summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/arch/arm64/include/uapi/asm/kvm.h6
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h11
-rw-r--r--tools/arch/x86/include/uapi/asm/kvm.h1
-rw-r--r--tools/bpf/bpftool/prog.c17
-rw-r--r--tools/hv/.gitignore3
-rw-r--r--tools/hv/hv_fcopy_uio_daemon.c12
-rwxr-xr-xtools/hv/hv_get_dns_info.sh4
-rw-r--r--tools/hv/hv_kvp_daemon.c9
-rwxr-xr-xtools/hv/hv_set_ifconfig.sh2
-rw-r--r--tools/include/uapi/asm-generic/mman.h4
-rw-r--r--tools/include/uapi/asm-generic/unistd.h11
-rw-r--r--tools/include/uapi/drm/drm.h17
-rw-r--r--tools/include/uapi/linux/kvm.h8
-rw-r--r--tools/include/uapi/linux/perf_event.h11
-rw-r--r--tools/include/uapi/linux/stddef.h15
-rw-r--r--tools/lib/perf/evlist.c18
-rw-r--r--tools/net/ynl/lib/ynl.py6
-rwxr-xr-xtools/net/ynl/ynl-gen-c.py16
-rw-r--r--tools/objtool/check.c9
-rw-r--r--tools/objtool/noreturns.h1
-rw-r--r--tools/perf/Documentation/perf-arm-spe.txt26
-rw-r--r--tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl4
-rw-r--r--tools/perf/arch/powerpc/entry/syscalls/syscall.tbl4
-rw-r--r--tools/perf/arch/s390/entry/syscalls/syscall.tbl4
-rw-r--r--tools/perf/arch/x86/entry/syscalls/syscall_32.tbl4
-rw-r--r--tools/perf/arch/x86/entry/syscalls/syscall_64.tbl4
-rw-r--r--tools/perf/builtin-ftrace.c3
-rw-r--r--tools/perf/tests/builtin-test.c2
-rw-r--r--tools/perf/tests/expr.c19
-rw-r--r--tools/perf/tests/hwmon_pmu.c29
-rwxr-xr-xtools/perf/trace/beauty/fs_at_flags.sh3
-rw-r--r--tools/perf/trace/beauty/include/uapi/linux/fcntl.h5
-rw-r--r--tools/perf/trace/beauty/include/uapi/linux/mount.h14
-rw-r--r--tools/perf/trace/beauty/include/uapi/linux/prctl.h27
-rw-r--r--tools/perf/util/build-id.c4
-rw-r--r--tools/perf/util/evsel.c6
-rw-r--r--tools/perf/util/hwmon_pmu.c15
-rw-r--r--tools/perf/util/machine.c2
-rw-r--r--tools/perf/util/probe-event.c2
-rw-r--r--tools/sched_ext/include/scx/common.bpf.h6
-rw-r--r--tools/sched_ext/scx_central.c2
-rw-r--r--tools/scripts/Makefile.arch4
-rw-r--r--tools/testing/cxl/cxl_core_exports.c2
-rw-r--r--tools/testing/cxl/test/cxl.c4
-rw-r--r--tools/testing/cxl/test/mem.c2
-rw-r--r--tools/testing/cxl/test/mock.c28
-rw-r--r--tools/testing/nvdimm/test/ndtest.c2
-rw-r--r--tools/testing/selftests/alsa/Makefile2
-rw-r--r--tools/testing/selftests/arm64/abi/hwcap.c235
-rw-r--r--tools/testing/selftests/arm64/abi/syscall-abi-asm.S32
-rw-r--r--tools/testing/selftests/bpf/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/Makefile2
-rw-r--r--tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c (renamed from tools/testing/selftests/bpf/test_lpm_map.c)405
-rw-r--r--tools/testing/selftests/bpf/map_tests/task_storage_map.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c107
-rw-r--r--tools/testing/selftests/bpf/prog_tests/raw_tp_null.c3
-rw-r--r--tools/testing/selftests/bpf/prog_tests/socket_helpers.h394
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_basic.c136
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h385
-rw-r--r--tools/testing/selftests/bpf/prog_tests/task_local_storage.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tc_change_tail.c62
-rw-r--r--tools/testing/selftests/bpf/prog_tests/verifier.c19
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_misc.h12
-rw-r--r--tools/testing/selftests/bpf/progs/changes_pkt_data.c39
-rw-r--r--tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c18
-rw-r--r--tools/testing/selftests/bpf/progs/dynptr_fail.c22
-rw-r--r--tools/testing/selftests/bpf/progs/iters.c26
-rw-r--r--tools/testing/selftests/bpf/progs/iters_state_safety.c14
-rw-r--r--tools/testing/selftests/bpf/progs/iters_testmod_seq.c4
-rw-r--r--tools/testing/selftests/bpf/progs/raw_tp_null.c19
-rw-r--r--tools/testing/selftests/bpf/progs/raw_tp_null_fail.c24
-rw-r--r--tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c4
-rw-r--r--tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c4
-rw-r--r--tools/testing/selftests/bpf/progs/tc_bpf2bpf.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c40
-rw-r--r--tools/testing/selftests/bpf/progs/test_tc_change_tail.c106
-rw-r--r--tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c6
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_bits_iter.c8
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c40
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_d_path.c4
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_mtu.c4
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_sock.c56
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_spill_fill.c35
-rw-r--r--tools/testing/selftests/bpf/sdt.h2
-rw-r--r--tools/testing/selftests/bpf/test_loader.c46
-rw-r--r--tools/testing/selftests/bpf/test_sockmap.c6
-rw-r--r--tools/testing/selftests/bpf/trace_helpers.c4
-rwxr-xr-xtools/testing/selftests/cgroup/test_cpuset_prs.sh33
-rw-r--r--tools/testing/selftests/coredump/Makefile7
-rw-r--r--tools/testing/selftests/coredump/README.rst50
-rwxr-xr-xtools/testing/selftests/coredump/stackdump14
-rw-r--r--tools/testing/selftests/coredump/stackdump_test.c151
-rw-r--r--tools/testing/selftests/damon/Makefile2
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/rss_ctx.py12
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh55
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh9
-rwxr-xr-xtools/testing/selftests/drivers/net/queues.py51
-rwxr-xr-xtools/testing/selftests/drivers/net/stats.py19
-rw-r--r--tools/testing/selftests/exec/execveat.c75
-rw-r--r--tools/testing/selftests/filesystems/nsfs/.gitignore (renamed from tools/testing/selftests/nsfs/.gitignore)1
-rw-r--r--tools/testing/selftests/filesystems/nsfs/Makefile (renamed from tools/testing/selftests/nsfs/Makefile)4
-rw-r--r--tools/testing/selftests/filesystems/nsfs/config (renamed from tools/testing/selftests/nsfs/config)0
-rw-r--r--tools/testing/selftests/filesystems/nsfs/iterate_mntns.c149
-rw-r--r--tools/testing/selftests/filesystems/nsfs/owner.c (renamed from tools/testing/selftests/nsfs/owner.c)0
-rw-r--r--tools/testing/selftests/filesystems/nsfs/pidns.c (renamed from tools/testing/selftests/nsfs/pidns.c)0
-rw-r--r--tools/testing/selftests/filesystems/statmount/Makefile2
-rw-r--r--tools/testing/selftests/filesystems/statmount/listmount_test.c66
-rw-r--r--tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc2
-rw-r--r--tools/testing/selftests/hid/progs/hid_bpf_helpers.h19
-rwxr-xr-xtools/testing/selftests/hid/run-hid-tools-tests.sh16
-rw-r--r--tools/testing/selftests/iommu/iommufd_fail_nth.c14
-rw-r--r--tools/testing/selftests/kvm/aarch64/set_id_regs.c1
-rw-r--r--tools/testing/selftests/kvm/s390x/ucontrol_test.c172
-rw-r--r--tools/testing/selftests/memfd/memfd_test.c57
-rw-r--r--tools/testing/selftests/mm/cow.c8
-rw-r--r--tools/testing/selftests/mm/hugetlb_dio.c14
-rwxr-xr-xtools/testing/selftests/net/forwarding/local_termination.sh1
-rw-r--r--tools/testing/selftests/net/lib/py/ynl.py16
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c43
-rwxr-xr-xtools/testing/selftests/net/netfilter/rpath.sh18
-rwxr-xr-xtools/testing/selftests/net/openvswitch/openvswitch.sh6
-rw-r--r--tools/testing/selftests/pid_namespace/.gitignore1
-rw-r--r--tools/testing/selftests/pid_namespace/Makefile2
-rw-r--r--tools/testing/selftests/pid_namespace/pid_max.c358
-rw-r--r--tools/testing/selftests/pidfd/.gitignore2
-rw-r--r--tools/testing/selftests/pidfd/Makefile3
-rw-r--r--tools/testing/selftests/pidfd/pidfd.h40
-rw-r--r--tools/testing/selftests/pidfd/pidfd_bind_mount.c188
-rw-r--r--tools/testing/selftests/pidfd/pidfd_file_handle_test.c503
-rw-r--r--tools/testing/selftests/pidfd/pidfd_setns_test.c47
-rw-r--r--tools/testing/selftests/pidfd/pidfd_wait.c47
-rw-r--r--tools/testing/selftests/powerpc/benchmarks/gettimeofday.c2
-rw-r--r--tools/testing/selftests/powerpc/include/pkeys.h8
-rw-r--r--tools/testing/selftests/powerpc/ptrace/core-pkey.c31
-rw-r--r--tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c26
-rw-r--r--tools/testing/selftests/powerpc/vphn/test-vphn.c2
-rw-r--r--tools/testing/selftests/riscv/abi/pointer_masking.c28
-rw-r--r--tools/testing/selftests/riscv/vector/v_initval_nolibc.c4
-rw-r--r--tools/testing/selftests/riscv/vector/vstate_prctl.c2
-rw-r--r--tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c2
-rw-r--r--tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c4
-rw-r--r--tools/testing/selftests/sched_ext/dsp_local_on.bpf.c7
-rw-r--r--tools/testing/selftests/sched_ext/dsp_local_on.c5
-rw-r--r--tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c2
-rw-r--r--tools/testing/selftests/sched_ext/exit.bpf.c4
-rw-r--r--tools/testing/selftests/sched_ext/maximal.bpf.c8
-rw-r--r--tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c2
-rw-r--r--tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c2
-rw-r--r--tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c2
-rw-r--r--tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c2
-rw-r--r--tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c4
-rw-r--r--tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c8
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/filters/flow.json4
-rw-r--r--tools/testing/shared/linux/maple_tree.h2
-rw-r--r--tools/testing/vma/linux/atomic.h2
-rw-r--r--tools/testing/vsock/control.c9
-rw-r--r--tools/testing/vsock/msg_zerocopy_common.c10
-rw-r--r--tools/testing/vsock/msg_zerocopy_common.h1
-rw-r--r--tools/testing/vsock/util.c142
-rw-r--r--tools/testing/vsock/util.h7
-rw-r--r--tools/testing/vsock/vsock_perf.c20
-rw-r--r--tools/testing/vsock/vsock_test.c75
-rw-r--r--tools/testing/vsock/vsock_test_zerocopy.c2
-rw-r--r--tools/testing/vsock/vsock_uring_test.c2
-rw-r--r--tools/tracing/rtla/src/timerlat_hist.c177
166 files changed, 4621 insertions, 1009 deletions
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 964df31da975..66736ff04011 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -484,6 +484,12 @@ enum {
*/
#define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (1ULL << 0)
+/*
+ * Shutdown caused by a PSCI v1.3 SYSTEM_OFF2 call.
+ * Valid only when the system event has a type of KVM_SYSTEM_EVENT_SHUTDOWN.
+ */
+#define KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2 (1ULL << 0)
+
/* run->fail_entry.hardware_entry_failure_reason codes. */
#define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED (1ULL << 0)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 23698d0f4bb4..17b6590748c0 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -215,7 +215,7 @@
#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */
#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */
#define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */
-#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier without a guaranteed RSB flush */
#define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */
#define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */
#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */
@@ -317,6 +317,9 @@
#define X86_FEATURE_ZEN1 (11*32+31) /* CPU based on Zen1 microarchitecture */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_SHA512 (12*32+ 0) /* SHA512 instructions */
+#define X86_FEATURE_SM3 (12*32+ 1) /* SM3 instructions */
+#define X86_FEATURE_SM4 (12*32+ 2) /* SM4 instructions */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */
#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* CMPccXADD instructions */
@@ -348,6 +351,7 @@
#define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */
#define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */
#define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */
+#define X86_FEATURE_AMD_IBPB_RET (13*32+30) /* IBPB clears return address predictor */
#define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
@@ -472,7 +476,9 @@
#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */
#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */
#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */
-#define X86_FEATURE_AMD_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */
+#define X86_FEATURE_AMD_FAST_CPPC (21*32 + 5) /* Fast CPPC */
+#define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */
+#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */
/*
* BUG word(s)
@@ -523,4 +529,5 @@
#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */
#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
+#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index a8debbf2f702..88585c1de416 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -440,6 +440,7 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5)
#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6)
#define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7)
+#define KVM_X86_QUIRK_STUFF_FEATURE_MSRS (1 << 8)
#define KVM_STATE_NESTED_FORMAT_VMX 0
#define KVM_STATE_NESTED_FORMAT_SVM 1
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 2ff949ea82fa..e71be67f1d86 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -822,11 +822,18 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode,
printf("%s:\n", sym_name);
}
- if (disasm_print_insn(img, lens[i], opcodes,
- name, disasm_opt, btf,
- prog_linfo, ksyms[i], i,
- linum))
- goto exit_free;
+ if (ksyms) {
+ if (disasm_print_insn(img, lens[i], opcodes,
+ name, disasm_opt, btf,
+ prog_linfo, ksyms[i], i,
+ linum))
+ goto exit_free;
+ } else {
+ if (disasm_print_insn(img, lens[i], opcodes,
+ name, disasm_opt, btf,
+ NULL, 0, 0, false))
+ goto exit_free;
+ }
img += lens[i];
diff --git a/tools/hv/.gitignore b/tools/hv/.gitignore
new file mode 100644
index 000000000000..0c5bc15d602f
--- /dev/null
+++ b/tools/hv/.gitignore
@@ -0,0 +1,3 @@
+hv_fcopy_uio_daemon
+hv_kvp_daemon
+hv_vss_daemon
diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c
index 7a00f3066a98..0198321d14a2 100644
--- a/tools/hv/hv_fcopy_uio_daemon.c
+++ b/tools/hv/hv_fcopy_uio_daemon.c
@@ -35,8 +35,6 @@
#define WIN8_SRV_MINOR 1
#define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
-#define MAX_FOLDER_NAME 15
-#define MAX_PATH_LEN 15
#define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio"
#define FCOPY_VER_COUNT 1
@@ -51,7 +49,7 @@ static const int fw_versions[] = {
#define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */
-unsigned char desc[HV_RING_SIZE];
+static unsigned char desc[HV_RING_SIZE];
static int target_fd;
static char target_fname[PATH_MAX];
@@ -409,8 +407,8 @@ int main(int argc, char *argv[])
struct vmbus_br txbr, rxbr;
void *ring;
uint32_t len = HV_RING_SIZE;
- char uio_name[MAX_FOLDER_NAME] = {0};
- char uio_dev_path[MAX_PATH_LEN] = {0};
+ char uio_name[NAME_MAX] = {0};
+ char uio_dev_path[PATH_MAX] = {0};
static struct option long_options[] = {
{"help", no_argument, 0, 'h' },
@@ -468,8 +466,10 @@ int main(int argc, char *argv[])
*/
ret = pread(fcopy_fd, &tmp, sizeof(int), 0);
if (ret < 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ continue;
syslog(LOG_ERR, "pread failed: %s", strerror(errno));
- continue;
+ goto close;
}
len = HV_RING_SIZE;
diff --git a/tools/hv/hv_get_dns_info.sh b/tools/hv/hv_get_dns_info.sh
index 058c17b46ffc..268521234d4b 100755
--- a/tools/hv/hv_get_dns_info.sh
+++ b/tools/hv/hv_get_dns_info.sh
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
# This example script parses /etc/resolv.conf to retrive DNS information.
# In the interest of keeping the KVP daemon code free of distro specific
@@ -10,4 +10,4 @@
# this script can be based on the Network Manager APIs for retrieving DNS
# entries.
-cat /etc/resolv.conf 2>/dev/null | awk '/^nameserver/ { print $2 }'
+exec awk '/^nameserver/ { print $2 }' /etc/resolv.conf 2>/dev/null
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index ae57bf69ad4a..04ba035d67e9 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -725,7 +725,7 @@ static void kvp_get_ipconfig_info(char *if_name,
* .
*/
- sprintf(cmd, KVP_SCRIPTS_PATH "%s", "hv_get_dns_info");
+ sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dns_info", if_name);
/*
* Execute the command to gather DNS info.
@@ -742,7 +742,7 @@ static void kvp_get_ipconfig_info(char *if_name,
* Enabled: DHCP enabled.
*/
- sprintf(cmd, KVP_SCRIPTS_PATH "%s %s", "hv_get_dhcp_info", if_name);
+ sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dhcp_info", if_name);
file = popen(cmd, "r");
if (file == NULL)
@@ -1606,8 +1606,9 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
* invoke the external script to do its magic.
*/
- str_len = snprintf(cmd, sizeof(cmd), KVP_SCRIPTS_PATH "%s %s %s",
- "hv_set_ifconfig", if_filename, nm_filename);
+ str_len = snprintf(cmd, sizeof(cmd), "exec %s %s %s",
+ KVP_SCRIPTS_PATH "hv_set_ifconfig",
+ if_filename, nm_filename);
/*
* This is a little overcautious, but it's necessary to suppress some
* false warnings from gcc 8.0.1.
diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh
index 440a91b35823..2f8baed2b8f7 100755
--- a/tools/hv/hv_set_ifconfig.sh
+++ b/tools/hv/hv_set_ifconfig.sh
@@ -81,7 +81,7 @@ echo "ONBOOT=yes" >> $1
cp $1 /etc/sysconfig/network-scripts/
-chmod 600 $2
+umask 0177
interface=$(echo $2 | awk -F - '{ print $2 }')
filename="${2##*/}"
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 406f7718f9ad..51d2556af54a 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -19,4 +19,8 @@
#define MCL_FUTURE 2 /* lock all future mappings */
#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
+#define SHADOW_STACK_SET_TOKEN (1ULL << 0) /* Set up a restore token in the shadow stack */
+#define SHADOW_STACK_SET_MARKER (1ULL << 1) /* Set up a top of stack marker in the shadow stack */
+
+
#endif /* __ASM_GENERIC_MMAN_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 5bf6148cac2b..88dc393c2bca 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -841,8 +841,17 @@ __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
#define __NR_mseal 462
__SYSCALL(__NR_mseal, sys_mseal)
+#define __NR_setxattrat 463
+__SYSCALL(__NR_setxattrat, sys_setxattrat)
+#define __NR_getxattrat 464
+__SYSCALL(__NR_getxattrat, sys_getxattrat)
+#define __NR_listxattrat 465
+__SYSCALL(__NR_listxattrat, sys_listxattrat)
+#define __NR_removexattrat 466
+__SYSCALL(__NR_removexattrat, sys_removexattrat)
+
#undef __NR_syscalls
-#define __NR_syscalls 463
+#define __NR_syscalls 467
/*
* 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 16122819edfe..7fba37b94401 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -1024,6 +1024,13 @@ struct drm_crtc_queue_sequence {
__u64 user_data; /* user data passed to event */
};
+#define DRM_CLIENT_NAME_MAX_LEN 64
+struct drm_set_client_name {
+ __u64 name_len;
+ __u64 name;
+};
+
+
#if defined(__cplusplus)
}
#endif
@@ -1288,6 +1295,16 @@ extern "C" {
*/
#define DRM_IOCTL_MODE_CLOSEFB DRM_IOWR(0xD0, struct drm_mode_closefb)
+/**
+ * DRM_IOCTL_SET_CLIENT_NAME - Attach a name to a drm_file
+ *
+ * Having a name allows for easier tracking and debugging.
+ * The length of the name (without null ending char) must be
+ * <= DRM_CLIENT_NAME_MAX_LEN.
+ * The call will fail if the name contains whitespaces or non-printable chars.
+ */
+#define DRM_IOCTL_SET_CLIENT_NAME DRM_IOWR(0xD1, struct drm_set_client_name)
+
/*
* Device specific ioctls should only be in their respective headers
* The device specific ioctl range is from 0x40 to 0x9f.
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 637efc055145..502ea63b5d2e 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1158,7 +1158,15 @@ enum kvm_device_type {
#define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME
KVM_DEV_TYPE_RISCV_AIA,
#define KVM_DEV_TYPE_RISCV_AIA KVM_DEV_TYPE_RISCV_AIA
+ KVM_DEV_TYPE_LOONGARCH_IPI,
+#define KVM_DEV_TYPE_LOONGARCH_IPI KVM_DEV_TYPE_LOONGARCH_IPI
+ KVM_DEV_TYPE_LOONGARCH_EIOINTC,
+#define KVM_DEV_TYPE_LOONGARCH_EIOINTC KVM_DEV_TYPE_LOONGARCH_EIOINTC
+ KVM_DEV_TYPE_LOONGARCH_PCHPIC,
+#define KVM_DEV_TYPE_LOONGARCH_PCHPIC KVM_DEV_TYPE_LOONGARCH_PCHPIC
+
KVM_DEV_TYPE_MAX,
+
};
struct kvm_vfio_spapr_tce {
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 4842c36fdf80..0524d541d4e3 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -511,7 +511,16 @@ struct perf_event_attr {
__u16 sample_max_stack;
__u16 __reserved_2;
__u32 aux_sample_size;
- __u32 __reserved_3;
+
+ union {
+ __u32 aux_action;
+ struct {
+ __u32 aux_start_paused : 1, /* start AUX area tracing paused */
+ aux_pause : 1, /* on overflow, pause AUX area tracing */
+ aux_resume : 1, /* on overflow, resume AUX area tracing */
+ __reserved_3 : 29;
+ };
+ };
/*
* User provided data if sigtrap=1, passed back to user via
diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h
index bb6ea517efb5..c53cde425406 100644
--- a/tools/include/uapi/linux/stddef.h
+++ b/tools/include/uapi/linux/stddef.h
@@ -8,6 +8,13 @@
#define __always_inline __inline__
#endif
+/* Not all C++ standards support type declarations inside an anonymous union */
+#ifndef __cplusplus
+#define __struct_group_tag(TAG) TAG
+#else
+#define __struct_group_tag(TAG)
+#endif
+
/**
* __struct_group() - Create a mirrored named and anonyomous struct
*
@@ -20,14 +27,14 @@
* and size: one anonymous and one named. The former's members can be used
* normally without sub-struct naming, and the latter can be used to
* reason about the start, end, and size of the group of struct members.
- * The named struct can also be explicitly tagged for layer reuse, as well
- * as both having struct attributes appended.
+ * The named struct can also be explicitly tagged for layer reuse (C only),
+ * as well as both having struct attributes appended.
*/
#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
union { \
struct { MEMBERS } ATTRS; \
- struct TAG { MEMBERS } ATTRS NAME; \
- }
+ struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \
+ } ATTRS
/**
* __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index c6d67fc9e57e..83c43dc13313 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -47,6 +47,20 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
*/
perf_cpu_map__put(evsel->cpus);
evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus);
+
+ /*
+ * Empty cpu lists would eventually get opened as "any" so remove
+ * genuinely empty ones before they're opened in the wrong place.
+ */
+ if (perf_cpu_map__is_empty(evsel->cpus)) {
+ struct perf_evsel *next = perf_evlist__next(evlist, evsel);
+
+ perf_evlist__remove(evlist, evsel);
+ /* Keep idx contiguous */
+ if (next)
+ list_for_each_entry_from(next, &evlist->entries, node)
+ next->idx--;
+ }
} else if (!evsel->own_cpus || evlist->has_user_cpus ||
(!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) {
/*
@@ -80,11 +94,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel;
+ struct perf_evsel *evsel, *n;
evlist->needs_map_propagation = true;
- perf_evlist__for_each_evsel(evlist, evsel)
+ list_for_each_entry_safe(evsel, n, &evlist->entries, node)
__perf_evlist__propagate_maps(evlist, evsel);
}
diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 01ec01a90e76..eea29359a899 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -556,10 +556,10 @@ class YnlFamily(SpecFamily):
if attr["type"] == 'nest':
nl_type |= Netlink.NLA_F_NESTED
attr_payload = b''
- sub_attrs = SpaceAttrs(self.attr_sets[space], value, search_attrs)
+ sub_space = attr['nested-attributes']
+ sub_attrs = SpaceAttrs(self.attr_sets[sub_space], value, search_attrs)
for subname, subvalue in value.items():
- attr_payload += self._add_attr(attr['nested-attributes'],
- subname, subvalue, sub_attrs)
+ attr_payload += self._add_attr(sub_space, subname, subvalue, sub_attrs)
elif attr["type"] == 'flag':
if not value:
# If value is absent or false then skip attribute creation.
diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index d8201c4b1520..6750fdb42564 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -2384,6 +2384,17 @@ def print_kernel_family_struct_src(family, cw):
if not kernel_can_gen_family_struct(family):
return
+ if 'sock-priv' in family.kernel_family:
+ # Generate "trampolines" to make CFI happy
+ cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_init",
+ [f"{family.c_name}_nl_sock_priv_init(priv);"],
+ ["void *priv"])
+ cw.nl()
+ cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_destroy",
+ [f"{family.c_name}_nl_sock_priv_destroy(priv);"],
+ ["void *priv"])
+ cw.nl()
+
cw.block_start(f"struct genl_family {family.ident_name}_nl_family __ro_after_init =")
cw.p('.name\t\t= ' + family.fam_key + ',')
cw.p('.version\t= ' + family.ver_key + ',')
@@ -2401,9 +2412,8 @@ def print_kernel_family_struct_src(family, cw):
cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.c_name}_nl_mcgrps),')
if 'sock-priv' in family.kernel_family:
cw.p(f'.sock_priv_size\t= sizeof({family.kernel_family["sock-priv"]}),')
- # Force cast here, actual helpers take pointer to the real type.
- cw.p(f'.sock_priv_init\t= (void *){family.c_name}_nl_sock_priv_init,')
- cw.p(f'.sock_priv_destroy = (void *){family.c_name}_nl_sock_priv_destroy,')
+ cw.p(f'.sock_priv_init\t= __{family.c_name}_nl_sock_priv_init,')
+ cw.p(f'.sock_priv_destroy = __{family.c_name}_nl_sock_priv_destroy,')
cw.block_end(';')
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 4ce176ad411f..76060da755b5 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3820,9 +3820,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
break;
case INSN_CONTEXT_SWITCH:
- if (func && (!next_insn || !next_insn->hint)) {
- WARN_INSN(insn, "unsupported instruction in callable function");
- return 1;
+ if (func) {
+ if (!next_insn || !next_insn->hint) {
+ WARN_INSN(insn, "unsupported instruction in callable function");
+ return 1;
+ }
+ break;
}
return 0;
diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h
index f37614cc2c1b..b2174894f9f7 100644
--- a/tools/objtool/noreturns.h
+++ b/tools/objtool/noreturns.h
@@ -19,6 +19,7 @@ NORETURN(__x64_sys_exit_group)
NORETURN(arch_cpu_idle_dead)
NORETURN(bch2_trans_in_restart_error)
NORETURN(bch2_trans_restart_error)
+NORETURN(bch2_trans_unlocked_error)
NORETURN(cpu_bringup_and_idle)
NORETURN(cpu_startup_entry)
NORETURN(do_exit)
diff --git a/tools/perf/Documentation/perf-arm-spe.txt b/tools/perf/Documentation/perf-arm-spe.txt
index de2b0b479249..37afade4f1b2 100644
--- a/tools/perf/Documentation/perf-arm-spe.txt
+++ b/tools/perf/Documentation/perf-arm-spe.txt
@@ -150,6 +150,7 @@ arm_spe/load_filter=1,min_latency=10/'
pct_enable=1 - collect physical timestamp instead of virtual timestamp (PMSCR.PCT) - requires privilege
store_filter=1 - collect stores only (PMSFCR.ST)
ts_enable=1 - enable timestamping with value of generic timer (PMSCR.TS)
+ discard=1 - enable SPE PMU events but don't collect sample data - see 'Discard mode' (PMBLIMITR.FM = DISCARD)
+++*+++ Latency is the total latency from the point at which sampling started on that instruction, rather
than only the execution latency.
@@ -220,6 +221,31 @@ Common errors
Increase sampling interval (see above)
+PMU events
+~~~~~~~~~~
+
+SPE has events that can be counted on core PMUs. These are prefixed with
+SAMPLE_, for example SAMPLE_POP, SAMPLE_FEED, SAMPLE_COLLISION and
+SAMPLE_FEED_BR.
+
+These events will only count when an SPE event is running on the same core that
+the PMU event is opened on, otherwise they read as 0. There are various ways to
+ensure that the PMU event and SPE event are scheduled together depending on the
+way the event is opened. For example opening both events as per-process events
+on the same process, although it's not guaranteed that the PMU event is enabled
+first when context switching. For that reason it may be better to open the PMU
+event as a systemwide event and then open SPE on the process of interest.
+
+Discard mode
+~~~~~~~~~~~~
+
+SPE related (SAMPLE_* etc) core PMU events can be used without the overhead of
+collecting sample data if discard mode is supported (optional from Armv8.6).
+First run a system wide SPE session (or on the core of interest) using options
+to minimize output. Then run perf stat:
+
+ perf record -e arm_spe/discard/ -a -N -B --no-bpf-event -o - > /dev/null &
+ perf stat -e SAMPLE_FEED_LD
SEE ALSO
--------
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 1464c6be6eb3..c844cd5cda62 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -377,3 +377,7 @@
460 n64 lsm_set_self_attr sys_lsm_set_self_attr
461 n64 lsm_list_modules sys_lsm_list_modules
462 n64 mseal sys_mseal
+463 n64 setxattrat sys_setxattrat
+464 n64 getxattrat sys_getxattrat
+465 n64 listxattrat sys_listxattrat
+466 n64 removexattrat sys_removexattrat
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index ebae8415dfbb..d8b4ab78bef0 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -553,3 +553,7 @@
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
462 common mseal sys_mseal
+463 common setxattrat sys_setxattrat
+464 common getxattrat sys_getxattrat
+465 common listxattrat sys_listxattrat
+466 common removexattrat sys_removexattrat
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 01071182763e..e9115b4d8b63 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -465,3 +465,7 @@
460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules
462 common mseal sys_mseal sys_mseal
+463 common setxattrat sys_setxattrat sys_setxattrat
+464 common getxattrat sys_getxattrat sys_getxattrat
+465 common listxattrat sys_listxattrat sys_listxattrat
+466 common removexattrat sys_removexattrat sys_removexattrat
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
index 534c74b14fab..4d0fb2fba7e2 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
@@ -468,3 +468,7 @@
460 i386 lsm_set_self_attr sys_lsm_set_self_attr
461 i386 lsm_list_modules sys_lsm_list_modules
462 i386 mseal sys_mseal
+463 i386 setxattrat sys_setxattrat
+464 i386 getxattrat sys_getxattrat
+465 i386 listxattrat sys_listxattrat
+466 i386 removexattrat sys_removexattrat
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 7093ee21c0d1..5eb708bff1c7 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -386,6 +386,10 @@
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
462 common mseal sys_mseal
+463 common setxattrat sys_setxattrat
+464 common getxattrat sys_getxattrat
+465 common listxattrat sys_listxattrat
+466 common removexattrat sys_removexattrat
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 272d3c70810e..a56cf8b0a7d4 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -1151,8 +1151,9 @@ static int cmp_profile_data(const void *a, const void *b)
if (v1 > v2)
return -1;
- else
+ if (v1 < v2)
return 1;
+ return 0;
}
static void print_profile_result(struct perf_ftrace *ftrace)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 8dcf74d3c0a3..4751dd3c6f67 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -508,7 +508,7 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[],
for (size_t x = 0; x < num_tests; x++) {
struct child_test *child_test = child_tests[x];
- if (!child_test)
+ if (!child_test || child_test->process.pid <= 0)
continue;
pr_debug3("Killing %d pid %d\n",
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 41ff1affdfcd..726cf8d4da28 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -75,14 +75,12 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
double val, num_cpus_online, num_cpus, num_cores, num_dies, num_packages;
int ret;
struct expr_parse_ctx *ctx;
- bool is_intel = false;
char strcmp_cpuid_buf[256];
struct perf_cpu cpu = {-1};
char *cpuid = get_cpuid_allow_env_override(cpu);
char *escaped_cpuid1, *escaped_cpuid2;
TEST_ASSERT_VAL("get_cpuid", cpuid);
- is_intel = strstr(cpuid, "Intel") != NULL;
TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0);
@@ -245,12 +243,19 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
if (num_dies) // Some platforms do not have CPU die support, for example s390
TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
- TEST_ASSERT_VAL("#system_tsc_freq", expr__parse(&val, ctx, "#system_tsc_freq") == 0);
- if (is_intel)
- TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0);
- else
- TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO);
+ if (expr__parse(&val, ctx, "#system_tsc_freq") == 0) {
+ bool is_intel = strstr(cpuid, "Intel") != NULL;
+
+ if (is_intel)
+ TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0);
+ else
+ TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO);
+ } else {
+#if defined(__i386__) || defined(__x86_64__)
+ TEST_ASSERT_VAL("#system_tsc_freq unsupported", 0);
+#endif
+ }
/*
* Source count returns the number of events aggregating in a leader
* event including the leader. Check parsing yields an id.
diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
index f8bcee9660d5..d2b066a2b557 100644
--- a/tools/perf/tests/hwmon_pmu.c
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -65,7 +65,7 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz)
{ "temp2_label", "test hwmon event2\n", },
{ "temp2_input", "50000\n", },
};
- int dirfd, file;
+ int hwmon_dirfd = -1, test_dirfd = -1, file;
struct perf_pmu *hwm = NULL;
ssize_t len;
@@ -76,19 +76,24 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz)
dir[0] = '\0';
return NULL;
}
- dirfd = open(dir, O_DIRECTORY);
- if (dirfd < 0) {
+ test_dirfd = open(dir, O_PATH|O_DIRECTORY);
+ if (test_dirfd < 0) {
pr_err("Failed to open test directory \"%s\"\n", dir);
goto err_out;
}
/* Create the test hwmon directory and give it a name. */
- if (mkdirat(dirfd, "hwmon1234", 0755) < 0) {
+ if (mkdirat(test_dirfd, "hwmon1234", 0755) < 0) {
pr_err("Failed to mkdir hwmon directory\n");
goto err_out;
}
- file = openat(dirfd, "hwmon1234/name", O_WRONLY | O_CREAT, 0600);
- if (!file) {
+ hwmon_dirfd = openat(test_dirfd, "hwmon1234", O_DIRECTORY);
+ if (hwmon_dirfd < 0) {
+ pr_err("Failed to open test hwmon directory \"%s/hwmon1234\"\n", dir);
+ goto err_out;
+ }
+ file = openat(hwmon_dirfd, "name", O_WRONLY | O_CREAT, 0600);
+ if (file < 0) {
pr_err("Failed to open for writing file \"name\"\n");
goto err_out;
}
@@ -104,8 +109,8 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz)
for (size_t i = 0; i < ARRAY_SIZE(test_items); i++) {
const struct test_item *item = &test_items[i];
- file = openat(dirfd, item->name, O_WRONLY | O_CREAT, 0600);
- if (!file) {
+ file = openat(hwmon_dirfd, item->name, O_WRONLY | O_CREAT, 0600);
+ if (file < 0) {
pr_err("Failed to open for writing file \"%s\"\n", item->name);
goto err_out;
}
@@ -119,16 +124,18 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz)
}
/* Make the PMU reading the files created above. */
- hwm = perf_pmus__add_test_hwmon_pmu(dirfd, "hwmon1234", test_hwmon_name);
+ hwm = perf_pmus__add_test_hwmon_pmu(hwmon_dirfd, "hwmon1234", test_hwmon_name);
if (!hwm)
pr_err("Test hwmon creation failed\n");
err_out:
if (!hwm) {
test_pmu_put(dir, hwm);
- if (dirfd >= 0)
- close(dirfd);
+ if (hwmon_dirfd >= 0)
+ close(hwmon_dirfd);
}
+ if (test_dirfd >= 0)
+ close(test_dirfd);
return hwm;
}
diff --git a/tools/perf/trace/beauty/fs_at_flags.sh b/tools/perf/trace/beauty/fs_at_flags.sh
index e3f13f96a27c..fac4d0c049fc 100755
--- a/tools/perf/trace/beauty/fs_at_flags.sh
+++ b/tools/perf/trace/beauty/fs_at_flags.sh
@@ -13,13 +13,14 @@ printf "static const char *fs_at_flags[] = {\n"
regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+AT_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
# AT_EACCESS is only meaningful to faccessat, so we will special case it there...
# AT_STATX_SYNC_TYPE is not a bit, its a mask of AT_STATX_SYNC_AS_STAT, AT_STATX_FORCE_SYNC and AT_STATX_DONT_SYNC
-# AT_HANDLE_FID and AT_HANDLE_MNT_ID_UNIQUE are reusing values and are valid only for name_to_handle_at()
+# AT_HANDLE_FID, AT_HANDLE_MNT_ID_UNIQUE and AT_HANDLE_CONNECTABLE are reusing values and are valid only for name_to_handle_at()
# AT_RENAME_NOREPLACE reuses 0x1 and is valid only for renameat2()
grep -E $regex ${linux_fcntl} | \
grep -v AT_EACCESS | \
grep -v AT_STATX_SYNC_TYPE | \
grep -v AT_HANDLE_FID | \
grep -v AT_HANDLE_MNT_ID_UNIQUE | \
+ grep -v AT_HANDLE_CONNECTABLE | \
grep -v AT_RENAME_NOREPLACE | \
sed -r "s/$regex/\2 \1/g" | \
xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
index 87e2dec79fea..6e6907e63bfc 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
@@ -153,9 +153,6 @@
object identity and may not be
usable with open_by_handle_at(2). */
#define AT_HANDLE_MNT_ID_UNIQUE 0x001 /* Return the u64 unique mount ID. */
-
-#if defined(__KERNEL__)
-#define AT_GETATTR_NOSEC 0x80000000
-#endif
+#define AT_HANDLE_CONNECTABLE 0x002 /* Request a connectable file handle */
#endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h
index 225bc366ffcb..c07008816aca 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/mount.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h
@@ -154,7 +154,7 @@ struct mount_attr {
*/
struct statmount {
__u32 size; /* Total size, including strings */
- __u32 mnt_opts; /* [str] Mount options of the mount */
+ __u32 mnt_opts; /* [str] Options (comma separated, escaped) */
__u64 mask; /* What results were written */
__u32 sb_dev_major; /* Device ID */
__u32 sb_dev_minor;
@@ -173,7 +173,13 @@ struct statmount {
__u32 mnt_root; /* [str] Root of mount relative to root of fs */
__u32 mnt_point; /* [str] Mountpoint relative to current root */
__u64 mnt_ns_id; /* ID of the mount namespace */
- __u64 __spare2[49];
+ __u32 fs_subtype; /* [str] Subtype of fs_type (if any) */
+ __u32 sb_source; /* [str] Source string of the mount */
+ __u32 opt_num; /* Number of fs options */
+ __u32 opt_array; /* [str] Array of nul terminated fs options */
+ __u32 opt_sec_num; /* Number of security options */
+ __u32 opt_sec_array; /* [str] Array of nul terminated security options */
+ __u64 __spare2[46];
char str[]; /* Variable size part containing strings */
};
@@ -207,6 +213,10 @@ struct mnt_id_req {
#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */
#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */
#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */
+#define STATMOUNT_FS_SUBTYPE 0x00000100U /* Want/got fs_subtype */
+#define STATMOUNT_SB_SOURCE 0x00000200U /* Want/got sb_source */
+#define STATMOUNT_OPT_ARRAY 0x00000400U /* Want/got opt_... */
+#define STATMOUNT_OPT_SEC_ARRAY 0x00000800U /* Want/got opt_sec... */
/*
* Special @mnt_id values that can be passed to listmount
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 35791791a879..5c6080680cb2 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -230,7 +230,7 @@ struct prctl_mm_map {
# define PR_PAC_APDBKEY (1UL << 3)
# define PR_PAC_APGAKEY (1UL << 4)
-/* Tagged user address controls for arm64 */
+/* Tagged user address controls for arm64 and RISC-V */
#define PR_SET_TAGGED_ADDR_CTRL 55
#define PR_GET_TAGGED_ADDR_CTRL 56
# define PR_TAGGED_ADDR_ENABLE (1UL << 0)
@@ -244,6 +244,9 @@ struct prctl_mm_map {
# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT)
/* Unused; kept only for source compatibility */
# define PR_MTE_TCF_SHIFT 1
+/* RISC-V pointer masking tag length */
+# define PR_PMLEN_SHIFT 24
+# define PR_PMLEN_MASK (0x7fUL << PR_PMLEN_SHIFT)
/* Control reclaim behavior when allocating memory */
#define PR_SET_IO_FLUSHER 57
@@ -328,4 +331,26 @@ struct prctl_mm_map {
# define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */
# define PR_PPC_DEXCR_CTRL_MASK 0x1f
+/*
+ * Get the current shadow stack configuration for the current thread,
+ * this will be the value configured via PR_SET_SHADOW_STACK_STATUS.
+ */
+#define PR_GET_SHADOW_STACK_STATUS 74
+
+/*
+ * Set the current shadow stack configuration. Enabling the shadow
+ * stack will cause a shadow stack to be allocated for the thread.
+ */
+#define PR_SET_SHADOW_STACK_STATUS 75
+# define PR_SHADOW_STACK_ENABLE (1UL << 0)
+# define PR_SHADOW_STACK_WRITE (1UL << 1)
+# define PR_SHADOW_STACK_PUSH (1UL << 2)
+
+/*
+ * Prevent further changes to the specified shadow stack
+ * configuration. All bits may be locked via this call, including
+ * undefined bits.
+ */
+#define PR_LOCK_SHADOW_STACK_STATUS 76
+
#endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 8982f68e7230..e763e8d99a43 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -277,7 +277,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid
struct perf_record_header_build_id b;
size_t len;
- len = sizeof(b) + name_len + 1;
+ len = name_len + 1;
len = PERF_ALIGN(len, sizeof(u64));
memset(&b, 0, sizeof(b));
@@ -286,7 +286,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid
misc |= PERF_RECORD_MISC_BUILD_ID_SIZE;
b.pid = pid;
b.header.misc = misc;
- b.header.size = len;
+ b.header.size = sizeof(b) + len;
err = do_write(fd, &b, sizeof(b));
if (err < 0)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f745723d486b..d22c5df1701e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2571,12 +2571,12 @@ try_fallback:
if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit))
goto retry_open;
- if (err == -EOPNOTSUPP && evsel__precise_ip_fallback(evsel))
- goto retry_open;
-
if (err == -EINVAL && evsel__detect_missing_features(evsel))
goto fallback_missing_features;
+ if (evsel__precise_ip_fallback(evsel))
+ goto retry_open;
+
if (evsel__handle_error_quirks(evsel, err))
goto retry_open;
diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c
index e61429b38ba7..4acb9bb19b84 100644
--- a/tools/perf/util/hwmon_pmu.c
+++ b/tools/perf/util/hwmon_pmu.c
@@ -258,8 +258,12 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu)
if (pmu->pmu.sysfs_aliases_loaded)
return 0;
- /* Use a dup-ed fd as closedir will close it. */
- dup_fd = dup(pmu->hwmon_dir_fd);
+ /*
+ * Use a dup-ed fd as closedir will close it. Use openat so that the
+ * directory contents are refreshed.
+ */
+ dup_fd = openat(pmu->hwmon_dir_fd, ".", O_DIRECTORY);
+
if (dup_fd == -1)
return -ENOMEM;
@@ -336,6 +340,9 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu)
close(fd);
}
}
+ if (hashmap__size(&pmu->events) == 0)
+ pr_debug2("hwmon_pmu: %s has no events\n", pmu->pmu.name);
+
hashmap__for_each_entry_safe((&pmu->events), cur, tmp, bkt) {
union hwmon_pmu_event_key key = {
.type_and_num = cur->key,
@@ -343,8 +350,8 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu)
struct hwmon_pmu_event_value *value = cur->pvalue;
if (!test_bit(HWMON_ITEM_INPUT, value->items)) {
- pr_debug("hwmon_pmu: removing event '%s%d' that has no input file\n",
- hwmon_type_strs[key.type], key.num);
+ pr_debug("hwmon_pmu: %s removing event '%s%d' that has no input file\n",
+ pmu->pmu.name, hwmon_type_strs[key.type], key.num);
hashmap__delete(&pmu->events, key.type_and_num, &key, &value);
zfree(&value->label);
zfree(&value->name);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 4f0ac998b0cc..27d5345d2b30 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -134,6 +134,8 @@ struct machine *machine__new_host(void)
if (machine__create_kernel_maps(machine) < 0)
goto out_delete;
+
+ machine->env = &perf_env;
}
return machine;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 6d51a4c98ad7..eaa0318e9b87 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1370,7 +1370,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
{
char *buf = strdup(arg);
char *p;
- int err;
+ int err = 0;
if (!buf)
return -ENOMEM;
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 2f36b7b6418d..625f5b046776 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -40,9 +40,9 @@ void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_fl
void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak;
u32 scx_bpf_dispatch_nr_slots(void) __ksym;
void scx_bpf_dispatch_cancel(void) __ksym;
-bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym;
-void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym;
-void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym;
+bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym __weak;
+void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak;
+void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak;
bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
u32 scx_bpf_reenqueue_local(void) __ksym;
diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c
index 21deea320bd7..e938156ed0a0 100644
--- a/tools/sched_ext/scx_central.c
+++ b/tools/sched_ext/scx_central.c
@@ -97,7 +97,7 @@ restart:
SCX_BUG_ON(!cpuset, "Failed to allocate cpuset");
CPU_ZERO(cpuset);
CPU_SET(skel->rodata->central_cpu, cpuset);
- SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset),
+ SCX_BUG_ON(sched_setaffinity(0, sizeof(*cpuset), cpuset),
"Failed to affinitize to central CPU %d (max %d)",
skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1);
CPU_FREE(cpuset);
diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch
index f6a50f06dfc4..eabfe9f411d9 100644
--- a/tools/scripts/Makefile.arch
+++ b/tools/scripts/Makefile.arch
@@ -7,8 +7,8 @@ HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
-e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
-e s/riscv.*/riscv/ -e s/loongarch.*/loongarch/)
-ifndef ARCH
-ARCH := $(HOSTARCH)
+ifeq ($(strip $(ARCH)),)
+override ARCH := $(HOSTARCH)
endif
SRCARCH := $(ARCH)
diff --git a/tools/testing/cxl/cxl_core_exports.c b/tools/testing/cxl/cxl_core_exports.c
index 077e6883921d..f088792a8925 100644
--- a/tools/testing/cxl/cxl_core_exports.c
+++ b/tools/testing/cxl/cxl_core_exports.c
@@ -4,4 +4,4 @@
#include "cxl.h"
/* Exporting of cxl_core symbols that are only used by cxl_test */
-EXPORT_SYMBOL_NS_GPL(cxl_num_decoders_committed, CXL);
+EXPORT_SYMBOL_NS_GPL(cxl_num_decoders_committed, "CXL");
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index 050725afa45d..d0337c11f9ee 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -1531,5 +1531,5 @@ MODULE_PARM_DESC(interleave_arithmetic, "Modulo:0, XOR:1");
module_init(cxl_test_init);
module_exit(cxl_test_exit);
MODULE_LICENSE("GPL v2");
-MODULE_IMPORT_NS(ACPI);
-MODULE_IMPORT_NS(CXL);
+MODULE_IMPORT_NS("ACPI");
+MODULE_IMPORT_NS("CXL");
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 71916e0e1546..347c1e7b37bd 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -1679,4 +1679,4 @@ static struct platform_driver cxl_mock_mem_driver = {
module_platform_driver(cxl_mock_mem_driver);
MODULE_LICENSE("GPL v2");
-MODULE_IMPORT_NS(CXL);
+MODULE_IMPORT_NS("CXL");
diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c
index f4ce96cc11d4..450c7566c33f 100644
--- a/tools/testing/cxl/test/mock.c
+++ b/tools/testing/cxl/test/mock.c
@@ -76,7 +76,7 @@ int __wrap_acpi_table_parse_cedt(enum acpi_cedt_type id,
return rc;
}
-EXPORT_SYMBOL_NS_GPL(__wrap_acpi_table_parse_cedt, ACPI);
+EXPORT_SYMBOL_NS_GPL(__wrap_acpi_table_parse_cedt, "ACPI");
acpi_status __wrap_acpi_evaluate_integer(acpi_handle handle,
acpi_string pathname,
@@ -147,7 +147,7 @@ struct cxl_hdm *__wrap_devm_cxl_setup_hdm(struct cxl_port *port,
return cxlhdm;
}
-EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, "CXL");
int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port)
{
@@ -162,7 +162,7 @@ int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port)
return rc;
}
-EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_passthrough_decoder, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_passthrough_decoder, "CXL");
int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
struct cxl_endpoint_dvsec_info *info)
@@ -179,7 +179,7 @@ int __wrap_devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
return rc;
}
-EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enumerate_decoders, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enumerate_decoders, "CXL");
int __wrap_devm_cxl_port_enumerate_dports(struct cxl_port *port)
{
@@ -194,7 +194,7 @@ int __wrap_devm_cxl_port_enumerate_dports(struct cxl_port *port)
return rc;
}
-EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_port_enumerate_dports, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_port_enumerate_dports, "CXL");
int __wrap_cxl_await_media_ready(struct cxl_dev_state *cxlds)
{
@@ -209,7 +209,7 @@ int __wrap_cxl_await_media_ready(struct cxl_dev_state *cxlds)
return rc;
}
-EXPORT_SYMBOL_NS_GPL(__wrap_cxl_await_media_ready, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_cxl_await_media_ready, "CXL");
int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds,
struct cxl_hdm *cxlhdm,
@@ -226,7 +226,7 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds,
return rc;
}
-EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, "CXL");
int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port,
struct cxl_endpoint_dvsec_info *info)
@@ -242,7 +242,7 @@ int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port,
return rc;
}
-EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dvsec_rr_decode, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dvsec_rr_decode, "CXL");
struct cxl_dport *__wrap_devm_cxl_add_rch_dport(struct cxl_port *port,
struct device *dport_dev,
@@ -266,7 +266,7 @@ struct cxl_dport *__wrap_devm_cxl_add_rch_dport(struct cxl_port *port,
return dport;
}
-EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_rch_dport, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_add_rch_dport, "CXL");
resource_size_t __wrap_cxl_rcd_component_reg_phys(struct device *dev,
struct cxl_dport *dport)
@@ -283,7 +283,7 @@ resource_size_t __wrap_cxl_rcd_component_reg_phys(struct device *dev,
return component_reg_phys;
}
-EXPORT_SYMBOL_NS_GPL(__wrap_cxl_rcd_component_reg_phys, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_cxl_rcd_component_reg_phys, "CXL");
void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port)
{
@@ -297,7 +297,7 @@ void __wrap_cxl_endpoint_parse_cdat(struct cxl_port *port)
cxl_endpoint_parse_cdat(port);
put_cxl_mock_ops(index);
}
-EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_cxl_endpoint_parse_cdat, "CXL");
void __wrap_cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device *host)
{
@@ -309,8 +309,8 @@ void __wrap_cxl_dport_init_ras_reporting(struct cxl_dport *dport, struct device
put_cxl_mock_ops(index);
}
-EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dport_init_ras_reporting, CXL);
+EXPORT_SYMBOL_NS_GPL(__wrap_cxl_dport_init_ras_reporting, "CXL");
MODULE_LICENSE("GPL v2");
-MODULE_IMPORT_NS(ACPI);
-MODULE_IMPORT_NS(CXL);
+MODULE_IMPORT_NS("ACPI");
+MODULE_IMPORT_NS("CXL");
diff --git a/tools/testing/nvdimm/test/ndtest.c b/tools/testing/nvdimm/test/ndtest.c
index 892e990c034a..68a064ce598c 100644
--- a/tools/testing/nvdimm/test/ndtest.c
+++ b/tools/testing/nvdimm/test/ndtest.c
@@ -883,7 +883,7 @@ static const struct platform_device_id ndtest_id[] = {
static struct platform_driver ndtest_driver = {
.probe = ndtest_probe,
- .remove_new = ndtest_remove,
+ .remove = ndtest_remove,
.driver = {
.name = KBUILD_MODNAME,
},
diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile
index 944279160fed..8dab90ad22bb 100644
--- a/tools/testing/selftests/alsa/Makefile
+++ b/tools/testing/selftests/alsa/Makefile
@@ -27,5 +27,5 @@ include ../lib.mk
$(OUTPUT)/libatest.so: conf.c alsa-local.h
$(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
-$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) alsa-local.h
+$(OUTPUT)/%: %.c $(OUTPUT)/libatest.so alsa-local.h
$(CC) $(CFLAGS) $< $(LDLIBS) -latest -o $@
diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index 0029ed9c5c9a..35f521e5f41c 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -46,6 +46,12 @@ static void atomics_sigill(void)
asm volatile(".inst 0xb82003ff" : : : );
}
+static void cmpbr_sigill(void)
+{
+ /* Not implemented, too complicated and unreliable anyway */
+}
+
+
static void crc32_sigill(void)
{
/* CRC32W W0, W0, W1 */
@@ -82,6 +88,18 @@ static void f8fma_sigill(void)
asm volatile(".inst 0xec0fc00");
}
+static void f8mm4_sigill(void)
+{
+ /* FMMLA V0.4SH, V0.16B, V0.16B */
+ asm volatile(".inst 0x6e00ec00");
+}
+
+static void f8mm8_sigill(void)
+{
+ /* FMMLA V0.4S, V0.16B, V0.16B */
+ asm volatile(".inst 0x6e80ec00");
+}
+
static void faminmax_sigill(void)
{
/* FAMIN V0.4H, V0.4H, V0.4H */
@@ -98,6 +116,12 @@ static void fpmr_sigill(void)
asm volatile("mrs x0, S3_3_C4_C4_2" : : : "x0");
}
+static void fprcvt_sigill(void)
+{
+ /* FCVTAS S0, H0 */
+ asm volatile(".inst 0x1efa0000");
+}
+
static void gcs_sigill(void)
{
unsigned long *gcspr;
@@ -226,6 +250,42 @@ static void sme2p1_sigill(void)
asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
}
+static void sme2p2_sigill(void)
+{
+ /* SMSTART SM */
+ asm volatile("msr S0_3_C4_C3_3, xzr" : : : );
+
+ /* UXTB Z0.D, P0/Z, Z0.D */
+ asm volatile(".inst 0x4c1a000" : : : );
+
+ /* SMSTOP */
+ asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void sme_aes_sigill(void)
+{
+ /* SMSTART SM */
+ asm volatile("msr S0_3_C4_C3_3, xzr" : : : );
+
+ /* AESD z0.b, z0.b, z0.b */
+ asm volatile(".inst 0x4522e400" : : : "z0");
+
+ /* SMSTOP */
+ asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void sme_sbitperm_sigill(void)
+{
+ /* SMSTART SM */
+ asm volatile("msr S0_3_C4_C3_3, xzr" : : : );
+
+ /* BDEP Z0.B, Z0.B, Z0.B */
+ asm volatile(".inst 0x4500b400" : : : "z0");
+
+ /* SMSTOP */
+ asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
static void smei16i32_sigill(void)
{
/* SMSTART */
@@ -339,8 +399,44 @@ static void smesf8fma_sigill(void)
/* SMSTART */
asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
- /* FMLALB V0.8H, V0.16B, V0.16B */
- asm volatile(".inst 0xec0fc00");
+ /* FMLALB Z0.8H, Z0.B, Z0.B */
+ asm volatile(".inst 0x64205000");
+
+ /* SMSTOP */
+ asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smesfexpa_sigill(void)
+{
+ /* SMSTART */
+ asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+ /* FEXPA Z0.D, Z0.D */
+ asm volatile(".inst 0x04e0b800");
+
+ /* SMSTOP */
+ asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smesmop4_sigill(void)
+{
+ /* SMSTART */
+ asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+ /* SMOP4A ZA0.S, Z0.B, { Z0.B - Z1.B } */
+ asm volatile(".inst 0x80108000");
+
+ /* SMSTOP */
+ asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smestmop_sigill(void)
+{
+ /* SMSTART */
+ asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+ /* STMOPA ZA0.S, { Z0.H - Z1.H }, Z0.H, Z20[0] */
+ asm volatile(".inst 0x80408008");
/* SMSTOP */
asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
@@ -364,18 +460,42 @@ static void sve2p1_sigill(void)
asm volatile(".inst 0x65000000" : : : "z0");
}
+static void sve2p2_sigill(void)
+{
+ /* NOT Z0.D, P0/Z, Z0.D */
+ asm volatile(".inst 0x4cea000" : : : "z0");
+}
+
static void sveaes_sigill(void)
{
/* AESD z0.b, z0.b, z0.b */
asm volatile(".inst 0x4522e400" : : : "z0");
}
+static void sveaes2_sigill(void)
+{
+ /* AESD {Z0.B - Z1.B }, { Z0.B - Z1.B }, Z0.Q */
+ asm volatile(".inst 0x4522ec00" : : : "z0");
+}
+
static void sveb16b16_sigill(void)
{
/* BFADD Z0.H, Z0.H, Z0.H */
asm volatile(".inst 0x65000000" : : : );
}
+static void svebfscale_sigill(void)
+{
+ /* BFSCALE Z0.H, P0/M, Z0.H, Z0.H */
+ asm volatile(".inst 0x65098000" : : : "z0");
+}
+
+static void svef16mm_sigill(void)
+{
+ /* FMMLA Z0.S, Z0.H, Z0.H */
+ asm volatile(".inst 0x6420e400");
+}
+
static void svepmull_sigill(void)
{
/* PMULLB Z0.Q, Z0.D, Z0.D */
@@ -394,6 +514,12 @@ static void svesha3_sigill(void)
asm volatile(".inst 0x4203800" : : : "z0");
}
+static void sveeltperm_sigill(void)
+{
+ /* COMPACT Z0.B, P0, Z0.B */
+ asm volatile(".inst 0x5218000" : : : "x0");
+}
+
static void svesm4_sigill(void)
{
/* SM4E Z0.S, Z0.S, Z0.S */
@@ -470,6 +596,13 @@ static const struct hwcap_data {
.sigill_fn = aes_sigill,
},
{
+ .name = "CMPBR",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_CMPBR,
+ .cpuinfo = "cmpbr",
+ .sigill_fn = cmpbr_sigill,
+ },
+ {
.name = "CRC32",
.at_hwcap = AT_HWCAP,
.hwcap_bit = HWCAP_CRC32,
@@ -524,6 +657,20 @@ static const struct hwcap_data {
.sigill_fn = f8fma_sigill,
},
{
+ .name = "F8MM8",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_F8MM8,
+ .cpuinfo = "f8mm8",
+ .sigill_fn = f8mm8_sigill,
+ },
+ {
+ .name = "F8MM4",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_F8MM4,
+ .cpuinfo = "f8mm4",
+ .sigill_fn = f8mm4_sigill,
+ },
+ {
.name = "FAMINMAX",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_FAMINMAX,
@@ -546,6 +693,13 @@ static const struct hwcap_data {
.sigill_reliable = true,
},
{
+ .name = "FPRCVT",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_FPRCVT,
+ .cpuinfo = "fprcvt",
+ .sigill_fn = fprcvt_sigill,
+ },
+ {
.name = "GCS",
.at_hwcap = AT_HWCAP,
.hwcap_bit = HWCAP_GCS,
@@ -692,6 +846,20 @@ static const struct hwcap_data {
.sigill_fn = sme2p1_sigill,
},
{
+ .name = "SME 2.2",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SME2P2,
+ .cpuinfo = "sme2p2",
+ .sigill_fn = sme2p2_sigill,
+ },
+ {
+ .name = "SME AES",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SME_AES,
+ .cpuinfo = "smeaes",
+ .sigill_fn = sme_aes_sigill,
+ },
+ {
.name = "SME I16I32",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SME_I16I32,
@@ -741,6 +909,13 @@ static const struct hwcap_data {
.sigill_fn = smelutv2_sigill,
},
{
+ .name = "SME SBITPERM",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SME_SBITPERM,
+ .cpuinfo = "smesbitperm",
+ .sigill_fn = sme_sbitperm_sigill,
+ },
+ {
.name = "SME SF8FMA",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SME_SF8FMA,
@@ -762,6 +937,27 @@ static const struct hwcap_data {
.sigill_fn = smesf8dp4_sigill,
},
{
+ .name = "SME SFEXPA",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SME_SFEXPA,
+ .cpuinfo = "smesfexpa",
+ .sigill_fn = smesfexpa_sigill,
+ },
+ {
+ .name = "SME SMOP4",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SME_SMOP4,
+ .cpuinfo = "smesmop4",
+ .sigill_fn = smesmop4_sigill,
+ },
+ {
+ .name = "SME STMOP",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SME_STMOP,
+ .cpuinfo = "smestmop",
+ .sigill_fn = smestmop_sigill,
+ },
+ {
.name = "SVE",
.at_hwcap = AT_HWCAP,
.hwcap_bit = HWCAP_SVE,
@@ -784,6 +980,13 @@ static const struct hwcap_data {
.sigill_fn = sve2p1_sigill,
},
{
+ .name = "SVE 2.2",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SVE2P2,
+ .cpuinfo = "sve2p2",
+ .sigill_fn = sve2p2_sigill,
+ },
+ {
.name = "SVE AES",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SVEAES,
@@ -791,6 +994,34 @@ static const struct hwcap_data {
.sigill_fn = sveaes_sigill,
},
{
+ .name = "SVE AES2",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SVE_AES2,
+ .cpuinfo = "sveaes2",
+ .sigill_fn = sveaes2_sigill,
+ },
+ {
+ .name = "SVE BFSCALE",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SVE_BFSCALE,
+ .cpuinfo = "svebfscale",
+ .sigill_fn = svebfscale_sigill,
+ },
+ {
+ .name = "SVE ELTPERM",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SVE_ELTPERM,
+ .cpuinfo = "sveeltperm",
+ .sigill_fn = sveeltperm_sigill,
+ },
+ {
+ .name = "SVE F16MM",
+ .at_hwcap = AT_HWCAP,
+ .hwcap_bit = HWCAP_SVE_F16MM,
+ .cpuinfo = "svef16mm",
+ .sigill_fn = svef16mm_sigill,
+ },
+ {
.name = "SVE2 B16B16",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SVE_B16B16,
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
index df3230fdac39..66ab2e0bae5f 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
+++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
@@ -81,32 +81,31 @@ do_syscall:
stp x27, x28, [sp, #96]
// Set SVCR if we're doing SME
- cbz x1, 1f
+ cbz x1, load_gpr
adrp x2, svcr_in
ldr x2, [x2, :lo12:svcr_in]
msr S3_3_C4_C2_2, x2
-1:
// Load ZA and ZT0 if enabled - uses x12 as scratch due to SME LDR
- tbz x2, #SVCR_ZA_SHIFT, 1f
+ tbz x2, #SVCR_ZA_SHIFT, load_gpr
mov w12, #0
ldr x2, =za_in
-2: _ldr_za 12, 2
+1: _ldr_za 12, 2
add x2, x2, x1
add x12, x12, #1
cmp x1, x12
- bne 2b
+ bne 1b
// ZT0
mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1
ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \
#ID_AA64SMFR0_EL1_SMEver_WIDTH
- cbz x2, 1f
+ cbz x2, load_gpr
adrp x2, zt_in
add x2, x2, :lo12:zt_in
_ldr_zt 2
-1:
+load_gpr:
// Load GPRs x8-x28, and save our SP/FP for later comparison
ldr x2, =gpr_in
add x2, x2, #64
@@ -125,9 +124,9 @@ do_syscall:
str x30, [x2], #8 // LR
// Load FPRs if we're not doing neither SVE nor streaming SVE
- cbnz x0, 1f
+ cbnz x0, check_sve_in
ldr x2, =svcr_in
- tbnz x2, #SVCR_SM_SHIFT, 1f
+ tbnz x2, #SVCR_SM_SHIFT, check_sve_in
ldr x2, =fpr_in
ldp q0, q1, [x2]
@@ -148,8 +147,8 @@ do_syscall:
ldp q30, q31, [x2, #16 * 30]
b 2f
-1:
+check_sve_in:
// Load the SVE registers if we're doing SVE/SME
ldr x2, =z_in
@@ -256,32 +255,31 @@ do_syscall:
stp q30, q31, [x2, #16 * 30]
// Save SVCR if we're doing SME
- cbz x1, 1f
+ cbz x1, check_sve_out
mrs x2, S3_3_C4_C2_2
adrp x3, svcr_out
str x2, [x3, :lo12:svcr_out]
-1:
// Save ZA if it's enabled - uses x12 as scratch due to SME STR
- tbz x2, #SVCR_ZA_SHIFT, 1f
+ tbz x2, #SVCR_ZA_SHIFT, check_sve_out
mov w12, #0
ldr x2, =za_out
-2: _str_za 12, 2
+1: _str_za 12, 2
add x2, x2, x1
add x12, x12, #1
cmp x1, x12
- bne 2b
+ bne 1b
// ZT0
mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1
ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \
#ID_AA64SMFR0_EL1_SMEver_WIDTH
- cbz x2, 1f
+ cbz x2, check_sve_out
adrp x2, zt_out
add x2, x2, :lo12:zt_out
_str_zt 2
-1:
+check_sve_out:
// Save the SVE state if we have some
cbz x0, 1f
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index c2a1842c3d8b..e9c377001f93 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -5,7 +5,6 @@ bpf-syscall*
test_verifier
test_maps
test_lru_map
-test_lpm_map
test_tag
FEATURE-DUMP.libbpf
FEATURE-DUMP.selftests
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 6ad3b1ba1920..7eeb3cbe18c7 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -83,7 +83,7 @@ CLANG_CPUV4 := 1
endif
# Order correspond to 'make run_tests' order
-TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
+TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_progs \
test_sockmap \
test_tcpnotify_user test_sysctl \
test_progs-no_alu32
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c
index d98c72dc563e..d32e4edac930 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c
@@ -20,10 +20,12 @@
#include <string.h>
#include <time.h>
#include <unistd.h>
+#include <endian.h>
#include <arpa/inet.h>
#include <sys/time.h>
#include <bpf/bpf.h>
+#include <test_maps.h>
#include "bpf_util.h"
@@ -33,6 +35,22 @@ struct tlpm_node {
uint8_t key[];
};
+struct lpm_trie_bytes_key {
+ union {
+ struct bpf_lpm_trie_key_hdr hdr;
+ __u32 prefixlen;
+ };
+ unsigned char data[8];
+};
+
+struct lpm_trie_int_key {
+ union {
+ struct bpf_lpm_trie_key_hdr hdr;
+ __u32 prefixlen;
+ };
+ unsigned int data;
+};
+
static struct tlpm_node *tlpm_match(struct tlpm_node *list,
const uint8_t *key,
size_t n_bits);
@@ -223,7 +241,7 @@ static void test_lpm_map(int keysize)
n_matches = 0;
n_matches_after_delete = 0;
n_nodes = 1 << 8;
- n_lookups = 1 << 16;
+ n_lookups = 1 << 9;
data = alloca(keysize);
memset(data, 0, keysize);
@@ -770,16 +788,385 @@ static void test_lpm_multi_thread(void)
close(map_fd);
}
-int main(void)
+static int lpm_trie_create(unsigned int key_size, unsigned int value_size, unsigned int max_entries)
+{
+ LIBBPF_OPTS(bpf_map_create_opts, opts);
+ int fd;
+
+ opts.map_flags = BPF_F_NO_PREALLOC;
+ fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie", key_size, value_size, max_entries,
+ &opts);
+ CHECK(fd < 0, "bpf_map_create", "error %d\n", errno);
+
+ return fd;
+}
+
+static void test_lpm_trie_update_flags(void)
+{
+ struct lpm_trie_int_key key;
+ unsigned int value, got;
+ int fd, err;
+
+ fd = lpm_trie_create(sizeof(key), sizeof(value), 3);
+
+ /* invalid flags (Error) */
+ key.prefixlen = 32;
+ key.data = 0;
+ value = 0;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_F_LOCK);
+ CHECK(err != -EINVAL, "invalid update flag", "error %d\n", err);
+
+ /* invalid flags (Error) */
+ key.prefixlen = 32;
+ key.data = 0;
+ value = 0;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST | BPF_EXIST);
+ CHECK(err != -EINVAL, "invalid update flag", "error %d\n", err);
+
+ /* overwrite an empty qp-trie (Error) */
+ key.prefixlen = 32;
+ key.data = 0;
+ value = 2;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
+ CHECK(err != -ENOENT, "overwrite empty qp-trie", "error %d\n", err);
+
+ /* add a new node */
+ key.prefixlen = 16;
+ key.data = 0;
+ value = 1;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+ CHECK(err, "add new elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup elem", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ /* add the same node as new node (Error) */
+ err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+ CHECK(err != -EEXIST, "add new elem again", "error %d\n", err);
+
+ /* overwrite the existed node */
+ value = 4;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
+ CHECK(err, "overwrite elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup elem", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ /* overwrite the node */
+ value = 1;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
+ CHECK(err, "update elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup elem", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ /* overwrite a non-existent node which is the prefix of the first
+ * node (Error).
+ */
+ key.prefixlen = 8;
+ key.data = 0;
+ value = 2;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
+ CHECK(err != -ENOENT, "overwrite nonexistent elem", "error %d\n", err);
+
+ /* add a new node which is the prefix of the first node */
+ err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+ CHECK(err, "add new elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup key", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ /* add another new node which will be the sibling of the first node */
+ key.prefixlen = 9;
+ key.data = htobe32(1 << 23);
+ value = 5;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+ CHECK(err, "add new elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup key", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ /* overwrite the third node */
+ value = 3;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
+ CHECK(err, "overwrite elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup key", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ /* delete the second node to make it an intermediate node */
+ key.prefixlen = 8;
+ key.data = 0;
+ err = bpf_map_delete_elem(fd, &key);
+ CHECK(err, "del elem", "error %d\n", err);
+
+ /* overwrite the intermediate node (Error) */
+ value = 2;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
+ CHECK(err != -ENOENT, "overwrite nonexistent elem", "error %d\n", err);
+
+ close(fd);
+}
+
+static void test_lpm_trie_update_full_map(void)
+{
+ struct lpm_trie_int_key key;
+ int value, got;
+ int fd, err;
+
+ fd = lpm_trie_create(sizeof(key), sizeof(value), 3);
+
+ /* add a new node */
+ key.prefixlen = 16;
+ key.data = 0;
+ value = 0;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+ CHECK(err, "add new elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup elem", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ /* add new node */
+ key.prefixlen = 8;
+ key.data = 0;
+ value = 1;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+ CHECK(err, "add new elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup elem", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ /* add new node */
+ key.prefixlen = 9;
+ key.data = htobe32(1 << 23);
+ value = 2;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+ CHECK(err, "add new elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup elem", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ /* try to add more node (Error) */
+ key.prefixlen = 32;
+ key.data = 0;
+ value = 3;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
+ CHECK(err != -ENOSPC, "add to full trie", "error %d\n", err);
+
+ /* update the value of an existed node with BPF_EXIST */
+ key.prefixlen = 16;
+ key.data = 0;
+ value = 4;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
+ CHECK(err, "overwrite elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup elem", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ /* update the value of an existed node with BPF_ANY */
+ key.prefixlen = 9;
+ key.data = htobe32(1 << 23);
+ value = 5;
+ err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
+ CHECK(err, "overwrite elem", "error %d\n", err);
+ got = 0;
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup elem", "error %d\n", err);
+ CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+ close(fd);
+}
+
+static int cmp_str(const void *a, const void *b)
+{
+ const char *str_a = *(const char **)a, *str_b = *(const char **)b;
+
+ return strcmp(str_a, str_b);
+}
+
+/* Save strings in LPM trie. The trailing '\0' for each string will be
+ * accounted in the prefixlen. The strings returned during the iteration
+ * should be sorted as expected.
+ */
+static void test_lpm_trie_iterate_strs(void)
+{
+ static const char * const keys[] = {
+ "ab", "abO", "abc", "abo", "abS", "abcd",
+ };
+ const char *sorted_keys[ARRAY_SIZE(keys)];
+ struct lpm_trie_bytes_key key, next_key;
+ unsigned int value, got, i, j, len;
+ struct lpm_trie_bytes_key *cur;
+ int fd, err;
+
+ fd = lpm_trie_create(sizeof(key), sizeof(value), ARRAY_SIZE(keys));
+
+ for (i = 0; i < ARRAY_SIZE(keys); i++) {
+ unsigned int flags;
+
+ /* add i-th element */
+ flags = i % 2 ? BPF_NOEXIST : 0;
+ len = strlen(keys[i]);
+ /* include the trailing '\0' */
+ key.prefixlen = (len + 1) * 8;
+ memset(key.data, 0, sizeof(key.data));
+ memcpy(key.data, keys[i], len);
+ value = i + 100;
+ err = bpf_map_update_elem(fd, &key, &value, flags);
+ CHECK(err, "add elem", "#%u error %d\n", i, err);
+
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup elem", "#%u error %d\n", i, err);
+ CHECK(got != value, "lookup elem", "#%u expect %u got %u\n", i, value, got);
+
+ /* re-add i-th element (Error) */
+ err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+ CHECK(err != -EEXIST, "re-add elem", "#%u error %d\n", i, err);
+
+ /* Overwrite i-th element */
+ flags = i % 2 ? 0 : BPF_EXIST;
+ value = i;
+ err = bpf_map_update_elem(fd, &key, &value, flags);
+ CHECK(err, "update elem", "error %d\n", err);
+
+ /* Lookup #[0~i] elements */
+ for (j = 0; j <= i; j++) {
+ len = strlen(keys[j]);
+ key.prefixlen = (len + 1) * 8;
+ memset(key.data, 0, sizeof(key.data));
+ memcpy(key.data, keys[j], len);
+ err = bpf_map_lookup_elem(fd, &key, &got);
+ CHECK(err, "lookup elem", "#%u/%u error %d\n", i, j, err);
+ CHECK(got != j, "lookup elem", "#%u/%u expect %u got %u\n",
+ i, j, value, got);
+ }
+ }
+
+ /* Add element to a full qp-trie (Error) */
+ key.prefixlen = sizeof(key.data) * 8;
+ memset(key.data, 0, sizeof(key.data));
+ value = 0;
+ err = bpf_map_update_elem(fd, &key, &value, 0);
+ CHECK(err != -ENOSPC, "add to full qp-trie", "error %d\n", err);
+
+ /* Iterate sorted elements: no deletion */
+ memcpy(sorted_keys, keys, sizeof(keys));
+ qsort(sorted_keys, ARRAY_SIZE(sorted_keys), sizeof(sorted_keys[0]), cmp_str);
+ cur = NULL;
+ for (i = 0; i < ARRAY_SIZE(sorted_keys); i++) {
+ len = strlen(sorted_keys[i]);
+ err = bpf_map_get_next_key(fd, cur, &next_key);
+ CHECK(err, "iterate", "#%u error %d\n", i, err);
+ CHECK(next_key.prefixlen != (len + 1) * 8, "iterate",
+ "#%u invalid len %u expect %u\n",
+ i, next_key.prefixlen, (len + 1) * 8);
+ CHECK(memcmp(sorted_keys[i], next_key.data, len + 1), "iterate",
+ "#%u got %.*s exp %.*s\n", i, len, next_key.data, len, sorted_keys[i]);
+
+ cur = &next_key;
+ }
+ err = bpf_map_get_next_key(fd, cur, &next_key);
+ CHECK(err != -ENOENT, "more element", "error %d\n", err);
+
+ /* Iterate sorted elements: delete the found key after each iteration */
+ cur = NULL;
+ for (i = 0; i < ARRAY_SIZE(sorted_keys); i++) {
+ len = strlen(sorted_keys[i]);
+ err = bpf_map_get_next_key(fd, cur, &next_key);
+ CHECK(err, "iterate", "#%u error %d\n", i, err);
+ CHECK(next_key.prefixlen != (len + 1) * 8, "iterate",
+ "#%u invalid len %u expect %u\n",
+ i, next_key.prefixlen, (len + 1) * 8);
+ CHECK(memcmp(sorted_keys[i], next_key.data, len + 1), "iterate",
+ "#%u got %.*s exp %.*s\n", i, len, next_key.data, len, sorted_keys[i]);
+
+ cur = &next_key;
+
+ err = bpf_map_delete_elem(fd, cur);
+ CHECK(err, "delete", "#%u error %d\n", i, err);
+ }
+ err = bpf_map_get_next_key(fd, cur, &next_key);
+ CHECK(err != -ENOENT, "non-empty qp-trie", "error %d\n", err);
+
+ close(fd);
+}
+
+/* Use the fixed prefixlen (32) and save integers in LPM trie. The iteration of
+ * LPM trie will return these integers in big-endian order, therefore, convert
+ * these integers to big-endian before update. After each iteration, delete the
+ * found key (the smallest integer) and expect the next iteration will return
+ * the second smallest number.
+ */
+static void test_lpm_trie_iterate_ints(void)
+{
+ struct lpm_trie_int_key key, next_key;
+ unsigned int i, max_entries;
+ struct lpm_trie_int_key *cur;
+ unsigned int *data_set;
+ int fd, err;
+ bool value;
+
+ max_entries = 4096;
+ data_set = calloc(max_entries, sizeof(*data_set));
+ CHECK(!data_set, "malloc", "no mem\n");
+ for (i = 0; i < max_entries; i++)
+ data_set[i] = i;
+
+ fd = lpm_trie_create(sizeof(key), sizeof(value), max_entries);
+ value = true;
+ for (i = 0; i < max_entries; i++) {
+ key.prefixlen = 32;
+ key.data = htobe32(data_set[i]);
+
+ err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+ CHECK(err, "add elem", "#%u error %d\n", i, err);
+ }
+
+ cur = NULL;
+ for (i = 0; i < max_entries; i++) {
+ err = bpf_map_get_next_key(fd, cur, &next_key);
+ CHECK(err, "iterate", "#%u error %d\n", i, err);
+ CHECK(next_key.prefixlen != 32, "iterate", "#%u invalid len %u\n",
+ i, next_key.prefixlen);
+ CHECK(be32toh(next_key.data) != data_set[i], "iterate", "#%u got 0x%x exp 0x%x\n",
+ i, be32toh(next_key.data), data_set[i]);
+ cur = &next_key;
+
+ /*
+ * Delete the minimal key, the next call of bpf_get_next_key()
+ * will return the second minimal key.
+ */
+ err = bpf_map_delete_elem(fd, &next_key);
+ CHECK(err, "del elem", "#%u elem error %d\n", i, err);
+ }
+ err = bpf_map_get_next_key(fd, cur, &next_key);
+ CHECK(err != -ENOENT, "more element", "error %d\n", err);
+
+ err = bpf_map_get_next_key(fd, NULL, &next_key);
+ CHECK(err != -ENOENT, "no-empty qp-trie", "error %d\n", err);
+
+ free(data_set);
+
+ close(fd);
+}
+
+void test_lpm_trie_map_basic_ops(void)
{
int i;
/* we want predictable, pseudo random tests */
srand(0xf00ba1);
- /* Use libbpf 1.0 API mode */
- libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
test_lpm_basic();
test_lpm_order();
@@ -792,6 +1179,10 @@ int main(void)
test_lpm_get_next_key();
test_lpm_multi_thread();
- printf("test_lpm: OK\n");
- return 0;
+ test_lpm_trie_update_flags();
+ test_lpm_trie_update_full_map();
+ test_lpm_trie_iterate_strs();
+ test_lpm_trie_iterate_ints();
+
+ printf("%s: PASS\n", __func__);
}
diff --git a/tools/testing/selftests/bpf/map_tests/task_storage_map.c b/tools/testing/selftests/bpf/map_tests/task_storage_map.c
index 62971dbf2996..a4121d2248ac 100644
--- a/tools/testing/selftests/bpf/map_tests/task_storage_map.c
+++ b/tools/testing/selftests/bpf/map_tests/task_storage_map.c
@@ -78,8 +78,8 @@ void test_task_storage_map_stress_lookup(void)
CHECK(err, "open_and_load", "error %d\n", err);
/* Only for a fully preemptible kernel */
- if (!skel->kconfig->CONFIG_PREEMPT) {
- printf("%s SKIP (no CONFIG_PREEMPT)\n", __func__);
+ if (!skel->kconfig->CONFIG_PREEMPTION) {
+ printf("%s SKIP (no CONFIG_PREEMPTION)\n", __func__);
read_bpf_task_storage_busy__destroy(skel);
skips++;
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c b/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c
new file mode 100644
index 000000000000..7526de379081
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "bpf/libbpf.h"
+#include "changes_pkt_data_freplace.skel.h"
+#include "changes_pkt_data.skel.h"
+#include <test_progs.h>
+
+static void print_verifier_log(const char *log)
+{
+ if (env.verbosity >= VERBOSE_VERY)
+ fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log);
+}
+
+static void test_aux(const char *main_prog_name,
+ const char *to_be_replaced,
+ const char *replacement,
+ bool expect_load)
+{
+ struct changes_pkt_data_freplace *freplace = NULL;
+ struct bpf_program *freplace_prog = NULL;
+ struct bpf_program *main_prog = NULL;
+ LIBBPF_OPTS(bpf_object_open_opts, opts);
+ struct changes_pkt_data *main = NULL;
+ char log[16*1024];
+ int err;
+
+ opts.kernel_log_buf = log;
+ opts.kernel_log_size = sizeof(log);
+ if (env.verbosity >= VERBOSE_SUPER)
+ opts.kernel_log_level = 1 | 2 | 4;
+ main = changes_pkt_data__open_opts(&opts);
+ if (!ASSERT_OK_PTR(main, "changes_pkt_data__open"))
+ goto out;
+ main_prog = bpf_object__find_program_by_name(main->obj, main_prog_name);
+ if (!ASSERT_OK_PTR(main_prog, "main_prog"))
+ goto out;
+ bpf_program__set_autoload(main_prog, true);
+ err = changes_pkt_data__load(main);
+ print_verifier_log(log);
+ if (!ASSERT_OK(err, "changes_pkt_data__load"))
+ goto out;
+ freplace = changes_pkt_data_freplace__open_opts(&opts);
+ if (!ASSERT_OK_PTR(freplace, "changes_pkt_data_freplace__open"))
+ goto out;
+ freplace_prog = bpf_object__find_program_by_name(freplace->obj, replacement);
+ if (!ASSERT_OK_PTR(freplace_prog, "freplace_prog"))
+ goto out;
+ bpf_program__set_autoload(freplace_prog, true);
+ bpf_program__set_autoattach(freplace_prog, true);
+ bpf_program__set_attach_target(freplace_prog,
+ bpf_program__fd(main_prog),
+ to_be_replaced);
+ err = changes_pkt_data_freplace__load(freplace);
+ print_verifier_log(log);
+ if (expect_load) {
+ ASSERT_OK(err, "changes_pkt_data_freplace__load");
+ } else {
+ ASSERT_ERR(err, "changes_pkt_data_freplace__load");
+ ASSERT_HAS_SUBSTR(log, "Extension program changes packet data", "error log");
+ }
+
+out:
+ changes_pkt_data_freplace__destroy(freplace);
+ changes_pkt_data__destroy(main);
+}
+
+/* There are two global subprograms in both changes_pkt_data.skel.h:
+ * - one changes packet data;
+ * - another does not.
+ * It is ok to freplace subprograms that change packet data with those
+ * that either do or do not. It is only ok to freplace subprograms
+ * that do not change packet data with those that do not as well.
+ * The below tests check outcomes for each combination of such freplace.
+ * Also test a case when main subprogram itself is replaced and is a single
+ * subprogram in a program.
+ */
+void test_changes_pkt_data_freplace(void)
+{
+ struct {
+ const char *main;
+ const char *to_be_replaced;
+ bool changes;
+ } mains[] = {
+ { "main_with_subprogs", "changes_pkt_data", true },
+ { "main_with_subprogs", "does_not_change_pkt_data", false },
+ { "main_changes", "main_changes", true },
+ { "main_does_not_change", "main_does_not_change", false },
+ };
+ struct {
+ const char *func;
+ bool changes;
+ } replacements[] = {
+ { "changes_pkt_data", true },
+ { "does_not_change_pkt_data", false }
+ };
+ char buf[64];
+
+ for (int i = 0; i < ARRAY_SIZE(mains); ++i) {
+ for (int j = 0; j < ARRAY_SIZE(replacements); ++j) {
+ snprintf(buf, sizeof(buf), "%s_with_%s",
+ mains[i].to_be_replaced, replacements[j].func);
+ if (!test__start_subtest(buf))
+ continue;
+ test_aux(mains[i].main, mains[i].to_be_replaced, replacements[j].func,
+ mains[i].changes || !replacements[j].changes);
+ }
+ }
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
index 6fa19449297e..43676a9922dc 100644
--- a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
@@ -3,11 +3,14 @@
#include <test_progs.h>
#include "raw_tp_null.skel.h"
+#include "raw_tp_null_fail.skel.h"
void test_raw_tp_null(void)
{
struct raw_tp_null *skel;
+ RUN_TESTS(raw_tp_null_fail);
+
skel = raw_tp_null__open_and_load();
if (!ASSERT_OK_PTR(skel, "raw_tp_null__open_and_load"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
new file mode 100644
index 000000000000..1bdfb79ef009
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
@@ -0,0 +1,394 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __SOCKET_HELPERS__
+#define __SOCKET_HELPERS__
+
+#include <linux/vm_sockets.h>
+
+/* include/linux/net.h */
+#define SOCK_TYPE_MASK 0xf
+
+#define IO_TIMEOUT_SEC 30
+#define MAX_STRERR_LEN 256
+
+/* workaround for older vm_sockets.h */
+#ifndef VMADDR_CID_LOCAL
+#define VMADDR_CID_LOCAL 1
+#endif
+
+/* include/linux/cleanup.h */
+#define __get_and_null(p, nullvalue) \
+ ({ \
+ __auto_type __ptr = &(p); \
+ __auto_type __val = *__ptr; \
+ *__ptr = nullvalue; \
+ __val; \
+ })
+
+#define take_fd(fd) __get_and_null(fd, -EBADF)
+
+/* Wrappers that fail the test on error and report it. */
+
+#define _FAIL(errnum, fmt...) \
+ ({ \
+ error_at_line(0, (errnum), __func__, __LINE__, fmt); \
+ CHECK_FAIL(true); \
+ })
+#define FAIL(fmt...) _FAIL(0, fmt)
+#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt)
+#define FAIL_LIBBPF(err, msg) \
+ ({ \
+ char __buf[MAX_STRERR_LEN]; \
+ libbpf_strerror((err), __buf, sizeof(__buf)); \
+ FAIL("%s: %s", (msg), __buf); \
+ })
+
+
+#define xaccept_nonblock(fd, addr, len) \
+ ({ \
+ int __ret = \
+ accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \
+ if (__ret == -1) \
+ FAIL_ERRNO("accept"); \
+ __ret; \
+ })
+
+#define xbind(fd, addr, len) \
+ ({ \
+ int __ret = bind((fd), (addr), (len)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("bind"); \
+ __ret; \
+ })
+
+#define xclose(fd) \
+ ({ \
+ int __ret = close((fd)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("close"); \
+ __ret; \
+ })
+
+#define xconnect(fd, addr, len) \
+ ({ \
+ int __ret = connect((fd), (addr), (len)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("connect"); \
+ __ret; \
+ })
+
+#define xgetsockname(fd, addr, len) \
+ ({ \
+ int __ret = getsockname((fd), (addr), (len)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("getsockname"); \
+ __ret; \
+ })
+
+#define xgetsockopt(fd, level, name, val, len) \
+ ({ \
+ int __ret = getsockopt((fd), (level), (name), (val), (len)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("getsockopt(" #name ")"); \
+ __ret; \
+ })
+
+#define xlisten(fd, backlog) \
+ ({ \
+ int __ret = listen((fd), (backlog)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("listen"); \
+ __ret; \
+ })
+
+#define xsetsockopt(fd, level, name, val, len) \
+ ({ \
+ int __ret = setsockopt((fd), (level), (name), (val), (len)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("setsockopt(" #name ")"); \
+ __ret; \
+ })
+
+#define xsend(fd, buf, len, flags) \
+ ({ \
+ ssize_t __ret = send((fd), (buf), (len), (flags)); \
+ if (__ret == -1) \
+ FAIL_ERRNO("send"); \
+ __ret; \
+ })
+
+#define xrecv_nonblock(fd, buf, len, flags) \
+ ({ \
+ ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \
+ IO_TIMEOUT_SEC); \
+ if (__ret == -1) \
+ FAIL_ERRNO("recv"); \
+ __ret; \
+ })
+
+#define xsocket(family, sotype, flags) \
+ ({ \
+ int __ret = socket(family, sotype, flags); \
+ if (__ret == -1) \
+ FAIL_ERRNO("socket"); \
+ __ret; \
+ })
+
+static inline void close_fd(int *fd)
+{
+ if (*fd >= 0)
+ xclose(*fd);
+}
+
+#define __close_fd __attribute__((cleanup(close_fd)))
+
+static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss)
+{
+ return (struct sockaddr *)ss;
+}
+
+static inline void init_addr_loopback4(struct sockaddr_storage *ss,
+ socklen_t *len)
+{
+ struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
+
+ addr4->sin_family = AF_INET;
+ addr4->sin_port = 0;
+ addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ *len = sizeof(*addr4);
+}
+
+static inline void init_addr_loopback6(struct sockaddr_storage *ss,
+ socklen_t *len)
+{
+ struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss));
+
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = 0;
+ addr6->sin6_addr = in6addr_loopback;
+ *len = sizeof(*addr6);
+}
+
+static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss,
+ socklen_t *len)
+{
+ struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss));
+
+ addr->svm_family = AF_VSOCK;
+ addr->svm_port = VMADDR_PORT_ANY;
+ addr->svm_cid = VMADDR_CID_LOCAL;
+ *len = sizeof(*addr);
+}
+
+static inline void init_addr_loopback(int family, struct sockaddr_storage *ss,
+ socklen_t *len)
+{
+ switch (family) {
+ case AF_INET:
+ init_addr_loopback4(ss, len);
+ return;
+ case AF_INET6:
+ init_addr_loopback6(ss, len);
+ return;
+ case AF_VSOCK:
+ init_addr_loopback_vsock(ss, len);
+ return;
+ default:
+ FAIL("unsupported address family %d", family);
+ }
+}
+
+static inline int enable_reuseport(int s, int progfd)
+{
+ int err, one = 1;
+
+ err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
+ if (err)
+ return -1;
+ err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd,
+ sizeof(progfd));
+ if (err)
+ return -1;
+
+ return 0;
+}
+
+static inline int socket_loopback_reuseport(int family, int sotype, int progfd)
+{
+ struct sockaddr_storage addr;
+ socklen_t len = 0;
+ int err, s;
+
+ init_addr_loopback(family, &addr, &len);
+
+ s = xsocket(family, sotype, 0);
+ if (s == -1)
+ return -1;
+
+ if (progfd >= 0)
+ enable_reuseport(s, progfd);
+
+ err = xbind(s, sockaddr(&addr), len);
+ if (err)
+ goto close;
+
+ if (sotype & SOCK_DGRAM)
+ return s;
+
+ err = xlisten(s, SOMAXCONN);
+ if (err)
+ goto close;
+
+ return s;
+close:
+ xclose(s);
+ return -1;
+}
+
+static inline int socket_loopback(int family, int sotype)
+{
+ return socket_loopback_reuseport(family, sotype, -1);
+}
+
+static inline int poll_connect(int fd, unsigned int timeout_sec)
+{
+ struct timeval timeout = { .tv_sec = timeout_sec };
+ fd_set wfds;
+ int r, eval;
+ socklen_t esize = sizeof(eval);
+
+ FD_ZERO(&wfds);
+ FD_SET(fd, &wfds);
+
+ r = select(fd + 1, NULL, &wfds, NULL, &timeout);
+ if (r == 0)
+ errno = ETIME;
+ if (r != 1)
+ return -1;
+
+ if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0)
+ return -1;
+ if (eval != 0) {
+ errno = eval;
+ return -1;
+ }
+
+ return 0;
+}
+
+static inline int poll_read(int fd, unsigned int timeout_sec)
+{
+ struct timeval timeout = { .tv_sec = timeout_sec };
+ fd_set rfds;
+ int r;
+
+ FD_ZERO(&rfds);
+ FD_SET(fd, &rfds);
+
+ r = select(fd + 1, &rfds, NULL, NULL, &timeout);
+ if (r == 0)
+ errno = ETIME;
+
+ return r == 1 ? 0 : -1;
+}
+
+static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len,
+ unsigned int timeout_sec)
+{
+ if (poll_read(fd, timeout_sec))
+ return -1;
+
+ return accept(fd, addr, len);
+}
+
+static inline int recv_timeout(int fd, void *buf, size_t len, int flags,
+ unsigned int timeout_sec)
+{
+ if (poll_read(fd, timeout_sec))
+ return -1;
+
+ return recv(fd, buf, len, flags);
+}
+
+
+static inline int create_pair(int family, int sotype, int *p0, int *p1)
+{
+ __close_fd int s, c = -1, p = -1;
+ struct sockaddr_storage addr;
+ socklen_t len = sizeof(addr);
+ int err;
+
+ s = socket_loopback(family, sotype);
+ if (s < 0)
+ return s;
+
+ err = xgetsockname(s, sockaddr(&addr), &len);
+ if (err)
+ return err;
+
+ c = xsocket(family, sotype, 0);
+ if (c < 0)
+ return c;
+
+ err = connect(c, sockaddr(&addr), len);
+ if (err) {
+ if (errno != EINPROGRESS) {
+ FAIL_ERRNO("connect");
+ return err;
+ }
+
+ err = poll_connect(c, IO_TIMEOUT_SEC);
+ if (err) {
+ FAIL_ERRNO("poll_connect");
+ return err;
+ }
+ }
+
+ switch (sotype & SOCK_TYPE_MASK) {
+ case SOCK_DGRAM:
+ err = xgetsockname(c, sockaddr(&addr), &len);
+ if (err)
+ return err;
+
+ err = xconnect(s, sockaddr(&addr), len);
+ if (err)
+ return err;
+
+ *p0 = take_fd(s);
+ break;
+ case SOCK_STREAM:
+ case SOCK_SEQPACKET:
+ p = xaccept_nonblock(s, NULL, NULL);
+ if (p < 0)
+ return p;
+
+ *p0 = take_fd(p);
+ break;
+ default:
+ FAIL("Unsupported socket type %#x", sotype);
+ return -EOPNOTSUPP;
+ }
+
+ *p1 = take_fd(c);
+ return 0;
+}
+
+static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1,
+ int *p0, int *p1)
+{
+ int err;
+
+ err = create_pair(family, sotype, c0, p0);
+ if (err)
+ return err;
+
+ err = create_pair(family, sotype, c1, p1);
+ if (err) {
+ close(*c0);
+ close(*p0);
+ }
+
+ return err;
+}
+
+#endif // __SOCKET_HELPERS__
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index a2041f8e32eb..884ad87783d5 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -12,6 +12,7 @@
#include "test_sockmap_progs_query.skel.h"
#include "test_sockmap_pass_prog.skel.h"
#include "test_sockmap_drop_prog.skel.h"
+#include "test_sockmap_change_tail.skel.h"
#include "bpf_iter_sockmap.skel.h"
#include "sockmap_helpers.h"
@@ -108,6 +109,35 @@ out:
close(s);
}
+static void test_sockmap_vsock_delete_on_close(void)
+{
+ int err, c, p, map;
+ const int zero = 0;
+
+ err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p);
+ if (!ASSERT_OK(err, "create_pair(AF_VSOCK)"))
+ return;
+
+ map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int),
+ sizeof(int), 1, NULL);
+ if (!ASSERT_GE(map, 0, "bpf_map_create")) {
+ close(c);
+ goto out;
+ }
+
+ err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST);
+ close(c);
+ if (!ASSERT_OK(err, "bpf_map_update"))
+ goto out;
+
+ err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+ ASSERT_OK(err, "after close(), bpf_map_update");
+
+out:
+ close(p);
+ close(map);
+}
+
static void test_skmsg_helpers(enum bpf_map_type map_type)
{
struct test_skmsg_load_helpers *skel;
@@ -614,6 +644,54 @@ out:
test_sockmap_drop_prog__destroy(drop);
}
+static void test_sockmap_skb_verdict_change_tail(void)
+{
+ struct test_sockmap_change_tail *skel;
+ int err, map, verdict;
+ int c1, p1, sent, recvd;
+ int zero = 0;
+ char buf[2];
+
+ skel = test_sockmap_change_tail__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "open_and_load"))
+ return;
+ verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ map = bpf_map__fd(skel->maps.sock_map_rx);
+
+ err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+ if (!ASSERT_OK(err, "bpf_prog_attach"))
+ goto out;
+ err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1);
+ if (!ASSERT_OK(err, "create_pair()"))
+ goto out;
+ err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "bpf_map_update_elem(c1)"))
+ goto out_close;
+ sent = xsend(p1, "Tr", 2, 0);
+ ASSERT_EQ(sent, 2, "xsend(p1)");
+ recvd = recv(c1, buf, 2, 0);
+ ASSERT_EQ(recvd, 1, "recv(c1)");
+ ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+ sent = xsend(p1, "G", 1, 0);
+ ASSERT_EQ(sent, 1, "xsend(p1)");
+ recvd = recv(c1, buf, 2, 0);
+ ASSERT_EQ(recvd, 2, "recv(c1)");
+ ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+ sent = xsend(p1, "E", 1, 0);
+ ASSERT_EQ(sent, 1, "xsend(p1)");
+ recvd = recv(c1, buf, 1, 0);
+ ASSERT_EQ(recvd, 1, "recv(c1)");
+ ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+out_close:
+ close(c1);
+ close(p1);
+out:
+ test_sockmap_change_tail__destroy(skel);
+}
+
static void test_sockmap_skb_verdict_peek_helper(int map)
{
int err, c1, p1, zero = 0, sent, recvd, avail;
@@ -905,8 +983,10 @@ static void test_sockmap_same_sock(void)
err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
- if (err)
+ if (err) {
+ close(tcp);
goto out;
+ }
for (i = 0; i < 2; i++) {
err = bpf_map_update_elem(map, &zero, &stream[0], BPF_ANY);
@@ -925,24 +1005,70 @@ static void test_sockmap_same_sock(void)
ASSERT_OK(err, "bpf_map_update_elem(tcp)");
}
+ close(tcp);
err = bpf_map_delete_elem(map, &zero);
- ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+ ASSERT_ERR(err, "bpf_map_delete_elem(entry)");
close(stream[0]);
close(stream[1]);
out:
close(dgram);
- close(tcp);
close(udp);
test_sockmap_pass_prog__destroy(skel);
}
+static void test_sockmap_skb_verdict_vsock_poll(void)
+{
+ struct test_sockmap_pass_prog *skel;
+ int err, map, conn, peer;
+ struct bpf_program *prog;
+ struct bpf_link *link;
+ char buf = 'x';
+ int zero = 0;
+
+ skel = test_sockmap_pass_prog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "open_and_load"))
+ return;
+
+ if (create_pair(AF_VSOCK, SOCK_STREAM, &conn, &peer))
+ goto destroy;
+
+ prog = skel->progs.prog_skb_verdict;
+ map = bpf_map__fd(skel->maps.sock_map_rx);
+ link = bpf_program__attach_sockmap(prog, map);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap"))
+ goto close;
+
+ err = bpf_map_update_elem(map, &zero, &conn, BPF_ANY);
+ if (!ASSERT_OK(err, "bpf_map_update_elem"))
+ goto detach;
+
+ if (xsend(peer, &buf, 1, 0) != 1)
+ goto detach;
+
+ err = poll_read(conn, IO_TIMEOUT_SEC);
+ if (!ASSERT_OK(err, "poll"))
+ goto detach;
+
+ if (xrecv_nonblock(conn, &buf, 1, 0) != 1)
+ FAIL("xrecv_nonblock");
+detach:
+ bpf_link__detach(link);
+close:
+ xclose(conn);
+ xclose(peer);
+destroy:
+ test_sockmap_pass_prog__destroy(skel);
+}
+
void test_sockmap_basic(void)
{
if (test__start_subtest("sockmap create_update_free"))
test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP);
if (test__start_subtest("sockhash create_update_free"))
test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH);
+ if (test__start_subtest("sockmap vsock delete on close"))
+ test_sockmap_vsock_delete_on_close();
if (test__start_subtest("sockmap sk_msg load helpers"))
test_skmsg_helpers(BPF_MAP_TYPE_SOCKMAP);
if (test__start_subtest("sockhash sk_msg load helpers"))
@@ -981,6 +1107,8 @@ void test_sockmap_basic(void)
test_sockmap_skb_verdict_fionread(true);
if (test__start_subtest("sockmap skb_verdict fionread on drop"))
test_sockmap_skb_verdict_fionread(false);
+ if (test__start_subtest("sockmap skb_verdict change tail"))
+ test_sockmap_skb_verdict_change_tail();
if (test__start_subtest("sockmap skb_verdict msg_f_peek"))
test_sockmap_skb_verdict_peek();
if (test__start_subtest("sockmap skb_verdict msg_f_peek with link"))
@@ -997,4 +1125,6 @@ void test_sockmap_basic(void)
test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKMAP);
if (test__start_subtest("sockhash sk_msg attach sockhash helpers with link"))
test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKHASH);
+ if (test__start_subtest("sockmap skb_verdict vsock poll"))
+ test_sockmap_skb_verdict_vsock_poll();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
index 38e35c72bdaa..3e5571dd578d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -1,139 +1,12 @@
#ifndef __SOCKMAP_HELPERS__
#define __SOCKMAP_HELPERS__
-#include <linux/vm_sockets.h>
+#include "socket_helpers.h"
-/* include/linux/net.h */
-#define SOCK_TYPE_MASK 0xf
-
-#define IO_TIMEOUT_SEC 30
-#define MAX_STRERR_LEN 256
#define MAX_TEST_NAME 80
-/* workaround for older vm_sockets.h */
-#ifndef VMADDR_CID_LOCAL
-#define VMADDR_CID_LOCAL 1
-#endif
-
#define __always_unused __attribute__((__unused__))
-/* include/linux/cleanup.h */
-#define __get_and_null(p, nullvalue) \
- ({ \
- __auto_type __ptr = &(p); \
- __auto_type __val = *__ptr; \
- *__ptr = nullvalue; \
- __val; \
- })
-
-#define take_fd(fd) __get_and_null(fd, -EBADF)
-
-#define _FAIL(errnum, fmt...) \
- ({ \
- error_at_line(0, (errnum), __func__, __LINE__, fmt); \
- CHECK_FAIL(true); \
- })
-#define FAIL(fmt...) _FAIL(0, fmt)
-#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt)
-#define FAIL_LIBBPF(err, msg) \
- ({ \
- char __buf[MAX_STRERR_LEN]; \
- libbpf_strerror((err), __buf, sizeof(__buf)); \
- FAIL("%s: %s", (msg), __buf); \
- })
-
-/* Wrappers that fail the test on error and report it. */
-
-#define xaccept_nonblock(fd, addr, len) \
- ({ \
- int __ret = \
- accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC); \
- if (__ret == -1) \
- FAIL_ERRNO("accept"); \
- __ret; \
- })
-
-#define xbind(fd, addr, len) \
- ({ \
- int __ret = bind((fd), (addr), (len)); \
- if (__ret == -1) \
- FAIL_ERRNO("bind"); \
- __ret; \
- })
-
-#define xclose(fd) \
- ({ \
- int __ret = close((fd)); \
- if (__ret == -1) \
- FAIL_ERRNO("close"); \
- __ret; \
- })
-
-#define xconnect(fd, addr, len) \
- ({ \
- int __ret = connect((fd), (addr), (len)); \
- if (__ret == -1) \
- FAIL_ERRNO("connect"); \
- __ret; \
- })
-
-#define xgetsockname(fd, addr, len) \
- ({ \
- int __ret = getsockname((fd), (addr), (len)); \
- if (__ret == -1) \
- FAIL_ERRNO("getsockname"); \
- __ret; \
- })
-
-#define xgetsockopt(fd, level, name, val, len) \
- ({ \
- int __ret = getsockopt((fd), (level), (name), (val), (len)); \
- if (__ret == -1) \
- FAIL_ERRNO("getsockopt(" #name ")"); \
- __ret; \
- })
-
-#define xlisten(fd, backlog) \
- ({ \
- int __ret = listen((fd), (backlog)); \
- if (__ret == -1) \
- FAIL_ERRNO("listen"); \
- __ret; \
- })
-
-#define xsetsockopt(fd, level, name, val, len) \
- ({ \
- int __ret = setsockopt((fd), (level), (name), (val), (len)); \
- if (__ret == -1) \
- FAIL_ERRNO("setsockopt(" #name ")"); \
- __ret; \
- })
-
-#define xsend(fd, buf, len, flags) \
- ({ \
- ssize_t __ret = send((fd), (buf), (len), (flags)); \
- if (__ret == -1) \
- FAIL_ERRNO("send"); \
- __ret; \
- })
-
-#define xrecv_nonblock(fd, buf, len, flags) \
- ({ \
- ssize_t __ret = recv_timeout((fd), (buf), (len), (flags), \
- IO_TIMEOUT_SEC); \
- if (__ret == -1) \
- FAIL_ERRNO("recv"); \
- __ret; \
- })
-
-#define xsocket(family, sotype, flags) \
- ({ \
- int __ret = socket(family, sotype, flags); \
- if (__ret == -1) \
- FAIL_ERRNO("socket"); \
- __ret; \
- })
-
#define xbpf_map_delete_elem(fd, key) \
({ \
int __ret = bpf_map_delete_elem((fd), (key)); \
@@ -193,130 +66,6 @@
__ret; \
})
-static inline void close_fd(int *fd)
-{
- if (*fd >= 0)
- xclose(*fd);
-}
-
-#define __close_fd __attribute__((cleanup(close_fd)))
-
-static inline int poll_connect(int fd, unsigned int timeout_sec)
-{
- struct timeval timeout = { .tv_sec = timeout_sec };
- fd_set wfds;
- int r, eval;
- socklen_t esize = sizeof(eval);
-
- FD_ZERO(&wfds);
- FD_SET(fd, &wfds);
-
- r = select(fd + 1, NULL, &wfds, NULL, &timeout);
- if (r == 0)
- errno = ETIME;
- if (r != 1)
- return -1;
-
- if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0)
- return -1;
- if (eval != 0) {
- errno = eval;
- return -1;
- }
-
- return 0;
-}
-
-static inline int poll_read(int fd, unsigned int timeout_sec)
-{
- struct timeval timeout = { .tv_sec = timeout_sec };
- fd_set rfds;
- int r;
-
- FD_ZERO(&rfds);
- FD_SET(fd, &rfds);
-
- r = select(fd + 1, &rfds, NULL, NULL, &timeout);
- if (r == 0)
- errno = ETIME;
-
- return r == 1 ? 0 : -1;
-}
-
-static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len,
- unsigned int timeout_sec)
-{
- if (poll_read(fd, timeout_sec))
- return -1;
-
- return accept(fd, addr, len);
-}
-
-static inline int recv_timeout(int fd, void *buf, size_t len, int flags,
- unsigned int timeout_sec)
-{
- if (poll_read(fd, timeout_sec))
- return -1;
-
- return recv(fd, buf, len, flags);
-}
-
-static inline void init_addr_loopback4(struct sockaddr_storage *ss,
- socklen_t *len)
-{
- struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
-
- addr4->sin_family = AF_INET;
- addr4->sin_port = 0;
- addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
- *len = sizeof(*addr4);
-}
-
-static inline void init_addr_loopback6(struct sockaddr_storage *ss,
- socklen_t *len)
-{
- struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss));
-
- addr6->sin6_family = AF_INET6;
- addr6->sin6_port = 0;
- addr6->sin6_addr = in6addr_loopback;
- *len = sizeof(*addr6);
-}
-
-static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss,
- socklen_t *len)
-{
- struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss));
-
- addr->svm_family = AF_VSOCK;
- addr->svm_port = VMADDR_PORT_ANY;
- addr->svm_cid = VMADDR_CID_LOCAL;
- *len = sizeof(*addr);
-}
-
-static inline void init_addr_loopback(int family, struct sockaddr_storage *ss,
- socklen_t *len)
-{
- switch (family) {
- case AF_INET:
- init_addr_loopback4(ss, len);
- return;
- case AF_INET6:
- init_addr_loopback6(ss, len);
- return;
- case AF_VSOCK:
- init_addr_loopback_vsock(ss, len);
- return;
- default:
- FAIL("unsupported address family %d", family);
- }
-}
-
-static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss)
-{
- return (struct sockaddr *)ss;
-}
-
static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2)
{
u64 value;
@@ -334,136 +83,4 @@ static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2)
return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
}
-static inline int enable_reuseport(int s, int progfd)
-{
- int err, one = 1;
-
- err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
- if (err)
- return -1;
- err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd,
- sizeof(progfd));
- if (err)
- return -1;
-
- return 0;
-}
-
-static inline int socket_loopback_reuseport(int family, int sotype, int progfd)
-{
- struct sockaddr_storage addr;
- socklen_t len = 0;
- int err, s;
-
- init_addr_loopback(family, &addr, &len);
-
- s = xsocket(family, sotype, 0);
- if (s == -1)
- return -1;
-
- if (progfd >= 0)
- enable_reuseport(s, progfd);
-
- err = xbind(s, sockaddr(&addr), len);
- if (err)
- goto close;
-
- if (sotype & SOCK_DGRAM)
- return s;
-
- err = xlisten(s, SOMAXCONN);
- if (err)
- goto close;
-
- return s;
-close:
- xclose(s);
- return -1;
-}
-
-static inline int socket_loopback(int family, int sotype)
-{
- return socket_loopback_reuseport(family, sotype, -1);
-}
-
-static inline int create_pair(int family, int sotype, int *p0, int *p1)
-{
- __close_fd int s, c = -1, p = -1;
- struct sockaddr_storage addr;
- socklen_t len = sizeof(addr);
- int err;
-
- s = socket_loopback(family, sotype);
- if (s < 0)
- return s;
-
- err = xgetsockname(s, sockaddr(&addr), &len);
- if (err)
- return err;
-
- c = xsocket(family, sotype, 0);
- if (c < 0)
- return c;
-
- err = connect(c, sockaddr(&addr), len);
- if (err) {
- if (errno != EINPROGRESS) {
- FAIL_ERRNO("connect");
- return err;
- }
-
- err = poll_connect(c, IO_TIMEOUT_SEC);
- if (err) {
- FAIL_ERRNO("poll_connect");
- return err;
- }
- }
-
- switch (sotype & SOCK_TYPE_MASK) {
- case SOCK_DGRAM:
- err = xgetsockname(c, sockaddr(&addr), &len);
- if (err)
- return err;
-
- err = xconnect(s, sockaddr(&addr), len);
- if (err)
- return err;
-
- *p0 = take_fd(s);
- break;
- case SOCK_STREAM:
- case SOCK_SEQPACKET:
- p = xaccept_nonblock(s, NULL, NULL);
- if (p < 0)
- return p;
-
- *p0 = take_fd(p);
- break;
- default:
- FAIL("Unsupported socket type %#x", sotype);
- return -EOPNOTSUPP;
- }
-
- *p1 = take_fd(c);
- return 0;
-}
-
-static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1,
- int *p0, int *p1)
-{
- int err;
-
- err = create_pair(family, sotype, c0, p0);
- if (err)
- return err;
-
- err = create_pair(family, sotype, c1, p1);
- if (err) {
- close(*c0);
- close(*p0);
- }
-
- return err;
-}
-
#endif // __SOCKMAP_HELPERS__
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
index 60f474d965a9..42e822ea352f 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
@@ -197,7 +197,7 @@ static void test_nodeadlock(void)
/* Unnecessary recursion and deadlock detection are reproducible
* in the preemptible kernel.
*/
- if (!skel->kconfig->CONFIG_PREEMPT) {
+ if (!skel->kconfig->CONFIG_PREEMPTION) {
test__skip();
goto done;
}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c
new file mode 100644
index 000000000000..74752233e779
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <test_progs.h>
+#include <linux/pkt_cls.h>
+
+#include "test_tc_change_tail.skel.h"
+#include "socket_helpers.h"
+
+#define LO_IFINDEX 1
+
+void test_tc_change_tail(void)
+{
+ LIBBPF_OPTS(bpf_tcx_opts, tcx_opts);
+ struct test_tc_change_tail *skel = NULL;
+ struct bpf_link *link;
+ int c1, p1;
+ char buf[2];
+ int ret;
+
+ skel = test_tc_change_tail__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_tc_change_tail__open_and_load"))
+ return;
+
+ link = bpf_program__attach_tcx(skel->progs.change_tail, LO_IFINDEX,
+ &tcx_opts);
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_tcx"))
+ goto destroy;
+
+ skel->links.change_tail = link;
+ ret = create_pair(AF_INET, SOCK_DGRAM, &c1, &p1);
+ if (!ASSERT_OK(ret, "create_pair"))
+ goto destroy;
+
+ ret = xsend(p1, "Tr", 2, 0);
+ ASSERT_EQ(ret, 2, "xsend(p1)");
+ ret = recv(c1, buf, 2, 0);
+ ASSERT_EQ(ret, 2, "recv(c1)");
+ ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+ ret = xsend(p1, "G", 1, 0);
+ ASSERT_EQ(ret, 1, "xsend(p1)");
+ ret = recv(c1, buf, 2, 0);
+ ASSERT_EQ(ret, 1, "recv(c1)");
+ ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+ ret = xsend(p1, "E", 1, 0);
+ ASSERT_EQ(ret, 1, "xsend(p1)");
+ ret = recv(c1, buf, 1, 0);
+ ASSERT_EQ(ret, 1, "recv(c1)");
+ ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+ ret = xsend(p1, "Z", 1, 0);
+ ASSERT_EQ(ret, 1, "xsend(p1)");
+ ret = recv(c1, buf, 1, 0);
+ ASSERT_EQ(ret, 1, "recv(c1)");
+ ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+ close(c1);
+ close(p1);
+destroy:
+ test_tc_change_tail__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index d9f65adb456b..3ee40ee9413a 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -225,24 +225,7 @@ void test_verifier_xdp(void) { RUN(verifier_xdp); }
void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); }
void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); }
void test_verifier_lsm(void) { RUN(verifier_lsm); }
-
-void test_verifier_mtu(void)
-{
- __u64 caps = 0;
- int ret;
-
- /* In case CAP_BPF and CAP_PERFMON is not set */
- ret = cap_enable_effective(1ULL << CAP_BPF | 1ULL << CAP_NET_ADMIN, &caps);
- if (!ASSERT_OK(ret, "set_cap_bpf_cap_net_admin"))
- return;
- ret = cap_disable_effective(1ULL << CAP_SYS_ADMIN | 1ULL << CAP_PERFMON, NULL);
- if (!ASSERT_OK(ret, "disable_cap_sys_admin"))
- goto restore_cap;
- RUN(verifier_mtu);
-restore_cap:
- if (caps)
- cap_enable_effective(caps, NULL);
-}
+void test_verifier_mtu(void) { RUN(verifier_mtu); }
static int init_test_val_map(struct bpf_object *obj, char *map_name)
{
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index eccaf955e394..f45f4352feeb 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -5,6 +5,10 @@
#define XSTR(s) STR(s)
#define STR(s) #s
+/* Expand a macro and then stringize the expansion */
+#define QUOTE(str) #str
+#define EXPAND_QUOTE(str) QUOTE(str)
+
/* This set of attributes controls behavior of the
* test_loader.c:test_loader__run_subtests().
*
@@ -106,6 +110,7 @@
* __arch_* Specify on which architecture the test case should be tested.
* Several __arch_* annotations could be specified at once.
* When test case is not run on current arch it is marked as skipped.
+ * __caps_unpriv Specify the capabilities that should be set when running the test.
*/
#define __msg(msg) __attribute__((btf_decl_tag("comment:test_expect_msg=" XSTR(__COUNTER__) "=" msg)))
#define __xlated(msg) __attribute__((btf_decl_tag("comment:test_expect_xlated=" XSTR(__COUNTER__) "=" msg)))
@@ -129,6 +134,13 @@
#define __arch_x86_64 __arch("X86_64")
#define __arch_arm64 __arch("ARM64")
#define __arch_riscv64 __arch("RISCV64")
+#define __caps_unpriv(caps) __attribute__((btf_decl_tag("comment:test_caps_unpriv=" EXPAND_QUOTE(caps))))
+
+/* Define common capabilities tested using __caps_unpriv */
+#define CAP_NET_ADMIN 12
+#define CAP_SYS_ADMIN 21
+#define CAP_PERFMON 38
+#define CAP_BPF 39
/* Convenience macro for use with 'asm volatile' blocks */
#define __naked __attribute__((naked))
diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data.c b/tools/testing/selftests/bpf/progs/changes_pkt_data.c
new file mode 100644
index 000000000000..43cada48b28a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/changes_pkt_data.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__noinline
+long changes_pkt_data(struct __sk_buff *sk)
+{
+ return bpf_skb_pull_data(sk, 0);
+}
+
+__noinline __weak
+long does_not_change_pkt_data(struct __sk_buff *sk)
+{
+ return 0;
+}
+
+SEC("?tc")
+int main_with_subprogs(struct __sk_buff *sk)
+{
+ changes_pkt_data(sk);
+ does_not_change_pkt_data(sk);
+ return 0;
+}
+
+SEC("?tc")
+int main_changes(struct __sk_buff *sk)
+{
+ bpf_skb_pull_data(sk, 0);
+ return 0;
+}
+
+SEC("?tc")
+int main_does_not_change(struct __sk_buff *sk)
+{
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c b/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c
new file mode 100644
index 000000000000..f9a622705f1b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("?freplace")
+long changes_pkt_data(struct __sk_buff *sk)
+{
+ return bpf_skb_pull_data(sk, 0);
+}
+
+SEC("?freplace")
+long does_not_change_pkt_data(struct __sk_buff *sk)
+{
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c
index 8f36c9de7591..dfd817d0348c 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c
@@ -149,7 +149,7 @@ int ringbuf_release_uninit_dynptr(void *ctx)
/* A dynptr can't be used after it has been invalidated */
SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #3")
+__failure __msg("Expected an initialized dynptr as arg #2")
int use_after_invalid(void *ctx)
{
struct bpf_dynptr ptr;
@@ -428,7 +428,7 @@ int invalid_helper2(void *ctx)
/* A bpf_dynptr is invalidated if it's been written into */
SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #1")
+__failure __msg("Expected an initialized dynptr as arg #0")
int invalid_write1(void *ctx)
{
struct bpf_dynptr ptr;
@@ -1407,7 +1407,7 @@ int invalid_slice_rdwr_rdonly(struct __sk_buff *skb)
/* bpf_dynptr_adjust can only be called on initialized dynptrs */
SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #1")
+__failure __msg("Expected an initialized dynptr as arg #0")
int dynptr_adjust_invalid(void *ctx)
{
struct bpf_dynptr ptr = {};
@@ -1420,7 +1420,7 @@ int dynptr_adjust_invalid(void *ctx)
/* bpf_dynptr_is_null can only be called on initialized dynptrs */
SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #1")
+__failure __msg("Expected an initialized dynptr as arg #0")
int dynptr_is_null_invalid(void *ctx)
{
struct bpf_dynptr ptr = {};
@@ -1433,7 +1433,7 @@ int dynptr_is_null_invalid(void *ctx)
/* bpf_dynptr_is_rdonly can only be called on initialized dynptrs */
SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #1")
+__failure __msg("Expected an initialized dynptr as arg #0")
int dynptr_is_rdonly_invalid(void *ctx)
{
struct bpf_dynptr ptr = {};
@@ -1446,7 +1446,7 @@ int dynptr_is_rdonly_invalid(void *ctx)
/* bpf_dynptr_size can only be called on initialized dynptrs */
SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #1")
+__failure __msg("Expected an initialized dynptr as arg #0")
int dynptr_size_invalid(void *ctx)
{
struct bpf_dynptr ptr = {};
@@ -1459,7 +1459,7 @@ int dynptr_size_invalid(void *ctx)
/* Only initialized dynptrs can be cloned */
SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #1")
+__failure __msg("Expected an initialized dynptr as arg #0")
int clone_invalid1(void *ctx)
{
struct bpf_dynptr ptr1 = {};
@@ -1493,7 +1493,7 @@ int clone_invalid2(struct xdp_md *xdp)
/* Invalidating a dynptr should invalidate its clones */
SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #3")
+__failure __msg("Expected an initialized dynptr as arg #2")
int clone_invalidate1(void *ctx)
{
struct bpf_dynptr clone;
@@ -1514,7 +1514,7 @@ int clone_invalidate1(void *ctx)
/* Invalidating a dynptr should invalidate its parent */
SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #3")
+__failure __msg("Expected an initialized dynptr as arg #2")
int clone_invalidate2(void *ctx)
{
struct bpf_dynptr ptr;
@@ -1535,7 +1535,7 @@ int clone_invalidate2(void *ctx)
/* Invalidating a dynptr should invalidate its siblings */
SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #3")
+__failure __msg("Expected an initialized dynptr as arg #2")
int clone_invalidate3(void *ctx)
{
struct bpf_dynptr ptr;
@@ -1723,7 +1723,7 @@ __noinline long global_call_bpf_dynptr(const struct bpf_dynptr *dynptr)
}
SEC("?raw_tp")
-__failure __msg("arg#1 expected pointer to stack or const struct bpf_dynptr")
+__failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr")
int test_dynptr_reg_type(void *ctx)
{
struct task_struct *current = NULL;
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index ef70b88bccb2..7c969c127573 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -1486,4 +1486,30 @@ int iter_subprog_check_stacksafe(const void *ctx)
return 0;
}
+struct bpf_iter_num global_it;
+
+SEC("raw_tp")
+__failure __msg("arg#0 expected pointer to an iterator on stack")
+int iter_new_bad_arg(const void *ctx)
+{
+ bpf_iter_num_new(&global_it, 0, 1);
+ return 0;
+}
+
+SEC("raw_tp")
+__failure __msg("arg#0 expected pointer to an iterator on stack")
+int iter_next_bad_arg(const void *ctx)
+{
+ bpf_iter_num_next(&global_it);
+ return 0;
+}
+
+SEC("raw_tp")
+__failure __msg("arg#0 expected pointer to an iterator on stack")
+int iter_destroy_bad_arg(const void *ctx)
+{
+ bpf_iter_num_destroy(&global_it);
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters_state_safety.c b/tools/testing/selftests/bpf/progs/iters_state_safety.c
index d47e59aba6de..f41257eadbb2 100644
--- a/tools/testing/selftests/bpf/progs/iters_state_safety.c
+++ b/tools/testing/selftests/bpf/progs/iters_state_safety.c
@@ -73,7 +73,7 @@ int create_and_forget_to_destroy_fail(void *ctx)
}
SEC("?raw_tp")
-__failure __msg("expected an initialized iter_num as arg #1")
+__failure __msg("expected an initialized iter_num as arg #0")
int destroy_without_creating_fail(void *ctx)
{
/* init with zeros to stop verifier complaining about uninit stack */
@@ -91,7 +91,7 @@ int destroy_without_creating_fail(void *ctx)
}
SEC("?raw_tp")
-__failure __msg("expected an initialized iter_num as arg #1")
+__failure __msg("expected an initialized iter_num as arg #0")
int compromise_iter_w_direct_write_fail(void *ctx)
{
struct bpf_iter_num iter;
@@ -143,7 +143,7 @@ int compromise_iter_w_direct_write_and_skip_destroy_fail(void *ctx)
}
SEC("?raw_tp")
-__failure __msg("expected an initialized iter_num as arg #1")
+__failure __msg("expected an initialized iter_num as arg #0")
int compromise_iter_w_helper_write_fail(void *ctx)
{
struct bpf_iter_num iter;
@@ -230,7 +230,7 @@ int valid_stack_reuse(void *ctx)
}
SEC("?raw_tp")
-__failure __msg("expected uninitialized iter_num as arg #1")
+__failure __msg("expected uninitialized iter_num as arg #0")
int double_create_fail(void *ctx)
{
struct bpf_iter_num iter;
@@ -258,7 +258,7 @@ int double_create_fail(void *ctx)
}
SEC("?raw_tp")
-__failure __msg("expected an initialized iter_num as arg #1")
+__failure __msg("expected an initialized iter_num as arg #0")
int double_destroy_fail(void *ctx)
{
struct bpf_iter_num iter;
@@ -284,7 +284,7 @@ int double_destroy_fail(void *ctx)
}
SEC("?raw_tp")
-__failure __msg("expected an initialized iter_num as arg #1")
+__failure __msg("expected an initialized iter_num as arg #0")
int next_without_new_fail(void *ctx)
{
struct bpf_iter_num iter;
@@ -305,7 +305,7 @@ int next_without_new_fail(void *ctx)
}
SEC("?raw_tp")
-__failure __msg("expected an initialized iter_num as arg #1")
+__failure __msg("expected an initialized iter_num as arg #0")
int next_after_destroy_fail(void *ctx)
{
struct bpf_iter_num iter;
diff --git a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
index 4a176e6aede8..6543d5b6e0a9 100644
--- a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
+++ b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
@@ -79,7 +79,7 @@ int testmod_seq_truncated(const void *ctx)
SEC("?raw_tp")
__failure
-__msg("expected an initialized iter_testmod_seq as arg #2")
+__msg("expected an initialized iter_testmod_seq as arg #1")
int testmod_seq_getter_before_bad(const void *ctx)
{
struct bpf_iter_testmod_seq it;
@@ -89,7 +89,7 @@ int testmod_seq_getter_before_bad(const void *ctx)
SEC("?raw_tp")
__failure
-__msg("expected an initialized iter_testmod_seq as arg #2")
+__msg("expected an initialized iter_testmod_seq as arg #1")
int testmod_seq_getter_after_bad(const void *ctx)
{
struct bpf_iter_testmod_seq it;
diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null.c b/tools/testing/selftests/bpf/progs/raw_tp_null.c
index 457f34c151e3..5927054b6dd9 100644
--- a/tools/testing/selftests/bpf/progs/raw_tp_null.c
+++ b/tools/testing/selftests/bpf/progs/raw_tp_null.c
@@ -3,6 +3,7 @@
#include <vmlinux.h>
#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
char _license[] SEC("license") = "GPL";
@@ -17,16 +18,14 @@ int BPF_PROG(test_raw_tp_null, struct sk_buff *skb)
if (task->pid != tid)
return 0;
- i = i + skb->mark + 1;
- /* The compiler may move the NULL check before this deref, which causes
- * the load to fail as deref of scalar. Prevent that by using a barrier.
+ /* If dead code elimination kicks in, the increment +=2 will be
+ * removed. For raw_tp programs attaching to tracepoints in kernel
+ * modules, we mark input arguments as PTR_MAYBE_NULL, so branch
+ * prediction should never kick in.
*/
- barrier();
- /* If dead code elimination kicks in, the increment below will
- * be removed. For raw_tp programs, we mark input arguments as
- * PTR_MAYBE_NULL, so branch prediction should never kick in.
- */
- if (!skb)
- i += 2;
+ asm volatile ("%[i] += 1; if %[ctx] != 0 goto +1; %[i] += 2;"
+ : [i]"+r"(i)
+ : [ctx]"r"(skb)
+ : "memory");
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
new file mode 100644
index 000000000000..38d669957bf1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Ensure module parameter has PTR_MAYBE_NULL */
+SEC("tp_btf/bpf_testmod_test_raw_tp_null")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int test_raw_tp_null_bpf_testmod_test_raw_tp_null_arg_1(void *ctx) {
+ asm volatile("r1 = *(u64 *)(r1 +0); r1 = *(u64 *)(r1 +0);" ::: __clobber_all);
+ return 0;
+}
+
+/* Check NULL marking */
+SEC("tp_btf/sched_pi_setprio")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int test_raw_tp_null_sched_pi_setprio_arg_2(void *ctx) {
+ asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u64 *)(r1 +0);" ::: __clobber_all);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c
index 76556e0b42b2..69da05bb6c63 100644
--- a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c
+++ b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c
@@ -4,7 +4,7 @@
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
-extern bool CONFIG_PREEMPT __kconfig __weak;
+extern bool CONFIG_PREEMPTION __kconfig __weak;
extern const int bpf_task_storage_busy __ksym;
char _license[] SEC("license") = "GPL";
@@ -24,7 +24,7 @@ int BPF_PROG(read_bpf_task_storage_busy)
{
int *value;
- if (!CONFIG_PREEMPT)
+ if (!CONFIG_PREEMPTION)
return 0;
if (bpf_get_current_pid_tgid() >> 32 != pid)
diff --git a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c
index ea2dbb80f7b3..986829aaf73a 100644
--- a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c
+++ b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c
@@ -10,7 +10,7 @@ char _license[] SEC("license") = "GPL";
#define EBUSY 16
#endif
-extern bool CONFIG_PREEMPT __kconfig __weak;
+extern bool CONFIG_PREEMPTION __kconfig __weak;
int nr_get_errs = 0;
int nr_del_errs = 0;
@@ -29,7 +29,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
int ret, zero = 0;
int *value;
- if (!CONFIG_PREEMPT)
+ if (!CONFIG_PREEMPTION)
return 0;
task = bpf_get_current_task_btf();
diff --git a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
index d1a57f7d09bd..fe6249d99b31 100644
--- a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
@@ -11,6 +11,8 @@ int subprog_tc(struct __sk_buff *skb)
__sink(skb);
__sink(ret);
+ /* let verifier know that 'subprog_tc' can change pointers to skb->data */
+ bpf_skb_change_proto(skb, 0, 0);
return ret;
}
diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
index e68667aec6a6..cd4d752bd089 100644
--- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
+++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
@@ -45,7 +45,7 @@ int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size)
}
SEC("?lsm.s/bpf")
-__failure __msg("arg#1 expected pointer to stack or const struct bpf_dynptr")
+__failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr")
int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size)
{
unsigned long val = 0;
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c
new file mode 100644
index 000000000000..2796dd8545eb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 ByteDance */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKMAP);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, int);
+} sock_map_rx SEC(".maps");
+
+long change_tail_ret = 1;
+
+SEC("sk_skb")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+ char *data, *data_end;
+
+ bpf_skb_pull_data(skb, 1);
+ data = (char *)(unsigned long)skb->data;
+ data_end = (char *)(unsigned long)skb->data_end;
+
+ if (data + 1 > data_end)
+ return SK_PASS;
+
+ if (data[0] == 'T') { /* Trim the packet */
+ change_tail_ret = bpf_skb_change_tail(skb, skb->len - 1, 0);
+ return SK_PASS;
+ } else if (data[0] == 'G') { /* Grow the packet */
+ change_tail_ret = bpf_skb_change_tail(skb, skb->len + 1, 0);
+ return SK_PASS;
+ } else if (data[0] == 'E') { /* Error */
+ change_tail_ret = bpf_skb_change_tail(skb, 65535, 0);
+ return SK_PASS;
+ }
+ return SK_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c
new file mode 100644
index 000000000000..28edafe803f0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/pkt_cls.h>
+
+long change_tail_ret = 1;
+
+static __always_inline struct iphdr *parse_ip_header(struct __sk_buff *skb, int *ip_proto)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ void *data = (void *)(long)skb->data;
+ struct ethhdr *eth = data;
+ struct iphdr *iph;
+
+ /* Verify Ethernet header */
+ if ((void *)(data + sizeof(*eth)) > data_end)
+ return NULL;
+
+ /* Skip Ethernet header to get to IP header */
+ iph = (void *)(data + sizeof(struct ethhdr));
+
+ /* Verify IP header */
+ if ((void *)(data + sizeof(struct ethhdr) + sizeof(*iph)) > data_end)
+ return NULL;
+
+ /* Basic IP header validation */
+ if (iph->version != 4) /* Only support IPv4 */
+ return NULL;
+
+ if (iph->ihl < 5) /* Minimum IP header length */
+ return NULL;
+
+ *ip_proto = iph->protocol;
+ return iph;
+}
+
+static __always_inline struct udphdr *parse_udp_header(struct __sk_buff *skb, struct iphdr *iph)
+{
+ void *data_end = (void *)(long)skb->data_end;
+ void *hdr = (void *)iph;
+ struct udphdr *udp;
+
+ /* Calculate UDP header position */
+ udp = hdr + (iph->ihl * 4);
+ hdr = (void *)udp;
+
+ /* Verify UDP header bounds */
+ if ((void *)(hdr + sizeof(*udp)) > data_end)
+ return NULL;
+
+ return udp;
+}
+
+SEC("tc/ingress")
+int change_tail(struct __sk_buff *skb)
+{
+ int len = skb->len;
+ struct udphdr *udp;
+ struct iphdr *iph;
+ void *data_end;
+ char *payload;
+ int ip_proto;
+
+ bpf_skb_pull_data(skb, len);
+
+ data_end = (void *)(long)skb->data_end;
+ iph = parse_ip_header(skb, &ip_proto);
+ if (!iph)
+ return TCX_PASS;
+
+ if (ip_proto != IPPROTO_UDP)
+ return TCX_PASS;
+
+ udp = parse_udp_header(skb, iph);
+ if (!udp)
+ return TCX_PASS;
+
+ payload = (char *)udp + (sizeof(struct udphdr));
+ if (payload + 1 > (char *)data_end)
+ return TCX_PASS;
+
+ if (payload[0] == 'T') { /* Trim the packet */
+ change_tail_ret = bpf_skb_change_tail(skb, len - 1, 0);
+ if (!change_tail_ret)
+ bpf_skb_change_tail(skb, len, 0);
+ return TCX_PASS;
+ } else if (payload[0] == 'G') { /* Grow the packet */
+ change_tail_ret = bpf_skb_change_tail(skb, len + 1, 0);
+ if (!change_tail_ret)
+ bpf_skb_change_tail(skb, len, 0);
+ return TCX_PASS;
+ } else if (payload[0] == 'E') { /* Error */
+ change_tail_ret = bpf_skb_change_tail(skb, 65535, 0);
+ return TCX_PASS;
+ } else if (payload[0] == 'Z') { /* Zero */
+ change_tail_ret = bpf_skb_change_tail(skb, 0, 0);
+ return TCX_PASS;
+ }
+ return TCX_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
index 5aaf2b065f86..bba3e37f749b 100644
--- a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
+++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
@@ -7,11 +7,7 @@
#include "bpf_misc.h"
SEC("tp_btf/bpf_testmod_test_nullable_bare")
-/* This used to be a failure test, but raw_tp nullable arguments can now
- * directly be dereferenced, whether they have nullable annotation or not,
- * and don't need to be explicitly checked.
- */
-__success
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx)
{
return nullable_ctx->len;
diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
index 7c881bca9af5..8bcddadfc4da 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
@@ -32,18 +32,18 @@ int BPF_PROG(no_destroy, struct bpf_iter_meta *meta, struct cgroup *cgrp)
SEC("iter/cgroup")
__description("uninitialized iter in ->next()")
-__failure __msg("expected an initialized iter_bits as arg #1")
+__failure __msg("expected an initialized iter_bits as arg #0")
int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp)
{
- struct bpf_iter_bits *it = NULL;
+ struct bpf_iter_bits it = {};
- bpf_iter_bits_next(it);
+ bpf_iter_bits_next(&it);
return 0;
}
SEC("iter/cgroup")
__description("uninitialized iter in ->destroy()")
-__failure __msg("expected an initialized iter_bits as arg #1")
+__failure __msg("expected an initialized iter_bits as arg #0")
int BPF_PROG(destroy_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp)
{
struct bpf_iter_bits it = {};
diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
index a570e48b917a..28b939572cda 100644
--- a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
@@ -11,7 +11,7 @@ __success __retval(0)
__naked void btf_ctx_access_accept(void)
{
asm volatile (" \
- r2 = *(u32*)(r1 + 8); /* load 2nd argument value (int pointer) */\
+ r2 = *(u64 *)(r1 + 8); /* load 2nd argument value (int pointer) */\
r0 = 0; \
exit; \
" ::: __clobber_all);
@@ -23,7 +23,43 @@ __success __retval(0)
__naked void ctx_access_u32_pointer_accept(void)
{
asm volatile (" \
- r2 = *(u32*)(r1 + 0); /* load 1nd argument value (u32 pointer) */\
+ r2 = *(u64 *)(r1 + 0); /* load 1nd argument value (u32 pointer) */\
+ r0 = 0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u32")
+__failure __msg("size 4 must be 8")
+__naked void ctx_access_u32_pointer_reject_32(void)
+{
+ asm volatile (" \
+ r2 = *(u32 *)(r1 + 0); /* load 1st argument with narrow load */\
+ r0 = 0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u16")
+__failure __msg("size 2 must be 8")
+__naked void ctx_access_u32_pointer_reject_16(void)
+{
+ asm volatile (" \
+ r2 = *(u16 *)(r1 + 0); /* load 1st argument with narrow load */\
+ r0 = 0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u8")
+__failure __msg("size 1 must be 8")
+__naked void ctx_access_u32_pointer_reject_8(void)
+{
+ asm volatile (" \
+ r2 = *(u8 *)(r1 + 0); /* load 1st argument with narrow load */\
r0 = 0; \
exit; \
" ::: __clobber_all);
diff --git a/tools/testing/selftests/bpf/progs/verifier_d_path.c b/tools/testing/selftests/bpf/progs/verifier_d_path.c
index ec79cbcfde91..87e51a215558 100644
--- a/tools/testing/selftests/bpf/progs/verifier_d_path.c
+++ b/tools/testing/selftests/bpf/progs/verifier_d_path.c
@@ -11,7 +11,7 @@ __success __retval(0)
__naked void d_path_accept(void)
{
asm volatile (" \
- r1 = *(u32*)(r1 + 0); \
+ r1 = *(u64 *)(r1 + 0); \
r2 = r10; \
r2 += -8; \
r6 = 0; \
@@ -31,7 +31,7 @@ __failure __msg("helper call is not allowed in probe")
__naked void d_path_reject(void)
{
asm volatile (" \
- r1 = *(u32*)(r1 + 0); \
+ r1 = *(u64 *)(r1 + 0); \
r2 = r10; \
r2 += -8; \
r6 = 0; \
diff --git a/tools/testing/selftests/bpf/progs/verifier_mtu.c b/tools/testing/selftests/bpf/progs/verifier_mtu.c
index 70c7600a26a0..4ccf1ebc42d1 100644
--- a/tools/testing/selftests/bpf/progs/verifier_mtu.c
+++ b/tools/testing/selftests/bpf/progs/verifier_mtu.c
@@ -6,7 +6,9 @@
SEC("tc/ingress")
__description("uninit/mtu: write rejected")
-__failure __msg("invalid indirect read from stack")
+__success
+__caps_unpriv(CAP_BPF|CAP_NET_ADMIN)
+__failure_unpriv __msg_unpriv("invalid indirect read from stack")
int tc_uninit_mtu(struct __sk_buff *ctx)
{
__u32 mtu;
diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c
index d3e70e38e442..0d5e56dffabb 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sock.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sock.c
@@ -50,6 +50,13 @@ struct {
__uint(map_flags, BPF_F_NO_PREALLOC);
} sk_storage_map SEC(".maps");
+struct {
+ __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
SEC("cgroup/skb")
__description("skb->sk: no NULL check")
__failure __msg("invalid mem access 'sock_common_or_null'")
@@ -1037,4 +1044,53 @@ __naked void sock_create_read_src_port(void)
: __clobber_all);
}
+__noinline
+long skb_pull_data2(struct __sk_buff *sk, __u32 len)
+{
+ return bpf_skb_pull_data(sk, len);
+}
+
+__noinline
+long skb_pull_data1(struct __sk_buff *sk, __u32 len)
+{
+ return skb_pull_data2(sk, len);
+}
+
+/* global function calls bpf_skb_pull_data(), which invalidates packet
+ * pointers established before global function call.
+ */
+SEC("tc")
+__failure __msg("invalid mem access")
+int invalidate_pkt_pointers_from_global_func(struct __sk_buff *sk)
+{
+ int *p = (void *)(long)sk->data;
+
+ if ((void *)(p + 1) > (void *)(long)sk->data_end)
+ return TCX_DROP;
+ skb_pull_data1(sk, 0);
+ *p = 42; /* this is unsafe */
+ return TCX_PASS;
+}
+
+__noinline
+int tail_call(struct __sk_buff *sk)
+{
+ bpf_tail_call_static(sk, &jmp_table, 0);
+ return 0;
+}
+
+/* Tail calls invalidate packet pointers. */
+SEC("tc")
+__failure __msg("invalid mem access")
+int invalidate_pkt_pointers_by_tail_call(struct __sk_buff *sk)
+{
+ int *p = (void *)(long)sk->data;
+
+ if ((void *)(p + 1) > (void *)(long)sk->data_end)
+ return TCX_DROP;
+ tail_call(sk);
+ *p = 42; /* this is unsafe */
+ return TCX_PASS;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
index 671d9f415dbf..1e5a511e8494 100644
--- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
+++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
@@ -1244,4 +1244,39 @@ __naked void old_stack_misc_vs_cur_ctx_ptr(void)
: __clobber_all);
}
+SEC("socket")
+__description("stack_noperfmon: reject read of invalid slots")
+__success
+__caps_unpriv(CAP_BPF)
+__failure_unpriv __msg_unpriv("invalid read from stack off -8+1 size 8")
+__naked void stack_noperfmon_reject_invalid_read(void)
+{
+ asm volatile (" \
+ r2 = 1; \
+ r6 = r10; \
+ r6 += -8; \
+ *(u8 *)(r6 + 0) = r2; \
+ r2 = *(u64 *)(r6 + 0); \
+ r0 = 0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("stack_noperfmon: narrow spill onto 64-bit scalar spilled slots")
+__success
+__caps_unpriv(CAP_BPF)
+__success_unpriv
+__naked void stack_noperfmon_spill_32bit_onto_64bit_slot(void)
+{
+ asm volatile(" \
+ r0 = 0; \
+ *(u64 *)(r10 - 8) = r0; \
+ *(u32 *)(r10 - 8) = r0; \
+ exit; \
+" :
+ :
+ : __clobber_all);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h
index ca0162b4dc57..1fcfa5160231 100644
--- a/tools/testing/selftests/bpf/sdt.h
+++ b/tools/testing/selftests/bpf/sdt.h
@@ -102,6 +102,8 @@
# define STAP_SDT_ARG_CONSTRAINT nZr
# elif defined __arm__
# define STAP_SDT_ARG_CONSTRAINT g
+# elif defined __loongarch__
+# define STAP_SDT_ARG_CONSTRAINT nmr
# else
# define STAP_SDT_ARG_CONSTRAINT nor
# endif
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 3e9b009580d4..53b06647cf57 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -36,6 +36,7 @@
#define TEST_TAG_ARCH "comment:test_arch="
#define TEST_TAG_JITED_PFX "comment:test_jited="
#define TEST_TAG_JITED_PFX_UNPRIV "comment:test_jited_unpriv="
+#define TEST_TAG_CAPS_UNPRIV "comment:test_caps_unpriv="
/* Warning: duplicated in bpf_misc.h */
#define POINTER_VALUE 0xcafe4all
@@ -74,6 +75,7 @@ struct test_subspec {
struct expected_msgs jited;
int retval;
bool execute;
+ __u64 caps;
};
struct test_spec {
@@ -276,6 +278,37 @@ static int parse_int(const char *str, int *val, const char *name)
return 0;
}
+static int parse_caps(const char *str, __u64 *val, const char *name)
+{
+ int cap_flag = 0;
+ char *token = NULL, *saveptr = NULL;
+
+ char *str_cpy = strdup(str);
+ if (str_cpy == NULL) {
+ PRINT_FAIL("Memory allocation failed\n");
+ return -EINVAL;
+ }
+
+ token = strtok_r(str_cpy, "|", &saveptr);
+ while (token != NULL) {
+ errno = 0;
+ if (!strncmp("CAP_", token, sizeof("CAP_") - 1)) {
+ PRINT_FAIL("define %s constant in bpf_misc.h, failed to parse caps\n", token);
+ return -EINVAL;
+ }
+ cap_flag = strtol(token, NULL, 10);
+ if (!cap_flag || errno) {
+ PRINT_FAIL("failed to parse caps %s\n", name);
+ return -EINVAL;
+ }
+ *val |= (1ULL << cap_flag);
+ token = strtok_r(NULL, "|", &saveptr);
+ }
+
+ free(str_cpy);
+ return 0;
+}
+
static int parse_retval(const char *str, int *val, const char *name)
{
struct {
@@ -541,6 +574,12 @@ static int parse_test_spec(struct test_loader *tester,
jit_on_next_line = true;
} else if (str_has_pfx(s, TEST_BTF_PATH)) {
spec->btf_custom_path = s + sizeof(TEST_BTF_PATH) - 1;
+ } else if (str_has_pfx(s, TEST_TAG_CAPS_UNPRIV)) {
+ val = s + sizeof(TEST_TAG_CAPS_UNPRIV) - 1;
+ err = parse_caps(val, &spec->unpriv.caps, "test caps");
+ if (err)
+ goto cleanup;
+ spec->mode_mask |= UNPRIV;
}
}
@@ -917,6 +956,13 @@ void run_subtest(struct test_loader *tester,
test__end_subtest();
return;
}
+ if (subspec->caps) {
+ err = cap_enable_effective(subspec->caps, NULL);
+ if (err) {
+ PRINT_FAIL("failed to set capabilities: %i, %s\n", err, strerror(err));
+ goto subtest_cleanup;
+ }
+ }
}
/* Implicitly reset to NULL if next test case doesn't specify */
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index e5c7ecbe57e3..fd2da2234cc9 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1579,8 +1579,12 @@ static void test_txmsg_redir(int cgrp, struct sockmap_options *opt)
static void test_txmsg_redir_wait_sndmem(int cgrp, struct sockmap_options *opt)
{
- txmsg_redir = 1;
opt->tx_wait_mem = true;
+ txmsg_redir = 1;
+ test_send_large(opt, cgrp);
+
+ txmsg_redir = 1;
+ txmsg_apply = 4097;
test_send_large(opt, cgrp);
opt->tx_wait_mem = false;
}
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 2d742fdac6b9..81943c6254e6 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -293,6 +293,10 @@ static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *st
return 0;
}
#else
+# ifndef PROCMAP_QUERY_VMA_EXECUTABLE
+# define PROCMAP_QUERY_VMA_EXECUTABLE 0x04
+# endif
+
static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags)
{
return -EOPNOTSUPP;
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 03c1bdaed2c3..400a696a0d21 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -86,15 +86,15 @@ echo "" > test/cpuset.cpus
#
# If isolated CPUs have been reserved at boot time (as shown in
-# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-7
+# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-8
# that will be used by this script for testing purpose. If not, some of
-# the tests may fail incorrectly. These isolated CPUs will also be removed
-# before being compared with the expected results.
+# the tests may fail incorrectly. These pre-isolated CPUs should stay in
+# an isolated state throughout the testing process for now.
#
BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
if [[ -n "$BOOT_ISOLCPUS" ]]
then
- [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 7 ]] &&
+ [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 8 ]] &&
skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested"
echo "Pre-isolated CPUs: $BOOT_ISOLCPUS"
fi
@@ -684,14 +684,18 @@ check_isolcpus()
fi
#
+ # Appending pre-isolated CPUs
+ # Even though CPU #8 isn't used for testing, it can't be pre-isolated
+ # to make appending those CPUs easier.
+ #
+ [[ -n "$BOOT_ISOLCPUS" ]] && {
+ EXPECT_VAL=${EXPECT_VAL:+${EXPECT_VAL},}${BOOT_ISOLCPUS}
+ EXPECT_VAL2=${EXPECT_VAL2:+${EXPECT_VAL2},}${BOOT_ISOLCPUS}
+ }
+
+ #
# Check cpuset.cpus.isolated cpumask
#
- if [[ -z "$BOOT_ISOLCPUS" ]]
- then
- ISOLCPUS=$(cat $ISCPUS)
- else
- ISOLCPUS=$(cat $ISCPUS | sed -e "s/,*$BOOT_ISOLCPUS//")
- fi
[[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && {
# Take a 50ms pause and try again
pause 0.05
@@ -731,8 +735,6 @@ check_isolcpus()
fi
done
[[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU
- [[ -n "BOOT_ISOLCPUS" ]] &&
- ISOLCPUS=$(echo $ISOLCPUS | sed -e "s/,*$BOOT_ISOLCPUS//")
[[ "$EXPECT_VAL" = "$ISOLCPUS" ]]
}
@@ -836,8 +838,11 @@ run_state_test()
# if available
[[ -n "$ICPUS" ]] && {
check_isolcpus $ICPUS
- [[ $? -ne 0 ]] && test_fail $I "isolated CPU" \
- "Expect $ICPUS, get $ISOLCPUS instead"
+ [[ $? -ne 0 ]] && {
+ [[ -n "$BOOT_ISOLCPUS" ]] && ICPUS=${ICPUS},${BOOT_ISOLCPUS}
+ test_fail $I "isolated CPU" \
+ "Expect $ICPUS, get $ISOLCPUS instead"
+ }
}
reset_cgroup_states
#
diff --git a/tools/testing/selftests/coredump/Makefile b/tools/testing/selftests/coredump/Makefile
new file mode 100644
index 000000000000..ed210037b29d
--- /dev/null
+++ b/tools/testing/selftests/coredump/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+CFLAGS = $(KHDR_INCLUDES)
+
+TEST_GEN_PROGS := stackdump_test
+TEST_FILES := stackdump
+
+include ../lib.mk
diff --git a/tools/testing/selftests/coredump/README.rst b/tools/testing/selftests/coredump/README.rst
new file mode 100644
index 000000000000..164a7aa181c8
--- /dev/null
+++ b/tools/testing/selftests/coredump/README.rst
@@ -0,0 +1,50 @@
+coredump selftest
+=================
+
+Background context
+------------------
+
+`coredump` is a feature which dumps a process's memory space when the process terminates
+unexpectedly (e.g. due to segmentation fault), which can be useful for debugging. By default,
+`coredump` dumps the memory to the file named `core`, but this behavior can be changed by writing a
+different file name to `/proc/sys/kernel/core_pattern`. Furthermore, `coredump` can be piped to a
+user-space program by writing the pipe symbol (`|`) followed by the command to be executed to
+`/proc/sys/kernel/core_pattern`. For the full description, see `man 5 core`.
+
+The piped user program may be interested in reading the stack pointers of the crashed process. The
+crashed process's stack pointers can be read from `procfs`: it is the `kstkesp` field in
+`/proc/$PID/stat`. See `man 5 proc` for all the details.
+
+The problem
+-----------
+While a thread is active, the stack pointer is unsafe to read and therefore the `kstkesp` field
+reads zero. But when the thread is dead (e.g. during a coredump), this field should have valid
+value.
+
+However, this was broken in the past and `kstkesp` was zero even during coredump:
+
+* commit 0a1eb2d474ed ("fs/proc: Stop reporting eip and esp in /proc/PID/stat") changed kstkesp to
+ always be zero
+
+* commit fd7d56270b52 ("fs/proc: Report eip/esp in /prod/PID/stat for coredumping") fixed it for the
+ coredumping thread. However, other threads in a coredumping process still had the problem.
+
+* commit cb8f381f1613 ("fs/proc/array.c: allow reporting eip/esp for all coredumping threads") fixed
+ for all threads in a coredumping process.
+
+* commit 92307383082d ("coredump: Don't perform any cleanups before dumping core") broke it again
+ for the other threads in a coredumping process.
+
+The problem has been fixed now, but considering the history, it may appear again in the future.
+
+The goal of this test
+---------------------
+This test detects problem with reading `kstkesp` during coredump by doing the following:
+
+#. Tell the kernel to execute the "stackdump" script when a coredump happens. This script
+ reads the stack pointers of all threads of crashed processes.
+
+#. Spawn a child process who creates some threads and then crashes.
+
+#. Read the output from the "stackdump" script, and make sure all stack pointer values are
+ non-zero.
diff --git a/tools/testing/selftests/coredump/stackdump b/tools/testing/selftests/coredump/stackdump
new file mode 100755
index 000000000000..96714ce42d12
--- /dev/null
+++ b/tools/testing/selftests/coredump/stackdump
@@ -0,0 +1,14 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+CRASH_PROGRAM_ID=$1
+STACKDUMP_FILE=$2
+
+TMP=$(mktemp)
+
+for t in /proc/$CRASH_PROGRAM_ID/task/*; do
+ tid=$(basename $t)
+ cat /proc/$tid/stat | awk '{print $29}' >> $TMP
+done
+
+mv $TMP $STACKDUMP_FILE
diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c
new file mode 100644
index 000000000000..137b2364a082
--- /dev/null
+++ b/tools/testing/selftests/coredump/stackdump_test.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <fcntl.h>
+#include <libgen.h>
+#include <linux/limits.h>
+#include <pthread.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+#define STACKDUMP_FILE "stack_values"
+#define STACKDUMP_SCRIPT "stackdump"
+#define NUM_THREAD_SPAWN 128
+
+static void *do_nothing(void *)
+{
+ while (1)
+ pause();
+}
+
+static void crashing_child(void)
+{
+ pthread_t thread;
+ int i;
+
+ for (i = 0; i < NUM_THREAD_SPAWN; ++i)
+ pthread_create(&thread, NULL, do_nothing, NULL);
+
+ /* crash on purpose */
+ i = *(int *)NULL;
+}
+
+FIXTURE(coredump)
+{
+ char original_core_pattern[256];
+};
+
+FIXTURE_SETUP(coredump)
+{
+ char buf[PATH_MAX];
+ FILE *file;
+ char *dir;
+ int ret;
+
+ file = fopen("/proc/sys/kernel/core_pattern", "r");
+ ASSERT_NE(NULL, file);
+
+ ret = fread(self->original_core_pattern, 1, sizeof(self->original_core_pattern), file);
+ ASSERT_TRUE(ret || feof(file));
+ ASSERT_LT(ret, sizeof(self->original_core_pattern));
+
+ self->original_core_pattern[ret] = '\0';
+
+ ret = fclose(file);
+ ASSERT_EQ(0, ret);
+}
+
+FIXTURE_TEARDOWN(coredump)
+{
+ const char *reason;
+ FILE *file;
+ int ret;
+
+ unlink(STACKDUMP_FILE);
+
+ file = fopen("/proc/sys/kernel/core_pattern", "w");
+ if (!file) {
+ reason = "Unable to open core_pattern";
+ goto fail;
+ }
+
+ ret = fprintf(file, "%s", self->original_core_pattern);
+ if (ret < 0) {
+ reason = "Unable to write to core_pattern";
+ goto fail;
+ }
+
+ ret = fclose(file);
+ if (ret) {
+ reason = "Unable to close core_pattern";
+ goto fail;
+ }
+
+ return;
+fail:
+ /* This should never happen */
+ fprintf(stderr, "Failed to cleanup stackdump test: %s\n", reason);
+}
+
+TEST_F(coredump, stackdump)
+{
+ struct sigaction action = {};
+ unsigned long long stack;
+ char *test_dir, *line;
+ size_t line_length;
+ char buf[PATH_MAX];
+ int ret, i;
+ FILE *file;
+ pid_t pid;
+
+ /*
+ * Step 1: Setup core_pattern so that the stackdump script is executed when the child
+ * process crashes
+ */
+ ret = readlink("/proc/self/exe", buf, sizeof(buf));
+ ASSERT_NE(-1, ret);
+ ASSERT_LT(ret, sizeof(buf));
+ buf[ret] = '\0';
+
+ test_dir = dirname(buf);
+
+ file = fopen("/proc/sys/kernel/core_pattern", "w");
+ ASSERT_NE(NULL, file);
+
+ ret = fprintf(file, "|%1$s/%2$s %%P %1$s/%3$s", test_dir, STACKDUMP_SCRIPT, STACKDUMP_FILE);
+ ASSERT_LT(0, ret);
+
+ ret = fclose(file);
+ ASSERT_EQ(0, ret);
+
+ /* Step 2: Create a process who spawns some threads then crashes */
+ pid = fork();
+ ASSERT_TRUE(pid >= 0);
+ if (pid == 0)
+ crashing_child();
+
+ /*
+ * Step 3: Wait for the stackdump script to write the stack pointers to the stackdump file
+ */
+ for (i = 0; i < 10; ++i) {
+ file = fopen(STACKDUMP_FILE, "r");
+ if (file)
+ break;
+ sleep(1);
+ }
+ ASSERT_NE(file, NULL);
+
+ /* Step 4: Make sure all stack pointer values are non-zero */
+ for (i = 0; -1 != getline(&line, &line_length, file); ++i) {
+ stack = strtoull(line, NULL, 10);
+ ASSERT_NE(stack, 0);
+ }
+
+ ASSERT_EQ(i, 1 + NUM_THREAD_SPAWN);
+
+ fclose(file);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 5b2a6a5dd1af..812f656260fb 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -6,7 +6,7 @@ TEST_GEN_FILES += debugfs_target_ids_read_before_terminate_race
TEST_GEN_FILES += debugfs_target_ids_pid_leak
TEST_GEN_FILES += access_memory access_memory_even
-TEST_FILES = _chk_dependency.sh _debugfs_common.sh
+TEST_FILES = _chk_dependency.sh _debugfs_common.sh _damon_sysfs.py
# functionality tests
TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh
diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 0b49ce7ae678..ca8a7edff3dd 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -3,7 +3,8 @@
import datetime
import random
-from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt
+import re
+from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt, ksft_true
from lib.py import NetDrvEpEnv
from lib.py import EthtoolFamily, NetdevFamily
from lib.py import KsftSkipEx, KsftFailEx
@@ -96,6 +97,13 @@ def _send_traffic_check(cfg, port, name, params):
f"traffic on inactive queues ({name}): " + str(cnts))
+def _ntuple_rule_check(cfg, rule_id, ctx_id):
+ """Check that ntuple rule references RSS context ID"""
+ text = ethtool(f"-n {cfg.ifname} rule {rule_id}").stdout
+ pattern = f"RSS Context (ID: )?{ctx_id}"
+ ksft_true(re.search(pattern, text), "RSS context not referenced in ntuple rule")
+
+
def test_rss_key_indir(cfg):
"""Test basics like updating the main RSS key and indirection table."""
@@ -459,6 +467,8 @@ def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None):
ntuple = ethtool_create(cfg, "-N", flow)
defer(ethtool, f"-N {cfg.ifname} delete {ntuple}")
+ _ntuple_rule_check(cfg, ntuple, ctx_id)
+
for i in range(ctx_cnt):
_send_traffic_check(cfg, ports[i], f"context {i}",
{ 'target': (2+i*2, 3+i*2),
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
index 0c47faff9274..c068e6c2a580 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
@@ -22,20 +22,34 @@ SB_ITC=0
h1_create()
{
simple_if_init $h1 192.0.1.1/24
+ tc qdisc add dev $h1 clsact
+
+ # Add egress filter on $h1 that will guarantee that the packet sent,
+ # will be the only packet being passed to the device.
+ tc filter add dev $h1 egress pref 2 handle 102 matchall action drop
}
h1_destroy()
{
+ tc filter del dev $h1 egress pref 2 handle 102 matchall action drop
+ tc qdisc del dev $h1 clsact
simple_if_fini $h1 192.0.1.1/24
}
h2_create()
{
simple_if_init $h2 192.0.1.2/24
+ tc qdisc add dev $h2 clsact
+
+ # Add egress filter on $h2 that will guarantee that the packet sent,
+ # will be the only packet being passed to the device.
+ tc filter add dev $h2 egress pref 1 handle 101 matchall action drop
}
h2_destroy()
{
+ tc filter del dev $h2 egress pref 1 handle 101 matchall action drop
+ tc qdisc del dev $h2 clsact
simple_if_fini $h2 192.0.1.2/24
}
@@ -101,6 +115,11 @@ port_pool_test()
local exp_max_occ=$(devlink_cell_size_get)
local max_occ
+ tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \
+ src_mac $h1mac dst_mac $h2mac \
+ src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+ action pass
+
devlink sb occupancy clearmax $DEVLINK_DEV
$MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
@@ -109,11 +128,6 @@ port_pool_test()
devlink sb occupancy snapshot $DEVLINK_DEV
RET=0
- max_occ=$(sb_occ_pool_check $dl_port1 $SB_POOL_ING $exp_max_occ)
- check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ"
- log_test "physical port's($h1) ingress pool"
-
- RET=0
max_occ=$(sb_occ_pool_check $dl_port2 $SB_POOL_ING $exp_max_occ)
check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ"
log_test "physical port's($h2) ingress pool"
@@ -122,6 +136,11 @@ port_pool_test()
max_occ=$(sb_occ_pool_check $cpu_dl_port $SB_POOL_EGR_CPU $exp_max_occ)
check_err $? "Expected ePool($SB_POOL_EGR_CPU) max occupancy to be $exp_max_occ, but got $max_occ"
log_test "CPU port's egress pool"
+
+ tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \
+ src_mac $h1mac dst_mac $h2mac \
+ src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+ action pass
}
port_tc_ip_test()
@@ -129,6 +148,11 @@ port_tc_ip_test()
local exp_max_occ=$(devlink_cell_size_get)
local max_occ
+ tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \
+ src_mac $h1mac dst_mac $h2mac \
+ src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+ action pass
+
devlink sb occupancy clearmax $DEVLINK_DEV
$MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
@@ -139,17 +163,17 @@ port_tc_ip_test()
RET=0
max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
- log_test "physical port's($h1) ingress TC - IP packet"
-
- RET=0
- max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
- check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
log_test "physical port's($h2) ingress TC - IP packet"
RET=0
max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_IP $exp_max_occ)
check_err $? "Expected egress TC($SB_ITC_CPU_IP) max occupancy to be $exp_max_occ, but got $max_occ"
log_test "CPU port's egress TC - IP packet"
+
+ tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \
+ src_mac $h1mac dst_mac $h2mac \
+ src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+ action pass
}
port_tc_arp_test()
@@ -157,6 +181,9 @@ port_tc_arp_test()
local exp_max_occ=$(devlink_cell_size_get)
local max_occ
+ tc filter add dev $h1 egress protocol arp pref 1 handle 101 flower \
+ src_mac $h1mac action pass
+
devlink sb occupancy clearmax $DEVLINK_DEV
$MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q
@@ -166,17 +193,15 @@ port_tc_arp_test()
RET=0
max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
- log_test "physical port's($h1) ingress TC - ARP packet"
-
- RET=0
- max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
- check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
log_test "physical port's($h2) ingress TC - ARP packet"
RET=0
max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_ARP $exp_max_occ)
check_err $? "Expected egress TC($SB_ITC_IP2ME) max occupancy to be $exp_max_occ, but got $max_occ"
log_test "CPU port's egress TC - ARP packet"
+
+ tc filter del dev $h1 egress protocol arp pref 1 handle 101 flower \
+ src_mac $h1mac action pass
}
setup_prepare()
diff --git a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh
index fd13c8cfb7a8..b411fe66510f 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh
@@ -58,9 +58,12 @@ for root in mq mqprio; do
ethtool -L $NDEV combined 4
n_child_assert 4 "One real queue, rest default"
- # Graft some
- tcq replace parent 100:1 handle 204:
- n_child_assert 3 "Grafted"
+ # Remove real one
+ tcq del parent 100:4 handle 204:
+
+ # Replace default with pfifo
+ tcq replace parent 100:1 handle 205: pfifo limit 1000
+ n_child_assert 3 "Deleting real one, replacing default one with pfifo"
ethtool -L $NDEV combined 1
n_child_assert 1 "Grafted, one"
diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index 30f29096e27c..38303da957ee 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -1,32 +1,37 @@
#!/usr/bin/env python3
# SPDX-License-Identifier: GPL-2.0
-from lib.py import ksft_run, ksft_exit, ksft_eq, KsftSkipEx
-from lib.py import EthtoolFamily, NetdevFamily
+from lib.py import ksft_disruptive, ksft_exit, ksft_run
+from lib.py import ksft_eq, ksft_raises, KsftSkipEx
+from lib.py import EthtoolFamily, NetdevFamily, NlError
from lib.py import NetDrvEnv
-from lib.py import cmd
+from lib.py import cmd, defer, ip
+import errno
import glob
-def sys_get_queues(ifname) -> int:
- folders = glob.glob(f'/sys/class/net/{ifname}/queues/rx-*')
+def sys_get_queues(ifname, qtype='rx') -> int:
+ folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*')
return len(folders)
-def nl_get_queues(cfg, nl):
+def nl_get_queues(cfg, nl, qtype='rx'):
queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True)
if queues:
- return len([q for q in queues if q['type'] == 'rx'])
+ return len([q for q in queues if q['type'] == qtype])
return None
def get_queues(cfg, nl) -> None:
- queues = nl_get_queues(cfg, nl)
- if not queues:
- raise KsftSkipEx('queue-get not supported by device')
+ snl = NetdevFamily(recv_size=4096)
- expected = sys_get_queues(cfg.dev['ifname'])
- ksft_eq(queues, expected)
+ for qtype in ['rx', 'tx']:
+ queues = nl_get_queues(cfg, snl, qtype)
+ if not queues:
+ raise KsftSkipEx('queue-get not supported by device')
+
+ expected = sys_get_queues(cfg.dev['ifname'], qtype)
+ ksft_eq(queues, expected)
def addremove_queues(cfg, nl) -> None:
@@ -56,9 +61,27 @@ def addremove_queues(cfg, nl) -> None:
ksft_eq(queues, expected)
+@ksft_disruptive
+def check_down(cfg, nl) -> None:
+ # Check the NAPI IDs before interface goes down and hides them
+ napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True)
+
+ ip(f"link set dev {cfg.dev['ifname']} down")
+ defer(ip, f"link set dev {cfg.dev['ifname']} up")
+
+ with ksft_raises(NlError) as cm:
+ nl.queue_get({'ifindex': cfg.ifindex, 'id': 0, 'type': 'rx'})
+ ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT)
+
+ if napis:
+ with ksft_raises(NlError) as cm:
+ nl.napi_get({'id': napis[0]['id']})
+ ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT)
+
+
def main() -> None:
- with NetDrvEnv(__file__, queue_count=3) as cfg:
- ksft_run([get_queues, addremove_queues], args=(cfg, NetdevFamily()))
+ with NetDrvEnv(__file__, queue_count=100) as cfg:
+ ksft_run([get_queues, addremove_queues, check_down], args=(cfg, NetdevFamily()))
ksft_exit()
diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py
index 63e3c045a3b2..031ac9def6c0 100755
--- a/tools/testing/selftests/drivers/net/stats.py
+++ b/tools/testing/selftests/drivers/net/stats.py
@@ -110,6 +110,23 @@ def qstat_by_ifindex(cfg) -> None:
ksft_ge(triple[1][key], triple[0][key], comment="bad key: " + key)
ksft_ge(triple[2][key], triple[1][key], comment="bad key: " + key)
+ # Sanity check the dumps
+ queues = NetdevFamily(recv_size=4096).qstats_get({"scope": "queue"}, dump=True)
+ # Reformat the output into {ifindex: {rx: [id, id, ...], tx: [id, id, ...]}}
+ parsed = {}
+ for entry in queues:
+ ifindex = entry["ifindex"]
+ if ifindex not in parsed:
+ parsed[ifindex] = {"rx":[], "tx": []}
+ parsed[ifindex][entry["queue-type"]].append(entry['queue-id'])
+ # Now, validate
+ for ifindex, queues in parsed.items():
+ for qtype in ['rx', 'tx']:
+ ksft_eq(len(queues[qtype]), len(set(queues[qtype])),
+ comment="repeated queue keys")
+ ksft_eq(len(queues[qtype]), max(queues[qtype]) + 1,
+ comment="missing queue keys")
+
# Test invalid dumps
# 0 is invalid
with ksft_raises(NlError) as cm:
@@ -158,7 +175,7 @@ def check_down(cfg) -> None:
def main() -> None:
- with NetDrvEnv(__file__) as cfg:
+ with NetDrvEnv(__file__, queue_count=100) as cfg:
ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex,
check_down],
args=(cfg, ))
diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c
index 071e03532cba..8fb7395fd35b 100644
--- a/tools/testing/selftests/exec/execveat.c
+++ b/tools/testing/selftests/exec/execveat.c
@@ -23,9 +23,11 @@
#include "../kselftest.h"
-#define TESTS_EXPECTED 51
+#define TESTS_EXPECTED 54
#define TEST_NAME_LEN (PATH_MAX * 4)
+#define CHECK_COMM "CHECK_COMM"
+
static char longpath[2 * PATH_MAX] = "";
static char *envp[] = { "IN_TEST=yes", NULL, NULL };
static char *argv[] = { "execveat", "99", NULL };
@@ -237,6 +239,29 @@ static int check_execveat_pathmax(int root_dfd, const char *src, int is_script)
return fail;
}
+static int check_execveat_comm(int fd, char *argv0, char *expected)
+{
+ char buf[128], *old_env, *old_argv0;
+ int ret;
+
+ snprintf(buf, sizeof(buf), CHECK_COMM "=%s", expected);
+
+ old_env = envp[1];
+ envp[1] = buf;
+
+ old_argv0 = argv[0];
+ argv[0] = argv0;
+
+ ksft_print_msg("Check execveat(AT_EMPTY_PATH)'s comm is %s\n",
+ expected);
+ ret = check_execveat_invoked_rc(fd, "", AT_EMPTY_PATH, 0, 0);
+
+ envp[1] = old_env;
+ argv[0] = old_argv0;
+
+ return ret;
+}
+
static int run_tests(void)
{
int fail = 0;
@@ -389,6 +414,14 @@ static int run_tests(void)
fail += check_execveat_pathmax(root_dfd, "execveat", 0);
fail += check_execveat_pathmax(root_dfd, "script", 1);
+
+ /* /proc/pid/comm gives filename by default */
+ fail += check_execveat_comm(fd, "sentinel", "execveat");
+ /* /proc/pid/comm gives argv[0] when invoked via link */
+ fail += check_execveat_comm(fd_symlink, "sentinel", "execveat");
+ /* /proc/pid/comm gives filename if NULL is passed */
+ fail += check_execveat_comm(fd, NULL, "execveat");
+
return fail;
}
@@ -415,9 +448,13 @@ int main(int argc, char **argv)
int ii;
int rc;
const char *verbose = getenv("VERBOSE");
+ const char *check_comm = getenv(CHECK_COMM);
- if (argc >= 2) {
- /* If we are invoked with an argument, don't run tests. */
+ if (argc >= 2 || check_comm) {
+ /*
+ * If we are invoked with an argument, or no arguments but a
+ * command to check, don't run tests.
+ */
const char *in_test = getenv("IN_TEST");
if (verbose) {
@@ -426,6 +463,38 @@ int main(int argc, char **argv)
ksft_print_msg("\t[%d]='%s\n'", ii, argv[ii]);
}
+ /* If the tests wanted us to check the command, do so. */
+ if (check_comm) {
+ /* TASK_COMM_LEN == 16 */
+ char buf[32];
+ int fd, ret;
+
+ fd = open("/proc/self/comm", O_RDONLY);
+ if (fd < 0) {
+ ksft_perror("open() comm failed");
+ exit(1);
+ }
+
+ ret = read(fd, buf, sizeof(buf));
+ if (ret < 0) {
+ ksft_perror("read() comm failed");
+ close(fd);
+ exit(1);
+ }
+ close(fd);
+
+ // trim off the \n
+ buf[ret-1] = 0;
+
+ if (strcmp(buf, check_comm)) {
+ ksft_print_msg("bad comm, got: %s expected: %s\n",
+ buf, check_comm);
+ exit(1);
+ }
+
+ exit(0);
+ }
+
/* Check expected environment transferred. */
if (!in_test || strcmp(in_test, "yes") != 0) {
ksft_print_msg("no IN_TEST=yes in env\n");
diff --git a/tools/testing/selftests/nsfs/.gitignore b/tools/testing/selftests/filesystems/nsfs/.gitignore
index ed79ebdf286e..92a8249006d1 100644
--- a/tools/testing/selftests/nsfs/.gitignore
+++ b/tools/testing/selftests/filesystems/nsfs/.gitignore
@@ -1,3 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
owner
pidns
+iterate_mntns
diff --git a/tools/testing/selftests/nsfs/Makefile b/tools/testing/selftests/filesystems/nsfs/Makefile
index dd9bd50b7b93..231aaa7dfd95 100644
--- a/tools/testing/selftests/nsfs/Makefile
+++ b/tools/testing/selftests/filesystems/nsfs/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
-TEST_GEN_PROGS := owner pidns
+TEST_GEN_PROGS := owner pidns iterate_mntns
CFLAGS := -Wall -Werror
-include ../lib.mk
+include ../../lib.mk
diff --git a/tools/testing/selftests/nsfs/config b/tools/testing/selftests/filesystems/nsfs/config
index 598d0a225fc9..598d0a225fc9 100644
--- a/tools/testing/selftests/nsfs/config
+++ b/tools/testing/selftests/filesystems/nsfs/config
diff --git a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c
new file mode 100644
index 000000000000..457cf76f3c5f
--- /dev/null
+++ b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+// Copyright (c) 2024 Christian Brauner <brauner@kernel.org>
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/mount.h>
+#include <unistd.h>
+
+#include "../../kselftest_harness.h"
+
+#define MNT_NS_COUNT 11
+#define MNT_NS_LAST_INDEX 10
+
+struct mnt_ns_info {
+ __u32 size;
+ __u32 nr_mounts;
+ __u64 mnt_ns_id;
+};
+
+#define MNT_NS_INFO_SIZE_VER0 16 /* size of first published struct */
+
+/* Get information about namespace. */
+#define NS_MNT_GET_INFO _IOR(0xb7, 10, struct mnt_ns_info)
+/* Get next namespace. */
+#define NS_MNT_GET_NEXT _IOR(0xb7, 11, struct mnt_ns_info)
+/* Get previous namespace. */
+#define NS_MNT_GET_PREV _IOR(0xb7, 12, struct mnt_ns_info)
+
+FIXTURE(iterate_mount_namespaces) {
+ int fd_mnt_ns[MNT_NS_COUNT];
+ __u64 mnt_ns_id[MNT_NS_COUNT];
+};
+
+FIXTURE_SETUP(iterate_mount_namespaces)
+{
+ for (int i = 0; i < MNT_NS_COUNT; i++)
+ self->fd_mnt_ns[i] = -EBADF;
+
+ /*
+ * Creating a new user namespace let's us guarantee that we only see
+ * mount namespaces that we did actually create.
+ */
+ ASSERT_EQ(unshare(CLONE_NEWUSER), 0);
+
+ for (int i = 0; i < MNT_NS_COUNT; i++) {
+ struct mnt_ns_info info = {};
+
+ ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+ self->fd_mnt_ns[i] = open("/proc/self/ns/mnt", O_RDONLY | O_CLOEXEC);
+ ASSERT_GE(self->fd_mnt_ns[i], 0);
+ ASSERT_EQ(ioctl(self->fd_mnt_ns[i], NS_MNT_GET_INFO, &info), 0);
+ self->mnt_ns_id[i] = info.mnt_ns_id;
+ }
+}
+
+FIXTURE_TEARDOWN(iterate_mount_namespaces)
+{
+ for (int i = 0; i < MNT_NS_COUNT; i++) {
+ if (self->fd_mnt_ns[i] < 0)
+ continue;
+ ASSERT_EQ(close(self->fd_mnt_ns[i]), 0);
+ }
+}
+
+TEST_F(iterate_mount_namespaces, iterate_all_forward)
+{
+ int fd_mnt_ns_cur, count = 0;
+
+ fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[0], F_DUPFD_CLOEXEC);
+ ASSERT_GE(fd_mnt_ns_cur, 0);
+
+ for (;; count++) {
+ struct mnt_ns_info info = {};
+ int fd_mnt_ns_next;
+
+ fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info);
+ if (fd_mnt_ns_next < 0 && errno == ENOENT)
+ break;
+ ASSERT_GE(fd_mnt_ns_next, 0);
+ ASSERT_EQ(close(fd_mnt_ns_cur), 0);
+ fd_mnt_ns_cur = fd_mnt_ns_next;
+ }
+ ASSERT_EQ(count, MNT_NS_LAST_INDEX);
+}
+
+TEST_F(iterate_mount_namespaces, iterate_all_backwards)
+{
+ int fd_mnt_ns_cur, count = 0;
+
+ fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[MNT_NS_LAST_INDEX], F_DUPFD_CLOEXEC);
+ ASSERT_GE(fd_mnt_ns_cur, 0);
+
+ for (;; count++) {
+ struct mnt_ns_info info = {};
+ int fd_mnt_ns_prev;
+
+ fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info);
+ if (fd_mnt_ns_prev < 0 && errno == ENOENT)
+ break;
+ ASSERT_GE(fd_mnt_ns_prev, 0);
+ ASSERT_EQ(close(fd_mnt_ns_cur), 0);
+ fd_mnt_ns_cur = fd_mnt_ns_prev;
+ }
+ ASSERT_EQ(count, MNT_NS_LAST_INDEX);
+}
+
+TEST_F(iterate_mount_namespaces, iterate_forward)
+{
+ int fd_mnt_ns_cur;
+
+ ASSERT_EQ(setns(self->fd_mnt_ns[0], CLONE_NEWNS), 0);
+
+ fd_mnt_ns_cur = self->fd_mnt_ns[0];
+ for (int i = 1; i < MNT_NS_COUNT; i++) {
+ struct mnt_ns_info info = {};
+ int fd_mnt_ns_next;
+
+ fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info);
+ ASSERT_GE(fd_mnt_ns_next, 0);
+ ASSERT_EQ(close(fd_mnt_ns_cur), 0);
+ fd_mnt_ns_cur = fd_mnt_ns_next;
+ ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]);
+ }
+}
+
+TEST_F(iterate_mount_namespaces, iterate_backward)
+{
+ int fd_mnt_ns_cur;
+
+ ASSERT_EQ(setns(self->fd_mnt_ns[MNT_NS_LAST_INDEX], CLONE_NEWNS), 0);
+
+ fd_mnt_ns_cur = self->fd_mnt_ns[MNT_NS_LAST_INDEX];
+ for (int i = MNT_NS_LAST_INDEX - 1; i >= 0; i--) {
+ struct mnt_ns_info info = {};
+ int fd_mnt_ns_prev;
+
+ fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info);
+ ASSERT_GE(fd_mnt_ns_prev, 0);
+ ASSERT_EQ(close(fd_mnt_ns_cur), 0);
+ fd_mnt_ns_cur = fd_mnt_ns_prev;
+ ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]);
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/nsfs/owner.c b/tools/testing/selftests/filesystems/nsfs/owner.c
index 96a976c74550..96a976c74550 100644
--- a/tools/testing/selftests/nsfs/owner.c
+++ b/tools/testing/selftests/filesystems/nsfs/owner.c
diff --git a/tools/testing/selftests/nsfs/pidns.c b/tools/testing/selftests/filesystems/nsfs/pidns.c
index e3c772c6a7c7..e3c772c6a7c7 100644
--- a/tools/testing/selftests/nsfs/pidns.c
+++ b/tools/testing/selftests/filesystems/nsfs/pidns.c
diff --git a/tools/testing/selftests/filesystems/statmount/Makefile b/tools/testing/selftests/filesystems/statmount/Makefile
index 3af3136e35a4..14ee91a41650 100644
--- a/tools/testing/selftests/filesystems/statmount/Makefile
+++ b/tools/testing/selftests/filesystems/statmount/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-or-later
CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES)
-TEST_GEN_PROGS := statmount_test statmount_test_ns
+TEST_GEN_PROGS := statmount_test statmount_test_ns listmount_test
include ../../lib.mk
diff --git a/tools/testing/selftests/filesystems/statmount/listmount_test.c b/tools/testing/selftests/filesystems/statmount/listmount_test.c
new file mode 100644
index 000000000000..15f0834f7557
--- /dev/null
+++ b/tools/testing/selftests/filesystems/statmount/listmount_test.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+// Copyright (c) 2024 Christian Brauner <brauner@kernel.org>
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/mount.h>
+#include <unistd.h>
+
+#include "statmount.h"
+#include "../../kselftest_harness.h"
+
+#ifndef LISTMOUNT_REVERSE
+#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */
+#endif
+
+#define LISTMNT_BUFFER 10
+
+/* Check that all mount ids are in increasing order. */
+TEST(listmount_forward)
+{
+ uint64_t list[LISTMNT_BUFFER], last_mnt_id = 0;
+
+ for (;;) {
+ ssize_t nr_mounts;
+
+ nr_mounts = listmount(LSMT_ROOT, 0, last_mnt_id,
+ list, LISTMNT_BUFFER, 0);
+ ASSERT_GE(nr_mounts, 0);
+ if (nr_mounts == 0)
+ break;
+
+ for (size_t cur = 0; cur < nr_mounts; cur++) {
+ if (cur < nr_mounts - 1)
+ ASSERT_LT(list[cur], list[cur + 1]);
+ last_mnt_id = list[cur];
+ }
+ }
+}
+
+/* Check that all mount ids are in decreasing order. */
+TEST(listmount_backward)
+{
+ uint64_t list[LISTMNT_BUFFER], last_mnt_id = 0;
+
+ for (;;) {
+ ssize_t nr_mounts;
+
+ nr_mounts = listmount(LSMT_ROOT, 0, last_mnt_id,
+ list, LISTMNT_BUFFER, LISTMOUNT_REVERSE);
+ ASSERT_GE(nr_mounts, 0);
+ if (nr_mounts == 0)
+ break;
+
+ for (size_t cur = 0; cur < nr_mounts; cur++) {
+ if (cur < nr_mounts - 1)
+ ASSERT_GT(list[cur], list[cur + 1]);
+ last_mnt_id = list[cur];
+ }
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
index a16c6a6f6055..8f1c58f0c239 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
@@ -111,7 +111,7 @@ check_error 'p vfs_read $arg* ^$arg*' # DOUBLE_ARGS
if !grep -q 'kernel return probes support:' README; then
check_error 'r vfs_read ^$arg*' # NOFENTRY_ARGS
fi
-check_error 'p vfs_read+8 ^$arg*' # NOFENTRY_ARGS
+check_error 'p vfs_read+20 ^$arg*' # NOFENTRY_ARGS
check_error 'p vfs_read ^hoge' # NO_BTFARG
check_error 'p kfree ^$arg10' # NO_BTFARG (exceed the number of parameters)
check_error 'r kfree ^$retval' # NO_RETVAL
diff --git a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
index e5db897586bb..531228b849da 100644
--- a/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
+++ b/tools/testing/selftests/hid/progs/hid_bpf_helpers.h
@@ -22,6 +22,9 @@
#define HID_REQ_SET_IDLE HID_REQ_SET_IDLE___not_used
#define HID_REQ_SET_PROTOCOL HID_REQ_SET_PROTOCOL___not_used
+/* do not define kfunc through vmlinux.h as this messes up our custom hack */
+#define BPF_NO_KFUNC_PROTOTYPES
+
#include "vmlinux.h"
#undef hid_bpf_ctx
@@ -91,31 +94,31 @@ struct hid_bpf_ops {
/* following are kfuncs exported by HID for HID-BPF */
extern __u8 *hid_bpf_get_data(struct hid_bpf_ctx *ctx,
unsigned int offset,
- const size_t __sz) __ksym;
-extern struct hid_bpf_ctx *hid_bpf_allocate_context(unsigned int hid_id) __ksym;
-extern void hid_bpf_release_context(struct hid_bpf_ctx *ctx) __ksym;
+ const size_t __sz) __weak __ksym;
+extern struct hid_bpf_ctx *hid_bpf_allocate_context(unsigned int hid_id) __weak __ksym;
+extern void hid_bpf_release_context(struct hid_bpf_ctx *ctx) __weak __ksym;
extern int hid_bpf_hw_request(struct hid_bpf_ctx *ctx,
__u8 *data,
size_t buf__sz,
enum hid_report_type type,
- enum hid_class_request reqtype) __ksym;
+ enum hid_class_request reqtype) __weak __ksym;
extern int hid_bpf_hw_output_report(struct hid_bpf_ctx *ctx,
- __u8 *buf, size_t buf__sz) __ksym;
+ __u8 *buf, size_t buf__sz) __weak __ksym;
extern int hid_bpf_input_report(struct hid_bpf_ctx *ctx,
enum hid_report_type type,
__u8 *data,
- size_t buf__sz) __ksym;
+ size_t buf__sz) __weak __ksym;
extern int hid_bpf_try_input_report(struct hid_bpf_ctx *ctx,
enum hid_report_type type,
__u8 *data,
- size_t buf__sz) __ksym;
+ size_t buf__sz) __weak __ksym;
/* bpf_wq implementation */
extern int bpf_wq_init(struct bpf_wq *wq, void *p__map, unsigned int flags) __weak __ksym;
extern int bpf_wq_start(struct bpf_wq *wq, unsigned int flags) __weak __ksym;
extern int bpf_wq_set_callback_impl(struct bpf_wq *wq,
int (callback_fn)(void *map, int *key, void *wq),
- unsigned int flags__k, void *aux__ign) __ksym;
+ unsigned int flags__k, void *aux__ign) __weak __ksym;
#define bpf_wq_set_callback(timer, cb, flags) \
bpf_wq_set_callback_impl(timer, cb, flags, NULL)
diff --git a/tools/testing/selftests/hid/run-hid-tools-tests.sh b/tools/testing/selftests/hid/run-hid-tools-tests.sh
index bdae8464da86..af1682a53c27 100755
--- a/tools/testing/selftests/hid/run-hid-tools-tests.sh
+++ b/tools/testing/selftests/hid/run-hid-tools-tests.sh
@@ -2,24 +2,26 @@
# SPDX-License-Identifier: GPL-2.0
# Runs tests for the HID subsystem
+KSELFTEST_SKIP_TEST=4
+
if ! command -v python3 > /dev/null 2>&1; then
echo "hid-tools: [SKIP] python3 not installed"
- exit 77
+ exit $KSELFTEST_SKIP_TEST
fi
if ! python3 -c "import pytest" > /dev/null 2>&1; then
- echo "hid: [SKIP/ pytest module not installed"
- exit 77
+ echo "hid: [SKIP] pytest module not installed"
+ exit $KSELFTEST_SKIP_TEST
fi
if ! python3 -c "import pytest_tap" > /dev/null 2>&1; then
- echo "hid: [SKIP/ pytest_tap module not installed"
- exit 77
+ echo "hid: [SKIP] pytest_tap module not installed"
+ exit $KSELFTEST_SKIP_TEST
fi
if ! python3 -c "import hidtools" > /dev/null 2>&1; then
- echo "hid: [SKIP/ hid-tools module not installed"
- exit 77
+ echo "hid: [SKIP] hid-tools module not installed"
+ exit $KSELFTEST_SKIP_TEST
fi
TARGET=${TARGET:=.}
diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c
index 22f6fd5f0f74..64b1f8e1b0cf 100644
--- a/tools/testing/selftests/iommu/iommufd_fail_nth.c
+++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c
@@ -615,7 +615,12 @@ TEST_FAIL_NTH(basic_fail_nth, access_pin_domain)
/* device.c */
TEST_FAIL_NTH(basic_fail_nth, device)
{
+ struct iommu_hwpt_selftest data = {
+ .iotlb = IOMMU_TEST_IOTLB_DEFAULT,
+ };
struct iommu_test_hw_info info;
+ uint32_t fault_id, fault_fd;
+ uint32_t fault_hwpt_id;
uint32_t ioas_id;
uint32_t ioas_id2;
uint32_t stdev_id;
@@ -678,6 +683,15 @@ TEST_FAIL_NTH(basic_fail_nth, device)
if (_test_cmd_vdevice_alloc(self->fd, viommu_id, idev_id, 0, &vdev_id))
return -1;
+ if (_test_ioctl_fault_alloc(self->fd, &fault_id, &fault_fd))
+ return -1;
+ close(fault_fd);
+
+ if (_test_cmd_hwpt_alloc(self->fd, idev_id, hwpt_id, fault_id,
+ IOMMU_HWPT_FAULT_ID_VALID, &fault_hwpt_id,
+ IOMMU_HWPT_DATA_SELFTEST, &data, sizeof(data)))
+ return -1;
+
return 0;
}
diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/aarch64/set_id_regs.c
index a79b7f18452d..3a97c160b5fe 100644
--- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/aarch64/set_id_regs.c
@@ -152,7 +152,6 @@ static const struct reg_ftr_bits ftr_id_aa64mmfr0_el1[] = {
REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGENDEL0, 0),
REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, SNSMEM, 0),
REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGEND, 0),
- REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, ASIDBITS, 0),
REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, PARANGE, 0),
REG_FTR_END,
};
diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390x/ucontrol_test.c
index 0c112319dab1..135ee22856cf 100644
--- a/tools/testing/selftests/kvm/s390x/ucontrol_test.c
+++ b/tools/testing/selftests/kvm/s390x/ucontrol_test.c
@@ -210,10 +210,13 @@ TEST_F(uc_kvm, uc_attr_mem_limit)
struct kvm_device_attr attr = {
.group = KVM_S390_VM_MEM_CTRL,
.attr = KVM_S390_VM_MEM_LIMIT_SIZE,
- .addr = (unsigned long)&limit,
+ .addr = (u64)&limit,
};
int rc;
+ rc = ioctl(self->vm_fd, KVM_HAS_DEVICE_ATTR, &attr);
+ EXPECT_EQ(0, rc);
+
rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr);
EXPECT_EQ(0, rc);
EXPECT_EQ(~0UL, limit);
@@ -635,4 +638,171 @@ TEST_F(uc_kvm, uc_skey)
uc_assert_diag44(self);
}
+static char uc_flic_b[PAGE_SIZE];
+static struct kvm_s390_io_adapter uc_flic_ioa = { .id = 0 };
+static struct kvm_s390_io_adapter_req uc_flic_ioam = { .id = 0 };
+static struct kvm_s390_ais_req uc_flic_asim = { .isc = 0 };
+static struct kvm_s390_ais_all uc_flic_asima = { .simm = 0 };
+static struct uc_flic_attr_test {
+ char *name;
+ struct kvm_device_attr a;
+ int hasrc;
+ int geterrno;
+ int seterrno;
+} uc_flic_attr_tests[] = {
+ {
+ .name = "KVM_DEV_FLIC_GET_ALL_IRQS",
+ .seterrno = EINVAL,
+ .a = {
+ .group = KVM_DEV_FLIC_GET_ALL_IRQS,
+ .addr = (u64)&uc_flic_b,
+ .attr = PAGE_SIZE,
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_ENQUEUE",
+ .geterrno = EINVAL,
+ .a = { .group = KVM_DEV_FLIC_ENQUEUE, },
+ },
+ {
+ .name = "KVM_DEV_FLIC_CLEAR_IRQS",
+ .geterrno = EINVAL,
+ .a = { .group = KVM_DEV_FLIC_CLEAR_IRQS, },
+ },
+ {
+ .name = "KVM_DEV_FLIC_ADAPTER_REGISTER",
+ .geterrno = EINVAL,
+ .a = {
+ .group = KVM_DEV_FLIC_ADAPTER_REGISTER,
+ .addr = (u64)&uc_flic_ioa,
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_ADAPTER_MODIFY",
+ .geterrno = EINVAL,
+ .seterrno = EINVAL,
+ .a = {
+ .group = KVM_DEV_FLIC_ADAPTER_MODIFY,
+ .addr = (u64)&uc_flic_ioam,
+ .attr = sizeof(uc_flic_ioam),
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_CLEAR_IO_IRQ",
+ .geterrno = EINVAL,
+ .seterrno = EINVAL,
+ .a = {
+ .group = KVM_DEV_FLIC_CLEAR_IO_IRQ,
+ .attr = 32,
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_AISM",
+ .geterrno = EINVAL,
+ .seterrno = ENOTSUP,
+ .a = {
+ .group = KVM_DEV_FLIC_AISM,
+ .addr = (u64)&uc_flic_asim,
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_AIRQ_INJECT",
+ .geterrno = EINVAL,
+ .a = { .group = KVM_DEV_FLIC_AIRQ_INJECT, },
+ },
+ {
+ .name = "KVM_DEV_FLIC_AISM_ALL",
+ .geterrno = ENOTSUP,
+ .seterrno = ENOTSUP,
+ .a = {
+ .group = KVM_DEV_FLIC_AISM_ALL,
+ .addr = (u64)&uc_flic_asima,
+ .attr = sizeof(uc_flic_asima),
+ },
+ },
+ {
+ .name = "KVM_DEV_FLIC_APF_ENABLE",
+ .geterrno = EINVAL,
+ .seterrno = EINVAL,
+ .a = { .group = KVM_DEV_FLIC_APF_ENABLE, },
+ },
+ {
+ .name = "KVM_DEV_FLIC_APF_DISABLE_WAIT",
+ .geterrno = EINVAL,
+ .seterrno = EINVAL,
+ .a = { .group = KVM_DEV_FLIC_APF_DISABLE_WAIT, },
+ },
+};
+
+TEST_F(uc_kvm, uc_flic_attrs)
+{
+ struct kvm_create_device cd = { .type = KVM_DEV_TYPE_FLIC };
+ struct kvm_device_attr attr;
+ u64 value;
+ int rc, i;
+
+ rc = ioctl(self->vm_fd, KVM_CREATE_DEVICE, &cd);
+ ASSERT_EQ(0, rc) TH_LOG("create device failed with err %s (%i)",
+ strerror(errno), errno);
+
+ for (i = 0; i < ARRAY_SIZE(uc_flic_attr_tests); i++) {
+ TH_LOG("test %s", uc_flic_attr_tests[i].name);
+ attr = (struct kvm_device_attr) {
+ .group = uc_flic_attr_tests[i].a.group,
+ .attr = uc_flic_attr_tests[i].a.attr,
+ .addr = uc_flic_attr_tests[i].a.addr,
+ };
+ if (attr.addr == 0)
+ attr.addr = (u64)&value;
+
+ rc = ioctl(cd.fd, KVM_HAS_DEVICE_ATTR, &attr);
+ EXPECT_EQ(uc_flic_attr_tests[i].hasrc, !!rc)
+ TH_LOG("expected dev attr missing %s",
+ uc_flic_attr_tests[i].name);
+
+ rc = ioctl(cd.fd, KVM_GET_DEVICE_ATTR, &attr);
+ EXPECT_EQ(!!uc_flic_attr_tests[i].geterrno, !!rc)
+ TH_LOG("get dev attr rc not expected on %s %s (%i)",
+ uc_flic_attr_tests[i].name,
+ strerror(errno), errno);
+ if (uc_flic_attr_tests[i].geterrno)
+ EXPECT_EQ(uc_flic_attr_tests[i].geterrno, errno)
+ TH_LOG("get dev attr errno not expected on %s %s (%i)",
+ uc_flic_attr_tests[i].name,
+ strerror(errno), errno);
+
+ rc = ioctl(cd.fd, KVM_SET_DEVICE_ATTR, &attr);
+ EXPECT_EQ(!!uc_flic_attr_tests[i].seterrno, !!rc)
+ TH_LOG("set sev attr rc not expected on %s %s (%i)",
+ uc_flic_attr_tests[i].name,
+ strerror(errno), errno);
+ if (uc_flic_attr_tests[i].seterrno)
+ EXPECT_EQ(uc_flic_attr_tests[i].seterrno, errno)
+ TH_LOG("set dev attr errno not expected on %s %s (%i)",
+ uc_flic_attr_tests[i].name,
+ strerror(errno), errno);
+ }
+
+ close(cd.fd);
+}
+
+TEST_F(uc_kvm, uc_set_gsi_routing)
+{
+ struct kvm_irq_routing *routing = kvm_gsi_routing_create();
+ struct kvm_irq_routing_entry ue = {
+ .type = KVM_IRQ_ROUTING_S390_ADAPTER,
+ .gsi = 1,
+ .u.adapter = (struct kvm_irq_routing_s390_adapter) {
+ .ind_addr = 0,
+ },
+ };
+ int rc;
+
+ routing->entries[0] = ue;
+ routing->nr = 1;
+ rc = ioctl(self->vm_fd, KVM_SET_GSI_ROUTING, routing);
+ ASSERT_EQ(-1, rc) TH_LOG("err %s (%i)", strerror(errno), errno);
+ ASSERT_EQ(EINVAL, errno) TH_LOG("err %s (%i)", strerror(errno), errno);
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 95af2d78fd31..c0c53451a16d 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -9,6 +9,7 @@
#include <fcntl.h>
#include <linux/memfd.h>
#include <sched.h>
+#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <signal.h>
@@ -281,6 +282,24 @@ static void *mfd_assert_mmap_shared(int fd)
return p;
}
+static void *mfd_assert_mmap_read_shared(int fd)
+{
+ void *p;
+
+ p = mmap(NULL,
+ mfd_def_size,
+ PROT_READ,
+ MAP_SHARED,
+ fd,
+ 0);
+ if (p == MAP_FAILED) {
+ printf("mmap() failed: %m\n");
+ abort();
+ }
+
+ return p;
+}
+
static void *mfd_assert_mmap_private(int fd)
{
void *p;
@@ -979,6 +998,30 @@ static void test_seal_future_write(void)
close(fd);
}
+static void test_seal_write_map_read_shared(void)
+{
+ int fd;
+ void *p;
+
+ printf("%s SEAL-WRITE-MAP-READ\n", memfd_str);
+
+ fd = mfd_assert_new("kern_memfd_seal_write_map_read",
+ mfd_def_size,
+ MFD_CLOEXEC | MFD_ALLOW_SEALING);
+
+ mfd_assert_add_seals(fd, F_SEAL_WRITE);
+ mfd_assert_has_seals(fd, F_SEAL_WRITE);
+
+ p = mfd_assert_mmap_read_shared(fd);
+
+ mfd_assert_read(fd);
+ mfd_assert_read_shared(fd);
+ mfd_fail_write(fd);
+
+ munmap(p, mfd_def_size);
+ close(fd);
+}
+
/*
* Test SEAL_SHRINK
* Test whether SEAL_SHRINK actually prevents shrinking
@@ -1557,6 +1600,11 @@ static void test_share_fork(char *banner, char *b_suffix)
close(fd);
}
+static bool pid_ns_supported(void)
+{
+ return access("/proc/self/ns/pid", F_OK) == 0;
+}
+
int main(int argc, char **argv)
{
pid_t pid;
@@ -1587,12 +1635,17 @@ int main(int argc, char **argv)
test_seal_write();
test_seal_future_write();
+ test_seal_write_map_read_shared();
test_seal_shrink();
test_seal_grow();
test_seal_resize();
- test_sysctl_simple();
- test_sysctl_nested();
+ if (pid_ns_supported()) {
+ test_sysctl_simple();
+ test_sysctl_nested();
+ } else {
+ printf("PID namespaces are not supported; skipping sysctl tests\n");
+ }
test_share_dup("SHARE-DUP", "");
test_share_mmap("SHARE-MMAP", "");
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index 32c6ccc2a6be..1238e1c5aae1 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -758,7 +758,7 @@ static void do_run_with_base_page(test_fn fn, bool swapout)
}
/* Populate a base page. */
- memset(mem, 0, pagesize);
+ memset(mem, 1, pagesize);
if (swapout) {
madvise(mem, pagesize, MADV_PAGEOUT);
@@ -824,12 +824,12 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
* Try to populate a THP. Touch the first sub-page and test if
* we get the last sub-page populated automatically.
*/
- mem[0] = 0;
+ mem[0] = 1;
if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) {
ksft_test_result_skip("Did not get a THP populated\n");
goto munmap;
}
- memset(mem, 0, thpsize);
+ memset(mem, 1, thpsize);
size = thpsize;
switch (thp_run) {
@@ -1012,7 +1012,7 @@ static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize)
}
/* Populate an huge page. */
- memset(mem, 0, hugetlbsize);
+ memset(mem, 1, hugetlbsize);
/*
* We need a total of two hugetlb pages to handle COW/unsharing
diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c
index 432d5af15e66..db63abe5ee5e 100644
--- a/tools/testing/selftests/mm/hugetlb_dio.c
+++ b/tools/testing/selftests/mm/hugetlb_dio.c
@@ -76,19 +76,15 @@ void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off)
/* Get the free huge pages after unmap*/
free_hpage_a = get_free_hugepages();
+ ksft_print_msg("No. Free pages before allocation : %d\n", free_hpage_b);
+ ksft_print_msg("No. Free pages after munmap : %d\n", free_hpage_a);
+
/*
* If the no. of free hugepages before allocation and after unmap does
* not match - that means there could still be a page which is pinned.
*/
- if (free_hpage_a != free_hpage_b) {
- ksft_print_msg("No. Free pages before allocation : %d\n", free_hpage_b);
- ksft_print_msg("No. Free pages after munmap : %d\n", free_hpage_a);
- ksft_test_result_fail(": Huge pages not freed!\n");
- } else {
- ksft_print_msg("No. Free pages before allocation : %d\n", free_hpage_b);
- ksft_print_msg("No. Free pages after munmap : %d\n", free_hpage_a);
- ksft_test_result_pass(": Huge pages freed successfully !\n");
- }
+ ksft_test_result(free_hpage_a == free_hpage_b,
+ "free huge pages from %u-%u\n", start_off, end_off);
}
int main(void)
diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
index c35548767756..ecd34f364125 100755
--- a/tools/testing/selftests/net/forwarding/local_termination.sh
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -7,7 +7,6 @@ ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \
NUM_NETIFS=2
PING_COUNT=1
REQUIRE_MTOOLS=yes
-REQUIRE_MZ=no
source lib.sh
diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py
index a0d689d58c57..076a7e8dc3eb 100644
--- a/tools/testing/selftests/net/lib/py/ynl.py
+++ b/tools/testing/selftests/net/lib/py/ynl.py
@@ -32,23 +32,23 @@ except ModuleNotFoundError as e:
# Set schema='' to avoid jsonschema validation, it's slow
#
class EthtoolFamily(YnlFamily):
- def __init__(self):
+ def __init__(self, recv_size=0):
super().__init__((SPEC_PATH / Path('ethtool.yaml')).as_posix(),
- schema='')
+ schema='', recv_size=recv_size)
class RtnlFamily(YnlFamily):
- def __init__(self):
+ def __init__(self, recv_size=0):
super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(),
- schema='')
+ schema='', recv_size=recv_size)
class NetdevFamily(YnlFamily):
- def __init__(self):
+ def __init__(self, recv_size=0):
super().__init__((SPEC_PATH / Path('netdev.yaml')).as_posix(),
- schema='')
+ schema='', recv_size=recv_size)
class NetshaperFamily(YnlFamily):
- def __init__(self):
+ def __init__(self, recv_size=0):
super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(),
- schema='')
+ schema='', recv_size=recv_size)
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 4209b9569039..414addef9a45 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -25,6 +25,8 @@
#include <sys/types.h>
#include <sys/mman.h>
+#include <arpa/inet.h>
+
#include <netdb.h>
#include <netinet/in.h>
@@ -1211,23 +1213,42 @@ static void parse_setsock_options(const char *name)
exit(1);
}
-void xdisconnect(int fd, int addrlen)
+void xdisconnect(int fd)
{
- struct sockaddr_storage empty;
+ socklen_t addrlen = sizeof(struct sockaddr_storage);
+ struct sockaddr_storage addr, empty;
int msec_sleep = 10;
- int queued = 1;
- int i;
+ void *raw_addr;
+ int i, cmdlen;
+ char cmd[128];
+
+ /* get the local address and convert it to string */
+ if (getsockname(fd, (struct sockaddr *)&addr, &addrlen) < 0)
+ xerror("getsockname");
+
+ if (addr.ss_family == AF_INET)
+ raw_addr = &(((struct sockaddr_in *)&addr)->sin_addr);
+ else if (addr.ss_family == AF_INET6)
+ raw_addr = &(((struct sockaddr_in6 *)&addr)->sin6_addr);
+ else
+ xerror("bad family");
+
+ strcpy(cmd, "ss -M | grep -q ");
+ cmdlen = strlen(cmd);
+ if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen],
+ sizeof(cmd) - cmdlen))
+ xerror("inet_ntop");
shutdown(fd, SHUT_WR);
- /* while until the pending data is completely flushed, the later
+ /*
+ * wait until the pending data is completely flushed and all
+ * the MPTCP sockets reached the closed status.
* disconnect will bypass/ignore/drop any pending data.
*/
for (i = 0; ; i += msec_sleep) {
- if (ioctl(fd, SIOCOUTQ, &queued) < 0)
- xerror("can't query out socket queue: %d", errno);
-
- if (!queued)
+ /* closed socket are not listed by 'ss' */
+ if (system(cmd) != 0)
break;
if (i > poll_timeout)
@@ -1281,9 +1302,9 @@ again:
return ret;
if (cfg_truncate > 0) {
- xdisconnect(fd, peer->ai_addrlen);
+ xdisconnect(fd);
} else if (--cfg_repeat > 0) {
- xdisconnect(fd, peer->ai_addrlen);
+ xdisconnect(fd);
/* the socket could be unblocking at this point, we need the
* connect to be blocking
diff --git a/tools/testing/selftests/net/netfilter/rpath.sh b/tools/testing/selftests/net/netfilter/rpath.sh
index 4485fd7675ed..86ec4e68594d 100755
--- a/tools/testing/selftests/net/netfilter/rpath.sh
+++ b/tools/testing/selftests/net/netfilter/rpath.sh
@@ -61,9 +61,20 @@ ip -net "$ns2" a a 192.168.42.1/24 dev d0
ip -net "$ns1" a a fec0:42::2/64 dev v0 nodad
ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad
+# avoid neighbor lookups and enable martian IPv6 pings
+ns2_hwaddr=$(ip -net "$ns2" link show dev v0 | \
+ sed -n 's, *link/ether \([^ ]*\) .*,\1,p')
+ns1_hwaddr=$(ip -net "$ns1" link show dev v0 | \
+ sed -n 's, *link/ether \([^ ]*\) .*,\1,p')
+ip -net "$ns1" neigh add fec0:42::1 lladdr "$ns2_hwaddr" nud permanent dev v0
+ip -net "$ns1" neigh add fec0:23::1 lladdr "$ns2_hwaddr" nud permanent dev v0
+ip -net "$ns2" neigh add fec0:42::2 lladdr "$ns1_hwaddr" nud permanent dev d0
+ip -net "$ns2" neigh add fec0:23::2 lladdr "$ns1_hwaddr" nud permanent dev v0
+
# firewall matches to test
[ -n "$iptables" ] && {
common='-t raw -A PREROUTING -s 192.168.0.0/16'
+ common+=' -p icmp --icmp-type echo-request'
if ! ip netns exec "$ns2" "$iptables" $common -m rpfilter;then
echo "Cannot add rpfilter rule"
exit $ksft_skip
@@ -72,6 +83,7 @@ ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad
}
[ -n "$ip6tables" ] && {
common='-t raw -A PREROUTING -s fec0::/16'
+ common+=' -p icmpv6 --icmpv6-type echo-request'
if ! ip netns exec "$ns2" "$ip6tables" $common -m rpfilter;then
echo "Cannot add rpfilter rule"
exit $ksft_skip
@@ -82,8 +94,10 @@ ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad
table inet t {
chain c {
type filter hook prerouting priority raw;
- ip saddr 192.168.0.0/16 fib saddr . iif oif exists counter
- ip6 saddr fec0::/16 fib saddr . iif oif exists counter
+ ip saddr 192.168.0.0/16 icmp type echo-request \
+ fib saddr . iif oif exists counter
+ ip6 saddr fec0::/16 icmpv6 type echo-request \
+ fib saddr . iif oif exists counter
}
}
EOF
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index cc0bfae2bafa..960e1ab4dd04 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -171,8 +171,10 @@ ovs_add_netns_and_veths () {
ovs_add_if "$1" "$2" "$4" -u || return 1
fi
- [ $TRACING -eq 1 ] && ovs_netns_spawn_daemon "$1" "$ns" \
- tcpdump -i any -s 65535
+ if [ $TRACING -eq 1 ]; then
+ ovs_netns_spawn_daemon "$1" "$3" tcpdump -l -i any -s 6553
+ ovs_wait grep -q "listening on any" ${ovs_dir}/stderr
+ fi
return 0
}
diff --git a/tools/testing/selftests/pid_namespace/.gitignore b/tools/testing/selftests/pid_namespace/.gitignore
index 93ab9d7e5b7e..5118f0f3edf4 100644
--- a/tools/testing/selftests/pid_namespace/.gitignore
+++ b/tools/testing/selftests/pid_namespace/.gitignore
@@ -1 +1,2 @@
+pid_max
regression_enomem
diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile
index 9286a1d22cd3..b972f55d07ae 100644
--- a/tools/testing/selftests/pid_namespace/Makefile
+++ b/tools/testing/selftests/pid_namespace/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS += -g $(KHDR_INCLUDES)
-TEST_GEN_PROGS = regression_enomem
+TEST_GEN_PROGS = regression_enomem pid_max
LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h
diff --git a/tools/testing/selftests/pid_namespace/pid_max.c b/tools/testing/selftests/pid_namespace/pid_max.c
new file mode 100644
index 000000000000..51c414faabb0
--- /dev/null
+++ b/tools/testing/selftests/pid_namespace/pid_max.c
@@ -0,0 +1,358 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define _GNU_SOURCE
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/types.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/wait.h>
+
+#include "../kselftest_harness.h"
+#include "../pidfd/pidfd.h"
+
+#define __STACK_SIZE (8 * 1024 * 1024)
+static pid_t do_clone(int (*fn)(void *), void *arg, int flags)
+{
+ char *stack;
+ pid_t ret;
+
+ stack = malloc(__STACK_SIZE);
+ if (!stack)
+ return -ENOMEM;
+
+#ifdef __ia64__
+ ret = __clone2(fn, stack, __STACK_SIZE, flags | SIGCHLD, arg);
+#else
+ ret = clone(fn, stack + __STACK_SIZE, flags | SIGCHLD, arg);
+#endif
+ free(stack);
+ return ret;
+}
+
+static int pid_max_cb(void *data)
+{
+ int fd, ret;
+ pid_t pid;
+
+ ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0);
+ if (ret) {
+ fprintf(stderr, "%m - Failed to make rootfs private mount\n");
+ return -1;
+ }
+
+ umount2("/proc", MNT_DETACH);
+
+ ret = mount("proc", "/proc", "proc", 0, NULL);
+ if (ret) {
+ fprintf(stderr, "%m - Failed to mount proc\n");
+ return -1;
+ }
+
+ fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY);
+ if (fd < 0) {
+ fprintf(stderr, "%m - Failed to open pid_max\n");
+ return -1;
+ }
+
+ ret = write(fd, "500", sizeof("500") - 1);
+ if (ret < 0) {
+ fprintf(stderr, "%m - Failed to write pid_max\n");
+ return -1;
+ }
+
+ for (int i = 0; i < 501; i++) {
+ pid = fork();
+ if (pid == 0)
+ exit(EXIT_SUCCESS);
+ wait_for_pid(pid);
+ if (pid > 500) {
+ fprintf(stderr, "Managed to create pid number beyond limit\n");
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static int pid_max_nested_inner(void *data)
+{
+ int fret = -1;
+ pid_t pids[2];
+ int fd, i, ret;
+
+ ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0);
+ if (ret) {
+ fprintf(stderr, "%m - Failed to make rootfs private mount\n");
+ return fret;
+ }
+
+ umount2("/proc", MNT_DETACH);
+
+ ret = mount("proc", "/proc", "proc", 0, NULL);
+ if (ret) {
+ fprintf(stderr, "%m - Failed to mount proc\n");
+ return fret;
+ }
+
+ fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY);
+ if (fd < 0) {
+ fprintf(stderr, "%m - Failed to open pid_max\n");
+ return fret;
+ }
+
+ ret = write(fd, "500", sizeof("500") - 1);
+ close(fd);
+ if (ret < 0) {
+ fprintf(stderr, "%m - Failed to write pid_max\n");
+ return fret;
+ }
+
+ pids[0] = fork();
+ if (pids[0] < 0) {
+ fprintf(stderr, "Failed to create first new process\n");
+ return fret;
+ }
+
+ if (pids[0] == 0)
+ exit(EXIT_SUCCESS);
+
+ pids[1] = fork();
+ wait_for_pid(pids[0]);
+ if (pids[1] >= 0) {
+ if (pids[1] == 0)
+ exit(EXIT_SUCCESS);
+ wait_for_pid(pids[1]);
+
+ fprintf(stderr, "Managed to create process even though ancestor pid namespace had a limit\n");
+ return fret;
+ }
+
+ /* Now make sure that we wrap pids at 400. */
+ for (i = 0; i < 510; i++) {
+ pid_t pid;
+
+ pid = fork();
+ if (pid < 0)
+ return fret;
+
+ if (pid == 0)
+ exit(EXIT_SUCCESS);
+
+ wait_for_pid(pid);
+ if (pid >= 500) {
+ fprintf(stderr, "Managed to create process with pid %d beyond configured limit\n", pid);
+ return fret;
+ }
+ }
+
+ return 0;
+}
+
+static int pid_max_nested_outer(void *data)
+{
+ int fret = -1, nr_procs = 400;
+ pid_t pids[1000];
+ int fd, i, ret;
+ pid_t pid;
+
+ ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0);
+ if (ret) {
+ fprintf(stderr, "%m - Failed to make rootfs private mount\n");
+ return fret;
+ }
+
+ umount2("/proc", MNT_DETACH);
+
+ ret = mount("proc", "/proc", "proc", 0, NULL);
+ if (ret) {
+ fprintf(stderr, "%m - Failed to mount proc\n");
+ return fret;
+ }
+
+ fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY);
+ if (fd < 0) {
+ fprintf(stderr, "%m - Failed to open pid_max\n");
+ return fret;
+ }
+
+ ret = write(fd, "400", sizeof("400") - 1);
+ close(fd);
+ if (ret < 0) {
+ fprintf(stderr, "%m - Failed to write pid_max\n");
+ return fret;
+ }
+
+ /*
+ * Create 397 processes. This leaves room for do_clone() (398) and
+ * one more 399. So creating another process needs to fail.
+ */
+ for (nr_procs = 0; nr_procs < 396; nr_procs++) {
+ pid = fork();
+ if (pid < 0)
+ goto reap;
+
+ if (pid == 0)
+ exit(EXIT_SUCCESS);
+
+ pids[nr_procs] = pid;
+ }
+
+ pid = do_clone(pid_max_nested_inner, NULL, CLONE_NEWPID | CLONE_NEWNS);
+ if (pid < 0) {
+ fprintf(stderr, "%m - Failed to clone nested pidns\n");
+ goto reap;
+ }
+
+ if (wait_for_pid(pid)) {
+ fprintf(stderr, "%m - Nested pid_max failed\n");
+ goto reap;
+ }
+
+ fret = 0;
+
+reap:
+ for (int i = 0; i < nr_procs; i++)
+ wait_for_pid(pids[i]);
+
+ return fret;
+}
+
+static int pid_max_nested_limit_inner(void *data)
+{
+ int fret = -1, nr_procs = 400;
+ int fd, ret;
+ pid_t pid;
+ pid_t pids[1000];
+
+ ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0);
+ if (ret) {
+ fprintf(stderr, "%m - Failed to make rootfs private mount\n");
+ return fret;
+ }
+
+ umount2("/proc", MNT_DETACH);
+
+ ret = mount("proc", "/proc", "proc", 0, NULL);
+ if (ret) {
+ fprintf(stderr, "%m - Failed to mount proc\n");
+ return fret;
+ }
+
+ fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY);
+ if (fd < 0) {
+ fprintf(stderr, "%m - Failed to open pid_max\n");
+ return fret;
+ }
+
+ ret = write(fd, "500", sizeof("500") - 1);
+ close(fd);
+ if (ret < 0) {
+ fprintf(stderr, "%m - Failed to write pid_max\n");
+ return fret;
+ }
+
+ for (nr_procs = 0; nr_procs < 500; nr_procs++) {
+ pid = fork();
+ if (pid < 0)
+ break;
+
+ if (pid == 0)
+ exit(EXIT_SUCCESS);
+
+ pids[nr_procs] = pid;
+ }
+
+ if (nr_procs >= 400) {
+ fprintf(stderr, "Managed to create processes beyond the configured outer limit\n");
+ goto reap;
+ }
+
+ fret = 0;
+
+reap:
+ for (int i = 0; i < nr_procs; i++)
+ wait_for_pid(pids[i]);
+
+ return fret;
+}
+
+static int pid_max_nested_limit_outer(void *data)
+{
+ int fd, ret;
+ pid_t pid;
+
+ ret = mount("", "/", NULL, MS_PRIVATE | MS_REC, 0);
+ if (ret) {
+ fprintf(stderr, "%m - Failed to make rootfs private mount\n");
+ return -1;
+ }
+
+ umount2("/proc", MNT_DETACH);
+
+ ret = mount("proc", "/proc", "proc", 0, NULL);
+ if (ret) {
+ fprintf(stderr, "%m - Failed to mount proc\n");
+ return -1;
+ }
+
+ fd = open("/proc/sys/kernel/pid_max", O_RDWR | O_CLOEXEC | O_NOCTTY);
+ if (fd < 0) {
+ fprintf(stderr, "%m - Failed to open pid_max\n");
+ return -1;
+ }
+
+ ret = write(fd, "400", sizeof("400") - 1);
+ close(fd);
+ if (ret < 0) {
+ fprintf(stderr, "%m - Failed to write pid_max\n");
+ return -1;
+ }
+
+ pid = do_clone(pid_max_nested_limit_inner, NULL, CLONE_NEWPID | CLONE_NEWNS);
+ if (pid < 0) {
+ fprintf(stderr, "%m - Failed to clone nested pidns\n");
+ return -1;
+ }
+
+ if (wait_for_pid(pid)) {
+ fprintf(stderr, "%m - Nested pid_max failed\n");
+ return -1;
+ }
+
+ return 0;
+}
+
+TEST(pid_max_simple)
+{
+ pid_t pid;
+
+
+ pid = do_clone(pid_max_cb, NULL, CLONE_NEWPID | CLONE_NEWNS);
+ ASSERT_GT(pid, 0);
+ ASSERT_EQ(0, wait_for_pid(pid));
+}
+
+TEST(pid_max_nested_limit)
+{
+ pid_t pid;
+
+ pid = do_clone(pid_max_nested_limit_outer, NULL, CLONE_NEWPID | CLONE_NEWNS);
+ ASSERT_GT(pid, 0);
+ ASSERT_EQ(0, wait_for_pid(pid));
+}
+
+TEST(pid_max_nested)
+{
+ pid_t pid;
+
+ pid = do_clone(pid_max_nested_outer, NULL, CLONE_NEWPID | CLONE_NEWNS);
+ ASSERT_GT(pid, 0);
+ ASSERT_EQ(0, wait_for_pid(pid));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore
index 973198a3ec3d..bf92481f925c 100644
--- a/tools/testing/selftests/pidfd/.gitignore
+++ b/tools/testing/selftests/pidfd/.gitignore
@@ -6,3 +6,5 @@ pidfd_wait
pidfd_fdinfo_test
pidfd_getfd_test
pidfd_setns_test
+pidfd_file_handle_test
+pidfd_bind_mount
diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile
index d731e3e76d5b..301343a11b62 100644
--- a/tools/testing/selftests/pidfd/Makefile
+++ b/tools/testing/selftests/pidfd/Makefile
@@ -2,7 +2,8 @@
CFLAGS += -g $(KHDR_INCLUDES) -pthread -Wall
TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \
- pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test
+ pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test \
+ pidfd_file_handle_test pidfd_bind_mount
include ../lib.mk
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index 88d6830ee004..0b96ac4b8ce5 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -12,11 +12,11 @@
#include <stdlib.h>
#include <string.h>
#include <syscall.h>
-#include <sys/mount.h>
#include <sys/types.h>
#include <sys/wait.h>
#include "../kselftest.h"
+#include "../clone3/clone3_selftests.h"
#ifndef P_PIDFD
#define P_PIDFD 3
@@ -68,6 +68,11 @@
#define PIDFD_SKIP 3
#define PIDFD_XFAIL 4
+static inline int sys_waitid(int which, pid_t pid, siginfo_t *info, int options)
+{
+ return syscall(__NR_waitid, which, pid, info, options, NULL);
+}
+
static inline int wait_for_pid(pid_t pid)
{
int status, ret;
@@ -114,4 +119,37 @@ static inline int sys_memfd_create(const char *name, unsigned int flags)
return syscall(__NR_memfd_create, name, flags);
}
+static inline pid_t create_child(int *pidfd, unsigned flags)
+{
+ struct __clone_args args = {
+ .flags = CLONE_PIDFD | flags,
+ .exit_signal = SIGCHLD,
+ .pidfd = ptr_to_u64(pidfd),
+ };
+
+ return sys_clone3(&args, sizeof(struct __clone_args));
+}
+
+static inline ssize_t read_nointr(int fd, void *buf, size_t count)
+{
+ ssize_t ret;
+
+ do {
+ ret = read(fd, buf, count);
+ } while (ret < 0 && errno == EINTR);
+
+ return ret;
+}
+
+static inline ssize_t write_nointr(int fd, const void *buf, size_t count)
+{
+ ssize_t ret;
+
+ do {
+ ret = write(fd, buf, count);
+ } while (ret < 0 && errno == EINTR);
+
+ return ret;
+}
+
#endif /* __PIDFD_H */
diff --git a/tools/testing/selftests/pidfd/pidfd_bind_mount.c b/tools/testing/selftests/pidfd/pidfd_bind_mount.c
new file mode 100644
index 000000000000..7822dd080258
--- /dev/null
+++ b/tools/testing/selftests/pidfd/pidfd_bind_mount.c
@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+// Copyright (c) 2024 Christian Brauner <brauner@kernel.org>
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <limits.h>
+#include <sched.h>
+#include <stdio.h>
+#include <string.h>
+#include <linux/fs.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <sys/mount.h>
+#include <unistd.h>
+
+#include "pidfd.h"
+#include "../kselftest_harness.h"
+
+#ifndef __NR_open_tree
+ #if defined __alpha__
+ #define __NR_open_tree 538
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_open_tree 4428
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_open_tree 6428
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_open_tree 5428
+ #endif
+ #elif defined __ia64__
+ #define __NR_open_tree (428 + 1024)
+ #else
+ #define __NR_open_tree 428
+ #endif
+#endif
+
+#ifndef __NR_move_mount
+ #if defined __alpha__
+ #define __NR_move_mount 539
+ #elif defined _MIPS_SIM
+ #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */
+ #define __NR_move_mount 4429
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */
+ #define __NR_move_mount 6429
+ #endif
+ #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */
+ #define __NR_move_mount 5429
+ #endif
+ #elif defined __ia64__
+ #define __NR_move_mount (428 + 1024)
+ #else
+ #define __NR_move_mount 429
+ #endif
+#endif
+
+#ifndef MOVE_MOUNT_F_EMPTY_PATH
+#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
+#endif
+
+#ifndef MOVE_MOUNT_F_EMPTY_PATH
+#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */
+#endif
+
+static inline int sys_move_mount(int from_dfd, const char *from_pathname,
+ int to_dfd, const char *to_pathname,
+ unsigned int flags)
+{
+ return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd,
+ to_pathname, flags);
+}
+
+#ifndef OPEN_TREE_CLONE
+#define OPEN_TREE_CLONE 1
+#endif
+
+#ifndef OPEN_TREE_CLOEXEC
+#define OPEN_TREE_CLOEXEC O_CLOEXEC
+#endif
+
+#ifndef AT_RECURSIVE
+#define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */
+#endif
+
+static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags)
+{
+ return syscall(__NR_open_tree, dfd, filename, flags);
+}
+
+FIXTURE(pidfd_bind_mount) {
+ char template[PATH_MAX];
+ int fd_tmp;
+ int pidfd;
+ struct stat st1;
+ struct stat st2;
+ __u32 gen1;
+ __u32 gen2;
+ bool must_unmount;
+};
+
+FIXTURE_SETUP(pidfd_bind_mount)
+{
+ self->fd_tmp = -EBADF;
+ self->must_unmount = false;
+ ASSERT_EQ(unshare(CLONE_NEWNS), 0);
+ ASSERT_LE(snprintf(self->template, PATH_MAX, "%s", P_tmpdir "/pidfd_bind_mount_XXXXXX"), PATH_MAX);
+ self->fd_tmp = mkstemp(self->template);
+ ASSERT_GE(self->fd_tmp, 0);
+ self->pidfd = sys_pidfd_open(getpid(), 0);
+ ASSERT_GE(self->pidfd, 0);
+ ASSERT_GE(fstat(self->pidfd, &self->st1), 0);
+ ASSERT_EQ(ioctl(self->pidfd, FS_IOC_GETVERSION, &self->gen1), 0);
+}
+
+FIXTURE_TEARDOWN(pidfd_bind_mount)
+{
+ ASSERT_EQ(close(self->fd_tmp), 0);
+ if (self->must_unmount)
+ ASSERT_EQ(umount2(self->template, 0), 0);
+ ASSERT_EQ(unlink(self->template), 0);
+}
+
+/*
+ * Test that a detached mount can be created for a pidfd and then
+ * attached to the filesystem hierarchy.
+ */
+TEST_F(pidfd_bind_mount, bind_mount)
+{
+ int fd_tree;
+
+ fd_tree = sys_open_tree(self->pidfd, "", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | AT_EMPTY_PATH);
+ ASSERT_GE(fd_tree, 0);
+
+ ASSERT_EQ(move_mount(fd_tree, "", self->fd_tmp, "", MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH), 0);
+ self->must_unmount = true;
+
+ ASSERT_EQ(close(fd_tree), 0);
+}
+
+/* Test that a pidfd can be reopened through procfs. */
+TEST_F(pidfd_bind_mount, reopen)
+{
+ int pidfd;
+ char proc_path[PATH_MAX];
+
+ sprintf(proc_path, "/proc/self/fd/%d", self->pidfd);
+ pidfd = open(proc_path, O_RDONLY | O_NOCTTY | O_CLOEXEC);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_GE(fstat(self->pidfd, &self->st2), 0);
+ ASSERT_EQ(ioctl(self->pidfd, FS_IOC_GETVERSION, &self->gen2), 0);
+
+ ASSERT_TRUE(self->st1.st_dev == self->st2.st_dev && self->st1.st_ino == self->st2.st_ino);
+ ASSERT_TRUE(self->gen1 == self->gen2);
+
+ ASSERT_EQ(close(pidfd), 0);
+}
+
+/*
+ * Test that a detached mount can be created for a pidfd and then
+ * attached to the filesystem hierarchy and reopened.
+ */
+TEST_F(pidfd_bind_mount, bind_mount_reopen)
+{
+ int fd_tree, fd_pidfd_mnt;
+
+ fd_tree = sys_open_tree(self->pidfd, "", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | AT_EMPTY_PATH);
+ ASSERT_GE(fd_tree, 0);
+
+ ASSERT_EQ(move_mount(fd_tree, "", self->fd_tmp, "", MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH), 0);
+ self->must_unmount = true;
+
+ fd_pidfd_mnt = openat(-EBADF, self->template, O_RDONLY | O_NOCTTY | O_CLOEXEC);
+ ASSERT_GE(fd_pidfd_mnt, 0);
+
+ ASSERT_GE(fstat(fd_tree, &self->st2), 0);
+ ASSERT_EQ(ioctl(fd_pidfd_mnt, FS_IOC_GETVERSION, &self->gen2), 0);
+
+ ASSERT_TRUE(self->st1.st_dev == self->st2.st_dev && self->st1.st_ino == self->st2.st_ino);
+ ASSERT_TRUE(self->gen1 == self->gen2);
+
+ ASSERT_EQ(close(fd_tree), 0);
+ ASSERT_EQ(close(fd_pidfd_mnt), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/pidfd/pidfd_file_handle_test.c b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c
new file mode 100644
index 000000000000..439b9c6c0457
--- /dev/null
+++ b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c
@@ -0,0 +1,503 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/types.h>
+#include <poll.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <linux/kcmp.h>
+#include <sys/stat.h>
+
+#include "pidfd.h"
+#include "../kselftest_harness.h"
+
+FIXTURE(file_handle)
+{
+ pid_t pid;
+ int pidfd;
+
+ pid_t child_pid1;
+ int child_pidfd1;
+
+ pid_t child_pid2;
+ int child_pidfd2;
+
+ pid_t child_pid3;
+ int child_pidfd3;
+};
+
+FIXTURE_SETUP(file_handle)
+{
+ int ret;
+ int ipc_sockets[2];
+ char c;
+
+ self->pid = getpid();
+ self->pidfd = sys_pidfd_open(self->pid, 0);
+ ASSERT_GE(self->pidfd, 0);
+
+ ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ EXPECT_EQ(ret, 0);
+
+ self->child_pid1 = create_child(&self->child_pidfd1, CLONE_NEWUSER);
+ EXPECT_GE(self->child_pid1, 0);
+
+ if (self->child_pid1 == 0) {
+ close(ipc_sockets[0]);
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+ _exit(EXIT_FAILURE);
+
+ close(ipc_sockets[1]);
+
+ pause();
+ _exit(EXIT_SUCCESS);
+ }
+
+ close(ipc_sockets[1]);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ close(ipc_sockets[0]);
+
+ ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ EXPECT_EQ(ret, 0);
+
+ self->child_pid2 = create_child(&self->child_pidfd2, CLONE_NEWUSER | CLONE_NEWPID);
+ EXPECT_GE(self->child_pid2, 0);
+
+ if (self->child_pid2 == 0) {
+ close(ipc_sockets[0]);
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+ _exit(EXIT_FAILURE);
+
+ close(ipc_sockets[1]);
+
+ pause();
+ _exit(EXIT_SUCCESS);
+ }
+
+ close(ipc_sockets[1]);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ close(ipc_sockets[0]);
+
+ ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+ EXPECT_EQ(ret, 0);
+
+ self->child_pid3 = create_child(&self->child_pidfd3, CLONE_NEWUSER | CLONE_NEWPID);
+ EXPECT_GE(self->child_pid3, 0);
+
+ if (self->child_pid3 == 0) {
+ close(ipc_sockets[0]);
+
+ if (write_nointr(ipc_sockets[1], "1", 1) < 0)
+ _exit(EXIT_FAILURE);
+
+ close(ipc_sockets[1]);
+
+ pause();
+ _exit(EXIT_SUCCESS);
+ }
+
+ close(ipc_sockets[1]);
+ ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+ close(ipc_sockets[0]);
+}
+
+FIXTURE_TEARDOWN(file_handle)
+{
+ EXPECT_EQ(close(self->pidfd), 0);
+
+ EXPECT_EQ(sys_pidfd_send_signal(self->child_pidfd1, SIGKILL, NULL, 0), 0);
+ if (self->child_pidfd1 >= 0)
+ EXPECT_EQ(0, close(self->child_pidfd1));
+
+ EXPECT_EQ(sys_waitid(P_PID, self->child_pid1, NULL, WEXITED), 0);
+
+ EXPECT_EQ(sys_pidfd_send_signal(self->child_pidfd2, SIGKILL, NULL, 0), 0);
+ if (self->child_pidfd2 >= 0)
+ EXPECT_EQ(0, close(self->child_pidfd2));
+
+ EXPECT_EQ(sys_waitid(P_PID, self->child_pid2, NULL, WEXITED), 0);
+
+ if (self->child_pidfd3 >= 0) {
+ EXPECT_EQ(sys_pidfd_send_signal(self->child_pidfd3, SIGKILL, NULL, 0), 0);
+ EXPECT_EQ(0, close(self->child_pidfd3));
+ EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED), 0);
+ }
+}
+
+/*
+ * Test that we can decode a pidfs file handle in the same pid
+ * namespace.
+ */
+TEST_F(file_handle, file_handle_same_pidns)
+{
+ int mnt_id;
+ struct file_handle *fh;
+ int pidfd = -EBADF;
+ struct stat st1, st2;
+
+ fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(fh, NULL);
+ memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ fh->handle_bytes = MAX_HANDLE_SZ;
+
+ ASSERT_EQ(name_to_handle_at(self->child_pidfd1, "", fh, &mnt_id, AT_EMPTY_PATH), 0);
+
+ ASSERT_EQ(fstat(self->child_pidfd1, &st1), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, 0);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_EQ(fstat(pidfd, &st2), 0);
+ ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino);
+
+ ASSERT_EQ(close(pidfd), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, O_CLOEXEC);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_EQ(fstat(pidfd, &st2), 0);
+ ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino);
+
+ ASSERT_EQ(close(pidfd), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, O_NONBLOCK);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_EQ(fstat(pidfd, &st2), 0);
+ ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino);
+
+ ASSERT_EQ(close(pidfd), 0);
+
+ free(fh);
+}
+
+/*
+ * Test that we can decode a pidfs file handle from a child pid
+ * namespace.
+ */
+TEST_F(file_handle, file_handle_child_pidns)
+{
+ int mnt_id;
+ struct file_handle *fh;
+ int pidfd = -EBADF;
+ struct stat st1, st2;
+
+ fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(fh, NULL);
+ memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ fh->handle_bytes = MAX_HANDLE_SZ;
+
+ ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH), 0);
+
+ ASSERT_EQ(fstat(self->child_pidfd2, &st1), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, 0);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_EQ(fstat(pidfd, &st2), 0);
+ ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino);
+
+ ASSERT_EQ(close(pidfd), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, O_CLOEXEC);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_EQ(fstat(pidfd, &st2), 0);
+ ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino);
+
+ ASSERT_EQ(close(pidfd), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, O_NONBLOCK);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_EQ(fstat(pidfd, &st2), 0);
+ ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino);
+
+ ASSERT_EQ(close(pidfd), 0);
+
+ free(fh);
+}
+
+/*
+ * Test that we fail to decode a pidfs file handle from an ancestor
+ * child pid namespace.
+ */
+TEST_F(file_handle, file_handle_foreign_pidns)
+{
+ int mnt_id;
+ struct file_handle *fh;
+ pid_t pid;
+
+ fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(fh, NULL);
+ memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ fh->handle_bytes = MAX_HANDLE_SZ;
+
+ ASSERT_EQ(name_to_handle_at(self->pidfd, "", fh, &mnt_id, AT_EMPTY_PATH), 0);
+
+ ASSERT_EQ(setns(self->child_pidfd2, CLONE_NEWUSER | CLONE_NEWPID), 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ int pidfd = open_by_handle_at(self->pidfd, fh, 0);
+ if (pidfd >= 0) {
+ TH_LOG("Managed to open pidfd outside of the caller's pid namespace hierarchy");
+ _exit(1);
+ }
+ _exit(0);
+ }
+
+ ASSERT_EQ(wait_for_pid(pid), 0);
+
+ free(fh);
+}
+
+/*
+ * Test that we can decode a pidfs file handle of a process that has
+ * exited but not been reaped.
+ */
+TEST_F(file_handle, pid_has_exited)
+{
+ int mnt_id, pidfd, child_pidfd3;
+ struct file_handle *fh;
+ struct stat st1, st2;
+
+ fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(fh, NULL);
+ memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ fh->handle_bytes = MAX_HANDLE_SZ;
+
+ ASSERT_EQ(name_to_handle_at(self->child_pidfd3, "", fh, &mnt_id, AT_EMPTY_PATH), 0);
+
+ ASSERT_EQ(fstat(self->child_pidfd3, &st1), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, 0);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_EQ(fstat(pidfd, &st2), 0);
+ ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino);
+
+ ASSERT_EQ(close(pidfd), 0);
+
+ child_pidfd3 = self->child_pidfd3;
+ self->child_pidfd3 = -EBADF;
+ EXPECT_EQ(sys_pidfd_send_signal(child_pidfd3, SIGKILL, NULL, 0), 0);
+ EXPECT_EQ(close(child_pidfd3), 0);
+ EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED | WNOWAIT), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, 0);
+ ASSERT_GE(pidfd, 0);
+
+ EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED), 0);
+}
+
+/*
+ * Test that we fail to decode a pidfs file handle of a process that has
+ * already been reaped.
+ */
+TEST_F(file_handle, pid_has_been_reaped)
+{
+ int mnt_id, pidfd, child_pidfd3;
+ struct file_handle *fh;
+ struct stat st1, st2;
+
+ fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(fh, NULL);
+ memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ fh->handle_bytes = MAX_HANDLE_SZ;
+
+ ASSERT_EQ(name_to_handle_at(self->child_pidfd3, "", fh, &mnt_id, AT_EMPTY_PATH), 0);
+
+ ASSERT_EQ(fstat(self->child_pidfd3, &st1), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, 0);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_EQ(fstat(pidfd, &st2), 0);
+ ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino);
+
+ ASSERT_EQ(close(pidfd), 0);
+
+ child_pidfd3 = self->child_pidfd3;
+ self->child_pidfd3 = -EBADF;
+ EXPECT_EQ(sys_pidfd_send_signal(child_pidfd3, SIGKILL, NULL, 0), 0);
+ EXPECT_EQ(close(child_pidfd3), 0);
+ EXPECT_EQ(sys_waitid(P_PID, self->child_pid3, NULL, WEXITED), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, 0);
+ ASSERT_LT(pidfd, 0);
+}
+
+/*
+ * Test valid flags to open a pidfd file handle. Note, that
+ * PIDFD_NONBLOCK is defined as O_NONBLOCK and O_NONBLOCK is an alias to
+ * O_NDELAY. Also note that PIDFD_THREAD is an alias for O_EXCL.
+ */
+TEST_F(file_handle, open_by_handle_at_valid_flags)
+{
+ int mnt_id;
+ struct file_handle *fh;
+ int pidfd = -EBADF;
+ struct stat st1, st2;
+
+ fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(fh, NULL);
+ memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ fh->handle_bytes = MAX_HANDLE_SZ;
+
+ ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH), 0);
+
+ ASSERT_EQ(fstat(self->child_pidfd2, &st1), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh,
+ O_RDONLY |
+ O_WRONLY |
+ O_RDWR |
+ O_NONBLOCK |
+ O_NDELAY |
+ O_CLOEXEC |
+ O_EXCL);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_EQ(fstat(pidfd, &st2), 0);
+ ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino);
+
+ ASSERT_EQ(close(pidfd), 0);
+}
+
+/*
+ * Test that invalid flags passed to open a pidfd file handle are
+ * rejected.
+ */
+TEST_F(file_handle, open_by_handle_at_invalid_flags)
+{
+ int mnt_id;
+ struct file_handle *fh;
+ int pidfd = -EBADF;
+ static const struct invalid_pidfs_file_handle_flags {
+ int oflag;
+ const char *oflag_name;
+ } invalid_pidfs_file_handle_flags[] = {
+ { FASYNC, "FASYNC" },
+ { O_CREAT, "O_CREAT" },
+ { O_NOCTTY, "O_NOCTTY" },
+ { O_CREAT, "O_CREAT" },
+ { O_TRUNC, "O_TRUNC" },
+ { O_APPEND, "O_APPEND" },
+ { O_SYNC, "O_SYNC" },
+ { O_DSYNC, "O_DSYNC" },
+ { O_DIRECT, "O_DIRECT" },
+ { O_DIRECTORY, "O_DIRECTORY" },
+ { O_NOFOLLOW, "O_NOFOLLOW" },
+ { O_NOATIME, "O_NOATIME" },
+ { O_PATH, "O_PATH" },
+ { O_TMPFILE, "O_TMPFILE" },
+ /*
+ * O_LARGEFILE is added implicitly by
+ * open_by_handle_at() so pidfs simply masks it off.
+ */
+ };
+
+ fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(fh, NULL);
+ memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ fh->handle_bytes = MAX_HANDLE_SZ;
+
+ ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH), 0);
+
+ for (int i = 0; i < ARRAY_SIZE(invalid_pidfs_file_handle_flags); i++) {
+ pidfd = open_by_handle_at(self->pidfd, fh, invalid_pidfs_file_handle_flags[i].oflag);
+ ASSERT_LT(pidfd, 0) {
+ TH_LOG("open_by_handle_at() succeeded with invalid flags: %s", invalid_pidfs_file_handle_flags[i].oflag_name);
+ }
+ }
+}
+
+/* Test that lookup fails. */
+TEST_F(file_handle, lookup_must_fail)
+{
+ int mnt_id;
+ struct file_handle *fh;
+
+ fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(fh, NULL);
+ memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ fh->handle_bytes = MAX_HANDLE_SZ;
+
+ ASSERT_NE(name_to_handle_at(self->child_pidfd2, "lookup-is-not-possible-with-pidfs", fh, &mnt_id, AT_EMPTY_PATH), 0);
+ ASSERT_EQ(errno, ENOTDIR);
+ ASSERT_NE(name_to_handle_at(self->child_pidfd2, "lookup-is-not-possible-with-pidfs", fh, &mnt_id, 0), 0);
+ ASSERT_EQ(errno, ENOTDIR);
+}
+
+#ifndef AT_HANDLE_CONNECTABLE
+#define AT_HANDLE_CONNECTABLE 0x002
+#endif
+
+/*
+ * Test that AT_HANDLE_CONNECTABLE is rejected. Connectable file handles
+ * don't make sense for pidfs. Note that currently AT_HANDLE_CONNECTABLE
+ * is rejected because it is incompatible with AT_EMPTY_PATH which is
+ * required with pidfds as we don't support lookup.
+ */
+TEST_F(file_handle, invalid_name_to_handle_at_flags)
+{
+ int mnt_id;
+ struct file_handle *fh;
+
+ fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(fh, NULL);
+ memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ fh->handle_bytes = MAX_HANDLE_SZ;
+
+ ASSERT_NE(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH | AT_HANDLE_CONNECTABLE), 0);
+}
+
+#ifndef AT_HANDLE_FID
+#define AT_HANDLE_FID 0x200
+#endif
+
+/*
+ * Test that a request with AT_HANDLE_FID always leads to decodable file
+ * handle as pidfs always provides export operations.
+ */
+TEST_F(file_handle, valid_name_to_handle_at_flags)
+{
+ int mnt_id, pidfd;
+ struct file_handle *fh;
+ struct stat st1, st2;
+
+ fh = malloc(sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ ASSERT_NE(fh, NULL);
+ memset(fh, 0, sizeof(struct file_handle) + MAX_HANDLE_SZ);
+ fh->handle_bytes = MAX_HANDLE_SZ;
+
+ ASSERT_EQ(name_to_handle_at(self->child_pidfd2, "", fh, &mnt_id, AT_EMPTY_PATH | AT_HANDLE_FID), 0);
+
+ ASSERT_EQ(fstat(self->child_pidfd2, &st1), 0);
+
+ pidfd = open_by_handle_at(self->pidfd, fh, 0);
+ ASSERT_GE(pidfd, 0);
+
+ ASSERT_EQ(fstat(pidfd, &st2), 0);
+ ASSERT_TRUE(st1.st_dev == st2.st_dev && st1.st_ino == st2.st_ino);
+
+ ASSERT_EQ(close(pidfd), 0);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c
index 7c2a4349170a..222f8131283b 100644
--- a/tools/testing/selftests/pidfd/pidfd_setns_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c
@@ -19,7 +19,6 @@
#include <linux/ioctl.h>
#include "pidfd.h"
-#include "../clone3/clone3_selftests.h"
#include "../kselftest_harness.h"
#ifndef PIDFS_IOCTL_MAGIC
@@ -118,22 +117,6 @@ FIXTURE(current_nsset)
int child_pidfd_derived_nsfds2[PIDFD_NS_MAX];
};
-static int sys_waitid(int which, pid_t pid, int options)
-{
- return syscall(__NR_waitid, which, pid, NULL, options, NULL);
-}
-
-pid_t create_child(int *pidfd, unsigned flags)
-{
- struct __clone_args args = {
- .flags = CLONE_PIDFD | flags,
- .exit_signal = SIGCHLD,
- .pidfd = ptr_to_u64(pidfd),
- };
-
- return sys_clone3(&args, sizeof(struct clone_args));
-}
-
static bool switch_timens(void)
{
int fd, ret;
@@ -150,28 +133,6 @@ static bool switch_timens(void)
return ret == 0;
}
-static ssize_t read_nointr(int fd, void *buf, size_t count)
-{
- ssize_t ret;
-
- do {
- ret = read(fd, buf, count);
- } while (ret < 0 && errno == EINTR);
-
- return ret;
-}
-
-static ssize_t write_nointr(int fd, const void *buf, size_t count)
-{
- ssize_t ret;
-
- do {
- ret = write(fd, buf, count);
- } while (ret < 0 && errno == EINTR);
-
- return ret;
-}
-
FIXTURE_SETUP(current_nsset)
{
int i, proc_fd, ret;
@@ -229,7 +190,7 @@ FIXTURE_SETUP(current_nsset)
_exit(EXIT_SUCCESS);
}
- ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, WEXITED | WNOWAIT), 0);
+ ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, NULL, WEXITED | WNOWAIT), 0);
self->pidfd = sys_pidfd_open(self->pid, 0);
EXPECT_GE(self->pidfd, 0) {
@@ -432,9 +393,9 @@ FIXTURE_TEARDOWN(current_nsset)
EXPECT_EQ(0, close(self->child_pidfd1));
if (self->child_pidfd2 >= 0)
EXPECT_EQ(0, close(self->child_pidfd2));
- ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, WEXITED), 0);
- ASSERT_EQ(sys_waitid(P_PID, self->child_pid1, WEXITED), 0);
- ASSERT_EQ(sys_waitid(P_PID, self->child_pid2, WEXITED), 0);
+ ASSERT_EQ(sys_waitid(P_PID, self->child_pid_exited, NULL, WEXITED), 0);
+ ASSERT_EQ(sys_waitid(P_PID, self->child_pid1, NULL, WEXITED), 0);
+ ASSERT_EQ(sys_waitid(P_PID, self->child_pid2, NULL, WEXITED), 0);
}
static int preserve_ns(const int pid, const char *ns)
diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c
index 0dcb8365ddc3..1e2d49751cde 100644
--- a/tools/testing/selftests/pidfd/pidfd_wait.c
+++ b/tools/testing/selftests/pidfd/pidfd_wait.c
@@ -26,22 +26,11 @@
#define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__)
#endif
-static pid_t sys_clone3(struct clone_args *args)
-{
- return syscall(__NR_clone3, args, sizeof(struct clone_args));
-}
-
-static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options,
- struct rusage *ru)
-{
- return syscall(__NR_waitid, which, pid, info, options, ru);
-}
-
TEST(wait_simple)
{
int pidfd = -1;
pid_t parent_tid = -1;
- struct clone_args args = {
+ struct __clone_args args = {
.parent_tid = ptr_to_u64(&parent_tid),
.pidfd = ptr_to_u64(&pidfd),
.flags = CLONE_PIDFD | CLONE_PARENT_SETTID,
@@ -55,7 +44,7 @@ TEST(wait_simple)
pidfd = open("/proc/self", O_DIRECTORY | O_RDONLY | O_CLOEXEC);
ASSERT_GE(pidfd, 0);
- pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+ pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED);
ASSERT_NE(pid, 0);
EXPECT_EQ(close(pidfd), 0);
pidfd = -1;
@@ -63,18 +52,18 @@ TEST(wait_simple)
pidfd = open("/dev/null", O_RDONLY | O_CLOEXEC);
ASSERT_GE(pidfd, 0);
- pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+ pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED);
ASSERT_NE(pid, 0);
EXPECT_EQ(close(pidfd), 0);
pidfd = -1;
- pid = sys_clone3(&args);
+ pid = sys_clone3(&args, sizeof(args));
ASSERT_GE(pid, 0);
if (pid == 0)
exit(EXIT_SUCCESS);
- pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+ pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED);
ASSERT_GE(pid, 0);
ASSERT_EQ(WIFEXITED(info.si_status), true);
ASSERT_EQ(WEXITSTATUS(info.si_status), 0);
@@ -89,7 +78,7 @@ TEST(wait_states)
{
int pidfd = -1;
pid_t parent_tid = -1;
- struct clone_args args = {
+ struct __clone_args args = {
.parent_tid = ptr_to_u64(&parent_tid),
.pidfd = ptr_to_u64(&pidfd),
.flags = CLONE_PIDFD | CLONE_PARENT_SETTID,
@@ -102,7 +91,7 @@ TEST(wait_states)
};
ASSERT_EQ(pipe(pfd), 0);
- pid = sys_clone3(&args);
+ pid = sys_clone3(&args, sizeof(args));
ASSERT_GE(pid, 0);
if (pid == 0) {
@@ -117,28 +106,28 @@ TEST(wait_states)
}
close(pfd[0]);
- ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0);
+ ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED), 0);
ASSERT_EQ(info.si_signo, SIGCHLD);
ASSERT_EQ(info.si_code, CLD_STOPPED);
ASSERT_EQ(info.si_pid, parent_tid);
ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0);
- ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL), 0);
+ ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED), 0);
ASSERT_EQ(write(pfd[1], "C", 1), 1);
close(pfd[1]);
ASSERT_EQ(info.si_signo, SIGCHLD);
ASSERT_EQ(info.si_code, CLD_CONTINUED);
ASSERT_EQ(info.si_pid, parent_tid);
- ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WUNTRACED, NULL), 0);
+ ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WUNTRACED), 0);
ASSERT_EQ(info.si_signo, SIGCHLD);
ASSERT_EQ(info.si_code, CLD_STOPPED);
ASSERT_EQ(info.si_pid, parent_tid);
ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0), 0);
- ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL), 0);
+ ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED), 0);
ASSERT_EQ(info.si_signo, SIGCHLD);
ASSERT_EQ(info.si_code, CLD_KILLED);
ASSERT_EQ(info.si_pid, parent_tid);
@@ -151,7 +140,7 @@ TEST(wait_nonblock)
int pidfd;
unsigned int flags = 0;
pid_t parent_tid = -1;
- struct clone_args args = {
+ struct __clone_args args = {
.parent_tid = ptr_to_u64(&parent_tid),
.flags = CLONE_PARENT_SETTID,
.exit_signal = SIGCHLD,
@@ -173,12 +162,12 @@ TEST(wait_nonblock)
SKIP(return, "Skipping PIDFD_NONBLOCK test");
}
- ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+ ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED);
ASSERT_LT(ret, 0);
ASSERT_EQ(errno, ECHILD);
EXPECT_EQ(close(pidfd), 0);
- pid = sys_clone3(&args);
+ pid = sys_clone3(&args, sizeof(args));
ASSERT_GE(pid, 0);
if (pid == 0) {
@@ -201,7 +190,7 @@ TEST(wait_nonblock)
* Callers need to see EAGAIN/EWOULDBLOCK with non-blocking pidfd when
* child processes exist but none have exited.
*/
- ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+ ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED);
ASSERT_LT(ret, 0);
ASSERT_EQ(errno, EAGAIN);
@@ -210,19 +199,19 @@ TEST(wait_nonblock)
* WNOHANG raised explicitly when child processes exist but none have
* exited.
*/
- ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED | WNOHANG, NULL);
+ ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED | WNOHANG);
ASSERT_EQ(ret, 0);
ASSERT_EQ(fcntl(pidfd, F_SETFL, (flags & ~O_NONBLOCK)), 0);
- ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0);
+ ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED), 0);
ASSERT_EQ(info.si_signo, SIGCHLD);
ASSERT_EQ(info.si_code, CLD_STOPPED);
ASSERT_EQ(info.si_pid, parent_tid);
ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0);
- ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL), 0);
+ ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED), 0);
ASSERT_EQ(info.si_signo, SIGCHLD);
ASSERT_EQ(info.si_code, CLD_EXITED);
ASSERT_EQ(info.si_pid, parent_tid);
diff --git a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c
index 580fcac0a09f..b71ef8a493ed 100644
--- a/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c
+++ b/tools/testing/selftests/powerpc/benchmarks/gettimeofday.c
@@ -20,7 +20,7 @@ static int test_gettimeofday(void)
gettimeofday(&tv_end, NULL);
}
- timersub(&tv_start, &tv_end, &tv_diff);
+ timersub(&tv_end, &tv_start, &tv_diff);
printf("time = %.6f\n", tv_diff.tv_sec + (tv_diff.tv_usec) * 1e-6);
diff --git a/tools/testing/selftests/powerpc/include/pkeys.h b/tools/testing/selftests/powerpc/include/pkeys.h
index 51729d9a7111..3a0129467de6 100644
--- a/tools/testing/selftests/powerpc/include/pkeys.h
+++ b/tools/testing/selftests/powerpc/include/pkeys.h
@@ -35,10 +35,18 @@
#define __NR_pkey_alloc 384
#define __NR_pkey_free 385
+#ifndef NT_PPC_PKEY
+#define NT_PPC_PKEY 0x110
+#endif
+
#define PKEY_BITS_PER_PKEY 2
#define NR_PKEYS 32
#define PKEY_BITS_MASK ((1UL << PKEY_BITS_PER_PKEY) - 1)
+#define AMR_BITS_PER_PKEY 2
+#define PKEY_REG_BITS (sizeof(u64) * 8)
+#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY))
+
inline unsigned long pkeyreg_get(void)
{
return mfspr(SPRN_AMR);
diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c
index f6da4cb30cd6..f061434af452 100644
--- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c
@@ -16,26 +16,7 @@
#include <unistd.h>
#include "ptrace.h"
#include "child.h"
-
-#ifndef __NR_pkey_alloc
-#define __NR_pkey_alloc 384
-#endif
-
-#ifndef __NR_pkey_free
-#define __NR_pkey_free 385
-#endif
-
-#ifndef NT_PPC_PKEY
-#define NT_PPC_PKEY 0x110
-#endif
-
-#ifndef PKEY_DISABLE_EXECUTE
-#define PKEY_DISABLE_EXECUTE 0x4
-#endif
-
-#define AMR_BITS_PER_PKEY 2
-#define PKEY_REG_BITS (sizeof(u64) * 8)
-#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY))
+#include "pkeys.h"
#define CORE_FILE_LIMIT (5 * 1024 * 1024) /* 5 MB should be enough */
@@ -61,16 +42,6 @@ struct shared_info {
time_t core_time;
};
-static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights)
-{
- return syscall(__NR_pkey_alloc, flags, init_access_rights);
-}
-
-static int sys_pkey_free(int pkey)
-{
- return syscall(__NR_pkey_free, pkey);
-}
-
static int increase_core_file_limit(void)
{
struct rlimit rlim;
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
index d89474377f11..fc633014424f 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
@@ -7,26 +7,7 @@
*/
#include "ptrace.h"
#include "child.h"
-
-#ifndef __NR_pkey_alloc
-#define __NR_pkey_alloc 384
-#endif
-
-#ifndef __NR_pkey_free
-#define __NR_pkey_free 385
-#endif
-
-#ifndef NT_PPC_PKEY
-#define NT_PPC_PKEY 0x110
-#endif
-
-#ifndef PKEY_DISABLE_EXECUTE
-#define PKEY_DISABLE_EXECUTE 0x4
-#endif
-
-#define AMR_BITS_PER_PKEY 2
-#define PKEY_REG_BITS (sizeof(u64) * 8)
-#define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey + 1) * AMR_BITS_PER_PKEY))
+#include "pkeys.h"
static const char user_read[] = "[User Read (Running)]";
static const char user_write[] = "[User Write (Running)]";
@@ -61,11 +42,6 @@ struct shared_info {
unsigned long invalid_uamor;
};
-static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights)
-{
- return syscall(__NR_pkey_alloc, flags, init_access_rights);
-}
-
static int child(struct shared_info *info)
{
unsigned long reg;
diff --git a/tools/testing/selftests/powerpc/vphn/test-vphn.c b/tools/testing/selftests/powerpc/vphn/test-vphn.c
index 81d3069ffb84..f348f54914a9 100644
--- a/tools/testing/selftests/powerpc/vphn/test-vphn.c
+++ b/tools/testing/selftests/powerpc/vphn/test-vphn.c
@@ -275,7 +275,7 @@ static struct test {
}
},
{
- /* Parse a 32-bit value split accross two consecutives 64-bit
+ /* Parse a 32-bit value split across two consecutives 64-bit
* input values.
*/
"vphn: 16-bit value followed by 2 x 32-bit values",
diff --git a/tools/testing/selftests/riscv/abi/pointer_masking.c b/tools/testing/selftests/riscv/abi/pointer_masking.c
index dee41b7ee3e3..059d2e87eb1f 100644
--- a/tools/testing/selftests/riscv/abi/pointer_masking.c
+++ b/tools/testing/selftests/riscv/abi/pointer_masking.c
@@ -185,8 +185,20 @@ static void test_fork_exec(void)
}
}
+static bool pwrite_wrapper(int fd, void *buf, size_t count, const char *msg)
+{
+ int ret = pwrite(fd, buf, count, 0);
+
+ if (ret != count) {
+ ksft_perror(msg);
+ return false;
+ }
+ return true;
+}
+
static void test_tagged_addr_abi_sysctl(void)
{
+ char *err_pwrite_msg = "failed to write to /proc/sys/abi/tagged_addr_disabled\n";
char value;
int fd;
@@ -200,14 +212,18 @@ static void test_tagged_addr_abi_sysctl(void)
}
value = '1';
- pwrite(fd, &value, 1, 0);
- ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL,
- "sysctl disabled\n");
+ if (!pwrite_wrapper(fd, &value, 1, "write '1'"))
+ ksft_test_result_fail(err_pwrite_msg);
+ else
+ ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL,
+ "sysctl disabled\n");
value = '0';
- pwrite(fd, &value, 1, 0);
- ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0,
- "sysctl enabled\n");
+ if (!pwrite_wrapper(fd, &value, 1, "write '0'"))
+ ksft_test_result_fail(err_pwrite_msg);
+ else
+ ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0,
+ "sysctl enabled\n");
set_tagged_addr_ctrl(0, false);
diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
index 1dd94197da30..6174ffe016dc 100644
--- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
+++ b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
@@ -25,6 +25,8 @@ int main(void)
unsigned long vl;
char *datap, *tmp;
+ ksft_set_plan(1);
+
datap = malloc(MAX_VSIZE);
if (!datap) {
ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE);
@@ -63,6 +65,8 @@ int main(void)
}
free(datap);
+
+ ksft_test_result_pass("tests for v_initval_nolibc pass\n");
ksft_exit_pass();
return 0;
}
diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c
index 895177f6bf4c..40b3bffcbb40 100644
--- a/tools/testing/selftests/riscv/vector/vstate_prctl.c
+++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c
@@ -76,6 +76,8 @@ int main(void)
long flag, expected;
long rc;
+ ksft_set_plan(1);
+
pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0;
rc = riscv_hwprobe(&pair, 1, 0, NULL, 0);
if (rc < 0) {
diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
index 37d9bf6fb745..6f4c3f5a1c5d 100644
--- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
+++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
@@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p,
* If we dispatch to a bogus DSQ that will fall back to the
* builtin global DSQ, we fail gracefully.
*/
- scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL,
+ scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL,
p->scx.dsq_vtime, 0);
return cpu;
}
diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
index dffc97d9cdf1..e4a55027778f 100644
--- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
+++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
@@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p,
if (cpu >= 0) {
/* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */
- scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,
- p->scx.dsq_vtime, 0);
+ scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,
+ p->scx.dsq_vtime, 0);
return cpu;
}
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
index 6a7db1502c29..fbda6bf54671 100644
--- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
+++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
@@ -43,9 +43,12 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev)
if (!p)
return;
- target = bpf_get_prandom_u32() % nr_cpus;
+ if (p->nr_cpus_allowed == nr_cpus)
+ target = bpf_get_prandom_u32() % nr_cpus;
+ else
+ target = scx_bpf_task_cpu(p);
- scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
+ scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
bpf_task_release(p);
}
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c
index 472851b56854..0ff27e57fe43 100644
--- a/tools/testing/selftests/sched_ext/dsp_local_on.c
+++ b/tools/testing/selftests/sched_ext/dsp_local_on.c
@@ -34,9 +34,10 @@ static enum scx_test_status run(void *ctx)
/* Just sleeping is fine, plenty of scheduling events happening */
sleep(1);
- SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
bpf_link__destroy(link);
+ SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG));
+
return SCX_TEST_PASS;
}
@@ -50,7 +51,7 @@ static void cleanup(void *ctx)
struct scx_test dsp_local_on = {
.name = "dsp_local_on",
.description = "Verify we can directly dispatch tasks to a local DSQs "
- "from osp.dispatch()",
+ "from ops.dispatch()",
.setup = setup,
.run = run,
.cleanup = cleanup,
diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
index 1efb50d61040..a7cf868d5e31 100644
--- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
+++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
@@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p,
/* Can only call from ops.select_cpu() */
scx_bpf_select_cpu_dfl(p, 0, 0, &found);
- scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+ scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
}
SEC(".struct_ops.link")
diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c
index d75d4faf07f6..4bc36182d3ff 100644
--- a/tools/testing/selftests/sched_ext/exit.bpf.c
+++ b/tools/testing/selftests/sched_ext/exit.bpf.c
@@ -33,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags)
if (exit_point == EXIT_ENQUEUE)
EXIT_CLEANLY();
- scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
+ scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
}
void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
@@ -41,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
if (exit_point == EXIT_DISPATCH)
EXIT_CLEANLY();
- scx_bpf_consume(DSQ_ID);
+ scx_bpf_dsq_move_to_local(DSQ_ID);
}
void BPF_STRUCT_OPS(exit_enable, struct task_struct *p)
diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c
index 4d4cd8d966db..430f5e13bf55 100644
--- a/tools/testing/selftests/sched_ext/maximal.bpf.c
+++ b/tools/testing/selftests/sched_ext/maximal.bpf.c
@@ -12,6 +12,8 @@
char _license[] SEC("license") = "GPL";
+#define DSQ_ID 0
+
s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
u64 wake_flags)
{
@@ -20,7 +22,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags)
{
- scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+ scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
}
void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
@@ -28,7 +30,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev)
{
- scx_bpf_consume(SCX_DSQ_GLOBAL);
+ scx_bpf_dsq_move_to_local(DSQ_ID);
}
void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags)
@@ -123,7 +125,7 @@ void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight)
s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init)
{
- return 0;
+ return scx_bpf_create_dsq(DSQ_ID, -1);
}
void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
index f171ac470970..13d0f5be788d 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
@@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p,
}
scx_bpf_put_idle_cpumask(idle_mask);
- scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+ scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
}
SEC(".struct_ops.link")
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
index 9efdbb7da928..815f1d5d61ac 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
@@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p,
saw_local = true;
}
- scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags);
+ scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags);
}
s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task,
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
index 59bfc4f36167..4bb99699e920 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
@@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p,
cpu = prev_cpu;
dispatch:
- scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0);
+ scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0);
return cpu;
}
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
index 3bbd5fcdfb18..2a75de11b2cf 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
@@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p
s32 prev_cpu, u64 wake_flags)
{
/* Dispatching to a random DSQ should fail. */
- scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0);
+ scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0);
return prev_cpu;
}
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
index 0fda57fe0ecf..99d075695c97 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
@@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p
s32 prev_cpu, u64 wake_flags)
{
/* Dispatching twice in a row is disallowed. */
- scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
- scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+ scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+ scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
return prev_cpu;
}
diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
index e6c67bcf5e6e..bfcb96cd4954 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
@@ -2,8 +2,8 @@
/*
* A scheduler that validates that enqueue flags are properly stored and
* applied at dispatch time when a task is directly dispatched from
- * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and
- * making the test a very basic vtime scheduler.
+ * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(),
+ * and making the test a very basic vtime scheduler.
*
* Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
* Copyright (c) 2024 David Vernet <dvernet@meta.com>
@@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p,
cpu = prev_cpu;
scx_bpf_test_and_clear_cpu_idle(cpu);
ddsp:
- scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0);
+ scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0);
return cpu;
}
void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p)
{
- if (scx_bpf_consume(VTIME_DSQ))
+ if (scx_bpf_dsq_move_to_local(VTIME_DSQ))
consumed = true;
}
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
index 996448afe31b..91d120548bf5 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
@@ -78,10 +78,10 @@
"setup": [
"$TC qdisc add dev $DEV1 ingress"
],
- "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0xff",
+ "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0x1f",
"expExitCode": "0",
"verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 1 flow",
- "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 255 baseclass",
+ "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 31 baseclass",
"matchCount": "1",
"teardown": [
"$TC qdisc del dev $DEV1 ingress"
diff --git a/tools/testing/shared/linux/maple_tree.h b/tools/testing/shared/linux/maple_tree.h
index 06c89bdcc515..f67d47d32857 100644
--- a/tools/testing/shared/linux/maple_tree.h
+++ b/tools/testing/shared/linux/maple_tree.h
@@ -2,6 +2,6 @@
#define atomic_t int32_t
#define atomic_inc(x) uatomic_inc(x)
#define atomic_read(x) uatomic_read(x)
-#define atomic_set(x, y) do {} while (0)
+#define atomic_set(x, y) uatomic_set(x, y)
#define U8_MAX UCHAR_MAX
#include "../../../../include/linux/maple_tree.h"
diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h
index e01f66f98982..3e1b6adc027b 100644
--- a/tools/testing/vma/linux/atomic.h
+++ b/tools/testing/vma/linux/atomic.h
@@ -6,7 +6,7 @@
#define atomic_t int32_t
#define atomic_inc(x) uatomic_inc(x)
#define atomic_read(x) uatomic_read(x)
-#define atomic_set(x, y) do {} while (0)
+#define atomic_set(x, y) uatomic_set(x, y)
#define U8_MAX UCHAR_MAX
#endif /* _LINUX_ATOMIC_H */
diff --git a/tools/testing/vsock/control.c b/tools/testing/vsock/control.c
index d2deb4b15b94..0066e0324d35 100644
--- a/tools/testing/vsock/control.c
+++ b/tools/testing/vsock/control.c
@@ -27,6 +27,7 @@
#include "timeout.h"
#include "control.h"
+#include "util.h"
static int control_fd = -1;
@@ -50,7 +51,6 @@ void control_init(const char *control_host,
for (ai = result; ai; ai = ai->ai_next) {
int fd;
- int val = 1;
fd = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol);
if (fd < 0)
@@ -65,11 +65,8 @@ void control_init(const char *control_host,
break;
}
- if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR,
- &val, sizeof(val)) < 0) {
- perror("setsockopt");
- exit(EXIT_FAILURE);
- }
+ setsockopt_int_check(fd, SOL_SOCKET, SO_REUSEADDR, 1,
+ "setsockopt SO_REUSEADDR");
if (bind(fd, ai->ai_addr, ai->ai_addrlen) < 0)
goto next;
diff --git a/tools/testing/vsock/msg_zerocopy_common.c b/tools/testing/vsock/msg_zerocopy_common.c
index 5a4bdf7b5132..8622e5a0f8b7 100644
--- a/tools/testing/vsock/msg_zerocopy_common.c
+++ b/tools/testing/vsock/msg_zerocopy_common.c
@@ -14,16 +14,6 @@
#include "msg_zerocopy_common.h"
-void enable_so_zerocopy(int fd)
-{
- int val = 1;
-
- if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val))) {
- perror("setsockopt");
- exit(EXIT_FAILURE);
- }
-}
-
void vsock_recv_completion(int fd, const bool *zerocopied)
{
struct sock_extended_err *serr;
diff --git a/tools/testing/vsock/msg_zerocopy_common.h b/tools/testing/vsock/msg_zerocopy_common.h
index 3763c5ccedb9..ad14139e93ca 100644
--- a/tools/testing/vsock/msg_zerocopy_common.h
+++ b/tools/testing/vsock/msg_zerocopy_common.h
@@ -12,7 +12,6 @@
#define VSOCK_RECVERR 1
#endif
-void enable_so_zerocopy(int fd);
void vsock_recv_completion(int fd, const bool *zerocopied);
#endif /* MSG_ZEROCOPY_COMMON_H */
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index a3d448a075e3..34e9dac0a105 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -651,3 +651,145 @@ void free_test_iovec(const struct iovec *test_iovec,
free(iovec);
}
+
+/* Set "unsigned long long" socket option and check that it's indeed set */
+void setsockopt_ull_check(int fd, int level, int optname,
+ unsigned long long val, char const *errmsg)
+{
+ unsigned long long chkval;
+ socklen_t chklen;
+ int err;
+
+ err = setsockopt(fd, level, optname, &val, sizeof(val));
+ if (err) {
+ fprintf(stderr, "setsockopt err: %s (%d)\n",
+ strerror(errno), errno);
+ goto fail;
+ }
+
+ chkval = ~val; /* just make storage != val */
+ chklen = sizeof(chkval);
+
+ err = getsockopt(fd, level, optname, &chkval, &chklen);
+ if (err) {
+ fprintf(stderr, "getsockopt err: %s (%d)\n",
+ strerror(errno), errno);
+ goto fail;
+ }
+
+ if (chklen != sizeof(chkval)) {
+ fprintf(stderr, "size mismatch: set %zu got %d\n", sizeof(val),
+ chklen);
+ goto fail;
+ }
+
+ if (chkval != val) {
+ fprintf(stderr, "value mismatch: set %llu got %llu\n", val,
+ chkval);
+ goto fail;
+ }
+ return;
+fail:
+ fprintf(stderr, "%s val %llu\n", errmsg, val);
+ exit(EXIT_FAILURE);
+;
+}
+
+/* Set "int" socket option and check that it's indeed set */
+void setsockopt_int_check(int fd, int level, int optname, int val,
+ char const *errmsg)
+{
+ int chkval;
+ socklen_t chklen;
+ int err;
+
+ err = setsockopt(fd, level, optname, &val, sizeof(val));
+ if (err) {
+ fprintf(stderr, "setsockopt err: %s (%d)\n",
+ strerror(errno), errno);
+ goto fail;
+ }
+
+ chkval = ~val; /* just make storage != val */
+ chklen = sizeof(chkval);
+
+ err = getsockopt(fd, level, optname, &chkval, &chklen);
+ if (err) {
+ fprintf(stderr, "getsockopt err: %s (%d)\n",
+ strerror(errno), errno);
+ goto fail;
+ }
+
+ if (chklen != sizeof(chkval)) {
+ fprintf(stderr, "size mismatch: set %zu got %d\n", sizeof(val),
+ chklen);
+ goto fail;
+ }
+
+ if (chkval != val) {
+ fprintf(stderr, "value mismatch: set %d got %d\n", val, chkval);
+ goto fail;
+ }
+ return;
+fail:
+ fprintf(stderr, "%s val %d\n", errmsg, val);
+ exit(EXIT_FAILURE);
+}
+
+static void mem_invert(unsigned char *mem, size_t size)
+{
+ size_t i;
+
+ for (i = 0; i < size; i++)
+ mem[i] = ~mem[i];
+}
+
+/* Set "timeval" socket option and check that it's indeed set */
+void setsockopt_timeval_check(int fd, int level, int optname,
+ struct timeval val, char const *errmsg)
+{
+ struct timeval chkval;
+ socklen_t chklen;
+ int err;
+
+ err = setsockopt(fd, level, optname, &val, sizeof(val));
+ if (err) {
+ fprintf(stderr, "setsockopt err: %s (%d)\n",
+ strerror(errno), errno);
+ goto fail;
+ }
+
+ /* just make storage != val */
+ chkval = val;
+ mem_invert((unsigned char *)&chkval, sizeof(chkval));
+ chklen = sizeof(chkval);
+
+ err = getsockopt(fd, level, optname, &chkval, &chklen);
+ if (err) {
+ fprintf(stderr, "getsockopt err: %s (%d)\n",
+ strerror(errno), errno);
+ goto fail;
+ }
+
+ if (chklen != sizeof(chkval)) {
+ fprintf(stderr, "size mismatch: set %zu got %d\n", sizeof(val),
+ chklen);
+ goto fail;
+ }
+
+ if (memcmp(&chkval, &val, sizeof(val)) != 0) {
+ fprintf(stderr, "value mismatch: set %ld:%ld got %ld:%ld\n",
+ val.tv_sec, val.tv_usec, chkval.tv_sec, chkval.tv_usec);
+ goto fail;
+ }
+ return;
+fail:
+ fprintf(stderr, "%s val %ld:%ld\n", errmsg, val.tv_sec, val.tv_usec);
+ exit(EXIT_FAILURE);
+}
+
+void enable_so_zerocopy_check(int fd)
+{
+ setsockopt_int_check(fd, SOL_SOCKET, SO_ZEROCOPY, 1,
+ "setsockopt SO_ZEROCOPY");
+}
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index fff22d4a14c0..ba84d296d8b7 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -68,4 +68,11 @@ unsigned long iovec_hash_djb2(const struct iovec *iov, size_t iovnum);
struct iovec *alloc_test_iovec(const struct iovec *test_iovec, int iovnum);
void free_test_iovec(const struct iovec *test_iovec,
struct iovec *iovec, int iovnum);
+void setsockopt_ull_check(int fd, int level, int optname,
+ unsigned long long val, char const *errmsg);
+void setsockopt_int_check(int fd, int level, int optname, int val,
+ char const *errmsg);
+void setsockopt_timeval_check(int fd, int level, int optname,
+ struct timeval val, char const *errmsg);
+void enable_so_zerocopy_check(int fd);
#endif /* UTIL_H */
diff --git a/tools/testing/vsock/vsock_perf.c b/tools/testing/vsock/vsock_perf.c
index 4e8578f815e0..75971ac708c9 100644
--- a/tools/testing/vsock/vsock_perf.c
+++ b/tools/testing/vsock/vsock_perf.c
@@ -33,7 +33,7 @@
static unsigned int port = DEFAULT_PORT;
static unsigned long buf_size_bytes = DEFAULT_BUF_SIZE_BYTES;
-static unsigned long vsock_buf_bytes = DEFAULT_VSOCK_BUF_BYTES;
+static unsigned long long vsock_buf_bytes = DEFAULT_VSOCK_BUF_BYTES;
static bool zerocopy;
static void error(const char *s)
@@ -133,7 +133,7 @@ static float get_gbps(unsigned long bits, time_t ns_delta)
((float)ns_delta / NSEC_PER_SEC);
}
-static void run_receiver(unsigned long rcvlowat_bytes)
+static void run_receiver(int rcvlowat_bytes)
{
unsigned int read_cnt;
time_t rx_begin_ns;
@@ -162,8 +162,8 @@ static void run_receiver(unsigned long rcvlowat_bytes)
printf("Run as receiver\n");
printf("Listen port %u\n", port);
printf("RX buffer %lu bytes\n", buf_size_bytes);
- printf("vsock buffer %lu bytes\n", vsock_buf_bytes);
- printf("SO_RCVLOWAT %lu bytes\n", rcvlowat_bytes);
+ printf("vsock buffer %llu bytes\n", vsock_buf_bytes);
+ printf("SO_RCVLOWAT %d bytes\n", rcvlowat_bytes);
fd = socket(AF_VSOCK, SOCK_STREAM, 0);
@@ -251,6 +251,16 @@ static void run_receiver(unsigned long rcvlowat_bytes)
close(fd);
}
+static void enable_so_zerocopy(int fd)
+{
+ int val = 1;
+
+ if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val))) {
+ perror("setsockopt");
+ exit(EXIT_FAILURE);
+ }
+}
+
static void run_sender(int peer_cid, unsigned long to_send_bytes)
{
time_t tx_begin_ns;
@@ -439,7 +449,7 @@ static long strtolx(const char *arg)
int main(int argc, char **argv)
{
unsigned long to_send_bytes = DEFAULT_TO_SEND_BYTES;
- unsigned long rcvlowat_bytes = DEFAULT_RCVLOWAT_BYTES;
+ int rcvlowat_bytes = DEFAULT_RCVLOWAT_BYTES;
int peer_cid = -1;
bool sender = false;
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 8d38dbf8f41f..48f17641ca50 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -429,7 +429,7 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
static void test_seqpacket_msg_bounds_server(const struct test_opts *opts)
{
- unsigned long sock_buf_size;
+ unsigned long long sock_buf_size;
unsigned long remote_hash;
unsigned long curr_hash;
int fd;
@@ -444,17 +444,13 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts)
sock_buf_size = SOCK_BUF_SIZE;
- if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE,
- &sock_buf_size, sizeof(sock_buf_size))) {
- perror("setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)");
- exit(EXIT_FAILURE);
- }
+ setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_MAX_SIZE,
+ sock_buf_size,
+ "setsockopt(SO_VM_SOCKETS_BUFFER_MAX_SIZE)");
- if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE,
- &sock_buf_size, sizeof(sock_buf_size))) {
- perror("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)");
- exit(EXIT_FAILURE);
- }
+ setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE,
+ sock_buf_size,
+ "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)");
/* Ready to receive data. */
control_writeln("SRVREADY");
@@ -586,10 +582,8 @@ static void test_seqpacket_timeout_client(const struct test_opts *opts)
tv.tv_sec = RCVTIMEO_TIMEOUT_SEC;
tv.tv_usec = 0;
- if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, (void *)&tv, sizeof(tv)) == -1) {
- perror("setsockopt(SO_RCVTIMEO)");
- exit(EXIT_FAILURE);
- }
+ setsockopt_timeval_check(fd, SOL_SOCKET, SO_RCVTIMEO, tv,
+ "setsockopt(SO_RCVTIMEO)");
read_enter_ns = current_nsec();
@@ -634,7 +628,8 @@ static void test_seqpacket_timeout_server(const struct test_opts *opts)
static void test_seqpacket_bigmsg_client(const struct test_opts *opts)
{
- unsigned long sock_buf_size;
+ unsigned long long sock_buf_size;
+ size_t buf_size;
socklen_t len;
void *data;
int fd;
@@ -655,13 +650,20 @@ static void test_seqpacket_bigmsg_client(const struct test_opts *opts)
sock_buf_size++;
- data = malloc(sock_buf_size);
+ /* size_t can be < unsigned long long */
+ buf_size = (size_t)sock_buf_size;
+ if (buf_size != sock_buf_size) {
+ fprintf(stderr, "Returned BUFFER_SIZE too large\n");
+ exit(EXIT_FAILURE);
+ }
+
+ data = malloc(buf_size);
if (!data) {
perror("malloc");
exit(EXIT_FAILURE);
}
- send_buf(fd, data, sock_buf_size, 0, -EMSGSIZE);
+ send_buf(fd, data, buf_size, 0, -EMSGSIZE);
control_writeln("CLISENT");
@@ -835,7 +837,7 @@ static void test_stream_poll_rcvlowat_server(const struct test_opts *opts)
static void test_stream_poll_rcvlowat_client(const struct test_opts *opts)
{
- unsigned long lowat_val = RCVLOWAT_BUF_SIZE;
+ int lowat_val = RCVLOWAT_BUF_SIZE;
char buf[RCVLOWAT_BUF_SIZE];
struct pollfd fds;
short poll_flags;
@@ -847,11 +849,8 @@ static void test_stream_poll_rcvlowat_client(const struct test_opts *opts)
exit(EXIT_FAILURE);
}
- if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT,
- &lowat_val, sizeof(lowat_val))) {
- perror("setsockopt(SO_RCVLOWAT)");
- exit(EXIT_FAILURE);
- }
+ setsockopt_int_check(fd, SOL_SOCKET, SO_RCVLOWAT,
+ lowat_val, "setsockopt(SO_RCVLOWAT)");
control_expectln("SRVSENT");
@@ -1357,9 +1356,10 @@ static void test_stream_rcvlowat_def_cred_upd_client(const struct test_opts *opt
static void test_stream_credit_update_test(const struct test_opts *opts,
bool low_rx_bytes_test)
{
- size_t recv_buf_size;
+ int recv_buf_size;
struct pollfd fds;
size_t buf_size;
+ unsigned long long sock_buf_size;
void *buf;
int fd;
@@ -1371,11 +1371,12 @@ static void test_stream_credit_update_test(const struct test_opts *opts,
buf_size = RCVLOWAT_CREDIT_UPD_BUF_SIZE;
- if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE,
- &buf_size, sizeof(buf_size))) {
- perror("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)");
- exit(EXIT_FAILURE);
- }
+ /* size_t can be < unsigned long long */
+ sock_buf_size = buf_size;
+
+ setsockopt_ull_check(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE,
+ sock_buf_size,
+ "setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)");
if (low_rx_bytes_test) {
/* Set new SO_RCVLOWAT here. This enables sending credit
@@ -1384,11 +1385,8 @@ static void test_stream_credit_update_test(const struct test_opts *opts,
*/
recv_buf_size = 1 + VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;
- if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT,
- &recv_buf_size, sizeof(recv_buf_size))) {
- perror("setsockopt(SO_RCVLOWAT)");
- exit(EXIT_FAILURE);
- }
+ setsockopt_int_check(fd, SOL_SOCKET, SO_RCVLOWAT,
+ recv_buf_size, "setsockopt(SO_RCVLOWAT)");
}
/* Send one dummy byte here, because 'setsockopt()' above also
@@ -1430,11 +1428,8 @@ static void test_stream_credit_update_test(const struct test_opts *opts,
recv_buf_size++;
/* Updating SO_RCVLOWAT will send credit update. */
- if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT,
- &recv_buf_size, sizeof(recv_buf_size))) {
- perror("setsockopt(SO_RCVLOWAT)");
- exit(EXIT_FAILURE);
- }
+ setsockopt_int_check(fd, SOL_SOCKET, SO_RCVLOWAT,
+ recv_buf_size, "setsockopt(SO_RCVLOWAT)");
}
fds.fd = fd;
diff --git a/tools/testing/vsock/vsock_test_zerocopy.c b/tools/testing/vsock/vsock_test_zerocopy.c
index 04c376b6937f..9d9a6cb9614a 100644
--- a/tools/testing/vsock/vsock_test_zerocopy.c
+++ b/tools/testing/vsock/vsock_test_zerocopy.c
@@ -162,7 +162,7 @@ static void test_client(const struct test_opts *opts,
}
if (test_data->so_zerocopy)
- enable_so_zerocopy(fd);
+ enable_so_zerocopy_check(fd);
iovec = alloc_test_iovec(test_data->vecs, test_data->vecs_cnt);
diff --git a/tools/testing/vsock/vsock_uring_test.c b/tools/testing/vsock/vsock_uring_test.c
index 6c3e6f70c457..5c3078969659 100644
--- a/tools/testing/vsock/vsock_uring_test.c
+++ b/tools/testing/vsock/vsock_uring_test.c
@@ -73,7 +73,7 @@ static void vsock_io_uring_client(const struct test_opts *opts,
}
if (msg_zerocopy)
- enable_so_zerocopy(fd);
+ enable_so_zerocopy_check(fd);
iovec = alloc_test_iovec(test_data->vecs, test_data->vecs_cnt);
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 8b66387e5f35..4403cc4eba30 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -282,6 +282,21 @@ static void timerlat_hist_header(struct osnoise_tool *tool)
}
/*
+ * format_summary_value - format a line of summary value (min, max or avg)
+ * of hist data
+ */
+static void format_summary_value(struct trace_seq *seq,
+ int count,
+ unsigned long long val,
+ bool avg)
+{
+ if (count)
+ trace_seq_printf(seq, "%9llu ", avg ? val / count : val);
+ else
+ trace_seq_printf(seq, "%9c ", '-');
+}
+
+/*
* timerlat_print_summary - print the summary of the hist data to the output
*/
static void
@@ -328,29 +343,23 @@ timerlat_print_summary(struct timerlat_hist_params *params,
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
- if (!params->no_irq) {
- if (data->hist[cpu].irq_count)
- trace_seq_printf(trace->seq, "%9llu ",
- data->hist[cpu].min_irq);
- else
- trace_seq_printf(trace->seq, " - ");
- }
+ if (!params->no_irq)
+ format_summary_value(trace->seq,
+ data->hist[cpu].irq_count,
+ data->hist[cpu].min_irq,
+ false);
- if (!params->no_thread) {
- if (data->hist[cpu].thread_count)
- trace_seq_printf(trace->seq, "%9llu ",
- data->hist[cpu].min_thread);
- else
- trace_seq_printf(trace->seq, " - ");
- }
+ if (!params->no_thread)
+ format_summary_value(trace->seq,
+ data->hist[cpu].thread_count,
+ data->hist[cpu].min_thread,
+ false);
- if (params->user_hist) {
- if (data->hist[cpu].user_count)
- trace_seq_printf(trace->seq, "%9llu ",
- data->hist[cpu].min_user);
- else
- trace_seq_printf(trace->seq, " - ");
- }
+ if (params->user_hist)
+ format_summary_value(trace->seq,
+ data->hist[cpu].user_count,
+ data->hist[cpu].min_user,
+ false);
}
trace_seq_printf(trace->seq, "\n");
@@ -364,29 +373,23 @@ timerlat_print_summary(struct timerlat_hist_params *params,
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
- if (!params->no_irq) {
- if (data->hist[cpu].irq_count)
- trace_seq_printf(trace->seq, "%9llu ",
- data->hist[cpu].sum_irq / data->hist[cpu].irq_count);
- else
- trace_seq_printf(trace->seq, " - ");
- }
+ if (!params->no_irq)
+ format_summary_value(trace->seq,
+ data->hist[cpu].irq_count,
+ data->hist[cpu].sum_irq,
+ true);
- if (!params->no_thread) {
- if (data->hist[cpu].thread_count)
- trace_seq_printf(trace->seq, "%9llu ",
- data->hist[cpu].sum_thread / data->hist[cpu].thread_count);
- else
- trace_seq_printf(trace->seq, " - ");
- }
+ if (!params->no_thread)
+ format_summary_value(trace->seq,
+ data->hist[cpu].thread_count,
+ data->hist[cpu].sum_thread,
+ true);
- if (params->user_hist) {
- if (data->hist[cpu].user_count)
- trace_seq_printf(trace->seq, "%9llu ",
- data->hist[cpu].sum_user / data->hist[cpu].user_count);
- else
- trace_seq_printf(trace->seq, " - ");
- }
+ if (params->user_hist)
+ format_summary_value(trace->seq,
+ data->hist[cpu].user_count,
+ data->hist[cpu].sum_user,
+ true);
}
trace_seq_printf(trace->seq, "\n");
@@ -400,29 +403,23 @@ timerlat_print_summary(struct timerlat_hist_params *params,
if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
continue;
- if (!params->no_irq) {
- if (data->hist[cpu].irq_count)
- trace_seq_printf(trace->seq, "%9llu ",
- data->hist[cpu].max_irq);
- else
- trace_seq_printf(trace->seq, " - ");
- }
+ if (!params->no_irq)
+ format_summary_value(trace->seq,
+ data->hist[cpu].irq_count,
+ data->hist[cpu].max_irq,
+ false);
- if (!params->no_thread) {
- if (data->hist[cpu].thread_count)
- trace_seq_printf(trace->seq, "%9llu ",
- data->hist[cpu].max_thread);
- else
- trace_seq_printf(trace->seq, " - ");
- }
+ if (!params->no_thread)
+ format_summary_value(trace->seq,
+ data->hist[cpu].thread_count,
+ data->hist[cpu].max_thread,
+ false);
- if (params->user_hist) {
- if (data->hist[cpu].user_count)
- trace_seq_printf(trace->seq, "%9llu ",
- data->hist[cpu].max_user);
- else
- trace_seq_printf(trace->seq, " - ");
- }
+ if (params->user_hist)
+ format_summary_value(trace->seq,
+ data->hist[cpu].user_count,
+ data->hist[cpu].max_user,
+ false);
}
trace_seq_printf(trace->seq, "\n");
trace_seq_do_printf(trace->seq);
@@ -506,16 +503,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params,
trace_seq_printf(trace->seq, "min: ");
if (!params->no_irq)
- trace_seq_printf(trace->seq, "%9llu ",
- sum.min_irq);
+ format_summary_value(trace->seq,
+ sum.irq_count,
+ sum.min_irq,
+ false);
if (!params->no_thread)
- trace_seq_printf(trace->seq, "%9llu ",
- sum.min_thread);
+ format_summary_value(trace->seq,
+ sum.thread_count,
+ sum.min_thread,
+ false);
if (params->user_hist)
- trace_seq_printf(trace->seq, "%9llu ",
- sum.min_user);
+ format_summary_value(trace->seq,
+ sum.user_count,
+ sum.min_user,
+ false);
trace_seq_printf(trace->seq, "\n");
@@ -523,16 +526,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params,
trace_seq_printf(trace->seq, "avg: ");
if (!params->no_irq)
- trace_seq_printf(trace->seq, "%9llu ",
- sum.sum_irq / sum.irq_count);
+ format_summary_value(trace->seq,
+ sum.irq_count,
+ sum.sum_irq,
+ true);
if (!params->no_thread)
- trace_seq_printf(trace->seq, "%9llu ",
- sum.sum_thread / sum.thread_count);
+ format_summary_value(trace->seq,
+ sum.thread_count,
+ sum.sum_thread,
+ true);
if (params->user_hist)
- trace_seq_printf(trace->seq, "%9llu ",
- sum.sum_user / sum.user_count);
+ format_summary_value(trace->seq,
+ sum.user_count,
+ sum.sum_user,
+ true);
trace_seq_printf(trace->seq, "\n");
@@ -540,16 +549,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params,
trace_seq_printf(trace->seq, "max: ");
if (!params->no_irq)
- trace_seq_printf(trace->seq, "%9llu ",
- sum.max_irq);
+ format_summary_value(trace->seq,
+ sum.irq_count,
+ sum.max_irq,
+ false);
if (!params->no_thread)
- trace_seq_printf(trace->seq, "%9llu ",
- sum.max_thread);
+ format_summary_value(trace->seq,
+ sum.thread_count,
+ sum.max_thread,
+ false);
if (params->user_hist)
- trace_seq_printf(trace->seq, "%9llu ",
- sum.max_user);
+ format_summary_value(trace->seq,
+ sum.user_count,
+ sum.max_user,
+ false);
trace_seq_printf(trace->seq, "\n");
trace_seq_do_printf(trace->seq);