summaryrefslogtreecommitdiff
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rw-r--r--tools/testing/crypto/chacha20-s390/test-cipher.c4
-rw-r--r--tools/testing/cxl/Kbuild4
-rw-r--r--tools/testing/cxl/test/cxl.c32
-rw-r--r--tools/testing/cxl/test/mem.c217
-rw-r--r--tools/testing/kunit/configs/all_tests.config2
-rw-r--r--tools/testing/kunit/kunit_parser.py4
-rwxr-xr-xtools/testing/kunit/kunit_tool_test.py4
-rw-r--r--tools/testing/kunit/qemu_configs/sh.py4
-rw-r--r--tools/testing/memblock/internal.h6
-rw-r--r--tools/testing/memblock/linux/mutex.h14
-rw-r--r--tools/testing/radix-tree/Makefile1
-rw-r--r--tools/testing/rbtree/Makefile33
-rw-r--r--tools/testing/rbtree/interval_tree_test.c58
-rw-r--r--tools/testing/rbtree/rbtree_test.c48
-rw-r--r--tools/testing/rbtree/test.h4
-rw-r--r--tools/testing/selftests/.gitignore1
-rw-r--r--tools/testing/selftests/Makefile1
-rw-r--r--tools/testing/selftests/bpf/DENYLIST.aarch649
-rw-r--r--tools/testing/selftests/bpf/Makefile28
-rw-r--r--tools/testing/selftests/bpf/bpf_arena_spin_lock.h533
-rw-r--r--tools/testing/selftests/bpf/bpf_atomic.h140
-rw-r--r--tools/testing/selftests/bpf/bpf_experimental.h15
-rw-r--r--tools/testing/selftests/bpf/bpf_kfuncs.h5
-rw-r--r--tools/testing/selftests/bpf/cap_helpers.c8
-rw-r--r--tools/testing/selftests/bpf/cap_helpers.h1
-rw-r--r--tools/testing/selftests/bpf/config.x86_641
-rw-r--r--tools/testing/selftests/bpf/network_helpers.c111
-rw-r--r--tools/testing/selftests/bpf/network_helpers.h21
-rw-r--r--tools/testing/selftests/bpf/prog_tests/align.c11
-rw-r--r--tools/testing/selftests/bpf/prog_tests/arena_atomics.c66
-rw-r--r--tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c108
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c5
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_iter.c68
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_nf.c9
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf.c23
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_dump.c147
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c128
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c13
-rw-r--r--tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c107
-rw-r--r--tools/testing/selftests/bpf/prog_tests/compute_live_registers.c9
-rw-r--r--tools/testing/selftests/bpf/prog_tests/core_reloc.c6
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cpumask.c5
-rw-r--r--tools/testing/selftests/bpf/prog_tests/dynptr.c21
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fd_array.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c9
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c162
-rw-r--r--tools/testing/selftests/bpf/prog_tests/kernel_flag.c43
-rw-r--r--tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c540
-rw-r--r--tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c176
-rw-r--r--tools/testing/selftests/bpf/prog_tests/netns_cookie.c21
-rw-r--r--tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c47
-rw-r--r--tools/testing/selftests/bpf/prog_tests/prepare.c99
-rw-r--r--tools/testing/selftests/bpf/prog_tests/pro_epilogue.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c3
-rw-r--r--tools/testing/selftests/bpf/prog_tests/read_vsyscall.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/res_spin_lock.c101
-rw-r--r--tools/testing/selftests/bpf/prog_tests/setget_sockopt.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/spin_lock.c3
-rw-r--r--tools/testing/selftests/bpf/prog_tests/summarization.c144
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tailcalls.c1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tc_links.c28
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tc_opts.c40
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c16
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_tunnel.c633
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_veristat.c139
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c638
-rw-r--r--tools/testing/selftests/bpf/prog_tests/token.c97
-rw-r--r--tools/testing/selftests/bpf/prog_tests/usdt.c11
-rw-r--r--tools/testing/selftests/bpf/prog_tests/verifier.c8
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_vlan.c175
-rw-r--r--tools/testing/selftests/bpf/progs/arena_atomics.c121
-rw-r--r--tools/testing/selftests/bpf/progs/arena_spin_lock.c51
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_tasks.c110
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_misc.h22
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_tracing_net.h4
-rw-r--r--tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c3
-rw-r--r--tools/testing/selftests/bpf/progs/cgroup_preorder.c41
-rw-r--r--tools/testing/selftests/bpf/progs/changes_pkt_data.c39
-rw-r--r--tools/testing/selftests/bpf/progs/compute_live_registers.c424
-rw-r--r--tools/testing/selftests/bpf/progs/connect4_dropper.c4
-rw-r--r--tools/testing/selftests/bpf/progs/core_reloc_types.h10
-rw-r--r--tools/testing/selftests/bpf/progs/cpumask_common.h1
-rw-r--r--tools/testing/selftests/bpf/progs/cpumask_failure.c38
-rw-r--r--tools/testing/selftests/bpf/progs/cpumask_success.c120
-rw-r--r--tools/testing/selftests/bpf/progs/dynptr_success.c123
-rw-r--r--tools/testing/selftests/bpf/progs/fexit_noreturns.c15
-rw-r--r--tools/testing/selftests/bpf/progs/irq.c124
-rw-r--r--tools/testing/selftests/bpf/progs/iters.c139
-rw-r--r--tools/testing/selftests/bpf/progs/netns_cookie_prog.c9
-rw-r--r--tools/testing/selftests/bpf/progs/preempt_lock.c68
-rw-r--r--tools/testing/selftests/bpf/progs/prepare.c28
-rw-r--r--tools/testing/selftests/bpf/progs/priv_freplace_prog.c13
-rw-r--r--tools/testing/selftests/bpf/progs/priv_prog.c6
-rw-r--r--tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c88
-rw-r--r--tools/testing/selftests/bpf/progs/profiler.inc.h2
-rw-r--r--tools/testing/selftests/bpf/progs/rcu_read_lock.c61
-rw-r--r--tools/testing/selftests/bpf/progs/read_vsyscall.c11
-rw-r--r--tools/testing/selftests/bpf/progs/res_spin_lock.c147
-rw-r--r--tools/testing/selftests/bpf/progs/res_spin_lock_fail.c244
-rw-r--r--tools/testing/selftests/bpf/progs/set_global_vars.c47
-rw-r--r--tools/testing/selftests/bpf/progs/strncmp_bench.c5
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c30
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c26
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c34
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c25
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c30
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_refcounted.c31
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c39
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c22
-rw-r--r--tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c36
-rw-r--r--tools/testing/selftests/bpf/progs/summarization.c78
-rw-r--r--tools/testing/selftests/bpf/progs/summarization_freplace.c (renamed from tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c)17
-rw-r--r--tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c4
-rw-r--r--tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c5
-rw-r--r--tools/testing/selftests/bpf/progs/test_get_xattr.c28
-rw-r--r--tools/testing/selftests/bpf/progs/test_kernel_flag.c28
-rw-r--r--tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c6
-rw-r--r--tools/testing/selftests/bpf/progs/test_lookup_key.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_module_attach.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_ptr_untrusted.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c1
-rw-r--r--tools/testing/selftests/bpf/progs/test_set_remove_xattr.c133
-rw-r--r--tools/testing/selftests/bpf/progs/test_spin_lock_fail.c69
-rw-r--r--tools/testing/selftests/bpf/progs/test_subprogs_extable.c6
-rw-r--r--tools/testing/selftests/bpf/progs/test_task_under_cgroup.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_usdt.c14
-rw-r--r--tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_vlan.c20
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c64
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_gotol.c6
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c6
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_load_acquire.c218
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_may_goto_1.c34
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_precision.c49
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_private_stack.c6
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_stack_ptr.c52
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_store_release.c286
-rw-r--r--tools/testing/selftests/bpf/progs/xdp_redirect_map.c88
-rw-r--r--tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c41
-rw-r--r--tools/testing/selftests/bpf/test_btf.h6
-rw-r--r--tools/testing/selftests/bpf/test_kmods/bpf_testmod.c108
-rw-r--r--tools/testing/selftests/bpf/test_kmods/bpf_testmod.h6
-rw-r--r--tools/testing/selftests/bpf/test_loader.c32
-rwxr-xr-xtools/testing/selftests/bpf/test_lwt_ip_encap.sh476
-rwxr-xr-xtools/testing/selftests/bpf/test_lwt_seg6local.sh156
-rw-r--r--tools/testing/selftests/bpf/test_maps.c9
-rw-r--r--tools/testing/selftests/bpf/test_progs.c72
-rw-r--r--tools/testing/selftests/bpf/test_progs.h8
-rwxr-xr-xtools/testing/selftests/bpf/test_tunnel.sh645
-rwxr-xr-xtools/testing/selftests/bpf/test_xdp_redirect_multi.sh214
-rwxr-xr-xtools/testing/selftests/bpf/test_xdp_vlan.sh233
-rwxr-xr-xtools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh9
-rwxr-xr-xtools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh9
-rw-r--r--tools/testing/selftests/bpf/veristat.c367
-rwxr-xr-xtools/testing/selftests/bpf/with_addr.sh54
-rwxr-xr-xtools/testing/selftests/bpf/with_tunnels.sh36
-rw-r--r--tools/testing/selftests/bpf/xdp_redirect_multi.c226
-rwxr-xr-xtools/testing/selftests/cgroup/test_cpuset_prs.sh617
-rw-r--r--tools/testing/selftests/clone3/clone3_selftests.h2
-rwxr-xr-xtools/testing/selftests/drivers/net/hds.py35
-rw-r--r--tools/testing/selftests/drivers/net/hw/.gitignore2
-rw-r--r--tools/testing/selftests/drivers/net/hw/Makefile5
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/csum.py2
-rw-r--r--tools/testing/selftests/drivers/net/hw/iou-zcrx.c457
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/iou-zcrx.py91
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/irq.py2
-rw-r--r--tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c13
-rw-r--r--tools/testing/selftests/drivers/net/lib/py/env.py21
-rwxr-xr-xtools/testing/selftests/drivers/net/ping.py15
-rwxr-xr-xtools/testing/selftests/drivers/net/queues.py4
-rw-r--r--tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc23
-rw-r--r--tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc20
-rw-r--r--tools/testing/selftests/ftrace/test.d/ftrace/fgraph-multi-filter.tc177
-rw-r--r--tools/testing/selftests/futex/functional/futex_wait_wouldblock.c2
-rw-r--r--tools/testing/selftests/hid/config.common1
-rw-r--r--tools/testing/selftests/iommu/iommufd.c365
-rw-r--r--tools/testing/selftests/iommu/iommufd_fail_nth.c59
-rw-r--r--tools/testing/selftests/iommu/iommufd_utils.h229
-rw-r--r--tools/testing/selftests/kvm/Makefile.kvm45
-rw-r--r--tools/testing/selftests/kvm/arm64/page_fault_test.c2
-rw-r--r--tools/testing/selftests/kvm/include/arm64/processor.h67
-rw-r--r--tools/testing/selftests/kvm/lib/arm64/processor.c60
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c5
-rw-r--r--tools/testing/selftests/kvm/riscv/get-reg-list.c8
-rw-r--r--tools/testing/selftests/kvm/rseq_test.c31
-rw-r--r--tools/testing/selftests/kvm/x86/monitor_mwait_test.c108
-rw-r--r--tools/testing/selftests/landlock/.gitignore1
-rw-r--r--tools/testing/selftests/landlock/Makefile6
-rw-r--r--tools/testing/selftests/landlock/audit.h479
-rw-r--r--tools/testing/selftests/landlock/audit_test.c671
-rw-r--r--tools/testing/selftests/landlock/base_test.c130
-rw-r--r--tools/testing/selftests/landlock/common.h20
-rw-r--r--tools/testing/selftests/landlock/config1
-rw-r--r--tools/testing/selftests/landlock/fs_test.c595
-rw-r--r--tools/testing/selftests/landlock/net_test.c132
-rw-r--r--tools/testing/selftests/landlock/ptrace_test.c140
-rw-r--r--tools/testing/selftests/landlock/scoped_abstract_unix_test.c111
-rw-r--r--tools/testing/selftests/landlock/scoped_signal_test.c108
-rw-r--r--tools/testing/selftests/landlock/wait-pipe-sandbox.c131
-rw-r--r--tools/testing/selftests/lib/config1
-rw-r--r--tools/testing/selftests/mincore/mincore_selftest.c19
-rw-r--r--tools/testing/selftests/mm/.gitignore2
-rw-r--r--tools/testing/selftests/mm/Makefile2
-rwxr-xr-xtools/testing/selftests/mm/charge_reserved_hugetlb.sh4
-rw-r--r--tools/testing/selftests/mm/cow.c4
-rw-r--r--tools/testing/selftests/mm/guard-regions.c (renamed from tools/testing/selftests/mm/guard-pages.c)968
-rw-r--r--tools/testing/selftests/mm/gup_longterm.c41
-rwxr-xr-xtools/testing/selftests/mm/hugetlb_reparenting_test.sh2
-rw-r--r--tools/testing/selftests/mm/map_populate.c5
-rw-r--r--tools/testing/selftests/mm/mlock-random-test.c4
-rw-r--r--tools/testing/selftests/mm/mlock2.h8
-rwxr-xr-xtools/testing/selftests/mm/run_vmtests.sh95
-rw-r--r--tools/testing/selftests/mm/split_huge_page_test.c106
-rw-r--r--tools/testing/selftests/mm/thuge-gen.c4
-rw-r--r--tools/testing/selftests/mm/uffd-common.c12
-rw-r--r--tools/testing/selftests/mm/uffd-common.h2
-rw-r--r--tools/testing/selftests/mm/uffd-stress.c42
-rw-r--r--tools/testing/selftests/mm/uffd-unit-tests.c7
-rw-r--r--tools/testing/selftests/mm/uffd-wp-mremap.c5
-rwxr-xr-xtools/testing/selftests/mm/va_high_addr_switch.sh28
-rw-r--r--tools/testing/selftests/mm/vm_util.h19
-rw-r--r--tools/testing/selftests/mseal_system_mappings/.gitignore2
-rw-r--r--tools/testing/selftests/mseal_system_mappings/Makefile6
-rw-r--r--tools/testing/selftests/mseal_system_mappings/config1
-rw-r--r--tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c119
-rw-r--r--tools/testing/selftests/net/.gitignore1
-rw-r--r--tools/testing/selftests/net/Makefile2
-rwxr-xr-xtools/testing/selftests/net/amt.sh20
-rwxr-xr-xtools/testing/selftests/net/fib_rule_tests.sh34
-rw-r--r--tools/testing/selftests/net/lib.sh25
-rw-r--r--tools/testing/selftests/net/mptcp/.gitignore1
-rwxr-xr-xtools/testing/selftests/net/mptcp/diag.sh5
-rw-r--r--tools/testing/selftests/net/mptcp/mptcp_connect.c11
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh18
-rwxr-xr-xtools/testing/selftests/net/netfilter/nft_concat_range.sh39
-rwxr-xr-xtools/testing/selftests/net/netns-name.sh13
-rwxr-xr-xtools/testing/selftests/net/rtnetlink.py4
-rw-r--r--tools/testing/selftests/net/skf_net_off.c244
-rwxr-xr-xtools/testing/selftests/net/skf_net_off.sh30
-rw-r--r--tools/testing/selftests/net/tcp_ao/self-connect.c3
-rw-r--r--tools/testing/selftests/net/tls.c36
-rwxr-xr-xtools/testing/selftests/net/udpgro_bench.sh2
-rwxr-xr-xtools/testing/selftests/net/udpgro_frglist.sh2
-rwxr-xr-xtools/testing/selftests/net/udpgro_fwd.sh2
-rwxr-xr-xtools/testing/selftests/net/veth.sh2
-rw-r--r--tools/testing/selftests/net/xdp_dummy.bpf.c13
-rw-r--r--tools/testing/selftests/pci_endpoint/pci_endpoint_test.c31
-rw-r--r--tools/testing/selftests/pcie_bwctrl/Makefile2
-rw-r--r--tools/testing/selftests/pidfd/pidfd.h8
-rw-r--r--tools/testing/selftests/riscv/hwprobe/cbo.c66
-rw-r--r--tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c10
-rw-r--r--tools/testing/selftests/rtc/.gitignore1
-rw-r--r--tools/testing/selftests/rtc/Makefile2
-rw-r--r--tools/testing/selftests/rtc/rtctest.c19
-rw-r--r--tools/testing/selftests/rtc/setdate.c77
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/nat.json14
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/infra/actions.json22
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json228
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json36
-rw-r--r--tools/testing/selftests/tpm2/.gitignore3
-rwxr-xr-xtools/testing/selftests/tpm2/test_smoke.sh2
-rw-r--r--tools/testing/selftests/ublk/Makefile14
-rw-r--r--tools/testing/selftests/ublk/fault_inject.c98
-rw-r--r--tools/testing/selftests/ublk/kublk.c351
-rw-r--r--tools/testing/selftests/ublk/kublk.h51
-rw-r--r--tools/testing/selftests/ublk/null.c11
-rw-r--r--tools/testing/selftests/ublk/stripe.c97
-rwxr-xr-xtools/testing/selftests/ublk/test_common.sh148
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_02.sh44
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_03.sh28
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_04.sh40
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_05.sh44
-rwxr-xr-xtools/testing/selftests/ublk/test_generic_06.sh41
-rwxr-xr-xtools/testing/selftests/ublk/test_loop_01.sh22
-rwxr-xr-xtools/testing/selftests/ublk/test_loop_02.sh8
-rwxr-xr-xtools/testing/selftests/ublk/test_loop_03.sh22
-rwxr-xr-xtools/testing/selftests/ublk/test_loop_04.sh9
-rwxr-xr-xtools/testing/selftests/ublk/test_loop_05.sh26
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_01.sh45
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_02.sh45
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_03.sh38
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_04.sh37
-rwxr-xr-xtools/testing/selftests/ublk/test_stress_05.sh64
-rwxr-xr-xtools/testing/selftests/ublk/test_stripe_01.sh26
-rwxr-xr-xtools/testing/selftests/ublk/test_stripe_02.sh13
-rwxr-xr-xtools/testing/selftests/ublk/test_stripe_03.sh26
-rwxr-xr-xtools/testing/selftests/ublk/test_stripe_04.sh21
-rw-r--r--tools/testing/selftests/x86/test_mremap_vdso.c43
-rw-r--r--tools/testing/shared/interval_tree-shim.c5
-rw-r--r--tools/testing/shared/linux.c4
-rw-r--r--tools/testing/shared/linux/cleanup.h2
-rw-r--r--tools/testing/shared/linux/interval_tree.h7
-rw-r--r--tools/testing/shared/linux/interval_tree_generic.h2
-rw-r--r--tools/testing/shared/linux/rbtree.h8
-rw-r--r--tools/testing/shared/linux/rbtree_augmented.h7
-rw-r--r--tools/testing/shared/linux/rbtree_types.h8
-rw-r--r--tools/testing/shared/rbtree-shim.c6
-rw-r--r--tools/testing/vma/linux/atomic.h5
-rw-r--r--tools/testing/vma/vma.c105
-rw-r--r--tools/testing/vma/vma_internal.h131
301 files changed, 16824 insertions, 3925 deletions
diff --git a/tools/testing/crypto/chacha20-s390/test-cipher.c b/tools/testing/crypto/chacha20-s390/test-cipher.c
index 8141d45df51a..35ea65c54ffa 100644
--- a/tools/testing/crypto/chacha20-s390/test-cipher.c
+++ b/tools/testing/crypto/chacha20-s390/test-cipher.c
@@ -66,7 +66,7 @@ static int test_lib_chacha(u8 *revert, u8 *cipher, u8 *plain)
}
/* Encrypt */
- chacha_init_arch(chacha_state, (u32*)key, iv);
+ chacha_init(chacha_state, (u32 *)key, iv);
start = ktime_get_ns();
chacha_crypt_arch(chacha_state, cipher, plain, data_size, 20);
@@ -81,7 +81,7 @@ static int test_lib_chacha(u8 *revert, u8 *cipher, u8 *plain)
pr_info("lib encryption took: %lld nsec", end - start);
/* Decrypt */
- chacha_init_arch(chacha_state, (u32 *)key, iv);
+ chacha_init(chacha_state, (u32 *)key, iv);
start = ktime_get_ns();
chacha_crypt_arch(chacha_state, revert, cipher, data_size, 20);
diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild
index b1256fee3567..387f3df8b988 100644
--- a/tools/testing/cxl/Kbuild
+++ b/tools/testing/cxl/Kbuild
@@ -61,8 +61,12 @@ cxl_core-y += $(CXL_CORE_SRC)/pci.o
cxl_core-y += $(CXL_CORE_SRC)/hdm.o
cxl_core-y += $(CXL_CORE_SRC)/pmu.o
cxl_core-y += $(CXL_CORE_SRC)/cdat.o
+cxl_core-y += $(CXL_CORE_SRC)/ras.o
+cxl_core-y += $(CXL_CORE_SRC)/acpi.o
cxl_core-$(CONFIG_TRACING) += $(CXL_CORE_SRC)/trace.o
cxl_core-$(CONFIG_CXL_REGION) += $(CXL_CORE_SRC)/region.o
+cxl_core-$(CONFIG_CXL_MCE) += $(CXL_CORE_SRC)/mce.o
+cxl_core-$(CONFIG_CXL_FEATURES) += $(CXL_CORE_SRC)/features.o
cxl_core-y += config_check.o
cxl_core-y += cxl_core_test.o
cxl_core-y += cxl_core_exports.o
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index cc8948f49117..1c3336095923 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -155,7 +155,7 @@ static struct {
} cfmws7;
struct {
struct acpi_cedt_cfmws cfmws;
- u32 target[4];
+ u32 target[3];
} cfmws8;
struct {
struct acpi_cedt_cxims cxims;
@@ -331,14 +331,14 @@ static struct {
.length = sizeof(mock_cedt.cfmws8),
},
.interleave_arithmetic = ACPI_CEDT_CFMWS_ARITHMETIC_XOR,
- .interleave_ways = 2,
- .granularity = 0,
+ .interleave_ways = 8,
+ .granularity = 1,
.restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
ACPI_CEDT_CFMWS_RESTRICT_PMEM,
.qtg_id = FAKE_QTG_ID,
- .window_size = SZ_256M * 16UL,
+ .window_size = SZ_512M * 6UL,
},
- .target = { 0, 1, 0, 1, },
+ .target = { 0, 1, 2, },
},
.cxims0 = {
.cxims = {
@@ -1000,25 +1000,21 @@ static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port)
find_cxl_root(port);
struct cxl_memdev *cxlmd = to_cxl_memdev(port->uport_dev);
struct cxl_dev_state *cxlds = cxlmd->cxlds;
- struct cxl_memdev_state *mds = to_cxl_memdev_state(cxlds);
struct access_coordinate ep_c[ACCESS_COORDINATE_MAX];
- struct range pmem_range = {
- .start = cxlds->pmem_res.start,
- .end = cxlds->pmem_res.end,
- };
- struct range ram_range = {
- .start = cxlds->ram_res.start,
- .end = cxlds->ram_res.end,
- };
if (!cxl_root)
return;
- if (range_len(&ram_range))
- dpa_perf_setup(port, &ram_range, &mds->ram_perf);
+ for (int i = 0; i < cxlds->nr_partitions; i++) {
+ struct resource *res = &cxlds->part[i].res;
+ struct cxl_dpa_perf *perf = &cxlds->part[i].perf;
+ struct range range = {
+ .start = res->start,
+ .end = res->end,
+ };
- if (range_len(&pmem_range))
- dpa_perf_setup(port, &pmem_range, &mds->pmem_perf);
+ dpa_perf_setup(port, &range, perf);
+ }
cxl_memdev_update_perf(cxlmd);
diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index 8d731bd63988..f2957a3e36fe 100644
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -45,6 +45,18 @@ static struct cxl_cel_entry mock_cel[] = {
.effect = CXL_CMD_EFFECT_NONE,
},
{
+ .opcode = cpu_to_le16(CXL_MBOX_OP_GET_SUPPORTED_FEATURES),
+ .effect = CXL_CMD_EFFECT_NONE,
+ },
+ {
+ .opcode = cpu_to_le16(CXL_MBOX_OP_GET_FEATURE),
+ .effect = CXL_CMD_EFFECT_NONE,
+ },
+ {
+ .opcode = cpu_to_le16(CXL_MBOX_OP_SET_FEATURE),
+ .effect = cpu_to_le16(EFFECT(CONF_CHANGE_IMMEDIATE)),
+ },
+ {
.opcode = cpu_to_le16(CXL_MBOX_OP_IDENTIFY),
.effect = CXL_CMD_EFFECT_NONE,
},
@@ -66,6 +78,10 @@ static struct cxl_cel_entry mock_cel[] = {
.effect = CXL_CMD_EFFECT_NONE,
},
{
+ .opcode = cpu_to_le16(CXL_MBOX_OP_SET_SHUTDOWN_STATE),
+ .effect = POLICY_CHANGE_IMMEDIATE,
+ },
+ {
.opcode = cpu_to_le16(CXL_MBOX_OP_GET_POISON),
.effect = CXL_CMD_EFFECT_NONE,
},
@@ -145,6 +161,10 @@ struct mock_event_store {
u32 ev_status;
};
+struct vendor_test_feat {
+ __le32 data;
+} __packed;
+
struct cxl_mockmem_data {
void *lsa;
void *fw;
@@ -161,6 +181,8 @@ struct cxl_mockmem_data {
u8 event_buf[SZ_4K];
u64 timestamp;
unsigned long sanitize_timeout;
+ struct vendor_test_feat test_feat;
+ u8 shutdown_state;
};
static struct mock_event_log *event_find_log(struct device *dev, int log_type)
@@ -1088,6 +1110,21 @@ static int mock_health_info(struct cxl_mbox_cmd *cmd)
return 0;
}
+static int mock_set_shutdown_state(struct cxl_mockmem_data *mdata,
+ struct cxl_mbox_cmd *cmd)
+{
+ struct cxl_mbox_set_shutdown_state_in *ss = cmd->payload_in;
+
+ if (cmd->size_in != sizeof(*ss))
+ return -EINVAL;
+
+ if (cmd->size_out != 0)
+ return -EINVAL;
+
+ mdata->shutdown_state = ss->state;
+ return 0;
+}
+
static struct mock_poison {
struct cxl_dev_state *cxlds;
u64 dpa;
@@ -1354,6 +1391,151 @@ static int mock_activate_fw(struct cxl_mockmem_data *mdata,
return -EINVAL;
}
+#define CXL_VENDOR_FEATURE_TEST \
+ UUID_INIT(0xffffffff, 0xffff, 0xffff, 0xff, 0xff, 0xff, 0xff, 0xff, \
+ 0xff, 0xff, 0xff)
+
+static void fill_feature_vendor_test(struct cxl_feat_entry *feat)
+{
+ feat->uuid = CXL_VENDOR_FEATURE_TEST;
+ feat->id = 0;
+ feat->get_feat_size = cpu_to_le16(0x4);
+ feat->set_feat_size = cpu_to_le16(0x4);
+ feat->flags = cpu_to_le32(CXL_FEATURE_F_CHANGEABLE |
+ CXL_FEATURE_F_DEFAULT_SEL |
+ CXL_FEATURE_F_SAVED_SEL);
+ feat->get_feat_ver = 1;
+ feat->set_feat_ver = 1;
+ feat->effects = cpu_to_le16(CXL_CMD_CONFIG_CHANGE_COLD_RESET |
+ CXL_CMD_EFFECTS_VALID);
+}
+
+#define MAX_CXL_TEST_FEATS 1
+
+static int mock_get_test_feature(struct cxl_mockmem_data *mdata,
+ struct cxl_mbox_cmd *cmd)
+{
+ struct vendor_test_feat *output = cmd->payload_out;
+ struct cxl_mbox_get_feat_in *input = cmd->payload_in;
+ u16 offset = le16_to_cpu(input->offset);
+ u16 count = le16_to_cpu(input->count);
+ u8 *ptr;
+
+ if (offset > sizeof(*output)) {
+ cmd->return_code = CXL_MBOX_CMD_RC_INPUT;
+ return -EINVAL;
+ }
+
+ if (offset + count > sizeof(*output)) {
+ cmd->return_code = CXL_MBOX_CMD_RC_INPUT;
+ return -EINVAL;
+ }
+
+ ptr = (u8 *)&mdata->test_feat + offset;
+ memcpy((u8 *)output + offset, ptr, count);
+
+ return 0;
+}
+
+static int mock_get_feature(struct cxl_mockmem_data *mdata,
+ struct cxl_mbox_cmd *cmd)
+{
+ struct cxl_mbox_get_feat_in *input = cmd->payload_in;
+
+ if (uuid_equal(&input->uuid, &CXL_VENDOR_FEATURE_TEST))
+ return mock_get_test_feature(mdata, cmd);
+
+ cmd->return_code = CXL_MBOX_CMD_RC_UNSUPPORTED;
+
+ return -EOPNOTSUPP;
+}
+
+static int mock_set_test_feature(struct cxl_mockmem_data *mdata,
+ struct cxl_mbox_cmd *cmd)
+{
+ struct cxl_mbox_set_feat_in *input = cmd->payload_in;
+ struct vendor_test_feat *test =
+ (struct vendor_test_feat *)input->feat_data;
+ u32 action;
+
+ action = FIELD_GET(CXL_SET_FEAT_FLAG_DATA_TRANSFER_MASK,
+ le32_to_cpu(input->hdr.flags));
+ /*
+ * While it is spec compliant to support other set actions, it is not
+ * necessary to add the complication in the emulation currently. Reject
+ * anything besides full xfer.
+ */
+ if (action != CXL_SET_FEAT_FLAG_FULL_DATA_TRANSFER) {
+ cmd->return_code = CXL_MBOX_CMD_RC_INPUT;
+ return -EINVAL;
+ }
+
+ /* Offset should be reserved when doing full transfer */
+ if (input->hdr.offset) {
+ cmd->return_code = CXL_MBOX_CMD_RC_INPUT;
+ return -EINVAL;
+ }
+
+ memcpy(&mdata->test_feat.data, &test->data, sizeof(u32));
+
+ return 0;
+}
+
+static int mock_set_feature(struct cxl_mockmem_data *mdata,
+ struct cxl_mbox_cmd *cmd)
+{
+ struct cxl_mbox_set_feat_in *input = cmd->payload_in;
+
+ if (uuid_equal(&input->hdr.uuid, &CXL_VENDOR_FEATURE_TEST))
+ return mock_set_test_feature(mdata, cmd);
+
+ cmd->return_code = CXL_MBOX_CMD_RC_UNSUPPORTED;
+
+ return -EOPNOTSUPP;
+}
+
+static int mock_get_supported_features(struct cxl_mockmem_data *mdata,
+ struct cxl_mbox_cmd *cmd)
+{
+ struct cxl_mbox_get_sup_feats_in *in = cmd->payload_in;
+ struct cxl_mbox_get_sup_feats_out *out = cmd->payload_out;
+ struct cxl_feat_entry *feat;
+ u16 start_idx, count;
+
+ if (cmd->size_out < sizeof(*out)) {
+ cmd->return_code = CXL_MBOX_CMD_RC_PAYLOADLEN;
+ return -EINVAL;
+ }
+
+ /*
+ * Current emulation only supports 1 feature
+ */
+ start_idx = le16_to_cpu(in->start_idx);
+ if (start_idx != 0) {
+ cmd->return_code = CXL_MBOX_CMD_RC_INPUT;
+ return -EINVAL;
+ }
+
+ count = le16_to_cpu(in->count);
+ if (count < struct_size(out, ents, 0)) {
+ cmd->return_code = CXL_MBOX_CMD_RC_PAYLOADLEN;
+ return -EINVAL;
+ }
+
+ out->supported_feats = cpu_to_le16(MAX_CXL_TEST_FEATS);
+ cmd->return_code = 0;
+ if (count < struct_size(out, ents, MAX_CXL_TEST_FEATS)) {
+ out->num_entries = 0;
+ return 0;
+ }
+
+ out->num_entries = cpu_to_le16(MAX_CXL_TEST_FEATS);
+ feat = out->ents;
+ fill_feature_vendor_test(feat);
+
+ return 0;
+}
+
static int cxl_mock_mbox_send(struct cxl_mailbox *cxl_mbox,
struct cxl_mbox_cmd *cmd)
{
@@ -1421,6 +1603,9 @@ static int cxl_mock_mbox_send(struct cxl_mailbox *cxl_mbox,
case CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE:
rc = mock_passphrase_secure_erase(mdata, cmd);
break;
+ case CXL_MBOX_OP_SET_SHUTDOWN_STATE:
+ rc = mock_set_shutdown_state(mdata, cmd);
+ break;
case CXL_MBOX_OP_GET_POISON:
rc = mock_get_poison(cxlds, cmd);
break;
@@ -1439,6 +1624,15 @@ static int cxl_mock_mbox_send(struct cxl_mailbox *cxl_mbox,
case CXL_MBOX_OP_ACTIVATE_FW:
rc = mock_activate_fw(mdata, cmd);
break;
+ case CXL_MBOX_OP_GET_SUPPORTED_FEATURES:
+ rc = mock_get_supported_features(mdata, cmd);
+ break;
+ case CXL_MBOX_OP_GET_FEATURE:
+ rc = mock_get_feature(mdata, cmd);
+ break;
+ case CXL_MBOX_OP_SET_FEATURE:
+ rc = mock_set_feature(mdata, cmd);
+ break;
default:
break;
}
@@ -1486,6 +1680,11 @@ static int cxl_mock_mailbox_create(struct cxl_dev_state *cxlds)
return 0;
}
+static void cxl_mock_test_feat_init(struct cxl_mockmem_data *mdata)
+{
+ mdata->test_feat.data = cpu_to_le32(0xdeadbeef);
+}
+
static int cxl_mock_mem_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
@@ -1494,6 +1693,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
struct cxl_dev_state *cxlds;
struct cxl_mockmem_data *mdata;
struct cxl_mailbox *cxl_mbox;
+ struct cxl_dpa_info range_info = { 0 };
int rc;
mdata = devm_kzalloc(dev, sizeof(*mdata), GFP_KERNEL);
@@ -1533,7 +1733,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
mds->event.buf = (struct cxl_get_event_payload *) mdata->event_buf;
INIT_DELAYED_WORK(&mds->security.poll_dwork, cxl_mockmem_sanitize_work);
- cxlds->serial = pdev->id;
+ cxlds->serial = pdev->id + 1;
if (is_rcd(pdev))
cxlds->rcd = true;
@@ -1554,10 +1754,18 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
if (rc)
return rc;
- rc = cxl_mem_create_range_info(mds);
+ rc = cxl_mem_dpa_fetch(mds, &range_info);
if (rc)
return rc;
+ rc = cxl_dpa_setup(cxlds, &range_info);
+ if (rc)
+ return rc;
+
+ rc = devm_cxl_setup_features(cxlds);
+ if (rc)
+ dev_dbg(dev, "No CXL Features discovered\n");
+
cxl_mock_add_event_logs(&mdata->mes);
cxlmd = devm_cxl_add_memdev(&pdev->dev, cxlds);
@@ -1572,7 +1780,12 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
if (rc)
return rc;
+ rc = devm_cxl_setup_fwctl(cxlmd);
+ if (rc)
+ dev_dbg(dev, "No CXL FWCTL setup\n");
+
cxl_mem_get_event_records(mds, CXLDEV_EVENT_STATUS_ALL);
+ cxl_mock_test_feat_init(mdata);
return 0;
}
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config
index b0049be00c70..cdd9782f9646 100644
--- a/tools/testing/kunit/configs/all_tests.config
+++ b/tools/testing/kunit/configs/all_tests.config
@@ -41,6 +41,8 @@ CONFIG_DAMON_PADDR=y
CONFIG_REGMAP_BUILD=y
+CONFIG_AUDIT=y
+
CONFIG_SECURITY=y
CONFIG_SECURITY_APPARMOR=y
CONFIG_SECURITY_LANDLOCK=y
diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index da53a709773a..c176487356e6 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -809,6 +809,10 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest:
test.log.extend(parse_diagnostic(lines))
if test.name != "" and not peek_test_name_match(lines, test):
test.add_error(printer, 'missing subtest result line!')
+ elif not lines:
+ print_log(test.log, printer)
+ test.status = TestStatus.NO_TESTS
+ test.add_error(printer, 'No more test results!')
else:
parse_test_result(lines, test, expected_num, printer)
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
index 5ff4f6ffd873..bbba921e0eac 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -371,8 +371,8 @@ class KUnitParserTest(unittest.TestCase):
"""
result = kunit_parser.parse_run_tests(output.splitlines(), stdout)
# Missing test results after test plan should alert a suspected test crash.
- self.assertEqual(kunit_parser.TestStatus.TEST_CRASHED, result.status)
- self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, crashed=1, errors=1))
+ self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status)
+ self.assertEqual(result.counts, kunit_parser.TestCounts(passed=1, errors=2))
def line_stream_from_strs(strs: Iterable[str]) -> kunit_parser.LineStream:
return kunit_parser.LineStream(enumerate(strs, start=1))
diff --git a/tools/testing/kunit/qemu_configs/sh.py b/tools/testing/kunit/qemu_configs/sh.py
index 78a474a5b95f..f00cb89fdef6 100644
--- a/tools/testing/kunit/qemu_configs/sh.py
+++ b/tools/testing/kunit/qemu_configs/sh.py
@@ -7,7 +7,9 @@ CONFIG_CPU_SUBTYPE_SH7751R=y
CONFIG_MEMORY_START=0x0c000000
CONFIG_SH_RTS7751R2D=y
CONFIG_RTS7751R2D_PLUS=y
-CONFIG_SERIAL_SH_SCI=y''',
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_CMDLINE_EXTEND=y
+''',
qemu_arch='sh4',
kernel_path='arch/sh/boot/zImage',
kernel_command_line='console=ttySC1',
diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h
index 1cf82acb2a3e..0ab4b53bb4f3 100644
--- a/tools/testing/memblock/internal.h
+++ b/tools/testing/memblock/internal.h
@@ -24,4 +24,10 @@ static inline void accept_memory(phys_addr_t start, unsigned long size)
{
}
+static inline unsigned long free_reserved_area(void *start, void *end,
+ int poison, const char *s)
+{
+ return 0;
+}
+
#endif
diff --git a/tools/testing/memblock/linux/mutex.h b/tools/testing/memblock/linux/mutex.h
new file mode 100644
index 000000000000..ae3f497165d6
--- /dev/null
+++ b/tools/testing/memblock/linux/mutex.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MUTEX_H
+#define _MUTEX_H
+
+#define DEFINE_MUTEX(name) int name
+
+static inline void dummy_mutex_guard(int *name)
+{
+}
+
+#define guard(mutex) \
+ dummy_##mutex##_guard
+
+#endif /* _MUTEX_H */ \ No newline at end of file
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index 8b3591a51e1f..b2a6660bbd92 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -14,6 +14,7 @@ include ../shared/shared.mk
main: $(OFILES)
+xarray.o: ../../../lib/test_xarray.c
idr-test.o: ../../../lib/test_ida.c
idr-test: idr-test.o $(CORE_OFILES)
diff --git a/tools/testing/rbtree/Makefile b/tools/testing/rbtree/Makefile
new file mode 100644
index 000000000000..d7bbae2af4c7
--- /dev/null
+++ b/tools/testing/rbtree/Makefile
@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: GPL-2.0
+
+.PHONY: clean
+
+TARGETS = rbtree_test interval_tree_test
+OFILES = $(SHARED_OFILES) rbtree-shim.o interval_tree-shim.o maple-shim.o
+DEPS = ../../../include/linux/rbtree.h \
+ ../../../include/linux/rbtree_types.h \
+ ../../../include/linux/rbtree_augmented.h \
+ ../../../include/linux/interval_tree.h \
+ ../../../include/linux/interval_tree_generic.h \
+ ../../../lib/rbtree.c \
+ ../../../lib/interval_tree.c
+
+targets: $(TARGETS)
+
+include ../shared/shared.mk
+
+ifeq ($(DEBUG), 1)
+ CFLAGS += -g
+endif
+
+$(TARGETS): $(OFILES)
+
+rbtree-shim.o: $(DEPS)
+rbtree_test.o: ../../../lib/rbtree_test.c
+interval_tree-shim.o: $(DEPS)
+interval_tree-shim.o: CFLAGS += -DCONFIG_INTERVAL_TREE_SPAN_ITER
+interval_tree_test.o: ../../../lib/interval_tree_test.c
+interval_tree_test.o: CFLAGS += -DCONFIG_INTERVAL_TREE_SPAN_ITER
+
+clean:
+ $(RM) $(TARGETS) *.o radix-tree.c idr.c generated/*
diff --git a/tools/testing/rbtree/interval_tree_test.c b/tools/testing/rbtree/interval_tree_test.c
new file mode 100644
index 000000000000..49bc5b534330
--- /dev/null
+++ b/tools/testing/rbtree/interval_tree_test.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * interval_tree.c: Userspace Interval Tree test-suite
+ * Copyright (c) 2025 Wei Yang <richard.weiyang@gmail.com>
+ */
+#include <linux/math64.h>
+#include <linux/kern_levels.h>
+#include "shared.h"
+#include "maple-shared.h"
+
+#include "../../../lib/interval_tree_test.c"
+
+int usage(void)
+{
+ fprintf(stderr, "Userland interval tree test cases\n");
+ fprintf(stderr, " -n: Number of nodes in the interval tree\n");
+ fprintf(stderr, " -p: Number of iterations modifying the tree\n");
+ fprintf(stderr, " -q: Number of searches to the interval tree\n");
+ fprintf(stderr, " -s: Number of iterations searching the tree\n");
+ fprintf(stderr, " -a: Searches will iterate all nodes in the tree\n");
+ fprintf(stderr, " -m: Largest value for the interval's endpoint\n");
+ fprintf(stderr, " -r: Random seed\n");
+ exit(-1);
+}
+
+void interval_tree_tests(void)
+{
+ interval_tree_test_init();
+ interval_tree_test_exit();
+}
+
+int main(int argc, char **argv)
+{
+ int opt;
+
+ while ((opt = getopt(argc, argv, "n:p:q:s:am:r:")) != -1) {
+ if (opt == 'n')
+ nnodes = strtoul(optarg, NULL, 0);
+ else if (opt == 'p')
+ perf_loops = strtoul(optarg, NULL, 0);
+ else if (opt == 'q')
+ nsearches = strtoul(optarg, NULL, 0);
+ else if (opt == 's')
+ search_loops = strtoul(optarg, NULL, 0);
+ else if (opt == 'a')
+ search_all = true;
+ else if (opt == 'm')
+ max_endpoint = strtoul(optarg, NULL, 0);
+ else if (opt == 'r')
+ seed = strtoul(optarg, NULL, 0);
+ else
+ usage();
+ }
+
+ maple_tree_init();
+ interval_tree_tests();
+ return 0;
+}
diff --git a/tools/testing/rbtree/rbtree_test.c b/tools/testing/rbtree/rbtree_test.c
new file mode 100644
index 000000000000..585c970f679e
--- /dev/null
+++ b/tools/testing/rbtree/rbtree_test.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * rbtree_test.c: Userspace Red Black Tree test-suite
+ * Copyright (c) 2025 Wei Yang <richard.weiyang@gmail.com>
+ */
+#include <linux/init.h>
+#include <linux/math64.h>
+#include <linux/kern_levels.h>
+#include "shared.h"
+
+#include "../../../lib/rbtree_test.c"
+
+int usage(void)
+{
+ fprintf(stderr, "Userland rbtree test cases\n");
+ fprintf(stderr, " -n: Number of nodes in the rb-tree\n");
+ fprintf(stderr, " -p: Number of iterations modifying the rb-tree\n");
+ fprintf(stderr, " -c: Number of iterations modifying and verifying the rb-tree\n");
+ fprintf(stderr, " -r: Random seed\n");
+ exit(-1);
+}
+
+void rbtree_tests(void)
+{
+ rbtree_test_init();
+ rbtree_test_exit();
+}
+
+int main(int argc, char **argv)
+{
+ int opt;
+
+ while ((opt = getopt(argc, argv, "n:p:c:r:")) != -1) {
+ if (opt == 'n')
+ nnodes = strtoul(optarg, NULL, 0);
+ else if (opt == 'p')
+ perf_loops = strtoul(optarg, NULL, 0);
+ else if (opt == 'c')
+ check_loops = strtoul(optarg, NULL, 0);
+ else if (opt == 'r')
+ seed = strtoul(optarg, NULL, 0);
+ else
+ usage();
+ }
+
+ rbtree_tests();
+ return 0;
+}
diff --git a/tools/testing/rbtree/test.h b/tools/testing/rbtree/test.h
new file mode 100644
index 000000000000..f1f1b545b55a
--- /dev/null
+++ b/tools/testing/rbtree/test.h
@@ -0,0 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+void rbtree_tests(void);
+void interval_tree_tests(void);
diff --git a/tools/testing/selftests/.gitignore b/tools/testing/selftests/.gitignore
index cb24124ac5b9..674aaa02e396 100644
--- a/tools/testing/selftests/.gitignore
+++ b/tools/testing/selftests/.gitignore
@@ -4,7 +4,6 @@ gpiogpio-hammer
gpioinclude/
gpiolsgpio
kselftest_install/
-tpm2/SpaceTest.log
# Python bytecode and cache
__pycache__/
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 2694344274bf..c77c8c8e3d9b 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -62,6 +62,7 @@ TARGETS += mount
TARGETS += mount_setattr
TARGETS += move_mount_set_group
TARGETS += mqueue
+TARGETS += mseal_system_mappings
TARGETS += nci
TARGETS += net
TARGETS += net/af_unix
diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64
index 901349da680f..6d8feda27ce9 100644
--- a/tools/testing/selftests/bpf/DENYLIST.aarch64
+++ b/tools/testing/selftests/bpf/DENYLIST.aarch64
@@ -1,12 +1,3 @@
-bpf_cookie/multi_kprobe_attach_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
-bpf_cookie/multi_kprobe_link_api # kprobe_multi_link_api_subtest:FAIL:fentry_raw_skel_load unexpected error: -3
-kprobe_multi_bench_attach # needs CONFIG_FPROBE
-kprobe_multi_test # needs CONFIG_FPROBE
-module_attach # prog 'kprobe_multi': failed to auto-attach: -95
fentry_test/fentry_many_args # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524
fexit_test/fexit_many_args # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524
tracing_struct/struct_many_args # struct_many_args:FAIL:tracing_struct_many_args__attach unexpected error: -524
-fill_link_info/kprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-fill_link_info/kretprobe_multi_link_info # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-fill_link_info/kprobe_multi_invalid_ubuff # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-missed/kprobe_recursion # missed_kprobe_recursion__attach unexpected error: -95 (errno 95)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 87551628e112..66bb50356be0 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -95,18 +95,12 @@ TEST_GEN_PROGS += test_progs-cpuv4
TEST_INST_SUBDIRS += cpuv4
endif
-TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o
+TEST_GEN_FILES = test_tc_edt.bpf.o
TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c)
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
- test_xdp_redirect_multi.sh \
- test_tunnel.sh \
- test_lwt_seg6local.sh \
test_lirc_mode2.sh \
- test_xdp_vlan_mode_generic.sh \
- test_xdp_vlan_mode_native.sh \
- test_lwt_ip_encap.sh \
test_tc_tunnel.sh \
test_tc_edt.sh \
test_xdping.sh \
@@ -117,9 +111,9 @@ TEST_PROGS := test_kmod.sh \
test_xsk.sh \
test_xdp_features.sh
-TEST_PROGS_EXTENDED := with_addr.sh \
- with_tunnels.sh ima_setup.sh verify_sig_setup.sh \
- test_xdp_vlan.sh test_bpftool.py
+TEST_PROGS_EXTENDED := \
+ ima_setup.sh verify_sig_setup.sh \
+ test_bpftool.py
TEST_KMODS := bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \
bpf_test_modorder_y.ko
@@ -135,7 +129,6 @@ TEST_GEN_PROGS_EXTENDED = \
veristat \
xdp_features \
xdp_hw_metadata \
- xdp_redirect_multi \
xdp_synproxy \
xdping \
xskxceiver
@@ -184,9 +177,14 @@ ifeq ($(feature-llvm),1)
LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets
# both llvm-config and lib.mk add -D_GNU_SOURCE, which ends up as conflict
LLVM_CFLAGS += $(filter-out -D_GNU_SOURCE,$(shell $(LLVM_CONFIG) --cflags))
- LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-static --libs $(LLVM_CONFIG_LIB_COMPONENTS))
- LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-static --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))
- LLVM_LDLIBS += -lstdc++
+ # Prefer linking statically if it's available, otherwise fallback to shared
+ ifeq ($(shell $(LLVM_CONFIG) --link-static --libs >/dev/null 2>&1 && echo static),static)
+ LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-static --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+ LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-static --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))
+ LLVM_LDLIBS += -lstdc++
+ else
+ LLVM_LDLIBS += $(shell $(LLVM_CONFIG) --link-shared --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+ endif
LLVM_LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags)
endif
@@ -306,6 +304,7 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT)
BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \
BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf/ \
BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) \
+ BPF_TARGET_ENDIAN=$(BPF_TARGET_ENDIAN) \
EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)' \
EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' && \
cp $(RUNQSLOWER_OUTPUT)runqslower $@
@@ -684,6 +683,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \
$(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \
$(RESOLVE_BTFIDS) \
$(TRUNNER_BPFTOOL) \
+ $(OUTPUT)/veristat \
| $(TRUNNER_BINARY)-extras
$$(call msg,BINARY,,$$@)
$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) $$(LDFLAGS) -o $$@
diff --git a/tools/testing/selftests/bpf/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/bpf_arena_spin_lock.h
new file mode 100644
index 000000000000..fb8dc0768999
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_arena_spin_lock.h
@@ -0,0 +1,533 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#ifndef BPF_ARENA_SPIN_LOCK_H
+#define BPF_ARENA_SPIN_LOCK_H
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_atomic.h"
+
+#define arch_mcs_spin_lock_contended_label(l, label) smp_cond_load_acquire_label(l, VAL, label)
+#define arch_mcs_spin_unlock_contended(l) smp_store_release((l), 1)
+
+#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+
+#define EBUSY 16
+#define EOPNOTSUPP 95
+#define ETIMEDOUT 110
+
+#ifndef __arena
+#define __arena __attribute__((address_space(1)))
+#endif
+
+extern unsigned long CONFIG_NR_CPUS __kconfig;
+
+/*
+ * Typically, we'd just rely on the definition in vmlinux.h for qspinlock, but
+ * PowerPC overrides the definition to define lock->val as u32 instead of
+ * atomic_t, leading to compilation errors. Import a local definition below so
+ * that we don't depend on the vmlinux.h version.
+ */
+
+struct __qspinlock {
+ union {
+ atomic_t val;
+ struct {
+ u8 locked;
+ u8 pending;
+ };
+ struct {
+ u16 locked_pending;
+ u16 tail;
+ };
+ };
+};
+
+#define arena_spinlock_t struct __qspinlock
+/* FIXME: Using typedef causes CO-RE relocation error */
+/* typedef struct qspinlock arena_spinlock_t; */
+
+struct arena_mcs_spinlock {
+ struct arena_mcs_spinlock __arena *next;
+ int locked;
+ int count;
+};
+
+struct arena_qnode {
+ struct arena_mcs_spinlock mcs;
+};
+
+#define _Q_MAX_NODES 4
+#define _Q_PENDING_LOOPS 1
+
+/*
+ * Bitfields in the atomic value:
+ *
+ * 0- 7: locked byte
+ * 8: pending
+ * 9-15: not used
+ * 16-17: tail index
+ * 18-31: tail cpu (+1)
+ */
+#define _Q_MAX_CPUS 1024
+
+#define _Q_SET_MASK(type) (((1U << _Q_ ## type ## _BITS) - 1)\
+ << _Q_ ## type ## _OFFSET)
+#define _Q_LOCKED_OFFSET 0
+#define _Q_LOCKED_BITS 8
+#define _Q_LOCKED_MASK _Q_SET_MASK(LOCKED)
+
+#define _Q_PENDING_OFFSET (_Q_LOCKED_OFFSET + _Q_LOCKED_BITS)
+#define _Q_PENDING_BITS 8
+#define _Q_PENDING_MASK _Q_SET_MASK(PENDING)
+
+#define _Q_TAIL_IDX_OFFSET (_Q_PENDING_OFFSET + _Q_PENDING_BITS)
+#define _Q_TAIL_IDX_BITS 2
+#define _Q_TAIL_IDX_MASK _Q_SET_MASK(TAIL_IDX)
+
+#define _Q_TAIL_CPU_OFFSET (_Q_TAIL_IDX_OFFSET + _Q_TAIL_IDX_BITS)
+#define _Q_TAIL_CPU_BITS (32 - _Q_TAIL_CPU_OFFSET)
+#define _Q_TAIL_CPU_MASK _Q_SET_MASK(TAIL_CPU)
+
+#define _Q_TAIL_OFFSET _Q_TAIL_IDX_OFFSET
+#define _Q_TAIL_MASK (_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK)
+
+#define _Q_LOCKED_VAL (1U << _Q_LOCKED_OFFSET)
+#define _Q_PENDING_VAL (1U << _Q_PENDING_OFFSET)
+
+#define likely(x) __builtin_expect(!!(x), 1)
+#define unlikely(x) __builtin_expect(!!(x), 0)
+
+struct arena_qnode __arena qnodes[_Q_MAX_CPUS][_Q_MAX_NODES];
+
+static inline u32 encode_tail(int cpu, int idx)
+{
+ u32 tail;
+
+ tail = (cpu + 1) << _Q_TAIL_CPU_OFFSET;
+ tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */
+
+ return tail;
+}
+
+static inline struct arena_mcs_spinlock __arena *decode_tail(u32 tail)
+{
+ u32 cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1;
+ u32 idx = (tail & _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET;
+
+ return &qnodes[cpu][idx].mcs;
+}
+
+static inline
+struct arena_mcs_spinlock __arena *grab_mcs_node(struct arena_mcs_spinlock __arena *base, int idx)
+{
+ return &((struct arena_qnode __arena *)base + idx)->mcs;
+}
+
+#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
+
+/**
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(arena_spinlock_t __arena *lock, u32 tail)
+{
+ u32 old, new;
+
+ old = atomic_read(&lock->val);
+ do {
+ new = (old & _Q_LOCKED_PENDING_MASK) | tail;
+ /*
+ * We can use relaxed semantics since the caller ensures that
+ * the MCS node is properly initialized before updating the
+ * tail.
+ */
+ /* These loops are not expected to stall, but we still need to
+ * prove to the verifier they will terminate eventually.
+ */
+ cond_break_label(out);
+ } while (!atomic_try_cmpxchg_relaxed(&lock->val, &old, new));
+
+ return old;
+out:
+ bpf_printk("RUNTIME ERROR: %s unexpected cond_break exit!!!", __func__);
+ return old;
+}
+
+/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(arena_spinlock_t __arena *lock)
+{
+ WRITE_ONCE(lock->pending, 0);
+}
+
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ *
+ * Lock stealing is not allowed if this function is used.
+ */
+static __always_inline void clear_pending_set_locked(arena_spinlock_t __arena *lock)
+{
+ WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL);
+}
+
+/**
+ * set_locked - Set the lock bit and own the lock
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,*,0 -> *,0,1
+ */
+static __always_inline void set_locked(arena_spinlock_t __arena *lock)
+{
+ WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
+}
+
+static __always_inline
+u32 arena_fetch_set_pending_acquire(arena_spinlock_t __arena *lock)
+{
+ u32 old, new;
+
+ old = atomic_read(&lock->val);
+ do {
+ new = old | _Q_PENDING_VAL;
+ /*
+ * These loops are not expected to stall, but we still need to
+ * prove to the verifier they will terminate eventually.
+ */
+ cond_break_label(out);
+ } while (!atomic_try_cmpxchg_acquire(&lock->val, &old, new));
+
+ return old;
+out:
+ bpf_printk("RUNTIME ERROR: %s unexpected cond_break exit!!!", __func__);
+ return old;
+}
+
+/**
+ * arena_spin_trylock - try to acquire the queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static __always_inline int arena_spin_trylock(arena_spinlock_t __arena *lock)
+{
+ int val = atomic_read(&lock->val);
+
+ if (unlikely(val))
+ return 0;
+
+ return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL));
+}
+
+__noinline
+int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val)
+{
+ struct arena_mcs_spinlock __arena *prev, *next, *node0, *node;
+ int ret = -ETIMEDOUT;
+ u32 old, tail;
+ int idx;
+
+ /*
+ * Wait for in-progress pending->locked hand-overs with a bounded
+ * number of spins so that we guarantee forward progress.
+ *
+ * 0,1,0 -> 0,0,1
+ */
+ if (val == _Q_PENDING_VAL) {
+ int cnt = _Q_PENDING_LOOPS;
+ val = atomic_cond_read_relaxed_label(&lock->val,
+ (VAL != _Q_PENDING_VAL) || !cnt--,
+ release_err);
+ }
+
+ /*
+ * If we observe any contention; queue.
+ */
+ if (val & ~_Q_LOCKED_MASK)
+ goto queue;
+
+ /*
+ * trylock || pending
+ *
+ * 0,0,* -> 0,1,* -> 0,0,1 pending, trylock
+ */
+ val = arena_fetch_set_pending_acquire(lock);
+
+ /*
+ * If we observe contention, there is a concurrent locker.
+ *
+ * Undo and queue; our setting of PENDING might have made the
+ * n,0,0 -> 0,0,0 transition fail and it will now be waiting
+ * on @next to become !NULL.
+ */
+ if (unlikely(val & ~_Q_LOCKED_MASK)) {
+
+ /* Undo PENDING if we set it. */
+ if (!(val & _Q_PENDING_MASK))
+ clear_pending(lock);
+
+ goto queue;
+ }
+
+ /*
+ * We're pending, wait for the owner to go away.
+ *
+ * 0,1,1 -> *,1,0
+ *
+ * this wait loop must be a load-acquire such that we match the
+ * store-release that clears the locked bit and create lock
+ * sequentiality; this is because not all
+ * clear_pending_set_locked() implementations imply full
+ * barriers.
+ */
+ if (val & _Q_LOCKED_MASK)
+ smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
+
+ /*
+ * take ownership and clear the pending bit.
+ *
+ * 0,1,0 -> 0,0,1
+ */
+ clear_pending_set_locked(lock);
+ return 0;
+
+ /*
+ * End of pending bit optimistic spinning and beginning of MCS
+ * queuing.
+ */
+queue:
+ node0 = &(qnodes[bpf_get_smp_processor_id()])[0].mcs;
+ idx = node0->count++;
+ tail = encode_tail(bpf_get_smp_processor_id(), idx);
+
+ /*
+ * 4 nodes are allocated based on the assumption that there will not be
+ * nested NMIs taking spinlocks. That may not be true in some
+ * architectures even though the chance of needing more than 4 nodes
+ * will still be extremely unlikely. When that happens, we simply return
+ * an error. Original qspinlock has a trylock fallback in this case.
+ */
+ if (unlikely(idx >= _Q_MAX_NODES)) {
+ ret = -EBUSY;
+ goto release_node_err;
+ }
+
+ node = grab_mcs_node(node0, idx);
+
+ /*
+ * Ensure that we increment the head node->count before initialising
+ * the actual node. If the compiler is kind enough to reorder these
+ * stores, then an IRQ could overwrite our assignments.
+ */
+ barrier();
+
+ node->locked = 0;
+ node->next = NULL;
+
+ /*
+ * We touched a (possibly) cold cacheline in the per-cpu queue node;
+ * attempt the trylock once more in the hope someone let go while we
+ * weren't watching.
+ */
+ if (arena_spin_trylock(lock))
+ goto release;
+
+ /*
+ * Ensure that the initialisation of @node is complete before we
+ * publish the updated tail via xchg_tail() and potentially link
+ * @node into the waitqueue via WRITE_ONCE(prev->next, node) below.
+ */
+ smp_wmb();
+
+ /*
+ * Publish the updated tail.
+ * We have already touched the queueing cacheline; don't bother with
+ * pending stuff.
+ *
+ * p,*,* -> n,*,*
+ */
+ old = xchg_tail(lock, tail);
+ next = NULL;
+
+ /*
+ * if there was a previous node; link it and wait until reaching the
+ * head of the waitqueue.
+ */
+ if (old & _Q_TAIL_MASK) {
+ prev = decode_tail(old);
+
+ /* Link @node into the waitqueue. */
+ WRITE_ONCE(prev->next, node);
+
+ arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
+
+ /*
+ * While waiting for the MCS lock, the next pointer may have
+ * been set by another lock waiter. We cannot prefetch here
+ * due to lack of equivalent instruction in BPF ISA.
+ */
+ next = READ_ONCE(node->next);
+ }
+
+ /*
+ * we're at the head of the waitqueue, wait for the owner & pending to
+ * go away.
+ *
+ * *,x,y -> *,0,0
+ *
+ * this wait loop must use a load-acquire such that we match the
+ * store-release that clears the locked bit and create lock
+ * sequentiality; this is because the set_locked() function below
+ * does not imply a full barrier.
+ */
+ val = atomic_cond_read_acquire_label(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK),
+ release_node_err);
+
+ /*
+ * claim the lock:
+ *
+ * n,0,0 -> 0,0,1 : lock, uncontended
+ * *,*,0 -> *,*,1 : lock, contended
+ *
+ * If the queue head is the only one in the queue (lock value == tail)
+ * and nobody is pending, clear the tail code and grab the lock.
+ * Otherwise, we only need to grab the lock.
+ */
+
+ /*
+ * In the PV case we might already have _Q_LOCKED_VAL set, because
+ * of lock stealing; therefore we must also allow:
+ *
+ * n,0,1 -> 0,0,1
+ *
+ * Note: at this point: (val & _Q_PENDING_MASK) == 0, because of the
+ * above wait condition, therefore any concurrent setting of
+ * PENDING will make the uncontended transition fail.
+ */
+ if ((val & _Q_TAIL_MASK) == tail) {
+ if (atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
+ goto release; /* No contention */
+ }
+
+ /*
+ * Either somebody is queued behind us or _Q_PENDING_VAL got set
+ * which will then detect the remaining tail and queue behind us
+ * ensuring we'll see a @next.
+ */
+ set_locked(lock);
+
+ /*
+ * contended path; wait for next if not observed yet, release.
+ */
+ if (!next)
+ next = smp_cond_load_relaxed_label(&node->next, (VAL), release_node_err);
+
+ arch_mcs_spin_unlock_contended(&next->locked);
+
+release:;
+ /*
+ * release the node
+ *
+ * Doing a normal dec vs this_cpu_dec is fine. An upper context always
+ * decrements count it incremented before returning, thus we're fine.
+ * For contexts interrupting us, they either observe our dec or not.
+ * Just ensure the compiler doesn't reorder this statement, as a
+ * this_cpu_dec implicitly implied that.
+ */
+ barrier();
+ node0->count--;
+ return 0;
+release_node_err:
+ barrier();
+ node0->count--;
+ goto release_err;
+release_err:
+ return ret;
+}
+
+/**
+ * arena_spin_lock - acquire a queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ *
+ * On error, returned value will be negative.
+ * On success, zero is returned.
+ *
+ * The return value _must_ be tested against zero for success,
+ * instead of checking it against negative, for passing the
+ * BPF verifier.
+ *
+ * The user should do:
+ * if (arena_spin_lock(...) != 0) // failure
+ * or
+ * if (arena_spin_lock(...) == 0) // success
+ * or
+ * if (arena_spin_lock(...)) // failure
+ * or
+ * if (!arena_spin_lock(...)) // success
+ * instead of:
+ * if (arena_spin_lock(...) < 0) // failure
+ *
+ * The return value can still be inspected later.
+ */
+static __always_inline int arena_spin_lock(arena_spinlock_t __arena *lock)
+{
+ int val = 0;
+
+ if (CONFIG_NR_CPUS > 1024)
+ return -EOPNOTSUPP;
+
+ bpf_preempt_disable();
+ if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)))
+ return 0;
+
+ val = arena_spin_lock_slowpath(lock, val);
+ /* FIXME: bpf_assert_range(-MAX_ERRNO, 0) once we have it working for all cases. */
+ if (val)
+ bpf_preempt_enable();
+ return val;
+}
+
+/**
+ * arena_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static __always_inline void arena_spin_unlock(arena_spinlock_t __arena *lock)
+{
+ /*
+ * unlock() needs release semantics:
+ */
+ smp_store_release(&lock->locked, 0);
+ bpf_preempt_enable();
+}
+
+#define arena_spin_lock_irqsave(lock, flags) \
+ ({ \
+ int __ret; \
+ bpf_local_irq_save(&(flags)); \
+ __ret = arena_spin_lock((lock)); \
+ if (__ret) \
+ bpf_local_irq_restore(&(flags)); \
+ (__ret); \
+ })
+
+#define arena_spin_unlock_irqrestore(lock, flags) \
+ ({ \
+ arena_spin_unlock((lock)); \
+ bpf_local_irq_restore(&(flags)); \
+ })
+
+#endif
+
+#endif /* BPF_ARENA_SPIN_LOCK_H */
diff --git a/tools/testing/selftests/bpf/bpf_atomic.h b/tools/testing/selftests/bpf/bpf_atomic.h
new file mode 100644
index 000000000000..a9674e544322
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_atomic.h
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#ifndef BPF_ATOMIC_H
+#define BPF_ATOMIC_H
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_experimental.h"
+
+extern bool CONFIG_X86_64 __kconfig __weak;
+
+/*
+ * __unqual_typeof(x) - Declare an unqualified scalar type, leaving
+ * non-scalar types unchanged,
+ *
+ * Prefer C11 _Generic for better compile-times and simpler code. Note: 'char'
+ * is not type-compatible with 'signed char', and we define a separate case.
+ *
+ * This is copied verbatim from kernel's include/linux/compiler_types.h, but
+ * with default expression (for pointers) changed from (x) to (typeof(x)0).
+ *
+ * This is because LLVM has a bug where for lvalue (x), it does not get rid of
+ * an extra address_space qualifier, but does in case of rvalue (typeof(x)0).
+ * Hence, for pointers, we need to create an rvalue expression to get the
+ * desired type. See https://github.com/llvm/llvm-project/issues/53400.
+ */
+#define __scalar_type_to_expr_cases(type) \
+ unsigned type : (unsigned type)0, signed type : (signed type)0
+
+#define __unqual_typeof(x) \
+ typeof(_Generic((x), \
+ char: (char)0, \
+ __scalar_type_to_expr_cases(char), \
+ __scalar_type_to_expr_cases(short), \
+ __scalar_type_to_expr_cases(int), \
+ __scalar_type_to_expr_cases(long), \
+ __scalar_type_to_expr_cases(long long), \
+ default: (typeof(x))0))
+
+/* No-op for BPF */
+#define cpu_relax() ({})
+
+#define READ_ONCE(x) (*(volatile typeof(x) *)&(x))
+
+#define WRITE_ONCE(x, val) ((*(volatile typeof(x) *)&(x)) = (val))
+
+#define cmpxchg(p, old, new) __sync_val_compare_and_swap((p), old, new)
+
+#define try_cmpxchg(p, pold, new) \
+ ({ \
+ __unqual_typeof(*(pold)) __o = *(pold); \
+ __unqual_typeof(*(p)) __r = cmpxchg(p, __o, new); \
+ if (__r != __o) \
+ *(pold) = __r; \
+ __r == __o; \
+ })
+
+#define try_cmpxchg_relaxed(p, pold, new) try_cmpxchg(p, pold, new)
+
+#define try_cmpxchg_acquire(p, pold, new) try_cmpxchg(p, pold, new)
+
+#define smp_mb() \
+ ({ \
+ unsigned long __val; \
+ __sync_fetch_and_add(&__val, 0); \
+ })
+
+#define smp_rmb() \
+ ({ \
+ if (!CONFIG_X86_64) \
+ smp_mb(); \
+ else \
+ barrier(); \
+ })
+
+#define smp_wmb() \
+ ({ \
+ if (!CONFIG_X86_64) \
+ smp_mb(); \
+ else \
+ barrier(); \
+ })
+
+/* Control dependency provides LOAD->STORE, provide LOAD->LOAD */
+#define smp_acquire__after_ctrl_dep() ({ smp_rmb(); })
+
+#define smp_load_acquire(p) \
+ ({ \
+ __unqual_typeof(*(p)) __v = READ_ONCE(*(p)); \
+ if (!CONFIG_X86_64) \
+ smp_mb(); \
+ barrier(); \
+ __v; \
+ })
+
+#define smp_store_release(p, val) \
+ ({ \
+ if (!CONFIG_X86_64) \
+ smp_mb(); \
+ barrier(); \
+ WRITE_ONCE(*(p), val); \
+ })
+
+#define smp_cond_load_relaxed_label(p, cond_expr, label) \
+ ({ \
+ typeof(p) __ptr = (p); \
+ __unqual_typeof(*(p)) VAL; \
+ for (;;) { \
+ VAL = (__unqual_typeof(*(p)))READ_ONCE(*__ptr); \
+ if (cond_expr) \
+ break; \
+ cond_break_label(label); \
+ cpu_relax(); \
+ } \
+ (typeof(*(p)))VAL; \
+ })
+
+#define smp_cond_load_acquire_label(p, cond_expr, label) \
+ ({ \
+ __unqual_typeof(*p) __val = \
+ smp_cond_load_relaxed_label(p, cond_expr, label); \
+ smp_acquire__after_ctrl_dep(); \
+ (typeof(*(p)))__val; \
+ })
+
+#define atomic_read(p) READ_ONCE((p)->counter)
+
+#define atomic_cond_read_relaxed_label(p, cond_expr, label) \
+ smp_cond_load_relaxed_label(&(p)->counter, cond_expr, label)
+
+#define atomic_cond_read_acquire_label(p, cond_expr, label) \
+ smp_cond_load_acquire_label(&(p)->counter, cond_expr, label)
+
+#define atomic_try_cmpxchg_relaxed(p, pold, new) \
+ try_cmpxchg_relaxed(&(p)->counter, pold, new)
+
+#define atomic_try_cmpxchg_acquire(p, pold, new) \
+ try_cmpxchg_acquire(&(p)->counter, pold, new)
+
+#endif /* BPF_ATOMIC_H */
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index cd8ecd39c3f3..6535c8ae3c46 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -368,12 +368,12 @@ l_true: \
ret; \
})
-#define cond_break \
+#define __cond_break(expr) \
({ __label__ l_break, l_continue; \
asm volatile goto("may_goto %l[l_break]" \
:::: l_break); \
goto l_continue; \
- l_break: break; \
+ l_break: expr; \
l_continue:; \
})
#else
@@ -392,7 +392,7 @@ l_true: \
ret; \
})
-#define cond_break \
+#define __cond_break(expr) \
({ __label__ l_break, l_continue; \
asm volatile goto("1:.byte 0xe5; \
.byte 0; \
@@ -400,7 +400,7 @@ l_true: \
.short 0" \
:::: l_break); \
goto l_continue; \
- l_break: break; \
+ l_break: expr; \
l_continue:; \
})
#else
@@ -418,7 +418,7 @@ l_true: \
ret; \
})
-#define cond_break \
+#define __cond_break(expr) \
({ __label__ l_break, l_continue; \
asm volatile goto("1:.byte 0xe5; \
.byte 0; \
@@ -426,12 +426,15 @@ l_true: \
.short 0" \
:::: l_break); \
goto l_continue; \
- l_break: break; \
+ l_break: expr; \
l_continue:; \
})
#endif
#endif
+#define cond_break __cond_break(break)
+#define cond_break_label(label) __cond_break(goto label)
+
#ifndef bpf_nop_mov
#define bpf_nop_mov(var) \
asm volatile("%[reg]=%[reg]"::[reg]"r"((short)var))
diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index 2eb3483f2fb0..8215c9b3115e 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -87,4 +87,9 @@ struct dentry;
*/
extern int bpf_get_dentry_xattr(struct dentry *dentry, const char *name,
struct bpf_dynptr *value_ptr) __ksym __weak;
+
+extern int bpf_set_dentry_xattr(struct dentry *dentry, const char *name__str,
+ const struct bpf_dynptr *value_p, int flags) __ksym __weak;
+extern int bpf_remove_dentry_xattr(struct dentry *dentry, const char *name__str) __ksym __weak;
+
#endif
diff --git a/tools/testing/selftests/bpf/cap_helpers.c b/tools/testing/selftests/bpf/cap_helpers.c
index d5ac507401d7..98f840c3a38f 100644
--- a/tools/testing/selftests/bpf/cap_helpers.c
+++ b/tools/testing/selftests/bpf/cap_helpers.c
@@ -19,7 +19,7 @@ int cap_enable_effective(__u64 caps, __u64 *old_caps)
err = capget(&hdr, data);
if (err)
- return err;
+ return -errno;
if (old_caps)
*old_caps = (__u64)(data[1].effective) << 32 | data[0].effective;
@@ -32,7 +32,7 @@ int cap_enable_effective(__u64 caps, __u64 *old_caps)
data[1].effective |= cap1;
err = capset(&hdr, data);
if (err)
- return err;
+ return -errno;
return 0;
}
@@ -49,7 +49,7 @@ int cap_disable_effective(__u64 caps, __u64 *old_caps)
err = capget(&hdr, data);
if (err)
- return err;
+ return -errno;
if (old_caps)
*old_caps = (__u64)(data[1].effective) << 32 | data[0].effective;
@@ -61,7 +61,7 @@ int cap_disable_effective(__u64 caps, __u64 *old_caps)
data[1].effective &= ~cap1;
err = capset(&hdr, data);
if (err)
- return err;
+ return -errno;
return 0;
}
diff --git a/tools/testing/selftests/bpf/cap_helpers.h b/tools/testing/selftests/bpf/cap_helpers.h
index 6d163530cb0f..8dcb28557f76 100644
--- a/tools/testing/selftests/bpf/cap_helpers.h
+++ b/tools/testing/selftests/bpf/cap_helpers.h
@@ -4,6 +4,7 @@
#include <linux/types.h>
#include <linux/capability.h>
+#include <errno.h>
#ifndef CAP_PERFMON
#define CAP_PERFMON 38
diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64
index 5680befae8c6..5e713ef7caa3 100644
--- a/tools/testing/selftests/bpf/config.x86_64
+++ b/tools/testing/selftests/bpf/config.x86_64
@@ -39,7 +39,6 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y
CONFIG_CPU_FREQ_STAT=y
CONFIG_CPU_IDLE_GOV_LADDER=y
CONFIG_CPUSETS=y
-CONFIG_CRC_T10DIF=y
CONFIG_CRYPTO_BLAKE2B=y
CONFIG_CRYPTO_SEQIV=y
CONFIG_CRYPTO_XXHASH=y
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 29541d486c5e..72b5c174ab3b 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -446,6 +446,23 @@ char *ping_command(int family)
return "ping";
}
+int append_tid(char *str, size_t sz)
+{
+ size_t end;
+
+ if (!str)
+ return -1;
+
+ end = strlen(str);
+ if (end + 8 > sz)
+ return -1;
+
+ sprintf(&str[end], "%07d", gettid());
+ str[end + 7] = '\0';
+
+ return 0;
+}
+
int remove_netns(const char *name)
{
char *cmd;
@@ -761,6 +778,36 @@ struct tmonitor_ctx {
int pcap_fd;
};
+static int __base_pr(const char *format, va_list args)
+{
+ return vfprintf(stdout, format, args);
+}
+
+static tm_print_fn_t __tm_pr = __base_pr;
+
+tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn)
+{
+ tm_print_fn_t old_print_fn;
+
+ old_print_fn = __atomic_exchange_n(&__tm_pr, fn, __ATOMIC_RELAXED);
+
+ return old_print_fn;
+}
+
+void tm_print(const char *format, ...)
+{
+ tm_print_fn_t print_fn;
+ va_list args;
+
+ print_fn = __atomic_load_n(&__tm_pr, __ATOMIC_RELAXED);
+ if (!print_fn)
+ return;
+
+ va_start(args, format);
+ print_fn(format, args);
+ va_end(args);
+}
+
/* Is this packet captured with a Ethernet protocol type? */
static bool is_ethernet(const u_char *packet)
{
@@ -778,7 +825,7 @@ static bool is_ethernet(const u_char *packet)
case 770: /* ARPHRD_FRAD */
case 778: /* ARPHDR_IPGRE */
case 803: /* ARPHRD_IEEE80211_RADIOTAP */
- printf("Packet captured: arphdr_type=%d\n", arphdr_type);
+ tm_print("Packet captured: arphdr_type=%d\n", arphdr_type);
return false;
}
return true;
@@ -799,12 +846,13 @@ static const char *pkt_type_str(u16 pkt_type)
return "Unknown";
}
+#define MAX_FLAGS_STRLEN 21
/* Show the information of the transport layer in the packet */
static void show_transport(const u_char *packet, u16 len, u32 ifindex,
const char *src_addr, const char *dst_addr,
u16 proto, bool ipv6, u8 pkt_type)
{
- char *ifname, _ifname[IF_NAMESIZE];
+ char *ifname, _ifname[IF_NAMESIZE], flags[MAX_FLAGS_STRLEN] = "";
const char *transport_str;
u16 src_port, dst_port;
struct udphdr *udp;
@@ -827,47 +875,39 @@ static void show_transport(const u_char *packet, u16 len, u32 ifindex,
dst_port = ntohs(tcp->dest);
transport_str = "TCP";
} else if (proto == IPPROTO_ICMP) {
- printf("%-7s %-3s IPv4 %s > %s: ICMP, length %d, type %d, code %d\n",
- ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
- packet[0], packet[1]);
+ tm_print("%-7s %-3s IPv4 %s > %s: ICMP, length %d, type %d, code %d\n",
+ ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
+ packet[0], packet[1]);
return;
} else if (proto == IPPROTO_ICMPV6) {
- printf("%-7s %-3s IPv6 %s > %s: ICMPv6, length %d, type %d, code %d\n",
- ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
- packet[0], packet[1]);
+ tm_print("%-7s %-3s IPv6 %s > %s: ICMPv6, length %d, type %d, code %d\n",
+ ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
+ packet[0], packet[1]);
return;
} else {
- printf("%-7s %-3s %s %s > %s: protocol %d\n",
- ifname, pkt_type_str(pkt_type), ipv6 ? "IPv6" : "IPv4",
- src_addr, dst_addr, proto);
+ tm_print("%-7s %-3s %s %s > %s: protocol %d\n",
+ ifname, pkt_type_str(pkt_type), ipv6 ? "IPv6" : "IPv4",
+ src_addr, dst_addr, proto);
return;
}
/* TCP or UDP*/
- flockfile(stdout);
+ if (proto == IPPROTO_TCP)
+ snprintf(flags, MAX_FLAGS_STRLEN, "%s%s%s%s",
+ tcp->fin ? ", FIN" : "",
+ tcp->syn ? ", SYN" : "",
+ tcp->rst ? ", RST" : "",
+ tcp->ack ? ", ACK" : "");
+
if (ipv6)
- printf("%-7s %-3s IPv6 %s.%d > %s.%d: %s, length %d",
- ifname, pkt_type_str(pkt_type), src_addr, src_port,
- dst_addr, dst_port, transport_str, len);
+ tm_print("%-7s %-3s IPv6 %s.%d > %s.%d: %s, length %d%s\n",
+ ifname, pkt_type_str(pkt_type), src_addr, src_port,
+ dst_addr, dst_port, transport_str, len, flags);
else
- printf("%-7s %-3s IPv4 %s:%d > %s:%d: %s, length %d",
- ifname, pkt_type_str(pkt_type), src_addr, src_port,
- dst_addr, dst_port, transport_str, len);
-
- if (proto == IPPROTO_TCP) {
- if (tcp->fin)
- printf(", FIN");
- if (tcp->syn)
- printf(", SYN");
- if (tcp->rst)
- printf(", RST");
- if (tcp->ack)
- printf(", ACK");
- }
-
- printf("\n");
- funlockfile(stdout);
+ tm_print("%-7s %-3s IPv4 %s:%d > %s:%d: %s, length %d%s\n",
+ ifname, pkt_type_str(pkt_type), src_addr, src_port,
+ dst_addr, dst_port, transport_str, len, flags);
}
static void show_ipv6_packet(const u_char *packet, u32 ifindex, u8 pkt_type)
@@ -982,8 +1022,8 @@ static void *traffic_monitor_thread(void *arg)
ifname = _ifname;
}
- printf("%-7s %-3s Unknown network protocol type 0x%x\n",
- ifname, pkt_type_str(ptype), proto);
+ tm_print("%-7s %-3s Unknown network protocol type 0x%x\n",
+ ifname, pkt_type_str(ptype), proto);
}
}
@@ -1183,8 +1223,9 @@ void traffic_monitor_stop(struct tmonitor_ctx *ctx)
write(ctx->wake_fd, &w, sizeof(w));
pthread_join(ctx->thread, NULL);
- printf("Packet file: %s\n", strrchr(ctx->pkt_fname, '/') + 1);
+ tm_print("Packet file: %s\n", strrchr(ctx->pkt_fname, '/') + 1);
traffic_monitor_release(ctx);
}
+
#endif /* TRAFFIC_MONITOR */
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index 9235976d0c50..ef208eefd571 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -18,6 +18,7 @@ typedef __u16 __sum16;
#include <netinet/udp.h>
#include <bpf/bpf_endian.h>
#include <net/if.h>
+#include <stdio.h>
#define MAGIC_VAL 0x1234
#define NUM_ITER 100000
@@ -101,6 +102,18 @@ int send_recv_data(int lfd, int fd, uint32_t total_bytes);
int make_netns(const char *name);
int remove_netns(const char *name);
+/**
+ * append_tid() - Append thread ID to the given string.
+ *
+ * @str: string to extend
+ * @sz: string's size
+ *
+ * 8 characters are used to append the thread ID (7 digits + '\0')
+ *
+ * Returns -1 on errors, 0 otherwise
+ */
+int append_tid(char *str, size_t sz);
+
static __u16 csum_fold(__u32 csum)
{
csum = (csum & 0xffff) + (csum >> 16);
@@ -240,10 +253,13 @@ static inline __sum16 build_udp_v6_csum(const struct ipv6hdr *ip6h,
struct tmonitor_ctx;
+typedef int (*tm_print_fn_t)(const char *format, va_list args);
+
#ifdef TRAFFIC_MONITOR
struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name,
const char *subtest_name);
void traffic_monitor_stop(struct tmonitor_ctx *ctx);
+tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn);
#else
static inline struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name,
const char *subtest_name)
@@ -254,6 +270,11 @@ static inline struct tmonitor_ctx *traffic_monitor_start(const char *netns, cons
static inline void traffic_monitor_stop(struct tmonitor_ctx *ctx)
{
}
+
+static inline tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn)
+{
+ return NULL;
+}
#endif
#endif
diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 4ebd0da898f5..1d53a8561ee2 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -610,9 +610,11 @@ static int do_test_single(struct bpf_align_test *test)
.log_size = sizeof(bpf_vlog),
.log_level = 2,
);
+ const char *main_pass_start = "0: R1=ctx() R10=fp0";
const char *line_ptr;
int cur_line = -1;
int prog_len, i;
+ char *start;
int fd_prog;
int ret;
@@ -632,7 +634,13 @@ static int do_test_single(struct bpf_align_test *test)
ret = 0;
/* We make a local copy so that we can strtok() it */
strncpy(bpf_vlog_copy, bpf_vlog, sizeof(bpf_vlog_copy));
- line_ptr = strtok(bpf_vlog_copy, "\n");
+ start = strstr(bpf_vlog_copy, main_pass_start);
+ if (!start) {
+ ret = 1;
+ printf("Can't find initial line '%s'\n", main_pass_start);
+ goto out;
+ }
+ line_ptr = strtok(start, "\n");
for (i = 0; i < MAX_MATCHES; i++) {
struct bpf_reg_match m = test->matches[i];
const char *p;
@@ -682,6 +690,7 @@ static int do_test_single(struct bpf_align_test *test)
break;
}
}
+out:
if (fd_prog >= 0)
close(fd_prog);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_atomics.c b/tools/testing/selftests/bpf/prog_tests/arena_atomics.c
index 26e7c06c6cb4..d98577a6babc 100644
--- a/tools/testing/selftests/bpf/prog_tests/arena_atomics.c
+++ b/tools/testing/selftests/bpf/prog_tests/arena_atomics.c
@@ -162,6 +162,66 @@ static void test_uaf(struct arena_atomics *skel)
ASSERT_EQ(skel->arena->uaf_recovery_fails, 0, "uaf_recovery_fails");
}
+static void test_load_acquire(struct arena_atomics *skel)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ int err, prog_fd;
+
+ if (skel->data->skip_lacq_srel_tests) {
+ printf("%s:SKIP: ENABLE_ATOMICS_TESTS not defined, Clang doesn't support addr_space_cast, and/or JIT doesn't support load-acquire\n",
+ __func__);
+ test__skip();
+ return;
+ }
+
+ /* No need to attach it, just run it directly */
+ prog_fd = bpf_program__fd(skel->progs.load_acquire);
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ if (!ASSERT_OK(err, "test_run_opts err"))
+ return;
+ if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+ return;
+
+ ASSERT_EQ(skel->arena->load_acquire8_result, 0x12,
+ "load_acquire8_result");
+ ASSERT_EQ(skel->arena->load_acquire16_result, 0x1234,
+ "load_acquire16_result");
+ ASSERT_EQ(skel->arena->load_acquire32_result, 0x12345678,
+ "load_acquire32_result");
+ ASSERT_EQ(skel->arena->load_acquire64_result, 0x1234567890abcdef,
+ "load_acquire64_result");
+}
+
+static void test_store_release(struct arena_atomics *skel)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ int err, prog_fd;
+
+ if (skel->data->skip_lacq_srel_tests) {
+ printf("%s:SKIP: ENABLE_ATOMICS_TESTS not defined, Clang doesn't support addr_space_cast, and/or JIT doesn't support store-release\n",
+ __func__);
+ test__skip();
+ return;
+ }
+
+ /* No need to attach it, just run it directly */
+ prog_fd = bpf_program__fd(skel->progs.store_release);
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ if (!ASSERT_OK(err, "test_run_opts err"))
+ return;
+ if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+ return;
+
+ ASSERT_EQ(skel->arena->store_release8_result, 0x12,
+ "store_release8_result");
+ ASSERT_EQ(skel->arena->store_release16_result, 0x1234,
+ "store_release16_result");
+ ASSERT_EQ(skel->arena->store_release32_result, 0x12345678,
+ "store_release32_result");
+ ASSERT_EQ(skel->arena->store_release64_result, 0x1234567890abcdef,
+ "store_release64_result");
+}
+
void test_arena_atomics(void)
{
struct arena_atomics *skel;
@@ -171,7 +231,7 @@ void test_arena_atomics(void)
if (!ASSERT_OK_PTR(skel, "arena atomics skeleton open"))
return;
- if (skel->data->skip_tests) {
+ if (skel->data->skip_all_tests) {
printf("%s:SKIP:no ENABLE_ATOMICS_TESTS or no addr_space_cast support in clang",
__func__);
test__skip();
@@ -198,6 +258,10 @@ void test_arena_atomics(void)
test_xchg(skel);
if (test__start_subtest("uaf"))
test_uaf(skel);
+ if (test__start_subtest("load_acquire"))
+ test_load_acquire(skel);
+ if (test__start_subtest("store_release"))
+ test_store_release(skel);
cleanup:
arena_atomics__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c
new file mode 100644
index 000000000000..7565fc7690c2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <sys/sysinfo.h>
+
+struct __qspinlock { int val; };
+typedef struct __qspinlock arena_spinlock_t;
+
+struct arena_qnode {
+ unsigned long next;
+ int count;
+ int locked;
+};
+
+#include "arena_spin_lock.skel.h"
+
+static long cpu;
+static int repeat;
+
+pthread_barrier_t barrier;
+
+static void *spin_lock_thread(void *arg)
+{
+ int err, prog_fd = *(u32 *)arg;
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .repeat = repeat,
+ );
+ cpu_set_t cpuset;
+
+ CPU_ZERO(&cpuset);
+ CPU_SET(__sync_fetch_and_add(&cpu, 1), &cpuset);
+ ASSERT_OK(pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset), "cpu affinity");
+
+ err = pthread_barrier_wait(&barrier);
+ if (err != PTHREAD_BARRIER_SERIAL_THREAD && err != 0)
+ ASSERT_FALSE(true, "pthread_barrier");
+
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ ASSERT_OK(err, "test_run err");
+ ASSERT_EQ((int)topts.retval, 0, "test_run retval");
+
+ pthread_exit(arg);
+}
+
+static void test_arena_spin_lock_size(int size)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ struct arena_spin_lock *skel;
+ pthread_t thread_id[16];
+ int prog_fd, i, err;
+ void *ret;
+
+ if (get_nprocs() < 2) {
+ test__skip();
+ return;
+ }
+
+ skel = arena_spin_lock__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "arena_spin_lock__open_and_load"))
+ return;
+ if (skel->data->test_skip == 2) {
+ test__skip();
+ goto end;
+ }
+ skel->bss->cs_count = size;
+ skel->bss->limit = repeat * 16;
+
+ ASSERT_OK(pthread_barrier_init(&barrier, NULL, 16), "barrier init");
+
+ prog_fd = bpf_program__fd(skel->progs.prog);
+ for (i = 0; i < 16; i++) {
+ err = pthread_create(&thread_id[i], NULL, &spin_lock_thread, &prog_fd);
+ if (!ASSERT_OK(err, "pthread_create"))
+ goto end_barrier;
+ }
+
+ for (i = 0; i < 16; i++) {
+ if (!ASSERT_OK(pthread_join(thread_id[i], &ret), "pthread_join"))
+ goto end_barrier;
+ if (!ASSERT_EQ(ret, &prog_fd, "ret == prog_fd"))
+ goto end_barrier;
+ }
+
+ ASSERT_EQ(skel->bss->counter, repeat * 16, "check counter value");
+
+end_barrier:
+ pthread_barrier_destroy(&barrier);
+end:
+ arena_spin_lock__destroy(skel);
+ return;
+}
+
+void test_arena_spin_lock(void)
+{
+ repeat = 1000;
+ if (test__start_subtest("arena_spin_lock_1"))
+ test_arena_spin_lock_size(1);
+ cpu = 0;
+ if (test__start_subtest("arena_spin_lock_1000"))
+ test_arena_spin_lock_size(1000);
+ cpu = 0;
+ repeat = 100;
+ if (test__start_subtest("arena_spin_lock_50000"))
+ test_arena_spin_lock_size(50000);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
index cc184e4420f6..67557cda2208 100644
--- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
@@ -6,6 +6,10 @@
#include <test_progs.h>
#include "bloom_filter_map.skel.h"
+#ifndef NUMA_NO_NODE
+#define NUMA_NO_NODE (-1)
+#endif
+
static void test_fail_cases(void)
{
LIBBPF_OPTS(bpf_map_create_opts, opts);
@@ -69,6 +73,7 @@ static void test_success_cases(void)
/* Create a map */
opts.map_flags = BPF_F_ZERO_SEED | BPF_F_NUMA_NODE;
+ opts.numa_node = NUMA_NO_NODE;
fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 100, &opts);
if (!ASSERT_GE(fd, 0, "bpf_map_create bloom filter success case"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 6f1bfacd7375..add4a18c33bd 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -323,19 +323,87 @@ static void test_task_pidfd(void)
static void test_task_sleepable(void)
{
struct bpf_iter_tasks *skel;
+ int pid, status, err, data_pipe[2], finish_pipe[2], c;
+ char *test_data = NULL;
+ char *test_data_long = NULL;
+ char *data[2];
+
+ if (!ASSERT_OK(pipe(data_pipe), "data_pipe") ||
+ !ASSERT_OK(pipe(finish_pipe), "finish_pipe"))
+ return;
skel = bpf_iter_tasks__open_and_load();
if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load"))
return;
+ pid = fork();
+ if (!ASSERT_GE(pid, 0, "fork"))
+ return;
+
+ if (pid == 0) {
+ /* child */
+ close(data_pipe[0]);
+ close(finish_pipe[1]);
+
+ test_data = malloc(sizeof(char) * 10);
+ strncpy(test_data, "test_data", 10);
+ test_data[9] = '\0';
+
+ test_data_long = malloc(sizeof(char) * 5000);
+ for (int i = 0; i < 5000; ++i) {
+ if (i % 2 == 0)
+ test_data_long[i] = 'b';
+ else
+ test_data_long[i] = 'a';
+ }
+ test_data_long[4999] = '\0';
+
+ data[0] = test_data;
+ data[1] = test_data_long;
+
+ write(data_pipe[1], &data, sizeof(data));
+
+ /* keep child alive until after the test */
+ err = read(finish_pipe[0], &c, 1);
+ if (err != 1)
+ exit(-1);
+
+ close(data_pipe[1]);
+ close(finish_pipe[0]);
+ _exit(0);
+ }
+
+ /* parent */
+ close(data_pipe[1]);
+ close(finish_pipe[0]);
+
+ err = read(data_pipe[0], &data, sizeof(data));
+ ASSERT_EQ(err, sizeof(data), "read_check");
+
+ skel->bss->user_ptr = data[0];
+ skel->bss->user_ptr_long = data[1];
+ skel->bss->pid = pid;
+
do_dummy_read(skel->progs.dump_task_sleepable);
ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task, 0,
"num_expected_failure_copy_from_user_task");
ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0,
"num_success_copy_from_user_task");
+ ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task_str, 0,
+ "num_expected_failure_copy_from_user_task_str");
+ ASSERT_GT(skel->bss->num_success_copy_from_user_task_str, 0,
+ "num_success_copy_from_user_task_str");
bpf_iter_tasks__destroy(skel);
+
+ write(finish_pipe[1], &c, 1);
+ err = waitpid(pid, &status, 0);
+ ASSERT_EQ(err, pid, "waitpid");
+ ASSERT_EQ(status, 0, "zero_child_exit");
+
+ close(data_pipe[0]);
+ close(finish_pipe[1]);
}
static void test_task_stack(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
index a4a1f93878d4..dbd13f8e42a7 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
@@ -72,11 +72,14 @@ static void test_bpf_nf_ct(int mode)
if (!ASSERT_OK(system(cmd), cmd))
goto end;
- srv_port = (mode == TEST_XDP) ? 5005 : 5006;
- srv_fd = start_server(AF_INET, SOCK_STREAM, "127.0.0.1", srv_port, TIMEOUT_MS);
+ srv_fd = start_server(AF_INET, SOCK_STREAM, "127.0.0.1", 0, TIMEOUT_MS);
if (!ASSERT_GE(srv_fd, 0, "start_server"))
goto end;
+ srv_port = get_socket_local_port(srv_fd);
+ if (!ASSERT_GE(srv_port, 0, "get_sock_local_port"))
+ goto end;
+
client_fd = connect_to_server(srv_fd);
if (!ASSERT_GE(client_fd, 0, "connect_to_server"))
goto end;
@@ -91,7 +94,7 @@ static void test_bpf_nf_ct(int mode)
skel->bss->saddr = peer_addr.sin_addr.s_addr;
skel->bss->sport = peer_addr.sin_port;
skel->bss->daddr = peer_addr.sin_addr.s_addr;
- skel->bss->dport = htons(srv_port);
+ skel->bss->dport = srv_port;
if (mode == TEST_XDP)
prog_fd = bpf_program__fd(skel->progs.nf_xdp_ct_test);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index e63d74ce046f..8a9ba4292109 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -3866,11 +3866,11 @@ static struct btf_raw_test raw_tests[] = {
.err_str = "vlen != 0",
},
{
- .descr = "decl_tag test #8, invalid kflag",
+ .descr = "decl_tag test #8, tag with kflag",
.raw_types = {
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */
- BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), 2), (-1),
+ BTF_DECL_ATTR_ENC(NAME_TBD, 2, -1),
BTF_END_RAW,
},
BTF_STR_SEC("\0local\0tag1"),
@@ -3881,8 +3881,6 @@ static struct btf_raw_test raw_tests[] = {
.key_type_id = 1,
.value_type_id = 1,
.max_entries = 1,
- .btf_load_err = true,
- .err_str = "Invalid btf_info kind_flag",
},
{
.descr = "decl_tag test #9, var, invalid component_idx",
@@ -4207,6 +4205,23 @@ static struct btf_raw_test raw_tests[] = {
.err_str = "Type tags don't precede modifiers",
},
{
+ .descr = "type_tag test #7, tag with kflag",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ATTR_ENC(NAME_TBD, 1), /* [2] */
+ BTF_PTR_ENC(2), /* [3] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0tag"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "tag_type_check_btf",
+ .key_size = sizeof(int),
+ .value_size = 4,
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 1,
+},
+{
.descr = "enum64 test #1, unsigned, size 8",
.raw_types = {
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index b293b8501fd6..c0a776feec23 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -126,26 +126,69 @@ done:
return err;
}
-static char *dump_buf;
-static size_t dump_buf_sz;
-static FILE *dump_buf_file;
+struct test_ctx {
+ struct btf *btf;
+ struct btf_dump *d;
+ char *dump_buf;
+ size_t dump_buf_sz;
+ FILE *dump_buf_file;
+};
-static void test_btf_dump_incremental(void)
+static void test_ctx__free(struct test_ctx *t)
{
- struct btf *btf = NULL;
- struct btf_dump *d = NULL;
- int id, err, i;
+ fclose(t->dump_buf_file);
+ free(t->dump_buf);
+ btf_dump__free(t->d);
+ btf__free(t->btf);
+}
- dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz);
- if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream"))
- return;
- btf = btf__new_empty();
- if (!ASSERT_OK_PTR(btf, "new_empty"))
+static int test_ctx__init(struct test_ctx *t)
+{
+ t->dump_buf_file = open_memstream(&t->dump_buf, &t->dump_buf_sz);
+ if (!ASSERT_OK_PTR(t->dump_buf_file, "dump_memstream"))
+ return -1;
+ t->btf = btf__new_empty();
+ if (!ASSERT_OK_PTR(t->btf, "new_empty"))
goto err_out;
- d = btf_dump__new(btf, btf_dump_printf, dump_buf_file, NULL);
- if (!ASSERT_OK(libbpf_get_error(d), "btf_dump__new"))
+ t->d = btf_dump__new(t->btf, btf_dump_printf, t->dump_buf_file, NULL);
+ if (!ASSERT_OK(libbpf_get_error(t->d), "btf_dump__new"))
goto err_out;
+ return 0;
+
+err_out:
+ test_ctx__free(t);
+ return -1;
+}
+
+static void test_ctx__dump_and_compare(struct test_ctx *t,
+ const char *expected_output,
+ const char *message)
+{
+ int i, err;
+
+ for (i = 1; i < btf__type_cnt(t->btf); i++) {
+ err = btf_dump__dump_type(t->d, i);
+ ASSERT_OK(err, "dump_type_ok");
+ }
+
+ fflush(t->dump_buf_file);
+ t->dump_buf[t->dump_buf_sz] = 0; /* some libc implementations don't do this */
+
+ ASSERT_STREQ(t->dump_buf, expected_output, message);
+}
+
+static void test_btf_dump_incremental(void)
+{
+ struct test_ctx t = {};
+ struct btf *btf;
+ int id, err;
+
+ if (test_ctx__init(&t))
+ return;
+
+ btf = t.btf;
+
/* First, generate BTF corresponding to the following C code:
*
* enum x;
@@ -182,15 +225,7 @@ static void test_btf_dump_incremental(void)
err = btf__add_field(btf, "x", 4, 0, 0);
ASSERT_OK(err, "field_ok");
- for (i = 1; i < btf__type_cnt(btf); i++) {
- err = btf_dump__dump_type(d, i);
- ASSERT_OK(err, "dump_type_ok");
- }
-
- fflush(dump_buf_file);
- dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
-
- ASSERT_STREQ(dump_buf,
+ test_ctx__dump_and_compare(&t,
"enum x;\n"
"\n"
"enum x {\n"
@@ -221,7 +256,7 @@ static void test_btf_dump_incremental(void)
* enum values don't conflict;
*
*/
- fseek(dump_buf_file, 0, SEEK_SET);
+ fseek(t.dump_buf_file, 0, SEEK_SET);
id = btf__add_struct(btf, "s", 4);
ASSERT_EQ(id, 7, "struct_id");
@@ -232,14 +267,7 @@ static void test_btf_dump_incremental(void)
err = btf__add_field(btf, "s", 6, 64, 0);
ASSERT_OK(err, "field_ok");
- for (i = 1; i < btf__type_cnt(btf); i++) {
- err = btf_dump__dump_type(d, i);
- ASSERT_OK(err, "dump_type_ok");
- }
-
- fflush(dump_buf_file);
- dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
- ASSERT_STREQ(dump_buf,
+ test_ctx__dump_and_compare(&t,
"struct s___2 {\n"
" enum x x;\n"
" enum {\n"
@@ -248,11 +276,53 @@ static void test_btf_dump_incremental(void)
" struct s s;\n"
"};\n\n" , "c_dump1");
-err_out:
- fclose(dump_buf_file);
- free(dump_buf);
- btf_dump__free(d);
- btf__free(btf);
+ test_ctx__free(&t);
+}
+
+static void test_btf_dump_type_tags(void)
+{
+ struct test_ctx t = {};
+ struct btf *btf;
+ int id, err;
+
+ if (test_ctx__init(&t))
+ return;
+
+ btf = t.btf;
+
+ /* Generate BTF corresponding to the following C code:
+ *
+ * struct s {
+ * void __attribute__((btf_type_tag(\"void_tag\"))) *p1;
+ * void __attribute__((void_attr)) *p2;
+ * };
+ *
+ */
+
+ id = btf__add_type_tag(btf, "void_tag", 0);
+ ASSERT_EQ(id, 1, "type_tag_id");
+ id = btf__add_ptr(btf, id);
+ ASSERT_EQ(id, 2, "void_ptr_id1");
+
+ id = btf__add_type_attr(btf, "void_attr", 0);
+ ASSERT_EQ(id, 3, "type_attr_id");
+ id = btf__add_ptr(btf, id);
+ ASSERT_EQ(id, 4, "void_ptr_id2");
+
+ id = btf__add_struct(btf, "s", 8);
+ ASSERT_EQ(id, 5, "struct_id");
+ err = btf__add_field(btf, "p1", 2, 0, 0);
+ ASSERT_OK(err, "field_ok1");
+ err = btf__add_field(btf, "p2", 4, 0, 0);
+ ASSERT_OK(err, "field_ok2");
+
+ test_ctx__dump_and_compare(&t,
+"struct s {\n"
+" void __attribute__((btf_type_tag(\"void_tag\"))) *p1;\n"
+" void __attribute__((void_attr)) *p2;\n"
+"};\n\n", "dump_and_compare");
+
+ test_ctx__free(&t);
}
#define STRSIZE 4096
@@ -874,6 +944,9 @@ void test_btf_dump() {
if (test__start_subtest("btf_dump: incremental"))
test_btf_dump_incremental();
+ if (test__start_subtest("btf_dump: type_tags"))
+ test_btf_dump_type_tags();
+
btf = libbpf_find_kernel_btf();
if (!ASSERT_OK_PTR(btf, "no kernel BTF found"))
return;
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c b/tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c
new file mode 100644
index 000000000000..d4d583872fa2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "cgroup_preorder.skel.h"
+
+static int run_getsockopt_test(int cg_parent, int cg_child, int sock_fd, bool all_preorder)
+{
+ LIBBPF_OPTS(bpf_prog_attach_opts, opts);
+ enum bpf_attach_type prog_c_atype, prog_c2_atype, prog_p_atype, prog_p2_atype;
+ int prog_c_fd, prog_c2_fd, prog_p_fd, prog_p2_fd;
+ struct cgroup_preorder *skel = NULL;
+ struct bpf_program *prog;
+ __u8 *result, buf;
+ socklen_t optlen;
+ int err = 0;
+
+ skel = cgroup_preorder__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "cgroup_preorder__open_and_load"))
+ return 0;
+
+ buf = 0x00;
+ err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+ if (!ASSERT_OK(err, "setsockopt"))
+ goto close_skel;
+
+ opts.flags = BPF_F_ALLOW_MULTI;
+ if (all_preorder)
+ opts.flags |= BPF_F_PREORDER;
+ prog = skel->progs.child;
+ prog_c_fd = bpf_program__fd(prog);
+ prog_c_atype = bpf_program__expected_attach_type(prog);
+ err = bpf_prog_attach_opts(prog_c_fd, cg_child, prog_c_atype, &opts);
+ if (!ASSERT_OK(err, "bpf_prog_attach_opts-child"))
+ goto close_skel;
+
+ opts.flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER;
+ prog = skel->progs.child_2;
+ prog_c2_fd = bpf_program__fd(prog);
+ prog_c2_atype = bpf_program__expected_attach_type(prog);
+ err = bpf_prog_attach_opts(prog_c2_fd, cg_child, prog_c2_atype, &opts);
+ if (!ASSERT_OK(err, "bpf_prog_attach_opts-child_2"))
+ goto detach_child;
+
+ optlen = 1;
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (!ASSERT_OK(err, "getsockopt"))
+ goto detach_child_2;
+
+ result = skel->bss->result;
+ if (all_preorder)
+ ASSERT_TRUE(result[0] == 1 && result[1] == 2, "child only");
+ else
+ ASSERT_TRUE(result[0] == 2 && result[1] == 1, "child only");
+
+ skel->bss->idx = 0;
+ memset(result, 0, 4);
+
+ opts.flags = BPF_F_ALLOW_MULTI;
+ if (all_preorder)
+ opts.flags |= BPF_F_PREORDER;
+ prog = skel->progs.parent;
+ prog_p_fd = bpf_program__fd(prog);
+ prog_p_atype = bpf_program__expected_attach_type(prog);
+ err = bpf_prog_attach_opts(prog_p_fd, cg_parent, prog_p_atype, &opts);
+ if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent"))
+ goto detach_child_2;
+
+ opts.flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER;
+ prog = skel->progs.parent_2;
+ prog_p2_fd = bpf_program__fd(prog);
+ prog_p2_atype = bpf_program__expected_attach_type(prog);
+ err = bpf_prog_attach_opts(prog_p2_fd, cg_parent, prog_p2_atype, &opts);
+ if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent_2"))
+ goto detach_parent;
+
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (!ASSERT_OK(err, "getsockopt"))
+ goto detach_parent_2;
+
+ if (all_preorder)
+ ASSERT_TRUE(result[0] == 3 && result[1] == 4 && result[2] == 1 && result[3] == 2,
+ "parent and child");
+ else
+ ASSERT_TRUE(result[0] == 4 && result[1] == 2 && result[2] == 1 && result[3] == 3,
+ "parent and child");
+
+detach_parent_2:
+ ASSERT_OK(bpf_prog_detach2(prog_p2_fd, cg_parent, prog_p2_atype),
+ "bpf_prog_detach2-parent_2");
+detach_parent:
+ ASSERT_OK(bpf_prog_detach2(prog_p_fd, cg_parent, prog_p_atype),
+ "bpf_prog_detach2-parent");
+detach_child_2:
+ ASSERT_OK(bpf_prog_detach2(prog_c2_fd, cg_child, prog_c2_atype),
+ "bpf_prog_detach2-child_2");
+detach_child:
+ ASSERT_OK(bpf_prog_detach2(prog_c_fd, cg_child, prog_c_atype),
+ "bpf_prog_detach2-child");
+close_skel:
+ cgroup_preorder__destroy(skel);
+ return err;
+}
+
+void test_cgroup_preorder(void)
+{
+ int cg_parent = -1, cg_child = -1, sock_fd = -1;
+
+ cg_parent = test__join_cgroup("/parent");
+ if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent"))
+ goto out;
+
+ cg_child = test__join_cgroup("/parent/child");
+ if (!ASSERT_GE(cg_child, 0, "join_cgroup /parent/child"))
+ goto out;
+
+ sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+ if (!ASSERT_GE(sock_fd, 0, "socket"))
+ goto out;
+
+ ASSERT_OK(run_getsockopt_test(cg_parent, cg_child, sock_fd, false), "getsockopt_test_1");
+ ASSERT_OK(run_getsockopt_test(cg_parent, cg_child, sock_fd, true), "getsockopt_test_2");
+
+out:
+ close(sock_fd);
+ close(cg_child);
+ close(cg_parent);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
index 64abba72ac10..37c1cc52ed98 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
@@ -10,12 +10,18 @@
static int run_test(int cgroup_fd, int server_fd, bool classid)
{
struct connect4_dropper *skel;
- int fd, err = 0;
+ int fd, err = 0, port;
skel = connect4_dropper__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_open"))
return -1;
+ port = get_socket_local_port(server_fd);
+ if (!ASSERT_GE(port, 0, "get_socket_local_port"))
+ return -1;
+
+ skel->bss->port = ntohs(port);
+
skel->links.connect_v4_dropper =
bpf_program__attach_cgroup(skel->progs.connect_v4_dropper,
cgroup_fd);
@@ -48,10 +54,9 @@ void test_cgroup_v1v2(void)
{
struct network_helper_opts opts = {};
int server_fd, client_fd, cgroup_fd;
- static const int port = 60120;
/* Step 1: Check base connectivity works without any BPF. */
- server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
+ server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
if (!ASSERT_GE(server_fd, 0, "server_fd"))
return;
client_fd = connect_to_fd_opts(server_fd, &opts);
@@ -66,7 +71,7 @@ void test_cgroup_v1v2(void)
cgroup_fd = test__join_cgroup("/connect_dropper");
if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd"))
return;
- server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
+ server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
if (!ASSERT_GE(server_fd, 0, "server_fd")) {
close(cgroup_fd);
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
deleted file mode 100644
index 7526de379081..000000000000
--- a/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c
+++ /dev/null
@@ -1,107 +0,0 @@
-// 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/compute_live_registers.c b/tools/testing/selftests/bpf/prog_tests/compute_live_registers.c
new file mode 100644
index 000000000000..285f20241fe1
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/compute_live_registers.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "compute_live_registers.skel.h"
+#include "test_progs.h"
+
+void test_compute_live_registers(void)
+{
+ RUN_TESTS(compute_live_registers);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index e10ea92c3fe2..08963c82f30b 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -85,11 +85,11 @@ static int duration = 0;
#define NESTING_ERR_CASE(name) { \
NESTING_CASE_COMMON(name), \
.fails = true, \
- .run_btfgen_fails = true, \
+ .run_btfgen_fails = true, \
}
#define ARRAYS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \
- .a = { [2] = 1 }, \
+ .a = { [2] = 1, [3] = 11 }, \
.b = { [1] = { [2] = { [3] = 2 } } }, \
.c = { [1] = { .c = 3 } }, \
.d = { [0] = { [0] = { .d = 4 } } }, \
@@ -108,6 +108,7 @@ static int duration = 0;
.input_len = sizeof(struct core_reloc_##name), \
.output = STRUCT_TO_CHAR_PTR(core_reloc_arrays_output) { \
.a2 = 1, \
+ .a3 = 12, \
.b123 = 2, \
.c1c = 3, \
.d00d = 4, \
@@ -602,6 +603,7 @@ static const struct core_reloc_test_case test_cases[] = {
ARRAYS_ERR_CASE(arrays___err_non_array),
ARRAYS_ERR_CASE(arrays___err_wrong_val_type),
ARRAYS_ERR_CASE(arrays___err_bad_zero_sz_arr),
+ ARRAYS_ERR_CASE(arrays___err_bad_signed_arr_elem_sz),
/* enum/ptr/int handling scenarios */
PRIMITIVES_CASE(primitives),
diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c
index e58a04654238..6c45330a5ca3 100644
--- a/tools/testing/selftests/bpf/prog_tests/cpumask.c
+++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c
@@ -25,6 +25,10 @@ static const char * const cpumask_success_testcases[] = {
"test_global_mask_nested_deep_rcu",
"test_global_mask_nested_deep_array_rcu",
"test_cpumask_weight",
+ "test_refcount_null_tracking",
+ "test_populate_reject_small_mask",
+ "test_populate_reject_unaligned",
+ "test_populate",
};
static void verify_success(const char *prog_name)
@@ -78,6 +82,5 @@ void test_cpumask(void)
verify_success(cpumask_success_testcases[i]);
}
- RUN_TESTS(cpumask_success);
RUN_TESTS(cpumask_failure);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c
index b614a5272dfd..e29cc16124c2 100644
--- a/tools/testing/selftests/bpf/prog_tests/dynptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c
@@ -10,6 +10,7 @@ enum test_setup_type {
SETUP_SYSCALL_SLEEP,
SETUP_SKB_PROG,
SETUP_SKB_PROG_TP,
+ SETUP_XDP_PROG,
};
static struct {
@@ -18,6 +19,8 @@ static struct {
} success_tests[] = {
{"test_read_write", SETUP_SYSCALL_SLEEP},
{"test_dynptr_data", SETUP_SYSCALL_SLEEP},
+ {"test_dynptr_copy", SETUP_SYSCALL_SLEEP},
+ {"test_dynptr_copy_xdp", SETUP_XDP_PROG},
{"test_ringbuf", SETUP_SYSCALL_SLEEP},
{"test_skb_readonly", SETUP_SKB_PROG},
{"test_dynptr_skb_data", SETUP_SKB_PROG},
@@ -120,6 +123,24 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
break;
}
+ case SETUP_XDP_PROG:
+ {
+ char data[5000];
+ int err, prog_fd;
+ LIBBPF_OPTS(bpf_test_run_opts, opts,
+ .data_in = &data,
+ .data_size_in = sizeof(data),
+ .repeat = 1,
+ );
+
+ prog_fd = bpf_program__fd(prog);
+ err = bpf_prog_test_run_opts(prog_fd, &opts);
+
+ if (!ASSERT_OK(err, "test_run"))
+ goto cleanup;
+
+ break;
+ }
}
ASSERT_EQ(skel->bss->err, 0, "err");
diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c
index a1d52e73fb16..9add890c2d37 100644
--- a/tools/testing/selftests/bpf/prog_tests/fd_array.c
+++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c
@@ -83,8 +83,8 @@ static inline int bpf_prog_get_map_ids(int prog_fd, __u32 *nr_map_ids, __u32 *ma
int err;
memset(&info, 0, len);
- info.nr_map_ids = *nr_map_ids,
- info.map_ids = ptr_to_u64(map_ids),
+ info.nr_map_ids = *nr_map_ids;
+ info.map_ids = ptr_to_u64(map_ids);
err = bpf_prog_get_info_by_fd(prog_fd, &info, &len);
if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c b/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c
new file mode 100644
index 000000000000..568d3aa48a78
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_noreturns.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "fexit_noreturns.skel.h"
+
+void test_fexit_noreturns(void)
+{
+ RUN_TESTS(fexit_noreturns);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
index 5a0b51157451..43a26ec69a8e 100644
--- a/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
+++ b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
@@ -8,11 +8,12 @@
#include <unistd.h>
#include <test_progs.h>
#include "test_get_xattr.skel.h"
+#include "test_set_remove_xattr.skel.h"
#include "test_fsverity.skel.h"
static const char testfile[] = "/tmp/test_progs_fs_kfuncs";
-static void test_xattr(void)
+static void test_get_xattr(const char *name, const char *value, bool allow_access)
{
struct test_get_xattr *skel = NULL;
int fd = -1, err;
@@ -25,7 +26,7 @@ static void test_xattr(void)
close(fd);
fd = -1;
- err = setxattr(testfile, "user.kfuncs", "hello", sizeof("hello"), 0);
+ err = setxattr(testfile, name, value, strlen(value) + 1, 0);
if (err && errno == EOPNOTSUPP) {
printf("%s:SKIP:local fs doesn't support xattr (%d)\n"
"To run this test, make sure /tmp filesystem supports xattr.\n",
@@ -48,16 +49,23 @@ static void test_xattr(void)
goto out;
fd = open(testfile, O_RDONLY, 0644);
+
if (!ASSERT_GE(fd, 0, "open_file"))
goto out;
- ASSERT_EQ(skel->bss->found_xattr_from_file, 1, "found_xattr_from_file");
-
/* Trigger security_inode_getxattr */
- err = getxattr(testfile, "user.kfuncs", v, sizeof(v));
- ASSERT_EQ(err, -1, "getxattr_return");
- ASSERT_EQ(errno, EINVAL, "getxattr_errno");
- ASSERT_EQ(skel->bss->found_xattr_from_dentry, 1, "found_xattr_from_dentry");
+ err = getxattr(testfile, name, v, sizeof(v));
+
+ if (allow_access) {
+ ASSERT_EQ(err, -1, "getxattr_return");
+ ASSERT_EQ(errno, EINVAL, "getxattr_errno");
+ ASSERT_EQ(skel->bss->found_xattr_from_file, 1, "found_xattr_from_file");
+ ASSERT_EQ(skel->bss->found_xattr_from_dentry, 1, "found_xattr_from_dentry");
+ } else {
+ ASSERT_EQ(err, strlen(value) + 1, "getxattr_return");
+ ASSERT_EQ(skel->bss->found_xattr_from_file, 0, "found_xattr_from_file");
+ ASSERT_EQ(skel->bss->found_xattr_from_dentry, 0, "found_xattr_from_dentry");
+ }
out:
close(fd);
@@ -65,6 +73,127 @@ out:
remove(testfile);
}
+/* xattr value we will set to security.bpf.foo */
+static const char value_foo[] = "hello";
+
+static void read_and_validate_foo(struct test_set_remove_xattr *skel)
+{
+ char value_out[32];
+ int err;
+
+ err = getxattr(testfile, skel->rodata->xattr_foo, value_out, sizeof(value_out));
+ ASSERT_EQ(err, sizeof(value_foo), "getxattr size foo");
+ ASSERT_EQ(strncmp(value_out, value_foo, sizeof(value_foo)), 0, "strncmp value_foo");
+}
+
+static void set_foo(struct test_set_remove_xattr *skel)
+{
+ ASSERT_OK(setxattr(testfile, skel->rodata->xattr_foo, value_foo, strlen(value_foo) + 1, 0),
+ "setxattr foo");
+}
+
+static void validate_bar_match(struct test_set_remove_xattr *skel)
+{
+ char value_out[32];
+ int err;
+
+ err = getxattr(testfile, skel->rodata->xattr_bar, value_out, sizeof(value_out));
+ ASSERT_EQ(err, sizeof(skel->data->value_bar), "getxattr size bar");
+ ASSERT_EQ(strncmp(value_out, skel->data->value_bar, sizeof(skel->data->value_bar)), 0,
+ "strncmp value_bar");
+}
+
+static void validate_bar_removed(struct test_set_remove_xattr *skel)
+{
+ char value_out[32];
+ int err;
+
+ err = getxattr(testfile, skel->rodata->xattr_bar, value_out, sizeof(value_out));
+ ASSERT_LT(err, 0, "getxattr size bar should fail");
+}
+
+static void test_set_remove_xattr(void)
+{
+ struct test_set_remove_xattr *skel = NULL;
+ int fd = -1, err;
+
+ fd = open(testfile, O_CREAT | O_RDONLY, 0644);
+ if (!ASSERT_GE(fd, 0, "create_file"))
+ return;
+
+ close(fd);
+ fd = -1;
+
+ skel = test_set_remove_xattr__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_set_remove_xattr__open_and_load"))
+ return;
+
+ /* Set security.bpf.foo to "hello" */
+ err = setxattr(testfile, skel->rodata->xattr_foo, value_foo, strlen(value_foo) + 1, 0);
+ if (err && errno == EOPNOTSUPP) {
+ printf("%s:SKIP:local fs doesn't support xattr (%d)\n"
+ "To run this test, make sure /tmp filesystem supports xattr.\n",
+ __func__, errno);
+ test__skip();
+ goto out;
+ }
+
+ if (!ASSERT_OK(err, "setxattr"))
+ goto out;
+
+ skel->bss->monitored_pid = getpid();
+ err = test_set_remove_xattr__attach(skel);
+ if (!ASSERT_OK(err, "test_set_remove_xattr__attach"))
+ goto out;
+
+ /* First, test not _locked version of the kfuncs with getxattr. */
+
+ /* Read security.bpf.foo and trigger test_inode_getxattr. This
+ * bpf program will set security.bpf.bar to "world".
+ */
+ read_and_validate_foo(skel);
+ validate_bar_match(skel);
+
+ /* Read security.bpf.foo and trigger test_inode_getxattr again.
+ * This will remove xattr security.bpf.bar.
+ */
+ read_and_validate_foo(skel);
+ validate_bar_removed(skel);
+
+ ASSERT_TRUE(skel->bss->set_security_bpf_bar_success, "set_security_bpf_bar_success");
+ ASSERT_TRUE(skel->bss->remove_security_bpf_bar_success, "remove_security_bpf_bar_success");
+ ASSERT_TRUE(skel->bss->set_security_selinux_fail, "set_security_selinux_fail");
+ ASSERT_TRUE(skel->bss->remove_security_selinux_fail, "remove_security_selinux_fail");
+
+ /* Second, test _locked version of the kfuncs, with setxattr */
+
+ /* Set security.bpf.foo and trigger test_inode_setxattr. This
+ * bpf program will set security.bpf.bar to "world".
+ */
+ set_foo(skel);
+ validate_bar_match(skel);
+
+ /* Set security.bpf.foo and trigger test_inode_setxattr again.
+ * This will remove xattr security.bpf.bar.
+ */
+ set_foo(skel);
+ validate_bar_removed(skel);
+
+ ASSERT_TRUE(skel->bss->locked_set_security_bpf_bar_success,
+ "locked_set_security_bpf_bar_success");
+ ASSERT_TRUE(skel->bss->locked_remove_security_bpf_bar_success,
+ "locked_remove_security_bpf_bar_success");
+ ASSERT_TRUE(skel->bss->locked_set_security_selinux_fail,
+ "locked_set_security_selinux_fail");
+ ASSERT_TRUE(skel->bss->locked_remove_security_selinux_fail,
+ "locked_remove_security_selinux_fail");
+
+out:
+ close(fd);
+ test_set_remove_xattr__destroy(skel);
+ remove(testfile);
+}
+
#ifndef SHA256_DIGEST_SIZE
#define SHA256_DIGEST_SIZE 32
#endif
@@ -141,8 +270,21 @@ out:
void test_fs_kfuncs(void)
{
- if (test__start_subtest("xattr"))
- test_xattr();
+ /* Matches xattr_names in progs/test_get_xattr.c */
+ if (test__start_subtest("user_xattr"))
+ test_get_xattr("user.kfuncs", "hello", true);
+
+ if (test__start_subtest("security_bpf_xattr"))
+ test_get_xattr("security.bpf.xxx", "hello", true);
+
+ if (test__start_subtest("security_bpf_xattr_error"))
+ test_get_xattr("security.bpf", "hello", false);
+
+ if (test__start_subtest("security_selinux_xattr_error"))
+ test_get_xattr("security.selinux", "hello", false);
+
+ if (test__start_subtest("set_remove_xattr"))
+ test_set_remove_xattr();
if (test__start_subtest("fsverity"))
test_fsverity();
diff --git a/tools/testing/selftests/bpf/prog_tests/kernel_flag.c b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c
new file mode 100644
index 000000000000..a133354ac9bc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Microsoft */
+#include <test_progs.h>
+#include "kfunc_call_test.skel.h"
+#include "kfunc_call_test.lskel.h"
+#include "test_kernel_flag.skel.h"
+
+void test_kernel_flag(void)
+{
+ struct test_kernel_flag *lsm_skel;
+ struct kfunc_call_test *skel = NULL;
+ struct kfunc_call_test_lskel *lskel = NULL;
+ int ret;
+
+ lsm_skel = test_kernel_flag__open_and_load();
+ if (!ASSERT_OK_PTR(lsm_skel, "lsm_skel"))
+ return;
+
+ lsm_skel->bss->monitored_tid = gettid();
+
+ ret = test_kernel_flag__attach(lsm_skel);
+ if (!ASSERT_OK(ret, "test_kernel_flag__attach"))
+ goto close_prog;
+
+ /* Test with skel. This should pass the gatekeeper */
+ skel = kfunc_call_test__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel"))
+ goto close_prog;
+
+ /* Test with lskel. This should fail due to blocking kernel-based bpf() invocations */
+ lskel = kfunc_call_test_lskel__open_and_load();
+ if (!ASSERT_ERR_PTR(lskel, "lskel"))
+ goto close_prog;
+
+close_prog:
+ if (skel)
+ kfunc_call_test__destroy(skel);
+ if (lskel)
+ kfunc_call_test_lskel__destroy(lskel);
+
+ lsm_skel->bss->monitored_tid = 0;
+ test_kernel_flag__destroy(lsm_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c
new file mode 100644
index 000000000000..b6391af5f6f9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c
@@ -0,0 +1,540 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <netinet/in.h>
+
+#include "network_helpers.h"
+#include "test_progs.h"
+
+#define BPF_FILE "test_lwt_ip_encap.bpf.o"
+
+#define NETNS_NAME_SIZE 32
+#define NETNS_BASE "ns-lwt-ip-encap"
+
+#define IP4_ADDR_1 "172.16.1.100"
+#define IP4_ADDR_2 "172.16.2.100"
+#define IP4_ADDR_3 "172.16.3.100"
+#define IP4_ADDR_4 "172.16.4.100"
+#define IP4_ADDR_5 "172.16.5.100"
+#define IP4_ADDR_6 "172.16.6.100"
+#define IP4_ADDR_7 "172.16.7.100"
+#define IP4_ADDR_8 "172.16.8.100"
+#define IP4_ADDR_GRE "172.16.16.100"
+
+#define IP4_ADDR_SRC IP4_ADDR_1
+#define IP4_ADDR_DST IP4_ADDR_4
+
+#define IP6_ADDR_1 "fb01::1"
+#define IP6_ADDR_2 "fb02::1"
+#define IP6_ADDR_3 "fb03::1"
+#define IP6_ADDR_4 "fb04::1"
+#define IP6_ADDR_5 "fb05::1"
+#define IP6_ADDR_6 "fb06::1"
+#define IP6_ADDR_7 "fb07::1"
+#define IP6_ADDR_8 "fb08::1"
+#define IP6_ADDR_GRE "fb10::1"
+
+#define IP6_ADDR_SRC IP6_ADDR_1
+#define IP6_ADDR_DST IP6_ADDR_4
+
+/* Setup/topology:
+ *
+ * NS1 NS2 NS3
+ * veth1 <---> veth2 veth3 <---> veth4 (the top route)
+ * veth5 <---> veth6 veth7 <---> veth8 (the bottom route)
+ *
+ * Each vethN gets IP[4|6]_ADDR_N address.
+ *
+ * IP*_ADDR_SRC = IP*_ADDR_1
+ * IP*_ADDR_DST = IP*_ADDR_4
+ *
+ * All tests test pings from IP*_ADDR__SRC to IP*_ADDR_DST.
+ *
+ * By default, routes are configured to allow packets to go
+ * IP*_ADDR_1 <=> IP*_ADDR_2 <=> IP*_ADDR_3 <=> IP*_ADDR_4 (the top route).
+ *
+ * A GRE device is installed in NS3 with IP*_ADDR_GRE, and
+ * NS1/NS2 are configured to route packets to IP*_ADDR_GRE via IP*_ADDR_8
+ * (the bottom route).
+ *
+ * Tests:
+ *
+ * 1. Routes NS2->IP*_ADDR_DST are brought down, so the only way a ping
+ * from IP*_ADDR_SRC to IP*_ADDR_DST can work is via IP*_ADDR_GRE.
+ *
+ * 2a. In an egress test, a bpf LWT_XMIT program is installed on veth1
+ * that encaps the packets with an IP/GRE header to route to IP*_ADDR_GRE.
+ *
+ * ping: SRC->[encap at veth1:egress]->GRE:decap->DST
+ * ping replies go DST->SRC directly
+ *
+ * 2b. In an ingress test, a bpf LWT_IN program is installed on veth2
+ * that encaps the packets with an IP/GRE header to route to IP*_ADDR_GRE.
+ *
+ * ping: SRC->[encap at veth2:ingress]->GRE:decap->DST
+ * ping replies go DST->SRC directly
+ */
+
+static int create_ns(char *name, size_t name_sz)
+{
+ if (!name)
+ goto fail;
+
+ if (!ASSERT_OK(append_tid(name, name_sz), "append TID"))
+ goto fail;
+
+ SYS(fail, "ip netns add %s", name);
+
+ /* rp_filter gets confused by what these tests are doing, so disable it */
+ SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.conf.all.rp_filter=0", name);
+ SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.conf.default.rp_filter=0", name);
+ /* Disable IPv6 DAD because it sometimes takes too long and fails tests */
+ SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.all.accept_dad=0", name);
+ SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.default.accept_dad=0", name);
+
+ return 0;
+fail:
+ return -1;
+}
+
+static int set_top_addr(const char *ns1, const char *ns2, const char *ns3)
+{
+ SYS(fail, "ip -n %s a add %s/24 dev veth1", ns1, IP4_ADDR_1);
+ SYS(fail, "ip -n %s a add %s/24 dev veth2", ns2, IP4_ADDR_2);
+ SYS(fail, "ip -n %s a add %s/24 dev veth3", ns2, IP4_ADDR_3);
+ SYS(fail, "ip -n %s a add %s/24 dev veth4", ns3, IP4_ADDR_4);
+ SYS(fail, "ip -n %s -6 a add %s/128 dev veth1", ns1, IP6_ADDR_1);
+ SYS(fail, "ip -n %s -6 a add %s/128 dev veth2", ns2, IP6_ADDR_2);
+ SYS(fail, "ip -n %s -6 a add %s/128 dev veth3", ns2, IP6_ADDR_3);
+ SYS(fail, "ip -n %s -6 a add %s/128 dev veth4", ns3, IP6_ADDR_4);
+
+ SYS(fail, "ip -n %s link set dev veth1 up", ns1);
+ SYS(fail, "ip -n %s link set dev veth2 up", ns2);
+ SYS(fail, "ip -n %s link set dev veth3 up", ns2);
+ SYS(fail, "ip -n %s link set dev veth4 up", ns3);
+
+ return 0;
+fail:
+ return 1;
+}
+
+static int set_bottom_addr(const char *ns1, const char *ns2, const char *ns3)
+{
+ SYS(fail, "ip -n %s a add %s/24 dev veth5", ns1, IP4_ADDR_5);
+ SYS(fail, "ip -n %s a add %s/24 dev veth6", ns2, IP4_ADDR_6);
+ SYS(fail, "ip -n %s a add %s/24 dev veth7", ns2, IP4_ADDR_7);
+ SYS(fail, "ip -n %s a add %s/24 dev veth8", ns3, IP4_ADDR_8);
+ SYS(fail, "ip -n %s -6 a add %s/128 dev veth5", ns1, IP6_ADDR_5);
+ SYS(fail, "ip -n %s -6 a add %s/128 dev veth6", ns2, IP6_ADDR_6);
+ SYS(fail, "ip -n %s -6 a add %s/128 dev veth7", ns2, IP6_ADDR_7);
+ SYS(fail, "ip -n %s -6 a add %s/128 dev veth8", ns3, IP6_ADDR_8);
+
+ SYS(fail, "ip -n %s link set dev veth5 up", ns1);
+ SYS(fail, "ip -n %s link set dev veth6 up", ns2);
+ SYS(fail, "ip -n %s link set dev veth7 up", ns2);
+ SYS(fail, "ip -n %s link set dev veth8 up", ns3);
+
+ return 0;
+fail:
+ return 1;
+}
+
+static int configure_vrf(const char *ns1, const char *ns2)
+{
+ if (!ns1 || !ns2)
+ goto fail;
+
+ SYS(fail, "ip -n %s link add red type vrf table 1001", ns1);
+ SYS(fail, "ip -n %s link set red up", ns1);
+ SYS(fail, "ip -n %s route add table 1001 unreachable default metric 8192", ns1);
+ SYS(fail, "ip -n %s -6 route add table 1001 unreachable default metric 8192", ns1);
+ SYS(fail, "ip -n %s link set veth1 vrf red", ns1);
+ SYS(fail, "ip -n %s link set veth5 vrf red", ns1);
+
+ SYS(fail, "ip -n %s link add red type vrf table 1001", ns2);
+ SYS(fail, "ip -n %s link set red up", ns2);
+ SYS(fail, "ip -n %s route add table 1001 unreachable default metric 8192", ns2);
+ SYS(fail, "ip -n %s -6 route add table 1001 unreachable default metric 8192", ns2);
+ SYS(fail, "ip -n %s link set veth2 vrf red", ns2);
+ SYS(fail, "ip -n %s link set veth3 vrf red", ns2);
+ SYS(fail, "ip -n %s link set veth6 vrf red", ns2);
+ SYS(fail, "ip -n %s link set veth7 vrf red", ns2);
+
+ return 0;
+fail:
+ return -1;
+}
+
+static int configure_ns1(const char *ns1, const char *vrf)
+{
+ struct nstoken *nstoken = NULL;
+
+ if (!ns1 || !vrf)
+ goto fail;
+
+ nstoken = open_netns(ns1);
+ if (!ASSERT_OK_PTR(nstoken, "open ns1"))
+ goto fail;
+
+ /* Top route */
+ SYS(fail, "ip route add %s/32 dev veth1 %s", IP4_ADDR_2, vrf);
+ SYS(fail, "ip route add default dev veth1 via %s %s", IP4_ADDR_2, vrf);
+ SYS(fail, "ip -6 route add %s/128 dev veth1 %s", IP6_ADDR_2, vrf);
+ SYS(fail, "ip -6 route add default dev veth1 via %s %s", IP6_ADDR_2, vrf);
+ /* Bottom route */
+ SYS(fail, "ip route add %s/32 dev veth5 %s", IP4_ADDR_6, vrf);
+ SYS(fail, "ip route add %s/32 dev veth5 via %s %s", IP4_ADDR_7, IP4_ADDR_6, vrf);
+ SYS(fail, "ip route add %s/32 dev veth5 via %s %s", IP4_ADDR_8, IP4_ADDR_6, vrf);
+ SYS(fail, "ip -6 route add %s/128 dev veth5 %s", IP6_ADDR_6, vrf);
+ SYS(fail, "ip -6 route add %s/128 dev veth5 via %s %s", IP6_ADDR_7, IP6_ADDR_6, vrf);
+ SYS(fail, "ip -6 route add %s/128 dev veth5 via %s %s", IP6_ADDR_8, IP6_ADDR_6, vrf);
+
+ close_netns(nstoken);
+ return 0;
+fail:
+ close_netns(nstoken);
+ return -1;
+}
+
+static int configure_ns2(const char *ns2, const char *vrf)
+{
+ struct nstoken *nstoken = NULL;
+
+ if (!ns2 || !vrf)
+ goto fail;
+
+ nstoken = open_netns(ns2);
+ if (!ASSERT_OK_PTR(nstoken, "open ns2"))
+ goto fail;
+
+ SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.ip_forward=1", ns2);
+ SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.all.forwarding=1", ns2);
+
+ /* Top route */
+ SYS(fail, "ip route add %s/32 dev veth2 %s", IP4_ADDR_1, vrf);
+ SYS(fail, "ip route add %s/32 dev veth3 %s", IP4_ADDR_4, vrf);
+ SYS(fail, "ip -6 route add %s/128 dev veth2 %s", IP6_ADDR_1, vrf);
+ SYS(fail, "ip -6 route add %s/128 dev veth3 %s", IP6_ADDR_4, vrf);
+ /* Bottom route */
+ SYS(fail, "ip route add %s/32 dev veth6 %s", IP4_ADDR_5, vrf);
+ SYS(fail, "ip route add %s/32 dev veth7 %s", IP4_ADDR_8, vrf);
+ SYS(fail, "ip -6 route add %s/128 dev veth6 %s", IP6_ADDR_5, vrf);
+ SYS(fail, "ip -6 route add %s/128 dev veth7 %s", IP6_ADDR_8, vrf);
+
+ close_netns(nstoken);
+ return 0;
+fail:
+ close_netns(nstoken);
+ return -1;
+}
+
+static int configure_ns3(const char *ns3)
+{
+ struct nstoken *nstoken = NULL;
+
+ if (!ns3)
+ goto fail;
+
+ nstoken = open_netns(ns3);
+ if (!ASSERT_OK_PTR(nstoken, "open ns3"))
+ goto fail;
+
+ /* Top route */
+ SYS(fail, "ip route add %s/32 dev veth4", IP4_ADDR_3);
+ SYS(fail, "ip route add %s/32 dev veth4 via %s", IP4_ADDR_1, IP4_ADDR_3);
+ SYS(fail, "ip route add %s/32 dev veth4 via %s", IP4_ADDR_2, IP4_ADDR_3);
+ SYS(fail, "ip -6 route add %s/128 dev veth4", IP6_ADDR_3);
+ SYS(fail, "ip -6 route add %s/128 dev veth4 via %s", IP6_ADDR_1, IP6_ADDR_3);
+ SYS(fail, "ip -6 route add %s/128 dev veth4 via %s", IP6_ADDR_2, IP6_ADDR_3);
+ /* Bottom route */
+ SYS(fail, "ip route add %s/32 dev veth8", IP4_ADDR_7);
+ SYS(fail, "ip route add %s/32 dev veth8 via %s", IP4_ADDR_5, IP4_ADDR_7);
+ SYS(fail, "ip route add %s/32 dev veth8 via %s", IP4_ADDR_6, IP4_ADDR_7);
+ SYS(fail, "ip -6 route add %s/128 dev veth8", IP6_ADDR_7);
+ SYS(fail, "ip -6 route add %s/128 dev veth8 via %s", IP6_ADDR_5, IP6_ADDR_7);
+ SYS(fail, "ip -6 route add %s/128 dev veth8 via %s", IP6_ADDR_6, IP6_ADDR_7);
+
+ /* Configure IPv4 GRE device */
+ SYS(fail, "ip tunnel add gre_dev mode gre remote %s local %s ttl 255",
+ IP4_ADDR_1, IP4_ADDR_GRE);
+ SYS(fail, "ip link set gre_dev up");
+ SYS(fail, "ip a add %s dev gre_dev", IP4_ADDR_GRE);
+
+ /* Configure IPv6 GRE device */
+ SYS(fail, "ip tunnel add gre6_dev mode ip6gre remote %s local %s ttl 255",
+ IP6_ADDR_1, IP6_ADDR_GRE);
+ SYS(fail, "ip link set gre6_dev up");
+ SYS(fail, "ip a add %s dev gre6_dev", IP6_ADDR_GRE);
+
+ close_netns(nstoken);
+ return 0;
+fail:
+ close_netns(nstoken);
+ return -1;
+}
+
+static int setup_network(char *ns1, char *ns2, char *ns3, const char *vrf)
+{
+ if (!ns1 || !ns2 || !ns3 || !vrf)
+ goto fail;
+
+ SYS(fail, "ip -n %s link add veth1 type veth peer name veth2 netns %s", ns1, ns2);
+ SYS(fail, "ip -n %s link add veth3 type veth peer name veth4 netns %s", ns2, ns3);
+ SYS(fail, "ip -n %s link add veth5 type veth peer name veth6 netns %s", ns1, ns2);
+ SYS(fail, "ip -n %s link add veth7 type veth peer name veth8 netns %s", ns2, ns3);
+
+ if (vrf[0]) {
+ if (!ASSERT_OK(configure_vrf(ns1, ns2), "configure vrf"))
+ goto fail;
+ }
+ if (!ASSERT_OK(set_top_addr(ns1, ns2, ns3), "set top addresses"))
+ goto fail;
+
+ if (!ASSERT_OK(set_bottom_addr(ns1, ns2, ns3), "set bottom addresses"))
+ goto fail;
+
+ if (!ASSERT_OK(configure_ns1(ns1, vrf), "configure ns1 routes"))
+ goto fail;
+
+ if (!ASSERT_OK(configure_ns2(ns2, vrf), "configure ns2 routes"))
+ goto fail;
+
+ if (!ASSERT_OK(configure_ns3(ns3), "configure ns3 routes"))
+ goto fail;
+
+ /* Link bottom route to the GRE tunnels */
+ SYS(fail, "ip -n %s route add %s/32 dev veth5 via %s %s",
+ ns1, IP4_ADDR_GRE, IP4_ADDR_6, vrf);
+ SYS(fail, "ip -n %s route add %s/32 dev veth7 via %s %s",
+ ns2, IP4_ADDR_GRE, IP4_ADDR_8, vrf);
+ SYS(fail, "ip -n %s -6 route add %s/128 dev veth5 via %s %s",
+ ns1, IP6_ADDR_GRE, IP6_ADDR_6, vrf);
+ SYS(fail, "ip -n %s -6 route add %s/128 dev veth7 via %s %s",
+ ns2, IP6_ADDR_GRE, IP6_ADDR_8, vrf);
+
+ return 0;
+fail:
+ return -1;
+}
+
+static int remove_routes_to_gredev(const char *ns1, const char *ns2, const char *vrf)
+{
+ SYS(fail, "ip -n %s route del %s dev veth5 %s", ns1, IP4_ADDR_GRE, vrf);
+ SYS(fail, "ip -n %s route del %s dev veth7 %s", ns2, IP4_ADDR_GRE, vrf);
+ SYS(fail, "ip -n %s -6 route del %s/128 dev veth5 %s", ns1, IP6_ADDR_GRE, vrf);
+ SYS(fail, "ip -n %s -6 route del %s/128 dev veth7 %s", ns2, IP6_ADDR_GRE, vrf);
+
+ return 0;
+fail:
+ return -1;
+}
+
+static int add_unreachable_routes_to_gredev(const char *ns1, const char *ns2, const char *vrf)
+{
+ SYS(fail, "ip -n %s route add unreachable %s/32 %s", ns1, IP4_ADDR_GRE, vrf);
+ SYS(fail, "ip -n %s route add unreachable %s/32 %s", ns2, IP4_ADDR_GRE, vrf);
+ SYS(fail, "ip -n %s -6 route add unreachable %s/128 %s", ns1, IP6_ADDR_GRE, vrf);
+ SYS(fail, "ip -n %s -6 route add unreachable %s/128 %s", ns2, IP6_ADDR_GRE, vrf);
+
+ return 0;
+fail:
+ return -1;
+}
+
+#define GSO_SIZE 5000
+#define GSO_TCP_PORT 9000
+/* This tests the fix from commit ea0371f78799 ("net: fix GSO in bpf_lwt_push_ip_encap") */
+static int test_gso_fix(const char *ns1, const char *ns3, int family)
+{
+ const char *ip_addr = family == AF_INET ? IP4_ADDR_DST : IP6_ADDR_DST;
+ char gso_packet[GSO_SIZE] = {};
+ struct nstoken *nstoken = NULL;
+ int sfd, cfd, afd;
+ ssize_t bytes;
+ int ret = -1;
+
+ if (!ns1 || !ns3)
+ return ret;
+
+ nstoken = open_netns(ns3);
+ if (!ASSERT_OK_PTR(nstoken, "open ns3"))
+ return ret;
+
+ sfd = start_server_str(family, SOCK_STREAM, ip_addr, GSO_TCP_PORT, NULL);
+ if (!ASSERT_OK_FD(sfd, "start server"))
+ goto close_netns;
+
+ close_netns(nstoken);
+
+ nstoken = open_netns(ns1);
+ if (!ASSERT_OK_PTR(nstoken, "open ns1"))
+ goto close_server;
+
+ cfd = connect_to_addr_str(family, SOCK_STREAM, ip_addr, GSO_TCP_PORT, NULL);
+ if (!ASSERT_OK_FD(cfd, "connect to server"))
+ goto close_server;
+
+ close_netns(nstoken);
+ nstoken = NULL;
+
+ afd = accept(sfd, NULL, NULL);
+ if (!ASSERT_OK_FD(afd, "accept"))
+ goto close_client;
+
+ /* Send a packet larger than MTU */
+ bytes = send(cfd, gso_packet, GSO_SIZE, 0);
+ if (!ASSERT_EQ(bytes, GSO_SIZE, "send packet"))
+ goto close_accept;
+
+ /* Verify we received all expected bytes */
+ bytes = read(afd, gso_packet, GSO_SIZE);
+ if (!ASSERT_EQ(bytes, GSO_SIZE, "receive packet"))
+ goto close_accept;
+
+ ret = 0;
+
+close_accept:
+ close(afd);
+close_client:
+ close(cfd);
+close_server:
+ close(sfd);
+close_netns:
+ close_netns(nstoken);
+
+ return ret;
+}
+
+static int check_ping_ok(const char *ns1)
+{
+ SYS(fail, "ip netns exec %s ping -c 1 -W1 -I veth1 %s > /dev/null", ns1, IP4_ADDR_DST);
+ SYS(fail, "ip netns exec %s ping6 -c 1 -W1 -I veth1 %s > /dev/null", ns1, IP6_ADDR_DST);
+ return 0;
+fail:
+ return -1;
+}
+
+static int check_ping_fails(const char *ns1)
+{
+ int ret;
+
+ ret = SYS_NOFAIL("ip netns exec %s ping -c 1 -W1 -I veth1 %s", ns1, IP4_ADDR_DST);
+ if (!ret)
+ return -1;
+
+ ret = SYS_NOFAIL("ip netns exec %s ping6 -c 1 -W1 -I veth1 %s", ns1, IP6_ADDR_DST);
+ if (!ret)
+ return -1;
+
+ return 0;
+}
+
+#define EGRESS true
+#define INGRESS false
+#define IPV4_ENCAP true
+#define IPV6_ENCAP false
+static void lwt_ip_encap(bool ipv4_encap, bool egress, const char *vrf)
+{
+ char ns1[NETNS_NAME_SIZE] = NETNS_BASE "-1-";
+ char ns2[NETNS_NAME_SIZE] = NETNS_BASE "-2-";
+ char ns3[NETNS_NAME_SIZE] = NETNS_BASE "-3-";
+ char *sec = ipv4_encap ? "encap_gre" : "encap_gre6";
+
+ if (!vrf)
+ return;
+
+ if (!ASSERT_OK(create_ns(ns1, NETNS_NAME_SIZE), "create ns1"))
+ goto out;
+ if (!ASSERT_OK(create_ns(ns2, NETNS_NAME_SIZE), "create ns2"))
+ goto out;
+ if (!ASSERT_OK(create_ns(ns3, NETNS_NAME_SIZE), "create ns3"))
+ goto out;
+
+ if (!ASSERT_OK(setup_network(ns1, ns2, ns3, vrf), "setup network"))
+ goto out;
+
+ /* By default, pings work */
+ if (!ASSERT_OK(check_ping_ok(ns1), "ping OK"))
+ goto out;
+
+ /* Remove NS2->DST routes, ping fails */
+ SYS(out, "ip -n %s route del %s/32 dev veth3 %s", ns2, IP4_ADDR_DST, vrf);
+ SYS(out, "ip -n %s -6 route del %s/128 dev veth3 %s", ns2, IP6_ADDR_DST, vrf);
+ if (!ASSERT_OK(check_ping_fails(ns1), "ping expected fail"))
+ goto out;
+
+ /* Install replacement routes (LWT/eBPF), pings succeed */
+ if (egress) {
+ SYS(out, "ip -n %s route add %s encap bpf xmit obj %s sec %s dev veth1 %s",
+ ns1, IP4_ADDR_DST, BPF_FILE, sec, vrf);
+ SYS(out, "ip -n %s -6 route add %s encap bpf xmit obj %s sec %s dev veth1 %s",
+ ns1, IP6_ADDR_DST, BPF_FILE, sec, vrf);
+ } else {
+ SYS(out, "ip -n %s route add %s encap bpf in obj %s sec %s dev veth2 %s",
+ ns2, IP4_ADDR_DST, BPF_FILE, sec, vrf);
+ SYS(out, "ip -n %s -6 route add %s encap bpf in obj %s sec %s dev veth2 %s",
+ ns2, IP6_ADDR_DST, BPF_FILE, sec, vrf);
+ }
+
+ if (!ASSERT_OK(check_ping_ok(ns1), "ping OK"))
+ goto out;
+
+ /* Skip GSO tests with VRF: VRF routing needs properly assigned
+ * source IP/device, which is easy to do with ping but hard with TCP.
+ */
+ if (egress && !vrf[0]) {
+ if (!ASSERT_OK(test_gso_fix(ns1, ns3, AF_INET), "test GSO"))
+ goto out;
+ }
+
+ /* Negative test: remove routes to GRE devices: ping fails */
+ if (!ASSERT_OK(remove_routes_to_gredev(ns1, ns2, vrf), "remove routes to gredev"))
+ goto out;
+ if (!ASSERT_OK(check_ping_fails(ns1), "ping expected fail"))
+ goto out;
+
+ /* Another negative test */
+ if (!ASSERT_OK(add_unreachable_routes_to_gredev(ns1, ns2, vrf),
+ "add unreachable routes"))
+ goto out;
+ ASSERT_OK(check_ping_fails(ns1), "ping expected fail");
+
+out:
+ SYS_NOFAIL("ip netns del %s", ns1);
+ SYS_NOFAIL("ip netns del %s", ns2);
+ SYS_NOFAIL("ip netns del %s", ns3);
+}
+
+void test_lwt_ip_encap_vrf_ipv6(void)
+{
+ if (test__start_subtest("egress"))
+ lwt_ip_encap(IPV6_ENCAP, EGRESS, "vrf red");
+
+ if (test__start_subtest("ingress"))
+ lwt_ip_encap(IPV6_ENCAP, INGRESS, "vrf red");
+}
+
+void test_lwt_ip_encap_vrf_ipv4(void)
+{
+ if (test__start_subtest("egress"))
+ lwt_ip_encap(IPV4_ENCAP, EGRESS, "vrf red");
+
+ if (test__start_subtest("ingress"))
+ lwt_ip_encap(IPV4_ENCAP, INGRESS, "vrf red");
+}
+
+void test_lwt_ip_encap_ipv6(void)
+{
+ if (test__start_subtest("egress"))
+ lwt_ip_encap(IPV6_ENCAP, EGRESS, "");
+
+ if (test__start_subtest("ingress"))
+ lwt_ip_encap(IPV6_ENCAP, INGRESS, "");
+}
+
+void test_lwt_ip_encap_ipv4(void)
+{
+ if (test__start_subtest("egress"))
+ lwt_ip_encap(IPV4_ENCAP, EGRESS, "");
+
+ if (test__start_subtest("ingress"))
+ lwt_ip_encap(IPV4_ENCAP, INGRESS, "");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c
new file mode 100644
index 000000000000..3bc730b7c7fa
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* Connects 6 network namespaces through veths.
+ * Each NS may have different IPv6 global scope addresses :
+ *
+ * NS1 NS2 NS3 NS4 NS5 NS6
+ * lo veth1 <-> veth2 veth3 <-> veth4 veth5 <-> veth6 lo veth7 <-> veth8 veth9 <-> veth10 lo
+ * fb00 ::1 ::12 ::21 ::34 ::43 ::56 ::65 ::78 ::87 ::910 ::109 ::6
+ * fd00 ::4
+ * fc42 ::1
+ *
+ * All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a
+ * IPv6 header with a Segment Routing Header, with segments :
+ * fd00::1 -> fd00::2 -> fd00::3 -> fd00::4
+ *
+ * 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions :
+ * - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1
+ * - fd00::2 : remove the TLV, change the flags, add a tag
+ * - fd00::3 : apply an End.T action to fd00::4, through routing table 117
+ *
+ * fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet.
+ * Each End.BPF action will validate the operations applied on the SRH by the
+ * previous BPF program in the chain, otherwise the packet is dropped.
+ *
+ * An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
+ * datagram can be read on NS6 when binding to fb00::6.
+ */
+
+#include "network_helpers.h"
+#include "test_progs.h"
+
+#define NETNS_BASE "lwt-seg6local-"
+#define BPF_FILE "test_lwt_seg6local.bpf.o"
+
+static void cleanup(void)
+{
+ int ns;
+
+ for (ns = 1; ns < 7; ns++)
+ SYS_NOFAIL("ip netns del %s%d", NETNS_BASE, ns);
+}
+
+static int setup(void)
+{
+ int ns;
+
+ for (ns = 1; ns < 7; ns++)
+ SYS(fail, "ip netns add %s%d", NETNS_BASE, ns);
+
+ SYS(fail, "ip -n %s6 link set dev lo up", NETNS_BASE);
+
+ for (ns = 1; ns < 6; ns++) {
+ int local_id = ns * 2 - 1;
+ int peer_id = ns * 2;
+ int next_ns = ns + 1;
+
+ SYS(fail, "ip -n %s%d link add veth%d type veth peer name veth%d netns %s%d",
+ NETNS_BASE, ns, local_id, peer_id, NETNS_BASE, next_ns);
+
+ SYS(fail, "ip -n %s%d link set dev veth%d up", NETNS_BASE, ns, local_id);
+ SYS(fail, "ip -n %s%d link set dev veth%d up", NETNS_BASE, next_ns, peer_id);
+
+ /* All link scope addresses to veths */
+ SYS(fail, "ip -n %s%d -6 addr add fb00::%d%d/16 dev veth%d scope link",
+ NETNS_BASE, ns, local_id, peer_id, local_id);
+ SYS(fail, "ip -n %s%d -6 addr add fb00::%d%d/16 dev veth%d scope link",
+ NETNS_BASE, next_ns, peer_id, local_id, peer_id);
+ }
+
+
+ SYS(fail, "ip -n %s5 -6 route add fb00::109 table 117 dev veth9 scope link", NETNS_BASE);
+
+ SYS(fail, "ip -n %s1 -6 addr add fb00::1/16 dev lo", NETNS_BASE);
+ SYS(fail, "ip -n %s1 -6 route add fb00::6 dev veth1 via fb00::21", NETNS_BASE);
+
+ SYS(fail, "ip -n %s2 -6 route add fb00::6 encap bpf in obj %s sec encap_srh dev veth2",
+ NETNS_BASE, BPF_FILE);
+ SYS(fail, "ip -n %s2 -6 route add fd00::1 dev veth3 via fb00::43 scope link", NETNS_BASE);
+
+ SYS(fail, "ip -n %s3 -6 route add fc42::1 dev veth5 via fb00::65", NETNS_BASE);
+ SYS(fail,
+ "ip -n %s3 -6 route add fd00::1 encap seg6local action End.BPF endpoint obj %s sec add_egr_x dev veth4",
+ NETNS_BASE, BPF_FILE);
+
+ SYS(fail,
+ "ip -n %s4 -6 route add fd00::2 encap seg6local action End.BPF endpoint obj %s sec pop_egr dev veth6",
+ NETNS_BASE, BPF_FILE);
+ SYS(fail, "ip -n %s4 -6 addr add fc42::1 dev lo", NETNS_BASE);
+ SYS(fail, "ip -n %s4 -6 route add fd00::3 dev veth7 via fb00::87", NETNS_BASE);
+
+ SYS(fail, "ip -n %s5 -6 route add fd00::4 table 117 dev veth9 via fb00::109", NETNS_BASE);
+ SYS(fail,
+ "ip -n %s5 -6 route add fd00::3 encap seg6local action End.BPF endpoint obj %s sec inspect_t dev veth8",
+ NETNS_BASE, BPF_FILE);
+
+ SYS(fail, "ip -n %s6 -6 addr add fb00::6/16 dev lo", NETNS_BASE);
+ SYS(fail, "ip -n %s6 -6 addr add fd00::4/16 dev lo", NETNS_BASE);
+
+ for (ns = 1; ns < 6; ns++)
+ SYS(fail, "ip netns exec %s%d sysctl -wq net.ipv6.conf.all.forwarding=1",
+ NETNS_BASE, ns);
+
+ SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.all.seg6_enabled=1", NETNS_BASE);
+ SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.lo.seg6_enabled=1", NETNS_BASE);
+ SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.veth10.seg6_enabled=1", NETNS_BASE);
+
+ return 0;
+fail:
+ return -1;
+}
+
+#define SERVER_PORT 7330
+#define CLIENT_PORT 2121
+void test_lwt_seg6local(void)
+{
+ struct sockaddr_in6 server_addr = {};
+ const char *ns1 = NETNS_BASE "1";
+ const char *ns6 = NETNS_BASE "6";
+ struct nstoken *nstoken = NULL;
+ const char *foobar = "foobar";
+ ssize_t bytes;
+ int sfd, cfd;
+ char buf[7];
+
+ if (!ASSERT_OK(setup(), "setup"))
+ goto out;
+
+ nstoken = open_netns(ns6);
+ if (!ASSERT_OK_PTR(nstoken, "open ns6"))
+ goto out;
+
+ sfd = start_server_str(AF_INET6, SOCK_DGRAM, "fb00::6", SERVER_PORT, NULL);
+ if (!ASSERT_OK_FD(sfd, "start server"))
+ goto close_netns;
+
+ close_netns(nstoken);
+
+ nstoken = open_netns(ns1);
+ if (!ASSERT_OK_PTR(nstoken, "open ns1"))
+ goto close_server;
+
+ cfd = start_server_str(AF_INET6, SOCK_DGRAM, "fb00::1", CLIENT_PORT, NULL);
+ if (!ASSERT_OK_FD(cfd, "start client"))
+ goto close_server;
+
+ close_netns(nstoken);
+ nstoken = NULL;
+
+ /* Send a packet larger than MTU */
+ server_addr.sin6_family = AF_INET6;
+ server_addr.sin6_port = htons(SERVER_PORT);
+ if (!ASSERT_EQ(inet_pton(AF_INET6, "fb00::6", &server_addr.sin6_addr), 1,
+ "build target addr"))
+ goto close_client;
+
+ bytes = sendto(cfd, foobar, sizeof(foobar), 0,
+ (struct sockaddr *)&server_addr, sizeof(server_addr));
+ if (!ASSERT_EQ(bytes, sizeof(foobar), "send packet"))
+ goto close_client;
+
+ /* Verify we received all expected bytes */
+ bytes = read(sfd, buf, sizeof(buf));
+ if (!ASSERT_EQ(bytes, sizeof(buf), "receive packet"))
+ goto close_client;
+ ASSERT_STREQ(buf, foobar, "check udp packet");
+
+close_client:
+ close(cfd);
+close_server:
+ close(sfd);
+close_netns:
+ close_netns(nstoken);
+
+out:
+ cleanup();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
index ac3c3c097c0e..e00cd34586dd 100644
--- a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
@@ -33,20 +33,25 @@ void test_netns_cookie(void)
skel->links.get_netns_cookie_sockops = bpf_program__attach_cgroup(
skel->progs.get_netns_cookie_sockops, cgroup_fd);
- if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_sockops, "prog_attach"))
+ if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_sockops, "prog_attach_sockops"))
goto done;
verdict = bpf_program__fd(skel->progs.get_netns_cookie_sk_msg);
map = bpf_map__fd(skel->maps.sock_map);
err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0);
- if (!ASSERT_OK(err, "prog_attach"))
+ if (!ASSERT_OK(err, "prog_attach_sk_msg"))
goto done;
tc_fd = bpf_program__fd(skel->progs.get_netns_cookie_tcx);
err = bpf_prog_attach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &opta);
- if (!ASSERT_OK(err, "prog_attach"))
+ if (!ASSERT_OK(err, "prog_attach_tcx"))
goto done;
+ skel->links.get_netns_cookie_cgroup_skb = bpf_program__attach_cgroup(
+ skel->progs.get_netns_cookie_cgroup_skb, cgroup_fd);
+ if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_cgroup_skb, "prog_attach_cgroup_skb"))
+ goto cleanup_tc;
+
server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
if (CHECK(server_fd < 0, "start_server", "errno %d\n", errno))
goto cleanup_tc;
@@ -69,16 +74,18 @@ void test_netns_cookie(void)
if (!ASSERT_OK(err, "getsockopt"))
goto cleanup_tc;
- ASSERT_EQ(val, cookie_expected_value, "cookie_value");
+ ASSERT_EQ(val, cookie_expected_value, "cookie_value_sockops");
err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sk_msg_netns_cookies),
&client_fd, &val);
if (!ASSERT_OK(err, "map_lookup(sk_msg_netns_cookies)"))
goto cleanup_tc;
- ASSERT_EQ(val, cookie_expected_value, "cookie_value");
- ASSERT_EQ(skel->bss->tcx_init_netns_cookie, cookie_expected_value, "cookie_value");
- ASSERT_EQ(skel->bss->tcx_netns_cookie, cookie_expected_value, "cookie_value");
+ ASSERT_EQ(val, cookie_expected_value, "cookie_value_sk_msg");
+ ASSERT_EQ(skel->bss->tcx_init_netns_cookie, cookie_expected_value, "cookie_value_init_tcx");
+ ASSERT_EQ(skel->bss->tcx_netns_cookie, cookie_expected_value, "cookie_value_tcx");
+ ASSERT_EQ(skel->bss->cgroup_skb_init_netns_cookie, cookie_expected_value, "cookie_value_init_cgroup_skb");
+ ASSERT_EQ(skel->bss->cgroup_skb_netns_cookie, cookie_expected_value, "cookie_value_cgroup_skb");
cleanup_tc:
err = bpf_prog_detach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &optd);
diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
index 761ce24bce38..99c953f2be21 100644
--- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -200,41 +200,28 @@ static void test_ns_current_pid_tgid_new_ns(int (*fn)(void *), void *arg)
return;
}
-static void test_in_netns(int (*fn)(void *), void *arg)
-{
- struct nstoken *nstoken = NULL;
-
- SYS(cleanup, "ip netns add ns_current_pid_tgid");
- SYS(cleanup, "ip -net ns_current_pid_tgid link set dev lo up");
-
- nstoken = open_netns("ns_current_pid_tgid");
- if (!ASSERT_OK_PTR(nstoken, "open_netns"))
- goto cleanup;
-
- test_ns_current_pid_tgid_new_ns(fn, arg);
-
-cleanup:
- if (nstoken)
- close_netns(nstoken);
- SYS_NOFAIL("ip netns del ns_current_pid_tgid");
-}
-
/* TODO: use a different tracepoint */
-void serial_test_ns_current_pid_tgid(void)
+void serial_test_current_pid_tgid(void)
{
if (test__start_subtest("root_ns_tp"))
test_current_pid_tgid_tp(NULL);
if (test__start_subtest("new_ns_tp"))
test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_tp, NULL);
- if (test__start_subtest("new_ns_cgrp")) {
- int cgroup_fd = -1;
-
- cgroup_fd = test__join_cgroup("/sock_addr");
- if (ASSERT_GE(cgroup_fd, 0, "join_cgroup")) {
- test_in_netns(test_current_pid_tgid_cgrp, &cgroup_fd);
- close(cgroup_fd);
- }
+}
+
+void test_ns_current_pid_tgid_cgrp(void)
+{
+ int cgroup_fd = test__join_cgroup("/sock_addr");
+
+ if (ASSERT_OK_FD(cgroup_fd, "join_cgroup")) {
+ test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_cgrp, &cgroup_fd);
+ close(cgroup_fd);
}
- if (test__start_subtest("new_ns_sk_msg"))
- test_in_netns(test_current_pid_tgid_sk_msg, NULL);
}
+
+void test_ns_current_pid_tgid_sk_msg(void)
+{
+ test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_sk_msg, NULL);
+}
+
+
diff --git a/tools/testing/selftests/bpf/prog_tests/prepare.c b/tools/testing/selftests/bpf/prog_tests/prepare.c
new file mode 100644
index 000000000000..fb5cdad97116
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/prepare.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "prepare.skel.h"
+
+static bool check_prepared(struct bpf_object *obj)
+{
+ bool is_prepared = true;
+ const struct bpf_map *map;
+
+ bpf_object__for_each_map(map, obj) {
+ if (bpf_map__fd(map) < 0)
+ is_prepared = false;
+ }
+
+ return is_prepared;
+}
+
+static void test_prepare_no_load(void)
+{
+ struct prepare *skel;
+ int err;
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ );
+
+ skel = prepare__open();
+ if (!ASSERT_OK_PTR(skel, "prepare__open"))
+ return;
+
+ if (!ASSERT_FALSE(check_prepared(skel->obj), "not check_prepared"))
+ goto cleanup;
+
+ err = bpf_object__prepare(skel->obj);
+
+ if (!ASSERT_TRUE(check_prepared(skel->obj), "check_prepared"))
+ goto cleanup;
+
+ if (!ASSERT_OK(err, "bpf_object__prepare"))
+ goto cleanup;
+
+cleanup:
+ prepare__destroy(skel);
+}
+
+static void test_prepare_load(void)
+{
+ struct prepare *skel;
+ int err, prog_fd;
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ );
+
+ skel = prepare__open();
+ if (!ASSERT_OK_PTR(skel, "prepare__open"))
+ return;
+
+ if (!ASSERT_FALSE(check_prepared(skel->obj), "not check_prepared"))
+ goto cleanup;
+
+ err = bpf_object__prepare(skel->obj);
+ if (!ASSERT_OK(err, "bpf_object__prepare"))
+ goto cleanup;
+
+ err = prepare__load(skel);
+ if (!ASSERT_OK(err, "prepare__load"))
+ goto cleanup;
+
+ if (!ASSERT_TRUE(check_prepared(skel->obj), "check_prepared"))
+ goto cleanup;
+
+ prog_fd = bpf_program__fd(skel->progs.program);
+ if (!ASSERT_GE(prog_fd, 0, "prog_fd"))
+ goto cleanup;
+
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ if (!ASSERT_OK(err, "test_run_opts err"))
+ goto cleanup;
+
+ if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+ goto cleanup;
+
+ ASSERT_EQ(skel->bss->err, 0, "err");
+
+cleanup:
+ prepare__destroy(skel);
+}
+
+void test_prepare(void)
+{
+ if (test__start_subtest("prepare_load"))
+ test_prepare_load();
+ if (test__start_subtest("prepare_no_load"))
+ test_prepare_no_load();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c b/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c
index 509883e6823a..5d3c00a08a88 100644
--- a/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c
+++ b/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c
@@ -6,6 +6,7 @@
#include "epilogue_tailcall.skel.h"
#include "pro_epilogue_goto_start.skel.h"
#include "epilogue_exit.skel.h"
+#include "pro_epilogue_with_kfunc.skel.h"
struct st_ops_args {
__u64 a;
@@ -55,6 +56,7 @@ void test_pro_epilogue(void)
RUN_TESTS(pro_epilogue);
RUN_TESTS(pro_epilogue_goto_start);
RUN_TESTS(epilogue_exit);
+ RUN_TESTS(pro_epilogue_with_kfunc);
if (test__start_subtest("tailcall"))
test_tailcall();
}
diff --git a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
index ebe0c12b5536..c9f855e5da24 100644
--- a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
@@ -81,6 +81,9 @@ static const char * const inproper_region_tests[] = {
"nested_rcu_region",
"rcu_read_lock_global_subprog_lock",
"rcu_read_lock_global_subprog_unlock",
+ "rcu_read_lock_sleepable_helper_global_subprog",
+ "rcu_read_lock_sleepable_kfunc_global_subprog",
+ "rcu_read_lock_sleepable_global_subprog_indirect",
};
static void test_inproper_region(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
index c7b9ba8b1d06..a8d1eaa67020 100644
--- a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
@@ -24,6 +24,7 @@ struct read_ret_desc {
{ .name = "copy_from_user", .ret = -EFAULT },
{ .name = "copy_from_user_task", .ret = -EFAULT },
{ .name = "copy_from_user_str", .ret = -EFAULT },
+ { .name = "copy_from_user_task_str", .ret = -EFAULT },
};
void test_read_vsyscall(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
new file mode 100644
index 000000000000..0703e987df89
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024-2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <sys/sysinfo.h>
+
+#include "res_spin_lock.skel.h"
+#include "res_spin_lock_fail.skel.h"
+
+void test_res_spin_lock_failure(void)
+{
+ RUN_TESTS(res_spin_lock_fail);
+}
+
+static volatile int skip;
+
+static void *spin_lock_thread(void *arg)
+{
+ int err, prog_fd = *(u32 *) arg;
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .repeat = 10000,
+ );
+
+ while (!READ_ONCE(skip)) {
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ if (err || topts.retval) {
+ ASSERT_OK(err, "test_run");
+ ASSERT_OK(topts.retval, "test_run retval");
+ break;
+ }
+ }
+ pthread_exit(arg);
+}
+
+void test_res_spin_lock_success(void)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, topts,
+ .data_in = &pkt_v4,
+ .data_size_in = sizeof(pkt_v4),
+ .repeat = 1,
+ );
+ struct res_spin_lock *skel;
+ pthread_t thread_id[16];
+ int prog_fd, i, err;
+ void *ret;
+
+ if (get_nprocs() < 2) {
+ test__skip();
+ return;
+ }
+
+ skel = res_spin_lock__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "res_spin_lock__open_and_load"))
+ return;
+ /* AA deadlock */
+ prog_fd = bpf_program__fd(skel->progs.res_spin_lock_test);
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ ASSERT_OK(err, "error");
+ ASSERT_OK(topts.retval, "retval");
+
+ prog_fd = bpf_program__fd(skel->progs.res_spin_lock_test_held_lock_max);
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ ASSERT_OK(err, "error");
+ ASSERT_OK(topts.retval, "retval");
+
+ /* Multi-threaded ABBA deadlock. */
+
+ prog_fd = bpf_program__fd(skel->progs.res_spin_lock_test_AB);
+ for (i = 0; i < 16; i++) {
+ int err;
+
+ err = pthread_create(&thread_id[i], NULL, &spin_lock_thread, &prog_fd);
+ if (!ASSERT_OK(err, "pthread_create"))
+ goto end;
+ }
+
+ topts.retval = 0;
+ topts.repeat = 1000;
+ int fd = bpf_program__fd(skel->progs.res_spin_lock_test_BA);
+ while (!topts.retval && !err && !READ_ONCE(skel->bss->err)) {
+ err = bpf_prog_test_run_opts(fd, &topts);
+ }
+
+ WRITE_ONCE(skip, true);
+
+ for (i = 0; i < 16; i++) {
+ if (!ASSERT_OK(pthread_join(thread_id[i], &ret), "pthread_join"))
+ goto end;
+ if (!ASSERT_EQ(ret, &prog_fd, "ret == prog_fd"))
+ goto end;
+ }
+
+ ASSERT_EQ(READ_ONCE(skel->bss->err), -EDEADLK, "timeout err");
+ ASSERT_OK(err, "err");
+ ASSERT_EQ(topts.retval, -EDEADLK, "timeout");
+end:
+ res_spin_lock__destroy(skel);
+ return;
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
index e12255121c15..e4dac529d424 100644
--- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
@@ -202,7 +202,7 @@ err_out:
void test_setget_sockopt(void)
{
cg_fd = test__join_cgroup(CG_NAME);
- if (cg_fd < 0)
+ if (!ASSERT_OK_FD(cg_fd, "join cgroup"))
return;
if (create_netns())
diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
index 2b0068742ef9..e3ea5dc2f697 100644
--- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
@@ -50,6 +50,9 @@ static struct {
{ "lock_id_mismatch_innermapval_mapval", "bpf_spin_unlock of different lock" },
{ "lock_global_subprog_call1", "global function calls are not allowed while holding a lock" },
{ "lock_global_subprog_call2", "global function calls are not allowed while holding a lock" },
+ { "lock_global_sleepable_helper_subprog", "global function calls are not allowed while holding a lock" },
+ { "lock_global_sleepable_kfunc_subprog", "global function calls are not allowed while holding a lock" },
+ { "lock_global_sleepable_subprog_indirect", "global function calls are not allowed while holding a lock" },
};
static int match_regex(const char *pattern, const char *string)
diff --git a/tools/testing/selftests/bpf/prog_tests/summarization.c b/tools/testing/selftests/bpf/prog_tests/summarization.c
new file mode 100644
index 000000000000..5dd6c120a838
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/summarization.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "bpf/libbpf.h"
+#include "summarization_freplace.skel.h"
+#include "summarization.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,
+ const char *err_msg)
+{
+ struct summarization_freplace *freplace = NULL;
+ struct bpf_program *freplace_prog = NULL;
+ struct bpf_program *main_prog = NULL;
+ LIBBPF_OPTS(bpf_object_open_opts, opts);
+ struct summarization *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 = summarization__open_opts(&opts);
+ if (!ASSERT_OK_PTR(main, "summarization__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 = summarization__load(main);
+ print_verifier_log(log);
+ if (!ASSERT_OK(err, "summarization__load"))
+ goto out;
+ freplace = summarization_freplace__open_opts(&opts);
+ if (!ASSERT_OK_PTR(freplace, "summarization_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 = summarization_freplace__load(freplace);
+ print_verifier_log(log);
+
+ /* The might_sleep extension doesn't work yet as sleepable calls are not
+ * allowed, but preserve the check in case it's supported later and then
+ * this particular combination can be enabled.
+ */
+ if (!strcmp("might_sleep", replacement) && err) {
+ ASSERT_HAS_SUBSTR(log, "helper call might sleep in a non-sleepable prog", "error log");
+ ASSERT_EQ(err, -EINVAL, "err");
+ test__skip();
+ goto out;
+ }
+
+ if (expect_load) {
+ ASSERT_OK(err, "summarization_freplace__load");
+ } else {
+ ASSERT_ERR(err, "summarization_freplace__load");
+ ASSERT_HAS_SUBSTR(log, err_msg, "error log");
+ }
+
+out:
+ summarization_freplace__destroy(freplace);
+ summarization__destroy(main);
+}
+
+/* There are two global subprograms in both summarization.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.
+ *
+ * This holds for might_sleep programs. It is ok to replace might_sleep with
+ * might_sleep and with does_not_sleep, but does_not_sleep cannot be replaced
+ * with might_sleep.
+ */
+void test_summarization_freplace(void)
+{
+ struct {
+ const char *main;
+ const char *to_be_replaced;
+ bool has_side_effect;
+ } mains[2][4] = {
+ {
+ { "main_changes_with_subprogs", "changes_pkt_data", true },
+ { "main_changes_with_subprogs", "does_not_change_pkt_data", false },
+ { "main_changes", "main_changes", true },
+ { "main_does_not_change", "main_does_not_change", false },
+ },
+ {
+ { "main_might_sleep_with_subprogs", "might_sleep", true },
+ { "main_might_sleep_with_subprogs", "does_not_sleep", false },
+ { "main_might_sleep", "main_might_sleep", true },
+ { "main_does_not_sleep", "main_does_not_sleep", false },
+ },
+ };
+ const char *pkt_err = "Extension program changes packet data";
+ const char *slp_err = "Extension program may sleep";
+ struct {
+ const char *func;
+ bool has_side_effect;
+ const char *err_msg;
+ } replacements[2][2] = {
+ {
+ { "changes_pkt_data", true, pkt_err },
+ { "does_not_change_pkt_data", false, pkt_err },
+ },
+ {
+ { "might_sleep", true, slp_err },
+ { "does_not_sleep", false, slp_err },
+ },
+ };
+ char buf[64];
+
+ for (int t = 0; t < 2; t++) {
+ 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[t][i].to_be_replaced, replacements[t][j].func);
+ if (!test__start_subtest(buf))
+ continue;
+ test_aux(mains[t][i].main, mains[t][i].to_be_replaced, replacements[t][j].func,
+ mains[t][i].has_side_effect || !replacements[t][j].has_side_effect,
+ replacements[t][j].err_msg);
+ }
+ }
+ }
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 544144620ca6..66a900327f91 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -1600,6 +1600,7 @@ static void test_tailcall_bpf2bpf_freplace(void)
goto out;
err = bpf_link__destroy(freplace_link);
+ freplace_link = NULL;
if (!ASSERT_OK(err, "destroy link"))
goto out;
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_links.c b/tools/testing/selftests/bpf/prog_tests/tc_links.c
index 1af9ec1149aa..2186a24e7d8a 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_links.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_links.c
@@ -13,7 +13,7 @@
#include "netlink_helpers.h"
#include "tc_helpers.h"
-void serial_test_tc_links_basic(void)
+void test_ns_tc_links_basic(void)
{
LIBBPF_OPTS(bpf_prog_query_opts, optq);
LIBBPF_OPTS(bpf_tcx_opts, optl);
@@ -260,7 +260,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_links_before(void)
+void test_ns_tc_links_before(void)
{
test_tc_links_before_target(BPF_TCX_INGRESS);
test_tc_links_before_target(BPF_TCX_EGRESS);
@@ -414,7 +414,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_links_after(void)
+void test_ns_tc_links_after(void)
{
test_tc_links_after_target(BPF_TCX_INGRESS);
test_tc_links_after_target(BPF_TCX_EGRESS);
@@ -514,7 +514,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_links_revision(void)
+void test_ns_tc_links_revision(void)
{
test_tc_links_revision_target(BPF_TCX_INGRESS);
test_tc_links_revision_target(BPF_TCX_EGRESS);
@@ -618,7 +618,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_links_chain_classic(void)
+void test_ns_tc_links_chain_classic(void)
{
test_tc_chain_classic(BPF_TCX_INGRESS, false);
test_tc_chain_classic(BPF_TCX_EGRESS, false);
@@ -846,7 +846,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_links_replace(void)
+void test_ns_tc_links_replace(void)
{
test_tc_links_replace_target(BPF_TCX_INGRESS);
test_tc_links_replace_target(BPF_TCX_EGRESS);
@@ -1158,7 +1158,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_links_invalid(void)
+void test_ns_tc_links_invalid(void)
{
test_tc_links_invalid_target(BPF_TCX_INGRESS);
test_tc_links_invalid_target(BPF_TCX_EGRESS);
@@ -1314,7 +1314,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_links_prepend(void)
+void test_ns_tc_links_prepend(void)
{
test_tc_links_prepend_target(BPF_TCX_INGRESS);
test_tc_links_prepend_target(BPF_TCX_EGRESS);
@@ -1470,7 +1470,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_links_append(void)
+void test_ns_tc_links_append(void)
{
test_tc_links_append_target(BPF_TCX_INGRESS);
test_tc_links_append_target(BPF_TCX_EGRESS);
@@ -1568,7 +1568,7 @@ cleanup:
ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
}
-void serial_test_tc_links_dev_cleanup(void)
+void test_ns_tc_links_dev_cleanup(void)
{
test_tc_links_dev_cleanup_target(BPF_TCX_INGRESS);
test_tc_links_dev_cleanup_target(BPF_TCX_EGRESS);
@@ -1672,7 +1672,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_links_chain_mixed(void)
+void test_ns_tc_links_chain_mixed(void)
{
test_tc_chain_mixed(BPF_TCX_INGRESS);
test_tc_chain_mixed(BPF_TCX_EGRESS);
@@ -1782,7 +1782,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_links_ingress(void)
+void test_ns_tc_links_ingress(void)
{
test_tc_links_ingress(BPF_TCX_INGRESS, true, true);
test_tc_links_ingress(BPF_TCX_INGRESS, true, false);
@@ -1823,7 +1823,7 @@ static int qdisc_replace(int ifindex, const char *kind, bool block)
return err;
}
-void serial_test_tc_links_dev_chain0(void)
+void test_ns_tc_links_dev_chain0(void)
{
int err, ifindex;
@@ -1955,7 +1955,7 @@ cleanup:
ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
}
-void serial_test_tc_links_dev_mixed(void)
+void test_ns_tc_links_dev_mixed(void)
{
test_tc_links_dev_mixed(BPF_TCX_INGRESS);
test_tc_links_dev_mixed(BPF_TCX_EGRESS);
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
index f77f604389aa..dd7a138d8c3d 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
@@ -10,7 +10,7 @@
#include "test_tc_link.skel.h"
#include "tc_helpers.h"
-void serial_test_tc_opts_basic(void)
+void test_ns_tc_opts_basic(void)
{
LIBBPF_OPTS(bpf_prog_attach_opts, opta);
LIBBPF_OPTS(bpf_prog_detach_opts, optd);
@@ -254,7 +254,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_before(void)
+void test_ns_tc_opts_before(void)
{
test_tc_opts_before_target(BPF_TCX_INGRESS);
test_tc_opts_before_target(BPF_TCX_EGRESS);
@@ -445,7 +445,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_after(void)
+void test_ns_tc_opts_after(void)
{
test_tc_opts_after_target(BPF_TCX_INGRESS);
test_tc_opts_after_target(BPF_TCX_EGRESS);
@@ -554,7 +554,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_revision(void)
+void test_ns_tc_opts_revision(void)
{
test_tc_opts_revision_target(BPF_TCX_INGRESS);
test_tc_opts_revision_target(BPF_TCX_EGRESS);
@@ -655,7 +655,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_opts_chain_classic(void)
+void test_ns_tc_opts_chain_classic(void)
{
test_tc_chain_classic(BPF_TCX_INGRESS, false);
test_tc_chain_classic(BPF_TCX_EGRESS, false);
@@ -864,7 +864,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_replace(void)
+void test_ns_tc_opts_replace(void)
{
test_tc_opts_replace_target(BPF_TCX_INGRESS);
test_tc_opts_replace_target(BPF_TCX_EGRESS);
@@ -1017,7 +1017,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_invalid(void)
+void test_ns_tc_opts_invalid(void)
{
test_tc_opts_invalid_target(BPF_TCX_INGRESS);
test_tc_opts_invalid_target(BPF_TCX_EGRESS);
@@ -1157,7 +1157,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_prepend(void)
+void test_ns_tc_opts_prepend(void)
{
test_tc_opts_prepend_target(BPF_TCX_INGRESS);
test_tc_opts_prepend_target(BPF_TCX_EGRESS);
@@ -1297,7 +1297,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_append(void)
+void test_ns_tc_opts_append(void)
{
test_tc_opts_append_target(BPF_TCX_INGRESS);
test_tc_opts_append_target(BPF_TCX_EGRESS);
@@ -1387,7 +1387,7 @@ cleanup:
ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
}
-void serial_test_tc_opts_dev_cleanup(void)
+void test_ns_tc_opts_dev_cleanup(void)
{
test_tc_opts_dev_cleanup_target(BPF_TCX_INGRESS);
test_tc_opts_dev_cleanup_target(BPF_TCX_EGRESS);
@@ -1563,7 +1563,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_opts_mixed(void)
+void test_ns_tc_opts_mixed(void)
{
test_tc_opts_mixed_target(BPF_TCX_INGRESS);
test_tc_opts_mixed_target(BPF_TCX_EGRESS);
@@ -1642,7 +1642,7 @@ cleanup:
assert_mprog_count(target, 0);
}
-void serial_test_tc_opts_demixed(void)
+void test_ns_tc_opts_demixed(void)
{
test_tc_opts_demixed_target(BPF_TCX_INGRESS);
test_tc_opts_demixed_target(BPF_TCX_EGRESS);
@@ -1813,7 +1813,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_detach(void)
+void test_ns_tc_opts_detach(void)
{
test_tc_opts_detach_target(BPF_TCX_INGRESS);
test_tc_opts_detach_target(BPF_TCX_EGRESS);
@@ -2020,7 +2020,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_detach_before(void)
+void test_ns_tc_opts_detach_before(void)
{
test_tc_opts_detach_before_target(BPF_TCX_INGRESS);
test_tc_opts_detach_before_target(BPF_TCX_EGRESS);
@@ -2236,7 +2236,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_detach_after(void)
+void test_ns_tc_opts_detach_after(void)
{
test_tc_opts_detach_after_target(BPF_TCX_INGRESS);
test_tc_opts_detach_after_target(BPF_TCX_EGRESS);
@@ -2265,7 +2265,7 @@ static void test_tc_opts_delete_empty(int target, bool chain_tc_old)
assert_mprog_count(target, 0);
}
-void serial_test_tc_opts_delete_empty(void)
+void test_ns_tc_opts_delete_empty(void)
{
test_tc_opts_delete_empty(BPF_TCX_INGRESS, false);
test_tc_opts_delete_empty(BPF_TCX_EGRESS, false);
@@ -2372,7 +2372,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_chain_mixed(void)
+void test_ns_tc_opts_chain_mixed(void)
{
test_tc_chain_mixed(BPF_TCX_INGRESS);
test_tc_chain_mixed(BPF_TCX_EGRESS);
@@ -2446,7 +2446,7 @@ cleanup:
ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
}
-void serial_test_tc_opts_max(void)
+void test_ns_tc_opts_max(void)
{
test_tc_opts_max_target(BPF_TCX_INGRESS, 0, false);
test_tc_opts_max_target(BPF_TCX_EGRESS, 0, false);
@@ -2748,7 +2748,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_query(void)
+void test_ns_tc_opts_query(void)
{
test_tc_opts_query_target(BPF_TCX_INGRESS);
test_tc_opts_query_target(BPF_TCX_EGRESS);
@@ -2807,7 +2807,7 @@ cleanup:
test_tc_link__destroy(skel);
}
-void serial_test_tc_opts_query_attach(void)
+void test_ns_tc_opts_query_attach(void)
{
test_tc_opts_query_attach_target(BPF_TCX_INGRESS);
test_tc_opts_query_attach_target(BPF_TCX_EGRESS);
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c
new file mode 100644
index 000000000000..467cc72a3588
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c
@@ -0,0 +1,16 @@
+#include <test_progs.h>
+
+#include "struct_ops_kptr_return.skel.h"
+#include "struct_ops_kptr_return_fail__wrong_type.skel.h"
+#include "struct_ops_kptr_return_fail__invalid_scalar.skel.h"
+#include "struct_ops_kptr_return_fail__nonzero_offset.skel.h"
+#include "struct_ops_kptr_return_fail__local_kptr.skel.h"
+
+void test_struct_ops_kptr_return(void)
+{
+ RUN_TESTS(struct_ops_kptr_return);
+ RUN_TESTS(struct_ops_kptr_return_fail__wrong_type);
+ RUN_TESTS(struct_ops_kptr_return_fail__invalid_scalar);
+ RUN_TESTS(struct_ops_kptr_return_fail__nonzero_offset);
+ RUN_TESTS(struct_ops_kptr_return_fail__local_kptr);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c
new file mode 100644
index 000000000000..da60c715fc59
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c
@@ -0,0 +1,14 @@
+#include <test_progs.h>
+
+#include "struct_ops_refcounted.skel.h"
+#include "struct_ops_refcounted_fail__ref_leak.skel.h"
+#include "struct_ops_refcounted_fail__global_subprog.skel.h"
+#include "struct_ops_refcounted_fail__tail_call.skel.h"
+
+void test_struct_ops_refcounted(void)
+{
+ RUN_TESTS(struct_ops_refcounted);
+ RUN_TESTS(struct_ops_refcounted_fail__ref_leak);
+ RUN_TESTS(struct_ops_refcounted_fail__global_subprog);
+ RUN_TESTS(struct_ops_refcounted_fail__tail_call);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
index cec746e77cd3..bae0e9de277d 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
@@ -71,6 +71,8 @@
#define IP4_ADDR2_VETH1 "172.16.1.20"
#define IP4_ADDR_TUNL_DEV0 "10.1.1.100"
#define IP4_ADDR_TUNL_DEV1 "10.1.1.200"
+#define IP6_ADDR_TUNL_DEV0 "fc80::100"
+#define IP6_ADDR_TUNL_DEV1 "fc80::200"
#define IP6_ADDR_VETH0 "::11"
#define IP6_ADDR1_VETH1 "::22"
@@ -98,6 +100,27 @@
#define XFRM_SPI_IN_TO_OUT 0x1
#define XFRM_SPI_OUT_TO_IN 0x2
+#define GRE_TUNL_DEV0 "gre00"
+#define GRE_TUNL_DEV1 "gre11"
+
+#define IP6GRE_TUNL_DEV0 "ip6gre00"
+#define IP6GRE_TUNL_DEV1 "ip6gre11"
+
+#define ERSPAN_TUNL_DEV0 "erspan00"
+#define ERSPAN_TUNL_DEV1 "erspan11"
+
+#define IP6ERSPAN_TUNL_DEV0 "ip6erspan00"
+#define IP6ERSPAN_TUNL_DEV1 "ip6erspan11"
+
+#define GENEVE_TUNL_DEV0 "geneve00"
+#define GENEVE_TUNL_DEV1 "geneve11"
+
+#define IP6GENEVE_TUNL_DEV0 "ip6geneve00"
+#define IP6GENEVE_TUNL_DEV1 "ip6geneve11"
+
+#define IP6TNL_TUNL_DEV0 "ip6tnl00"
+#define IP6TNL_TUNL_DEV1 "ip6tnl11"
+
#define PING_ARGS "-i 0.01 -c 3 -w 10 -q"
static int config_device(void)
@@ -216,6 +239,18 @@ fail:
return -1;
}
+static int set_ipv4_addr(const char *dev0, const char *dev1)
+{
+ SYS(fail, "ip -n at_ns0 link set dev %s up", dev0);
+ SYS(fail, "ip -n at_ns0 addr add dev %s %s/24", dev0, IP4_ADDR_TUNL_DEV0);
+ SYS(fail, "ip link set dev %s up", dev1);
+ SYS(fail, "ip addr add dev %s %s/24", dev1, IP4_ADDR_TUNL_DEV1);
+
+ return 0;
+fail:
+ return 1;
+}
+
static int add_ipip_tunnel(enum ipip_encap encap)
{
int err;
@@ -356,6 +391,99 @@ static void delete_xfrm_tunnel(void)
IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN);
}
+static int add_ipv4_tunnel(const char *dev0, const char *dev1,
+ const char *type, const char *opt)
+{
+ if (!type || !opt || !dev0 || !dev1)
+ return -1;
+
+ SYS(fail, "ip -n at_ns0 link add dev %s type %s %s local %s remote %s",
+ dev0, type, opt, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+ SYS(fail, "ip link add dev %s type %s external", dev1, type);
+
+ return set_ipv4_addr(dev0, dev1);
+fail:
+ return -1;
+}
+
+static void delete_tunnel(const char *dev0, const char *dev1)
+{
+ if (!dev0 || !dev1)
+ return;
+
+ SYS_NOFAIL("ip netns exec at_ns0 ip link delete dev %s", dev0);
+ SYS_NOFAIL("ip link delete dev %s", dev1);
+}
+
+static int set_ipv6_addr(const char *dev0, const char *dev1)
+{
+ /* disable IPv6 DAD because it might take too long and fail tests */
+ SYS(fail, "ip -n at_ns0 addr add %s/96 dev veth0 nodad", IP6_ADDR_VETH0);
+ SYS(fail, "ip -n at_ns0 link set dev veth0 up");
+ SYS(fail, "ip addr add %s/96 dev veth1 nodad", IP6_ADDR1_VETH1);
+ SYS(fail, "ip link set dev veth1 up");
+
+ SYS(fail, "ip -n at_ns0 addr add dev %s %s/24", dev0, IP4_ADDR_TUNL_DEV0);
+ SYS(fail, "ip -n at_ns0 addr add dev %s %s/96 nodad", dev0, IP6_ADDR_TUNL_DEV0);
+ SYS(fail, "ip -n at_ns0 link set dev %s up", dev0);
+
+ SYS(fail, "ip addr add dev %s %s/24", dev1, IP4_ADDR_TUNL_DEV1);
+ SYS(fail, "ip addr add dev %s %s/96 nodad", dev1, IP6_ADDR_TUNL_DEV1);
+ SYS(fail, "ip link set dev %s up", dev1);
+ return 0;
+fail:
+ return 1;
+}
+
+static int add_ipv6_tunnel(const char *dev0, const char *dev1,
+ const char *type, const char *opt)
+{
+ if (!type || !opt || !dev0 || !dev1)
+ return -1;
+
+ SYS(fail, "ip -n at_ns0 link add dev %s type %s %s local %s remote %s",
+ dev0, type, opt, IP6_ADDR_VETH0, IP6_ADDR1_VETH1);
+
+ SYS(fail, "ip link add dev %s type %s external", dev1, type);
+
+ return set_ipv6_addr(dev0, dev1);
+fail:
+ return -1;
+}
+
+static int add_geneve_tunnel(const char *dev0, const char *dev1,
+ const char *type, const char *opt)
+{
+ if (!type || !opt || !dev0 || !dev1)
+ return -1;
+
+ SYS(fail, "ip -n at_ns0 link add dev %s type %s id 2 %s remote %s",
+ dev0, type, opt, IP4_ADDR1_VETH1);
+
+ SYS(fail, "ip link add dev %s type %s %s external", dev1, type, opt);
+
+ return set_ipv4_addr(dev0, dev1);
+fail:
+ return -1;
+}
+
+static int add_ip6geneve_tunnel(const char *dev0, const char *dev1,
+ const char *type, const char *opt)
+{
+ if (!type || !opt || !dev0 || !dev1)
+ return -1;
+
+ SYS(fail, "ip -n at_ns0 link add dev %s type %s id 22 %s remote %s",
+ dev0, type, opt, IP6_ADDR1_VETH1);
+
+ SYS(fail, "ip link add dev %s type %s %s external", dev1, type, opt);
+
+ return set_ipv6_addr(dev0, dev1);
+fail:
+ return -1;
+}
+
static int test_ping(int family, const char *addr)
{
SYS(fail, "%s %s %s > /dev/null", ping_command(family), PING_ARGS, addr);
@@ -364,32 +492,76 @@ fail:
return -1;
}
-static int attach_tc_prog(struct bpf_tc_hook *hook, int igr_fd, int egr_fd)
+static void ping_dev0(void)
{
+ /* ping from root namespace test */
+ test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
+}
+
+static void ping_dev1(void)
+{
+ struct nstoken *nstoken;
+
+ /* ping from at_ns0 namespace test */
+ nstoken = open_netns("at_ns0");
+ if (!ASSERT_OK_PTR(nstoken, "setns"))
+ return;
+
+ test_ping(AF_INET, IP4_ADDR_TUNL_DEV1);
+ close_netns(nstoken);
+}
+
+static void ping6_veth0(void)
+{
+ test_ping(AF_INET6, IP6_ADDR_VETH0);
+}
+
+static void ping6_dev0(void)
+{
+ test_ping(AF_INET6, IP6_ADDR_TUNL_DEV0);
+}
+
+static void ping6_dev1(void)
+{
+ struct nstoken *nstoken;
+
+ /* ping from at_ns0 namespace test */
+ nstoken = open_netns("at_ns0");
+ if (!ASSERT_OK_PTR(nstoken, "setns"))
+ return;
+
+ test_ping(AF_INET, IP6_ADDR_TUNL_DEV1);
+ close_netns(nstoken);
+}
+
+static int attach_tc_prog(int ifindex, int igr_fd, int egr_fd)
+{
+ DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = ifindex,
+ .attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS);
DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts1, .handle = 1,
.priority = 1, .prog_fd = igr_fd);
DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts2, .handle = 1,
.priority = 1, .prog_fd = egr_fd);
int ret;
- ret = bpf_tc_hook_create(hook);
+ ret = bpf_tc_hook_create(&hook);
if (!ASSERT_OK(ret, "create tc hook"))
return ret;
if (igr_fd >= 0) {
- hook->attach_point = BPF_TC_INGRESS;
- ret = bpf_tc_attach(hook, &opts1);
+ hook.attach_point = BPF_TC_INGRESS;
+ ret = bpf_tc_attach(&hook, &opts1);
if (!ASSERT_OK(ret, "bpf_tc_attach")) {
- bpf_tc_hook_destroy(hook);
+ bpf_tc_hook_destroy(&hook);
return ret;
}
}
if (egr_fd >= 0) {
- hook->attach_point = BPF_TC_EGRESS;
- ret = bpf_tc_attach(hook, &opts2);
+ hook.attach_point = BPF_TC_EGRESS;
+ ret = bpf_tc_attach(&hook, &opts2);
if (!ASSERT_OK(ret, "bpf_tc_attach")) {
- bpf_tc_hook_destroy(hook);
+ bpf_tc_hook_destroy(&hook);
return ret;
}
}
@@ -397,6 +569,50 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int igr_fd, int egr_fd)
return 0;
}
+static int generic_attach(const char *dev, int igr_fd, int egr_fd)
+{
+ int ifindex;
+
+ if (!ASSERT_OK_FD(igr_fd, "check ingress fd"))
+ return -1;
+ if (!ASSERT_OK_FD(egr_fd, "check egress fd"))
+ return -1;
+
+ ifindex = if_nametoindex(dev);
+ if (!ASSERT_NEQ(ifindex, 0, "get ifindex"))
+ return -1;
+
+ return attach_tc_prog(ifindex, igr_fd, egr_fd);
+}
+
+static int generic_attach_igr(const char *dev, int igr_fd)
+{
+ int ifindex;
+
+ if (!ASSERT_OK_FD(igr_fd, "check ingress fd"))
+ return -1;
+
+ ifindex = if_nametoindex(dev);
+ if (!ASSERT_NEQ(ifindex, 0, "get ifindex"))
+ return -1;
+
+ return attach_tc_prog(ifindex, igr_fd, -1);
+}
+
+static int generic_attach_egr(const char *dev, int egr_fd)
+{
+ int ifindex;
+
+ if (!ASSERT_OK_FD(egr_fd, "check egress fd"))
+ return -1;
+
+ ifindex = if_nametoindex(dev);
+ if (!ASSERT_NEQ(ifindex, 0, "get ifindex"))
+ return -1;
+
+ return attach_tc_prog(ifindex, -1, egr_fd);
+}
+
static void test_vxlan_tunnel(void)
{
struct test_tunnel_kern *skel = NULL;
@@ -404,11 +620,9 @@ static void test_vxlan_tunnel(void)
int local_ip_map_fd = -1;
int set_src_prog_fd, get_src_prog_fd;
int set_dst_prog_fd;
- int key = 0, ifindex = -1;
+ int key = 0;
uint local_ip;
int err;
- DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
- .attach_point = BPF_TC_INGRESS);
/* add vxlan tunnel */
err = add_vxlan_tunnel();
@@ -419,42 +633,22 @@ static void test_vxlan_tunnel(void)
skel = test_tunnel_kern__open_and_load();
if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
goto done;
- ifindex = if_nametoindex(VXLAN_TUNL_DEV1);
- if (!ASSERT_NEQ(ifindex, 0, "vxlan11 ifindex"))
- goto done;
- tc_hook.ifindex = ifindex;
get_src_prog_fd = bpf_program__fd(skel->progs.vxlan_get_tunnel_src);
set_src_prog_fd = bpf_program__fd(skel->progs.vxlan_set_tunnel_src);
- if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd"))
- goto done;
- if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd"))
- goto done;
- if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd))
+ if (generic_attach(VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd))
goto done;
/* load and attach bpf prog to veth dev tc hook point */
- ifindex = if_nametoindex("veth1");
- if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
- goto done;
- tc_hook.ifindex = ifindex;
set_dst_prog_fd = bpf_program__fd(skel->progs.veth_set_outer_dst);
- if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
- goto done;
- if (attach_tc_prog(&tc_hook, set_dst_prog_fd, -1))
+ if (generic_attach_igr("veth1", set_dst_prog_fd))
goto done;
/* load and attach prog set_md to tunnel dev tc hook point at_ns0 */
nstoken = open_netns("at_ns0");
if (!ASSERT_OK_PTR(nstoken, "setns src"))
goto done;
- ifindex = if_nametoindex(VXLAN_TUNL_DEV0);
- if (!ASSERT_NEQ(ifindex, 0, "vxlan00 ifindex"))
- goto done;
- tc_hook.ifindex = ifindex;
set_dst_prog_fd = bpf_program__fd(skel->progs.vxlan_set_tunnel_dst);
- if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
- goto done;
- if (attach_tc_prog(&tc_hook, -1, set_dst_prog_fd))
+ if (generic_attach_egr(VXLAN_TUNL_DEV0, set_dst_prog_fd))
goto done;
close_netns(nstoken);
@@ -468,9 +662,7 @@ static void test_vxlan_tunnel(void)
goto done;
/* ping test */
- err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
- if (!ASSERT_OK(err, "test_ping"))
- goto done;
+ ping_dev0();
done:
/* delete vxlan tunnel */
@@ -488,11 +680,9 @@ static void test_ip6vxlan_tunnel(void)
int local_ip_map_fd = -1;
int set_src_prog_fd, get_src_prog_fd;
int set_dst_prog_fd;
- int key = 0, ifindex = -1;
+ int key = 0;
uint local_ip;
int err;
- DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
- .attach_point = BPF_TC_INGRESS);
/* add vxlan tunnel */
err = add_ip6vxlan_tunnel();
@@ -503,31 +693,17 @@ static void test_ip6vxlan_tunnel(void)
skel = test_tunnel_kern__open_and_load();
if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
goto done;
- ifindex = if_nametoindex(IP6VXLAN_TUNL_DEV1);
- if (!ASSERT_NEQ(ifindex, 0, "ip6vxlan11 ifindex"))
- goto done;
- tc_hook.ifindex = ifindex;
get_src_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_get_tunnel_src);
set_src_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_set_tunnel_src);
- if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd"))
- goto done;
- if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd"))
- goto done;
- if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd))
+ if (generic_attach(IP6VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd))
goto done;
/* load and attach prog set_md to tunnel dev tc hook point at_ns0 */
nstoken = open_netns("at_ns0");
if (!ASSERT_OK_PTR(nstoken, "setns src"))
goto done;
- ifindex = if_nametoindex(IP6VXLAN_TUNL_DEV0);
- if (!ASSERT_NEQ(ifindex, 0, "ip6vxlan00 ifindex"))
- goto done;
- tc_hook.ifindex = ifindex;
set_dst_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_set_tunnel_dst);
- if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
- goto done;
- if (attach_tc_prog(&tc_hook, -1, set_dst_prog_fd))
+ if (generic_attach_egr(IP6VXLAN_TUNL_DEV0, set_dst_prog_fd))
goto done;
close_netns(nstoken);
@@ -541,9 +717,7 @@ static void test_ip6vxlan_tunnel(void)
goto done;
/* ping test */
- err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
- if (!ASSERT_OK(err, "test_ping"))
- goto done;
+ ping_dev0();
done:
/* delete ipv6 vxlan tunnel */
@@ -557,12 +731,8 @@ done:
static void test_ipip_tunnel(enum ipip_encap encap)
{
struct test_tunnel_kern *skel = NULL;
- struct nstoken *nstoken;
int set_src_prog_fd, get_src_prog_fd;
- int ifindex = -1;
int err;
- DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
- .attach_point = BPF_TC_INGRESS);
/* add ipip tunnel */
err = add_ipip_tunnel(encap);
@@ -573,10 +743,6 @@ static void test_ipip_tunnel(enum ipip_encap encap)
skel = test_tunnel_kern__open_and_load();
if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
goto done;
- ifindex = if_nametoindex(IPIP_TUNL_DEV1);
- if (!ASSERT_NEQ(ifindex, 0, "ipip11 ifindex"))
- goto done;
- tc_hook.ifindex = ifindex;
switch (encap) {
case FOU:
@@ -598,26 +764,11 @@ static void test_ipip_tunnel(enum ipip_encap encap)
skel->progs.ipip_set_tunnel);
}
- if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd"))
- goto done;
- if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd"))
- goto done;
- if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd))
+ if (generic_attach(IPIP_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd))
goto done;
- /* ping from root namespace test */
- err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
- if (!ASSERT_OK(err, "test_ping"))
- goto done;
-
- /* ping from at_ns0 namespace test */
- nstoken = open_netns("at_ns0");
- if (!ASSERT_OK_PTR(nstoken, "setns"))
- goto done;
- err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1);
- if (!ASSERT_OK(err, "test_ping"))
- goto done;
- close_netns(nstoken);
+ ping_dev0();
+ ping_dev1();
done:
/* delete ipip tunnel */
@@ -628,11 +779,8 @@ done:
static void test_xfrm_tunnel(void)
{
- DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
- .attach_point = BPF_TC_INGRESS);
LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
struct test_tunnel_kern *skel = NULL;
- struct nstoken *nstoken;
int xdp_prog_fd;
int tc_prog_fd;
int ifindex;
@@ -646,19 +794,16 @@ static void test_xfrm_tunnel(void)
if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
goto done;
- ifindex = if_nametoindex("veth1");
- if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
- goto done;
/* attach tc prog to tunnel dev */
- tc_hook.ifindex = ifindex;
tc_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state);
- if (!ASSERT_GE(tc_prog_fd, 0, "bpf_program__fd"))
- goto done;
- if (attach_tc_prog(&tc_hook, tc_prog_fd, -1))
+ if (generic_attach_igr("veth1", tc_prog_fd))
goto done;
/* attach xdp prog to tunnel dev */
+ ifindex = if_nametoindex("veth1");
+ if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
+ goto done;
xdp_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state_xdp);
if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__fd"))
goto done;
@@ -666,14 +811,7 @@ static void test_xfrm_tunnel(void)
if (!ASSERT_OK(err, "bpf_xdp_attach"))
goto done;
- /* ping from at_ns0 namespace test */
- nstoken = open_netns("at_ns0");
- if (!ASSERT_OK_PTR(nstoken, "setns"))
- goto done;
- err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1);
- close_netns(nstoken);
- if (!ASSERT_OK(err, "test_ping"))
- goto done;
+ ping_dev1();
if (!ASSERT_EQ(skel->bss->xfrm_reqid, 1, "req_id"))
goto done;
@@ -690,6 +828,281 @@ done:
test_tunnel_kern__destroy(skel);
}
+enum gre_test {
+ GRE,
+ GRE_NOKEY,
+ GRETAP,
+ GRETAP_NOKEY,
+};
+
+static void test_gre_tunnel(enum gre_test test)
+{
+ struct test_tunnel_kern *skel;
+ int set_fd, get_fd;
+ int err;
+
+ skel = test_tunnel_kern__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+ return;
+
+ switch (test) {
+ case GRE:
+ err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gre", "seq");
+ set_fd = bpf_program__fd(skel->progs.gre_set_tunnel_no_key);
+ get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+ break;
+ case GRE_NOKEY:
+ err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gre", "seq key 2");
+ set_fd = bpf_program__fd(skel->progs.gre_set_tunnel);
+ get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+ break;
+ case GRETAP:
+ err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gretap", "seq");
+ set_fd = bpf_program__fd(skel->progs.gre_set_tunnel_no_key);
+ get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+ break;
+ case GRETAP_NOKEY:
+ err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gretap", "seq key 2");
+ set_fd = bpf_program__fd(skel->progs.gre_set_tunnel);
+ get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+ break;
+ }
+ if (!ASSERT_OK(err, "add tunnel"))
+ goto done;
+
+ if (generic_attach(GRE_TUNL_DEV1, get_fd, set_fd))
+ goto done;
+
+ ping_dev0();
+ ping_dev1();
+
+done:
+ delete_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1);
+ test_tunnel_kern__destroy(skel);
+}
+
+enum ip6gre_test {
+ IP6GRE,
+ IP6GRETAP
+};
+
+static void test_ip6gre_tunnel(enum ip6gre_test test)
+{
+ struct test_tunnel_kern *skel;
+ int set_fd, get_fd;
+ int err;
+
+ skel = test_tunnel_kern__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+ return;
+
+ switch (test) {
+ case IP6GRE:
+ err = add_ipv6_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1,
+ "ip6gre", "flowlabel 0xbcdef key 2");
+ break;
+ case IP6GRETAP:
+ err = add_ipv6_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1,
+ "ip6gretap", "flowlabel 0xbcdef key 2");
+ break;
+ }
+ if (!ASSERT_OK(err, "add tunnel"))
+ goto done;
+
+ set_fd = bpf_program__fd(skel->progs.ip6gretap_set_tunnel);
+ get_fd = bpf_program__fd(skel->progs.ip6gretap_get_tunnel);
+ if (generic_attach(IP6GRE_TUNL_DEV1, get_fd, set_fd))
+ goto done;
+
+ ping6_veth0();
+ ping6_dev1();
+ ping_dev0();
+ ping_dev1();
+done:
+ delete_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1);
+ test_tunnel_kern__destroy(skel);
+}
+
+enum erspan_test {
+ V1,
+ V2
+};
+
+static void test_erspan_tunnel(enum erspan_test test)
+{
+ struct test_tunnel_kern *skel;
+ int set_fd, get_fd;
+ int err;
+
+ skel = test_tunnel_kern__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+ return;
+
+ switch (test) {
+ case V1:
+ err = add_ipv4_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1,
+ "erspan", "seq key 2 erspan_ver 1 erspan 123");
+ break;
+ case V2:
+ err = add_ipv4_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1,
+ "erspan",
+ "seq key 2 erspan_ver 2 erspan_dir egress erspan_hwid 3");
+ break;
+ }
+ if (!ASSERT_OK(err, "add tunnel"))
+ goto done;
+
+ set_fd = bpf_program__fd(skel->progs.erspan_set_tunnel);
+ get_fd = bpf_program__fd(skel->progs.erspan_get_tunnel);
+ if (generic_attach(ERSPAN_TUNL_DEV1, get_fd, set_fd))
+ goto done;
+
+ ping_dev0();
+ ping_dev1();
+done:
+ delete_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1);
+ test_tunnel_kern__destroy(skel);
+}
+
+static void test_ip6erspan_tunnel(enum erspan_test test)
+{
+ struct test_tunnel_kern *skel;
+ int set_fd, get_fd;
+ int err;
+
+ skel = test_tunnel_kern__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+ return;
+
+ switch (test) {
+ case V1:
+ err = add_ipv6_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1,
+ "ip6erspan", "seq key 2 erspan_ver 1 erspan 123");
+ break;
+ case V2:
+ err = add_ipv6_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1,
+ "ip6erspan",
+ "seq key 2 erspan_ver 2 erspan_dir egress erspan_hwid 7");
+ break;
+ }
+ if (!ASSERT_OK(err, "add tunnel"))
+ goto done;
+
+ set_fd = bpf_program__fd(skel->progs.ip4ip6erspan_set_tunnel);
+ get_fd = bpf_program__fd(skel->progs.ip4ip6erspan_get_tunnel);
+ if (generic_attach(IP6ERSPAN_TUNL_DEV1, get_fd, set_fd))
+ goto done;
+
+ ping6_veth0();
+ ping_dev1();
+done:
+ delete_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1);
+ test_tunnel_kern__destroy(skel);
+}
+
+static void test_geneve_tunnel(void)
+{
+ struct test_tunnel_kern *skel;
+ int set_fd, get_fd;
+ int err;
+
+ skel = test_tunnel_kern__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+ return;
+
+ err = add_geneve_tunnel(GENEVE_TUNL_DEV0, GENEVE_TUNL_DEV1,
+ "geneve", "dstport 6081");
+ if (!ASSERT_OK(err, "add tunnel"))
+ goto done;
+
+ set_fd = bpf_program__fd(skel->progs.geneve_set_tunnel);
+ get_fd = bpf_program__fd(skel->progs.geneve_get_tunnel);
+ if (generic_attach(GENEVE_TUNL_DEV1, get_fd, set_fd))
+ goto done;
+
+ ping_dev0();
+ ping_dev1();
+done:
+ delete_tunnel(GENEVE_TUNL_DEV0, GENEVE_TUNL_DEV1);
+ test_tunnel_kern__destroy(skel);
+}
+
+static void test_ip6geneve_tunnel(void)
+{
+ struct test_tunnel_kern *skel;
+ int set_fd, get_fd;
+ int err;
+
+ skel = test_tunnel_kern__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+ return;
+
+ err = add_ip6geneve_tunnel(IP6GENEVE_TUNL_DEV0, IP6GENEVE_TUNL_DEV1,
+ "geneve", "");
+ if (!ASSERT_OK(err, "add tunnel"))
+ goto done;
+
+ set_fd = bpf_program__fd(skel->progs.ip6geneve_set_tunnel);
+ get_fd = bpf_program__fd(skel->progs.ip6geneve_get_tunnel);
+ if (generic_attach(IP6GENEVE_TUNL_DEV1, get_fd, set_fd))
+ goto done;
+
+ ping_dev0();
+ ping_dev1();
+done:
+ delete_tunnel(IP6GENEVE_TUNL_DEV0, IP6GENEVE_TUNL_DEV1);
+ test_tunnel_kern__destroy(skel);
+}
+
+enum ip6tnl_test {
+ IPIP6,
+ IP6IP6
+};
+
+static void test_ip6tnl_tunnel(enum ip6tnl_test test)
+{
+ struct test_tunnel_kern *skel;
+ int set_fd, get_fd;
+ int err;
+
+ skel = test_tunnel_kern__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+ return;
+
+ err = add_ipv6_tunnel(IP6TNL_TUNL_DEV0, IP6TNL_TUNL_DEV1, "ip6tnl", "");
+ if (!ASSERT_OK(err, "add tunnel"))
+ goto done;
+
+ switch (test) {
+ case IPIP6:
+ set_fd = bpf_program__fd(skel->progs.ipip6_set_tunnel);
+ get_fd = bpf_program__fd(skel->progs.ipip6_get_tunnel);
+ break;
+ case IP6IP6:
+ set_fd = bpf_program__fd(skel->progs.ip6ip6_set_tunnel);
+ get_fd = bpf_program__fd(skel->progs.ip6ip6_get_tunnel);
+ break;
+ }
+ if (generic_attach(IP6TNL_TUNL_DEV1, get_fd, set_fd))
+ goto done;
+
+ ping6_veth0();
+ switch (test) {
+ case IPIP6:
+ ping_dev0();
+ ping_dev1();
+ break;
+ case IP6IP6:
+ ping6_dev0();
+ ping6_dev1();
+ break;
+ }
+
+done:
+ delete_tunnel(IP6TNL_TUNL_DEV0, IP6TNL_TUNL_DEV1);
+ test_tunnel_kern__destroy(skel);
+}
+
#define RUN_TEST(name, ...) \
({ \
if (test__start_subtest(#name)) { \
@@ -707,6 +1120,20 @@ static void *test_tunnel_run_tests(void *arg)
RUN_TEST(ipip_tunnel, FOU);
RUN_TEST(ipip_tunnel, GUE);
RUN_TEST(xfrm_tunnel);
+ RUN_TEST(gre_tunnel, GRE);
+ RUN_TEST(gre_tunnel, GRE_NOKEY);
+ RUN_TEST(gre_tunnel, GRETAP);
+ RUN_TEST(gre_tunnel, GRETAP_NOKEY);
+ RUN_TEST(ip6gre_tunnel, IP6GRE);
+ RUN_TEST(ip6gre_tunnel, IP6GRETAP);
+ RUN_TEST(erspan_tunnel, V1);
+ RUN_TEST(erspan_tunnel, V2);
+ RUN_TEST(ip6erspan_tunnel, V1);
+ RUN_TEST(ip6erspan_tunnel, V2);
+ RUN_TEST(geneve_tunnel);
+ RUN_TEST(ip6geneve_tunnel);
+ RUN_TEST(ip6tnl_tunnel, IPIP6);
+ RUN_TEST(ip6tnl_tunnel, IP6IP6);
return NULL;
}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
new file mode 100644
index 000000000000..a95b42bf744a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <string.h>
+#include <stdio.h>
+
+#define __CHECK_STR(str, name) \
+ do { \
+ if (!ASSERT_HAS_SUBSTR(fix->output, (str), (name))) \
+ goto out; \
+ } while (0)
+
+struct fixture {
+ char tmpfile[80];
+ int fd;
+ char *output;
+ size_t sz;
+ char veristat[80];
+};
+
+static struct fixture *init_fixture(void)
+{
+ struct fixture *fix = malloc(sizeof(struct fixture));
+
+ /* for no_alu32 and cpuv4 veristat is in parent folder */
+ if (access("./veristat", F_OK) == 0)
+ strcpy(fix->veristat, "./veristat");
+ else if (access("../veristat", F_OK) == 0)
+ strcpy(fix->veristat, "../veristat");
+ else
+ PRINT_FAIL("Can't find veristat binary");
+
+ snprintf(fix->tmpfile, sizeof(fix->tmpfile), "/tmp/test_veristat.XXXXXX");
+ fix->fd = mkstemp(fix->tmpfile);
+ fix->sz = 1000000;
+ fix->output = malloc(fix->sz);
+ return fix;
+}
+
+static void teardown_fixture(struct fixture *fix)
+{
+ free(fix->output);
+ close(fix->fd);
+ remove(fix->tmpfile);
+ free(fix);
+}
+
+static void test_set_global_vars_succeeds(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS(out,
+ "%s set_global_vars.bpf.o"\
+ " -G \"var_s64 = 0xf000000000000001\" "\
+ " -G \"var_u64 = 0xfedcba9876543210\" "\
+ " -G \"var_s32 = -0x80000000\" "\
+ " -G \"var_u32 = 0x76543210\" "\
+ " -G \"var_s16 = -32768\" "\
+ " -G \"var_u16 = 60652\" "\
+ " -G \"var_s8 = -128\" "\
+ " -G \"var_u8 = 255\" "\
+ " -G \"var_ea = EA2\" "\
+ " -G \"var_eb = EB2\" "\
+ " -G \"var_ec = EC2\" "\
+ " -G \"var_b = 1\" "\
+ "-vl2 > %s", fix->veristat, fix->tmpfile);
+
+ read(fix->fd, fix->output, fix->sz);
+ __CHECK_STR("_w=0xf000000000000001 ", "var_s64 = 0xf000000000000001");
+ __CHECK_STR("_w=0xfedcba9876543210 ", "var_u64 = 0xfedcba9876543210");
+ __CHECK_STR("_w=0x80000000 ", "var_s32 = -0x80000000");
+ __CHECK_STR("_w=0x76543210 ", "var_u32 = 0x76543210");
+ __CHECK_STR("_w=0x8000 ", "var_s16 = -32768");
+ __CHECK_STR("_w=0xecec ", "var_u16 = 60652");
+ __CHECK_STR("_w=128 ", "var_s8 = -128");
+ __CHECK_STR("_w=255 ", "var_u8 = 255");
+ __CHECK_STR("_w=11 ", "var_ea = EA2");
+ __CHECK_STR("_w=12 ", "var_eb = EB2");
+ __CHECK_STR("_w=13 ", "var_ec = EC2");
+ __CHECK_STR("_w=1 ", "var_b = 1");
+
+out:
+ teardown_fixture(fix);
+}
+
+static void test_set_global_vars_from_file_succeeds(void)
+{
+ struct fixture *fix = init_fixture();
+ char input_file[80];
+ const char *vars = "var_s16 = -32768\nvar_u16 = 60652";
+ int fd;
+
+ snprintf(input_file, sizeof(input_file), "/tmp/veristat_input.XXXXXX");
+ fd = mkstemp(input_file);
+ if (!ASSERT_GE(fd, 0, "valid fd"))
+ goto out;
+
+ write(fd, vars, strlen(vars));
+ syncfs(fd);
+ SYS(out, "%s set_global_vars.bpf.o -G \"@%s\" -vl2 > %s",
+ fix->veristat, input_file, fix->tmpfile);
+ read(fix->fd, fix->output, fix->sz);
+ __CHECK_STR("_w=0x8000 ", "var_s16 = -32768");
+ __CHECK_STR("_w=0xecec ", "var_u16 = 60652");
+
+out:
+ close(fd);
+ remove(input_file);
+ teardown_fixture(fix);
+}
+
+static void test_set_global_vars_out_of_range(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"var_s32 = 2147483648\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ read(fix->fd, fix->output, fix->sz);
+ __CHECK_STR("is out of range [-2147483648; 2147483647]", "out of range");
+
+out:
+ teardown_fixture(fix);
+}
+
+void test_veristat(void)
+{
+ if (test__start_subtest("set_global_vars_succeeds"))
+ test_set_global_vars_succeeds();
+
+ if (test__start_subtest("set_global_vars_out_of_range"))
+ test_set_global_vars_out_of_range();
+
+ if (test__start_subtest("set_global_vars_from_file_succeeds"))
+ test_set_global_vars_from_file_succeeds();
+}
+
+#undef __CHECK_STR
diff --git a/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c b/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c
index 8d75424fe6bc..3e98a1665936 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c
@@ -3,17 +3,50 @@
/* Create 3 namespaces with 3 veth peers, and forward packets in-between using
* native XDP
*
- * XDP_TX
- * NS1(veth11) NS2(veth22) NS3(veth33)
- * | | |
- * | | |
- * (veth1, (veth2, (veth3,
- * id:111) id:122) id:133)
- * ^ | ^ | ^ |
- * | | XDP_REDIRECT | | XDP_REDIRECT | |
- * | ------------------ ------------------ |
- * -----------------------------------------
- * XDP_REDIRECT
+ * Network topology:
+ * ---------- ---------- ----------
+ * | NS1 | | NS2 | | NS3 |
+ * | veth11 | | veth22 | | veth33 |
+ * ----|----- -----|---- -----|----
+ * | | |
+ * ----|------------------|----------------|----
+ * | veth1 veth2 veth3 |
+ * | |
+ * | NSO |
+ * ---------------------------------------------
+ *
+ * Test cases:
+ * - [test_xdp_veth_redirect] : ping veth33 from veth11
+ *
+ * veth11 veth22 veth33
+ * (XDP_PASS) (XDP_TX) (XDP_PASS)
+ * | | |
+ * | | |
+ * veth1 veth2 veth3
+ * (XDP_REDIRECT) (XDP_REDIRECT) (XDP_REDIRECT)
+ * ^ | ^ | ^ |
+ * | | | | | |
+ * | ------------------ ------------------ |
+ * -----------------------------------------
+ *
+ * - [test_xdp_veth_broadcast_redirect]: broadcast from veth11
+ * - IPv4 ping : BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS
+ * -> echo request received by all except veth11
+ * - IPv4 ping : BPF_F_BROADCAST
+ * -> echo request received by all veth
+ * - [test_xdp_veth_egress]:
+ * - all src mac should be the magic mac
+ *
+ * veth11 veth22 veth33
+ * (XDP_PASS) (XDP_PASS) (XDP_PASS)
+ * | | |
+ * | | |
+ * veth1 veth2 veth3
+ * (XDP_REDIRECT) (XDP_REDIRECT) (XDP_REDIRECT)
+ * | ^ ^
+ * | | |
+ * ----------------------------------------
+ *
*/
#define _GNU_SOURCE
@@ -22,192 +55,545 @@
#include "network_helpers.h"
#include "xdp_dummy.skel.h"
#include "xdp_redirect_map.skel.h"
+#include "xdp_redirect_multi_kern.skel.h"
#include "xdp_tx.skel.h"
+#include <uapi/linux/if_link.h>
#define VETH_PAIRS_COUNT 3
-#define NS_SUFFIX_LEN 6
-#define VETH_NAME_MAX_LEN 16
+#define VETH_NAME_MAX_LEN 32
+#define IP_MAX_LEN 16
#define IP_SRC "10.1.1.11"
#define IP_DST "10.1.1.33"
-#define IP_CMD_MAX_LEN 128
-
-struct skeletons {
- struct xdp_dummy *xdp_dummy;
- struct xdp_tx *xdp_tx;
- struct xdp_redirect_map *xdp_redirect_maps;
-};
+#define IP_NEIGH "10.1.1.253"
+#define PROG_NAME_MAX_LEN 128
+#define NS_NAME_MAX_LEN 32
struct veth_configuration {
char local_veth[VETH_NAME_MAX_LEN]; /* Interface in main namespace */
char remote_veth[VETH_NAME_MAX_LEN]; /* Peer interface in dedicated namespace*/
- const char *namespace; /* Namespace for the remote veth */
- char next_veth[VETH_NAME_MAX_LEN]; /* Local interface to redirect traffic to */
- char *remote_addr; /* IP address of the remote veth */
+ char namespace[NS_NAME_MAX_LEN]; /* Namespace for the remote veth */
+ int next_veth; /* Local interface to redirect traffic to */
+ char remote_addr[IP_MAX_LEN]; /* IP address of the remote veth */
};
-static struct veth_configuration config[VETH_PAIRS_COUNT] = {
- {
- .local_veth = "veth1",
- .remote_veth = "veth11",
- .next_veth = "veth2",
- .remote_addr = IP_SRC,
- .namespace = "ns-veth11"
- },
- {
- .local_veth = "veth2",
- .remote_veth = "veth22",
- .next_veth = "veth3",
- .remote_addr = NULL,
- .namespace = "ns-veth22"
- },
+struct net_configuration {
+ char ns0_name[NS_NAME_MAX_LEN];
+ struct veth_configuration veth_cfg[VETH_PAIRS_COUNT];
+};
+
+static const struct net_configuration default_config = {
+ .ns0_name = "ns0-",
{
- .local_veth = "veth3",
- .remote_veth = "veth33",
- .next_veth = "veth1",
- .remote_addr = IP_DST,
- .namespace = "ns-veth33"
+ {
+ .local_veth = "veth1-",
+ .remote_veth = "veth11",
+ .next_veth = 1,
+ .remote_addr = IP_SRC,
+ .namespace = "ns-veth11-"
+ },
+ {
+ .local_veth = "veth2-",
+ .remote_veth = "veth22",
+ .next_veth = 2,
+ .remote_addr = "",
+ .namespace = "ns-veth22-"
+ },
+ {
+ .local_veth = "veth3-",
+ .remote_veth = "veth33",
+ .next_veth = 0,
+ .remote_addr = IP_DST,
+ .namespace = "ns-veth33-"
+ }
}
};
-static int attach_programs_to_veth_pair(struct skeletons *skeletons, int index)
+struct prog_configuration {
+ char local_name[PROG_NAME_MAX_LEN]; /* BPF prog to attach to local_veth */
+ char remote_name[PROG_NAME_MAX_LEN]; /* BPF prog to attach to remote_veth */
+ u32 local_flags; /* XDP flags to use on local_veth */
+ u32 remote_flags; /* XDP flags to use on remote_veth */
+};
+
+static int attach_programs_to_veth_pair(struct bpf_object **objs, size_t nb_obj,
+ struct net_configuration *net_config,
+ struct prog_configuration *prog, int index)
{
struct bpf_program *local_prog, *remote_prog;
- struct bpf_link **local_link, **remote_link;
struct nstoken *nstoken;
- struct bpf_link *link;
- int interface;
-
- switch (index) {
- case 0:
- local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_0;
- local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_0;
- remote_prog = skeletons->xdp_dummy->progs.xdp_dummy_prog;
- remote_link = &skeletons->xdp_dummy->links.xdp_dummy_prog;
- break;
- case 1:
- local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_1;
- local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_1;
- remote_prog = skeletons->xdp_tx->progs.xdp_tx;
- remote_link = &skeletons->xdp_tx->links.xdp_tx;
- break;
- case 2:
- local_prog = skeletons->xdp_redirect_maps->progs.xdp_redirect_map_2;
- local_link = &skeletons->xdp_redirect_maps->links.xdp_redirect_map_2;
- remote_prog = skeletons->xdp_dummy->progs.xdp_dummy_prog;
- remote_link = &skeletons->xdp_dummy->links.xdp_dummy_prog;
- break;
+ int interface, ret, i;
+
+ for (i = 0; i < nb_obj; i++) {
+ local_prog = bpf_object__find_program_by_name(objs[i], prog[index].local_name);
+ if (local_prog)
+ break;
}
- interface = if_nametoindex(config[index].local_veth);
+ if (!ASSERT_OK_PTR(local_prog, "find local program"))
+ return -1;
+
+ for (i = 0; i < nb_obj; i++) {
+ remote_prog = bpf_object__find_program_by_name(objs[i], prog[index].remote_name);
+ if (remote_prog)
+ break;
+ }
+ if (!ASSERT_OK_PTR(remote_prog, "find remote program"))
+ return -1;
+
+ interface = if_nametoindex(net_config->veth_cfg[index].local_veth);
if (!ASSERT_NEQ(interface, 0, "non zero interface index"))
return -1;
- link = bpf_program__attach_xdp(local_prog, interface);
- if (!ASSERT_OK_PTR(link, "attach xdp program to local veth"))
+
+ ret = bpf_xdp_attach(interface, bpf_program__fd(local_prog),
+ prog[index].local_flags, NULL);
+ if (!ASSERT_OK(ret, "attach xdp program to local veth"))
return -1;
- *local_link = link;
- nstoken = open_netns(config[index].namespace);
+
+ nstoken = open_netns(net_config->veth_cfg[index].namespace);
if (!ASSERT_OK_PTR(nstoken, "switch to remote veth namespace"))
return -1;
- interface = if_nametoindex(config[index].remote_veth);
+
+ interface = if_nametoindex(net_config->veth_cfg[index].remote_veth);
if (!ASSERT_NEQ(interface, 0, "non zero interface index")) {
close_netns(nstoken);
return -1;
}
- link = bpf_program__attach_xdp(remote_prog, interface);
- *remote_link = link;
- close_netns(nstoken);
- if (!ASSERT_OK_PTR(link, "attach xdp program to remote veth"))
+
+ ret = bpf_xdp_attach(interface, bpf_program__fd(remote_prog),
+ prog[index].remote_flags, NULL);
+ if (!ASSERT_OK(ret, "attach xdp program to remote veth")) {
+ close_netns(nstoken);
return -1;
+ }
+ close_netns(nstoken);
return 0;
}
-static int configure_network(struct skeletons *skeletons)
+static int create_network(struct net_configuration *net_config)
{
- int interface_id;
- int map_fd;
- int err;
- int i = 0;
+ struct nstoken *nstoken = NULL;
+ int i, err;
+
+ memcpy(net_config, &default_config, sizeof(struct net_configuration));
+
+ /* Create unique namespaces */
+ err = append_tid(net_config->ns0_name, NS_NAME_MAX_LEN);
+ if (!ASSERT_OK(err, "append TID to ns0 name"))
+ goto fail;
+ SYS(fail, "ip netns add %s", net_config->ns0_name);
- /* First create and configure all interfaces */
for (i = 0; i < VETH_PAIRS_COUNT; i++) {
- SYS(fail, "ip netns add %s", config[i].namespace);
- SYS(fail, "ip link add %s type veth peer name %s netns %s",
- config[i].local_veth, config[i].remote_veth, config[i].namespace);
- SYS(fail, "ip link set dev %s up", config[i].local_veth);
- if (config[i].remote_addr)
- SYS(fail, "ip -n %s addr add %s/24 dev %s", config[i].namespace,
- config[i].remote_addr, config[i].remote_veth);
- SYS(fail, "ip -n %s link set dev %s up", config[i].namespace,
- config[i].remote_veth);
+ err = append_tid(net_config->veth_cfg[i].namespace, NS_NAME_MAX_LEN);
+ if (!ASSERT_OK(err, "append TID to ns name"))
+ goto fail;
+ SYS(fail, "ip netns add %s", net_config->veth_cfg[i].namespace);
}
- /* Then configure the redirect map and attach programs to interfaces */
- map_fd = bpf_map__fd(skeletons->xdp_redirect_maps->maps.tx_port);
- if (!ASSERT_GE(map_fd, 0, "open redirect map"))
+ /* Create interfaces */
+ nstoken = open_netns(net_config->ns0_name);
+ if (!nstoken)
goto fail;
+
for (i = 0; i < VETH_PAIRS_COUNT; i++) {
- interface_id = if_nametoindex(config[i].next_veth);
- if (!ASSERT_NEQ(interface_id, 0, "non zero interface index"))
- goto fail;
- err = bpf_map_update_elem(map_fd, &i, &interface_id, BPF_ANY);
- if (!ASSERT_OK(err, "configure interface redirection through map"))
- goto fail;
- if (attach_programs_to_veth_pair(skeletons, i))
- goto fail;
+ SYS(fail, "ip link add %s type veth peer name %s netns %s",
+ net_config->veth_cfg[i].local_veth, net_config->veth_cfg[i].remote_veth,
+ net_config->veth_cfg[i].namespace);
+ SYS(fail, "ip link set dev %s up", net_config->veth_cfg[i].local_veth);
+ if (net_config->veth_cfg[i].remote_addr[0])
+ SYS(fail, "ip -n %s addr add %s/24 dev %s",
+ net_config->veth_cfg[i].namespace,
+ net_config->veth_cfg[i].remote_addr,
+ net_config->veth_cfg[i].remote_veth);
+ SYS(fail, "ip -n %s link set dev %s up", net_config->veth_cfg[i].namespace,
+ net_config->veth_cfg[i].remote_veth);
}
+ close_netns(nstoken);
return 0;
fail:
+ close_netns(nstoken);
return -1;
}
-static void cleanup_network(void)
+static void cleanup_network(struct net_configuration *net_config)
{
int i;
- /* Deleting namespaces is enough to automatically remove veth pairs as well
- */
+ SYS_NOFAIL("ip netns del %s", net_config->ns0_name);
for (i = 0; i < VETH_PAIRS_COUNT; i++)
- SYS_NOFAIL("ip netns del %s", config[i].namespace);
+ SYS_NOFAIL("ip netns del %s", net_config->veth_cfg[i].namespace);
}
-static int check_ping(struct skeletons *skeletons)
+#define VETH_REDIRECT_SKEL_NB 3
+static void xdp_veth_redirect(u32 flags)
{
+ struct prog_configuration ping_config[VETH_PAIRS_COUNT] = {
+ {
+ .local_name = "xdp_redirect_map_0",
+ .remote_name = "xdp_dummy_prog",
+ .local_flags = flags,
+ .remote_flags = flags,
+ },
+ {
+ .local_name = "xdp_redirect_map_1",
+ .remote_name = "xdp_tx",
+ .local_flags = flags,
+ .remote_flags = flags,
+ },
+ {
+ .local_name = "xdp_redirect_map_2",
+ .remote_name = "xdp_dummy_prog",
+ .local_flags = flags,
+ .remote_flags = flags,
+ }
+ };
+ struct bpf_object *bpf_objs[VETH_REDIRECT_SKEL_NB];
+ struct xdp_redirect_map *xdp_redirect_map;
+ struct net_configuration net_config;
+ struct nstoken *nstoken = NULL;
+ struct xdp_dummy *xdp_dummy;
+ struct xdp_tx *xdp_tx;
+ int map_fd;
+ int i;
+
+ xdp_dummy = xdp_dummy__open_and_load();
+ if (!ASSERT_OK_PTR(xdp_dummy, "xdp_dummy__open_and_load"))
+ return;
+
+ xdp_tx = xdp_tx__open_and_load();
+ if (!ASSERT_OK_PTR(xdp_tx, "xdp_tx__open_and_load"))
+ goto destroy_xdp_dummy;
+
+ xdp_redirect_map = xdp_redirect_map__open_and_load();
+ if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load"))
+ goto destroy_xdp_tx;
+
+ if (!ASSERT_OK(create_network(&net_config), "create network"))
+ goto destroy_xdp_redirect_map;
+
+ /* Then configure the redirect map and attach programs to interfaces */
+ map_fd = bpf_map__fd(xdp_redirect_map->maps.tx_port);
+ if (!ASSERT_OK_FD(map_fd, "open redirect map"))
+ goto destroy_xdp_redirect_map;
+
+ bpf_objs[0] = xdp_dummy->obj;
+ bpf_objs[1] = xdp_tx->obj;
+ bpf_objs[2] = xdp_redirect_map->obj;
+
+ nstoken = open_netns(net_config.ns0_name);
+ if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+ goto destroy_xdp_redirect_map;
+
+ for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+ int next_veth = net_config.veth_cfg[i].next_veth;
+ int interface_id;
+ int err;
+
+ interface_id = if_nametoindex(net_config.veth_cfg[next_veth].local_veth);
+ if (!ASSERT_NEQ(interface_id, 0, "non zero interface index"))
+ goto destroy_xdp_redirect_map;
+ err = bpf_map_update_elem(map_fd, &i, &interface_id, BPF_ANY);
+ if (!ASSERT_OK(err, "configure interface redirection through map"))
+ goto destroy_xdp_redirect_map;
+ if (attach_programs_to_veth_pair(bpf_objs, VETH_REDIRECT_SKEL_NB,
+ &net_config, ping_config, i))
+ goto destroy_xdp_redirect_map;
+ }
+
/* Test: if all interfaces are properly configured, we must be able to ping
* veth33 from veth11
*/
- return SYS_NOFAIL("ip netns exec %s ping -c 1 -W 1 %s > /dev/null",
- config[0].namespace, IP_DST);
+ ASSERT_OK(SYS_NOFAIL("ip netns exec %s ping -c 1 -W 1 %s > /dev/null",
+ net_config.veth_cfg[0].namespace, IP_DST), "ping");
+
+destroy_xdp_redirect_map:
+ close_netns(nstoken);
+ xdp_redirect_map__destroy(xdp_redirect_map);
+destroy_xdp_tx:
+ xdp_tx__destroy(xdp_tx);
+destroy_xdp_dummy:
+ xdp_dummy__destroy(xdp_dummy);
+
+ cleanup_network(&net_config);
}
-void test_xdp_veth_redirect(void)
+#define BROADCAST_REDIRECT_SKEL_NB 2
+static void xdp_veth_broadcast_redirect(u32 attach_flags, u64 redirect_flags)
{
- struct skeletons skeletons = {};
+ struct prog_configuration prog_cfg[VETH_PAIRS_COUNT] = {
+ {
+ .local_name = "xdp_redirect_map_multi_prog",
+ .remote_name = "xdp_count_0",
+ .local_flags = attach_flags,
+ .remote_flags = attach_flags,
+ },
+ {
+ .local_name = "xdp_redirect_map_multi_prog",
+ .remote_name = "xdp_count_1",
+ .local_flags = attach_flags,
+ .remote_flags = attach_flags,
+ },
+ {
+ .local_name = "xdp_redirect_map_multi_prog",
+ .remote_name = "xdp_count_2",
+ .local_flags = attach_flags,
+ .remote_flags = attach_flags,
+ }
+ };
+ struct bpf_object *bpf_objs[BROADCAST_REDIRECT_SKEL_NB];
+ struct xdp_redirect_multi_kern *xdp_redirect_multi_kern;
+ struct xdp_redirect_map *xdp_redirect_map;
+ struct bpf_devmap_val devmap_val = {};
+ struct net_configuration net_config;
+ struct nstoken *nstoken = NULL;
+ u16 protocol = ETH_P_IP;
+ int group_map;
+ int flags_map;
+ int cnt_map;
+ u64 cnt = 0;
+ int i, err;
- skeletons.xdp_dummy = xdp_dummy__open_and_load();
- if (!ASSERT_OK_PTR(skeletons.xdp_dummy, "xdp_dummy__open_and_load"))
+ xdp_redirect_multi_kern = xdp_redirect_multi_kern__open_and_load();
+ if (!ASSERT_OK_PTR(xdp_redirect_multi_kern, "xdp_redirect_multi_kern__open_and_load"))
return;
- skeletons.xdp_tx = xdp_tx__open_and_load();
- if (!ASSERT_OK_PTR(skeletons.xdp_tx, "xdp_tx__open_and_load"))
+ xdp_redirect_map = xdp_redirect_map__open_and_load();
+ if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load"))
+ goto destroy_xdp_redirect_multi_kern;
+
+ if (!ASSERT_OK(create_network(&net_config), "create network"))
+ goto destroy_xdp_redirect_map;
+
+ group_map = bpf_map__fd(xdp_redirect_multi_kern->maps.map_all);
+ if (!ASSERT_OK_FD(group_map, "open map_all"))
+ goto destroy_xdp_redirect_map;
+
+ flags_map = bpf_map__fd(xdp_redirect_multi_kern->maps.redirect_flags);
+ if (!ASSERT_OK_FD(group_map, "open map_all"))
+ goto destroy_xdp_redirect_map;
+
+ err = bpf_map_update_elem(flags_map, &protocol, &redirect_flags, BPF_NOEXIST);
+ if (!ASSERT_OK(err, "init IP count"))
+ goto destroy_xdp_redirect_map;
+
+ cnt_map = bpf_map__fd(xdp_redirect_map->maps.rxcnt);
+ if (!ASSERT_OK_FD(cnt_map, "open rxcnt map"))
+ goto destroy_xdp_redirect_map;
+
+ bpf_objs[0] = xdp_redirect_multi_kern->obj;
+ bpf_objs[1] = xdp_redirect_map->obj;
+
+ nstoken = open_netns(net_config.ns0_name);
+ if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+ goto destroy_xdp_redirect_map;
+
+ for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+ int ifindex = if_nametoindex(net_config.veth_cfg[i].local_veth);
+
+ if (attach_programs_to_veth_pair(bpf_objs, BROADCAST_REDIRECT_SKEL_NB,
+ &net_config, prog_cfg, i))
+ goto destroy_xdp_redirect_map;
+
+ SYS(destroy_xdp_redirect_map,
+ "ip -n %s neigh add %s lladdr 00:00:00:00:00:01 dev %s",
+ net_config.veth_cfg[i].namespace, IP_NEIGH, net_config.veth_cfg[i].remote_veth);
+
+ devmap_val.ifindex = ifindex;
+ err = bpf_map_update_elem(group_map, &ifindex, &devmap_val, 0);
+ if (!ASSERT_OK(err, "bpf_map_update_elem"))
+ goto destroy_xdp_redirect_map;
+
+ }
+
+ SYS_NOFAIL("ip netns exec %s ping %s -i 0.1 -c 4 -W1 > /dev/null ",
+ net_config.veth_cfg[0].namespace, IP_NEIGH);
+
+ for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+ err = bpf_map_lookup_elem(cnt_map, &i, &cnt);
+ if (!ASSERT_OK(err, "get IP cnt"))
+ goto destroy_xdp_redirect_map;
+
+ if (redirect_flags & BPF_F_EXCLUDE_INGRESS)
+ /* veth11 shouldn't receive the ICMP requests;
+ * others should
+ */
+ ASSERT_EQ(cnt, i ? 4 : 0, "compare IP cnt");
+ else
+ /* All remote veth should receive the ICMP requests */
+ ASSERT_EQ(cnt, 4, "compare IP cnt");
+ }
+
+destroy_xdp_redirect_map:
+ close_netns(nstoken);
+ xdp_redirect_map__destroy(xdp_redirect_map);
+destroy_xdp_redirect_multi_kern:
+ xdp_redirect_multi_kern__destroy(xdp_redirect_multi_kern);
+
+ cleanup_network(&net_config);
+}
+
+#define VETH_EGRESS_SKEL_NB 3
+static void xdp_veth_egress(u32 flags)
+{
+ struct prog_configuration prog_cfg[VETH_PAIRS_COUNT] = {
+ {
+ .local_name = "xdp_redirect_map_all_prog",
+ .remote_name = "xdp_dummy_prog",
+ .local_flags = flags,
+ .remote_flags = flags,
+ },
+ {
+ .local_name = "xdp_redirect_map_all_prog",
+ .remote_name = "store_mac_1",
+ .local_flags = flags,
+ .remote_flags = flags,
+ },
+ {
+ .local_name = "xdp_redirect_map_all_prog",
+ .remote_name = "store_mac_2",
+ .local_flags = flags,
+ .remote_flags = flags,
+ }
+ };
+ const char magic_mac[6] = { 0xAA, 0xBB, 0xCC, 0xDD, 0xEE, 0xFF};
+ struct xdp_redirect_multi_kern *xdp_redirect_multi_kern;
+ struct bpf_object *bpf_objs[VETH_EGRESS_SKEL_NB];
+ struct xdp_redirect_map *xdp_redirect_map;
+ struct bpf_devmap_val devmap_val = {};
+ struct net_configuration net_config;
+ int mac_map, egress_map, res_map;
+ struct nstoken *nstoken = NULL;
+ struct xdp_dummy *xdp_dummy;
+ int err;
+ int i;
+
+ xdp_dummy = xdp_dummy__open_and_load();
+ if (!ASSERT_OK_PTR(xdp_dummy, "xdp_dummy__open_and_load"))
+ return;
+
+ xdp_redirect_multi_kern = xdp_redirect_multi_kern__open_and_load();
+ if (!ASSERT_OK_PTR(xdp_redirect_multi_kern, "xdp_redirect_multi_kern__open_and_load"))
goto destroy_xdp_dummy;
- skeletons.xdp_redirect_maps = xdp_redirect_map__open_and_load();
- if (!ASSERT_OK_PTR(skeletons.xdp_redirect_maps, "xdp_redirect_map__open_and_load"))
- goto destroy_xdp_tx;
+ xdp_redirect_map = xdp_redirect_map__open_and_load();
+ if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load"))
+ goto destroy_xdp_redirect_multi_kern;
- if (configure_network(&skeletons))
+ if (!ASSERT_OK(create_network(&net_config), "create network"))
goto destroy_xdp_redirect_map;
- ASSERT_OK(check_ping(&skeletons), "ping");
+ mac_map = bpf_map__fd(xdp_redirect_multi_kern->maps.mac_map);
+ if (!ASSERT_OK_FD(mac_map, "open mac_map"))
+ goto destroy_xdp_redirect_map;
+
+ egress_map = bpf_map__fd(xdp_redirect_multi_kern->maps.map_egress);
+ if (!ASSERT_OK_FD(egress_map, "open map_egress"))
+ goto destroy_xdp_redirect_map;
+
+ devmap_val.bpf_prog.fd = bpf_program__fd(xdp_redirect_multi_kern->progs.xdp_devmap_prog);
+
+ bpf_objs[0] = xdp_dummy->obj;
+ bpf_objs[1] = xdp_redirect_multi_kern->obj;
+ bpf_objs[2] = xdp_redirect_map->obj;
+
+ nstoken = open_netns(net_config.ns0_name);
+ if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+ goto destroy_xdp_redirect_map;
+
+ for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+ int ifindex = if_nametoindex(net_config.veth_cfg[i].local_veth);
+
+ SYS(destroy_xdp_redirect_map,
+ "ip -n %s neigh add %s lladdr 00:00:00:00:00:01 dev %s",
+ net_config.veth_cfg[i].namespace, IP_NEIGH, net_config.veth_cfg[i].remote_veth);
+
+ if (attach_programs_to_veth_pair(bpf_objs, VETH_REDIRECT_SKEL_NB,
+ &net_config, prog_cfg, i))
+ goto destroy_xdp_redirect_map;
+
+ err = bpf_map_update_elem(mac_map, &ifindex, magic_mac, 0);
+ if (!ASSERT_OK(err, "bpf_map_update_elem"))
+ goto destroy_xdp_redirect_map;
+
+ devmap_val.ifindex = ifindex;
+ err = bpf_map_update_elem(egress_map, &ifindex, &devmap_val, 0);
+ if (!ASSERT_OK(err, "bpf_map_update_elem"))
+ goto destroy_xdp_redirect_map;
+ }
+
+ SYS_NOFAIL("ip netns exec %s ping %s -i 0.1 -c 4 -W1 > /dev/null ",
+ net_config.veth_cfg[0].namespace, IP_NEIGH);
+
+ res_map = bpf_map__fd(xdp_redirect_map->maps.rx_mac);
+ if (!ASSERT_OK_FD(res_map, "open rx_map"))
+ goto destroy_xdp_redirect_map;
+
+ for (i = 0; i < 2; i++) {
+ u32 key = i;
+ u64 res;
+
+ err = bpf_map_lookup_elem(res_map, &key, &res);
+ if (!ASSERT_OK(err, "get MAC res"))
+ goto destroy_xdp_redirect_map;
+
+ ASSERT_STRNEQ((const char *)&res, magic_mac, ETH_ALEN, "compare mac");
+ }
destroy_xdp_redirect_map:
- xdp_redirect_map__destroy(skeletons.xdp_redirect_maps);
-destroy_xdp_tx:
- xdp_tx__destroy(skeletons.xdp_tx);
+ close_netns(nstoken);
+ xdp_redirect_map__destroy(xdp_redirect_map);
+destroy_xdp_redirect_multi_kern:
+ xdp_redirect_multi_kern__destroy(xdp_redirect_multi_kern);
destroy_xdp_dummy:
- xdp_dummy__destroy(skeletons.xdp_dummy);
+ xdp_dummy__destroy(xdp_dummy);
+
+ cleanup_network(&net_config);
+}
+
+void test_xdp_veth_redirect(void)
+{
+ if (test__start_subtest("0"))
+ xdp_veth_redirect(0);
+
+ if (test__start_subtest("DRV_MODE"))
+ xdp_veth_redirect(XDP_FLAGS_DRV_MODE);
+
+ if (test__start_subtest("SKB_MODE"))
+ xdp_veth_redirect(XDP_FLAGS_SKB_MODE);
+}
+
+void test_xdp_veth_broadcast_redirect(void)
+{
+ if (test__start_subtest("0/BROADCAST"))
+ xdp_veth_broadcast_redirect(0, BPF_F_BROADCAST);
+
+ if (test__start_subtest("0/(BROADCAST | EXCLUDE_INGRESS)"))
+ xdp_veth_broadcast_redirect(0, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+
+ if (test__start_subtest("DRV_MODE/BROADCAST"))
+ xdp_veth_broadcast_redirect(XDP_FLAGS_DRV_MODE, BPF_F_BROADCAST);
+
+ if (test__start_subtest("DRV_MODE/(BROADCAST | EXCLUDE_INGRESS)"))
+ xdp_veth_broadcast_redirect(XDP_FLAGS_DRV_MODE,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+
+ if (test__start_subtest("SKB_MODE/BROADCAST"))
+ xdp_veth_broadcast_redirect(XDP_FLAGS_SKB_MODE, BPF_F_BROADCAST);
+
+ if (test__start_subtest("SKB_MODE/(BROADCAST | EXCLUDE_INGRESS)"))
+ xdp_veth_broadcast_redirect(XDP_FLAGS_SKB_MODE,
+ BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+}
+
+void test_xdp_veth_egress(void)
+{
+ if (test__start_subtest("0/egress"))
+ xdp_veth_egress(0);
+
+ if (test__start_subtest("DRV_MODE/egress"))
+ xdp_veth_egress(XDP_FLAGS_DRV_MODE);
- cleanup_network();
+ if (test__start_subtest("SKB_MODE/egress"))
+ xdp_veth_egress(XDP_FLAGS_SKB_MODE);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c
index c3ab9b6fb069..f9392df23f8a 100644
--- a/tools/testing/selftests/bpf/prog_tests/token.c
+++ b/tools/testing/selftests/bpf/prog_tests/token.c
@@ -19,6 +19,7 @@
#include "priv_prog.skel.h"
#include "dummy_st_ops_success.skel.h"
#include "token_lsm.skel.h"
+#include "priv_freplace_prog.skel.h"
static inline int sys_mount(const char *dev_name, const char *dir_name,
const char *type, unsigned long flags,
@@ -788,6 +789,84 @@ static int userns_obj_priv_prog(int mnt_fd, struct token_lsm *lsm_skel)
return 0;
}
+static int userns_obj_priv_freplace_setup(int mnt_fd, struct priv_freplace_prog **fr_skel,
+ struct priv_prog **skel, int *tgt_fd)
+{
+ LIBBPF_OPTS(bpf_object_open_opts, opts);
+ int err;
+ char buf[256];
+
+ /* use bpf_token_path to provide BPF FS path */
+ snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
+ opts.bpf_token_path = buf;
+ *skel = priv_prog__open_opts(&opts);
+ if (!ASSERT_OK_PTR(*skel, "priv_prog__open_opts"))
+ return -EINVAL;
+ err = priv_prog__load(*skel);
+ if (!ASSERT_OK(err, "priv_prog__load"))
+ return -EINVAL;
+
+ *fr_skel = priv_freplace_prog__open_opts(&opts);
+ if (!ASSERT_OK_PTR(*skel, "priv_freplace_prog__open_opts"))
+ return -EINVAL;
+
+ *tgt_fd = bpf_program__fd((*skel)->progs.xdp_prog1);
+ return 0;
+}
+
+/* Verify that freplace works from user namespace, because bpf token is loaded
+ * in bpf_object__prepare
+ */
+static int userns_obj_priv_freplace_prog(int mnt_fd, struct token_lsm *lsm_skel)
+{
+ struct priv_freplace_prog *fr_skel = NULL;
+ struct priv_prog *skel = NULL;
+ int err, tgt_fd;
+
+ err = userns_obj_priv_freplace_setup(mnt_fd, &fr_skel, &skel, &tgt_fd);
+ if (!ASSERT_OK(err, "setup"))
+ goto out;
+
+ err = bpf_object__prepare(fr_skel->obj);
+ if (!ASSERT_OK(err, "freplace__prepare"))
+ goto out;
+
+ err = bpf_program__set_attach_target(fr_skel->progs.new_xdp_prog2, tgt_fd, "xdp_prog1");
+ if (!ASSERT_OK(err, "set_attach_target"))
+ goto out;
+
+ err = priv_freplace_prog__load(fr_skel);
+ ASSERT_OK(err, "priv_freplace_prog__load");
+
+out:
+ priv_freplace_prog__destroy(fr_skel);
+ priv_prog__destroy(skel);
+ return err;
+}
+
+/* Verify that replace fails to set attach target from user namespace without bpf token */
+static int userns_obj_priv_freplace_prog_fail(int mnt_fd, struct token_lsm *lsm_skel)
+{
+ struct priv_freplace_prog *fr_skel = NULL;
+ struct priv_prog *skel = NULL;
+ int err, tgt_fd;
+
+ err = userns_obj_priv_freplace_setup(mnt_fd, &fr_skel, &skel, &tgt_fd);
+ if (!ASSERT_OK(err, "setup"))
+ goto out;
+
+ err = bpf_program__set_attach_target(fr_skel->progs.new_xdp_prog2, tgt_fd, "xdp_prog1");
+ if (ASSERT_ERR(err, "attach fails"))
+ err = 0;
+ else
+ err = -EINVAL;
+
+out:
+ priv_freplace_prog__destroy(fr_skel);
+ priv_prog__destroy(skel);
+ return err;
+}
+
/* this test is called with BPF FS that doesn't delegate BPF_BTF_LOAD command,
* which should cause struct_ops application to fail, as BTF won't be uploaded
* into the kernel, even if STRUCT_OPS programs themselves are allowed
@@ -1004,12 +1083,28 @@ void test_token(void)
if (test__start_subtest("obj_priv_prog")) {
struct bpffs_opts opts = {
.cmds = bit(BPF_PROG_LOAD),
- .progs = bit(BPF_PROG_TYPE_KPROBE),
+ .progs = bit(BPF_PROG_TYPE_XDP),
.attachs = ~0ULL,
};
subtest_userns(&opts, userns_obj_priv_prog);
}
+ if (test__start_subtest("obj_priv_freplace_prog")) {
+ struct bpffs_opts opts = {
+ .cmds = bit(BPF_BTF_LOAD) | bit(BPF_PROG_LOAD) | bit(BPF_BTF_GET_FD_BY_ID),
+ .progs = bit(BPF_PROG_TYPE_EXT) | bit(BPF_PROG_TYPE_XDP),
+ .attachs = ~0ULL,
+ };
+ subtest_userns(&opts, userns_obj_priv_freplace_prog);
+ }
+ if (test__start_subtest("obj_priv_freplace_prog_fail")) {
+ struct bpffs_opts opts = {
+ .cmds = bit(BPF_BTF_LOAD) | bit(BPF_PROG_LOAD) | bit(BPF_BTF_GET_FD_BY_ID),
+ .progs = bit(BPF_PROG_TYPE_EXT) | bit(BPF_PROG_TYPE_XDP),
+ .attachs = ~0ULL,
+ };
+ subtest_userns(&opts, userns_obj_priv_freplace_prog_fail);
+ }
if (test__start_subtest("obj_priv_btf_fail")) {
struct bpffs_opts opts = {
/* disallow BTF loading */
diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c
index 56ed1eb9b527..495d66414b57 100644
--- a/tools/testing/selftests/bpf/prog_tests/usdt.c
+++ b/tools/testing/selftests/bpf/prog_tests/usdt.c
@@ -45,7 +45,7 @@ static void subtest_basic_usdt(void)
LIBBPF_OPTS(bpf_usdt_opts, opts);
struct test_usdt *skel;
struct test_usdt__bss *bss;
- int err;
+ int err, i;
skel = test_usdt__open_and_load();
if (!ASSERT_OK_PTR(skel, "skel_open"))
@@ -75,6 +75,7 @@ static void subtest_basic_usdt(void)
ASSERT_EQ(bss->usdt0_cookie, 0xcafedeadbeeffeed, "usdt0_cookie");
ASSERT_EQ(bss->usdt0_arg_cnt, 0, "usdt0_arg_cnt");
ASSERT_EQ(bss->usdt0_arg_ret, -ENOENT, "usdt0_arg_ret");
+ ASSERT_EQ(bss->usdt0_arg_size, -ENOENT, "usdt0_arg_size");
/* auto-attached usdt3 gets default zero cookie value */
ASSERT_EQ(bss->usdt3_cookie, 0, "usdt3_cookie");
@@ -86,6 +87,9 @@ static void subtest_basic_usdt(void)
ASSERT_EQ(bss->usdt3_args[0], 1, "usdt3_arg1");
ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2");
ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3");
+ ASSERT_EQ(bss->usdt3_arg_sizes[0], 4, "usdt3_arg1_size");
+ ASSERT_EQ(bss->usdt3_arg_sizes[1], 8, "usdt3_arg2_size");
+ ASSERT_EQ(bss->usdt3_arg_sizes[2], 8, "usdt3_arg3_size");
/* auto-attached usdt12 gets default zero cookie value */
ASSERT_EQ(bss->usdt12_cookie, 0, "usdt12_cookie");
@@ -104,6 +108,11 @@ static void subtest_basic_usdt(void)
ASSERT_EQ(bss->usdt12_args[10], nums[idx], "usdt12_arg11");
ASSERT_EQ(bss->usdt12_args[11], t1.y, "usdt12_arg12");
+ int usdt12_expected_arg_sizes[12] = { 4, 4, 8, 8, 4, 8, 8, 8, 4, 2, 2, 1 };
+
+ for (i = 0; i < 12; i++)
+ ASSERT_EQ(bss->usdt12_arg_sizes[i], usdt12_expected_arg_sizes[i], "usdt12_arg_size");
+
/* trigger_func() is marked __always_inline, so USDT invocations will be
* inlined in two different places, meaning that each USDT will have
* at least 2 different places to be attached to. This verifies that
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 8a0e1ff8a2dc..e66a57970d28 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -45,6 +45,7 @@
#include "verifier_ldsx.skel.h"
#include "verifier_leak_ptr.skel.h"
#include "verifier_linked_scalars.skel.h"
+#include "verifier_load_acquire.skel.h"
#include "verifier_loops1.skel.h"
#include "verifier_lwt.skel.h"
#include "verifier_map_in_map.skel.h"
@@ -80,6 +81,7 @@
#include "verifier_spill_fill.skel.h"
#include "verifier_spin_lock.skel.h"
#include "verifier_stack_ptr.skel.h"
+#include "verifier_store_release.skel.h"
#include "verifier_subprog_precision.skel.h"
#include "verifier_subreg.skel.h"
#include "verifier_tailcall_jit.skel.h"
@@ -121,7 +123,7 @@ static void run_tests_aux(const char *skel_name,
/* test_verifier tests are executed w/o CAP_SYS_ADMIN, do the same here */
err = cap_disable_effective(1ULL << CAP_SYS_ADMIN, &old_caps);
if (err) {
- PRINT_FAIL("failed to drop CAP_SYS_ADMIN: %i, %s\n", err, strerror(err));
+ PRINT_FAIL("failed to drop CAP_SYS_ADMIN: %i, %s\n", err, strerror(-err));
return;
}
@@ -131,7 +133,7 @@ static void run_tests_aux(const char *skel_name,
err = cap_enable_effective(old_caps, NULL);
if (err)
- PRINT_FAIL("failed to restore CAP_SYS_ADMIN: %i, %s\n", err, strerror(err));
+ PRINT_FAIL("failed to restore CAP_SYS_ADMIN: %i, %s\n", err, strerror(-err));
}
#define RUN(skel) run_tests_aux(#skel, skel##__elf_bytes, NULL)
@@ -173,6 +175,7 @@ void test_verifier_int_ptr(void) { RUN(verifier_int_ptr); }
void test_verifier_iterating_callbacks(void) { RUN(verifier_iterating_callbacks); }
void test_verifier_jeq_infer_not_null(void) { RUN(verifier_jeq_infer_not_null); }
void test_verifier_jit_convergence(void) { RUN(verifier_jit_convergence); }
+void test_verifier_load_acquire(void) { RUN(verifier_load_acquire); }
void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); }
void test_verifier_ldsx(void) { RUN(verifier_ldsx); }
void test_verifier_leak_ptr(void) { RUN(verifier_leak_ptr); }
@@ -211,6 +214,7 @@ void test_verifier_sockmap_mutate(void) { RUN(verifier_sockmap_mutate); }
void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); }
void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); }
void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); }
+void test_verifier_store_release(void) { RUN(verifier_store_release); }
void test_verifier_subprog_precision(void) { RUN(verifier_subprog_precision); }
void test_verifier_subreg(void) { RUN(verifier_subreg); }
void test_verifier_tailcall_jit(void) { RUN(verifier_tailcall_jit); }
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_vlan.c b/tools/testing/selftests/bpf/prog_tests/xdp_vlan.c
new file mode 100644
index 000000000000..18dd25344de7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_vlan.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Network topology:
+ * ----------- -----------
+ * | NS1 | | NS2 |
+ * | veth0 -|--------|- veth0 |
+ * ----------- -----------
+ *
+ */
+
+#define _GNU_SOURCE
+#include <net/if.h>
+#include <uapi/linux/if_link.h>
+
+#include "network_helpers.h"
+#include "test_progs.h"
+#include "test_xdp_vlan.skel.h"
+
+
+#define VETH_NAME "veth0"
+#define NS_MAX_SIZE 32
+#define NS1_NAME "ns-xdp-vlan-1-"
+#define NS2_NAME "ns-xdp-vlan-2-"
+#define NS1_IP_ADDR "100.64.10.1"
+#define NS2_IP_ADDR "100.64.10.2"
+#define VLAN_ID 4011
+
+static int setup_network(char *ns1, char *ns2)
+{
+ if (!ASSERT_OK(append_tid(ns1, NS_MAX_SIZE), "create ns1 name"))
+ goto fail;
+ if (!ASSERT_OK(append_tid(ns2, NS_MAX_SIZE), "create ns2 name"))
+ goto fail;
+
+ SYS(fail, "ip netns add %s", ns1);
+ SYS(fail, "ip netns add %s", ns2);
+ SYS(fail, "ip -n %s link add %s type veth peer name %s netns %s",
+ ns1, VETH_NAME, VETH_NAME, ns2);
+
+ /* NOTICE: XDP require VLAN header inside packet payload
+ * - Thus, disable VLAN offloading driver features
+ */
+ SYS(fail, "ip netns exec %s ethtool -K %s rxvlan off txvlan off", ns1, VETH_NAME);
+ SYS(fail, "ip netns exec %s ethtool -K %s rxvlan off txvlan off", ns2, VETH_NAME);
+
+ /* NS1 configuration */
+ SYS(fail, "ip -n %s addr add %s/24 dev %s", ns1, NS1_IP_ADDR, VETH_NAME);
+ SYS(fail, "ip -n %s link set %s up", ns1, VETH_NAME);
+
+ /* NS2 configuration */
+ SYS(fail, "ip -n %s link add link %s name %s.%d type vlan id %d",
+ ns2, VETH_NAME, VETH_NAME, VLAN_ID, VLAN_ID);
+ SYS(fail, "ip -n %s addr add %s/24 dev %s.%d", ns2, NS2_IP_ADDR, VETH_NAME, VLAN_ID);
+ SYS(fail, "ip -n %s link set %s up", ns2, VETH_NAME);
+ SYS(fail, "ip -n %s link set %s.%d up", ns2, VETH_NAME, VLAN_ID);
+
+ /* At this point ping should fail because VLAN tags are only used by NS2 */
+ return !SYS_NOFAIL("ip netns exec %s ping -W 1 -c1 %s", ns2, NS1_IP_ADDR);
+
+fail:
+ return -1;
+}
+
+static void cleanup_network(const char *ns1, const char *ns2)
+{
+ SYS_NOFAIL("ip netns del %s", ns1);
+ SYS_NOFAIL("ip netns del %s", ns2);
+}
+
+static void xdp_vlan(struct bpf_program *xdp, struct bpf_program *tc, u32 flags)
+{
+ LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_EGRESS);
+ LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+ char ns1[NS_MAX_SIZE] = NS1_NAME;
+ char ns2[NS_MAX_SIZE] = NS2_NAME;
+ struct nstoken *nstoken = NULL;
+ int interface;
+ int ret;
+
+ if (!ASSERT_OK(setup_network(ns1, ns2), "setup network"))
+ goto cleanup;
+
+ nstoken = open_netns(ns1);
+ if (!ASSERT_OK_PTR(nstoken, "open NS1"))
+ goto cleanup;
+
+ interface = if_nametoindex(VETH_NAME);
+ if (!ASSERT_NEQ(interface, 0, "get interface index"))
+ goto cleanup;
+
+ ret = bpf_xdp_attach(interface, bpf_program__fd(xdp), flags, NULL);
+ if (!ASSERT_OK(ret, "attach xdp_vlan_change"))
+ goto cleanup;
+
+ tc_hook.ifindex = interface;
+ ret = bpf_tc_hook_create(&tc_hook);
+ if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+ goto detach_xdp;
+
+ /* Now we'll use BPF programs to pop/push the VLAN tags */
+ tc_opts.prog_fd = bpf_program__fd(tc);
+ ret = bpf_tc_attach(&tc_hook, &tc_opts);
+ if (!ASSERT_OK(ret, "bpf_tc_attach"))
+ goto detach_xdp;
+
+ close_netns(nstoken);
+ nstoken = NULL;
+
+ /* Now the namespaces can reach each-other, test with pings */
+ SYS(detach_tc, "ip netns exec %s ping -i 0.2 -W 2 -c 2 %s > /dev/null", ns1, NS2_IP_ADDR);
+ SYS(detach_tc, "ip netns exec %s ping -i 0.2 -W 2 -c 2 %s > /dev/null", ns2, NS1_IP_ADDR);
+
+
+detach_tc:
+ bpf_tc_detach(&tc_hook, &tc_opts);
+detach_xdp:
+ bpf_xdp_detach(interface, flags, NULL);
+cleanup:
+ close_netns(nstoken);
+ cleanup_network(ns1, ns2);
+}
+
+/* First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change"
+ * egress use TC to add back VLAN tag 4011
+ */
+void test_xdp_vlan_change(void)
+{
+ struct test_xdp_vlan *skel;
+
+ skel = test_xdp_vlan__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "xdp_vlan__open_and_load"))
+ return;
+
+ if (test__start_subtest("0"))
+ xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push, 0);
+
+ if (test__start_subtest("DRV_MODE"))
+ xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push,
+ XDP_FLAGS_DRV_MODE);
+
+ if (test__start_subtest("SKB_MODE"))
+ xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push,
+ XDP_FLAGS_SKB_MODE);
+
+ test_xdp_vlan__destroy(skel);
+}
+
+/* Second test: XDP prog fully remove vlan header
+ *
+ * Catch kernel bug for generic-XDP, that doesn't allow us to
+ * remove a VLAN header, because skb->protocol still contain VLAN
+ * ETH_P_8021Q indication, and this cause overwriting of our changes.
+ */
+void test_xdp_vlan_remove(void)
+{
+ struct test_xdp_vlan *skel;
+
+ skel = test_xdp_vlan__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "xdp_vlan__open_and_load"))
+ return;
+
+ if (test__start_subtest("0"))
+ xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push, 0);
+
+ if (test__start_subtest("DRV_MODE"))
+ xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push,
+ XDP_FLAGS_DRV_MODE);
+
+ if (test__start_subtest("SKB_MODE"))
+ xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push,
+ XDP_FLAGS_SKB_MODE);
+
+ test_xdp_vlan__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/arena_atomics.c b/tools/testing/selftests/bpf/progs/arena_atomics.c
index 40dd57fca5cc..a52feff98112 100644
--- a/tools/testing/selftests/bpf/progs/arena_atomics.c
+++ b/tools/testing/selftests/bpf/progs/arena_atomics.c
@@ -6,6 +6,8 @@
#include <stdbool.h>
#include <stdatomic.h>
#include "bpf_arena_common.h"
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
struct {
__uint(type, BPF_MAP_TYPE_ARENA);
@@ -19,9 +21,17 @@ struct {
} arena SEC(".maps");
#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
-bool skip_tests __attribute((__section__(".data"))) = false;
+bool skip_all_tests __attribute((__section__(".data"))) = false;
#else
-bool skip_tests = true;
+bool skip_all_tests = true;
+#endif
+
+#if defined(ENABLE_ATOMICS_TESTS) && \
+ defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
+ (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+bool skip_lacq_srel_tests __attribute((__section__(".data"))) = false;
+#else
+bool skip_lacq_srel_tests = true;
#endif
__u32 pid = 0;
@@ -274,4 +284,111 @@ int uaf(const void *ctx)
return 0;
}
+#if __clang_major__ >= 18
+__u8 __arena_global load_acquire8_value = 0x12;
+__u16 __arena_global load_acquire16_value = 0x1234;
+__u32 __arena_global load_acquire32_value = 0x12345678;
+__u64 __arena_global load_acquire64_value = 0x1234567890abcdef;
+
+__u8 __arena_global load_acquire8_result = 0;
+__u16 __arena_global load_acquire16_result = 0;
+__u32 __arena_global load_acquire32_result = 0;
+__u64 __arena_global load_acquire64_result = 0;
+#else
+/* clang-17 crashes if the .addr_space.1 ELF section has holes. Work around
+ * this issue by defining the below variables as 64-bit.
+ */
+__u64 __arena_global load_acquire8_value;
+__u64 __arena_global load_acquire16_value;
+__u64 __arena_global load_acquire32_value;
+__u64 __arena_global load_acquire64_value;
+
+__u64 __arena_global load_acquire8_result;
+__u64 __arena_global load_acquire16_result;
+__u64 __arena_global load_acquire32_result;
+__u64 __arena_global load_acquire64_result;
+#endif
+
+SEC("raw_tp/sys_enter")
+int load_acquire(const void *ctx)
+{
+#if defined(ENABLE_ATOMICS_TESTS) && \
+ defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
+ (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+
+#define LOAD_ACQUIRE_ARENA(SIZEOP, SIZE, SRC, DST) \
+ { asm volatile ( \
+ "r1 = %[" #SRC "] ll;" \
+ "r1 = addr_space_cast(r1, 0x0, 0x1);" \
+ ".8byte %[load_acquire_insn];" \
+ "r3 = %[" #DST "] ll;" \
+ "r3 = addr_space_cast(r3, 0x0, 0x1);" \
+ "*(" #SIZE " *)(r3 + 0) = r2;" \
+ : \
+ : __imm_addr(SRC), \
+ __imm_insn(load_acquire_insn, \
+ BPF_ATOMIC_OP(BPF_##SIZEOP, BPF_LOAD_ACQ, \
+ BPF_REG_2, BPF_REG_1, 0)), \
+ __imm_addr(DST) \
+ : __clobber_all); } \
+
+ LOAD_ACQUIRE_ARENA(B, u8, load_acquire8_value, load_acquire8_result)
+ LOAD_ACQUIRE_ARENA(H, u16, load_acquire16_value,
+ load_acquire16_result)
+ LOAD_ACQUIRE_ARENA(W, u32, load_acquire32_value,
+ load_acquire32_result)
+ LOAD_ACQUIRE_ARENA(DW, u64, load_acquire64_value,
+ load_acquire64_result)
+#undef LOAD_ACQUIRE_ARENA
+
+#endif
+ return 0;
+}
+
+#if __clang_major__ >= 18
+__u8 __arena_global store_release8_result = 0;
+__u16 __arena_global store_release16_result = 0;
+__u32 __arena_global store_release32_result = 0;
+__u64 __arena_global store_release64_result = 0;
+#else
+/* clang-17 crashes if the .addr_space.1 ELF section has holes. Work around
+ * this issue by defining the below variables as 64-bit.
+ */
+__u64 __arena_global store_release8_result;
+__u64 __arena_global store_release16_result;
+__u64 __arena_global store_release32_result;
+__u64 __arena_global store_release64_result;
+#endif
+
+SEC("raw_tp/sys_enter")
+int store_release(const void *ctx)
+{
+#if defined(ENABLE_ATOMICS_TESTS) && \
+ defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
+ (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+
+#define STORE_RELEASE_ARENA(SIZEOP, DST, VAL) \
+ { asm volatile ( \
+ "r1 = " VAL ";" \
+ "r2 = %[" #DST "] ll;" \
+ "r2 = addr_space_cast(r2, 0x0, 0x1);" \
+ ".8byte %[store_release_insn];" \
+ : \
+ : __imm_addr(DST), \
+ __imm_insn(store_release_insn, \
+ BPF_ATOMIC_OP(BPF_##SIZEOP, BPF_STORE_REL, \
+ BPF_REG_2, BPF_REG_1, 0)) \
+ : __clobber_all); } \
+
+ STORE_RELEASE_ARENA(B, store_release8_result, "0x12")
+ STORE_RELEASE_ARENA(H, store_release16_result, "0x1234")
+ STORE_RELEASE_ARENA(W, store_release32_result, "0x12345678")
+ STORE_RELEASE_ARENA(DW, store_release64_result,
+ "0x1234567890abcdef ll")
+#undef STORE_RELEASE_ARENA
+
+#endif
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/arena_spin_lock.c b/tools/testing/selftests/bpf/progs/arena_spin_lock.c
new file mode 100644
index 000000000000..c4500c37f85e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_spin_lock.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_arena_spin_lock.h"
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARENA);
+ __uint(map_flags, BPF_F_MMAPABLE);
+ __uint(max_entries, 100); /* number of pages */
+#ifdef __TARGET_ARCH_arm64
+ __ulong(map_extra, 0x1ull << 32); /* start of mmap() region */
+#else
+ __ulong(map_extra, 0x1ull << 44); /* start of mmap() region */
+#endif
+} arena SEC(".maps");
+
+int cs_count;
+
+#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+arena_spinlock_t __arena lock;
+int test_skip = 1;
+#else
+int test_skip = 2;
+#endif
+
+int counter;
+int limit;
+
+SEC("tc")
+int prog(void *ctx)
+{
+ int ret = -2;
+
+#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+ unsigned long flags;
+
+ if ((ret = arena_spin_lock_irqsave(&lock, flags)))
+ return ret;
+ if (counter != limit)
+ counter++;
+ bpf_repeat(cs_count);
+ ret = 0;
+ arena_spin_unlock_irqrestore(&lock, flags);
+#endif
+ return ret;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
index bc10c4e4b4fa..966ee5a7b066 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
@@ -9,6 +9,13 @@ char _license[] SEC("license") = "GPL";
uint32_t tid = 0;
int num_unknown_tid = 0;
int num_known_tid = 0;
+void *user_ptr = 0;
+void *user_ptr_long = 0;
+uint32_t pid = 0;
+
+static char big_str1[5000];
+static char big_str2[5005];
+static char big_str3[4996];
SEC("iter/task")
int dump_task(struct bpf_iter__task *ctx)
@@ -35,7 +42,9 @@ int dump_task(struct bpf_iter__task *ctx)
}
int num_expected_failure_copy_from_user_task = 0;
+int num_expected_failure_copy_from_user_task_str = 0;
int num_success_copy_from_user_task = 0;
+int num_success_copy_from_user_task_str = 0;
SEC("iter.s/task")
int dump_task_sleepable(struct bpf_iter__task *ctx)
@@ -44,6 +53,9 @@ int dump_task_sleepable(struct bpf_iter__task *ctx)
struct task_struct *task = ctx->task;
static const char info[] = " === END ===";
struct pt_regs *regs;
+ char task_str1[10] = "aaaaaaaaaa";
+ char task_str2[10], task_str3[10];
+ char task_str4[20] = "aaaaaaaaaaaaaaaaaaaa";
void *ptr;
uint32_t user_data = 0;
int ret;
@@ -78,8 +90,106 @@ int dump_task_sleepable(struct bpf_iter__task *ctx)
BPF_SEQ_PRINTF(seq, "%s\n", info);
return 0;
}
+
++num_success_copy_from_user_task;
+ /* Read an invalid pointer and ensure we get an error */
+ ptr = NULL;
+ ret = bpf_copy_from_user_task_str((char *)task_str1, sizeof(task_str1), ptr, task, 0);
+ if (ret >= 0 || task_str1[9] != 'a' || task_str1[0] != '\0') {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+
+ /* Read an invalid pointer and ensure we get error with pad zeros flag */
+ ptr = NULL;
+ ret = bpf_copy_from_user_task_str((char *)task_str1, sizeof(task_str1),
+ ptr, task, BPF_F_PAD_ZEROS);
+ if (ret >= 0 || task_str1[9] != '\0' || task_str1[0] != '\0') {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+
+ ++num_expected_failure_copy_from_user_task_str;
+
+ /* Same length as the string */
+ ret = bpf_copy_from_user_task_str((char *)task_str2, 10, user_ptr, task, 0);
+ /* only need to do the task pid check once */
+ if (bpf_strncmp(task_str2, 10, "test_data\0") != 0 || ret != 10 || task->tgid != pid) {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+
+ /* Shorter length than the string */
+ ret = bpf_copy_from_user_task_str((char *)task_str3, 2, user_ptr, task, 0);
+ if (bpf_strncmp(task_str3, 2, "t\0") != 0 || ret != 2) {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+
+ /* Longer length than the string */
+ ret = bpf_copy_from_user_task_str((char *)task_str4, 20, user_ptr, task, 0);
+ if (bpf_strncmp(task_str4, 10, "test_data\0") != 0 || ret != 10
+ || task_str4[sizeof(task_str4) - 1] != 'a') {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+
+ /* Longer length than the string with pad zeros flag */
+ ret = bpf_copy_from_user_task_str((char *)task_str4, 20, user_ptr, task, BPF_F_PAD_ZEROS);
+ if (bpf_strncmp(task_str4, 10, "test_data\0") != 0 || ret != 10
+ || task_str4[sizeof(task_str4) - 1] != '\0') {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+
+ /* Longer length than the string past a page boundary */
+ ret = bpf_copy_from_user_task_str(big_str1, 5000, user_ptr, task, 0);
+ if (bpf_strncmp(big_str1, 10, "test_data\0") != 0 || ret != 10) {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+
+ /* String that crosses a page boundary */
+ ret = bpf_copy_from_user_task_str(big_str1, 5000, user_ptr_long, task, BPF_F_PAD_ZEROS);
+ if (bpf_strncmp(big_str1, 4, "baba") != 0 || ret != 5000
+ || bpf_strncmp(big_str1 + 4996, 4, "bab\0") != 0) {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+
+ for (int i = 0; i < 4999; ++i) {
+ if (i % 2 == 0) {
+ if (big_str1[i] != 'b') {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+ } else {
+ if (big_str1[i] != 'a') {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+ }
+ }
+
+ /* Longer length than the string that crosses a page boundary */
+ ret = bpf_copy_from_user_task_str(big_str2, 5005, user_ptr_long, task, BPF_F_PAD_ZEROS);
+ if (bpf_strncmp(big_str2, 4, "baba") != 0 || ret != 5000
+ || bpf_strncmp(big_str2 + 4996, 5, "bab\0\0") != 0) {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+
+ /* Shorter length than the string that crosses a page boundary */
+ ret = bpf_copy_from_user_task_str(big_str3, 4996, user_ptr_long, task, 0);
+ if (bpf_strncmp(big_str3, 4, "baba") != 0 || ret != 4996
+ || bpf_strncmp(big_str3 + 4992, 4, "bab\0") != 0) {
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
+ return 0;
+ }
+
+ ++num_success_copy_from_user_task_str;
+
if (ctx->meta->seq_num == 0)
BPF_SEQ_PRINTF(seq, " tgid gid data\n");
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index f45f4352feeb..13a2e22f5465 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -135,6 +135,8 @@
#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 __load_if_JITed() __attribute__((btf_decl_tag("comment:load_mode=jited")))
+#define __load_if_no_JITed() __attribute__((btf_decl_tag("comment:load_mode=no_jited")))
/* Define common capabilities tested using __caps_unpriv */
#define CAP_NET_ADMIN 12
@@ -172,6 +174,9 @@
#elif defined(__TARGET_ARCH_riscv)
#define SYSCALL_WRAPPER 1
#define SYS_PREFIX "__riscv_"
+#elif defined(__TARGET_ARCH_powerpc)
+#define SYSCALL_WRAPPER 1
+#define SYS_PREFIX ""
#else
#define SYSCALL_WRAPPER 0
#define SYS_PREFIX "__se_"
@@ -208,4 +213,21 @@
#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#endif
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+ (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+ defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+ defined(__TARGET_ARCH_loongarch)) && \
+ __clang_major__ >= 18
+#define CAN_USE_GOTOL
+#endif
+
+#if _clang_major__ >= 18
+#define CAN_USE_BPF_ST
+#endif
+
+#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \
+ (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+#define CAN_USE_LOAD_ACQ_STORE_REL
+#endif
+
#endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index eb6ed1b7b2ef..659694162739 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -15,7 +15,11 @@
#define SO_KEEPALIVE 9
#define SO_PRIORITY 12
#define SO_REUSEPORT 15
+#if defined(__TARGET_ARCH_powerpc)
+#define SO_RCVLOWAT 16
+#else
#define SO_RCVLOWAT 18
+#endif
#define SO_BINDTODEVICE 25
#define SO_MARK 36
#define SO_MAX_PACING_RATE 47
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c
new file mode 100644
index 000000000000..21a560427b10
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___err_bad_signed_arr_elem_sz x) {}
diff --git a/tools/testing/selftests/bpf/progs/cgroup_preorder.c b/tools/testing/selftests/bpf/progs/cgroup_preorder.c
new file mode 100644
index 000000000000..4ef6202baa0a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_preorder.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+unsigned int idx;
+__u8 result[4];
+
+SEC("cgroup/getsockopt")
+int child(struct bpf_sockopt *ctx)
+{
+ if (idx < 4)
+ result[idx++] = 1;
+ return 1;
+}
+
+SEC("cgroup/getsockopt")
+int child_2(struct bpf_sockopt *ctx)
+{
+ if (idx < 4)
+ result[idx++] = 2;
+ return 1;
+}
+
+SEC("cgroup/getsockopt")
+int parent(struct bpf_sockopt *ctx)
+{
+ if (idx < 4)
+ result[idx++] = 3;
+ return 1;
+}
+
+SEC("cgroup/getsockopt")
+int parent_2(struct bpf_sockopt *ctx)
+{
+ if (idx < 4)
+ result[idx++] = 4;
+ return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data.c b/tools/testing/selftests/bpf/progs/changes_pkt_data.c
deleted file mode 100644
index 43cada48b28a..000000000000
--- a/tools/testing/selftests/bpf/progs/changes_pkt_data.c
+++ /dev/null
@@ -1,39 +0,0 @@
-// 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/compute_live_registers.c b/tools/testing/selftests/bpf/progs/compute_live_registers.c
new file mode 100644
index 000000000000..f3d79aecbf93
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/compute_live_registers.c
@@ -0,0 +1,424 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_arena_common.h"
+#include "bpf_misc.h"
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+} test_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARENA);
+ __uint(map_flags, BPF_F_MMAPABLE);
+ __uint(max_entries, 1);
+} arena SEC(".maps");
+
+SEC("socket")
+__log_level(2)
+__msg(" 0: .......... (b7) r0 = 42")
+__msg(" 1: 0......... (bf) r1 = r0")
+__msg(" 2: .1........ (bf) r2 = r1")
+__msg(" 3: ..2....... (bf) r3 = r2")
+__msg(" 4: ...3...... (bf) r4 = r3")
+__msg(" 5: ....4..... (bf) r5 = r4")
+__msg(" 6: .....5.... (bf) r6 = r5")
+__msg(" 7: ......6... (bf) r7 = r6")
+__msg(" 8: .......7.. (bf) r8 = r7")
+__msg(" 9: ........8. (bf) r9 = r8")
+__msg("10: .........9 (bf) r0 = r9")
+__msg("11: 0......... (95) exit")
+__naked void assign_chain(void)
+{
+ asm volatile (
+ "r0 = 42;"
+ "r1 = r0;"
+ "r2 = r1;"
+ "r3 = r2;"
+ "r4 = r3;"
+ "r5 = r4;"
+ "r6 = r5;"
+ "r7 = r6;"
+ "r8 = r7;"
+ "r9 = r8;"
+ "r0 = r9;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: .......... (b7) r1 = 7")
+__msg("1: .1........ (07) r1 += 7")
+__msg("2: .......... (b7) r2 = 7")
+__msg("3: ..2....... (b7) r3 = 42")
+__msg("4: ..23...... (0f) r2 += r3")
+__msg("5: .......... (b7) r0 = 0")
+__msg("6: 0......... (95) exit")
+__naked void arithmetics(void)
+{
+ asm volatile (
+ "r1 = 7;"
+ "r1 += 7;"
+ "r2 = 7;"
+ "r3 = 42;"
+ "r2 += r3;"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+#ifdef CAN_USE_BPF_ST
+SEC("socket")
+__log_level(2)
+__msg(" 1: .1........ (07) r1 += -8")
+__msg(" 2: .1........ (7a) *(u64 *)(r1 +0) = 7")
+__msg(" 3: .1........ (b7) r2 = 42")
+__msg(" 4: .12....... (7b) *(u64 *)(r1 +0) = r2")
+__msg(" 5: .12....... (7b) *(u64 *)(r1 +0) = r2")
+__msg(" 6: .......... (b7) r0 = 0")
+__naked void store(void)
+{
+ asm volatile (
+ "r1 = r10;"
+ "r1 += -8;"
+ "*(u64 *)(r1 +0) = 7;"
+ "r2 = 42;"
+ "*(u64 *)(r1 +0) = r2;"
+ "*(u64 *)(r1 +0) = r2;"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+#endif
+
+SEC("socket")
+__log_level(2)
+__msg("1: ....4..... (07) r4 += -8")
+__msg("2: ....4..... (79) r5 = *(u64 *)(r4 +0)")
+__msg("3: ....45.... (07) r4 += -8")
+__naked void load(void)
+{
+ asm volatile (
+ "r4 = r10;"
+ "r4 += -8;"
+ "r5 = *(u64 *)(r4 +0);"
+ "r4 += -8;"
+ "r0 = r5;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: .1........ (61) r2 = *(u32 *)(r1 +0)")
+__msg("1: ..2....... (d4) r2 = le64 r2")
+__msg("2: ..2....... (bf) r0 = r2")
+__naked void endian(void)
+{
+ asm volatile (
+ "r2 = *(u32 *)(r1 +0);"
+ "r2 = le64 r2;"
+ "r0 = r2;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg(" 8: 0......... (b7) r1 = 1")
+__msg(" 9: 01........ (db) r1 = atomic64_fetch_add((u64 *)(r0 +0), r1)")
+__msg("10: 01........ (c3) lock *(u32 *)(r0 +0) += r1")
+__msg("11: 01........ (db) r1 = atomic64_xchg((u64 *)(r0 +0), r1)")
+__msg("12: 01........ (bf) r2 = r0")
+__msg("13: .12....... (bf) r0 = r1")
+__msg("14: 012....... (db) r0 = atomic64_cmpxchg((u64 *)(r2 +0), r0, r1)")
+__naked void atomic(void)
+{
+ asm volatile (
+ "r2 = r10;"
+ "r2 += -8;"
+ "r1 = 0;"
+ "*(u64 *)(r2 +0) = r1;"
+ "r1 = %[test_map] ll;"
+ "call %[bpf_map_lookup_elem];"
+ "if r0 == 0 goto 1f;"
+ "r1 = 1;"
+ "r1 = atomic_fetch_add((u64 *)(r0 +0), r1);"
+ ".8byte %[add_nofetch];" /* same as "lock *(u32 *)(r0 +0) += r1;" */
+ "r1 = xchg_64(r0 + 0, r1);"
+ "r2 = r0;"
+ "r0 = r1;"
+ "r0 = cmpxchg_64(r2 + 0, r0, r1);"
+ "1: exit;"
+ :
+ : __imm(bpf_map_lookup_elem),
+ __imm_addr(test_map),
+ __imm_insn(add_nofetch, BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_0, BPF_REG_1, 0))
+ : __clobber_all);
+}
+
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
+
+SEC("socket")
+__log_level(2)
+__msg("2: .12....... (db) store_release((u64 *)(r2 -8), r1)")
+__msg("3: .......... (bf) r3 = r10")
+__msg("4: ...3...... (db) r4 = load_acquire((u64 *)(r3 -8))")
+__naked void atomic_load_acq_store_rel(void)
+{
+ asm volatile (
+ "r1 = 42;"
+ "r2 = r10;"
+ ".8byte %[store_release_insn];" /* store_release((u64 *)(r2 - 8), r1); */
+ "r3 = r10;"
+ ".8byte %[load_acquire_insn];" /* r4 = load_acquire((u64 *)(r3 + 0)); */
+ "r0 = r4;"
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_2, BPF_REG_1, -8)),
+ __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_4, BPF_REG_3, -8))
+ : __clobber_all);
+}
+
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+SEC("socket")
+__log_level(2)
+__msg("4: .12....7.. (85) call bpf_trace_printk#6")
+__msg("5: 0......7.. (0f) r0 += r7")
+__naked void regular_call(void)
+{
+ asm volatile (
+ "r7 = 1;"
+ "r1 = r10;"
+ "r1 += -8;"
+ "r2 = 1;"
+ "call %[bpf_trace_printk];"
+ "r0 += r7;"
+ "exit;"
+ :
+ : __imm(bpf_trace_printk)
+ : __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("2: 012....... (25) if r1 > 0x7 goto pc+1")
+__msg("3: ..2....... (bf) r0 = r2")
+__naked void if1(void)
+{
+ asm volatile (
+ "r0 = 1;"
+ "r2 = 2;"
+ "if r1 > 0x7 goto +1;"
+ "r0 = r2;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("3: 0123...... (2d) if r1 > r3 goto pc+1")
+__msg("4: ..2....... (bf) r0 = r2")
+__naked void if2(void)
+{
+ asm volatile (
+ "r0 = 1;"
+ "r2 = 2;"
+ "r3 = 7;"
+ "if r1 > r3 goto +1;"
+ "r0 = r2;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: .......... (b7) r1 = 0")
+__msg("1: .1........ (b7) r2 = 7")
+__msg("2: .12....... (25) if r1 > 0x7 goto pc+4")
+__msg("3: .12....... (07) r1 += 1")
+__msg("4: .12....... (27) r2 *= 2")
+__msg("5: .12....... (05) goto pc+0")
+__msg("6: .12....... (05) goto pc-5")
+__msg("7: .......... (b7) r0 = 0")
+__msg("8: 0......... (95) exit")
+__naked void loop(void)
+{
+ asm volatile (
+ "r1 = 0;"
+ "r2 = 7;"
+ "if r1 > 0x7 goto +4;"
+ "r1 += 1;"
+ "r2 *= 2;"
+ "goto +0;"
+ "goto -5;"
+ "r0 = 0;"
+ "exit;"
+ :
+ : __imm(bpf_trace_printk)
+ : __clobber_all);
+}
+
+#ifdef CAN_USE_GOTOL
+SEC("socket")
+__log_level(2)
+__msg("2: .123...... (25) if r1 > 0x7 goto pc+2")
+__msg("3: ..2....... (bf) r0 = r2")
+__msg("4: 0......... (06) gotol pc+1")
+__msg("5: ...3...... (bf) r0 = r3")
+__msg("6: 0......... (95) exit")
+__naked void gotol(void)
+{
+ asm volatile (
+ "r2 = 42;"
+ "r3 = 24;"
+ "if r1 > 0x7 goto +2;"
+ "r0 = r2;"
+ "gotol +1;"
+ "r0 = r3;"
+ "exit;"
+ :
+ : __imm(bpf_trace_printk)
+ : __clobber_all);
+}
+#endif
+
+SEC("socket")
+__log_level(2)
+__msg("0: .......... (b7) r1 = 1")
+__msg("1: .1........ (e5) may_goto pc+1")
+__msg("2: .......... (05) goto pc-3")
+__msg("3: .1........ (bf) r0 = r1")
+__msg("4: 0......... (95) exit")
+__naked void may_goto(void)
+{
+ asm volatile (
+ "1: r1 = 1;"
+ ".8byte %[may_goto];"
+ "goto 1b;"
+ "r0 = r1;"
+ "exit;"
+ :
+ : __imm(bpf_get_smp_processor_id),
+ __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, +1 /* offset */, 0))
+ : __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("1: 0......... (18) r2 = 0x7")
+__msg("3: 0.2....... (0f) r0 += r2")
+__naked void ldimm64(void)
+{
+ asm volatile (
+ "r0 = 0;"
+ "r2 = 0x7 ll;"
+ "r0 += r2;"
+ "exit;"
+ :
+ :: __clobber_all);
+}
+
+/* No rules specific for LD_ABS/LD_IND, default behaviour kicks in */
+SEC("socket")
+__log_level(2)
+__msg("2: 0123456789 (30) r0 = *(u8 *)skb[42]")
+__msg("3: 012.456789 (0f) r7 += r0")
+__msg("4: 012.456789 (b7) r3 = 42")
+__msg("5: 0123456789 (50) r0 = *(u8 *)skb[r3 + 0]")
+__msg("6: 0......7.. (0f) r7 += r0")
+__naked void ldabs(void)
+{
+ asm volatile (
+ "r6 = r1;"
+ "r7 = 0;"
+ "r0 = *(u8 *)skb[42];"
+ "r7 += r0;"
+ "r3 = 42;"
+ ".8byte %[ld_ind];" /* same as "r0 = *(u8 *)skb[r3];" */
+ "r7 += r0;"
+ "r0 = r7;"
+ "exit;"
+ :
+ : __imm_insn(ld_ind, BPF_LD_IND(BPF_B, BPF_REG_3, 0))
+ : __clobber_all);
+}
+
+
+#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__log_level(2)
+__msg(" 6: .12345.... (85) call bpf_arena_alloc_pages")
+__msg(" 7: 0......... (bf) r1 = addr_space_cast(r0, 0, 1)")
+__msg(" 8: .1........ (b7) r2 = 42")
+__naked void addr_space_cast(void)
+{
+ asm volatile (
+ "r1 = %[arena] ll;"
+ "r2 = 0;"
+ "r3 = 1;"
+ "r4 = 0;"
+ "r5 = 0;"
+ "call %[bpf_arena_alloc_pages];"
+ "r1 = addr_space_cast(r0, 0, 1);"
+ "r2 = 42;"
+ "*(u64 *)(r1 +0) = r2;"
+ "r0 = 0;"
+ "exit;"
+ :
+ : __imm(bpf_arena_alloc_pages),
+ __imm_addr(arena)
+ : __clobber_all);
+}
+#endif
+
+static __used __naked int aux1(void)
+{
+ asm volatile (
+ "r0 = r1;"
+ "r0 += r2;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: ....45.... (b7) r1 = 1")
+__msg("1: .1..45.... (b7) r2 = 2")
+__msg("2: .12.45.... (b7) r3 = 3")
+/* Conservative liveness for subprog parameters. */
+__msg("3: .12345.... (85) call pc+2")
+__msg("4: .......... (b7) r0 = 0")
+__msg("5: 0......... (95) exit")
+__msg("6: .12....... (bf) r0 = r1")
+__msg("7: 0.2....... (0f) r0 += r2")
+/* Conservative liveness for subprog return value. */
+__msg("8: 0......... (95) exit")
+__naked void subprog1(void)
+{
+ asm volatile (
+ "r1 = 1;"
+ "r2 = 2;"
+ "r3 = 3;"
+ "call aux1;"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+/* to retain debug info for BTF generation */
+void kfunc_root(void)
+{
+ bpf_arena_alloc_pages(0, 0, 0, 0, 0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c
index d3f4c5e4fb69..a3819a5d09c8 100644
--- a/tools/testing/selftests/bpf/progs/connect4_dropper.c
+++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c
@@ -13,12 +13,14 @@
#define VERDICT_REJECT 0
#define VERDICT_PROCEED 1
+int port;
+
SEC("cgroup/connect4")
int connect_v4_dropper(struct bpf_sock_addr *ctx)
{
if (ctx->type != SOCK_STREAM)
return VERDICT_PROCEED;
- if (ctx->user_port == bpf_htons(60120))
+ if (ctx->user_port == bpf_htons(port))
return VERDICT_REJECT;
return VERDICT_PROCEED;
}
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index fd8e1b4c6762..5760ae015e09 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -347,6 +347,7 @@ struct core_reloc_nesting___err_too_deep {
*/
struct core_reloc_arrays_output {
int a2;
+ int a3;
char b123;
int c1c;
int d00d;
@@ -455,6 +456,15 @@ struct core_reloc_arrays___err_bad_zero_sz_arr {
struct core_reloc_arrays_substruct d[1][2];
};
+struct core_reloc_arrays___err_bad_signed_arr_elem_sz {
+ /* int -> short (signed!): not supported case */
+ short a[5];
+ char b[2][3][4];
+ struct core_reloc_arrays_substruct c[3];
+ struct core_reloc_arrays_substruct d[1][2];
+ struct core_reloc_arrays_substruct f[][2];
+};
+
/*
* PRIMITIVES
*/
diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h
index 4ece7873ba60..86085b79f5ca 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_common.h
+++ b/tools/testing/selftests/bpf/progs/cpumask_common.h
@@ -61,6 +61,7 @@ u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym __weak;
u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
const struct cpumask *src2) __ksym __weak;
u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym __weak;
+int bpf_cpumask_populate(struct cpumask *cpumask, void *src, size_t src__sz) __ksym __weak;
void bpf_rcu_read_lock(void) __ksym __weak;
void bpf_rcu_read_unlock(void) __ksym __weak;
diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c
index b40b52548ffb..8a2fd596c8a3 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_failure.c
+++ b/tools/testing/selftests/bpf/progs/cpumask_failure.c
@@ -222,3 +222,41 @@ int BPF_PROG(test_invalid_nested_array, struct task_struct *task, u64 clone_flag
return 0;
}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("type=scalar expected=fp")
+int BPF_PROG(test_populate_invalid_destination, struct task_struct *task, u64 clone_flags)
+{
+ struct bpf_cpumask *invalid = (struct bpf_cpumask *)0x123456;
+ u64 bits;
+ int ret;
+
+ ret = bpf_cpumask_populate((struct cpumask *)invalid, &bits, sizeof(bits));
+ if (!ret)
+ err = 2;
+
+ return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("leads to invalid memory access")
+int BPF_PROG(test_populate_invalid_source, struct task_struct *task, u64 clone_flags)
+{
+ void *garbage = (void *)0x123456;
+ struct bpf_cpumask *local;
+ int ret;
+
+ local = create_cpumask();
+ if (!local) {
+ err = 1;
+ return 0;
+ }
+
+ ret = bpf_cpumask_populate((struct cpumask *)local, garbage, 8);
+ if (!ret)
+ err = 2;
+
+ bpf_cpumask_release(local);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c
index 80ee469b0b60..0e04c31b91c0 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_success.c
+++ b/tools/testing/selftests/bpf/progs/cpumask_success.c
@@ -749,7 +749,6 @@ out:
}
SEC("tp_btf/task_newtask")
-__success
int BPF_PROG(test_refcount_null_tracking, struct task_struct *task, u64 clone_flags)
{
struct bpf_cpumask *mask1, *mask2;
@@ -770,3 +769,122 @@ free_masks_return:
bpf_cpumask_release(mask2);
return 0;
}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_populate_reject_small_mask, struct task_struct *task, u64 clone_flags)
+{
+ struct bpf_cpumask *local;
+ u8 toofewbits;
+ int ret;
+
+ if (!is_test_task())
+ return 0;
+
+ local = create_cpumask();
+ if (!local)
+ return 0;
+
+ /* The kfunc should prevent this operation */
+ ret = bpf_cpumask_populate((struct cpumask *)local, &toofewbits, sizeof(toofewbits));
+ if (ret != -EACCES)
+ err = 2;
+
+ bpf_cpumask_release(local);
+
+ return 0;
+}
+
+/* Mask is guaranteed to be large enough for bpf_cpumask_t. */
+#define CPUMASK_TEST_MASKLEN (sizeof(cpumask_t))
+
+/* Add an extra word for the test_populate_reject_unaligned test. */
+u64 bits[CPUMASK_TEST_MASKLEN / 8 + 1];
+extern bool CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS __kconfig __weak;
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_populate_reject_unaligned, struct task_struct *task, u64 clone_flags)
+{
+ struct bpf_cpumask *mask;
+ char *src;
+ int ret;
+
+ if (!is_test_task())
+ return 0;
+
+ /* Skip if unaligned accesses are fine for this arch. */
+ if (CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+ return 0;
+
+ mask = bpf_cpumask_create();
+ if (!mask) {
+ err = 1;
+ return 0;
+ }
+
+ /* Misalign the source array by a byte. */
+ src = &((char *)bits)[1];
+
+ ret = bpf_cpumask_populate((struct cpumask *)mask, src, CPUMASK_TEST_MASKLEN);
+ if (ret != -EINVAL)
+ err = 2;
+
+ bpf_cpumask_release(mask);
+
+ return 0;
+}
+
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_populate, struct task_struct *task, u64 clone_flags)
+{
+ struct bpf_cpumask *mask;
+ bool bit;
+ int ret;
+ int i;
+
+ if (!is_test_task())
+ return 0;
+
+ /* Set only odd bits. */
+ __builtin_memset(bits, 0xaa, CPUMASK_TEST_MASKLEN);
+
+ mask = bpf_cpumask_create();
+ if (!mask) {
+ err = 1;
+ return 0;
+ }
+
+ /* Pass the entire bits array, the kfunc will only copy the valid bits. */
+ ret = bpf_cpumask_populate((struct cpumask *)mask, bits, CPUMASK_TEST_MASKLEN);
+ if (ret) {
+ err = 2;
+ goto out;
+ }
+
+ /*
+ * Test is there to appease the verifier. We cannot directly
+ * access NR_CPUS, the upper bound for nr_cpus, so we infer
+ * it from the size of cpumask_t.
+ */
+ if (nr_cpus < 0 || nr_cpus >= CPUMASK_TEST_MASKLEN * 8) {
+ err = 3;
+ goto out;
+ }
+
+ bpf_for(i, 0, nr_cpus) {
+ /* Odd-numbered bits should be set, even ones unset. */
+ bit = bpf_cpumask_test_cpu(i, (const struct cpumask *)mask);
+ if (bit == (i % 2 != 0))
+ continue;
+
+ err = 4;
+ break;
+ }
+
+out:
+ bpf_cpumask_release(mask);
+
+ return 0;
+}
+
+#undef CPUMASK_TEST_MASKLEN
diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c
index bfcc85686cf0..e1fba28e4a86 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_success.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_success.c
@@ -1,20 +1,19 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2022 Facebook */
+#include <vmlinux.h>
#include <string.h>
#include <stdbool.h>
-#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include "bpf_misc.h"
-#include "bpf_kfuncs.h"
#include "errno.h"
char _license[] SEC("license") = "GPL";
int pid, err, val;
-struct sample {
+struct ringbuf_sample {
int pid;
int seq;
long value;
@@ -121,7 +120,7 @@ int test_dynptr_data(void *ctx)
static int ringbuf_callback(__u32 index, void *data)
{
- struct sample *sample;
+ struct ringbuf_sample *sample;
struct bpf_dynptr *ptr = (struct bpf_dynptr *)data;
@@ -138,7 +137,7 @@ SEC("?tp/syscalls/sys_enter_nanosleep")
int test_ringbuf(void *ctx)
{
struct bpf_dynptr ptr;
- struct sample *sample;
+ struct ringbuf_sample *sample;
if (bpf_get_current_pid_tgid() >> 32 != pid)
return 0;
@@ -567,3 +566,117 @@ int BPF_PROG(test_dynptr_skb_tp_btf, void *skb, void *location)
return 1;
}
+
+static inline int bpf_memcmp(const char *a, const char *b, u32 size)
+{
+ int i;
+
+ bpf_for(i, 0, size) {
+ if (a[i] != b[i])
+ return a[i] < b[i] ? -1 : 1;
+ }
+ return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_copy(void *ctx)
+{
+ char data[] = "hello there, world!!";
+ char buf[32] = {'\0'};
+ __u32 sz = sizeof(data);
+ struct bpf_dynptr src, dst;
+
+ bpf_ringbuf_reserve_dynptr(&ringbuf, sz, 0, &src);
+ bpf_ringbuf_reserve_dynptr(&ringbuf, sz, 0, &dst);
+
+ /* Test basic case of copying contiguous memory backed dynptrs */
+ err = bpf_dynptr_write(&src, 0, data, sz, 0);
+ err = err ?: bpf_dynptr_copy(&dst, 0, &src, 0, sz);
+ err = err ?: bpf_dynptr_read(buf, sz, &dst, 0, 0);
+ err = err ?: bpf_memcmp(data, buf, sz);
+
+ /* Test that offsets are handled correctly */
+ err = err ?: bpf_dynptr_copy(&dst, 3, &src, 5, sz - 5);
+ err = err ?: bpf_dynptr_read(buf, sz - 5, &dst, 3, 0);
+ err = err ?: bpf_memcmp(data + 5, buf, sz - 5);
+
+ bpf_ringbuf_discard_dynptr(&src, 0);
+ bpf_ringbuf_discard_dynptr(&dst, 0);
+ return 0;
+}
+
+SEC("xdp")
+int test_dynptr_copy_xdp(struct xdp_md *xdp)
+{
+ struct bpf_dynptr ptr_buf, ptr_xdp;
+ char data[] = "qwertyuiopasdfghjkl";
+ char buf[32] = {'\0'};
+ __u32 len = sizeof(data);
+ int i, chunks = 200;
+
+ /* ptr_xdp is backed by non-contiguous memory */
+ bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp);
+ bpf_ringbuf_reserve_dynptr(&ringbuf, len * chunks, 0, &ptr_buf);
+
+ /* Destination dynptr is backed by non-contiguous memory */
+ bpf_for(i, 0, chunks) {
+ err = bpf_dynptr_write(&ptr_buf, i * len, data, len, 0);
+ if (err)
+ goto out;
+ }
+
+ err = bpf_dynptr_copy(&ptr_xdp, 0, &ptr_buf, 0, len * chunks);
+ if (err)
+ goto out;
+
+ bpf_for(i, 0, chunks) {
+ __builtin_memset(buf, 0, sizeof(buf));
+ err = bpf_dynptr_read(&buf, len, &ptr_xdp, i * len, 0);
+ if (err)
+ goto out;
+ if (bpf_memcmp(data, buf, len) != 0)
+ goto out;
+ }
+
+ /* Source dynptr is backed by non-contiguous memory */
+ __builtin_memset(buf, 0, sizeof(buf));
+ bpf_for(i, 0, chunks) {
+ err = bpf_dynptr_write(&ptr_buf, i * len, buf, len, 0);
+ if (err)
+ goto out;
+ }
+
+ err = bpf_dynptr_copy(&ptr_buf, 0, &ptr_xdp, 0, len * chunks);
+ if (err)
+ goto out;
+
+ bpf_for(i, 0, chunks) {
+ __builtin_memset(buf, 0, sizeof(buf));
+ err = bpf_dynptr_read(&buf, len, &ptr_buf, i * len, 0);
+ if (err)
+ goto out;
+ if (bpf_memcmp(data, buf, len) != 0)
+ goto out;
+ }
+
+ /* Both source and destination dynptrs are backed by non-contiguous memory */
+ err = bpf_dynptr_copy(&ptr_xdp, 2, &ptr_xdp, len, len * (chunks - 1));
+ if (err)
+ goto out;
+
+ bpf_for(i, 0, chunks - 1) {
+ __builtin_memset(buf, 0, sizeof(buf));
+ err = bpf_dynptr_read(&buf, len, &ptr_xdp, 2 + i * len, 0);
+ if (err)
+ goto out;
+ if (bpf_memcmp(data, buf, len) != 0)
+ goto out;
+ }
+
+ if (bpf_dynptr_copy(&ptr_xdp, 2000, &ptr_xdp, 0, len * chunks) != -E2BIG)
+ err = 1;
+
+out:
+ bpf_ringbuf_discard_dynptr(&ptr_buf, 0);
+ return XDP_DROP;
+}
diff --git a/tools/testing/selftests/bpf/progs/fexit_noreturns.c b/tools/testing/selftests/bpf/progs/fexit_noreturns.c
new file mode 100644
index 000000000000..54654539f550
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fexit_noreturns.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fexit/do_exit")
+__failure __msg("Attaching fexit/fmod_ret to __noreturn functions is rejected.")
+int BPF_PROG(noreturns)
+{
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/irq.c b/tools/testing/selftests/bpf/progs/irq.c
index b0b53d980964..74d912b22de9 100644
--- a/tools/testing/selftests/bpf/progs/irq.c
+++ b/tools/testing/selftests/bpf/progs/irq.c
@@ -11,6 +11,9 @@ extern void bpf_local_irq_save(unsigned long *) __weak __ksym;
extern void bpf_local_irq_restore(unsigned long *) __weak __ksym;
extern int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void *unsafe_ptr__ign, u64 flags) __weak __ksym;
+struct bpf_res_spin_lock lockA __hidden SEC(".data.A");
+struct bpf_res_spin_lock lockB __hidden SEC(".data.B");
+
SEC("?tc")
__failure __msg("arg#0 doesn't point to an irq flag on stack")
int irq_save_bad_arg(struct __sk_buff *ctx)
@@ -222,7 +225,7 @@ int __noinline global_local_irq_balance(void)
}
SEC("?tc")
-__failure __msg("global function calls are not allowed with IRQs disabled")
+__success
int irq_global_subprog(struct __sk_buff *ctx)
{
unsigned long flags;
@@ -441,4 +444,123 @@ int irq_ooo_refs_array(struct __sk_buff *ctx)
return 0;
}
+int __noinline
+global_subprog(int i)
+{
+ if (i)
+ bpf_printk("%p", &i);
+ return i;
+}
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+ if (i)
+ bpf_copy_from_user(&i, sizeof(i), NULL);
+ return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+ if (i)
+ bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+ global_subprog(i);
+ return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+ if (!i)
+ global_sleepable_kfunc_subprog(i);
+ return i;
+}
+
+SEC("?syscall")
+__success
+int irq_non_sleepable_global_subprog(void *ctx)
+{
+ unsigned long flags;
+
+ bpf_local_irq_save(&flags);
+ global_subprog(0);
+ bpf_local_irq_restore(&flags);
+ return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int irq_sleepable_helper_global_subprog(void *ctx)
+{
+ unsigned long flags;
+
+ bpf_local_irq_save(&flags);
+ global_sleepable_helper_subprog(0);
+ bpf_local_irq_restore(&flags);
+ return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int irq_sleepable_global_subprog_indirect(void *ctx)
+{
+ unsigned long flags;
+
+ bpf_local_irq_save(&flags);
+ global_subprog_calling_sleepable_global(0);
+ bpf_local_irq_restore(&flags);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot restore irq state out of order")
+int irq_ooo_lock_cond_inv(struct __sk_buff *ctx)
+{
+ unsigned long flags1, flags2;
+
+ if (bpf_res_spin_lock_irqsave(&lockA, &flags1))
+ return 0;
+ if (bpf_res_spin_lock_irqsave(&lockB, &flags2)) {
+ bpf_res_spin_unlock_irqrestore(&lockA, &flags1);
+ return 0;
+ }
+
+ bpf_res_spin_unlock_irqrestore(&lockB, &flags1);
+ bpf_res_spin_unlock_irqrestore(&lockA, &flags2);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("function calls are not allowed")
+int irq_wrong_kfunc_class_1(struct __sk_buff *ctx)
+{
+ unsigned long flags1;
+
+ if (bpf_res_spin_lock_irqsave(&lockA, &flags1))
+ return 0;
+ /* For now, bpf_local_irq_restore is not allowed in critical section,
+ * but this test ensures error will be caught with kfunc_class when it's
+ * opened up. Tested by temporarily permitting this kfunc in critical
+ * section.
+ */
+ bpf_local_irq_restore(&flags1);
+ bpf_res_spin_unlock_irqrestore(&lockA, &flags1);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("function calls are not allowed")
+int irq_wrong_kfunc_class_2(struct __sk_buff *ctx)
+{
+ unsigned long flags1, flags2;
+
+ bpf_local_irq_save(&flags1);
+ if (bpf_res_spin_lock_irqsave(&lockA, &flags2))
+ return 0;
+ bpf_local_irq_restore(&flags2);
+ bpf_res_spin_unlock_irqrestore(&lockA, &flags1);
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 190822b2f08b..427b72954b87 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -7,6 +7,8 @@
#include "bpf_misc.h"
#include "bpf_compiler.h"
+#define unlikely(x) __builtin_expect(!!(x), 0)
+
static volatile int zero = 0;
int my_pid;
@@ -1175,6 +1177,122 @@ __naked int loop_state_deps2(void)
}
SEC("?raw_tp")
+__failure
+__msg("math between fp pointer and register with unbounded")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked int loop_state_deps3(void)
+{
+ /* This is equivalent to a C program below.
+ *
+ * if (random() != 24) { // assume false branch is placed first
+ * i = iter_new(); // fp[-8]
+ * while (iter_next(i));
+ * iter_destroy(i);
+ * return;
+ * }
+ *
+ * for (i = 10; i > 0; i--); // increase dfs_depth for child states
+ *
+ * i = iter_new(); // fp[-8]
+ * b = -24; // r8
+ * for (;;) { // checkpoint (L)
+ * if (iter_next(i)) // checkpoint (N)
+ * break;
+ * if (random() == 77) { // assume false branch is placed first
+ * *(u64 *)(r10 + b) = 7; // this is not safe when b == -25
+ * iter_destroy(i);
+ * return;
+ * }
+ * if (random() == 42) { // assume false branch is placed first
+ * b = -25;
+ * }
+ * }
+ * iter_destroy(i);
+ *
+ * In case of a buggy verifier first loop might poison
+ * env->cur_state->loop_entry with a state having 0 branches
+ * and small dfs_depth. This would trigger NOT_EXACT states
+ * comparison for some states within second loop.
+ * Specifically, checkpoint (L) might be problematic if:
+ * - branch with '*(u64 *)(r10 + b) = 7' is not explored yet;
+ * - checkpoint (L) is first reached in state {b=-24};
+ * - traversal is pruned at checkpoint (N) setting checkpoint's (L)
+ * branch count to 0, thus making it eligible for use in pruning;
+ * - checkpoint (L) is next reached in state {b=-25},
+ * this would cause NOT_EXACT comparison with a state {b=-24}
+ * while 'b' is not marked precise yet.
+ */
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == 24 goto 2f;"
+ "r1 = r10;"
+ "r1 += -8;"
+ "r2 = 0;"
+ "r3 = 5;"
+ "call %[bpf_iter_num_new];"
+ "1:"
+ "r1 = r10;"
+ "r1 += -8;"
+ "call %[bpf_iter_num_next];"
+ "if r0 != 0 goto 1b;"
+ "r1 = r10;"
+ "r1 += -8;"
+ "call %[bpf_iter_num_destroy];"
+ "r0 = 0;"
+ "exit;"
+ "2:"
+ /* loop to increase dfs_depth */
+ "r0 = 10;"
+ "3:"
+ "r0 -= 1;"
+ "if r0 != 0 goto 3b;"
+ /* end of loop */
+ "r1 = r10;"
+ "r1 += -8;"
+ "r2 = 0;"
+ "r3 = 10;"
+ "call %[bpf_iter_num_new];"
+ "r8 = -24;"
+ "main_loop_%=:"
+ "r1 = r10;"
+ "r1 += -8;"
+ "call %[bpf_iter_num_next];"
+ "if r0 == 0 goto main_loop_end_%=;"
+ /* first if */
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == 77 goto unsafe_write_%=;"
+ /* second if */
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == 42 goto poison_r8_%=;"
+ /* iterate */
+ "goto main_loop_%=;"
+ "main_loop_end_%=:"
+ "r1 = r10;"
+ "r1 += -8;"
+ "call %[bpf_iter_num_destroy];"
+ "r0 = 0;"
+ "exit;"
+
+ "unsafe_write_%=:"
+ "r0 = r10;"
+ "r0 += r8;"
+ "r1 = 7;"
+ "*(u64 *)(r0 + 0) = r1;"
+ "goto main_loop_end_%=;"
+
+ "poison_r8_%=:"
+ "r8 = -25;"
+ "goto main_loop_%=;"
+ :
+ : __imm(bpf_get_prandom_u32),
+ __imm(bpf_iter_num_new),
+ __imm(bpf_iter_num_next),
+ __imm(bpf_iter_num_destroy)
+ : __clobber_all
+ );
+}
+
+SEC("?raw_tp")
__success
__naked int triple_continue(void)
{
@@ -1512,4 +1630,25 @@ int iter_destroy_bad_arg(const void *ctx)
return 0;
}
+SEC("raw_tp")
+__success
+int clean_live_states(const void *ctx)
+{
+ char buf[1];
+ int i, j, k, l, m, n, o;
+
+ bpf_for(i, 0, 10)
+ bpf_for(j, 0, 10)
+ bpf_for(k, 0, 10)
+ bpf_for(l, 0, 10)
+ bpf_for(m, 0, 10)
+ bpf_for(n, 0, 10)
+ bpf_for(o, 0, 10) {
+ if (unlikely(bpf_get_prandom_u32()))
+ buf[0] = 42;
+ bpf_printk("%s", buf);
+ }
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
index c6edf8dbefeb..94040714af18 100644
--- a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
+++ b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
@@ -28,6 +28,7 @@ struct {
} sock_map SEC(".maps");
int tcx_init_netns_cookie, tcx_netns_cookie;
+int cgroup_skb_init_netns_cookie, cgroup_skb_netns_cookie;
SEC("sockops")
int get_netns_cookie_sockops(struct bpf_sock_ops *ctx)
@@ -91,4 +92,12 @@ int get_netns_cookie_tcx(struct __sk_buff *skb)
return TCX_PASS;
}
+SEC("cgroup_skb/ingress")
+int get_netns_cookie_cgroup_skb(struct __sk_buff *skb)
+{
+ cgroup_skb_init_netns_cookie = bpf_get_netns_cookie(NULL);
+ cgroup_skb_netns_cookie = bpf_get_netns_cookie(skb);
+ return SK_PASS;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/preempt_lock.c b/tools/testing/selftests/bpf/progs/preempt_lock.c
index 6c5797bf0ead..7d04254e61f1 100644
--- a/tools/testing/selftests/bpf/progs/preempt_lock.c
+++ b/tools/testing/selftests/bpf/progs/preempt_lock.c
@@ -134,7 +134,7 @@ int __noinline preempt_global_subprog(void)
}
SEC("?tc")
-__failure __msg("global function calls are not allowed with preemption disabled")
+__success
int preempt_global_subprog_test(struct __sk_buff *ctx)
{
preempt_disable();
@@ -143,4 +143,70 @@ int preempt_global_subprog_test(struct __sk_buff *ctx)
return 0;
}
+int __noinline
+global_subprog(int i)
+{
+ if (i)
+ bpf_printk("%p", &i);
+ return i;
+}
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+ if (i)
+ bpf_copy_from_user(&i, sizeof(i), NULL);
+ return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+ if (i)
+ bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+ global_subprog(i);
+ return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+ if (!i)
+ global_sleepable_kfunc_subprog(i);
+ return i;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int preempt_global_sleepable_helper_subprog(struct __sk_buff *ctx)
+{
+ preempt_disable();
+ if (ctx->mark)
+ global_sleepable_helper_subprog(ctx->mark);
+ preempt_enable();
+ return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int preempt_global_sleepable_kfunc_subprog(struct __sk_buff *ctx)
+{
+ preempt_disable();
+ if (ctx->mark)
+ global_sleepable_kfunc_subprog(ctx->mark);
+ preempt_enable();
+ return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int preempt_global_sleepable_subprog_indirect(struct __sk_buff *ctx)
+{
+ preempt_disable();
+ if (ctx->mark)
+ global_subprog_calling_sleepable_global(ctx->mark);
+ preempt_enable();
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/prepare.c b/tools/testing/selftests/bpf/progs/prepare.c
new file mode 100644
index 000000000000..1f1dd547e4ee
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/prepare.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+//#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int err;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_RINGBUF);
+ __uint(max_entries, 4096);
+} ringbuf SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u32);
+} array_map SEC(".maps");
+
+SEC("cgroup_skb/egress")
+int program(struct __sk_buff *skb)
+{
+ err = 0;
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/priv_freplace_prog.c b/tools/testing/selftests/bpf/progs/priv_freplace_prog.c
new file mode 100644
index 000000000000..ccf1b04010ba
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/priv_freplace_prog.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("freplace/xdp_prog1")
+int new_xdp_prog2(struct xdp_md *xd)
+{
+ return XDP_DROP;
+}
diff --git a/tools/testing/selftests/bpf/progs/priv_prog.c b/tools/testing/selftests/bpf/progs/priv_prog.c
index 3c7b2b618c8a..725e29595079 100644
--- a/tools/testing/selftests/bpf/progs/priv_prog.c
+++ b/tools/testing/selftests/bpf/progs/priv_prog.c
@@ -6,8 +6,8 @@
char _license[] SEC("license") = "GPL";
-SEC("kprobe")
-int kprobe_prog(void *ctx)
+SEC("xdp")
+int xdp_prog1(struct xdp_md *xdp)
{
- return 1;
+ return XDP_DROP;
}
diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c b/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c
new file mode 100644
index 000000000000..a5a8f08ac8fb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+void __kfunc_btf_root(void)
+{
+ bpf_kfunc_st_ops_inc10(NULL);
+}
+
+static __noinline __used int subprog(struct st_ops_args *args)
+{
+ args->a += 1;
+ return args->a;
+}
+
+__success
+/* prologue */
+__xlated("0: r8 = r1")
+__xlated("1: r1 = 0")
+__xlated("2: call kernel-function")
+__xlated("3: if r0 != 0x0 goto pc+5")
+__xlated("4: r6 = *(u64 *)(r8 +0)")
+__xlated("5: r7 = *(u64 *)(r6 +0)")
+__xlated("6: r7 += 1000")
+__xlated("7: *(u64 *)(r6 +0) = r7")
+__xlated("8: goto pc+2")
+__xlated("9: r1 = r0")
+__xlated("10: call kernel-function")
+__xlated("11: r1 = r8")
+/* save __u64 *ctx to stack */
+__xlated("12: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("13: r1 = *(u64 *)(r1 +0)")
+__xlated("14: r6 = r1")
+__xlated("15: call kernel-function")
+__xlated("16: r1 = r6")
+__xlated("17: call pc+")
+/* epilogue */
+__xlated("18: r1 = 0")
+__xlated("19: r6 = 0")
+__xlated("20: call kernel-function")
+__xlated("21: if r0 != 0x0 goto pc+6")
+__xlated("22: r1 = *(u64 *)(r10 -8)")
+__xlated("23: r1 = *(u64 *)(r1 +0)")
+__xlated("24: r6 = *(u64 *)(r1 +0)")
+__xlated("25: r6 += 10000")
+__xlated("26: *(u64 *)(r1 +0) = r6")
+__xlated("27: goto pc+2")
+__xlated("28: r1 = r0")
+__xlated("29: call kernel-function")
+__xlated("30: r0 = r6")
+__xlated("31: r0 *= 2")
+__xlated("32: exit")
+SEC("struct_ops/test_pro_epilogue")
+__naked int test_kfunc_pro_epilogue(void)
+{
+ asm volatile (
+ "r1 = *(u64 *)(r1 +0);"
+ "r6 = r1;"
+ "call %[bpf_kfunc_st_ops_inc10];"
+ "r1 = r6;"
+ "call subprog;"
+ "exit;"
+ :
+ : __imm(bpf_kfunc_st_ops_inc10)
+ : __clobber_all);
+}
+
+SEC("syscall")
+__retval(22022) /* (PROLOGUE_A [1000] + KFUNC_INC10 + SUBPROG_A [1] + EPILOGUE_A [10000]) * 2 */
+int syscall_pro_epilogue(void *ctx)
+{
+ struct st_ops_args args = {};
+
+ return bpf_kfunc_st_ops_test_pro_epilogue(&args);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops pro_epilogue_with_kfunc = {
+ .test_pro_epilogue = (void *)test_kfunc_pro_epilogue,
+};
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 8bd1ebd7d6af..813143b4985d 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -223,7 +223,7 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node,
if (bpf_cmp_likely(filepart_length, <=, MAX_PATH)) {
payload += filepart_length;
}
- cgroup_node = BPF_CORE_READ(cgroup_node, parent);
+ cgroup_node = BPF_CORE_READ(cgroup_node, __parent);
}
return payload;
}
diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
index ab3a532b7dd6..43637ee2cdcd 100644
--- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c
+++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
@@ -242,7 +242,8 @@ out:
}
SEC("?lsm.s/bpf")
-int BPF_PROG(inproper_sleepable_kfunc, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(inproper_sleepable_kfunc, int cmd, union bpf_attr *attr, unsigned int size,
+ bool kernel)
{
struct bpf_key *bkey;
@@ -439,3 +440,61 @@ int rcu_read_lock_global_subprog_unlock(void *ctx)
ret += global_subprog_unlock(ret);
return 0;
}
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+ if (i)
+ bpf_copy_from_user(&i, sizeof(i), NULL);
+ return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+ if (i)
+ bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+ global_subprog(i);
+ return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+ if (!i)
+ global_sleepable_kfunc_subprog(i);
+ return i;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_sleepable_helper_global_subprog(void *ctx)
+{
+ volatile int ret = 0;
+
+ bpf_rcu_read_lock();
+ ret += global_sleepable_helper_subprog(ret);
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_sleepable_kfunc_global_subprog(void *ctx)
+{
+ volatile int ret = 0;
+
+ bpf_rcu_read_lock();
+ ret += global_sleepable_kfunc_subprog(ret);
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_sleepable_global_subprog_indirect(void *ctx)
+{
+ volatile int ret = 0;
+
+ bpf_rcu_read_lock();
+ ret += global_subprog_calling_sleepable_global(ret);
+ bpf_rcu_read_unlock();
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c
index 39ebef430059..395591374d4f 100644
--- a/tools/testing/selftests/bpf/progs/read_vsyscall.c
+++ b/tools/testing/selftests/bpf/progs/read_vsyscall.c
@@ -8,14 +8,16 @@
int target_pid = 0;
void *user_ptr = 0;
-int read_ret[9];
+int read_ret[10];
char _license[] SEC("license") = "GPL";
/*
- * This is the only kfunc, the others are helpers
+ * These are the kfuncs, the others are helpers
*/
int bpf_copy_from_user_str(void *dst, u32, const void *, u64) __weak __ksym;
+int bpf_copy_from_user_task_str(void *dst, u32, const void *,
+ struct task_struct *, u64) __weak __ksym;
SEC("fentry/" SYS_PREFIX "sys_nanosleep")
int do_probe_read(void *ctx)
@@ -47,6 +49,11 @@ int do_copy_from_user(void *ctx)
read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr,
bpf_get_current_task_btf(), 0);
read_ret[8] = bpf_copy_from_user_str((char *)buf, sizeof(buf), user_ptr, 0);
+ read_ret[9] = bpf_copy_from_user_task_str((char *)buf,
+ sizeof(buf),
+ user_ptr,
+ bpf_get_current_task_btf(),
+ 0);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/res_spin_lock.c b/tools/testing/selftests/bpf/progs/res_spin_lock.c
new file mode 100644
index 000000000000..22c4fb8b9266
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/res_spin_lock.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024-2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define EDEADLK 35
+#define ETIMEDOUT 110
+
+struct arr_elem {
+ struct bpf_res_spin_lock lock;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 64);
+ __type(key, int);
+ __type(value, struct arr_elem);
+} arrmap SEC(".maps");
+
+struct bpf_res_spin_lock lockA __hidden SEC(".data.A");
+struct bpf_res_spin_lock lockB __hidden SEC(".data.B");
+
+SEC("tc")
+int res_spin_lock_test(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem1, *elem2;
+ int r;
+
+ elem1 = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem1)
+ return -1;
+ elem2 = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem2)
+ return -1;
+
+ r = bpf_res_spin_lock(&elem1->lock);
+ if (r)
+ return r;
+ r = bpf_res_spin_lock(&elem2->lock);
+ if (!r) {
+ bpf_res_spin_unlock(&elem2->lock);
+ bpf_res_spin_unlock(&elem1->lock);
+ return -1;
+ }
+ bpf_res_spin_unlock(&elem1->lock);
+ return r != -EDEADLK;
+}
+
+SEC("tc")
+int res_spin_lock_test_AB(struct __sk_buff *ctx)
+{
+ int r;
+
+ r = bpf_res_spin_lock(&lockA);
+ if (r)
+ return !r;
+ /* Only unlock if we took the lock. */
+ if (!bpf_res_spin_lock(&lockB))
+ bpf_res_spin_unlock(&lockB);
+ bpf_res_spin_unlock(&lockA);
+ return 0;
+}
+
+int err;
+
+SEC("tc")
+int res_spin_lock_test_BA(struct __sk_buff *ctx)
+{
+ int r;
+
+ r = bpf_res_spin_lock(&lockB);
+ if (r)
+ return !r;
+ if (!bpf_res_spin_lock(&lockA))
+ bpf_res_spin_unlock(&lockA);
+ else
+ err = -EDEADLK;
+ bpf_res_spin_unlock(&lockB);
+ return err ?: 0;
+}
+
+SEC("tc")
+int res_spin_lock_test_held_lock_max(struct __sk_buff *ctx)
+{
+ struct bpf_res_spin_lock *locks[48] = {};
+ struct arr_elem *e;
+ u64 time_beg, time;
+ int ret = 0, i;
+
+ _Static_assert(ARRAY_SIZE(((struct rqspinlock_held){}).locks) == 31,
+ "RES_NR_HELD assumed to be 31");
+
+ for (i = 0; i < 34; i++) {
+ int key = i;
+
+ /* We cannot pass in i as it will get spilled/filled by the compiler and
+ * loses bounds in verifier state.
+ */
+ e = bpf_map_lookup_elem(&arrmap, &key);
+ if (!e)
+ return 1;
+ locks[i] = &e->lock;
+ }
+
+ for (; i < 48; i++) {
+ int key = i - 2;
+
+ /* We cannot pass in i as it will get spilled/filled by the compiler and
+ * loses bounds in verifier state.
+ */
+ e = bpf_map_lookup_elem(&arrmap, &key);
+ if (!e)
+ return 1;
+ locks[i] = &e->lock;
+ }
+
+ time_beg = bpf_ktime_get_ns();
+ for (i = 0; i < 34; i++) {
+ if (bpf_res_spin_lock(locks[i]))
+ goto end;
+ }
+
+ /* Trigger AA, after exhausting entries in the held lock table. This
+ * time, only the timeout can save us, as AA detection won't succeed.
+ */
+ ret = bpf_res_spin_lock(locks[34]);
+ if (!ret) {
+ bpf_res_spin_unlock(locks[34]);
+ ret = 1;
+ goto end;
+ }
+
+ ret = ret != -ETIMEDOUT ? 2 : 0;
+
+end:
+ for (i = i - 1; i >= 0; i--)
+ bpf_res_spin_unlock(locks[i]);
+ time = bpf_ktime_get_ns() - time_beg;
+ /* Time spent should be easily above our limit (1/4 s), since AA
+ * detection won't be expedited due to lack of held lock entry.
+ */
+ return ret ?: (time > 1000000000 / 4 ? 0 : 1);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/res_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/res_spin_lock_fail.c
new file mode 100644
index 000000000000..330682a88c16
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/res_spin_lock_fail.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024-2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct arr_elem {
+ struct bpf_res_spin_lock lock;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, struct arr_elem);
+} arrmap SEC(".maps");
+
+long value;
+
+struct bpf_spin_lock lock __hidden SEC(".data.A");
+struct bpf_res_spin_lock res_lock __hidden SEC(".data.B");
+
+SEC("?tc")
+__failure __msg("point to map value or allocated object")
+int res_spin_lock_arg(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem)
+ return 0;
+ bpf_res_spin_lock((struct bpf_res_spin_lock *)bpf_core_cast(&elem->lock, struct __sk_buff));
+ bpf_res_spin_lock(&elem->lock);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("AA deadlock detected")
+int res_spin_lock_AA(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem)
+ return 0;
+ bpf_res_spin_lock(&elem->lock);
+ bpf_res_spin_lock(&elem->lock);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("AA deadlock detected")
+int res_spin_lock_cond_AA(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem)
+ return 0;
+ if (bpf_res_spin_lock(&elem->lock))
+ return 0;
+ bpf_res_spin_lock(&elem->lock);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("unlock of different lock")
+int res_spin_lock_mismatch_1(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem)
+ return 0;
+ if (bpf_res_spin_lock(&elem->lock))
+ return 0;
+ bpf_res_spin_unlock(&res_lock);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("unlock of different lock")
+int res_spin_lock_mismatch_2(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem)
+ return 0;
+ if (bpf_res_spin_lock(&res_lock))
+ return 0;
+ bpf_res_spin_unlock(&elem->lock);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("unlock of different lock")
+int res_spin_lock_irq_mismatch_1(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+ unsigned long f1;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem)
+ return 0;
+ bpf_local_irq_save(&f1);
+ if (bpf_res_spin_lock(&res_lock))
+ return 0;
+ bpf_res_spin_unlock_irqrestore(&res_lock, &f1);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("unlock of different lock")
+int res_spin_lock_irq_mismatch_2(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+ unsigned long f1;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem)
+ return 0;
+ if (bpf_res_spin_lock_irqsave(&res_lock, &f1))
+ return 0;
+ bpf_res_spin_unlock(&res_lock);
+ return 0;
+}
+
+SEC("?tc")
+__success
+int res_spin_lock_ooo(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem)
+ return 0;
+ if (bpf_res_spin_lock(&res_lock))
+ return 0;
+ if (bpf_res_spin_lock(&elem->lock)) {
+ bpf_res_spin_unlock(&res_lock);
+ return 0;
+ }
+ bpf_res_spin_unlock(&elem->lock);
+ bpf_res_spin_unlock(&res_lock);
+ return 0;
+}
+
+SEC("?tc")
+__success
+int res_spin_lock_ooo_irq(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+ unsigned long f1, f2;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem)
+ return 0;
+ if (bpf_res_spin_lock_irqsave(&res_lock, &f1))
+ return 0;
+ if (bpf_res_spin_lock_irqsave(&elem->lock, &f2)) {
+ bpf_res_spin_unlock_irqrestore(&res_lock, &f1);
+ /* We won't have a unreleased IRQ flag error here. */
+ return 0;
+ }
+ bpf_res_spin_unlock_irqrestore(&elem->lock, &f2);
+ bpf_res_spin_unlock_irqrestore(&res_lock, &f1);
+ return 0;
+}
+
+struct bpf_res_spin_lock lock1 __hidden SEC(".data.OO1");
+struct bpf_res_spin_lock lock2 __hidden SEC(".data.OO2");
+
+SEC("?tc")
+__failure __msg("bpf_res_spin_unlock cannot be out of order")
+int res_spin_lock_ooo_unlock(struct __sk_buff *ctx)
+{
+ if (bpf_res_spin_lock(&lock1))
+ return 0;
+ if (bpf_res_spin_lock(&lock2)) {
+ bpf_res_spin_unlock(&lock1);
+ return 0;
+ }
+ bpf_res_spin_unlock(&lock1);
+ bpf_res_spin_unlock(&lock2);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("off 1 doesn't point to 'struct bpf_res_spin_lock' that is at 0")
+int res_spin_lock_bad_off(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem)
+ return 0;
+ bpf_res_spin_lock((void *)&elem->lock + 1);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("R1 doesn't have constant offset. bpf_res_spin_lock has to be at the constant offset")
+int res_spin_lock_var_off(struct __sk_buff *ctx)
+{
+ struct arr_elem *elem;
+ u64 val = value;
+
+ elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+ if (!elem) {
+ // FIXME: Only inline assembly use in assert macro doesn't emit
+ // BTF definition.
+ bpf_throw(0);
+ return 0;
+ }
+ bpf_assert_range(val, 0, 40);
+ bpf_res_spin_lock((void *)&value + val);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("map 'res_spin.bss' has no valid bpf_res_spin_lock")
+int res_spin_lock_no_lock_map(struct __sk_buff *ctx)
+{
+ bpf_res_spin_lock((void *)&value + 1);
+ return 0;
+}
+
+SEC("?tc")
+__failure __msg("local 'kptr' has no valid bpf_res_spin_lock")
+int res_spin_lock_no_lock_kptr(struct __sk_buff *ctx)
+{
+ struct { int i; } *p = bpf_obj_new(typeof(*p));
+
+ if (!p)
+ return 0;
+ bpf_res_spin_lock((void *)p);
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/set_global_vars.c b/tools/testing/selftests/bpf/progs/set_global_vars.c
new file mode 100644
index 000000000000..9adb5ba4cd4d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/set_global_vars.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include "bpf_experimental.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include <stdbool.h>
+
+char _license[] SEC("license") = "GPL";
+
+enum Enum { EA1 = 0, EA2 = 11 };
+enum Enumu64 {EB1 = 0llu, EB2 = 12llu };
+enum Enums64 { EC1 = 0ll, EC2 = 13ll };
+
+const volatile __s64 var_s64 = -1;
+const volatile __u64 var_u64 = 0;
+const volatile __s32 var_s32 = -1;
+const volatile __u32 var_u32 = 0;
+const volatile __s16 var_s16 = -1;
+const volatile __u16 var_u16 = 0;
+const volatile __s8 var_s8 = -1;
+const volatile __u8 var_u8 = 0;
+const volatile enum Enum var_ea = EA1;
+const volatile enum Enumu64 var_eb = EB1;
+const volatile enum Enums64 var_ec = EC1;
+const volatile bool var_b = false;
+
+char arr[4] = {0};
+
+SEC("socket")
+int test_set_globals(void *ctx)
+{
+ volatile __s8 a;
+
+ a = var_s64;
+ a = var_u64;
+ a = var_s32;
+ a = var_u32;
+ a = var_s16;
+ a = var_u16;
+ a = var_s8;
+ a = var_u8;
+ a = var_ea;
+ a = var_eb;
+ a = var_ec;
+ a = var_b;
+ return a;
+}
diff --git a/tools/testing/selftests/bpf/progs/strncmp_bench.c b/tools/testing/selftests/bpf/progs/strncmp_bench.c
index 18373a7df76e..f47bf88f8d2a 100644
--- a/tools/testing/selftests/bpf/progs/strncmp_bench.c
+++ b/tools/testing/selftests/bpf/progs/strncmp_bench.c
@@ -35,7 +35,10 @@ static __always_inline int local_strncmp(const char *s1, unsigned int sz,
SEC("tp/syscalls/sys_enter_getpgid")
int strncmp_no_helper(void *ctx)
{
- if (local_strncmp(str, cmp_str_len + 1, target) < 0)
+ const char *target_str = target;
+
+ barrier_var(target_str);
+ if (local_strncmp(str, cmp_str_len + 1, target_str) < 0)
__sync_add_and_fetch(&hits, 1);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c
new file mode 100644
index 000000000000..36386b3c23a1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c
@@ -0,0 +1,30 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * allow a referenced kptr or a NULL pointer to be returned. A referenced kptr to task
+ * here is acquried automatically as the task argument is tagged with "__ref".
+ */
+SEC("struct_ops/test_return_ref_kptr")
+struct task_struct *BPF_PROG(kptr_return, int dummy,
+ struct task_struct *task, struct cgroup *cgrp)
+{
+ if (dummy % 2) {
+ bpf_task_release(task);
+ return NULL;
+ }
+ return task;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+ .test_return_ref_kptr = (void *)kptr_return,
+};
+
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c
new file mode 100644
index 000000000000..caeea158ef69
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c
@@ -0,0 +1,26 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a non-zero scalar value.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("At program exit the register R0 has smin=1 smax=1 should have been in [0, 0]")
+struct task_struct *BPF_PROG(kptr_return_fail__invalid_scalar, int dummy,
+ struct task_struct *task, struct cgroup *cgrp)
+{
+ bpf_task_release(task);
+ return (struct task_struct *)1;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+ .test_return_ref_kptr = (void *)kptr_return_fail__invalid_scalar,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c
new file mode 100644
index 000000000000..b8b4f05c3d7f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c
@@ -0,0 +1,34 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a local kptr.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("At program exit the register R0 is not a known value (ptr_or_null_)")
+struct task_struct *BPF_PROG(kptr_return_fail__local_kptr, int dummy,
+ struct task_struct *task, struct cgroup *cgrp)
+{
+ struct task_struct *t;
+
+ bpf_task_release(task);
+
+ t = bpf_obj_new(typeof(*task));
+ if (!t)
+ return NULL;
+
+ return t;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+ .test_return_ref_kptr = (void *)kptr_return_fail__local_kptr,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c
new file mode 100644
index 000000000000..7ddeb28c2329
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c
@@ -0,0 +1,25 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a modified referenced kptr.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("dereference of modified trusted_ptr_ ptr R0 off={{[0-9]+}} disallowed")
+struct task_struct *BPF_PROG(kptr_return_fail__nonzero_offset, int dummy,
+ struct task_struct *task, struct cgroup *cgrp)
+{
+ return (struct task_struct *)&task->jobctl;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+ .test_return_ref_kptr = (void *)kptr_return_fail__nonzero_offset,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c
new file mode 100644
index 000000000000..6a2dd5367802
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c
@@ -0,0 +1,30 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a referenced kptr of the wrong type.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("At program exit the register R0 is not a known value (ptr_or_null_)")
+struct task_struct *BPF_PROG(kptr_return_fail__wrong_type, int dummy,
+ struct task_struct *task, struct cgroup *cgrp)
+{
+ struct task_struct *ret;
+
+ ret = (struct task_struct *)bpf_cgroup_acquire(cgrp);
+ bpf_task_release(task);
+
+ return ret;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+ .test_return_ref_kptr = (void *)kptr_return_fail__wrong_type,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c
new file mode 100644
index 000000000000..76dcb6089d7f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c
@@ -0,0 +1,31 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__attribute__((nomerge)) extern void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This is a test BPF program that uses struct_ops to access a referenced
+ * kptr argument. This is a test for the verifier to ensure that it
+ * 1) recongnizes the task as a referenced object (i.e., ref_obj_id > 0), and
+ * 2) the same reference can be acquired from multiple paths as long as it
+ * has not been released.
+ */
+SEC("struct_ops/test_refcounted")
+int BPF_PROG(refcounted, int dummy, struct task_struct *task)
+{
+ if (dummy == 1)
+ bpf_task_release(task);
+ else
+ bpf_task_release(task);
+ return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_refcounted = {
+ .test_refcounted = (void *)refcounted,
+};
+
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c
new file mode 100644
index 000000000000..ae074aa62852
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c
@@ -0,0 +1,39 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+extern void bpf_task_release(struct task_struct *p) __ksym;
+
+__noinline int subprog_release(__u64 *ctx __arg_ctx)
+{
+ struct task_struct *task = (struct task_struct *)ctx[1];
+ int dummy = (int)ctx[0];
+
+ bpf_task_release(task);
+
+ return dummy + 1;
+}
+
+/* Test that the verifier rejects a program that contains a global
+ * subprogram with referenced kptr arguments
+ */
+SEC("struct_ops/test_refcounted")
+__failure __log_level(2)
+__msg("Validating subprog_release() func#1...")
+__msg("invalid bpf_context access off=8. Reference may already be released")
+int refcounted_fail__global_subprog(unsigned long long *ctx)
+{
+ struct task_struct *task = (struct task_struct *)ctx[1];
+
+ bpf_task_release(task);
+
+ return subprog_release(ctx);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_ref_acquire = {
+ .test_refcounted = (void *)refcounted_fail__global_subprog,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c
new file mode 100644
index 000000000000..e945b1a04294
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c
@@ -0,0 +1,22 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Test that the verifier rejects a program that acquires a referenced
+ * kptr through context without releasing the reference
+ */
+SEC("struct_ops/test_refcounted")
+__failure __msg("Unreleased reference id=1 alloc_insn=0")
+int BPF_PROG(refcounted_fail__ref_leak, int dummy,
+ struct task_struct *task)
+{
+ return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_ref_acquire = {
+ .test_refcounted = (void *)refcounted_fail__ref_leak,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c
new file mode 100644
index 000000000000..3b125025a1f2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} prog_array SEC(".maps");
+
+/* Test that the verifier rejects a program with referenced kptr arguments
+ * that tail call
+ */
+SEC("struct_ops/test_refcounted")
+__failure __msg("program with __ref argument cannot tail call")
+int refcounted_fail__tail_call(unsigned long long *ctx)
+{
+ struct task_struct *task = (struct task_struct *)ctx[1];
+
+ bpf_task_release(task);
+ bpf_tail_call(ctx, &prog_array, 0);
+
+ return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_ref_acquire = {
+ .test_refcounted = (void *)refcounted_fail__tail_call,
+};
+
diff --git a/tools/testing/selftests/bpf/progs/summarization.c b/tools/testing/selftests/bpf/progs/summarization.c
new file mode 100644
index 000000000000..f89effe82c9e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/summarization.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.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_changes_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;
+}
+
+__noinline
+long might_sleep(struct pt_regs *ctx __arg_ctx)
+{
+ int i;
+
+ bpf_copy_from_user(&i, sizeof(i), NULL);
+ return i;
+}
+
+__noinline __weak
+long does_not_sleep(struct pt_regs *ctx __arg_ctx)
+{
+ return 0;
+}
+
+SEC("?uprobe.s")
+int main_might_sleep_with_subprogs(struct pt_regs *ctx)
+{
+ might_sleep(ctx);
+ does_not_sleep(ctx);
+ return 0;
+}
+
+SEC("?uprobe.s")
+int main_might_sleep(struct pt_regs *ctx)
+{
+ int i;
+
+ bpf_copy_from_user(&i, sizeof(i), NULL);
+ return i;
+}
+
+SEC("?uprobe.s")
+int main_does_not_sleep(struct pt_regs *ctx)
+{
+ 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/summarization_freplace.c
index f9a622705f1b..935f00e0e9ea 100644
--- a/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c
+++ b/tools/testing/selftests/bpf/progs/summarization_freplace.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include <vmlinux.h>
#include <bpf/bpf_helpers.h>
SEC("?freplace")
@@ -15,4 +15,19 @@ long does_not_change_pkt_data(struct __sk_buff *sk)
return 0;
}
+SEC("?freplace")
+long might_sleep(struct pt_regs *ctx)
+{
+ int i;
+
+ bpf_copy_from_user(&i, sizeof(i), NULL);
+ return i;
+}
+
+SEC("?freplace")
+long does_not_sleep(struct pt_regs *ctx)
+{
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
index 44628865fe1d..4fee0fdc7607 100644
--- a/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
+++ b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
@@ -51,13 +51,13 @@ out:
}
SEC("lsm/bpf")
-int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
{
return bpf_link_create_verify(cmd);
}
SEC("lsm.s/bpf")
-int BPF_PROG(lsm_s_run, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(lsm_s_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
{
return bpf_link_create_verify(cmd);
}
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
index 51b3f79df523..448403634eea 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
@@ -15,6 +15,7 @@ struct {
struct core_reloc_arrays_output {
int a2;
+ int a3;
char b123;
int c1c;
int d00d;
@@ -41,6 +42,7 @@ int test_core_arrays(void *ctx)
{
struct core_reloc_arrays *in = (void *)&data.in;
struct core_reloc_arrays_output *out = (void *)&data.out;
+ int *a;
if (CORE_READ(&out->a2, &in->a[2]))
return 1;
@@ -53,6 +55,9 @@ int test_core_arrays(void *ctx)
if (CORE_READ(&out->f01c, &in->f[0][1].c))
return 1;
+ a = __builtin_preserve_access_index(({ in->a; }));
+ out->a3 = a[0] + a[1] + a[2] + a[3];
+
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/test_get_xattr.c b/tools/testing/selftests/bpf/progs/test_get_xattr.c
index 66e737720f7c..54305f4c9f2d 100644
--- a/tools/testing/selftests/bpf/progs/test_get_xattr.c
+++ b/tools/testing/selftests/bpf/progs/test_get_xattr.c
@@ -6,6 +6,7 @@
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
char _license[] SEC("license") = "GPL";
@@ -17,12 +18,23 @@ static const char expected_value[] = "hello";
char value1[32];
char value2[32];
+/* Matches caller of test_get_xattr() in prog_tests/fs_kfuncs.c */
+static const char xattr_names[][64] = {
+ /* The following work. */
+ "user.kfuncs",
+ "security.bpf.xxx",
+
+ /* The following do not work. */
+ "security.bpf",
+ "security.selinux"
+};
+
SEC("lsm.s/file_open")
int BPF_PROG(test_file_open, struct file *f)
{
struct bpf_dynptr value_ptr;
__u32 pid;
- int ret;
+ int ret, i;
pid = bpf_get_current_pid_tgid() >> 32;
if (pid != monitored_pid)
@@ -30,7 +42,11 @@ int BPF_PROG(test_file_open, struct file *f)
bpf_dynptr_from_mem(value1, sizeof(value1), 0, &value_ptr);
- ret = bpf_get_file_xattr(f, "user.kfuncs", &value_ptr);
+ for (i = 0; i < ARRAY_SIZE(xattr_names); i++) {
+ ret = bpf_get_file_xattr(f, xattr_names[i], &value_ptr);
+ if (ret == sizeof(expected_value))
+ break;
+ }
if (ret != sizeof(expected_value))
return 0;
if (bpf_strncmp(value1, ret, expected_value))
@@ -44,7 +60,7 @@ int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name)
{
struct bpf_dynptr value_ptr;
__u32 pid;
- int ret;
+ int ret, i;
pid = bpf_get_current_pid_tgid() >> 32;
if (pid != monitored_pid)
@@ -52,7 +68,11 @@ int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name)
bpf_dynptr_from_mem(value2, sizeof(value2), 0, &value_ptr);
- ret = bpf_get_dentry_xattr(dentry, "user.kfuncs", &value_ptr);
+ for (i = 0; i < ARRAY_SIZE(xattr_names); i++) {
+ ret = bpf_get_dentry_xattr(dentry, xattr_names[i], &value_ptr);
+ if (ret == sizeof(expected_value))
+ break;
+ }
if (ret != sizeof(expected_value))
return 0;
if (bpf_strncmp(value2, ret, expected_value))
diff --git a/tools/testing/selftests/bpf/progs/test_kernel_flag.c b/tools/testing/selftests/bpf/progs/test_kernel_flag.c
new file mode 100644
index 000000000000..b45fab3be352
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_kernel_flag.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2025 Microsoft Corporation
+ *
+ * Author: Blaise Boscaccy <bboscaccy@linux.microsoft.com>
+ */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u32 monitored_tid;
+
+SEC("lsm.s/bpf")
+int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
+{
+ __u32 tid;
+
+ tid = bpf_get_current_pid_tgid() & 0xFFFFFFFF;
+ if (!kernel || tid != monitored_tid)
+ return 0;
+ else
+ return -EINVAL;
+}
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 cd4d752bd089..061befb004c2 100644
--- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
+++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
@@ -36,7 +36,7 @@ char _license[] SEC("license") = "GPL";
SEC("?lsm.s/bpf")
__failure __msg("cannot pass in dynptr at an offset=-8")
-int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
{
unsigned long val;
@@ -46,7 +46,7 @@ int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size)
SEC("?lsm.s/bpf")
__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)
+int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
{
unsigned long val = 0;
@@ -55,7 +55,7 @@ int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size)
}
SEC("lsm.s/bpf")
-int BPF_PROG(dynptr_data_null, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(dynptr_data_null, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
{
struct bpf_key *trusted_keyring;
struct bpf_dynptr ptr;
diff --git a/tools/testing/selftests/bpf/progs/test_lookup_key.c b/tools/testing/selftests/bpf/progs/test_lookup_key.c
index c73776990ae3..cdbbb12f1491 100644
--- a/tools/testing/selftests/bpf/progs/test_lookup_key.c
+++ b/tools/testing/selftests/bpf/progs/test_lookup_key.c
@@ -23,7 +23,7 @@ extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
extern void bpf_key_put(struct bpf_key *key) __ksym;
SEC("lsm.s/bpf")
-int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
{
struct bpf_key *bkey;
__u32 pid;
diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c
index fb07f5773888..7f3c233943b3 100644
--- a/tools/testing/selftests/bpf/progs/test_module_attach.c
+++ b/tools/testing/selftests/bpf/progs/test_module_attach.c
@@ -117,7 +117,7 @@ int BPF_PROG(handle_fexit_ret, int arg, struct file *ret)
bpf_probe_read_kernel(&buf, 8, ret);
bpf_probe_read_kernel(&buf, 8, (char *)ret + 256);
- *(volatile long long *)ret;
+ *(volatile int *)ret;
*(volatile int *)&ret->f_mode;
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
index 2fdc44e76624..89b0cd5a3e06 100644
--- a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
+++ b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
@@ -7,7 +7,7 @@
char tp_name[128];
SEC("lsm.s/bpf")
-int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
{
switch (cmd) {
case BPF_RAW_TRACEPOINT_OPEN:
diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
index 5eb25c6ad75b..a5be3267dbb0 100644
--- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
@@ -1,7 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2018 Facebook */
-#include <stdlib.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
diff --git a/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c b/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c
new file mode 100644
index 000000000000..6a612cf168d3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u32 monitored_pid;
+
+const char xattr_foo[] = "security.bpf.foo";
+const char xattr_bar[] = "security.bpf.bar";
+static const char xattr_selinux[] = "security.selinux";
+char value_bar[] = "world";
+char read_value[32];
+
+bool set_security_bpf_bar_success;
+bool remove_security_bpf_bar_success;
+bool set_security_selinux_fail;
+bool remove_security_selinux_fail;
+
+char name_buf[32];
+
+static inline bool name_match_foo(const char *name)
+{
+ bpf_probe_read_kernel(name_buf, sizeof(name_buf), name);
+
+ return !bpf_strncmp(name_buf, sizeof(xattr_foo), xattr_foo);
+}
+
+/* Test bpf_set_dentry_xattr and bpf_remove_dentry_xattr */
+SEC("lsm.s/inode_getxattr")
+int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name)
+{
+ struct bpf_dynptr value_ptr;
+ __u32 pid;
+ int ret;
+
+ pid = bpf_get_current_pid_tgid() >> 32;
+ if (pid != monitored_pid)
+ return 0;
+
+ /* Only do the following for security.bpf.foo */
+ if (!name_match_foo(name))
+ return 0;
+
+ bpf_dynptr_from_mem(read_value, sizeof(read_value), 0, &value_ptr);
+
+ /* read security.bpf.bar */
+ ret = bpf_get_dentry_xattr(dentry, xattr_bar, &value_ptr);
+
+ if (ret < 0) {
+ /* If security.bpf.bar doesn't exist, set it */
+ bpf_dynptr_from_mem(value_bar, sizeof(value_bar), 0, &value_ptr);
+
+ ret = bpf_set_dentry_xattr(dentry, xattr_bar, &value_ptr, 0);
+ if (!ret)
+ set_security_bpf_bar_success = true;
+ ret = bpf_set_dentry_xattr(dentry, xattr_selinux, &value_ptr, 0);
+ if (ret)
+ set_security_selinux_fail = true;
+ } else {
+ /* If security.bpf.bar exists, remove it */
+ ret = bpf_remove_dentry_xattr(dentry, xattr_bar);
+ if (!ret)
+ remove_security_bpf_bar_success = true;
+
+ ret = bpf_remove_dentry_xattr(dentry, xattr_selinux);
+ if (ret)
+ remove_security_selinux_fail = true;
+ }
+
+ return 0;
+}
+
+bool locked_set_security_bpf_bar_success;
+bool locked_remove_security_bpf_bar_success;
+bool locked_set_security_selinux_fail;
+bool locked_remove_security_selinux_fail;
+
+/* Test bpf_set_dentry_xattr_locked and bpf_remove_dentry_xattr_locked.
+ * It not necessary to differentiate the _locked version and the
+ * not-_locked version in the BPF program. The verifier will fix them up
+ * properly.
+ */
+SEC("lsm.s/inode_setxattr")
+int BPF_PROG(test_inode_setxattr, struct mnt_idmap *idmap,
+ struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ struct bpf_dynptr value_ptr;
+ __u32 pid;
+ int ret;
+
+ pid = bpf_get_current_pid_tgid() >> 32;
+ if (pid != monitored_pid)
+ return 0;
+
+ /* Only do the following for security.bpf.foo */
+ if (!name_match_foo(name))
+ return 0;
+
+ bpf_dynptr_from_mem(read_value, sizeof(read_value), 0, &value_ptr);
+
+ /* read security.bpf.bar */
+ ret = bpf_get_dentry_xattr(dentry, xattr_bar, &value_ptr);
+
+ if (ret < 0) {
+ /* If security.bpf.bar doesn't exist, set it */
+ bpf_dynptr_from_mem(value_bar, sizeof(value_bar), 0, &value_ptr);
+
+ ret = bpf_set_dentry_xattr(dentry, xattr_bar, &value_ptr, 0);
+ if (!ret)
+ locked_set_security_bpf_bar_success = true;
+ ret = bpf_set_dentry_xattr(dentry, xattr_selinux, &value_ptr, 0);
+ if (ret)
+ locked_set_security_selinux_fail = true;
+ } else {
+ /* If security.bpf.bar exists, remove it */
+ ret = bpf_remove_dentry_xattr(dentry, xattr_bar);
+ if (!ret)
+ locked_remove_security_bpf_bar_success = true;
+
+ ret = bpf_remove_dentry_xattr(dentry, xattr_selinux);
+ if (ret)
+ locked_remove_security_selinux_fail = true;
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
index 1c8b678e2e9a..f678ee6bd7ea 100644
--- a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
@@ -245,4 +245,73 @@ int lock_global_subprog_call2(struct __sk_buff *ctx)
return ret;
}
+int __noinline
+global_subprog_int(int i)
+{
+ if (i)
+ bpf_printk("%p", &i);
+ return i;
+}
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+ if (i)
+ bpf_copy_from_user(&i, sizeof(i), NULL);
+ return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+ if (i)
+ bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+ global_subprog_int(i);
+ return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+ if (!i)
+ global_sleepable_kfunc_subprog(i);
+ return i;
+}
+
+SEC("?syscall")
+int lock_global_sleepable_helper_subprog(struct __sk_buff *ctx)
+{
+ int ret = 0;
+
+ bpf_spin_lock(&lockA);
+ if (ctx->mark == 42)
+ ret = global_sleepable_helper_subprog(ctx->mark);
+ bpf_spin_unlock(&lockA);
+ return ret;
+}
+
+SEC("?syscall")
+int lock_global_sleepable_kfunc_subprog(struct __sk_buff *ctx)
+{
+ int ret = 0;
+
+ bpf_spin_lock(&lockA);
+ if (ctx->mark == 42)
+ ret = global_sleepable_kfunc_subprog(ctx->mark);
+ bpf_spin_unlock(&lockA);
+ return ret;
+}
+
+SEC("?syscall")
+int lock_global_sleepable_subprog_indirect(struct __sk_buff *ctx)
+{
+ int ret = 0;
+
+ bpf_spin_lock(&lockA);
+ if (ctx->mark == 42)
+ ret = global_subprog_calling_sleepable_global(ctx->mark);
+ bpf_spin_unlock(&lockA);
+ return ret;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_extable.c b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c
index e2a21fbd4e44..dcac69f5928a 100644
--- a/tools/testing/selftests/bpf/progs/test_subprogs_extable.c
+++ b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c
@@ -21,7 +21,7 @@ static __u64 test_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data)
SEC("fexit/bpf_testmod_return_ptr")
int BPF_PROG(handle_fexit_ret_subprogs, int arg, struct file *ret)
{
- *(volatile long *)ret;
+ *(volatile int *)ret;
*(volatile int *)&ret->f_mode;
bpf_for_each_map_elem(&test_array, test_cb, NULL, 0);
triggered++;
@@ -31,7 +31,7 @@ int BPF_PROG(handle_fexit_ret_subprogs, int arg, struct file *ret)
SEC("fexit/bpf_testmod_return_ptr")
int BPF_PROG(handle_fexit_ret_subprogs2, int arg, struct file *ret)
{
- *(volatile long *)ret;
+ *(volatile int *)ret;
*(volatile int *)&ret->f_mode;
bpf_for_each_map_elem(&test_array, test_cb, NULL, 0);
triggered++;
@@ -41,7 +41,7 @@ int BPF_PROG(handle_fexit_ret_subprogs2, int arg, struct file *ret)
SEC("fexit/bpf_testmod_return_ptr")
int BPF_PROG(handle_fexit_ret_subprogs3, int arg, struct file *ret)
{
- *(volatile long *)ret;
+ *(volatile int *)ret;
*(volatile int *)&ret->f_mode;
bpf_for_each_map_elem(&test_array, test_cb, NULL, 0);
triggered++;
diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
index 7e750309ce27..0b74b8bd22e8 100644
--- a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
@@ -49,7 +49,7 @@ out:
}
SEC("lsm.s/bpf")
-int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
{
struct cgroup *cgrp = NULL;
struct task_struct *task;
diff --git a/tools/testing/selftests/bpf/progs/test_usdt.c b/tools/testing/selftests/bpf/progs/test_usdt.c
index 505aab9a5234..096488f47fbc 100644
--- a/tools/testing/selftests/bpf/progs/test_usdt.c
+++ b/tools/testing/selftests/bpf/progs/test_usdt.c
@@ -11,6 +11,7 @@ int usdt0_called;
u64 usdt0_cookie;
int usdt0_arg_cnt;
int usdt0_arg_ret;
+int usdt0_arg_size;
SEC("usdt")
int usdt0(struct pt_regs *ctx)
@@ -26,6 +27,7 @@ int usdt0(struct pt_regs *ctx)
usdt0_arg_cnt = bpf_usdt_arg_cnt(ctx);
/* should return -ENOENT for any arg_num */
usdt0_arg_ret = bpf_usdt_arg(ctx, bpf_get_prandom_u32(), &tmp);
+ usdt0_arg_size = bpf_usdt_arg_size(ctx, bpf_get_prandom_u32());
return 0;
}
@@ -34,6 +36,7 @@ u64 usdt3_cookie;
int usdt3_arg_cnt;
int usdt3_arg_rets[3];
u64 usdt3_args[3];
+int usdt3_arg_sizes[3];
SEC("usdt//proc/self/exe:test:usdt3")
int usdt3(struct pt_regs *ctx)
@@ -50,12 +53,15 @@ int usdt3(struct pt_regs *ctx)
usdt3_arg_rets[0] = bpf_usdt_arg(ctx, 0, &tmp);
usdt3_args[0] = (int)tmp;
+ usdt3_arg_sizes[0] = bpf_usdt_arg_size(ctx, 0);
usdt3_arg_rets[1] = bpf_usdt_arg(ctx, 1, &tmp);
usdt3_args[1] = (long)tmp;
+ usdt3_arg_sizes[1] = bpf_usdt_arg_size(ctx, 1);
usdt3_arg_rets[2] = bpf_usdt_arg(ctx, 2, &tmp);
usdt3_args[2] = (uintptr_t)tmp;
+ usdt3_arg_sizes[2] = bpf_usdt_arg_size(ctx, 2);
return 0;
}
@@ -64,12 +70,15 @@ int usdt12_called;
u64 usdt12_cookie;
int usdt12_arg_cnt;
u64 usdt12_args[12];
+int usdt12_arg_sizes[12];
SEC("usdt//proc/self/exe:test:usdt12")
int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5,
long a6, __u64 a7, uintptr_t a8, int a9, short a10,
short a11, signed char a12)
{
+ int i;
+
if (my_pid != (bpf_get_current_pid_tgid() >> 32))
return 0;
@@ -90,6 +99,11 @@ int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5,
usdt12_args[9] = a10;
usdt12_args[10] = a11;
usdt12_args[11] = a12;
+
+ bpf_for(i, 0, 12) {
+ usdt12_arg_sizes[i] = bpf_usdt_arg_size(ctx, i);
+ }
+
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
index 12034a73ee2d..e96d09e11115 100644
--- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
@@ -37,7 +37,7 @@ struct {
char _license[] SEC("license") = "GPL";
SEC("lsm.s/bpf")
-int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
{
struct bpf_dynptr data_ptr, sig_ptr;
struct data *data_val;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
index a7588302268d..a80cc5f2f4f2 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
@@ -102,8 +102,8 @@ bool parse_eth_frame(struct ethhdr *eth, void *data_end, struct parse_pkt *pkt)
#define TESTVLAN 4011 /* 0xFAB */
// #define TO_VLAN 4000 /* 0xFA0 (hint 0xOA0 = 160) */
-SEC("xdp_drop_vlan_4011")
-int xdp_prognum0(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_drop_vlan_4011(struct xdp_md *ctx)
{
void *data_end = (void *)(long)ctx->data_end;
void *data = (void *)(long)ctx->data;
@@ -144,8 +144,8 @@ Load prog with ip tool:
/* Changing VLAN to zero, have same practical effect as removing the VLAN. */
#define TO_VLAN 0
-SEC("xdp_vlan_change")
-int xdp_prognum1(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_vlan_change(struct xdp_md *ctx)
{
void *data_end = (void *)(long)ctx->data_end;
void *data = (void *)(long)ctx->data;
@@ -178,8 +178,8 @@ int xdp_prognum1(struct xdp_md *ctx)
#endif
#define VLAN_HDR_SZ 4 /* bytes */
-SEC("xdp_vlan_remove_outer")
-int xdp_prognum2(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_vlan_remove_outer(struct xdp_md *ctx)
{
void *data_end = (void *)(long)ctx->data_end;
void *data = (void *)(long)ctx->data;
@@ -224,8 +224,8 @@ void shift_mac_4bytes_32bit(void *data)
p[1] = p[0];
}
-SEC("xdp_vlan_remove_outer2")
-int xdp_prognum3(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_vlan_remove_outer2(struct xdp_md *ctx)
{
void *data_end = (void *)(long)ctx->data_end;
void *data = (void *)(long)ctx->data;
@@ -254,8 +254,8 @@ int xdp_prognum3(struct xdp_md *ctx)
* The TC-clsact eBPF programs (currently) need to be attach via TC commands
*/
-SEC("tc_vlan_push")
-int _tc_progA(struct __sk_buff *ctx)
+SEC("tc")
+int tc_vlan_push(struct __sk_buff *ctx)
{
bpf_skb_vlan_push(ctx, bpf_htons(ETH_P_8021Q), TESTVLAN);
diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
index 5094c288cfd7..c258b0722e04 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
@@ -12,7 +12,7 @@ SEC("raw_tp")
__arch_x86_64
__log_level(4) __msg("stack depth 8")
__xlated("4: r5 = 5")
-__xlated("5: w0 = ")
+__xlated("5: r0 = ")
__xlated("6: r0 = &(void __percpu *)(r0)")
__xlated("7: r0 = *(u32 *)(r0 +0)")
__xlated("8: exit")
@@ -620,23 +620,61 @@ __naked void helper_call_does_not_prevent_bpf_fastcall(void)
SEC("raw_tp")
__arch_x86_64
+__log_level(4) __msg("stack depth 24")
+/* may_goto counter at -24 */
+__xlated("0: *(u64 *)(r10 -24) =")
+/* may_goto timestamp at -16 */
+__xlated("1: *(u64 *)(r10 -16) =")
+__xlated("2: r1 = 1")
+__xlated("...")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+/* may_goto expansion starts */
+__xlated("6: r11 = *(u64 *)(r10 -24)")
+__xlated("7: if r11 == 0x0 goto pc+6")
+__xlated("8: r11 -= 1")
+__xlated("9: if r11 != 0x0 goto pc+2")
+__xlated("10: r11 = -24")
+__xlated("11: call unknown")
+__xlated("12: *(u64 *)(r10 -24) = r11")
+/* may_goto expansion ends */
+__xlated("13: *(u64 *)(r10 -8) = r1")
+__xlated("14: exit")
+__success
+__naked void may_goto_interaction_x86_64(void)
+{
+ asm volatile (
+ "r1 = 1;"
+ "*(u64 *)(r10 - 16) = r1;"
+ "call %[bpf_get_smp_processor_id];"
+ "r1 = *(u64 *)(r10 - 16);"
+ ".8byte %[may_goto];"
+ /* just touch some stack at -8 */
+ "*(u64 *)(r10 - 8) = r1;"
+ "exit;"
+ :
+ : __imm(bpf_get_smp_processor_id),
+ __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, +1 /* offset */, 0))
+ : __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_arm64
__log_level(4) __msg("stack depth 16")
/* may_goto counter at -16 */
__xlated("0: *(u64 *)(r10 -16) =")
__xlated("1: r1 = 1")
-__xlated("...")
-__xlated("3: r0 = &(void __percpu *)(r0)")
-__xlated("...")
+__xlated("2: call bpf_get_smp_processor_id")
/* may_goto expansion starts */
-__xlated("5: r11 = *(u64 *)(r10 -16)")
-__xlated("6: if r11 == 0x0 goto pc+3")
-__xlated("7: r11 -= 1")
-__xlated("8: *(u64 *)(r10 -16) = r11")
+__xlated("3: r11 = *(u64 *)(r10 -16)")
+__xlated("4: if r11 == 0x0 goto pc+3")
+__xlated("5: r11 -= 1")
+__xlated("6: *(u64 *)(r10 -16) = r11")
/* may_goto expansion ends */
-__xlated("9: *(u64 *)(r10 -8) = r1")
-__xlated("10: exit")
+__xlated("7: *(u64 *)(r10 -8) = r1")
+__xlated("8: exit")
__success
-__naked void may_goto_interaction(void)
+__naked void may_goto_interaction_arm64(void)
{
asm volatile (
"r1 = 1;"
@@ -666,7 +704,7 @@ SEC("raw_tp")
__arch_x86_64
__log_level(4) __msg("stack depth 32+0")
__xlated("2: r1 = 1")
-__xlated("3: w0 =")
+__xlated("3: r0 =")
__xlated("4: r0 = &(void __percpu *)(r0)")
__xlated("5: r0 = *(u32 *)(r0 +0)")
/* bpf_loop params setup */
@@ -715,7 +753,7 @@ __arch_x86_64
__log_level(4) __msg("stack depth 40+0")
/* call bpf_get_smp_processor_id */
__xlated("2: r1 = 42")
-__xlated("3: w0 =")
+__xlated("3: r0 =")
__xlated("4: r0 = &(void __percpu *)(r0)")
__xlated("5: r0 = *(u32 *)(r0 +0)")
/* call bpf_get_prandom_u32 */
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index 05a329ee45ee..d5d8f24df394 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -4,11 +4,7 @@
#include <bpf/bpf_helpers.h>
#include "bpf_misc.h"
-#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
- (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
- defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
- defined(__TARGET_ARCH_loongarch)) && \
- __clang_major__ >= 18
+#ifdef CAN_USE_GOTOL
SEC("socket")
__description("gotol, small_imm")
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
index e54bb5385bc1..75dd922e4e9f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -407,11 +407,7 @@ l0_%=: call %[bpf_jiffies64]; \
: __clobber_all);
}
-#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
- (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
- defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
- defined(__TARGET_ARCH_loongarch)) && \
- __clang_major__ >= 18
+#ifdef CAN_USE_GOTOL
SEC("socket")
__success __retval(0)
__naked void gotol_and_may_goto(void)
diff --git a/tools/testing/selftests/bpf/progs/verifier_load_acquire.c b/tools/testing/selftests/bpf/progs/verifier_load_acquire.c
new file mode 100644
index 000000000000..77698d5a19e4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_load_acquire.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Google LLC. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
+
+SEC("socket")
+__description("load-acquire, 8-bit")
+__success __success_unpriv __retval(0x12)
+__naked void load_acquire_8(void)
+{
+ asm volatile (
+ "w1 = 0x12;"
+ "*(u8 *)(r10 - 1) = w1;"
+ ".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r10 - 1));
+ "exit;"
+ :
+ : __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -1))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire, 16-bit")
+__success __success_unpriv __retval(0x1234)
+__naked void load_acquire_16(void)
+{
+ asm volatile (
+ "w1 = 0x1234;"
+ "*(u16 *)(r10 - 2) = w1;"
+ ".8byte %[load_acquire_insn];" // w0 = load_acquire((u16 *)(r10 - 2));
+ "exit;"
+ :
+ : __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_H, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -2))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire, 32-bit")
+__success __success_unpriv __retval(0x12345678)
+__naked void load_acquire_32(void)
+{
+ asm volatile (
+ "w1 = 0x12345678;"
+ "*(u32 *)(r10 - 4) = w1;"
+ ".8byte %[load_acquire_insn];" // w0 = load_acquire((u32 *)(r10 - 4));
+ "exit;"
+ :
+ : __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -4))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire, 64-bit")
+__success __success_unpriv __retval(0x1234567890abcdef)
+__naked void load_acquire_64(void)
+{
+ asm volatile (
+ "r1 = 0x1234567890abcdef ll;"
+ "*(u64 *)(r10 - 8) = r1;"
+ ".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r10 - 8));
+ "exit;"
+ :
+ : __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -8))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire with uninitialized src_reg")
+__failure __failure_unpriv __msg("R2 !read_ok")
+__naked void load_acquire_with_uninitialized_src_reg(void)
+{
+ asm volatile (
+ ".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r2 + 0));
+ "exit;"
+ :
+ : __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire with non-pointer src_reg")
+__failure __failure_unpriv __msg("R1 invalid mem access 'scalar'")
+__naked void load_acquire_with_non_pointer_src_reg(void)
+{
+ asm volatile (
+ "r1 = 0;"
+ ".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r1 + 0));
+ "exit;"
+ :
+ : __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_1, 0))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("misaligned load-acquire")
+__failure __failure_unpriv __msg("misaligned stack access off")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void load_acquire_misaligned(void)
+{
+ asm volatile (
+ "r1 = 0;"
+ "*(u64 *)(r10 - 8) = r1;"
+ ".8byte %[load_acquire_insn];" // w0 = load_acquire((u32 *)(r10 - 5));
+ "exit;"
+ :
+ : __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -5))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire from ctx pointer")
+__failure __failure_unpriv __msg("BPF_ATOMIC loads from R1 ctx is not allowed")
+__naked void load_acquire_from_ctx_pointer(void)
+{
+ asm volatile (
+ ".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r1 + 0));
+ "exit;"
+ :
+ : __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_1, 0))
+ : __clobber_all);
+}
+
+SEC("xdp")
+__description("load-acquire from pkt pointer")
+__failure __msg("BPF_ATOMIC loads from R2 pkt is not allowed")
+__naked void load_acquire_from_pkt_pointer(void)
+{
+ asm volatile (
+ "r2 = *(u32 *)(r1 + %[xdp_md_data]);"
+ "r3 = *(u32 *)(r1 + %[xdp_md_data_end]);"
+ "r1 = r2;"
+ "r1 += 8;"
+ "if r1 >= r3 goto l0_%=;"
+ ".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r2 + 0));
+"l0_%=: r0 = 0;"
+ "exit;"
+ :
+ : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+ __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+ __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0))
+ : __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("load-acquire from flow_keys pointer")
+__failure __msg("BPF_ATOMIC loads from R2 flow_keys is not allowed")
+__naked void load_acquire_from_flow_keys_pointer(void)
+{
+ asm volatile (
+ "r2 = *(u64 *)(r1 + %[__sk_buff_flow_keys]);"
+ ".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r2 + 0));
+ "exit;"
+ :
+ : __imm_const(__sk_buff_flow_keys,
+ offsetof(struct __sk_buff, flow_keys)),
+ __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0))
+ : __clobber_all);
+}
+
+SEC("sk_reuseport")
+__description("load-acquire from sock pointer")
+__failure __msg("BPF_ATOMIC loads from R2 sock is not allowed")
+__naked void load_acquire_from_sock_pointer(void)
+{
+ asm volatile (
+ "r2 = *(u64 *)(r1 + %[sk_reuseport_md_sk]);"
+ // w0 = load_acquire((u8 *)(r2 + offsetof(struct bpf_sock, family)));
+ ".8byte %[load_acquire_insn];"
+ "exit;"
+ :
+ : __imm_const(sk_reuseport_md_sk, offsetof(struct sk_reuseport_md, sk)),
+ __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2,
+ offsetof(struct bpf_sock, family)))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire with invalid register R15")
+__failure __failure_unpriv __msg("R15 is invalid")
+__naked void load_acquire_with_invalid_reg(void)
+{
+ asm volatile (
+ ".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r15 + 0));
+ "exit;"
+ :
+ : __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, 15 /* invalid reg */, 0))
+ : __clobber_all);
+}
+
+#else /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+SEC("socket")
+__description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support load-acquire, use a dummy test")
+__success
+int dummy_test(void)
+{
+ return 0;
+}
+
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
index e81097c96fe2..3966d827f288 100644
--- a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
+++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
@@ -69,8 +69,38 @@ __naked void may_goto_batch_1(void)
}
SEC("raw_tp")
-__description("may_goto batch with offsets 2/0")
+__description("may_goto batch with offsets 2/0 - x86_64")
__arch_x86_64
+__xlated("0: *(u64 *)(r10 -16) = 65535")
+__xlated("1: *(u64 *)(r10 -8) = 0")
+__xlated("2: r11 = *(u64 *)(r10 -16)")
+__xlated("3: if r11 == 0x0 goto pc+6")
+__xlated("4: r11 -= 1")
+__xlated("5: if r11 != 0x0 goto pc+2")
+__xlated("6: r11 = -16")
+__xlated("7: call unknown")
+__xlated("8: *(u64 *)(r10 -16) = r11")
+__xlated("9: r0 = 1")
+__xlated("10: r0 = 2")
+__xlated("11: exit")
+__success
+__naked void may_goto_batch_2_x86_64(void)
+{
+ asm volatile (
+ ".8byte %[may_goto1];"
+ ".8byte %[may_goto3];"
+ "r0 = 1;"
+ "r0 = 2;"
+ "exit;"
+ :
+ : __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)),
+ __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0))
+ : __clobber_all);
+}
+
+SEC("raw_tp")
+__description("may_goto batch with offsets 2/0 - arm64")
+__arch_arm64
__xlated("0: *(u64 *)(r10 -8) = 8388608")
__xlated("1: r11 = *(u64 *)(r10 -8)")
__xlated("2: if r11 == 0x0 goto pc+3")
@@ -80,7 +110,7 @@ __xlated("5: r0 = 1")
__xlated("6: r0 = 2")
__xlated("7: exit")
__success
-__naked void may_goto_batch_2(void)
+__naked void may_goto_batch_2_arm64(void)
{
asm volatile (
".8byte %[may_goto1];"
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
index 6b564d4c0986..6662d4b39969 100644
--- a/tools/testing/selftests/bpf/progs/verifier_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -2,6 +2,7 @@
/* Copyright (C) 2023 SUSE LLC */
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
#include "bpf_misc.h"
SEC("?raw_tp")
@@ -90,6 +91,54 @@ __naked int bpf_end_bswap(void)
::: __clobber_all);
}
+#if defined(ENABLE_ATOMICS_TESTS) && \
+ (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (db) r2 = load_acquire((u64 *)(r10 -8))")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_load_acquire(void)
+{
+ asm volatile (
+ "r1 = 8;"
+ "*(u64 *)(r10 - 8) = r1;"
+ ".8byte %[load_acquire_insn];" /* r2 = load_acquire((u64 *)(r10 - 8)); */
+ "r3 = r10;"
+ "r3 += r2;" /* mark_precise */
+ "r0 = 0;"
+ "exit;"
+ :
+ : __imm_insn(load_acquire_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -8))
+ : __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r2 = r10")
+__msg("mark_precise: frame0: regs=r1 stack= before 2: (79) r1 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (db) store_release((u64 *)(r10 -8), r1)")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_store_release(void)
+{
+ asm volatile (
+ "r1 = 8;"
+ ".8byte %[store_release_insn];" /* store_release((u64 *)(r10 - 8), r1); */
+ "r1 = *(u64 *)(r10 - 8);"
+ "r2 = r10;"
+ "r2 += r1;" /* mark_precise */
+ "r0 = 0;"
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8))
+ : __clobber_all);
+}
+
+#endif /* load-acquire, store-release */
#endif /* v4 instruction */
SEC("?raw_tp")
diff --git a/tools/testing/selftests/bpf/progs/verifier_private_stack.c b/tools/testing/selftests/bpf/progs/verifier_private_stack.c
index b1fbdf119553..fc91b414364e 100644
--- a/tools/testing/selftests/bpf/progs/verifier_private_stack.c
+++ b/tools/testing/selftests/bpf/progs/verifier_private_stack.c
@@ -27,7 +27,7 @@ __description("Private stack, single prog")
__success
__arch_x86_64
__jited(" movabsq $0x{{.*}}, %r9")
-__jited(" addq %gs:0x{{.*}}, %r9")
+__jited(" addq %gs:{{.*}}, %r9")
__jited(" movl $0x2a, %edi")
__jited(" movq %rdi, -0x100(%r9)")
__naked void private_stack_single_prog(void)
@@ -74,7 +74,7 @@ __success
__arch_x86_64
/* private stack fp for the main prog */
__jited(" movabsq $0x{{.*}}, %r9")
-__jited(" addq %gs:0x{{.*}}, %r9")
+__jited(" addq %gs:{{.*}}, %r9")
__jited(" movl $0x2a, %edi")
__jited(" movq %rdi, -0x200(%r9)")
__jited(" pushq %r9")
@@ -122,7 +122,7 @@ __jited(" pushq %rbp")
__jited(" movq %rsp, %rbp")
__jited(" endbr64")
__jited(" movabsq $0x{{.*}}, %r9")
-__jited(" addq %gs:0x{{.*}}, %r9")
+__jited(" addq %gs:{{.*}}, %r9")
__jited(" pushq %r9")
__jited(" callq")
__jited(" popq %r9")
diff --git a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
index 417c61cd4b19..24aabc6083fd 100644
--- a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
+++ b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
@@ -481,4 +481,56 @@ l1_%=: r0 = 42; \
: __clobber_all);
}
+SEC("socket")
+__description("PTR_TO_STACK stack size > 512")
+__failure __msg("invalid write to stack R1 off=-520 size=8")
+__naked void stack_check_size_gt_512(void)
+{
+ asm volatile (" \
+ r1 = r10; \
+ r1 += -520; \
+ r0 = 42; \
+ *(u64*)(r1 + 0) = r0; \
+ exit; \
+" ::: __clobber_all);
+}
+
+#ifdef __BPF_FEATURE_MAY_GOTO
+SEC("socket")
+__description("PTR_TO_STACK stack size 512 with may_goto with jit")
+__load_if_JITed()
+__success __retval(42)
+__naked void stack_check_size_512_with_may_goto_jit(void)
+{
+ asm volatile (" \
+ r1 = r10; \
+ r1 += -512; \
+ r0 = 42; \
+ *(u32*)(r1 + 0) = r0; \
+ may_goto l0_%=; \
+ r2 = 100; \
+ l0_%=: \
+ exit; \
+" ::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK stack size 512 with may_goto without jit")
+__load_if_no_JITed()
+__failure __msg("stack size 520(extra 8) is too large")
+__naked void stack_check_size_512_with_may_goto(void)
+{
+ asm volatile (" \
+ r1 = r10; \
+ r1 += -512; \
+ r0 = 42; \
+ *(u32*)(r1 + 0) = r0; \
+ may_goto l0_%=; \
+ r2 = 100; \
+ l0_%=: \
+ exit; \
+" ::: __clobber_all);
+}
+#endif
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_store_release.c b/tools/testing/selftests/bpf/progs/verifier_store_release.c
new file mode 100644
index 000000000000..c0442d5bb049
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_store_release.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Google LLC. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \
+ (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+
+SEC("socket")
+__description("store-release, 8-bit")
+__success __success_unpriv __retval(0x12)
+__naked void store_release_8(void)
+{
+ asm volatile (
+ "w1 = 0x12;"
+ ".8byte %[store_release_insn];" // store_release((u8 *)(r10 - 1), w1);
+ "w0 = *(u8 *)(r10 - 1);"
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -1))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, 16-bit")
+__success __success_unpriv __retval(0x1234)
+__naked void store_release_16(void)
+{
+ asm volatile (
+ "w1 = 0x1234;"
+ ".8byte %[store_release_insn];" // store_release((u16 *)(r10 - 2), w1);
+ "w0 = *(u16 *)(r10 - 2);"
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_H, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -2))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, 32-bit")
+__success __success_unpriv __retval(0x12345678)
+__naked void store_release_32(void)
+{
+ asm volatile (
+ "w1 = 0x12345678;"
+ ".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 4), w1);
+ "w0 = *(u32 *)(r10 - 4);"
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_W, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -4))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, 64-bit")
+__success __success_unpriv __retval(0x1234567890abcdef)
+__naked void store_release_64(void)
+{
+ asm volatile (
+ "r1 = 0x1234567890abcdef ll;"
+ ".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1);
+ "r0 = *(u64 *)(r10 - 8);"
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with uninitialized src_reg")
+__failure __failure_unpriv __msg("R2 !read_ok")
+__naked void store_release_with_uninitialized_src_reg(void)
+{
+ asm volatile (
+ ".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r2);
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_2, -8))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with uninitialized dst_reg")
+__failure __failure_unpriv __msg("R2 !read_ok")
+__naked void store_release_with_uninitialized_dst_reg(void)
+{
+ asm volatile (
+ "r1 = 0;"
+ ".8byte %[store_release_insn];" // store_release((u64 *)(r2 - 8), r1);
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_2, BPF_REG_1, -8))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with non-pointer dst_reg")
+__failure __failure_unpriv __msg("R1 invalid mem access 'scalar'")
+__naked void store_release_with_non_pointer_dst_reg(void)
+{
+ asm volatile (
+ "r1 = 0;"
+ ".8byte %[store_release_insn];" // store_release((u64 *)(r1 + 0), r1);
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_1, BPF_REG_1, 0))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("misaligned store-release")
+__failure __failure_unpriv __msg("misaligned stack access off")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void store_release_misaligned(void)
+{
+ asm volatile (
+ "w0 = 0;"
+ ".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 5), w0);
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_W, BPF_STORE_REL, BPF_REG_10, BPF_REG_0, -5))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("store-release to ctx pointer")
+__failure __failure_unpriv __msg("BPF_ATOMIC stores into R1 ctx is not allowed")
+__naked void store_release_to_ctx_pointer(void)
+{
+ asm volatile (
+ "w0 = 0;"
+ // store_release((u8 *)(r1 + offsetof(struct __sk_buff, cb[0])), w0);
+ ".8byte %[store_release_insn];"
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_1, BPF_REG_0,
+ offsetof(struct __sk_buff, cb[0])))
+ : __clobber_all);
+}
+
+SEC("xdp")
+__description("store-release to pkt pointer")
+__failure __msg("BPF_ATOMIC stores into R2 pkt is not allowed")
+__naked void store_release_to_pkt_pointer(void)
+{
+ asm volatile (
+ "w0 = 0;"
+ "r2 = *(u32 *)(r1 + %[xdp_md_data]);"
+ "r3 = *(u32 *)(r1 + %[xdp_md_data_end]);"
+ "r1 = r2;"
+ "r1 += 8;"
+ "if r1 >= r3 goto l0_%=;"
+ ".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0);
+"l0_%=: r0 = 0;"
+ "exit;"
+ :
+ : __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+ __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+ __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0))
+ : __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("store-release to flow_keys pointer")
+__failure __msg("BPF_ATOMIC stores into R2 flow_keys is not allowed")
+__naked void store_release_to_flow_keys_pointer(void)
+{
+ asm volatile (
+ "w0 = 0;"
+ "r2 = *(u64 *)(r1 + %[__sk_buff_flow_keys]);"
+ ".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0);
+ "exit;"
+ :
+ : __imm_const(__sk_buff_flow_keys,
+ offsetof(struct __sk_buff, flow_keys)),
+ __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0))
+ : __clobber_all);
+}
+
+SEC("sk_reuseport")
+__description("store-release to sock pointer")
+__failure __msg("R2 cannot write into sock")
+__naked void store_release_to_sock_pointer(void)
+{
+ asm volatile (
+ "w0 = 0;"
+ "r2 = *(u64 *)(r1 + %[sk_reuseport_md_sk]);"
+ ".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0);
+ "exit;"
+ :
+ : __imm_const(sk_reuseport_md_sk, offsetof(struct sk_reuseport_md, sk)),
+ __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, leak pointer to stack")
+__success __success_unpriv __retval(0)
+__naked void store_release_leak_pointer_to_stack(void)
+{
+ asm volatile (
+ ".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1);
+ "r0 = 0;"
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8))
+ : __clobber_all);
+}
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1);
+ __type(key, long long);
+ __type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("socket")
+__description("store-release, leak pointer to map")
+__success __retval(0)
+__failure_unpriv __msg_unpriv("R6 leaks addr into map")
+__naked void store_release_leak_pointer_to_map(void)
+{
+ asm volatile (
+ "r6 = r1;"
+ "r1 = %[map_hash_8b] ll;"
+ "r2 = 0;"
+ "*(u64 *)(r10 - 8) = r2;"
+ "r2 = r10;"
+ "r2 += -8;"
+ "call %[bpf_map_lookup_elem];"
+ "if r0 == 0 goto l0_%=;"
+ ".8byte %[store_release_insn];" // store_release((u64 *)(r0 + 0), r6);
+"l0_%=:"
+ "r0 = 0;"
+ "exit;"
+ :
+ : __imm_addr(map_hash_8b),
+ __imm(bpf_map_lookup_elem),
+ __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_0, BPF_REG_6, 0))
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with invalid register R15")
+__failure __failure_unpriv __msg("R15 is invalid")
+__naked void store_release_with_invalid_reg(void)
+{
+ asm volatile (
+ ".8byte %[store_release_insn];" // store_release((u64 *)(r15 + 0), r1);
+ "exit;"
+ :
+ : __imm_insn(store_release_insn,
+ BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, 15 /* invalid reg */, BPF_REG_1, 0))
+ : __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support store-release, use a dummy test")
+__success
+int dummy_test(void)
+{
+ return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
index 682dda8dabbc..50c8958f94e5 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
@@ -1,7 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/if_ether.h>
+
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
struct {
__uint(type, BPF_MAP_TYPE_DEVMAP);
@@ -28,4 +31,89 @@ int xdp_redirect_map_2(struct xdp_md *xdp)
return bpf_redirect_map(&tx_port, 2, 0);
}
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 3);
+ __type(key, __u32);
+ __type(value, __u64);
+} rxcnt SEC(".maps");
+
+static int xdp_count(struct xdp_md *xdp, __u32 key)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ struct ethhdr *eth = data;
+ __u64 *count;
+
+ if (data + sizeof(*eth) > data_end)
+ return XDP_DROP;
+
+ if (bpf_htons(eth->h_proto) == ETH_P_IP) {
+ /* We only count IPv4 packets */
+ count = bpf_map_lookup_elem(&rxcnt, &key);
+ if (count)
+ *count += 1;
+ }
+
+ return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_count_0(struct xdp_md *xdp)
+{
+ return xdp_count(xdp, 0);
+}
+
+SEC("xdp")
+int xdp_count_1(struct xdp_md *xdp)
+{
+ return xdp_count(xdp, 1);
+}
+
+SEC("xdp")
+int xdp_count_2(struct xdp_md *xdp)
+{
+ return xdp_count(xdp, 2);
+}
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 2);
+ __type(key, __u32);
+ __type(value, __be64);
+} rx_mac SEC(".maps");
+
+static int store_mac(struct xdp_md *xdp, __u32 id)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ struct ethhdr *eth = data;
+ __u32 key = id;
+ __be64 mac = 0;
+
+ if (data + sizeof(*eth) > data_end)
+ return XDP_DROP;
+
+ /* Only store IPv4 MAC to avoid being polluted by IPv6 packets */
+ if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+ __builtin_memcpy(&mac, eth->h_source, ETH_ALEN);
+ bpf_map_update_elem(&rx_mac, &key, &mac, 0);
+ bpf_printk("%s - %x", __func__, mac);
+ }
+
+ return XDP_PASS;
+}
+
+SEC("xdp")
+int store_mac_1(struct xdp_md *xdp)
+{
+ return store_mac(xdp, 0);
+}
+
+SEC("xdp")
+int store_mac_2(struct xdp_md *xdp)
+{
+ return store_mac(xdp, 1);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
index 97b26a30b59a..bc2945ed8a80 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
@@ -34,6 +34,14 @@ struct {
__uint(max_entries, 128);
} mac_map SEC(".maps");
+/* map to store redirect flags for each protocol*/
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, __u16);
+ __type(value, __u64);
+ __uint(max_entries, 16);
+} redirect_flags SEC(".maps");
+
SEC("xdp")
int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
{
@@ -41,25 +49,34 @@ int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
void *data = (void *)(long)ctx->data;
int if_index = ctx->ingress_ifindex;
struct ethhdr *eth = data;
+ __u64 *flags_from_map;
__u16 h_proto;
__u64 nh_off;
+ __u64 flags;
nh_off = sizeof(*eth);
if (data + nh_off > data_end)
return XDP_DROP;
- h_proto = eth->h_proto;
-
- /* Using IPv4 for (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) testing */
- if (h_proto == bpf_htons(ETH_P_IP))
- return bpf_redirect_map(&map_all, 0,
- BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
- /* Using IPv6 for none flag testing */
- else if (h_proto == bpf_htons(ETH_P_IPV6))
- return bpf_redirect_map(&map_all, if_index, 0);
- /* All others for BPF_F_BROADCAST testing */
- else
- return bpf_redirect_map(&map_all, 0, BPF_F_BROADCAST);
+ h_proto = bpf_htons(eth->h_proto);
+
+ flags_from_map = bpf_map_lookup_elem(&redirect_flags, &h_proto);
+
+ /* Default flags for IPv4 : (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) */
+ if (h_proto == ETH_P_IP) {
+ flags = flags_from_map ? *flags_from_map : BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS;
+ return bpf_redirect_map(&map_all, 0, flags);
+ }
+ /* Default flags for IPv6 : 0 */
+ if (h_proto == ETH_P_IPV6) {
+ flags = flags_from_map ? *flags_from_map : 0;
+ return bpf_redirect_map(&map_all, if_index, flags);
+ }
+ /* Default flags for others BPF_F_BROADCAST : 0 */
+ else {
+ flags = flags_from_map ? *flags_from_map : BPF_F_BROADCAST;
+ return bpf_redirect_map(&map_all, 0, flags);
+ }
}
/* The following 2 progs are for 2nd devmap prog testing */
diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h
index fb4f4714eeb4..e65889ab4adf 100644
--- a/tools/testing/selftests/bpf/test_btf.h
+++ b/tools/testing/selftests/bpf/test_btf.h
@@ -72,9 +72,15 @@
#define BTF_TYPE_FLOAT_ENC(name, sz) \
BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
+#define BTF_DECL_ATTR_ENC(value, type, component_idx) \
+ BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), type), (component_idx)
+
#define BTF_DECL_TAG_ENC(value, type, component_idx) \
BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx)
+#define BTF_TYPE_ATTR_ENC(value, type) \
+ BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 1, 0), type)
+
#define BTF_TYPE_TAG_ENC(value, type) \
BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 0, 0), type)
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
index cc9dde507aba..3220f1d28697 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
@@ -1130,6 +1130,7 @@ static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = {
};
static const struct bpf_verifier_ops bpf_testmod_verifier_ops = {
+ .get_func_proto = bpf_base_func_proto,
.is_valid_access = bpf_testmod_ops_is_valid_access,
};
@@ -1176,10 +1177,25 @@ static int bpf_testmod_ops__test_maybe_null(int dummy,
return 0;
}
+static int bpf_testmod_ops__test_refcounted(int dummy,
+ struct task_struct *task__ref)
+{
+ return 0;
+}
+
+static struct task_struct *
+bpf_testmod_ops__test_return_ref_kptr(int dummy, struct task_struct *task__ref,
+ struct cgroup *cgrp)
+{
+ return NULL;
+}
+
static struct bpf_testmod_ops __bpf_testmod_ops = {
.test_1 = bpf_testmod_test_1,
.test_2 = bpf_testmod_test_2,
.test_maybe_null = bpf_testmod_ops__test_maybe_null,
+ .test_refcounted = bpf_testmod_ops__test_refcounted,
+ .test_return_ref_kptr = bpf_testmod_ops__test_return_ref_kptr,
};
struct bpf_struct_ops bpf_bpf_testmod_ops = {
@@ -1293,6 +1309,85 @@ static int bpf_test_mod_st_ops__test_pro_epilogue(struct st_ops_args *args)
return 0;
}
+static int bpf_cgroup_from_id_id;
+static int bpf_cgroup_release_id;
+
+static int st_ops_gen_prologue_with_kfunc(struct bpf_insn *insn_buf, bool direct_write,
+ const struct bpf_prog *prog)
+{
+ struct bpf_insn *insn = insn_buf;
+
+ /* r8 = r1; // r8 will be "u64 *ctx".
+ * r1 = 0;
+ * r0 = bpf_cgroup_from_id(r1);
+ * if r0 != 0 goto pc+5;
+ * r6 = r8[0]; // r6 will be "struct st_ops *args".
+ * r7 = r6->a;
+ * r7 += 1000;
+ * r6->a = r7;
+ * goto pc+2;
+ * r1 = r0;
+ * bpf_cgroup_release(r1);
+ * r1 = r8;
+ */
+ *insn++ = BPF_MOV64_REG(BPF_REG_8, BPF_REG_1);
+ *insn++ = BPF_MOV64_IMM(BPF_REG_1, 0);
+ *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_from_id_id);
+ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 5);
+ *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_8, 0);
+ *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_6, offsetof(struct st_ops_args, a));
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 1000);
+ *insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, offsetof(struct st_ops_args, a));
+ *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 2);
+ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0);
+ *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_release_id),
+ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_8);
+ *insn++ = prog->insnsi[0];
+
+ return insn - insn_buf;
+}
+
+static int st_ops_gen_epilogue_with_kfunc(struct bpf_insn *insn_buf, const struct bpf_prog *prog,
+ s16 ctx_stack_off)
+{
+ struct bpf_insn *insn = insn_buf;
+
+ /* r1 = 0;
+ * r6 = 0;
+ * r0 = bpf_cgroup_from_id(r1);
+ * if r0 != 0 goto pc+6;
+ * r1 = stack[ctx_stack_off]; // r1 will be "u64 *ctx"
+ * r1 = r1[0]; // r1 will be "struct st_ops *args"
+ * r6 = r1->a;
+ * r6 += 10000;
+ * r1->a = r6;
+ * goto pc+2
+ * r1 = r0;
+ * bpf_cgroup_release(r1);
+ * r0 = r6;
+ * r0 *= 2;
+ * BPF_EXIT;
+ */
+ *insn++ = BPF_MOV64_IMM(BPF_REG_1, 0);
+ *insn++ = BPF_MOV64_IMM(BPF_REG_6, 0);
+ *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_from_id_id);
+ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 6);
+ *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_FP, ctx_stack_off);
+ *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+ *insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, offsetof(struct st_ops_args, a));
+ *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 10000);
+ *insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, offsetof(struct st_ops_args, a));
+ *insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 2);
+ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0);
+ *insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_release_id),
+ *insn++ = BPF_MOV64_REG(BPF_REG_0, BPF_REG_6);
+ *insn++ = BPF_ALU64_IMM(BPF_MUL, BPF_REG_0, 2);
+ *insn++ = BPF_EXIT_INSN();
+
+ return insn - insn_buf;
+}
+
+#define KFUNC_PRO_EPI_PREFIX "test_kfunc_"
static int st_ops_gen_prologue(struct bpf_insn *insn_buf, bool direct_write,
const struct bpf_prog *prog)
{
@@ -1302,6 +1397,9 @@ static int st_ops_gen_prologue(struct bpf_insn *insn_buf, bool direct_write,
strcmp(prog->aux->attach_func_name, "test_pro_epilogue"))
return 0;
+ if (!strncmp(prog->aux->name, KFUNC_PRO_EPI_PREFIX, strlen(KFUNC_PRO_EPI_PREFIX)))
+ return st_ops_gen_prologue_with_kfunc(insn_buf, direct_write, prog);
+
/* r6 = r1[0]; // r6 will be "struct st_ops *args". r1 is "u64 *ctx".
* r7 = r6->a;
* r7 += 1000;
@@ -1325,6 +1423,9 @@ static int st_ops_gen_epilogue(struct bpf_insn *insn_buf, const struct bpf_prog
strcmp(prog->aux->attach_func_name, "test_pro_epilogue"))
return 0;
+ if (!strncmp(prog->aux->name, KFUNC_PRO_EPI_PREFIX, strlen(KFUNC_PRO_EPI_PREFIX)))
+ return st_ops_gen_epilogue_with_kfunc(insn_buf, prog, ctx_stack_off);
+
/* r1 = stack[ctx_stack_off]; // r1 will be "u64 *ctx"
* r1 = r1[0]; // r1 will be "struct st_ops *args"
* r6 = r1->a;
@@ -1395,6 +1496,13 @@ static void st_ops_unreg(void *kdata, struct bpf_link *link)
static int st_ops_init(struct btf *btf)
{
+ struct btf *kfunc_btf;
+
+ bpf_cgroup_from_id_id = bpf_find_btf_id("bpf_cgroup_from_id", BTF_KIND_FUNC, &kfunc_btf);
+ bpf_cgroup_release_id = bpf_find_btf_id("bpf_cgroup_release", BTF_KIND_FUNC, &kfunc_btf);
+ if (bpf_cgroup_from_id_id < 0 || bpf_cgroup_release_id < 0)
+ return -EINVAL;
+
return 0;
}
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h
index 356803d1c10e..c9fab51f16e2 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h
@@ -6,6 +6,7 @@
#include <linux/types.h>
struct task_struct;
+struct cgroup;
struct bpf_testmod_test_read_ctx {
char *buf;
@@ -36,6 +37,11 @@ struct bpf_testmod_ops {
/* Used to test nullable arguments. */
int (*test_maybe_null)(int dummy, struct task_struct *task);
int (*unsupported_ops)(void);
+ /* Used to test ref_acquired arguments. */
+ int (*test_refcounted)(int dummy, struct task_struct *task);
+ /* Used to test returning referenced kptr. */
+ struct task_struct *(*test_return_ref_kptr)(int dummy, struct task_struct *task,
+ struct cgroup *cgrp);
/* The following fields are used to test shadow copies. */
char onebyte;
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 53b06647cf57..49f2fc61061f 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -37,6 +37,7 @@
#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="
+#define TEST_TAG_LOAD_MODE_PFX "comment:load_mode="
/* Warning: duplicated in bpf_misc.h */
#define POINTER_VALUE 0xcafe4all
@@ -55,6 +56,11 @@ enum mode {
UNPRIV = 2
};
+enum load_mode {
+ JITED = 1 << 0,
+ NO_JITED = 1 << 1,
+};
+
struct expect_msg {
const char *substr; /* substring match */
regex_t regex;
@@ -87,6 +93,7 @@ struct test_spec {
int prog_flags;
int mode_mask;
int arch_mask;
+ int load_mask;
bool auxiliary;
bool valid;
};
@@ -406,6 +413,7 @@ static int parse_test_spec(struct test_loader *tester,
bool collect_jit = false;
int func_id, i, err = 0;
u32 arch_mask = 0;
+ u32 load_mask = 0;
struct btf *btf;
enum arch arch;
@@ -580,10 +588,22 @@ static int parse_test_spec(struct test_loader *tester,
if (err)
goto cleanup;
spec->mode_mask |= UNPRIV;
+ } else if (str_has_pfx(s, TEST_TAG_LOAD_MODE_PFX)) {
+ val = s + sizeof(TEST_TAG_LOAD_MODE_PFX) - 1;
+ if (strcmp(val, "jited") == 0) {
+ load_mask = JITED;
+ } else if (strcmp(val, "no_jited") == 0) {
+ load_mask = NO_JITED;
+ } else {
+ PRINT_FAIL("bad load spec: '%s'", val);
+ err = -EINVAL;
+ goto cleanup;
+ }
}
}
spec->arch_mask = arch_mask ?: -1;
+ spec->load_mask = load_mask ?: (JITED | NO_JITED);
if (spec->mode_mask == 0)
spec->mode_mask = PRIV;
@@ -773,7 +793,7 @@ static int drop_capabilities(struct cap_state *caps)
err = cap_disable_effective(caps_to_drop, &caps->old_caps);
if (err) {
- PRINT_FAIL("failed to drop capabilities: %i, %s\n", err, strerror(err));
+ PRINT_FAIL("failed to drop capabilities: %i, %s\n", err, strerror(-err));
return err;
}
@@ -790,7 +810,7 @@ static int restore_capabilities(struct cap_state *caps)
err = cap_enable_effective(caps->old_caps, NULL);
if (err)
- PRINT_FAIL("failed to restore capabilities: %i, %s\n", err, strerror(err));
+ PRINT_FAIL("failed to restore capabilities: %i, %s\n", err, strerror(-err));
caps->initialized = false;
return err;
}
@@ -928,6 +948,7 @@ void run_subtest(struct test_loader *tester,
bool unpriv)
{
struct test_subspec *subspec = unpriv ? &spec->unpriv : &spec->priv;
+ int current_runtime = is_jit_enabled() ? JITED : NO_JITED;
struct bpf_program *tprog = NULL, *tprog_iter;
struct bpf_link *link, *links[32] = {};
struct test_spec *spec_iter;
@@ -946,6 +967,11 @@ void run_subtest(struct test_loader *tester,
return;
}
+ if ((current_runtime & spec->load_mask) == 0) {
+ test__skip();
+ return;
+ }
+
if (unpriv) {
if (!can_execute_unpriv(tester, spec)) {
test__skip();
@@ -959,7 +985,7 @@ void run_subtest(struct test_loader *tester,
if (subspec->caps) {
err = cap_enable_effective(subspec->caps, NULL);
if (err) {
- PRINT_FAIL("failed to set capabilities: %i, %s\n", err, strerror(err));
+ PRINT_FAIL("failed to set capabilities: %i, %s\n", err, strerror(-err));
goto subtest_cleanup;
}
}
diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
deleted file mode 100755
index 1e565f47aca9..000000000000
--- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
+++ /dev/null
@@ -1,476 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# Setup/topology:
-#
-# NS1 NS2 NS3
-# veth1 <---> veth2 veth3 <---> veth4 (the top route)
-# veth5 <---> veth6 veth7 <---> veth8 (the bottom route)
-#
-# each vethN gets IPv[4|6]_N address
-#
-# IPv*_SRC = IPv*_1
-# IPv*_DST = IPv*_4
-#
-# all tests test pings from IPv*_SRC to IPv*_DST
-#
-# by default, routes are configured to allow packets to go
-# IP*_1 <=> IP*_2 <=> IP*_3 <=> IP*_4 (the top route)
-#
-# a GRE device is installed in NS3 with IPv*_GRE, and
-# NS1/NS2 are configured to route packets to IPv*_GRE via IP*_8
-# (the bottom route)
-#
-# Tests:
-#
-# 1. routes NS2->IPv*_DST are brought down, so the only way a ping
-# from IP*_SRC to IP*_DST can work is via IPv*_GRE
-#
-# 2a. in an egress test, a bpf LWT_XMIT program is installed on veth1
-# that encaps the packets with an IP/GRE header to route to IPv*_GRE
-#
-# ping: SRC->[encap at veth1:egress]->GRE:decap->DST
-# ping replies go DST->SRC directly
-#
-# 2b. in an ingress test, a bpf LWT_IN program is installed on veth2
-# that encaps the packets with an IP/GRE header to route to IPv*_GRE
-#
-# ping: SRC->[encap at veth2:ingress]->GRE:decap->DST
-# ping replies go DST->SRC directly
-
-BPF_FILE="test_lwt_ip_encap.bpf.o"
-if [[ $EUID -ne 0 ]]; then
- echo "This script must be run as root"
- echo "FAIL"
- exit 1
-fi
-
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-readonly NS2="ns2-$(mktemp -u XXXXXX)"
-readonly NS3="ns3-$(mktemp -u XXXXXX)"
-
-readonly IPv4_1="172.16.1.100"
-readonly IPv4_2="172.16.2.100"
-readonly IPv4_3="172.16.3.100"
-readonly IPv4_4="172.16.4.100"
-readonly IPv4_5="172.16.5.100"
-readonly IPv4_6="172.16.6.100"
-readonly IPv4_7="172.16.7.100"
-readonly IPv4_8="172.16.8.100"
-readonly IPv4_GRE="172.16.16.100"
-
-readonly IPv4_SRC=$IPv4_1
-readonly IPv4_DST=$IPv4_4
-
-readonly IPv6_1="fb01::1"
-readonly IPv6_2="fb02::1"
-readonly IPv6_3="fb03::1"
-readonly IPv6_4="fb04::1"
-readonly IPv6_5="fb05::1"
-readonly IPv6_6="fb06::1"
-readonly IPv6_7="fb07::1"
-readonly IPv6_8="fb08::1"
-readonly IPv6_GRE="fb10::1"
-
-readonly IPv6_SRC=$IPv6_1
-readonly IPv6_DST=$IPv6_4
-
-TEST_STATUS=0
-TESTS_SUCCEEDED=0
-TESTS_FAILED=0
-
-TMPFILE=""
-
-process_test_results()
-{
- if [[ "${TEST_STATUS}" -eq 0 ]] ; then
- echo "PASS"
- TESTS_SUCCEEDED=$((TESTS_SUCCEEDED+1))
- else
- echo "FAIL"
- TESTS_FAILED=$((TESTS_FAILED+1))
- fi
-}
-
-print_test_summary_and_exit()
-{
- echo "passed tests: ${TESTS_SUCCEEDED}"
- echo "failed tests: ${TESTS_FAILED}"
- if [ "${TESTS_FAILED}" -eq "0" ] ; then
- exit 0
- else
- exit 1
- fi
-}
-
-setup()
-{
- set -e # exit on error
- TEST_STATUS=0
-
- # create devices and namespaces
- ip netns add "${NS1}"
- ip netns add "${NS2}"
- ip netns add "${NS3}"
-
- # rp_filter gets confused by what these tests are doing, so disable it
- ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0
- ip netns exec ${NS1} sysctl -wq net.ipv4.conf.default.rp_filter=0
- ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0
- ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0
-
- # disable IPv6 DAD because it sometimes takes too long and fails tests
- ip netns exec ${NS1} sysctl -wq net.ipv6.conf.all.accept_dad=0
- ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.accept_dad=0
- ip netns exec ${NS3} sysctl -wq net.ipv6.conf.all.accept_dad=0
- ip netns exec ${NS1} sysctl -wq net.ipv6.conf.default.accept_dad=0
- ip netns exec ${NS2} sysctl -wq net.ipv6.conf.default.accept_dad=0
- ip netns exec ${NS3} sysctl -wq net.ipv6.conf.default.accept_dad=0
-
- ip link add veth1 type veth peer name veth2
- ip link add veth3 type veth peer name veth4
- ip link add veth5 type veth peer name veth6
- ip link add veth7 type veth peer name veth8
-
- ip netns exec ${NS2} sysctl -wq net.ipv4.ip_forward=1
- ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.forwarding=1
-
- ip link set veth1 netns ${NS1}
- ip link set veth2 netns ${NS2}
- ip link set veth3 netns ${NS2}
- ip link set veth4 netns ${NS3}
- ip link set veth5 netns ${NS1}
- ip link set veth6 netns ${NS2}
- ip link set veth7 netns ${NS2}
- ip link set veth8 netns ${NS3}
-
- if [ ! -z "${VRF}" ] ; then
- ip -netns ${NS1} link add red type vrf table 1001
- ip -netns ${NS1} link set red up
- ip -netns ${NS1} route add table 1001 unreachable default metric 8192
- ip -netns ${NS1} -6 route add table 1001 unreachable default metric 8192
- ip -netns ${NS1} link set veth1 vrf red
- ip -netns ${NS1} link set veth5 vrf red
-
- ip -netns ${NS2} link add red type vrf table 1001
- ip -netns ${NS2} link set red up
- ip -netns ${NS2} route add table 1001 unreachable default metric 8192
- ip -netns ${NS2} -6 route add table 1001 unreachable default metric 8192
- ip -netns ${NS2} link set veth2 vrf red
- ip -netns ${NS2} link set veth3 vrf red
- ip -netns ${NS2} link set veth6 vrf red
- ip -netns ${NS2} link set veth7 vrf red
- fi
-
- # configure addesses: the top route (1-2-3-4)
- ip -netns ${NS1} addr add ${IPv4_1}/24 dev veth1
- ip -netns ${NS2} addr add ${IPv4_2}/24 dev veth2
- ip -netns ${NS2} addr add ${IPv4_3}/24 dev veth3
- ip -netns ${NS3} addr add ${IPv4_4}/24 dev veth4
- ip -netns ${NS1} -6 addr add ${IPv6_1}/128 nodad dev veth1
- ip -netns ${NS2} -6 addr add ${IPv6_2}/128 nodad dev veth2
- ip -netns ${NS2} -6 addr add ${IPv6_3}/128 nodad dev veth3
- ip -netns ${NS3} -6 addr add ${IPv6_4}/128 nodad dev veth4
-
- # configure addresses: the bottom route (5-6-7-8)
- ip -netns ${NS1} addr add ${IPv4_5}/24 dev veth5
- ip -netns ${NS2} addr add ${IPv4_6}/24 dev veth6
- ip -netns ${NS2} addr add ${IPv4_7}/24 dev veth7
- ip -netns ${NS3} addr add ${IPv4_8}/24 dev veth8
- ip -netns ${NS1} -6 addr add ${IPv6_5}/128 nodad dev veth5
- ip -netns ${NS2} -6 addr add ${IPv6_6}/128 nodad dev veth6
- ip -netns ${NS2} -6 addr add ${IPv6_7}/128 nodad dev veth7
- ip -netns ${NS3} -6 addr add ${IPv6_8}/128 nodad dev veth8
-
- ip -netns ${NS1} link set dev veth1 up
- ip -netns ${NS2} link set dev veth2 up
- ip -netns ${NS2} link set dev veth3 up
- ip -netns ${NS3} link set dev veth4 up
- ip -netns ${NS1} link set dev veth5 up
- ip -netns ${NS2} link set dev veth6 up
- ip -netns ${NS2} link set dev veth7 up
- ip -netns ${NS3} link set dev veth8 up
-
- # configure routes: IP*_SRC -> veth1/IP*_2 (= top route) default;
- # the bottom route to specific bottom addresses
-
- # NS1
- # top route
- ip -netns ${NS1} route add ${IPv4_2}/32 dev veth1 ${VRF}
- ip -netns ${NS1} route add default dev veth1 via ${IPv4_2} ${VRF} # go top by default
- ip -netns ${NS1} -6 route add ${IPv6_2}/128 dev veth1 ${VRF}
- ip -netns ${NS1} -6 route add default dev veth1 via ${IPv6_2} ${VRF} # go top by default
- # bottom route
- ip -netns ${NS1} route add ${IPv4_6}/32 dev veth5 ${VRF}
- ip -netns ${NS1} route add ${IPv4_7}/32 dev veth5 via ${IPv4_6} ${VRF}
- ip -netns ${NS1} route add ${IPv4_8}/32 dev veth5 via ${IPv4_6} ${VRF}
- ip -netns ${NS1} -6 route add ${IPv6_6}/128 dev veth5 ${VRF}
- ip -netns ${NS1} -6 route add ${IPv6_7}/128 dev veth5 via ${IPv6_6} ${VRF}
- ip -netns ${NS1} -6 route add ${IPv6_8}/128 dev veth5 via ${IPv6_6} ${VRF}
-
- # NS2
- # top route
- ip -netns ${NS2} route add ${IPv4_1}/32 dev veth2 ${VRF}
- ip -netns ${NS2} route add ${IPv4_4}/32 dev veth3 ${VRF}
- ip -netns ${NS2} -6 route add ${IPv6_1}/128 dev veth2 ${VRF}
- ip -netns ${NS2} -6 route add ${IPv6_4}/128 dev veth3 ${VRF}
- # bottom route
- ip -netns ${NS2} route add ${IPv4_5}/32 dev veth6 ${VRF}
- ip -netns ${NS2} route add ${IPv4_8}/32 dev veth7 ${VRF}
- ip -netns ${NS2} -6 route add ${IPv6_5}/128 dev veth6 ${VRF}
- ip -netns ${NS2} -6 route add ${IPv6_8}/128 dev veth7 ${VRF}
-
- # NS3
- # top route
- ip -netns ${NS3} route add ${IPv4_3}/32 dev veth4
- ip -netns ${NS3} route add ${IPv4_1}/32 dev veth4 via ${IPv4_3}
- ip -netns ${NS3} route add ${IPv4_2}/32 dev veth4 via ${IPv4_3}
- ip -netns ${NS3} -6 route add ${IPv6_3}/128 dev veth4
- ip -netns ${NS3} -6 route add ${IPv6_1}/128 dev veth4 via ${IPv6_3}
- ip -netns ${NS3} -6 route add ${IPv6_2}/128 dev veth4 via ${IPv6_3}
- # bottom route
- ip -netns ${NS3} route add ${IPv4_7}/32 dev veth8
- ip -netns ${NS3} route add ${IPv4_5}/32 dev veth8 via ${IPv4_7}
- ip -netns ${NS3} route add ${IPv4_6}/32 dev veth8 via ${IPv4_7}
- ip -netns ${NS3} -6 route add ${IPv6_7}/128 dev veth8
- ip -netns ${NS3} -6 route add ${IPv6_5}/128 dev veth8 via ${IPv6_7}
- ip -netns ${NS3} -6 route add ${IPv6_6}/128 dev veth8 via ${IPv6_7}
-
- # configure IPv4 GRE device in NS3, and a route to it via the "bottom" route
- ip -netns ${NS3} tunnel add gre_dev mode gre remote ${IPv4_1} local ${IPv4_GRE} ttl 255
- ip -netns ${NS3} link set gre_dev up
- ip -netns ${NS3} addr add ${IPv4_GRE} dev gre_dev
- ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6} ${VRF}
- ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8} ${VRF}
-
-
- # configure IPv6 GRE device in NS3, and a route to it via the "bottom" route
- ip -netns ${NS3} -6 tunnel add name gre6_dev mode ip6gre remote ${IPv6_1} local ${IPv6_GRE} ttl 255
- ip -netns ${NS3} link set gre6_dev up
- ip -netns ${NS3} -6 addr add ${IPv6_GRE} nodad dev gre6_dev
- ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF}
- ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF}
-
- TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX)
-
- sleep 1 # reduce flakiness
- set +e
-}
-
-cleanup()
-{
- if [ -f ${TMPFILE} ] ; then
- rm ${TMPFILE}
- fi
-
- ip netns del ${NS1} 2> /dev/null
- ip netns del ${NS2} 2> /dev/null
- ip netns del ${NS3} 2> /dev/null
-}
-
-trap cleanup EXIT
-
-remove_routes_to_gredev()
-{
- ip -netns ${NS1} route del ${IPv4_GRE} dev veth5 ${VRF}
- ip -netns ${NS2} route del ${IPv4_GRE} dev veth7 ${VRF}
- ip -netns ${NS1} -6 route del ${IPv6_GRE}/128 dev veth5 ${VRF}
- ip -netns ${NS2} -6 route del ${IPv6_GRE}/128 dev veth7 ${VRF}
-}
-
-add_unreachable_routes_to_gredev()
-{
- ip -netns ${NS1} route add unreachable ${IPv4_GRE}/32 ${VRF}
- ip -netns ${NS2} route add unreachable ${IPv4_GRE}/32 ${VRF}
- ip -netns ${NS1} -6 route add unreachable ${IPv6_GRE}/128 ${VRF}
- ip -netns ${NS2} -6 route add unreachable ${IPv6_GRE}/128 ${VRF}
-}
-
-test_ping()
-{
- local readonly PROTO=$1
- local readonly EXPECTED=$2
- local RET=0
-
- if [ "${PROTO}" == "IPv4" ] ; then
- ip netns exec ${NS1} ping -c 1 -W 1 -I veth1 ${IPv4_DST} 2>&1 > /dev/null
- RET=$?
- elif [ "${PROTO}" == "IPv6" ] ; then
- ip netns exec ${NS1} ping6 -c 1 -W 1 -I veth1 ${IPv6_DST} 2>&1 > /dev/null
- RET=$?
- else
- echo " test_ping: unknown PROTO: ${PROTO}"
- TEST_STATUS=1
- fi
-
- if [ "0" != "${RET}" ]; then
- RET=1
- fi
-
- if [ "${EXPECTED}" != "${RET}" ] ; then
- echo " test_ping failed: expected: ${EXPECTED}; got ${RET}"
- TEST_STATUS=1
- fi
-}
-
-test_gso()
-{
- local readonly PROTO=$1
- local readonly PKT_SZ=5000
- local IP_DST=""
- : > ${TMPFILE} # trim the capture file
-
- # check that nc is present
- command -v nc >/dev/null 2>&1 || \
- { echo >&2 "nc is not available: skipping TSO tests"; return; }
-
- # listen on port 9000, capture TCP into $TMPFILE
- if [ "${PROTO}" == "IPv4" ] ; then
- IP_DST=${IPv4_DST}
- ip netns exec ${NS3} bash -c \
- "nc -4 -l -p 9000 > ${TMPFILE} &"
- elif [ "${PROTO}" == "IPv6" ] ; then
- IP_DST=${IPv6_DST}
- ip netns exec ${NS3} bash -c \
- "nc -6 -l -p 9000 > ${TMPFILE} &"
- RET=$?
- else
- echo " test_gso: unknown PROTO: ${PROTO}"
- TEST_STATUS=1
- fi
- sleep 1 # let nc start listening
-
- # send a packet larger than MTU
- ip netns exec ${NS1} bash -c \
- "dd if=/dev/zero bs=$PKT_SZ count=1 > /dev/tcp/${IP_DST}/9000 2>/dev/null"
- sleep 2 # let the packet get delivered
-
- # verify we received all expected bytes
- SZ=$(stat -c %s ${TMPFILE})
- if [ "$SZ" != "$PKT_SZ" ] ; then
- echo " test_gso failed: ${PROTO}"
- TEST_STATUS=1
- fi
-}
-
-test_egress()
-{
- local readonly ENCAP=$1
- echo "starting egress ${ENCAP} encap test ${VRF}"
- setup
-
- # by default, pings work
- test_ping IPv4 0
- test_ping IPv6 0
-
- # remove NS2->DST routes, ping fails
- ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 ${VRF}
- ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 ${VRF}
- test_ping IPv4 1
- test_ping IPv6 1
-
- # install replacement routes (LWT/eBPF), pings succeed
- if [ "${ENCAP}" == "IPv4" ] ; then
- ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj \
- ${BPF_FILE} sec encap_gre dev veth1 ${VRF}
- ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj \
- ${BPF_FILE} sec encap_gre dev veth1 ${VRF}
- elif [ "${ENCAP}" == "IPv6" ] ; then
- ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj \
- ${BPF_FILE} sec encap_gre6 dev veth1 ${VRF}
- ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj \
- ${BPF_FILE} sec encap_gre6 dev veth1 ${VRF}
- else
- echo " unknown encap ${ENCAP}"
- TEST_STATUS=1
- fi
- test_ping IPv4 0
- test_ping IPv6 0
-
- # skip GSO tests with VRF: VRF routing needs properly assigned
- # source IP/device, which is easy to do with ping and hard with dd/nc.
- if [ -z "${VRF}" ] ; then
- test_gso IPv4
- test_gso IPv6
- fi
-
- # a negative test: remove routes to GRE devices: ping fails
- remove_routes_to_gredev
- test_ping IPv4 1
- test_ping IPv6 1
-
- # another negative test
- add_unreachable_routes_to_gredev
- test_ping IPv4 1
- test_ping IPv6 1
-
- cleanup
- process_test_results
-}
-
-test_ingress()
-{
- local readonly ENCAP=$1
- echo "starting ingress ${ENCAP} encap test ${VRF}"
- setup
-
- # need to wait a bit for IPv6 to autoconf, otherwise
- # ping6 sometimes fails with "unable to bind to address"
-
- # by default, pings work
- test_ping IPv4 0
- test_ping IPv6 0
-
- # remove NS2->DST routes, pings fail
- ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 ${VRF}
- ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 ${VRF}
- test_ping IPv4 1
- test_ping IPv6 1
-
- # install replacement routes (LWT/eBPF), pings succeed
- if [ "${ENCAP}" == "IPv4" ] ; then
- ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj \
- ${BPF_FILE} sec encap_gre dev veth2 ${VRF}
- ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj \
- ${BPF_FILE} sec encap_gre dev veth2 ${VRF}
- elif [ "${ENCAP}" == "IPv6" ] ; then
- ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj \
- ${BPF_FILE} sec encap_gre6 dev veth2 ${VRF}
- ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj \
- ${BPF_FILE} sec encap_gre6 dev veth2 ${VRF}
- else
- echo "FAIL: unknown encap ${ENCAP}"
- TEST_STATUS=1
- fi
- test_ping IPv4 0
- test_ping IPv6 0
-
- # a negative test: remove routes to GRE devices: ping fails
- remove_routes_to_gredev
- test_ping IPv4 1
- test_ping IPv6 1
-
- # another negative test
- add_unreachable_routes_to_gredev
- test_ping IPv4 1
- test_ping IPv6 1
-
- cleanup
- process_test_results
-}
-
-VRF=""
-test_egress IPv4
-test_egress IPv6
-test_ingress IPv4
-test_ingress IPv6
-
-VRF="vrf red"
-test_egress IPv4
-test_egress IPv6
-test_ingress IPv4
-test_ingress IPv6
-
-print_test_summary_and_exit
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
deleted file mode 100755
index 0efea2292d6a..000000000000
--- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh
+++ /dev/null
@@ -1,156 +0,0 @@
-#!/bin/bash
-# Connects 6 network namespaces through veths.
-# Each NS may have different IPv6 global scope addresses :
-# NS1 ---- NS2 ---- NS3 ---- NS4 ---- NS5 ---- NS6
-# fb00::1 fd00::1 fd00::2 fd00::3 fb00::6
-# fc42::1 fd00::4
-#
-# All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a
-# IPv6 header with a Segment Routing Header, with segments :
-# fd00::1 -> fd00::2 -> fd00::3 -> fd00::4
-#
-# 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions :
-# - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1
-# - fd00::2 : remove the TLV, change the flags, add a tag
-# - fd00::3 : apply an End.T action to fd00::4, through routing table 117
-#
-# fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet.
-# Each End.BPF action will validate the operations applied on the SRH by the
-# previous BPF program in the chain, otherwise the packet is dropped.
-#
-# An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
-# datagram can be read on NS6 when binding to fb00::6.
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-BPF_FILE="test_lwt_seg6local.bpf.o"
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-readonly NS2="ns2-$(mktemp -u XXXXXX)"
-readonly NS3="ns3-$(mktemp -u XXXXXX)"
-readonly NS4="ns4-$(mktemp -u XXXXXX)"
-readonly NS5="ns5-$(mktemp -u XXXXXX)"
-readonly NS6="ns6-$(mktemp -u XXXXXX)"
-
-msg="skip all tests:"
-if [ $UID != 0 ]; then
- echo $msg please run this as root >&2
- exit $ksft_skip
-fi
-
-TMP_FILE="/tmp/selftest_lwt_seg6local.txt"
-
-cleanup()
-{
- if [ "$?" = "0" ]; then
- echo "selftests: test_lwt_seg6local [PASS]";
- else
- echo "selftests: test_lwt_seg6local [FAILED]";
- fi
-
- set +e
- ip netns del ${NS1} 2> /dev/null
- ip netns del ${NS2} 2> /dev/null
- ip netns del ${NS3} 2> /dev/null
- ip netns del ${NS4} 2> /dev/null
- ip netns del ${NS5} 2> /dev/null
- ip netns del ${NS6} 2> /dev/null
- rm -f $TMP_FILE
-}
-
-set -e
-
-ip netns add ${NS1}
-ip netns add ${NS2}
-ip netns add ${NS3}
-ip netns add ${NS4}
-ip netns add ${NS5}
-ip netns add ${NS6}
-
-trap cleanup 0 2 3 6 9
-
-ip link add veth1 type veth peer name veth2
-ip link add veth3 type veth peer name veth4
-ip link add veth5 type veth peer name veth6
-ip link add veth7 type veth peer name veth8
-ip link add veth9 type veth peer name veth10
-
-ip link set veth1 netns ${NS1}
-ip link set veth2 netns ${NS2}
-ip link set veth3 netns ${NS2}
-ip link set veth4 netns ${NS3}
-ip link set veth5 netns ${NS3}
-ip link set veth6 netns ${NS4}
-ip link set veth7 netns ${NS4}
-ip link set veth8 netns ${NS5}
-ip link set veth9 netns ${NS5}
-ip link set veth10 netns ${NS6}
-
-ip netns exec ${NS1} ip link set dev veth1 up
-ip netns exec ${NS2} ip link set dev veth2 up
-ip netns exec ${NS2} ip link set dev veth3 up
-ip netns exec ${NS3} ip link set dev veth4 up
-ip netns exec ${NS3} ip link set dev veth5 up
-ip netns exec ${NS4} ip link set dev veth6 up
-ip netns exec ${NS4} ip link set dev veth7 up
-ip netns exec ${NS5} ip link set dev veth8 up
-ip netns exec ${NS5} ip link set dev veth9 up
-ip netns exec ${NS6} ip link set dev veth10 up
-ip netns exec ${NS6} ip link set dev lo up
-
-# All link scope addresses and routes required between veths
-ip netns exec ${NS1} ip -6 addr add fb00::12/16 dev veth1 scope link
-ip netns exec ${NS1} ip -6 route add fb00::21 dev veth1 scope link
-ip netns exec ${NS2} ip -6 addr add fb00::21/16 dev veth2 scope link
-ip netns exec ${NS2} ip -6 addr add fb00::34/16 dev veth3 scope link
-ip netns exec ${NS2} ip -6 route add fb00::43 dev veth3 scope link
-ip netns exec ${NS3} ip -6 route add fb00::65 dev veth5 scope link
-ip netns exec ${NS3} ip -6 addr add fb00::43/16 dev veth4 scope link
-ip netns exec ${NS3} ip -6 addr add fb00::56/16 dev veth5 scope link
-ip netns exec ${NS4} ip -6 addr add fb00::65/16 dev veth6 scope link
-ip netns exec ${NS4} ip -6 addr add fb00::78/16 dev veth7 scope link
-ip netns exec ${NS4} ip -6 route add fb00::87 dev veth7 scope link
-ip netns exec ${NS5} ip -6 addr add fb00::87/16 dev veth8 scope link
-ip netns exec ${NS5} ip -6 addr add fb00::910/16 dev veth9 scope link
-ip netns exec ${NS5} ip -6 route add fb00::109 dev veth9 scope link
-ip netns exec ${NS5} ip -6 route add fb00::109 table 117 dev veth9 scope link
-ip netns exec ${NS6} ip -6 addr add fb00::109/16 dev veth10 scope link
-
-ip netns exec ${NS1} ip -6 addr add fb00::1/16 dev lo
-ip netns exec ${NS1} ip -6 route add fb00::6 dev veth1 via fb00::21
-
-ip netns exec ${NS2} ip -6 route add fb00::6 encap bpf in obj ${BPF_FILE} sec encap_srh dev veth2
-ip netns exec ${NS2} ip -6 route add fd00::1 dev veth3 via fb00::43 scope link
-
-ip netns exec ${NS3} ip -6 route add fc42::1 dev veth5 via fb00::65
-ip netns exec ${NS3} ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj ${BPF_FILE} sec add_egr_x dev veth4
-
-ip netns exec ${NS4} ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj ${BPF_FILE} sec pop_egr dev veth6
-ip netns exec ${NS4} ip -6 addr add fc42::1 dev lo
-ip netns exec ${NS4} ip -6 route add fd00::3 dev veth7 via fb00::87
-
-ip netns exec ${NS5} ip -6 route add fd00::4 table 117 dev veth9 via fb00::109
-ip netns exec ${NS5} ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj ${BPF_FILE} sec inspect_t dev veth8
-
-ip netns exec ${NS6} ip -6 addr add fb00::6/16 dev lo
-ip netns exec ${NS6} ip -6 addr add fd00::4/16 dev lo
-
-ip netns exec ${NS1} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec ${NS2} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec ${NS3} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec ${NS4} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec ${NS5} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
-
-ip netns exec ${NS6} sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null
-ip netns exec ${NS6} sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null
-ip netns exec ${NS6} sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null
-
-ip netns exec ${NS6} nc -l -6 -u -d 7330 > $TMP_FILE &
-ip netns exec ${NS1} bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330"
-sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment
-kill -TERM $!
-
-if [[ $(< $TMP_FILE) != "foobar" ]]; then
- exit 1
-fi
-
-exit 0
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 8b40e9496af1..986ce32b113a 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1396,9 +1396,10 @@ static void test_map_stress(void)
#define MAX_DELAY_US 50000
#define MIN_DELAY_RANGE_US 5000
-static bool retry_for_again_or_busy(int err)
+static bool can_retry(int err)
{
- return (err == EAGAIN || err == EBUSY);
+ return (err == EAGAIN || err == EBUSY ||
+ (err == ENOMEM && map_opts.map_flags == BPF_F_NO_PREALLOC));
}
int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts,
@@ -1451,12 +1452,12 @@ static void test_update_delete(unsigned int fn, void *data)
if (do_update) {
err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES,
- retry_for_again_or_busy);
+ can_retry);
if (err)
printf("error %d %d\n", err, errno);
assert(err == 0);
err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES,
- retry_for_again_or_busy);
+ can_retry);
if (err)
printf("error %d %d\n", err, errno);
assert(err == 0);
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index c9e745d49493..309d9d4a8ace 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -88,7 +88,9 @@ static void stdio_hijack(char **log_buf, size_t *log_cnt)
#endif
}
-static void stdio_restore_cleanup(void)
+static pthread_mutex_t stdout_lock = PTHREAD_MUTEX_INITIALIZER;
+
+static void stdio_restore(void)
{
#ifdef __GLIBC__
if (verbose() && env.worker_id == -1) {
@@ -98,34 +100,33 @@ static void stdio_restore_cleanup(void)
fflush(stdout);
+ pthread_mutex_lock(&stdout_lock);
+
if (env.subtest_state) {
- fclose(env.subtest_state->stdout_saved);
+ if (env.subtest_state->stdout_saved)
+ fclose(env.subtest_state->stdout_saved);
env.subtest_state->stdout_saved = NULL;
stdout = env.test_state->stdout_saved;
stderr = env.test_state->stdout_saved;
} else {
- fclose(env.test_state->stdout_saved);
+ if (env.test_state->stdout_saved)
+ fclose(env.test_state->stdout_saved);
env.test_state->stdout_saved = NULL;
+ stdout = env.stdout_saved;
+ stderr = env.stderr_saved;
}
+
+ pthread_mutex_unlock(&stdout_lock);
#endif
}
-static void stdio_restore(void)
+static int traffic_monitor_print_fn(const char *format, va_list args)
{
-#ifdef __GLIBC__
- if (verbose() && env.worker_id == -1) {
- /* nothing to do, output to stdout by default */
- return;
- }
-
- if (stdout == env.stdout_saved)
- return;
-
- stdio_restore_cleanup();
+ pthread_mutex_lock(&stdout_lock);
+ vfprintf(stdout, format, args);
+ pthread_mutex_unlock(&stdout_lock);
- stdout = env.stdout_saved;
- stderr = env.stderr_saved;
-#endif
+ return 0;
}
/* Adapted from perf/util/string.c */
@@ -474,8 +475,6 @@ static void dump_test_log(const struct prog_test_def *test,
print_test_result(test, test_state);
}
-static void stdio_restore(void);
-
/* A bunch of tests set custom affinity per-thread and/or per-process. Reset
* it after each test/sub-test.
*/
@@ -490,13 +489,11 @@ static void reset_affinity(void)
err = sched_setaffinity(0, sizeof(cpuset), &cpuset);
if (err < 0) {
- stdio_restore();
fprintf(stderr, "Failed to reset process affinity: %d!\n", err);
exit(EXIT_ERR_SETUP_INFRA);
}
err = pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
if (err < 0) {
- stdio_restore();
fprintf(stderr, "Failed to reset thread affinity: %d!\n", err);
exit(EXIT_ERR_SETUP_INFRA);
}
@@ -514,7 +511,6 @@ static void save_netns(void)
static void restore_netns(void)
{
if (setns(env.saved_netns_fd, CLONE_NEWNET) == -1) {
- stdio_restore();
perror("setns(CLONE_NEWNS)");
exit(EXIT_ERR_SETUP_INFRA);
}
@@ -541,7 +537,8 @@ void test__end_subtest(void)
test_result(subtest_state->error_cnt,
subtest_state->skipped));
- stdio_restore_cleanup();
+ stdio_restore();
+
env.subtest_state = NULL;
}
@@ -1270,8 +1267,10 @@ void crash_handler(int signum)
sz = backtrace(bt, ARRAY_SIZE(bt));
- if (env.stdout_saved)
- stdio_restore();
+ fflush(stdout);
+ stdout = env.stdout_saved;
+ stderr = env.stderr_saved;
+
if (env.test) {
env.test_state->error_cnt++;
dump_test_log(env.test, env.test_state, true, false, NULL);
@@ -1365,10 +1364,19 @@ static int recv_message(int sock, struct msg *msg)
return ret;
}
+static bool ns_is_needed(const char *test_name)
+{
+ if (strlen(test_name) < 3)
+ return false;
+
+ return !strncmp(test_name, "ns_", 3);
+}
+
static void run_one_test(int test_num)
{
struct prog_test_def *test = &prog_test_defs[test_num];
struct test_state *state = &test_states[test_num];
+ struct netns_obj *ns = NULL;
env.test = test;
env.test_state = state;
@@ -1376,10 +1384,13 @@ static void run_one_test(int test_num)
stdio_hijack(&state->log_buf, &state->log_cnt);
watchdog_start();
+ if (ns_is_needed(test->test_name))
+ ns = netns_new(test->test_name, true);
if (test->run_test)
test->run_test();
else if (test->run_serial_test)
test->run_serial_test();
+ netns_free(ns);
watchdog_stop();
/* ensure last sub-test is finalized properly */
@@ -1388,6 +1399,8 @@ static void run_one_test(int test_num)
state->tested = true;
+ stdio_restore();
+
if (verbose() && env.worker_id == -1)
print_test_result(test, state);
@@ -1396,7 +1409,6 @@ static void run_one_test(int test_num)
if (test->need_cgroup_cleanup)
cleanup_cgroup_environment();
- stdio_restore();
free(stop_libbpf_log_capture());
dump_test_log(test, state, false, false, NULL);
@@ -1931,6 +1943,9 @@ int main(int argc, char **argv)
sigaction(SIGSEGV, &sigact, NULL);
+ env.stdout_saved = stdout;
+ env.stderr_saved = stderr;
+
env.secs_till_notify = 10;
env.secs_till_kill = 120;
err = argp_parse(&argp, argc, argv, 0, NULL, &env);
@@ -1947,6 +1962,8 @@ int main(int argc, char **argv)
libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
libbpf_set_print(libbpf_print_fn);
+ traffic_monitor_set_print(traffic_monitor_print_fn);
+
srand(time(NULL));
env.jit_enabled = is_jit_enabled();
@@ -1957,9 +1974,6 @@ int main(int argc, char **argv)
return -1;
}
- env.stdout_saved = stdout;
- env.stderr_saved = stderr;
-
env.has_testmod = true;
if (!env.list_test_names) {
/* ensure previous instance of the module is unloaded */
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 404d0d4915d5..870694f2a359 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -427,6 +427,14 @@ void hexdump(const char *prefix, const void *buf, size_t len);
goto goto_label; \
})
+#define SYS_FAIL(goto_label, fmt, ...) \
+ ({ \
+ char cmd[1024]; \
+ snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \
+ if (!ASSERT_NEQ(0, system(cmd), cmd)) \
+ goto goto_label; \
+ })
+
#define ALL_TO_DEV_NULL " >/dev/null 2>&1"
#define SYS_NOFAIL(fmt, ...) \
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh
deleted file mode 100755
index d9661b9988ba..000000000000
--- a/tools/testing/selftests/bpf/test_tunnel.sh
+++ /dev/null
@@ -1,645 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-# End-to-end eBPF tunnel test suite
-# The script tests BPF network tunnel implementation.
-#
-# Topology:
-# ---------
-# root namespace | at_ns0 namespace
-# |
-# ----------- | -----------
-# | tnl dev | | | tnl dev | (overlay network)
-# ----------- | -----------
-# metadata-mode | native-mode
-# with bpf |
-# |
-# ---------- | ----------
-# | veth1 | --------- | veth0 | (underlay network)
-# ---------- peer ----------
-#
-#
-# Device Configuration
-# --------------------
-# Root namespace with metadata-mode tunnel + BPF
-# Device names and addresses:
-# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay)
-# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200, IPv6: 1::22 (overlay)
-#
-# Namespace at_ns0 with native tunnel
-# Device names and addresses:
-# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay)
-# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100, IPv6: 1::11 (overlay)
-#
-#
-# End-to-end ping packet flow
-# ---------------------------
-# Most of the tests start by namespace creation, device configuration,
-# then ping the underlay and overlay network. When doing 'ping 10.1.1.100'
-# from root namespace, the following operations happen:
-# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev.
-# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata,
-# with remote_ip=172.16.1.100 and others.
-# 3) Outer tunnel header is prepended and route the packet to veth1's egress
-# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0
-# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet
-# 6) Forward the packet to the overlay tnl dev
-
-BPF_FILE="test_tunnel_kern.bpf.o"
-BPF_PIN_TUNNEL_DIR="/sys/fs/bpf/tc/tunnel"
-PING_ARG="-c 3 -w 10 -q"
-ret=0
-GREEN='\033[0;92m'
-RED='\033[0;31m'
-NC='\033[0m' # No Color
-
-config_device()
-{
- ip netns add at_ns0
- ip link add veth0 type veth peer name veth1
- ip link set veth0 netns at_ns0
- ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip link set dev veth1 up mtu 1500
- ip addr add dev veth1 172.16.1.200/24
-}
-
-add_gre_tunnel()
-{
- tun_key=
- if [ -n "$1" ]; then
- tun_key="key $1"
- fi
-
- # at_ns0 namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq $tun_key \
- local 172.16.1.100 remote 172.16.1.200
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
- # root namespace
- ip link add dev $DEV type $TYPE $tun_key external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-add_ip6gretap_tunnel()
-{
-
- # assign ipv6 address
- ip netns exec at_ns0 ip addr add ::11/96 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip addr add dev veth1 ::22/96
- ip link set dev veth1 up
-
- # at_ns0 namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \
- local ::11 remote ::22
-
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96
- ip netns exec at_ns0 ip link set dev $DEV_NS up
-
- # root namespace
- ip link add dev $DEV type $TYPE external
- ip addr add dev $DEV 10.1.1.200/24
- ip addr add dev $DEV fc80::200/24
- ip link set dev $DEV up
-}
-
-add_erspan_tunnel()
-{
- # at_ns0 namespace
- if [ "$1" == "v1" ]; then
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local 172.16.1.100 remote 172.16.1.200 \
- erspan_ver 1 erspan 123
- else
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local 172.16.1.100 remote 172.16.1.200 \
- erspan_ver 2 erspan_dir egress erspan_hwid 3
- fi
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
- # root namespace
- ip link add dev $DEV type $TYPE external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-add_ip6erspan_tunnel()
-{
-
- # assign ipv6 address
- ip netns exec at_ns0 ip addr add ::11/96 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip addr add dev veth1 ::22/96
- ip link set dev veth1 up
-
- # at_ns0 namespace
- if [ "$1" == "v1" ]; then
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local ::11 remote ::22 \
- erspan_ver 1 erspan 123
- else
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE seq key 2 \
- local ::11 remote ::22 \
- erspan_ver 2 erspan_dir egress erspan_hwid 7
- fi
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns0 ip link set dev $DEV_NS up
-
- # root namespace
- ip link add dev $DEV type $TYPE external
- ip addr add dev $DEV 10.1.1.200/24
- ip link set dev $DEV up
-}
-
-add_geneve_tunnel()
-{
- # at_ns0 namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE \
- id 2 dstport 6081 remote 172.16.1.200
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
- # root namespace
- ip link add dev $DEV type $TYPE dstport 6081 external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-add_ip6geneve_tunnel()
-{
- ip netns exec at_ns0 ip addr add ::11/96 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip addr add dev veth1 ::22/96
- ip link set dev veth1 up
-
- # at_ns0 namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE id 22 \
- remote ::22 # geneve has no local option
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns0 ip link set dev $DEV_NS up
-
- # root namespace
- ip link add dev $DEV type $TYPE external
- ip addr add dev $DEV 10.1.1.200/24
- ip link set dev $DEV up
-}
-
-add_ipip_tunnel()
-{
- # at_ns0 namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE \
- local 172.16.1.100 remote 172.16.1.200
- ip netns exec at_ns0 ip link set dev $DEV_NS up
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
- # root namespace
- ip link add dev $DEV type $TYPE external
- ip link set dev $DEV up
- ip addr add dev $DEV 10.1.1.200/24
-}
-
-add_ip6tnl_tunnel()
-{
- ip netns exec at_ns0 ip addr add ::11/96 dev veth0
- ip netns exec at_ns0 ip link set dev veth0 up
- ip addr add dev veth1 ::22/96
- ip link set dev veth1 up
-
- # at_ns0 namespace
- ip netns exec at_ns0 \
- ip link add dev $DEV_NS type $TYPE \
- local ::11 remote ::22
- ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
- ip netns exec at_ns0 ip addr add dev $DEV_NS 1::11/96
- ip netns exec at_ns0 ip link set dev $DEV_NS up
-
- # root namespace
- ip link add dev $DEV type $TYPE external
- ip addr add dev $DEV 10.1.1.200/24
- ip addr add dev $DEV 1::22/96
- ip link set dev $DEV up
-}
-
-test_gre()
-{
- TYPE=gretap
- DEV_NS=gretap00
- DEV=gretap11
- ret=0
-
- check $TYPE
- config_device
- add_gre_tunnel 2
- attach_bpf $DEV gre_set_tunnel gre_get_tunnel
- ping $PING_ARG 10.1.1.100
- check_err $?
- ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: $TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_gre_no_tunnel_key()
-{
- TYPE=gre
- DEV_NS=gre00
- DEV=gre11
- ret=0
-
- check $TYPE
- config_device
- add_gre_tunnel
- attach_bpf $DEV gre_set_tunnel_no_key gre_get_tunnel
- ping $PING_ARG 10.1.1.100
- check_err $?
- ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: $TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ip6gre()
-{
- TYPE=ip6gre
- DEV_NS=ip6gre00
- DEV=ip6gre11
- ret=0
-
- check $TYPE
- config_device
- # reuse the ip6gretap function
- add_ip6gretap_tunnel
- attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
- # underlay
- ping6 $PING_ARG ::11
- # overlay: ipv4 over ipv6
- ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
- ping $PING_ARG 10.1.1.100
- check_err $?
- # overlay: ipv6 over ipv6
- ip netns exec at_ns0 ping6 $PING_ARG fc80::200
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: $TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ip6gretap()
-{
- TYPE=ip6gretap
- DEV_NS=ip6gretap00
- DEV=ip6gretap11
- ret=0
-
- check $TYPE
- config_device
- add_ip6gretap_tunnel
- attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
- # underlay
- ping6 $PING_ARG ::11
- # overlay: ipv4 over ipv6
- ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
- ping $PING_ARG 10.1.1.100
- check_err $?
- # overlay: ipv6 over ipv6
- ip netns exec at_ns0 ping6 $PING_ARG fc80::200
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: $TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_erspan()
-{
- TYPE=erspan
- DEV_NS=erspan00
- DEV=erspan11
- ret=0
-
- check $TYPE
- config_device
- add_erspan_tunnel $1
- attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel
- ping $PING_ARG 10.1.1.100
- check_err $?
- ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: $TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ip6erspan()
-{
- TYPE=ip6erspan
- DEV_NS=ip6erspan00
- DEV=ip6erspan11
- ret=0
-
- check $TYPE
- config_device
- add_ip6erspan_tunnel $1
- attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel
- ping6 $PING_ARG ::11
- ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: $TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_geneve()
-{
- TYPE=geneve
- DEV_NS=geneve00
- DEV=geneve11
- ret=0
-
- check $TYPE
- config_device
- add_geneve_tunnel
- attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel
- ping $PING_ARG 10.1.1.100
- check_err $?
- ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: $TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ip6geneve()
-{
- TYPE=geneve
- DEV_NS=ip6geneve00
- DEV=ip6geneve11
- ret=0
-
- check $TYPE
- config_device
- add_ip6geneve_tunnel
- attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel
- ping $PING_ARG 10.1.1.100
- check_err $?
- ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: ip6$TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
-}
-
-test_ipip()
-{
- TYPE=ipip
- DEV_NS=ipip00
- DEV=ipip11
- ret=0
-
- check $TYPE
- config_device
- add_ipip_tunnel
- ip link set dev veth1 mtu 1500
- attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel
- ping $PING_ARG 10.1.1.100
- check_err $?
- ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: $TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ipip6()
-{
- TYPE=ip6tnl
- DEV_NS=ipip6tnl00
- DEV=ipip6tnl11
- ret=0
-
- check $TYPE
- config_device
- add_ip6tnl_tunnel
- ip link set dev veth1 mtu 1500
- attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
- # underlay
- ping6 $PING_ARG ::11
- # ip4 over ip6
- ping $PING_ARG 10.1.1.100
- check_err $?
- ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: $TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ip6ip6()
-{
- TYPE=ip6tnl
- DEV_NS=ip6ip6tnl00
- DEV=ip6ip6tnl11
- ret=0
-
- check $TYPE
- config_device
- add_ip6tnl_tunnel
- ip link set dev veth1 mtu 1500
- attach_bpf $DEV ip6ip6_set_tunnel ip6ip6_get_tunnel
- # underlay
- ping6 $PING_ARG ::11
- # ip6 over ip6
- ping6 $PING_ARG 1::11
- check_err $?
- ip netns exec at_ns0 ping6 $PING_ARG 1::22
- check_err $?
- cleanup
-
- if [ $ret -ne 0 ]; then
- echo -e ${RED}"FAIL: ip6$TYPE"${NC}
- return 1
- fi
- echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
-}
-
-attach_bpf()
-{
- DEV=$1
- SET=$2
- GET=$3
- mkdir -p ${BPF_PIN_TUNNEL_DIR}
- bpftool prog loadall ${BPF_FILE} ${BPF_PIN_TUNNEL_DIR}/
- tc qdisc add dev $DEV clsact
- tc filter add dev $DEV egress bpf da object-pinned ${BPF_PIN_TUNNEL_DIR}/$SET
- tc filter add dev $DEV ingress bpf da object-pinned ${BPF_PIN_TUNNEL_DIR}/$GET
-}
-
-cleanup()
-{
- rm -rf ${BPF_PIN_TUNNEL_DIR}
-
- ip netns delete at_ns0 2> /dev/null
- ip link del veth1 2> /dev/null
- ip link del ipip11 2> /dev/null
- ip link del ipip6tnl11 2> /dev/null
- ip link del ip6ip6tnl11 2> /dev/null
- ip link del gretap11 2> /dev/null
- ip link del gre11 2> /dev/null
- ip link del ip6gre11 2> /dev/null
- ip link del ip6gretap11 2> /dev/null
- ip link del geneve11 2> /dev/null
- ip link del ip6geneve11 2> /dev/null
- ip link del erspan11 2> /dev/null
- ip link del ip6erspan11 2> /dev/null
-}
-
-cleanup_exit()
-{
- echo "CATCH SIGKILL or SIGINT, cleanup and exit"
- cleanup
- exit 0
-}
-
-check()
-{
- ip link help 2>&1 | grep -q "\s$1\s"
- if [ $? -ne 0 ];then
- echo "SKIP $1: iproute2 not support"
- cleanup
- return 1
- fi
-}
-
-enable_debug()
-{
- echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
- echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
- echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control
- echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control
-}
-
-check_err()
-{
- if [ $ret -eq 0 ]; then
- ret=$1
- fi
-}
-
-bpf_tunnel_test()
-{
- local errors=0
-
- echo "Testing GRE tunnel..."
- test_gre
- errors=$(( $errors + $? ))
-
- echo "Testing GRE tunnel (without tunnel keys)..."
- test_gre_no_tunnel_key
- errors=$(( $errors + $? ))
-
- echo "Testing IP6GRE tunnel..."
- test_ip6gre
- errors=$(( $errors + $? ))
-
- echo "Testing IP6GRETAP tunnel..."
- test_ip6gretap
- errors=$(( $errors + $? ))
-
- echo "Testing ERSPAN tunnel..."
- test_erspan v2
- errors=$(( $errors + $? ))
-
- echo "Testing IP6ERSPAN tunnel..."
- test_ip6erspan v2
- errors=$(( $errors + $? ))
-
- echo "Testing GENEVE tunnel..."
- test_geneve
- errors=$(( $errors + $? ))
-
- echo "Testing IP6GENEVE tunnel..."
- test_ip6geneve
- errors=$(( $errors + $? ))
-
- echo "Testing IPIP tunnel..."
- test_ipip
- errors=$(( $errors + $? ))
-
- echo "Testing IPIP6 tunnel..."
- test_ipip6
- errors=$(( $errors + $? ))
-
- echo "Testing IP6IP6 tunnel..."
- test_ip6ip6
- errors=$(( $errors + $? ))
-
- return $errors
-}
-
-trap cleanup 0 3 6
-trap cleanup_exit 2 9
-
-cleanup
-bpf_tunnel_test
-
-if [ $? -ne 0 ]; then
- echo -e "$(basename $0): ${RED}FAIL${NC}"
- exit 1
-fi
-echo -e "$(basename $0): ${GREEN}PASS${NC}"
-exit 0
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
deleted file mode 100755
index 4c3c3fdd2d73..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
+++ /dev/null
@@ -1,214 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# Test topology:
-# - - - - - - - - - - - - - - - - - - -
-# | veth1 veth2 veth3 | ns0
-# - -| - - - - - - | - - - - - - | - -
-# --------- --------- ---------
-# | veth0 | | veth0 | | veth0 |
-# --------- --------- ---------
-# ns1 ns2 ns3
-#
-# Test modules:
-# XDP modes: generic, native, native + egress_prog
-#
-# Test cases:
-# ARP: Testing BPF_F_BROADCAST, the ingress interface also should receive
-# the redirects.
-# ns1 -> gw: ns1, ns2, ns3, should receive the arp request
-# IPv4: Testing BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, the ingress
-# interface should not receive the redirects.
-# ns1 -> gw: ns1 should not receive, ns2, ns3 should receive redirects.
-# IPv6: Testing none flag, all the pkts should be redirected back
-# ping test: ns1 -> ns2 (block), echo requests will be redirect back
-# egress_prog:
-# all src mac should be egress interface's mac
-
-# netns numbers
-NUM=3
-IFACES=""
-DRV_MODE="xdpgeneric xdpdrv xdpegress"
-PASS=0
-FAIL=0
-LOG_DIR=$(mktemp -d)
-declare -a NS
-NS[0]="ns0-$(mktemp -u XXXXXX)"
-NS[1]="ns1-$(mktemp -u XXXXXX)"
-NS[2]="ns2-$(mktemp -u XXXXXX)"
-NS[3]="ns3-$(mktemp -u XXXXXX)"
-
-test_pass()
-{
- echo "Pass: $@"
- PASS=$((PASS + 1))
-}
-
-test_fail()
-{
- echo "fail: $@"
- FAIL=$((FAIL + 1))
-}
-
-clean_up()
-{
- for i in $(seq 0 $NUM); do
- ip netns del ${NS[$i]} 2> /dev/null
- done
-}
-
-# Kselftest framework requirement - SKIP code is 4.
-check_env()
-{
- ip link set dev lo xdpgeneric off &>/dev/null
- if [ $? -ne 0 ];then
- echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support"
- exit 4
- fi
-
- which tcpdump &>/dev/null
- if [ $? -ne 0 ];then
- echo "selftests: [SKIP] Could not run test without tcpdump"
- exit 4
- fi
-}
-
-setup_ns()
-{
- local mode=$1
- IFACES=""
-
- if [ "$mode" = "xdpegress" ]; then
- mode="xdpdrv"
- fi
-
- ip netns add ${NS[0]}
- for i in $(seq $NUM); do
- ip netns add ${NS[$i]}
- ip -n ${NS[$i]} link add veth0 type veth peer name veth$i netns ${NS[0]}
- ip -n ${NS[$i]} link set veth0 up
- ip -n ${NS[0]} link set veth$i up
-
- ip -n ${NS[$i]} addr add 192.0.2.$i/24 dev veth0
- ip -n ${NS[$i]} addr add 2001:db8::$i/64 dev veth0
- # Add a neigh entry for IPv4 ping test
- ip -n ${NS[$i]} neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0
- ip -n ${NS[$i]} link set veth0 $mode obj \
- xdp_dummy.bpf.o sec xdp &> /dev/null || \
- { test_fail "Unable to load dummy xdp" && exit 1; }
- IFACES="$IFACES veth$i"
- veth_mac[$i]=$(ip -n ${NS[0]} link show veth$i | awk '/link\/ether/ {print $2}')
- done
-}
-
-do_egress_tests()
-{
- local mode=$1
-
- # mac test
- ip netns exec ${NS[2]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log &
- ip netns exec ${NS[3]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log &
- sleep 0.5
- ip netns exec ${NS[1]} ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null
- sleep 0.5
- pkill tcpdump
-
- # mac check
- grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" ${LOG_DIR}/mac_ns1-2_${mode}.log && \
- test_pass "$mode mac ns1-2" || test_fail "$mode mac ns1-2"
- grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" ${LOG_DIR}/mac_ns1-3_${mode}.log && \
- test_pass "$mode mac ns1-3" || test_fail "$mode mac ns1-3"
-}
-
-do_ping_tests()
-{
- local mode=$1
-
- # ping6 test: echo request should be redirect back to itself, not others
- ip netns exec ${NS[1]} ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02
-
- ip netns exec ${NS[1]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log &
- ip netns exec ${NS[2]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log &
- ip netns exec ${NS[3]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log &
- sleep 0.5
- # ARP test
- ip netns exec ${NS[1]} arping -q -c 2 -I veth0 192.0.2.254
- # IPv4 test
- ip netns exec ${NS[1]} ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null
- # IPv6 test
- ip netns exec ${NS[1]} ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null
- sleep 0.5
- pkill tcpdump
-
- # All netns should receive the redirect arp requests
- [ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \
- test_pass "$mode arp(F_BROADCAST) ns1-1" || \
- test_fail "$mode arp(F_BROADCAST) ns1-1"
- [ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-2_${mode}.log) -eq 2 ] && \
- test_pass "$mode arp(F_BROADCAST) ns1-2" || \
- test_fail "$mode arp(F_BROADCAST) ns1-2"
- [ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-3_${mode}.log) -eq 2 ] && \
- test_pass "$mode arp(F_BROADCAST) ns1-3" || \
- test_fail "$mode arp(F_BROADCAST) ns1-3"
-
- # ns1 should not receive the redirect echo request, others should
- [ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \
- test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" || \
- test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1"
- [ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-2_${mode}.log) -eq 4 ] && \
- test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" || \
- test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2"
- [ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-3_${mode}.log) -eq 4 ] && \
- test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" || \
- test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3"
-
- # ns1 should receive the echo request, ns2 should not
- [ $(grep -c "ICMP6, echo request" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \
- test_pass "$mode IPv6 (no flags) ns1-1" || \
- test_fail "$mode IPv6 (no flags) ns1-1"
- [ $(grep -c "ICMP6, echo request" ${LOG_DIR}/ns1-2_${mode}.log) -eq 0 ] && \
- test_pass "$mode IPv6 (no flags) ns1-2" || \
- test_fail "$mode IPv6 (no flags) ns1-2"
-}
-
-do_tests()
-{
- local mode=$1
- local drv_p
-
- case ${mode} in
- xdpdrv) drv_p="-N";;
- xdpegress) drv_p="-X";;
- xdpgeneric) drv_p="-S";;
- esac
-
- ip netns exec ${NS[0]} ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log &
- xdp_pid=$!
- sleep 1
- if ! ps -p $xdp_pid > /dev/null; then
- test_fail "$mode xdp_redirect_multi start failed"
- return 1
- fi
-
- if [ "$mode" = "xdpegress" ]; then
- do_egress_tests $mode
- else
- do_ping_tests $mode
- fi
-
- kill $xdp_pid
-}
-
-check_env
-
-trap clean_up EXIT
-
-for mode in ${DRV_MODE}; do
- setup_ns $mode
- do_tests $mode
- clean_up
-done
-rm -rf ${LOG_DIR}
-
-echo "Summary: PASS $PASS, FAIL $FAIL"
-[ $FAIL -eq 0 ] && exit 0 || exit 1
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh
deleted file mode 100755
index fbcaa9f0120b..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_vlan.sh
+++ /dev/null
@@ -1,233 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-# Author: Jesper Dangaard Brouer <hawk@kernel.org>
-
-# Kselftest framework requirement - SKIP code is 4.
-readonly KSFT_SKIP=4
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-readonly NS2="ns2-$(mktemp -u XXXXXX)"
-
-# Allow wrapper scripts to name test
-if [ -z "$TESTNAME" ]; then
- TESTNAME=xdp_vlan
-fi
-
-# Default XDP mode
-XDP_MODE=xdpgeneric
-
-usage() {
- echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME"
- echo ""
- echo "Usage: $0 [-vfh]"
- echo " -v | --verbose : Verbose"
- echo " --flush : Flush before starting (e.g. after --interactive)"
- echo " --interactive : Keep netns setup running after test-run"
- echo " --mode=XXX : Choose XDP mode (xdp | xdpgeneric | xdpdrv)"
- echo ""
-}
-
-valid_xdp_mode()
-{
- local mode=$1
-
- case "$mode" in
- xdpgeneric | xdpdrv | xdp)
- return 0
- ;;
- *)
- return 1
- esac
-}
-
-cleanup()
-{
- local status=$?
-
- if [ "$status" = "0" ]; then
- echo "selftests: $TESTNAME [PASS]";
- else
- echo "selftests: $TESTNAME [FAILED]";
- fi
-
- if [ -n "$INTERACTIVE" ]; then
- echo "Namespace setup still active explore with:"
- echo " ip netns exec ${NS1} bash"
- echo " ip netns exec ${NS2} bash"
- exit $status
- fi
-
- set +e
- ip link del veth1 2> /dev/null
- ip netns del ${NS1} 2> /dev/null
- ip netns del ${NS2} 2> /dev/null
-}
-
-# Using external program "getopt" to get --long-options
-OPTIONS=$(getopt -o hvfi: \
- --long verbose,flush,help,interactive,debug,mode: -- "$@")
-if (( $? != 0 )); then
- usage
- echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?"
- exit 2
-fi
-eval set -- "$OPTIONS"
-
-## --- Parse command line arguments / parameters ---
-while true; do
- case "$1" in
- -v | --verbose)
- export VERBOSE=yes
- shift
- ;;
- -i | --interactive | --debug )
- INTERACTIVE=yes
- shift
- ;;
- -f | --flush )
- cleanup
- shift
- ;;
- --mode )
- shift
- XDP_MODE=$1
- shift
- ;;
- -- )
- shift
- break
- ;;
- -h | --help )
- usage;
- echo "selftests: $TESTNAME [SKIP] usage help info requested"
- exit $KSFT_SKIP
- ;;
- * )
- shift
- break
- ;;
- esac
-done
-
-if [ "$EUID" -ne 0 ]; then
- echo "selftests: $TESTNAME [FAILED] need root privileges"
- exit 1
-fi
-
-valid_xdp_mode $XDP_MODE
-if [ $? -ne 0 ]; then
- echo "selftests: $TESTNAME [FAILED] unknown XDP mode ($XDP_MODE)"
- exit 1
-fi
-
-ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null
-if [ $? -ne 0 ]; then
- echo "selftests: $TESTNAME [SKIP] need ip xdp support"
- exit $KSFT_SKIP
-fi
-
-# Interactive mode likely require us to cleanup netns
-if [ -n "$INTERACTIVE" ]; then
- ip link del veth1 2> /dev/null
- ip netns del ${NS1} 2> /dev/null
- ip netns del ${NS2} 2> /dev/null
-fi
-
-# Exit on failure
-set -e
-
-# Some shell-tools dependencies
-which ip > /dev/null
-which tc > /dev/null
-which ethtool > /dev/null
-
-# Make rest of shell verbose, showing comments as doc/info
-if [ -n "$VERBOSE" ]; then
- set -v
-fi
-
-# Create two namespaces
-ip netns add ${NS1}
-ip netns add ${NS2}
-
-# Run cleanup if failing or on kill
-trap cleanup 0 2 3 6 9
-
-# Create veth pair
-ip link add veth1 type veth peer name veth2
-
-# Move veth1 and veth2 into the respective namespaces
-ip link set veth1 netns ${NS1}
-ip link set veth2 netns ${NS2}
-
-# NOTICE: XDP require VLAN header inside packet payload
-# - Thus, disable VLAN offloading driver features
-# - For veth REMEMBER TX side VLAN-offload
-#
-# Disable rx-vlan-offload (mostly needed on ns1)
-ip netns exec ${NS1} ethtool -K veth1 rxvlan off
-ip netns exec ${NS2} ethtool -K veth2 rxvlan off
-#
-# Disable tx-vlan-offload (mostly needed on ns2)
-ip netns exec ${NS2} ethtool -K veth2 txvlan off
-ip netns exec ${NS1} ethtool -K veth1 txvlan off
-
-export IPADDR1=100.64.41.1
-export IPADDR2=100.64.41.2
-
-# In ns1/veth1 add IP-addr on plain net_device
-ip netns exec ${NS1} ip addr add ${IPADDR1}/24 dev veth1
-ip netns exec ${NS1} ip link set veth1 up
-
-# In ns2/veth2 create VLAN device
-export VLAN=4011
-export DEVNS2=veth2
-ip netns exec ${NS2} ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN
-ip netns exec ${NS2} ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN
-ip netns exec ${NS2} ip link set $DEVNS2 up
-ip netns exec ${NS2} ip link set $DEVNS2.$VLAN up
-
-# Bringup lo in netns (to avoids confusing people using --interactive)
-ip netns exec ${NS1} ip link set lo up
-ip netns exec ${NS2} ip link set lo up
-
-# At this point, the hosts cannot reach each-other,
-# because ns2 are using VLAN tags on the packets.
-
-ip netns exec ${NS2} sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"'
-
-
-# Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags
-# ----------------------------------------------------------------------
-# In ns1: ingress use XDP to remove VLAN tags
-export DEVNS1=veth1
-export BPF_FILE=test_xdp_vlan.bpf.o
-
-# First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change"
-export XDP_PROG=xdp_vlan_change
-ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $BPF_FILE section $XDP_PROG
-
-# In ns1: egress use TC to add back VLAN tag 4011
-# (del cmd)
-# tc qdisc del dev $DEVNS1 clsact 2> /dev/null
-#
-ip netns exec ${NS1} tc qdisc add dev $DEVNS1 clsact
-ip netns exec ${NS1} tc filter add dev $DEVNS1 egress \
- prio 1 handle 1 bpf da obj $BPF_FILE sec tc_vlan_push
-
-# Now the namespaces can reach each-other, test with ping:
-ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1
-ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2
-
-# Second test: Replace xdp prog, that fully remove vlan header
-#
-# Catch kernel bug for generic-XDP, that does didn't allow us to
-# remove a VLAN header, because skb->protocol still contain VLAN
-# ETH_P_8021Q indication, and this cause overwriting of our changes.
-#
-export XDP_PROG=xdp_vlan_remove_outer2
-ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE off
-ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $BPF_FILE section $XDP_PROG
-
-# Now the namespaces should still be able reach each-other, test with ping:
-ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1
-ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh
deleted file mode 100755
index c515326d6d59..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh
+++ /dev/null
@@ -1,9 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-# Exit on failure
-set -e
-
-# Wrapper script to test generic-XDP
-export TESTNAME=xdp_vlan_mode_generic
-./test_xdp_vlan.sh --mode=xdpgeneric
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh
deleted file mode 100755
index 5cf7ce1f16c1..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh
+++ /dev/null
@@ -1,9 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-# Exit on failure
-set -e
-
-# Wrapper script to test native-XDP
-export TESTNAME=xdp_vlan_mode_native
-./test_xdp_vlan.sh --mode=xdpdrv
diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index 06af5029885b..a18972ffdeb6 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -3,6 +3,7 @@
#define _GNU_SOURCE
#include <argp.h>
#include <libgen.h>
+#include <ctype.h>
#include <string.h>
#include <stdlib.h>
#include <sched.h>
@@ -154,6 +155,16 @@ struct filter {
bool abs;
};
+struct var_preset {
+ char *name;
+ enum { INTEGRAL, ENUMERATOR } type;
+ union {
+ long long ivalue;
+ char *svalue;
+ };
+ bool applied;
+};
+
static struct env {
char **filenames;
int filename_cnt;
@@ -195,6 +206,8 @@ static struct env {
int progs_processed;
int progs_skipped;
int top_src_lines;
+ struct var_preset *presets;
+ int npresets;
} env;
static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
@@ -246,16 +259,20 @@ static const struct argp_option opts[] = {
{ "test-reg-invariants", 'r', NULL, 0,
"Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" },
{ "top-src-lines", 'S', "N", 0, "Emit N most frequent source code lines" },
+ { "set-global-vars", 'G', "GLOBAL", 0, "Set global variables provided in the expression, for example \"var1 = 1\"" },
{},
};
static int parse_stats(const char *stats_str, struct stat_specs *specs);
static int append_filter(struct filter **filters, int *cnt, const char *str);
static int append_filter_file(const char *path);
+static int append_var_preset(struct var_preset **presets, int *cnt, const char *expr);
+static int append_var_preset_file(const char *filename);
+static int append_file(const char *path);
+static int append_file_from_file(const char *path);
static error_t parse_arg(int key, char *arg, struct argp_state *state)
{
- void *tmp;
int err;
switch (key) {
@@ -353,15 +370,26 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
argp_usage(state);
}
break;
+ case 'G': {
+ if (arg[0] == '@')
+ err = append_var_preset_file(arg + 1);
+ else
+ err = append_var_preset(&env.presets, &env.npresets, arg);
+ if (err) {
+ fprintf(stderr, "Failed to parse global variable presets: %s\n", arg);
+ return err;
+ }
+ break;
+ }
case ARGP_KEY_ARG:
- tmp = realloc(env.filenames, (env.filename_cnt + 1) * sizeof(*env.filenames));
- if (!tmp)
- return -ENOMEM;
- env.filenames = tmp;
- env.filenames[env.filename_cnt] = strdup(arg);
- if (!env.filenames[env.filename_cnt])
- return -ENOMEM;
- env.filename_cnt++;
+ if (arg[0] == '@')
+ err = append_file_from_file(arg + 1);
+ else
+ err = append_file(arg);
+ if (err) {
+ fprintf(stderr, "Failed to collect BPF object files: %d\n", err);
+ return err;
+ }
break;
default:
return ARGP_ERR_UNKNOWN;
@@ -632,7 +660,7 @@ static int append_filter_file(const char *path)
f = fopen(path, "r");
if (!f) {
err = -errno;
- fprintf(stderr, "Failed to open filters in '%s': %d\n", path, err);
+ fprintf(stderr, "Failed to open filters in '%s': %s\n", path, strerror(-err));
return err;
}
@@ -662,6 +690,49 @@ static const struct stat_specs default_output_spec = {
},
};
+static int append_file(const char *path)
+{
+ void *tmp;
+
+ tmp = realloc(env.filenames, (env.filename_cnt + 1) * sizeof(*env.filenames));
+ if (!tmp)
+ return -ENOMEM;
+ env.filenames = tmp;
+ env.filenames[env.filename_cnt] = strdup(path);
+ if (!env.filenames[env.filename_cnt])
+ return -ENOMEM;
+ env.filename_cnt++;
+ return 0;
+}
+
+static int append_file_from_file(const char *path)
+{
+ char buf[1024];
+ int err = 0;
+ FILE *f;
+
+ f = fopen(path, "r");
+ if (!f) {
+ err = -errno;
+ fprintf(stderr, "Failed to open object files list in '%s': %s\n",
+ path, strerror(errno));
+ return err;
+ }
+
+ while (fscanf(f, " %1023[^\n]\n", buf) == 1) {
+ /* lines starting with # are comments, skip them */
+ if (buf[0] == '\0' || buf[0] == '#')
+ continue;
+ err = append_file(buf);
+ if (err)
+ goto cleanup;
+ }
+
+cleanup:
+ fclose(f);
+ return err;
+}
+
static const struct stat_specs default_csv_output_spec = {
.spec_cnt = 14,
.ids = {
@@ -1163,13 +1234,13 @@ static void fixup_obj(struct bpf_object *obj, struct bpf_program *prog, const ch
bpf_program__set_expected_attach_type(prog, attach_type);
if (!env.quiet) {
- printf("Using guessed program type '%s' for %s/%s...\n",
+ fprintf(stderr, "Using guessed program type '%s' for %s/%s...\n",
libbpf_bpf_prog_type_str(prog_type),
filename, prog_name);
}
} else {
if (!env.quiet) {
- printf("Failed to guess program type for freplace program with context type name '%s' for %s/%s. Consider using canonical type names to help veristat...\n",
+ fprintf(stderr, "Failed to guess program type for freplace program with context type name '%s' for %s/%s. Consider using canonical type names to help veristat...\n",
ctx_name, filename, prog_name);
}
}
@@ -1292,6 +1363,261 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
return 0;
};
+static int append_var_preset(struct var_preset **presets, int *cnt, const char *expr)
+{
+ void *tmp;
+ struct var_preset *cur;
+ char var[256], val[256], *val_end;
+ long long value;
+ int n;
+
+ tmp = realloc(*presets, (*cnt + 1) * sizeof(**presets));
+ if (!tmp)
+ return -ENOMEM;
+ *presets = tmp;
+ cur = &(*presets)[*cnt];
+ memset(cur, 0, sizeof(*cur));
+ (*cnt)++;
+
+ if (sscanf(expr, "%s = %s %n", var, val, &n) != 2 || n != strlen(expr)) {
+ fprintf(stderr, "Failed to parse expression '%s'\n", expr);
+ return -EINVAL;
+ }
+
+ if (val[0] == '-' || isdigit(val[0])) {
+ /* must be a number */
+ errno = 0;
+ value = strtoll(val, &val_end, 0);
+ if (errno == ERANGE) {
+ errno = 0;
+ value = strtoull(val, &val_end, 0);
+ }
+ if (errno || *val_end != '\0') {
+ fprintf(stderr, "Failed to parse value '%s'\n", val);
+ return -EINVAL;
+ }
+ cur->ivalue = value;
+ cur->type = INTEGRAL;
+ } else {
+ /* if not a number, consider it enum value */
+ cur->svalue = strdup(val);
+ if (!cur->svalue)
+ return -ENOMEM;
+ cur->type = ENUMERATOR;
+ }
+
+ cur->name = strdup(var);
+ if (!cur->name)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int append_var_preset_file(const char *filename)
+{
+ char buf[1024];
+ FILE *f;
+ int err = 0;
+
+ f = fopen(filename, "rt");
+ if (!f) {
+ err = -errno;
+ fprintf(stderr, "Failed to open presets in '%s': %s\n", filename, strerror(-err));
+ return -EINVAL;
+ }
+
+ while (fscanf(f, " %1023[^\n]\n", buf) == 1) {
+ if (buf[0] == '\0' || buf[0] == '#')
+ continue;
+
+ err = append_var_preset(&env.presets, &env.npresets, buf);
+ if (err)
+ goto cleanup;
+ }
+
+cleanup:
+ fclose(f);
+ return err;
+}
+
+static bool is_signed_type(const struct btf_type *t)
+{
+ if (btf_is_int(t))
+ return btf_int_encoding(t) & BTF_INT_SIGNED;
+ if (btf_is_any_enum(t))
+ return btf_kflag(t);
+ return true;
+}
+
+static int enum_value_from_name(const struct btf *btf, const struct btf_type *t,
+ const char *evalue, long long *retval)
+{
+ if (btf_is_enum(t)) {
+ struct btf_enum *e = btf_enum(t);
+ int i, n = btf_vlen(t);
+
+ for (i = 0; i < n; ++i, ++e) {
+ const char *cur_name = btf__name_by_offset(btf, e->name_off);
+
+ if (strcmp(cur_name, evalue) == 0) {
+ *retval = e->val;
+ return 0;
+ }
+ }
+ } else if (btf_is_enum64(t)) {
+ struct btf_enum64 *e = btf_enum64(t);
+ int i, n = btf_vlen(t);
+
+ for (i = 0; i < n; ++i, ++e) {
+ const char *cur_name = btf__name_by_offset(btf, e->name_off);
+ __u64 value = btf_enum64_value(e);
+
+ if (strcmp(cur_name, evalue) == 0) {
+ *retval = value;
+ return 0;
+ }
+ }
+ }
+ return -EINVAL;
+}
+
+static bool is_preset_supported(const struct btf_type *t)
+{
+ return btf_is_int(t) || btf_is_enum(t) || btf_is_enum64(t);
+}
+
+static int set_global_var(struct bpf_object *obj, struct btf *btf, const struct btf_type *t,
+ struct bpf_map *map, struct btf_var_secinfo *sinfo,
+ struct var_preset *preset)
+{
+ const struct btf_type *base_type;
+ void *ptr;
+ long long value = preset->ivalue;
+ size_t size;
+
+ base_type = btf__type_by_id(btf, btf__resolve_type(btf, t->type));
+ if (!base_type) {
+ fprintf(stderr, "Failed to resolve type %d\n", t->type);
+ return -EINVAL;
+ }
+ if (!is_preset_supported(base_type)) {
+ fprintf(stderr, "Setting value for type %s is not supported\n",
+ btf__name_by_offset(btf, base_type->name_off));
+ return -EINVAL;
+ }
+
+ if (preset->type == ENUMERATOR) {
+ if (btf_is_any_enum(base_type)) {
+ if (enum_value_from_name(btf, base_type, preset->svalue, &value)) {
+ fprintf(stderr,
+ "Failed to find integer value for enum element %s\n",
+ preset->svalue);
+ return -EINVAL;
+ }
+ } else {
+ fprintf(stderr, "Value %s is not supported for type %s\n",
+ preset->svalue, btf__name_by_offset(btf, base_type->name_off));
+ return -EINVAL;
+ }
+ }
+
+ /* Check if value fits into the target variable size */
+ if (sinfo->size < sizeof(value)) {
+ bool is_signed = is_signed_type(base_type);
+ __u32 unsigned_bits = sinfo->size * 8 - (is_signed ? 1 : 0);
+ long long max_val = 1ll << unsigned_bits;
+
+ if (value >= max_val || value < -max_val) {
+ fprintf(stderr,
+ "Variable %s value %lld is out of range [%lld; %lld]\n",
+ btf__name_by_offset(btf, t->name_off), value,
+ is_signed ? -max_val : 0, max_val - 1);
+ return -EINVAL;
+ }
+ }
+
+ ptr = bpf_map__initial_value(map, &size);
+ if (!ptr || sinfo->offset + sinfo->size > size)
+ return -EINVAL;
+
+ if (__BYTE_ORDER == __LITTLE_ENDIAN) {
+ memcpy(ptr + sinfo->offset, &value, sinfo->size);
+ } else { /* __BYTE_ORDER == __BIG_ENDIAN */
+ __u8 src_offset = sizeof(value) - sinfo->size;
+
+ memcpy(ptr + sinfo->offset, (void *)&value + src_offset, sinfo->size);
+ }
+ return 0;
+}
+
+static int set_global_vars(struct bpf_object *obj, struct var_preset *presets, int npresets)
+{
+ struct btf_var_secinfo *sinfo;
+ const char *sec_name;
+ const struct btf_type *t;
+ struct bpf_map *map;
+ struct btf *btf;
+ int i, j, k, n, cnt, err = 0;
+
+ if (npresets == 0)
+ return 0;
+
+ btf = bpf_object__btf(obj);
+ if (!btf)
+ return -EINVAL;
+
+ cnt = btf__type_cnt(btf);
+ for (i = 1; i != cnt; ++i) {
+ t = btf__type_by_id(btf, i);
+
+ if (!btf_is_datasec(t))
+ continue;
+
+ sinfo = btf_var_secinfos(t);
+ sec_name = btf__name_by_offset(btf, t->name_off);
+ map = bpf_object__find_map_by_name(obj, sec_name);
+ if (!map)
+ continue;
+
+ n = btf_vlen(t);
+ for (j = 0; j < n; ++j, ++sinfo) {
+ const struct btf_type *var_type = btf__type_by_id(btf, sinfo->type);
+ const char *var_name;
+
+ if (!btf_is_var(var_type))
+ continue;
+
+ var_name = btf__name_by_offset(btf, var_type->name_off);
+
+ for (k = 0; k < npresets; ++k) {
+ if (strcmp(var_name, presets[k].name) != 0)
+ continue;
+
+ if (presets[k].applied) {
+ fprintf(stderr, "Variable %s is set more than once",
+ var_name);
+ return -EINVAL;
+ }
+
+ err = set_global_var(obj, btf, var_type, map, sinfo, presets + k);
+ if (err)
+ return err;
+
+ presets[k].applied = true;
+ break;
+ }
+ }
+ }
+ for (i = 0; i < npresets; ++i) {
+ if (!presets[i].applied) {
+ fprintf(stderr, "Global variable preset %s has not been applied\n",
+ presets[i].name);
+ }
+ presets[i].applied = false;
+ }
+ return err;
+}
+
static int process_obj(const char *filename)
{
const char *base_filename = basename(strdupa(filename));
@@ -1341,6 +1667,11 @@ static int process_obj(const char *filename)
if (prog_cnt == 1) {
prog = bpf_object__next_program(obj, NULL);
bpf_program__set_autoload(prog, true);
+ err = set_global_vars(obj, env.presets, env.npresets);
+ if (err) {
+ fprintf(stderr, "Failed to set global variables %d\n", err);
+ goto cleanup;
+ }
process_prog(filename, obj, prog);
goto cleanup;
}
@@ -1355,6 +1686,12 @@ static int process_obj(const char *filename)
goto cleanup;
}
+ err = set_global_vars(tobj, env.presets, env.npresets);
+ if (err) {
+ fprintf(stderr, "Failed to set global variables %d\n", err);
+ goto cleanup;
+ }
+
lprog = NULL;
bpf_object__for_each_program(tprog, tobj) {
const char *tprog_name = bpf_program__name(tprog);
@@ -2460,5 +2797,11 @@ int main(int argc, char **argv)
free(env.deny_filters[i].prog_glob);
}
free(env.deny_filters);
+ for (i = 0; i < env.npresets; ++i) {
+ free(env.presets[i].name);
+ if (env.presets[i].type == ENUMERATOR)
+ free(env.presets[i].svalue);
+ }
+ free(env.presets);
return -err;
}
diff --git a/tools/testing/selftests/bpf/with_addr.sh b/tools/testing/selftests/bpf/with_addr.sh
deleted file mode 100755
index ffcd3953f94c..000000000000
--- a/tools/testing/selftests/bpf/with_addr.sh
+++ /dev/null
@@ -1,54 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# add private ipv4 and ipv6 addresses to loopback
-
-readonly V6_INNER='100::a/128'
-readonly V4_INNER='192.168.0.1/32'
-
-if getopts ":s" opt; then
- readonly SIT_DEV_NAME='sixtofourtest0'
- readonly V6_SIT='2::/64'
- readonly V4_SIT='172.17.0.1/32'
- shift
-fi
-
-fail() {
- echo "error: $*" 1>&2
- exit 1
-}
-
-setup() {
- ip -6 addr add "${V6_INNER}" dev lo || fail 'failed to setup v6 address'
- ip -4 addr add "${V4_INNER}" dev lo || fail 'failed to setup v4 address'
-
- if [[ -n "${V6_SIT}" ]]; then
- ip link add "${SIT_DEV_NAME}" type sit remote any local any \
- || fail 'failed to add sit'
- ip link set dev "${SIT_DEV_NAME}" up \
- || fail 'failed to bring sit device up'
- ip -6 addr add "${V6_SIT}" dev "${SIT_DEV_NAME}" \
- || fail 'failed to setup v6 SIT address'
- ip -4 addr add "${V4_SIT}" dev "${SIT_DEV_NAME}" \
- || fail 'failed to setup v4 SIT address'
- fi
-
- sleep 2 # avoid race causing bind to fail
-}
-
-cleanup() {
- if [[ -n "${V6_SIT}" ]]; then
- ip -4 addr del "${V4_SIT}" dev "${SIT_DEV_NAME}"
- ip -6 addr del "${V6_SIT}" dev "${SIT_DEV_NAME}"
- ip link del "${SIT_DEV_NAME}"
- fi
-
- ip -4 addr del "${V4_INNER}" dev lo
- ip -6 addr del "${V6_INNER}" dev lo
-}
-
-trap cleanup EXIT
-
-setup
-"$@"
-exit "$?"
diff --git a/tools/testing/selftests/bpf/with_tunnels.sh b/tools/testing/selftests/bpf/with_tunnels.sh
deleted file mode 100755
index e24949ed3a20..000000000000
--- a/tools/testing/selftests/bpf/with_tunnels.sh
+++ /dev/null
@@ -1,36 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# setup tunnels for flow dissection test
-
-readonly SUFFIX="test_$(mktemp -u XXXX)"
-CONFIG="remote 127.0.0.2 local 127.0.0.1 dev lo"
-
-setup() {
- ip link add "ipip_${SUFFIX}" type ipip ${CONFIG}
- ip link add "gre_${SUFFIX}" type gre ${CONFIG}
- ip link add "sit_${SUFFIX}" type sit ${CONFIG}
-
- echo "tunnels before test:"
- ip tunnel show
-
- ip link set "ipip_${SUFFIX}" up
- ip link set "gre_${SUFFIX}" up
- ip link set "sit_${SUFFIX}" up
-}
-
-
-cleanup() {
- ip tunnel del "ipip_${SUFFIX}"
- ip tunnel del "gre_${SUFFIX}"
- ip tunnel del "sit_${SUFFIX}"
-
- echo "tunnels after test:"
- ip tunnel show
-}
-
-trap cleanup EXIT
-
-setup
-"$@"
-exit "$?"
diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c
deleted file mode 100644
index c1fc44c87c30..000000000000
--- a/tools/testing/selftests/bpf/xdp_redirect_multi.c
+++ /dev/null
@@ -1,226 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
-#include <linux/if_link.h>
-#include <assert.h>
-#include <errno.h>
-#include <signal.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <net/if.h>
-#include <unistd.h>
-#include <libgen.h>
-#include <sys/ioctl.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <netinet/in.h>
-
-#include "bpf_util.h"
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#define MAX_IFACE_NUM 32
-#define MAX_INDEX_NUM 1024
-
-static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-static int ifaces[MAX_IFACE_NUM] = {};
-
-static void int_exit(int sig)
-{
- __u32 prog_id = 0;
- int i;
-
- for (i = 0; ifaces[i] > 0; i++) {
- if (bpf_xdp_query_id(ifaces[i], xdp_flags, &prog_id)) {
- printf("bpf_xdp_query_id failed\n");
- exit(1);
- }
- if (prog_id)
- bpf_xdp_detach(ifaces[i], xdp_flags, NULL);
- }
-
- exit(0);
-}
-
-static int get_mac_addr(unsigned int ifindex, void *mac_addr)
-{
- char ifname[IF_NAMESIZE];
- struct ifreq ifr;
- int fd, ret = -1;
-
- fd = socket(AF_INET, SOCK_DGRAM, 0);
- if (fd < 0)
- return ret;
-
- if (!if_indextoname(ifindex, ifname))
- goto err_out;
-
- strcpy(ifr.ifr_name, ifname);
-
- if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
- goto err_out;
-
- memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
- ret = 0;
-
-err_out:
- close(fd);
- return ret;
-}
-
-static void usage(const char *prog)
-{
- fprintf(stderr,
- "usage: %s [OPTS] <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n"
- "OPTS:\n"
- " -S use skb-mode\n"
- " -N enforce native mode\n"
- " -F force loading prog\n"
- " -X load xdp program on egress\n",
- prog);
-}
-
-int main(int argc, char **argv)
-{
- int prog_fd, group_all, mac_map;
- struct bpf_program *ingress_prog, *egress_prog;
- int i, err, ret, opt, egress_prog_fd = 0;
- struct bpf_devmap_val devmap_val;
- bool attach_egress_prog = false;
- unsigned char mac_addr[6];
- char ifname[IF_NAMESIZE];
- struct bpf_object *obj;
- unsigned int ifindex;
- char filename[256];
-
- while ((opt = getopt(argc, argv, "SNFX")) != -1) {
- switch (opt) {
- case 'S':
- xdp_flags |= XDP_FLAGS_SKB_MODE;
- break;
- case 'N':
- /* default, set below */
- break;
- case 'F':
- xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
- break;
- case 'X':
- attach_egress_prog = true;
- break;
- default:
- usage(basename(argv[0]));
- return 1;
- }
- }
-
- if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) {
- xdp_flags |= XDP_FLAGS_DRV_MODE;
- } else if (attach_egress_prog) {
- printf("Load xdp program on egress with SKB mode not supported yet\n");
- goto err_out;
- }
-
- if (optind == argc) {
- printf("usage: %s <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n", argv[0]);
- goto err_out;
- }
-
- printf("Get interfaces:");
- for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
- ifaces[i] = if_nametoindex(argv[optind + i]);
- if (!ifaces[i])
- ifaces[i] = strtoul(argv[optind + i], NULL, 0);
- if (!if_indextoname(ifaces[i], ifname)) {
- perror("Invalid interface name or i");
- goto err_out;
- }
- if (ifaces[i] > MAX_INDEX_NUM) {
- printf(" interface index too large\n");
- goto err_out;
- }
- printf(" %d", ifaces[i]);
- }
- printf("\n");
-
- snprintf(filename, sizeof(filename), "%s_kern.bpf.o", argv[0]);
- obj = bpf_object__open_file(filename, NULL);
- err = libbpf_get_error(obj);
- if (err)
- goto err_out;
- err = bpf_object__load(obj);
- if (err)
- goto err_out;
- prog_fd = bpf_program__fd(bpf_object__next_program(obj, NULL));
-
- if (attach_egress_prog)
- group_all = bpf_object__find_map_fd_by_name(obj, "map_egress");
- else
- group_all = bpf_object__find_map_fd_by_name(obj, "map_all");
- mac_map = bpf_object__find_map_fd_by_name(obj, "mac_map");
-
- if (group_all < 0 || mac_map < 0) {
- printf("bpf_object__find_map_fd_by_name failed\n");
- goto err_out;
- }
-
- if (attach_egress_prog) {
- /* Find ingress/egress prog for 2nd xdp prog */
- ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_all_prog");
- egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog");
- if (!ingress_prog || !egress_prog) {
- printf("finding ingress/egress_prog in obj file failed\n");
- goto err_out;
- }
- prog_fd = bpf_program__fd(ingress_prog);
- egress_prog_fd = bpf_program__fd(egress_prog);
- if (prog_fd < 0 || egress_prog_fd < 0) {
- printf("find egress_prog fd failed\n");
- goto err_out;
- }
- }
-
- signal(SIGINT, int_exit);
- signal(SIGTERM, int_exit);
-
- /* Init forward multicast groups and exclude group */
- for (i = 0; ifaces[i] > 0; i++) {
- ifindex = ifaces[i];
-
- if (attach_egress_prog) {
- ret = get_mac_addr(ifindex, mac_addr);
- if (ret < 0) {
- printf("get interface %d mac failed\n", ifindex);
- goto err_out;
- }
- ret = bpf_map_update_elem(mac_map, &ifindex, mac_addr, 0);
- if (ret) {
- perror("bpf_update_elem mac_map failed\n");
- goto err_out;
- }
- }
-
- /* Add all the interfaces to group all */
- devmap_val.ifindex = ifindex;
- devmap_val.bpf_prog.fd = egress_prog_fd;
- ret = bpf_map_update_elem(group_all, &ifindex, &devmap_val, 0);
- if (ret) {
- perror("bpf_map_update_elem");
- goto err_out;
- }
-
- /* bind prog_fd to each interface */
- ret = bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL);
- if (ret) {
- printf("Set xdp fd failed on %d\n", ifindex);
- goto err_out;
- }
- }
-
- /* sleep some time for testing */
- sleep(999);
-
- return 0;
-
-err_out:
- return 1;
-}
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 400a696a0d21..a17256d9f88a 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -88,22 +88,32 @@ 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 0-8
# that will be used by this script for testing purpose. If not, some of
-# the tests may fail incorrectly. These pre-isolated CPUs should stay in
-# an isolated state throughout the testing process for now.
+# the tests may fail incorrectly. Wait a bit and retry again just in case
+# these isolated CPUs are leftover from previous run and have just been
+# cleaned up earlier in this script.
+#
+# These pre-isolated CPUs should stay in an isolated state throughout the
+# testing process for now.
#
BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
+[[ -n "$BOOT_ISOLCPUS" ]] && {
+ sleep 0.5
+ BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
+}
if [[ -n "$BOOT_ISOLCPUS" ]]
then
[[ $(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
+
cleanup()
{
online_cpus
cd $CGROUP2
- rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1
- rmdir test > /dev/null 2>&1
+ rmdir A1/A2/A3 A1/A2 A1 B1 test/A1 test/B1 test > /dev/null 2>&1
+ rmdir rtest/p1/c11 rtest/p1/c12 rtest/p2/c21 \
+ rtest/p2/c22 rtest/p1 rtest/p2 rtest > /dev/null 2>&1
[[ -n "$SCHED_DEBUG" ]] &&
echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose
}
@@ -173,14 +183,22 @@ test_add_proc()
#
# Cgroup test hierarchy
#
-# root -- A1 -- A2 -- A3
-# +- B1
+# root
+# |
+# +------+------+
+# | |
+# A1 B1
+# |
+# A2
+# |
+# A3
#
# P<v> = set cpus.partition (0:member, 1:root, 2:isolated)
# C<l> = add cpu-list to cpuset.cpus
# X<l> = add cpu-list to cpuset.cpus.exclusive
# S<p> = use prefix in subtree_control
# T = put a task into cgroup
+# CX<l> = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive
# O<c>=<v> = Write <v> to CPU online file of <c>
#
# ECPUs - effective CPUs of cpusets
@@ -207,130 +225,129 @@ TEST_MATRIX=(
" C0-1:P1 . . C2-3 S+:C4-5 . . . 0 A1:4-5"
" C0-1 . . C2-3:P1 . . . C2 0 "
" C0-1 . . C2-3:P1 . . . C4-5 0 B1:4-5"
- "C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1,A2:2-3"
- "C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1,A2:2-3"
- "C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:,A2:3 A1:P1,A2:P1"
- "C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3,A2:3 A1:P1,A2:P0"
- "C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4,A2:2"
- "C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:,B1:0-2 A1:P1,A2:P1"
- "$SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+ "C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3"
+ "C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3"
+ "C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
+ "C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0"
+ "C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2"
+ "C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1"
+ "$SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
# CPU offlining cases:
- " C0-1 . . C2-3 S+ C4-5 . O2=0 0 A1:0-1,B1:3"
- "C0-3:P1:S+ C2-3:P1 . . O2=0 . . . 0 A1:0-1,A2:3"
- "C0-3:P1:S+ C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1,A2:2-3"
- "C0-3:P1:S+ C2-3:P1 . . O1=0 . . . 0 A1:0,A2:2-3"
- "C0-3:P1:S+ C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1,A2:2-3"
- "C2-3:P1:S+ C3:P1 . . O3=0 O3=1 . . 0 A1:2,A2:3 A1:P1,A2:P1"
- "C2-3:P1:S+ C3:P2 . . O3=0 O3=1 . . 0 A1:2,A2:3 A1:P1,A2:P2"
- "C2-3:P1:S+ C3:P1 . . O2=0 O2=1 . . 0 A1:2,A2:3 A1:P1,A2:P1"
- "C2-3:P1:S+ C3:P2 . . O2=0 O2=1 . . 0 A1:2,A2:3 A1:P1,A2:P2"
- "C2-3:P1:S+ C3:P1 . . O2=0 . . . 0 A1:,A2:3 A1:P1,A2:P1"
- "C2-3:P1:S+ C3:P1 . . O3=0 . . . 0 A1:2,A2: A1:P1,A2:P1"
- "C2-3:P1:S+ C3:P1 . . T:O2=0 . . . 0 A1:3,A2:3 A1:P1,A2:P-1"
- "C2-3:P1:S+ C3:P1 . . . T:O3=0 . . 0 A1:2,A2:2 A1:P1,A2:P-1"
- "$SETUP_A123_PARTITIONS . O1=0 . . . 0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . O2=0 . . . 0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . O3=0 . . . 0 A1:1,A2:2,A3: A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . T:O1=0 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
- "$SETUP_A123_PARTITIONS . . T:O2=0 . . 0 A1:1,A2:3,A3:3 A1:P1,A2:P1,A3:P-1"
- "$SETUP_A123_PARTITIONS . . . T:O3=0 . 0 A1:1,A2:2,A3:2 A1:P1,A2:P1,A3:P-1"
- "$SETUP_A123_PARTITIONS . T:O1=0 O1=1 . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . . T:O2=0 O2=1 . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . . . T:O3=0 O3=1 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . T:O1=0 O2=0 O1=1 . 0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1"
- "$SETUP_A123_PARTITIONS . T:O1=0 O2=0 O2=1 . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
+ " C0-1 . . C2-3 S+ C4-5 . O2=0 0 A1:0-1|B1:3"
+ "C0-3:P1:S+ C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3"
+ "C0-3:P1:S+ C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3"
+ "C0-3:P1:S+ C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3"
+ "C0-3:P1:S+ C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3"
+ "C2-3:P1:S+ C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
+ "C2-3:P1:S+ C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2"
+ "C2-3:P1:S+ C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
+ "C2-3:P1:S+ C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2"
+ "C2-3:P1:S+ C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1"
+ "C2-3:P1:S+ C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1"
+ "C2-3:P1:S+ C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1"
+ "C2-3:P1:S+ C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1"
+ "$SETUP_A123_PARTITIONS . O1=0 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . O2=0 . . . 0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . O3=0 . . . 0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . T:O1=0 . . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
+ "$SETUP_A123_PARTITIONS . . T:O2=0 . . 0 A1:1|A2:3|A3:3 A1:P1|A2:P1|A3:P-1"
+ "$SETUP_A123_PARTITIONS . . . T:O3=0 . 0 A1:1|A2:2|A3:2 A1:P1|A2:P1|A3:P-1"
+ "$SETUP_A123_PARTITIONS . T:O1=0 O1=1 . . 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . . T:O2=0 O2=1 . 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . . . T:O3=0 O3=1 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . T:O1=0 O2=0 O1=1 . 0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
+ "$SETUP_A123_PARTITIONS . T:O1=0 O2=0 O2=1 . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
#
# Remote partition and cpuset.cpus.exclusive tests
#
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 . . . 0 A1:0-3,A2:1-3,A3:2-3,XA1:2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1,A2:2-3,A3:2-3 A1:P0,A2:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2,A2:3,A3:3 A1:P0,A2:P2 3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-3,A2:1-3,A3:2-3,B1:2-3 A1:P0,A3:P0,B1:P-2"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-3|A2:1-3|A3:2-3|B1:2-3 A1:P0|A3:P0|B1:P-2"
" C0-3:S+ C1-3:S+ C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3,B1:4 A3:P2,B1:P2 2-4"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3,B1:4 A3:P2,B1:P2 2-4"
- " C0-3:S+ C1-3:S+ C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1,A3:2-3 A2:P2,A3:P2 1-3"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3,B1:4-5 A3:P2,B1:P2 2-5"
- " C4:X0-3:S+ X1-3:S+ X2-3 . . P2 . . 0 A1:4,A2:1-3,A3:1-3 A2:P2 1-3"
- " C4:X0-3:S+ X1-3:S+ X2-3 . . . P2 . 0 A1:4,A2:4,A3:2-3 A3:P2 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
+ " C4:X0-3:S+ X1-3:S+ X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
+ " C4:X0-3:S+ X1-3:S+ X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
# Nested remote/local partition tests
- " C0-3:S+ C1-3:S+ C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1,A2:,A3:2-3,B1:4-5 \
- A1:P0,A2:P1,A3:P2,B1:P1 2-3"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1,A2:,A3:2-3,B1:4 \
- A1:P0,A2:P1,A3:P2,B1:P1 2-4,2-3"
- " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1,A2:2-3,A3:2-3,B1:4 \
- A1:P0,A2:P1,A3:P0,B1:P1"
- " C0-3:S+ C1-3:S+ C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1,A2:2,A3:3,B1:4 \
- A1:P0,A2:P1,A3:P2,B1:P1 2-4,3"
- " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1,A2:2-3,A3:4 \
- A1:P0,A2:P2,A3:P1 2-4,2-3"
- " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1,A2:2,A3:3-4 \
- A1:P0,A2:P2,A3:P1 2"
+ " C0-3:S+ C1-3:S+ C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \
+ A1:P0|A2:P1|A3:P2|B1:P1 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \
+ A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3"
+ " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
+ A1:P0|A2:P1|A3:P0|B1:P1"
+ " C0-3:S+ C1-3:S+ C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \
+ A1:P0|A2:P1|A3:P2|B1:P1 2-4|3"
+ " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \
+ A1:P0|A2:P2|A3:P1 2-4|2-3"
+ " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \
+ A1:P0|A2:P2|A3:P1 2"
" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
- . . X5 . . 0 A1:0-4,A2:1-4,A3:2-4 \
- A1:P0,A2:P-2,A3:P-1"
+ . . X5 . . 0 A1:0-4|A2:1-4|A3:2-4 \
+ A1:P0|A2:P-2|A3:P-1 ."
" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
- . . . X1 . 0 A1:0-1,A2:2-4,A3:2-4 \
- A1:P0,A2:P2,A3:P-1 2-4"
+ . . . X1 . 0 A1:0-1|A2:2-4|A3:2-4 \
+ A1:P0|A2:P2|A3:P-1 2-4"
# Remote partition offline tests
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1,A2:1,A3:3 A1:P0,A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1,A2:1,A3:2-3 A1:P0,A3:P2 2-3"
- " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2,A2:1-2,A3: A1:P0,A3:P2 3"
- " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2,A2:1-2,A3:1-2 A1:P0,A3:P-2 3,"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
+ " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+ " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
+ " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
# An invalidated remote partition cannot self-recover from hotplug
- " C0-3:S+ C1-3:S+ C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3,A2:1-3,A3:2 A1:P0,A3:P-2"
+ " C0-3:S+ C1-3:S+ C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
# cpus.exclusive.effective clearing test
- " C0-3:S+ C1-3:S+ C2 . X2-3:X . . . 0 A1:0-3,A2:1-3,A3:2,XA1:"
+ " C0-3:S+ C1-3:S+ C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:"
# Invalid to valid remote partition transition test
- " C0-3:S+ C1-3 . . . X3:P2 . . 0 A1:0-3,A2:1-3,XA2: A2:P-2"
+ " C0-3:S+ C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
" C0-3:S+ C1-3:X3:P2
- . . X2-3 P2 . . 0 A1:0-2,A2:3,XA2:3 A2:P2 3"
+ . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3"
# Invalid to valid local partition direct transition tests
- " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3,XA1:1-3,A2:1-3:XA2: A1:P2,A2:P-2 1-3"
- " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2,XA1:1-3,A2:3:XA2:3 A1:P2,A2:P2 1-3"
- " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4,B1:4-6 A1:P-2,B1:P0"
- " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3,B1:4-6 A1:P2,B1:P0 0-3"
- " C0-3:P2 . . C3-5:C4-5 . . . . 0 A1:0-3,B1:4-5 A1:P2,B1:P0 0-3"
+ " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
+ " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
+ " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:4-6 A1:P-2|B1:P0"
+ " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
# Local partition invalidation tests
" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
- . . . . . 0 A1:1,A2:2,A3:3 A1:P2,A2:P2,A3:P2 1-3"
+ . . . . . 0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3"
" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
- . . X4 . . 0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3"
+ . . X4 . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
- . . C4:X . . 0 A1:1-3,A2:1-3,A3:2-3,XA2:,XA3: A1:P2,A2:P-2,A3:P-2 1-3"
+ . . C4:X . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
# Local partition CPU change tests
- " C0-5:S+:P2 C4-5:S+:P1 . . . C3-5 . . 0 A1:0-2,A2:3-5 A1:P2,A2:P1 0-2"
- " C0-5:S+:P2 C4-5:S+:P1 . . C1-5 . . . 0 A1:1-3,A2:4-5 A1:P2,A2:P1 1-3"
+ " C0-5:S+:P2 C4-5:S+:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
+ " C0-5:S+:P2 C4-5:S+:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
# cpus_allowed/exclusive_cpus update tests
" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
- . X:C4 . P2 . 0 A1:4,A2:4,XA2:,XA3:,A3:4 \
- A1:P0,A3:P-2"
+ . X:C4 . P2 . 0 A1:4|A2:4|XA2:|XA3:|A3:4 \
+ A1:P0|A3:P-2 ."
" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
- . X1 . P2 . 0 A1:0-3,A2:1-3,XA1:1,XA2:,XA3:,A3:2-3 \
- A1:P0,A3:P-2"
+ . X1 . P2 . 0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \
+ A1:P0|A3:P-2 ."
" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
- . . X3 P2 . 0 A1:0-2,A2:1-2,XA2:3,XA3:3,A3:3 \
- A1:P0,A3:P2 3"
+ . . X3 P2 . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \
+ A1:P0|A3:P2 3"
" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
- . . X3 . . 0 A1:0-3,A2:1-3,XA2:3,XA3:3,A3:2-3 \
- A1:P0,A3:P-2"
+ . . X3 . . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \
+ A1:P0|A3:P2 3"
" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
- . X4 . . . 0 A1:0-3,A2:1-3,A3:2-3,XA1:4,XA2:,XA3 \
- A1:P0,A3:P-2"
+ . X4 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \
+ A1:P0|A3:P-2"
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
@@ -339,68 +356,127 @@ TEST_MATRIX=(
#
# Adding CPUs to partition root that are not in parent's
# cpuset.cpus is allowed, but those extra CPUs are ignored.
- "C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:,A2:2-3 A1:P1,A2:P1"
+ "C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1"
# Taking away all CPUs from parent or itself if there are tasks
# will make the partition invalid.
- "C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3,A2:2-3 A1:P1,A2:P-1"
- " C3:P1:S+ C3 . . T P1 . . 0 A1:3,A2:3 A1:P1,A2:P-1"
- "$SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
- "$SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+ "C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
+ " C3:P1:S+ C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1"
+ "$SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
+ "$SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
# Changing a partition root to member makes child partitions invalid
- "C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3,A2:3 A1:P0,A2:P-1"
- "$SETUP_A123_PARTITIONS . C2-3 P0 . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P0,A3:P-1"
+ "C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1"
+ "$SETUP_A123_PARTITIONS . C2-3 P0 . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1"
# cpuset.cpus can contains cpus not in parent's cpuset.cpus as long
# as they overlap.
- "C2-3:P1:S+ . . . . C3-4:P1 . . 0 A1:2,A2:3 A1:P1,A2:P1"
+ "C2-3:P1:S+ . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1"
# Deletion of CPUs distributed to child cgroup is allowed.
- "C0-1:P1:S+ C1 . C2-3 C4-5 . . . 0 A1:4-5,A2:4-5"
+ "C0-1:P1:S+ C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5"
# To become a valid partition root, cpuset.cpus must overlap parent's
# cpuset.cpus.
- " C0-1:P1 . . C2-3 S+ C4-5:P1 . . 0 A1:0-1,A2:0-1 A1:P1,A2:P-1"
+ " C0-1:P1 . . C2-3 S+ C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
# Enabling partition with child cpusets is allowed
- " C0-1:S+ C1 . C2-3 P1 . . . 0 A1:0-1,A2:1 A1:P1"
+ " C0-1:S+ C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1"
- # A partition root with non-partition root parent is invalid, but it
+ # A partition root with non-partition root parent is invalid| but it
# can be made valid if its parent becomes a partition root too.
- " C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1,A2:1 A1:P0,A2:P-2"
- " C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0,A2:1 A1:P1,A2:P2"
+ " C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2"
+ " C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
# A non-exclusive cpuset.cpus change will invalidate partition and its siblings
- " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2,B1:2-3 A1:P-1,B1:P0"
- " C0-1:P1 . . P1:C2-3 C0-2 . . . 0 A1:0-2,B1:2-3 A1:P-1,B1:P-1"
- " C0-1 . . P1:C2-3 C0-2 . . . 0 A1:0-2,B1:2-3 A1:P0,B1:P-1"
+ " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P-1|B1:P0"
+ " C0-1:P1 . . P1:C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P-1|B1:P-1"
+ " C0-1 . . P1:C2-3 C0-2 . . . 0 A1:0-2|B1:2-3 A1:P0|B1:P-1"
# cpuset.cpus can overlap with sibling cpuset.cpus.exclusive but not subsumed by it
- " C0-3 . . C4-5 X5 . . . 0 A1:0-3,B1:4-5"
+ " C0-3 . . C4-5 X5 . . . 0 A1:0-3|B1:4-5"
# Child partition root that try to take all CPUs from parent partition
# with tasks will remain invalid.
- " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4,A2:1-4 A1:P1,A2:P-1"
- " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1,A2:1-4 A1:P1,A2:P1"
- " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4,A2:1-4 A1:P1,A2:P-1"
+ " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+ " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1"
+ " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
# Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't
# affect cpuset.cpus.exclusive.effective.
- " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4,XA2:3"
+ " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4|XA2:3"
+
+ # cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive
+ # but creating a local partition out of it is not allowed. Similarly and change
+ # in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will
+ # invalidate it.
+ " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
+ A1:P0|A2:P2:B1:P1 2-4"
+ " CX1-4:S+ CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \
+ A1:P0|A2:P2:B1:P-1 2-4"
+ " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \
+ A1:P0|A2:P2:B1:P-1 2-4"
# old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
# ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
# Failure cases:
# A task cannot be added to a partition with no cpu
- "C2-3:P1:S+ C3:P1 . . O2=0:T . . . 1 A1:,A2:3 A1:P1,A2:P1"
+ "C2-3:P1:S+ C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1"
# Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected
- " C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3,B1:4-5"
+ " C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3|B1:4-5"
# cpuset.cpus cannot be a subset of sibling cpuset.cpus.exclusive
- " C0-3 . . C4-5 X3-5 . . . 1 A1:0-3,B1:4-5"
+ " C0-3 . . C4-5 X3-5 . . . 1 A1:0-3|B1:4-5"
+)
+
+#
+# Cpuset controller remote partition test matrix.
+#
+# Cgroup test hierarchy
+#
+# root
+# |
+# rtest (cpuset.cpus.exclusive=1-7)
+# |
+# +------+------+
+# | |
+# p1 p2
+# +--+--+ +--+--+
+# | | | |
+# c11 c12 c21 c22
+#
+# REMOTE_TEST_MATRIX uses the same notational convention as TEST_MATRIX.
+# Only CPUs 1-7 should be used.
+#
+REMOTE_TEST_MATRIX=(
+ # old-p1 old-p2 old-c11 old-c12 old-c21 old-c22
+ # new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS
+ # ------ ------ ------- ------- ------- ------- ----- ------ --------
+ " X1-3:S+ X4-6:S+ X1-2 X3 X4-5 X6 \
+ . . P2 P2 P2 P2 c11:1-2|c12:3|c21:4-5|c22:6 \
+ c11:P2|c12:P2|c21:P2|c22:P2 1-6"
+ " CX1-4:S+ . X1-2:P2 C3 . . \
+ . . . C3-4 . . p1:3-4|c11:1-2|c12:3-4 \
+ p1:P0|c11:P2|c12:P0 1-2"
+ " CX1-4:S+ . X1-2:P2 . . . \
+ X2-4 . . . . . p1:1,3-4|c11:2 \
+ p1:P0|c11:P2 2"
+ " CX1-5:S+ . X1-2:P2 X3-5:P1 . . \
+ X2-4 . . . . . p1:1,5|c11:2|c12:3-4 \
+ p1:P0|c11:P2|c12:P1 2"
+ " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \
+ . . X2 . . . p1:1|c11:2|c12:3-4 \
+ p1:P0|c11:P2|c12:P1 2"
+ # p1 as member, will get its effective CPUs from its parent rtest
+ " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \
+ . . X1 CX2-4 . . p1:5-7|c11:1|c12:2-4 \
+ p1:P0|c11:P2|c12:P1 1"
+ " CX1-4:S+ X5-6:P1:S+ . . . . \
+ . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
+ p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \
+ 1-2,4-6|1-2,5-6"
)
#
@@ -453,25 +529,26 @@ set_ctrl_state()
PFILE=$CGRP/cpuset.cpus.partition
CFILE=$CGRP/cpuset.cpus
XFILE=$CGRP/cpuset.cpus.exclusive
- S=$(expr substr $CMD 1 1)
- if [[ $S = S ]]
- then
- PREFIX=${CMD#?}
+ case $CMD in
+ S*) PREFIX=${CMD#?}
COMM="echo ${PREFIX}${CTRL} > $SFILE"
eval $COMM $REDIRECT
- elif [[ $S = X ]]
- then
+ ;;
+ X*)
CPUS=${CMD#?}
COMM="echo $CPUS > $XFILE"
eval $COMM $REDIRECT
- elif [[ $S = C ]]
- then
- CPUS=${CMD#?}
+ ;;
+ CX*)
+ CPUS=${CMD#??}
+ COMM="echo $CPUS > $CFILE; echo $CPUS > $XFILE"
+ eval $COMM $REDIRECT
+ ;;
+ C*) CPUS=${CMD#?}
COMM="echo $CPUS > $CFILE"
eval $COMM $REDIRECT
- elif [[ $S = P ]]
- then
- VAL=${CMD#?}
+ ;;
+ P*) VAL=${CMD#?}
case $VAL in
0) VAL=member
;;
@@ -486,15 +563,17 @@ set_ctrl_state()
esac
COMM="echo $VAL > $PFILE"
eval $COMM $REDIRECT
- elif [[ $S = O ]]
- then
- VAL=${CMD#?}
+ ;;
+ O*) VAL=${CMD#?}
write_cpu_online $VAL
- elif [[ $S = T ]]
- then
- COMM="echo 0 > $TFILE"
+ ;;
+ T*) COMM="echo 0 > $TFILE"
eval $COMM $REDIRECT
- fi
+ ;;
+ *) echo "Unknown command: $CMD"
+ exit 1
+ ;;
+ esac
RET=$?
[[ $RET -ne 0 ]] && {
[[ -n "$SHOWERR" ]] && {
@@ -532,21 +611,18 @@ online_cpus()
}
#
-# Return 1 if the list of effective cpus isn't the same as the initial list.
+# Remove all the test cgroup directories
#
reset_cgroup_states()
{
echo 0 > $CGROUP2/cgroup.procs
online_cpus
- rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1
- pause 0.02
- set_ctrl_state . R-
- pause 0.01
+ rmdir $RESET_LIST > /dev/null 2>&1
}
dump_states()
{
- for DIR in . A1 A1/A2 A1/A2/A3 B1
+ for DIR in $CGROUP_LIST
do
CPUS=$DIR/cpuset.cpus
ECPUS=$DIR/cpuset.cpus.effective
@@ -566,17 +642,33 @@ dump_states()
}
#
+# Set the actual cgroup directory into $CGRP_DIR
+# $1 - cgroup name
+#
+set_cgroup_dir()
+{
+ CGRP_DIR=$1
+ [[ $CGRP_DIR = A2 ]] && CGRP_DIR=A1/A2
+ [[ $CGRP_DIR = A3 ]] && CGRP_DIR=A1/A2/A3
+ [[ $CGRP_DIR = c11 ]] && CGRP_DIR=p1/c11
+ [[ $CGRP_DIR = c12 ]] && CGRP_DIR=p1/c12
+ [[ $CGRP_DIR = c21 ]] && CGRP_DIR=p2/c21
+ [[ $CGRP_DIR = c22 ]] && CGRP_DIR=p2/c22
+}
+
+#
# Check effective cpus
-# $1 - check string, format: <cgroup>:<cpu-list>[,<cgroup>:<cpu-list>]*
+# $1 - check string, format: <cgroup>:<cpu-list>[|<cgroup>:<cpu-list>]*
#
check_effective_cpus()
{
CHK_STR=$1
- for CHK in $(echo $CHK_STR | sed -e "s/,/ /g")
+ for CHK in $(echo $CHK_STR | sed -e "s/|/ /g")
do
set -- $(echo $CHK | sed -e "s/:/ /g")
CGRP=$1
- CPUS=$2
+ EXPECTED_CPUS=$2
+ ACTUAL_CPUS=
if [[ $CGRP = X* ]]
then
CGRP=${CGRP#X}
@@ -584,41 +676,39 @@ check_effective_cpus()
else
FILE=cpuset.cpus.effective
fi
- [[ $CGRP = A2 ]] && CGRP=A1/A2
- [[ $CGRP = A3 ]] && CGRP=A1/A2/A3
- [[ -e $CGRP/$FILE ]] || return 1
- [[ $CPUS = $(cat $CGRP/$FILE) ]] || return 1
+ set_cgroup_dir $CGRP
+ [[ -e $CGRP_DIR/$FILE ]] || return 1
+ ACTUAL_CPUS=$(cat $CGRP_DIR/$FILE)
+ [[ $EXPECTED_CPUS = $ACTUAL_CPUS ]] || return 1
done
}
#
# Check cgroup states
-# $1 - check string, format: <cgroup>:<state>[,<cgroup>:<state>]*
+# $1 - check string, format: <cgroup>:<state>[|<cgroup>:<state>]*
#
check_cgroup_states()
{
CHK_STR=$1
- for CHK in $(echo $CHK_STR | sed -e "s/,/ /g")
+ for CHK in $(echo $CHK_STR | sed -e "s/|/ /g")
do
set -- $(echo $CHK | sed -e "s/:/ /g")
CGRP=$1
- CGRP_DIR=$CGRP
- STATE=$2
+ EXPECTED_STATE=$2
FILE=
- EVAL=$(expr substr $STATE 2 2)
- [[ $CGRP = A2 ]] && CGRP_DIR=A1/A2
- [[ $CGRP = A3 ]] && CGRP_DIR=A1/A2/A3
+ EVAL=$(expr substr $EXPECTED_STATE 2 2)
- case $STATE in
+ set_cgroup_dir $CGRP
+ case $EXPECTED_STATE in
P*) FILE=$CGRP_DIR/cpuset.cpus.partition
;;
- *) echo "Unknown state: $STATE!"
+ *) echo "Unknown state: $EXPECTED_STATE!"
exit 1
;;
esac
- VAL=$(cat $FILE)
+ ACTUAL_STATE=$(cat $FILE)
- case "$VAL" in
+ case "$ACTUAL_STATE" in
member) VAL=0
;;
root) VAL=1
@@ -642,7 +732,7 @@ check_cgroup_states()
[[ $VAL -eq 1 && $VERBOSE -gt 0 ]] && {
DOMS=$(cat $CGRP_DIR/cpuset.cpus.effective)
[[ -n "$DOMS" ]] &&
- echo " [$CGRP] sched-domain: $DOMS" > $CONSOLE
+ echo " [$CGRP_DIR] sched-domain: $DOMS" > $CONSOLE
}
done
return 0
@@ -665,22 +755,22 @@ check_cgroup_states()
#
check_isolcpus()
{
- EXPECT_VAL=$1
- ISOLCPUS=
+ EXPECTED_ISOLCPUS=$1
+ ISCPUS=${CGROUP2}/cpuset.cpus.isolated
+ ISOLCPUS=$(cat $ISCPUS)
LASTISOLCPU=
SCHED_DOMAINS=/sys/kernel/debug/sched/domains
- ISCPUS=${CGROUP2}/cpuset.cpus.isolated
- if [[ $EXPECT_VAL = . ]]
+ if [[ $EXPECTED_ISOLCPUS = . ]]
then
- EXPECT_VAL=
- EXPECT_VAL2=
- elif [[ $(expr $EXPECT_VAL : ".*,.*") > 0 ]]
+ EXPECTED_ISOLCPUS=
+ EXPECTED_SDOMAIN=
+ elif [[ $(expr $EXPECTED_ISOLCPUS : ".*|.*") > 0 ]]
then
- set -- $(echo $EXPECT_VAL | sed -e "s/,/ /g")
- EXPECT_VAL=$1
- EXPECT_VAL2=$2
+ set -- $(echo $EXPECTED_ISOLCPUS | sed -e "s/|/ /g")
+ EXPECTED_ISOLCPUS=$2
+ EXPECTED_SDOMAIN=$1
else
- EXPECT_VAL2=$EXPECT_VAL
+ EXPECTED_SDOMAIN=$EXPECTED_ISOLCPUS
fi
#
@@ -689,20 +779,21 @@ check_isolcpus()
# to make appending those CPUs easier.
#
[[ -n "$BOOT_ISOLCPUS" ]] && {
- EXPECT_VAL=${EXPECT_VAL:+${EXPECT_VAL},}${BOOT_ISOLCPUS}
- EXPECT_VAL2=${EXPECT_VAL2:+${EXPECT_VAL2},}${BOOT_ISOLCPUS}
+ EXPECTED_ISOLCPUS=${EXPECTED_ISOLCPUS:+${EXPECTED_ISOLCPUS},}${BOOT_ISOLCPUS}
+ EXPECTED_SDOMAIN=${EXPECTED_SDOMAIN:+${EXPECTED_SDOMAIN},}${BOOT_ISOLCPUS}
}
#
# Check cpuset.cpus.isolated cpumask
#
- [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && {
+ [[ "$EXPECTED_ISOLCPUS" != "$ISOLCPUS" ]] && {
# Take a 50ms pause and try again
pause 0.05
ISOLCPUS=$(cat $ISCPUS)
}
- [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && return 1
+ [[ "$EXPECTED_ISOLCPUS" != "$ISOLCPUS" ]] && return 1
ISOLCPUS=
+ EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN
#
# Use the sched domain in debugfs to check isolated CPUs, if available
@@ -736,7 +827,7 @@ check_isolcpus()
done
[[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU
- [[ "$EXPECT_VAL" = "$ISOLCPUS" ]]
+ [[ "$EXPECTED_SDOMAIN" = "$ISOLCPUS" ]]
}
test_fail()
@@ -774,6 +865,63 @@ null_isolcpus_check()
}
#
+# Check state transition test result
+# $1 - Test number
+# $2 - Expected effective CPU values
+# $3 - Expected partition states
+# $4 - Expected isolated CPUs
+#
+check_test_results()
+{
+ _NR=$1
+ _ECPUS="$2"
+ _PSTATES="$3"
+ _ISOLCPUS="$4"
+
+ [[ -n "$_ECPUS" && "$_ECPUS" != . ]] && {
+ check_effective_cpus $_ECPUS
+ [[ $? -ne 0 ]] && test_fail $_NR "effective CPU" \
+ "Cgroup $CGRP: expected $EXPECTED_CPUS, got $ACTUAL_CPUS"
+ }
+
+ [[ -n "$_PSTATES" && "$_PSTATES" != . ]] && {
+ check_cgroup_states $_PSTATES
+ [[ $? -ne 0 ]] && test_fail $_NR states \
+ "Cgroup $CGRP: expected $EXPECTED_STATE, got $ACTUAL_STATE"
+ }
+
+ # Compare the expected isolated CPUs with the actual ones,
+ # if available
+ [[ -n "$_ISOLCPUS" ]] && {
+ check_isolcpus $_ISOLCPUS
+ [[ $? -ne 0 ]] && {
+ [[ -n "$BOOT_ISOLCPUS" ]] && _ISOLCPUS=${_ISOLCPUS},${BOOT_ISOLCPUS}
+ test_fail $_NR "isolated CPU" \
+ "Expect $_ISOLCPUS, get $ISOLCPUS instead"
+ }
+ }
+ reset_cgroup_states
+ #
+ # Check to see if effective cpu list changes
+ #
+ _NEWLIST=$(cat $CGROUP2/cpuset.cpus.effective)
+ RETRY=0
+ while [[ $_NEWLIST != $CPULIST && $RETRY -lt 8 ]]
+ do
+ # Wait a bit longer & recheck a few times
+ pause 0.02
+ ((RETRY++))
+ _NEWLIST=$(cat $CGROUP2/cpuset.cpus.effective)
+ done
+ [[ $_NEWLIST != $CPULIST ]] && {
+ echo "Effective cpus changed to $_NEWLIST after test $_NR!"
+ exit 1
+ }
+ null_isolcpus_check
+ [[ $VERBOSE -gt 0 ]] && echo "Test $I done."
+}
+
+#
# Run cpuset state transition test
# $1 - test matrix name
#
@@ -785,6 +933,8 @@ run_state_test()
{
TEST=$1
CONTROLLER=cpuset
+ CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1"
+ RESET_LIST="A1/A2/A3 A1/A2 A1 B1"
I=0
eval CNT="\${#$TEST[@]}"
@@ -812,10 +962,11 @@ run_state_test()
STATES=${11}
ICPUS=${12}
- set_ctrl_state_noerr B1 $OLD_B1
set_ctrl_state_noerr A1 $OLD_A1
set_ctrl_state_noerr A1/A2 $OLD_A2
set_ctrl_state_noerr A1/A2/A3 $OLD_A3
+ set_ctrl_state_noerr B1 $OLD_B1
+
RETVAL=0
set_ctrl_state A1 $NEW_A1; ((RETVAL += $?))
set_ctrl_state A1/A2 $NEW_A2; ((RETVAL += $?))
@@ -824,47 +975,79 @@ run_state_test()
[[ $RETVAL -ne $RESULT ]] && test_fail $I result
- [[ -n "$ECPUS" && "$ECPUS" != . ]] && {
- check_effective_cpus $ECPUS
- [[ $? -ne 0 ]] && test_fail $I "effective CPU"
- }
+ check_test_results $I "$ECPUS" "$STATES" "$ICPUS"
+ ((I++))
+ done
+ echo "All $I tests of $TEST PASSED."
+}
- [[ -n "$STATES" && "$STATES" != . ]] && {
- check_cgroup_states $STATES
- [[ $? -ne 0 ]] && test_fail $I states
- }
+#
+# Run cpuset remote partition state transition test
+# $1 - test matrix name
+#
+run_remote_state_test()
+{
+ TEST=$1
+ CONTROLLER=cpuset
+ [[ -d rtest ]] || mkdir rtest
+ cd rtest
+ echo +cpuset > cgroup.subtree_control
+ echo "1-7" > cpuset.cpus
+ echo "1-7" > cpuset.cpus.exclusive
+ CGROUP_LIST=".. . p1 p2 p1/c11 p1/c12 p2/c21 p2/c22"
+ RESET_LIST="p1/c11 p1/c12 p2/c21 p2/c22 p1 p2"
+ I=0
+ eval CNT="\${#$TEST[@]}"
- # Compare the expected isolated CPUs with the actual ones,
- # if available
- [[ -n "$ICPUS" ]] && {
- check_isolcpus $ICPUS
- [[ $? -ne 0 ]] && {
- [[ -n "$BOOT_ISOLCPUS" ]] && ICPUS=${ICPUS},${BOOT_ISOLCPUS}
- test_fail $I "isolated CPU" \
- "Expect $ICPUS, get $ISOLCPUS instead"
- }
- }
- reset_cgroup_states
- #
- # Check to see if effective cpu list changes
- #
- NEWLIST=$(cat cpuset.cpus.effective)
- RETRY=0
- while [[ $NEWLIST != $CPULIST && $RETRY -lt 8 ]]
- do
- # Wait a bit longer & recheck a few times
- pause 0.02
- ((RETRY++))
- NEWLIST=$(cat cpuset.cpus.effective)
- done
- [[ $NEWLIST != $CPULIST ]] && {
- echo "Effective cpus changed to $NEWLIST after test $I!"
- exit 1
+ reset_cgroup_states
+ console_msg "Running remote partition state transition test ..."
+
+ while [[ $I -lt $CNT ]]
+ do
+ echo "Running test $I ..." > $CONSOLE
+ [[ $VERBOSE -gt 1 ]] && {
+ echo ""
+ eval echo \${$TEST[$I]}
}
- null_isolcpus_check
- [[ $VERBOSE -gt 0 ]] && echo "Test $I done."
+ eval set -- "\${$TEST[$I]}"
+ OLD_p1=$1
+ OLD_p2=$2
+ OLD_c11=$3
+ OLD_c12=$4
+ OLD_c21=$5
+ OLD_c22=$6
+ NEW_p1=$7
+ NEW_p2=$8
+ NEW_c11=$9
+ NEW_c12=${10}
+ NEW_c21=${11}
+ NEW_c22=${12}
+ ECPUS=${13}
+ STATES=${14}
+ ICPUS=${15}
+
+ set_ctrl_state_noerr p1 $OLD_p1
+ set_ctrl_state_noerr p2 $OLD_p2
+ set_ctrl_state_noerr p1/c11 $OLD_c11
+ set_ctrl_state_noerr p1/c12 $OLD_c12
+ set_ctrl_state_noerr p2/c21 $OLD_c21
+ set_ctrl_state_noerr p2/c22 $OLD_c22
+
+ RETVAL=0
+ set_ctrl_state p1 $NEW_p1 ; ((RETVAL += $?))
+ set_ctrl_state p2 $NEW_p2 ; ((RETVAL += $?))
+ set_ctrl_state p1/c11 $NEW_c11; ((RETVAL += $?))
+ set_ctrl_state p1/c12 $NEW_c12; ((RETVAL += $?))
+ set_ctrl_state p2/c21 $NEW_c21; ((RETVAL += $?))
+ set_ctrl_state p2/c22 $NEW_c22; ((RETVAL += $?))
+
+ [[ $RETVAL -ne 0 ]] && test_fail $I result
+
+ check_test_results $I "$ECPUS" "$STATES" "$ICPUS"
((I++))
done
+ cd ..
+ rmdir rtest
echo "All $I tests of $TEST PASSED."
}
@@ -932,6 +1115,7 @@ test_isolated()
echo $$ > $CGROUP2/cgroup.procs
[[ -d A1 ]] && rmdir A1
null_isolcpus_check
+ pause 0.05
}
#
@@ -997,10 +1181,13 @@ test_inotify()
else
echo "Inotify test PASSED"
fi
+ echo member > cpuset.cpus.partition
+ echo "" > cpuset.cpus
}
trap cleanup 0 2 3 6
run_state_test TEST_MATRIX
+run_remote_state_test REMOTE_TEST_MATRIX
test_isolated
test_inotify
echo "All tests PASSED."
diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h
index 3d2663fe50ba..eeca8005723f 100644
--- a/tools/testing/selftests/clone3/clone3_selftests.h
+++ b/tools/testing/selftests/clone3/clone3_selftests.h
@@ -16,7 +16,7 @@
#define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr)))
#ifndef __NR_clone3
-#define __NR_clone3 -1
+#define __NR_clone3 435
#endif
struct __clone_args {
diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py
index 7cc74faed743..7c90a040ce45 100755
--- a/tools/testing/selftests/drivers/net/hds.py
+++ b/tools/testing/selftests/drivers/net/hds.py
@@ -6,7 +6,7 @@ import os
from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx
from lib.py import CmdExitFailure, EthtoolFamily, NlError
from lib.py import NetDrvEnv
-from lib.py import defer, ethtool, ip
+from lib.py import defer, ethtool, ip, random
def _get_hds_mode(cfg, netnl) -> str:
@@ -20,7 +20,7 @@ def _get_hds_mode(cfg, netnl) -> str:
def _xdp_onoff(cfg):
- prog = cfg.rpath("../../net/lib/xdp_dummy.bpf.o")
+ prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
ip("link set dev %s xdp obj %s sec xdp" %
(cfg.ifname, prog))
ip("link set dev %s xdp off" % cfg.ifname)
@@ -109,6 +109,36 @@ def set_hds_thresh_zero(cfg, netnl) -> None:
ksft_eq(0, rings['hds-thresh'])
+def set_hds_thresh_random(cfg, netnl) -> None:
+ try:
+ rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+ except NlError as e:
+ raise KsftSkipEx('ring-get not supported by device')
+ if 'hds-thresh' not in rings:
+ raise KsftSkipEx('hds-thresh not supported by device')
+ if 'hds-thresh-max' not in rings:
+ raise KsftSkipEx('hds-thresh-max not defined by device')
+
+ if rings['hds-thresh-max'] < 2:
+ raise KsftSkipEx('hds-thresh-max is too small')
+ elif rings['hds-thresh-max'] == 2:
+ hds_thresh = 1
+ else:
+ while True:
+ hds_thresh = random.randint(1, rings['hds-thresh-max'] - 1)
+ if hds_thresh != rings['hds-thresh']:
+ break
+
+ try:
+ netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_thresh})
+ except NlError as e:
+ if e.error == errno.EINVAL:
+ raise KsftSkipEx("hds-thresh-set not supported by the device")
+ elif e.error == errno.EOPNOTSUPP:
+ raise KsftSkipEx("ring-set not supported by the device")
+ rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+ ksft_eq(hds_thresh, rings['hds-thresh'])
+
def set_hds_thresh_max(cfg, netnl) -> None:
try:
rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
@@ -243,6 +273,7 @@ def main() -> None:
get_hds_thresh,
set_hds_disable,
set_hds_enable,
+ set_hds_thresh_random,
set_hds_thresh_zero,
set_hds_thresh_max,
set_hds_thresh_gt,
diff --git a/tools/testing/selftests/drivers/net/hw/.gitignore b/tools/testing/selftests/drivers/net/hw/.gitignore
index e9fe6ede681a..6942bf575497 100644
--- a/tools/testing/selftests/drivers/net/hw/.gitignore
+++ b/tools/testing/selftests/drivers/net/hw/.gitignore
@@ -1 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+iou-zcrx
ncdevmem
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index cde5814ff9a7..07cddb19ba35 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -1,5 +1,7 @@
# SPDX-License-Identifier: GPL-2.0+ OR MIT
+TEST_GEN_FILES = iou-zcrx
+
TEST_PROGS = \
csum.py \
devlink_port_split.py \
@@ -10,6 +12,7 @@ TEST_PROGS = \
ethtool_rmon.sh \
hw_stats_l3.sh \
hw_stats_l3_gre.sh \
+ iou-zcrx.py \
irq.py \
loopback.sh \
nic_link_layer.py \
@@ -44,3 +47,5 @@ YNL_GENS := ethtool netdev
include ../../../net/ynl.mk
include ../../../net/bpf.mk
+
+$(OUTPUT)/iou-zcrx: LDLIBS += -luring
diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py
index 701aca1361e0..cd23af875317 100755
--- a/tools/testing/selftests/drivers/net/hw/csum.py
+++ b/tools/testing/selftests/drivers/net/hw/csum.py
@@ -88,7 +88,7 @@ def main() -> None:
with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
check_nic_features(cfg)
- cfg.bin_local = cfg.rpath("../../../net/lib/csum")
+ cfg.bin_local = cfg.net_lib_dir / "csum"
cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
cases = []
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
new file mode 100644
index 000000000000..c26b4180eddd
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
@@ -0,0 +1,457 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <linux/errqueue.h>
+#include <linux/if_packet.h>
+#include <linux/ipv6.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+
+#include <liburing.h>
+
+#define PAGE_SIZE (4096)
+#define AREA_SIZE (8192 * PAGE_SIZE)
+#define SEND_SIZE (512 * 4096)
+#define min(a, b) \
+ ({ \
+ typeof(a) _a = (a); \
+ typeof(b) _b = (b); \
+ _a < _b ? _a : _b; \
+ })
+#define min_t(t, a, b) \
+ ({ \
+ t _ta = (a); \
+ t _tb = (b); \
+ min(_ta, _tb); \
+ })
+
+#define ALIGN_UP(v, align) (((v) + (align) - 1) & ~((align) - 1))
+
+static int cfg_server;
+static int cfg_client;
+static int cfg_port = 8000;
+static int cfg_payload_len;
+static const char *cfg_ifname;
+static int cfg_queue_id = -1;
+static bool cfg_oneshot;
+static int cfg_oneshot_recvs;
+static int cfg_send_size = SEND_SIZE;
+static struct sockaddr_in6 cfg_addr;
+
+static char payload[SEND_SIZE] __attribute__((aligned(PAGE_SIZE)));
+static void *area_ptr;
+static void *ring_ptr;
+static size_t ring_size;
+static struct io_uring_zcrx_rq rq_ring;
+static unsigned long area_token;
+static int connfd;
+static bool stop;
+static size_t received;
+
+static unsigned long gettimeofday_ms(void)
+{
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+ return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+ int ret;
+
+ sin6->sin6_family = AF_INET6;
+ sin6->sin6_port = htons(port);
+
+ ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+ if (ret != 1) {
+ /* fallback to plain IPv4 */
+ ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+ if (ret != 1)
+ return -1;
+
+ /* add ::ffff prefix */
+ sin6->sin6_addr.s6_addr32[0] = 0;
+ sin6->sin6_addr.s6_addr32[1] = 0;
+ sin6->sin6_addr.s6_addr16[4] = 0;
+ sin6->sin6_addr.s6_addr16[5] = 0xffff;
+ }
+
+ return 0;
+}
+
+static inline size_t get_refill_ring_size(unsigned int rq_entries)
+{
+ size_t size;
+
+ ring_size = rq_entries * sizeof(struct io_uring_zcrx_rqe);
+ /* add space for the header (head/tail/etc.) */
+ ring_size += PAGE_SIZE;
+ return ALIGN_UP(ring_size, 4096);
+}
+
+static void setup_zcrx(struct io_uring *ring)
+{
+ unsigned int ifindex;
+ unsigned int rq_entries = 4096;
+ int ret;
+
+ ifindex = if_nametoindex(cfg_ifname);
+ if (!ifindex)
+ error(1, 0, "bad interface name: %s", cfg_ifname);
+
+ area_ptr = mmap(NULL,
+ AREA_SIZE,
+ PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE,
+ 0,
+ 0);
+ if (area_ptr == MAP_FAILED)
+ error(1, 0, "mmap(): zero copy area");
+
+ ring_size = get_refill_ring_size(rq_entries);
+ ring_ptr = mmap(NULL,
+ ring_size,
+ PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE,
+ 0,
+ 0);
+
+ struct io_uring_region_desc region_reg = {
+ .size = ring_size,
+ .user_addr = (__u64)(unsigned long)ring_ptr,
+ .flags = IORING_MEM_REGION_TYPE_USER,
+ };
+
+ struct io_uring_zcrx_area_reg area_reg = {
+ .addr = (__u64)(unsigned long)area_ptr,
+ .len = AREA_SIZE,
+ .flags = 0,
+ };
+
+ struct io_uring_zcrx_ifq_reg reg = {
+ .if_idx = ifindex,
+ .if_rxq = cfg_queue_id,
+ .rq_entries = rq_entries,
+ .area_ptr = (__u64)(unsigned long)&area_reg,
+ .region_ptr = (__u64)(unsigned long)&region_reg,
+ };
+
+ ret = io_uring_register_ifq(ring, &reg);
+ if (ret)
+ error(1, 0, "io_uring_register_ifq(): %d", ret);
+
+ rq_ring.khead = (unsigned int *)((char *)ring_ptr + reg.offsets.head);
+ rq_ring.ktail = (unsigned int *)((char *)ring_ptr + reg.offsets.tail);
+ rq_ring.rqes = (struct io_uring_zcrx_rqe *)((char *)ring_ptr + reg.offsets.rqes);
+ rq_ring.rq_tail = 0;
+ rq_ring.ring_entries = reg.rq_entries;
+
+ area_token = area_reg.rq_area_token;
+}
+
+static void add_accept(struct io_uring *ring, int sockfd)
+{
+ struct io_uring_sqe *sqe;
+
+ sqe = io_uring_get_sqe(ring);
+
+ io_uring_prep_accept(sqe, sockfd, NULL, NULL, 0);
+ sqe->user_data = 1;
+}
+
+static void add_recvzc(struct io_uring *ring, int sockfd)
+{
+ struct io_uring_sqe *sqe;
+
+ sqe = io_uring_get_sqe(ring);
+
+ io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, sockfd, NULL, 0, 0);
+ sqe->ioprio |= IORING_RECV_MULTISHOT;
+ sqe->user_data = 2;
+}
+
+static void add_recvzc_oneshot(struct io_uring *ring, int sockfd, size_t len)
+{
+ struct io_uring_sqe *sqe;
+
+ sqe = io_uring_get_sqe(ring);
+
+ io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, sockfd, NULL, len, 0);
+ sqe->ioprio |= IORING_RECV_MULTISHOT;
+ sqe->user_data = 2;
+}
+
+static void process_accept(struct io_uring *ring, struct io_uring_cqe *cqe)
+{
+ if (cqe->res < 0)
+ error(1, 0, "accept()");
+ if (connfd)
+ error(1, 0, "Unexpected second connection");
+
+ connfd = cqe->res;
+ if (cfg_oneshot)
+ add_recvzc_oneshot(ring, connfd, PAGE_SIZE);
+ else
+ add_recvzc(ring, connfd);
+}
+
+static void process_recvzc(struct io_uring *ring, struct io_uring_cqe *cqe)
+{
+ unsigned rq_mask = rq_ring.ring_entries - 1;
+ struct io_uring_zcrx_cqe *rcqe;
+ struct io_uring_zcrx_rqe *rqe;
+ struct io_uring_sqe *sqe;
+ uint64_t mask;
+ char *data;
+ ssize_t n;
+ int i;
+
+ if (cqe->res == 0 && cqe->flags == 0 && cfg_oneshot_recvs == 0) {
+ stop = true;
+ return;
+ }
+
+ if (cqe->res < 0)
+ error(1, 0, "recvzc(): %d", cqe->res);
+
+ if (cfg_oneshot) {
+ if (cqe->res == 0 && cqe->flags == 0 && cfg_oneshot_recvs) {
+ add_recvzc_oneshot(ring, connfd, PAGE_SIZE);
+ cfg_oneshot_recvs--;
+ }
+ } else if (!(cqe->flags & IORING_CQE_F_MORE)) {
+ add_recvzc(ring, connfd);
+ }
+
+ rcqe = (struct io_uring_zcrx_cqe *)(cqe + 1);
+
+ n = cqe->res;
+ mask = (1ULL << IORING_ZCRX_AREA_SHIFT) - 1;
+ data = (char *)area_ptr + (rcqe->off & mask);
+
+ for (i = 0; i < n; i++) {
+ if (*(data + i) != payload[(received + i)])
+ error(1, 0, "payload mismatch at ", i);
+ }
+ received += n;
+
+ rqe = &rq_ring.rqes[(rq_ring.rq_tail & rq_mask)];
+ rqe->off = (rcqe->off & ~IORING_ZCRX_AREA_MASK) | area_token;
+ rqe->len = cqe->res;
+ io_uring_smp_store_release(rq_ring.ktail, ++rq_ring.rq_tail);
+}
+
+static void server_loop(struct io_uring *ring)
+{
+ struct io_uring_cqe *cqe;
+ unsigned int count = 0;
+ unsigned int head;
+ int i, ret;
+
+ io_uring_submit_and_wait(ring, 1);
+
+ io_uring_for_each_cqe(ring, head, cqe) {
+ if (cqe->user_data == 1)
+ process_accept(ring, cqe);
+ else if (cqe->user_data == 2)
+ process_recvzc(ring, cqe);
+ else
+ error(1, 0, "unknown cqe");
+ count++;
+ }
+ io_uring_cq_advance(ring, count);
+}
+
+static void run_server(void)
+{
+ unsigned int flags = 0;
+ struct io_uring ring;
+ int fd, enable, ret;
+ uint64_t tstop;
+
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (fd == -1)
+ error(1, 0, "socket()");
+
+ enable = 1;
+ ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &enable, sizeof(int));
+ if (ret < 0)
+ error(1, 0, "setsockopt(SO_REUSEADDR)");
+
+ ret = bind(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr));
+ if (ret < 0)
+ error(1, 0, "bind()");
+
+ if (listen(fd, 1024) < 0)
+ error(1, 0, "listen()");
+
+ flags |= IORING_SETUP_COOP_TASKRUN;
+ flags |= IORING_SETUP_SINGLE_ISSUER;
+ flags |= IORING_SETUP_DEFER_TASKRUN;
+ flags |= IORING_SETUP_SUBMIT_ALL;
+ flags |= IORING_SETUP_CQE32;
+
+ io_uring_queue_init(512, &ring, flags);
+
+ setup_zcrx(&ring);
+
+ add_accept(&ring, fd);
+
+ tstop = gettimeofday_ms() + 5000;
+ while (!stop && gettimeofday_ms() < tstop)
+ server_loop(&ring);
+
+ if (!stop)
+ error(1, 0, "test failed\n");
+}
+
+static void run_client(void)
+{
+ ssize_t to_send = cfg_send_size;
+ ssize_t sent = 0;
+ ssize_t chunk, res;
+ int fd;
+
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (fd == -1)
+ error(1, 0, "socket()");
+
+ if (connect(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr)))
+ error(1, 0, "connect()");
+
+ while (to_send) {
+ void *src = &payload[sent];
+
+ chunk = min_t(ssize_t, cfg_payload_len, to_send);
+ res = send(fd, src, chunk, 0);
+ if (res < 0)
+ error(1, 0, "send(): %d", sent);
+ sent += res;
+ to_send -= res;
+ }
+
+ close(fd);
+}
+
+static void usage(const char *filepath)
+{
+ error(1, 0, "Usage: %s (-4|-6) (-s|-c) -h<server_ip> -p<port> "
+ "-l<payload_size> -i<ifname> -q<rxq_id>", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ const int max_payload_len = sizeof(payload) -
+ sizeof(struct ipv6hdr) -
+ sizeof(struct tcphdr) -
+ 40 /* max tcp options */;
+ struct sockaddr_in6 *addr6 = (void *) &cfg_addr;
+ char *addr = NULL;
+ int ret;
+ int c;
+
+ if (argc <= 1)
+ usage(argv[0]);
+ cfg_payload_len = max_payload_len;
+
+ while ((c = getopt(argc, argv, "sch:p:l:i:q:o:z:")) != -1) {
+ switch (c) {
+ case 's':
+ if (cfg_client)
+ error(1, 0, "Pass one of -s or -c");
+ cfg_server = 1;
+ break;
+ case 'c':
+ if (cfg_server)
+ error(1, 0, "Pass one of -s or -c");
+ cfg_client = 1;
+ break;
+ case 'h':
+ addr = optarg;
+ break;
+ case 'p':
+ cfg_port = strtoul(optarg, NULL, 0);
+ break;
+ case 'l':
+ cfg_payload_len = strtoul(optarg, NULL, 0);
+ break;
+ case 'i':
+ cfg_ifname = optarg;
+ break;
+ case 'q':
+ cfg_queue_id = strtoul(optarg, NULL, 0);
+ break;
+ case 'o': {
+ cfg_oneshot = true;
+ cfg_oneshot_recvs = strtoul(optarg, NULL, 0);
+ break;
+ }
+ case 'z':
+ cfg_send_size = strtoul(optarg, NULL, 0);
+ break;
+ }
+ }
+
+ if (cfg_server && addr)
+ error(1, 0, "Receiver cannot have -h specified");
+
+ memset(addr6, 0, sizeof(*addr6));
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(cfg_port);
+ addr6->sin6_addr = in6addr_any;
+ if (addr) {
+ ret = parse_address(addr, cfg_port, addr6);
+ if (ret)
+ error(1, 0, "receiver address parse error: %s", addr);
+ }
+
+ if (cfg_payload_len > max_payload_len)
+ error(1, 0, "-l: payload exceeds max (%d)", max_payload_len);
+}
+
+int main(int argc, char **argv)
+{
+ const char *cfg_test = argv[argc - 1];
+ int i;
+
+ parse_opts(argc, argv);
+
+ for (i = 0; i < SEND_SIZE; i++)
+ payload[i] = 'a' + (i % 26);
+
+ if (cfg_server)
+ run_server();
+ else if (cfg_client)
+ run_client();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
new file mode 100755
index 000000000000..6a0378e06cab
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
@@ -0,0 +1,91 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import re
+from os import path
+from lib.py import ksft_run, ksft_exit
+from lib.py import NetDrvEpEnv
+from lib.py import bkg, cmd, ethtool, wait_port_listen
+
+
+def _get_rx_ring_entries(cfg):
+ output = ethtool(f"-g {cfg.ifname}", host=cfg.remote).stdout
+ values = re.findall(r'RX:\s+(\d+)', output)
+ return int(values[1])
+
+
+def _get_combined_channels(cfg):
+ output = ethtool(f"-l {cfg.ifname}", host=cfg.remote).stdout
+ values = re.findall(r'Combined:\s+(\d+)', output)
+ return int(values[1])
+
+
+def _set_flow_rule(cfg, chan):
+ output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port 9999 action {chan}", host=cfg.remote).stdout
+ values = re.search(r'ID (\d+)', output).group(1)
+ return int(values)
+
+
+def test_zcrx(cfg) -> None:
+ cfg.require_ipver('6')
+
+ combined_chans = _get_combined_channels(cfg)
+ if combined_chans < 2:
+ raise KsftSkipEx('at least 2 combined channels required')
+ rx_ring = _get_rx_ring_entries(cfg)
+
+ try:
+ ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
+ ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
+ ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
+ flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
+
+ rx_cmd = f"{cfg.bin_remote} -s -p 9999 -i {cfg.ifname} -q {combined_chans - 1}"
+ tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p 9999 -l 12840"
+ with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+ wait_port_listen(9999, proto="tcp", host=cfg.remote)
+ cmd(tx_cmd)
+ finally:
+ ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
+ ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
+ ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+ ethtool(f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
+
+
+def test_zcrx_oneshot(cfg) -> None:
+ cfg.require_ipver('6')
+
+ combined_chans = _get_combined_channels(cfg)
+ if combined_chans < 2:
+ raise KsftSkipEx('at least 2 combined channels required')
+ rx_ring = _get_rx_ring_entries(cfg)
+
+ try:
+ ethtool(f"-G {cfg.ifname} tcp-data-split on", host=cfg.remote)
+ ethtool(f"-G {cfg.ifname} rx 64", host=cfg.remote)
+ ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}", host=cfg.remote)
+ flow_rule_id = _set_flow_rule(cfg, combined_chans - 1)
+
+ rx_cmd = f"{cfg.bin_remote} -s -p 9999 -i {cfg.ifname} -q {combined_chans - 1} -o 4"
+ tx_cmd = f"{cfg.bin_local} -c -h {cfg.remote_addr_v['6']} -p 9999 -l 4096 -z 16384"
+ with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+ wait_port_listen(9999, proto="tcp", host=cfg.remote)
+ cmd(tx_cmd)
+ finally:
+ ethtool(f"-N {cfg.ifname} delete {flow_rule_id}", host=cfg.remote)
+ ethtool(f"-X {cfg.ifname} default", host=cfg.remote)
+ ethtool(f"-G {cfg.ifname} rx {rx_ring}", host=cfg.remote)
+ ethtool(f"-G {cfg.ifname} tcp-data-split auto", host=cfg.remote)
+
+
+def main() -> None:
+ with NetDrvEpEnv(__file__) as cfg:
+ cfg.bin_local = path.abspath(path.dirname(__file__) + "/../../../drivers/net/hw/iou-zcrx")
+ cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+ ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, ))
+ ksft_exit()
+
+
+if __name__ == "__main__":
+ main()
diff --git a/tools/testing/selftests/drivers/net/hw/irq.py b/tools/testing/selftests/drivers/net/hw/irq.py
index 42ab98370245..0699d6a8b4e2 100755
--- a/tools/testing/selftests/drivers/net/hw/irq.py
+++ b/tools/testing/selftests/drivers/net/hw/irq.py
@@ -69,7 +69,7 @@ def check_reconfig_queues(cfg) -> None:
def check_reconfig_xdp(cfg) -> None:
def reconfig(cfg) -> None:
ip(f"link set dev %s xdp obj %s sec xdp" %
- (cfg.ifname, cfg.rpath("xdp_dummy.bpf.o")))
+ (cfg.ifname, cfg.net_lib_dir / "xdp_dummy.bpf.o"))
ip(f"link set dev %s xdp off" % cfg.ifname)
_check_reconfig(cfg, reconfig)
diff --git a/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c b/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c
deleted file mode 100644
index d988b2e0cee8..000000000000
--- a/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#define KBUILD_MODNAME "xdp_dummy"
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-
-SEC("xdp")
-int xdp_dummy_prog(struct xdp_md *ctx)
-{
- return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index fd4d674e6c72..ad5ff645183a 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -13,22 +13,17 @@ from .remote import Remote
class NetDrvEnvBase:
"""
Base class for a NIC / host envirnoments
+
+ Attributes:
+ test_dir: Path to the source directory of the test
+ net_lib_dir: Path to the net/lib directory
"""
def __init__(self, src_path):
- self.src_path = src_path
- self.env = self._load_env_file()
-
- def rpath(self, path):
- """
- Get an absolute path to a file based on a path relative to the directory
- containing the test which constructed env.
+ self.src_path = Path(src_path)
+ self.test_dir = self.src_path.parent.resolve()
+ self.net_lib_dir = (Path(__file__).parent / "../../../../net/lib").resolve()
- For example, if the test.py is in the same directory as
- a binary (built from helper.c), the test can use env.rpath("helper")
- to get the absolute path to the binary
- """
- src_dir = Path(self.src_path).parent.resolve()
- return (src_dir / path).as_posix()
+ self.env = self._load_env_file()
def _load_env_file(self):
env = os.environ.copy()
diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
index 93120e86e102..4b6822866066 100755
--- a/tools/testing/selftests/drivers/net/ping.py
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -56,8 +56,7 @@ def _set_offload_checksum(cfg, netnl, on) -> None:
return
def _set_xdp_generic_sb_on(cfg) -> None:
- test_dir = os.path.dirname(os.path.realpath(__file__))
- prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+ prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True)
defer(cmd, f"ip link set dev {cfg.ifname} xdpgeneric off")
@@ -66,8 +65,7 @@ def _set_xdp_generic_sb_on(cfg) -> None:
time.sleep(10)
def _set_xdp_generic_mb_on(cfg) -> None:
- test_dir = os.path.dirname(os.path.realpath(__file__))
- prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+ prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog))
@@ -77,8 +75,7 @@ def _set_xdp_generic_mb_on(cfg) -> None:
time.sleep(10)
def _set_xdp_native_sb_on(cfg) -> None:
- test_dir = os.path.dirname(os.path.realpath(__file__))
- prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+ prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True)
defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
@@ -95,8 +92,7 @@ def _set_xdp_native_sb_on(cfg) -> None:
time.sleep(10)
def _set_xdp_native_mb_on(cfg) -> None:
- test_dir = os.path.dirname(os.path.realpath(__file__))
- prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+ prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
try:
@@ -109,8 +105,7 @@ def _set_xdp_native_mb_on(cfg) -> None:
time.sleep(10)
def _set_xdp_offload_on(cfg) -> None:
- test_dir = os.path.dirname(os.path.realpath(__file__))
- prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+ prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
cmd(f"ip link set dev {cfg.ifname} mtu 1500", shell=True)
try:
cmd(f"ip link set dev {cfg.ifname} xdpoffload obj {prog} sec xdp", shell=True)
diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index cae923f84f69..06abd3f233e1 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -26,13 +26,13 @@ def nl_get_queues(cfg, nl, qtype='rx'):
def check_xsk(cfg, nl, xdp_queue_id=0) -> None:
# Probe for support
- xdp = cmd(cfg.rpath("xdp_helper") + ' - -', fail=False)
+ xdp = cmd(f'{cfg.test_dir / "xdp_helper"} - -', fail=False)
if xdp.ret == 255:
raise KsftSkipEx('AF_XDP unsupported')
elif xdp.ret > 0:
raise KsftFailEx('unable to create AF_XDP socket')
- with bkg(f'{cfg.rpath("xdp_helper")} {cfg.ifindex} {xdp_queue_id}',
+ with bkg(f'{cfg.test_dir / "xdp_helper"} {cfg.ifindex} {xdp_queue_id}',
ksft_wait=3):
rx = tx = False
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc b/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
index 6b94b678741a..f656bccb1a14 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/dynevent_limitations.tc
@@ -7,11 +7,32 @@
MAX_ARGS=128
EXCEED_ARGS=$((MAX_ARGS + 1))
+# bash and dash evaluate variables differently.
+# dash will evaluate '\\' every time it is read whereas bash does not.
+#
+# TEST_STRING="$TEST_STRING \\$i"
+# echo $TEST_STRING
+#
+# With i=123
+# On bash, that will print "\123"
+# but on dash, that will print the escape sequence of \123 as the \ will
+# be interpreted again in the echo.
+#
+# Set a variable "bs" to save a double backslash, then echo that
+# to "ts" to see if $ts changed or not. If it changed, it's dash,
+# if not, it's bash, and then bs can equal a single backslash.
+bs='\\'
+ts=`echo $bs`
+if [ "$ts" = '\\' ]; then
+ # this is bash
+ bs='\'
+fi
+
check_max_args() { # event_header
TEST_STRING=$1
# Acceptable
for i in `seq 1 $MAX_ARGS`; do
- TEST_STRING="$TEST_STRING \\$i"
+ TEST_STRING="$TEST_STRING $bs$i"
done
echo "$TEST_STRING" >> dynamic_events
echo > dynamic_events
diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
index 118247b8dd84..c62165fabd0c 100644
--- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
+++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc
@@ -80,6 +80,26 @@ if [ $misscnt -gt 0 ]; then
exit_fail
fi
+# Check strings too
+if [ -f events/syscalls/sys_enter_openat/filter ]; then
+ DIRNAME=`basename $TMPDIR`
+ echo "filename.ustring ~ \"*$DIRNAME*\"" > events/syscalls/sys_enter_openat/filter
+ echo 1 > events/syscalls/sys_enter_openat/enable
+ echo 1 > tracing_on
+ ls /bin/sh
+ nocnt=`grep openat trace | wc -l`
+ ls $TMPDIR
+ echo 0 > tracing_on
+ hitcnt=`grep openat trace | wc -l`;
+ echo 0 > events/syscalls/sys_enter_openat/enable
+ if [ $nocnt -gt 0 ]; then
+ exit_fail
+ fi
+ if [ $hitcnt -eq 0 ]; then
+ exit_fail
+ fi
+fi
+
reset_events_filter
exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-multi-filter.tc b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-multi-filter.tc
new file mode 100644
index 000000000000..b6d6a312ead5
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/ftrace/fgraph-multi-filter.tc
@@ -0,0 +1,177 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: ftrace - function graph filters
+# requires: set_ftrace_filter function_graph:tracer
+
+# Make sure that function graph filtering works
+
+INSTANCE1="instances/test1_$$"
+INSTANCE2="instances/test2_$$"
+
+WD=`pwd`
+
+do_reset() {
+ cd $WD
+ if [ -d $INSTANCE1 ]; then
+ echo nop > $INSTANCE1/current_tracer
+ rmdir $INSTANCE1
+ fi
+ if [ -d $INSTANCE2 ]; then
+ echo nop > $INSTANCE2/current_tracer
+ rmdir $INSTANCE2
+ fi
+}
+
+mkdir $INSTANCE1
+if ! grep -q function_graph $INSTANCE1/available_tracers; then
+ echo "function_graph not allowed with instances"
+ rmdir $INSTANCE1
+ exit_unsupported
+fi
+
+mkdir $INSTANCE2
+
+fail() { # msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+disable_tracing
+clear_trace
+
+function_count() {
+ search=$1
+ vsearch=$2
+
+ if [ -z "$search" ]; then
+ cat enabled_functions | wc -l
+ elif [ -z "$vsearch" ]; then
+ grep $search enabled_functions | wc -l
+ else
+ grep $search enabled_functions | grep $vsearch| wc -l
+ fi
+}
+
+set_fgraph() {
+ instance=$1
+ filter="$2"
+ notrace="$3"
+
+ echo "$filter" > $instance/set_ftrace_filter
+ echo "$notrace" > $instance/set_ftrace_notrace
+ echo function_graph > $instance/current_tracer
+}
+
+check_functions() {
+ orig_cnt=$1
+ test=$2
+
+ cnt=`function_count $test`
+ if [ $cnt -gt $orig_cnt ]; then
+ fail
+ fi
+}
+
+check_cnt() {
+ orig_cnt=$1
+ search=$2
+ vsearch=$3
+
+ cnt=`function_count $search $vsearch`
+ if [ $cnt -gt $orig_cnt ]; then
+ fail
+ fi
+}
+
+reset_graph() {
+ instance=$1
+ echo nop > $instance/current_tracer
+}
+
+# get any functions that were enabled before the test
+total_cnt=`function_count`
+sched_cnt=`function_count sched`
+lock_cnt=`function_count lock`
+time_cnt=`function_count time`
+clock_cnt=`function_count clock`
+locks_clock_cnt=`function_count locks clock`
+clock_locks_cnt=`function_count clock locks`
+
+# Trace functions with "sched" but not "time"
+set_fgraph $INSTANCE1 '*sched*' '*time*'
+
+# Make sure "time" isn't listed
+check_functions $time_cnt 'time'
+instance1_cnt=`function_count`
+
+# Trace functions with "lock" but not "clock"
+set_fgraph $INSTANCE2 '*lock*' '*clock*'
+instance1_2_cnt=`function_count`
+
+# Turn off the first instance
+reset_graph $INSTANCE1
+
+# The second instance doesn't trace "clock" functions
+check_functions $clock_cnt 'clock'
+instance2_cnt=`function_count`
+
+# Start from a clean slate
+reset_graph $INSTANCE2
+check_functions $total_cnt
+
+# Trace functions with "lock" but not "clock"
+set_fgraph $INSTANCE2 '*lock*' '*clock*'
+
+# This should match the last time instance 2 was by itself
+cnt=`function_count`
+if [ $instance2_cnt -ne $cnt ]; then
+ fail
+fi
+
+# And it should not be tracing "clock" functions
+check_functions $clock_cnt 'clock'
+
+# Trace functions with "sched" but not "time"
+set_fgraph $INSTANCE1 '*sched*' '*time*'
+
+# This should match the last time both instances were enabled
+cnt=`function_count`
+if [ $instance1_2_cnt -ne $cnt ]; then
+ fail
+fi
+
+# Turn off the second instance
+reset_graph $INSTANCE2
+
+# This should match the last time instance 1 was by itself
+cnt=`function_count`
+if [ $instance1_cnt -ne $cnt ]; then
+ fail
+fi
+
+# And it should not be tracing "time" functions
+check_functions $time_cnt 'time'
+
+# Start from a clean slate
+reset_graph $INSTANCE1
+check_functions $total_cnt
+
+# Enable all functions but those that have "locks"
+set_fgraph $INSTANCE1 '' '*locks*'
+
+# Enable all functions but those that have "clock"
+set_fgraph $INSTANCE2 '' '*clock*'
+
+# If a function has "locks" it should not have "clock"
+check_cnt $locks_clock_cnt locks clock
+
+# If a function has "clock" it should not have "locks"
+check_cnt $clock_locks_cnt clock locks
+
+reset_graph $INSTANCE1
+reset_graph $INSTANCE2
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
index 7d7a6a06cdb7..2d8230da9064 100644
--- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
+++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c
@@ -98,7 +98,7 @@ int main(int argc, char *argv[])
info("Calling futex_waitv on f1: %u @ %p with val=%u\n", f1, &f1, f1+1);
res = futex_waitv(&waitv, 1, 0, &to, CLOCK_MONOTONIC);
if (!res || errno != EWOULDBLOCK) {
- ksft_test_result_pass("futex_waitv returned: %d %s\n",
+ ksft_test_result_fail("futex_waitv returned: %d %s\n",
res ? errno : res,
res ? strerror(errno) : "");
ret = RET_FAIL;
diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common
index 45b5570441ce..b1f40857307d 100644
--- a/tools/testing/selftests/hid/config.common
+++ b/tools/testing/selftests/hid/config.common
@@ -39,7 +39,6 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y
CONFIG_CPU_FREQ_STAT=y
CONFIG_CPU_IDLE_GOV_LADDER=y
CONFIG_CPUSETS=y
-CONFIG_CRC_T10DIF=y
CONFIG_CRYPTO_BLAKE2B=y
CONFIG_CRYPTO_DEV_VIRTIO=y
CONFIG_CRYPTO_SEQIV=y
diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index a1b2b657999d..1a8e85afe9aa 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -342,12 +342,14 @@ FIXTURE(iommufd_ioas)
uint32_t hwpt_id;
uint32_t device_id;
uint64_t base_iova;
+ uint32_t device_pasid_id;
};
FIXTURE_VARIANT(iommufd_ioas)
{
unsigned int mock_domains;
unsigned int memory_limit;
+ bool pasid_capable;
};
FIXTURE_SETUP(iommufd_ioas)
@@ -372,6 +374,12 @@ FIXTURE_SETUP(iommufd_ioas)
IOMMU_TEST_DEV_CACHE_DEFAULT);
self->base_iova = MOCK_APERTURE_START;
}
+
+ if (variant->pasid_capable)
+ test_cmd_mock_domain_flags(self->ioas_id,
+ MOCK_FLAGS_DEVICE_PASID,
+ NULL, NULL,
+ &self->device_pasid_id);
}
FIXTURE_TEARDOWN(iommufd_ioas)
@@ -387,6 +395,7 @@ FIXTURE_VARIANT_ADD(iommufd_ioas, no_domain)
FIXTURE_VARIANT_ADD(iommufd_ioas, mock_domain)
{
.mock_domains = 1,
+ .pasid_capable = true,
};
FIXTURE_VARIANT_ADD(iommufd_ioas, two_mock_domain)
@@ -439,6 +448,10 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
&test_hwpt_id);
test_err_hwpt_alloc(EINVAL, self->device_id, self->device_id, 0,
&test_hwpt_id);
+ test_err_hwpt_alloc(EOPNOTSUPP, self->device_id, self->ioas_id,
+ IOMMU_HWPT_ALLOC_NEST_PARENT |
+ IOMMU_HWPT_FAULT_ID_VALID,
+ &test_hwpt_id);
test_cmd_hwpt_alloc(self->device_id, self->ioas_id,
IOMMU_HWPT_ALLOC_NEST_PARENT,
@@ -748,6 +761,8 @@ TEST_F(iommufd_ioas, get_hw_info)
} buffer_smaller;
if (self->device_id) {
+ uint8_t max_pasid = 0;
+
/* Provide a zero-size user_buffer */
test_cmd_get_hw_info(self->device_id, NULL, 0);
/* Provide a user_buffer with exact size */
@@ -762,6 +777,13 @@ TEST_F(iommufd_ioas, get_hw_info)
* the fields within the size range still gets updated.
*/
test_cmd_get_hw_info(self->device_id, &buffer_smaller, sizeof(buffer_smaller));
+ test_cmd_get_hw_info_pasid(self->device_id, &max_pasid);
+ ASSERT_EQ(0, max_pasid);
+ if (variant->pasid_capable) {
+ test_cmd_get_hw_info_pasid(self->device_pasid_id,
+ &max_pasid);
+ ASSERT_EQ(MOCK_PASID_WIDTH, max_pasid);
+ }
} else {
test_err_get_hw_info(ENOENT, self->device_id,
&buffer_exact, sizeof(buffer_exact));
@@ -2736,6 +2758,7 @@ TEST_F(iommufd_viommu, viommu_alloc_nested_iopf)
uint32_t iopf_hwpt_id;
uint32_t fault_id;
uint32_t fault_fd;
+ uint32_t vdev_id;
if (self->device_id) {
test_ioctl_fault_alloc(&fault_id, &fault_fd);
@@ -2752,6 +2775,10 @@ TEST_F(iommufd_viommu, viommu_alloc_nested_iopf)
&iopf_hwpt_id, IOMMU_HWPT_DATA_SELFTEST, &data,
sizeof(data));
+ /* Must allocate vdevice before attaching to a nested hwpt */
+ test_err_mock_domain_replace(ENOENT, self->stdev_id,
+ iopf_hwpt_id);
+ test_cmd_vdevice_alloc(viommu_id, dev_id, 0x99, &vdev_id);
test_cmd_mock_domain_replace(self->stdev_id, iopf_hwpt_id);
EXPECT_ERRNO(EBUSY,
_test_ioctl_destroy(self->fd, iopf_hwpt_id));
@@ -2769,15 +2796,46 @@ TEST_F(iommufd_viommu, vdevice_alloc)
uint32_t viommu_id = self->viommu_id;
uint32_t dev_id = self->device_id;
uint32_t vdev_id = 0;
+ uint32_t veventq_id;
+ uint32_t veventq_fd;
+ int prev_seq = -1;
if (dev_id) {
+ /* Must allocate vdevice before attaching to a nested hwpt */
+ test_err_mock_domain_replace(ENOENT, self->stdev_id,
+ self->nested_hwpt_id);
+
+ /* Allocate a vEVENTQ with veventq_depth=2 */
+ test_cmd_veventq_alloc(viommu_id, IOMMU_VEVENTQ_TYPE_SELFTEST,
+ &veventq_id, &veventq_fd);
+ test_err_veventq_alloc(EEXIST, viommu_id,
+ IOMMU_VEVENTQ_TYPE_SELFTEST, NULL, NULL);
/* Set vdev_id to 0x99, unset it, and set to 0x88 */
test_cmd_vdevice_alloc(viommu_id, dev_id, 0x99, &vdev_id);
+ test_cmd_mock_domain_replace(self->stdev_id,
+ self->nested_hwpt_id);
+ test_cmd_trigger_vevents(dev_id, 1);
+ test_cmd_read_vevents(veventq_fd, 1, 0x99, &prev_seq);
test_err_vdevice_alloc(EEXIST, viommu_id, dev_id, 0x99,
&vdev_id);
+ test_cmd_mock_domain_replace(self->stdev_id, self->ioas_id);
test_ioctl_destroy(vdev_id);
+
+ /* Try again with 0x88 */
test_cmd_vdevice_alloc(viommu_id, dev_id, 0x88, &vdev_id);
+ test_cmd_mock_domain_replace(self->stdev_id,
+ self->nested_hwpt_id);
+ /* Trigger an overflow with three events */
+ test_cmd_trigger_vevents(dev_id, 3);
+ test_err_read_vevents(EOVERFLOW, veventq_fd, 3, 0x88,
+ &prev_seq);
+ /* Overflow must be gone after the previous reads */
+ test_cmd_trigger_vevents(dev_id, 1);
+ test_cmd_read_vevents(veventq_fd, 1, 0x88, &prev_seq);
+ close(veventq_fd);
+ test_cmd_mock_domain_replace(self->stdev_id, self->ioas_id);
test_ioctl_destroy(vdev_id);
+ test_ioctl_destroy(veventq_id);
} else {
test_err_vdevice_alloc(ENOENT, viommu_id, dev_id, 0x99, NULL);
}
@@ -2956,4 +3014,311 @@ TEST_F(iommufd_viommu, vdevice_cache)
}
}
+FIXTURE(iommufd_device_pasid)
+{
+ int fd;
+ uint32_t ioas_id;
+ uint32_t hwpt_id;
+ uint32_t stdev_id;
+ uint32_t device_id;
+ uint32_t no_pasid_stdev_id;
+ uint32_t no_pasid_device_id;
+};
+
+FIXTURE_VARIANT(iommufd_device_pasid)
+{
+ bool pasid_capable;
+};
+
+FIXTURE_SETUP(iommufd_device_pasid)
+{
+ self->fd = open("/dev/iommu", O_RDWR);
+ ASSERT_NE(-1, self->fd);
+ test_ioctl_ioas_alloc(&self->ioas_id);
+
+ test_cmd_mock_domain_flags(self->ioas_id,
+ MOCK_FLAGS_DEVICE_PASID,
+ &self->stdev_id, &self->hwpt_id,
+ &self->device_id);
+ if (!variant->pasid_capable)
+ test_cmd_mock_domain_flags(self->ioas_id, 0,
+ &self->no_pasid_stdev_id, NULL,
+ &self->no_pasid_device_id);
+}
+
+FIXTURE_TEARDOWN(iommufd_device_pasid)
+{
+ teardown_iommufd(self->fd, _metadata);
+}
+
+FIXTURE_VARIANT_ADD(iommufd_device_pasid, no_pasid)
+{
+ .pasid_capable = false,
+};
+
+FIXTURE_VARIANT_ADD(iommufd_device_pasid, has_pasid)
+{
+ .pasid_capable = true,
+};
+
+TEST_F(iommufd_device_pasid, pasid_attach)
+{
+ struct iommu_hwpt_selftest data = {
+ .iotlb = IOMMU_TEST_IOTLB_DEFAULT,
+ };
+ uint32_t nested_hwpt_id[3] = {};
+ uint32_t parent_hwpt_id = 0;
+ uint32_t fault_id, fault_fd;
+ uint32_t s2_hwpt_id = 0;
+ uint32_t iopf_hwpt_id;
+ uint32_t pasid = 100;
+ uint32_t viommu_id;
+
+ /*
+ * Negative, detach pasid without attaching, this is not expected.
+ * But it should not result in failure anyway.
+ */
+ test_cmd_pasid_detach(pasid);
+
+ /* Allocate two nested hwpts sharing one common parent hwpt */
+ test_cmd_hwpt_alloc(self->device_id, self->ioas_id,
+ IOMMU_HWPT_ALLOC_NEST_PARENT,
+ &parent_hwpt_id);
+ test_cmd_hwpt_alloc_nested(self->device_id, parent_hwpt_id,
+ IOMMU_HWPT_ALLOC_PASID,
+ &nested_hwpt_id[0],
+ IOMMU_HWPT_DATA_SELFTEST,
+ &data, sizeof(data));
+ test_cmd_hwpt_alloc_nested(self->device_id, parent_hwpt_id,
+ IOMMU_HWPT_ALLOC_PASID,
+ &nested_hwpt_id[1],
+ IOMMU_HWPT_DATA_SELFTEST,
+ &data, sizeof(data));
+
+ /* Fault related preparation */
+ test_ioctl_fault_alloc(&fault_id, &fault_fd);
+ test_cmd_hwpt_alloc_iopf(self->device_id, parent_hwpt_id, fault_id,
+ IOMMU_HWPT_FAULT_ID_VALID | IOMMU_HWPT_ALLOC_PASID,
+ &iopf_hwpt_id,
+ IOMMU_HWPT_DATA_SELFTEST, &data,
+ sizeof(data));
+
+ /* Allocate a regular nested hwpt based on viommu */
+ test_cmd_viommu_alloc(self->device_id, parent_hwpt_id,
+ IOMMU_VIOMMU_TYPE_SELFTEST,
+ &viommu_id);
+ test_cmd_hwpt_alloc_nested(self->device_id, viommu_id,
+ IOMMU_HWPT_ALLOC_PASID,
+ &nested_hwpt_id[2],
+ IOMMU_HWPT_DATA_SELFTEST, &data,
+ sizeof(data));
+
+ test_cmd_hwpt_alloc(self->device_id, self->ioas_id,
+ IOMMU_HWPT_ALLOC_PASID,
+ &s2_hwpt_id);
+
+ /* Attach RID to non-pasid compat domain, */
+ test_cmd_mock_domain_replace(self->stdev_id, parent_hwpt_id);
+ /* then attach to pasid should fail */
+ test_err_pasid_attach(EINVAL, pasid, s2_hwpt_id);
+
+ /* Attach RID to pasid compat domain, */
+ test_cmd_mock_domain_replace(self->stdev_id, s2_hwpt_id);
+ /* then attach to pasid should succeed, */
+ test_cmd_pasid_attach(pasid, nested_hwpt_id[0]);
+ /* but attach RID to non-pasid compat domain should fail now. */
+ test_err_mock_domain_replace(EINVAL, self->stdev_id, parent_hwpt_id);
+ /*
+ * Detach hwpt from pasid 100, and check if the pasid 100
+ * has null domain.
+ */
+ test_cmd_pasid_detach(pasid);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, 0));
+ /* RID is attached to pasid-comapt domain, pasid path is not used */
+
+ if (!variant->pasid_capable) {
+ /*
+ * PASID-compatible domain can be used by non-PASID-capable
+ * device.
+ */
+ test_cmd_mock_domain_replace(self->no_pasid_stdev_id, nested_hwpt_id[0]);
+ test_cmd_mock_domain_replace(self->no_pasid_stdev_id, self->ioas_id);
+ /*
+ * Attach hwpt to pasid 100 of non-PASID-capable device,
+ * should fail, no matter domain is pasid-comapt or not.
+ */
+ EXPECT_ERRNO(EINVAL,
+ _test_cmd_pasid_attach(self->fd, self->no_pasid_stdev_id,
+ pasid, parent_hwpt_id));
+ EXPECT_ERRNO(EINVAL,
+ _test_cmd_pasid_attach(self->fd, self->no_pasid_stdev_id,
+ pasid, s2_hwpt_id));
+ }
+
+ /*
+ * Attach non pasid compat hwpt to pasid-capable device, should
+ * fail, and have null domain.
+ */
+ test_err_pasid_attach(EINVAL, pasid, parent_hwpt_id);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, 0));
+
+ /*
+ * Attach ioas to pasid 100, should fail, domain should
+ * be null.
+ */
+ test_err_pasid_attach(EINVAL, pasid, self->ioas_id);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, 0));
+
+ /*
+ * Attach the s2_hwpt to pasid 100, should succeed, domain should
+ * be valid.
+ */
+ test_cmd_pasid_attach(pasid, s2_hwpt_id);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, s2_hwpt_id));
+
+ /*
+ * Try attach pasid 100 with another hwpt, should FAIL
+ * as attach does not allow overwrite, use REPLACE instead.
+ */
+ test_err_pasid_attach(EBUSY, pasid, nested_hwpt_id[0]);
+
+ /*
+ * Detach hwpt from pasid 100 for next test, should succeed,
+ * and have null domain.
+ */
+ test_cmd_pasid_detach(pasid);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, 0));
+
+ /*
+ * Attach nested hwpt to pasid 100, should succeed, domain
+ * should be valid.
+ */
+ test_cmd_pasid_attach(pasid, nested_hwpt_id[0]);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, nested_hwpt_id[0]));
+
+ /* Attach to pasid 100 which has been attached, should fail. */
+ test_err_pasid_attach(EBUSY, pasid, nested_hwpt_id[0]);
+
+ /* cleanup pasid 100 */
+ test_cmd_pasid_detach(pasid);
+
+ /* Replace tests */
+
+ pasid = 200;
+ /*
+ * Replace pasid 200 without attaching it, should fail
+ * with -EINVAL.
+ */
+ test_err_pasid_replace(EINVAL, pasid, s2_hwpt_id);
+
+ /*
+ * Attach the s2 hwpt to pasid 200, should succeed, domain should
+ * be valid.
+ */
+ test_cmd_pasid_attach(pasid, s2_hwpt_id);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, s2_hwpt_id));
+
+ /*
+ * Replace pasid 200 with self->ioas_id, should fail
+ * and domain should be the prior s2 hwpt.
+ */
+ test_err_pasid_replace(EINVAL, pasid, self->ioas_id);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, s2_hwpt_id));
+
+ /*
+ * Replace a nested hwpt for pasid 200, should succeed,
+ * and have valid domain.
+ */
+ test_cmd_pasid_replace(pasid, nested_hwpt_id[0]);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, nested_hwpt_id[0]));
+
+ /*
+ * Replace with another nested hwpt for pasid 200, should
+ * succeed, and have valid domain.
+ */
+ test_cmd_pasid_replace(pasid, nested_hwpt_id[1]);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, nested_hwpt_id[1]));
+
+ /* cleanup pasid 200 */
+ test_cmd_pasid_detach(pasid);
+
+ /* Negative Tests for pasid replace, use pasid 1024 */
+
+ /*
+ * Attach the s2 hwpt to pasid 1024, should succeed, domain should
+ * be valid.
+ */
+ pasid = 1024;
+ test_cmd_pasid_attach(pasid, s2_hwpt_id);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, s2_hwpt_id));
+
+ /*
+ * Replace pasid 1024 with nested_hwpt_id[0], should fail,
+ * but have the old valid domain. This is a designed
+ * negative case. Normally, this shall succeed.
+ */
+ test_err_pasid_replace(ENOMEM, pasid, nested_hwpt_id[0]);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, s2_hwpt_id));
+
+ /* cleanup pasid 1024 */
+ test_cmd_pasid_detach(pasid);
+
+ /* Attach to iopf-capable hwpt */
+
+ /*
+ * Attach an iopf hwpt to pasid 2048, should succeed, domain should
+ * be valid.
+ */
+ pasid = 2048;
+ test_cmd_pasid_attach(pasid, iopf_hwpt_id);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, iopf_hwpt_id));
+
+ test_cmd_trigger_iopf_pasid(self->device_id, pasid, fault_fd);
+
+ /*
+ * Replace with s2_hwpt_id for pasid 2048, should
+ * succeed, and have valid domain.
+ */
+ test_cmd_pasid_replace(pasid, s2_hwpt_id);
+ ASSERT_EQ(0,
+ test_cmd_pasid_check_hwpt(self->fd, self->stdev_id,
+ pasid, s2_hwpt_id));
+
+ /* cleanup pasid 2048 */
+ test_cmd_pasid_detach(pasid);
+
+ test_ioctl_destroy(iopf_hwpt_id);
+ close(fault_fd);
+ test_ioctl_destroy(fault_id);
+
+ /* Detach the s2_hwpt_id from RID */
+ test_cmd_mock_domain_replace(self->stdev_id, self->ioas_id);
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c
index 64b1f8e1b0cf..e11ec4b121fc 100644
--- a/tools/testing/selftests/iommu/iommufd_fail_nth.c
+++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c
@@ -209,12 +209,16 @@ FIXTURE(basic_fail_nth)
{
int fd;
uint32_t access_id;
+ uint32_t stdev_id;
+ uint32_t pasid;
};
FIXTURE_SETUP(basic_fail_nth)
{
self->fd = -1;
self->access_id = 0;
+ self->stdev_id = 0;
+ self->pasid = 0; //test should use a non-zero value
}
FIXTURE_TEARDOWN(basic_fail_nth)
@@ -226,6 +230,8 @@ FIXTURE_TEARDOWN(basic_fail_nth)
rc = _test_cmd_destroy_access(self->access_id);
assert(rc == 0);
}
+ if (self->pasid && self->stdev_id)
+ _test_cmd_pasid_detach(self->fd, self->stdev_id, self->pasid);
teardown_iommufd(self->fd, _metadata);
}
@@ -620,10 +626,11 @@ TEST_FAIL_NTH(basic_fail_nth, device)
};
struct iommu_test_hw_info info;
uint32_t fault_id, fault_fd;
+ uint32_t veventq_id, veventq_fd;
uint32_t fault_hwpt_id;
+ uint32_t test_hwpt_id;
uint32_t ioas_id;
uint32_t ioas_id2;
- uint32_t stdev_id;
uint32_t idev_id;
uint32_t hwpt_id;
uint32_t viommu_id;
@@ -654,25 +661,30 @@ TEST_FAIL_NTH(basic_fail_nth, device)
fail_nth_enable();
- if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, NULL,
- &idev_id))
+ if (_test_cmd_mock_domain_flags(self->fd, ioas_id,
+ MOCK_FLAGS_DEVICE_PASID,
+ &self->stdev_id, NULL, &idev_id))
return -1;
- if (_test_cmd_get_hw_info(self->fd, idev_id, &info, sizeof(info), NULL))
+ if (_test_cmd_get_hw_info(self->fd, idev_id, &info,
+ sizeof(info), NULL, NULL))
return -1;
- if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0, 0, &hwpt_id,
+ if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0,
+ IOMMU_HWPT_ALLOC_PASID, &hwpt_id,
IOMMU_HWPT_DATA_NONE, 0, 0))
return -1;
- if (_test_cmd_mock_domain_replace(self->fd, stdev_id, ioas_id2, NULL))
+ if (_test_cmd_mock_domain_replace(self->fd, self->stdev_id, ioas_id2, NULL))
return -1;
- if (_test_cmd_mock_domain_replace(self->fd, stdev_id, hwpt_id, NULL))
+ if (_test_cmd_mock_domain_replace(self->fd, self->stdev_id, hwpt_id, NULL))
return -1;
if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0,
- IOMMU_HWPT_ALLOC_NEST_PARENT, &hwpt_id,
+ IOMMU_HWPT_ALLOC_NEST_PARENT |
+ IOMMU_HWPT_ALLOC_PASID,
+ &hwpt_id,
IOMMU_HWPT_DATA_NONE, 0, 0))
return -1;
@@ -692,6 +704,37 @@ TEST_FAIL_NTH(basic_fail_nth, device)
IOMMU_HWPT_DATA_SELFTEST, &data, sizeof(data)))
return -1;
+ if (_test_cmd_veventq_alloc(self->fd, viommu_id,
+ IOMMU_VEVENTQ_TYPE_SELFTEST, &veventq_id,
+ &veventq_fd))
+ return -1;
+ close(veventq_fd);
+
+ if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0,
+ IOMMU_HWPT_ALLOC_PASID,
+ &test_hwpt_id,
+ IOMMU_HWPT_DATA_NONE, 0, 0))
+ return -1;
+
+ /* Tests for pasid attach/replace/detach */
+
+ self->pasid = 200;
+
+ if (_test_cmd_pasid_attach(self->fd, self->stdev_id,
+ self->pasid, hwpt_id)) {
+ self->pasid = 0;
+ return -1;
+ }
+
+ if (_test_cmd_pasid_replace(self->fd, self->stdev_id,
+ self->pasid, test_hwpt_id))
+ return -1;
+
+ if (_test_cmd_pasid_detach(self->fd, self->stdev_id, self->pasid))
+ return -1;
+
+ self->pasid = 0;
+
return 0;
}
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index d979f5b0efe8..72f6636e5d90 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -9,6 +9,7 @@
#include <sys/ioctl.h>
#include <stdint.h>
#include <assert.h>
+#include <poll.h>
#include "../kselftest_harness.h"
#include "../../../../drivers/iommu/iommufd/iommufd_test.h"
@@ -757,7 +758,8 @@ static void teardown_iommufd(int fd, struct __test_metadata *_metadata)
/* @data can be NULL */
static int _test_cmd_get_hw_info(int fd, __u32 device_id, void *data,
- size_t data_len, uint32_t *capabilities)
+ size_t data_len, uint32_t *capabilities,
+ uint8_t *max_pasid)
{
struct iommu_test_hw_info *info = (struct iommu_test_hw_info *)data;
struct iommu_hw_info cmd = {
@@ -802,6 +804,9 @@ static int _test_cmd_get_hw_info(int fd, __u32 device_id, void *data,
assert(!info->flags);
}
+ if (max_pasid)
+ *max_pasid = cmd.out_max_pasid_log2;
+
if (capabilities)
*capabilities = cmd.out_capabilities;
@@ -810,14 +815,19 @@ static int _test_cmd_get_hw_info(int fd, __u32 device_id, void *data,
#define test_cmd_get_hw_info(device_id, data, data_len) \
ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, data, \
- data_len, NULL))
+ data_len, NULL, NULL))
#define test_err_get_hw_info(_errno, device_id, data, data_len) \
EXPECT_ERRNO(_errno, _test_cmd_get_hw_info(self->fd, device_id, data, \
- data_len, NULL))
+ data_len, NULL, NULL))
#define test_cmd_get_hw_capabilities(device_id, caps, mask) \
- ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, NULL, 0, &caps))
+ ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, NULL, \
+ 0, &caps, NULL))
+
+#define test_cmd_get_hw_info_pasid(device_id, max_pasid) \
+ ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, NULL, \
+ 0, NULL, max_pasid))
static int _test_ioctl_fault_alloc(int fd, __u32 *fault_id, __u32 *fault_fd)
{
@@ -842,14 +852,15 @@ static int _test_ioctl_fault_alloc(int fd, __u32 *fault_id, __u32 *fault_fd)
ASSERT_NE(0, *(fault_fd)); \
})
-static int _test_cmd_trigger_iopf(int fd, __u32 device_id, __u32 fault_fd)
+static int _test_cmd_trigger_iopf(int fd, __u32 device_id, __u32 pasid,
+ __u32 fault_fd)
{
struct iommu_test_cmd trigger_iopf_cmd = {
.size = sizeof(trigger_iopf_cmd),
.op = IOMMU_TEST_OP_TRIGGER_IOPF,
.trigger_iopf = {
.dev_id = device_id,
- .pasid = 0x1,
+ .pasid = pasid,
.grpid = 0x2,
.perm = IOMMU_PGFAULT_PERM_READ | IOMMU_PGFAULT_PERM_WRITE,
.addr = 0xdeadbeaf,
@@ -880,7 +891,10 @@ static int _test_cmd_trigger_iopf(int fd, __u32 device_id, __u32 fault_fd)
}
#define test_cmd_trigger_iopf(device_id, fault_fd) \
- ASSERT_EQ(0, _test_cmd_trigger_iopf(self->fd, device_id, fault_fd))
+ ASSERT_EQ(0, _test_cmd_trigger_iopf(self->fd, device_id, 0x1, fault_fd))
+#define test_cmd_trigger_iopf_pasid(device_id, pasid, fault_fd) \
+ ASSERT_EQ(0, _test_cmd_trigger_iopf(self->fd, device_id, \
+ pasid, fault_fd))
static int _test_cmd_viommu_alloc(int fd, __u32 device_id, __u32 hwpt_id,
__u32 type, __u32 flags, __u32 *viommu_id)
@@ -936,3 +950,204 @@ static int _test_cmd_vdevice_alloc(int fd, __u32 viommu_id, __u32 idev_id,
EXPECT_ERRNO(_errno, \
_test_cmd_vdevice_alloc(self->fd, viommu_id, idev_id, \
virt_id, vdev_id))
+
+static int _test_cmd_veventq_alloc(int fd, __u32 viommu_id, __u32 type,
+ __u32 *veventq_id, __u32 *veventq_fd)
+{
+ struct iommu_veventq_alloc cmd = {
+ .size = sizeof(cmd),
+ .type = type,
+ .veventq_depth = 2,
+ .viommu_id = viommu_id,
+ };
+ int ret;
+
+ ret = ioctl(fd, IOMMU_VEVENTQ_ALLOC, &cmd);
+ if (ret)
+ return ret;
+ if (veventq_id)
+ *veventq_id = cmd.out_veventq_id;
+ if (veventq_fd)
+ *veventq_fd = cmd.out_veventq_fd;
+ return 0;
+}
+
+#define test_cmd_veventq_alloc(viommu_id, type, veventq_id, veventq_fd) \
+ ASSERT_EQ(0, _test_cmd_veventq_alloc(self->fd, viommu_id, type, \
+ veventq_id, veventq_fd))
+#define test_err_veventq_alloc(_errno, viommu_id, type, veventq_id, \
+ veventq_fd) \
+ EXPECT_ERRNO(_errno, \
+ _test_cmd_veventq_alloc(self->fd, viommu_id, type, \
+ veventq_id, veventq_fd))
+
+static int _test_cmd_trigger_vevents(int fd, __u32 dev_id, __u32 nvevents)
+{
+ struct iommu_test_cmd trigger_vevent_cmd = {
+ .size = sizeof(trigger_vevent_cmd),
+ .op = IOMMU_TEST_OP_TRIGGER_VEVENT,
+ .trigger_vevent = {
+ .dev_id = dev_id,
+ },
+ };
+ int ret;
+
+ while (nvevents--) {
+ ret = ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_TRIGGER_VEVENT),
+ &trigger_vevent_cmd);
+ if (ret < 0)
+ return -1;
+ }
+ return ret;
+}
+
+#define test_cmd_trigger_vevents(dev_id, nvevents) \
+ ASSERT_EQ(0, _test_cmd_trigger_vevents(self->fd, dev_id, nvevents))
+
+static int _test_cmd_read_vevents(int fd, __u32 event_fd, __u32 nvevents,
+ __u32 virt_id, int *prev_seq)
+{
+ struct pollfd pollfd = { .fd = event_fd, .events = POLLIN };
+ struct iommu_viommu_event_selftest *event;
+ struct iommufd_vevent_header *hdr;
+ ssize_t bytes;
+ void *data;
+ int ret, i;
+
+ ret = poll(&pollfd, 1, 1000);
+ if (ret < 0)
+ return -1;
+
+ data = calloc(nvevents, sizeof(*hdr) + sizeof(*event));
+ if (!data) {
+ errno = ENOMEM;
+ return -1;
+ }
+
+ bytes = read(event_fd, data,
+ nvevents * (sizeof(*hdr) + sizeof(*event)));
+ if (bytes <= 0) {
+ errno = EFAULT;
+ ret = -1;
+ goto out_free;
+ }
+
+ for (i = 0; i < nvevents; i++) {
+ hdr = data + i * (sizeof(*hdr) + sizeof(*event));
+
+ if (hdr->flags & IOMMU_VEVENTQ_FLAG_LOST_EVENTS ||
+ hdr->sequence - *prev_seq > 1) {
+ *prev_seq = hdr->sequence;
+ errno = EOVERFLOW;
+ ret = -1;
+ goto out_free;
+ }
+ *prev_seq = hdr->sequence;
+ event = data + sizeof(*hdr);
+ if (event->virt_id != virt_id) {
+ errno = EINVAL;
+ ret = -1;
+ goto out_free;
+ }
+ }
+
+ ret = 0;
+out_free:
+ free(data);
+ return ret;
+}
+
+#define test_cmd_read_vevents(event_fd, nvevents, virt_id, prev_seq) \
+ ASSERT_EQ(0, _test_cmd_read_vevents(self->fd, event_fd, nvevents, \
+ virt_id, prev_seq))
+#define test_err_read_vevents(_errno, event_fd, nvevents, virt_id, prev_seq) \
+ EXPECT_ERRNO(_errno, \
+ _test_cmd_read_vevents(self->fd, event_fd, nvevents, \
+ virt_id, prev_seq))
+
+static int _test_cmd_pasid_attach(int fd, __u32 stdev_id, __u32 pasid,
+ __u32 pt_id)
+{
+ struct iommu_test_cmd test_attach = {
+ .size = sizeof(test_attach),
+ .op = IOMMU_TEST_OP_PASID_ATTACH,
+ .id = stdev_id,
+ .pasid_attach = {
+ .pasid = pasid,
+ .pt_id = pt_id,
+ },
+ };
+
+ return ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_PASID_ATTACH),
+ &test_attach);
+}
+
+#define test_cmd_pasid_attach(pasid, hwpt_id) \
+ ASSERT_EQ(0, _test_cmd_pasid_attach(self->fd, self->stdev_id, \
+ pasid, hwpt_id))
+
+#define test_err_pasid_attach(_errno, pasid, hwpt_id) \
+ EXPECT_ERRNO(_errno, \
+ _test_cmd_pasid_attach(self->fd, self->stdev_id, \
+ pasid, hwpt_id))
+
+static int _test_cmd_pasid_replace(int fd, __u32 stdev_id, __u32 pasid,
+ __u32 pt_id)
+{
+ struct iommu_test_cmd test_replace = {
+ .size = sizeof(test_replace),
+ .op = IOMMU_TEST_OP_PASID_REPLACE,
+ .id = stdev_id,
+ .pasid_replace = {
+ .pasid = pasid,
+ .pt_id = pt_id,
+ },
+ };
+
+ return ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_PASID_REPLACE),
+ &test_replace);
+}
+
+#define test_cmd_pasid_replace(pasid, hwpt_id) \
+ ASSERT_EQ(0, _test_cmd_pasid_replace(self->fd, self->stdev_id, \
+ pasid, hwpt_id))
+
+#define test_err_pasid_replace(_errno, pasid, hwpt_id) \
+ EXPECT_ERRNO(_errno, \
+ _test_cmd_pasid_replace(self->fd, self->stdev_id, \
+ pasid, hwpt_id))
+
+static int _test_cmd_pasid_detach(int fd, __u32 stdev_id, __u32 pasid)
+{
+ struct iommu_test_cmd test_detach = {
+ .size = sizeof(test_detach),
+ .op = IOMMU_TEST_OP_PASID_DETACH,
+ .id = stdev_id,
+ .pasid_detach = {
+ .pasid = pasid,
+ },
+ };
+
+ return ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_PASID_DETACH),
+ &test_detach);
+}
+
+#define test_cmd_pasid_detach(pasid) \
+ ASSERT_EQ(0, _test_cmd_pasid_detach(self->fd, self->stdev_id, pasid))
+
+static int test_cmd_pasid_check_hwpt(int fd, __u32 stdev_id, __u32 pasid,
+ __u32 hwpt_id)
+{
+ struct iommu_test_cmd test_pasid_check = {
+ .size = sizeof(test_pasid_check),
+ .op = IOMMU_TEST_OP_PASID_CHECK_HWPT,
+ .id = stdev_id,
+ .pasid_check = {
+ .pasid = pasid,
+ .hwpt_id = hwpt_id,
+ },
+ };
+
+ return ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_PASID_CHECK_HWPT),
+ &test_pasid_check);
+}
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index f773f8f99249..f62b0a5aba35 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -50,8 +50,18 @@ LIBKVM_riscv += lib/riscv/ucall.c
# Non-compiled test targets
TEST_PROGS_x86 += x86/nx_huge_pages_test.sh
+# Compiled test targets valid on all architectures with libkvm support
+TEST_GEN_PROGS_COMMON = demand_paging_test
+TEST_GEN_PROGS_COMMON += dirty_log_test
+TEST_GEN_PROGS_COMMON += guest_print_test
+TEST_GEN_PROGS_COMMON += kvm_binary_stats_test
+TEST_GEN_PROGS_COMMON += kvm_create_max_vcpus
+TEST_GEN_PROGS_COMMON += kvm_page_table_test
+TEST_GEN_PROGS_COMMON += set_memory_region_test
+
# Compiled test targets
-TEST_GEN_PROGS_x86 = x86/cpuid_test
+TEST_GEN_PROGS_x86 = $(TEST_GEN_PROGS_COMMON)
+TEST_GEN_PROGS_x86 += x86/cpuid_test
TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test
TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test
TEST_GEN_PROGS_x86 += x86/feature_msrs_test
@@ -119,27 +129,21 @@ TEST_GEN_PROGS_x86 += x86/triple_fault_event_test
TEST_GEN_PROGS_x86 += x86/recalc_apic_map_test
TEST_GEN_PROGS_x86 += access_tracking_perf_test
TEST_GEN_PROGS_x86 += coalesced_io_test
-TEST_GEN_PROGS_x86 += demand_paging_test
-TEST_GEN_PROGS_x86 += dirty_log_test
TEST_GEN_PROGS_x86 += dirty_log_perf_test
TEST_GEN_PROGS_x86 += guest_memfd_test
-TEST_GEN_PROGS_x86 += guest_print_test
TEST_GEN_PROGS_x86 += hardware_disable_test
-TEST_GEN_PROGS_x86 += kvm_create_max_vcpus
-TEST_GEN_PROGS_x86 += kvm_page_table_test
TEST_GEN_PROGS_x86 += memslot_modification_stress_test
TEST_GEN_PROGS_x86 += memslot_perf_test
TEST_GEN_PROGS_x86 += mmu_stress_test
TEST_GEN_PROGS_x86 += rseq_test
-TEST_GEN_PROGS_x86 += set_memory_region_test
TEST_GEN_PROGS_x86 += steal_time
-TEST_GEN_PROGS_x86 += kvm_binary_stats_test
TEST_GEN_PROGS_x86 += system_counter_offset_test
TEST_GEN_PROGS_x86 += pre_fault_memory_test
# Compiled outputs used by test targets
TEST_GEN_PROGS_EXTENDED_x86 += x86/nx_huge_pages_test
+TEST_GEN_PROGS_arm64 = $(TEST_GEN_PROGS_COMMON)
TEST_GEN_PROGS_arm64 += arm64/aarch32_id_regs
TEST_GEN_PROGS_arm64 += arm64/arch_timer_edge_cases
TEST_GEN_PROGS_arm64 += arm64/debug-exceptions
@@ -158,22 +162,16 @@ TEST_GEN_PROGS_arm64 += arm64/no-vgic-v3
TEST_GEN_PROGS_arm64 += access_tracking_perf_test
TEST_GEN_PROGS_arm64 += arch_timer
TEST_GEN_PROGS_arm64 += coalesced_io_test
-TEST_GEN_PROGS_arm64 += demand_paging_test
-TEST_GEN_PROGS_arm64 += dirty_log_test
TEST_GEN_PROGS_arm64 += dirty_log_perf_test
-TEST_GEN_PROGS_arm64 += guest_print_test
TEST_GEN_PROGS_arm64 += get-reg-list
-TEST_GEN_PROGS_arm64 += kvm_create_max_vcpus
-TEST_GEN_PROGS_arm64 += kvm_page_table_test
TEST_GEN_PROGS_arm64 += memslot_modification_stress_test
TEST_GEN_PROGS_arm64 += memslot_perf_test
TEST_GEN_PROGS_arm64 += mmu_stress_test
TEST_GEN_PROGS_arm64 += rseq_test
-TEST_GEN_PROGS_arm64 += set_memory_region_test
TEST_GEN_PROGS_arm64 += steal_time
-TEST_GEN_PROGS_arm64 += kvm_binary_stats_test
-TEST_GEN_PROGS_s390 = s390/memop
+TEST_GEN_PROGS_s390 = $(TEST_GEN_PROGS_COMMON)
+TEST_GEN_PROGS_s390 += s390/memop
TEST_GEN_PROGS_s390 += s390/resets
TEST_GEN_PROGS_s390 += s390/sync_regs_test
TEST_GEN_PROGS_s390 += s390/tprot
@@ -182,27 +180,14 @@ TEST_GEN_PROGS_s390 += s390/debug_test
TEST_GEN_PROGS_s390 += s390/cpumodel_subfuncs_test
TEST_GEN_PROGS_s390 += s390/shared_zeropage_test
TEST_GEN_PROGS_s390 += s390/ucontrol_test
-TEST_GEN_PROGS_s390 += demand_paging_test
-TEST_GEN_PROGS_s390 += dirty_log_test
-TEST_GEN_PROGS_s390 += guest_print_test
-TEST_GEN_PROGS_s390 += kvm_create_max_vcpus
-TEST_GEN_PROGS_s390 += kvm_page_table_test
TEST_GEN_PROGS_s390 += rseq_test
-TEST_GEN_PROGS_s390 += set_memory_region_test
-TEST_GEN_PROGS_s390 += kvm_binary_stats_test
+TEST_GEN_PROGS_riscv = $(TEST_GEN_PROGS_COMMON)
TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test
TEST_GEN_PROGS_riscv += riscv/ebreak_test
TEST_GEN_PROGS_riscv += arch_timer
TEST_GEN_PROGS_riscv += coalesced_io_test
-TEST_GEN_PROGS_riscv += demand_paging_test
-TEST_GEN_PROGS_riscv += dirty_log_test
TEST_GEN_PROGS_riscv += get-reg-list
-TEST_GEN_PROGS_riscv += guest_print_test
-TEST_GEN_PROGS_riscv += kvm_binary_stats_test
-TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
-TEST_GEN_PROGS_riscv += kvm_page_table_test
-TEST_GEN_PROGS_riscv += set_memory_region_test
TEST_GEN_PROGS_riscv += steal_time
SPLIT_TESTS += arch_timer
diff --git a/tools/testing/selftests/kvm/arm64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c
index ec33a8f9c908..dc6559dad9d8 100644
--- a/tools/testing/selftests/kvm/arm64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c
@@ -199,7 +199,7 @@ static bool guest_set_ha(void)
if (hadbs == 0)
return false;
- tcr = read_sysreg(tcr_el1) | TCR_EL1_HA;
+ tcr = read_sysreg(tcr_el1) | TCR_HA;
write_sysreg(tcr, tcr_el1);
isb();
diff --git a/tools/testing/selftests/kvm/include/arm64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h
index 1e8d0d531fbd..b0fc0f945766 100644
--- a/tools/testing/selftests/kvm/include/arm64/processor.h
+++ b/tools/testing/selftests/kvm/include/arm64/processor.h
@@ -62,6 +62,67 @@
MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) | \
MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT))
+/* TCR_EL1 specific flags */
+#define TCR_T0SZ_OFFSET 0
+#define TCR_T0SZ(x) ((UL(64) - (x)) << TCR_T0SZ_OFFSET)
+
+#define TCR_IRGN0_SHIFT 8
+#define TCR_IRGN0_MASK (UL(3) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_NC (UL(0) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBWA (UL(1) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WT (UL(2) << TCR_IRGN0_SHIFT)
+#define TCR_IRGN0_WBnWA (UL(3) << TCR_IRGN0_SHIFT)
+
+#define TCR_ORGN0_SHIFT 10
+#define TCR_ORGN0_MASK (UL(3) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_NC (UL(0) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBWA (UL(1) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WT (UL(2) << TCR_ORGN0_SHIFT)
+#define TCR_ORGN0_WBnWA (UL(3) << TCR_ORGN0_SHIFT)
+
+#define TCR_SH0_SHIFT 12
+#define TCR_SH0_MASK (UL(3) << TCR_SH0_SHIFT)
+#define TCR_SH0_INNER (UL(3) << TCR_SH0_SHIFT)
+
+#define TCR_TG0_SHIFT 14
+#define TCR_TG0_MASK (UL(3) << TCR_TG0_SHIFT)
+#define TCR_TG0_4K (UL(0) << TCR_TG0_SHIFT)
+#define TCR_TG0_64K (UL(1) << TCR_TG0_SHIFT)
+#define TCR_TG0_16K (UL(2) << TCR_TG0_SHIFT)
+
+#define TCR_IPS_SHIFT 32
+#define TCR_IPS_MASK (UL(7) << TCR_IPS_SHIFT)
+#define TCR_IPS_52_BITS (UL(6) << TCR_IPS_SHIFT)
+#define TCR_IPS_48_BITS (UL(5) << TCR_IPS_SHIFT)
+#define TCR_IPS_40_BITS (UL(2) << TCR_IPS_SHIFT)
+#define TCR_IPS_36_BITS (UL(1) << TCR_IPS_SHIFT)
+
+#define TCR_HA (UL(1) << 39)
+#define TCR_DS (UL(1) << 59)
+
+/*
+ * AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
+ */
+#define PTE_ATTRINDX(t) ((t) << 2)
+#define PTE_ATTRINDX_MASK GENMASK(4, 2)
+#define PTE_ATTRINDX_SHIFT 2
+
+#define PTE_VALID BIT(0)
+#define PGD_TYPE_TABLE BIT(1)
+#define PUD_TYPE_TABLE BIT(1)
+#define PMD_TYPE_TABLE BIT(1)
+#define PTE_TYPE_PAGE BIT(1)
+
+#define PTE_SHARED (UL(3) << 8) /* SH[1:0], inner shareable */
+#define PTE_AF BIT(10)
+
+#define PTE_ADDR_MASK(page_shift) GENMASK(47, (page_shift))
+#define PTE_ADDR_51_48 GENMASK(15, 12)
+#define PTE_ADDR_51_48_SHIFT 12
+#define PTE_ADDR_MASK_LPA2(page_shift) GENMASK(49, (page_shift))
+#define PTE_ADDR_51_50_LPA2 GENMASK(9, 8)
+#define PTE_ADDR_51_50_LPA2_SHIFT 8
+
void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init);
struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
struct kvm_vcpu_init *init, void *guest_code);
@@ -102,12 +163,6 @@ enum {
(v) == VECTOR_SYNC_LOWER_64 || \
(v) == VECTOR_SYNC_LOWER_32)
-/* Access flag */
-#define PTE_AF (1ULL << 10)
-
-/* Access flag update enable/disable */
-#define TCR_EL1_HA (1ULL << 39)
-
void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
uint32_t *ipa16k, uint32_t *ipa64k);
diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c
index 7ba3aa3755f3..9d69904cb608 100644
--- a/tools/testing/selftests/kvm/lib/arm64/processor.c
+++ b/tools/testing/selftests/kvm/lib/arm64/processor.c
@@ -72,13 +72,13 @@ static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs)
uint64_t pte;
if (use_lpa2_pte_format(vm)) {
- pte = pa & GENMASK(49, vm->page_shift);
- pte |= FIELD_GET(GENMASK(51, 50), pa) << 8;
- attrs &= ~GENMASK(9, 8);
+ pte = pa & PTE_ADDR_MASK_LPA2(vm->page_shift);
+ pte |= FIELD_GET(GENMASK(51, 50), pa) << PTE_ADDR_51_50_LPA2_SHIFT;
+ attrs &= ~PTE_ADDR_51_50_LPA2;
} else {
- pte = pa & GENMASK(47, vm->page_shift);
+ pte = pa & PTE_ADDR_MASK(vm->page_shift);
if (vm->page_shift == 16)
- pte |= FIELD_GET(GENMASK(51, 48), pa) << 12;
+ pte |= FIELD_GET(GENMASK(51, 48), pa) << PTE_ADDR_51_48_SHIFT;
}
pte |= attrs;
@@ -90,12 +90,12 @@ static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte)
uint64_t pa;
if (use_lpa2_pte_format(vm)) {
- pa = pte & GENMASK(49, vm->page_shift);
- pa |= FIELD_GET(GENMASK(9, 8), pte) << 50;
+ pa = pte & PTE_ADDR_MASK_LPA2(vm->page_shift);
+ pa |= FIELD_GET(PTE_ADDR_51_50_LPA2, pte) << 50;
} else {
- pa = pte & GENMASK(47, vm->page_shift);
+ pa = pte & PTE_ADDR_MASK(vm->page_shift);
if (vm->page_shift == 16)
- pa |= FIELD_GET(GENMASK(15, 12), pte) << 48;
+ pa |= FIELD_GET(PTE_ADDR_51_48, pte) << 48;
}
return pa;
@@ -128,7 +128,8 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
uint64_t flags)
{
- uint8_t attr_idx = flags & 7;
+ uint8_t attr_idx = flags & (PTE_ATTRINDX_MASK >> PTE_ATTRINDX_SHIFT);
+ uint64_t pg_attr;
uint64_t *ptep;
TEST_ASSERT((vaddr % vm->page_size) == 0,
@@ -147,18 +148,21 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8;
if (!*ptep)
- *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+ *ptep = addr_pte(vm, vm_alloc_page_table(vm),
+ PGD_TYPE_TABLE | PTE_VALID);
switch (vm->pgtable_levels) {
case 4:
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8;
if (!*ptep)
- *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+ *ptep = addr_pte(vm, vm_alloc_page_table(vm),
+ PUD_TYPE_TABLE | PTE_VALID);
/* fall through */
case 3:
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8;
if (!*ptep)
- *ptep = addr_pte(vm, vm_alloc_page_table(vm), 3);
+ *ptep = addr_pte(vm, vm_alloc_page_table(vm),
+ PMD_TYPE_TABLE | PTE_VALID);
/* fall through */
case 2:
ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
@@ -167,7 +171,11 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
TEST_FAIL("Page table levels must be 2, 3, or 4");
}
- *ptep = addr_pte(vm, paddr, (attr_idx << 2) | (1 << 10) | 3); /* AF */
+ pg_attr = PTE_AF | PTE_ATTRINDX(attr_idx) | PTE_TYPE_PAGE | PTE_VALID;
+ if (!use_lpa2_pte_format(vm))
+ pg_attr |= PTE_SHARED;
+
+ *ptep = addr_pte(vm, paddr, pg_attr);
}
void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -293,20 +301,20 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
case VM_MODE_P48V48_64K:
case VM_MODE_P40V48_64K:
case VM_MODE_P36V48_64K:
- tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+ tcr_el1 |= TCR_TG0_64K;
break;
case VM_MODE_P52V48_16K:
case VM_MODE_P48V48_16K:
case VM_MODE_P40V48_16K:
case VM_MODE_P36V48_16K:
case VM_MODE_P36V47_16K:
- tcr_el1 |= 2ul << 14; /* TG0 = 16KB */
+ tcr_el1 |= TCR_TG0_16K;
break;
case VM_MODE_P52V48_4K:
case VM_MODE_P48V48_4K:
case VM_MODE_P40V48_4K:
case VM_MODE_P36V48_4K:
- tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+ tcr_el1 |= TCR_TG0_4K;
break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
@@ -319,35 +327,35 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
case VM_MODE_P52V48_4K:
case VM_MODE_P52V48_16K:
case VM_MODE_P52V48_64K:
- tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+ tcr_el1 |= TCR_IPS_52_BITS;
ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2;
break;
case VM_MODE_P48V48_4K:
case VM_MODE_P48V48_16K:
case VM_MODE_P48V48_64K:
- tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
+ tcr_el1 |= TCR_IPS_48_BITS;
break;
case VM_MODE_P40V48_4K:
case VM_MODE_P40V48_16K:
case VM_MODE_P40V48_64K:
- tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+ tcr_el1 |= TCR_IPS_40_BITS;
break;
case VM_MODE_P36V48_4K:
case VM_MODE_P36V48_16K:
case VM_MODE_P36V48_64K:
case VM_MODE_P36V47_16K:
- tcr_el1 |= 1ul << 32; /* IPS = 36 bits */
+ tcr_el1 |= TCR_IPS_36_BITS;
break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
}
- sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */;
- /* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
- tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
- tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+ sctlr_el1 |= SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_I;
+
+ tcr_el1 |= TCR_IRGN0_WBWA | TCR_ORGN0_WBWA | TCR_SH0_INNER;
+ tcr_el1 |= TCR_T0SZ(vm->va_bits);
if (use_lpa2_pte_format(vm))
- tcr_el1 |= (1ul << 59) /* DS */;
+ tcr_el1 |= TCR_DS;
vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1);
vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 279ad8946040..815bc45dd8dc 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -2019,9 +2019,8 @@ static struct exit_reason {
KVM_EXIT_STRING(RISCV_SBI),
KVM_EXIT_STRING(RISCV_CSR),
KVM_EXIT_STRING(NOTIFY),
-#ifdef KVM_EXIT_MEMORY_NOT_PRESENT
- KVM_EXIT_STRING(MEMORY_NOT_PRESENT),
-#endif
+ KVM_EXIT_STRING(LOONGARCH_IOCSR),
+ KVM_EXIT_STRING(MEMORY_FAULT),
};
/*
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 8515921dfdbf..569f2d67c9b8 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -53,8 +53,10 @@ bool filter_reg(__u64 reg)
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVVPTC:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZAAMO:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZABHA:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZACAS:
+ case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZALRSC:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZAWRS:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA:
case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB:
@@ -434,8 +436,10 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
KVM_ISA_EXT_ARR(SVNAPOT),
KVM_ISA_EXT_ARR(SVPBMT),
KVM_ISA_EXT_ARR(SVVPTC),
+ KVM_ISA_EXT_ARR(ZAAMO),
KVM_ISA_EXT_ARR(ZABHA),
KVM_ISA_EXT_ARR(ZACAS),
+ KVM_ISA_EXT_ARR(ZALRSC),
KVM_ISA_EXT_ARR(ZAWRS),
KVM_ISA_EXT_ARR(ZBA),
KVM_ISA_EXT_ARR(ZBB),
@@ -974,8 +978,10 @@ KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL);
KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT);
KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT);
KVM_ISA_EXT_SIMPLE_CONFIG(svvptc, SVVPTC);
+KVM_ISA_EXT_SIMPLE_CONFIG(zaamo, ZAAMO);
KVM_ISA_EXT_SIMPLE_CONFIG(zabha, ZABHA);
KVM_ISA_EXT_SIMPLE_CONFIG(zacas, ZACAS);
+KVM_ISA_EXT_SIMPLE_CONFIG(zalrsc, ZALRSC);
KVM_ISA_EXT_SIMPLE_CONFIG(zawrs, ZAWRS);
KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA);
KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB);
@@ -1045,8 +1051,10 @@ struct vcpu_reg_list *vcpu_configs[] = {
&config_svnapot,
&config_svpbmt,
&config_svvptc,
+ &config_zaamo,
&config_zabha,
&config_zacas,
+ &config_zalrsc,
&config_zawrs,
&config_zba,
&config_zbb,
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
index e5898678bfab..1375fca80bcd 100644
--- a/tools/testing/selftests/kvm/rseq_test.c
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -196,25 +196,27 @@ static void calc_min_max_cpu(void)
static void help(const char *name)
{
puts("");
- printf("usage: %s [-h] [-u]\n", name);
+ printf("usage: %s [-h] [-u] [-l latency]\n", name);
printf(" -u: Don't sanity check the number of successful KVM_RUNs\n");
+ printf(" -l: Set /dev/cpu_dma_latency to suppress deep sleep states\n");
puts("");
exit(0);
}
int main(int argc, char *argv[])
{
+ int r, i, snapshot, opt, fd = -1, latency = -1;
bool skip_sanity_check = false;
- int r, i, snapshot;
struct kvm_vm *vm;
struct kvm_vcpu *vcpu;
u32 cpu, rseq_cpu;
- int opt;
- while ((opt = getopt(argc, argv, "hu")) != -1) {
+ while ((opt = getopt(argc, argv, "hl:u")) != -1) {
switch (opt) {
case 'u':
skip_sanity_check = true;
+ case 'l':
+ latency = atoi_paranoid(optarg);
break;
case 'h':
default:
@@ -243,6 +245,20 @@ int main(int argc, char *argv[])
pthread_create(&migration_thread, NULL, migration_worker,
(void *)(unsigned long)syscall(SYS_gettid));
+ if (latency >= 0) {
+ /*
+ * Writes to cpu_dma_latency persist only while the file is
+ * open, i.e. it allows userspace to provide guaranteed latency
+ * while running a workload. Keep the file open until the test
+ * completes, otherwise writing cpu_dma_latency is meaningless.
+ */
+ fd = open("/dev/cpu_dma_latency", O_RDWR);
+ TEST_ASSERT(fd >= 0, __KVM_SYSCALL_ERROR("open() /dev/cpu_dma_latency", fd));
+
+ r = write(fd, &latency, 4);
+ TEST_ASSERT(r >= 1, "Error setting /dev/cpu_dma_latency");
+ }
+
for (i = 0; !done; i++) {
vcpu_run(vcpu);
TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
@@ -278,6 +294,9 @@ int main(int argc, char *argv[])
"rseq CPU = %d, sched CPU = %d", rseq_cpu, cpu);
}
+ if (fd > 0)
+ close(fd);
+
/*
* Sanity check that the test was able to enter the guest a reasonable
* number of times, e.g. didn't get stalled too often/long waiting for
@@ -293,8 +312,8 @@ int main(int argc, char *argv[])
TEST_ASSERT(skip_sanity_check || i > (NR_TASK_MIGRATIONS / 2),
"Only performed %d KVM_RUNs, task stalled too much?\n\n"
" Try disabling deep sleep states to reduce CPU wakeup latency,\n"
- " e.g. via cpuidle.off=1 or setting /dev/cpu_dma_latency to '0',\n"
- " or run with -u to disable this sanity check.", i);
+ " e.g. via cpuidle.off=1 or via -l <latency>, or run with -u to\n"
+ " disable this sanity check.", i);
pthread_join(migration_thread, NULL);
diff --git a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
index 2b550eff35f1..390ae2d87493 100644
--- a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
+++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
@@ -7,6 +7,7 @@
#include "kvm_util.h"
#include "processor.h"
+#include "kselftest.h"
#define CPUID_MWAIT (1u << 3)
@@ -14,6 +15,8 @@ enum monitor_mwait_testcases {
MWAIT_QUIRK_DISABLED = BIT(0),
MISC_ENABLES_QUIRK_DISABLED = BIT(1),
MWAIT_DISABLED = BIT(2),
+ CPUID_DISABLED = BIT(3),
+ TEST_MAX = CPUID_DISABLED * 2 - 1,
};
/*
@@ -35,11 +38,19 @@ do { \
testcase, vector); \
} while (0)
-static void guest_monitor_wait(int testcase)
+static void guest_monitor_wait(void *arg)
{
+ int testcase = (int) (long) arg;
u8 vector;
- GUEST_SYNC(testcase);
+ u64 val = rdmsr(MSR_IA32_MISC_ENABLE) & ~MSR_IA32_MISC_ENABLE_MWAIT;
+ if (!(testcase & MWAIT_DISABLED))
+ val |= MSR_IA32_MISC_ENABLE_MWAIT;
+ wrmsr(MSR_IA32_MISC_ENABLE, val);
+
+ __GUEST_ASSERT(this_cpu_has(X86_FEATURE_MWAIT) == !(testcase & MWAIT_DISABLED),
+ "Expected CPUID.MWAIT %s\n",
+ (testcase & MWAIT_DISABLED) ? "cleared" : "set");
/*
* Arbitrarily MONITOR this function, SVM performs fault checks before
@@ -50,19 +61,6 @@ static void guest_monitor_wait(int testcase)
vector = kvm_asm_safe("mwait", "a"(guest_monitor_wait), "c"(0), "d"(0));
GUEST_ASSERT_MONITOR_MWAIT("MWAIT", testcase, vector);
-}
-
-static void guest_code(void)
-{
- guest_monitor_wait(MWAIT_DISABLED);
-
- guest_monitor_wait(MWAIT_QUIRK_DISABLED | MWAIT_DISABLED);
-
- guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_DISABLED);
- guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED);
-
- guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_QUIRK_DISABLED | MWAIT_DISABLED);
- guest_monitor_wait(MISC_ENABLES_QUIRK_DISABLED | MWAIT_QUIRK_DISABLED);
GUEST_DONE();
}
@@ -74,56 +72,64 @@ int main(int argc, char *argv[])
struct kvm_vm *vm;
struct ucall uc;
int testcase;
+ char test[80];
- TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT));
TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2));
- vm = vm_create_with_one_vcpu(&vcpu, guest_code);
- vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_MWAIT);
+ ksft_print_header();
+ ksft_set_plan(12);
+ for (testcase = 0; testcase <= TEST_MAX; testcase++) {
+ vm = vm_create_with_one_vcpu(&vcpu, guest_monitor_wait);
+ vcpu_args_set(vcpu, 1, (void *)(long)testcase);
+
+ disabled_quirks = 0;
+ if (testcase & MWAIT_QUIRK_DISABLED) {
+ disabled_quirks |= KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS;
+ strcpy(test, "MWAIT can fault");
+ } else {
+ strcpy(test, "MWAIT never faults");
+ }
+ if (testcase & MISC_ENABLES_QUIRK_DISABLED) {
+ disabled_quirks |= KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT;
+ strcat(test, ", MISC_ENABLE updates CPUID");
+ } else {
+ strcat(test, ", no CPUID updates");
+ }
+
+ vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, disabled_quirks);
+
+ if (!(testcase & MISC_ENABLES_QUIRK_DISABLED) &&
+ (!!(testcase & CPUID_DISABLED) ^ !!(testcase & MWAIT_DISABLED)))
+ continue;
+
+ if (testcase & CPUID_DISABLED) {
+ strcat(test, ", CPUID clear");
+ vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_MWAIT);
+ } else {
+ strcat(test, ", CPUID set");
+ vcpu_set_cpuid_feature(vcpu, X86_FEATURE_MWAIT);
+ }
+
+ if (testcase & MWAIT_DISABLED)
+ strcat(test, ", MWAIT disabled");
- while (1) {
vcpu_run(vcpu);
TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
switch (get_ucall(vcpu, &uc)) {
- case UCALL_SYNC:
- testcase = uc.args[1];
- break;
case UCALL_ABORT:
- REPORT_GUEST_ASSERT(uc);
- goto done;
+ /* Detected in vcpu_run */
+ break;
case UCALL_DONE:
- goto done;
+ ksft_test_result_pass("%s\n", test);
+ break;
default:
TEST_FAIL("Unknown ucall %lu", uc.cmd);
- goto done;
- }
-
- disabled_quirks = 0;
- if (testcase & MWAIT_QUIRK_DISABLED)
- disabled_quirks |= KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS;
- if (testcase & MISC_ENABLES_QUIRK_DISABLED)
- disabled_quirks |= KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT;
- vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, disabled_quirks);
-
- /*
- * If the MISC_ENABLES quirk (KVM neglects to update CPUID to
- * enable/disable MWAIT) is disabled, toggle the ENABLE_MWAIT
- * bit in MISC_ENABLES accordingly. If the quirk is enabled,
- * the only valid configuration is MWAIT disabled, as CPUID
- * can't be manually changed after running the vCPU.
- */
- if (!(testcase & MISC_ENABLES_QUIRK_DISABLED)) {
- TEST_ASSERT(testcase & MWAIT_DISABLED,
- "Can't toggle CPUID features after running vCPU");
- continue;
+ break;
}
-
- vcpu_set_msr(vcpu, MSR_IA32_MISC_ENABLE,
- (testcase & MWAIT_DISABLED) ? 0 : MSR_IA32_MISC_ENABLE_MWAIT);
+ kvm_vm_free(vm);
}
+ ksft_finished();
-done:
- kvm_vm_free(vm);
return 0;
}
diff --git a/tools/testing/selftests/landlock/.gitignore b/tools/testing/selftests/landlock/.gitignore
index 335b2b1a3463..a820329cae0d 100644
--- a/tools/testing/selftests/landlock/.gitignore
+++ b/tools/testing/selftests/landlock/.gitignore
@@ -2,3 +2,4 @@
/sandbox-and-launch
/true
/wait-pipe
+/wait-pipe-sandbox
diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile
index 5cb0828f0514..a3f449914bf9 100644
--- a/tools/testing/selftests/landlock/Makefile
+++ b/tools/testing/selftests/landlock/Makefile
@@ -10,7 +10,11 @@ src_test := $(wildcard *_test.c)
TEST_GEN_PROGS := $(src_test:.c=)
-TEST_GEN_PROGS_EXTENDED := true sandbox-and-launch wait-pipe
+TEST_GEN_PROGS_EXTENDED := \
+ true \
+ sandbox-and-launch \
+ wait-pipe \
+ wait-pipe-sandbox
# Short targets:
$(TEST_GEN_PROGS): LDLIBS += -lcap -lpthread
diff --git a/tools/testing/selftests/landlock/audit.h b/tools/testing/selftests/landlock/audit.h
new file mode 100644
index 000000000000..18a6014920b5
--- /dev/null
+++ b/tools/testing/selftests/landlock/audit.h
@@ -0,0 +1,479 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Landlock audit helpers
+ *
+ * Copyright © 2024-2025 Microsoft Corporation
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <linux/audit.h>
+#include <linux/limits.h>
+#include <linux/netlink.h>
+#include <regex.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <unistd.h>
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+#endif
+
+#ifndef __maybe_unused
+#define __maybe_unused __attribute__((__unused__))
+#endif
+
+#define REGEX_LANDLOCK_PREFIX "^audit([0-9.:]\\+): domain=\\([0-9a-f]\\+\\)"
+
+struct audit_filter {
+ __u32 record_type;
+ size_t exe_len;
+ char exe[PATH_MAX];
+};
+
+struct audit_message {
+ struct nlmsghdr header;
+ union {
+ struct audit_status status;
+ struct audit_features features;
+ struct audit_rule_data rule;
+ struct nlmsgerr err;
+ char data[PATH_MAX + 200];
+ };
+};
+
+static const struct timeval audit_tv_dom_drop = {
+ /*
+ * Because domain deallocation is tied to asynchronous credential
+ * freeing, receiving such event may take some time. In practice,
+ * on a small VM, it should not exceed 100k usec, but let's wait up
+ * to 1 second to be safe.
+ */
+ .tv_sec = 1,
+};
+
+static const struct timeval audit_tv_default = {
+ .tv_usec = 1,
+};
+
+static int audit_send(const int fd, const struct audit_message *const msg)
+{
+ struct sockaddr_nl addr = {
+ .nl_family = AF_NETLINK,
+ };
+ int ret;
+
+ do {
+ ret = sendto(fd, msg, msg->header.nlmsg_len, 0,
+ (struct sockaddr *)&addr, sizeof(addr));
+ } while (ret < 0 && errno == EINTR);
+
+ if (ret < 0)
+ return -errno;
+
+ if (ret != msg->header.nlmsg_len)
+ return -E2BIG;
+
+ return 0;
+}
+
+static int audit_recv(const int fd, struct audit_message *msg)
+{
+ struct sockaddr_nl addr;
+ socklen_t addrlen = sizeof(addr);
+ struct audit_message msg_tmp;
+ int err;
+
+ if (!msg)
+ msg = &msg_tmp;
+
+ do {
+ err = recvfrom(fd, msg, sizeof(*msg), 0,
+ (struct sockaddr *)&addr, &addrlen);
+ } while (err < 0 && errno == EINTR);
+
+ if (err < 0)
+ return -errno;
+
+ if (addrlen != sizeof(addr) || addr.nl_pid != 0)
+ return -EINVAL;
+
+ /* Checks Netlink error or end of messages. */
+ if (msg->header.nlmsg_type == NLMSG_ERROR)
+ return msg->err.error;
+
+ return 0;
+}
+
+static int audit_request(const int fd,
+ const struct audit_message *const request,
+ struct audit_message *reply)
+{
+ struct audit_message msg_tmp;
+ bool first_reply = true;
+ int err;
+
+ err = audit_send(fd, request);
+ if (err)
+ return err;
+
+ if (!reply)
+ reply = &msg_tmp;
+
+ do {
+ if (first_reply)
+ first_reply = false;
+ else
+ reply = &msg_tmp;
+
+ err = audit_recv(fd, reply);
+ if (err)
+ return err;
+ } while (reply->header.nlmsg_type != NLMSG_ERROR &&
+ reply->err.msg.nlmsg_type != request->header.nlmsg_type);
+
+ return reply->err.error;
+}
+
+static int audit_filter_exe(const int audit_fd,
+ const struct audit_filter *const filter,
+ const __u16 type)
+{
+ struct audit_message msg = {
+ .header = {
+ .nlmsg_len = NLMSG_SPACE(sizeof(msg.rule)) +
+ NLMSG_ALIGN(filter->exe_len),
+ .nlmsg_type = type,
+ .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK,
+ },
+ .rule = {
+ .flags = AUDIT_FILTER_EXCLUDE,
+ .action = AUDIT_NEVER,
+ .field_count = 1,
+ .fields[0] = filter->record_type,
+ .fieldflags[0] = AUDIT_NOT_EQUAL,
+ .values[0] = filter->exe_len,
+ .buflen = filter->exe_len,
+ }
+ };
+
+ if (filter->record_type != AUDIT_EXE)
+ return -EINVAL;
+
+ memcpy(msg.rule.buf, filter->exe, filter->exe_len);
+ return audit_request(audit_fd, &msg, NULL);
+}
+
+static int audit_filter_drop(const int audit_fd, const __u16 type)
+{
+ struct audit_message msg = {
+ .header = {
+ .nlmsg_len = NLMSG_SPACE(sizeof(msg.rule)),
+ .nlmsg_type = type,
+ .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK,
+ },
+ .rule = {
+ .flags = AUDIT_FILTER_EXCLUDE,
+ .action = AUDIT_NEVER,
+ .field_count = 1,
+ .fields[0] = AUDIT_MSGTYPE,
+ .fieldflags[0] = AUDIT_NOT_EQUAL,
+ .values[0] = AUDIT_LANDLOCK_DOMAIN,
+ }
+ };
+
+ return audit_request(audit_fd, &msg, NULL);
+}
+
+static int audit_set_status(int fd, __u32 key, __u32 val)
+{
+ const struct audit_message msg = {
+ .header = {
+ .nlmsg_len = NLMSG_SPACE(sizeof(msg.status)),
+ .nlmsg_type = AUDIT_SET,
+ .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK,
+ },
+ .status = {
+ .mask = key,
+ .enabled = key == AUDIT_STATUS_ENABLED ? val : 0,
+ .pid = key == AUDIT_STATUS_PID ? val : 0,
+ }
+ };
+
+ return audit_request(fd, &msg, NULL);
+}
+
+/* Returns a pointer to the last filled character of @dst, which is `\0`. */
+static __maybe_unused char *regex_escape(const char *const src, char *dst,
+ size_t dst_size)
+{
+ char *d = dst;
+
+ for (const char *s = src; *s; s++) {
+ switch (*s) {
+ case '$':
+ case '*':
+ case '.':
+ case '[':
+ case '\\':
+ case ']':
+ case '^':
+ if (d >= dst + dst_size - 2)
+ return (char *)-ENOMEM;
+
+ *d++ = '\\';
+ *d++ = *s;
+ break;
+ default:
+ if (d >= dst + dst_size - 1)
+ return (char *)-ENOMEM;
+
+ *d++ = *s;
+ }
+ }
+ if (d >= dst + dst_size - 1)
+ return (char *)-ENOMEM;
+
+ *d = '\0';
+ return d;
+}
+
+/*
+ * @domain_id: The domain ID extracted from the audit message (if the first part
+ * of @pattern is REGEX_LANDLOCK_PREFIX). It is set to 0 if the domain ID is
+ * not found.
+ */
+static int audit_match_record(int audit_fd, const __u16 type,
+ const char *const pattern, __u64 *domain_id)
+{
+ struct audit_message msg;
+ int ret, err = 0;
+ bool matches_record = !type;
+ regmatch_t matches[2];
+ regex_t regex;
+
+ ret = regcomp(&regex, pattern, 0);
+ if (ret)
+ return -EINVAL;
+
+ do {
+ memset(&msg, 0, sizeof(msg));
+ err = audit_recv(audit_fd, &msg);
+ if (err)
+ goto out;
+
+ if (msg.header.nlmsg_type == type)
+ matches_record = true;
+ } while (!matches_record);
+
+ ret = regexec(&regex, msg.data, ARRAY_SIZE(matches), matches, 0);
+ if (ret) {
+ printf("DATA: %s\n", msg.data);
+ printf("ERROR: no match for pattern: %s\n", pattern);
+ err = -ENOENT;
+ }
+
+ if (domain_id) {
+ *domain_id = 0;
+ if (matches[1].rm_so != -1) {
+ int match_len = matches[1].rm_eo - matches[1].rm_so;
+ /* The maximal characters of a 2^64 hexadecimal number is 17. */
+ char dom_id[18];
+
+ if (match_len > 0 && match_len < sizeof(dom_id)) {
+ memcpy(dom_id, msg.data + matches[1].rm_so,
+ match_len);
+ dom_id[match_len] = '\0';
+ if (domain_id)
+ *domain_id = strtoull(dom_id, NULL, 16);
+ }
+ }
+ }
+
+out:
+ regfree(&regex);
+ return err;
+}
+
+static int __maybe_unused matches_log_domain_allocated(int audit_fd, pid_t pid,
+ __u64 *domain_id)
+{
+ static const char log_template[] = REGEX_LANDLOCK_PREFIX
+ " status=allocated mode=enforcing pid=%d uid=[0-9]\\+"
+ " exe=\"[^\"]\\+\" comm=\".*_test\"$";
+ char log_match[sizeof(log_template) + 10];
+ int log_match_len;
+
+ log_match_len =
+ snprintf(log_match, sizeof(log_match), log_template, pid);
+ if (log_match_len > sizeof(log_match))
+ return -E2BIG;
+
+ return audit_match_record(audit_fd, AUDIT_LANDLOCK_DOMAIN, log_match,
+ domain_id);
+}
+
+static int __maybe_unused matches_log_domain_deallocated(
+ int audit_fd, unsigned int num_denials, __u64 *domain_id)
+{
+ static const char log_template[] = REGEX_LANDLOCK_PREFIX
+ " status=deallocated denials=%u$";
+ char log_match[sizeof(log_template) + 10];
+ int log_match_len;
+
+ log_match_len = snprintf(log_match, sizeof(log_match), log_template,
+ num_denials);
+ if (log_match_len > sizeof(log_match))
+ return -E2BIG;
+
+ return audit_match_record(audit_fd, AUDIT_LANDLOCK_DOMAIN, log_match,
+ domain_id);
+}
+
+struct audit_records {
+ size_t access;
+ size_t domain;
+};
+
+static int audit_count_records(int audit_fd, struct audit_records *records)
+{
+ struct audit_message msg;
+ int err;
+
+ records->access = 0;
+ records->domain = 0;
+
+ do {
+ memset(&msg, 0, sizeof(msg));
+ err = audit_recv(audit_fd, &msg);
+ if (err) {
+ if (err == -EAGAIN)
+ return 0;
+ else
+ return err;
+ }
+
+ switch (msg.header.nlmsg_type) {
+ case AUDIT_LANDLOCK_ACCESS:
+ records->access++;
+ break;
+ case AUDIT_LANDLOCK_DOMAIN:
+ records->domain++;
+ break;
+ }
+ } while (true);
+
+ return 0;
+}
+
+static int audit_init(void)
+{
+ int fd, err;
+
+ fd = socket(PF_NETLINK, SOCK_RAW, NETLINK_AUDIT);
+ if (fd < 0)
+ return -errno;
+
+ err = audit_set_status(fd, AUDIT_STATUS_ENABLED, 1);
+ if (err)
+ return err;
+
+ err = audit_set_status(fd, AUDIT_STATUS_PID, getpid());
+ if (err)
+ return err;
+
+ /* Sets a timeout for negative tests. */
+ err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &audit_tv_default,
+ sizeof(audit_tv_default));
+ if (err)
+ return -errno;
+
+ return fd;
+}
+
+static int audit_init_filter_exe(struct audit_filter *filter, const char *path)
+{
+ char *absolute_path = NULL;
+
+ /* It is assume that there is not already filtering rules. */
+ filter->record_type = AUDIT_EXE;
+ if (!path) {
+ filter->exe_len = readlink("/proc/self/exe", filter->exe,
+ sizeof(filter->exe) - 1);
+ if (filter->exe_len < 0)
+ return -errno;
+
+ return 0;
+ }
+
+ absolute_path = realpath(path, NULL);
+ if (!absolute_path)
+ return -errno;
+
+ /* No need for the terminating NULL byte. */
+ filter->exe_len = strlen(absolute_path);
+ if (filter->exe_len > sizeof(filter->exe))
+ return -E2BIG;
+
+ memcpy(filter->exe, absolute_path, filter->exe_len);
+ free(absolute_path);
+ return 0;
+}
+
+static int audit_cleanup(int audit_fd, struct audit_filter *filter)
+{
+ struct audit_filter new_filter;
+
+ if (audit_fd < 0 || !filter) {
+ int err;
+
+ /*
+ * Simulates audit_init_with_exe_filter() when called from
+ * FIXTURE_TEARDOWN_PARENT().
+ */
+ audit_fd = audit_init();
+ if (audit_fd < 0)
+ return audit_fd;
+
+ filter = &new_filter;
+ err = audit_init_filter_exe(filter, NULL);
+ if (err)
+ return err;
+ }
+
+ /* Filters might not be in place. */
+ audit_filter_exe(audit_fd, filter, AUDIT_DEL_RULE);
+ audit_filter_drop(audit_fd, AUDIT_DEL_RULE);
+
+ /*
+ * Because audit_cleanup() might not be called by the test auditd
+ * process, it might not be possible to explicitly set it. Anyway,
+ * AUDIT_STATUS_ENABLED will implicitly be set to 0 when the auditd
+ * process will exit.
+ */
+ return close(audit_fd);
+}
+
+static int audit_init_with_exe_filter(struct audit_filter *filter)
+{
+ int fd, err;
+
+ fd = audit_init();
+ if (fd < 0)
+ return fd;
+
+ err = audit_init_filter_exe(filter, NULL);
+ if (err)
+ return err;
+
+ err = audit_filter_exe(fd, filter, AUDIT_ADD_RULE);
+ if (err)
+ return err;
+
+ return fd;
+}
diff --git a/tools/testing/selftests/landlock/audit_test.c b/tools/testing/selftests/landlock/audit_test.c
new file mode 100644
index 000000000000..cfc571afd0eb
--- /dev/null
+++ b/tools/testing/selftests/landlock/audit_test.c
@@ -0,0 +1,671 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Landlock tests - Audit
+ *
+ * Copyright © 2024-2025 Microsoft Corporation
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <limits.h>
+#include <linux/landlock.h>
+#include <pthread.h>
+#include <stdlib.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "audit.h"
+#include "common.h"
+
+static int matches_log_signal(struct __test_metadata *const _metadata,
+ int audit_fd, const pid_t opid, __u64 *domain_id)
+{
+ static const char log_template[] = REGEX_LANDLOCK_PREFIX
+ " blockers=scope\\.signal opid=%d ocomm=\"audit_test\"$";
+ char log_match[sizeof(log_template) + 10];
+ int log_match_len;
+
+ log_match_len =
+ snprintf(log_match, sizeof(log_match), log_template, opid);
+ if (log_match_len > sizeof(log_match))
+ return -E2BIG;
+
+ return audit_match_record(audit_fd, AUDIT_LANDLOCK_ACCESS, log_match,
+ domain_id);
+}
+
+FIXTURE(audit)
+{
+ struct audit_filter audit_filter;
+ int audit_fd;
+};
+
+FIXTURE_SETUP(audit)
+{
+ disable_caps(_metadata);
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ self->audit_fd = audit_init_with_exe_filter(&self->audit_filter);
+ EXPECT_LE(0, self->audit_fd)
+ {
+ const char *error_msg;
+
+ /* kill "$(auditctl -s | sed -ne 's/^pid \([0-9]\+\)$/\1/p')" */
+ if (self->audit_fd == -EEXIST)
+ error_msg = "socket already in use (e.g. auditd)";
+ else
+ error_msg = strerror(-self->audit_fd);
+ TH_LOG("Failed to initialize audit: %s", error_msg);
+ }
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+}
+
+FIXTURE_TEARDOWN(audit)
+{
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, audit_cleanup(self->audit_fd, &self->audit_filter));
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+}
+
+TEST_F(audit, layers)
+{
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .scoped = LANDLOCK_SCOPE_SIGNAL,
+ };
+ int status, ruleset_fd, i;
+ __u64(*domain_stack)[16];
+ __u64 prev_dom = 3;
+ pid_t child;
+
+ domain_stack = mmap(NULL, sizeof(*domain_stack), PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(MAP_FAILED, domain_stack);
+ memset(domain_stack, 0, sizeof(*domain_stack));
+
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd);
+ EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+
+ child = fork();
+ ASSERT_LE(0, child);
+ if (child == 0) {
+ for (i = 0; i < ARRAY_SIZE(*domain_stack); i++) {
+ __u64 denial_dom = 1;
+ __u64 allocated_dom = 2;
+
+ EXPECT_EQ(0, landlock_restrict_self(ruleset_fd, 0));
+
+ /* Creates a denial to get the domain ID. */
+ EXPECT_EQ(-1, kill(getppid(), 0));
+ EXPECT_EQ(EPERM, errno);
+ EXPECT_EQ(0,
+ matches_log_signal(_metadata, self->audit_fd,
+ getppid(), &denial_dom));
+ EXPECT_EQ(0, matches_log_domain_allocated(
+ self->audit_fd, getpid(),
+ &allocated_dom));
+ EXPECT_NE(denial_dom, 1);
+ EXPECT_NE(denial_dom, 0);
+ EXPECT_EQ(denial_dom, allocated_dom);
+
+ /* Checks that the new domain is younger than the previous one. */
+ EXPECT_GT(allocated_dom, prev_dom);
+ prev_dom = allocated_dom;
+ (*domain_stack)[i] = allocated_dom;
+ }
+
+ /* Checks that we reached the maximum number of layers. */
+ EXPECT_EQ(-1, landlock_restrict_self(ruleset_fd, 0));
+ EXPECT_EQ(E2BIG, errno);
+
+ /* Updates filter rules to match the drop record. */
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, audit_filter_drop(self->audit_fd, AUDIT_ADD_RULE));
+ EXPECT_EQ(0,
+ audit_filter_exe(self->audit_fd, &self->audit_filter,
+ AUDIT_DEL_RULE));
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+
+ _exit(_metadata->exit_code);
+ return;
+ }
+
+ ASSERT_EQ(child, waitpid(child, &status, 0));
+ if (WIFSIGNALED(status) || !WIFEXITED(status) ||
+ WEXITSTATUS(status) != EXIT_SUCCESS)
+ _metadata->exit_code = KSFT_FAIL;
+
+ /* Purges log from deallocated domains. */
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
+ for (i = ARRAY_SIZE(*domain_stack) - 1; i >= 0; i--) {
+ __u64 deallocated_dom = 2;
+
+ EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
+ &deallocated_dom));
+ EXPECT_EQ((*domain_stack)[i], deallocated_dom)
+ {
+ TH_LOG("Failed to match domain %llx (#%d)",
+ (*domain_stack)[i], i);
+ }
+ }
+ EXPECT_EQ(0, munmap(domain_stack, sizeof(*domain_stack)));
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_default, sizeof(audit_tv_default)));
+ EXPECT_EQ(0, close(ruleset_fd));
+}
+
+struct thread_data {
+ pid_t parent_pid;
+ int ruleset_fd, pipe_child, pipe_parent;
+};
+
+static void *thread_audit_test(void *arg)
+{
+ const struct thread_data *data = (struct thread_data *)arg;
+ uintptr_t err = 0;
+ char buffer;
+
+ /* TGID and TID are different for a second thread. */
+ if (getpid() == gettid()) {
+ err = 1;
+ goto out;
+ }
+
+ if (landlock_restrict_self(data->ruleset_fd, 0)) {
+ err = 2;
+ goto out;
+ }
+
+ if (close(data->ruleset_fd)) {
+ err = 3;
+ goto out;
+ }
+
+ /* Creates a denial to get the domain ID. */
+ if (kill(data->parent_pid, 0) != -1) {
+ err = 4;
+ goto out;
+ }
+
+ if (EPERM != errno) {
+ err = 5;
+ goto out;
+ }
+
+ /* Signals the parent to read denial logs. */
+ if (write(data->pipe_child, ".", 1) != 1) {
+ err = 6;
+ goto out;
+ }
+
+ /* Waits for the parent to update audit filters. */
+ if (read(data->pipe_parent, &buffer, 1) != 1) {
+ err = 7;
+ goto out;
+ }
+
+out:
+ close(data->pipe_child);
+ close(data->pipe_parent);
+ return (void *)err;
+}
+
+/* Checks that the PID tied to a domain is not a TID but the TGID. */
+TEST_F(audit, thread)
+{
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .scoped = LANDLOCK_SCOPE_SIGNAL,
+ };
+ __u64 denial_dom = 1;
+ __u64 allocated_dom = 2;
+ __u64 deallocated_dom = 3;
+ pthread_t thread;
+ int pipe_child[2], pipe_parent[2];
+ char buffer;
+ struct thread_data child_data;
+
+ child_data.parent_pid = getppid();
+ ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC));
+ child_data.pipe_child = pipe_child[1];
+ ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));
+ child_data.pipe_parent = pipe_parent[0];
+ child_data.ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, child_data.ruleset_fd);
+
+ /* TGID and TID are the same for the initial thread . */
+ EXPECT_EQ(getpid(), gettid());
+ EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ ASSERT_EQ(0, pthread_create(&thread, NULL, thread_audit_test,
+ &child_data));
+
+ /* Waits for the child to generate a denial. */
+ ASSERT_EQ(1, read(pipe_child[0], &buffer, 1));
+ EXPECT_EQ(0, close(pipe_child[0]));
+
+ /* Matches the signal log to get the domain ID. */
+ EXPECT_EQ(0, matches_log_signal(_metadata, self->audit_fd,
+ child_data.parent_pid, &denial_dom));
+ EXPECT_NE(denial_dom, 1);
+ EXPECT_NE(denial_dom, 0);
+
+ EXPECT_EQ(0, matches_log_domain_allocated(self->audit_fd, getpid(),
+ &allocated_dom));
+ EXPECT_EQ(denial_dom, allocated_dom);
+
+ /* Updates filter rules to match the drop record. */
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, audit_filter_drop(self->audit_fd, AUDIT_ADD_RULE));
+ EXPECT_EQ(0, audit_filter_exe(self->audit_fd, &self->audit_filter,
+ AUDIT_DEL_RULE));
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+
+ /* Signals the thread to exit, which will generate a domain deallocation. */
+ ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+ EXPECT_EQ(0, close(pipe_parent[1]));
+ ASSERT_EQ(0, pthread_join(thread, NULL));
+
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_dom_drop, sizeof(audit_tv_dom_drop)));
+ EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 1,
+ &deallocated_dom));
+ EXPECT_EQ(denial_dom, deallocated_dom);
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_default, sizeof(audit_tv_default)));
+}
+
+FIXTURE(audit_flags)
+{
+ struct audit_filter audit_filter;
+ int audit_fd;
+ __u64 *domain_id;
+};
+
+FIXTURE_VARIANT(audit_flags)
+{
+ const int restrict_flags;
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit_flags, default) {
+ /* clang-format on */
+ .restrict_flags = 0,
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit_flags, same_exec_off) {
+ /* clang-format on */
+ .restrict_flags = LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF,
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit_flags, subdomains_off) {
+ /* clang-format on */
+ .restrict_flags = LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF,
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit_flags, cross_exec_on) {
+ /* clang-format on */
+ .restrict_flags = LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON,
+};
+
+FIXTURE_SETUP(audit_flags)
+{
+ disable_caps(_metadata);
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ self->audit_fd = audit_init_with_exe_filter(&self->audit_filter);
+ EXPECT_LE(0, self->audit_fd)
+ {
+ const char *error_msg;
+
+ /* kill "$(auditctl -s | sed -ne 's/^pid \([0-9]\+\)$/\1/p')" */
+ if (self->audit_fd == -EEXIST)
+ error_msg = "socket already in use (e.g. auditd)";
+ else
+ error_msg = strerror(-self->audit_fd);
+ TH_LOG("Failed to initialize audit: %s", error_msg);
+ }
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+
+ self->domain_id = mmap(NULL, sizeof(*self->domain_id),
+ PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+ ASSERT_NE(MAP_FAILED, self->domain_id);
+ /* Domain IDs are greater or equal to 2^32. */
+ *self->domain_id = 1;
+}
+
+FIXTURE_TEARDOWN(audit_flags)
+{
+ EXPECT_EQ(0, munmap(self->domain_id, sizeof(*self->domain_id)));
+
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, audit_cleanup(self->audit_fd, &self->audit_filter));
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+}
+
+TEST_F(audit_flags, signal)
+{
+ int status;
+ pid_t child;
+ struct audit_records records;
+ __u64 deallocated_dom = 2;
+
+ child = fork();
+ ASSERT_LE(0, child);
+ if (child == 0) {
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .scoped = LANDLOCK_SCOPE_SIGNAL,
+ };
+ int ruleset_fd;
+
+ /* Add filesystem restrictions. */
+ ruleset_fd = landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd);
+ EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ ASSERT_EQ(0, landlock_restrict_self(ruleset_fd,
+ variant->restrict_flags));
+ EXPECT_EQ(0, close(ruleset_fd));
+
+ /* First signal checks to test log entries. */
+ EXPECT_EQ(-1, kill(getppid(), 0));
+ EXPECT_EQ(EPERM, errno);
+
+ if (variant->restrict_flags &
+ LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF) {
+ EXPECT_EQ(-EAGAIN, matches_log_signal(
+ _metadata, self->audit_fd,
+ getppid(), self->domain_id));
+ EXPECT_EQ(*self->domain_id, 1);
+ } else {
+ __u64 allocated_dom = 3;
+
+ EXPECT_EQ(0, matches_log_signal(
+ _metadata, self->audit_fd,
+ getppid(), self->domain_id));
+
+ /* Checks domain information records. */
+ EXPECT_EQ(0, matches_log_domain_allocated(
+ self->audit_fd, getpid(),
+ &allocated_dom));
+ EXPECT_NE(*self->domain_id, 1);
+ EXPECT_NE(*self->domain_id, 0);
+ EXPECT_EQ(*self->domain_id, allocated_dom);
+ }
+
+ /* Second signal checks to test audit_count_records(). */
+ EXPECT_EQ(-1, kill(getppid(), 0));
+ EXPECT_EQ(EPERM, errno);
+
+ /* Makes sure there is no superfluous logged records. */
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ if (variant->restrict_flags &
+ LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF) {
+ EXPECT_EQ(0, records.access);
+ } else {
+ EXPECT_EQ(1, records.access);
+ }
+ EXPECT_EQ(0, records.domain);
+
+ /* Updates filter rules to match the drop record. */
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, audit_filter_drop(self->audit_fd, AUDIT_ADD_RULE));
+ EXPECT_EQ(0,
+ audit_filter_exe(self->audit_fd, &self->audit_filter,
+ AUDIT_DEL_RULE));
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+
+ _exit(_metadata->exit_code);
+ return;
+ }
+
+ ASSERT_EQ(child, waitpid(child, &status, 0));
+ if (WIFSIGNALED(status) || !WIFEXITED(status) ||
+ WEXITSTATUS(status) != EXIT_SUCCESS)
+ _metadata->exit_code = KSFT_FAIL;
+
+ if (variant->restrict_flags &
+ LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF) {
+ EXPECT_EQ(-EAGAIN,
+ matches_log_domain_deallocated(self->audit_fd, 0,
+ &deallocated_dom));
+ EXPECT_EQ(deallocated_dom, 2);
+ } else {
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_dom_drop,
+ sizeof(audit_tv_dom_drop)));
+ EXPECT_EQ(0, matches_log_domain_deallocated(self->audit_fd, 2,
+ &deallocated_dom));
+ EXPECT_NE(deallocated_dom, 2);
+ EXPECT_NE(deallocated_dom, 0);
+ EXPECT_EQ(deallocated_dom, *self->domain_id);
+ EXPECT_EQ(0, setsockopt(self->audit_fd, SOL_SOCKET, SO_RCVTIMEO,
+ &audit_tv_default,
+ sizeof(audit_tv_default)));
+ }
+}
+
+static int matches_log_fs_read_root(int audit_fd)
+{
+ return audit_match_record(
+ audit_fd, AUDIT_LANDLOCK_ACCESS,
+ REGEX_LANDLOCK_PREFIX
+ " blockers=fs\\.read_dir path=\"/\" dev=\"[^\"]\\+\" ino=[0-9]\\+$",
+ NULL);
+}
+
+FIXTURE(audit_exec)
+{
+ struct audit_filter audit_filter;
+ int audit_fd;
+};
+
+FIXTURE_VARIANT(audit_exec)
+{
+ const int restrict_flags;
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit_exec, default) {
+ /* clang-format on */
+ .restrict_flags = 0,
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit_exec, same_exec_off) {
+ /* clang-format on */
+ .restrict_flags = LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF,
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit_exec, subdomains_off) {
+ /* clang-format on */
+ .restrict_flags = LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF,
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit_exec, cross_exec_on) {
+ /* clang-format on */
+ .restrict_flags = LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON,
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit_exec, subdomains_off_and_cross_exec_on) {
+ /* clang-format on */
+ .restrict_flags = LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF |
+ LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON,
+};
+
+FIXTURE_SETUP(audit_exec)
+{
+ disable_caps(_metadata);
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+
+ self->audit_fd = audit_init();
+ EXPECT_LE(0, self->audit_fd)
+ {
+ const char *error_msg;
+
+ /* kill "$(auditctl -s | sed -ne 's/^pid \([0-9]\+\)$/\1/p')" */
+ if (self->audit_fd == -EEXIST)
+ error_msg = "socket already in use (e.g. auditd)";
+ else
+ error_msg = strerror(-self->audit_fd);
+ TH_LOG("Failed to initialize audit: %s", error_msg);
+ }
+
+ /* Applies test filter for the bin_wait_pipe_sandbox program. */
+ EXPECT_EQ(0, audit_init_filter_exe(&self->audit_filter,
+ bin_wait_pipe_sandbox));
+ EXPECT_EQ(0, audit_filter_exe(self->audit_fd, &self->audit_filter,
+ AUDIT_ADD_RULE));
+
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+}
+
+FIXTURE_TEARDOWN(audit_exec)
+{
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, audit_filter_exe(self->audit_fd, &self->audit_filter,
+ AUDIT_DEL_RULE));
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, close(self->audit_fd));
+}
+
+TEST_F(audit_exec, signal_and_open)
+{
+ struct audit_records records;
+ int pipe_child[2], pipe_parent[2];
+ char buf_parent;
+ pid_t child;
+ int status;
+
+ ASSERT_EQ(0, pipe2(pipe_child, 0));
+ ASSERT_EQ(0, pipe2(pipe_parent, 0));
+
+ child = fork();
+ ASSERT_LE(0, child);
+ if (child == 0) {
+ const struct landlock_ruleset_attr layer1 = {
+ .scoped = LANDLOCK_SCOPE_SIGNAL,
+ };
+ char pipe_child_str[12], pipe_parent_str[12];
+ char *const argv[] = { (char *)bin_wait_pipe_sandbox,
+ pipe_child_str, pipe_parent_str, NULL };
+ int ruleset_fd;
+
+ /* Passes the pipe FDs to the executed binary. */
+ EXPECT_EQ(0, close(pipe_child[0]));
+ EXPECT_EQ(0, close(pipe_parent[1]));
+ snprintf(pipe_child_str, sizeof(pipe_child_str), "%d",
+ pipe_child[1]);
+ snprintf(pipe_parent_str, sizeof(pipe_parent_str), "%d",
+ pipe_parent[0]);
+
+ ruleset_fd =
+ landlock_create_ruleset(&layer1, sizeof(layer1), 0);
+ if (ruleset_fd < 0) {
+ perror("Failed to create a ruleset");
+ _exit(1);
+ }
+ prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ if (landlock_restrict_self(ruleset_fd,
+ variant->restrict_flags)) {
+ perror("Failed to restrict self");
+ _exit(1);
+ }
+ close(ruleset_fd);
+
+ ASSERT_EQ(0, execve(argv[0], argv, NULL))
+ {
+ TH_LOG("Failed to execute \"%s\": %s", argv[0],
+ strerror(errno));
+ };
+ _exit(1);
+ return;
+ }
+
+ EXPECT_EQ(0, close(pipe_child[1]));
+ EXPECT_EQ(0, close(pipe_parent[0]));
+
+ /* Waits for the child. */
+ EXPECT_EQ(1, read(pipe_child[0], &buf_parent, 1));
+
+ /* Tests that there was no denial until now. */
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+
+ /*
+ * Wait for the child to do a first denied action by layer1 and
+ * sandbox itself with layer2.
+ */
+ EXPECT_EQ(1, write(pipe_parent[1], ".", 1));
+ EXPECT_EQ(1, read(pipe_child[0], &buf_parent, 1));
+
+ /* Tests that the audit record only matches the child. */
+ if (variant->restrict_flags & LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON) {
+ /* Matches the current domain. */
+ EXPECT_EQ(0, matches_log_signal(_metadata, self->audit_fd,
+ getpid(), NULL));
+ }
+
+ /* Checks that we didn't miss anything. */
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+
+ /*
+ * Wait for the child to do a second denied action by layer1 and
+ * layer2, and sandbox itself with layer3.
+ */
+ EXPECT_EQ(1, write(pipe_parent[1], ".", 1));
+ EXPECT_EQ(1, read(pipe_child[0], &buf_parent, 1));
+
+ /* Tests that the audit record only matches the child. */
+ if (variant->restrict_flags & LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON) {
+ /* Matches the current domain. */
+ EXPECT_EQ(0, matches_log_signal(_metadata, self->audit_fd,
+ getpid(), NULL));
+ }
+
+ if (!(variant->restrict_flags &
+ LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF)) {
+ /* Matches the child domain. */
+ EXPECT_EQ(0, matches_log_fs_read_root(self->audit_fd));
+ }
+
+ /* Checks that we didn't miss anything. */
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+
+ /* Waits for the child to terminate. */
+ EXPECT_EQ(1, write(pipe_parent[1], ".", 1));
+ ASSERT_EQ(child, waitpid(child, &status, 0));
+ ASSERT_EQ(1, WIFEXITED(status));
+ ASSERT_EQ(0, WEXITSTATUS(status));
+
+ /* Tests that the audit record only matches the child. */
+ if (!(variant->restrict_flags &
+ LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF)) {
+ /*
+ * Matches the child domains, which tests that the
+ * llcred->domain_exec bitmask is correctly updated with a new
+ * domain.
+ */
+ EXPECT_EQ(0, matches_log_fs_read_root(self->audit_fd));
+ EXPECT_EQ(0, matches_log_signal(_metadata, self->audit_fd,
+ getpid(), NULL));
+ }
+
+ /* Checks that we didn't miss anything. */
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c
index 1bc16fde2e8a..7b69002239d7 100644
--- a/tools/testing/selftests/landlock/base_test.c
+++ b/tools/testing/selftests/landlock/base_test.c
@@ -76,7 +76,7 @@ TEST(abi_version)
const struct landlock_ruleset_attr ruleset_attr = {
.handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE,
};
- ASSERT_EQ(6, landlock_create_ruleset(NULL, 0,
+ ASSERT_EQ(7, landlock_create_ruleset(NULL, 0,
LANDLOCK_CREATE_RULESET_VERSION));
ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0,
@@ -98,10 +98,54 @@ TEST(abi_version)
ASSERT_EQ(EINVAL, errno);
}
+/*
+ * Old source trees might not have the set of Kselftest fixes related to kernel
+ * UAPI headers.
+ */
+#ifndef LANDLOCK_CREATE_RULESET_ERRATA
+#define LANDLOCK_CREATE_RULESET_ERRATA (1U << 1)
+#endif
+
+TEST(errata)
+{
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE,
+ };
+ int errata;
+
+ errata = landlock_create_ruleset(NULL, 0,
+ LANDLOCK_CREATE_RULESET_ERRATA);
+ /* The errata bitmask will not be backported to tests. */
+ ASSERT_LE(0, errata);
+ TH_LOG("errata: 0x%x", errata);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0,
+ LANDLOCK_CREATE_RULESET_ERRATA));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(NULL, sizeof(ruleset_attr),
+ LANDLOCK_CREATE_RULESET_ERRATA));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1,
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr),
+ LANDLOCK_CREATE_RULESET_ERRATA));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1, landlock_create_ruleset(
+ NULL, 0,
+ LANDLOCK_CREATE_RULESET_VERSION |
+ LANDLOCK_CREATE_RULESET_ERRATA));
+ ASSERT_EQ(-1, landlock_create_ruleset(NULL, 0,
+ LANDLOCK_CREATE_RULESET_ERRATA |
+ 1 << 31));
+ ASSERT_EQ(EINVAL, errno);
+}
+
/* Tests ordering of syscall argument checks. */
TEST(create_ruleset_checks_ordering)
{
- const int last_flag = LANDLOCK_CREATE_RULESET_VERSION;
+ const int last_flag = LANDLOCK_CREATE_RULESET_ERRATA;
const int invalid_flag = last_flag << 1;
int ruleset_fd;
const struct landlock_ruleset_attr ruleset_attr = {
@@ -233,6 +277,88 @@ TEST(restrict_self_checks_ordering)
ASSERT_EQ(0, close(ruleset_fd));
}
+TEST(restrict_self_fd)
+{
+ int fd;
+
+ fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+ ASSERT_LE(0, fd);
+
+ EXPECT_EQ(-1, landlock_restrict_self(fd, 0));
+ EXPECT_EQ(EBADFD, errno);
+}
+
+TEST(restrict_self_fd_flags)
+{
+ int fd;
+
+ fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+ ASSERT_LE(0, fd);
+
+ /*
+ * LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF accepts -1 but not any file
+ * descriptor.
+ */
+ EXPECT_EQ(-1, landlock_restrict_self(
+ fd, LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF));
+ EXPECT_EQ(EBADFD, errno);
+}
+
+TEST(restrict_self_flags)
+{
+ const __u32 last_flag = LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF;
+
+ /* Tests invalid flag combinations. */
+
+ EXPECT_EQ(-1, landlock_restrict_self(-1, last_flag << 1));
+ EXPECT_EQ(EINVAL, errno);
+
+ EXPECT_EQ(-1, landlock_restrict_self(-1, -1));
+ EXPECT_EQ(EINVAL, errno);
+
+ /* Tests valid flag combinations. */
+
+ EXPECT_EQ(-1, landlock_restrict_self(-1, 0));
+ EXPECT_EQ(EBADF, errno);
+
+ EXPECT_EQ(-1, landlock_restrict_self(
+ -1, LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF));
+ EXPECT_EQ(EBADF, errno);
+
+ EXPECT_EQ(-1,
+ landlock_restrict_self(
+ -1,
+ LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF |
+ LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF));
+ EXPECT_EQ(EBADF, errno);
+
+ EXPECT_EQ(-1,
+ landlock_restrict_self(
+ -1,
+ LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON |
+ LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF));
+ EXPECT_EQ(EBADF, errno);
+
+ EXPECT_EQ(-1, landlock_restrict_self(
+ -1, LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON));
+ EXPECT_EQ(EBADF, errno);
+
+ EXPECT_EQ(-1,
+ landlock_restrict_self(
+ -1, LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF |
+ LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON));
+ EXPECT_EQ(EBADF, errno);
+
+ /* Tests with an invalid ruleset_fd. */
+
+ EXPECT_EQ(-1, landlock_restrict_self(
+ -2, LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF));
+ EXPECT_EQ(EBADF, errno);
+
+ EXPECT_EQ(0, landlock_restrict_self(
+ -1, LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF));
+}
+
TEST(ruleset_fd_io)
{
struct landlock_ruleset_attr ruleset_attr = {
diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h
index 6064c9ac0532..88a3c78f5d98 100644
--- a/tools/testing/selftests/landlock/common.h
+++ b/tools/testing/selftests/landlock/common.h
@@ -11,6 +11,7 @@
#include <errno.h>
#include <linux/securebits.h>
#include <sys/capability.h>
+#include <sys/prctl.h>
#include <sys/socket.h>
#include <sys/un.h>
#include <sys/wait.h>
@@ -30,6 +31,7 @@
static const char bin_sandbox_and_launch[] = "./sandbox-and-launch";
static const char bin_wait_pipe[] = "./wait-pipe";
+static const char bin_wait_pipe_sandbox[] = "./wait-pipe-sandbox";
static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
{
@@ -37,10 +39,12 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
/* Only these three capabilities are useful for the tests. */
const cap_value_t caps[] = {
/* clang-format off */
+ CAP_AUDIT_CONTROL,
CAP_DAC_OVERRIDE,
CAP_MKNOD,
CAP_NET_ADMIN,
CAP_NET_BIND_SERVICE,
+ CAP_SETUID,
CAP_SYS_ADMIN,
CAP_SYS_CHROOT,
/* clang-format on */
@@ -204,6 +208,22 @@ enforce_ruleset(struct __test_metadata *const _metadata, const int ruleset_fd)
}
}
+static void __maybe_unused
+drop_access_rights(struct __test_metadata *const _metadata,
+ const struct landlock_ruleset_attr *const ruleset_attr)
+{
+ int ruleset_fd;
+
+ ruleset_fd =
+ landlock_create_ruleset(ruleset_attr, sizeof(*ruleset_attr), 0);
+ EXPECT_LE(0, ruleset_fd)
+ {
+ TH_LOG("Failed to create a ruleset: %s", strerror(errno));
+ }
+ enforce_ruleset(_metadata, ruleset_fd);
+ EXPECT_EQ(0, close(ruleset_fd));
+}
+
struct protocol_variant {
int domain;
int type;
diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config
index 425de4c20271..8fe9b461b1fd 100644
--- a/tools/testing/selftests/landlock/config
+++ b/tools/testing/selftests/landlock/config
@@ -1,4 +1,5 @@
CONFIG_AF_UNIX_OOB=y
+CONFIG_AUDIT=y
CONFIG_CGROUPS=y
CONFIG_CGROUP_SCHED=y
CONFIG_INET=y
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index aa6f2c1cbec7..73729382d40f 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -41,6 +41,7 @@
#define _ASM_GENERIC_FCNTL_H
#include <linux/fcntl.h>
+#include "audit.h"
#include "common.h"
#ifndef renameat2
@@ -5554,4 +5555,598 @@ TEST_F_FORK(layout3_fs, release_inodes)
ASSERT_EQ(EACCES, test_open(TMP_DIR, O_RDONLY));
}
+static int matches_log_fs_extra(struct __test_metadata *const _metadata,
+ int audit_fd, const char *const blockers,
+ const char *const path, const char *const extra)
+{
+ static const char log_template[] = REGEX_LANDLOCK_PREFIX
+ " blockers=fs\\.%s path=\"%s\" dev=\"[^\"]\\+\" ino=[0-9]\\+$";
+ char *absolute_path = NULL;
+ size_t log_match_remaining = sizeof(log_template) + strlen(blockers) +
+ PATH_MAX * 2 +
+ (extra ? strlen(extra) : 0) + 1;
+ char log_match[log_match_remaining];
+ char *log_match_cursor = log_match;
+ size_t chunk_len;
+
+ chunk_len = snprintf(log_match_cursor, log_match_remaining,
+ REGEX_LANDLOCK_PREFIX " blockers=%s path=\"",
+ blockers);
+ if (chunk_len < 0 || chunk_len >= log_match_remaining)
+ return -E2BIG;
+
+ /*
+ * It is assume that absolute_path does not contain control characters nor
+ * spaces, see audit_string_contains_control().
+ */
+ absolute_path = realpath(path, NULL);
+ if (!absolute_path)
+ return -errno;
+
+ log_match_remaining -= chunk_len;
+ log_match_cursor += chunk_len;
+ log_match_cursor = regex_escape(absolute_path, log_match_cursor,
+ log_match_remaining);
+ free(absolute_path);
+ if (log_match_cursor < 0)
+ return (long long)log_match_cursor;
+
+ log_match_remaining -= log_match_cursor - log_match;
+ chunk_len = snprintf(log_match_cursor, log_match_remaining,
+ "\" dev=\"[^\"]\\+\" ino=[0-9]\\+%s$",
+ extra ?: "");
+ if (chunk_len < 0 || chunk_len >= log_match_remaining)
+ return -E2BIG;
+
+ return audit_match_record(audit_fd, AUDIT_LANDLOCK_ACCESS, log_match,
+ NULL);
+}
+
+static int matches_log_fs(struct __test_metadata *const _metadata, int audit_fd,
+ const char *const blockers, const char *const path)
+{
+ return matches_log_fs_extra(_metadata, audit_fd, blockers, path, NULL);
+}
+
+FIXTURE(audit_layout1)
+{
+ struct audit_filter audit_filter;
+ int audit_fd;
+};
+
+FIXTURE_SETUP(audit_layout1)
+{
+ prepare_layout(_metadata);
+
+ create_layout1(_metadata);
+
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ self->audit_fd = audit_init_with_exe_filter(&self->audit_filter);
+ EXPECT_LE(0, self->audit_fd);
+ disable_caps(_metadata);
+}
+
+FIXTURE_TEARDOWN_PARENT(audit_layout1)
+{
+ remove_layout1(_metadata);
+
+ cleanup_layout(_metadata);
+
+ EXPECT_EQ(0, audit_cleanup(-1, NULL));
+}
+
+TEST_F(audit_layout1, execute_make)
+{
+ struct audit_records records;
+
+ copy_file(_metadata, bin_true, file1_s1d1);
+ test_execute(_metadata, 0, file1_s1d1);
+ test_check_exec(_metadata, 0, file1_s1d1);
+
+ drop_access_rights(_metadata,
+ &(struct landlock_ruleset_attr){
+ .handled_access_fs =
+ LANDLOCK_ACCESS_FS_EXECUTE,
+ });
+
+ test_execute(_metadata, EACCES, file1_s1d1);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.execute",
+ file1_s1d1));
+ test_check_exec(_metadata, EACCES, file1_s1d1);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.execute",
+ file1_s1d1));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+}
+
+/*
+ * Using a set of handled/denied access rights make it possible to check that
+ * only the blocked ones are logged.
+ */
+
+/* clang-format off */
+static const __u64 access_fs_16 =
+ LANDLOCK_ACCESS_FS_EXECUTE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE |
+ LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_READ_DIR |
+ LANDLOCK_ACCESS_FS_REMOVE_DIR |
+ LANDLOCK_ACCESS_FS_REMOVE_FILE |
+ LANDLOCK_ACCESS_FS_MAKE_CHAR |
+ LANDLOCK_ACCESS_FS_MAKE_DIR |
+ LANDLOCK_ACCESS_FS_MAKE_REG |
+ LANDLOCK_ACCESS_FS_MAKE_SOCK |
+ LANDLOCK_ACCESS_FS_MAKE_FIFO |
+ LANDLOCK_ACCESS_FS_MAKE_BLOCK |
+ LANDLOCK_ACCESS_FS_MAKE_SYM |
+ LANDLOCK_ACCESS_FS_REFER |
+ LANDLOCK_ACCESS_FS_TRUNCATE |
+ LANDLOCK_ACCESS_FS_IOCTL_DEV;
+/* clang-format on */
+
+TEST_F(audit_layout1, execute_read)
+{
+ struct audit_records records;
+
+ copy_file(_metadata, bin_true, file1_s1d1);
+ test_execute(_metadata, 0, file1_s1d1);
+ test_check_exec(_metadata, 0, file1_s1d1);
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ /*
+ * The only difference with the previous audit_layout1.execute_read test is
+ * the extra ",fs\\.read_file" blocked by the executable file.
+ */
+ test_execute(_metadata, EACCES, file1_s1d1);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.execute,fs\\.read_file", file1_s1d1));
+ test_check_exec(_metadata, EACCES, file1_s1d1);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.execute,fs\\.read_file", file1_s1d1));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+}
+
+TEST_F(audit_layout1, write_file)
+{
+ struct audit_records records;
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.write_file", file1_s1d1));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, read_file)
+{
+ struct audit_records records;
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.read_file",
+ file1_s1d1));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, read_dir)
+{
+ struct audit_records records;
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(EACCES, test_open(dir_s1d1, O_DIRECTORY));
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.read_dir",
+ dir_s1d1));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, remove_dir)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+ EXPECT_EQ(0, unlink(file2_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(-1, rmdir(dir_s1d3));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.remove_dir", dir_s1d2));
+
+ EXPECT_EQ(-1, unlinkat(AT_FDCWD, dir_s1d3, AT_REMOVEDIR));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.remove_dir", dir_s1d2));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+}
+
+TEST_F(audit_layout1, remove_file)
+{
+ struct audit_records records;
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(-1, unlink(file1_s1d3));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.remove_file", dir_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, make_char)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(-1, mknod(file1_s1d3, S_IFCHR | 0644, 0));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.make_char",
+ dir_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, make_dir)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(-1, mkdir(file1_s1d3, 0755));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.make_dir",
+ dir_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, make_reg)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(-1, mknod(file1_s1d3, S_IFREG | 0644, 0));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.make_reg",
+ dir_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, make_sock)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(-1, mknod(file1_s1d3, S_IFSOCK | 0644, 0));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.make_sock",
+ dir_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, make_fifo)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(-1, mknod(file1_s1d3, S_IFIFO | 0644, 0));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.make_fifo",
+ dir_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, make_block)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(-1, mknod(file1_s1d3, S_IFBLK | 0644, 0));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.make_block", dir_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, make_sym)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(-1, symlink("target", file1_s1d3));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.make_sym",
+ dir_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, refer_handled)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs =
+ LANDLOCK_ACCESS_FS_REFER,
+ });
+
+ EXPECT_EQ(-1, link(file1_s1d1, file1_s1d3));
+ EXPECT_EQ(EXDEV, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
+ dir_s1d1));
+ EXPECT_EQ(0,
+ matches_log_domain_allocated(self->audit_fd, getpid(), NULL));
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
+ dir_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+}
+
+TEST_F(audit_layout1, refer_make)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata,
+ &(struct landlock_ruleset_attr){
+ .handled_access_fs =
+ LANDLOCK_ACCESS_FS_MAKE_REG |
+ LANDLOCK_ACCESS_FS_REFER,
+ });
+
+ EXPECT_EQ(-1, link(file1_s1d1, file1_s1d3));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
+ dir_s1d1));
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.make_reg,fs\\.refer", dir_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+}
+
+TEST_F(audit_layout1, refer_rename)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(EACCES, test_rename(file1_s1d2, file1_s2d3));
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.remove_file,fs\\.refer", dir_s1d2));
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.remove_file,fs\\.make_reg,fs\\.refer",
+ dir_s2d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+}
+
+TEST_F(audit_layout1, refer_exchange)
+{
+ struct audit_records records;
+
+ EXPECT_EQ(0, unlink(file1_s1d3));
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ /*
+ * The only difference with the previous audit_layout1.refer_rename test is
+ * the extra ",fs\\.make_reg" blocked by the source directory.
+ */
+ EXPECT_EQ(EACCES, test_exchange(file1_s1d2, file1_s2d3));
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.remove_file,fs\\.make_reg,fs\\.refer",
+ dir_s1d2));
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.remove_file,fs\\.make_reg,fs\\.refer",
+ dir_s2d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+}
+
+/*
+ * This test checks that the audit record is correctly generated when the
+ * operation is only partially denied. This is the case for rename(2) when the
+ * source file is allowed to be referenced but the destination directory is not.
+ *
+ * This is also a regression test for commit d617f0d72d80 ("landlock: Optimize
+ * file path walks and prepare for audit support") and commit 058518c20920
+ * ("landlock: Align partial refer access checks with final ones").
+ */
+TEST_F(audit_layout1, refer_rename_half)
+{
+ struct audit_records records;
+ const struct rule layer1[] = {
+ {
+ .path = dir_s2d2,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {},
+ };
+ int ruleset_fd =
+ create_ruleset(_metadata, LANDLOCK_ACCESS_FS_REFER, layer1);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(-1, rename(dir_s1d2, dir_s2d3));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Only half of the request is denied. */
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.refer",
+ dir_s1d1));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, truncate)
+{
+ struct audit_records records;
+
+ drop_access_rights(_metadata, &(struct landlock_ruleset_attr){
+ .handled_access_fs = access_fs_16,
+ });
+
+ EXPECT_EQ(-1, truncate(file1_s1d3, 0));
+ EXPECT_EQ(EACCES, errno);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd, "fs\\.truncate",
+ file1_s1d3));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, ioctl_dev)
+{
+ struct audit_records records;
+ int fd;
+
+ drop_access_rights(_metadata,
+ &(struct landlock_ruleset_attr){
+ .handled_access_fs =
+ access_fs_16 &
+ ~LANDLOCK_ACCESS_FS_READ_FILE,
+ });
+
+ fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+ ASSERT_LE(0, fd);
+ EXPECT_EQ(EACCES, ioctl_error(_metadata, fd, FIONREAD));
+ EXPECT_EQ(0, matches_log_fs_extra(_metadata, self->audit_fd,
+ "fs\\.ioctl_dev", "/dev/null",
+ " ioctlcmd=0x541b"));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
+TEST_F(audit_layout1, mount)
+{
+ struct audit_records records;
+
+ drop_access_rights(_metadata,
+ &(struct landlock_ruleset_attr){
+ .handled_access_fs =
+ LANDLOCK_ACCESS_FS_EXECUTE,
+ });
+
+ set_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(-1, mount(NULL, dir_s3d2, NULL, MS_RDONLY, NULL));
+ EXPECT_EQ(EPERM, errno);
+ clear_cap(_metadata, CAP_SYS_ADMIN);
+ EXPECT_EQ(0, matches_log_fs(_metadata, self->audit_fd,
+ "fs\\.change_topology", dir_s3d2));
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index d9de0ee49ebc..2a45208551e6 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -20,6 +20,7 @@
#include <sys/syscall.h>
#include <sys/un.h>
+#include "audit.h"
#include "common.h"
const short sock_port_start = (1 << 10);
@@ -1868,4 +1869,135 @@ TEST_F(port_specific, bind_connect_1023)
EXPECT_EQ(0, close(bind_fd));
}
+static int matches_log_tcp(const int audit_fd, const char *const blockers,
+ const char *const dir_addr, const char *const addr,
+ const char *const dir_port)
+{
+ static const char log_template[] = REGEX_LANDLOCK_PREFIX
+ " blockers=%s %s=%s %s=1024$";
+ /*
+ * Max strlen(blockers): 16
+ * Max strlen(dir_addr): 5
+ * Max strlen(addr): 12
+ * Max strlen(dir_port): 4
+ */
+ char log_match[sizeof(log_template) + 37];
+ int log_match_len;
+
+ log_match_len = snprintf(log_match, sizeof(log_match), log_template,
+ blockers, dir_addr, addr, dir_port);
+ if (log_match_len > sizeof(log_match))
+ return -E2BIG;
+
+ return audit_match_record(audit_fd, AUDIT_LANDLOCK_ACCESS, log_match,
+ NULL);
+}
+
+FIXTURE(audit)
+{
+ struct service_fixture srv0;
+ struct audit_filter audit_filter;
+ int audit_fd;
+};
+
+FIXTURE_VARIANT(audit)
+{
+ const char *const addr;
+ const struct protocol_variant prot;
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit, ipv4) {
+ /* clang-format on */
+ .addr = "127\\.0\\.0\\.1",
+ .prot = {
+ .domain = AF_INET,
+ .type = SOCK_STREAM,
+ },
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(audit, ipv6) {
+ /* clang-format on */
+ .addr = "::1",
+ .prot = {
+ .domain = AF_INET6,
+ .type = SOCK_STREAM,
+ },
+};
+
+FIXTURE_SETUP(audit)
+{
+ ASSERT_EQ(0, set_service(&self->srv0, variant->prot, 0));
+ setup_loopback(_metadata);
+
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ self->audit_fd = audit_init_with_exe_filter(&self->audit_filter);
+ EXPECT_LE(0, self->audit_fd);
+ disable_caps(_metadata);
+};
+
+FIXTURE_TEARDOWN(audit)
+{
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ EXPECT_EQ(0, audit_cleanup(self->audit_fd, &self->audit_filter));
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+}
+
+TEST_F(audit, bind)
+{
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_net = LANDLOCK_ACCESS_NET_BIND_TCP |
+ LANDLOCK_ACCESS_NET_CONNECT_TCP,
+ };
+ struct audit_records records;
+ int ruleset_fd, sock_fd;
+
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ EXPECT_EQ(0, close(ruleset_fd));
+
+ sock_fd = socket_variant(&self->srv0);
+ ASSERT_LE(0, sock_fd);
+ EXPECT_EQ(-EACCES, bind_variant(sock_fd, &self->srv0));
+ EXPECT_EQ(0, matches_log_tcp(self->audit_fd, "net\\.bind_tcp", "saddr",
+ variant->addr, "src"));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+
+ EXPECT_EQ(0, close(sock_fd));
+}
+
+TEST_F(audit, connect)
+{
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_net = LANDLOCK_ACCESS_NET_BIND_TCP |
+ LANDLOCK_ACCESS_NET_CONNECT_TCP,
+ };
+ struct audit_records records;
+ int ruleset_fd, sock_fd;
+
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ EXPECT_EQ(0, close(ruleset_fd));
+
+ sock_fd = socket_variant(&self->srv0);
+ ASSERT_LE(0, sock_fd);
+ EXPECT_EQ(-EACCES, connect_variant(sock_fd, &self->srv0));
+ EXPECT_EQ(0, matches_log_tcp(self->audit_fd, "net\\.connect_tcp",
+ "daddr", variant->addr, "dest"));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(1, records.domain);
+
+ EXPECT_EQ(0, close(sock_fd));
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/landlock/ptrace_test.c b/tools/testing/selftests/landlock/ptrace_test.c
index 8f31b673ff2d..4e356334ecb7 100644
--- a/tools/testing/selftests/landlock/ptrace_test.c
+++ b/tools/testing/selftests/landlock/ptrace_test.c
@@ -4,6 +4,7 @@
*
* Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
* Copyright © 2019-2020 ANSSI
+ * Copyright © 2024-2025 Microsoft Corporation
*/
#define _GNU_SOURCE
@@ -17,6 +18,7 @@
#include <sys/wait.h>
#include <unistd.h>
+#include "audit.h"
#include "common.h"
/* Copied from security/yama/yama_lsm.c */
@@ -434,4 +436,142 @@ TEST_F(hierarchy, trace)
_metadata->exit_code = KSFT_FAIL;
}
+static int matches_log_ptrace(struct __test_metadata *const _metadata,
+ int audit_fd, const pid_t opid)
+{
+ static const char log_template[] = REGEX_LANDLOCK_PREFIX
+ " blockers=ptrace opid=%d ocomm=\"ptrace_test\"$";
+ char log_match[sizeof(log_template) + 10];
+ int log_match_len;
+
+ log_match_len =
+ snprintf(log_match, sizeof(log_match), log_template, opid);
+ if (log_match_len > sizeof(log_match))
+ return -E2BIG;
+
+ return audit_match_record(audit_fd, AUDIT_LANDLOCK_ACCESS, log_match,
+ NULL);
+}
+
+FIXTURE(audit)
+{
+ struct audit_filter audit_filter;
+ int audit_fd;
+};
+
+FIXTURE_SETUP(audit)
+{
+ disable_caps(_metadata);
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ self->audit_fd = audit_init_with_exe_filter(&self->audit_filter);
+ EXPECT_LE(0, self->audit_fd);
+ clear_cap(_metadata, CAP_AUDIT_CONTROL);
+}
+
+FIXTURE_TEARDOWN_PARENT(audit)
+{
+ EXPECT_EQ(0, audit_cleanup(-1, NULL));
+}
+
+/* Test PTRACE_TRACEME and PTRACE_ATTACH for parent and child. */
+TEST_F(audit, trace)
+{
+ pid_t child;
+ int status;
+ int pipe_child[2], pipe_parent[2];
+ int yama_ptrace_scope;
+ char buf_parent;
+ struct audit_records records;
+
+ /* Makes sure there is no superfluous logged records. */
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+
+ yama_ptrace_scope = get_yama_ptrace_scope();
+ ASSERT_LE(0, yama_ptrace_scope);
+
+ if (yama_ptrace_scope > YAMA_SCOPE_DISABLED)
+ TH_LOG("Incomplete tests due to Yama restrictions (scope %d)",
+ yama_ptrace_scope);
+
+ /*
+ * Removes all effective and permitted capabilities to not interfere
+ * with cap_ptrace_access_check() in case of PTRACE_MODE_FSCREDS.
+ */
+ drop_caps(_metadata);
+
+ ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC));
+ ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));
+
+ child = fork();
+ ASSERT_LE(0, child);
+ if (child == 0) {
+ char buf_child;
+
+ ASSERT_EQ(0, close(pipe_parent[1]));
+ ASSERT_EQ(0, close(pipe_child[0]));
+
+ /* Waits for the parent to be in a domain, if any. */
+ ASSERT_EQ(1, read(pipe_parent[0], &buf_child, 1));
+
+ /* Tests child PTRACE_TRACEME. */
+ EXPECT_EQ(-1, ptrace(PTRACE_TRACEME));
+ EXPECT_EQ(EPERM, errno);
+ /* We should see the child process. */
+ EXPECT_EQ(0, matches_log_ptrace(_metadata, self->audit_fd,
+ getpid()));
+
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ /* Checks for a domain creation. */
+ EXPECT_EQ(1, records.domain);
+
+ /*
+ * Signals that the PTRACE_ATTACH test is done and the
+ * PTRACE_TRACEME test is ongoing.
+ */
+ ASSERT_EQ(1, write(pipe_child[1], ".", 1));
+
+ /* Waits for the parent PTRACE_ATTACH test. */
+ ASSERT_EQ(1, read(pipe_parent[0], &buf_child, 1));
+ _exit(_metadata->exit_code);
+ return;
+ }
+
+ ASSERT_EQ(0, close(pipe_child[1]));
+ ASSERT_EQ(0, close(pipe_parent[0]));
+ create_domain(_metadata);
+
+ /* Signals that the parent is in a domain. */
+ ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+
+ /*
+ * Waits for the child to test PTRACE_ATTACH on the parent and start
+ * testing PTRACE_TRACEME.
+ */
+ ASSERT_EQ(1, read(pipe_child[0], &buf_parent, 1));
+
+ /* The child should not be traced by the parent. */
+ EXPECT_EQ(-1, ptrace(PTRACE_DETACH, child, NULL, 0));
+ EXPECT_EQ(ESRCH, errno);
+
+ /* Tests PTRACE_ATTACH on the child. */
+ EXPECT_EQ(-1, ptrace(PTRACE_ATTACH, child, NULL, 0));
+ EXPECT_EQ(EPERM, errno);
+ EXPECT_EQ(0, matches_log_ptrace(_metadata, self->audit_fd, child));
+
+ /* Signals that the parent PTRACE_ATTACH test is done. */
+ ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+ ASSERT_EQ(child, waitpid(child, &status, 0));
+ if (WIFSIGNALED(status) || !WIFEXITED(status) ||
+ WEXITSTATUS(status) != EXIT_SUCCESS)
+ _metadata->exit_code = KSFT_FAIL;
+
+ /* Makes sure there is no superfluous logged records. */
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/landlock/scoped_abstract_unix_test.c b/tools/testing/selftests/landlock/scoped_abstract_unix_test.c
index a6b59d2ab1b4..6825082c079c 100644
--- a/tools/testing/selftests/landlock/scoped_abstract_unix_test.c
+++ b/tools/testing/selftests/landlock/scoped_abstract_unix_test.c
@@ -20,6 +20,7 @@
#include <sys/wait.h>
#include <unistd.h>
+#include "audit.h"
#include "common.h"
#include "scoped_common.h"
@@ -267,6 +268,116 @@ TEST_F(scoped_domains, connect_to_child)
_metadata->exit_code = KSFT_FAIL;
}
+FIXTURE(scoped_audit)
+{
+ struct service_fixture dgram_address;
+ struct audit_filter audit_filter;
+ int audit_fd;
+};
+
+FIXTURE_SETUP(scoped_audit)
+{
+ disable_caps(_metadata);
+
+ memset(&self->dgram_address, 0, sizeof(self->dgram_address));
+ set_unix_address(&self->dgram_address, 1);
+
+ set_cap(_metadata, CAP_AUDIT_CONTROL);
+ self->audit_fd = audit_init_with_exe_filter(&self->audit_filter);
+ EXPECT_LE(0, self->audit_fd);
+ drop_caps(_metadata);
+}
+
+FIXTURE_TEARDOWN_PARENT(scoped_audit)
+{
+ EXPECT_EQ(0, audit_cleanup(-1, NULL));
+}
+
+/* python -c 'print(b"\0selftests-landlock-abstract-unix-".hex().upper())' */
+#define ABSTRACT_SOCKET_PATH_PREFIX \
+ "0073656C6674657374732D6C616E646C6F636B2D61627374726163742D756E69782D"
+
+/*
+ * Simpler version of scoped_domains.connect_to_child, but with audit tests.
+ */
+TEST_F(scoped_audit, connect_to_child)
+{
+ pid_t child;
+ int err_dgram, status;
+ int pipe_child[2], pipe_parent[2];
+ char buf;
+ int dgram_client;
+ struct audit_records records;
+
+ /* Makes sure there is no superfluous logged records. */
+ EXPECT_EQ(0, audit_count_records(self->audit_fd, &records));
+ EXPECT_EQ(0, records.access);
+ EXPECT_EQ(0, records.domain);
+
+ ASSERT_EQ(0, pipe2(pipe_child, O_CLOEXEC));
+ ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));
+
+ child = fork();
+ ASSERT_LE(0, child);
+ if (child == 0) {
+ int dgram_server;
+
+ EXPECT_EQ(0, close(pipe_parent[1]));
+ EXPECT_EQ(0, close(pipe_child[0]));
+
+ /* Waits for the parent to be in a domain. */
+ ASSERT_EQ(1, read(pipe_parent[0], &buf, 1));
+
+ dgram_server = socket(AF_UNIX, SOCK_DGRAM, 0);
+ ASSERT_LE(0, dgram_server);
+ ASSERT_EQ(0, bind(dgram_server, &self->dgram_address.unix_addr,
+ self->dgram_address.unix_addr_len));
+
+ /* Signals to the parent that child is listening. */
+ ASSERT_EQ(1, write(pipe_child[1], ".", 1));
+
+ /* Waits to connect. */
+ ASSERT_EQ(1, read(pipe_parent[0], &buf, 1));
+ EXPECT_EQ(0, close(dgram_server));
+ _exit(_metadata->exit_code);
+ return;
+ }
+ EXPECT_EQ(0, close(pipe_child[1]));
+ EXPECT_EQ(0, close(pipe_parent[0]));
+
+ create_scoped_domain(_metadata, LANDLOCK_SCOPE_ABSTRACT_UNIX_SOCKET);
+
+ /* Signals that the parent is in a domain, if any. */
+ ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+
+ dgram_client = socket(AF_UNIX, SOCK_DGRAM, 0);
+ ASSERT_LE(0, dgram_client);
+
+ /* Waits for the child to listen */
+ ASSERT_EQ(1, read(pipe_child[0], &buf, 1));
+ err_dgram = connect(dgram_client, &self->dgram_address.unix_addr,
+ self->dgram_address.unix_addr_len);
+ EXPECT_EQ(-1, err_dgram);
+ EXPECT_EQ(EPERM, errno);
+
+ EXPECT_EQ(
+ 0,
+ audit_match_record(
+ self->audit_fd, AUDIT_LANDLOCK_ACCESS,
+ REGEX_LANDLOCK_PREFIX
+ " blockers=scope\\.abstract_unix_socket path=" ABSTRACT_SOCKET_PATH_PREFIX
+ "[0-9A-F]\\+$",
+ NULL));
+
+ ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
+ EXPECT_EQ(0, close(dgram_client));
+
+ ASSERT_EQ(child, waitpid(child, &status, 0));
+ if (WIFSIGNALED(status) || !WIFEXITED(status) ||
+ WEXITSTATUS(status) != EXIT_SUCCESS)
+ _metadata->exit_code = KSFT_FAIL;
+}
+
FIXTURE(scoped_vs_unscoped)
{
struct service_fixture parent_stream_address, parent_dgram_address,
diff --git a/tools/testing/selftests/landlock/scoped_signal_test.c b/tools/testing/selftests/landlock/scoped_signal_test.c
index 475ee62a832d..d8bf33417619 100644
--- a/tools/testing/selftests/landlock/scoped_signal_test.c
+++ b/tools/testing/selftests/landlock/scoped_signal_test.c
@@ -249,47 +249,67 @@ TEST_F(scoped_domains, check_access_signal)
_metadata->exit_code = KSFT_FAIL;
}
-static int thread_pipe[2];
-
enum thread_return {
THREAD_INVALID = 0,
THREAD_SUCCESS = 1,
THREAD_ERROR = 2,
+ THREAD_TEST_FAILED = 3,
};
-void *thread_func(void *arg)
+static void *thread_sync(void *arg)
{
+ const int pipe_read = *(int *)arg;
char buf;
- if (read(thread_pipe[0], &buf, 1) != 1)
+ if (read(pipe_read, &buf, 1) != 1)
return (void *)THREAD_ERROR;
return (void *)THREAD_SUCCESS;
}
-TEST(signal_scoping_threads)
+TEST(signal_scoping_thread_before)
{
- pthread_t no_sandbox_thread, scoped_thread;
+ pthread_t no_sandbox_thread;
enum thread_return ret = THREAD_INVALID;
+ int thread_pipe[2];
drop_caps(_metadata);
ASSERT_EQ(0, pipe2(thread_pipe, O_CLOEXEC));
- ASSERT_EQ(0,
- pthread_create(&no_sandbox_thread, NULL, thread_func, NULL));
+ ASSERT_EQ(0, pthread_create(&no_sandbox_thread, NULL, thread_sync,
+ &thread_pipe[0]));
- /* Restricts the domain after creating the first thread. */
+ /* Enforces restriction after creating the thread. */
create_scoped_domain(_metadata, LANDLOCK_SCOPE_SIGNAL);
- ASSERT_EQ(EPERM, pthread_kill(no_sandbox_thread, 0));
- ASSERT_EQ(1, write(thread_pipe[1], ".", 1));
-
- ASSERT_EQ(0, pthread_create(&scoped_thread, NULL, thread_func, NULL));
- ASSERT_EQ(0, pthread_kill(scoped_thread, 0));
- ASSERT_EQ(1, write(thread_pipe[1], ".", 1));
+ EXPECT_EQ(0, pthread_kill(no_sandbox_thread, 0));
+ EXPECT_EQ(1, write(thread_pipe[1], ".", 1));
EXPECT_EQ(0, pthread_join(no_sandbox_thread, (void **)&ret));
EXPECT_EQ(THREAD_SUCCESS, ret);
+
+ EXPECT_EQ(0, close(thread_pipe[0]));
+ EXPECT_EQ(0, close(thread_pipe[1]));
+}
+
+TEST(signal_scoping_thread_after)
+{
+ pthread_t scoped_thread;
+ enum thread_return ret = THREAD_INVALID;
+ int thread_pipe[2];
+
+ drop_caps(_metadata);
+ ASSERT_EQ(0, pipe2(thread_pipe, O_CLOEXEC));
+
+ /* Enforces restriction before creating the thread. */
+ create_scoped_domain(_metadata, LANDLOCK_SCOPE_SIGNAL);
+
+ ASSERT_EQ(0, pthread_create(&scoped_thread, NULL, thread_sync,
+ &thread_pipe[0]));
+
+ EXPECT_EQ(0, pthread_kill(scoped_thread, 0));
+ EXPECT_EQ(1, write(thread_pipe[1], ".", 1));
+
EXPECT_EQ(0, pthread_join(scoped_thread, (void **)&ret));
EXPECT_EQ(THREAD_SUCCESS, ret);
@@ -297,6 +317,64 @@ TEST(signal_scoping_threads)
EXPECT_EQ(0, close(thread_pipe[1]));
}
+struct thread_setuid_args {
+ int pipe_read, new_uid;
+};
+
+void *thread_setuid(void *ptr)
+{
+ const struct thread_setuid_args *arg = ptr;
+ char buf;
+
+ if (read(arg->pipe_read, &buf, 1) != 1)
+ return (void *)THREAD_ERROR;
+
+ /* libc's setuid() should update all thread's credentials. */
+ if (getuid() != arg->new_uid)
+ return (void *)THREAD_TEST_FAILED;
+
+ return (void *)THREAD_SUCCESS;
+}
+
+TEST(signal_scoping_thread_setuid)
+{
+ struct thread_setuid_args arg;
+ pthread_t no_sandbox_thread;
+ enum thread_return ret = THREAD_INVALID;
+ int pipe_parent[2];
+ int prev_uid;
+
+ disable_caps(_metadata);
+
+ /* This test does not need to be run as root. */
+ prev_uid = getuid();
+ arg.new_uid = prev_uid + 1;
+ EXPECT_LT(0, arg.new_uid);
+
+ ASSERT_EQ(0, pipe2(pipe_parent, O_CLOEXEC));
+ arg.pipe_read = pipe_parent[0];
+
+ /* Capabilities must be set before creating a new thread. */
+ set_cap(_metadata, CAP_SETUID);
+ ASSERT_EQ(0, pthread_create(&no_sandbox_thread, NULL, thread_setuid,
+ &arg));
+
+ /* Enforces restriction after creating the thread. */
+ create_scoped_domain(_metadata, LANDLOCK_SCOPE_SIGNAL);
+
+ EXPECT_NE(arg.new_uid, getuid());
+ EXPECT_EQ(0, setuid(arg.new_uid));
+ EXPECT_EQ(arg.new_uid, getuid());
+ EXPECT_EQ(1, write(pipe_parent[1], ".", 1));
+
+ EXPECT_EQ(0, pthread_join(no_sandbox_thread, (void **)&ret));
+ EXPECT_EQ(THREAD_SUCCESS, ret);
+
+ clear_cap(_metadata, CAP_SETUID);
+ EXPECT_EQ(0, close(pipe_parent[0]));
+ EXPECT_EQ(0, close(pipe_parent[1]));
+}
+
const short backlog = 10;
static volatile sig_atomic_t signal_received;
diff --git a/tools/testing/selftests/landlock/wait-pipe-sandbox.c b/tools/testing/selftests/landlock/wait-pipe-sandbox.c
new file mode 100644
index 000000000000..87dbc9164430
--- /dev/null
+++ b/tools/testing/selftests/landlock/wait-pipe-sandbox.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Write in a pipe, wait, sandbox itself, test sandboxing, and wait again.
+ *
+ * Used by audit_exec.flags from audit_test.c
+ *
+ * Copyright © 2024-2025 Microsoft Corporation
+ */
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <linux/landlock.h>
+#include <linux/prctl.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+
+#include "wrappers.h"
+
+static int sync_with(int pipe_child, int pipe_parent)
+{
+ char buf;
+
+ /* Signals that we are waiting. */
+ if (write(pipe_child, ".", 1) != 1) {
+ perror("Failed to write to first argument");
+ return 1;
+ }
+
+ /* Waits for the parent do its test. */
+ if (read(pipe_parent, &buf, 1) != 1) {
+ perror("Failed to write to the second argument");
+ return 1;
+ }
+
+ return 0;
+}
+
+int main(int argc, char *argv[])
+{
+ const struct landlock_ruleset_attr layer2 = {
+ .handled_access_fs = LANDLOCK_ACCESS_FS_READ_DIR,
+ };
+ const struct landlock_ruleset_attr layer3 = {
+ .scoped = LANDLOCK_SCOPE_SIGNAL,
+ };
+ int err, pipe_child, pipe_parent, ruleset_fd;
+
+ /* The first argument must be the file descriptor number of a pipe. */
+ if (argc != 3) {
+ fprintf(stderr, "Wrong number of arguments (not two)\n");
+ return 1;
+ }
+
+ pipe_child = atoi(argv[1]);
+ pipe_parent = atoi(argv[2]);
+ /* PR_SET_NO_NEW_PRIVS already set by parent. */
+
+ /* First step to test parent's layer1. */
+ err = sync_with(pipe_child, pipe_parent);
+ if (err)
+ return err;
+
+ /* Tries to send a signal, denied by layer1. */
+ if (!kill(getppid(), 0)) {
+ fprintf(stderr, "Successfully sent a signal to the parent");
+ return 1;
+ }
+
+ /* Second step to test parent's layer1 and our layer2. */
+ err = sync_with(pipe_child, pipe_parent);
+ if (err)
+ return err;
+
+ ruleset_fd = landlock_create_ruleset(&layer2, sizeof(layer2), 0);
+ if (ruleset_fd < 0) {
+ perror("Failed to create the layer2 ruleset");
+ return 1;
+ }
+
+ if (landlock_restrict_self(ruleset_fd, 0)) {
+ perror("Failed to restrict self");
+ return 1;
+ }
+ close(ruleset_fd);
+
+ /* Tries to send a signal, denied by layer1. */
+ if (!kill(getppid(), 0)) {
+ fprintf(stderr, "Successfully sent a signal to the parent");
+ return 1;
+ }
+
+ /* Tries to open ., denied by layer2. */
+ if (open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC) >= 0) {
+ fprintf(stderr, "Successfully opened /");
+ return 1;
+ }
+
+ /* Third step to test our layer2 and layer3. */
+ err = sync_with(pipe_child, pipe_parent);
+ if (err)
+ return err;
+
+ ruleset_fd = landlock_create_ruleset(&layer3, sizeof(layer3), 0);
+ if (ruleset_fd < 0) {
+ perror("Failed to create the layer3 ruleset");
+ return 1;
+ }
+
+ if (landlock_restrict_self(ruleset_fd, 0)) {
+ perror("Failed to restrict self");
+ return 1;
+ }
+ close(ruleset_fd);
+
+ /* Tries to open ., denied by layer2. */
+ if (open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC) >= 0) {
+ fprintf(stderr, "Successfully opened /");
+ return 1;
+ }
+
+ /* Tries to send a signal, denied by layer3. */
+ if (!kill(getppid(), 0)) {
+ fprintf(stderr, "Successfully sent a signal to the parent");
+ return 1;
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/lib/config b/tools/testing/selftests/lib/config
index 81a1f64a22e8..377b3699ff31 100644
--- a/tools/testing/selftests/lib/config
+++ b/tools/testing/selftests/lib/config
@@ -1,2 +1,3 @@
CONFIG_TEST_BITMAP=m
+CONFIG_PRIME_NUMBERS=m
CONFIG_TEST_BITOPS=m
diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c
index e949a43a6145..17ed3e9917ca 100644
--- a/tools/testing/selftests/mincore/mincore_selftest.c
+++ b/tools/testing/selftests/mincore/mincore_selftest.c
@@ -261,9 +261,6 @@ TEST(check_file_mmap)
TH_LOG("No read-ahead pages found in memory");
}
- EXPECT_LT(i, vec_size) {
- TH_LOG("Read-ahead pages reached the end of the file");
- }
/*
* End of the readahead window. The rest of the pages shouldn't
* be in memory.
@@ -286,8 +283,7 @@ out_free:
/*
* Test mincore() behavior on a page backed by a tmpfs file. This test
- * performs the same steps as the previous one. However, we don't expect
- * any readahead in this case.
+ * performs the same steps as the previous one.
*/
TEST(check_tmpfs_mmap)
{
@@ -298,7 +294,6 @@ TEST(check_tmpfs_mmap)
int page_size;
int fd;
int i;
- int ra_pages = 0;
page_size = sysconf(_SC_PAGESIZE);
vec_size = FILE_SIZE / page_size;
@@ -341,8 +336,7 @@ TEST(check_tmpfs_mmap)
}
/*
- * Touch a page in the middle of the mapping. We expect only
- * that page to be fetched into memory.
+ * Touch a page in the middle of the mapping.
*/
addr[FILE_SIZE / 2] = 1;
retval = mincore(addr, FILE_SIZE, vec);
@@ -351,15 +345,6 @@ TEST(check_tmpfs_mmap)
TH_LOG("Page not found in memory after use");
}
- i = FILE_SIZE / 2 / page_size + 1;
- while (i < vec_size && vec[i]) {
- ra_pages++;
- i++;
- }
- ASSERT_EQ(ra_pages, 0) {
- TH_LOG("Read-ahead pages found in memory");
- }
-
munmap(addr, FILE_SIZE);
close(fd);
free(vec);
diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore
index 121000c28c10..c5241b193db8 100644
--- a/tools/testing/selftests/mm/.gitignore
+++ b/tools/testing/selftests/mm/.gitignore
@@ -57,4 +57,4 @@ droppable
hugetlb_dio
pkey_sighandler_tests_32
pkey_sighandler_tests_64
-guard-pages
+guard-regions
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 63ce39d024bb..8270895039d1 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -97,7 +97,7 @@ TEST_GEN_FILES += hugetlb_fault_after_madv
TEST_GEN_FILES += hugetlb_madv_vs_map
TEST_GEN_FILES += hugetlb_dio
TEST_GEN_FILES += droppable
-TEST_GEN_FILES += guard-pages
+TEST_GEN_FILES += guard-regions
ifneq ($(ARCH),arm64)
TEST_GEN_FILES += soft-dirty
diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
index 67df7b47087f..e1fe16bcbbe8 100755
--- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
+++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh
@@ -29,7 +29,7 @@ fi
if [[ $cgroup2 ]]; then
cgroup_path=$(mount -t cgroup2 | head -1 | awk '{print $3}')
if [[ -z "$cgroup_path" ]]; then
- cgroup_path=/dev/cgroup/memory
+ cgroup_path=$(mktemp -d)
mount -t cgroup2 none $cgroup_path
do_umount=1
fi
@@ -37,7 +37,7 @@ if [[ $cgroup2 ]]; then
else
cgroup_path=$(mount -t cgroup | grep ",hugetlb" | awk '{print $3}')
if [[ -z "$cgroup_path" ]]; then
- cgroup_path=/dev/cgroup/memory
+ cgroup_path=$(mktemp -d)
mount -t cgroup memory,hugetlb $cgroup_path
do_umount=1
fi
diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index 9446673645eb..b6cfe0a4b7df 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -293,7 +293,7 @@ static void do_test_vmsplice_in_parent(char *mem, size_t size,
.iov_base = mem,
.iov_len = size,
};
- ssize_t cur, total, transferred;
+ ssize_t cur, total, transferred = 0;
struct comm_pipes comm_pipes;
char *old, *new;
int ret, fds[2];
@@ -876,7 +876,7 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize)
mremap_size = thpsize / 2;
mremap_mem = mmap(NULL, mremap_size, PROT_NONE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
- if (mem == MAP_FAILED) {
+ if (mremap_mem == MAP_FAILED) {
ksft_test_result_fail("mmap() failed\n");
goto munmap;
}
diff --git a/tools/testing/selftests/mm/guard-pages.c b/tools/testing/selftests/mm/guard-regions.c
index 525c50d3ec23..b3d0e2771096 100644
--- a/tools/testing/selftests/mm/guard-pages.c
+++ b/tools/testing/selftests/mm/guard-regions.c
@@ -6,6 +6,7 @@
#include <assert.h>
#include <errno.h>
#include <fcntl.h>
+#include <linux/limits.h>
#include <linux/userfaultfd.h>
#include <setjmp.h>
#include <signal.h>
@@ -18,6 +19,7 @@
#include <sys/syscall.h>
#include <sys/uio.h>
#include <unistd.h>
+#include "vm_util.h"
#include "../pidfd/pidfd.h"
@@ -39,6 +41,79 @@ static sigjmp_buf signal_jmp_buf;
*/
#define FORCE_READ(x) (*(volatile typeof(x) *)x)
+/*
+ * How is the test backing the mapping being tested?
+ */
+enum backing_type {
+ ANON_BACKED,
+ SHMEM_BACKED,
+ LOCAL_FILE_BACKED,
+};
+
+FIXTURE(guard_regions)
+{
+ unsigned long page_size;
+ char path[PATH_MAX];
+ int fd;
+};
+
+FIXTURE_VARIANT(guard_regions)
+{
+ enum backing_type backing;
+};
+
+FIXTURE_VARIANT_ADD(guard_regions, anon)
+{
+ .backing = ANON_BACKED,
+};
+
+FIXTURE_VARIANT_ADD(guard_regions, shmem)
+{
+ .backing = SHMEM_BACKED,
+};
+
+FIXTURE_VARIANT_ADD(guard_regions, file)
+{
+ .backing = LOCAL_FILE_BACKED,
+};
+
+static bool is_anon_backed(const FIXTURE_VARIANT(guard_regions) * variant)
+{
+ switch (variant->backing) {
+ case ANON_BACKED:
+ case SHMEM_BACKED:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static void *mmap_(FIXTURE_DATA(guard_regions) * self,
+ const FIXTURE_VARIANT(guard_regions) * variant,
+ void *addr, size_t length, int prot, int extra_flags,
+ off_t offset)
+{
+ int fd;
+ int flags = extra_flags;
+
+ switch (variant->backing) {
+ case ANON_BACKED:
+ flags |= MAP_PRIVATE | MAP_ANON;
+ fd = -1;
+ break;
+ case SHMEM_BACKED:
+ case LOCAL_FILE_BACKED:
+ flags |= MAP_SHARED;
+ fd = self->fd;
+ break;
+ default:
+ ksft_exit_fail();
+ break;
+ }
+
+ return mmap(addr, length, prot, flags, fd, offset);
+}
+
static int userfaultfd(int flags)
{
return syscall(SYS_userfaultfd, flags);
@@ -104,12 +179,7 @@ static bool try_read_write_buf(char *ptr)
return try_read_buf(ptr) && try_write_buf(ptr);
}
-FIXTURE(guard_pages)
-{
- unsigned long page_size;
-};
-
-FIXTURE_SETUP(guard_pages)
+static void setup_sighandler(void)
{
struct sigaction act = {
.sa_handler = &handle_fatal,
@@ -119,11 +189,9 @@ FIXTURE_SETUP(guard_pages)
sigemptyset(&act.sa_mask);
if (sigaction(SIGSEGV, &act, NULL))
ksft_exit_fail_perror("sigaction");
+}
- self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
-};
-
-FIXTURE_TEARDOWN(guard_pages)
+static void teardown_sighandler(void)
{
struct sigaction act = {
.sa_handler = SIG_DFL,
@@ -134,15 +202,109 @@ FIXTURE_TEARDOWN(guard_pages)
sigaction(SIGSEGV, &act, NULL);
}
-TEST_F(guard_pages, basic)
+static int open_file(const char *prefix, char *path)
+{
+ int fd;
+
+ snprintf(path, PATH_MAX, "%sguard_regions_test_file_XXXXXX", prefix);
+ fd = mkstemp(path);
+ if (fd < 0)
+ ksft_exit_fail_perror("mkstemp");
+
+ return fd;
+}
+
+/* Establish a varying pattern in a buffer. */
+static void set_pattern(char *ptr, size_t num_pages, size_t page_size)
+{
+ size_t i;
+
+ for (i = 0; i < num_pages; i++) {
+ char *ptr2 = &ptr[i * page_size];
+
+ memset(ptr2, 'a' + (i % 26), page_size);
+ }
+}
+
+/*
+ * Check that a buffer contains the pattern set by set_pattern(), starting at a
+ * page offset of pgoff within the buffer.
+ */
+static bool check_pattern_offset(char *ptr, size_t num_pages, size_t page_size,
+ size_t pgoff)
+{
+ size_t i;
+
+ for (i = 0; i < num_pages * page_size; i++) {
+ size_t offset = pgoff * page_size + i;
+ char actual = ptr[offset];
+ char expected = 'a' + ((offset / page_size) % 26);
+
+ if (actual != expected)
+ return false;
+ }
+
+ return true;
+}
+
+/* Check that a buffer contains the pattern set by set_pattern(). */
+static bool check_pattern(char *ptr, size_t num_pages, size_t page_size)
+{
+ return check_pattern_offset(ptr, num_pages, page_size, 0);
+}
+
+/* Determine if a buffer contains only repetitions of a specified char. */
+static bool is_buf_eq(char *buf, size_t size, char chr)
+{
+ size_t i;
+
+ for (i = 0; i < size; i++) {
+ if (buf[i] != chr)
+ return false;
+ }
+
+ return true;
+}
+
+FIXTURE_SETUP(guard_regions)
+{
+ self->page_size = (unsigned long)sysconf(_SC_PAGESIZE);
+ setup_sighandler();
+
+ if (variant->backing == ANON_BACKED)
+ return;
+
+ self->fd = open_file(
+ variant->backing == SHMEM_BACKED ? "/tmp/" : "",
+ self->path);
+
+ /* We truncate file to at least 100 pages, tests can modify as needed. */
+ ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0);
+};
+
+FIXTURE_TEARDOWN_PARENT(guard_regions)
+{
+ teardown_sighandler();
+
+ if (variant->backing == ANON_BACKED)
+ return;
+
+ if (self->fd >= 0)
+ close(self->fd);
+
+ if (self->path[0] != '\0')
+ unlink(self->path);
+}
+
+TEST_F(guard_regions, basic)
{
const unsigned long NUM_PAGES = 10;
const unsigned long page_size = self->page_size;
char *ptr;
int i;
- ptr = mmap(NULL, NUM_PAGES * page_size, PROT_READ | PROT_WRITE,
- MAP_PRIVATE | MAP_ANON, -1, 0);
+ ptr = mmap_(self, variant, NULL, NUM_PAGES * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Trivially assert we can touch the first page. */
@@ -228,32 +390,30 @@ TEST_F(guard_pages, basic)
}
/* Assert that operations applied across multiple VMAs work as expected. */
-TEST_F(guard_pages, multi_vma)
+TEST_F(guard_regions, multi_vma)
{
const unsigned long page_size = self->page_size;
char *ptr_region, *ptr, *ptr1, *ptr2, *ptr3;
int i;
/* Reserve a 100 page region over which we can install VMAs. */
- ptr_region = mmap(NULL, 100 * page_size, PROT_NONE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr_region = mmap_(self, variant, NULL, 100 * page_size,
+ PROT_NONE, 0, 0);
ASSERT_NE(ptr_region, MAP_FAILED);
/* Place a VMA of 10 pages size at the start of the region. */
- ptr1 = mmap(ptr_region, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr1 = mmap_(self, variant, ptr_region, 10 * page_size,
+ PROT_READ | PROT_WRITE, MAP_FIXED, 0);
ASSERT_NE(ptr1, MAP_FAILED);
/* Place a VMA of 5 pages size 50 pages into the region. */
- ptr2 = mmap(&ptr_region[50 * page_size], 5 * page_size,
- PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr2 = mmap_(self, variant, &ptr_region[50 * page_size], 5 * page_size,
+ PROT_READ | PROT_WRITE, MAP_FIXED, 0);
ASSERT_NE(ptr2, MAP_FAILED);
/* Place a VMA of 20 pages size at the end of the region. */
- ptr3 = mmap(&ptr_region[80 * page_size], 20 * page_size,
- PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr3 = mmap_(self, variant, &ptr_region[80 * page_size], 20 * page_size,
+ PROT_READ | PROT_WRITE, MAP_FIXED, 0);
ASSERT_NE(ptr3, MAP_FAILED);
/* Unmap gaps. */
@@ -323,13 +483,11 @@ TEST_F(guard_pages, multi_vma)
}
/* Now map incompatible VMAs in the gaps. */
- ptr = mmap(&ptr_region[10 * page_size], 40 * page_size,
- PROT_READ | PROT_WRITE | PROT_EXEC,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, &ptr_region[10 * page_size], 40 * page_size,
+ PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED, 0);
ASSERT_NE(ptr, MAP_FAILED);
- ptr = mmap(&ptr_region[55 * page_size], 25 * page_size,
- PROT_READ | PROT_WRITE | PROT_EXEC,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, &ptr_region[55 * page_size], 25 * page_size,
+ PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED, 0);
ASSERT_NE(ptr, MAP_FAILED);
/*
@@ -364,7 +522,7 @@ TEST_F(guard_pages, multi_vma)
* Assert that batched operations performed using process_madvise() work as
* expected.
*/
-TEST_F(guard_pages, process_madvise)
+TEST_F(guard_regions, process_madvise)
{
const unsigned long page_size = self->page_size;
char *ptr_region, *ptr1, *ptr2, *ptr3;
@@ -372,8 +530,8 @@ TEST_F(guard_pages, process_madvise)
struct iovec vec[6];
/* Reserve region to map over. */
- ptr_region = mmap(NULL, 100 * page_size, PROT_NONE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr_region = mmap_(self, variant, NULL, 100 * page_size,
+ PROT_NONE, 0, 0);
ASSERT_NE(ptr_region, MAP_FAILED);
/*
@@ -381,9 +539,8 @@ TEST_F(guard_pages, process_madvise)
* overwrite existing entries and test this code path against
* overwriting existing entries.
*/
- ptr1 = mmap(&ptr_region[page_size], 10 * page_size,
- PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE | MAP_POPULATE, -1, 0);
+ ptr1 = mmap_(self, variant, &ptr_region[page_size], 10 * page_size,
+ PROT_READ | PROT_WRITE, MAP_FIXED | MAP_POPULATE, 0);
ASSERT_NE(ptr1, MAP_FAILED);
/* We want guard markers at start/end of each VMA. */
vec[0].iov_base = ptr1;
@@ -392,9 +549,8 @@ TEST_F(guard_pages, process_madvise)
vec[1].iov_len = page_size;
/* 5 pages offset 50 pages into reserve region. */
- ptr2 = mmap(&ptr_region[50 * page_size], 5 * page_size,
- PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr2 = mmap_(self, variant, &ptr_region[50 * page_size], 5 * page_size,
+ PROT_READ | PROT_WRITE, MAP_FIXED, 0);
ASSERT_NE(ptr2, MAP_FAILED);
vec[2].iov_base = ptr2;
vec[2].iov_len = page_size;
@@ -402,9 +558,8 @@ TEST_F(guard_pages, process_madvise)
vec[3].iov_len = page_size;
/* 20 pages offset 79 pages into reserve region. */
- ptr3 = mmap(&ptr_region[79 * page_size], 20 * page_size,
- PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr3 = mmap_(self, variant, &ptr_region[79 * page_size], 20 * page_size,
+ PROT_READ | PROT_WRITE, MAP_FIXED, 0);
ASSERT_NE(ptr3, MAP_FAILED);
vec[4].iov_base = ptr3;
vec[4].iov_len = page_size;
@@ -459,13 +614,13 @@ TEST_F(guard_pages, process_madvise)
}
/* Assert that unmapping ranges does not leave guard markers behind. */
-TEST_F(guard_pages, munmap)
+TEST_F(guard_regions, munmap)
{
const unsigned long page_size = self->page_size;
char *ptr, *ptr_new1, *ptr_new2;
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Guard first and last pages. */
@@ -481,11 +636,11 @@ TEST_F(guard_pages, munmap)
ASSERT_EQ(munmap(&ptr[9 * page_size], page_size), 0);
/* Map over them.*/
- ptr_new1 = mmap(ptr, page_size, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr_new1 = mmap_(self, variant, ptr, page_size, PROT_READ | PROT_WRITE,
+ MAP_FIXED, 0);
ASSERT_NE(ptr_new1, MAP_FAILED);
- ptr_new2 = mmap(&ptr[9 * page_size], page_size, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr_new2 = mmap_(self, variant, &ptr[9 * page_size], page_size,
+ PROT_READ | PROT_WRITE, MAP_FIXED, 0);
ASSERT_NE(ptr_new2, MAP_FAILED);
/* Assert that they are now not guarded. */
@@ -497,14 +652,14 @@ TEST_F(guard_pages, munmap)
}
/* Assert that mprotect() operations have no bearing on guard markers. */
-TEST_F(guard_pages, mprotect)
+TEST_F(guard_regions, mprotect)
{
const unsigned long page_size = self->page_size;
char *ptr;
int i;
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Guard the middle of the range. */
@@ -545,14 +700,14 @@ TEST_F(guard_pages, mprotect)
}
/* Split and merge VMAs and make sure guard pages still behave. */
-TEST_F(guard_pages, split_merge)
+TEST_F(guard_regions, split_merge)
{
const unsigned long page_size = self->page_size;
char *ptr, *ptr_new;
int i;
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Guard the whole range. */
@@ -593,14 +748,14 @@ TEST_F(guard_pages, split_merge)
}
/* Now map them again - the unmap will have cleared the guards. */
- ptr_new = mmap(&ptr[2 * page_size], page_size, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr_new = mmap_(self, variant, &ptr[2 * page_size], page_size,
+ PROT_READ | PROT_WRITE, MAP_FIXED, 0);
ASSERT_NE(ptr_new, MAP_FAILED);
- ptr_new = mmap(&ptr[5 * page_size], page_size, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr_new = mmap_(self, variant, &ptr[5 * page_size], page_size,
+ PROT_READ | PROT_WRITE, MAP_FIXED, 0);
ASSERT_NE(ptr_new, MAP_FAILED);
- ptr_new = mmap(&ptr[8 * page_size], page_size, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr_new = mmap_(self, variant, &ptr[8 * page_size], page_size,
+ PROT_READ | PROT_WRITE, MAP_FIXED, 0);
ASSERT_NE(ptr_new, MAP_FAILED);
/* Now make sure guard pages are established. */
@@ -676,14 +831,14 @@ TEST_F(guard_pages, split_merge)
}
/* Assert that MADV_DONTNEED does not remove guard markers. */
-TEST_F(guard_pages, dontneed)
+TEST_F(guard_regions, dontneed)
{
const unsigned long page_size = self->page_size;
char *ptr;
int i;
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Back the whole range. */
@@ -713,8 +868,16 @@ TEST_F(guard_pages, dontneed)
ASSERT_FALSE(result);
} else {
ASSERT_TRUE(result);
- /* Make sure we really did get reset to zero page. */
- ASSERT_EQ(*curr, '\0');
+ switch (variant->backing) {
+ case ANON_BACKED:
+ /* If anon, then we get a zero page. */
+ ASSERT_EQ(*curr, '\0');
+ break;
+ default:
+ /* Otherwise, we get the file data. */
+ ASSERT_EQ(*curr, 'y');
+ break;
+ }
}
/* Now write... */
@@ -729,14 +892,14 @@ TEST_F(guard_pages, dontneed)
}
/* Assert that mlock()'ed pages work correctly with guard markers. */
-TEST_F(guard_pages, mlock)
+TEST_F(guard_regions, mlock)
{
const unsigned long page_size = self->page_size;
char *ptr;
int i;
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Populate. */
@@ -802,14 +965,14 @@ TEST_F(guard_pages, mlock)
*
* - Moving a mapping alone should retain markers as they are.
*/
-TEST_F(guard_pages, mremap_move)
+TEST_F(guard_regions, mremap_move)
{
const unsigned long page_size = self->page_size;
char *ptr, *ptr_new;
/* Map 5 pages. */
- ptr = mmap(NULL, 5 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 5 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Place guard markers at both ends of the 5 page span. */
@@ -823,8 +986,7 @@ TEST_F(guard_pages, mremap_move)
/* Map a new region we will move this range into. Doing this ensures
* that we have reserved a range to map into.
*/
- ptr_new = mmap(NULL, 5 * page_size, PROT_NONE, MAP_ANON | MAP_PRIVATE,
- -1, 0);
+ ptr_new = mmap_(self, variant, NULL, 5 * page_size, PROT_NONE, 0, 0);
ASSERT_NE(ptr_new, MAP_FAILED);
ASSERT_EQ(mremap(ptr, 5 * page_size, 5 * page_size,
@@ -849,14 +1011,14 @@ TEST_F(guard_pages, mremap_move)
* will have to remove guard pages manually to fix up (they'd have to do the
* same if it were a PROT_NONE mapping).
*/
-TEST_F(guard_pages, mremap_expand)
+TEST_F(guard_regions, mremap_expand)
{
const unsigned long page_size = self->page_size;
char *ptr, *ptr_new;
/* Map 10 pages... */
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* ...But unmap the last 5 so we can ensure we can expand into them. */
ASSERT_EQ(munmap(&ptr[5 * page_size], 5 * page_size), 0);
@@ -880,8 +1042,7 @@ TEST_F(guard_pages, mremap_expand)
ASSERT_FALSE(try_read_write_buf(&ptr[4 * page_size]));
/* Reserve a region which we can move to and expand into. */
- ptr_new = mmap(NULL, 20 * page_size, PROT_NONE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr_new = mmap_(self, variant, NULL, 20 * page_size, PROT_NONE, 0, 0);
ASSERT_NE(ptr_new, MAP_FAILED);
/* Now move and expand into it. */
@@ -912,15 +1073,15 @@ TEST_F(guard_pages, mremap_expand)
* if the user were using a PROT_NONE mapping they'd have to manually fix this
* up also so this is OK.
*/
-TEST_F(guard_pages, mremap_shrink)
+TEST_F(guard_regions, mremap_shrink)
{
const unsigned long page_size = self->page_size;
char *ptr;
int i;
/* Map 5 pages. */
- ptr = mmap(NULL, 5 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 5 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Place guard markers at both ends of the 5 page span. */
@@ -976,7 +1137,7 @@ TEST_F(guard_pages, mremap_shrink)
* Assert that forking a process with VMAs that do not have VM_WIPEONFORK set
* retain guard pages.
*/
-TEST_F(guard_pages, fork)
+TEST_F(guard_regions, fork)
{
const unsigned long page_size = self->page_size;
char *ptr;
@@ -984,8 +1145,8 @@ TEST_F(guard_pages, fork)
int i;
/* Map 10 pages. */
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Establish guard pages in the first 5 pages. */
@@ -1031,16 +1192,19 @@ TEST_F(guard_pages, fork)
* Assert expected behaviour after we fork populated ranges of anonymous memory
* and then guard and unguard the range.
*/
-TEST_F(guard_pages, fork_cow)
+TEST_F(guard_regions, fork_cow)
{
const unsigned long page_size = self->page_size;
char *ptr;
pid_t pid;
int i;
+ if (variant->backing != ANON_BACKED)
+ SKIP(return, "CoW only supported on anon mappings");
+
/* Map 10 pages. */
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Populate range. */
@@ -1102,16 +1266,19 @@ TEST_F(guard_pages, fork_cow)
* Assert that forking a process with VMAs that do have VM_WIPEONFORK set
* behave as expected.
*/
-TEST_F(guard_pages, fork_wipeonfork)
+TEST_F(guard_regions, fork_wipeonfork)
{
const unsigned long page_size = self->page_size;
char *ptr;
pid_t pid;
int i;
+ if (variant->backing != ANON_BACKED)
+ SKIP(return, "Wipe on fork only supported on anon mappings");
+
/* Map 10 pages. */
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Mark wipe on fork. */
@@ -1152,15 +1319,18 @@ TEST_F(guard_pages, fork_wipeonfork)
}
/* Ensure that MADV_FREE retains guard entries as expected. */
-TEST_F(guard_pages, lazyfree)
+TEST_F(guard_regions, lazyfree)
{
const unsigned long page_size = self->page_size;
char *ptr;
int i;
+ if (variant->backing != ANON_BACKED)
+ SKIP(return, "MADV_FREE only supported on anon mappings");
+
/* Map 10 pages. */
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Guard range. */
@@ -1188,14 +1358,14 @@ TEST_F(guard_pages, lazyfree)
}
/* Ensure that MADV_POPULATE_READ, MADV_POPULATE_WRITE behave as expected. */
-TEST_F(guard_pages, populate)
+TEST_F(guard_regions, populate)
{
const unsigned long page_size = self->page_size;
char *ptr;
/* Map 10 pages. */
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Guard range. */
@@ -1214,15 +1384,15 @@ TEST_F(guard_pages, populate)
}
/* Ensure that MADV_COLD, MADV_PAGEOUT do not remove guard markers. */
-TEST_F(guard_pages, cold_pageout)
+TEST_F(guard_regions, cold_pageout)
{
const unsigned long page_size = self->page_size;
char *ptr;
int i;
/* Map 10 pages. */
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Guard range. */
@@ -1260,7 +1430,7 @@ TEST_F(guard_pages, cold_pageout)
}
/* Ensure that guard pages do not break userfaultd. */
-TEST_F(guard_pages, uffd)
+TEST_F(guard_regions, uffd)
{
const unsigned long page_size = self->page_size;
int uffd;
@@ -1273,6 +1443,9 @@ TEST_F(guard_pages, uffd)
struct uffdio_register reg;
struct uffdio_range range;
+ if (!is_anon_backed(variant))
+ SKIP(return, "uffd only works on anon backing");
+
/* Set up uffd. */
uffd = userfaultfd(0);
if (uffd == -1 && errno == EPERM)
@@ -1282,8 +1455,8 @@ TEST_F(guard_pages, uffd)
ASSERT_EQ(ioctl(uffd, UFFDIO_API, &api), 0);
/* Map 10 pages. */
- ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE,
- MAP_ANON | MAP_PRIVATE, -1, 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
ASSERT_NE(ptr, MAP_FAILED);
/* Register the range with uffd. */
@@ -1309,4 +1482,593 @@ TEST_F(guard_pages, uffd)
ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
}
+/*
+ * Mark a region within a file-backed mapping using MADV_SEQUENTIAL so we
+ * aggressively read-ahead, then install guard regions and assert that it
+ * behaves correctly.
+ *
+ * We page out using MADV_PAGEOUT before checking guard regions so we drop page
+ * cache folios, meaning we maximise the possibility of some broken readahead.
+ */
+TEST_F(guard_regions, madvise_sequential)
+{
+ char *ptr;
+ int i;
+ const unsigned long page_size = self->page_size;
+
+ if (variant->backing == ANON_BACKED)
+ SKIP(return, "MADV_SEQUENTIAL meaningful only for file-backed");
+
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Establish a pattern of data in the file. */
+ set_pattern(ptr, 10, page_size);
+ ASSERT_TRUE(check_pattern(ptr, 10, page_size));
+
+ /* Mark it as being accessed sequentially. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_SEQUENTIAL), 0);
+
+ /* Mark every other page a guard page. */
+ for (i = 0; i < 10; i += 2) {
+ char *ptr2 = &ptr[i * page_size];
+
+ ASSERT_EQ(madvise(ptr2, page_size, MADV_GUARD_INSTALL), 0);
+ }
+
+ /* Now page it out. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_PAGEOUT), 0);
+
+ /* Now make sure pages are as expected. */
+ for (i = 0; i < 10; i++) {
+ char *chrp = &ptr[i * page_size];
+
+ if (i % 2 == 0) {
+ bool result = try_read_write_buf(chrp);
+
+ ASSERT_FALSE(result);
+ } else {
+ ASSERT_EQ(*chrp, 'a' + i);
+ }
+ }
+
+ /* Now remove guard pages. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ /* Now make sure all data is as expected. */
+ if (!check_pattern(ptr, 10, page_size))
+ ASSERT_TRUE(false);
+
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/*
+ * Check that file-backed mappings implement guard regions with MAP_PRIVATE
+ * correctly.
+ */
+TEST_F(guard_regions, map_private)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr_shared, *ptr_private;
+ int i;
+
+ if (variant->backing == ANON_BACKED)
+ SKIP(return, "MAP_PRIVATE test specific to file-backed");
+
+ ptr_shared = mmap_(self, variant, NULL, 10 * page_size, PROT_READ | PROT_WRITE, 0, 0);
+ ASSERT_NE(ptr_shared, MAP_FAILED);
+
+ /* Manually mmap(), do not use mmap_() wrapper so we can force MAP_PRIVATE. */
+ ptr_private = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, self->fd, 0);
+ ASSERT_NE(ptr_private, MAP_FAILED);
+
+ /* Set pattern in shared mapping. */
+ set_pattern(ptr_shared, 10, page_size);
+
+ /* Install guard regions in every other page in the shared mapping. */
+ for (i = 0; i < 10; i += 2) {
+ char *ptr = &ptr_shared[i * page_size];
+
+ ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0);
+ }
+
+ for (i = 0; i < 10; i++) {
+ /* Every even shared page should be guarded. */
+ ASSERT_EQ(try_read_buf(&ptr_shared[i * page_size]), i % 2 != 0);
+ /* Private mappings should always be readable. */
+ ASSERT_TRUE(try_read_buf(&ptr_private[i * page_size]));
+ }
+
+ /* Install guard regions in every other page in the private mapping. */
+ for (i = 0; i < 10; i += 2) {
+ char *ptr = &ptr_private[i * page_size];
+
+ ASSERT_EQ(madvise(ptr, page_size, MADV_GUARD_INSTALL), 0);
+ }
+
+ for (i = 0; i < 10; i++) {
+ /* Every even shared page should be guarded. */
+ ASSERT_EQ(try_read_buf(&ptr_shared[i * page_size]), i % 2 != 0);
+ /* Every odd private page should be guarded. */
+ ASSERT_EQ(try_read_buf(&ptr_private[i * page_size]), i % 2 != 0);
+ }
+
+ /* Remove guard regions from shared mapping. */
+ ASSERT_EQ(madvise(ptr_shared, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ for (i = 0; i < 10; i++) {
+ /* Shared mappings should always be readable. */
+ ASSERT_TRUE(try_read_buf(&ptr_shared[i * page_size]));
+ /* Every even private page should be guarded. */
+ ASSERT_EQ(try_read_buf(&ptr_private[i * page_size]), i % 2 != 0);
+ }
+
+ /* Remove guard regions from private mapping. */
+ ASSERT_EQ(madvise(ptr_private, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ for (i = 0; i < 10; i++) {
+ /* Shared mappings should always be readable. */
+ ASSERT_TRUE(try_read_buf(&ptr_shared[i * page_size]));
+ /* Private mappings should always be readable. */
+ ASSERT_TRUE(try_read_buf(&ptr_private[i * page_size]));
+ }
+
+ /* Ensure patterns are intact. */
+ ASSERT_TRUE(check_pattern(ptr_shared, 10, page_size));
+ ASSERT_TRUE(check_pattern(ptr_private, 10, page_size));
+
+ /* Now write out every other page to MAP_PRIVATE. */
+ for (i = 0; i < 10; i += 2) {
+ char *ptr = &ptr_private[i * page_size];
+
+ memset(ptr, 'a' + i, page_size);
+ }
+
+ /*
+ * At this point the mapping is:
+ *
+ * 0123456789
+ * SPSPSPSPSP
+ *
+ * Where S = shared, P = private mappings.
+ */
+
+ /* Now mark the beginning of the mapping guarded. */
+ ASSERT_EQ(madvise(ptr_private, 5 * page_size, MADV_GUARD_INSTALL), 0);
+
+ /*
+ * This renders the mapping:
+ *
+ * 0123456789
+ * xxxxxPSPSP
+ */
+
+ for (i = 0; i < 10; i++) {
+ char *ptr = &ptr_private[i * page_size];
+
+ /* Ensure guard regions as expected. */
+ ASSERT_EQ(try_read_buf(ptr), i >= 5);
+ /* The shared mapping should always succeed. */
+ ASSERT_TRUE(try_read_buf(&ptr_shared[i * page_size]));
+ }
+
+ /* Remove the guard regions altogether. */
+ ASSERT_EQ(madvise(ptr_private, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ /*
+ *
+ * We now expect the mapping to be:
+ *
+ * 0123456789
+ * SSSSSPSPSP
+ *
+ * As we removed guard regions, the private pages from the first 5 will
+ * have been zapped, so on fault will reestablish the shared mapping.
+ */
+
+ for (i = 0; i < 10; i++) {
+ char *ptr = &ptr_private[i * page_size];
+
+ /*
+ * Assert that shared mappings in the MAP_PRIVATE mapping match
+ * the shared mapping.
+ */
+ if (i < 5 || i % 2 == 0) {
+ char *ptr_s = &ptr_shared[i * page_size];
+
+ ASSERT_EQ(memcmp(ptr, ptr_s, page_size), 0);
+ continue;
+ }
+
+ /* Everything else is a private mapping. */
+ ASSERT_TRUE(is_buf_eq(ptr, page_size, 'a' + i));
+ }
+
+ ASSERT_EQ(munmap(ptr_shared, 10 * page_size), 0);
+ ASSERT_EQ(munmap(ptr_private, 10 * page_size), 0);
+}
+
+/* Test that guard regions established over a read-only mapping function correctly. */
+TEST_F(guard_regions, readonly_file)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ if (variant->backing == ANON_BACKED)
+ SKIP(return, "Read-only test specific to file-backed");
+
+ /* Map shared so we can populate with pattern, populate it, unmap. */
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+ set_pattern(ptr, 10, page_size);
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+ /* Close the fd so we can re-open read-only. */
+ ASSERT_EQ(close(self->fd), 0);
+
+ /* Re-open read-only. */
+ self->fd = open(self->path, O_RDONLY);
+ ASSERT_NE(self->fd, -1);
+ /* Re-map read-only. */
+ ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Mark every other page guarded. */
+ for (i = 0; i < 10; i += 2) {
+ char *ptr_pg = &ptr[i * page_size];
+
+ ASSERT_EQ(madvise(ptr_pg, page_size, MADV_GUARD_INSTALL), 0);
+ }
+
+ /* Assert that the guard regions are in place.*/
+ for (i = 0; i < 10; i++) {
+ char *ptr_pg = &ptr[i * page_size];
+
+ ASSERT_EQ(try_read_buf(ptr_pg), i % 2 != 0);
+ }
+
+ /* Remove guard regions. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ /* Ensure the data is as expected. */
+ ASSERT_TRUE(check_pattern(ptr, 10, page_size));
+
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+TEST_F(guard_regions, fault_around)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ if (variant->backing == ANON_BACKED)
+ SKIP(return, "Fault-around test specific to file-backed");
+
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Establish a pattern in the backing file. */
+ set_pattern(ptr, 10, page_size);
+
+ /*
+ * Now drop it from the page cache so we get major faults when next we
+ * map it.
+ */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_PAGEOUT), 0);
+
+ /* Unmap and remap 'to be sure'. */
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Now make every even page guarded. */
+ for (i = 0; i < 10; i += 2) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(madvise(ptr_p, page_size, MADV_GUARD_INSTALL), 0);
+ }
+
+ /* Now fault in every odd page. This should trigger fault-around. */
+ for (i = 1; i < 10; i += 2) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_buf(ptr_p));
+ }
+
+ /* Finally, ensure that guard regions are intact as expected. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(try_read_buf(ptr_p), i % 2 != 0);
+ }
+
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+TEST_F(guard_regions, truncation)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ if (variant->backing == ANON_BACKED)
+ SKIP(return, "Truncation test specific to file-backed");
+
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /*
+ * Establish a pattern in the backing file, just so there is data
+ * there.
+ */
+ set_pattern(ptr, 10, page_size);
+
+ /* Now make every even page guarded. */
+ for (i = 0; i < 10; i += 2) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(madvise(ptr_p, page_size, MADV_GUARD_INSTALL), 0);
+ }
+
+ /* Now assert things are as expected. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(try_read_write_buf(ptr_p), i % 2 != 0);
+ }
+
+ /* Now truncate to actually used size (initialised to 100). */
+ ASSERT_EQ(ftruncate(self->fd, 10 * page_size), 0);
+
+ /* Here the guard regions will remain intact. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(try_read_write_buf(ptr_p), i % 2 != 0);
+ }
+
+ /* Now truncate to half the size, then truncate again to the full size. */
+ ASSERT_EQ(ftruncate(self->fd, 5 * page_size), 0);
+ ASSERT_EQ(ftruncate(self->fd, 10 * page_size), 0);
+
+ /* Again, guard pages will remain intact. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(try_read_write_buf(ptr_p), i % 2 != 0);
+ }
+
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+TEST_F(guard_regions, hole_punch)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ if (variant->backing == ANON_BACKED)
+ SKIP(return, "Truncation test specific to file-backed");
+
+ /* Establish pattern in mapping. */
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+ set_pattern(ptr, 10, page_size);
+
+ /* Install a guard region in the middle of the mapping. */
+ ASSERT_EQ(madvise(&ptr[3 * page_size], 4 * page_size,
+ MADV_GUARD_INSTALL), 0);
+
+ /*
+ * The buffer will now be:
+ *
+ * 0123456789
+ * ***xxxx***
+ *
+ * Where * is data and x is the guard region.
+ */
+
+ /* Ensure established. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(try_read_buf(ptr_p), i < 3 || i >= 7);
+ }
+
+ /* Now hole punch the guarded region. */
+ ASSERT_EQ(madvise(&ptr[3 * page_size], 4 * page_size,
+ MADV_REMOVE), 0);
+
+ /* Ensure guard regions remain. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(try_read_buf(ptr_p), i < 3 || i >= 7);
+ }
+
+ /* Now remove guard region throughout. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ /* Check that the pattern exists in non-hole punched region. */
+ ASSERT_TRUE(check_pattern(ptr, 3, page_size));
+ /* Check that hole punched region is zeroed. */
+ ASSERT_TRUE(is_buf_eq(&ptr[3 * page_size], 4 * page_size, '\0'));
+ /* Check that the pattern exists in the remainder of the file. */
+ ASSERT_TRUE(check_pattern_offset(ptr, 3, page_size, 7));
+
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/*
+ * Ensure that a memfd works correctly with guard regions, that we can write
+ * seal it then open the mapping read-only and still establish guard regions
+ * within, remove those guard regions and have everything work correctly.
+ */
+TEST_F(guard_regions, memfd_write_seal)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ if (variant->backing != SHMEM_BACKED)
+ SKIP(return, "memfd write seal test specific to shmem");
+
+ /* OK, we need a memfd, so close existing one. */
+ ASSERT_EQ(close(self->fd), 0);
+
+ /* Create and truncate memfd. */
+ self->fd = memfd_create("guard_regions_memfd_seals_test",
+ MFD_ALLOW_SEALING);
+ ASSERT_NE(self->fd, -1);
+ ASSERT_EQ(ftruncate(self->fd, 10 * page_size), 0);
+
+ /* Map, set pattern, unmap. */
+ ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ | PROT_WRITE, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+ set_pattern(ptr, 10, page_size);
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+
+ /* Write-seal the memfd. */
+ ASSERT_EQ(fcntl(self->fd, F_ADD_SEALS, F_SEAL_WRITE), 0);
+
+ /* Now map the memfd readonly. */
+ ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Ensure pattern is as expected. */
+ ASSERT_TRUE(check_pattern(ptr, 10, page_size));
+
+ /* Now make every even page guarded. */
+ for (i = 0; i < 10; i += 2) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(madvise(ptr_p, page_size, MADV_GUARD_INSTALL), 0);
+ }
+
+ /* Now assert things are as expected. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(try_read_buf(ptr_p), i % 2 != 0);
+ }
+
+ /* Now remove guard regions. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ /* Ensure pattern is as expected. */
+ ASSERT_TRUE(check_pattern(ptr, 10, page_size));
+
+ /* Ensure write seal intact. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_FALSE(try_write_buf(ptr_p));
+ }
+
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+
+/*
+ * Since we are now permitted to establish guard regions in read-only anonymous
+ * mappings, for the sake of thoroughness, though it probably has no practical
+ * use, test that guard regions function with a mapping to the anonymous zero
+ * page.
+ */
+TEST_F(guard_regions, anon_zeropage)
+{
+ const unsigned long page_size = self->page_size;
+ char *ptr;
+ int i;
+
+ if (!is_anon_backed(variant))
+ SKIP(return, "anon zero page test specific to anon/shmem");
+
+ /* Obtain a read-only i.e. anon zero page mapping. */
+ ptr = mmap_(self, variant, NULL, 10 * page_size, PROT_READ, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Now make every even page guarded. */
+ for (i = 0; i < 10; i += 2) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(madvise(ptr_p, page_size, MADV_GUARD_INSTALL), 0);
+ }
+
+ /* Now assert things are as expected. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(try_read_buf(ptr_p), i % 2 != 0);
+ }
+
+ /* Now remove all guard regions. */
+ ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0);
+
+ /* Now assert things are as expected. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_TRUE(try_read_buf(ptr_p));
+ }
+
+ /* Ensure zero page...*/
+ ASSERT_TRUE(is_buf_eq(ptr, 10 * page_size, '\0'));
+
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
+/*
+ * Assert that /proc/$pid/pagemap correctly identifies guard region ranges.
+ */
+TEST_F(guard_regions, pagemap)
+{
+ const unsigned long page_size = self->page_size;
+ int proc_fd;
+ char *ptr;
+ int i;
+
+ proc_fd = open("/proc/self/pagemap", O_RDONLY);
+ ASSERT_NE(proc_fd, -1);
+
+ ptr = mmap_(self, variant, NULL, 10 * page_size,
+ PROT_READ | PROT_WRITE, 0, 0);
+ ASSERT_NE(ptr, MAP_FAILED);
+
+ /* Read from pagemap, and assert no guard regions are detected. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+ unsigned long entry = pagemap_get_entry(proc_fd, ptr_p);
+ unsigned long masked = entry & PM_GUARD_REGION;
+
+ ASSERT_EQ(masked, 0);
+ }
+
+ /* Install a guard region in every other page. */
+ for (i = 0; i < 10; i += 2) {
+ char *ptr_p = &ptr[i * page_size];
+
+ ASSERT_EQ(madvise(ptr_p, page_size, MADV_GUARD_INSTALL), 0);
+ }
+
+ /* Re-read from pagemap, and assert guard regions are detected. */
+ for (i = 0; i < 10; i++) {
+ char *ptr_p = &ptr[i * page_size];
+ unsigned long entry = pagemap_get_entry(proc_fd, ptr_p);
+ unsigned long masked = entry & PM_GUARD_REGION;
+
+ ASSERT_EQ(masked, i % 2 == 0 ? PM_GUARD_REGION : 0);
+ }
+
+ ASSERT_EQ(close(proc_fd), 0);
+ ASSERT_EQ(munmap(ptr, 10 * page_size), 0);
+}
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c
index 9423ad439a61..21595b20bbc3 100644
--- a/tools/testing/selftests/mm/gup_longterm.c
+++ b/tools/testing/selftests/mm/gup_longterm.c
@@ -96,13 +96,17 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
int ret;
if (ftruncate(fd, size)) {
- ksft_test_result_fail("ftruncate() failed\n");
+ if (errno == ENOENT) {
+ skip_test_dodgy_fs("ftruncate()");
+ } else {
+ ksft_test_result_fail("ftruncate() failed (%s)\n", strerror(errno));
+ }
return;
}
if (fallocate(fd, 0, 0, size)) {
if (size == pagesize)
- ksft_test_result_fail("fallocate() failed\n");
+ ksft_test_result_fail("fallocate() failed (%s)\n", strerror(errno));
else
ksft_test_result_skip("need more free huge pages\n");
return;
@@ -112,7 +116,7 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
shared ? MAP_SHARED : MAP_PRIVATE, fd, 0);
if (mem == MAP_FAILED) {
if (size == pagesize || shared)
- ksft_test_result_fail("mmap() failed\n");
+ ksft_test_result_fail("mmap() failed (%s)\n", strerror(errno));
else
ksft_test_result_skip("need more free huge pages\n");
return;
@@ -130,7 +134,7 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
*/
ret = mprotect(mem, size, PROT_READ);
if (ret) {
- ksft_test_result_fail("mprotect() failed\n");
+ ksft_test_result_fail("mprotect() failed (%s)\n", strerror(errno));
goto munmap;
}
/* FALLTHROUGH */
@@ -165,18 +169,20 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
args.flags |= rw ? PIN_LONGTERM_TEST_FLAG_USE_WRITE : 0;
ret = ioctl(gup_fd, PIN_LONGTERM_TEST_START, &args);
if (ret && errno == EINVAL) {
- ksft_test_result_skip("PIN_LONGTERM_TEST_START failed\n");
+ ksft_test_result_skip("PIN_LONGTERM_TEST_START failed (EINVAL)n");
break;
} else if (ret && errno == EFAULT) {
ksft_test_result(!should_work, "Should have failed\n");
break;
} else if (ret) {
- ksft_test_result_fail("PIN_LONGTERM_TEST_START failed\n");
+ ksft_test_result_fail("PIN_LONGTERM_TEST_START failed (%s)\n",
+ strerror(errno));
break;
}
if (ioctl(gup_fd, PIN_LONGTERM_TEST_STOP))
- ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed\n");
+ ksft_print_msg("[INFO] PIN_LONGTERM_TEST_STOP failed (%s)\n",
+ strerror(errno));
/*
* TODO: if the kernel ever supports long-term R/W pinning on
@@ -202,7 +208,8 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
/* Skip on errors, as we might just lack kernel support. */
ret = io_uring_queue_init(1, &ring, 0);
if (ret < 0) {
- ksft_test_result_skip("io_uring_queue_init() failed\n");
+ ksft_test_result_skip("io_uring_queue_init() failed (%s)\n",
+ strerror(-ret));
break;
}
/*
@@ -215,13 +222,15 @@ static void do_test(int fd, size_t size, enum test_type type, bool shared)
/* Only new kernels return EFAULT. */
if (ret && (errno == ENOSPC || errno == EOPNOTSUPP ||
errno == EFAULT)) {
- ksft_test_result(!should_work, "Should have failed\n");
+ ksft_test_result(!should_work, "Should have failed (%s)\n",
+ strerror(errno));
} else if (ret) {
/*
* We might just lack support or have insufficient
* MEMLOCK limits.
*/
- ksft_test_result_skip("io_uring_register_buffers() failed\n");
+ ksft_test_result_skip("io_uring_register_buffers() failed (%s)\n",
+ strerror(-ret));
} else {
ksft_test_result(should_work, "Should have worked\n");
io_uring_unregister_buffers(&ring);
@@ -249,7 +258,7 @@ static void run_with_memfd(test_fn fn, const char *desc)
fd = memfd_create("test", 0);
if (fd < 0) {
- ksft_test_result_fail("memfd_create() failed\n");
+ ksft_test_result_fail("memfd_create() failed (%s)\n", strerror(errno));
return;
}
@@ -266,13 +275,13 @@ static void run_with_tmpfile(test_fn fn, const char *desc)
file = tmpfile();
if (!file) {
- ksft_test_result_fail("tmpfile() failed\n");
+ ksft_test_result_fail("tmpfile() failed (%s)\n", strerror(errno));
return;
}
fd = fileno(file);
if (fd < 0) {
- ksft_test_result_fail("fileno() failed\n");
+ ksft_test_result_fail("fileno() failed (%s)\n", strerror(errno));
goto close;
}
@@ -290,12 +299,12 @@ static void run_with_local_tmpfile(test_fn fn, const char *desc)
fd = mkstemp(filename);
if (fd < 0) {
- ksft_test_result_fail("mkstemp() failed\n");
+ ksft_test_result_fail("mkstemp() failed (%s)\n", strerror(errno));
return;
}
if (unlink(filename)) {
- ksft_test_result_fail("unlink() failed\n");
+ ksft_test_result_fail("unlink() failed (%s)\n", strerror(errno));
goto close;
}
@@ -317,7 +326,7 @@ static void run_with_memfd_hugetlb(test_fn fn, const char *desc,
fd = memfd_create("test", flags);
if (fd < 0) {
- ksft_test_result_skip("memfd_create() failed\n");
+ ksft_test_result_skip("memfd_create() failed (%s)\n", strerror(errno));
return;
}
diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
index 11f9bbe7dc22..0b0d4ba1af27 100755
--- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
+++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh
@@ -23,7 +23,7 @@ fi
if [[ $cgroup2 ]]; then
CGROUP_ROOT=$(mount -t cgroup2 | head -1 | awk '{print $3}')
if [[ -z "$CGROUP_ROOT" ]]; then
- CGROUP_ROOT=/dev/cgroup/memory
+ CGROUP_ROOT=$(mktemp -d)
mount -t cgroup2 none $CGROUP_ROOT
do_umount=1
fi
diff --git a/tools/testing/selftests/mm/map_populate.c b/tools/testing/selftests/mm/map_populate.c
index 5c8a53869b1b..9df2636c829b 100644
--- a/tools/testing/selftests/mm/map_populate.c
+++ b/tools/testing/selftests/mm/map_populate.c
@@ -18,6 +18,8 @@
#include <unistd.h>
#include "../kselftest.h"
+#include "vm_util.h"
+
#define MMAP_SZ 4096
#define BUG_ON(condition, description) \
@@ -87,6 +89,9 @@ int main(int argc, char **argv)
BUG_ON(!ftmp, "tmpfile()");
ret = ftruncate(fileno(ftmp), MMAP_SZ);
+ if (ret < 0 && errno == ENOENT) {
+ skip_test_dodgy_fs("ftruncate()");
+ }
BUG_ON(ret, "ftruncate()");
smap = mmap(0, MMAP_SZ, PROT_READ | PROT_WRITE,
diff --git a/tools/testing/selftests/mm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c
index 1cd80b0f76c3..b8d7e966f44c 100644
--- a/tools/testing/selftests/mm/mlock-random-test.c
+++ b/tools/testing/selftests/mm/mlock-random-test.c
@@ -161,9 +161,9 @@ static void test_mlock_within_limit(char *p, int alloc_size)
MLOCK_ONFAULT);
if (ret)
- ksft_exit_fail_msg("%s() failure at |%p(%d)| mlock:|%p(%d)|\n",
+ ksft_exit_fail_msg("%s() failure (%s) at |%p(%d)| mlock:|%p(%d)|\n",
is_mlock ? "mlock" : "mlock2",
- p, alloc_size,
+ strerror(errno), p, alloc_size,
p + start_offset, lock_size);
}
diff --git a/tools/testing/selftests/mm/mlock2.h b/tools/testing/selftests/mm/mlock2.h
index 4417eaa5cfb7..81e77fa41901 100644
--- a/tools/testing/selftests/mm/mlock2.h
+++ b/tools/testing/selftests/mm/mlock2.h
@@ -6,7 +6,13 @@
static int mlock2_(void *start, size_t len, int flags)
{
- return syscall(__NR_mlock2, start, len, flags);
+ int ret = syscall(__NR_mlock2, start, len, flags);
+
+ if (ret) {
+ errno = ret;
+ return -1;
+ }
+ return 0;
}
static FILE *seek_to_smaps_entry(unsigned long addr)
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 7cc71d942f83..9aff33b10999 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -187,9 +187,10 @@ if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then
printf "Not enough huge pages available (%d < %d)\n" \
"$freepgs" "$needpgs"
fi
+ HAVE_HUGEPAGES=1
else
echo "no hugetlbfs support in kernel?"
- exit 1
+ HAVE_HUGEPAGES=0
fi
# filter 64bit architectures
@@ -218,13 +219,20 @@ pretty_name() {
# Usage: run_test [test binary] [arbitrary test arguments...]
run_test() {
if test_selected ${CATEGORY}; then
+ local skip=0
+
# On memory constrainted systems some tests can fail to allocate hugepages.
# perform some cleanup before the test for a higher success rate.
if [ ${CATEGORY} == "thp" -o ${CATEGORY} == "hugetlb" ]; then
- echo 3 > /proc/sys/vm/drop_caches
- sleep 2
- echo 1 > /proc/sys/vm/compact_memory
- sleep 2
+ if [ "${HAVE_HUGEPAGES}" = "1" ]; then
+ echo 3 > /proc/sys/vm/drop_caches
+ sleep 2
+ echo 1 > /proc/sys/vm/compact_memory
+ sleep 2
+ else
+ echo "hugepages not supported" | tap_prefix
+ skip=1
+ fi
fi
local test=$(pretty_name "$*")
@@ -232,8 +240,12 @@ run_test() {
local sep=$(echo -n "$title" | tr "[:graph:][:space:]" -)
printf "%s\n%s\n%s\n" "$sep" "$title" "$sep" | tap_prefix
- ("$@" 2>&1) | tap_prefix
- local ret=${PIPESTATUS[0]}
+ if [ "${skip}" != "1" ]; then
+ ("$@" 2>&1) | tap_prefix
+ local ret=${PIPESTATUS[0]}
+ else
+ local ret=$ksft_skip
+ fi
count_total=$(( count_total + 1 ))
if [ $ret -eq 0 ]; then
count_pass=$(( count_pass + 1 ))
@@ -271,13 +283,15 @@ CATEGORY="hugetlb" run_test ./hugepage-vmemmap
CATEGORY="hugetlb" run_test ./hugetlb-madvise
CATEGORY="hugetlb" run_test ./hugetlb_dio
-nr_hugepages_tmp=$(cat /proc/sys/vm/nr_hugepages)
-# For this test, we need one and just one huge page
-echo 1 > /proc/sys/vm/nr_hugepages
-CATEGORY="hugetlb" run_test ./hugetlb_fault_after_madv
-CATEGORY="hugetlb" run_test ./hugetlb_madv_vs_map
-# Restore the previous number of huge pages, since further tests rely on it
-echo "$nr_hugepages_tmp" > /proc/sys/vm/nr_hugepages
+if [ "${HAVE_HUGEPAGES}" = "1" ]; then
+ nr_hugepages_tmp=$(cat /proc/sys/vm/nr_hugepages)
+ # For this test, we need one and just one huge page
+ echo 1 > /proc/sys/vm/nr_hugepages
+ CATEGORY="hugetlb" run_test ./hugetlb_fault_after_madv
+ CATEGORY="hugetlb" run_test ./hugetlb_madv_vs_map
+ # Restore the previous number of huge pages, since further tests rely on it
+ echo "$nr_hugepages_tmp" > /proc/sys/vm/nr_hugepages
+fi
if test_selected "hugetlb"; then
echo "NOTE: These hugetlb tests provide minimal coverage. Use" | tap_prefix
@@ -311,14 +325,35 @@ CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 3
CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32
CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16
CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem-private 20 16
-CATEGORY="userfaultfd" run_test ./uffd-wp-mremap
+# uffd-wp-mremap requires at least one page of each size.
+have_all_size_hugepgs=true
+declare -A nr_size_hugepgs
+for f in /sys/kernel/mm/hugepages/**/nr_hugepages; do
+ old=$(cat $f)
+ nr_size_hugepgs["$f"]="$old"
+ if [ "$old" == 0 ]; then
+ echo 1 > "$f"
+ fi
+ if [ $(cat "$f") == 0 ]; then
+ have_all_size_hugepgs=false
+ break
+ fi
+done
+if $have_all_size_hugepgs; then
+ CATEGORY="userfaultfd" run_test ./uffd-wp-mremap
+else
+ echo "# SKIP ./uffd-wp-mremap"
+fi
#cleanup
+for f in "${!nr_size_hugepgs[@]}"; do
+ echo "${nr_size_hugepgs["$f"]}" > "$f"
+done
echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages
CATEGORY="compaction" run_test ./compaction_test
-if command -v sudo &> /dev/null;
+if command -v sudo &> /dev/null && sudo -u nobody ls ./on-fault-limit >/dev/null;
then
CATEGORY="mlock" run_test sudo -u nobody ./on-fault-limit
else
@@ -381,19 +416,21 @@ CATEGORY="mremap" run_test ./mremap_dontunmap
CATEGORY="hmm" run_test bash ./test_hmm.sh smoke
# MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests
-CATEGORY="madv_guard" run_test ./guard-pages
+CATEGORY="madv_guard" run_test ./guard-regions
# MADV_POPULATE_READ and MADV_POPULATE_WRITE tests
CATEGORY="madv_populate" run_test ./madv_populate
if [ -x ./memfd_secret ]
then
-(echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix
+(echo 0 > /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix
CATEGORY="memfd_secret" run_test ./memfd_secret
fi
# KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100
-CATEGORY="ksm" run_test ./ksm_tests -H -s 100
+if [ "${HAVE_HUGEPAGES}" = "1" ]; then
+ CATEGORY="ksm" run_test ./ksm_tests -H -s 100
+fi
# KSM KSM_MERGE_TIME test with size of 100
CATEGORY="ksm" run_test ./ksm_tests -P -s 100
# KSM MADV_MERGEABLE test with 10 identical pages
@@ -442,15 +479,17 @@ CATEGORY="thp" run_test ./transhuge-stress -d 20
# Try to create XFS if not provided
if [ -z "${SPLIT_HUGE_PAGE_TEST_XFS_PATH}" ]; then
- if test_selected "thp"; then
- if grep xfs /proc/filesystems &>/dev/null; then
- XFS_IMG=$(mktemp /tmp/xfs_img_XXXXXX)
- SPLIT_HUGE_PAGE_TEST_XFS_PATH=$(mktemp -d /tmp/xfs_dir_XXXXXX)
- truncate -s 314572800 ${XFS_IMG}
- mkfs.xfs -q ${XFS_IMG}
- mount -o loop ${XFS_IMG} ${SPLIT_HUGE_PAGE_TEST_XFS_PATH}
- MOUNTED_XFS=1
- fi
+ if [ "${HAVE_HUGEPAGES}" = "1" ]; then
+ if test_selected "thp"; then
+ if grep xfs /proc/filesystems &>/dev/null; then
+ XFS_IMG=$(mktemp /tmp/xfs_img_XXXXXX)
+ SPLIT_HUGE_PAGE_TEST_XFS_PATH=$(mktemp -d /tmp/xfs_dir_XXXXXX)
+ truncate -s 314572800 ${XFS_IMG}
+ mkfs.xfs -q ${XFS_IMG}
+ mount -o loop ${XFS_IMG} ${SPLIT_HUGE_PAGE_TEST_XFS_PATH}
+ MOUNTED_XFS=1
+ fi
+ fi
fi
fi
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index 3f353f3d070f..aa7400ed0e99 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -5,6 +5,7 @@
*/
#define _GNU_SOURCE
+#include <assert.h>
#include <stdio.h>
#include <stdlib.h>
#include <stdarg.h>
@@ -14,6 +15,7 @@
#include <fcntl.h>
#include <sys/mman.h>
#include <sys/mount.h>
+#include <sys/param.h>
#include <malloc.h>
#include <stdbool.h>
#include <time.h>
@@ -261,18 +263,32 @@ void split_pte_mapped_thp(void)
close(kpageflags_fd);
}
-void split_file_backed_thp(void)
+void split_file_backed_thp(int order)
{
int status;
int fd;
- ssize_t num_written;
char tmpfs_template[] = "/tmp/thp_split_XXXXXX";
const char *tmpfs_loc = mkdtemp(tmpfs_template);
char testfile[INPUT_MAX];
+ ssize_t num_written, num_read;
+ char *file_buf1, *file_buf2;
uint64_t pgoff_start = 0, pgoff_end = 1024;
+ int i;
ksft_print_msg("Please enable pr_debug in split_huge_pages_in_file() for more info.\n");
+ file_buf1 = (char *)malloc(pmd_pagesize);
+ file_buf2 = (char *)malloc(pmd_pagesize);
+
+ if (!file_buf1 || !file_buf2) {
+ ksft_print_msg("cannot allocate file buffers\n");
+ goto out;
+ }
+
+ for (i = 0; i < pmd_pagesize; i++)
+ file_buf1[i] = (char)i;
+ memset(file_buf2, 0, pmd_pagesize);
+
status = mount("tmpfs", tmpfs_loc, "tmpfs", 0, "huge=always,size=4m");
if (status)
@@ -281,26 +297,45 @@ void split_file_backed_thp(void)
status = snprintf(testfile, INPUT_MAX, "%s/thp_file", tmpfs_loc);
if (status >= INPUT_MAX) {
ksft_exit_fail_msg("Fail to create file-backed THP split testing file\n");
+ goto cleanup;
}
- fd = open(testfile, O_CREAT|O_WRONLY, 0664);
+ fd = open(testfile, O_CREAT|O_RDWR, 0664);
if (fd == -1) {
ksft_perror("Cannot open testing file");
goto cleanup;
}
- /* write something to the file, so a file-backed THP can be allocated */
- num_written = write(fd, tmpfs_loc, strlen(tmpfs_loc) + 1);
- close(fd);
+ /* write pmd size data to the file, so a file-backed THP can be allocated */
+ num_written = write(fd, file_buf1, pmd_pagesize);
- if (num_written < 1) {
- ksft_perror("Fail to write data to testing file");
- goto cleanup;
+ if (num_written == -1 || num_written != pmd_pagesize) {
+ ksft_perror("Failed to write data to testing file");
+ goto close_file;
}
/* split the file-backed THP */
- write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end, 0);
+ write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end, order);
+
+ /* check file content after split */
+ status = lseek(fd, 0, SEEK_SET);
+ if (status == -1) {
+ ksft_perror("Cannot lseek file");
+ goto close_file;
+ }
+
+ num_read = read(fd, file_buf2, num_written);
+ if (num_read == -1 || num_read != num_written) {
+ ksft_perror("Cannot read file content back");
+ goto close_file;
+ }
+
+ if (strncmp(file_buf1, file_buf2, pmd_pagesize) != 0) {
+ ksft_print_msg("File content changed\n");
+ goto close_file;
+ }
+ close(fd);
status = unlink(testfile);
if (status) {
ksft_perror("Cannot remove testing file");
@@ -318,12 +353,15 @@ void split_file_backed_thp(void)
ksft_exit_fail_msg("cannot remove tmp dir: %s\n", strerror(errno));
ksft_print_msg("Please check dmesg for more information\n");
- ksft_test_result_pass("File-backed THP split test done\n");
+ ksft_test_result_pass("File-backed THP split to order %d test done\n", order);
return;
+close_file:
+ close(fd);
cleanup:
umount(tmpfs_loc);
rmdir(tmpfs_loc);
+out:
ksft_exit_fail_msg("Error occurred\n");
}
@@ -361,6 +399,7 @@ int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd,
{
size_t i;
int dummy = 0;
+ unsigned char buf[1024];
srand(time(NULL));
@@ -368,11 +407,12 @@ int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd,
if (*fd == -1)
ksft_exit_fail_msg("Failed to create a file at %s\n", testfile);
- for (i = 0; i < fd_size; i++) {
- unsigned char byte = (unsigned char)i;
+ assert(fd_size % sizeof(buf) == 0);
+ for (i = 0; i < sizeof(buf); i++)
+ buf[i] = (unsigned char)i;
+ for (i = 0; i < fd_size; i += sizeof(buf))
+ write(*fd, buf, sizeof(buf));
- write(*fd, &byte, sizeof(byte));
- }
close(*fd);
sync();
*fd = open("/proc/sys/vm/drop_caches", O_WRONLY);
@@ -420,7 +460,8 @@ err_out_unlink:
return -1;
}
-void split_thp_in_pagecache_to_order(size_t fd_size, int order, const char *fs_loc)
+void split_thp_in_pagecache_to_order_at(size_t fd_size, const char *fs_loc,
+ int order, int offset)
{
int fd;
char *addr;
@@ -438,7 +479,12 @@ void split_thp_in_pagecache_to_order(size_t fd_size, int order, const char *fs_l
return;
err = 0;
- write_debugfs(PID_FMT, getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order);
+ if (offset == -1)
+ write_debugfs(PID_FMT, getpid(), (uint64_t)addr,
+ (uint64_t)addr + fd_size, order);
+ else
+ write_debugfs(PID_FMT, getpid(), (uint64_t)addr,
+ (uint64_t)addr + fd_size, order, offset);
for (i = 0; i < fd_size; i++)
if (*(addr + i) != (char)i) {
@@ -457,9 +503,15 @@ out:
munmap(addr, fd_size);
close(fd);
unlink(testfile);
- if (err)
- ksft_exit_fail_msg("Split PMD-mapped pagecache folio to order %d failed\n", order);
- ksft_test_result_pass("Split PMD-mapped pagecache folio to order %d passed\n", order);
+ if (offset == -1) {
+ if (err)
+ ksft_exit_fail_msg("Split PMD-mapped pagecache folio to order %d failed\n", order);
+ ksft_test_result_pass("Split PMD-mapped pagecache folio to order %d passed\n", order);
+ } else {
+ if (err)
+ ksft_exit_fail_msg("Split PMD-mapped pagecache folio to order %d at in-folio offset %d failed\n", order, offset);
+ ksft_test_result_pass("Split PMD-mapped pagecache folio to order %d at in-folio offset %d passed\n", order, offset);
+ }
}
int main(int argc, char **argv)
@@ -470,6 +522,7 @@ int main(int argc, char **argv)
char fs_loc_template[] = "/tmp/thp_fs_XXXXXX";
const char *fs_loc;
bool created_tmp;
+ int offset;
ksft_print_header();
@@ -481,7 +534,7 @@ int main(int argc, char **argv)
if (argc > 1)
optional_xfs_path = argv[1];
- ksft_set_plan(1+8+2+9);
+ ksft_set_plan(1+8+1+9+9+8*4+2);
pagesize = getpagesize();
pageshift = ffs(pagesize) - 1;
@@ -498,12 +551,19 @@ int main(int argc, char **argv)
split_pmd_thp_to_order(i);
split_pte_mapped_thp();
- split_file_backed_thp();
+ for (i = 0; i < 9; i++)
+ split_file_backed_thp(i);
created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template,
&fs_loc);
for (i = 8; i >= 0; i--)
- split_thp_in_pagecache_to_order(fd_size, i, fs_loc);
+ split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, -1);
+
+ for (i = 0; i < 9; i++)
+ for (offset = 0;
+ offset < pmd_pagesize / pagesize;
+ offset += MAX(pmd_pagesize / pagesize / 4, 1 << i))
+ split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, offset);
cleanup_thp_fs(fs_loc, created_tmp);
ksft_finished();
diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c
index e4370b79b62f..cd5174d735be 100644
--- a/tools/testing/selftests/mm/thuge-gen.c
+++ b/tools/testing/selftests/mm/thuge-gen.c
@@ -127,7 +127,7 @@ void test_mmap(unsigned long size, unsigned flags)
show(size);
ksft_test_result(size == getpagesize() || (before - after) == NUM_PAGES,
- "%s mmap\n", __func__);
+ "%s mmap %lu\n", __func__, size);
if (munmap(map, size * NUM_PAGES))
ksft_exit_fail_msg("%s: unmap %s\n", __func__, strerror(errno));
@@ -165,7 +165,7 @@ void test_shmget(unsigned long size, unsigned flags)
show(size);
ksft_test_result(size == getpagesize() || (before - after) == NUM_PAGES,
- "%s: mmap\n", __func__);
+ "%s: mmap %lu\n", __func__, size);
if (shmdt(map))
ksft_exit_fail_msg("%s: shmdt: %s\n", __func__, strerror(errno));
}
diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
index 7ad6ba660c7d..a37088a23ffe 100644
--- a/tools/testing/selftests/mm/uffd-common.c
+++ b/tools/testing/selftests/mm/uffd-common.c
@@ -10,7 +10,7 @@
#define BASE_PMD_ADDR ((void *)(1UL << 30))
volatile bool test_uffdio_copy_eexist = true;
-unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
+unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size;
char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap;
int uffd = -1, uffd_flags, finished, *pipefd, test_type;
bool map_shared;
@@ -269,7 +269,7 @@ void uffd_test_ctx_clear(void)
size_t i;
if (pipefd) {
- for (i = 0; i < nr_cpus * 2; ++i) {
+ for (i = 0; i < nr_parallel * 2; ++i) {
if (close(pipefd[i]))
err("close pipefd");
}
@@ -323,7 +323,7 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg)
ret = userfaultfd_open(&features);
if (ret) {
if (errmsg)
- *errmsg = "possible lack of priviledge";
+ *errmsg = "possible lack of privilege";
return ret;
}
@@ -348,7 +348,7 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg)
/*
* After initialization of area_src, we must explicitly release pages
* for area_dst to make sure it's fully empty. Otherwise we could have
- * some area_dst pages be errornously initialized with zero pages,
+ * some area_dst pages be erroneously initialized with zero pages,
* hence we could hit memory corruption later in the test.
*
* One example is when THP is globally enabled, above allocate_area()
@@ -365,10 +365,10 @@ int uffd_test_ctx_init(uint64_t features, const char **errmsg)
*/
uffd_test_ops->release_pages(area_dst);
- pipefd = malloc(sizeof(int) * nr_cpus * 2);
+ pipefd = malloc(sizeof(int) * nr_parallel * 2);
if (!pipefd)
err("pipefd");
- for (cpu = 0; cpu < nr_cpus; cpu++)
+ for (cpu = 0; cpu < nr_parallel; cpu++)
if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK))
err("pipe");
diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h
index a70ae10b5f62..7700cbfa3975 100644
--- a/tools/testing/selftests/mm/uffd-common.h
+++ b/tools/testing/selftests/mm/uffd-common.h
@@ -98,7 +98,7 @@ struct uffd_test_case_ops {
};
typedef struct uffd_test_case_ops uffd_test_case_ops_t;
-extern unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
+extern unsigned long nr_parallel, nr_pages, nr_pages_per_cpu, page_size;
extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap;
extern int uffd, uffd_flags, finished, *pipefd, test_type;
extern bool map_shared;
diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c
index 944d559ade21..40af7f67c407 100644
--- a/tools/testing/selftests/mm/uffd-stress.c
+++ b/tools/testing/selftests/mm/uffd-stress.c
@@ -180,12 +180,12 @@ static void *background_thread(void *arg)
static int stress(struct uffd_args *args)
{
unsigned long cpu;
- pthread_t locking_threads[nr_cpus];
- pthread_t uffd_threads[nr_cpus];
- pthread_t background_threads[nr_cpus];
+ pthread_t locking_threads[nr_parallel];
+ pthread_t uffd_threads[nr_parallel];
+ pthread_t background_threads[nr_parallel];
finished = 0;
- for (cpu = 0; cpu < nr_cpus; cpu++) {
+ for (cpu = 0; cpu < nr_parallel; cpu++) {
if (pthread_create(&locking_threads[cpu], &attr,
locking_thread, (void *)cpu))
return 1;
@@ -203,7 +203,7 @@ static int stress(struct uffd_args *args)
background_thread, (void *)cpu))
return 1;
}
- for (cpu = 0; cpu < nr_cpus; cpu++)
+ for (cpu = 0; cpu < nr_parallel; cpu++)
if (pthread_join(background_threads[cpu], NULL))
return 1;
@@ -219,11 +219,11 @@ static int stress(struct uffd_args *args)
uffd_test_ops->release_pages(area_src);
finished = 1;
- for (cpu = 0; cpu < nr_cpus; cpu++)
+ for (cpu = 0; cpu < nr_parallel; cpu++)
if (pthread_join(locking_threads[cpu], NULL))
return 1;
- for (cpu = 0; cpu < nr_cpus; cpu++) {
+ for (cpu = 0; cpu < nr_parallel; cpu++) {
char c;
if (bounces & BOUNCE_POLL) {
if (write(pipefd[cpu*2+1], &c, 1) != 1)
@@ -246,11 +246,11 @@ static int userfaultfd_stress(void)
{
void *area;
unsigned long nr;
- struct uffd_args args[nr_cpus];
+ struct uffd_args args[nr_parallel];
uint64_t mem_size = nr_pages * page_size;
int flags = 0;
- memset(args, 0, sizeof(struct uffd_args) * nr_cpus);
+ memset(args, 0, sizeof(struct uffd_args) * nr_parallel);
if (features & UFFD_FEATURE_WP_UNPOPULATED && test_type == TEST_ANON)
flags = UFFD_FEATURE_WP_UNPOPULATED;
@@ -325,7 +325,7 @@ static int userfaultfd_stress(void)
*/
uffd_test_ops->release_pages(area_dst);
- uffd_stats_reset(args, nr_cpus);
+ uffd_stats_reset(args, nr_parallel);
/* bounce pass */
if (stress(args)) {
@@ -359,7 +359,7 @@ static int userfaultfd_stress(void)
swap(area_src_alias, area_dst_alias);
- uffd_stats_report(args, nr_cpus);
+ uffd_stats_report(args, nr_parallel);
}
uffd_test_ctx_clear();
@@ -412,8 +412,8 @@ static void parse_test_type_arg(const char *raw_type)
* feature.
*/
- if (uffd_get_features(&features))
- err("failed to get available features");
+ if (uffd_get_features(&features) && errno == ENOENT)
+ ksft_exit_skip("failed to get available features (%d)\n", errno);
test_uffdio_wp = test_uffdio_wp &&
(features & UFFD_FEATURE_PAGEFAULT_FLAG_WP);
@@ -435,6 +435,7 @@ static void sigalrm(int sig)
int main(int argc, char **argv)
{
+ unsigned long nr_cpus;
size_t bytes;
if (argc < 4)
@@ -454,10 +455,19 @@ int main(int argc, char **argv)
}
nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+ if (nr_cpus > 32) {
+ /* Don't let calculation below go to zero. */
+ ksft_print_msg("_SC_NPROCESSORS_ONLN (%lu) too large, capping nr_threads to 32\n",
+ nr_cpus);
+ nr_parallel = 32;
+ } else {
+ nr_parallel = nr_cpus;
+ }
- nr_pages_per_cpu = bytes / page_size / nr_cpus;
+ nr_pages_per_cpu = bytes / page_size / nr_parallel;
if (!nr_pages_per_cpu) {
- _err("invalid MiB");
+ _err("pages_per_cpu = 0, cannot test (%lu / %lu / %lu)",
+ bytes, page_size, nr_parallel);
usage();
}
@@ -466,7 +476,7 @@ int main(int argc, char **argv)
_err("invalid bounces");
usage();
}
- nr_pages = nr_pages_per_cpu * nr_cpus;
+ nr_pages = nr_pages_per_cpu * nr_parallel;
printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n",
nr_pages, nr_pages_per_cpu);
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index 74c8bc02b506..e8fd9011c2a3 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -26,6 +26,8 @@
#define ALIGN_UP(x, align_to) \
((__typeof__(x))((((unsigned long)(x)) + ((align_to)-1)) & ~((align_to)-1)))
+#define MAX(a, b) (((a) > (b)) ? (a) : (b))
+
struct mem_type {
const char *name;
unsigned int mem_flag;
@@ -196,9 +198,10 @@ uffd_setup_environment(uffd_test_args_t *args, uffd_test_case_t *test,
else
page_size = psize();
- nr_pages = UFFD_TEST_MEM_SIZE / page_size;
+ /* Ensure we have at least 2 pages */
+ nr_pages = MAX(UFFD_TEST_MEM_SIZE, page_size * 2) / page_size;
/* TODO: remove this global var.. it's so ugly */
- nr_cpus = 1;
+ nr_parallel = 1;
/* Initialize test arguments */
args->mem_type = mem_type;
diff --git a/tools/testing/selftests/mm/uffd-wp-mremap.c b/tools/testing/selftests/mm/uffd-wp-mremap.c
index 2c4f984bd73c..c2ba7d46c7b4 100644
--- a/tools/testing/selftests/mm/uffd-wp-mremap.c
+++ b/tools/testing/selftests/mm/uffd-wp-mremap.c
@@ -182,7 +182,10 @@ static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb
/* Register range for uffd-wp. */
if (userfaultfd_open(&features)) {
- ksft_test_result_fail("userfaultfd_open() failed\n");
+ if (errno == ENOENT)
+ ksft_test_result_skip("userfaultfd not available\n");
+ else
+ ksft_test_result_fail("userfaultfd_open() failed\n");
goto out;
}
if (uffd_register(uffd, mem, size, false, true, false)) {
diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh
index 2c725773cd79..1f92e8caceac 100755
--- a/tools/testing/selftests/mm/va_high_addr_switch.sh
+++ b/tools/testing/selftests/mm/va_high_addr_switch.sh
@@ -41,6 +41,31 @@ check_supported_x86_64()
fi
}
+check_supported_ppc64()
+{
+ local config="/proc/config.gz"
+ [[ -f "${config}" ]] || config="/boot/config-$(uname -r)"
+ [[ -f "${config}" ]] || fail "Cannot find kernel config in /proc or /boot"
+
+ local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2)
+ if [[ "${pg_table_levels}" -lt 5 ]]; then
+ echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test"
+ exit $ksft_skip
+ fi
+
+ local mmu_support=$(grep -m1 "mmu" /proc/cpuinfo | awk '{print $3}')
+ if [[ "$mmu_support" != "radix" ]]; then
+ echo "$0: System does not use Radix MMU, required for 5-level paging"
+ exit $ksft_skip
+ fi
+
+ local hugepages_total=$(awk '/HugePages_Total/ {print $2}' /proc/meminfo)
+ if [[ "${hugepages_total}" -eq 0 ]]; then
+ echo "$0: HugePages are not enabled, required for some tests"
+ exit $ksft_skip
+ fi
+}
+
check_test_requirements()
{
# The test supports x86_64 and powerpc64. We currently have no useful
@@ -50,6 +75,9 @@ check_test_requirements()
"x86_64")
check_supported_x86_64
;;
+ "ppc64le"|"ppc64")
+ check_supported_ppc64
+ ;;
*)
return 0
;;
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index b60ac68a9dc8..6effafdc4d8a 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -5,11 +5,13 @@
#include <err.h>
#include <strings.h> /* ffsl() */
#include <unistd.h> /* _SC_PAGESIZE */
+#include "../kselftest.h"
#define BIT_ULL(nr) (1ULL << (nr))
#define PM_SOFT_DIRTY BIT_ULL(55)
#define PM_MMAP_EXCLUSIVE BIT_ULL(56)
#define PM_UFFD_WP BIT_ULL(57)
+#define PM_GUARD_REGION BIT_ULL(58)
#define PM_FILE BIT_ULL(61)
#define PM_SWAP BIT_ULL(62)
#define PM_PRESENT BIT_ULL(63)
@@ -31,6 +33,23 @@ static inline unsigned int pshift(void)
return __page_shift;
}
+/*
+ * Plan 9 FS has bugs (at least on QEMU) where certain operations fail with
+ * ENOENT on unlinked files. See
+ * https://gitlab.com/qemu-project/qemu/-/issues/103 for some info about such
+ * bugs. There are rumours of NFS implementations with similar bugs.
+ *
+ * Ideally, tests should just detect filesystems known to have such issues and
+ * bail early. But 9pfs has the additional "feature" that it causes fstatfs to
+ * pass through the f_type field from the host filesystem. To avoid having to
+ * scrape /proc/mounts or some other hackery, tests can call this function when
+ * it seems such a bug might have been encountered.
+ */
+static inline void skip_test_dodgy_fs(const char *op_name)
+{
+ ksft_test_result_skip("%s failed with ENOENT. Filesystem might be buggy (9pfs?)\n", op_name);
+}
+
uint64_t pagemap_get_entry(int fd, char *start);
bool pagemap_is_softdirty(int fd, char *start);
bool pagemap_is_swapped(int fd, char *start);
diff --git a/tools/testing/selftests/mseal_system_mappings/.gitignore b/tools/testing/selftests/mseal_system_mappings/.gitignore
new file mode 100644
index 000000000000..319c497a595e
--- /dev/null
+++ b/tools/testing/selftests/mseal_system_mappings/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+sysmap_is_sealed
diff --git a/tools/testing/selftests/mseal_system_mappings/Makefile b/tools/testing/selftests/mseal_system_mappings/Makefile
new file mode 100644
index 000000000000..2b4504e2f52f
--- /dev/null
+++ b/tools/testing/selftests/mseal_system_mappings/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+CFLAGS += -std=c99 -pthread -Wall $(KHDR_INCLUDES)
+
+TEST_GEN_PROGS := sysmap_is_sealed
+
+include ../lib.mk
diff --git a/tools/testing/selftests/mseal_system_mappings/config b/tools/testing/selftests/mseal_system_mappings/config
new file mode 100644
index 000000000000..675cb9f37b86
--- /dev/null
+++ b/tools/testing/selftests/mseal_system_mappings/config
@@ -0,0 +1 @@
+CONFIG_MSEAL_SYSTEM_MAPPINGS=y
diff --git a/tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c b/tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c
new file mode 100644
index 000000000000..0d2af30c3bf5
--- /dev/null
+++ b/tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * test system mappings are sealed when
+ * KCONFIG_MSEAL_SYSTEM_MAPPINGS=y
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdbool.h>
+
+#include "../kselftest.h"
+#include "../kselftest_harness.h"
+
+#define VMFLAGS "VmFlags:"
+#define MSEAL_FLAGS "sl"
+#define MAX_LINE_LEN 512
+
+bool has_mapping(char *name, FILE *maps)
+{
+ char line[MAX_LINE_LEN];
+
+ while (fgets(line, sizeof(line), maps)) {
+ if (strstr(line, name))
+ return true;
+ }
+
+ return false;
+}
+
+bool mapping_is_sealed(char *name, FILE *maps)
+{
+ char line[MAX_LINE_LEN];
+
+ while (fgets(line, sizeof(line), maps)) {
+ if (!strncmp(line, VMFLAGS, strlen(VMFLAGS))) {
+ if (strstr(line, MSEAL_FLAGS))
+ return true;
+
+ return false;
+ }
+ }
+
+ return false;
+}
+
+FIXTURE(basic) {
+ FILE *maps;
+};
+
+FIXTURE_SETUP(basic)
+{
+ self->maps = fopen("/proc/self/smaps", "r");
+ if (!self->maps)
+ SKIP(return, "Could not open /proc/self/smap, errno=%d",
+ errno);
+};
+
+FIXTURE_TEARDOWN(basic)
+{
+ if (self->maps)
+ fclose(self->maps);
+};
+
+FIXTURE_VARIANT(basic)
+{
+ char *name;
+ bool sealed;
+};
+
+FIXTURE_VARIANT_ADD(basic, vdso) {
+ .name = "[vdso]",
+ .sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, vvar) {
+ .name = "[vvar]",
+ .sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, vvar_vclock) {
+ .name = "[vvar_vclock]",
+ .sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, sigpage) {
+ .name = "[sigpage]",
+ .sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, vectors) {
+ .name = "[vectors]",
+ .sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, uprobes) {
+ .name = "[uprobes]",
+ .sealed = true,
+};
+
+FIXTURE_VARIANT_ADD(basic, stack) {
+ .name = "[stack]",
+ .sealed = false,
+};
+
+TEST_F(basic, check_sealed)
+{
+ if (!has_mapping(variant->name, self->maps)) {
+ SKIP(return, "could not find the mapping, %s",
+ variant->name);
+ }
+
+ EXPECT_EQ(variant->sealed,
+ mapping_is_sealed(variant->name, self->maps));
+};
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 679542f565a4..532bb732bc6d 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -39,6 +39,7 @@ scm_rights
sk_bind_sendto_listen
sk_connect_zero_addr
sk_so_peek_off
+skf_net_off
socket
so_incoming_cpu
so_netns_cookie
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 6d718b478ed8..124078b56fa4 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -106,6 +106,8 @@ TEST_PROGS += ipv6_route_update_soft_lockup.sh
TEST_PROGS += busy_poll_test.sh
TEST_GEN_PROGS += proc_net_pktgen
TEST_PROGS += lwt_dst_cache_ref_loop.sh
+TEST_PROGS += skf_net_off.sh
+TEST_GEN_FILES += skf_net_off
# YNL files, must be before "include ..lib.mk"
YNL_GEN_FILES := busy_poller netlink-dumps
diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh
index d458b45c775b..3ef209cacb8e 100755
--- a/tools/testing/selftests/net/amt.sh
+++ b/tools/testing/selftests/net/amt.sh
@@ -194,15 +194,21 @@ test_remote_ip()
send_mcast_torture4()
{
- ip netns exec "${SOURCE}" bash -c \
- 'cat /dev/urandom | head -c 1G | nc -w 1 -u 239.0.0.1 4001'
+ for i in `seq 10`; do
+ ip netns exec "${SOURCE}" bash -c \
+ 'cat /dev/urandom | head -c 100M | nc -w 1 -u 239.0.0.1 4001'
+ echo -n "."
+ done
}
send_mcast_torture6()
{
- ip netns exec "${SOURCE}" bash -c \
- 'cat /dev/urandom | head -c 1G | nc -w 1 -u ff0e::5:6 6001'
+ for i in `seq 10`; do
+ ip netns exec "${SOURCE}" bash -c \
+ 'cat /dev/urandom | head -c 100M | nc -w 1 -u ff0e::5:6 6001'
+ echo -n "."
+ done
}
check_features()
@@ -278,10 +284,12 @@ wait $pid || err=$?
if [ $err -eq 1 ]; then
ERR=1
fi
+printf "TEST: %-50s" "IPv4 amt traffic forwarding torture"
send_mcast_torture4
-printf "TEST: %-60s [ OK ]\n" "IPv4 amt traffic forwarding torture"
+printf " [ OK ]\n"
+printf "TEST: %-50s" "IPv6 amt traffic forwarding torture"
send_mcast_torture6
-printf "TEST: %-60s [ OK ]\n" "IPv6 amt traffic forwarding torture"
+printf " [ OK ]\n"
sleep 5
if [ "${ERR}" -eq 1 ]; then
echo "Some tests failed." >&2
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index b866bab1d92a..c7cea556b416 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -359,6 +359,23 @@ fib_rule6_test()
"$getnomatch" "iif flowlabel masked redirect to table" \
"iif flowlabel masked no redirect to table"
fi
+
+ $IP link show dev $DEV | grep -q vrf0
+ if [ $? -eq 0 ]; then
+ match="oif vrf0"
+ getmatch="oif $DEV"
+ getnomatch="oif lo"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF oif redirect to table" \
+ "VRF oif no redirect to table"
+
+ match="from $SRC_IP6 iif vrf0"
+ getmatch="from $SRC_IP6 iif $DEV"
+ getnomatch="from $SRC_IP6 iif lo"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF iif redirect to table" \
+ "VRF iif no redirect to table"
+ fi
}
fib_rule6_vrf_test()
@@ -635,6 +652,23 @@ fib_rule4_test()
"$getnomatch" "iif dscp masked redirect to table" \
"iif dscp masked no redirect to table"
fi
+
+ $IP link show dev $DEV | grep -q vrf0
+ if [ $? -eq 0 ]; then
+ match="oif vrf0"
+ getmatch="oif $DEV"
+ getnomatch="oif lo"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF oif redirect to table" \
+ "VRF oif no redirect to table"
+
+ match="from $SRC_IP iif vrf0"
+ getmatch="from $SRC_IP iif $DEV"
+ getnomatch="from $SRC_IP iif lo"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+ "$getnomatch" "VRF iif redirect to table" \
+ "VRF iif no redirect to table"
+ fi
}
fib_rule4_vrf_test()
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 975be4fdbcdb..701905eeff66 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -222,6 +222,31 @@ setup_ns()
NS_LIST+=("${ns_list[@]}")
}
+# Create netdevsim with given id and net namespace.
+create_netdevsim() {
+ local id="$1"
+ local ns="$2"
+
+ modprobe netdevsim &> /dev/null
+ udevadm settle
+
+ echo "$id 1" | ip netns exec $ns tee /sys/bus/netdevsim/new_device >/dev/null
+ local dev=$(ip netns exec $ns ls /sys/bus/netdevsim/devices/netdevsim$id/net)
+ ip -netns $ns link set dev $dev name nsim$id
+ ip -netns $ns link set dev nsim$id up
+
+ echo nsim$id
+}
+
+# Remove netdevsim with given id.
+cleanup_netdevsim() {
+ local id="$1"
+
+ if [ -d "/sys/bus/netdevsim/devices/netdevsim$id/net" ]; then
+ echo "$id" > /sys/bus/netdevsim/del_device
+ fi
+}
+
tc_rule_stats_get()
{
local dev=$1; shift
diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
index 49daae73c41e..833279fb34e2 100644
--- a/tools/testing/selftests/net/mptcp/.gitignore
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
mptcp_connect
+mptcp_diag
mptcp_inq
mptcp_sockopt
pm_nl_ctl
diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 4f55477ffe08..e7a75341f0f3 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -206,9 +206,8 @@ chk_dump_one()
local token
local msg
- ss_token="$(ss -inmHMN $ns | grep 'token:' |\
- head -n 1 |\
- sed 's/.*token:\([0-9a-f]*\).*/\1/')"
+ ss_token="$(ss -inmHMN $ns |
+ mptcp_lib_get_info_value "token" "token")"
token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\
awk -F':[ \t]+' '/^token/ {print $2}')"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index d240d02fa443..c83a8b47bbdf 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -1270,7 +1270,7 @@ int main_loop(void)
if (cfg_input && cfg_sockopt_types.mptfo) {
fd_in = open(cfg_input, O_RDONLY);
- if (fd < 0)
+ if (fd_in < 0)
xerror("can't open %s:%d", cfg_input, errno);
}
@@ -1293,13 +1293,13 @@ again:
if (cfg_input && !cfg_sockopt_types.mptfo) {
fd_in = open(cfg_input, O_RDONLY);
- if (fd < 0)
+ if (fd_in < 0)
xerror("can't open %s:%d", cfg_input, errno);
}
ret = copyfd_io(fd_in, fd, 1, 0, &winfo);
if (ret)
- return ret;
+ goto out;
if (cfg_truncate > 0) {
shutdown(fd, SHUT_WR);
@@ -1320,7 +1320,10 @@ again:
close(fd);
}
- return 0;
+out:
+ if (cfg_input)
+ close(fd_in);
+ return ret;
}
int parse_proto(const char *proto)
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 13a3b68181ee..befa66f5a366 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -1441,6 +1441,15 @@ chk_join_nr()
fi
fi
+ count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckHMacFailure")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "0" ]; then
+ rc=${KSFT_FAIL}
+ print_check "synack HMAC"
+ fail_test "got $count JOIN[s] synack HMAC failure expected 0"
+ fi
+
count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckRx")
if [ -z "$count" ]; then
rc=${KSFT_SKIP}
@@ -1450,6 +1459,15 @@ chk_join_nr()
fail_test "got $count JOIN[s] ack rx expected $ack_nr"
fi
+ count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckHMacFailure")
+ if [ -z "$count" ]; then
+ rc=${KSFT_SKIP}
+ elif [ "$count" != "0" ]; then
+ rc=${KSFT_FAIL}
+ print_check "ack HMAC"
+ fail_test "got $count JOIN[s] ack HMAC failure expected 0"
+ fi
+
print_results "join Rx" ${rc}
join_syn_tx="${join_syn_tx:-${syn_nr}}" \
diff --git a/tools/testing/selftests/net/netfilter/nft_concat_range.sh b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
index 47088b005390..1f5979c1510c 100755
--- a/tools/testing/selftests/net/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/net/netfilter/nft_concat_range.sh
@@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
net6_port_net6_port net_port_mac_proto_net"
# Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add reload net_port_proto_match"
+BUGS="flush_remove_add reload net_port_proto_match avx2_mismatch"
# List of possible paths to pktgen script from kernel tree for performance tests
PKTGEN_SCRIPT_PATHS="
@@ -387,6 +387,25 @@ race_repeat 0
perf_duration 0
"
+
+TYPE_avx2_mismatch="
+display avx2 false match
+type_spec inet_proto . ipv6_addr
+chain_spec meta l4proto . ip6 daddr
+dst proto addr6
+src
+start 1
+count 1
+src_delta 1
+tools ping
+proto icmp6
+
+race_repeat 0
+
+perf_duration 0
+"
+
+
# Set template for all tests, types and rules are filled in depending on test
set_template='
flush ruleset
@@ -1629,6 +1648,24 @@ test_bug_net_port_proto_match() {
nft flush ruleset
}
+test_bug_avx2_mismatch()
+{
+ setup veth send_"${proto}" set || return ${ksft_skip}
+
+ local a1="fe80:dead:01ff:0a02:0b03:6007:8009:a001"
+ local a2="fe80:dead:01fe:0a02:0b03:6007:8009:a001"
+
+ nft "add element inet filter test { icmpv6 . $a1 }"
+
+ dst_addr6="$a2"
+ send_icmp6
+
+ if [ "$(count_packets)" -gt "0" ]; then
+ err "False match for $a2"
+ return 1
+ fi
+}
+
test_reported_issues() {
eval test_bug_"${subtest}"
}
diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh
index 0be1905d1f2f..38871bdef67f 100755
--- a/tools/testing/selftests/net/netns-name.sh
+++ b/tools/testing/selftests/net/netns-name.sh
@@ -7,10 +7,12 @@ set -o pipefail
DEV=dummy-dev0
DEV2=dummy-dev1
ALT_NAME=some-alt-name
+NSIM_ADDR=2025
RET_CODE=0
cleanup() {
+ cleanup_netdevsim $NSIM_ADDR
cleanup_ns $NS $test_ns
}
@@ -25,12 +27,15 @@ setup_ns NS test_ns
#
# Test basic move without a rename
+# Use netdevsim because it has extra asserts for notifiers.
#
-ip -netns $NS link add name $DEV type dummy || fail
-ip -netns $NS link set dev $DEV netns $test_ns ||
+
+nsim=$(create_netdevsim $NSIM_ADDR $NS)
+ip -netns $NS link set dev $nsim netns $test_ns ||
fail "Can't perform a netns move"
-ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found after move"
-ip -netns $test_ns link del $DEV || fail
+ip -netns $test_ns link show dev $nsim >> /dev/null ||
+ fail "Device not found after move"
+cleanup_netdevsim $NSIM_ADDR
#
# Test move with a conflict
diff --git a/tools/testing/selftests/net/rtnetlink.py b/tools/testing/selftests/net/rtnetlink.py
index 80950888800b..e9ad5e88da97 100755
--- a/tools/testing/selftests/net/rtnetlink.py
+++ b/tools/testing/selftests/net/rtnetlink.py
@@ -12,10 +12,10 @@ def dump_mcaddr_check(rtnl: RtnlAddrFamily) -> None:
At least the loopback interface should have this address.
"""
- addresses = rtnl.getmaddrs({"ifa-family": socket.AF_INET}, dump=True)
+ addresses = rtnl.getmulticast({"ifa-family": socket.AF_INET}, dump=True)
all_host_multicasts = [
- addr for addr in addresses if addr['ifa-multicast'] == IPV4_ALL_HOSTS_MULTICAST
+ addr for addr in addresses if addr['multicast'] == IPV4_ALL_HOSTS_MULTICAST
]
ksft_ge(len(all_host_multicasts), 1,
diff --git a/tools/testing/selftests/net/skf_net_off.c b/tools/testing/selftests/net/skf_net_off.c
new file mode 100644
index 000000000000..1fdf61d6cd7f
--- /dev/null
+++ b/tools/testing/selftests/net/skf_net_off.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Open a tun device.
+ *
+ * [modifications: use IFF_NAPI_FRAGS, add sk filter]
+ *
+ * Expects the device to have been configured previously, e.g.:
+ * sudo ip tuntap add name tap1 mode tap
+ * sudo ip link set tap1 up
+ * sudo ip link set dev tap1 addr 02:00:00:00:00:01
+ * sudo ip -6 addr add fdab::1 peer fdab::2 dev tap1 nodad
+ *
+ * And to avoid premature pskb_may_pull:
+ *
+ * sudo ethtool -K tap1 gro off
+ * sudo bash -c 'echo 0 > /proc/sys/net/ipv4/ip_early_demux'
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <linux/filter.h>
+#include <linux/if.h>
+#include <linux/if_packet.h>
+#include <linux/if_tun.h>
+#include <linux/ipv6.h>
+#include <netinet/if_ether.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/poll.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <unistd.h>
+
+static bool cfg_do_filter;
+static bool cfg_do_frags;
+static int cfg_dst_port = 8000;
+static char *cfg_ifname;
+
+static int tun_open(const char *tun_name)
+{
+ struct ifreq ifr = {0};
+ int fd, ret;
+
+ fd = open("/dev/net/tun", O_RDWR);
+ if (fd == -1)
+ error(1, errno, "open /dev/net/tun");
+
+ ifr.ifr_flags = IFF_TAP;
+ if (cfg_do_frags)
+ ifr.ifr_flags |= IFF_NAPI | IFF_NAPI_FRAGS;
+
+ strncpy(ifr.ifr_name, tun_name, IFNAMSIZ - 1);
+
+ ret = ioctl(fd, TUNSETIFF, &ifr);
+ if (ret)
+ error(1, ret, "ioctl TUNSETIFF");
+
+ return fd;
+}
+
+static void sk_set_filter(int fd)
+{
+ const int offset_proto = offsetof(struct ip6_hdr, ip6_nxt);
+ const int offset_dport = sizeof(struct ip6_hdr) + offsetof(struct udphdr, dest);
+
+ /* Filter UDP packets with destination port cfg_dst_port */
+ struct sock_filter filter_code[] = {
+ BPF_STMT(BPF_LD + BPF_B + BPF_ABS, SKF_AD_OFF + SKF_AD_PKTTYPE),
+ BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, PACKET_HOST, 0, 4),
+ BPF_STMT(BPF_LD + BPF_B + BPF_ABS, SKF_NET_OFF + offset_proto),
+ BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_UDP, 0, 2),
+ BPF_STMT(BPF_LD + BPF_H + BPF_ABS, SKF_NET_OFF + offset_dport),
+ BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, cfg_dst_port, 1, 0),
+ BPF_STMT(BPF_RET + BPF_K, 0),
+ BPF_STMT(BPF_RET + BPF_K, 0xFFFF),
+ };
+
+ struct sock_fprog filter = {
+ sizeof(filter_code) / sizeof(filter_code[0]),
+ filter_code,
+ };
+
+ if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &filter, sizeof(filter)))
+ error(1, errno, "setsockopt attach filter");
+}
+
+static int raw_open(void)
+{
+ int fd;
+
+ fd = socket(PF_INET6, SOCK_RAW, IPPROTO_UDP);
+ if (fd == -1)
+ error(1, errno, "socket raw (udp)");
+
+ if (cfg_do_filter)
+ sk_set_filter(fd);
+
+ return fd;
+}
+
+static void tun_write(int fd)
+{
+ const char eth_src[] = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x02 };
+ const char eth_dst[] = { 0x02, 0x00, 0x00, 0x00, 0x00, 0x01 };
+ struct tun_pi pi = {0};
+ struct ipv6hdr ip6h = {0};
+ struct udphdr uh = {0};
+ struct ethhdr eth = {0};
+ uint32_t payload;
+ struct iovec iov[5];
+ int ret;
+
+ pi.proto = htons(ETH_P_IPV6);
+
+ memcpy(eth.h_source, eth_src, sizeof(eth_src));
+ memcpy(eth.h_dest, eth_dst, sizeof(eth_dst));
+ eth.h_proto = htons(ETH_P_IPV6);
+
+ ip6h.version = 6;
+ ip6h.payload_len = htons(sizeof(uh) + sizeof(uint32_t));
+ ip6h.nexthdr = IPPROTO_UDP;
+ ip6h.hop_limit = 8;
+ if (inet_pton(AF_INET6, "fdab::2", &ip6h.saddr) != 1)
+ error(1, errno, "inet_pton src");
+ if (inet_pton(AF_INET6, "fdab::1", &ip6h.daddr) != 1)
+ error(1, errno, "inet_pton src");
+
+ uh.source = htons(8000);
+ uh.dest = htons(cfg_dst_port);
+ uh.len = ip6h.payload_len;
+ uh.check = 0;
+
+ payload = htonl(0xABABABAB); /* Covered in IPv6 length */
+
+ iov[0].iov_base = &pi;
+ iov[0].iov_len = sizeof(pi);
+ iov[1].iov_base = &eth;
+ iov[1].iov_len = sizeof(eth);
+ iov[2].iov_base = &ip6h;
+ iov[2].iov_len = sizeof(ip6h);
+ iov[3].iov_base = &uh;
+ iov[3].iov_len = sizeof(uh);
+ iov[4].iov_base = &payload;
+ iov[4].iov_len = sizeof(payload);
+
+ ret = writev(fd, iov, sizeof(iov) / sizeof(iov[0]));
+ if (ret <= 0)
+ error(1, errno, "writev");
+}
+
+static void raw_read(int fd)
+{
+ struct timeval tv = { .tv_usec = 100 * 1000 };
+ struct msghdr msg = {0};
+ struct iovec iov[2];
+ struct udphdr uh;
+ uint32_t payload[2];
+ int ret;
+
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+ error(1, errno, "setsockopt rcvtimeo udp");
+
+ iov[0].iov_base = &uh;
+ iov[0].iov_len = sizeof(uh);
+
+ iov[1].iov_base = payload;
+ iov[1].iov_len = sizeof(payload);
+
+ msg.msg_iov = iov;
+ msg.msg_iovlen = sizeof(iov) / sizeof(iov[0]);
+
+ ret = recvmsg(fd, &msg, 0);
+ if (ret <= 0)
+ error(1, errno, "read raw");
+ if (ret != sizeof(uh) + sizeof(payload[0]))
+ error(1, errno, "read raw: len=%d\n", ret);
+
+ fprintf(stderr, "raw recv: 0x%x\n", payload[0]);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "fFi:")) != -1) {
+ switch (c) {
+ case 'f':
+ cfg_do_filter = true;
+ printf("bpf filter enabled\n");
+ break;
+ case 'F':
+ cfg_do_frags = true;
+ printf("napi frags mode enabled\n");
+ break;
+ case 'i':
+ cfg_ifname = optarg;
+ break;
+ default:
+ error(1, 0, "unknown option %c", optopt);
+ break;
+ }
+ }
+
+ if (!cfg_ifname)
+ error(1, 0, "must specify tap interface name (-i)");
+}
+
+int main(int argc, char **argv)
+{
+ int fdt, fdr;
+
+ parse_opts(argc, argv);
+
+ fdr = raw_open();
+ fdt = tun_open(cfg_ifname);
+
+ tun_write(fdt);
+ raw_read(fdr);
+
+ if (close(fdt))
+ error(1, errno, "close tun");
+ if (close(fdr))
+ error(1, errno, "close udp");
+
+ fprintf(stderr, "OK\n");
+ return 0;
+}
+
diff --git a/tools/testing/selftests/net/skf_net_off.sh b/tools/testing/selftests/net/skf_net_off.sh
new file mode 100755
index 000000000000..5da5066fb465
--- /dev/null
+++ b/tools/testing/selftests/net/skf_net_off.sh
@@ -0,0 +1,30 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NS="ns-$(mktemp -u XXXXXX)"
+
+cleanup() {
+ ip netns del $NS
+}
+
+ip netns add $NS
+trap cleanup EXIT
+
+ip -netns $NS link set lo up
+ip -netns $NS tuntap add name tap1 mode tap
+ip -netns $NS link set tap1 up
+ip -netns $NS link set dev tap1 addr 02:00:00:00:00:01
+ip -netns $NS -6 addr add fdab::1 peer fdab::2 dev tap1 nodad
+ip netns exec $NS ethtool -K tap1 gro off
+
+# disable early demux, else udp_v6_early_demux pulls udp header into linear
+ip netns exec $NS sysctl -w net.ipv4.ip_early_demux=0
+
+echo "no filter"
+ip netns exec $NS ./skf_net_off -i tap1
+
+echo "filter, linear skb (-f)"
+ip netns exec $NS ./skf_net_off -i tap1 -f
+
+echo "filter, fragmented skb (-f) (-F)"
+ip netns exec $NS ./skf_net_off -i tap1 -f -F
diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c
index 73b2f2276f3f..2c73bea698a6 100644
--- a/tools/testing/selftests/net/tcp_ao/self-connect.c
+++ b/tools/testing/selftests/net/tcp_ao/self-connect.c
@@ -16,6 +16,9 @@ static void __setup_lo_intf(const char *lo_intf,
if (link_set_up(lo_intf))
test_error("Failed to bring %s up", lo_intf);
+
+ if (ip_route_add(lo_intf, TEST_FAMILY, local_addr, local_addr))
+ test_error("Failed to add a local route %s", lo_intf);
}
static void setup_lo_intf(const char *lo_intf)
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 9a85f93c33d8..5ded3b3a7538 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -1753,6 +1753,42 @@ TEST_F(tls_basic, rekey_tx)
EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
}
+TEST_F(tls_basic, disconnect)
+{
+ char const *test_str = "test_message";
+ int send_len = strlen(test_str) + 1;
+ struct tls_crypto_info_keys key;
+ struct sockaddr_in addr;
+ char buf[20];
+ int ret;
+
+ if (self->notls)
+ return;
+
+ tls_crypto_info_init(TLS_1_3_VERSION, TLS_CIPHER_AES_GCM_128,
+ &key, 0);
+
+ ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &key, key.len);
+ ASSERT_EQ(ret, 0);
+
+ /* Pre-queue the data so that setsockopt parses it but doesn't
+ * dequeue it from the TCP socket. recvmsg would dequeue.
+ */
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+
+ ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &key, key.len);
+ ASSERT_EQ(ret, 0);
+
+ addr.sin_family = AF_UNSPEC;
+ addr.sin_addr.s_addr = htonl(INADDR_ANY);
+ addr.sin_port = 0;
+ ret = connect(self->cfd, &addr, sizeof(addr));
+ EXPECT_EQ(ret, -1);
+ EXPECT_EQ(errno, EOPNOTSUPP);
+
+ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+}
+
TEST_F(tls, rekey)
{
char const *test_str_1 = "test_message_before_rekey";
diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh
index c51ea90a1395..815fad8c53a8 100755
--- a/tools/testing/selftests/net/udpgro_bench.sh
+++ b/tools/testing/selftests/net/udpgro_bench.sh
@@ -7,7 +7,7 @@ source net_helper.sh
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
-BPF_FILE="xdp_dummy.bpf.o"
+BPF_FILE="lib/xdp_dummy.bpf.o"
cleanup() {
local -r jobs="$(jobs -p)"
diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh
index 17404f49cdb6..5f3d1a110d11 100755
--- a/tools/testing/selftests/net/udpgro_frglist.sh
+++ b/tools/testing/selftests/net/udpgro_frglist.sh
@@ -7,7 +7,7 @@ source net_helper.sh
readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
-BPF_FILE="xdp_dummy.bpf.o"
+BPF_FILE="lib/xdp_dummy.bpf.o"
cleanup() {
local -r jobs="$(jobs -p)"
diff --git a/tools/testing/selftests/net/udpgro_fwd.sh b/tools/testing/selftests/net/udpgro_fwd.sh
index 550d8eb3e224..f22f6c66997e 100755
--- a/tools/testing/selftests/net/udpgro_fwd.sh
+++ b/tools/testing/selftests/net/udpgro_fwd.sh
@@ -3,7 +3,7 @@
source net_helper.sh
-BPF_FILE="xdp_dummy.bpf.o"
+BPF_FILE="lib/xdp_dummy.bpf.o"
readonly BASE="ns-$(mktemp -u XXXXXX)"
readonly SRC=2
readonly DST=1
diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh
index 6bb7dfaa30b6..9709dd067c72 100755
--- a/tools/testing/selftests/net/veth.sh
+++ b/tools/testing/selftests/net/veth.sh
@@ -1,7 +1,7 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
-BPF_FILE="xdp_dummy.bpf.o"
+BPF_FILE="lib/xdp_dummy.bpf.o"
readonly STATS="$(mktemp -p /tmp ns-XXXXXX)"
readonly BASE=`basename $STATS`
readonly SRC=2
diff --git a/tools/testing/selftests/net/xdp_dummy.bpf.c b/tools/testing/selftests/net/xdp_dummy.bpf.c
deleted file mode 100644
index d988b2e0cee8..000000000000
--- a/tools/testing/selftests/net/xdp_dummy.bpf.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#define KBUILD_MODNAME "xdp_dummy"
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-
-SEC("xdp")
-int xdp_dummy_prog(struct xdp_md *ctx)
-{
- return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c b/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c
index c267b822c108..ac26481d29d9 100644
--- a/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c
+++ b/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c
@@ -25,7 +25,7 @@
#define pci_ep_ioctl(cmd, arg) \
({ \
ret = ioctl(self->fd, cmd, arg); \
- ret = ret < 0 ? -errno : 0; \
+ ret = ret < 0 ? -errno : ret; \
})
static const char *test_device = "/dev/pci-endpoint-test.0";
@@ -65,6 +65,8 @@ TEST_F(pci_ep_bar, BAR_TEST)
int ret;
pci_ep_ioctl(PCITEST_BAR, variant->barno);
+ if (ret == -ENODATA)
+ SKIP(return, "BAR is disabled");
EXPECT_FALSE(ret) TH_LOG("Test failed for BAR%d", variant->barno);
}
@@ -97,9 +99,12 @@ TEST_F(pci_ep_basic, LEGACY_IRQ_TEST)
{
int ret;
- pci_ep_ioctl(PCITEST_SET_IRQTYPE, 0);
+ pci_ep_ioctl(PCITEST_SET_IRQTYPE, PCITEST_IRQ_TYPE_INTX);
ASSERT_EQ(0, ret) TH_LOG("Can't set Legacy IRQ type");
+ pci_ep_ioctl(PCITEST_GET_IRQTYPE, 0);
+ ASSERT_EQ(PCITEST_IRQ_TYPE_INTX, ret) TH_LOG("Can't get Legacy IRQ type");
+
pci_ep_ioctl(PCITEST_LEGACY_IRQ, 0);
EXPECT_FALSE(ret) TH_LOG("Test failed for Legacy IRQ");
}
@@ -108,9 +113,12 @@ TEST_F(pci_ep_basic, MSI_TEST)
{
int ret, i;
- pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1);
+ pci_ep_ioctl(PCITEST_SET_IRQTYPE, PCITEST_IRQ_TYPE_MSI);
ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type");
+ pci_ep_ioctl(PCITEST_GET_IRQTYPE, 0);
+ ASSERT_EQ(PCITEST_IRQ_TYPE_MSI, ret) TH_LOG("Can't get MSI IRQ type");
+
for (i = 1; i <= 32; i++) {
pci_ep_ioctl(PCITEST_MSI, i);
EXPECT_FALSE(ret) TH_LOG("Test failed for MSI%d", i);
@@ -121,9 +129,12 @@ TEST_F(pci_ep_basic, MSIX_TEST)
{
int ret, i;
- pci_ep_ioctl(PCITEST_SET_IRQTYPE, 2);
+ pci_ep_ioctl(PCITEST_SET_IRQTYPE, PCITEST_IRQ_TYPE_MSIX);
ASSERT_EQ(0, ret) TH_LOG("Can't set MSI-X IRQ type");
+ pci_ep_ioctl(PCITEST_GET_IRQTYPE, 0);
+ ASSERT_EQ(PCITEST_IRQ_TYPE_MSIX, ret) TH_LOG("Can't get MSI-X IRQ type");
+
for (i = 1; i <= 2048; i++) {
pci_ep_ioctl(PCITEST_MSIX, i);
EXPECT_FALSE(ret) TH_LOG("Test failed for MSI-X%d", i);
@@ -170,8 +181,8 @@ TEST_F(pci_ep_data_transfer, READ_TEST)
if (variant->use_dma)
param.flags = PCITEST_FLAGS_USE_DMA;
- pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1);
- ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type");
+ pci_ep_ioctl(PCITEST_SET_IRQTYPE, PCITEST_IRQ_TYPE_AUTO);
+ ASSERT_EQ(0, ret) TH_LOG("Can't set AUTO IRQ type");
for (i = 0; i < ARRAY_SIZE(test_size); i++) {
param.size = test_size[i];
@@ -189,8 +200,8 @@ TEST_F(pci_ep_data_transfer, WRITE_TEST)
if (variant->use_dma)
param.flags = PCITEST_FLAGS_USE_DMA;
- pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1);
- ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type");
+ pci_ep_ioctl(PCITEST_SET_IRQTYPE, PCITEST_IRQ_TYPE_AUTO);
+ ASSERT_EQ(0, ret) TH_LOG("Can't set AUTO IRQ type");
for (i = 0; i < ARRAY_SIZE(test_size); i++) {
param.size = test_size[i];
@@ -208,8 +219,8 @@ TEST_F(pci_ep_data_transfer, COPY_TEST)
if (variant->use_dma)
param.flags = PCITEST_FLAGS_USE_DMA;
- pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1);
- ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type");
+ pci_ep_ioctl(PCITEST_SET_IRQTYPE, PCITEST_IRQ_TYPE_AUTO);
+ ASSERT_EQ(0, ret) TH_LOG("Can't set AUTO IRQ type");
for (i = 0; i < ARRAY_SIZE(test_size); i++) {
param.size = test_size[i];
diff --git a/tools/testing/selftests/pcie_bwctrl/Makefile b/tools/testing/selftests/pcie_bwctrl/Makefile
index 3e84e26341d1..48ec048f47af 100644
--- a/tools/testing/selftests/pcie_bwctrl/Makefile
+++ b/tools/testing/selftests/pcie_bwctrl/Makefile
@@ -1,2 +1,2 @@
-TEST_PROGS = set_pcie_cooling_state.sh
+TEST_PROGS = set_pcie_cooling_state.sh set_pcie_speed.sh
include ../lib.mk
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index cec22aa11cdf..55bcf81a2b9a 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -32,19 +32,19 @@
#endif
#ifndef __NR_pidfd_open
-#define __NR_pidfd_open -1
+#define __NR_pidfd_open 434
#endif
#ifndef __NR_pidfd_send_signal
-#define __NR_pidfd_send_signal -1
+#define __NR_pidfd_send_signal 424
#endif
#ifndef __NR_clone3
-#define __NR_clone3 -1
+#define __NR_clone3 435
#endif
#ifndef __NR_pidfd_getfd
-#define __NR_pidfd_getfd -1
+#define __NR_pidfd_getfd 438
#endif
#ifndef PIDFD_NONBLOCK
diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c
index a40541bb7c7d..5e96ef785d0d 100644
--- a/tools/testing/selftests/riscv/hwprobe/cbo.c
+++ b/tools/testing/selftests/riscv/hwprobe/cbo.c
@@ -50,6 +50,14 @@ static void cbo_clean(char *base) { cbo_insn(base, 1); }
static void cbo_flush(char *base) { cbo_insn(base, 2); }
static void cbo_zero(char *base) { cbo_insn(base, 4); }
+static void test_no_cbo_inval(void *arg)
+{
+ ksft_print_msg("Testing cbo.inval instruction remain privileged\n");
+ illegal_insn = false;
+ cbo_inval(&mem[0]);
+ ksft_test_result(illegal_insn, "No cbo.inval\n");
+}
+
static void test_no_zicbom(void *arg)
{
ksft_print_msg("Testing Zicbom instructions remain privileged\n");
@@ -61,10 +69,6 @@ static void test_no_zicbom(void *arg)
illegal_insn = false;
cbo_flush(&mem[0]);
ksft_test_result(illegal_insn, "No cbo.flush\n");
-
- illegal_insn = false;
- cbo_inval(&mem[0]);
- ksft_test_result(illegal_insn, "No cbo.inval\n");
}
static void test_no_zicboz(void *arg)
@@ -81,6 +85,30 @@ static bool is_power_of_2(__u64 n)
return n != 0 && (n & (n - 1)) == 0;
}
+static void test_zicbom(void *arg)
+{
+ struct riscv_hwprobe pair = {
+ .key = RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE,
+ };
+ cpu_set_t *cpus = (cpu_set_t *)arg;
+ __u64 block_size;
+ long rc;
+
+ rc = riscv_hwprobe(&pair, 1, sizeof(cpu_set_t), (unsigned long *)cpus, 0);
+ block_size = pair.value;
+ ksft_test_result(rc == 0 && pair.key == RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE &&
+ is_power_of_2(block_size), "Zicbom block size\n");
+ ksft_print_msg("Zicbom block size: %llu\n", block_size);
+
+ illegal_insn = false;
+ cbo_clean(&mem[block_size]);
+ ksft_test_result(!illegal_insn, "cbo.clean\n");
+
+ illegal_insn = false;
+ cbo_flush(&mem[block_size]);
+ ksft_test_result(!illegal_insn, "cbo.flush\n");
+}
+
static void test_zicboz(void *arg)
{
struct riscv_hwprobe pair = {
@@ -129,7 +157,7 @@ static void test_zicboz(void *arg)
ksft_test_result_pass("cbo.zero check\n");
}
-static void check_no_zicboz_cpus(cpu_set_t *cpus)
+static void check_no_zicbo_cpus(cpu_set_t *cpus, __u64 cbo)
{
struct riscv_hwprobe pair = {
.key = RISCV_HWPROBE_KEY_IMA_EXT_0,
@@ -137,6 +165,7 @@ static void check_no_zicboz_cpus(cpu_set_t *cpus)
cpu_set_t one_cpu;
int i = 0, c = 0;
long rc;
+ char *cbostr;
while (i++ < CPU_COUNT(cpus)) {
while (!CPU_ISSET(c, cpus))
@@ -148,10 +177,13 @@ static void check_no_zicboz_cpus(cpu_set_t *cpus)
rc = riscv_hwprobe(&pair, 1, sizeof(cpu_set_t), (unsigned long *)&one_cpu, 0);
assert(rc == 0 && pair.key == RISCV_HWPROBE_KEY_IMA_EXT_0);
- if (pair.value & RISCV_HWPROBE_EXT_ZICBOZ)
- ksft_exit_fail_msg("Zicboz is only present on a subset of harts.\n"
- "Use taskset to select a set of harts where Zicboz\n"
- "presence (present or not) is consistent for each hart\n");
+ cbostr = cbo == RISCV_HWPROBE_EXT_ZICBOZ ? "Zicboz" : "Zicbom";
+
+ if (pair.value & cbo)
+ ksft_exit_fail_msg("%s is only present on a subset of harts.\n"
+ "Use taskset to select a set of harts where %s\n"
+ "presence (present or not) is consistent for each hart\n",
+ cbostr, cbostr);
++c;
}
}
@@ -159,7 +191,9 @@ static void check_no_zicboz_cpus(cpu_set_t *cpus)
enum {
TEST_ZICBOZ,
TEST_NO_ZICBOZ,
+ TEST_ZICBOM,
TEST_NO_ZICBOM,
+ TEST_NO_CBO_INVAL,
};
static struct test_info {
@@ -169,7 +203,9 @@ static struct test_info {
} tests[] = {
[TEST_ZICBOZ] = { .nr_tests = 3, test_zicboz },
[TEST_NO_ZICBOZ] = { .nr_tests = 1, test_no_zicboz },
- [TEST_NO_ZICBOM] = { .nr_tests = 3, test_no_zicbom },
+ [TEST_ZICBOM] = { .nr_tests = 3, test_zicbom },
+ [TEST_NO_ZICBOM] = { .nr_tests = 2, test_no_zicbom },
+ [TEST_NO_CBO_INVAL] = { .nr_tests = 1, test_no_cbo_inval },
};
int main(int argc, char **argv)
@@ -189,6 +225,7 @@ int main(int argc, char **argv)
assert(rc == 0);
tests[TEST_NO_ZICBOZ].enabled = true;
tests[TEST_NO_ZICBOM].enabled = true;
+ tests[TEST_NO_CBO_INVAL].enabled = true;
}
rc = sched_getaffinity(0, sizeof(cpu_set_t), &cpus);
@@ -206,7 +243,14 @@ int main(int argc, char **argv)
tests[TEST_ZICBOZ].enabled = true;
tests[TEST_NO_ZICBOZ].enabled = false;
} else {
- check_no_zicboz_cpus(&cpus);
+ check_no_zicbo_cpus(&cpus, RISCV_HWPROBE_EXT_ZICBOZ);
+ }
+
+ if (pair.value & RISCV_HWPROBE_EXT_ZICBOM) {
+ tests[TEST_ZICBOM].enabled = true;
+ tests[TEST_NO_ZICBOM].enabled = false;
+ } else {
+ check_no_zicbo_cpus(&cpus, RISCV_HWPROBE_EXT_ZICBOM);
}
for (i = 0; i < ARRAY_SIZE(tests); ++i)
diff --git a/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c
index 35c0812e32de..4dde05e45a04 100644
--- a/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c
+++ b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c
@@ -6,7 +6,7 @@
* the values. To further ensure consistency, this file is compiled without
* libc and without auto-vectorization.
*
- * To be "clean" all values must be either all ones or all zeroes.
+ * To be "clean" all values must be all zeroes.
*/
#define __stringify_1(x...) #x
@@ -14,9 +14,8 @@
int main(int argc, char **argv)
{
- char prev_value = 0, value;
+ char value = 0;
unsigned long vl;
- int first = 1;
if (argc > 2 && strcmp(argv[2], "x"))
asm volatile (
@@ -44,14 +43,11 @@ int main(int argc, char **argv)
"vsrl.vi " __stringify(register) ", " __stringify(register) ", 8\n\t" \
".option pop\n\t" \
: "=r" (value)); \
- if (first) { \
- first = 0; \
- } else if (value != prev_value || !(value == 0x00 || value == 0xff)) { \
+ if (value != 0x00) { \
printf("Register " __stringify(register) \
" values not clean! value: %u\n", value); \
exit(-1); \
} \
- prev_value = value; \
} \
})
diff --git a/tools/testing/selftests/rtc/.gitignore b/tools/testing/selftests/rtc/.gitignore
index fb2d533aa575..a2afe7994e85 100644
--- a/tools/testing/selftests/rtc/.gitignore
+++ b/tools/testing/selftests/rtc/.gitignore
@@ -1,3 +1,2 @@
# SPDX-License-Identifier: GPL-2.0-only
rtctest
-setdate
diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile
index 9dbb395c5c79..547c244a2ca5 100644
--- a/tools/testing/selftests/rtc/Makefile
+++ b/tools/testing/selftests/rtc/Makefile
@@ -4,8 +4,6 @@ LDLIBS += -lrt -lpthread -lm
TEST_GEN_PROGS = rtctest
-TEST_GEN_PROGS_EXTENDED = setdate
-
TEST_FILES := settings
include ../lib.mk
diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c
index e103097d0b5b..be175c0e6ae3 100644
--- a/tools/testing/selftests/rtc/rtctest.c
+++ b/tools/testing/selftests/rtc/rtctest.c
@@ -29,6 +29,7 @@ enum rtc_alarm_state {
RTC_ALARM_UNKNOWN,
RTC_ALARM_ENABLED,
RTC_ALARM_DISABLED,
+ RTC_ALARM_RES_MINUTE,
};
FIXTURE(rtc) {
@@ -88,7 +89,7 @@ static void nanosleep_with_retries(long ns)
}
}
-static enum rtc_alarm_state get_rtc_alarm_state(int fd)
+static enum rtc_alarm_state get_rtc_alarm_state(int fd, int need_seconds)
{
struct rtc_param param = { 0 };
int rc;
@@ -103,6 +104,10 @@ static enum rtc_alarm_state get_rtc_alarm_state(int fd)
if ((param.uvalue & _BITUL(RTC_FEATURE_ALARM)) == 0)
return RTC_ALARM_DISABLED;
+ /* Check if alarm has desired granularity */
+ if (need_seconds && (param.uvalue & _BITUL(RTC_FEATURE_ALARM_RES_MINUTE)))
+ return RTC_ALARM_RES_MINUTE;
+
return RTC_ALARM_ENABLED;
}
@@ -227,9 +232,11 @@ TEST_F(rtc, alarm_alm_set) {
SKIP(return, "Skipping test since %s does not exist", rtc_file);
ASSERT_NE(-1, self->fd);
- alarm_state = get_rtc_alarm_state(self->fd);
+ alarm_state = get_rtc_alarm_state(self->fd, 1);
if (alarm_state == RTC_ALARM_DISABLED)
SKIP(return, "Skipping test since alarms are not supported.");
+ if (alarm_state == RTC_ALARM_RES_MINUTE)
+ SKIP(return, "Skipping test since alarms has only minute granularity.");
rc = ioctl(self->fd, RTC_RD_TIME, &tm);
ASSERT_NE(-1, rc);
@@ -295,9 +302,11 @@ TEST_F(rtc, alarm_wkalm_set) {
SKIP(return, "Skipping test since %s does not exist", rtc_file);
ASSERT_NE(-1, self->fd);
- alarm_state = get_rtc_alarm_state(self->fd);
+ alarm_state = get_rtc_alarm_state(self->fd, 1);
if (alarm_state == RTC_ALARM_DISABLED)
SKIP(return, "Skipping test since alarms are not supported.");
+ if (alarm_state == RTC_ALARM_RES_MINUTE)
+ SKIP(return, "Skipping test since alarms has only minute granularity.");
rc = ioctl(self->fd, RTC_RD_TIME, &alarm.time);
ASSERT_NE(-1, rc);
@@ -357,7 +366,7 @@ TEST_F_TIMEOUT(rtc, alarm_alm_set_minute, 65) {
SKIP(return, "Skipping test since %s does not exist", rtc_file);
ASSERT_NE(-1, self->fd);
- alarm_state = get_rtc_alarm_state(self->fd);
+ alarm_state = get_rtc_alarm_state(self->fd, 0);
if (alarm_state == RTC_ALARM_DISABLED)
SKIP(return, "Skipping test since alarms are not supported.");
@@ -425,7 +434,7 @@ TEST_F_TIMEOUT(rtc, alarm_wkalm_set_minute, 65) {
SKIP(return, "Skipping test since %s does not exist", rtc_file);
ASSERT_NE(-1, self->fd);
- alarm_state = get_rtc_alarm_state(self->fd);
+ alarm_state = get_rtc_alarm_state(self->fd, 0);
if (alarm_state == RTC_ALARM_DISABLED)
SKIP(return, "Skipping test since alarms are not supported.");
diff --git a/tools/testing/selftests/rtc/setdate.c b/tools/testing/selftests/rtc/setdate.c
deleted file mode 100644
index b303890b3de2..000000000000
--- a/tools/testing/selftests/rtc/setdate.c
+++ /dev/null
@@ -1,77 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/* Real Time Clock Driver Test
- * by: Benjamin Gaignard (benjamin.gaignard@linaro.org)
- *
- * To build
- * gcc rtctest_setdate.c -o rtctest_setdate
- */
-
-#include <stdio.h>
-#include <linux/rtc.h>
-#include <sys/ioctl.h>
-#include <sys/time.h>
-#include <sys/types.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <errno.h>
-
-static const char default_time[] = "00:00:00";
-
-int main(int argc, char **argv)
-{
- int fd, retval;
- struct rtc_time new, current;
- const char *rtc, *date;
- const char *time = default_time;
-
- switch (argc) {
- case 4:
- time = argv[3];
- /* FALLTHROUGH */
- case 3:
- date = argv[2];
- rtc = argv[1];
- break;
- default:
- fprintf(stderr, "usage: rtctest_setdate <rtcdev> <DD-MM-YYYY> [HH:MM:SS]\n");
- return 1;
- }
-
- fd = open(rtc, O_RDONLY);
- if (fd == -1) {
- perror(rtc);
- exit(errno);
- }
-
- sscanf(date, "%d-%d-%d", &new.tm_mday, &new.tm_mon, &new.tm_year);
- new.tm_mon -= 1;
- new.tm_year -= 1900;
- sscanf(time, "%d:%d:%d", &new.tm_hour, &new.tm_min, &new.tm_sec);
-
- fprintf(stderr, "Test will set RTC date/time to %d-%d-%d, %02d:%02d:%02d.\n",
- new.tm_mday, new.tm_mon + 1, new.tm_year + 1900,
- new.tm_hour, new.tm_min, new.tm_sec);
-
- /* Write the new date in RTC */
- retval = ioctl(fd, RTC_SET_TIME, &new);
- if (retval == -1) {
- perror("RTC_SET_TIME ioctl");
- close(fd);
- exit(errno);
- }
-
- /* Read back */
- retval = ioctl(fd, RTC_RD_TIME, &current);
- if (retval == -1) {
- perror("RTC_RD_TIME ioctl");
- exit(errno);
- }
-
- fprintf(stderr, "\n\nCurrent RTC date/time is %d-%d-%d, %02d:%02d:%02d.\n",
- current.tm_mday, current.tm_mon + 1, current.tm_year + 1900,
- current.tm_hour, current.tm_min, current.tm_sec);
-
- close(fd);
- return 0;
-}
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
index ee2792998c89..4f21aeb8a3fb 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
@@ -305,7 +305,7 @@
"cmdUnderTest": "$TC actions add action nat ingress default 10.10.10.1 index 12",
"expExitCode": "0",
"verifyCmd": "$TC actions get action nat index 12",
- "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref",
+ "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/0 10.10.10.1 pass.*index 12 ref",
"matchCount": "1",
"teardown": [
"$TC actions flush action nat"
@@ -332,7 +332,7 @@
"cmdUnderTest": "$TC actions add action nat ingress any 10.10.10.1 index 12",
"expExitCode": "0",
"verifyCmd": "$TC actions get action nat index 12",
- "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref",
+ "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/0 10.10.10.1 pass.*index 12 ref",
"matchCount": "1",
"teardown": [
"$TC actions flush action nat"
@@ -359,7 +359,7 @@
"cmdUnderTest": "$TC actions add action nat ingress all 10.10.10.1 index 12",
"expExitCode": "0",
"verifyCmd": "$TC actions get action nat index 12",
- "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref",
+ "matchPattern": "action order [0-9]+: nat ingress 0.0.0.0/0 10.10.10.1 pass.*index 12 ref",
"matchCount": "1",
"teardown": [
"$TC actions flush action nat"
@@ -548,7 +548,7 @@
"cmdUnderTest": "$TC actions add action nat egress default 20.20.20.1 pipe index 10",
"expExitCode": "0",
"verifyCmd": "$TC actions get action nat index 10",
- "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref",
+ "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/0 20.20.20.1 pipe.*index 10 ref",
"matchCount": "1",
"teardown": [
"$TC actions flush action nat"
@@ -575,7 +575,7 @@
"cmdUnderTest": "$TC actions add action nat egress any 20.20.20.1 pipe index 10",
"expExitCode": "0",
"verifyCmd": "$TC actions get action nat index 10",
- "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref",
+ "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/0 20.20.20.1 pipe.*index 10 ref",
"matchCount": "1",
"teardown": [
"$TC actions flush action nat"
@@ -602,7 +602,7 @@
"cmdUnderTest": "$TC actions add action nat egress all 20.20.20.1 pipe index 10",
"expExitCode": "0",
"verifyCmd": "$TC actions get action nat index 10",
- "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref",
+ "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/0 20.20.20.1 pipe.*index 10 ref",
"matchCount": "1",
"teardown": [
"$TC actions flush action nat"
@@ -629,7 +629,7 @@
"cmdUnderTest": "$TC actions add action nat egress all 20.20.20.1 pipe index 10 cookie aa1bc2d3eeff112233445566778800a1",
"expExitCode": "0",
"verifyCmd": "$TC actions get action nat index 10",
- "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref.*cookie aa1bc2d3eeff112233445566778800a1",
+ "matchPattern": "action order [0-9]+: nat egress 0.0.0.0/0 20.20.20.1 pipe.*index 10 ref.*cookie aa1bc2d3eeff112233445566778800a1",
"matchCount": "1",
"teardown": [
"$TC actions flush action nat"
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json b/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
index 1ba96c467754..d9fc62ab476c 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/actions.json
@@ -412,5 +412,27 @@
"teardown": [
"$TC qdisc del dev $DUMMY ingress"
]
+ },
+ {
+ "id": "33f4",
+ "name": "Check echo of big filter command",
+ "category": [
+ "infra",
+ "u32"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$TC qdisc add dev $DUMMY parent root handle 10: fq_codel"
+ ],
+ "cmdUnderTest": "bash -c '$TC -echo filter add dev $DUMMY parent 10: u32 match u32 0 0 $(for i in $(seq 32); do echo action pedit munge ip dport set 22; done) | grep \"added filter\"'",
+ "verifyCmd": "",
+ "expExitCode": "0",
+ "matchCount": "0",
+ "matchPattern": "",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY parent root fq_codel"
+ ]
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 9044ac054167..e26bbc169783 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -126,5 +126,231 @@
"$TC qdisc del dev $DUMMY root handle 1: drr",
"$IP addr del 10.10.10.10/24 dev $DUMMY"
]
- }
+ },
+ {
+ "id": "c024",
+ "name": "Test TBF with SKBPRIO - catch qlen corner cases",
+ "category": [
+ "qdisc",
+ "tbf",
+ "skbprio"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root tbf rate 100bit burst 2000 limit 1000",
+ "$TC qdisc add dev $DUMMY parent 1: handle 10: skbprio limit 1",
+ "ping -c 1 -W 0.1 -Q 0x00 -s 1400 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "ping -c 1 -W 0.1 -Q 0x1c -s 1400 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "ping -c 1 -W 0.1 -Q 0x00 -s 1400 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "ping -c 1 -W 0.1 -Q 0x1c -s 1400 -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.5"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc skbprio'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4bb",
+ "name": "Test FQ_CODEL with HTB parent - force packet drop with empty queue",
+ "category": [
+ "qdisc",
+ "fq_codel",
+ "htb"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root htb default 10",
+ "$TC class add dev $DUMMY parent 1: classid 1:10 htb rate 1kbit",
+ "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+ "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+ "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.1"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4be",
+ "name": "Test FQ_CODEL with QFQ parent - force packet drop with empty queue",
+ "category": [
+ "qdisc",
+ "fq_codel",
+ "qfq"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root qfq",
+ "$TC class add dev $DUMMY parent 1: classid 1:10 qfq weight 1 maxpkt 1000",
+ "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+ "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+ "ping -c 10 -s 1000 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.1"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4bf",
+ "name": "Test FQ_CODEL with HFSC parent - force packet drop with empty queue",
+ "category": [
+ "qdisc",
+ "fq_codel",
+ "hfsc"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root hfsc default 10",
+ "$TC class add dev $DUMMY parent 1: classid 1:10 hfsc sc rate 1kbit ul rate 1kbit",
+ "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+ "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+ "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.1"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4c0",
+ "name": "Test FQ_CODEL with DRR parent - force packet drop with empty queue",
+ "category": [
+ "qdisc",
+ "fq_codel",
+ "drr"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root drr",
+ "$TC class add dev $DUMMY parent 1: classid 1:10 drr quantum 1500",
+ "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+ "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+ "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.1"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4c1",
+ "name": "Test FQ_CODEL with ETS parent - force packet drop with empty queue",
+ "category": [
+ "qdisc",
+ "fq_codel",
+ "ets"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 strict 1",
+ "$TC class change dev $DUMMY parent 1: classid 1:1 ets",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+ "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1",
+ "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+ "sleep 0.1"
+ ],
+ "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "dropped [1-9][0-9]*",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1: root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ },
+ {
+ "id": "a4c3",
+ "name": "Test HFSC with netem/blackhole - queue emptying during peek operation",
+ "category": [
+ "qdisc",
+ "hfsc",
+ "netem",
+ "blackhole"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [
+ "$IP link set dev $DUMMY up || true",
+ "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+ "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+ "$TC class add dev $DUMMY parent 1:0 classid 1:2 drr",
+ "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 plug limit 1024",
+ "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 hfsc default 1",
+ "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+ "$TC qdisc add dev $DUMMY parent 3:1 handle 4:0 netem delay 1ms",
+ "$TC qdisc add dev $DUMMY parent 4:1 handle 5:0 blackhole",
+ "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true",
+ "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+ "$TC class del dev $DUMMY parent 3:0 classid 3:1",
+ "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+ "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true"
+ ],
+ "cmdUnderTest": "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+ "matchPattern": "qdisc hfsc 3:.*parent 1:2.*default 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DUMMY handle 1:0 root",
+ "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+ ]
+ }
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
index 50e8d72781cb..28c6ce6da7db 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/sfq.json
@@ -228,5 +228,41 @@
"matchCount": "0",
"teardown": [
]
+ },
+ {
+ "id": "7f8f",
+ "name": "Check that a derived limit of 1 is rejected (limit 2 depth 1 flows 1)",
+ "category": [
+ "qdisc",
+ "sfq"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq limit 2 depth 1 flows 1",
+ "expExitCode": "2",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "sfq",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "5168",
+ "name": "Check that a derived limit of 1 is rejected (limit 2 depth 1 divisor 1)",
+ "category": [
+ "qdisc",
+ "sfq"
+ ],
+ "plugins": {
+ "requires": "nsPlugin"
+ },
+ "setup": [],
+ "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root sfq limit 2 depth 1 divisor 1",
+ "expExitCode": "2",
+ "verifyCmd": "$TC qdisc show dev $DUMMY",
+ "matchPattern": "sfq",
+ "matchCount": "0",
+ "teardown": []
}
]
diff --git a/tools/testing/selftests/tpm2/.gitignore b/tools/testing/selftests/tpm2/.gitignore
new file mode 100644
index 000000000000..6d6165c5e35d
--- /dev/null
+++ b/tools/testing/selftests/tpm2/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+AsyncTest.log
+SpaceTest.log
diff --git a/tools/testing/selftests/tpm2/test_smoke.sh b/tools/testing/selftests/tpm2/test_smoke.sh
index 168f4b166234..3a60e6c6f5c9 100755
--- a/tools/testing/selftests/tpm2/test_smoke.sh
+++ b/tools/testing/selftests/tpm2/test_smoke.sh
@@ -6,6 +6,6 @@ ksft_skip=4
[ -e /dev/tpm0 ] || exit $ksft_skip
read tpm_version < /sys/class/tpm/tpm0/tpm_version_major
-[ "$tpm_version" == 2 ] || exit $ksft_skip
+[ "$tpm_version" = 2 ] || exit $ksft_skip
python3 -m unittest -v tpm2_tests.SmokeTest 2>&1
diff --git a/tools/testing/selftests/ublk/Makefile b/tools/testing/selftests/ublk/Makefile
index 7817afe29005..ec4624a283bc 100644
--- a/tools/testing/selftests/ublk/Makefile
+++ b/tools/testing/selftests/ublk/Makefile
@@ -4,6 +4,11 @@ CFLAGS += -O3 -Wl,-no-as-needed -Wall -I $(top_srcdir)
LDLIBS += -lpthread -lm -luring
TEST_PROGS := test_generic_01.sh
+TEST_PROGS += test_generic_02.sh
+TEST_PROGS += test_generic_03.sh
+TEST_PROGS += test_generic_04.sh
+TEST_PROGS += test_generic_05.sh
+TEST_PROGS += test_generic_06.sh
TEST_PROGS += test_null_01.sh
TEST_PROGS += test_null_02.sh
@@ -11,17 +16,24 @@ TEST_PROGS += test_loop_01.sh
TEST_PROGS += test_loop_02.sh
TEST_PROGS += test_loop_03.sh
TEST_PROGS += test_loop_04.sh
+TEST_PROGS += test_loop_05.sh
TEST_PROGS += test_stripe_01.sh
TEST_PROGS += test_stripe_02.sh
+TEST_PROGS += test_stripe_03.sh
+TEST_PROGS += test_stripe_04.sh
TEST_PROGS += test_stress_01.sh
TEST_PROGS += test_stress_02.sh
+TEST_PROGS += test_stress_03.sh
+TEST_PROGS += test_stress_04.sh
+TEST_PROGS += test_stress_05.sh
TEST_GEN_PROGS_EXTENDED = kublk
include ../lib.mk
-$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c
+$(TEST_GEN_PROGS_EXTENDED): kublk.c null.c file_backed.c common.c stripe.c \
+ fault_inject.c
check:
shellcheck -x -f gcc *.sh
diff --git a/tools/testing/selftests/ublk/fault_inject.c b/tools/testing/selftests/ublk/fault_inject.c
new file mode 100644
index 000000000000..94a8e729ba4c
--- /dev/null
+++ b/tools/testing/selftests/ublk/fault_inject.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Fault injection ublk target. Hack this up however you like for
+ * testing specific behaviors of ublk_drv. Currently is a null target
+ * with a configurable delay before completing each I/O. This delay can
+ * be used to test ublk_drv's handling of I/O outstanding to the ublk
+ * server when it dies.
+ */
+
+#include "kublk.h"
+
+static int ublk_fault_inject_tgt_init(const struct dev_ctx *ctx,
+ struct ublk_dev *dev)
+{
+ const struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
+ unsigned long dev_size = 250UL << 30;
+
+ dev->tgt.dev_size = dev_size;
+ dev->tgt.params = (struct ublk_params) {
+ .types = UBLK_PARAM_TYPE_BASIC,
+ .basic = {
+ .logical_bs_shift = 9,
+ .physical_bs_shift = 12,
+ .io_opt_shift = 12,
+ .io_min_shift = 9,
+ .max_sectors = info->max_io_buf_bytes >> 9,
+ .dev_sectors = dev_size >> 9,
+ },
+ };
+
+ dev->private_data = (void *)(unsigned long)(ctx->fault_inject.delay_us * 1000);
+ return 0;
+}
+
+static int ublk_fault_inject_queue_io(struct ublk_queue *q, int tag)
+{
+ const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+ struct io_uring_sqe *sqe;
+ struct __kernel_timespec ts = {
+ .tv_nsec = (long long)q->dev->private_data,
+ };
+
+ ublk_queue_alloc_sqes(q, &sqe, 1);
+ io_uring_prep_timeout(sqe, &ts, 1, 0);
+ sqe->user_data = build_user_data(tag, ublksrv_get_op(iod), 0, 1);
+
+ ublk_queued_tgt_io(q, tag, 1);
+
+ return 0;
+}
+
+static void ublk_fault_inject_tgt_io_done(struct ublk_queue *q, int tag,
+ const struct io_uring_cqe *cqe)
+{
+ const struct ublksrv_io_desc *iod = ublk_get_iod(q, tag);
+
+ if (cqe->res != -ETIME)
+ ublk_err("%s: unexpected cqe res %d\n", __func__, cqe->res);
+
+ if (ublk_completed_tgt_io(q, tag))
+ ublk_complete_io(q, tag, iod->nr_sectors << 9);
+ else
+ ublk_err("%s: io not complete after 1 cqe\n", __func__);
+}
+
+static void ublk_fault_inject_cmd_line(struct dev_ctx *ctx, int argc, char *argv[])
+{
+ static const struct option longopts[] = {
+ { "delay_us", 1, NULL, 0 },
+ { 0, 0, 0, 0 }
+ };
+ int option_idx, opt;
+
+ ctx->fault_inject.delay_us = 0;
+ while ((opt = getopt_long(argc, argv, "",
+ longopts, &option_idx)) != -1) {
+ switch (opt) {
+ case 0:
+ if (!strcmp(longopts[option_idx].name, "delay_us"))
+ ctx->fault_inject.delay_us = strtoll(optarg, NULL, 10);
+ }
+ }
+}
+
+static void ublk_fault_inject_usage(const struct ublk_tgt_ops *ops)
+{
+ printf("\tfault_inject: [--delay_us us (default 0)]\n");
+}
+
+const struct ublk_tgt_ops fault_inject_tgt_ops = {
+ .name = "fault_inject",
+ .init_tgt = ublk_fault_inject_tgt_init,
+ .queue_io = ublk_fault_inject_queue_io,
+ .tgt_io_done = ublk_fault_inject_tgt_io_done,
+ .parse_cmd_line = ublk_fault_inject_cmd_line,
+ .usage = ublk_fault_inject_usage,
+};
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index 05147b53c361..759f06637146 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -5,22 +5,24 @@
#include "kublk.h"
+#define MAX_NR_TGT_ARG 64
+
unsigned int ublk_dbg_mask = UBLK_LOG;
static const struct ublk_tgt_ops *tgt_ops_list[] = {
&null_tgt_ops,
&loop_tgt_ops,
&stripe_tgt_ops,
+ &fault_inject_tgt_ops,
};
static const struct ublk_tgt_ops *ublk_find_tgt(const char *name)
{
- const struct ublk_tgt_ops *ops;
int i;
if (name == NULL)
return NULL;
- for (i = 0; sizeof(tgt_ops_list) / sizeof(ops); i++)
+ for (i = 0; i < ARRAY_SIZE(tgt_ops_list); i++)
if (strcmp(tgt_ops_list[i]->name, name) == 0)
return tgt_ops_list[i];
return NULL;
@@ -99,7 +101,7 @@ static int __ublk_ctrl_cmd(struct ublk_dev *dev,
static int ublk_ctrl_stop_dev(struct ublk_dev *dev)
{
struct ublk_ctrl_cmd_data data = {
- .cmd_op = UBLK_CMD_STOP_DEV,
+ .cmd_op = UBLK_U_CMD_STOP_DEV,
};
return __ublk_ctrl_cmd(dev, &data);
@@ -118,6 +120,27 @@ static int ublk_ctrl_start_dev(struct ublk_dev *dev,
return __ublk_ctrl_cmd(dev, &data);
}
+static int ublk_ctrl_start_user_recovery(struct ublk_dev *dev)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_START_USER_RECOVERY,
+ };
+
+ return __ublk_ctrl_cmd(dev, &data);
+}
+
+static int ublk_ctrl_end_user_recovery(struct ublk_dev *dev, int daemon_pid)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_END_USER_RECOVERY,
+ .flags = CTRL_CMD_HAS_DATA,
+ };
+
+ dev->dev_info.ublksrv_pid = data.data[0] = daemon_pid;
+
+ return __ublk_ctrl_cmd(dev, &data);
+}
+
static int ublk_ctrl_add_dev(struct ublk_dev *dev)
{
struct ublk_ctrl_cmd_data data = {
@@ -169,7 +192,7 @@ static int ublk_ctrl_get_params(struct ublk_dev *dev,
struct ublk_params *params)
{
struct ublk_ctrl_cmd_data data = {
- .cmd_op = UBLK_CMD_GET_PARAMS,
+ .cmd_op = UBLK_U_CMD_GET_PARAMS,
.flags = CTRL_CMD_HAS_BUF,
.addr = (__u64)params,
.len = sizeof(*params),
@@ -207,15 +230,84 @@ static const char *ublk_dev_state_desc(struct ublk_dev *dev)
};
}
+static void ublk_print_cpu_set(const cpu_set_t *set, char *buf, unsigned len)
+{
+ unsigned done = 0;
+ int i;
+
+ for (i = 0; i < CPU_SETSIZE; i++) {
+ if (CPU_ISSET(i, set))
+ done += snprintf(&buf[done], len - done, "%d ", i);
+ }
+}
+
+static void ublk_adjust_affinity(cpu_set_t *set)
+{
+ int j, updated = 0;
+
+ /*
+ * Just keep the 1st CPU now.
+ *
+ * In future, auto affinity selection can be tried.
+ */
+ for (j = 0; j < CPU_SETSIZE; j++) {
+ if (CPU_ISSET(j, set)) {
+ if (!updated) {
+ updated = 1;
+ continue;
+ }
+ CPU_CLR(j, set);
+ }
+ }
+}
+
+/* Caller must free the allocated buffer */
+static int ublk_ctrl_get_affinity(struct ublk_dev *ctrl_dev, cpu_set_t **ptr_buf)
+{
+ struct ublk_ctrl_cmd_data data = {
+ .cmd_op = UBLK_U_CMD_GET_QUEUE_AFFINITY,
+ .flags = CTRL_CMD_HAS_DATA | CTRL_CMD_HAS_BUF,
+ };
+ cpu_set_t *buf;
+ int i, ret;
+
+ buf = malloc(sizeof(cpu_set_t) * ctrl_dev->dev_info.nr_hw_queues);
+ if (!buf)
+ return -ENOMEM;
+
+ for (i = 0; i < ctrl_dev->dev_info.nr_hw_queues; i++) {
+ data.data[0] = i;
+ data.len = sizeof(cpu_set_t);
+ data.addr = (__u64)&buf[i];
+
+ ret = __ublk_ctrl_cmd(ctrl_dev, &data);
+ if (ret < 0) {
+ free(buf);
+ return ret;
+ }
+ ublk_adjust_affinity(&buf[i]);
+ }
+
+ *ptr_buf = buf;
+ return 0;
+}
+
static void ublk_ctrl_dump(struct ublk_dev *dev)
{
struct ublksrv_ctrl_dev_info *info = &dev->dev_info;
struct ublk_params p;
+ cpu_set_t *affinity;
int ret;
ret = ublk_ctrl_get_params(dev, &p);
if (ret < 0) {
- ublk_err("failed to get params %m\n");
+ ublk_err("failed to get params %d %s\n", ret, strerror(-ret));
+ return;
+ }
+
+ ret = ublk_ctrl_get_affinity(dev, &affinity);
+ if (ret < 0) {
+ ublk_err("failed to get affinity %m\n");
return;
}
@@ -225,6 +317,19 @@ static void ublk_ctrl_dump(struct ublk_dev *dev)
ublk_log("\tmax rq size %d daemon pid %d flags 0x%llx state %s\n",
info->max_io_buf_bytes, info->ublksrv_pid, info->flags,
ublk_dev_state_desc(dev));
+
+ if (affinity) {
+ char buf[512];
+ int i;
+
+ for (i = 0; i < info->nr_hw_queues; i++) {
+ ublk_print_cpu_set(&affinity[i], buf, sizeof(buf));
+ printf("\tqueue %u: tid %d affinity(%s)\n",
+ i, dev->q[i].tid, buf);
+ }
+ free(affinity);
+ }
+
fflush(stdout);
}
@@ -322,7 +427,7 @@ static int ublk_queue_init(struct ublk_queue *q)
cmd_buf_size = ublk_queue_cmd_buf_sz(q);
off = UBLKSRV_CMD_BUF_OFFSET + q->q_id * ublk_queue_max_cmd_buf_sz();
- q->io_cmd_buf = (char *)mmap(0, cmd_buf_size, PROT_READ,
+ q->io_cmd_buf = mmap(0, cmd_buf_size, PROT_READ,
MAP_SHARED | MAP_POPULATE, dev->fds[0], off);
if (q->io_cmd_buf == MAP_FAILED) {
ublk_err("ublk dev %d queue %d map io_cmd_buf failed %m\n",
@@ -347,7 +452,9 @@ static int ublk_queue_init(struct ublk_queue *q)
}
ret = ublk_setup_ring(&q->ring, ring_depth, cq_depth,
- IORING_SETUP_COOP_TASKRUN);
+ IORING_SETUP_COOP_TASKRUN |
+ IORING_SETUP_SINGLE_ISSUER |
+ IORING_SETUP_DEFER_TASKRUN);
if (ret < 0) {
ublk_err("ublk dev %d queue %d setup io_uring failed %d\n",
q->dev->dev_info.dev_id, q->q_id, ret);
@@ -602,9 +709,24 @@ static int ublk_process_io(struct ublk_queue *q)
return reapped;
}
+static void ublk_queue_set_sched_affinity(const struct ublk_queue *q,
+ cpu_set_t *cpuset)
+{
+ if (sched_setaffinity(0, sizeof(*cpuset), cpuset) < 0)
+ ublk_err("ublk dev %u queue %u set affinity failed",
+ q->dev->dev_info.dev_id, q->q_id);
+}
+
+struct ublk_queue_info {
+ struct ublk_queue *q;
+ sem_t *queue_sem;
+ cpu_set_t *affinity;
+};
+
static void *ublk_io_handler_fn(void *data)
{
- struct ublk_queue *q = data;
+ struct ublk_queue_info *info = data;
+ struct ublk_queue *q = info->q;
int dev_id = q->dev->dev_info.dev_id;
int ret;
@@ -614,6 +736,10 @@ static void *ublk_io_handler_fn(void *data)
dev_id, q->q_id);
return NULL;
}
+ /* IO perf is sensitive with queue pthread affinity on NUMA machine*/
+ ublk_queue_set_sched_affinity(q, info->affinity);
+ sem_post(info->queue_sem);
+
ublk_dbg(UBLK_DBG_QUEUE, "tid %d: ublk dev %d queue %d started\n",
q->tid, dev_id, q->q_id);
@@ -639,7 +765,7 @@ static void ublk_set_parameters(struct ublk_dev *dev)
dev->dev_info.dev_id, ret);
}
-static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id)
+static int ublk_send_dev_event(const struct dev_ctx *ctx, struct ublk_dev *dev, int dev_id)
{
uint64_t id;
int evtfd = ctx->_evtfd;
@@ -652,36 +778,68 @@ static int ublk_send_dev_event(const struct dev_ctx *ctx, int dev_id)
else
id = ERROR_EVTFD_DEVID;
+ if (dev && ctx->shadow_dev)
+ memcpy(&ctx->shadow_dev->q, &dev->q, sizeof(dev->q));
+
if (write(evtfd, &id, sizeof(id)) != sizeof(id))
return -EINVAL;
+ close(evtfd);
+ shmdt(ctx->shadow_dev);
+
return 0;
}
static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
{
- int ret, i;
- void *thread_ret;
const struct ublksrv_ctrl_dev_info *dinfo = &dev->dev_info;
+ struct ublk_queue_info *qinfo;
+ cpu_set_t *affinity_buf;
+ void *thread_ret;
+ sem_t queue_sem;
+ int ret, i;
ublk_dbg(UBLK_DBG_DEV, "%s enter\n", __func__);
+ qinfo = (struct ublk_queue_info *)calloc(sizeof(struct ublk_queue_info),
+ dinfo->nr_hw_queues);
+ if (!qinfo)
+ return -ENOMEM;
+
+ sem_init(&queue_sem, 0, 0);
ret = ublk_dev_prep(ctx, dev);
if (ret)
return ret;
+ ret = ublk_ctrl_get_affinity(dev, &affinity_buf);
+ if (ret)
+ return ret;
+
for (i = 0; i < dinfo->nr_hw_queues; i++) {
dev->q[i].dev = dev;
dev->q[i].q_id = i;
+
+ qinfo[i].q = &dev->q[i];
+ qinfo[i].queue_sem = &queue_sem;
+ qinfo[i].affinity = &affinity_buf[i];
pthread_create(&dev->q[i].thread, NULL,
ublk_io_handler_fn,
- &dev->q[i]);
+ &qinfo[i]);
}
+ for (i = 0; i < dinfo->nr_hw_queues; i++)
+ sem_wait(&queue_sem);
+ free(qinfo);
+ free(affinity_buf);
+
/* everything is fine now, start us */
- ublk_set_parameters(dev);
- ret = ublk_ctrl_start_dev(dev, getpid());
+ if (ctx->recovery)
+ ret = ublk_ctrl_end_user_recovery(dev, getpid());
+ else {
+ ublk_set_parameters(dev);
+ ret = ublk_ctrl_start_dev(dev, getpid());
+ }
if (ret < 0) {
ublk_err("%s: ublk_ctrl_start_dev failed: %d\n", __func__, ret);
goto fail;
@@ -691,7 +849,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
if (ctx->fg)
ublk_ctrl_dump(dev);
else
- ublk_send_dev_event(ctx, dev->dev_info.dev_id);
+ ublk_send_dev_event(ctx, dev, dev->dev_info.dev_id);
/* wait until we are terminated */
for (i = 0; i < dinfo->nr_hw_queues; i++)
@@ -856,7 +1014,10 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
}
}
- ret = ublk_ctrl_add_dev(dev);
+ if (ctx->recovery)
+ ret = ublk_ctrl_start_user_recovery(dev);
+ else
+ ret = ublk_ctrl_add_dev(dev);
if (ret < 0) {
ublk_err("%s: can't add dev id %d, type %s ret %d\n",
__func__, dev_id, tgt_type, ret);
@@ -870,7 +1031,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx)
fail:
if (ret < 0)
- ublk_send_dev_event(ctx, -1);
+ ublk_send_dev_event(ctx, dev, -1);
ublk_ctrl_deinit(dev);
return ret;
}
@@ -884,30 +1045,58 @@ static int cmd_dev_add(struct dev_ctx *ctx)
if (ctx->fg)
goto run;
+ ctx->_shmid = shmget(IPC_PRIVATE, sizeof(struct ublk_dev), IPC_CREAT | 0666);
+ if (ctx->_shmid < 0) {
+ ublk_err("%s: failed to shmget %s\n", __func__, strerror(errno));
+ exit(-1);
+ }
+ ctx->shadow_dev = (struct ublk_dev *)shmat(ctx->_shmid, NULL, 0);
+ if (ctx->shadow_dev == (struct ublk_dev *)-1) {
+ ublk_err("%s: failed to shmat %s\n", __func__, strerror(errno));
+ exit(-1);
+ }
ctx->_evtfd = eventfd(0, 0);
if (ctx->_evtfd < 0) {
ublk_err("%s: failed to create eventfd %s\n", __func__, strerror(errno));
exit(-1);
}
- setsid();
res = fork();
if (res == 0) {
+ int res2;
+
+ setsid();
+ res2 = fork();
+ if (res2 == 0) {
+ /* prepare for detaching */
+ close(STDIN_FILENO);
+ close(STDOUT_FILENO);
+ close(STDERR_FILENO);
run:
- res = __cmd_dev_add(ctx);
- return res;
+ res = __cmd_dev_add(ctx);
+ return res;
+ } else {
+ /* detached from the foreground task */
+ exit(EXIT_SUCCESS);
+ }
} else if (res > 0) {
uint64_t id;
+ int exit_code = EXIT_FAILURE;
res = read(ctx->_evtfd, &id, sizeof(id));
close(ctx->_evtfd);
if (res == sizeof(id) && id != ERROR_EVTFD_DEVID) {
ctx->dev_id = id - 1;
- return __cmd_dev_list(ctx);
+ if (__cmd_dev_list(ctx) >= 0)
+ exit_code = EXIT_SUCCESS;
}
- exit(EXIT_FAILURE);
+ shmdt(ctx->shadow_dev);
+ shmctl(ctx->_shmid, IPC_RMID, NULL);
+ /* wait for child and detach from it */
+ wait(NULL);
+ exit(exit_code);
} else {
- return res;
+ exit(EXIT_FAILURE);
}
}
@@ -969,6 +1158,9 @@ static int __cmd_dev_list(struct dev_ctx *ctx)
ublk_err("%s: can't get dev info from %d: %d\n",
__func__, ctx->dev_id, ret);
} else {
+ if (ctx->shadow_dev)
+ memcpy(&dev->q, ctx->shadow_dev->q, sizeof(dev->q));
+
ublk_ctrl_dump(dev);
}
@@ -1039,14 +1231,47 @@ static int cmd_dev_get_features(void)
return ret;
}
+static void __cmd_create_help(char *exe, bool recovery)
+{
+ int i;
+
+ printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n",
+ exe, recovery ? "recover" : "add");
+ printf("\t[--foreground] [--quiet] [-z] [--debug_mask mask] [-r 0|1 ] [-g 0|1]\n");
+ printf("\t[-e 0|1 ] [-i 0|1]\n");
+ printf("\t[target options] [backfile1] [backfile2] ...\n");
+ printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
+
+ for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) {
+ const struct ublk_tgt_ops *ops = tgt_ops_list[i];
+
+ if (ops->usage)
+ ops->usage(ops);
+ }
+}
+
+static void cmd_add_help(char *exe)
+{
+ __cmd_create_help(exe, false);
+ printf("\n");
+}
+
+static void cmd_recover_help(char *exe)
+{
+ __cmd_create_help(exe, true);
+ printf("\tPlease provide exact command line for creating this device with real dev_id\n");
+ printf("\n");
+}
+
static int cmd_dev_help(char *exe)
{
- printf("%s add -t [null|loop] [-q nr_queues] [-d depth] [-n dev_id] [backfile1] [backfile2] ...\n", exe);
- printf("\t default: nr_queues=2(max 4), depth=128(max 128), dev_id=-1(auto allocation)\n");
+ cmd_add_help(exe);
+ cmd_recover_help(exe);
+
printf("%s del [-n dev_id] -a \n", exe);
- printf("\t -a delete all devices -n delete specified device\n");
+ printf("\t -a delete all devices -n delete specified device\n\n");
printf("%s list [-n dev_id] -a \n", exe);
- printf("\t -a list all devices, -n list specified device, default -a \n");
+ printf("\t -a list all devices, -n list specified device, default -a \n\n");
printf("%s features\n", exe);
return 0;
}
@@ -1063,9 +1288,13 @@ int main(int argc, char *argv[])
{ "quiet", 0, NULL, 0 },
{ "zero_copy", 0, NULL, 'z' },
{ "foreground", 0, NULL, 0 },
- { "chunk_size", 1, NULL, 0 },
+ { "recovery", 1, NULL, 'r' },
+ { "recovery_fail_io", 1, NULL, 'e'},
+ { "recovery_reissue", 1, NULL, 'i'},
+ { "get_data", 1, NULL, 'g'},
{ 0, 0, 0, 0 }
};
+ const struct ublk_tgt_ops *ops = NULL;
int option_idx, opt;
const char *cmd = argv[1];
struct dev_ctx ctx = {
@@ -1073,15 +1302,18 @@ int main(int argc, char *argv[])
.nr_hw_queues = 2,
.dev_id = -1,
.tgt_type = "unknown",
- .chunk_size = 65536, /* def chunk size is 64K */
};
int ret = -EINVAL, i;
+ int tgt_argc = 1;
+ char *tgt_argv[MAX_NR_TGT_ARG] = { NULL };
+ int value;
if (argc == 1)
return ret;
+ opterr = 0;
optind = 2;
- while ((opt = getopt_long(argc, argv, "t:n:d:q:az",
+ while ((opt = getopt_long(argc, argv, "t:n:d:q:r:e:i:az",
longopts, &option_idx)) != -1) {
switch (opt) {
case 'a':
@@ -1103,6 +1335,25 @@ int main(int argc, char *argv[])
case 'z':
ctx.flags |= UBLK_F_SUPPORT_ZERO_COPY | UBLK_F_USER_COPY;
break;
+ case 'r':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_USER_RECOVERY;
+ break;
+ case 'e':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_FAIL_IO;
+ break;
+ case 'i':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_REISSUE;
+ break;
+ case 'g':
+ value = strtol(optarg, NULL, 10);
+ if (value)
+ ctx.flags |= UBLK_F_NEED_GET_DATA;
case 0:
if (!strcmp(longopts[option_idx].name, "debug_mask"))
ublk_dbg_mask = strtol(optarg, NULL, 16);
@@ -1110,8 +1361,26 @@ int main(int argc, char *argv[])
ublk_dbg_mask = 0;
if (!strcmp(longopts[option_idx].name, "foreground"))
ctx.fg = 1;
- if (!strcmp(longopts[option_idx].name, "chunk_size"))
- ctx.chunk_size = strtol(optarg, NULL, 10);
+ break;
+ case '?':
+ /*
+ * target requires every option must have argument
+ */
+ if (argv[optind][0] == '-' || argv[optind - 1][0] != '-') {
+ fprintf(stderr, "every target option requires argument: %s %s\n",
+ argv[optind - 1], argv[optind]);
+ exit(EXIT_FAILURE);
+ }
+
+ if (tgt_argc < (MAX_NR_TGT_ARG - 1) / 2) {
+ tgt_argv[tgt_argc++] = argv[optind - 1];
+ tgt_argv[tgt_argc++] = argv[optind];
+ } else {
+ fprintf(stderr, "too many target options\n");
+ exit(EXIT_FAILURE);
+ }
+ optind += 1;
+ break;
}
}
@@ -1120,9 +1389,25 @@ int main(int argc, char *argv[])
ctx.files[ctx.nr_files++] = argv[i++];
}
+ ops = ublk_find_tgt(ctx.tgt_type);
+ if (ops && ops->parse_cmd_line) {
+ optind = 0;
+
+ tgt_argv[0] = ctx.tgt_type;
+ ops->parse_cmd_line(&ctx, tgt_argc, tgt_argv);
+ }
+
if (!strcmp(cmd, "add"))
ret = cmd_dev_add(&ctx);
- else if (!strcmp(cmd, "del"))
+ else if (!strcmp(cmd, "recover")) {
+ if (ctx.dev_id < 0) {
+ fprintf(stderr, "device id isn't provided for recovering\n");
+ ret = -EINVAL;
+ } else {
+ ctx.recovery = 1;
+ ret = cmd_dev_add(&ctx);
+ }
+ } else if (!strcmp(cmd, "del"))
ret = cmd_dev_del(&ctx);
else if (!strcmp(cmd, "list")) {
ctx.all = 1;
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
index f31a5c4d4143..29571eb296f1 100644
--- a/tools/testing/selftests/ublk/kublk.h
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -20,9 +20,15 @@
#include <sys/wait.h>
#include <sys/eventfd.h>
#include <sys/uio.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <linux/io_uring.h>
#include <liburing.h>
-#include <linux/ublk_cmd.h>
+#include <semaphore.h>
+
+/* allow ublk_dep.h to override ublk_cmd.h */
#include "ublk_dep.h"
+#include <linux/ublk_cmd.h>
#define __maybe_unused __attribute__((unused))
#define MAX_BACK_FILES 4
@@ -30,6 +36,8 @@
#define min(a, b) ((a) < (b) ? (a) : (b))
#endif
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(x[0]))
+
/****************** part 1: libublk ********************/
#define CTRL_DEV "/dev/ublk-control"
@@ -42,8 +50,8 @@
#define UBLKSRV_IO_IDLE_SECS 20
#define UBLK_IO_MAX_BYTES (1 << 20)
-#define UBLK_MAX_QUEUES 4
-#define UBLK_QUEUE_DEPTH 128
+#define UBLK_MAX_QUEUES 32
+#define UBLK_QUEUE_DEPTH 1024
#define UBLK_DBG_DEV (1U << 0)
#define UBLK_DBG_QUEUE (1U << 1)
@@ -55,6 +63,16 @@
struct ublk_dev;
struct ublk_queue;
+struct stripe_ctx {
+ /* stripe */
+ unsigned int chunk_size;
+};
+
+struct fault_inject_ctx {
+ /* fault_inject */
+ unsigned long delay_us;
+};
+
struct dev_ctx {
char tgt_type[16];
unsigned long flags;
@@ -66,11 +84,21 @@ struct dev_ctx {
unsigned int logging:1;
unsigned int all:1;
unsigned int fg:1;
+ unsigned int recovery:1;
- /* stripe */
- unsigned int chunk_size;
+ /* fault_inject */
+ long long delay_us;
int _evtfd;
+ int _shmid;
+
+ /* built from shmem, only for ublk_dump_dev() */
+ struct ublk_dev *shadow_dev;
+
+ union {
+ struct stripe_ctx stripe;
+ struct fault_inject_ctx fault_inject;
+ };
};
struct ublk_ctrl_cmd_data {
@@ -107,6 +135,14 @@ struct ublk_tgt_ops {
int (*queue_io)(struct ublk_queue *, int tag);
void (*tgt_io_done)(struct ublk_queue *,
int tag, const struct io_uring_cqe *);
+
+ /*
+ * Target specific command line handling
+ *
+ * each option requires argument for target command line
+ */
+ void (*parse_cmd_line)(struct dev_ctx *ctx, int argc, char *argv[]);
+ void (*usage)(const struct ublk_tgt_ops *ops);
};
struct ublk_tgt {
@@ -128,7 +164,7 @@ struct ublk_queue {
unsigned int io_inflight;
struct ublk_dev *dev;
const struct ublk_tgt_ops *tgt_ops;
- char *io_cmd_buf;
+ struct ublksrv_io_desc *io_cmd_buf;
struct io_uring ring;
struct ublk_io ios[UBLK_QUEUE_DEPTH];
#define UBLKSRV_QUEUE_STOPPING (1U << 0)
@@ -302,7 +338,7 @@ static inline void ublk_mark_io_done(struct ublk_io *io, int res)
static inline const struct ublksrv_io_desc *ublk_get_iod(const struct ublk_queue *q, int tag)
{
- return (struct ublksrv_io_desc *)&(q->io_cmd_buf[tag * sizeof(struct ublksrv_io_desc)]);
+ return &q->io_cmd_buf[tag];
}
static inline void ublk_set_sqe_cmd_op(struct io_uring_sqe *sqe, __u32 cmd_op)
@@ -357,6 +393,7 @@ static inline int ublk_queue_use_zc(const struct ublk_queue *q)
extern const struct ublk_tgt_ops null_tgt_ops;
extern const struct ublk_tgt_ops loop_tgt_ops;
extern const struct ublk_tgt_ops stripe_tgt_ops;
+extern const struct ublk_tgt_ops fault_inject_tgt_ops;
void backing_file_tgt_deinit(struct ublk_dev *dev);
int backing_file_tgt_init(struct ublk_dev *dev);
diff --git a/tools/testing/selftests/ublk/null.c b/tools/testing/selftests/ublk/null.c
index 899875ff50fe..91fec3690d4b 100644
--- a/tools/testing/selftests/ublk/null.c
+++ b/tools/testing/selftests/ublk/null.c
@@ -17,7 +17,8 @@ static int ublk_null_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
dev->tgt.dev_size = dev_size;
dev->tgt.params = (struct ublk_params) {
- .types = UBLK_PARAM_TYPE_BASIC,
+ .types = UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DMA_ALIGN |
+ UBLK_PARAM_TYPE_SEGMENT,
.basic = {
.logical_bs_shift = 9,
.physical_bs_shift = 12,
@@ -26,6 +27,14 @@ static int ublk_null_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
.max_sectors = info->max_io_buf_bytes >> 9,
.dev_sectors = dev_size >> 9,
},
+ .dma = {
+ .alignment = 4095,
+ },
+ .seg = {
+ .seg_boundary_mask = 4095,
+ .max_segment_size = 32 << 10,
+ .max_segments = 32,
+ },
};
if (info->flags & UBLK_F_SUPPORT_ZERO_COPY)
diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c
index 98c564b12f3c..5dbd6392d83d 100644
--- a/tools/testing/selftests/ublk/stripe.c
+++ b/tools/testing/selftests/ublk/stripe.c
@@ -111,43 +111,67 @@ static void calculate_stripe_array(const struct stripe_conf *conf,
}
}
-static inline enum io_uring_op stripe_to_uring_op(const struct ublksrv_io_desc *iod)
+static inline enum io_uring_op stripe_to_uring_op(
+ const struct ublksrv_io_desc *iod, int zc)
{
unsigned ublk_op = ublksrv_get_op(iod);
if (ublk_op == UBLK_IO_OP_READ)
- return IORING_OP_READV;
+ return zc ? IORING_OP_READV_FIXED : IORING_OP_READV;
else if (ublk_op == UBLK_IO_OP_WRITE)
- return IORING_OP_WRITEV;
+ return zc ? IORING_OP_WRITEV_FIXED : IORING_OP_WRITEV;
assert(0);
}
static int stripe_queue_tgt_rw_io(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag)
{
const struct stripe_conf *conf = get_chunk_shift(q);
- enum io_uring_op op = stripe_to_uring_op(iod);
+ int zc = !!(ublk_queue_use_zc(q) != 0);
+ enum io_uring_op op = stripe_to_uring_op(iod, zc);
struct io_uring_sqe *sqe[NR_STRIPE];
struct stripe_array *s = alloc_stripe_array(conf, iod);
struct ublk_io *io = ublk_get_io(q, tag);
- int i;
+ int i, extra = zc ? 2 : 0;
io->private_data = s;
calculate_stripe_array(conf, iod, s);
- ublk_queue_alloc_sqes(q, sqe, s->nr);
- for (i = 0; i < s->nr; i++) {
- struct stripe *t = &s->s[i];
+ ublk_queue_alloc_sqes(q, sqe, s->nr + extra);
+
+ if (zc) {
+ io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, tag);
+ sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
+ sqe[0]->user_data = build_user_data(tag,
+ ublk_cmd_op_nr(sqe[0]->cmd_op), 0, 1);
+ }
+
+ for (i = zc; i < s->nr + extra - zc; i++) {
+ struct stripe *t = &s->s[i - zc];
io_uring_prep_rw(op, sqe[i],
t->seq + 1,
(void *)t->vec,
t->nr_vec,
t->start << 9);
- io_uring_sqe_set_flags(sqe[i], IOSQE_FIXED_FILE);
+ if (zc) {
+ sqe[i]->buf_index = tag;
+ io_uring_sqe_set_flags(sqe[i],
+ IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK);
+ } else {
+ io_uring_sqe_set_flags(sqe[i], IOSQE_FIXED_FILE);
+ }
/* bit63 marks us as tgt io */
- sqe[i]->user_data = build_user_data(tag, ublksrv_get_op(iod), i, 1);
+ sqe[i]->user_data = build_user_data(tag, ublksrv_get_op(iod), i - zc, 1);
+ }
+ if (zc) {
+ struct io_uring_sqe *unreg = sqe[s->nr + 1];
+
+ io_uring_prep_buf_unregister(unreg, 0, tag, q->q_id, tag);
+ unreg->user_data = build_user_data(tag, ublk_cmd_op_nr(unreg->cmd_op), 0, 1);
}
- return s->nr;
+
+ /* register buffer is skip_success */
+ return s->nr + zc;
}
static int handle_flush(struct ublk_queue *q, const struct ublksrv_io_desc *iod, int tag)
@@ -208,19 +232,27 @@ static void ublk_stripe_io_done(struct ublk_queue *q, int tag,
struct ublk_io *io = ublk_get_io(q, tag);
int res = cqe->res;
- if (res < 0) {
+ if (res < 0 || op != ublk_cmd_op_nr(UBLK_U_IO_UNREGISTER_IO_BUF)) {
if (!io->result)
io->result = res;
- ublk_err("%s: io failure %d tag %u\n", __func__, res, tag);
+ if (res < 0)
+ ublk_err("%s: io failure %d tag %u\n", __func__, res, tag);
}
+ /* buffer register op is IOSQE_CQE_SKIP_SUCCESS */
+ if (op == ublk_cmd_op_nr(UBLK_U_IO_REGISTER_IO_BUF))
+ io->tgt_ios += 1;
+
/* fail short READ/WRITE simply */
if (op == UBLK_IO_OP_READ || op == UBLK_IO_OP_WRITE) {
unsigned seq = user_data_to_tgt_data(cqe->user_data);
struct stripe_array *s = io->private_data;
- if (res < s->s[seq].vec->iov_len)
+ if (res < s->s[seq].nr_sects << 9) {
io->result = -EIO;
+ ublk_err("%s: short rw op %u res %d exp %u tag %u\n",
+ __func__, op, res, s->s[seq].vec->iov_len, tag);
+ }
}
if (ublk_completed_tgt_io(q, tag)) {
@@ -249,11 +281,11 @@ static int ublk_stripe_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
.max_sectors = dev->dev_info.max_io_buf_bytes >> 9,
},
};
- unsigned chunk_size = ctx->chunk_size;
+ unsigned chunk_size = ctx->stripe.chunk_size;
struct stripe_conf *conf;
unsigned chunk_shift;
loff_t bytes = 0;
- int ret, i;
+ int ret, i, mul = 1;
if ((chunk_size & (chunk_size - 1)) || !chunk_size) {
ublk_err("invalid chunk size %u\n", chunk_size);
@@ -295,8 +327,11 @@ static int ublk_stripe_tgt_init(const struct dev_ctx *ctx, struct ublk_dev *dev)
dev->tgt.dev_size = bytes;
p.basic.dev_sectors = bytes >> 9;
dev->tgt.params = p;
- dev->tgt.sq_depth = dev->dev_info.queue_depth * conf->nr_files;
- dev->tgt.cq_depth = dev->dev_info.queue_depth * conf->nr_files;
+
+ if (dev->dev_info.flags & UBLK_F_SUPPORT_ZERO_COPY)
+ mul = 2;
+ dev->tgt.sq_depth = mul * dev->dev_info.queue_depth * conf->nr_files;
+ dev->tgt.cq_depth = mul * dev->dev_info.queue_depth * conf->nr_files;
printf("%s: shift %u files %u\n", __func__, conf->shift, conf->nr_files);
@@ -309,10 +344,36 @@ static void ublk_stripe_tgt_deinit(struct ublk_dev *dev)
backing_file_tgt_deinit(dev);
}
+static void ublk_stripe_cmd_line(struct dev_ctx *ctx, int argc, char *argv[])
+{
+ static const struct option longopts[] = {
+ { "chunk_size", 1, NULL, 0 },
+ { 0, 0, 0, 0 }
+ };
+ int option_idx, opt;
+
+ ctx->stripe.chunk_size = 65536;
+ while ((opt = getopt_long(argc, argv, "",
+ longopts, &option_idx)) != -1) {
+ switch (opt) {
+ case 0:
+ if (!strcmp(longopts[option_idx].name, "chunk_size"))
+ ctx->stripe.chunk_size = strtol(optarg, NULL, 10);
+ }
+ }
+}
+
+static void ublk_stripe_usage(const struct ublk_tgt_ops *ops)
+{
+ printf("\tstripe: [--chunk_size chunk_size (default 65536)]\n");
+}
+
const struct ublk_tgt_ops stripe_tgt_ops = {
.name = "stripe",
.init_tgt = ublk_stripe_tgt_init,
.deinit_tgt = ublk_stripe_tgt_deinit,
.queue_io = ublk_stripe_queue_io,
.tgt_io_done = ublk_stripe_io_done,
+ .parse_cmd_line = ublk_stripe_cmd_line,
+ .usage = ublk_stripe_usage,
};
diff --git a/tools/testing/selftests/ublk/test_common.sh b/tools/testing/selftests/ublk/test_common.sh
index 75f54ac6b1c4..9fc111f64576 100755
--- a/tools/testing/selftests/ublk/test_common.sh
+++ b/tools/testing/selftests/ublk/test_common.sh
@@ -23,19 +23,33 @@ _get_disk_dev_t() {
echo $(( (major & 0xfff) << 20 | (minor & 0xfffff) ))
}
+_run_fio_verify_io() {
+ fio --name=verify --rw=randwrite --direct=1 --ioengine=libaio \
+ --bs=8k --iodepth=32 --verify=crc32c --do_verify=1 \
+ --verify_state_save=0 "$@" > /dev/null
+}
+
_create_backfile() {
- local my_size=$1
- local my_file
+ local index=$1
+ local new_size=$2
+ local old_file
+ local new_file
- my_file=$(mktemp ublk_file_"${my_size}"_XXXXX)
- truncate -s "${my_size}" "${my_file}"
- echo "$my_file"
+ old_file="${UBLK_BACKFILES[$index]}"
+ [ -f "$old_file" ] && rm -f "$old_file"
+
+ new_file=$(mktemp ublk_file_"${new_size}"_XXXXX)
+ truncate -s "${new_size}" "${new_file}"
+ UBLK_BACKFILES["$index"]="$new_file"
}
-_remove_backfile() {
- local file=$1
+_remove_files() {
+ local file
- [ -f "$file" ] && rm -f "$file"
+ for file in "${UBLK_BACKFILES[@]}"; do
+ [ -f "$file" ] && rm -f "$file"
+ done
+ [ -f "$UBLK_TMP" ] && rm -f "$UBLK_TMP"
}
_create_tmp_dir() {
@@ -100,6 +114,7 @@ _prep_test() {
local type=$1
shift 1
modprobe ublk_drv > /dev/null 2>&1
+ UBLK_TMP=$(mktemp ublk_test_XXXXX)
[ "$UBLK_TEST_QUIET" -eq 0 ] && echo "ublk $type: $*"
}
@@ -123,7 +138,10 @@ _show_result()
echo "$1 : [FAIL]"
fi
fi
- [ "$2" -ne 0 ] && exit "$2"
+ if [ "$2" -ne 0 ]; then
+ _remove_files
+ exit "$2"
+ fi
return 0
}
@@ -132,16 +150,16 @@ _check_add_dev()
{
local tid=$1
local code=$2
- shift 2
+
if [ "${code}" -ne 0 ]; then
- _remove_test_files "$@"
_show_result "${tid}" "${code}"
fi
}
_cleanup_test() {
"${UBLK_PROG}" del -a
- rm -f "$UBLK_TMP"
+
+ _remove_files
}
_have_feature()
@@ -152,9 +170,11 @@ _have_feature()
return 1
}
-_add_ublk_dev() {
- local kublk_temp;
+_create_ublk_dev() {
local dev_id;
+ local cmd=$1
+
+ shift 1
if [ ! -c /dev/ublk-control ]; then
return ${UBLK_SKIP_CODE}
@@ -165,17 +185,34 @@ _add_ublk_dev() {
fi
fi
- kublk_temp=$(mktemp /tmp/kublk-XXXXXX)
- if ! "${UBLK_PROG}" add "$@" > "${kublk_temp}" 2>&1; then
+ if ! dev_id=$("${UBLK_PROG}" "$cmd" "$@" | grep "dev id" | awk -F '[ :]' '{print $3}'); then
echo "fail to add ublk dev $*"
- rm -f "${kublk_temp}"
return 255
fi
-
- dev_id=$(grep "dev id" "${kublk_temp}" | awk -F '[ :]' '{print $3}')
udevadm settle
- rm -f "${kublk_temp}"
- echo "${dev_id}"
+
+ if [[ "$dev_id" =~ ^[0-9]+$ ]]; then
+ echo "${dev_id}"
+ else
+ return 255
+ fi
+}
+
+_add_ublk_dev() {
+ _create_ublk_dev "add" "$@"
+}
+
+_recover_ublk_dev() {
+ local dev_id
+ local state
+
+ dev_id=$(_create_ublk_dev "recover" "$@")
+ for ((j=0;j<20;j++)); do
+ state=$(_get_ublk_dev_state "${dev_id}")
+ [ "$state" == "LIVE" ] && break
+ sleep 1
+ done
+ echo "$state"
}
# kill the ublk daemon and return ublk device state
@@ -214,7 +251,7 @@ __run_io_and_remove()
local kill_server=$3
fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
- --rw=readwrite --iodepth=64 --size="${size}" --numjobs=4 \
+ --rw=readwrite --iodepth=256 --size="${size}" --numjobs=4 \
--runtime=20 --time_based > /dev/null 2>&1 &
sleep 2
if [ "${kill_server}" = "yes" ]; then
@@ -232,15 +269,80 @@ __run_io_and_remove()
wait
}
+run_io_and_remove()
+{
+ local size=$1
+ local dev_id
+ shift 1
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev "$TID" $?
+
+ [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
+ if ! __run_io_and_remove "$dev_id" "${size}" "no"; then
+ echo "/dev/ublkc$dev_id isn't removed"
+ exit 255
+ fi
+}
+
+run_io_and_kill_daemon()
+{
+ local size=$1
+ local dev_id
+ shift 1
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev "$TID" $?
+
+ [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)"
+ if ! __run_io_and_remove "$dev_id" "${size}" "yes"; then
+ echo "/dev/ublkc$dev_id isn't removed res ${res}"
+ exit 255
+ fi
+}
+
+run_io_and_recover()
+{
+ local state
+ local dev_id
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev "$TID" $?
+
+ fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
+ --rw=readwrite --iodepth=256 --size="${size}" --numjobs=4 \
+ --runtime=20 --time_based > /dev/null 2>&1 &
+ sleep 4
+
+ state=$(__ublk_kill_daemon "${dev_id}" "QUIESCED")
+ if [ "$state" != "QUIESCED" ]; then
+ echo "device isn't quiesced($state) after killing daemon"
+ return 255
+ fi
+
+ state=$(_recover_ublk_dev -n "$dev_id" "$@")
+ if [ "$state" != "LIVE" ]; then
+ echo "faile to recover to LIVE($state)"
+ return 255
+ fi
+
+ if ! __remove_ublk_dev_return "${dev_id}"; then
+ echo "delete dev ${dev_id} failed"
+ return 255
+ fi
+ wait
+}
+
+
_ublk_test_top_dir()
{
cd "$(dirname "$0")" && pwd
}
-UBLK_TMP=$(mktemp ublk_test_XXXXX)
UBLK_PROG=$(_ublk_test_top_dir)/kublk
UBLK_TEST_QUIET=1
UBLK_TEST_SHOW_RESULT=1
+UBLK_BACKFILES=()
export UBLK_PROG
export UBLK_TEST_QUIET
export UBLK_TEST_SHOW_RESULT
diff --git a/tools/testing/selftests/ublk/test_generic_02.sh b/tools/testing/selftests/ublk/test_generic_02.sh
new file mode 100755
index 000000000000..3e80121e3bf5
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_02.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_02"
+ERR_CODE=0
+
+if ! _have_program bpftrace; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "null" "sequential io order for MQ"
+
+dev_id=$(_add_ublk_dev -t null -q 2)
+_check_add_dev $TID $?
+
+dev_t=$(_get_disk_dev_t "$dev_id")
+bpftrace trace/seq_io.bt "$dev_t" "W" 1 > "$UBLK_TMP" 2>&1 &
+btrace_pid=$!
+sleep 2
+
+if ! kill -0 "$btrace_pid" > /dev/null 2>&1; then
+ _cleanup_test "null"
+ exit "$UBLK_SKIP_CODE"
+fi
+
+# run fio over this ublk disk
+fio --name=write_seq \
+ --filename=/dev/ublkb"${dev_id}" \
+ --ioengine=libaio --iodepth=16 \
+ --rw=write \
+ --size=512M \
+ --direct=1 \
+ --bs=4k > /dev/null 2>&1
+ERR_CODE=$?
+kill "$btrace_pid"
+wait
+if grep -q "io_out_of_order" "$UBLK_TMP"; then
+ cat "$UBLK_TMP"
+ ERR_CODE=255
+fi
+_cleanup_test "null"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_03.sh b/tools/testing/selftests/ublk/test_generic_03.sh
new file mode 100755
index 000000000000..b551aa76cb0d
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_03.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_03"
+ERR_CODE=0
+
+_prep_test "null" "check dma & segment limits for zero copy"
+
+dev_id=$(_add_ublk_dev -t null -z)
+_check_add_dev $TID $?
+
+sysfs_path=/sys/block/ublkb"${dev_id}"
+dma_align=$(cat "$sysfs_path"/queue/dma_alignment)
+max_segments=$(cat "$sysfs_path"/queue/max_segments)
+max_segment_size=$(cat "$sysfs_path"/queue/max_segment_size)
+if [ "$dma_align" != "4095" ]; then
+ ERR_CODE=255
+fi
+if [ "$max_segments" != "32" ]; then
+ ERR_CODE=255
+fi
+if [ "$max_segment_size" != "32768" ]; then
+ ERR_CODE=255
+fi
+_cleanup_test "null"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_04.sh b/tools/testing/selftests/ublk/test_generic_04.sh
new file mode 100755
index 000000000000..8a3bc080c577
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_04.sh
@@ -0,0 +1,40 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_04"
+ERR_CODE=0
+
+ublk_run_recover_test()
+{
+ run_io_and_recover "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "recover" "basic recover function verification"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_run_recover_test -t null -q 2 -r 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+ublk_run_recover_test -t null -q 2 -r 1 -i 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 -i 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "recover"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_05.sh b/tools/testing/selftests/ublk/test_generic_05.sh
new file mode 100755
index 000000000000..714630b4b329
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_05.sh
@@ -0,0 +1,44 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_04"
+ERR_CODE=0
+
+ublk_run_recover_test()
+{
+ run_io_and_recover "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+if ! _have_feature "ZERO_COPY"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "recover" "basic recover function verification (zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_run_recover_test -t null -q 2 -r 1 -z &
+ublk_run_recover_test -t loop -q 2 -r 1 -z "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+ublk_run_recover_test -t null -q 2 -r 1 -z -i 1 &
+ublk_run_recover_test -t loop -q 2 -r 1 -z -i 1 "${UBLK_BACKFILES[0]}" &
+ublk_run_recover_test -t stripe -q 2 -r 1 -z -i 1 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "recover"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_generic_06.sh b/tools/testing/selftests/ublk/test_generic_06.sh
new file mode 100755
index 000000000000..b67230c42c84
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_generic_06.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="generic_06"
+ERR_CODE=0
+
+_prep_test "fault_inject" "fast cleanup when all I/Os of one hctx are in server"
+
+# configure ublk server to sleep 2s before completing each I/O
+dev_id=$(_add_ublk_dev -t fault_inject -q 2 -d 1 --delay_us 2000000)
+_check_add_dev $TID $?
+
+STARTTIME=${SECONDS}
+
+dd if=/dev/urandom of=/dev/ublkb${dev_id} oflag=direct bs=4k count=1 status=none > /dev/null 2>&1 &
+dd_pid=$!
+
+__ublk_kill_daemon ${dev_id} "DEAD"
+
+wait $dd_pid
+dd_exitcode=$?
+
+ENDTIME=${SECONDS}
+ELAPSED=$(($ENDTIME - $STARTTIME))
+
+# assert that dd sees an error and exits quickly after ublk server is
+# killed. previously this relied on seeing an I/O timeout and so would
+# take ~30s
+if [ $dd_exitcode -eq 0 ]; then
+ echo "dd unexpectedly exited successfully!"
+ ERR_CODE=255
+fi
+if [ $ELAPSED -ge 5 ]; then
+ echo "dd took $ELAPSED seconds to exit (>= 5s tolerance)!"
+ ERR_CODE=255
+fi
+
+_cleanup_test "fault_inject"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_01.sh b/tools/testing/selftests/ublk/test_loop_01.sh
index c882d2a08e13..833fa0dbc700 100755
--- a/tools/testing/selftests/ublk/test_loop_01.sh
+++ b/tools/testing/selftests/ublk/test_loop_01.sh
@@ -6,27 +6,21 @@
TID="loop_01"
ERR_CODE=0
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "loop" "write and verify test"
-backfile_0=$(_create_backfile 256M)
+_create_backfile 0 256M
-dev_id=$(_add_ublk_dev -t loop "$backfile_0")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
-fio --name=write_and_verify \
- --filename=/dev/ublkb"${dev_id}" \
- --ioengine=libaio --iodepth=16 \
- --rw=write \
- --size=256M \
- --direct=1 \
- --verify=crc32c \
- --do_verify=1 \
- --bs=4k > /dev/null 2>&1
+_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_02.sh b/tools/testing/selftests/ublk/test_loop_02.sh
index 03863d825e07..874568b3646b 100755
--- a/tools/testing/selftests/ublk/test_loop_02.sh
+++ b/tools/testing/selftests/ublk/test_loop_02.sh
@@ -8,15 +8,13 @@ ERR_CODE=0
_prep_test "loop" "mkfs & mount & umount"
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
_mkfs_mount_test /dev/ublkb"${dev_id}"
ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_03.sh b/tools/testing/selftests/ublk/test_loop_03.sh
index 269c96787d7d..c30f797c6429 100755
--- a/tools/testing/selftests/ublk/test_loop_03.sh
+++ b/tools/testing/selftests/ublk/test_loop_03.sh
@@ -6,26 +6,20 @@
TID="loop_03"
ERR_CODE=0
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "loop" "write and verify over zero copy"
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop -z "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+dev_id=$(_add_ublk_dev -t loop -z "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
-fio --name=write_and_verify \
- --filename=/dev/ublkb"${dev_id}" \
- --ioengine=libaio --iodepth=64 \
- --rw=write \
- --size=256M \
- --direct=1 \
- --verify=crc32c \
- --do_verify=1 \
- --bs=4k > /dev/null 2>&1
+_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_04.sh b/tools/testing/selftests/ublk/test_loop_04.sh
index 1435422c38ec..b01d75b3214d 100755
--- a/tools/testing/selftests/ublk/test_loop_04.sh
+++ b/tools/testing/selftests/ublk/test_loop_04.sh
@@ -8,15 +8,14 @@ ERR_CODE=0
_prep_test "loop" "mkfs & mount & umount with zero copy"
-backfile_0=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t loop -z "$backfile_0")
-_check_add_dev $TID $? "$backfile_0"
+_create_backfile 0 256M
+
+dev_id=$(_add_ublk_dev -t loop -z "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
_mkfs_mount_test /dev/ublkb"${dev_id}"
ERR_CODE=$?
_cleanup_test "loop"
-_remove_backfile "$backfile_0"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_loop_05.sh b/tools/testing/selftests/ublk/test_loop_05.sh
new file mode 100755
index 000000000000..de2141533074
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_loop_05.sh
@@ -0,0 +1,26 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="loop_05"
+ERR_CODE=0
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "loop" "write and verify test"
+
+_create_backfile 0 256M
+
+dev_id=$(_add_ublk_dev -q 2 -t loop "${UBLK_BACKFILES[0]}")
+_check_add_dev $TID $?
+
+# run fio over the ublk disk
+_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=256M
+ERR_CODE=$?
+
+_cleanup_test "loop"
+
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_01.sh b/tools/testing/selftests/ublk/test_stress_01.sh
index 7177f6c57bc5..7d3150f057d4 100755
--- a/tools/testing/selftests/ublk/test_stress_01.sh
+++ b/tools/testing/selftests/ublk/test_stress_01.sh
@@ -4,44 +4,31 @@
. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
TID="stress_01"
ERR_CODE=0
-DEV_ID=-1
ublk_io_and_remove()
{
- local size=$1
- shift 1
- local backfile=""
- if echo "$@" | grep -q "loop"; then
- backfile=${*: -1}
- fi
- DEV_ID=$(_add_ublk_dev "$@")
- _check_add_dev $TID $? "${backfile}"
-
- [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
- if ! __run_io_and_remove "${DEV_ID}" "${size}" "no"; then
- echo "/dev/ublkc${DEV_ID} isn't removed"
- _remove_backfile "${backfile}"
- exit 255
+ run_io_and_remove "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
fi
}
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "stress" "run IO and remove device"
-ublk_io_and_remove 8G -t null
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
-BACK_FILE=$(_create_backfile 256M)
-ublk_io_and_remove 256M -t loop "${BACK_FILE}"
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+ublk_io_and_remove 8G -t null -q 4 &
+ublk_io_and_remove 256M -t loop -q 4 "${UBLK_BACKFILES[0]}" &
+ublk_io_and_remove 256M -t stripe -q 4 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
-ublk_io_and_remove 256M -t loop -z "${BACK_FILE}"
-ERR_CODE=$?
_cleanup_test "stress"
-_remove_backfile "${BACK_FILE}"
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_02.sh b/tools/testing/selftests/ublk/test_stress_02.sh
index 2a8e60579a06..1a9065125ae1 100755
--- a/tools/testing/selftests/ublk/test_stress_02.sh
+++ b/tools/testing/selftests/ublk/test_stress_02.sh
@@ -4,44 +4,31 @@
. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
TID="stress_02"
ERR_CODE=0
-DEV_ID=-1
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
ublk_io_and_kill_daemon()
{
- local size=$1
- shift 1
- local backfile=""
- if echo "$@" | grep -q "loop"; then
- backfile=${*: -1}
- fi
- DEV_ID=$(_add_ublk_dev "$@")
- _check_add_dev $TID $? "${backfile}"
-
- [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs kill ublk server(ublk add $*)"
- if ! __run_io_and_remove "${DEV_ID}" "${size}" "yes"; then
- echo "/dev/ublkc${DEV_ID} isn't removed res ${res}"
- _remove_backfile "${backfile}"
- exit 255
+ run_io_and_kill_daemon "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
fi
}
_prep_test "stress" "run IO and kill ublk server"
-ublk_io_and_kill_daemon 8G -t null
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
-BACK_FILE=$(_create_backfile 256M)
-ublk_io_and_kill_daemon 256M -t loop "${BACK_FILE}"
-ERR_CODE=$?
-if [ ${ERR_CODE} -ne 0 ]; then
- _show_result $TID $ERR_CODE
-fi
+ublk_io_and_kill_daemon 8G -t null -q 4 &
+ublk_io_and_kill_daemon 256M -t loop -q 4 "${UBLK_BACKFILES[0]}" &
+ublk_io_and_kill_daemon 256M -t stripe -q 4 "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
-ublk_io_and_kill_daemon 256M -t loop -z "${BACK_FILE}"
-ERR_CODE=$?
_cleanup_test "stress"
-_remove_backfile "${BACK_FILE}"
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_03.sh b/tools/testing/selftests/ublk/test_stress_03.sh
new file mode 100755
index 000000000000..e0854f71d35b
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_03.sh
@@ -0,0 +1,38 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_03"
+ERR_CODE=0
+
+ublk_io_and_remove()
+{
+ run_io_and_remove "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+if ! _have_feature "ZERO_COPY"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "stress" "run IO and remove device(zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_io_and_remove 8G -t null -q 4 -z &
+ublk_io_and_remove 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_remove 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh
new file mode 100755
index 000000000000..1798a98387e8
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_04.sh
@@ -0,0 +1,37 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_04"
+ERR_CODE=0
+
+ublk_io_and_kill_daemon()
+{
+ run_io_and_kill_daemon "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+if ! _have_feature "ZERO_COPY"; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "stress" "run IO and kill ublk server(zero copy)"
+
+_create_backfile 0 256M
+_create_backfile 1 128M
+_create_backfile 2 128M
+
+ublk_io_and_kill_daemon 8G -t null -q 4 -z &
+ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stress_05.sh b/tools/testing/selftests/ublk/test_stress_05.sh
new file mode 100755
index 000000000000..a7071b10224d
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stress_05.sh
@@ -0,0 +1,64 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+TID="stress_05"
+ERR_CODE=0
+
+run_io_and_remove()
+{
+ local size=$1
+ local dev_id
+ local dev_pid
+ shift 1
+
+ dev_id=$(_add_ublk_dev "$@")
+ _check_add_dev $TID $?
+
+ [ "$UBLK_TEST_QUIET" -eq 0 ] && echo "run ublk IO vs. remove device(ublk add $*)"
+
+ fio --name=job1 --filename=/dev/ublkb"${dev_id}" --ioengine=libaio \
+ --rw=readwrite --iodepth=128 --size="${size}" --numjobs=4 \
+ --runtime=40 --time_based > /dev/null 2>&1 &
+ sleep 4
+
+ dev_pid=$(_get_ublk_daemon_pid "$dev_id")
+ kill -9 "$dev_pid"
+
+ if ! __remove_ublk_dev_return "${dev_id}"; then
+ echo "delete dev ${dev_id} failed"
+ return 255
+ fi
+}
+
+ublk_io_and_remove()
+{
+ run_io_and_remove "$@"
+ ERR_CODE=$?
+ if [ ${ERR_CODE} -ne 0 ]; then
+ echo "$TID failure: $*"
+ _show_result $TID $ERR_CODE
+ fi
+}
+
+_prep_test "stress" "run IO and remove device with recovery enabled"
+
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+for reissue in $(seq 0 1); do
+ ublk_io_and_remove 8G -t null -q 4 -g 1 -r 1 -i "$reissue" &
+ ublk_io_and_remove 256M -t loop -q 4 -g 1 -r 1 -i "$reissue" "${UBLK_BACKFILES[0]}" &
+ wait
+done
+
+if _have_feature "ZERO_COPY"; then
+ for reissue in $(seq 0 1); do
+ ublk_io_and_remove 8G -t null -q 4 -g 1 -z -r 1 -i "$reissue" &
+ ublk_io_and_remove 256M -t loop -q 4 -g 1 -z -r 1 -i "$reissue" "${UBLK_BACKFILES[1]}" &
+ wait
+ done
+fi
+
+_cleanup_test "stress"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_01.sh b/tools/testing/selftests/ublk/test_stripe_01.sh
index c01f3dc325ab..4e4f0fdf3c9b 100755
--- a/tools/testing/selftests/ublk/test_stripe_01.sh
+++ b/tools/testing/selftests/ublk/test_stripe_01.sh
@@ -6,29 +6,21 @@
TID="stripe_01"
ERR_CODE=0
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
_prep_test "stripe" "write and verify test"
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
+_create_backfile 0 256M
+_create_backfile 1 256M
-dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "${backfile_0}"
+dev_id=$(_add_ublk_dev -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
# run fio over the ublk disk
-fio --name=write_and_verify \
- --filename=/dev/ublkb"${dev_id}" \
- --ioengine=libaio --iodepth=32 \
- --rw=write \
- --size=512M \
- --direct=1 \
- --verify=crc32c \
- --do_verify=1 \
- --bs=4k > /dev/null 2>&1
+_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M
ERR_CODE=$?
_cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_02.sh b/tools/testing/selftests/ublk/test_stripe_02.sh
index e8a45fa82dde..5820ab2efba4 100755
--- a/tools/testing/selftests/ublk/test_stripe_02.sh
+++ b/tools/testing/selftests/ublk/test_stripe_02.sh
@@ -8,17 +8,14 @@ ERR_CODE=0
_prep_test "stripe" "mkfs & mount & umount"
-backfile_0=$(_create_backfile 256M)
-backfile_1=$(_create_backfile 256M)
-dev_id=$(_add_ublk_dev -t stripe "$backfile_0" "$backfile_1")
-_check_add_dev $TID $? "$backfile_0" "$backfile_1"
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+dev_id=$(_add_ublk_dev -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
_mkfs_mount_test /dev/ublkb"${dev_id}"
ERR_CODE=$?
_cleanup_test "stripe"
-
-_remove_backfile "$backfile_0"
-_remove_backfile "$backfile_1"
-
_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_03.sh b/tools/testing/selftests/ublk/test_stripe_03.sh
new file mode 100755
index 000000000000..20b977e27814
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stripe_03.sh
@@ -0,0 +1,26 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="stripe_03"
+ERR_CODE=0
+
+if ! _have_program fio; then
+ exit "$UBLK_SKIP_CODE"
+fi
+
+_prep_test "stripe" "write and verify test"
+
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+dev_id=$(_add_ublk_dev -q 2 -t stripe "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
+
+# run fio over the ublk disk
+_run_fio_verify_io --filename=/dev/ublkb"${dev_id}" --size=512M
+ERR_CODE=$?
+
+_cleanup_test "stripe"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/ublk/test_stripe_04.sh b/tools/testing/selftests/ublk/test_stripe_04.sh
new file mode 100755
index 000000000000..1b51ed2f1d84
--- /dev/null
+++ b/tools/testing/selftests/ublk/test_stripe_04.sh
@@ -0,0 +1,21 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+TID="stripe_04"
+ERR_CODE=0
+
+_prep_test "stripe" "mkfs & mount & umount on zero copy"
+
+_create_backfile 0 256M
+_create_backfile 1 256M
+
+dev_id=$(_add_ublk_dev -t stripe -z -q 2 "${UBLK_BACKFILES[0]}" "${UBLK_BACKFILES[1]}")
+_check_add_dev $TID $?
+
+_mkfs_mount_test /dev/ublkb"${dev_id}"
+ERR_CODE=$?
+
+_cleanup_test "stripe"
+_show_result $TID $ERR_CODE
diff --git a/tools/testing/selftests/x86/test_mremap_vdso.c b/tools/testing/selftests/x86/test_mremap_vdso.c
index d53959e03593..94bee6e0c813 100644
--- a/tools/testing/selftests/x86/test_mremap_vdso.c
+++ b/tools/testing/selftests/x86/test_mremap_vdso.c
@@ -14,6 +14,7 @@
#include <errno.h>
#include <unistd.h>
#include <string.h>
+#include <stdbool.h>
#include <sys/mman.h>
#include <sys/auxv.h>
@@ -55,13 +56,55 @@ static int try_to_remap(void *vdso_addr, unsigned long size)
}
+#define VDSO_NAME "[vdso]"
+#define VMFLAGS "VmFlags:"
+#define MSEAL_FLAGS "sl"
+#define MAX_LINE_LEN 512
+
+bool vdso_sealed(FILE *maps)
+{
+ char line[MAX_LINE_LEN];
+ bool has_vdso = false;
+
+ while (fgets(line, sizeof(line), maps)) {
+ if (strstr(line, VDSO_NAME))
+ has_vdso = true;
+
+ if (has_vdso && !strncmp(line, VMFLAGS, strlen(VMFLAGS))) {
+ if (strstr(line, MSEAL_FLAGS))
+ return true;
+
+ return false;
+ }
+ }
+
+ return false;
+}
+
int main(int argc, char **argv, char **envp)
{
pid_t child;
+ FILE *maps;
ksft_print_header();
ksft_set_plan(1);
+ maps = fopen("/proc/self/smaps", "r");
+ if (!maps) {
+ ksft_test_result_skip(
+ "Could not open /proc/self/smaps, errno=%d\n",
+ errno);
+
+ return 0;
+ }
+
+ if (vdso_sealed(maps)) {
+ ksft_test_result_skip("vdso is sealed\n");
+ return 0;
+ }
+
+ fclose(maps);
+
child = fork();
if (child == -1)
ksft_exit_fail_msg("failed to fork (%d): %m\n", errno);
diff --git a/tools/testing/shared/interval_tree-shim.c b/tools/testing/shared/interval_tree-shim.c
new file mode 100644
index 000000000000..122e74756571
--- /dev/null
+++ b/tools/testing/shared/interval_tree-shim.c
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Very simple shim around the interval tree. */
+
+#include "../../../lib/interval_tree.c"
diff --git a/tools/testing/shared/linux.c b/tools/testing/shared/linux.c
index 66dbb362385f..0f97fb0d19e1 100644
--- a/tools/testing/shared/linux.c
+++ b/tools/testing/shared/linux.c
@@ -150,7 +150,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
{
if (kmalloc_verbose)
- pr_debug("Bulk free %p[0-%lu]\n", list, size - 1);
+ pr_debug("Bulk free %p[0-%zu]\n", list, size - 1);
pthread_mutex_lock(&cachep->lock);
for (int i = 0; i < size; i++)
@@ -168,7 +168,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
size_t i;
if (kmalloc_verbose)
- pr_debug("Bulk alloc %lu\n", size);
+ pr_debug("Bulk alloc %zu\n", size);
pthread_mutex_lock(&cachep->lock);
if (cachep->nr_objs >= size) {
diff --git a/tools/testing/shared/linux/cleanup.h b/tools/testing/shared/linux/cleanup.h
new file mode 100644
index 000000000000..ea3081426ee9
--- /dev/null
+++ b/tools/testing/shared/linux/cleanup.h
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "../../../../include/linux/cleanup.h"
diff --git a/tools/testing/shared/linux/interval_tree.h b/tools/testing/shared/linux/interval_tree.h
new file mode 100644
index 000000000000..129faf9f1d0a
--- /dev/null
+++ b/tools/testing/shared/linux/interval_tree.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TEST_INTERVAL_TREE_H
+#define _TEST_INTERVAL_TREE_H
+
+#include "../../../../include/linux/interval_tree.h"
+
+#endif /* _TEST_INTERVAL_TREE_H */
diff --git a/tools/testing/shared/linux/interval_tree_generic.h b/tools/testing/shared/linux/interval_tree_generic.h
new file mode 100644
index 000000000000..34cd654bee61
--- /dev/null
+++ b/tools/testing/shared/linux/interval_tree_generic.h
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "../../../../include/linux/interval_tree_generic.h"
diff --git a/tools/testing/shared/linux/rbtree.h b/tools/testing/shared/linux/rbtree.h
new file mode 100644
index 000000000000..d644bb7360bf
--- /dev/null
+++ b/tools/testing/shared/linux/rbtree.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TEST_RBTREE_H
+#define _TEST_RBTREE_H
+
+#include <linux/kernel.h>
+#include "../../../../include/linux/rbtree.h"
+
+#endif /* _TEST_RBTREE_H */
diff --git a/tools/testing/shared/linux/rbtree_augmented.h b/tools/testing/shared/linux/rbtree_augmented.h
new file mode 100644
index 000000000000..ad138fcf6652
--- /dev/null
+++ b/tools/testing/shared/linux/rbtree_augmented.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TEST_RBTREE_AUGMENTED_H
+#define _TEST_RBTREE_AUGMENTED_H
+
+#include "../../../../include/linux/rbtree_augmented.h"
+
+#endif /* _TEST_RBTREE_AUGMENTED_H */
diff --git a/tools/testing/shared/linux/rbtree_types.h b/tools/testing/shared/linux/rbtree_types.h
new file mode 100644
index 000000000000..194194a5bf92
--- /dev/null
+++ b/tools/testing/shared/linux/rbtree_types.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TEST_RBTREE_TYPES_H
+#define _TEST_RBTREE_TYPES_H
+
+#include "../../../../include/linux/rbtree_types.h"
+
+#endif /* _TEST_RBTREE_TYPES_H */
+
diff --git a/tools/testing/shared/rbtree-shim.c b/tools/testing/shared/rbtree-shim.c
new file mode 100644
index 000000000000..7692a993e5f1
--- /dev/null
+++ b/tools/testing/shared/rbtree-shim.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Very simple shim around the rbtree. */
+
+#include "../../../lib/rbtree.c"
+
diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h
index 3e1b6adc027b..788c597c4fde 100644
--- a/tools/testing/vma/linux/atomic.h
+++ b/tools/testing/vma/linux/atomic.h
@@ -9,4 +9,9 @@
#define atomic_set(x, y) uatomic_set(x, y)
#define U8_MAX UCHAR_MAX
+#ifndef atomic_cmpxchg_relaxed
+#define atomic_cmpxchg_relaxed uatomic_cmpxchg
+#define atomic_cmpxchg_release uatomic_cmpxchg
+#endif /* atomic_cmpxchg_relaxed */
+
#endif /* _LINUX_ATOMIC_H */
diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c
index 04ab45e27fb8..11f761769b5b 100644
--- a/tools/testing/vma/vma.c
+++ b/tools/testing/vma/vma.c
@@ -74,11 +74,23 @@ static struct vm_area_struct *alloc_vma(struct mm_struct *mm,
ret->vm_end = end;
ret->vm_pgoff = pgoff;
ret->__vm_flags = flags;
+ vma_assert_detached(ret);
return ret;
}
/* Helper function to allocate a VMA and link it to the tree. */
+static int attach_vma(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+ int res;
+
+ res = vma_link(mm, vma);
+ if (!res)
+ vma_assert_attached(vma);
+ return res;
+}
+
+/* Helper function to allocate a VMA and link it to the tree. */
static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
unsigned long start,
unsigned long end,
@@ -90,7 +102,7 @@ static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
if (vma == NULL)
return NULL;
- if (vma_link(mm, vma)) {
+ if (attach_vma(mm, vma)) {
vm_area_free(vma);
return NULL;
}
@@ -108,6 +120,7 @@ static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
/* Helper function which provides a wrapper around a merge new VMA operation. */
static struct vm_area_struct *merge_new(struct vma_merge_struct *vmg)
{
+ struct vm_area_struct *vma;
/*
* For convenience, get prev and next VMAs. Which the new VMA operation
* requires.
@@ -116,7 +129,11 @@ static struct vm_area_struct *merge_new(struct vma_merge_struct *vmg)
vmg->prev = vma_prev(vmg->vmi);
vma_iter_next_range(vmg->vmi);
- return vma_merge_new_range(vmg);
+ vma = vma_merge_new_range(vmg);
+ if (vma)
+ vma_assert_attached(vma);
+
+ return vma;
}
/*
@@ -125,7 +142,12 @@ static struct vm_area_struct *merge_new(struct vma_merge_struct *vmg)
*/
static struct vm_area_struct *merge_existing(struct vma_merge_struct *vmg)
{
- return vma_merge_existing_range(vmg);
+ struct vm_area_struct *vma;
+
+ vma = vma_merge_existing_range(vmg);
+ if (vma)
+ vma_assert_attached(vma);
+ return vma;
}
/*
@@ -147,13 +169,20 @@ static void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start,
vma_iter_set(vmg->vmi, start);
vmg->prev = NULL;
+ vmg->middle = NULL;
vmg->next = NULL;
- vmg->vma = NULL;
+ vmg->target = NULL;
vmg->start = start;
vmg->end = end;
vmg->pgoff = pgoff;
vmg->flags = flags;
+
+ vmg->just_expand = false;
+ vmg->__remove_middle = false;
+ vmg->__remove_next = false;
+ vmg->__adjust_middle_start = false;
+ vmg->__adjust_next_start = false;
}
/*
@@ -253,8 +282,8 @@ static bool test_simple_merge(void)
.pgoff = 1,
};
- ASSERT_FALSE(vma_link(&mm, vma_left));
- ASSERT_FALSE(vma_link(&mm, vma_right));
+ ASSERT_FALSE(attach_vma(&mm, vma_left));
+ ASSERT_FALSE(attach_vma(&mm, vma_right));
vma = merge_new(&vmg);
ASSERT_NE(vma, NULL);
@@ -278,7 +307,7 @@ static bool test_simple_modify(void)
struct vm_area_struct *init_vma = alloc_vma(&mm, 0, 0x3000, 0, flags);
VMA_ITERATOR(vmi, &mm, 0x1000);
- ASSERT_FALSE(vma_link(&mm, init_vma));
+ ASSERT_FALSE(attach_vma(&mm, init_vma));
/*
* The flags will not be changed, the vma_modify_flags() function
@@ -338,13 +367,13 @@ static bool test_simple_expand(void)
VMA_ITERATOR(vmi, &mm, 0);
struct vma_merge_struct vmg = {
.vmi = &vmi,
- .vma = vma,
+ .middle = vma,
.start = 0,
.end = 0x3000,
.pgoff = 0,
};
- ASSERT_FALSE(vma_link(&mm, vma));
+ ASSERT_FALSE(attach_vma(&mm, vma));
ASSERT_FALSE(expand_existing(&vmg));
@@ -365,7 +394,7 @@ static bool test_simple_shrink(void)
struct vm_area_struct *vma = alloc_vma(&mm, 0, 0x3000, 0, flags);
VMA_ITERATOR(vmi, &mm, 0);
- ASSERT_FALSE(vma_link(&mm, vma));
+ ASSERT_FALSE(attach_vma(&mm, vma));
ASSERT_FALSE(vma_shrink(&vmi, vma, 0, 0x1000, 0));
@@ -631,7 +660,7 @@ static bool test_vma_merge_special_flags(void)
*/
vma = alloc_and_link_vma(&mm, 0x3000, 0x4000, 3, flags);
ASSERT_NE(vma, NULL);
- vmg.vma = vma;
+ vmg.middle = vma;
for (i = 0; i < ARRAY_SIZE(special_flags); i++) {
vm_flags_t special_flag = special_flags[i];
@@ -760,7 +789,7 @@ static bool test_vma_merge_with_close(void)
vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
/*
* The VMA being modified in a way that would otherwise merge should
@@ -787,7 +816,7 @@ static bool test_vma_merge_with_close(void)
vma->vm_ops = &vm_ops;
vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), NULL);
/*
* Initially this is misapprehended as an out of memory report, as the
@@ -817,7 +846,7 @@ static bool test_vma_merge_with_close(void)
vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), NULL);
ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
@@ -843,7 +872,7 @@ static bool test_vma_merge_with_close(void)
vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), vma_prev);
ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
@@ -940,7 +969,7 @@ static bool test_merge_existing(void)
vma_next = alloc_and_link_vma(&mm, 0x6000, 0x9000, 6, flags);
vma_next->vm_ops = &vm_ops; /* This should have no impact. */
vmg_set_range(&vmg, 0x3000, 0x6000, 3, flags);
- vmg.vma = vma;
+ vmg.middle = vma;
vmg.prev = vma;
vma->anon_vma = &dummy_anon_vma;
ASSERT_EQ(merge_existing(&vmg), vma_next);
@@ -973,7 +1002,7 @@ static bool test_merge_existing(void)
vma_next = alloc_and_link_vma(&mm, 0x6000, 0x9000, 6, flags);
vma_next->vm_ops = &vm_ops; /* This should have no impact. */
vmg_set_range(&vmg, 0x2000, 0x6000, 2, flags);
- vmg.vma = vma;
+ vmg.middle = vma;
vma->anon_vma = &dummy_anon_vma;
ASSERT_EQ(merge_existing(&vmg), vma_next);
ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
@@ -1003,7 +1032,7 @@ static bool test_merge_existing(void)
vma->vm_ops = &vm_ops; /* This should have no impact. */
vmg_set_range(&vmg, 0x3000, 0x6000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
vma->anon_vma = &dummy_anon_vma;
ASSERT_EQ(merge_existing(&vmg), vma_prev);
@@ -1037,7 +1066,7 @@ static bool test_merge_existing(void)
vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, flags);
vmg_set_range(&vmg, 0x3000, 0x7000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
vma->anon_vma = &dummy_anon_vma;
ASSERT_EQ(merge_existing(&vmg), vma_prev);
ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
@@ -1067,7 +1096,7 @@ static bool test_merge_existing(void)
vma_next = alloc_and_link_vma(&mm, 0x7000, 0x9000, 7, flags);
vmg_set_range(&vmg, 0x3000, 0x7000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
vma->anon_vma = &dummy_anon_vma;
ASSERT_EQ(merge_existing(&vmg), vma_prev);
ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
@@ -1102,37 +1131,37 @@ static bool test_merge_existing(void)
vmg_set_range(&vmg, 0x4000, 0x5000, 4, flags);
vmg.prev = vma;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), NULL);
ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
vmg_set_range(&vmg, 0x5000, 0x6000, 5, flags);
vmg.prev = vma;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), NULL);
ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
vmg_set_range(&vmg, 0x6000, 0x7000, 6, flags);
vmg.prev = vma;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), NULL);
ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
vmg_set_range(&vmg, 0x4000, 0x7000, 4, flags);
vmg.prev = vma;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), NULL);
ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
vmg_set_range(&vmg, 0x4000, 0x6000, 4, flags);
vmg.prev = vma;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), NULL);
ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
vmg_set_range(&vmg, 0x5000, 0x6000, 5, flags);
vmg.prev = vma;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), NULL);
ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
@@ -1197,7 +1226,7 @@ static bool test_anon_vma_non_mergeable(void)
vmg_set_range(&vmg, 0x3000, 0x7000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), vma_prev);
ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
@@ -1277,7 +1306,7 @@ static bool test_dup_anon_vma(void)
vma_next->anon_vma = &dummy_anon_vma;
vmg_set_range(&vmg, 0, 0x5000, 0, flags);
- vmg.vma = vma_prev;
+ vmg.middle = vma_prev;
vmg.next = vma_next;
ASSERT_EQ(expand_existing(&vmg), 0);
@@ -1309,7 +1338,7 @@ static bool test_dup_anon_vma(void)
vma_next->anon_vma = &dummy_anon_vma;
vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), vma_prev);
ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
@@ -1338,7 +1367,7 @@ static bool test_dup_anon_vma(void)
vma->anon_vma = &dummy_anon_vma;
vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), vma_prev);
ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
@@ -1366,7 +1395,7 @@ static bool test_dup_anon_vma(void)
vma->anon_vma = &dummy_anon_vma;
vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), vma_prev);
ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
@@ -1394,7 +1423,7 @@ static bool test_dup_anon_vma(void)
vma->anon_vma = &dummy_anon_vma;
vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
vmg.prev = vma;
- vmg.vma = vma;
+ vmg.middle = vma;
ASSERT_EQ(merge_existing(&vmg), vma_next);
ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
@@ -1432,7 +1461,7 @@ static bool test_vmi_prealloc_fail(void)
vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
vmg.prev = vma_prev;
- vmg.vma = vma;
+ vmg.middle = vma;
fail_prealloc = true;
@@ -1458,7 +1487,7 @@ static bool test_vmi_prealloc_fail(void)
vma->anon_vma = &dummy_anon_vma;
vmg_set_range(&vmg, 0, 0x5000, 3, flags);
- vmg.vma = vma_prev;
+ vmg.middle = vma_prev;
vmg.next = vma;
fail_prealloc = true;
@@ -1515,11 +1544,11 @@ static bool test_copy_vma(void)
vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
vma_new = copy_vma(&vma, 0, 0x2000, 0, &need_locks);
-
ASSERT_NE(vma_new, vma);
ASSERT_EQ(vma_new->vm_start, 0);
ASSERT_EQ(vma_new->vm_end, 0x2000);
ASSERT_EQ(vma_new->vm_pgoff, 0);
+ vma_assert_attached(vma_new);
cleanup_mm(&mm, &vmi);
@@ -1528,6 +1557,7 @@ static bool test_copy_vma(void)
vma = alloc_and_link_vma(&mm, 0, 0x2000, 0, flags);
vma_next = alloc_and_link_vma(&mm, 0x6000, 0x8000, 6, flags);
vma_new = copy_vma(&vma, 0x4000, 0x2000, 4, &need_locks);
+ vma_assert_attached(vma_new);
ASSERT_EQ(vma_new, vma_next);
@@ -1546,7 +1576,7 @@ static bool test_expand_only_mode(void)
/*
* Place a VMA prior to the one we're expanding so we assert that we do
* not erroneously try to traverse to the previous VMA even though we
- * have, through the use of VMG_FLAG_JUST_EXPAND, indicated we do not
+ * have, through the use of the just_expand flag, indicated we do not
* need to do so.
*/
alloc_and_link_vma(&mm, 0, 0x2000, 0, flags);
@@ -1558,7 +1588,7 @@ static bool test_expand_only_mode(void)
vma_iter_set(&vmi, 0x3000);
vma_prev = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
vmg.prev = vma_prev;
- vmg.merge_flags = VMG_FLAG_JUST_EXPAND;
+ vmg.just_expand = true;
vma = vma_merge_new_range(&vmg);
ASSERT_NE(vma, NULL);
@@ -1569,6 +1599,7 @@ static bool test_expand_only_mode(void)
ASSERT_EQ(vma->vm_pgoff, 3);
ASSERT_TRUE(vma_write_started(vma));
ASSERT_EQ(vma_iter_addr(&vmi), 0x3000);
+ vma_assert_attached(vma);
cleanup_mm(&mm, &vmi);
return true;
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 1eae23039854..572ab2cea763 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -25,7 +25,7 @@
#include <linux/maple_tree.h>
#include <linux/mm.h>
#include <linux/rbtree.h>
-#include <linux/rwsem.h>
+#include <linux/refcount.h>
extern unsigned long stack_guard_gap;
#ifdef CONFIG_MMU
@@ -135,10 +135,6 @@ typedef __bitwise unsigned int vm_fault_t;
*/
#define pr_warn_once pr_err
-typedef struct refcount_struct {
- atomic_t refs;
-} refcount_t;
-
struct kref {
refcount_t refcount;
};
@@ -233,15 +229,12 @@ struct mm_struct {
unsigned long flags; /* Must use atomic bitops to access */
};
-struct vma_lock {
- struct rw_semaphore lock;
-};
-
-
struct file {
struct address_space *f_mapping;
};
+#define VMA_LOCK_OFFSET 0x40000000
+
struct vm_area_struct {
/* The first cache line has the info for VMA tree walking. */
@@ -269,16 +262,13 @@ struct vm_area_struct {
};
#ifdef CONFIG_PER_VMA_LOCK
- /* Flag to indicate areas detached from the mm->mm_mt tree */
- bool detached;
-
/*
* Can only be written (using WRITE_ONCE()) while holding both:
* - mmap_lock (in write mode)
- * - vm_lock->lock (in write mode)
+ * - vm_refcnt bit at VMA_LOCK_OFFSET is set
* Can be read reliably while holding one of:
* - mmap_lock (in read or write mode)
- * - vm_lock->lock (in read or write mode)
+ * - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1
* Can be read unreliably (using READ_ONCE()) for pessimistic bailout
* while holding nothing (except RCU to keep the VMA struct allocated).
*
@@ -287,20 +277,9 @@ struct vm_area_struct {
* slowpath.
*/
unsigned int vm_lock_seq;
- struct vma_lock *vm_lock;
#endif
/*
- * For areas with an address space and backing store,
- * linkage into the address_space->i_mmap interval tree.
- *
- */
- struct {
- struct rb_node rb;
- unsigned long rb_subtree_last;
- } shared;
-
- /*
* A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
* list, after a COW of one of the file pages. A MAP_SHARED vma
* can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack
@@ -319,14 +298,6 @@ struct vm_area_struct {
struct file * vm_file; /* File we map to (can be NULL). */
void * vm_private_data; /* was vm_pte (shared mem) */
-#ifdef CONFIG_ANON_VMA_NAME
- /*
- * For private and shared anonymous mappings, a pointer to a null
- * terminated string containing the name given to the vma, or NULL if
- * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
- */
- struct anon_vma_name *anon_name;
-#endif
#ifdef CONFIG_SWAP
atomic_long_t swap_readahead_info;
#endif
@@ -339,6 +310,27 @@ struct vm_area_struct {
#ifdef CONFIG_NUMA_BALANCING
struct vma_numab_state *numab_state; /* NUMA Balancing state */
#endif
+#ifdef CONFIG_PER_VMA_LOCK
+ /* Unstable RCU readers are allowed to read this. */
+ refcount_t vm_refcnt;
+#endif
+ /*
+ * For areas with an address space and backing store,
+ * linkage into the address_space->i_mmap interval tree.
+ *
+ */
+ struct {
+ struct rb_node rb;
+ unsigned long rb_subtree_last;
+ } shared;
+#ifdef CONFIG_ANON_VMA_NAME
+ /*
+ * For private and shared anonymous mappings, a pointer to a null
+ * terminated string containing the name given to the vma, or NULL if
+ * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
+ */
+ struct anon_vma_name *anon_name;
+#endif
struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
} __randomize_layout;
@@ -464,26 +456,40 @@ static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi)
return mas_find(&vmi->mas, ULONG_MAX);
}
-static inline bool vma_lock_alloc(struct vm_area_struct *vma)
+/*
+ * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these
+ * assertions should be made either under mmap_write_lock or when the object
+ * has been isolated under mmap_write_lock, ensuring no competing writers.
+ */
+static inline void vma_assert_attached(struct vm_area_struct *vma)
{
- vma->vm_lock = calloc(1, sizeof(struct vma_lock));
-
- if (!vma->vm_lock)
- return false;
-
- init_rwsem(&vma->vm_lock->lock);
- vma->vm_lock_seq = UINT_MAX;
+ WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt));
+}
- return true;
+static inline void vma_assert_detached(struct vm_area_struct *vma)
+{
+ WARN_ON_ONCE(refcount_read(&vma->vm_refcnt));
}
static inline void vma_assert_write_locked(struct vm_area_struct *);
-static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached)
+static inline void vma_mark_attached(struct vm_area_struct *vma)
{
- /* When detaching vma should be write-locked */
- if (detached)
- vma_assert_write_locked(vma);
- vma->detached = detached;
+ vma_assert_write_locked(vma);
+ vma_assert_detached(vma);
+ refcount_set_release(&vma->vm_refcnt, 1);
+}
+
+static inline void vma_mark_detached(struct vm_area_struct *vma)
+{
+ vma_assert_write_locked(vma);
+ vma_assert_attached(vma);
+ /* We are the only writer, so no need to use vma_refcount_put(). */
+ if (unlikely(!refcount_dec_and_test(&vma->vm_refcnt))) {
+ /*
+ * Reader must have temporarily raised vm_refcnt but it will
+ * drop it without using the vma since vma is write-locked.
+ */
+ }
}
extern const struct vm_operations_struct vma_dummy_vm_ops;
@@ -496,7 +502,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
vma->vm_mm = mm;
vma->vm_ops = &vma_dummy_vm_ops;
INIT_LIST_HEAD(&vma->anon_vma_chain);
- vma_mark_detached(vma, false);
+ vma->vm_lock_seq = UINT_MAX;
}
static inline struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
@@ -507,10 +513,6 @@ static inline struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
return NULL;
vma_init(vma, mm);
- if (!vma_lock_alloc(vma)) {
- free(vma);
- return NULL;
- }
return vma;
}
@@ -523,10 +525,8 @@ static inline struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
return NULL;
memcpy(new, orig, sizeof(*new));
- if (!vma_lock_alloc(new)) {
- free(new);
- return NULL;
- }
+ refcount_set(&new->vm_refcnt, 0);
+ new->vm_lock_seq = UINT_MAX;
INIT_LIST_HEAD(&new->anon_vma_chain);
return new;
@@ -696,20 +696,9 @@ static inline void mpol_put(struct mempolicy *)
{
}
-static inline void vma_lock_free(struct vm_area_struct *vma)
-{
- free(vma->vm_lock);
-}
-
-static inline void __vm_area_free(struct vm_area_struct *vma)
-{
- vma_lock_free(vma);
- free(vma);
-}
-
static inline void vm_area_free(struct vm_area_struct *vma)
{
- __vm_area_free(vma);
+ free(vma);
}
static inline void lru_add_drain(void)
@@ -796,12 +785,12 @@ static inline void vma_start_write(struct vm_area_struct *vma)
static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
unsigned long start,
unsigned long end,
- long adjust_next)
+ struct vm_area_struct *next)
{
(void)vma;
(void)start;
(void)end;
- (void)adjust_next;
+ (void)next;
}
static inline void vma_iter_free(struct vma_iterator *vmi)