diff mbox series

[RESEND,bpf-next,v2,4/4] selftests/bpf: Add cases to test global percpu data

Message ID 20250213161931.46399-5-leon.hwang@linux.dev (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series bpf: Introduce global percpu data | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR success PR summary
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success Errors and warnings before: 26 (+1) this patch: 26 (+1)
netdev/cc_maintainers warning 9 maintainers not CCed: kpsingh@kernel.org sdf@fomichev.me jolsa@kernel.org shuah@kernel.org john.fastabend@gmail.com linux-kselftest@vger.kernel.org haoluo@google.com mykolal@fb.com martin.lau@linux.dev
netdev/build_clang success Errors and warnings before: 47 this patch: 47
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 10 this patch: 10
netdev/checkpatch warning CHECK: No space is necessary after a cast CHECK: spaces preferred around that '|' (ctx:VxV) WARNING: Missing a blank line after declarations WARNING: added, moved or deleted file(s), does MAINTAINERS need updating? WARNING: externs should be avoided in .c files WARNING: line length of 87 exceeds 80 columns WARNING: line length of 90 exceeds 80 columns WARNING: line length of 91 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-12 success Logs for aarch64-gcc / veristat-meta
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-20 success Logs for s390x-gcc / veristat-meta
bpf/vmtest-bpf-next-VM_Test-11 success Logs for aarch64-gcc / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / GCC BPF
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / GCC BPF
bpf/vmtest-bpf-next-VM_Test-18 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-19 success Logs for s390x-gcc / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-17 / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-17 / veristat-meta
bpf/vmtest-bpf-next-VM_Test-43 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-44 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-next-VM_Test-50 success Logs for x86_64-llvm-18 / veristat-kernel
bpf/vmtest-bpf-next-VM_Test-51 success Logs for x86_64-llvm-18 / veristat-meta
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / GCC BPF / GCC BPF
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-gcc / veristat-kernel / x86_64-gcc veristat_kernel
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-gcc / veristat-meta / x86_64-gcc veristat_meta
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / GCC BPF / GCC BPF
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-49 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-42 success Logs for x86_64-llvm-18 / GCC BPF / GCC BPF
bpf/vmtest-bpf-next-VM_Test-45 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-46 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-47 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-48 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18

Commit Message

Leon Hwang Feb. 13, 2025, 4:19 p.m. UTC 
If the arch, like s390x, does not support percpu insn, this case won't
test global percpu data by checking -EOPNOTSUPP after loading prog.

The following APIs have been tested for global percpu data:
1. bpf_map__set_initial_value()
2. bpf_map__initial_value()
3. generated percpu struct pointer pointing to internal map's mmaped
4. bpf_map__lookup_elem() for global percpu data map
5. bpf_map__is_internal_percpu()

At the same time, the case is also tested with 'bpftool gen skeleton -L'.

125     global_percpu_data_init:OK
126     global_percpu_data_lskel:OK
Summary: 2/0 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 tools/testing/selftests/bpf/Makefile          |   2 +-
 .../bpf/prog_tests/global_data_init.c         | 217 +++++++++++++++++-
 .../bpf/progs/test_global_percpu_data.c       |  20 ++
 3 files changed, 237 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/test_global_percpu_data.c

Comments

Alexei Starovoitov Feb. 19, 2025, 1:54 a.m. UTC | #1 
On Thu, Feb 13, 2025 at 8:20 AM Leon Hwang <leon.hwang@linux.dev> wrote:
>
> If the arch, like s390x, does not support percpu insn, this case won't
> test global percpu data by checking -EOPNOTSUPP after loading prog.
>
> The following APIs have been tested for global percpu data:
> 1. bpf_map__set_initial_value()
> 2. bpf_map__initial_value()
> 3. generated percpu struct pointer pointing to internal map's mmaped
> 4. bpf_map__lookup_elem() for global percpu data map
> 5. bpf_map__is_internal_percpu()
>
> At the same time, the case is also tested with 'bpftool gen skeleton -L'.
>
> 125     global_percpu_data_init:OK
> 126     global_percpu_data_lskel:OK
> Summary: 2/0 PASSED, 0 SKIPPED, 0 FAILED
>
> Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
> ---
>  tools/testing/selftests/bpf/Makefile          |   2 +-
>  .../bpf/prog_tests/global_data_init.c         | 217 +++++++++++++++++-
>  .../bpf/progs/test_global_percpu_data.c       |  20 ++
>  3 files changed, 237 insertions(+), 2 deletions(-)
>  create mode 100644 tools/testing/selftests/bpf/progs/test_global_percpu_data.c
>
> diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
> index 0d552bfcfe7da..7991de79d55c5 100644
> --- a/tools/testing/selftests/bpf/Makefile
> +++ b/tools/testing/selftests/bpf/Makefile
> @@ -503,7 +503,7 @@ LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c                \
>
>  # Generate both light skeleton and libbpf skeleton for these
>  LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test.c \
> -       kfunc_call_test_subprog.c
> +       kfunc_call_test_subprog.c test_global_percpu_data.c
>  SKEL_BLACKLIST += $$(LSKELS)
>
>  test_static_linked.skel.h-deps := test_static_linked1.bpf.o test_static_linked2.bpf.o
> diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
> index 8466332d7406f..5ace86a0eace7 100644
> --- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c
> +++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
> @@ -1,5 +1,8 @@
>  // SPDX-License-Identifier: GPL-2.0
>  #include <test_progs.h>
> +#include "bpf/libbpf_internal.h"
> +#include "test_global_percpu_data.skel.h"
> +#include "test_global_percpu_data.lskel.h"
>
>  void test_global_data_init(void)
>  {
> @@ -8,7 +11,7 @@ void test_global_data_init(void)
>         __u8 *buff = NULL, *newval = NULL;
>         struct bpf_object *obj;
>         struct bpf_map *map;
> -        __u32 duration = 0;
> +       __u32 duration = 0;
>         size_t sz;
>
>         obj = bpf_object__open_file(file, NULL);
> @@ -60,3 +63,215 @@ void test_global_data_init(void)
>         free(newval);
>         bpf_object__close(obj);
>  }
> +
> +void test_global_percpu_data_init(void)
> +{
> +       struct test_global_percpu_data__percpu init_value, *init_data, *data, *percpu_data;
> +       int key, prog_fd, err, num_cpus, num_online, comm_fd = -1, i;
> +       struct test_global_percpu_data *skel = NULL;
> +       __u64 args[2] = {0x1234ULL, 0x5678ULL};
> +       size_t elem_sz, init_data_sz;
> +       char buf[] = "new_name";
> +       struct bpf_map *map;
> +       bool *online;
> +       LIBBPF_OPTS(bpf_test_run_opts, topts,
> +                   .ctx_in = args,
> +                   .ctx_size_in = sizeof(args),
> +                   .flags = BPF_F_TEST_RUN_ON_CPU,
> +       );
> +
> +       num_cpus = libbpf_num_possible_cpus();
> +       if (!ASSERT_GT(num_cpus, 0, "libbpf_num_possible_cpus"))
> +               return;
> +
> +       err = parse_cpu_mask_file("/sys/devices/system/cpu/online",
> +                                 &online, &num_online);
> +       if (!ASSERT_OK(err, "parse_cpu_mask_file"))
> +               return;
> +
> +       elem_sz = sizeof(*percpu_data);
> +       percpu_data = calloc(num_cpus, elem_sz);
> +       if (!ASSERT_OK_PTR(percpu_data, "calloc percpu_data"))
> +               goto out;
> +
> +       skel = test_global_percpu_data__open();
> +       if (!ASSERT_OK_PTR(skel, "test_global_percpu_data__open"))
> +               goto out;
> +       if (!ASSERT_OK_PTR(skel->percpu, "skel->percpu"))
> +               goto out;
> +
> +       ASSERT_EQ(skel->percpu->data, -1, "skel->percpu->data");
> +       ASSERT_FALSE(skel->percpu->run, "skel->percpu->run");
> +       ASSERT_EQ(skel->percpu->data2, 0, "skel->percpu->data2");

this will only check the value on cpu0, right?
Let's check it on all ?

> +       map = skel->maps.percpu;
> +       if (!ASSERT_EQ(bpf_map__type(map), BPF_MAP_TYPE_PERCPU_ARRAY, "bpf_map__type"))
> +               goto out;
> +       if (!ASSERT_TRUE(bpf_map__is_internal_percpu(map), "bpf_map__is_internal_percpu"))
> +               goto out;
> +
> +       init_value.data = 2;
> +       init_value.run = false;
> +       err = bpf_map__set_initial_value(map, &init_value, sizeof(init_value));
> +       if (!ASSERT_OK(err, "bpf_map__set_initial_value"))
> +               goto out;
> +
> +       init_data = bpf_map__initial_value(map, &init_data_sz);
> +       if (!ASSERT_OK_PTR(init_data, "bpf_map__initial_value"))
> +               goto out;
> +
> +       ASSERT_EQ(init_data->data, init_value.data, "initial_value data");
> +       ASSERT_EQ(init_data->run, init_value.run, "initial_value run");
> +       ASSERT_EQ(init_data_sz, sizeof(init_value), "initial_value size");
> +       ASSERT_EQ((void *) init_data, (void *) skel->percpu, "skel->percpu eq init_data");
> +       ASSERT_EQ(skel->percpu->data, init_value.data, "skel->percpu->data");
> +       ASSERT_EQ(skel->percpu->run, init_value.run, "skel->percpu->run");
> +
> +       err = test_global_percpu_data__load(skel);
> +       if (err == -EOPNOTSUPP) {
> +               test__skip();
> +               goto out;
> +       }
> +       if (!ASSERT_OK(err, "test_global_percpu_data__load"))
> +               goto out;
> +
> +       ASSERT_NULL(skel->percpu, "NULL skel->percpu");
> +
> +       err = test_global_percpu_data__attach(skel);
> +       if (!ASSERT_OK(err, "test_global_percpu_data__attach"))
> +               goto out;
> +
> +       comm_fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
> +       if (!ASSERT_GE(comm_fd, 0, "open /proc/self/comm"))
> +               goto out;
> +
> +       err = write(comm_fd, buf, sizeof(buf));
> +       if (!ASSERT_GE(err, 0, "task rename"))
> +               goto out;
> +
> +       prog_fd = bpf_program__fd(skel->progs.update_percpu_data);
> +
> +       /* run on every CPU */
> +       for (i = 0; i < num_online; i++) {
> +               if (!online[i])
> +                       continue;
> +
> +               topts.cpu = i;
> +               topts.retval = 0;
> +               err = bpf_prog_test_run_opts(prog_fd, &topts);
> +               ASSERT_OK(err, "bpf_prog_test_run_opts");
> +               ASSERT_EQ(topts.retval, 0, "bpf_prog_test_run_opts retval");
> +       }
> +
> +       key = 0;
> +       err = bpf_map__lookup_elem(map, &key, sizeof(key), percpu_data,
> +                                  elem_sz * num_cpus, 0);
> +       if (!ASSERT_OK(err, "bpf_map__lookup_elem"))
> +               goto out;
> +
> +       for (i = 0; i < num_online; i++) {
> +               if (!online[i])
> +                       continue;
> +
> +               data = percpu_data + i;
> +               ASSERT_EQ(data->data, 1, "percpu_data->data");
> +               ASSERT_TRUE(data->run, "percpu_data->run");
> +               ASSERT_EQ(data->data2, 0xc0de, "percpu_data->data2");
> +       }
> +
> +out:
> +       close(comm_fd);
> +       test_global_percpu_data__destroy(skel);
> +       if (percpu_data)
> +               free(percpu_data);
> +       free(online);
> +}
> +
> +void test_global_percpu_data_lskel(void)
> +{
> +       int key, prog_fd, map_fd, err, num_cpus, num_online, comm_fd = -1, i;
> +       struct test_global_percpu_data__percpu *data, *percpu_data;
> +       struct test_global_percpu_data_lskel *lskel = NULL;
> +       __u64 args[2] = {0x1234ULL, 0x5678ULL};
> +       char buf[] = "new_name";
> +       bool *online;
> +       LIBBPF_OPTS(bpf_test_run_opts, topts,
> +                   .ctx_in = args,
> +                   .ctx_size_in = sizeof(args),
> +                   .flags = BPF_F_TEST_RUN_ON_CPU,
> +       );
> +
> +       num_cpus = libbpf_num_possible_cpus();
> +       if (!ASSERT_GT(num_cpus, 0, "libbpf_num_possible_cpus"))
> +               return;
> +
> +       err = parse_cpu_mask_file("/sys/devices/system/cpu/online",
> +                                 &online, &num_online);
> +       if (!ASSERT_OK(err, "parse_cpu_mask_file"))
> +               return;
> +
> +       percpu_data = calloc(num_cpus, sizeof(*percpu_data));
> +       if (!ASSERT_OK_PTR(percpu_data, "calloc percpu_data"))
> +               goto out;
> +
> +       lskel = test_global_percpu_data_lskel__open();
> +       if (!ASSERT_OK_PTR(lskel, "test_global_percpu_data_lskel__open"))
> +               goto out;
> +
> +       err = test_global_percpu_data_lskel__load(lskel);
> +       if (err == -EOPNOTSUPP) {
> +               test__skip();
> +               goto out;
> +       }
> +       if (!ASSERT_OK(err, "test_global_percpu_data_lskel__load"))
> +               goto out;
> +
> +       err = test_global_percpu_data_lskel__attach(lskel);
> +       if (!ASSERT_OK(err, "test_global_percpu_data_lskel__attach"))
> +               goto out;
> +
> +       comm_fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
> +       if (!ASSERT_GE(comm_fd, 0, "open /proc/self/comm"))
> +               goto out;
> +
> +       err = write(comm_fd, buf, sizeof(buf));
> +       if (!ASSERT_GE(err, 0, "task rename"))
> +               goto out;

why this odd double run of bpf prog?
First via task_rename and then directly?
Only use bpf_prog_test_run_opts() and avoiding attaching to a tracepoint?

> +
> +       prog_fd = lskel->progs.update_percpu_data.prog_fd;
> +
> +       /* run on every CPU */
> +       for (i = 0; i < num_online; i++) {
> +               if (!online[i])
> +                       continue;
> +
> +               topts.cpu = i;
> +               topts.retval = 0;
> +               err = bpf_prog_test_run_opts(prog_fd, &topts);
> +               ASSERT_OK(err, "bpf_prog_test_run_opts");
> +               ASSERT_EQ(topts.retval, 0, "bpf_prog_test_run_opts retval");
> +       }
> +
> +       key = 0;
> +       map_fd = lskel->maps.percpu.map_fd;
> +       err = bpf_map_lookup_elem(map_fd, &key, percpu_data);
> +       if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
> +               goto out;
> +
> +       for (i = 0; i < num_online; i++) {
> +               if (!online[i])
> +                       continue;
> +
> +               data = percpu_data + i;
> +               ASSERT_EQ(data->data, 1, "percpu_data->data");
> +               ASSERT_TRUE(data->run, "percpu_data->run");
> +               ASSERT_EQ(data->data2, 0xc0de, "percpu_data->data2");
> +       }
> +
> +out:
> +       close(comm_fd);
> +       test_global_percpu_data_lskel__destroy(lskel);
> +       if (percpu_data)
> +               free(percpu_data);
> +       free(online);
> +}
> diff --git a/tools/testing/selftests/bpf/progs/test_global_percpu_data.c b/tools/testing/selftests/bpf/progs/test_global_percpu_data.c
> new file mode 100644
> index 0000000000000..ada292d3a164c
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/test_global_percpu_data.c
> @@ -0,0 +1,20 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* Copyright Leon Hwang */

Are you sure you can do it in your country?
Often enough copyright belongs to the company you work for.

> +#include <linux/bpf.h>
> +#include <bpf/bpf_helpers.h>
> +
> +int data SEC(".percpu") = -1;
> +int run SEC(".percpu") = 0;
> +int data2 SEC(".percpu");

Pls add u8, array of ints and struct { .. } vars for completeness.

pw-bot: cr
diff mbox series

Patch

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 0d552bfcfe7da..7991de79d55c5 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -503,7 +503,7 @@  LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c 		\
 
 # Generate both light skeleton and libbpf skeleton for these
 LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test.c \
-	kfunc_call_test_subprog.c
+	kfunc_call_test_subprog.c test_global_percpu_data.c
 SKEL_BLACKLIST += $$(LSKELS)
 
 test_static_linked.skel.h-deps := test_static_linked1.bpf.o test_static_linked2.bpf.o
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
index 8466332d7406f..5ace86a0eace7 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
@@ -1,5 +1,8 @@ 
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "bpf/libbpf_internal.h"
+#include "test_global_percpu_data.skel.h"
+#include "test_global_percpu_data.lskel.h"
 
 void test_global_data_init(void)
 {
@@ -8,7 +11,7 @@  void test_global_data_init(void)
 	__u8 *buff = NULL, *newval = NULL;
 	struct bpf_object *obj;
 	struct bpf_map *map;
-        __u32 duration = 0;
+	__u32 duration = 0;
 	size_t sz;
 
 	obj = bpf_object__open_file(file, NULL);
@@ -60,3 +63,215 @@  void test_global_data_init(void)
 	free(newval);
 	bpf_object__close(obj);
 }
+
+void test_global_percpu_data_init(void)
+{
+	struct test_global_percpu_data__percpu init_value, *init_data, *data, *percpu_data;
+	int key, prog_fd, err, num_cpus, num_online, comm_fd = -1, i;
+	struct test_global_percpu_data *skel = NULL;
+	__u64 args[2] = {0x1234ULL, 0x5678ULL};
+	size_t elem_sz, init_data_sz;
+	char buf[] = "new_name";
+	struct bpf_map *map;
+	bool *online;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .ctx_in = args,
+		    .ctx_size_in = sizeof(args),
+		    .flags = BPF_F_TEST_RUN_ON_CPU,
+	);
+
+	num_cpus = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(num_cpus, 0, "libbpf_num_possible_cpus"))
+		return;
+
+	err = parse_cpu_mask_file("/sys/devices/system/cpu/online",
+				  &online, &num_online);
+	if (!ASSERT_OK(err, "parse_cpu_mask_file"))
+		return;
+
+	elem_sz = sizeof(*percpu_data);
+	percpu_data = calloc(num_cpus, elem_sz);
+	if (!ASSERT_OK_PTR(percpu_data, "calloc percpu_data"))
+		goto out;
+
+	skel = test_global_percpu_data__open();
+	if (!ASSERT_OK_PTR(skel, "test_global_percpu_data__open"))
+		goto out;
+	if (!ASSERT_OK_PTR(skel->percpu, "skel->percpu"))
+		goto out;
+
+	ASSERT_EQ(skel->percpu->data, -1, "skel->percpu->data");
+	ASSERT_FALSE(skel->percpu->run, "skel->percpu->run");
+	ASSERT_EQ(skel->percpu->data2, 0, "skel->percpu->data2");
+
+	map = skel->maps.percpu;
+	if (!ASSERT_EQ(bpf_map__type(map), BPF_MAP_TYPE_PERCPU_ARRAY, "bpf_map__type"))
+		goto out;
+	if (!ASSERT_TRUE(bpf_map__is_internal_percpu(map), "bpf_map__is_internal_percpu"))
+		goto out;
+
+	init_value.data = 2;
+	init_value.run = false;
+	err = bpf_map__set_initial_value(map, &init_value, sizeof(init_value));
+	if (!ASSERT_OK(err, "bpf_map__set_initial_value"))
+		goto out;
+
+	init_data = bpf_map__initial_value(map, &init_data_sz);
+	if (!ASSERT_OK_PTR(init_data, "bpf_map__initial_value"))
+		goto out;
+
+	ASSERT_EQ(init_data->data, init_value.data, "initial_value data");
+	ASSERT_EQ(init_data->run, init_value.run, "initial_value run");
+	ASSERT_EQ(init_data_sz, sizeof(init_value), "initial_value size");
+	ASSERT_EQ((void *) init_data, (void *) skel->percpu, "skel->percpu eq init_data");
+	ASSERT_EQ(skel->percpu->data, init_value.data, "skel->percpu->data");
+	ASSERT_EQ(skel->percpu->run, init_value.run, "skel->percpu->run");
+
+	err = test_global_percpu_data__load(skel);
+	if (err == -EOPNOTSUPP) {
+		test__skip();
+		goto out;
+	}
+	if (!ASSERT_OK(err, "test_global_percpu_data__load"))
+		goto out;
+
+	ASSERT_NULL(skel->percpu, "NULL skel->percpu");
+
+	err = test_global_percpu_data__attach(skel);
+	if (!ASSERT_OK(err, "test_global_percpu_data__attach"))
+		goto out;
+
+	comm_fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
+	if (!ASSERT_GE(comm_fd, 0, "open /proc/self/comm"))
+		goto out;
+
+	err = write(comm_fd, buf, sizeof(buf));
+	if (!ASSERT_GE(err, 0, "task rename"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.update_percpu_data);
+
+	/* run on every CPU */
+	for (i = 0; i < num_online; i++) {
+		if (!online[i])
+			continue;
+
+		topts.cpu = i;
+		topts.retval = 0;
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+		ASSERT_OK(err, "bpf_prog_test_run_opts");
+		ASSERT_EQ(topts.retval, 0, "bpf_prog_test_run_opts retval");
+	}
+
+	key = 0;
+	err = bpf_map__lookup_elem(map, &key, sizeof(key), percpu_data,
+				   elem_sz * num_cpus, 0);
+	if (!ASSERT_OK(err, "bpf_map__lookup_elem"))
+		goto out;
+
+	for (i = 0; i < num_online; i++) {
+		if (!online[i])
+			continue;
+
+		data = percpu_data + i;
+		ASSERT_EQ(data->data, 1, "percpu_data->data");
+		ASSERT_TRUE(data->run, "percpu_data->run");
+		ASSERT_EQ(data->data2, 0xc0de, "percpu_data->data2");
+	}
+
+out:
+	close(comm_fd);
+	test_global_percpu_data__destroy(skel);
+	if (percpu_data)
+		free(percpu_data);
+	free(online);
+}
+
+void test_global_percpu_data_lskel(void)
+{
+	int key, prog_fd, map_fd, err, num_cpus, num_online, comm_fd = -1, i;
+	struct test_global_percpu_data__percpu *data, *percpu_data;
+	struct test_global_percpu_data_lskel *lskel = NULL;
+	__u64 args[2] = {0x1234ULL, 0x5678ULL};
+	char buf[] = "new_name";
+	bool *online;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .ctx_in = args,
+		    .ctx_size_in = sizeof(args),
+		    .flags = BPF_F_TEST_RUN_ON_CPU,
+	);
+
+	num_cpus = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(num_cpus, 0, "libbpf_num_possible_cpus"))
+		return;
+
+	err = parse_cpu_mask_file("/sys/devices/system/cpu/online",
+				  &online, &num_online);
+	if (!ASSERT_OK(err, "parse_cpu_mask_file"))
+		return;
+
+	percpu_data = calloc(num_cpus, sizeof(*percpu_data));
+	if (!ASSERT_OK_PTR(percpu_data, "calloc percpu_data"))
+		goto out;
+
+	lskel = test_global_percpu_data_lskel__open();
+	if (!ASSERT_OK_PTR(lskel, "test_global_percpu_data_lskel__open"))
+		goto out;
+
+	err = test_global_percpu_data_lskel__load(lskel);
+	if (err == -EOPNOTSUPP) {
+		test__skip();
+		goto out;
+	}
+	if (!ASSERT_OK(err, "test_global_percpu_data_lskel__load"))
+		goto out;
+
+	err = test_global_percpu_data_lskel__attach(lskel);
+	if (!ASSERT_OK(err, "test_global_percpu_data_lskel__attach"))
+		goto out;
+
+	comm_fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
+	if (!ASSERT_GE(comm_fd, 0, "open /proc/self/comm"))
+		goto out;
+
+	err = write(comm_fd, buf, sizeof(buf));
+	if (!ASSERT_GE(err, 0, "task rename"))
+		goto out;
+
+	prog_fd = lskel->progs.update_percpu_data.prog_fd;
+
+	/* run on every CPU */
+	for (i = 0; i < num_online; i++) {
+		if (!online[i])
+			continue;
+
+		topts.cpu = i;
+		topts.retval = 0;
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+		ASSERT_OK(err, "bpf_prog_test_run_opts");
+		ASSERT_EQ(topts.retval, 0, "bpf_prog_test_run_opts retval");
+	}
+
+	key = 0;
+	map_fd = lskel->maps.percpu.map_fd;
+	err = bpf_map_lookup_elem(map_fd, &key, percpu_data);
+	if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
+		goto out;
+
+	for (i = 0; i < num_online; i++) {
+		if (!online[i])
+			continue;
+
+		data = percpu_data + i;
+		ASSERT_EQ(data->data, 1, "percpu_data->data");
+		ASSERT_TRUE(data->run, "percpu_data->run");
+		ASSERT_EQ(data->data2, 0xc0de, "percpu_data->data2");
+	}
+
+out:
+	close(comm_fd);
+	test_global_percpu_data_lskel__destroy(lskel);
+	if (percpu_data)
+		free(percpu_data);
+	free(online);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_percpu_data.c b/tools/testing/selftests/bpf/progs/test_global_percpu_data.c
new file mode 100644
index 0000000000000..ada292d3a164c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_percpu_data.c
@@ -0,0 +1,20 @@ 
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Leon Hwang */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+int data SEC(".percpu") = -1;
+int run SEC(".percpu") = 0;
+int data2 SEC(".percpu");
+
+SEC("raw_tp/task_rename")
+int update_percpu_data(struct __sk_buff *skb)
+{
+	data = 1;
+	run = 1;
+	data2 = 0xc0de;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";