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 53d2b5d04b82..d8cf851ab119 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -85,6 +85,33 @@ int kvm_check_cap(long cap)
return ret;
}
+/* VM Check Capability
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * cap - Capability
+ *
+ * Output Args: None
+ *
+ * Return:
+ * On success, the Value corresponding to the capability (KVM_CAP_*)
+ * specified by the value of cap. On failure a TEST_ASSERT failure
+ * is produced.
+ *
+ * Looks up and returns the value corresponding to the capability
+ * (KVM_CAP_*) given by cap.
+ */
+int vm_check_cap(struct kvm_vm *vm, long cap)
+{
+ int ret;
+
+ ret = ioctl(vm->fd, KVM_CHECK_EXTENSION, cap);
+ TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION VM IOCTL failed,\n"
+ " rc: %i errno: %i", ret, errno);
+
+ return ret;
+}
+
/* VM Enable Capability
*
* Input Args:
@@ -166,12 +193,18 @@ const char *vm_guest_mode_string(uint32_t i)
[VM_MODE_P52V48_4K] = "PA-bits:52, VA-bits:48, 4K pages",
[VM_MODE_P52V48_64K] = "PA-bits:52, VA-bits:48, 64K pages",
[VM_MODE_P48V48_4K] = "PA-bits:48, VA-bits:48, 4K pages",
+ [VM_MODE_P48V48_16K] = "PA-bits:48, VA-bits:48, 16K pages",
[VM_MODE_P48V48_64K] = "PA-bits:48, VA-bits:48, 64K pages",
[VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages",
+ [VM_MODE_P40V48_16K] = "PA-bits:40, VA-bits:48, 16K 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",
[VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages",
+ [VM_MODE_P36V48_4K] = "PA-bits:36, VA-bits:48, 4K pages",
+ [VM_MODE_P36V48_16K] = "PA-bits:36, VA-bits:48, 16K pages",
+ [VM_MODE_P36V48_64K] = "PA-bits:36, VA-bits:48, 64K pages",
+ [VM_MODE_P36V47_16K] = "PA-bits:36, VA-bits:47, 16K pages",
};
_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
@@ -185,12 +218,18 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
[VM_MODE_P52V48_4K] = { 52, 48, 0x1000, 12 },
[VM_MODE_P52V48_64K] = { 52, 48, 0x10000, 16 },
[VM_MODE_P48V48_4K] = { 48, 48, 0x1000, 12 },
+ [VM_MODE_P48V48_16K] = { 48, 48, 0x4000, 14 },
[VM_MODE_P48V48_64K] = { 48, 48, 0x10000, 16 },
[VM_MODE_P40V48_4K] = { 40, 48, 0x1000, 12 },
+ [VM_MODE_P40V48_16K] = { 40, 48, 0x4000, 14 },
[VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 },
[VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 },
[VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 },
[VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 },
+ [VM_MODE_P36V48_4K] = { 36, 48, 0x1000, 12 },
+ [VM_MODE_P36V48_16K] = { 36, 48, 0x4000, 14 },
+ [VM_MODE_P36V48_64K] = { 36, 48, 0x10000, 16 },
+ [VM_MODE_P36V47_16K] = { 36, 47, 0x4000, 14 },
};
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
"Missing new mode params?");
@@ -252,9 +291,19 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
vm->pgtable_levels = 3;
break;
case VM_MODE_P40V48_4K:
+ case VM_MODE_P36V48_4K:
vm->pgtable_levels = 4;
break;
case VM_MODE_P40V48_64K:
+ case VM_MODE_P36V48_64K:
+ vm->pgtable_levels = 3;
+ break;
+ case VM_MODE_P48V48_16K:
+ case VM_MODE_P40V48_16K:
+ case VM_MODE_P36V48_16K:
+ vm->pgtable_levels = 4;
+ break;
+ case VM_MODE_P36V47_16K:
vm->pgtable_levels = 3;
break;
case VM_MODE_PXXV48_4K:
@@ -443,9 +492,11 @@ void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log)
void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
uint64_t first_page, uint32_t num_pages)
{
- struct kvm_clear_dirty_log args = { .dirty_bitmap = log, .slot = slot,
- .first_page = first_page,
- .num_pages = num_pages };
+ struct kvm_clear_dirty_log args = {
+ .dirty_bitmap = log, .slot = slot,
+ .first_page = first_page,
+ .num_pages = num_pages
+ };
int ret;
ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args);
@@ -2087,6 +2138,78 @@ int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group,
}
/*
+ * IRQ related functions.
+ */
+
+int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level)
+{
+ struct kvm_irq_level irq_level = {
+ .irq = irq,
+ .level = level,
+ };
+
+ return _vm_ioctl(vm, KVM_IRQ_LINE, &irq_level);
+}
+
+void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level)
+{
+ int ret = _kvm_irq_line(vm, irq, level);
+
+ TEST_ASSERT(ret >= 0, "KVM_IRQ_LINE failed, rc: %i errno: %i", ret, errno);
+}
+
+struct kvm_irq_routing *kvm_gsi_routing_create(void)
+{
+ struct kvm_irq_routing *routing;
+ size_t size;
+
+ size = sizeof(struct kvm_irq_routing);
+ /* Allocate space for the max number of entries: this wastes 196 KBs. */
+ size += KVM_MAX_IRQ_ROUTES * sizeof(struct kvm_irq_routing_entry);
+ routing = calloc(1, size);
+ assert(routing);
+
+ return routing;
+}
+
+void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing,
+ uint32_t gsi, uint32_t pin)
+{
+ int i;
+
+ assert(routing);
+ assert(routing->nr < KVM_MAX_IRQ_ROUTES);
+
+ i = routing->nr;
+ routing->entries[i].gsi = gsi;
+ routing->entries[i].type = KVM_IRQ_ROUTING_IRQCHIP;
+ routing->entries[i].flags = 0;
+ routing->entries[i].u.irqchip.irqchip = 0;
+ routing->entries[i].u.irqchip.pin = pin;
+ routing->nr++;
+}
+
+int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing)
+{
+ int ret;
+
+ assert(routing);
+ ret = ioctl(vm_get_fd(vm), KVM_SET_GSI_ROUTING, routing);
+ free(routing);
+
+ return ret;
+}
+
+void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing)
+{
+ int ret;
+
+ ret = _kvm_gsi_routing_write(vm, routing);
+ TEST_ASSERT(ret == 0, "KVM_SET_GSI_ROUTING failed, rc: %i errno: %i",
+ ret, errno);
+}
+
+/*
* VM Dump
*
* Input Args:
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
new file mode 100644
index 000000000000..d377f2603d98
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -0,0 +1,362 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * RISC-V code
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/compiler.h>
+#include <assert.h>
+
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+
+#define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN 0xac0000
+
+static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
+{
+ return (v + vm->page_size) & ~(vm->page_size - 1);
+}
+
+static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry)
+{
+ return ((entry & PGTBL_PTE_ADDR_MASK) >> PGTBL_PTE_ADDR_SHIFT) <<
+ PGTBL_PAGE_SIZE_SHIFT;
+}
+
+static uint64_t ptrs_per_pte(struct kvm_vm *vm)
+{
+ return PGTBL_PAGE_SIZE / sizeof(uint64_t);
+}
+
+static uint64_t pte_index_mask[] = {
+ PGTBL_L0_INDEX_MASK,
+ PGTBL_L1_INDEX_MASK,
+ PGTBL_L2_INDEX_MASK,
+ PGTBL_L3_INDEX_MASK,
+};
+
+static uint32_t pte_index_shift[] = {
+ PGTBL_L0_INDEX_SHIFT,
+ PGTBL_L1_INDEX_SHIFT,
+ PGTBL_L2_INDEX_SHIFT,
+ PGTBL_L3_INDEX_SHIFT,
+};
+
+static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level)
+{
+ TEST_ASSERT(level > -1,
+ "Negative page table level (%d) not possible", level);
+ TEST_ASSERT(level < vm->pgtable_levels,
+ "Invalid page table level (%d)", level);
+
+ return (gva & pte_index_mask[level]) >> pte_index_shift[level];
+}
+
+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_pte(vm) * 8) / vm->page_size,
+ 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)
+{
+ uint64_t *ptep, next_ppn;
+ int level = vm->pgtable_levels - 1;
+
+ 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 maximum supported,\n"
+ " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->max_gfn, vm->page_size);
+
+ ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, vaddr, level) * 8;
+ if (!*ptep) {
+ next_ppn = vm_alloc_page_table(vm) >> PGTBL_PAGE_SIZE_SHIFT;
+ *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) |
+ PGTBL_PTE_VALID_MASK;
+ }
+ level--;
+
+ while (level > -1) {
+ ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) +
+ pte_index(vm, vaddr, level) * 8;
+ if (!*ptep && level > 0) {
+ next_ppn = vm_alloc_page_table(vm) >>
+ PGTBL_PAGE_SIZE_SHIFT;
+ *ptep = (next_ppn << PGTBL_PTE_ADDR_SHIFT) |
+ PGTBL_PTE_VALID_MASK;
+ }
+ level--;
+ }
+
+ paddr = paddr >> PGTBL_PAGE_SIZE_SHIFT;
+ *ptep = (paddr << PGTBL_PTE_ADDR_SHIFT) |
+ PGTBL_PTE_PERM_MASK | PGTBL_PTE_VALID_MASK;
+}
+
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ uint64_t *ptep;
+ int level = vm->pgtable_levels - 1;
+
+ if (!vm->pgd_created)
+ goto unmapped_gva;
+
+ ptep = addr_gpa2hva(vm, vm->pgd) + pte_index(vm, gva, level) * 8;
+ if (!ptep)
+ goto unmapped_gva;
+ level--;
+
+ while (level > -1) {
+ ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) +
+ pte_index(vm, gva, level) * 8;
+ if (!ptep)
+ goto unmapped_gva;
+ level--;
+ }
+
+ return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
+
+unmapped_gva:
+ TEST_FAIL("No mapping for vm virtual address gva: 0x%lx level: %d",
+ gva, level);
+ exit(1);
+}
+
+static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent,
+ uint64_t page, int level)
+{
+#ifdef DEBUG
+ static const char *const type[] = { "pte", "pmd", "pud", "p4d"};
+ uint64_t pte, *ptep;
+
+ if (level < 0)
+ return;
+
+ for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) {
+ ptep = addr_gpa2hva(vm, pte);
+ if (!*ptep)
+ continue;
+ fprintf(stream, "%*s%s: %lx: %lx at %p\n", indent, "",
+ type[level], pte, *ptep, ptep);
+ pte_dump(stream, vm, indent + 1,
+ pte_addr(vm, *ptep), level - 1);
+ }
+#endif
+}
+
+void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+ int level = vm->pgtable_levels - 1;
+ uint64_t pgd, *ptep;
+
+ if (!vm->pgd_created)
+ return;
+
+ for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pte(vm) * 8; pgd += 8) {
+ ptep = addr_gpa2hva(vm, pgd);
+ if (!*ptep)
+ continue;
+ fprintf(stream, "%*spgd: %lx: %lx at %p\n", indent, "",
+ pgd, *ptep, ptep);
+ pte_dump(stream, vm, indent + 1,
+ pte_addr(vm, *ptep), level - 1);
+ }
+}
+
+void riscv_vcpu_mmu_setup(struct kvm_vm *vm, int vcpuid)
+{
+ unsigned long satp;
+
+ /*
+ * The RISC-V Sv48 MMU mode supports 56-bit physical address
+ * for 48-bit virtual address with 4KB last level page size.
+ */
+ switch (vm->mode) {
+ case VM_MODE_P52V48_4K:
+ case VM_MODE_P48V48_4K:
+ case VM_MODE_P40V48_4K:
+ break;
+ default:
+ TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
+ }
+
+ satp = (vm->pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN;
+ satp |= SATP_MODE_48;
+
+ set_reg(vm, vcpuid, RISCV_CSR_REG(satp), satp);
+}
+
+void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
+{
+ struct kvm_riscv_core core;
+
+ get_reg(vm, vcpuid, RISCV_CORE_REG(mode), &core.mode);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.pc), &core.regs.pc);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.ra), &core.regs.ra);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.sp), &core.regs.sp);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.gp), &core.regs.gp);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.tp), &core.regs.tp);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t0), &core.regs.t0);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t1), &core.regs.t1);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t2), &core.regs.t2);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s0), &core.regs.s0);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s1), &core.regs.s1);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a0), &core.regs.a0);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a1), &core.regs.a1);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a2), &core.regs.a2);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a3), &core.regs.a3);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a4), &core.regs.a4);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a5), &core.regs.a5);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a6), &core.regs.a6);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.a7), &core.regs.a7);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s2), &core.regs.s2);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s3), &core.regs.s3);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s4), &core.regs.s4);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s5), &core.regs.s5);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s6), &core.regs.s6);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s7), &core.regs.s7);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s8), &core.regs.s8);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s9), &core.regs.s9);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s10), &core.regs.s10);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.s11), &core.regs.s11);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t3), &core.regs.t3);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t4), &core.regs.t4);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t5), &core.regs.t5);
+ get_reg(vm, vcpuid, RISCV_CORE_REG(regs.t6), &core.regs.t6);
+
+ fprintf(stream,
+ " MODE: 0x%lx\n", core.mode);
+ fprintf(stream,
+ " PC: 0x%016lx RA: 0x%016lx SP: 0x%016lx GP: 0x%016lx\n",
+ core.regs.pc, core.regs.ra, core.regs.sp, core.regs.gp);
+ fprintf(stream,
+ " TP: 0x%016lx T0: 0x%016lx T1: 0x%016lx T2: 0x%016lx\n",
+ core.regs.tp, core.regs.t0, core.regs.t1, core.regs.t2);
+ fprintf(stream,
+ " S0: 0x%016lx S1: 0x%016lx A0: 0x%016lx A1: 0x%016lx\n",
+ core.regs.s0, core.regs.s1, core.regs.a0, core.regs.a1);
+ fprintf(stream,
+ " A2: 0x%016lx A3: 0x%016lx A4: 0x%016lx A5: 0x%016lx\n",
+ core.regs.a2, core.regs.a3, core.regs.a4, core.regs.a5);
+ fprintf(stream,
+ " A6: 0x%016lx A7: 0x%016lx S2: 0x%016lx S3: 0x%016lx\n",
+ core.regs.a6, core.regs.a7, core.regs.s2, core.regs.s3);
+ fprintf(stream,
+ " S4: 0x%016lx S5: 0x%016lx S6: 0x%016lx S7: 0x%016lx\n",
+ core.regs.s4, core.regs.s5, core.regs.s6, core.regs.s7);
+ fprintf(stream,
+ " S8: 0x%016lx S9: 0x%016lx S10: 0x%016lx S11: 0x%016lx\n",
+ core.regs.s8, core.regs.s9, core.regs.s10, core.regs.s11);
+ fprintf(stream,
+ " T3: 0x%016lx T4: 0x%016lx T5: 0x%016lx T6: 0x%016lx\n",
+ core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6);
+}
+
+static void guest_hang(void)
+{
+ while (1)
+ ;
+}
+
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
+{
+ int r;
+ size_t stack_size = vm->page_size == 4096 ?
+ DEFAULT_STACK_PGS * vm->page_size :
+ vm->page_size;
+ unsigned long stack_vaddr = vm_vaddr_alloc(vm, stack_size,
+ DEFAULT_RISCV_GUEST_STACK_VADDR_MIN);
+ unsigned long current_gp = 0;
+ struct kvm_mp_state mps;
+
+ vm_vcpu_add(vm, vcpuid);
+ riscv_vcpu_mmu_setup(vm, vcpuid);
+
+ /*
+ * With SBI HSM support in KVM RISC-V, all secondary VCPUs are
+ * powered-off by default so we ensure that all secondary VCPUs
+ * are powered-on using KVM_SET_MP_STATE ioctl().
+ */
+ mps.mp_state = KVM_MP_STATE_RUNNABLE;
+ r = _vcpu_ioctl(vm, vcpuid, KVM_SET_MP_STATE, &mps);
+ TEST_ASSERT(!r, "IOCTL KVM_SET_MP_STATE failed (error %d)", r);
+
+ /* Setup global pointer of guest to be same as the host */
+ asm volatile (
+ "add %0, gp, zero" : "=r" (current_gp) : : "memory");
+ set_reg(vm, vcpuid, RISCV_CORE_REG(regs.gp), current_gp);
+
+ /* Setup stack pointer and program counter of guest */
+ set_reg(vm, vcpuid, RISCV_CORE_REG(regs.sp),
+ stack_vaddr + stack_size);
+ set_reg(vm, vcpuid, RISCV_CORE_REG(regs.pc),
+ (unsigned long)guest_code);
+
+ /* Setup default exception vector of guest */
+ set_reg(vm, vcpuid, RISCV_CSR_REG(stvec),
+ (unsigned long)guest_hang);
+}
+
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+ va_list ap;
+ uint64_t id = RISCV_CORE_REG(regs.a0);
+ int i;
+
+ TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
+ " num: %u\n", num);
+
+ va_start(ap, num);
+
+ for (i = 0; i < num; i++) {
+ switch (i) {
+ case 0:
+ id = RISCV_CORE_REG(regs.a0);
+ break;
+ case 1:
+ id = RISCV_CORE_REG(regs.a1);
+ break;
+ case 2:
+ id = RISCV_CORE_REG(regs.a2);
+ break;
+ case 3:
+ id = RISCV_CORE_REG(regs.a3);
+ break;
+ case 4:
+ id = RISCV_CORE_REG(regs.a4);
+ break;
+ case 5:
+ id = RISCV_CORE_REG(regs.a5);
+ break;
+ case 6:
+ id = RISCV_CORE_REG(regs.a6);
+ break;
+ case 7:
+ id = RISCV_CORE_REG(regs.a7);
+ break;
+ };
+ set_reg(vm, vcpuid, id, va_arg(ap, uint64_t));
+ }
+
+ va_end(ap);
+}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}
diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c
new file mode 100644
index 000000000000..9e42d8248fa6
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ucall support. A ucall is a "hypercall to userspace".
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/kvm.h>
+
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "processor.h"
+
+void ucall_init(struct kvm_vm *vm, void *arg)
+{
+}
+
+void ucall_uninit(struct kvm_vm *vm)
+{
+}
+
+struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+ unsigned long arg1, unsigned long arg2,
+ unsigned long arg3, unsigned long arg4,
+ unsigned long arg5)
+{
+ register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
+ register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
+ register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
+ register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
+ register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
+ register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
+ register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
+ register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
+ struct sbiret ret;
+
+ asm volatile (
+ "ecall"
+ : "+r" (a0), "+r" (a1)
+ : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
+ : "memory");
+ ret.error = a0;
+ ret.value = a1;
+
+ return ret;
+}
+
+void ucall(uint64_t cmd, int nargs, ...)
+{
+ struct ucall uc = {
+ .cmd = cmd,
+ };
+ va_list va;
+ int i;
+
+ nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS;
+
+ va_start(va, nargs);
+ for (i = 0; i < nargs; ++i)
+ uc.args[i] = va_arg(va, uint64_t);
+ va_end(va);
+
+ sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT, 0, (vm_vaddr_t)&uc,
+ 0, 0, 0, 0, 0);
+}
+
+uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
+{
+ struct kvm_run *run = vcpu_state(vm, vcpu_id);
+ struct ucall ucall = {};
+
+ if (uc)
+ memset(uc, 0, sizeof(*uc));
+
+ if (run->exit_reason == KVM_EXIT_RISCV_SBI &&
+ run->riscv_sbi.extension_id == KVM_RISCV_SELFTESTS_SBI_EXT &&
+ run->riscv_sbi.function_id == 0) {
+ memcpy(&ucall, addr_gva2hva(vm, run->riscv_sbi.args[0]),
+ sizeof(ucall));
+
+ vcpu_run_complete_io(vm, vcpu_id);
+ if (uc)
+ memcpy(uc, &ucall, sizeof(ucall));
+ }
+
+ return ucall.cmd;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index eef7b34756d5..9f000dfb5594 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -650,6 +650,60 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid)
vcpu_sregs_set(vm, vcpuid, &sregs);
}
+#define CPUID_XFD_BIT (1 << 4)
+static bool is_xfd_supported(void)
+{
+ int eax, ebx, ecx, edx;
+ const int leaf = 0xd, subleaf = 0x1;
+
+ __asm__ __volatile__(
+ "cpuid"
+ : /* output */ "=a"(eax), "=b"(ebx),
+ "=c"(ecx), "=d"(edx)
+ : /* input */ "0"(leaf), "2"(subleaf));
+
+ return !!(eax & CPUID_XFD_BIT);
+}
+
+void vm_xsave_req_perm(int bit)
+{
+ int kvm_fd;
+ u64 bitmask;
+ long rc;
+ struct kvm_device_attr attr = {
+ .group = 0,
+ .attr = KVM_X86_XCOMP_GUEST_SUPP,
+ .addr = (unsigned long) &bitmask
+ };
+
+ kvm_fd = open_kvm_dev_path_or_exit();
+ rc = ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr);
+ close(kvm_fd);
+ if (rc == -1 && (errno == ENXIO || errno == EINVAL))
+ exit(KSFT_SKIP);
+ TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc);
+ if (!(bitmask & (1ULL << bit)))
+ exit(KSFT_SKIP);
+
+ if (!is_xfd_supported())
+ exit(KSFT_SKIP);
+
+ rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit);
+
+ /*
+ * The older kernel version(<5.15) can't support
+ * ARCH_REQ_XCOMP_GUEST_PERM and directly return.
+ */
+ if (rc)
+ return;
+
+ rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask);
+ TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc);
+ TEST_ASSERT(bitmask & (1ULL << bit),
+ "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx",
+ bitmask);
+}
+
void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
{
struct kvm_mp_state mp_state;
@@ -847,6 +901,17 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
return entry;
}
+
+int __vcpu_set_cpuid(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_cpuid2 *cpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ return ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
+}
+
/*
* VM VCPU CPUID Set
*
@@ -864,12 +929,9 @@ kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
void vcpu_set_cpuid(struct kvm_vm *vm,
uint32_t vcpuid, struct kvm_cpuid2 *cpuid)
{
- struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int rc;
- TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
-
- rc = ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
+ rc = __vcpu_set_cpuid(vm, vcpuid, cpuid);
TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i",
rc, errno);
@@ -1017,21 +1079,6 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
sregs_dump(stream, &sregs, indent + 4);
}
-struct kvm_x86_state {
- struct kvm_vcpu_events events;
- struct kvm_mp_state mp_state;
- struct kvm_regs regs;
- struct kvm_xsave xsave;
- struct kvm_xcrs xcrs;
- struct kvm_sregs sregs;
- struct kvm_debugregs debugregs;
- union {
- struct kvm_nested_state nested;
- char nested_[16384];
- };
- struct kvm_msrs msrs;
-};
-
static int kvm_get_num_msrs_fd(int kvm_fd)
{
struct kvm_msr_list nmsrs;
@@ -1069,6 +1116,22 @@ struct kvm_msr_list *kvm_get_msr_index_list(void)
return list;
}
+static int vcpu_save_xsave_state(struct kvm_vm *vm, struct vcpu *vcpu,
+ struct kvm_x86_state *state)
+{
+ int size;
+
+ size = vm_check_cap(vm, KVM_CAP_XSAVE2);
+ if (!size)
+ size = sizeof(struct kvm_xsave);
+
+ state->xsave = malloc(size);
+ if (size == sizeof(struct kvm_xsave))
+ return ioctl(vcpu->fd, KVM_GET_XSAVE, state->xsave);
+ else
+ return ioctl(vcpu->fd, KVM_GET_XSAVE2, state->xsave);
+}
+
struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
{
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
@@ -1096,25 +1159,25 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
list->nmsrs = nmsrs;
r = ioctl(vm->kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MSR_INDEX_LIST, r: %i",
+ r);
state = malloc(sizeof(*state) + nmsrs * sizeof(state->msrs.entries[0]));
r = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, &state->events);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_VCPU_EVENTS, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_GET_MP_STATE, &state->mp_state);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_MP_STATE, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_GET_REGS, &state->regs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_REGS, r: %i",
+ r);
- r = ioctl(vcpu->fd, KVM_GET_XSAVE, &state->xsave);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
- r);
+ r = vcpu_save_xsave_state(vm, vcpu, state);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
+ r);
if (kvm_check_cap(KVM_CAP_XCRS)) {
r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs);
@@ -1123,17 +1186,17 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
}
r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
+ r);
if (nested_size) {
state->nested.size = sizeof(state->nested_);
r = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, &state->nested);
TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_NESTED_STATE, r: %i",
- r);
+ r);
TEST_ASSERT(state->nested.size <= nested_size,
- "Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
- state->nested.size, nested_size);
+ "Nested state size too big, %i (KVM_CHECK_CAP gave %i)",
+ state->nested.size, nested_size);
} else
state->nested.size = 0;
@@ -1141,12 +1204,12 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
for (i = 0; i < nmsrs; i++)
state->msrs.entries[i].index = list->indices[i];
r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs);
- TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)",
- r, r == nmsrs ? -1 : list->indices[r]);
+ TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)",
+ r, r == nmsrs ? -1 : list->indices[r]);
r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_DEBUGREGS, r: %i",
+ r);
free(list);
return state;
@@ -1157,9 +1220,14 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
struct vcpu *vcpu = vcpu_find(vm, vcpuid);
int r;
- r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
- r);
+ r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
+ r);
+
+ r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs);
+ TEST_ASSERT(r == state->msrs.nmsrs,
+ "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)",
+ r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index);
if (kvm_check_cap(KVM_CAP_XCRS)) {
r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs);
@@ -1167,41 +1235,43 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
r);
}
- r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
- r);
-
- r = ioctl(vcpu->fd, KVM_SET_MSRS, &state->msrs);
- TEST_ASSERT(r == state->msrs.nmsrs, "Unexpected result from KVM_SET_MSRS, r: %i (failed at %x)",
- r, r == state->msrs.nmsrs ? -1 : state->msrs.entries[r].index);
+ r = ioctl(vcpu->fd, KVM_SET_XSAVE, state->xsave);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, &state->events);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_VCPU_EVENTS, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_MP_STATE, &state->mp_state);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_MP_STATE, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_DEBUGREGS, &state->debugregs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_DEBUGREGS, r: %i",
+ r);
r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
- r);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
+ r);
if (state->nested.size) {
r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
- r);
+ r);
}
}
-bool is_intel_cpu(void)
+void kvm_x86_state_cleanup(struct kvm_x86_state *state)
+{
+ free(state->xsave);
+ free(state);
+}
+
+static bool cpu_vendor_string_is(const char *vendor)
{
+ const uint32_t *chunk = (const uint32_t *)vendor;
int eax, ebx, ecx, edx;
- const uint32_t *chunk;
const int leaf = 0;
__asm__ __volatile__(
@@ -1210,10 +1280,22 @@ bool is_intel_cpu(void)
"=c"(ecx), "=d"(edx)
: /* input */ "0"(leaf), "2"(0));
- chunk = (const uint32_t *)("GenuineIntel");
return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]);
}
+bool is_intel_cpu(void)
+{
+ return cpu_vendor_string_is("GenuineIntel");
+}
+
+/*
+ * Exclude early K5 samples with a vendor string of "AMDisbetter!"
+ */
+bool is_amd_cpu(void)
+{
+ return cpu_vendor_string_is("AuthenticAMD");
+}
+
uint32_t kvm_get_cpuid_max_basic(void)
{
return kvm_get_supported_cpuid_entry(0)->eax;
@@ -1337,6 +1419,23 @@ void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
}
}
+struct kvm_cpuid_entry2 *get_cpuid(struct kvm_cpuid2 *cpuid, uint32_t function,
+ uint32_t index)
+{
+ int i;
+
+ for (i = 0; i < cpuid->nent; i++) {
+ struct kvm_cpuid_entry2 *cur = &cpuid->entries[i];
+
+ if (cur->function == function && cur->index == index)
+ return cur;
+ }
+
+ TEST_FAIL("CPUID function 0x%x index 0x%x not found ", function, index);
+
+ return NULL;
+}
+
bool set_cpuid(struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 *ent)
{
@@ -1432,22 +1531,6 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui
return cpuid;
}
-#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
-#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
-#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
-
-static inline unsigned x86_family(unsigned int eax)
-{
- unsigned int x86;
-
- x86 = (eax >> 8) & 0xf;
-
- if (x86 == 0xf)
- x86 += (eax >> 20) & 0xff;
-
- return x86;
-}
-
unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
{
const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */
@@ -1457,11 +1540,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1;
/* Avoid reserved HyperTransport region on AMD processors. */
- eax = ecx = 0;
- cpuid(&eax, &ebx, &ecx, &edx);
- if (ebx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx ||
- ecx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx ||
- edx != X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+ if (!is_amd_cpu())
return max_gfn;
/* On parts with <40 physical address bits, the area is fully hidden */
@@ -1471,6 +1550,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
/* Before family 17h, the HyperTransport area is just below 1T. */
ht_gfn = (1 << 28) - num_ht_pages;
eax = 1;
+ ecx = 0;
cpuid(&eax, &ebx, &ecx, &edx);
if (x86_family(eax) < 0x17)
goto done;
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
new file mode 100644
index 000000000000..52a3ef6629e8
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -0,0 +1,450 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * amx tests
+ *
+ * Copyright (C) 2021, Intel, Inc.
+ *
+ * Tests for amx #NM exception and save/restore.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#ifndef __x86_64__
+# error This test is 64-bit only
+#endif
+
+#define VCPU_ID 0
+#define X86_FEATURE_XSAVE (1 << 26)
+#define X86_FEATURE_OSXSAVE (1 << 27)
+
+#define PAGE_SIZE (1 << 12)
+#define NUM_TILES 8
+#define TILE_SIZE 1024
+#define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE)
+
+/* Tile configuration associated: */
+#define MAX_TILES 16
+#define RESERVED_BYTES 14
+
+#define XFEATURE_XTILECFG 17
+#define XFEATURE_XTILEDATA 18
+#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG)
+#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA)
+#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
+
+#define TILE_CPUID 0x1d
+#define XSTATE_CPUID 0xd
+#define TILE_PALETTE_CPUID_SUBLEAVE 0x1
+#define XSTATE_USER_STATE_SUBLEAVE 0x0
+
+#define XSAVE_HDR_OFFSET 512
+
+struct xsave_data {
+ u8 area[XSAVE_SIZE];
+} __aligned(64);
+
+struct tile_config {
+ u8 palette_id;
+ u8 start_row;
+ u8 reserved[RESERVED_BYTES];
+ u16 colsb[MAX_TILES];
+ u8 rows[MAX_TILES];
+};
+
+struct tile_data {
+ u8 data[NUM_TILES * TILE_SIZE];
+};
+
+struct xtile_info {
+ u16 bytes_per_tile;
+ u16 bytes_per_row;
+ u16 max_names;
+ u16 max_rows;
+ u32 xsave_offset;
+ u32 xsave_size;
+};
+
+static struct xtile_info xtile;
+
+static inline u64 __xgetbv(u32 index)
+{
+ u32 eax, edx;
+
+ asm volatile("xgetbv;"
+ : "=a" (eax), "=d" (edx)
+ : "c" (index));
+ return eax + ((u64)edx << 32);
+}
+
+static inline void __xsetbv(u32 index, u64 value)
+{
+ u32 eax = value;
+ u32 edx = value >> 32;
+
+ asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
+}
+
+static inline void __ldtilecfg(void *cfg)
+{
+ asm volatile(".byte 0xc4,0xe2,0x78,0x49,0x00"
+ : : "a"(cfg));
+}
+
+static inline void __tileloadd(void *tile)
+{
+ asm volatile(".byte 0xc4,0xe2,0x7b,0x4b,0x04,0x10"
+ : : "a"(tile), "d"(0));
+}
+
+static inline void __tilerelease(void)
+{
+ asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0" ::);
+}
+
+static inline void __xsavec(struct xsave_data *data, uint64_t rfbm)
+{
+ uint32_t rfbm_lo = rfbm;
+ uint32_t rfbm_hi = rfbm >> 32;
+
+ asm volatile("xsavec (%%rdi)"
+ : : "D" (data), "a" (rfbm_lo), "d" (rfbm_hi)
+ : "memory");
+}
+
+static inline void check_cpuid_xsave(void)
+{
+ uint32_t eax, ebx, ecx, edx;
+
+ eax = 1;
+ ecx = 0;
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (!(ecx & X86_FEATURE_XSAVE))
+ GUEST_ASSERT(!"cpuid: no CPU xsave support!");
+ if (!(ecx & X86_FEATURE_OSXSAVE))
+ GUEST_ASSERT(!"cpuid: no OS xsave support!");
+}
+
+static bool check_xsave_supports_xtile(void)
+{
+ return __xgetbv(0) & XFEATURE_MASK_XTILE;
+}
+
+static bool enum_xtile_config(void)
+{
+ u32 eax, ebx, ecx, edx;
+
+ eax = TILE_CPUID;
+ ecx = TILE_PALETTE_CPUID_SUBLEAVE;
+
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (!eax || !ebx || !ecx)
+ return false;
+
+ xtile.max_names = ebx >> 16;
+ if (xtile.max_names < NUM_TILES)
+ return false;
+
+ xtile.bytes_per_tile = eax >> 16;
+ if (xtile.bytes_per_tile < TILE_SIZE)
+ return false;
+
+ xtile.bytes_per_row = ebx;
+ xtile.max_rows = ecx;
+
+ return true;
+}
+
+static bool enum_xsave_tile(void)
+{
+ u32 eax, ebx, ecx, edx;
+
+ eax = XSTATE_CPUID;
+ ecx = XFEATURE_XTILEDATA;
+
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (!eax || !ebx)
+ return false;
+
+ xtile.xsave_offset = ebx;
+ xtile.xsave_size = eax;
+
+ return true;
+}
+
+static bool check_xsave_size(void)
+{
+ u32 eax, ebx, ecx, edx;
+ bool valid = false;
+
+ eax = XSTATE_CPUID;
+ ecx = XSTATE_USER_STATE_SUBLEAVE;
+
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (ebx && ebx <= XSAVE_SIZE)
+ valid = true;
+
+ return valid;
+}
+
+static bool check_xtile_info(void)
+{
+ bool ret = false;
+
+ if (!check_xsave_size())
+ return ret;
+
+ if (!enum_xsave_tile())
+ return ret;
+
+ if (!enum_xtile_config())
+ return ret;
+
+ if (sizeof(struct tile_data) >= xtile.xsave_size)
+ ret = true;
+
+ return ret;
+}
+
+static void set_tilecfg(struct tile_config *cfg)
+{
+ int i;
+
+ /* Only palette id 1 */
+ cfg->palette_id = 1;
+ for (i = 0; i < xtile.max_names; i++) {
+ cfg->colsb[i] = xtile.bytes_per_row;
+ cfg->rows[i] = xtile.max_rows;
+ }
+}
+
+static void set_xstatebv(void *data, uint64_t bv)
+{
+ *(uint64_t *)(data + XSAVE_HDR_OFFSET) = bv;
+}
+
+static u64 get_xstatebv(void *data)
+{
+ return *(u64 *)(data + XSAVE_HDR_OFFSET);
+}
+
+static void init_regs(void)
+{
+ uint64_t cr4, xcr0;
+
+ /* turn on CR4.OSXSAVE */
+ cr4 = get_cr4();
+ cr4 |= X86_CR4_OSXSAVE;
+ set_cr4(cr4);
+
+ xcr0 = __xgetbv(0);
+ xcr0 |= XFEATURE_MASK_XTILE;
+ __xsetbv(0x0, xcr0);
+}
+
+static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg,
+ struct tile_data *tiledata,
+ struct xsave_data *xsave_data)
+{
+ init_regs();
+ check_cpuid_xsave();
+ GUEST_ASSERT(check_xsave_supports_xtile());
+ GUEST_ASSERT(check_xtile_info());
+
+ /* check xtile configs */
+ GUEST_ASSERT(xtile.xsave_offset == 2816);
+ GUEST_ASSERT(xtile.xsave_size == 8192);
+ GUEST_ASSERT(xtile.max_names == 8);
+ GUEST_ASSERT(xtile.bytes_per_tile == 1024);
+ GUEST_ASSERT(xtile.bytes_per_row == 64);
+ GUEST_ASSERT(xtile.max_rows == 16);
+ GUEST_SYNC(1);
+
+ /* xfd=0, enable amx */
+ wrmsr(MSR_IA32_XFD, 0);
+ GUEST_SYNC(2);
+ GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == 0);
+ set_tilecfg(amx_cfg);
+ __ldtilecfg(amx_cfg);
+ GUEST_SYNC(3);
+ /* Check save/restore when trap to userspace */
+ __tileloadd(tiledata);
+ GUEST_SYNC(4);
+ __tilerelease();
+ GUEST_SYNC(5);
+ /* bit 18 not in the XCOMP_BV after xsavec() */
+ set_xstatebv(xsave_data, XFEATURE_MASK_XTILEDATA);
+ __xsavec(xsave_data, XFEATURE_MASK_XTILEDATA);
+ GUEST_ASSERT((get_xstatebv(xsave_data) & XFEATURE_MASK_XTILEDATA) == 0);
+
+ /* xfd=0x40000, disable amx tiledata */
+ wrmsr(MSR_IA32_XFD, XFEATURE_MASK_XTILEDATA);
+ GUEST_SYNC(6);
+ GUEST_ASSERT(rdmsr(MSR_IA32_XFD) == XFEATURE_MASK_XTILEDATA);
+ set_tilecfg(amx_cfg);
+ __ldtilecfg(amx_cfg);
+ /* Trigger #NM exception */
+ __tileloadd(tiledata);
+ GUEST_SYNC(10);
+
+ GUEST_DONE();
+}
+
+void guest_nm_handler(struct ex_regs *regs)
+{
+ /* Check if #NM is triggered by XFEATURE_MASK_XTILEDATA */
+ GUEST_SYNC(7);
+ GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA);
+ GUEST_SYNC(8);
+ GUEST_ASSERT(rdmsr(MSR_IA32_XFD_ERR) == XFEATURE_MASK_XTILEDATA);
+ /* Clear xfd_err */
+ wrmsr(MSR_IA32_XFD_ERR, 0);
+ /* xfd=0, enable amx */
+ wrmsr(MSR_IA32_XFD, 0);
+ GUEST_SYNC(9);
+}
+
+int main(int argc, char *argv[])
+{
+ struct kvm_cpuid_entry2 *entry;
+ struct kvm_regs regs1, regs2;
+ bool amx_supported = false;
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ struct kvm_x86_state *state;
+ int xsave_restore_size = 0;
+ vm_vaddr_t amx_cfg, tiledata, xsavedata;
+ struct ucall uc;
+ u32 amx_offset;
+ int stage, ret;
+
+ vm_xsave_req_perm(XSTATE_XTILE_DATA_BIT);
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ entry = kvm_get_supported_cpuid_entry(1);
+ if (!(entry->ecx & X86_FEATURE_XSAVE)) {
+ print_skip("XSAVE feature not supported");
+ exit(KSFT_SKIP);
+ }
+
+ if (kvm_get_cpuid_max_basic() >= 0xd) {
+ entry = kvm_get_supported_cpuid_index(0xd, 0);
+ amx_supported = entry && !!(entry->eax & XFEATURE_MASK_XTILE);
+ if (!amx_supported) {
+ print_skip("AMX is not supported by the vCPU (eax=0x%x)", entry->eax);
+ exit(KSFT_SKIP);
+ }
+ /* Get xsave/restore max size */
+ xsave_restore_size = entry->ecx;
+ }
+
+ run = vcpu_state(vm, VCPU_ID);
+ vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+ /* Register #NM handler */
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+ vm_install_exception_handler(vm, NM_VECTOR, guest_nm_handler);
+
+ /* amx cfg for guest_code */
+ amx_cfg = vm_vaddr_alloc_page(vm);
+ memset(addr_gva2hva(vm, amx_cfg), 0x0, getpagesize());
+
+ /* amx tiledata for guest_code */
+ tiledata = vm_vaddr_alloc_pages(vm, 2);
+ memset(addr_gva2hva(vm, tiledata), rand() | 1, 2 * getpagesize());
+
+ /* xsave data for guest_code */
+ xsavedata = vm_vaddr_alloc_pages(vm, 3);
+ memset(addr_gva2hva(vm, xsavedata), 0, 3 * getpagesize());
+ vcpu_args_set(vm, VCPU_ID, 3, amx_cfg, tiledata, xsavedata);
+
+ for (stage = 1; ; stage++) {
+ _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Stage %d: unexpected exit reason: %u (%s),\n",
+ stage, run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
+ /* NOT REACHED */
+ case UCALL_SYNC:
+ switch (uc.args[1]) {
+ case 1:
+ case 2:
+ case 3:
+ case 5:
+ case 6:
+ case 7:
+ case 8:
+ fprintf(stderr, "GUEST_SYNC(%ld)\n", uc.args[1]);
+ break;
+ case 4:
+ case 10:
+ fprintf(stderr,
+ "GUEST_SYNC(%ld), check save/restore status\n", uc.args[1]);
+
+ /* Compacted mode, get amx offset by xsave area
+ * size subtract 8K amx size.
+ */
+ amx_offset = xsave_restore_size - NUM_TILES*TILE_SIZE;
+ state = vcpu_save_state(vm, VCPU_ID);
+ void *amx_start = (void *)state->xsave + amx_offset;
+ void *tiles_data = (void *)addr_gva2hva(vm, tiledata);
+ /* Only check TMM0 register, 1 tile */
+ ret = memcmp(amx_start, tiles_data, TILE_SIZE);
+ TEST_ASSERT(ret == 0, "memcmp failed, ret=%d\n", ret);
+ kvm_x86_state_cleanup(state);
+ break;
+ case 9:
+ fprintf(stderr,
+ "GUEST_SYNC(%ld), #NM exception and enable amx\n", uc.args[1]);
+ break;
+ }
+ break;
+ case UCALL_DONE:
+ fprintf(stderr, "UCALL_DONE\n");
+ goto done;
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ }
+
+ state = vcpu_save_state(vm, VCPU_ID);
+ memset(&regs1, 0, sizeof(regs1));
+ vcpu_regs_get(vm, VCPU_ID, &regs1);
+
+ kvm_vm_release(vm);
+
+ /* Restore state in a new VM. */
+ kvm_vm_restart(vm, O_RDWR);
+ vm_vcpu_add(vm, VCPU_ID);
+ vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+ vcpu_load_state(vm, VCPU_ID, state);
+ run = vcpu_state(vm, VCPU_ID);
+ kvm_x86_state_cleanup(state);
+
+ memset(&regs2, 0, sizeof(regs2));
+ vcpu_regs_get(vm, VCPU_ID, &regs2);
+ TEST_ASSERT(!memcmp(&regs1, &regs2, sizeof(regs2)),
+ "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx",
+ (ulong) regs2.rdi, (ulong) regs2.rsi);
+ }
+done:
+ kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
index a711f83749ea..16d2465c5634 100644
--- a/tools/testing/selftests/kvm/x86_64/get_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
@@ -154,6 +154,34 @@ struct kvm_cpuid2 *vcpu_alloc_cpuid(struct kvm_vm *vm, vm_vaddr_t *p_gva, struct
return guest_cpuids;
}
+static void set_cpuid_after_run(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid)
+{
+ struct kvm_cpuid_entry2 *ent;
+ int rc;
+ u32 eax, ebx, x;
+
+ /* Setting unmodified CPUID is allowed */
+ rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+ TEST_ASSERT(!rc, "Setting unmodified CPUID after KVM_RUN failed: %d", rc);
+
+ /* Changing CPU features is forbidden */
+ ent = get_cpuid(cpuid, 0x7, 0);
+ ebx = ent->ebx;
+ ent->ebx--;
+ rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+ TEST_ASSERT(rc, "Changing CPU features should fail");
+ ent->ebx = ebx;
+
+ /* Changing MAXPHYADDR is forbidden */
+ ent = get_cpuid(cpuid, 0x80000008, 0);
+ eax = ent->eax;
+ x = eax & 0xff;
+ ent->eax = (eax & ~0xffu) | (x - 1);
+ rc = __vcpu_set_cpuid(vm, VCPU_ID, cpuid);
+ TEST_ASSERT(rc, "Changing MAXPHYADDR should fail");
+ ent->eax = eax;
+}
+
int main(void)
{
struct kvm_cpuid2 *supp_cpuid, *cpuid2;
@@ -175,5 +203,7 @@ int main(void)
for (stage = 0; stage < 3; stage++)
run_vcpu(vm, VCPU_ID, stage);
+ set_cpuid_after_run(vm, cpuid2);
+
kvm_vm_free(vm);
}
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index 2b46dcca86a8..4c7841dfd481 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -129,7 +129,7 @@ static void save_restore_vm(struct kvm_vm *vm)
vcpu_set_hv_cpuid(vm, VCPU_ID);
vcpu_enable_evmcs(vm, VCPU_ID);
vcpu_load_state(vm, VCPU_ID, state);
- free(state);
+ kvm_x86_state_cleanup(state);
memset(&regs2, 0, sizeof(regs2));
vcpu_regs_get(vm, VCPU_ID, &regs2);
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
new file mode 100644
index 000000000000..c715adcbd487
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -0,0 +1,434 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for x86 KVM_SET_PMU_EVENT_FILTER.
+ *
+ * Copyright (C) 2022, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Verifies the expected behavior of allow lists and deny lists for
+ * virtual PMU events.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+/*
+ * In lieu of copying perf_event.h into tools...
+ */
+#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17)
+#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22)
+
+union cpuid10_eax {
+ struct {
+ unsigned int version_id:8;
+ unsigned int num_counters:8;
+ unsigned int bit_width:8;
+ unsigned int mask_length:8;
+ } split;
+ unsigned int full;
+};
+
+union cpuid10_ebx {
+ struct {
+ unsigned int no_unhalted_core_cycles:1;
+ unsigned int no_instructions_retired:1;
+ unsigned int no_unhalted_reference_cycles:1;
+ unsigned int no_llc_reference:1;
+ unsigned int no_llc_misses:1;
+ unsigned int no_branch_instruction_retired:1;
+ unsigned int no_branch_misses_retired:1;
+ } split;
+ unsigned int full;
+};
+
+/* End of stuff taken from perf_event.h. */
+
+/* Oddly, this isn't in perf_event.h. */
+#define ARCH_PERFMON_BRANCHES_RETIRED 5
+
+#define VCPU_ID 0
+#define NUM_BRANCHES 42
+
+/*
+ * This is how the event selector and unit mask are stored in an AMD
+ * core performance event-select register. Intel's format is similar,
+ * but the event selector is only 8 bits.
+ */
+#define EVENT(select, umask) ((select & 0xf00UL) << 24 | (select & 0xff) | \
+ (umask & 0xff) << 8)
+
+/*
+ * "Branch instructions retired", from the Intel SDM, volume 3,
+ * "Pre-defined Architectural Performance Events."
+ */
+
+#define INTEL_BR_RETIRED EVENT(0xc4, 0)
+
+/*
+ * "Retired branch instructions", from Processor Programming Reference
+ * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors,
+ * Preliminary Processor Programming Reference (PPR) for AMD Family
+ * 17h Model 31h, Revision B0 Processors, and Preliminary Processor
+ * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision
+ * B1 Processors Volume 1 of 2.
+ */
+
+#define AMD_ZEN_BR_RETIRED EVENT(0xc2, 0)
+
+/*
+ * This event list comprises Intel's eight architectural events plus
+ * AMD's "retired branch instructions" for Zen[123] (and possibly
+ * other AMD CPUs).
+ */
+static const uint64_t event_list[] = {
+ EVENT(0x3c, 0),
+ EVENT(0xc0, 0),
+ EVENT(0x3c, 1),
+ EVENT(0x2e, 0x4f),
+ EVENT(0x2e, 0x41),
+ EVENT(0xc4, 0),
+ EVENT(0xc5, 0),
+ EVENT(0xa4, 1),
+ AMD_ZEN_BR_RETIRED,
+};
+
+/*
+ * If we encounter a #GP during the guest PMU sanity check, then the guest
+ * PMU is not functional. Inform the hypervisor via GUEST_SYNC(0).
+ */
+static void guest_gp_handler(struct ex_regs *regs)
+{
+ GUEST_SYNC(0);
+}
+
+/*
+ * Check that we can write a new value to the given MSR and read it back.
+ * The caller should provide a non-empty set of bits that are safe to flip.
+ *
+ * Return on success. GUEST_SYNC(0) on error.
+ */
+static void check_msr(uint32_t msr, uint64_t bits_to_flip)
+{
+ uint64_t v = rdmsr(msr) ^ bits_to_flip;
+
+ wrmsr(msr, v);
+ if (rdmsr(msr) != v)
+ GUEST_SYNC(0);
+
+ v ^= bits_to_flip;
+ wrmsr(msr, v);
+ if (rdmsr(msr) != v)
+ GUEST_SYNC(0);
+}
+
+static void intel_guest_code(void)
+{
+ check_msr(MSR_CORE_PERF_GLOBAL_CTRL, 1);
+ check_msr(MSR_P6_EVNTSEL0, 0xffff);
+ check_msr(MSR_IA32_PMC0, 0xffff);
+ GUEST_SYNC(1);
+
+ for (;;) {
+ uint64_t br0, br1;
+
+ wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+ wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE |
+ ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED);
+ wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 1);
+ br0 = rdmsr(MSR_IA32_PMC0);
+ __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+ br1 = rdmsr(MSR_IA32_PMC0);
+ GUEST_SYNC(br1 - br0);
+ }
+}
+
+/*
+ * To avoid needing a check for CPUID.80000001:ECX.PerfCtrExtCore[bit 23],
+ * this code uses the always-available, legacy K7 PMU MSRs, which alias to
+ * the first four of the six extended core PMU MSRs.
+ */
+static void amd_guest_code(void)
+{
+ check_msr(MSR_K7_EVNTSEL0, 0xffff);
+ check_msr(MSR_K7_PERFCTR0, 0xffff);
+ GUEST_SYNC(1);
+
+ for (;;) {
+ uint64_t br0, br1;
+
+ wrmsr(MSR_K7_EVNTSEL0, 0);
+ wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE |
+ ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED);
+ br0 = rdmsr(MSR_K7_PERFCTR0);
+ __asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+ br1 = rdmsr(MSR_K7_PERFCTR0);
+ GUEST_SYNC(br1 - br0);
+ }
+}
+
+/*
+ * Run the VM to the next GUEST_SYNC(value), and return the value passed
+ * to the sync. Any other exit from the guest is fatal.
+ */
+static uint64_t run_vm_to_sync(struct kvm_vm *vm)
+{
+ struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+ struct ucall uc;
+
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Exit_reason other than KVM_EXIT_IO: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+ get_ucall(vm, VCPU_ID, &uc);
+ TEST_ASSERT(uc.cmd == UCALL_SYNC,
+ "Received ucall other than UCALL_SYNC: %lu", uc.cmd);
+ return uc.args[1];
+}
+
+/*
+ * In a nested environment or if the vPMU is disabled, the guest PMU
+ * might not work as architected (accessing the PMU MSRs may raise
+ * #GP, or writes could simply be discarded). In those situations,
+ * there is no point in running these tests. The guest code will perform
+ * a sanity check and then GUEST_SYNC(success). In the case of failure,
+ * the behavior of the guest on resumption is undefined.
+ */
+static bool sanity_check_pmu(struct kvm_vm *vm)
+{
+ bool success;
+
+ vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
+ success = run_vm_to_sync(vm);
+ vm_install_exception_handler(vm, GP_VECTOR, NULL);
+
+ return success;
+}
+
+static struct kvm_pmu_event_filter *make_pmu_event_filter(uint32_t nevents)
+{
+ struct kvm_pmu_event_filter *f;
+ int size = sizeof(*f) + nevents * sizeof(f->events[0]);
+
+ f = malloc(size);
+ TEST_ASSERT(f, "Out of memory");
+ memset(f, 0, size);
+ f->nevents = nevents;
+ return f;
+}
+
+static struct kvm_pmu_event_filter *event_filter(uint32_t action)
+{
+ struct kvm_pmu_event_filter *f;
+ int i;
+
+ f = make_pmu_event_filter(ARRAY_SIZE(event_list));
+ f->action = action;
+ for (i = 0; i < ARRAY_SIZE(event_list); i++)
+ f->events[i] = event_list[i];
+
+ return f;
+}
+
+/*
+ * Remove the first occurrence of 'event' (if any) from the filter's
+ * event list.
+ */
+static struct kvm_pmu_event_filter *remove_event(struct kvm_pmu_event_filter *f,
+ uint64_t event)
+{
+ bool found = false;
+ int i;
+
+ for (i = 0; i < f->nevents; i++) {
+ if (found)
+ f->events[i - 1] = f->events[i];
+ else
+ found = f->events[i] == event;
+ }
+ if (found)
+ f->nevents--;
+ return f;
+}
+
+static void test_without_filter(struct kvm_vm *vm)
+{
+ uint64_t count = run_vm_to_sync(vm);
+
+ if (count != NUM_BRANCHES)
+ pr_info("%s: Branch instructions retired = %lu (expected %u)\n",
+ __func__, count, NUM_BRANCHES);
+ TEST_ASSERT(count, "Allowed PMU event is not counting");
+}
+
+static uint64_t test_with_filter(struct kvm_vm *vm,
+ struct kvm_pmu_event_filter *f)
+{
+ vm_ioctl(vm, KVM_SET_PMU_EVENT_FILTER, (void *)f);
+ return run_vm_to_sync(vm);
+}
+
+static void test_member_deny_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY);
+ uint64_t count = test_with_filter(vm, f);
+
+ free(f);
+ if (count)
+ pr_info("%s: Branch instructions retired = %lu (expected 0)\n",
+ __func__, count);
+ TEST_ASSERT(!count, "Disallowed PMU Event is counting");
+}
+
+static void test_member_allow_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW);
+ uint64_t count = test_with_filter(vm, f);
+
+ free(f);
+ if (count != NUM_BRANCHES)
+ pr_info("%s: Branch instructions retired = %lu (expected %u)\n",
+ __func__, count, NUM_BRANCHES);
+ TEST_ASSERT(count, "Allowed PMU event is not counting");
+}
+
+static void test_not_member_deny_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY);
+ uint64_t count;
+
+ remove_event(f, INTEL_BR_RETIRED);
+ remove_event(f, AMD_ZEN_BR_RETIRED);
+ count = test_with_filter(vm, f);
+ free(f);
+ if (count != NUM_BRANCHES)
+ pr_info("%s: Branch instructions retired = %lu (expected %u)\n",
+ __func__, count, NUM_BRANCHES);
+ TEST_ASSERT(count, "Allowed PMU event is not counting");
+}
+
+static void test_not_member_allow_list(struct kvm_vm *vm)
+{
+ struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_ALLOW);
+ uint64_t count;
+
+ remove_event(f, INTEL_BR_RETIRED);
+ remove_event(f, AMD_ZEN_BR_RETIRED);
+ count = test_with_filter(vm, f);
+ free(f);
+ if (count)
+ pr_info("%s: Branch instructions retired = %lu (expected 0)\n",
+ __func__, count);
+ TEST_ASSERT(!count, "Disallowed PMU Event is counting");
+}
+
+/*
+ * Check for a non-zero PMU version, at least one general-purpose
+ * counter per logical processor, an EBX bit vector of length greater
+ * than 5, and EBX[5] clear.
+ */
+static bool check_intel_pmu_leaf(struct kvm_cpuid_entry2 *entry)
+{
+ union cpuid10_eax eax = { .full = entry->eax };
+ union cpuid10_ebx ebx = { .full = entry->ebx };
+
+ return eax.split.version_id && eax.split.num_counters > 0 &&
+ eax.split.mask_length > ARCH_PERFMON_BRANCHES_RETIRED &&
+ !ebx.split.no_branch_instruction_retired;
+}
+
+/*
+ * Note that CPUID leaf 0xa is Intel-specific. This leaf should be
+ * clear on AMD hardware.
+ */
+static bool use_intel_pmu(void)
+{
+ struct kvm_cpuid_entry2 *entry;
+
+ entry = kvm_get_supported_cpuid_index(0xa, 0);
+ return is_intel_cpu() && entry && check_intel_pmu_leaf(entry);
+}
+
+static bool is_zen1(uint32_t eax)
+{
+ return x86_family(eax) == 0x17 && x86_model(eax) <= 0x0f;
+}
+
+static bool is_zen2(uint32_t eax)
+{
+ return x86_family(eax) == 0x17 &&
+ x86_model(eax) >= 0x30 && x86_model(eax) <= 0x3f;
+}
+
+static bool is_zen3(uint32_t eax)
+{
+ return x86_family(eax) == 0x19 && x86_model(eax) <= 0x0f;
+}
+
+/*
+ * Determining AMD support for a PMU event requires consulting the AMD
+ * PPR for the CPU or reference material derived therefrom. The AMD
+ * test code herein has been verified to work on Zen1, Zen2, and Zen3.
+ *
+ * Feel free to add more AMD CPUs that are documented to support event
+ * select 0xc2 umask 0 as "retired branch instructions."
+ */
+static bool use_amd_pmu(void)
+{
+ struct kvm_cpuid_entry2 *entry;
+
+ entry = kvm_get_supported_cpuid_index(1, 0);
+ return is_amd_cpu() && entry &&
+ (is_zen1(entry->eax) ||
+ is_zen2(entry->eax) ||
+ is_zen3(entry->eax));
+}
+
+int main(int argc, char *argv[])
+{
+ void (*guest_code)(void) = NULL;
+ struct kvm_vm *vm;
+ int r;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ r = kvm_check_cap(KVM_CAP_PMU_EVENT_FILTER);
+ if (!r) {
+ print_skip("KVM_CAP_PMU_EVENT_FILTER not supported");
+ exit(KSFT_SKIP);
+ }
+
+ if (use_intel_pmu())
+ guest_code = intel_guest_code;
+ else if (use_amd_pmu())
+ guest_code = amd_guest_code;
+
+ if (!guest_code) {
+ print_skip("Don't know how to test this guest PMU");
+ exit(KSFT_SKIP);
+ }
+
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+ if (!sanity_check_pmu(vm)) {
+ print_skip("Guest PMU is not functional");
+ exit(KSFT_SKIP);
+ }
+
+ test_without_filter(vm);
+ test_member_deny_list(vm);
+ test_member_allow_list(vm);
+ test_not_member_deny_list(vm);
+ test_not_member_allow_list(vm);
+
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
index 29b18d565cf4..80056bbbb003 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -21,7 +21,7 @@
#define NR_LOCK_TESTING_THREADS 3
#define NR_LOCK_TESTING_ITERATIONS 10000
-static void sev_ioctl(int vm_fd, int cmd_id, void *data)
+static int __sev_ioctl(int vm_fd, int cmd_id, void *data, __u32 *fw_error)
{
struct kvm_sev_cmd cmd = {
.id = cmd_id,
@@ -31,9 +31,19 @@ static void sev_ioctl(int vm_fd, int cmd_id, void *data)
int ret;
ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd);
- TEST_ASSERT((ret == 0 || cmd.error == SEV_RET_SUCCESS),
+ *fw_error = cmd.error;
+ return ret;
+}
+
+static void sev_ioctl(int vm_fd, int cmd_id, void *data)
+{
+ int ret;
+ __u32 fw_error;
+
+ ret = __sev_ioctl(vm_fd, cmd_id, data, &fw_error);
+ TEST_ASSERT(ret == 0 && fw_error == SEV_RET_SUCCESS,
"%d failed: return code: %d, errno: %d, fw error: %d",
- cmd_id, ret, errno, cmd.error);
+ cmd_id, ret, errno, fw_error);
}
static struct kvm_vm *sev_vm_create(bool es)
@@ -225,12 +235,45 @@ static void sev_mirror_create(int dst_fd, int src_fd)
TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d\n", ret, errno);
}
+static void verify_mirror_allowed_cmds(int vm_fd)
+{
+ struct kvm_sev_guest_status status;
+
+ for (int cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) {
+ int ret;
+ __u32 fw_error;
+
+ /*
+ * These commands are allowed for mirror VMs, all others are
+ * not.
+ */
+ switch (cmd_id) {
+ case KVM_SEV_LAUNCH_UPDATE_VMSA:
+ case KVM_SEV_GUEST_STATUS:
+ case KVM_SEV_DBG_DECRYPT:
+ case KVM_SEV_DBG_ENCRYPT:
+ continue;
+ default:
+ break;
+ }
+
+ /*
+ * These commands should be disallowed before the data
+ * parameter is examined so NULL is OK here.
+ */
+ ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error);
+ TEST_ASSERT(
+ ret == -1 && errno == EINVAL,
+ "Should not be able call command: %d. ret: %d, errno: %d\n",
+ cmd_id, ret, errno);
+ }
+
+ sev_ioctl(vm_fd, KVM_SEV_GUEST_STATUS, &status);
+}
+
static void test_sev_mirror(bool es)
{
struct kvm_vm *src_vm, *dst_vm;
- struct kvm_sev_launch_start start = {
- .policy = es ? SEV_POLICY_ES : 0
- };
int i;
src_vm = sev_vm_create(es);
@@ -241,10 +284,12 @@ static void test_sev_mirror(bool es)
/* Check that we can complete creation of the mirror VM. */
for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i)
vm_vcpu_add(dst_vm, i);
- sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_START, &start);
+
if (es)
sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+ verify_mirror_allowed_cmds(dst_vm->fd);
+
kvm_vm_free(src_vm);
kvm_vm_free(dst_vm);
}
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index d0fe2fdce58c..a626d40fdb48 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -105,7 +105,6 @@ static void guest_code(void *arg)
if (cpu_has_svm()) {
run_guest(svm->vmcb, svm->vmcb_gpa);
- svm->vmcb->save.rip += 3;
run_guest(svm->vmcb, svm->vmcb_gpa);
} else {
vmlaunch();
@@ -212,7 +211,7 @@ int main(int argc, char *argv[])
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
vcpu_load_state(vm, VCPU_ID, state);
run = vcpu_state(vm, VCPU_ID);
- free(state);
+ kvm_x86_state_cleanup(state);
}
done:
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 32854c1462ad..2e0a92da8ff5 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -218,7 +218,7 @@ int main(int argc, char *argv[])
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
vcpu_load_state(vm, VCPU_ID, state);
run = vcpu_state(vm, VCPU_ID);
- free(state);
+ kvm_x86_state_cleanup(state);
memset(&regs2, 0, sizeof(regs2));
vcpu_regs_get(vm, VCPU_ID, &regs2);
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
index 5a6a662f2e59..a426078b16a3 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
@@ -77,8 +77,8 @@ static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage)
switch (get_ucall(vm, vcpuid, &uc)) {
case UCALL_SYNC:
TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
- uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx",
- stage + 1, (ulong)uc.args[1]);
+ uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx",
+ stage + 1, (ulong)uc.args[1]);
return;
case UCALL_DONE:
return;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
index 2835a17f1b7a..edac8839e717 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
@@ -30,8 +30,8 @@ static struct kvm_vm *vm;
static void l2_guest_code(void)
{
/* Exit to L0 */
- asm volatile("inb %%dx, %%al"
- : : [port] "d" (PORT_L0_EXIT) : "rax");
+ asm volatile("inb %%dx, %%al"
+ : : [port] "d" (PORT_L0_EXIT) : "rax");
}
static void l1_guest_code(struct vmx_pages *vmx_pages)
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
new file mode 100644
index 000000000000..27a850f3d7ce
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#include <signal.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+
+#include "kselftest.h"
+
+#define VCPU_ID 0
+
+static struct kvm_vm *vm;
+
+static void guest_ud_handler(struct ex_regs *regs)
+{
+ /* Loop on the ud2 until guest state is made invalid. */
+}
+
+static void guest_code(void)
+{
+ asm volatile("ud2");
+}
+
+static void __run_vcpu_with_invalid_state(void)
+{
+ struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+ vcpu_run(vm, VCPU_ID);
+
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
+ "Expected KVM_EXIT_INTERNAL_ERROR, got %d (%s)\n",
+ run->exit_reason, exit_reason_str(run->exit_reason));
+ TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
+ "Expected emulation failure, got %d\n",
+ run->emulation_failure.suberror);
+}
+
+static void run_vcpu_with_invalid_state(void)
+{
+ /*
+ * Always run twice to verify KVM handles the case where _KVM_ queues
+ * an exception with invalid state and then exits to userspace, i.e.
+ * that KVM doesn't explode if userspace ignores the initial error.
+ */
+ __run_vcpu_with_invalid_state();
+ __run_vcpu_with_invalid_state();
+}
+
+static void set_timer(void)
+{
+ struct itimerval timer;
+
+ timer.it_value.tv_sec = 0;
+ timer.it_value.tv_usec = 200;
+ timer.it_interval = timer.it_value;
+ ASSERT_EQ(setitimer(ITIMER_REAL, &timer, NULL), 0);
+}
+
+static void set_or_clear_invalid_guest_state(bool set)
+{
+ static struct kvm_sregs sregs;
+
+ if (!sregs.cr0)
+ vcpu_sregs_get(vm, VCPU_ID, &sregs);
+ sregs.tr.unusable = !!set;
+ vcpu_sregs_set(vm, VCPU_ID, &sregs);
+}
+
+static void set_invalid_guest_state(void)
+{
+ set_or_clear_invalid_guest_state(true);
+}
+
+static void clear_invalid_guest_state(void)
+{
+ set_or_clear_invalid_guest_state(false);
+}
+
+static void sigalrm_handler(int sig)
+{
+ struct kvm_vcpu_events events;
+
+ TEST_ASSERT(sig == SIGALRM, "Unexpected signal = %d", sig);
+
+ vcpu_events_get(vm, VCPU_ID, &events);
+
+ /*
+ * If an exception is pending, attempt KVM_RUN with invalid guest,
+ * otherwise rearm the timer and keep doing so until the timer fires
+ * between KVM queueing an exception and re-entering the guest.
+ */
+ if (events.exception.pending) {
+ set_invalid_guest_state();
+ run_vcpu_with_invalid_state();
+ } else {
+ set_timer();
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ if (!is_intel_cpu() || vm_is_unrestricted_guest(NULL)) {
+ print_skip("Must be run with kvm_intel.unrestricted_guest=0");
+ exit(KSFT_SKIP);
+ }
+
+ vm = vm_create_default(VCPU_ID, 0, (void *)guest_code);
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+ vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+
+ /*
+ * Stuff invalid guest state for L2 by making TR unusuable. The next
+ * KVM_RUN should induce a TRIPLE_FAULT in L2 as KVM doesn't support
+ * emulating invalid guest state for L2.
+ */
+ set_invalid_guest_state();
+ run_vcpu_with_invalid_state();
+
+ /*
+ * Verify KVM also handles the case where userspace gains control while
+ * an exception is pending and stuffs invalid state. Run with valid
+ * guest state and a timer firing every 200us, and attempt to enter the
+ * guest with invalid state when the handler interrupts KVM with an
+ * exception pending.
+ */
+ clear_invalid_guest_state();
+ TEST_ASSERT(signal(SIGALRM, sigalrm_handler) != SIG_ERR,
+ "Failed to register SIGALRM handler, errno = %d (%s)",
+ errno, strerror(errno));
+
+ set_timer();
+ run_vcpu_with_invalid_state();
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
index a07480aed397..ff92e25b6f1e 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
@@ -244,7 +244,7 @@ int main(int argc, char *argv[])
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
vcpu_load_state(vm, VCPU_ID, state);
run = vcpu_state(vm, VCPU_ID);
- free(state);
+ kvm_x86_state_cleanup(state);
memset(&regs2, 0, sizeof(regs2));
vcpu_regs_get(vm, VCPU_ID, &regs2);
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index a0699f00b3d6..865e17146815 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -14,6 +14,9 @@
#include <stdint.h>
#include <time.h>
#include <sched.h>
+#include <signal.h>
+
+#include <sys/eventfd.h>
#define VCPU_ID 5
@@ -22,10 +25,15 @@
#define SHINFO_REGION_SLOT 10
#define PAGE_SIZE 4096
+#define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE))
+#define DUMMY_REGION_SLOT 11
+
+#define SHINFO_ADDR (SHINFO_REGION_GPA)
#define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE)
#define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20)
#define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40)
+#define SHINFO_VADDR (SHINFO_REGION_GVA)
#define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20)
#define VCPU_INFO_VADDR (SHINFO_REGION_GVA + 0x40)
@@ -38,20 +46,20 @@ static struct kvm_vm *vm;
#define MIN_STEAL_TIME 50000
struct pvclock_vcpu_time_info {
- u32 version;
- u32 pad0;
- u64 tsc_timestamp;
- u64 system_time;
- u32 tsc_to_system_mul;
- s8 tsc_shift;
- u8 flags;
- u8 pad[2];
+ u32 version;
+ u32 pad0;
+ u64 tsc_timestamp;
+ u64 system_time;
+ u32 tsc_to_system_mul;
+ s8 tsc_shift;
+ u8 flags;
+ u8 pad[2];
} __attribute__((__packed__)); /* 32 bytes */
struct pvclock_wall_clock {
- u32 version;
- u32 sec;
- u32 nsec;
+ u32 version;
+ u32 sec;
+ u32 nsec;
} __attribute__((__packed__));
struct vcpu_runstate_info {
@@ -66,22 +74,44 @@ struct arch_vcpu_info {
};
struct vcpu_info {
- uint8_t evtchn_upcall_pending;
- uint8_t evtchn_upcall_mask;
- unsigned long evtchn_pending_sel;
- struct arch_vcpu_info arch;
- struct pvclock_vcpu_time_info time;
+ uint8_t evtchn_upcall_pending;
+ uint8_t evtchn_upcall_mask;
+ unsigned long evtchn_pending_sel;
+ struct arch_vcpu_info arch;
+ struct pvclock_vcpu_time_info time;
}; /* 64 bytes (x86) */
+struct shared_info {
+ struct vcpu_info vcpu_info[32];
+ unsigned long evtchn_pending[64];
+ unsigned long evtchn_mask[64];
+ struct pvclock_wall_clock wc;
+ uint32_t wc_sec_hi;
+ /* arch_shared_info here */
+};
+
#define RUNSTATE_running 0
#define RUNSTATE_runnable 1
#define RUNSTATE_blocked 2
#define RUNSTATE_offline 3
+static const char *runstate_names[] = {
+ "running",
+ "runnable",
+ "blocked",
+ "offline"
+};
+
+struct {
+ struct kvm_irq_routing info;
+ struct kvm_irq_routing_entry entries[2];
+} irq_routes;
+
static void evtchn_handler(struct ex_regs *regs)
{
struct vcpu_info *vi = (void *)VCPU_INFO_VADDR;
vi->evtchn_upcall_pending = 0;
+ vi->evtchn_pending_sel = 0;
GUEST_SYNC(0x20);
}
@@ -127,7 +157,25 @@ static void guest_code(void)
GUEST_SYNC(6);
GUEST_ASSERT(rs->time[RUNSTATE_runnable] >= MIN_STEAL_TIME);
- GUEST_DONE();
+ /* Attempt to deliver a *masked* interrupt */
+ GUEST_SYNC(7);
+
+ /* Wait until we see the bit set */
+ struct shared_info *si = (void *)SHINFO_VADDR;
+ while (!si->evtchn_pending[0])
+ __asm__ __volatile__ ("rep nop" : : : "memory");
+
+ /* Now deliver an *unmasked* interrupt */
+ GUEST_SYNC(8);
+
+ while (!si->evtchn_pending[1])
+ __asm__ __volatile__ ("rep nop" : : : "memory");
+
+ /* Change memslots and deliver an interrupt */
+ GUEST_SYNC(9);
+
+ for (;;)
+ __asm__ __volatile__ ("rep nop" : : : "memory");
}
static int cmp_timespec(struct timespec *a, struct timespec *b)
@@ -144,9 +192,18 @@ static int cmp_timespec(struct timespec *a, struct timespec *b)
return 0;
}
+static void handle_alrm(int sig)
+{
+ TEST_FAIL("IRQ delivery timed out");
+}
+
int main(int argc, char *argv[])
{
struct timespec min_ts, max_ts, vm_ts;
+ bool verbose;
+
+ verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) ||
+ !strncmp(argv[1], "--verbose", 10));
int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM);
if (!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO) ) {
@@ -155,6 +212,7 @@ int main(int argc, char *argv[])
}
bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE);
+ bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL);
clock_gettime(CLOCK_REALTIME, &min_ts);
@@ -166,6 +224,11 @@ int main(int argc, char *argv[])
SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0);
virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2);
+ struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR);
+
+ int zero_fd = open("/dev/zero", O_RDONLY);
+ TEST_ASSERT(zero_fd != -1, "Failed to open /dev/zero");
+
struct kvm_xen_hvm_config hvmc = {
.flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL,
.msr = XEN_HYPERCALL_MSR,
@@ -184,6 +247,16 @@ int main(int argc, char *argv[])
};
vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha);
+ /*
+ * Test what happens when the HVA of the shinfo page is remapped after
+ * the kernel has a reference to it. But make sure we copy the clock
+ * info over since that's only set at setup time, and we test it later.
+ */
+ struct pvclock_wall_clock wc_copy = shinfo->wc;
+ void *m = mmap(shinfo, PAGE_SIZE, PROT_READ|PROT_WRITE, MAP_FIXED|MAP_PRIVATE, zero_fd, 0);
+ TEST_ASSERT(m == shinfo, "Failed to map /dev/zero over shared info");
+ shinfo->wc = wc_copy;
+
struct kvm_xen_vcpu_attr vi = {
.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO,
.u.gpa = VCPU_INFO_ADDR,
@@ -214,6 +287,49 @@ int main(int argc, char *argv[])
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
}
+ int irq_fd[2] = { -1, -1 };
+
+ if (do_eventfd_tests) {
+ irq_fd[0] = eventfd(0, 0);
+ irq_fd[1] = eventfd(0, 0);
+
+ /* Unexpected, but not a KVM failure */
+ if (irq_fd[0] == -1 || irq_fd[1] == -1)
+ do_eventfd_tests = false;
+ }
+
+ if (do_eventfd_tests) {
+ irq_routes.info.nr = 2;
+
+ irq_routes.entries[0].gsi = 32;
+ irq_routes.entries[0].type = KVM_IRQ_ROUTING_XEN_EVTCHN;
+ irq_routes.entries[0].u.xen_evtchn.port = 15;
+ irq_routes.entries[0].u.xen_evtchn.vcpu = VCPU_ID;
+ irq_routes.entries[0].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
+
+ irq_routes.entries[1].gsi = 33;
+ irq_routes.entries[1].type = KVM_IRQ_ROUTING_XEN_EVTCHN;
+ irq_routes.entries[1].u.xen_evtchn.port = 66;
+ irq_routes.entries[1].u.xen_evtchn.vcpu = VCPU_ID;
+ irq_routes.entries[1].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL;
+
+ vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes);
+
+ struct kvm_irqfd ifd = { };
+
+ ifd.fd = irq_fd[0];
+ ifd.gsi = 32;
+ vm_ioctl(vm, KVM_IRQFD, &ifd);
+
+ ifd.fd = irq_fd[1];
+ ifd.gsi = 33;
+ vm_ioctl(vm, KVM_IRQFD, &ifd);
+
+ struct sigaction sa = { };
+ sa.sa_handler = handle_alrm;
+ sigaction(SIGALRM, &sa, NULL);
+ }
+
struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
vinfo->evtchn_upcall_pending = 0;
@@ -248,6 +364,8 @@ int main(int argc, char *argv[])
switch (uc.args[1]) {
case 0:
+ if (verbose)
+ printf("Delivering evtchn upcall\n");
evtchn_irq_expected = true;
vinfo->evtchn_upcall_pending = 1;
break;
@@ -256,11 +374,16 @@ int main(int argc, char *argv[])
TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen");
if (!do_runstate_tests)
goto done;
+ if (verbose)
+ printf("Testing runstate %s\n", runstate_names[uc.args[1]]);
rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT;
rst.u.runstate.state = uc.args[1];
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
break;
+
case 4:
+ if (verbose)
+ printf("Testing RUNSTATE_ADJUST\n");
rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST;
memset(&rst.u, 0, sizeof(rst.u));
rst.u.runstate.state = (uint64_t)-1;
@@ -274,6 +397,8 @@ int main(int argc, char *argv[])
break;
case 5:
+ if (verbose)
+ printf("Testing RUNSTATE_DATA\n");
rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA;
memset(&rst.u, 0, sizeof(rst.u));
rst.u.runstate.state = RUNSTATE_running;
@@ -282,16 +407,54 @@ int main(int argc, char *argv[])
rst.u.runstate.time_offline = 0x5a;
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
break;
+
case 6:
+ if (verbose)
+ printf("Testing steal time\n");
/* Yield until scheduler delay exceeds target */
rundelay = get_run_delay() + MIN_STEAL_TIME;
do {
sched_yield();
} while (get_run_delay() < rundelay);
break;
+
+ case 7:
+ if (!do_eventfd_tests)
+ goto done;
+ if (verbose)
+ printf("Testing masked event channel\n");
+ shinfo->evtchn_mask[0] = 0x8000;
+ eventfd_write(irq_fd[0], 1UL);
+ alarm(1);
+ break;
+
+ case 8:
+ if (verbose)
+ printf("Testing unmasked event channel\n");
+ /* Unmask that, but deliver the other one */
+ shinfo->evtchn_pending[0] = 0;
+ shinfo->evtchn_mask[0] = 0;
+ eventfd_write(irq_fd[1], 1UL);
+ evtchn_irq_expected = true;
+ alarm(1);
+ break;
+
+ case 9:
+ if (verbose)
+ printf("Testing event channel after memslot change\n");
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ DUMMY_REGION_GPA, DUMMY_REGION_SLOT, 1, 0);
+ eventfd_write(irq_fd[0], 1UL);
+ evtchn_irq_expected = true;
+ alarm(1);
+ break;
+
case 0x20:
TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ");
evtchn_irq_expected = false;
+ if (shinfo->evtchn_pending[1] &&
+ shinfo->evtchn_pending[0])
+ goto done;
break;
}
break;
@@ -318,9 +481,19 @@ int main(int argc, char *argv[])
ti = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20);
ti2 = addr_gpa2hva(vm, PVTIME_ADDR);
+ if (verbose) {
+ printf("Wall clock (v %d) %d.%09d\n", wc->version, wc->sec, wc->nsec);
+ printf("Time info 1: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n",
+ ti->version, ti->tsc_timestamp, ti->system_time, ti->tsc_to_system_mul,
+ ti->tsc_shift, ti->flags);
+ printf("Time info 2: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n",
+ ti2->version, ti2->tsc_timestamp, ti2->system_time, ti2->tsc_to_system_mul,
+ ti2->tsc_shift, ti2->flags);
+ }
+
vm_ts.tv_sec = wc->sec;
vm_ts.tv_nsec = wc->nsec;
- TEST_ASSERT(wc->version && !(wc->version & 1),
+ TEST_ASSERT(wc->version && !(wc->version & 1),
"Bad wallclock version %x", wc->version);
TEST_ASSERT(cmp_timespec(&min_ts, &vm_ts) <= 0, "VM time too old");
TEST_ASSERT(cmp_timespec(&max_ts, &vm_ts) >= 0, "VM time too new");
@@ -341,6 +514,15 @@ int main(int argc, char *argv[])
};
vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst);
+ if (verbose) {
+ printf("Runstate: %s(%d), entry %" PRIu64 " ns\n",
+ rs->state <= RUNSTATE_offline ? runstate_names[rs->state] : "unknown",
+ rs->state, rs->state_entry_time);
+ for (int i = RUNSTATE_running; i <= RUNSTATE_offline; i++) {
+ printf("State %s: %" PRIu64 " ns\n",
+ runstate_names[i], rs->time[i]);
+ }
+ }
TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch");
TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time,
"State entry time mismatch");
diff --git a/tools/testing/selftests/lkdtm/stack-entropy.sh b/tools/testing/selftests/lkdtm/stack-entropy.sh
index 1b4d95d575f8..14fedeef762e 100755
--- a/tools/testing/selftests/lkdtm/stack-entropy.sh
+++ b/tools/testing/selftests/lkdtm/stack-entropy.sh
@@ -4,13 +4,27 @@
# Measure kernel stack entropy by sampling via LKDTM's REPORT_STACK test.
set -e
samples="${1:-1000}"
+TRIGGER=/sys/kernel/debug/provoke-crash/DIRECT
+KSELFTEST_SKIP_TEST=4
+
+# Verify we have LKDTM available in the kernel.
+if [ ! -r $TRIGGER ] ; then
+ /sbin/modprobe -q lkdtm || true
+ if [ ! -r $TRIGGER ] ; then
+ echo "Cannot find $TRIGGER (missing CONFIG_LKDTM?)"
+ else
+ echo "Cannot write $TRIGGER (need to run as root?)"
+ fi
+ # Skip this test
+ exit $KSELFTEST_SKIP_TEST
+fi
# Capture dmesg continuously since it may fill up depending on sample size.
log=$(mktemp -t stack-entropy-XXXXXX)
dmesg --follow >"$log" & pid=$!
report=-1
for i in $(seq 1 $samples); do
- echo "REPORT_STACK" >/sys/kernel/debug/provoke-crash/DIRECT
+ echo "REPORT_STACK" > $TRIGGER
if [ -t 1 ]; then
percent=$(( 100 * $i / $samples ))
if [ "$percent" -ne "$report" ]; then
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 192a2899bae8..94df2692e6e4 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -455,6 +455,7 @@ static void mfd_fail_write(int fd)
printf("mmap()+mprotect() didn't fail as expected\n");
abort();
}
+ munmap(p, mfd_def_size);
}
/* verify PUNCH_HOLE fails */
diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c
index e54106643337..4c88238fc8f0 100644
--- a/tools/testing/selftests/mincore/mincore_selftest.c
+++ b/tools/testing/selftests/mincore/mincore_selftest.c
@@ -207,15 +207,21 @@ TEST(check_file_mmap)
errno = 0;
fd = open(".", O_TMPFILE | O_RDWR, 0600);
- ASSERT_NE(-1, fd) {
- TH_LOG("Can't create temporary file: %s",
- strerror(errno));
+ if (fd < 0) {
+ ASSERT_EQ(errno, EOPNOTSUPP) {
+ TH_LOG("Can't create temporary file: %s",
+ strerror(errno));
+ }
+ SKIP(goto out_free, "O_TMPFILE not supported by filesystem.");
}
errno = 0;
retval = fallocate(fd, 0, 0, FILE_SIZE);
- ASSERT_EQ(0, retval) {
- TH_LOG("Error allocating space for the temporary file: %s",
- strerror(errno));
+ if (retval) {
+ ASSERT_EQ(errno, EOPNOTSUPP) {
+ TH_LOG("Error allocating space for the temporary file: %s",
+ strerror(errno));
+ }
+ SKIP(goto out_close, "fallocate not supported by filesystem.");
}
/*
@@ -271,7 +277,9 @@ TEST(check_file_mmap)
}
munmap(addr, FILE_SIZE);
+out_close:
close(fd);
+out_free:
free(vec);
}
diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
index f31205f04ee0..8c5fea68ae67 100644
--- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c
+++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
@@ -1236,7 +1236,7 @@ static int get_userns_fd(unsigned long nsid, unsigned long hostid, unsigned long
}
/**
- * Validate that an attached mount in our mount namespace can be idmapped.
+ * Validate that an attached mount in our mount namespace cannot be idmapped.
* (The kernel enforces that the mount's mount namespace and the caller's mount
* namespace match.)
*/
@@ -1259,7 +1259,7 @@ TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace)
attr.userns_fd = get_userns_fd(0, 10000, 10000);
ASSERT_GE(attr.userns_fd, 0);
- ASSERT_EQ(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+ ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
ASSERT_EQ(close(attr.userns_fd), 0);
ASSERT_EQ(close(open_tree_fd), 0);
}
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 412d85205546..3f4c8cfe7aca 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -4059,6 +4059,9 @@ usage: ${0##*/} OPTS
-p Pause on fail
-P Pause after each test
-v Be verbose
+
+Tests:
+ $TESTS_IPV4 $TESTS_IPV6 $TESTS_OTHER
EOF
}
diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c
index 8f6997d35816..d9d1d4190126 100644
--- a/tools/testing/selftests/net/ioam6_parser.c
+++ b/tools/testing/selftests/net/ioam6_parser.c
@@ -240,11 +240,8 @@ static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h,
*p += sizeof(__u32);
}
- if (ioam6h->type.bit6) {
- if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
- return 1;
+ if (ioam6h->type.bit6)
*p += sizeof(__u32);
- }
if (ioam6h->type.bit7) {
if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 2674ba20d524..ff821025d309 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -71,6 +71,36 @@ chk_msk_remote_key_nr()
__chk_nr "grep -c remote_key" $*
}
+# $1: ns, $2: port
+wait_local_port_listen()
+{
+ local listener_ns="${1}"
+ local port="${2}"
+
+ local port_hex i
+
+ port_hex="$(printf "%04X" "${port}")"
+ for i in $(seq 10); do
+ ip netns exec "${listener_ns}" cat /proc/net/tcp | \
+ awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" &&
+ break
+ sleep 0.1
+ done
+}
+
+wait_connected()
+{
+ local listener_ns="${1}"
+ local port="${2}"
+
+ local port_hex i
+
+ port_hex="$(printf "%04X" "${port}")"
+ for i in $(seq 10); do
+ ip netns exec ${listener_ns} grep -q " 0100007F:${port_hex} " /proc/net/tcp && break
+ sleep 0.1
+ done
+}
trap cleanup EXIT
ip netns add $ns
@@ -81,15 +111,15 @@ echo "a" | \
ip netns exec $ns \
./mptcp_connect -p 10000 -l -t ${timeout_poll} \
0.0.0.0 >/dev/null &
-sleep 0.1
+wait_local_port_listen $ns 10000
chk_msk_nr 0 "no msk on netns creation"
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10000 -j -t ${timeout_poll} \
+ ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \
127.0.0.1 >/dev/null &
-sleep 0.1
+wait_connected $ns 10000
chk_msk_nr 2 "after MPC handshake "
chk_msk_remote_key_nr 2 "....chk remote_key"
chk_msk_fallback_nr 0 "....chk no fallback"
@@ -101,13 +131,13 @@ echo "a" | \
ip netns exec $ns \
./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \
0.0.0.0 >/dev/null &
-sleep 0.1
+wait_local_port_listen $ns 10001
echo "b" | \
timeout ${timeout_test} \
ip netns exec $ns \
- ./mptcp_connect -p 10001 -j -t ${timeout_poll} \
+ ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \
127.0.0.1 >/dev/null &
-sleep 0.1
+wait_connected $ns 10001
chk_msk_fallback_nr 1 "check fallback"
flush_pids
@@ -119,7 +149,7 @@ for I in `seq 1 $NR_CLIENTS`; do
./mptcp_connect -p $((I+10001)) -l -w 10 \
-t ${timeout_poll} 0.0.0.0 >/dev/null &
done
-sleep 0.1
+wait_local_port_listen $ns $((NR_CLIENTS + 10001))
for I in `seq 1 $NR_CLIENTS`; do
echo "b" | \
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index cb5809b89081..f0f4ab96b8f3 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -763,8 +763,8 @@ run_tests_disconnect()
run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-I 3 -i $old_cin"
# restore previous status
- cout=$old_cout
- cout_disconnect="$cout".disconnect
+ sin=$old_sin
+ sin_disconnect="$cout".disconnect
cin=$old_cin
cin_disconnect="$cin".disconnect
connect_per_transfer=1
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 27d0eb9afdca..0c8a2a20b96c 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -75,6 +75,7 @@ init()
# let $ns2 reach any $ns1 address from any interface
ip -net "$ns2" route add default via 10.0.$i.1 dev ns2eth$i metric 10$i
+ ip -net "$ns2" route add default via dead:beef:$i::1 dev ns2eth$i metric 10$i
done
}
@@ -659,6 +660,7 @@ chk_join_nr()
local ack_nr=$4
local count
local dump_stats
+ local with_cookie
printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn"
count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'`
@@ -672,12 +674,20 @@ chk_join_nr()
fi
echo -n " - synack"
+ with_cookie=`ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies`
count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}'`
[ -z "$count" ] && count=0
if [ "$count" != "$syn_ack_nr" ]; then
- echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr"
- ret=1
- dump_stats=1
+ # simult connections exceeding the limit with cookie enabled could go up to
+ # synack validation as the conn limit can be enforced reliably only after
+ # the subflow creation
+ if [ "$with_cookie" = 2 ] && [ "$count" -gt "$syn_ack_nr" ] && [ "$count" -le "$syn_nr" ]; then
+ echo -n "[ ok ]"
+ else
+ echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr"
+ ret=1
+ dump_stats=1
+ fi
else
echo -n "[ ok ]"
fi
@@ -751,11 +761,17 @@ chk_add_nr()
local mis_ack_nr=${8:-0}
local count
local dump_stats
+ local timeout
+
+ timeout=`ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout`
printf "%-39s %s" " " "add"
- count=`ip netns exec $ns2 nstat -as | grep MPTcpExtAddAddr | awk '{print $2}'`
+ count=`ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}'`
[ -z "$count" ] && count=0
- if [ "$count" != "$add_nr" ]; then
+
+ # if the test configured a short timeout tolerate greater then expected
+ # add addrs options, due to retransmissions
+ if [ "$count" != "$add_nr" ] && [ "$timeout" -gt 1 -o "$count" -lt "$add_nr" ]; then
echo "[fail] got $count ADD_ADDR[s] expected $add_nr"
ret=1
dump_stats=1
@@ -960,7 +976,7 @@ wait_for_tw()
local ns=$1
while [ $time -lt $timeout_ms ]; do
- local cnt=$(ip netns exec $ns ss -t state time-wait |wc -l)
+ local cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}')
[ "$cnt" = 1 ] && return 1
time=$((time + 100))
@@ -1157,7 +1173,11 @@ signal_address_tests()
ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags signal
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal
ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal
- run_tests $ns1 $ns2 10.0.1.1
+
+ # the peer could possibly miss some addr notification, allow retransmission
+ ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1
+ run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
+ chk_join_nr "signal addresses race test" 3 3 3
# the server will not signal the address terminating
# the MPC subflow
@@ -1476,7 +1496,7 @@ ipv6_tests()
reset
ip netns exec $ns1 ./pm_nl_ctl limits 0 1
ip netns exec $ns2 ./pm_nl_ctl limits 0 1
- ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow
+ ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 dev ns2eth3 flags subflow
run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
chk_join_nr "single subflow IPv6" 1 1 1
@@ -1511,7 +1531,7 @@ ipv6_tests()
ip netns exec $ns1 ./pm_nl_ctl limits 0 2
ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
ip netns exec $ns2 ./pm_nl_ctl limits 1 2
- ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow
+ ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 dev ns2eth3 flags subflow
run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow
chk_join_nr "remove subflow and signal IPv6" 2 2 2
chk_add_nr 1 1
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 543ad7513a8e..694732e4b344 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -374,6 +374,16 @@ run_cmd() {
return $rc
}
+run_cmd_bg() {
+ cmd="$*"
+
+ if [ "$VERBOSE" = "1" ]; then
+ printf " COMMAND: %s &\n" "${cmd}"
+ fi
+
+ $cmd 2>&1 &
+}
+
# Find the auto-generated name for this namespace
nsname() {
eval echo \$NS_$1
@@ -670,10 +680,10 @@ setup_nettest_xfrm() {
[ ${1} -eq 6 ] && proto="-6" || proto=""
port=${2}
- run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ run_cmd_bg "${ns_a}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5
nettest_pids="${nettest_pids} $!"
- run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ run_cmd_bg "${ns_b}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5
nettest_pids="${nettest_pids} $!"
}
@@ -865,7 +875,6 @@ setup_ovs_bridge() {
setup() {
[ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip
- cleanup
for arg do
eval setup_${arg} || { echo " ${arg} not supported"; return 1; }
done
@@ -876,7 +885,7 @@ trace() {
for arg do
[ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue
- ${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
+ ${ns_cmd} tcpdump --immediate-mode -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
tcpdump_pids="${tcpdump_pids} $!"
ns_cmd=
done
@@ -1836,6 +1845,10 @@ run_test() {
unset IFS
+ # Since cleanup() relies on variables modified by this subshell, it
+ # has to run in this context.
+ trap cleanup EXIT
+
if [ "$VERBOSE" = "1" ]; then
printf "\n##########################################################################\n\n"
fi
diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings
index 694d70710ff0..dfc27cdc6c05 100644
--- a/tools/testing/selftests/net/settings
+++ b/tools/testing/selftests/net/settings
@@ -1 +1 @@
-timeout=300
+timeout=1500
diff --git a/tools/testing/selftests/netfilter/.gitignore b/tools/testing/selftests/netfilter/.gitignore
index 8448f74adfec..4cb887b57413 100644
--- a/tools/testing/selftests/netfilter/.gitignore
+++ b/tools/testing/selftests/netfilter/.gitignore
@@ -1,2 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
nf-queue
+connect_close
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index ffca314897c4..7e81c9a7fff9 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -6,9 +6,9 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
nft_concat_range.sh nft_conntrack_helper.sh \
nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \
- conntrack_vrf.sh
+ conntrack_vrf.sh nft_synproxy.sh
LDLIBS = -lmnl
-TEST_GEN_FILES = nf-queue
+TEST_GEN_FILES = nf-queue connect_close
include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/connect_close.c b/tools/testing/selftests/netfilter/connect_close.c
new file mode 100644
index 000000000000..1c3b0add54c4
--- /dev/null
+++ b/tools/testing/selftests/netfilter/connect_close.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include <signal.h>
+
+#include <arpa/inet.h>
+#include <sys/socket.h>
+
+#define PORT 12345
+#define RUNTIME 10
+
+static struct {
+ unsigned int timeout;
+ unsigned int port;
+} opts = {
+ .timeout = RUNTIME,
+ .port = PORT,
+};
+
+static void handler(int sig)
+{
+ _exit(sig == SIGALRM ? 0 : 1);
+}
+
+static void set_timeout(void)
+{
+ struct sigaction action = {
+ .sa_handler = handler,
+ };
+
+ sigaction(SIGALRM, &action, NULL);
+
+ alarm(opts.timeout);
+}
+
+static void do_connect(const struct sockaddr_in *dst)
+{
+ int s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+
+ if (s >= 0)
+ fcntl(s, F_SETFL, O_NONBLOCK);
+
+ connect(s, (struct sockaddr *)dst, sizeof(*dst));
+ close(s);
+}
+
+static void do_accept(const struct sockaddr_in *src)
+{
+ int c, one = 1, s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+
+ if (s < 0)
+ return;
+
+ setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one));
+ setsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
+
+ bind(s, (struct sockaddr *)src, sizeof(*src));
+
+ listen(s, 16);
+
+ c = accept(s, NULL, NULL);
+ if (c >= 0)
+ close(c);
+
+ close(s);
+}
+
+static int accept_loop(void)
+{
+ struct sockaddr_in src = {
+ .sin_family = AF_INET,
+ .sin_port = htons(opts.port),
+ };
+
+ inet_pton(AF_INET, "127.0.0.1", &src.sin_addr);
+
+ set_timeout();
+
+ for (;;)
+ do_accept(&src);
+
+ return 1;
+}
+
+static int connect_loop(void)
+{
+ struct sockaddr_in dst = {
+ .sin_family = AF_INET,
+ .sin_port = htons(opts.port),
+ };
+
+ inet_pton(AF_INET, "127.0.0.1", &dst.sin_addr);
+
+ set_timeout();
+
+ for (;;)
+ do_connect(&dst);
+
+ return 1;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "t:p:")) != -1) {
+ switch (c) {
+ case 't':
+ opts.timeout = atoi(optarg);
+ break;
+ case 'p':
+ opts.port = atoi(optarg);
+ break;
+ }
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ pid_t p;
+
+ parse_opts(argc, argv);
+
+ p = fork();
+ if (p < 0)
+ return 111;
+
+ if (p > 0)
+ return accept_loop();
+
+ return connect_loop();
+}
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index ed61f6cab60f..b35010cc7f6a 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
net6_port_net6_port net_port_mac_proto_net"
# Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add"
+BUGS="flush_remove_add reload"
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
@@ -354,6 +354,23 @@ TYPE_flush_remove_add="
display Add two elements, flush, re-add
"
+TYPE_reload="
+display net,mac with reload
+type_spec ipv4_addr . ether_addr
+chain_spec ip daddr . ether saddr
+dst addr4
+src mac
+start 1
+count 1
+src_delta 2000
+tools sendip nc bash
+proto udp
+
+race_repeat 0
+
+perf_duration 0
+"
+
# Set template for all tests, types and rules are filled in depending on test
set_template='
flush ruleset
@@ -1473,6 +1490,59 @@ test_bug_flush_remove_add() {
nft flush ruleset
}
+# - add ranged element, check that packets match it
+# - reload the set, check packets still match
+test_bug_reload() {
+ setup veth send_"${proto}" set || return ${KSELFTEST_SKIP}
+ rstart=${start}
+
+ range_size=1
+ for i in $(seq "${start}" $((start + count))); do
+ end=$((start + range_size))
+
+ # Avoid negative or zero-sized port ranges
+ if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+ start=${end}
+ end=$((end + 1))
+ fi
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ add "$(format)" || return 1
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+
+ # check kernel does allocate pcpu sctrach map
+ # for reload with no elemet add/delete
+ ( echo flush set inet filter test ;
+ nft list set inet filter test ) | nft -f -
+
+ start=${rstart}
+ range_size=1
+
+ for i in $(seq "${start}" $((start + count))); do
+ end=$((start + range_size))
+
+ # Avoid negative or zero-sized port ranges
+ if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+ start=${end}
+ end=$((end + 1))
+ fi
+ srcstart=$((start + src_delta))
+ srcend=$((end + src_delta))
+
+ for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do
+ send_match "${j}" $((j + src_delta)) || return 1
+ done
+
+ range_size=$((range_size + 1))
+ start=$((end + range_size))
+ done
+
+ nft flush ruleset
+}
+
test_reported_issues() {
eval test_bug_"${subtest}"
}
@@ -1531,4 +1601,4 @@ for name in ${TESTS}; do
done
done
-[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP}
+[ ${passed} -eq 0 ] && exit ${KSELFTEST_SKIP} || exit 0
diff --git a/tools/testing/selftests/netfilter/nft_fib.sh b/tools/testing/selftests/netfilter/nft_fib.sh
index 6caf6ac8c285..695a1958723f 100755
--- a/tools/testing/selftests/netfilter/nft_fib.sh
+++ b/tools/testing/selftests/netfilter/nft_fib.sh
@@ -174,6 +174,7 @@ test_ping() {
ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.rp_filter=0 > /dev/null
sleep 3
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 349a319a9e51..eb8543b9a5c4 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -880,9 +880,8 @@ EOF
return $ksft_skip
fi
- # test default behaviour. Packet from ns1 to ns0 is not redirected
- # due to automatic port translation.
- test_port_shadow "default" "ROUTER"
+ # test default behaviour. Packet from ns1 to ns0 is redirected to ns2.
+ test_port_shadow "default" "CLIENT"
# test packet filter based mitigation: prevent forwarding of
# packets claiming to come from the service port.
@@ -899,6 +898,144 @@ EOF
ip netns exec "$ns0" nft delete table $family nat
}
+test_stateless_nat_ip()
+{
+ local lret=0
+
+ ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+ ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping $ns1 from $ns2 before loading stateless rules"
+ return 1
+ fi
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table ip stateless {
+ map xlate_in {
+ typeof meta iifname . ip saddr . ip daddr : ip daddr
+ elements = {
+ "veth1" . 10.0.2.99 . 10.0.1.99 : 10.0.2.2,
+ }
+ }
+ map xlate_out {
+ typeof meta iifname . ip saddr . ip daddr : ip daddr
+ elements = {
+ "veth0" . 10.0.1.99 . 10.0.2.2 : 10.0.2.99
+ }
+ }
+
+ chain prerouting {
+ type filter hook prerouting priority -400; policy accept;
+ ip saddr set meta iifname . ip saddr . ip daddr map @xlate_in
+ ip daddr set meta iifname . ip saddr . ip daddr map @xlate_out
+ }
+}
+EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add ip statless rules"
+ return $ksft_skip
+ fi
+
+ reset_counters
+
+ ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: cannot ping $ns1 from $ns2 with stateless rules"
+ lret=1
+ fi
+
+ # ns1 should have seen packets from .2.2, due to stateless rewrite.
+ expect="packets 1 bytes 84"
+ cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns1" ns0insl "$expect" "test_stateless 1"
+ lret=1
+ fi
+
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns2" ns1$dir "$expect" "test_stateless 2"
+ lret=1
+ fi
+ done
+
+ # ns1 should not have seen packets from ns2, due to masquerade
+ expect="packets 0 bytes 0"
+ for dir in "in" "out" ; do
+ cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns1" ns0$dir "$expect" "test_stateless 3"
+ lret=1
+ fi
+
+ cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns0" ns1$dir "$expect" "test_stateless 4"
+ lret=1
+ fi
+ done
+
+ reset_counters
+
+ socat -h > /dev/null 2>&1
+ if [ $? -ne 0 ];then
+ echo "SKIP: Could not run stateless nat frag test without socat tool"
+ if [ $lret -eq 0 ]; then
+ return $ksft_skip
+ fi
+
+ ip netns exec "$ns0" nft delete table ip stateless
+ return $lret
+ fi
+
+ local tmpfile=$(mktemp)
+ dd if=/dev/urandom of=$tmpfile bs=4096 count=1 2>/dev/null
+
+ local outfile=$(mktemp)
+ ip netns exec "$ns1" timeout 3 socat -u UDP4-RECV:4233 OPEN:$outfile < /dev/null &
+ sc_r=$!
+
+ sleep 1
+ # re-do with large ping -> ip fragmentation
+ ip netns exec "$ns2" timeout 3 socat - UDP4-SENDTO:"10.0.1.99:4233" < "$tmpfile" > /dev/null
+ if [ $? -ne 0 ] ; then
+ echo "ERROR: failed to test udp $ns1 to $ns2 with stateless ip nat" 1>&2
+ lret=1
+ fi
+
+ wait
+
+ cmp "$tmpfile" "$outfile"
+ if [ $? -ne 0 ]; then
+ ls -l "$tmpfile" "$outfile"
+ echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2
+ lret=1
+ fi
+
+ rm -f "$tmpfile" "$outfile"
+
+ # ns1 should have seen packets from 2.2, due to stateless rewrite.
+ expect="packets 3 bytes 4164"
+ cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ bad_counter "$ns1" ns0insl "$expect" "test_stateless 5"
+ lret=1
+ fi
+
+ ip netns exec "$ns0" nft delete table ip stateless
+ if [ $? -ne 0 ]; then
+ echo "ERROR: Could not delete table ip stateless" 1>&2
+ lret=1
+ fi
+
+ test $lret -eq 0 && echo "PASS: IP statless for $ns2"
+
+ return $lret
+}
+
# ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99
for i in 0 1 2; do
ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF
@@ -965,6 +1102,19 @@ table inet filter {
EOF
done
+# special case for stateless nat check, counter needs to
+# be done before (input) ip defragmentation
+ip netns exec ns1-$sfx nft -f /dev/stdin <<EOF
+table inet filter {
+ counter ns0insl {}
+
+ chain pre {
+ type filter hook prerouting priority -400; policy accept;
+ ip saddr 10.0.2.2 counter name "ns0insl"
+ }
+}
+EOF
+
sleep 3
# test basic connectivity
for i in 1 2; do
@@ -1019,6 +1169,7 @@ $test_inet_nat && test_redirect inet
$test_inet_nat && test_redirect6 inet
test_port_shadowing
+test_stateless_nat_ip
if [ $ret -ne 0 ];then
echo -n "FAIL: "
diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh
index 7d27f1f3bc01..e12729753351 100755
--- a/tools/testing/selftests/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/netfilter/nft_queue.sh
@@ -113,6 +113,7 @@ table inet $name {
chain output {
type filter hook output priority $prio; policy accept;
tcp dport 12345 queue num 3
+ tcp sport 23456 queue num 3
jump nfq
}
chain post {
@@ -296,6 +297,23 @@ test_tcp_localhost()
wait 2>/dev/null
}
+test_tcp_localhost_connectclose()
+{
+ tmpfile=$(mktemp) || exit 1
+
+ ip netns exec ${nsrouter} ./connect_close -p 23456 -t $timeout &
+
+ ip netns exec ${nsrouter} ./nf-queue -q 3 -t $timeout &
+ local nfqpid=$!
+
+ sleep 1
+ rm -f "$tmpfile"
+
+ wait $rpid
+ [ $? -eq 0 ] && echo "PASS: tcp via loopback with connect/close"
+ wait 2>/dev/null
+}
+
test_tcp_localhost_requeue()
{
ip netns exec ${nsrouter} nft -f /dev/stdin <<EOF
@@ -424,6 +442,7 @@ test_queue 20
test_tcp_forward
test_tcp_localhost
+test_tcp_localhost_connectclose
test_tcp_localhost_requeue
test_icmp_vrf
diff --git a/tools/testing/selftests/netfilter/nft_synproxy.sh b/tools/testing/selftests/netfilter/nft_synproxy.sh
new file mode 100755
index 000000000000..b62933b680d6
--- /dev/null
+++ b/tools/testing/selftests/netfilter/nft_synproxy.sh
@@ -0,0 +1,117 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+rnd=$(mktemp -u XXXXXXXX)
+nsr="nsr-$rnd" # synproxy machine
+ns1="ns1-$rnd" # iperf client
+ns2="ns2-$rnd" # iperf server
+
+checktool (){
+ if ! $1 > /dev/null 2>&1; then
+ echo "SKIP: Could not $2"
+ exit $ksft_skip
+ fi
+}
+
+checktool "nft --version" "run test without nft tool"
+checktool "ip -Version" "run test without ip tool"
+checktool "iperf3 --version" "run test without iperf3"
+checktool "ip netns add $nsr" "create net namespace"
+
+modprobe -q nf_conntrack
+
+ip netns add $ns1
+ip netns add $ns2
+
+cleanup() {
+ ip netns pids $ns1 | xargs kill 2>/dev/null
+ ip netns pids $ns2 | xargs kill 2>/dev/null
+ ip netns del $ns1
+ ip netns del $ns2
+
+ ip netns del $nsr
+}
+
+trap cleanup EXIT
+
+ip link add veth0 netns $nsr type veth peer name eth0 netns $ns1
+ip link add veth1 netns $nsr type veth peer name eth0 netns $ns2
+
+for dev in lo veth0 veth1; do
+ip -net $nsr link set $dev up
+done
+
+ip -net $nsr addr add 10.0.1.1/24 dev veth0
+ip -net $nsr addr add 10.0.2.1/24 dev veth1
+
+ip netns exec $nsr sysctl -q net.ipv4.conf.veth0.forwarding=1
+ip netns exec $nsr sysctl -q net.ipv4.conf.veth1.forwarding=1
+ip netns exec $nsr sysctl -q net.netfilter.nf_conntrack_tcp_loose=0
+
+for n in $ns1 $ns2; do
+ ip -net $n link set lo up
+ ip -net $n link set eth0 up
+done
+ip -net $ns1 addr add 10.0.1.99/24 dev eth0
+ip -net $ns2 addr add 10.0.2.99/24 dev eth0
+ip -net $ns1 route add default via 10.0.1.1
+ip -net $ns2 route add default via 10.0.2.1
+
+# test basic connectivity
+if ! ip netns exec $ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
+ echo "ERROR: $ns1 cannot reach $ns2" 1>&2
+ exit 1
+fi
+
+if ! ip netns exec $ns2 ping -c 1 -q 10.0.1.99 > /dev/null; then
+ echo "ERROR: $ns2 cannot reach $ns1" 1>&2
+ exit 1
+fi
+
+ip netns exec $ns2 iperf3 -s > /dev/null 2>&1 &
+# ip netns exec $nsr tcpdump -vvv -n -i veth1 tcp | head -n 10 &
+
+sleep 1
+
+ip netns exec $nsr nft -f - <<EOF
+table inet filter {
+ chain prerouting {
+ type filter hook prerouting priority -300; policy accept;
+ meta iif veth0 tcp flags syn counter notrack
+ }
+
+ chain forward {
+ type filter hook forward priority 0; policy accept;
+
+ ct state new,established counter accept
+
+ meta iif veth0 meta l4proto tcp ct state untracked,invalid synproxy mss 1460 sack-perm timestamp
+
+ ct state invalid counter drop
+
+ # make ns2 unreachable w.o. tcp synproxy
+ tcp flags syn counter drop
+ }
+}
+EOF
+if [ $? -ne 0 ]; then
+ echo "SKIP: Cannot add nft synproxy"
+ exit $ksft_skip
+fi
+
+ip netns exec $ns1 timeout 5 iperf3 -c 10.0.2.99 -n $((1 * 1024 * 1024)) > /dev/null
+
+if [ $? -ne 0 ]; then
+ echo "FAIL: iperf3 returned an error" 1>&2
+ ret=$?
+ ip netns exec $nsr nft list ruleset
+else
+ echo "PASS: synproxy connection successful"
+fi
+
+exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh
index 04633119b29a..5a8db0b48928 100755
--- a/tools/testing/selftests/netfilter/nft_zones_many.sh
+++ b/tools/testing/selftests/netfilter/nft_zones_many.sh
@@ -9,7 +9,7 @@ ns="ns-$sfx"
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
-zones=20000
+zones=2000
have_ct_tool=0
ret=0
@@ -75,10 +75,10 @@ EOF
while [ $i -lt $max_zones ]; do
local start=$(date +%s%3N)
- i=$((i + 10000))
+ i=$((i + 1000))
j=$((j + 1))
# nft rule in output places each packet in a different zone.
- dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
+ dd if=/dev/zero of=/dev/stdout bs=8k count=1000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
if [ $? -ne 0 ] ;then
ret=1
break
@@ -86,7 +86,7 @@ EOF
stop=$(date +%s%3N)
local duration=$((stop-start))
- echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)"
+ echo "PASS: added 1000 entries in $duration ms (now $i total, loop $j)"
done
if [ $have_ct_tool -eq 1 ]; then
@@ -128,11 +128,11 @@ test_conntrack_tool() {
break
fi
- if [ $((i%10000)) -eq 0 ];then
+ if [ $((i%1000)) -eq 0 ];then
stop=$(date +%s%3N)
local duration=$((stop-start))
- echo "PASS: added 10000 entries in $duration ms (now $i total)"
+ echo "PASS: added 1000 entries in $duration ms (now $i total)"
start=$stop
fi
done
diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile
index 4b93b1417b86..843ba56d8e49 100644
--- a/tools/testing/selftests/openat2/Makefile
+++ b/tools/testing/selftests/openat2/Makefile
@@ -5,4 +5,4 @@ TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test
include ../lib.mk
-$(TEST_GEN_PROGS): helpers.c
+$(TEST_GEN_PROGS): helpers.c helpers.h
diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h
index a6ea27344db2..7056340b9339 100644
--- a/tools/testing/selftests/openat2/helpers.h
+++ b/tools/testing/selftests/openat2/helpers.h
@@ -9,6 +9,7 @@
#define _GNU_SOURCE
#include <stdint.h>
+#include <stdbool.h>
#include <errno.h>
#include <linux/types.h>
#include "../kselftest.h"
@@ -62,11 +63,12 @@ bool needs_openat2(const struct open_how *how);
(similar to chroot(2)). */
#endif /* RESOLVE_IN_ROOT */
-#define E_func(func, ...) \
- do { \
- if (func(__VA_ARGS__) < 0) \
- ksft_exit_fail_msg("%s:%d %s failed\n", \
- __FILE__, __LINE__, #func);\
+#define E_func(func, ...) \
+ do { \
+ errno = 0; \
+ if (func(__VA_ARGS__) < 0) \
+ ksft_exit_fail_msg("%s:%d %s failed - errno:%d\n", \
+ __FILE__, __LINE__, #func, errno); \
} while (0)
#define E_asprintf(...) E_func(asprintf, __VA_ARGS__)
diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c
index 1bddbe934204..7fb902099de4 100644
--- a/tools/testing/selftests/openat2/openat2_test.c
+++ b/tools/testing/selftests/openat2/openat2_test.c
@@ -259,6 +259,16 @@ void test_openat2_flags(void)
unlink(path);
fd = sys_openat2(AT_FDCWD, path, &test->how);
+ if (fd < 0 && fd == -EOPNOTSUPP) {
+ /*
+ * Skip the testcase if it failed because not supported
+ * by FS. (e.g. a valid O_TMPFILE combination on NFS)
+ */
+ ksft_test_result_skip("openat2 with %s fails with %d (%s)\n",
+ test->name, fd, strerror(-fd));
+ goto next;
+ }
+
if (test->err >= 0)
failed = (fd < 0);
else
@@ -303,7 +313,7 @@ skip:
else
resultfn("openat2 with %s fails with %d (%s)\n",
test->name, test->err, strerror(-test->err));
-
+next:
free(fdpath);
fflush(stdout);
}
diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c
index 8e83cf91513a..6d849dc2bee0 100644
--- a/tools/testing/selftests/perf_events/sigtrap_threads.c
+++ b/tools/testing/selftests/perf_events/sigtrap_threads.c
@@ -44,9 +44,10 @@ static struct {
} ctx;
/* Unique value to check si_perf_data is correctly set from perf_event_attr::sig_data. */
-#define TEST_SIG_DATA(addr) (~(unsigned long)(addr))
+#define TEST_SIG_DATA(addr, id) (~(unsigned long)(addr) + id)
-static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr)
+static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr,
+ unsigned long id)
{
struct perf_event_attr attr = {
.type = PERF_TYPE_BREAKPOINT,
@@ -60,7 +61,7 @@ static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr)
.inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */
.remove_on_exec = 1, /* Required by sigtrap. */
.sigtrap = 1, /* Request synchronous SIGTRAP on event. */
- .sig_data = TEST_SIG_DATA(addr),
+ .sig_data = TEST_SIG_DATA(addr, id),
};
return attr;
}
@@ -110,7 +111,7 @@ FIXTURE(sigtrap_threads)
FIXTURE_SETUP(sigtrap_threads)
{
- struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on);
+ struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on, 0);
struct sigaction action = {};
int i;
@@ -165,7 +166,7 @@ TEST_F(sigtrap_threads, enable_event)
EXPECT_EQ(ctx.tids_want_signal, 0);
EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
- EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
+ EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0));
/* Check enabled for parent. */
ctx.iterate_on = 0;
@@ -175,7 +176,7 @@ TEST_F(sigtrap_threads, enable_event)
/* Test that modification propagates to all inherited events. */
TEST_F(sigtrap_threads, modify_and_enable_event)
{
- struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on);
+ struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on, 42);
EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr), 0);
run_test_threads(_metadata, self);
@@ -184,7 +185,7 @@ TEST_F(sigtrap_threads, modify_and_enable_event)
EXPECT_EQ(ctx.tids_want_signal, 0);
EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
- EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
+ EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 42));
/* Check enabled for parent. */
ctx.iterate_on = 0;
@@ -204,7 +205,7 @@ TEST_F(sigtrap_threads, signal_stress)
EXPECT_EQ(ctx.tids_want_signal, 0);
EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT);
- EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on));
+ EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0));
}
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index 01f8d3c0cf2c..6922d6417e1c 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -68,7 +68,7 @@
#define PIDFD_SKIP 3
#define PIDFD_XFAIL 4
-int wait_for_pid(pid_t pid)
+static inline int wait_for_pid(pid_t pid)
{
int status, ret;
@@ -78,13 +78,20 @@ again:
if (errno == EINTR)
goto again;
+ ksft_print_msg("waitpid returned -1, errno=%d\n", errno);
return -1;
}
- if (!WIFEXITED(status))
+ if (!WIFEXITED(status)) {
+ ksft_print_msg(
+ "waitpid !WIFEXITED, WIFSIGNALED=%d, WTERMSIG=%d\n",
+ WIFSIGNALED(status), WTERMSIG(status));
return -1;
+ }
- return WEXITSTATUS(status);
+ ret = WEXITSTATUS(status);
+ ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret);
+ return ret;
}
static inline int sys_pidfd_open(pid_t pid, unsigned int flags)
diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c
index 22558524f71c..3fd8e903118f 100644
--- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c
@@ -12,6 +12,7 @@
#include <string.h>
#include <syscall.h>
#include <sys/wait.h>
+#include <sys/mman.h>
#include "pidfd.h"
#include "../kselftest.h"
@@ -80,7 +81,10 @@ static inline int error_check(struct error *err, const char *test_name)
return err->code;
}
+#define CHILD_STACK_SIZE 8192
+
struct child {
+ char *stack;
pid_t pid;
int fd;
};
@@ -89,17 +93,22 @@ static struct child clone_newns(int (*fn)(void *), void *args,
struct error *err)
{
static int flags = CLONE_PIDFD | CLONE_NEWPID | CLONE_NEWNS | SIGCHLD;
- size_t stack_size = 1024;
- char *stack[1024] = { 0 };
struct child ret;
if (!(flags & CLONE_NEWUSER) && geteuid() != 0)
flags |= CLONE_NEWUSER;
+ ret.stack = mmap(NULL, CHILD_STACK_SIZE, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0);
+ if (ret.stack == MAP_FAILED) {
+ error_set(err, -1, "mmap of stack failed (errno %d)", errno);
+ return ret;
+ }
+
#ifdef __ia64__
- ret.pid = __clone2(fn, stack, stack_size, flags, args, &ret.fd);
+ ret.pid = __clone2(fn, ret.stack, CHILD_STACK_SIZE, flags, args, &ret.fd);
#else
- ret.pid = clone(fn, stack + stack_size, flags, args, &ret.fd);
+ ret.pid = clone(fn, ret.stack + CHILD_STACK_SIZE, flags, args, &ret.fd);
#endif
if (ret.pid < 0) {
@@ -129,6 +138,11 @@ static inline int child_join(struct child *child, struct error *err)
else if (r > 0)
error_set(err, r, "child %d reported: %d", child->pid, r);
+ if (munmap(child->stack, CHILD_STACK_SIZE)) {
+ error_set(err, -1, "munmap of child stack failed (errno %d)", errno);
+ r = -1;
+ }
+
return r;
}
diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c
index 529eb700ac26..9a2d64901d59 100644
--- a/tools/testing/selftests/pidfd/pidfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_test.c
@@ -441,7 +441,6 @@ static void test_pidfd_poll_exec(int use_waitpid)
{
int pid, pidfd = 0;
int status, ret;
- pthread_t t1;
time_t prog_start = time(NULL);
const char *test_name = "pidfd_poll check for premature notification on child thread exec";
@@ -500,13 +499,14 @@ static int child_poll_leader_exit_test(void *args)
*/
*child_exit_secs = time(NULL);
syscall(SYS_exit, 0);
+ /* Never reached, but appeases compiler thinking we should return. */
+ exit(0);
}
static void test_pidfd_poll_leader_exit(int use_waitpid)
{
int pid, pidfd = 0;
- int status, ret;
- time_t prog_start = time(NULL);
+ int status, ret = 0;
const char *test_name = "pidfd_poll check for premature notification on non-empty"
"group leader exit";
diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c
index be2943f072f6..17999e082aa7 100644
--- a/tools/testing/selftests/pidfd/pidfd_wait.c
+++ b/tools/testing/selftests/pidfd/pidfd_wait.c
@@ -39,7 +39,7 @@ static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options,
TEST(wait_simple)
{
- int pidfd = -1, status = 0;
+ int pidfd = -1;
pid_t parent_tid = -1;
struct clone_args args = {
.parent_tid = ptr_to_u64(&parent_tid),
@@ -47,7 +47,6 @@ TEST(wait_simple)
.flags = CLONE_PIDFD | CLONE_PARENT_SETTID,
.exit_signal = SIGCHLD,
};
- int ret;
pid_t pid;
siginfo_t info = {
.si_signo = 0,
@@ -88,7 +87,7 @@ TEST(wait_simple)
TEST(wait_states)
{
- int pidfd = -1, status = 0;
+ int pidfd = -1;
pid_t parent_tid = -1;
struct clone_args args = {
.parent_tid = ptr_to_u64(&parent_tid),
diff --git a/tools/testing/selftests/powerpc/security/mitigation-patching.sh b/tools/testing/selftests/powerpc/security/mitigation-patching.sh
index b0b20e0b4e30..f43aa4b77fba 100755
--- a/tools/testing/selftests/powerpc/security/mitigation-patching.sh
+++ b/tools/testing/selftests/powerpc/security/mitigation-patching.sh
@@ -44,7 +44,10 @@ mitigations="barrier_nospec stf_barrier count_cache_flush rfi_flush entry_flush
for m in $mitigations
do
- do_one "$m" &
+ if [[ -f /sys/kernel/debug/powerpc/$m ]]
+ then
+ do_one "$m" &
+ fi
done
echo "Spawned threads enabling/disabling mitigations ..."
diff --git a/tools/testing/selftests/powerpc/security/spectre_v2.c b/tools/testing/selftests/powerpc/security/spectre_v2.c
index adc2b7294e5f..83647b8277e7 100644
--- a/tools/testing/selftests/powerpc/security/spectre_v2.c
+++ b/tools/testing/selftests/powerpc/security/spectre_v2.c
@@ -193,7 +193,7 @@ int spectre_v2_test(void)
* We are not vulnerable and reporting otherwise, so
* missing such a mismatch is safe.
*/
- if (state == VULNERABLE)
+ if (miss_percent > 95)
return 4;
return 1;
diff --git a/tools/testing/selftests/powerpc/signal/.gitignore b/tools/testing/selftests/powerpc/signal/.gitignore
index ce3375cd8e73..9d0915777fed 100644
--- a/tools/testing/selftests/powerpc/signal/.gitignore
+++ b/tools/testing/selftests/powerpc/signal/.gitignore
@@ -4,3 +4,5 @@ signal_tm
sigfuz
sigreturn_vdso
sig_sc_double_restart
+sigreturn_kernel
+sigreturn_unaligned
diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile
index d6ae54663aed..f679d260afc8 100644
--- a/tools/testing/selftests/powerpc/signal/Makefile
+++ b/tools/testing/selftests/powerpc/signal/Makefile
@@ -1,5 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
TEST_GEN_PROGS := signal signal_tm sigfuz sigreturn_vdso sig_sc_double_restart
+TEST_GEN_PROGS += sigreturn_kernel
+TEST_GEN_PROGS += sigreturn_unaligned
CFLAGS += -maltivec
$(OUTPUT)/signal_tm: CFLAGS += -mhtm
diff --git a/tools/testing/selftests/powerpc/signal/sigreturn_kernel.c b/tools/testing/selftests/powerpc/signal/sigreturn_kernel.c
new file mode 100644
index 000000000000..0a1b6e591eee
--- /dev/null
+++ b/tools/testing/selftests/powerpc/signal/sigreturn_kernel.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that we can't sigreturn to kernel addresses, or to kernel mode.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+#define MSR_PR (1ul << 14)
+
+static volatile unsigned long long sigreturn_addr;
+static volatile unsigned long long sigreturn_msr_mask;
+
+static void sigusr1_handler(int signo, siginfo_t *si, void *uc_ptr)
+{
+ ucontext_t *uc = (ucontext_t *)uc_ptr;
+
+ if (sigreturn_addr)
+ UCONTEXT_NIA(uc) = sigreturn_addr;
+
+ if (sigreturn_msr_mask)
+ UCONTEXT_MSR(uc) &= sigreturn_msr_mask;
+}
+
+static pid_t fork_child(void)
+{
+ pid_t pid;
+
+ pid = fork();
+ if (pid == 0) {
+ raise(SIGUSR1);
+ exit(0);
+ }
+
+ return pid;
+}
+
+static int expect_segv(pid_t pid)
+{
+ int child_ret;
+
+ waitpid(pid, &child_ret, 0);
+ FAIL_IF(WIFEXITED(child_ret));
+ FAIL_IF(!WIFSIGNALED(child_ret));
+ FAIL_IF(WTERMSIG(child_ret) != 11);
+
+ return 0;
+}
+
+int test_sigreturn_kernel(void)
+{
+ struct sigaction act;
+ int child_ret, i;
+ pid_t pid;
+
+ act.sa_sigaction = sigusr1_handler;
+ act.sa_flags = SA_SIGINFO;
+ sigemptyset(&act.sa_mask);
+
+ FAIL_IF(sigaction(SIGUSR1, &act, NULL));
+
+ for (i = 0; i < 2; i++) {
+ // Return to kernel
+ sigreturn_addr = 0xcull << 60;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to kernel virtual
+ sigreturn_addr = 0xc008ull << 48;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return out of range
+ sigreturn_addr = 0xc010ull << 48;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to no-man's land, just below PAGE_OFFSET
+ sigreturn_addr = (0xcull << 60) - (64 * 1024);
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to no-man's land, above TASK_SIZE_4PB
+ sigreturn_addr = 0x1ull << 52;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to 0xd space
+ sigreturn_addr = 0xdull << 60;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to 0xe space
+ sigreturn_addr = 0xeull << 60;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Return to 0xf space
+ sigreturn_addr = 0xfull << 60;
+ pid = fork_child();
+ expect_segv(pid);
+
+ // Attempt to set PR=0 for 2nd loop (should be blocked by kernel)
+ sigreturn_msr_mask = ~MSR_PR;
+ }
+
+ printf("All children killed as expected\n");
+
+ // Don't change address, just MSR, should return to user as normal
+ sigreturn_addr = 0;
+ sigreturn_msr_mask = ~MSR_PR;
+ pid = fork_child();
+ waitpid(pid, &child_ret, 0);
+ FAIL_IF(!WIFEXITED(child_ret));
+ FAIL_IF(WIFSIGNALED(child_ret));
+ FAIL_IF(WEXITSTATUS(child_ret) != 0);
+
+ return 0;
+}
+
+int main(void)
+{
+ return test_harness(test_sigreturn_kernel, "sigreturn_kernel");
+}
diff --git a/tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c b/tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c
new file mode 100644
index 000000000000..6e58ee4f0fdf
--- /dev/null
+++ b/tools/testing/selftests/powerpc/signal/sigreturn_unaligned.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test sigreturn to an unaligned address, ie. low 2 bits set.
+ * Nothing bad should happen.
+ * This was able to trigger warnings with CONFIG_PPC_RFI_SRR_DEBUG=y.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ucontext.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+
+static void sigusr1_handler(int signo, siginfo_t *info, void *ptr)
+{
+ ucontext_t *uc = ptr;
+
+ UCONTEXT_NIA(uc) |= 3;
+}
+
+static int test_sigreturn_unaligned(void)
+{
+ struct sigaction action;
+
+ memset(&action, 0, sizeof(action));
+ action.sa_sigaction = sigusr1_handler;
+ action.sa_flags = SA_SIGINFO;
+
+ FAIL_IF(sigaction(SIGUSR1, &action, NULL) == -1);
+
+ raise(SIGUSR1);
+
+ return 0;
+}
+
+int main(void)
+{
+ return test_harness(test_sigreturn_unaligned, "sigreturn_unaligned");
+}
diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh
index e6a132df6172..69f8a5958cef 100755
--- a/tools/testing/selftests/rcutorture/bin/console-badness.sh
+++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh
@@ -10,7 +10,7 @@
#
# Authors: Paul E. McKenney <[email protected]>
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' |
+egrep 'Badness|WARNING:|Warn|BUG|===========|BUG: KCSAN:|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' |
grep -v 'ODEBUG: ' |
grep -v 'This means that this is a DEBUG kernel and it is' |
grep -v 'Warning: unable to open an initial console' |
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-again.sh b/tools/testing/selftests/rcutorture/bin/kvm-again.sh
index 5a0023d183da..0941f1ddab65 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-again.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-again.sh
@@ -47,8 +47,8 @@ else
exit 1
fi
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
dryrun=
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
index 370406bbfeed..f17000a2ccf1 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
@@ -49,8 +49,8 @@ fi
mkdir $resdir/$ds
echo Results directory: $resdir/$ds
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
echo Using all `identify_qemu_vcpus` CPUs.
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh b/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh
index e4a00779b8c6..ee886b40a5d2 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-end-run-stats.sh
@@ -22,8 +22,8 @@ T=${TMPDIR-/tmp}/kvm-end-run-stats.sh.$$
trap 'rm -rf $T' 0
mkdir $T
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
default_starttime="`get_starttime`"
starttime="${2-default_starttime}"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
index 2e9e9e2eedb6..5f682fc892dd 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -30,10 +30,16 @@ editor=${EDITOR-vi}
files=
for i in ${rundir}/*/Make.out
do
+ scenariodir="`dirname $i`"
+ scenariobasedir="`echo ${scenariodir} | sed -e 's/\.[0-9]*$//'`"
if egrep -q "error:|warning:|^ld: .*undefined reference to" < $i
then
egrep "error:|warning:|^ld: .*undefined reference to" < $i > $i.diags
files="$files $i.diags $i"
+ elif ! test -f ${scenariobasedir}/vmlinux
+ then
+ echo No ${scenariobasedir}/vmlinux file > $i.diags
+ files="$files $i.diags $i"
fi
done
if test -n "$files"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 1c4c2c727dad..43e1387234d1 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -25,7 +25,7 @@ stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null |
tail -1 | sed -e 's/^\[[ 0-9.]*] //' |
awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' |
tr -d '\012\015'`"
-fwdprog="`grep 'rcu_torture_fwd_prog n_max_cbs: ' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k3nr | head -1 | awk '{ print $2 " " $3 }'`"
+fwdprog="`grep 'rcu_torture_fwd_prog n_max_cbs: ' $i/console.log 2> /dev/null | sed -e 's/^\[[^]]*] //' | sort -k3nr | head -1 | awk '{ print $2 " " $3 }' | tr -d '\015'`"
if test -z "$ngps"
then
echo "$configfile ------- " $stopstate
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
index e09b1bc78708..8c4c1e4792d0 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
@@ -19,8 +19,8 @@ then
exit 1
fi
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
starttime="`get_starttime`"
@@ -108,8 +108,8 @@ else
cat $T/kvm-again.sh.out | tee -a "$oldrun/remote-log"
exit 2
fi
- cp -a "$rundir" "$KVM/res/"
- oldrun="$KVM/res/$ds"
+ cp -a "$rundir" "$RCUTORTURE/res/"
+ oldrun="$RCUTORTURE/res/$ds"
fi
echo | tee -a "$oldrun/remote-log"
echo " ----" kvm-again.sh output: "(`date`)" | tee -a "$oldrun/remote-log"
@@ -155,18 +155,23 @@ do
echo Downloading tarball to $i `date` | tee -a "$oldrun/remote-log"
cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -"
ret=$?
- if test "$ret" -ne 0
- then
- echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. | tee -a "$oldrun/remote-log"
+ tries=0
+ while test "$ret" -ne 0
+ do
+ echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. $tries prior retries. | tee -a "$oldrun/remote-log"
sleep 60
cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -"
ret=$?
if test "$ret" -ne 0
then
- echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log"
- exit 10
+ if test "$tries" > 5
+ then
+ echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log"
+ exit 10
+ fi
fi
- fi
+ tries=$((tries+1))
+ done
done
# Function to check for presence of a file on the specified system.
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 6de0c183db5b..55b2c1533282 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -25,15 +25,15 @@ LANG=en_US.UTF-8; export LANG
dur=$((30*60))
dryrun=""
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`"
TORTURE_DEFCONFIG=defconfig
TORTURE_BOOT_IMAGE=""
TORTURE_BUILDONLY=
-TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
+TORTURE_INITRD="$RCUTORTURE/initrd"; export TORTURE_INITRD
TORTURE_KCONFIG_ARG=""
TORTURE_KCONFIG_GDB_ARG=""
TORTURE_BOOT_GDB_ARG=""
@@ -262,7 +262,7 @@ else
exit 1
fi
-CONFIGFRAG=${KVM}/configs/${TORTURE_SUITE}; export CONFIGFRAG
+CONFIGFRAG=${RCUTORTURE}/configs/${TORTURE_SUITE}; export CONFIGFRAG
defaultconfigs="`tr '\012' ' ' < $CONFIGFRAG/CFLIST`"
if test -z "$configs"
@@ -272,7 +272,7 @@ fi
if test -z "$resdir"
then
- resdir=$KVM/res
+ resdir=$RCUTORTURE/res
fi
# Create a file of test-name/#cpus pairs, sorted by decreasing #cpus.
@@ -280,7 +280,7 @@ configs_derep=
for CF in $configs
do
case $CF in
- [0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**)
+ [0-9]\**|[0-9][0-9]\**|[0-9][0-9][0-9]\**|[0-9][0-9][0-9][0-9]\**)
config_reps=`echo $CF | sed -e 's/\*.*$//'`
CF1=`echo $CF | sed -e 's/^[^*]*\*//'`
;;
@@ -386,7 +386,7 @@ END {
# Generate a script to execute the tests in appropriate batches.
cat << ___EOF___ > $T/script
CONFIGFRAG="$CONFIGFRAG"; export CONFIGFRAG
-KVM="$KVM"; export KVM
+RCUTORTURE="$RCUTORTURE"; export RCUTORTURE
PATH="$PATH"; export PATH
TORTURE_ALLOTED_CPUS="$TORTURE_ALLOTED_CPUS"; export TORTURE_ALLOTED_CPUS
TORTURE_BOOT_IMAGE="$TORTURE_BOOT_IMAGE"; export TORTURE_BOOT_IMAGE
@@ -569,7 +569,7 @@ ___EOF___
awk < $T/cfgcpu.pack \
-v TORTURE_BUILDONLY="$TORTURE_BUILDONLY" \
-v CONFIGDIR="$CONFIGFRAG/" \
- -v KVM="$KVM" \
+ -v RCUTORTURE="$RCUTORTURE" \
-v ncpus=$cpus \
-v jitter="$jitter" \
-v rd=$resdir/$ds/ \
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 9f624bd53c27..822eb037a057 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -138,6 +138,16 @@ then
then
summary="$summary Bugs: $n_bugs"
fi
+ n_kcsan=`egrep -c 'BUG: KCSAN: ' $file`
+ if test "$n_kcsan" -ne 0
+ then
+ if test "$n_bugs" = "$n_kcsan"
+ then
+ summary="$summary (all bugs kcsan)"
+ else
+ summary="$summary KCSAN: $n_kcsan"
+ fi
+ fi
n_calltrace=`grep -c 'Call Trace:' $file`
if test "$n_calltrace" -ne 0
then
diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh
index eae88aacca2a..bfe09e2829c8 100755
--- a/tools/testing/selftests/rcutorture/bin/torture.sh
+++ b/tools/testing/selftests/rcutorture/bin/torture.sh
@@ -13,8 +13,8 @@
scriptname=$0
args="$*"
-KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
-PATH=${KVM}/bin:$PATH; export PATH
+RCUTORTURE="`pwd`/tools/testing/selftests/rcutorture"; export RCUTORTURE
+PATH=${RCUTORTURE}/bin:$PATH; export PATH
. functions.sh
TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`"
@@ -37,7 +37,7 @@ configs_scftorture=
kcsan_kmake_args=
# Default compression, duration, and apportionment.
-compress_kasan_vmlinux="`identify_qemu_vcpus`"
+compress_concurrency="`identify_qemu_vcpus`"
duration_base=10
duration_rcutorture_frac=7
duration_locktorture_frac=1
@@ -67,12 +67,12 @@ function doyesno () {
usage () {
echo "Usage: $scriptname optional arguments:"
- echo " --compress-kasan-vmlinux concurrency"
+ echo " --compress-concurrency concurrency"
echo " --configs-rcutorture \"config-file list w/ repeat factor (3*TINY01)\""
echo " --configs-locktorture \"config-file list w/ repeat factor (10*LOCK01)\""
echo " --configs-scftorture \"config-file list w/ repeat factor (2*CFLIST)\""
- echo " --doall"
- echo " --doallmodconfig / --do-no-allmodconfig"
+ echo " --do-all"
+ echo " --do-allmodconfig / --do-no-allmodconfig"
echo " --do-clocksourcewd / --do-no-clocksourcewd"
echo " --do-kasan / --do-no-kasan"
echo " --do-kcsan / --do-no-kcsan"
@@ -91,9 +91,9 @@ usage () {
while test $# -gt 0
do
case "$1" in
- --compress-kasan-vmlinux)
- checkarg --compress-kasan-vmlinux "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error'
- compress_kasan_vmlinux=$2
+ --compress-concurrency)
+ checkarg --compress-concurrency "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error'
+ compress_concurrency=$2
shift
;;
--config-rcutorture|--configs-rcutorture)
@@ -414,8 +414,14 @@ nfailures=0
echo FAILURES: | tee -a $T/log
if test -s "$T/failures"
then
- cat "$T/failures" | tee -a $T/log
+ awk < "$T/failures" -v sq="'" '{ print "echo " sq $0 sq; print "sed -e " sq "1,/^ --- .* Test summary:$/d" sq " " $2 "/log | grep Summary: | sed -e " sq "s/^[^S]*/ /" sq; }' | sh | tee -a $T/log | tee "$T/failuresum"
nfailures="`wc -l "$T/failures" | awk '{ print $1 }'`"
+ grep "^ Summary: " "$T/failuresum" |
+ grep -v '^ Summary: Bugs: [0-9]* (all bugs kcsan)$' > "$T/nonkcsan"
+ if test -s "$T/nonkcsan"
+ then
+ nonkcsanbug="yes"
+ fi
ret=2
fi
if test "$do_kcsan" = "yes"
@@ -424,12 +430,16 @@ then
fi
echo Started at $startdate, ended at `date`, duration `get_starttime_duration $starttime`. | tee -a $T/log
echo Summary: Successes: $nsuccesses Failures: $nfailures. | tee -a $T/log
+if test -z "$nonkcsanbug" && test -s "$T/failuresum"
+then
+ echo " All bugs were KCSAN failures."
+fi
tdir="`cat $T/successes $T/failures | head -1 | awk '{ print $NF }' | sed -e 's,/[^/]\+/*$,,'`"
-if test -n "$tdir" && test $compress_kasan_vmlinux -gt 0
+if test -n "$tdir" && test $compress_concurrency -gt 0
then
# KASAN vmlinux files can approach 1GB in size, so compress them.
- echo Looking for KASAN files to compress: `date` > "$tdir/log-xz" 2>&1
- find "$tdir" -type d -name '*-kasan' -print > $T/xz-todo
+ echo Looking for K[AC]SAN files to compress: `date` > "$tdir/log-xz" 2>&1
+ find "$tdir" -type d -name '*-k[ac]san' -print > $T/xz-todo
ncompresses=0
batchno=1
if test -s $T/xz-todo
@@ -447,7 +457,7 @@ then
do
xz "$j" >> "$tdir/log-xz" 2>&1 &
ncompresses=$((ncompresses+1))
- if test $ncompresses -ge $compress_kasan_vmlinux
+ if test $ncompresses -ge $compress_concurrency
then
echo Waiting for batch $batchno of $ncompresses compressions `date` | tee -a "$tdir/log-xz" | tee -a $T/log
wait
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
index 3ca112444ce7..7093422050f6 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
@@ -1,5 +1,5 @@
CONFIG_SMP=y
-CONFIG_NR_CPUS=4
+CONFIG_NR_CPUS=3
CONFIG_HOTPLUG_CPU=y
CONFIG_PREEMPT_NONE=n
CONFIG_PREEMPT_VOLUNTARY=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot
index 238bfe3bd0cc..ce0694fd9b92 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N.boot
@@ -1 +1,2 @@
rcutorture.torture_type=srcu
+rcutorture.fwd_progress=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
index ce48c7b82673..2db39f298d18 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-P.boot
@@ -1,2 +1,4 @@
rcutorture.torture_type=srcud
rcupdate.rcu_self_test=1
+rcutorture.fwd_progress=3
+srcutree.big_cpu_lim=5
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
index 34c8ff5a12f2..e4d74e5fc1d0 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
@@ -1,5 +1,5 @@
CONFIG_SMP=y
-CONFIG_NR_CPUS=4
+CONFIG_NR_CPUS=5
CONFIG_HOTPLUG_CPU=y
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 2af9d39a9716..215e1067f037 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -6,7 +6,7 @@ endif
CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \
$(CLANG_FLAGS)
-LDLIBS += -lpthread
+LDLIBS += -lpthread -ldl
# Own dependencies because we only want to build against 1st prerequisite, but
# still track changes to header files and depend on shared object.
diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
index b953a52ff706..517756afc2a4 100644
--- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c
+++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c
@@ -167,7 +167,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
for (;;) {
struct percpu_list_node *head;
intptr_t *targetptr, expectnot, *load;
- off_t offset;
+ long offset;
int ret, cpu;
cpu = rseq_cpu_start();
diff --git a/tools/testing/selftests/rseq/compiler.h b/tools/testing/selftests/rseq/compiler.h
new file mode 100644
index 000000000000..876eb6a7f75b
--- /dev/null
+++ b/tools/testing/selftests/rseq/compiler.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq/compiler.h
+ *
+ * Work-around asm goto compiler bugs.
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <[email protected]>
+ */
+
+#ifndef RSEQ_COMPILER_H
+#define RSEQ_COMPILER_H
+
+/*
+ * gcc prior to 4.8.2 miscompiles asm goto.
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * gcc prior to 8.1.0 miscompiles asm goto at O1.
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103908
+ *
+ * clang prior to version 13.0.1 miscompiles asm goto at O2.
+ * https://github.com/llvm/llvm-project/issues/52735
+ *
+ * Work around these issues by adding a volatile inline asm with
+ * memory clobber in the fallthrough after the asm goto and at each
+ * label target. Emit this for all compilers in case other similar
+ * issues are found in the future.
+ */
+#define rseq_after_asm_goto() asm volatile ("" : : : "memory")
+
+#endif /* RSEQ_COMPILER_H_ */
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 699ad5f93c34..da23c22d5882 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -161,7 +161,7 @@ unsigned int yield_mod_cnt, nr_abort;
" cbnz " INJECT_ASM_REG ", 222b\n" \
"333:\n"
-#elif __PPC__
+#elif defined(__PPC__)
#define RSEQ_INJECT_INPUT \
, [loop_cnt_1]"m"(loop_cnt[1]) \
@@ -368,9 +368,7 @@ void *test_percpu_spinlock_thread(void *arg)
abort();
reps = thread_data->reps;
for (i = 0; i < reps; i++) {
- int cpu = rseq_cpu_start();
-
- cpu = rseq_this_cpu_lock(&data->lock);
+ int cpu = rseq_this_cpu_lock(&data->lock);
data->c[cpu].count++;
rseq_percpu_unlock(&data->lock, cpu);
#ifndef BENCHMARK
@@ -551,7 +549,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
for (;;) {
struct percpu_list_node *head;
intptr_t *targetptr, expectnot, *load;
- off_t offset;
+ long offset;
int ret;
cpu = rseq_cpu_start();
diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h
new file mode 100644
index 000000000000..a8c44d9af71f
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-abi.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _RSEQ_ABI_H
+#define _RSEQ_ABI_H
+
+/*
+ * rseq-abi.h
+ *
+ * Restartable sequences system call API
+ *
+ * Copyright (c) 2015-2022 Mathieu Desnoyers <[email protected]>
+ */
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+enum rseq_abi_cpu_id_state {
+ RSEQ_ABI_CPU_ID_UNINITIALIZED = -1,
+ RSEQ_ABI_CPU_ID_REGISTRATION_FAILED = -2,
+};
+
+enum rseq_abi_flags {
+ RSEQ_ABI_FLAG_UNREGISTER = (1 << 0),
+};
+
+enum rseq_abi_cs_flags_bit {
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT = 0,
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT = 1,
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT = 2,
+};
+
+enum rseq_abi_cs_flags {
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT =
+ (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT),
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL =
+ (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT),
+ RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE =
+ (1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
+};
+
+/*
+ * struct rseq_abi_cs is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line. It is usually declared as
+ * link-time constant data.
+ */
+struct rseq_abi_cs {
+ /* Version of this structure. */
+ __u32 version;
+ /* enum rseq_abi_cs_flags */
+ __u32 flags;
+ __u64 start_ip;
+ /* Offset from start_ip. */
+ __u64 post_commit_offset;
+ __u64 abort_ip;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+/*
+ * struct rseq_abi is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line.
+ *
+ * A single struct rseq_abi per thread is allowed.
+ */
+struct rseq_abi {
+ /*
+ * Restartable sequences cpu_id_start field. Updated by the
+ * kernel. Read by user-space with single-copy atomicity
+ * semantics. This field should only be read by the thread which
+ * registered this data structure. Aligned on 32-bit. Always
+ * contains a value in the range of possible CPUs, although the
+ * value may not be the actual current CPU (e.g. if rseq is not
+ * initialized). This CPU number value should always be compared
+ * against the value of the cpu_id field before performing a rseq
+ * commit or returning a value read from a data structure indexed
+ * using the cpu_id_start value.
+ */
+ __u32 cpu_id_start;
+ /*
+ * Restartable sequences cpu_id field. Updated by the kernel.
+ * Read by user-space with single-copy atomicity semantics. This
+ * field should only be read by the thread which registered this
+ * data structure. Aligned on 32-bit. Values
+ * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED
+ * have a special semantic: the former means "rseq uninitialized",
+ * and latter means "rseq initialization failed". This value is
+ * meant to be read within rseq critical sections and compared
+ * with the cpu_id_start value previously read, before performing
+ * the commit instruction, or read and compared with the
+ * cpu_id_start value before returning a value loaded from a data
+ * structure indexed using the cpu_id_start value.
+ */
+ __u32 cpu_id;
+ /*
+ * Restartable sequences rseq_cs field.
+ *
+ * Contains NULL when no critical section is active for the current
+ * thread, or holds a pointer to the currently active struct rseq_cs.
+ *
+ * Updated by user-space, which sets the address of the currently
+ * active rseq_cs at the beginning of assembly instruction sequence
+ * block, and set to NULL by the kernel when it restarts an assembly
+ * instruction sequence block, as well as when the kernel detects that
+ * it is preempting or delivering a signal outside of the range
+ * targeted by the rseq_cs. Also needs to be set to NULL by user-space
+ * before reclaiming memory that contains the targeted struct rseq_cs.
+ *
+ * Read and set by the kernel. Set by user-space with single-copy
+ * atomicity semantics. This field should only be updated by the
+ * thread which registered this data structure. Aligned on 64-bit.
+ */
+ union {
+ __u64 ptr64;
+
+ /*
+ * The "arch" field provides architecture accessor for
+ * the ptr field based on architecture pointer size and
+ * endianness.
+ */
+ struct {
+#ifdef __LP64__
+ __u64 ptr;
+#elif defined(__BYTE_ORDER) ? (__BYTE_ORDER == __BIG_ENDIAN) : defined(__BIG_ENDIAN)
+ __u32 padding; /* Initialized to zero. */
+ __u32 ptr;
+#else
+ __u32 ptr;
+ __u32 padding; /* Initialized to zero. */
+#endif
+ } arch;
+ } rseq_cs;
+
+ /*
+ * Restartable sequences flags field.
+ *
+ * This field should only be updated by the thread which
+ * registered this data structure. Read by the kernel.
+ * Mainly used for single-stepping through rseq critical sections
+ * with debuggers.
+ *
+ * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT
+ * Inhibit instruction sequence block restart on preemption
+ * for this thread.
+ * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL
+ * Inhibit instruction sequence block restart on signal
+ * delivery for this thread.
+ * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE
+ * Inhibit instruction sequence block restart on migration for
+ * this thread.
+ */
+ __u32 flags;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+#endif /* _RSEQ_ABI_H */
diff --git a/tools/testing/selftests/rseq/rseq-arm.h b/tools/testing/selftests/rseq/rseq-arm.h
index 5943c816c07c..893a11eca9d5 100644
--- a/tools/testing/selftests/rseq/rseq-arm.h
+++ b/tools/testing/selftests/rseq/rseq-arm.h
@@ -147,14 +147,11 @@ do { \
teardown \
"b %l[" __rseq_str(cmpfail_label) "]\n\t"
-#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("")
-
static inline __attribute__((always_inline))
int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -185,8 +182,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -198,30 +195,31 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -255,8 +253,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -270,19 +268,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -292,7 +292,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
#ifdef RSEQ_COMPARE_TWICE
@@ -316,8 +315,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[count] "Ir" (count)
RSEQ_INJECT_INPUT
@@ -328,14 +327,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -347,7 +347,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -381,8 +380,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -398,19 +397,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -422,7 +423,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -457,8 +457,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -474,19 +474,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -498,7 +500,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -537,8 +538,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -554,21 +555,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("1st expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -582,7 +586,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -657,8 +660,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
"8:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -678,21 +681,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -706,7 +709,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -782,8 +784,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
"8:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -803,21 +805,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
- rseq_workaround_gcc_asm_size_guess();
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h
index 200dae9e4208..cbe190a4d005 100644
--- a/tools/testing/selftests/rseq/rseq-arm64.h
+++ b/tools/testing/selftests/rseq/rseq-arm64.h
@@ -230,8 +230,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "Qo" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -242,24 +242,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
@@ -287,8 +291,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "Qo" (*v),
[expectnot] "r" (expectnot),
[load] "Qo" (*load),
@@ -300,16 +304,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -337,8 +346,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "Qo" (*v),
[count] "r" (count)
RSEQ_INJECT_INPUT
@@ -348,12 +357,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -388,8 +400,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[expect] "r" (expect),
[v] "Qo" (*v),
[newv] "r" (newv),
@@ -402,17 +414,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -447,8 +463,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[expect] "r" (expect),
[v] "Qo" (*v),
[newv] "r" (newv),
@@ -461,17 +477,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -508,8 +528,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "Qo" (*v),
[expect] "r" (expect),
[v2] "Qo" (*v2),
@@ -522,19 +542,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -569,8 +594,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[expect] "r" (expect),
[v] "Qo" (*v),
[newv] "r" (newv),
@@ -584,17 +609,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -629,8 +658,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "Qo" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[expect] "r" (expect),
[v] "Qo" (*v),
[newv] "r" (newv),
@@ -644,17 +673,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
-
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
diff --git a/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h
new file mode 100644
index 000000000000..38c584661571
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-generic-thread-pointer.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-generic-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <[email protected]>
+ */
+
+#ifndef _RSEQ_GENERIC_THREAD_POINTER
+#define _RSEQ_GENERIC_THREAD_POINTER
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Use gcc builtin thread pointer. */
+static inline void *rseq_thread_pointer(void)
+{
+ return __builtin_thread_pointer();
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-mips.h b/tools/testing/selftests/rseq/rseq-mips.h
index e989e7c14b09..878739fae2fd 100644
--- a/tools/testing/selftests/rseq/rseq-mips.h
+++ b/tools/testing/selftests/rseq/rseq-mips.h
@@ -154,14 +154,11 @@ do { \
teardown \
"b %l[" __rseq_str(cmpfail_label) "]\n\t"
-#define rseq_workaround_gcc_asm_size_guess() __asm__ __volatile__("")
-
static inline __attribute__((always_inline))
int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -190,8 +187,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -203,14 +200,11 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
@@ -222,11 +216,10 @@ error2:
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -258,8 +251,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -273,14 +266,11 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
@@ -295,7 +285,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
#ifdef RSEQ_COMPARE_TWICE
@@ -319,8 +308,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[count] "Ir" (count)
RSEQ_INJECT_INPUT
@@ -331,10 +320,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
@@ -350,7 +337,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -382,8 +368,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -399,14 +385,11 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
@@ -423,7 +406,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -456,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -473,14 +455,11 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
@@ -497,7 +476,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
{
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -532,8 +510,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
"5:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -549,14 +527,11 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
@@ -577,7 +552,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -649,8 +623,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
"8:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -670,21 +644,16 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
- rseq_workaround_gcc_asm_size_guess();
rseq_bug("cpu_id comparison failed");
error2:
- rseq_workaround_gcc_asm_size_guess();
rseq_bug("expected value comparison failed");
#endif
}
@@ -698,7 +667,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
RSEQ_INJECT_C(9)
- rseq_workaround_gcc_asm_size_guess();
__asm__ __volatile__ goto (
RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -771,8 +739,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
"8:\n\t"
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -792,21 +760,16 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
- rseq_workaround_gcc_asm_size_guess();
return 0;
abort:
- rseq_workaround_gcc_asm_size_guess();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
- rseq_workaround_gcc_asm_size_guess();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
- rseq_workaround_gcc_asm_size_guess();
rseq_bug("cpu_id comparison failed");
error2:
- rseq_workaround_gcc_asm_size_guess();
rseq_bug("expected value comparison failed");
#endif
}
diff --git a/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h
new file mode 100644
index 000000000000..263eee84fb76
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-ppc-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <[email protected]>
+ */
+
+#ifndef _RSEQ_PPC_THREAD_POINTER
+#define _RSEQ_PPC_THREAD_POINTER
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+static inline void *rseq_thread_pointer(void)
+{
+#ifdef __powerpc64__
+ register void *__result asm ("r13");
+#else
+ register void *__result asm ("r2");
+#endif
+ asm ("" : "=r" (__result));
+ return __result;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-ppc.h b/tools/testing/selftests/rseq/rseq-ppc.h
index 76be90196fe4..bab8e0b9fb11 100644
--- a/tools/testing/selftests/rseq/rseq-ppc.h
+++ b/tools/testing/selftests/rseq/rseq-ppc.h
@@ -47,10 +47,13 @@ do { \
#ifdef __PPC64__
-#define STORE_WORD "std "
-#define LOAD_WORD "ld "
-#define LOADX_WORD "ldx "
-#define CMP_WORD "cmpd "
+#define RSEQ_STORE_LONG(arg) "std%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */
+#define RSEQ_STORE_INT(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */
+#define RSEQ_LOAD_LONG(arg) "ld%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */
+#define RSEQ_LOAD_INT(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */
+#define RSEQ_LOADX_LONG "ldx " /* From base register ("b" constraint) */
+#define RSEQ_CMP_LONG "cmpd "
+#define RSEQ_CMP_LONG_INT "cmpdi "
#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \
start_ip, post_commit_offset, abort_ip) \
@@ -89,10 +92,13 @@ do { \
#else /* #ifdef __PPC64__ */
-#define STORE_WORD "stw "
-#define LOAD_WORD "lwz "
-#define LOADX_WORD "lwzx "
-#define CMP_WORD "cmpw "
+#define RSEQ_STORE_LONG(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */
+#define RSEQ_STORE_INT(arg) RSEQ_STORE_LONG(arg) /* To memory ("m" constraint) */
+#define RSEQ_LOAD_LONG(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */
+#define RSEQ_LOAD_INT(arg) RSEQ_LOAD_LONG(arg) /* From memory ("m" constraint) */
+#define RSEQ_LOADX_LONG "lwzx " /* From base register ("b" constraint) */
+#define RSEQ_CMP_LONG "cmpw "
+#define RSEQ_CMP_LONG_INT "cmpwi "
#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \
start_ip, post_commit_offset, abort_ip) \
@@ -125,7 +131,7 @@ do { \
RSEQ_INJECT_ASM(1) \
"lis %%r17, (" __rseq_str(cs_label) ")@ha\n\t" \
"addi %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t" \
- "stw %%r17, %[" __rseq_str(rseq_cs) "]\n\t" \
+ RSEQ_STORE_INT(rseq_cs) "%%r17, %[" __rseq_str(rseq_cs) "]\n\t" \
__rseq_str(label) ":\n\t"
#endif /* #ifdef __PPC64__ */
@@ -136,7 +142,7 @@ do { \
#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \
RSEQ_INJECT_ASM(2) \
- "lwz %%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \
+ RSEQ_LOAD_INT(current_cpu_id) "%%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \
"cmpw cr7, %[" __rseq_str(cpu_id) "], %%r17\n\t" \
"bne- cr7, " __rseq_str(label) "\n\t"
@@ -153,25 +159,25 @@ do { \
* RSEQ_ASM_OP_* (else): doesn't have hard-code registers(unless cr7)
*/
#define RSEQ_ASM_OP_CMPEQ(var, expect, label) \
- LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \
- CMP_WORD "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \
+ RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \
+ RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \
"bne- cr7, " __rseq_str(label) "\n\t"
#define RSEQ_ASM_OP_CMPNE(var, expectnot, label) \
- LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \
- CMP_WORD "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \
+ RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \
+ RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \
"beq- cr7, " __rseq_str(label) "\n\t"
#define RSEQ_ASM_OP_STORE(value, var) \
- STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t"
+ RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t"
/* Load @var to r17 */
#define RSEQ_ASM_OP_R_LOAD(var) \
- LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t"
+ RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"
/* Store r17 to @var */
#define RSEQ_ASM_OP_R_STORE(var) \
- STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t"
+ RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"
/* Add @count to r17 */
#define RSEQ_ASM_OP_R_ADD(count) \
@@ -179,11 +185,11 @@ do { \
/* Load (r17 + voffp) to r17 */
#define RSEQ_ASM_OP_R_LOADX(voffp) \
- LOADX_WORD "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t"
+ RSEQ_LOADX_LONG "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t"
/* TODO: implement a faster memcpy. */
#define RSEQ_ASM_OP_R_MEMCPY() \
- "cmpdi %%r19, 0\n\t" \
+ RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \
"beq 333f\n\t" \
"addi %%r20, %%r20, -1\n\t" \
"addi %%r21, %%r21, -1\n\t" \
@@ -191,16 +197,16 @@ do { \
"lbzu %%r18, 1(%%r20)\n\t" \
"stbu %%r18, 1(%%r21)\n\t" \
"addi %%r19, %%r19, -1\n\t" \
- "cmpdi %%r19, 0\n\t" \
+ RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \
"bne 222b\n\t" \
"333:\n\t" \
#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label) \
- STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \
+ RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \
__rseq_str(post_commit_label) ":\n\t"
#define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label) \
- STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \
+ RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \
__rseq_str(post_commit_label) ":\n\t"
static inline __attribute__((always_inline))
@@ -235,8 +241,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -248,23 +254,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
@@ -301,8 +312,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -316,16 +327,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -359,8 +375,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[count] "r" (count)
@@ -372,12 +388,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -419,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -436,16 +455,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -489,8 +513,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -506,16 +530,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -560,8 +589,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -577,18 +606,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("1st expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -635,8 +670,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -653,16 +688,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -711,8 +751,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -729,23 +769,23 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
-#undef STORE_WORD
-#undef LOAD_WORD
-#undef LOADX_WORD
-#undef CMP_WORD
-
#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
index 8ef94ad1cbb4..4e6dc5f0cb42 100644
--- a/tools/testing/selftests/rseq/rseq-s390.h
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -165,8 +165,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -178,16 +178,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -198,7 +203,7 @@ error2:
*/
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
@@ -233,8 +238,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -248,16 +253,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -288,8 +298,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[count] "r" (count)
@@ -301,12 +311,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -347,8 +360,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -364,16 +377,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -426,8 +444,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -443,18 +461,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("1st expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -534,8 +558,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
#endif
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [current_cpu_id] "m" (__rseq_abi.cpu_id),
- [rseq_cs] "m" (__rseq_abi.rseq_cs),
+ [current_cpu_id] "m" (rseq_get_abi()->cpu_id),
+ [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -555,16 +579,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
diff --git a/tools/testing/selftests/rseq/rseq-skip.h b/tools/testing/selftests/rseq/rseq-skip.h
index 72750b5905a9..7b53dac1fcdd 100644
--- a/tools/testing/selftests/rseq/rseq-skip.h
+++ b/tools/testing/selftests/rseq/rseq-skip.h
@@ -13,7 +13,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
return -1;
}
diff --git a/tools/testing/selftests/rseq/rseq-thread-pointer.h b/tools/testing/selftests/rseq/rseq-thread-pointer.h
new file mode 100644
index 000000000000..977c25d758b2
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-thread-pointer.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <[email protected]>
+ */
+
+#ifndef _RSEQ_THREAD_POINTER
+#define _RSEQ_THREAD_POINTER
+
+#if defined(__x86_64__) || defined(__i386__)
+#include "rseq-x86-thread-pointer.h"
+#elif defined(__PPC__)
+#include "rseq-ppc-thread-pointer.h"
+#else
+#include "rseq-generic-thread-pointer.h"
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h
new file mode 100644
index 000000000000..d3133587d996
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-x86-thread-pointer.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-x86-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <[email protected]>
+ */
+
+#ifndef _RSEQ_X86_THREAD_POINTER
+#define _RSEQ_X86_THREAD_POINTER
+
+#include <features.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#if __GNUC_PREREQ (11, 1)
+static inline void *rseq_thread_pointer(void)
+{
+ return __builtin_thread_pointer();
+}
+#else
+static inline void *rseq_thread_pointer(void)
+{
+ void *__result;
+
+# ifdef __x86_64__
+ __asm__ ("mov %%fs:0, %0" : "=r" (__result));
+# else
+ __asm__ ("mov %%gs:0, %0" : "=r" (__result));
+# endif
+ return __result;
+}
+#endif /* !GCC 11 */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rseq/rseq-x86.h b/tools/testing/selftests/rseq/rseq-x86.h
index 640411518e46..bd01dc41ca13 100644
--- a/tools/testing/selftests/rseq/rseq-x86.h
+++ b/tools/testing/selftests/rseq/rseq-x86.h
@@ -28,6 +28,8 @@
#ifdef __x86_64__
+#define RSEQ_ASM_TP_SEGMENT %%fs
+
#define rseq_smp_mb() \
__asm__ __volatile__ ("lock; addl $0,-128(%%rsp)" ::: "memory", "cc")
#define rseq_smp_rmb() rseq_barrier()
@@ -123,14 +125,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpq %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpq %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
#endif
@@ -141,7 +143,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -152,16 +154,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -172,7 +179,7 @@ error2:
*/
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
@@ -184,15 +191,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"movq %[v], %%rbx\n\t"
"cmpq %%rbx, %[expectnot]\n\t"
"je %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"movq %[v], %%rbx\n\t"
"cmpq %%rbx, %[expectnot]\n\t"
"je %l[error2]\n\t"
@@ -207,7 +214,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -220,16 +227,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -245,11 +257,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
#endif
/* final store */
"addq %[count], %[v]\n\t"
@@ -258,7 +270,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[count] "er" (count)
@@ -269,12 +281,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -286,7 +301,7 @@ error1:
* *pval += inc;
*/
static inline __attribute__((always_inline))
-int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
+int rseq_offset_deref_addv(intptr_t *ptr, long off, intptr_t inc, int cpu)
{
RSEQ_INJECT_C(9)
@@ -296,11 +311,11 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
#endif
/* get p+v */
"movq %[ptr], %%rbx\n\t"
@@ -314,7 +329,7 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[ptr] "m" (*ptr),
[off] "er" (off),
@@ -351,14 +366,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpq %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpq %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
#endif
@@ -372,7 +387,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -387,16 +402,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -426,8 +446,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpq %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
@@ -436,7 +456,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(5)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpq %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
"cmpq %[v2], %[expect2]\n\t"
@@ -449,7 +469,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -464,18 +484,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("1st expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -500,14 +526,14 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
"movq %[dst], %[rseq_scratch1]\n\t"
"movq %[len], %[rseq_scratch2]\n\t"
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpq %[v], %[expect]\n\t"
"jnz 5f\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
"cmpq %[v], %[expect]\n\t"
"jnz 7f\n\t"
#endif
@@ -555,7 +581,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
#endif
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[expect] "r" (expect),
@@ -574,16 +600,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -600,7 +631,9 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
#endif /* !RSEQ_SKIP_FASTPATH */
-#elif __i386__
+#elif defined(__i386__)
+
+#define RSEQ_ASM_TP_SEGMENT %%gs
#define rseq_smp_mb() \
__asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc")
@@ -701,14 +734,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpl %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpl %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
#endif
@@ -719,7 +752,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
[v] "m" (*v),
[expect] "r" (expect),
[newv] "r" (newv)
@@ -730,16 +763,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -750,7 +788,7 @@ error2:
*/
static inline __attribute__((always_inline))
int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
- off_t voffp, intptr_t *load, int cpu)
+ long voffp, intptr_t *load, int cpu)
{
RSEQ_INJECT_C(9)
@@ -762,15 +800,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"movl %[v], %%ebx\n\t"
"cmpl %%ebx, %[expectnot]\n\t"
"je %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"movl %[v], %%ebx\n\t"
"cmpl %%ebx, %[expectnot]\n\t"
"je %l[error2]\n\t"
@@ -785,7 +823,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[expectnot] "r" (expectnot),
@@ -798,16 +836,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -823,11 +866,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
#endif
/* final store */
"addl %[count], %[v]\n\t"
@@ -836,7 +879,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[count] "ir" (count)
@@ -847,12 +890,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
, error1
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
#endif
}
@@ -872,14 +918,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpl %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpl %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
#endif
@@ -894,7 +940,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* try store input */
[v2] "m" (*v2),
[newv2] "m" (newv2),
@@ -909,16 +955,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -938,15 +989,15 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"movl %[expect], %%eax\n\t"
"cmpl %[v], %%eax\n\t"
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"movl %[expect], %%eax\n\t"
"cmpl %[v], %%eax\n\t"
"jnz %l[error2]\n\t"
@@ -962,7 +1013,7 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* try store input */
[v2] "m" (*v2),
[newv2] "r" (newv2),
@@ -977,16 +1028,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
@@ -1008,8 +1064,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
#endif
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"cmpl %[v], %[expect]\n\t"
"jnz %l[cmpfail]\n\t"
@@ -1018,7 +1074,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
"jnz %l[cmpfail]\n\t"
RSEQ_INJECT_ASM(5)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
"cmpl %[v], %[expect]\n\t"
"jnz %l[error2]\n\t"
"cmpl %[expect2], %[v2]\n\t"
@@ -1032,7 +1088,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
RSEQ_ASM_DEFINE_ABORT(4, "", abort)
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* cmp2 input */
[v2] "m" (*v2),
[expect2] "r" (expect2),
@@ -1047,18 +1103,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
, error1, error2, error3
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("1st expected value comparison failed");
error3:
+ rseq_after_asm_goto();
rseq_bug("2nd expected value comparison failed");
#endif
}
@@ -1084,15 +1146,15 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
"movl %[dst], %[rseq_scratch1]\n\t"
"movl %[len], %[rseq_scratch2]\n\t"
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"movl %[expect], %%eax\n\t"
"cmpl %%eax, %[v]\n\t"
"jnz 5f\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
"movl %[expect], %%eax\n\t"
"cmpl %%eax, %[v]\n\t"
"jnz 7f\n\t"
@@ -1142,7 +1204,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
#endif
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[expect] "m" (expect),
@@ -1161,16 +1223,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
@@ -1196,15 +1263,15 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
"movl %[dst], %[rseq_scratch1]\n\t"
"movl %[len], %[rseq_scratch2]\n\t"
/* Start rseq by storing table entry pointer into rseq_cs. */
- RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+ RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
RSEQ_INJECT_ASM(3)
"movl %[expect], %%eax\n\t"
"cmpl %%eax, %[v]\n\t"
"jnz 5f\n\t"
RSEQ_INJECT_ASM(4)
#ifdef RSEQ_COMPARE_TWICE
- RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+ RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
"movl %[expect], %%eax\n\t"
"cmpl %%eax, %[v]\n\t"
"jnz 7f\n\t"
@@ -1255,7 +1322,7 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
#endif
: /* gcc asm goto does not allow outputs */
: [cpu_id] "r" (cpu),
- [rseq_abi] "r" (&__rseq_abi),
+ [rseq_offset] "r" (rseq_offset),
/* final store input */
[v] "m" (*v),
[expect] "m" (expect),
@@ -1274,16 +1341,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
, error1, error2
#endif
);
+ rseq_after_asm_goto();
return 0;
abort:
+ rseq_after_asm_goto();
RSEQ_INJECT_FAILED
return -1;
cmpfail:
+ rseq_after_asm_goto();
return 1;
#ifdef RSEQ_COMPARE_TWICE
error1:
+ rseq_after_asm_goto();
rseq_bug("cpu_id comparison failed");
error2:
+ rseq_after_asm_goto();
rseq_bug("expected value comparison failed");
#endif
}
diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c
index fb440dfca158..986b9458efb2 100644
--- a/tools/testing/selftests/rseq/rseq.c
+++ b/tools/testing/selftests/rseq/rseq.c
@@ -26,130 +26,124 @@
#include <assert.h>
#include <signal.h>
#include <limits.h>
+#include <dlfcn.h>
+#include <stddef.h>
#include "../kselftest.h"
#include "rseq.h"
-__thread volatile struct rseq __rseq_abi = {
- .cpu_id = RSEQ_CPU_ID_UNINITIALIZED,
-};
-
-/*
- * Shared with other libraries. This library may take rseq ownership if it is
- * still 0 when executing the library constructor. Set to 1 by library
- * constructor when handling rseq. Set to 0 in destructor if handling rseq.
- */
-int __rseq_handled;
-
-/* Whether this library have ownership of rseq registration. */
-static int rseq_ownership;
+static const ptrdiff_t *libc_rseq_offset_p;
+static const unsigned int *libc_rseq_size_p;
+static const unsigned int *libc_rseq_flags_p;
-static __thread volatile uint32_t __rseq_refcount;
+/* Offset from the thread pointer to the rseq area. */
+ptrdiff_t rseq_offset;
-static void signal_off_save(sigset_t *oldset)
-{
- sigset_t set;
- int ret;
+/* Size of the registered rseq area. 0 if the registration was
+ unsuccessful. */
+unsigned int rseq_size = -1U;
- sigfillset(&set);
- ret = pthread_sigmask(SIG_BLOCK, &set, oldset);
- if (ret)
- abort();
-}
+/* Flags used during rseq registration. */
+unsigned int rseq_flags;
-static void signal_restore(sigset_t oldset)
-{
- int ret;
+static int rseq_ownership;
- ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL);
- if (ret)
- abort();
-}
+static
+__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = {
+ .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
+};
-static int sys_rseq(volatile struct rseq *rseq_abi, uint32_t rseq_len,
+static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
int flags, uint32_t sig)
{
return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
}
-int rseq_register_current_thread(void)
+int rseq_available(void)
{
- int rc, ret = 0;
- sigset_t oldset;
+ int rc;
- if (!rseq_ownership)
+ rc = sys_rseq(NULL, 0, 0, 0);
+ if (rc != -1)
+ abort();
+ switch (errno) {
+ case ENOSYS:
return 0;
- signal_off_save(&oldset);
- if (__rseq_refcount == UINT_MAX) {
- ret = -1;
- goto end;
- }
- if (__rseq_refcount++)
- goto end;
- rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG);
- if (!rc) {
- assert(rseq_current_cpu_raw() >= 0);
- goto end;
+ case EINVAL:
+ return 1;
+ default:
+ abort();
}
- if (errno != EBUSY)
- __rseq_abi.cpu_id = RSEQ_CPU_ID_REGISTRATION_FAILED;
- ret = -1;
- __rseq_refcount--;
-end:
- signal_restore(oldset);
- return ret;
}
-int rseq_unregister_current_thread(void)
+int rseq_register_current_thread(void)
{
- int rc, ret = 0;
- sigset_t oldset;
+ int rc;
- if (!rseq_ownership)
+ if (!rseq_ownership) {
+ /* Treat libc's ownership as a successful registration. */
return 0;
- signal_off_save(&oldset);
- if (!__rseq_refcount) {
- ret = -1;
- goto end;
}
- if (--__rseq_refcount)
- goto end;
- rc = sys_rseq(&__rseq_abi, sizeof(struct rseq),
- RSEQ_FLAG_UNREGISTER, RSEQ_SIG);
- if (!rc)
- goto end;
- __rseq_refcount = 1;
- ret = -1;
-end:
- signal_restore(oldset);
- return ret;
+ rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG);
+ if (rc)
+ return -1;
+ assert(rseq_current_cpu_raw() >= 0);
+ return 0;
}
-int32_t rseq_fallback_current_cpu(void)
+int rseq_unregister_current_thread(void)
{
- int32_t cpu;
+ int rc;
- cpu = sched_getcpu();
- if (cpu < 0) {
- perror("sched_getcpu()");
- abort();
+ if (!rseq_ownership) {
+ /* Treat libc's ownership as a successful unregistration. */
+ return 0;
}
- return cpu;
+ rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
+ if (rc)
+ return -1;
+ return 0;
}
-void __attribute__((constructor)) rseq_init(void)
+static __attribute__((constructor))
+void rseq_init(void)
{
- /* Check whether rseq is handled by another library. */
- if (__rseq_handled)
+ libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset");
+ libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size");
+ libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags");
+ if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) {
+ /* rseq registration owned by glibc */
+ rseq_offset = *libc_rseq_offset_p;
+ rseq_size = *libc_rseq_size_p;
+ rseq_flags = *libc_rseq_flags_p;
+ return;
+ }
+ if (!rseq_available())
return;
- __rseq_handled = 1;
rseq_ownership = 1;
+ rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer();
+ rseq_size = sizeof(struct rseq_abi);
+ rseq_flags = 0;
}
-void __attribute__((destructor)) rseq_fini(void)
+static __attribute__((destructor))
+void rseq_exit(void)
{
if (!rseq_ownership)
return;
- __rseq_handled = 0;
+ rseq_offset = 0;
+ rseq_size = -1U;
rseq_ownership = 0;
}
+
+int32_t rseq_fallback_current_cpu(void)
+{
+ int32_t cpu;
+
+ cpu = sched_getcpu();
+ if (cpu < 0) {
+ perror("sched_getcpu()");
+ abort();
+ }
+ return cpu;
+}
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index 3f63eb362b92..9d850b290c2e 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -16,7 +16,9 @@
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
-#include <linux/rseq.h>
+#include <stddef.h>
+#include "rseq-abi.h"
+#include "compiler.h"
/*
* Empty code injection macros, override when testing.
@@ -43,8 +45,20 @@
#define RSEQ_INJECT_FAILED
#endif
-extern __thread volatile struct rseq __rseq_abi;
-extern int __rseq_handled;
+#include "rseq-thread-pointer.h"
+
+/* Offset from the thread pointer to the rseq area. */
+extern ptrdiff_t rseq_offset;
+/* Size of the registered rseq area. 0 if the registration was
+ unsuccessful. */
+extern unsigned int rseq_size;
+/* Flags used during rseq registration. */
+extern unsigned int rseq_flags;
+
+static inline struct rseq_abi *rseq_get_abi(void)
+{
+ return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset);
+}
#define rseq_likely(x) __builtin_expect(!!(x), 1)
#define rseq_unlikely(x) __builtin_expect(!!(x), 0)
@@ -108,7 +122,7 @@ int32_t rseq_fallback_current_cpu(void);
*/
static inline int32_t rseq_current_cpu_raw(void)
{
- return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id);
+ return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id);
}
/*
@@ -124,7 +138,7 @@ static inline int32_t rseq_current_cpu_raw(void)
*/
static inline uint32_t rseq_cpu_start(void)
{
- return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id_start);
+ return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id_start);
}
static inline uint32_t rseq_current_cpu(void)
@@ -139,11 +153,7 @@ static inline uint32_t rseq_current_cpu(void)
static inline void rseq_clear_rseq_cs(void)
{
-#ifdef __LP64__
- __rseq_abi.rseq_cs.ptr = 0;
-#else
- __rseq_abi.rseq_cs.ptr.ptr32 = 0;
-#endif
+ RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0);
}
/*
diff --git a/tools/testing/selftests/rtc/settings b/tools/testing/selftests/rtc/settings
index ba4d85f74cd6..a953c96aa16e 100644
--- a/tools/testing/selftests/rtc/settings
+++ b/tools/testing/selftests/rtc/settings
@@ -1 +1 @@
-timeout=90
+timeout=180
diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile
index 0ebfe8b0e147..585f7a0c10cb 100644
--- a/tools/testing/selftests/seccomp/Makefile
+++ b/tools/testing/selftests/seccomp/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -Wl,-no-as-needed -Wall
+CFLAGS += -Wl,-no-as-needed -Wall -isystem ../../../../usr/include/
LDFLAGS += -lpthread
TEST_GEN_PROGS := seccomp_bpf seccomp_benchmark
diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile
index 2956584e1e37..75af864e07b6 100644
--- a/tools/testing/selftests/sgx/Makefile
+++ b/tools/testing/selftests/sgx/Makefile
@@ -4,7 +4,7 @@ include ../lib.mk
.PHONY: all clean
-CAN_BUILD_X86_64 := $(shell ../x86/check_cc.sh $(CC) \
+CAN_BUILD_X86_64 := $(shell ../x86/check_cc.sh "$(CC)" \
../x86/trivial_64bit_program.c)
ifndef OBJCOPY
diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c
index 9d4322c946e2..006b464c8fc9 100644
--- a/tools/testing/selftests/sgx/load.c
+++ b/tools/testing/selftests/sgx/load.c
@@ -21,7 +21,7 @@
void encl_delete(struct encl *encl)
{
- struct encl_segment *heap_seg = &encl->segment_tbl[encl->nr_segments - 1];
+ struct encl_segment *heap_seg;
if (encl->encl_base)
munmap((void *)encl->encl_base, encl->encl_size);
@@ -32,10 +32,11 @@ void encl_delete(struct encl *encl)
if (encl->fd)
close(encl->fd);
- munmap(heap_seg->src, heap_seg->size);
-
- if (encl->segment_tbl)
+ if (encl->segment_tbl) {
+ heap_seg = &encl->segment_tbl[encl->nr_segments - 1];
+ munmap(heap_seg->src, heap_seg->size);
free(encl->segment_tbl);
+ }
memset(encl, 0, sizeof(*encl));
}
diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c
index 370c4995f7c4..dd74fa42302e 100644
--- a/tools/testing/selftests/sgx/main.c
+++ b/tools/testing/selftests/sgx/main.c
@@ -146,7 +146,8 @@ static bool setup_test_encl(unsigned long heap_size, struct encl *encl,
if (!encl_load("test_encl.elf", encl, heap_size)) {
encl_delete(encl);
- TH_LOG("Failed to load the test enclave.\n");
+ TH_LOG("Failed to load the test enclave.");
+ return false;
}
if (!encl_measure(encl))
@@ -185,8 +186,6 @@ static bool setup_test_encl(unsigned long heap_size, struct encl *encl,
return true;
err:
- encl_delete(encl);
-
for (i = 0; i < encl->nr_segments; i++) {
seg = &encl->segment_tbl[i];
@@ -205,7 +204,9 @@ err:
fclose(maps_file);
}
- TH_LOG("Failed to initialize the test enclave.\n");
+ TH_LOG("Failed to initialize the test enclave.");
+
+ encl_delete(encl);
return false;
}
diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py
index f34486cd7342..057a4f49c79d 100644
--- a/tools/testing/selftests/tpm2/tpm2.py
+++ b/tools/testing/selftests/tpm2/tpm2.py
@@ -56,6 +56,7 @@ TSS2_RESMGR_TPM_RC_LAYER = (11 << TSS2_RC_LAYER_SHIFT)
TPM2_CAP_HANDLES = 0x00000001
TPM2_CAP_COMMANDS = 0x00000002
+TPM2_CAP_PCRS = 0x00000005
TPM2_CAP_TPM_PROPERTIES = 0x00000006
TPM2_PT_FIXED = 0x100
@@ -712,3 +713,33 @@ class Client:
pt += 1
return handles
+
+ def get_cap_pcrs(self):
+ pcr_banks = {}
+
+ fmt = '>HII III'
+
+ cmd = struct.pack(fmt,
+ TPM2_ST_NO_SESSIONS,
+ struct.calcsize(fmt),
+ TPM2_CC_GET_CAPABILITY,
+ TPM2_CAP_PCRS, 0, 1)
+ rsp = self.send_cmd(cmd)[10:]
+ _, _, cnt = struct.unpack('>BII', rsp[:9])
+ rsp = rsp[9:]
+
+ # items are TPMS_PCR_SELECTION's
+ for i in range(0, cnt):
+ hash, sizeOfSelect = struct.unpack('>HB', rsp[:3])
+ rsp = rsp[3:]
+
+ pcrSelect = 0
+ if sizeOfSelect > 0:
+ pcrSelect, = struct.unpack('%ds' % sizeOfSelect,
+ rsp[:sizeOfSelect])
+ rsp = rsp[sizeOfSelect:]
+ pcrSelect = int.from_bytes(pcrSelect, byteorder='big')
+
+ pcr_banks[hash] = pcrSelect
+
+ return pcr_banks
diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py
index 9d764306887b..ffe98b5c8d22 100644
--- a/tools/testing/selftests/tpm2/tpm2_tests.py
+++ b/tools/testing/selftests/tpm2/tpm2_tests.py
@@ -27,7 +27,17 @@ class SmokeTest(unittest.TestCase):
result = self.client.unseal(self.root_key, blob, auth, None)
self.assertEqual(data, result)
+ def determine_bank_alg(self, mask):
+ pcr_banks = self.client.get_cap_pcrs()
+ for bank_alg, pcrSelection in pcr_banks.items():
+ if pcrSelection & mask == mask:
+ return bank_alg
+ return None
+
def test_seal_with_policy(self):
+ bank_alg = self.determine_bank_alg(1 << 16)
+ self.assertIsNotNone(bank_alg)
+
handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL)
data = ('X' * 64).encode()
@@ -35,7 +45,7 @@ class SmokeTest(unittest.TestCase):
pcrs = [16]
try:
- self.client.policy_pcr(handle, pcrs)
+ self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg)
self.client.policy_password(handle)
policy_dig = self.client.get_policy_digest(handle)
@@ -47,7 +57,7 @@ class SmokeTest(unittest.TestCase):
handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY)
try:
- self.client.policy_pcr(handle, pcrs)
+ self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg)
self.client.policy_password(handle)
result = self.client.unseal(self.root_key, blob, auth, handle)
@@ -72,6 +82,9 @@ class SmokeTest(unittest.TestCase):
self.assertEqual(rc, tpm2.TPM2_RC_AUTH_FAIL)
def test_unseal_with_wrong_policy(self):
+ bank_alg = self.determine_bank_alg(1 << 16 | 1 << 1)
+ self.assertIsNotNone(bank_alg)
+
handle = self.client.start_auth_session(tpm2.TPM2_SE_TRIAL)
data = ('X' * 64).encode()
@@ -79,7 +92,7 @@ class SmokeTest(unittest.TestCase):
pcrs = [16]
try:
- self.client.policy_pcr(handle, pcrs)
+ self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg)
self.client.policy_password(handle)
policy_dig = self.client.get_policy_digest(handle)
@@ -91,13 +104,13 @@ class SmokeTest(unittest.TestCase):
# Extend first a PCR that is not part of the policy and try to unseal.
# This should succeed.
- ds = tpm2.get_digest_size(tpm2.TPM2_ALG_SHA1)
- self.client.extend_pcr(1, ('X' * ds).encode())
+ ds = tpm2.get_digest_size(bank_alg)
+ self.client.extend_pcr(1, ('X' * ds).encode(), bank_alg=bank_alg)
handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY)
try:
- self.client.policy_pcr(handle, pcrs)
+ self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg)
self.client.policy_password(handle)
result = self.client.unseal(self.root_key, blob, auth, handle)
@@ -109,14 +122,14 @@ class SmokeTest(unittest.TestCase):
# Then, extend a PCR that is part of the policy and try to unseal.
# This should fail.
- self.client.extend_pcr(16, ('X' * ds).encode())
+ self.client.extend_pcr(16, ('X' * ds).encode(), bank_alg=bank_alg)
handle = self.client.start_auth_session(tpm2.TPM2_SE_POLICY)
rc = 0
try:
- self.client.policy_pcr(handle, pcrs)
+ self.client.policy_pcr(handle, pcrs, bank_alg=bank_alg)
self.client.policy_password(handle)
result = self.client.unseal(self.root_key, blob, auth, handle)
@@ -302,3 +315,19 @@ class AsyncTest(unittest.TestCase):
log.debug("Calling get_cap in a NON_BLOCKING mode")
async_client.get_cap(tpm2.TPM2_CAP_HANDLES, tpm2.HR_LOADED_SESSION)
async_client.close()
+
+ def test_flush_invalid_context(self):
+ log = logging.getLogger(__name__)
+ log.debug(sys._getframe().f_code.co_name)
+
+ async_client = tpm2.Client(tpm2.Client.FLAG_SPACE | tpm2.Client.FLAG_NONBLOCK)
+ log.debug("Calling flush_context passing in an invalid handle ")
+ handle = 0x80123456
+ rc = 0
+ try:
+ async_client.flush_context(handle)
+ except OSError as e:
+ rc = e.errno
+
+ self.assertEqual(rc, 22)
+ async_client.close()
diff --git a/tools/testing/selftests/user_events/Makefile b/tools/testing/selftests/user_events/Makefile
new file mode 100644
index 000000000000..c765d8635d9a
--- /dev/null
+++ b/tools/testing/selftests/user_events/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wl,-no-as-needed -Wall -I../../../../usr/include
+LDLIBS += -lrt -lpthread -lm
+
+TEST_GEN_PROGS = ftrace_test dyn_test perf_test
+
+TEST_FILES := settings
+
+include ../lib.mk
diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c
new file mode 100644
index 000000000000..d6265d14cd51
--- /dev/null
+++ b/tools/testing/selftests/user_events/dyn_test.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * User Events Dyn Events Test Program
+ *
+ * Copyright (c) 2021 Beau Belgrave <[email protected]>
+ */
+
+#include <errno.h>
+#include <linux/user_events.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+const char *dyn_file = "/sys/kernel/debug/tracing/dynamic_events";
+const char *clear = "!u:__test_event";
+
+static int Append(const char *value)
+{
+ int fd = open(dyn_file, O_RDWR | O_APPEND);
+ int ret = write(fd, value, strlen(value));
+
+ close(fd);
+ return ret;
+}
+
+#define CLEAR() \
+do { \
+ int ret = Append(clear); \
+ if (ret == -1) \
+ ASSERT_EQ(ENOENT, errno); \
+} while (0)
+
+#define TEST_PARSE(x) \
+do { \
+ ASSERT_NE(-1, Append(x)); \
+ CLEAR(); \
+} while (0)
+
+#define TEST_NPARSE(x) ASSERT_EQ(-1, Append(x))
+
+FIXTURE(user) {
+};
+
+FIXTURE_SETUP(user) {
+ CLEAR();
+}
+
+FIXTURE_TEARDOWN(user) {
+ CLEAR();
+}
+
+TEST_F(user, basic_types) {
+ /* All should work */
+ TEST_PARSE("u:__test_event u64 a");
+ TEST_PARSE("u:__test_event u32 a");
+ TEST_PARSE("u:__test_event u16 a");
+ TEST_PARSE("u:__test_event u8 a");
+ TEST_PARSE("u:__test_event char a");
+ TEST_PARSE("u:__test_event unsigned char a");
+ TEST_PARSE("u:__test_event int a");
+ TEST_PARSE("u:__test_event unsigned int a");
+ TEST_PARSE("u:__test_event short a");
+ TEST_PARSE("u:__test_event unsigned short a");
+ TEST_PARSE("u:__test_event char[20] a");
+ TEST_PARSE("u:__test_event unsigned char[20] a");
+ TEST_PARSE("u:__test_event char[0x14] a");
+ TEST_PARSE("u:__test_event unsigned char[0x14] a");
+ /* Bad size format should fail */
+ TEST_NPARSE("u:__test_event char[aa] a");
+ /* Large size should fail */
+ TEST_NPARSE("u:__test_event char[9999] a");
+ /* Long size string should fail */
+ TEST_NPARSE("u:__test_event char[0x0000000000001] a");
+}
+
+TEST_F(user, loc_types) {
+ /* All should work */
+ TEST_PARSE("u:__test_event __data_loc char[] a");
+ TEST_PARSE("u:__test_event __data_loc unsigned char[] a");
+ TEST_PARSE("u:__test_event __rel_loc char[] a");
+ TEST_PARSE("u:__test_event __rel_loc unsigned char[] a");
+}
+
+TEST_F(user, size_types) {
+ /* Should work */
+ TEST_PARSE("u:__test_event struct custom a 20");
+ /* Size not specified on struct should fail */
+ TEST_NPARSE("u:__test_event struct custom a");
+ /* Size specified on non-struct should fail */
+ TEST_NPARSE("u:__test_event char a 20");
+}
+
+TEST_F(user, flags) {
+ /* Should work */
+ TEST_PARSE("u:__test_event:BPF_ITER u32 a");
+ /* Forward compat */
+ TEST_PARSE("u:__test_event:BPF_ITER,FLAG_FUTURE u32 a");
+}
+
+TEST_F(user, matching) {
+ /* Register */
+ ASSERT_NE(-1, Append("u:__test_event struct custom a 20"));
+ /* Should not match */
+ TEST_NPARSE("!u:__test_event struct custom b");
+ /* Should match */
+ TEST_PARSE("!u:__test_event struct custom a");
+ /* Multi field reg */
+ ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b"));
+ /* Non matching cases */
+ TEST_NPARSE("!u:__test_event u32 a");
+ TEST_NPARSE("!u:__test_event u32 b");
+ TEST_NPARSE("!u:__test_event u32 a; u32 ");
+ TEST_NPARSE("!u:__test_event u32 a; u32 a");
+ /* Matching case */
+ TEST_PARSE("!u:__test_event u32 a; u32 b");
+ /* Register */
+ ASSERT_NE(-1, Append("u:__test_event u32 a; u32 b"));
+ /* Ensure trailing semi-colon case */
+ TEST_PARSE("!u:__test_event u32 a; u32 b;");
+}
+
+int main(int argc, char **argv)
+{
+ return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c
new file mode 100644
index 000000000000..a80fb5ef61d5
--- /dev/null
+++ b/tools/testing/selftests/user_events/ftrace_test.c
@@ -0,0 +1,452 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * User Events FTrace Test Program
+ *
+ * Copyright (c) 2021 Beau Belgrave <[email protected]>
+ */
+
+#include <errno.h>
+#include <linux/user_events.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+const char *data_file = "/sys/kernel/debug/tracing/user_events_data";
+const char *status_file = "/sys/kernel/debug/tracing/user_events_status";
+const char *enable_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/enable";
+const char *trace_file = "/sys/kernel/debug/tracing/trace";
+const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format";
+
+static int trace_bytes(void)
+{
+ int fd = open(trace_file, O_RDONLY);
+ char buf[256];
+ int bytes = 0, got;
+
+ if (fd == -1)
+ return -1;
+
+ while (true) {
+ got = read(fd, buf, sizeof(buf));
+
+ if (got == -1)
+ return -1;
+
+ if (got == 0)
+ break;
+
+ bytes += got;
+ }
+
+ close(fd);
+
+ return bytes;
+}
+
+static int skip_until_empty_line(FILE *fp)
+{
+ int c, last = 0;
+
+ while (true) {
+ c = getc(fp);
+
+ if (c == EOF)
+ break;
+
+ if (last == '\n' && c == '\n')
+ return 0;
+
+ last = c;
+ }
+
+ return -1;
+}
+
+static int get_print_fmt(char *buffer, int len)
+{
+ FILE *fp = fopen(fmt_file, "r");
+ char *newline;
+
+ if (!fp)
+ return -1;
+
+ /* Read until empty line (Skip Common) */
+ if (skip_until_empty_line(fp) < 0)
+ goto err;
+
+ /* Read until empty line (Skip Properties) */
+ if (skip_until_empty_line(fp) < 0)
+ goto err;
+
+ /* Read in print_fmt: */
+ if (fgets(buffer, len, fp) == NULL)
+ goto err;
+
+ newline = strchr(buffer, '\n');
+
+ if (newline)
+ *newline = '\0';
+
+ fclose(fp);
+
+ return 0;
+err:
+ fclose(fp);
+
+ return -1;
+}
+
+static int clear(void)
+{
+ int fd = open(data_file, O_RDWR);
+
+ if (fd == -1)
+ return -1;
+
+ if (ioctl(fd, DIAG_IOCSDEL, "__test_event") == -1)
+ if (errno != ENOENT)
+ return -1;
+
+ close(fd);
+
+ return 0;
+}
+
+static int check_print_fmt(const char *event, const char *expected)
+{
+ struct user_reg reg = {0};
+ char print_fmt[256];
+ int ret;
+ int fd;
+
+ /* Ensure cleared */
+ ret = clear();
+
+ if (ret != 0)
+ return ret;
+
+ fd = open(data_file, O_RDWR);
+
+ if (fd == -1)
+ return fd;
+
+ reg.size = sizeof(reg);
+ reg.name_args = (__u64)event;
+
+ /* Register should work */
+ ret = ioctl(fd, DIAG_IOCSREG, &reg);
+
+ close(fd);
+
+ if (ret != 0)
+ return ret;
+
+ /* Ensure correct print_fmt */
+ ret = get_print_fmt(print_fmt, sizeof(print_fmt));
+
+ if (ret != 0)
+ return ret;
+
+ return strcmp(print_fmt, expected);
+}
+
+FIXTURE(user) {
+ int status_fd;
+ int data_fd;
+ int enable_fd;
+};
+
+FIXTURE_SETUP(user) {
+ self->status_fd = open(status_file, O_RDONLY);
+ ASSERT_NE(-1, self->status_fd);
+
+ self->data_fd = open(data_file, O_RDWR);
+ ASSERT_NE(-1, self->data_fd);
+
+ self->enable_fd = -1;
+}
+
+FIXTURE_TEARDOWN(user) {
+ close(self->status_fd);
+ close(self->data_fd);
+
+ if (self->enable_fd != -1) {
+ write(self->enable_fd, "0", sizeof("0"));
+ close(self->enable_fd);
+ }
+
+ ASSERT_EQ(0, clear());
+}
+
+TEST_F(user, register_events) {
+ struct user_reg reg = {0};
+ int page_size = sysconf(_SC_PAGESIZE);
+ char *status_page;
+
+ reg.size = sizeof(reg);
+ reg.name_args = (__u64)"__test_event u32 field1; u32 field2";
+
+ status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED,
+ self->status_fd, 0);
+
+ /* Register should work */
+ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+ ASSERT_EQ(0, reg.write_index);
+ ASSERT_NE(0, reg.status_index);
+
+ /* Multiple registers should result in same index */
+ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+ ASSERT_EQ(0, reg.write_index);
+ ASSERT_NE(0, reg.status_index);
+
+ /* Ensure disabled */
+ self->enable_fd = open(enable_file, O_RDWR);
+ ASSERT_NE(-1, self->enable_fd);
+ ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0")))
+
+ /* MMAP should work and be zero'd */
+ ASSERT_NE(MAP_FAILED, status_page);
+ ASSERT_NE(NULL, status_page);
+ ASSERT_EQ(0, status_page[reg.status_index]);
+
+ /* Enable event and ensure bits updated in status */
+ ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1")))
+ ASSERT_EQ(EVENT_STATUS_FTRACE, status_page[reg.status_index]);
+
+ /* Disable event and ensure bits updated in status */
+ ASSERT_NE(-1, write(self->enable_fd, "0", sizeof("0")))
+ ASSERT_EQ(0, status_page[reg.status_index]);
+
+ /* File still open should return -EBUSY for delete */
+ ASSERT_EQ(-1, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event"));
+ ASSERT_EQ(EBUSY, errno);
+
+ /* Delete should work only after close */
+ close(self->data_fd);
+ self->data_fd = open(data_file, O_RDWR);
+ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSDEL, "__test_event"));
+
+ /* Unmap should work */
+ ASSERT_EQ(0, munmap(status_page, page_size));
+}
+
+TEST_F(user, write_events) {
+ struct user_reg reg = {0};
+ struct iovec io[3];
+ __u32 field1, field2;
+ int before = 0, after = 0;
+
+ reg.size = sizeof(reg);
+ reg.name_args = (__u64)"__test_event u32 field1; u32 field2";
+
+ field1 = 1;
+ field2 = 2;
+
+ io[0].iov_base = &reg.write_index;
+ io[0].iov_len = sizeof(reg.write_index);
+ io[1].iov_base = &field1;
+ io[1].iov_len = sizeof(field1);
+ io[2].iov_base = &field2;
+ io[2].iov_len = sizeof(field2);
+
+ /* Register should work */
+ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+ ASSERT_EQ(0, reg.write_index);
+ ASSERT_NE(0, reg.status_index);
+
+ /* Write should fail on invalid slot with ENOENT */
+ io[0].iov_base = &field2;
+ io[0].iov_len = sizeof(field2);
+ ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+ ASSERT_EQ(ENOENT, errno);
+ io[0].iov_base = &reg.write_index;
+ io[0].iov_len = sizeof(reg.write_index);
+
+ /* Enable event */
+ self->enable_fd = open(enable_file, O_RDWR);
+ ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1")))
+
+ /* Write should make it out to ftrace buffers */
+ before = trace_bytes();
+ ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+ after = trace_bytes();
+ ASSERT_GT(after, before);
+}
+
+TEST_F(user, write_fault) {
+ struct user_reg reg = {0};
+ struct iovec io[2];
+ int l = sizeof(__u64);
+ void *anon;
+
+ reg.size = sizeof(reg);
+ reg.name_args = (__u64)"__test_event u64 anon";
+
+ anon = mmap(NULL, l, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(MAP_FAILED, anon);
+
+ io[0].iov_base = &reg.write_index;
+ io[0].iov_len = sizeof(reg.write_index);
+ io[1].iov_base = anon;
+ io[1].iov_len = l;
+
+ /* Register should work */
+ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+ ASSERT_EQ(0, reg.write_index);
+ ASSERT_NE(0, reg.status_index);
+
+ /* Write should work normally */
+ ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2));
+
+ /* Faulted data should zero fill and work */
+ ASSERT_EQ(0, madvise(anon, l, MADV_DONTNEED));
+ ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 2));
+ ASSERT_EQ(0, munmap(anon, l));
+}
+
+TEST_F(user, write_validator) {
+ struct user_reg reg = {0};
+ struct iovec io[3];
+ int loc, bytes;
+ char data[8];
+ int before = 0, after = 0;
+
+ reg.size = sizeof(reg);
+ reg.name_args = (__u64)"__test_event __rel_loc char[] data";
+
+ /* Register should work */
+ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+ ASSERT_EQ(0, reg.write_index);
+ ASSERT_NE(0, reg.status_index);
+
+ io[0].iov_base = &reg.write_index;
+ io[0].iov_len = sizeof(reg.write_index);
+ io[1].iov_base = &loc;
+ io[1].iov_len = sizeof(loc);
+ io[2].iov_base = data;
+ bytes = snprintf(data, sizeof(data), "Test") + 1;
+ io[2].iov_len = bytes;
+
+ /* Undersized write should fail */
+ ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 1));
+ ASSERT_EQ(EINVAL, errno);
+
+ /* Enable event */
+ self->enable_fd = open(enable_file, O_RDWR);
+ ASSERT_NE(-1, write(self->enable_fd, "1", sizeof("1")))
+
+ /* Full in-bounds write should work */
+ before = trace_bytes();
+ loc = DYN_LOC(0, bytes);
+ ASSERT_NE(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+ after = trace_bytes();
+ ASSERT_GT(after, before);
+
+ /* Out of bounds write should fault (offset way out) */
+ loc = DYN_LOC(1024, bytes);
+ ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+ ASSERT_EQ(EFAULT, errno);
+
+ /* Out of bounds write should fault (offset 1 byte out) */
+ loc = DYN_LOC(1, bytes);
+ ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+ ASSERT_EQ(EFAULT, errno);
+
+ /* Out of bounds write should fault (size way out) */
+ loc = DYN_LOC(0, bytes + 1024);
+ ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+ ASSERT_EQ(EFAULT, errno);
+
+ /* Out of bounds write should fault (size 1 byte out) */
+ loc = DYN_LOC(0, bytes + 1);
+ ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+ ASSERT_EQ(EFAULT, errno);
+
+ /* Non-Null should fault */
+ memset(data, 'A', sizeof(data));
+ loc = DYN_LOC(0, bytes);
+ ASSERT_EQ(-1, writev(self->data_fd, (const struct iovec *)io, 3));
+ ASSERT_EQ(EFAULT, errno);
+}
+
+TEST_F(user, print_fmt) {
+ int ret;
+
+ ret = check_print_fmt("__test_event __rel_loc char[] data",
+ "print fmt: \"data=%s\", __get_rel_str(data)");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event __data_loc char[] data",
+ "print fmt: \"data=%s\", __get_str(data)");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event s64 data",
+ "print fmt: \"data=%lld\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event u64 data",
+ "print fmt: \"data=%llu\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event s32 data",
+ "print fmt: \"data=%d\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event u32 data",
+ "print fmt: \"data=%u\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event int data",
+ "print fmt: \"data=%d\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event unsigned int data",
+ "print fmt: \"data=%u\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event s16 data",
+ "print fmt: \"data=%d\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event u16 data",
+ "print fmt: \"data=%u\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event short data",
+ "print fmt: \"data=%d\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event unsigned short data",
+ "print fmt: \"data=%u\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event s8 data",
+ "print fmt: \"data=%d\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event u8 data",
+ "print fmt: \"data=%u\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event char data",
+ "print fmt: \"data=%d\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event unsigned char data",
+ "print fmt: \"data=%u\", REC->data");
+ ASSERT_EQ(0, ret);
+
+ ret = check_print_fmt("__test_event char[4] data",
+ "print fmt: \"data=%s\", REC->data");
+ ASSERT_EQ(0, ret);
+}
+
+int main(int argc, char **argv)
+{
+ return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c
new file mode 100644
index 000000000000..26851d51d6bb
--- /dev/null
+++ b/tools/testing/selftests/user_events/perf_test.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * User Events Perf Events Test Program
+ *
+ * Copyright (c) 2021 Beau Belgrave <[email protected]>
+ */
+
+#include <errno.h>
+#include <linux/user_events.h>
+#include <linux/perf_event.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <asm/unistd.h>
+
+#include "../kselftest_harness.h"
+
+const char *data_file = "/sys/kernel/debug/tracing/user_events_data";
+const char *status_file = "/sys/kernel/debug/tracing/user_events_status";
+const char *id_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/id";
+const char *fmt_file = "/sys/kernel/debug/tracing/events/user_events/__test_event/format";
+
+struct event {
+ __u32 index;
+ __u32 field1;
+ __u32 field2;
+};
+
+static long perf_event_open(struct perf_event_attr *pe, pid_t pid,
+ int cpu, int group_fd, unsigned long flags)
+{
+ return syscall(__NR_perf_event_open, pe, pid, cpu, group_fd, flags);
+}
+
+static int get_id(void)
+{
+ FILE *fp = fopen(id_file, "r");
+ int ret, id = 0;
+
+ if (!fp)
+ return -1;
+
+ ret = fscanf(fp, "%d", &id);
+ fclose(fp);
+
+ if (ret != 1)
+ return -1;
+
+ return id;
+}
+
+static int get_offset(void)
+{
+ FILE *fp = fopen(fmt_file, "r");
+ int ret, c, last = 0, offset = 0;
+
+ if (!fp)
+ return -1;
+
+ /* Read until empty line */
+ while (true) {
+ c = getc(fp);
+
+ if (c == EOF)
+ break;
+
+ if (last == '\n' && c == '\n')
+ break;
+
+ last = c;
+ }
+
+ ret = fscanf(fp, "\tfield:u32 field1;\toffset:%d;", &offset);
+ fclose(fp);
+
+ if (ret != 1)
+ return -1;
+
+ return offset;
+}
+
+FIXTURE(user) {
+ int status_fd;
+ int data_fd;
+};
+
+FIXTURE_SETUP(user) {
+ self->status_fd = open(status_file, O_RDONLY);
+ ASSERT_NE(-1, self->status_fd);
+
+ self->data_fd = open(data_file, O_RDWR);
+ ASSERT_NE(-1, self->data_fd);
+}
+
+FIXTURE_TEARDOWN(user) {
+ close(self->status_fd);
+ close(self->data_fd);
+}
+
+TEST_F(user, perf_write) {
+ struct perf_event_attr pe = {0};
+ struct user_reg reg = {0};
+ int page_size = sysconf(_SC_PAGESIZE);
+ char *status_page;
+ struct event event;
+ struct perf_event_mmap_page *perf_page;
+ int id, fd, offset;
+ __u32 *val;
+
+ reg.size = sizeof(reg);
+ reg.name_args = (__u64)"__test_event u32 field1; u32 field2";
+
+ status_page = mmap(NULL, page_size, PROT_READ, MAP_SHARED,
+ self->status_fd, 0);
+ ASSERT_NE(MAP_FAILED, status_page);
+
+ /* Register should work */
+ ASSERT_EQ(0, ioctl(self->data_fd, DIAG_IOCSREG, &reg));
+ ASSERT_EQ(0, reg.write_index);
+ ASSERT_NE(0, reg.status_index);
+ ASSERT_EQ(0, status_page[reg.status_index]);
+
+ /* Id should be there */
+ id = get_id();
+ ASSERT_NE(-1, id);
+ offset = get_offset();
+ ASSERT_NE(-1, offset);
+
+ pe.type = PERF_TYPE_TRACEPOINT;
+ pe.size = sizeof(pe);
+ pe.config = id;
+ pe.sample_type = PERF_SAMPLE_RAW;
+ pe.sample_period = 1;
+ pe.wakeup_events = 1;
+
+ /* Tracepoint attach should work */
+ fd = perf_event_open(&pe, 0, -1, -1, 0);
+ ASSERT_NE(-1, fd);
+
+ perf_page = mmap(NULL, page_size * 2, PROT_READ, MAP_SHARED, fd, 0);
+ ASSERT_NE(MAP_FAILED, perf_page);
+
+ /* Status should be updated */
+ ASSERT_EQ(EVENT_STATUS_PERF, status_page[reg.status_index]);
+
+ event.index = reg.write_index;
+ event.field1 = 0xc001;
+ event.field2 = 0xc01a;
+
+ /* Ensure write shows up at correct offset */
+ ASSERT_NE(-1, write(self->data_fd, &event, sizeof(event)));
+ val = (void *)(((char *)perf_page) + perf_page->data_offset);
+ ASSERT_EQ(PERF_RECORD_SAMPLE, *val);
+ /* Skip over header and size, move to offset */
+ val += 3;
+ val = (void *)((char *)val) + offset;
+ /* Ensure correct */
+ ASSERT_EQ(event.field1, *val++);
+ ASSERT_EQ(event.field2, *val++);
+}
+
+int main(int argc, char **argv)
+{
+ return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/user_events/settings b/tools/testing/selftests/user_events/settings
new file mode 100644
index 000000000000..ba4d85f74cd6
--- /dev/null
+++ b/tools/testing/selftests/user_events/settings
@@ -0,0 +1 @@
+timeout=90
diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c
index 3d603f1394af..883ca85424bc 100644
--- a/tools/testing/selftests/vDSO/vdso_test_abi.c
+++ b/tools/testing/selftests/vDSO/vdso_test_abi.c
@@ -33,110 +33,114 @@ typedef long (*vdso_clock_gettime_t)(clockid_t clk_id, struct timespec *ts);
typedef long (*vdso_clock_getres_t)(clockid_t clk_id, struct timespec *ts);
typedef time_t (*vdso_time_t)(time_t *t);
-static int vdso_test_gettimeofday(void)
+#define VDSO_TEST_PASS_MSG() "\n%s(): PASS\n", __func__
+#define VDSO_TEST_FAIL_MSG(x) "\n%s(): %s FAIL\n", __func__, x
+#define VDSO_TEST_SKIP_MSG(x) "\n%s(): SKIP: Could not find %s\n", __func__, x
+
+static void vdso_test_gettimeofday(void)
{
/* Find gettimeofday. */
vdso_gettimeofday_t vdso_gettimeofday =
(vdso_gettimeofday_t)vdso_sym(version, name[0]);
if (!vdso_gettimeofday) {
- printf("Could not find %s\n", name[0]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[0]));
+ return;
}
struct timeval tv;
long ret = vdso_gettimeofday(&tv, 0);
if (ret == 0) {
- printf("The time is %lld.%06lld\n",
- (long long)tv.tv_sec, (long long)tv.tv_usec);
+ ksft_print_msg("The time is %lld.%06lld\n",
+ (long long)tv.tv_sec, (long long)tv.tv_usec);
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
} else {
- printf("%s failed\n", name[0]);
- return KSFT_FAIL;
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[0]));
}
-
- return KSFT_PASS;
}
-static int vdso_test_clock_gettime(clockid_t clk_id)
+static void vdso_test_clock_gettime(clockid_t clk_id)
{
/* Find clock_gettime. */
vdso_clock_gettime_t vdso_clock_gettime =
(vdso_clock_gettime_t)vdso_sym(version, name[1]);
if (!vdso_clock_gettime) {
- printf("Could not find %s\n", name[1]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[1]));
+ return;
}
struct timespec ts;
long ret = vdso_clock_gettime(clk_id, &ts);
if (ret == 0) {
- printf("The time is %lld.%06lld\n",
- (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ ksft_print_msg("The time is %lld.%06lld\n",
+ (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
} else {
- printf("%s failed\n", name[1]);
- return KSFT_FAIL;
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[1]));
}
-
- return KSFT_PASS;
}
-static int vdso_test_time(void)
+static void vdso_test_time(void)
{
/* Find time. */
vdso_time_t vdso_time =
(vdso_time_t)vdso_sym(version, name[2]);
if (!vdso_time) {
- printf("Could not find %s\n", name[2]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[2]));
+ return;
}
long ret = vdso_time(NULL);
if (ret > 0) {
- printf("The time in hours since January 1, 1970 is %lld\n",
+ ksft_print_msg("The time in hours since January 1, 1970 is %lld\n",
(long long)(ret / 3600));
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
} else {
- printf("%s failed\n", name[2]);
- return KSFT_FAIL;
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[2]));
}
-
- return KSFT_PASS;
}
-static int vdso_test_clock_getres(clockid_t clk_id)
+static void vdso_test_clock_getres(clockid_t clk_id)
{
+ int clock_getres_fail = 0;
+
/* Find clock_getres. */
vdso_clock_getres_t vdso_clock_getres =
(vdso_clock_getres_t)vdso_sym(version, name[3]);
if (!vdso_clock_getres) {
- printf("Could not find %s\n", name[3]);
- return KSFT_SKIP;
+ ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[3]));
+ return;
}
struct timespec ts, sys_ts;
long ret = vdso_clock_getres(clk_id, &ts);
if (ret == 0) {
- printf("The resolution is %lld %lld\n",
- (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ ksft_print_msg("The vdso resolution is %lld %lld\n",
+ (long long)ts.tv_sec, (long long)ts.tv_nsec);
} else {
- printf("%s failed\n", name[3]);
- return KSFT_FAIL;
+ clock_getres_fail++;
}
ret = syscall(SYS_clock_getres, clk_id, &sys_ts);
- if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) {
- printf("%s failed\n", name[3]);
- return KSFT_FAIL;
- }
+ ksft_print_msg("The syscall resolution is %lld %lld\n",
+ (long long)sys_ts.tv_sec, (long long)sys_ts.tv_nsec);
- return KSFT_PASS;
+ if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec))
+ clock_getres_fail++;
+
+ if (clock_getres_fail > 0) {
+ ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[3]));
+ } else {
+ ksft_test_result_pass(VDSO_TEST_PASS_MSG());
+ }
}
const char *vdso_clock_name[12] = {
@@ -158,36 +162,23 @@ const char *vdso_clock_name[12] = {
* This function calls vdso_test_clock_gettime and vdso_test_clock_getres
* with different values for clock_id.
*/
-static inline int vdso_test_clock(clockid_t clock_id)
+static inline void vdso_test_clock(clockid_t clock_id)
{
- int ret0, ret1;
-
- ret0 = vdso_test_clock_gettime(clock_id);
- /* A skipped test is considered passed */
- if (ret0 == KSFT_SKIP)
- ret0 = KSFT_PASS;
-
- ret1 = vdso_test_clock_getres(clock_id);
- /* A skipped test is considered passed */
- if (ret1 == KSFT_SKIP)
- ret1 = KSFT_PASS;
+ ksft_print_msg("\nclock_id: %s\n", vdso_clock_name[clock_id]);
- ret0 += ret1;
+ vdso_test_clock_gettime(clock_id);
- printf("clock_id: %s", vdso_clock_name[clock_id]);
-
- if (ret0 > 0)
- printf(" [FAIL]\n");
- else
- printf(" [PASS]\n");
-
- return ret0;
+ vdso_test_clock_getres(clock_id);
}
+#define VDSO_TEST_PLAN 16
+
int main(int argc, char **argv)
{
unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
- int ret;
+
+ ksft_print_header();
+ ksft_set_plan(VDSO_TEST_PLAN);
if (!sysinfo_ehdr) {
printf("AT_SYSINFO_EHDR is not present!\n");
@@ -201,44 +192,42 @@ int main(int argc, char **argv)
vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR));
- ret = vdso_test_gettimeofday();
+ vdso_test_gettimeofday();
#if _POSIX_TIMERS > 0
#ifdef CLOCK_REALTIME
- ret += vdso_test_clock(CLOCK_REALTIME);
+ vdso_test_clock(CLOCK_REALTIME);
#endif
#ifdef CLOCK_BOOTTIME
- ret += vdso_test_clock(CLOCK_BOOTTIME);
+ vdso_test_clock(CLOCK_BOOTTIME);
#endif
#ifdef CLOCK_TAI
- ret += vdso_test_clock(CLOCK_TAI);
+ vdso_test_clock(CLOCK_TAI);
#endif
#ifdef CLOCK_REALTIME_COARSE
- ret += vdso_test_clock(CLOCK_REALTIME_COARSE);
+ vdso_test_clock(CLOCK_REALTIME_COARSE);
#endif
#ifdef CLOCK_MONOTONIC
- ret += vdso_test_clock(CLOCK_MONOTONIC);
+ vdso_test_clock(CLOCK_MONOTONIC);
#endif
#ifdef CLOCK_MONOTONIC_RAW
- ret += vdso_test_clock(CLOCK_MONOTONIC_RAW);
+ vdso_test_clock(CLOCK_MONOTONIC_RAW);
#endif
#ifdef CLOCK_MONOTONIC_COARSE
- ret += vdso_test_clock(CLOCK_MONOTONIC_COARSE);
+ vdso_test_clock(CLOCK_MONOTONIC_COARSE);
#endif
#endif
- ret += vdso_test_time();
-
- if (ret > 0)
- return KSFT_FAIL;
+ vdso_test_time();
- return KSFT_PASS;
+ ksft_print_cnts();
+ return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL;
}
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 2e7e86e85282..3b5faec3c04f 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -2,6 +2,7 @@
hugepage-mmap
hugepage-mremap
hugepage-shm
+hugepage-vmemmap
khugepaged
map_hugetlb
map_populate
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 1607322a112c..81040f01711f 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,6 +1,8 @@
# SPDX-License-Identifier: GPL-2.0
# Makefile for vm selftests
+LOCAL_HDRS += $(selfdir)/vm/local_config.h $(top_srcdir)/mm/gup_test.h
+
include local_config.mk
uname_M := $(shell uname -m 2>/dev/null || echo not)
@@ -31,6 +33,7 @@ TEST_GEN_FILES += hmm-tests
TEST_GEN_FILES += hugepage-mmap
TEST_GEN_FILES += hugepage-mremap
TEST_GEN_FILES += hugepage-shm
+TEST_GEN_FILES += hugepage-vmemmap
TEST_GEN_FILES += khugepaged
TEST_GEN_FILES += madv_populate
TEST_GEN_FILES += map_fixed_noreplace
@@ -49,9 +52,9 @@ TEST_GEN_FILES += split_huge_page_test
TEST_GEN_FILES += ksm_tests
ifeq ($(MACHINE),x86_64)
-CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
-CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_64bit_program.c)
-CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_program.c -no-pie)
+CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32)
+CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c)
+CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie)
TARGETS := protection_keys
BINARIES_32 := $(TARGETS:%=%_32)
@@ -140,10 +143,6 @@ endif
$(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap
-$(OUTPUT)/gup_test: ../../../../mm/gup_test.h
-
-$(OUTPUT)/hmm-tests: local_config.h
-
# HMM_EXTRA_LIBS may get set in local_config.mk, or it may be left empty.
$(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS)
diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh
index fe8fcfb334e0..a5cb4b09a46c 100644
--- a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh
@@ -24,19 +24,23 @@ if [[ "$1" == "-cgroup-v2" ]]; then
reservation_usage_file=rsvd.current
fi
-cgroup_path=/dev/cgroup/memory
-if [[ ! -e $cgroup_path ]]; then
- mkdir -p $cgroup_path
- if [[ $cgroup2 ]]; then
+if [[ $cgroup2 ]]; then
+ cgroup_path=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+ if [[ -z "$cgroup_path" ]]; then
+ cgroup_path=/dev/cgroup/memory
mount -t cgroup2 none $cgroup_path
- else
+ do_umount=1
+ fi
+ echo "+hugetlb" >$cgroup_path/cgroup.subtree_control
+else
+ cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}')
+ if [[ -z "$cgroup_path" ]]; then
+ cgroup_path=/dev/cgroup/memory
mount -t cgroup memory,hugetlb $cgroup_path
+ do_umount=1
fi
fi
-
-if [[ $cgroup2 ]]; then
- echo "+hugetlb" >/dev/cgroup/memory/cgroup.subtree_control
-fi
+export cgroup_path
function cleanup() {
if [[ $cgroup2 ]]; then
@@ -108,7 +112,7 @@ function setup_cgroup() {
function wait_for_hugetlb_memory_to_get_depleted() {
local cgroup="$1"
- local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
+ local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
# Wait for hugetlbfs memory to get depleted.
while [ $(cat $path) != 0 ]; do
echo Waiting for hugetlb memory to get depleted.
@@ -121,7 +125,7 @@ function wait_for_hugetlb_memory_to_get_reserved() {
local cgroup="$1"
local size="$2"
- local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
+ local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$reservation_usage_file"
# Wait for hugetlbfs memory to get written.
while [ $(cat $path) != $size ]; do
echo Waiting for hugetlb memory reservation to reach size $size.
@@ -134,7 +138,7 @@ function wait_for_hugetlb_memory_to_get_written() {
local cgroup="$1"
local size="$2"
- local path="/dev/cgroup/memory/$cgroup/hugetlb.${MB}MB.$fault_usage_file"
+ local path="$cgroup_path/$cgroup/hugetlb.${MB}MB.$fault_usage_file"
# Wait for hugetlbfs memory to get written.
while [ $(cat $path) != $size ]; do
echo Waiting for hugetlb memory to reach size $size.
@@ -574,5 +578,7 @@ for populate in "" "-o"; do
done # populate
done # method
-umount $cgroup_path
-rmdir $cgroup_path
+if [[ $do_umount ]]; then
+ umount $cgroup_path
+ rmdir $cgroup_path
+fi
diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
index 864f126ffd78..203323967b50 100644
--- a/tools/testing/selftests/vm/hmm-tests.c
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -1251,6 +1251,48 @@ TEST_F(hmm, anon_teardown)
/*
* Test memory snapshot without faulting in pages accessed by the device.
*/
+TEST_F(hmm, mixedmap)
+{
+ struct hmm_buffer *buffer;
+ unsigned long npages;
+ unsigned long size;
+ unsigned char *m;
+ int ret;
+
+ npages = 1;
+ size = npages << self->page_shift;
+
+ buffer = malloc(sizeof(*buffer));
+ ASSERT_NE(buffer, NULL);
+
+ buffer->fd = -1;
+ buffer->size = size;
+ buffer->mirror = malloc(npages);
+ ASSERT_NE(buffer->mirror, NULL);
+
+
+ /* Reserve a range of addresses. */
+ buffer->ptr = mmap(NULL, size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE,
+ self->fd, 0);
+ ASSERT_NE(buffer->ptr, MAP_FAILED);
+
+ /* Simulate a device snapshotting CPU pagetables. */
+ ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_SNAPSHOT, buffer, npages);
+ ASSERT_EQ(ret, 0);
+ ASSERT_EQ(buffer->cpages, npages);
+
+ /* Check what the device saw. */
+ m = buffer->mirror;
+ ASSERT_EQ(m[0], HMM_DMIRROR_PROT_READ);
+
+ hmm_buffer_free(buffer);
+}
+
+/*
+ * Test memory snapshot without faulting in pages accessed by the device.
+ */
TEST_F(hmm2, snapshot)
{
struct hmm_buffer *buffer;
diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c
index 257df94697a5..1d689084a54b 100644
--- a/tools/testing/selftests/vm/hugepage-mremap.c
+++ b/tools/testing/selftests/vm/hugepage-mremap.c
@@ -3,8 +3,13 @@
* hugepage-mremap:
*
* Example of remapping huge page memory in a user application using the
- * mremap system call. Code assumes a hugetlbfs filesystem is mounted
- * at './huge'. The code will use 10MB worth of huge pages.
+ * mremap system call. The path to a file in a hugetlbfs filesystem must
+ * be passed as the last argument to this test. The amount of memory used
+ * by this test in MBs can optionally be passed as an argument. If no memory
+ * amount is passed, the default amount is 10MB.
+ *
+ * To make sure the test triggers pmd sharing and goes through the 'unshare'
+ * path in the mremap code use 1GB (1024) or more.
*/
#define _GNU_SOURCE
@@ -18,7 +23,8 @@
#include <linux/userfaultfd.h>
#include <sys/ioctl.h>
-#define LENGTH (1UL * 1024 * 1024 * 1024)
+#define DEFAULT_LENGTH_MB 10UL
+#define MB_TO_BYTES(x) (x * 1024 * 1024)
#define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC)
#define FLAGS (MAP_SHARED | MAP_ANONYMOUS)
@@ -28,20 +34,20 @@ static void check_bytes(char *addr)
printf("First hex is %x\n", *((unsigned int *)addr));
}
-static void write_bytes(char *addr)
+static void write_bytes(char *addr, size_t len)
{
unsigned long i;
- for (i = 0; i < LENGTH; i++)
+ for (i = 0; i < len; i++)
*(addr + i) = (char)i;
}
-static int read_bytes(char *addr)
+static int read_bytes(char *addr, size_t len)
{
unsigned long i;
check_bytes(addr);
- for (i = 0; i < LENGTH; i++)
+ for (i = 0; i < len; i++)
if (*(addr + i) != (char)i) {
printf("Mismatch at %lu\n", i);
return 1;
@@ -99,11 +105,28 @@ static void register_region_with_uffd(char *addr, size_t len)
}
}
-int main(void)
+int main(int argc, char *argv[])
{
+ size_t length;
+
+ if (argc != 2 && argc != 3) {
+ printf("Usage: %s [length_in_MB] <hugetlb_file>\n", argv[0]);
+ exit(1);
+ }
+
+ /* Read memory length as the first arg if valid, otherwise fallback to
+ * the default length.
+ */
+ if (argc == 3)
+ length = argc > 2 ? (size_t)atoi(argv[1]) : 0UL;
+
+ length = length > 0 ? length : DEFAULT_LENGTH_MB;
+ length = MB_TO_BYTES(length);
+
int ret = 0;
- int fd = open("/huge/test", O_CREAT | O_RDWR, 0755);
+ /* last arg is the hugetlb file name */
+ int fd = open(argv[argc-1], O_CREAT | O_RDWR, 0755);
if (fd < 0) {
perror("Open failed");
@@ -112,7 +135,7 @@ int main(void)
/* mmap to a PUD aligned address to hopefully trigger pmd sharing. */
unsigned long suggested_addr = 0x7eaa40000000;
- void *haddr = mmap((void *)suggested_addr, LENGTH, PROTECTION,
+ void *haddr = mmap((void *)suggested_addr, length, PROTECTION,
MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0);
printf("Map haddr: Returned address is %p\n", haddr);
if (haddr == MAP_FAILED) {
@@ -122,7 +145,7 @@ int main(void)
/* mmap again to a dummy address to hopefully trigger pmd sharing. */
suggested_addr = 0x7daa40000000;
- void *daddr = mmap((void *)suggested_addr, LENGTH, PROTECTION,
+ void *daddr = mmap((void *)suggested_addr, length, PROTECTION,
MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0);
printf("Map daddr: Returned address is %p\n", daddr);
if (daddr == MAP_FAILED) {
@@ -132,16 +155,16 @@ int main(void)
suggested_addr = 0x7faa40000000;
void *vaddr =
- mmap((void *)suggested_addr, LENGTH, PROTECTION, FLAGS, -1, 0);
+ mmap((void *)suggested_addr, length, PROTECTION, FLAGS, -1, 0);
printf("Map vaddr: Returned address is %p\n", vaddr);
if (vaddr == MAP_FAILED) {
perror("mmap2");
exit(1);
}
- register_region_with_uffd(haddr, LENGTH);
+ register_region_with_uffd(haddr, length);
- void *addr = mremap(haddr, LENGTH, LENGTH,
+ void *addr = mremap(haddr, length, length,
MREMAP_MAYMOVE | MREMAP_FIXED, vaddr);
if (addr == MAP_FAILED) {
perror("mremap");
@@ -150,10 +173,13 @@ int main(void)
printf("Mremap: Returned address is %p\n", addr);
check_bytes(addr);
- write_bytes(addr);
- ret = read_bytes(addr);
+ write_bytes(addr, length);
+ ret = read_bytes(addr, length);
+
+ munmap(addr, length);
- munmap(addr, LENGTH);
+ close(fd);
+ unlink(argv[argc-1]);
return ret;
}
diff --git a/tools/testing/selftests/vm/hugepage-vmemmap.c b/tools/testing/selftests/vm/hugepage-vmemmap.c
new file mode 100644
index 000000000000..557bdbd4f87e
--- /dev/null
+++ b/tools/testing/selftests/vm/hugepage-vmemmap.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A test case of using hugepage memory in a user application using the
+ * mmap system call with MAP_HUGETLB flag. Before running this program
+ * make sure the administrator has allocated enough default sized huge
+ * pages to cover the 2 MB allocation.
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#define MAP_LENGTH (2UL * 1024 * 1024)
+
+#ifndef MAP_HUGETLB
+#define MAP_HUGETLB 0x40000 /* arch specific */
+#endif
+
+#define PAGE_SIZE 4096
+
+#define PAGE_COMPOUND_HEAD (1UL << 15)
+#define PAGE_COMPOUND_TAIL (1UL << 16)
+#define PAGE_HUGE (1UL << 17)
+
+#define HEAD_PAGE_FLAGS (PAGE_COMPOUND_HEAD | PAGE_HUGE)
+#define TAIL_PAGE_FLAGS (PAGE_COMPOUND_TAIL | PAGE_HUGE)
+
+#define PM_PFRAME_BITS 55
+#define PM_PFRAME_MASK ~((1UL << PM_PFRAME_BITS) - 1)
+
+/*
+ * For ia64 architecture, Linux kernel reserves Region number 4 for hugepages.
+ * That means the addresses starting with 0x800000... will need to be
+ * specified. Specifying a fixed address is not required on ppc64, i386
+ * or x86_64.
+ */
+#ifdef __ia64__
+#define MAP_ADDR (void *)(0x8000000000000000UL)
+#define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_FIXED)
+#else
+#define MAP_ADDR NULL
+#define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
+#endif
+
+static void write_bytes(char *addr, size_t length)
+{
+ unsigned long i;
+
+ for (i = 0; i < length; i++)
+ *(addr + i) = (char)i;
+}
+
+static unsigned long virt_to_pfn(void *addr)
+{
+ int fd;
+ unsigned long pagemap;
+
+ fd = open("/proc/self/pagemap", O_RDONLY);
+ if (fd < 0)
+ return -1UL;
+
+ lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET);
+ read(fd, &pagemap, sizeof(pagemap));
+ close(fd);
+
+ return pagemap & ~PM_PFRAME_MASK;
+}
+
+static int check_page_flags(unsigned long pfn)
+{
+ int fd, i;
+ unsigned long pageflags;
+
+ fd = open("/proc/kpageflags", O_RDONLY);
+ if (fd < 0)
+ return -1;
+
+ lseek(fd, pfn * sizeof(pageflags), SEEK_SET);
+
+ read(fd, &pageflags, sizeof(pageflags));
+ if ((pageflags & HEAD_PAGE_FLAGS) != HEAD_PAGE_FLAGS) {
+ close(fd);
+ printf("Head page flags (%lx) is invalid\n", pageflags);
+ return -1;
+ }
+
+ /*
+ * pages other than the first page must be tail and shouldn't be head;
+ * this also verifies kernel has correctly set the fake page_head to tail
+ * while hugetlb_free_vmemmap is enabled.
+ */
+ for (i = 1; i < MAP_LENGTH / PAGE_SIZE; i++) {
+ read(fd, &pageflags, sizeof(pageflags));
+ if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS ||
+ (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) {
+ close(fd);
+ printf("Tail page flags (%lx) is invalid\n", pageflags);
+ return -1;
+ }
+ }
+
+ close(fd);
+
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ void *addr;
+ unsigned long pfn;
+
+ addr = mmap(MAP_ADDR, MAP_LENGTH, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0);
+ if (addr == MAP_FAILED) {
+ perror("mmap");
+ exit(1);
+ }
+
+ /* Trigger allocation of HugeTLB page. */
+ write_bytes(addr, MAP_LENGTH);
+
+ pfn = virt_to_pfn(addr);
+ if (pfn == -1UL) {
+ munmap(addr, MAP_LENGTH);
+ perror("virt_to_pfn");
+ exit(1);
+ }
+
+ printf("Returned address is %p whose pfn is %lx\n", addr, pfn);
+
+ if (check_page_flags(pfn) < 0) {
+ munmap(addr, MAP_LENGTH);
+ perror("check_page_flags");
+ exit(1);
+ }
+
+ /* munmap() length of MAP_HUGETLB memory must be hugepage aligned */
+ if (munmap(addr, MAP_LENGTH)) {
+ perror("munmap");
+ exit(1);
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh
index 4a9a3afe9fd4..bf2d2a684edf 100644
--- a/tools/testing/selftests/vm/hugetlb_reparenting_test.sh
+++ b/tools/testing/selftests/vm/hugetlb_reparenting_test.sh
@@ -18,19 +18,24 @@ if [[ "$1" == "-cgroup-v2" ]]; then
usage_file=current
fi
-CGROUP_ROOT='/dev/cgroup/memory'
-MNT='/mnt/huge/'
-if [[ ! -e $CGROUP_ROOT ]]; then
- mkdir -p $CGROUP_ROOT
- if [[ $cgroup2 ]]; then
+if [[ $cgroup2 ]]; then
+ CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
+ if [[ -z "$CGROUP_ROOT" ]]; then
+ CGROUP_ROOT=/dev/cgroup/memory
mount -t cgroup2 none $CGROUP_ROOT
- sleep 1
- echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control
- else
+ do_umount=1
+ fi
+ echo "+hugetlb +memory" >$CGROUP_ROOT/cgroup.subtree_control
+else
+ CGROUP_ROOT=$(mount -t cgroup | grep ",hugetlb" | awk -e '{print $3}')
+ if [[ -z "$CGROUP_ROOT" ]]; then
+ CGROUP_ROOT=/dev/cgroup/memory
mount -t cgroup memory,hugetlb $CGROUP_ROOT
+ do_umount=1
fi
fi
+MNT='/mnt/huge/'
function get_machine_hugepage_size() {
hpz=$(grep -i hugepagesize /proc/meminfo)
diff --git a/tools/testing/selftests/vm/map_fixed_noreplace.c b/tools/testing/selftests/vm/map_fixed_noreplace.c
index d91bde511268..eed44322d1a6 100644
--- a/tools/testing/selftests/vm/map_fixed_noreplace.c
+++ b/tools/testing/selftests/vm/map_fixed_noreplace.c
@@ -17,9 +17,6 @@
#define MAP_FIXED_NOREPLACE 0x100000
#endif
-#define BASE_ADDRESS (256ul * 1024 * 1024)
-
-
static void dump_maps(void)
{
char cmd[32];
@@ -28,18 +25,46 @@ static void dump_maps(void)
system(cmd);
}
+static unsigned long find_base_addr(unsigned long size)
+{
+ void *addr;
+ unsigned long flags;
+
+ flags = MAP_PRIVATE | MAP_ANONYMOUS;
+ addr = mmap(NULL, size, PROT_NONE, flags, -1, 0);
+ if (addr == MAP_FAILED) {
+ printf("Error: couldn't map the space we need for the test\n");
+ return 0;
+ }
+
+ if (munmap(addr, size) != 0) {
+ printf("Error: couldn't map the space we need for the test\n");
+ return 0;
+ }
+ return (unsigned long)addr;
+}
+
int main(void)
{
+ unsigned long base_addr;
unsigned long flags, addr, size, page_size;
char *p;
page_size = sysconf(_SC_PAGE_SIZE);
+ //let's find a base addr that is free before we start the tests
+ size = 5 * page_size;
+ base_addr = find_base_addr(size);
+ if (!base_addr) {
+ printf("Error: couldn't map the space we need for the test\n");
+ return 1;
+ }
+
flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE;
// Check we can map all the areas we need below
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 5 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
@@ -60,7 +85,7 @@ int main(void)
printf("unmap() successful\n");
errno = 0;
- addr = BASE_ADDRESS + page_size;
+ addr = base_addr + page_size;
size = 3 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -80,7 +105,7 @@ int main(void)
* +4 | free | new
*/
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 5 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -101,7 +126,7 @@ int main(void)
* +4 | free |
*/
errno = 0;
- addr = BASE_ADDRESS + (2 * page_size);
+ addr = base_addr + (2 * page_size);
size = page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -121,7 +146,7 @@ int main(void)
* +4 | free | new
*/
errno = 0;
- addr = BASE_ADDRESS + (3 * page_size);
+ addr = base_addr + (3 * page_size);
size = 2 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -141,7 +166,7 @@ int main(void)
* +4 | free |
*/
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 2 * page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -161,7 +186,7 @@ int main(void)
* +4 | free |
*/
errno = 0;
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -181,7 +206,7 @@ int main(void)
* +4 | free | new
*/
errno = 0;
- addr = BASE_ADDRESS + (4 * page_size);
+ addr = base_addr + (4 * page_size);
size = page_size;
p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0);
printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p);
@@ -192,7 +217,7 @@ int main(void)
return 1;
}
- addr = BASE_ADDRESS;
+ addr = base_addr;
size = 5 * page_size;
if (munmap((void *)addr, size) != 0) {
dump_maps();
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index a24d30af3094..e10d50e0b8e8 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -111,7 +111,19 @@ fi
echo "-----------------------"
echo "running hugepage-mremap"
echo "-----------------------"
-./hugepage-mremap
+./hugepage-mremap $mnt/huge_mremap
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+rm -f $mnt/huge_mremap
+
+echo "------------------------"
+echo "running hugepage-vmemmap"
+echo "------------------------"
+./hugepage-vmemmap
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c
index 5e4c036f6ad3..a03cb3fce1f6 100644
--- a/tools/testing/selftests/vm/transhuge-stress.c
+++ b/tools/testing/selftests/vm/transhuge-stress.c
@@ -26,15 +26,17 @@
#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1))
int pagemap_fd;
+int backing_fd = -1;
+int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE;
+#define PROT_RW (PROT_READ | PROT_WRITE)
int64_t allocate_transhuge(void *ptr)
{
uint64_t ent[2];
/* drop pmd */
- if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANONYMOUS |
- MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr)
+ if (mmap(ptr, HPAGE_SIZE, PROT_RW, MAP_FIXED | mmap_flags,
+ backing_fd, 0) != ptr)
errx(2, "mmap transhuge");
if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE))
@@ -60,6 +62,8 @@ int main(int argc, char **argv)
size_t ram, len;
void *ptr, *p;
struct timespec a, b;
+ int i = 0;
+ char *name = NULL;
double s;
uint8_t *map;
size_t map_len;
@@ -69,13 +73,23 @@ int main(int argc, char **argv)
ram = SIZE_MAX / 4;
else
ram *= sysconf(_SC_PAGESIZE);
+ len = ram;
+
+ while (++i < argc) {
+ if (!strcmp(argv[i], "-h"))
+ errx(1, "usage: %s [size in MiB]", argv[0]);
+ else if (!strcmp(argv[i], "-f"))
+ name = argv[++i];
+ else
+ len = atoll(argv[i]) << 20;
+ }
- if (argc == 1)
- len = ram;
- else if (!strcmp(argv[1], "-h"))
- errx(1, "usage: %s [size in MiB]", argv[0]);
- else
- len = atoll(argv[1]) << 20;
+ if (name) {
+ backing_fd = open(name, O_RDWR);
+ if (backing_fd == -1)
+ errx(2, "open %s", name);
+ mmap_flags = MAP_SHARED;
+ }
warnx("allocate %zd transhuge pages, using %zd MiB virtual memory"
" and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20,
@@ -86,8 +100,7 @@ int main(int argc, char **argv)
err(2, "open pagemap");
len -= len % HPAGE_SIZE;
- ptr = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE,
- MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0);
+ ptr = mmap(NULL, len + HPAGE_SIZE, PROT_RW, mmap_flags, backing_fd, 0);
if (ptr == MAP_FAILED)
err(2, "initial mmap");
ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE;
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 9354a5e0321c..29cc6f247a9e 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -46,6 +46,7 @@
#include <signal.h>
#include <poll.h>
#include <string.h>
+#include <linux/mman.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
@@ -87,7 +88,7 @@ static bool test_uffdio_minor = false;
static bool map_shared;
static int shm_fd;
-static int huge_fd = -1; /* only used for hugetlb_shared test */
+static int huge_fd;
static char *huge_fd_off0;
static unsigned long long *count_verify;
static int uffd = -1;
@@ -223,9 +224,6 @@ static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)
static void hugetlb_release_pages(char *rel_area)
{
- if (huge_fd == -1)
- return;
-
if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
rel_area == huge_fd_off0 ? 0 : nr_pages * page_size,
nr_pages * page_size))
@@ -238,17 +236,17 @@ static void hugetlb_allocate_area(void **alloc_area)
char **alloc_area_alias;
*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
- map_shared ? MAP_SHARED :
- MAP_PRIVATE | MAP_HUGETLB |
+ (map_shared ? MAP_SHARED : MAP_PRIVATE) |
+ MAP_HUGETLB |
(*alloc_area == area_src ? 0 : MAP_NORESERVE),
- huge_fd,
- *alloc_area == area_src ? 0 : nr_pages * page_size);
+ huge_fd, *alloc_area == area_src ? 0 :
+ nr_pages * page_size);
if (*alloc_area == MAP_FAILED)
err("mmap of hugetlbfs file failed");
if (map_shared) {
area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
- MAP_SHARED,
+ MAP_SHARED | MAP_HUGETLB,
huge_fd, *alloc_area == area_src ? 0 :
nr_pages * page_size);
if (area_alias == MAP_FAILED)
@@ -542,7 +540,7 @@ static void continue_range(int ufd, __u64 start, __u64 len)
static void *locking_thread(void *arg)
{
unsigned long cpu = (unsigned long) arg;
- unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */
+ unsigned long page_nr;
unsigned long long count;
if (!(bounces & BOUNCE_RANDOM)) {
@@ -648,7 +646,7 @@ static int uffd_read_msg(int ufd, struct uffd_msg *msg)
if (ret != sizeof(*msg)) {
if (ret < 0) {
- if (errno == EAGAIN)
+ if (errno == EAGAIN || errno == EINTR)
return 1;
err("blocking read error");
} else {
@@ -724,8 +722,11 @@ static void *uffd_poll_thread(void *arg)
for (;;) {
ret = poll(pollfd, 2, -1);
- if (ret <= 0)
+ if (ret <= 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ continue;
err("poll error: %d", ret);
+ }
if (pollfd[1].revents & POLLIN) {
if (read(pollfd[1].fd, &tmp_chr, 1) != 1)
err("read pipefd error");
diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/vm/write_hugetlb_memory.sh
index d3d0d108924d..70a02301f4c2 100644
--- a/tools/testing/selftests/vm/write_hugetlb_memory.sh
+++ b/tools/testing/selftests/vm/write_hugetlb_memory.sh
@@ -14,7 +14,7 @@ want_sleep=$8
reserve=$9
echo "Putting task in cgroup '$cgroup'"
-echo $$ > /dev/cgroup/memory/"$cgroup"/cgroup.procs
+echo $$ > ${cgroup_path:-/dev/cgroup/memory}/"$cgroup"/cgroup.procs
echo "Method is $method"
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 8a1f62ab3c8e..53df7d3893d3 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -6,9 +6,9 @@ include ../lib.mk
.PHONY: all all_32 all_64 warn_32bit_failure clean
UNAME_M := $(shell uname -m)
-CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
-CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c)
-CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie)
+CAN_BUILD_I386 := $(shell ./check_cc.sh "$(CC)" trivial_32bit_program.c -m32)
+CAN_BUILD_X86_64 := $(shell ./check_cc.sh "$(CC)" trivial_64bit_program.c)
+CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh "$(CC)" trivial_program.c -no-pie)
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
check_initial_reg_state sigreturn iopl ioperm \
diff --git a/tools/testing/selftests/x86/check_cc.sh b/tools/testing/selftests/x86/check_cc.sh
index 3e2089c8cf54..8c669c0d662e 100755
--- a/tools/testing/selftests/x86/check_cc.sh
+++ b/tools/testing/selftests/x86/check_cc.sh
@@ -7,7 +7,7 @@ CC="$1"
TESTPROG="$2"
shift 2
-if "$CC" -o /dev/null "$TESTPROG" -O0 "$@" 2>/dev/null; then
+if [ -n "$CC" ] && $CC -o /dev/null "$TESTPROG" -O0 "$@" 2>/dev/null; then
echo 1
else
echo 0
diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh
index 232e958ec454..b0b91d9b0dc2 100755
--- a/tools/testing/selftests/zram/zram.sh
+++ b/tools/testing/selftests/zram/zram.sh
@@ -2,9 +2,6 @@
# SPDX-License-Identifier: GPL-2.0
TCID="zram.sh"
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
. ./zram_lib.sh
run_zram () {
@@ -18,14 +15,4 @@ echo ""
check_prereqs
-# check zram module exists
-MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko
-if [ -f $MODULE_PATH ]; then
- run_zram
-elif [ -b /dev/zram0 ]; then
- run_zram
-else
- echo "$TCID : No zram.ko module or /dev/zram0 device file not found"
- echo "$TCID : CONFIG_ZRAM is not set"
- exit $ksft_skip
-fi
+run_zram
diff --git a/tools/testing/selftests/zram/zram01.sh b/tools/testing/selftests/zram/zram01.sh
index 114863d9fb87..8f4affe34f3e 100755
--- a/tools/testing/selftests/zram/zram01.sh
+++ b/tools/testing/selftests/zram/zram01.sh
@@ -33,9 +33,7 @@ zram_algs="lzo"
zram_fill_fs()
{
- local mem_free0=$(free -m | awk 'NR==2 {print $4}')
-
- for i in $(seq 0 $(($dev_num - 1))); do
+ for i in $(seq $dev_start $dev_end); do
echo "fill zram$i..."
local b=0
while [ true ]; do
@@ -45,29 +43,17 @@ zram_fill_fs()
b=$(($b + 1))
done
echo "zram$i can be filled with '$b' KB"
- done
- local mem_free1=$(free -m | awk 'NR==2 {print $4}')
- local used_mem=$(($mem_free0 - $mem_free1))
+ local mem_used_total=`awk '{print $3}' "/sys/block/zram$i/mm_stat"`
+ local v=$((100 * 1024 * $b / $mem_used_total))
+ if [ "$v" -lt 100 ]; then
+ echo "FAIL compression ratio: 0.$v:1"
+ ERR_CODE=-1
+ return
+ fi
- local total_size=0
- for sm in $zram_sizes; do
- local s=$(echo $sm | sed 's/M//')
- total_size=$(($total_size + $s))
+ echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK"
done
-
- echo "zram used ${used_mem}M, zram disk sizes ${total_size}M"
-
- local v=$((100 * $total_size / $used_mem))
-
- if [ "$v" -lt 100 ]; then
- echo "FAIL compression ratio: 0.$v:1"
- ERR_CODE=-1
- zram_cleanup
- return
- fi
-
- echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK"
}
check_prereqs
@@ -81,7 +67,6 @@ zram_mount
zram_fill_fs
zram_cleanup
-zram_unload
if [ $ERR_CODE -ne 0 ]; then
echo "$TCID : [FAIL]"
diff --git a/tools/testing/selftests/zram/zram02.sh b/tools/testing/selftests/zram/zram02.sh
index e83b404807c0..2418b0c4ed13 100755
--- a/tools/testing/selftests/zram/zram02.sh
+++ b/tools/testing/selftests/zram/zram02.sh
@@ -36,7 +36,6 @@ zram_set_memlimit
zram_makeswap
zram_swapoff
zram_cleanup
-zram_unload
if [ $ERR_CODE -ne 0 ]; then
echo "$TCID : [FAIL]"
diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh
index 6f872f266fd1..21ec1966de76 100755
--- a/tools/testing/selftests/zram/zram_lib.sh
+++ b/tools/testing/selftests/zram/zram_lib.sh
@@ -5,12 +5,17 @@
# Author: Alexey Kodanev <[email protected]>
# Modified: Naresh Kamboju <[email protected]>
-MODULE=0
dev_makeswap=-1
dev_mounted=-1
-
+dev_start=0
+dev_end=-1
+module_load=-1
+sys_control=-1
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
+kernel_version=`uname -r | cut -d'.' -f1,2`
+kernel_major=${kernel_version%.*}
+kernel_minor=${kernel_version#*.}
trap INT
@@ -25,68 +30,104 @@ check_prereqs()
fi
}
+kernel_gte()
+{
+ major=${1%.*}
+ minor=${1#*.}
+
+ if [ $kernel_major -gt $major ]; then
+ return 0
+ elif [[ $kernel_major -eq $major && $kernel_minor -ge $minor ]]; then
+ return 0
+ fi
+
+ return 1
+}
+
zram_cleanup()
{
echo "zram cleanup"
local i=
- for i in $(seq 0 $dev_makeswap); do
+ for i in $(seq $dev_start $dev_makeswap); do
swapoff /dev/zram$i
done
- for i in $(seq 0 $dev_mounted); do
+ for i in $(seq $dev_start $dev_mounted); do
umount /dev/zram$i
done
- for i in $(seq 0 $(($dev_num - 1))); do
+ for i in $(seq $dev_start $dev_end); do
echo 1 > /sys/block/zram${i}/reset
rm -rf zram$i
done
-}
+ if [ $sys_control -eq 1 ]; then
+ for i in $(seq $dev_start $dev_end); do
+ echo $i > /sys/class/zram-control/hot_remove
+ done
+ fi
-zram_unload()
-{
- if [ $MODULE -ne 0 ] ; then
- echo "zram rmmod zram"
+ if [ $module_load -eq 1 ]; then
rmmod zram > /dev/null 2>&1
fi
}
zram_load()
{
- # check zram module exists
- MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko
- if [ -f $MODULE_PATH ]; then
- MODULE=1
- echo "create '$dev_num' zram device(s)"
- modprobe zram num_devices=$dev_num
- if [ $? -ne 0 ]; then
- echo "failed to insert zram module"
- exit 1
- fi
-
- dev_num_created=$(ls /dev/zram* | wc -w)
+ echo "create '$dev_num' zram device(s)"
+
+ # zram module loaded, new kernel
+ if [ -d "/sys/class/zram-control" ]; then
+ echo "zram modules already loaded, kernel supports" \
+ "zram-control interface"
+ dev_start=$(ls /dev/zram* | wc -w)
+ dev_end=$(($dev_start + $dev_num - 1))
+ sys_control=1
+
+ for i in $(seq $dev_start $dev_end); do
+ cat /sys/class/zram-control/hot_add > /dev/null
+ done
+
+ echo "all zram devices (/dev/zram$dev_start~$dev_end" \
+ "successfully created"
+ return 0
+ fi
- if [ "$dev_num_created" -ne "$dev_num" ]; then
- echo "unexpected num of devices: $dev_num_created"
- ERR_CODE=-1
+ # detect old kernel or built-in
+ modprobe zram num_devices=$dev_num
+ if [ ! -d "/sys/class/zram-control" ]; then
+ if grep -q '^zram' /proc/modules; then
+ rmmod zram > /dev/null 2>&1
+ if [ $? -ne 0 ]; then
+ echo "zram module is being used on old kernel" \
+ "without zram-control interface"
+ exit $ksft_skip
+ fi
else
- echo "zram load module successful"
+ echo "test needs CONFIG_ZRAM=m on old kernel without" \
+ "zram-control interface"
+ exit $ksft_skip
fi
- elif [ -b /dev/zram0 ]; then
- echo "/dev/zram0 device file found: OK"
- else
- echo "ERROR: No zram.ko module or no /dev/zram0 device found"
- echo "$TCID : CONFIG_ZRAM is not set"
- exit 1
+ modprobe zram num_devices=$dev_num
fi
+
+ module_load=1
+ dev_end=$(($dev_num - 1))
+ echo "all zram devices (/dev/zram0~$dev_end) successfully created"
}
zram_max_streams()
{
echo "set max_comp_streams to zram device(s)"
- local i=0
+ kernel_gte 4.7
+ if [ $? -eq 0 ]; then
+ echo "The device attribute max_comp_streams was"\
+ "deprecated in 4.7"
+ return 0
+ fi
+
+ local i=$dev_start
for max_s in $zram_max_streams; do
local sys_path="/sys/block/zram${i}/max_comp_streams"
echo $max_s > $sys_path || \
@@ -98,7 +139,7 @@ zram_max_streams()
echo "FAIL can't set max_streams '$max_s', get $max_stream"
i=$(($i + 1))
- echo "$sys_path = '$max_streams' ($i/$dev_num)"
+ echo "$sys_path = '$max_streams'"
done
echo "zram max streams: OK"
@@ -108,15 +149,16 @@ zram_compress_alg()
{
echo "test that we can set compression algorithm"
- local algs=$(cat /sys/block/zram0/comp_algorithm)
+ local i=$dev_start
+ local algs=$(cat /sys/block/zram${i}/comp_algorithm)
echo "supported algs: $algs"
- local i=0
+
for alg in $zram_algs; do
local sys_path="/sys/block/zram${i}/comp_algorithm"
echo "$alg" > $sys_path || \
echo "FAIL can't set '$alg' to $sys_path"
i=$(($i + 1))
- echo "$sys_path = '$alg' ($i/$dev_num)"
+ echo "$sys_path = '$alg'"
done
echo "zram set compression algorithm: OK"
@@ -125,14 +167,14 @@ zram_compress_alg()
zram_set_disksizes()
{
echo "set disk size to zram device(s)"
- local i=0
+ local i=$dev_start
for ds in $zram_sizes; do
local sys_path="/sys/block/zram${i}/disksize"
echo "$ds" > $sys_path || \
echo "FAIL can't set '$ds' to $sys_path"
i=$(($i + 1))
- echo "$sys_path = '$ds' ($i/$dev_num)"
+ echo "$sys_path = '$ds'"
done
echo "zram set disksizes: OK"
@@ -142,14 +184,14 @@ zram_set_memlimit()
{
echo "set memory limit to zram device(s)"
- local i=0
+ local i=$dev_start
for ds in $zram_mem_limits; do
local sys_path="/sys/block/zram${i}/mem_limit"
echo "$ds" > $sys_path || \
echo "FAIL can't set '$ds' to $sys_path"
i=$(($i + 1))
- echo "$sys_path = '$ds' ($i/$dev_num)"
+ echo "$sys_path = '$ds'"
done
echo "zram set memory limit: OK"
@@ -158,8 +200,8 @@ zram_set_memlimit()
zram_makeswap()
{
echo "make swap with zram device(s)"
- local i=0
- for i in $(seq 0 $(($dev_num - 1))); do
+ local i=$dev_start
+ for i in $(seq $dev_start $dev_end); do
mkswap /dev/zram$i > err.log 2>&1
if [ $? -ne 0 ]; then
cat err.log
@@ -182,7 +224,7 @@ zram_makeswap()
zram_swapoff()
{
local i=
- for i in $(seq 0 $dev_makeswap); do
+ for i in $(seq $dev_start $dev_end); do
swapoff /dev/zram$i > err.log 2>&1
if [ $? -ne 0 ]; then
cat err.log
@@ -196,7 +238,7 @@ zram_swapoff()
zram_makefs()
{
- local i=0
+ local i=$dev_start
for fs in $zram_filesystems; do
# if requested fs not supported default it to ext2
which mkfs.$fs > /dev/null 2>&1 || fs=ext2
@@ -215,7 +257,7 @@ zram_makefs()
zram_mount()
{
local i=0
- for i in $(seq 0 $(($dev_num - 1))); do
+ for i in $(seq $dev_start $dev_end); do
echo "mount /dev/zram$i"
mkdir zram$i
mount /dev/zram$i zram$i > /dev/null || \