From: Andrii Nakryiko <andrii@kernel.org>
To: <bpf@vger.kernel.org>, <ast@kernel.org>, <daniel@iogearbox.net>
Cc: <andrii@kernel.org>, <kernel-team@fb.com>,
Peter Zijlstra <peterz@infradead.org>
Subject: [PATCH v5 bpf-next 12/16] selftests/bpf: test low-level perf BPF link API
Date: Sun, 15 Aug 2021 00:06:05 -0700 [thread overview]
Message-ID: <20210815070609.987780-13-andrii@kernel.org> (raw)
In-Reply-To: <20210815070609.987780-1-andrii@kernel.org>
Add tests utilizing low-level bpf_link_create() API to create perf BPF link.
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
.../selftests/bpf/prog_tests/perf_link.c | 89 +++++++++++++++++++
.../selftests/bpf/progs/test_perf_link.c | 16 ++++
2 files changed, 105 insertions(+)
create mode 100644 tools/testing/selftests/bpf/prog_tests/perf_link.c
create mode 100644 tools/testing/selftests/bpf/progs/test_perf_link.c
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c
new file mode 100644
index 000000000000..b1abd0c46607
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sched.h>
+#include <test_progs.h>
+#include "test_perf_link.skel.h"
+
+static void burn_cpu(void)
+{
+ volatile int j = 0;
+ cpu_set_t cpu_set;
+ int i, err;
+
+ /* generate some branches on cpu 0 */
+ CPU_ZERO(&cpu_set);
+ CPU_SET(0, &cpu_set);
+ err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
+ ASSERT_OK(err, "set_thread_affinity");
+
+ /* spin the loop for a while (random high number) */
+ for (i = 0; i < 1000000; ++i)
+ ++j;
+}
+
+void test_perf_link(void)
+{
+ struct test_perf_link *skel = NULL;
+ struct perf_event_attr attr;
+ int pfd = -1, link_fd = -1, err;
+ int run_cnt_before, run_cnt_after;
+ struct bpf_link_info info;
+ __u32 info_len = sizeof(info);
+
+ /* create perf event */
+ memset(&attr, 0, sizeof(attr));
+ attr.size = sizeof(attr);
+ attr.type = PERF_TYPE_SOFTWARE;
+ attr.config = PERF_COUNT_SW_CPU_CLOCK;
+ attr.freq = 1;
+ attr.sample_freq = 4000;
+ pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
+ if (!ASSERT_GE(pfd, 0, "perf_fd"))
+ goto cleanup;
+
+ skel = test_perf_link__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ link_fd = bpf_link_create(bpf_program__fd(skel->progs.handler), pfd,
+ BPF_PERF_EVENT, NULL);
+ if (!ASSERT_GE(link_fd, 0, "link_fd"))
+ goto cleanup;
+
+ memset(&info, 0, sizeof(info));
+ err = bpf_obj_get_info_by_fd(link_fd, &info, &info_len);
+ if (!ASSERT_OK(err, "link_get_info"))
+ goto cleanup;
+
+ ASSERT_EQ(info.type, BPF_LINK_TYPE_PERF_EVENT, "link_type");
+ ASSERT_GT(info.id, 0, "link_id");
+ ASSERT_GT(info.prog_id, 0, "link_prog_id");
+
+ /* ensure we get at least one perf_event prog execution */
+ burn_cpu();
+ ASSERT_GT(skel->bss->run_cnt, 0, "run_cnt");
+
+ /* perf_event is still active, but we close link and BPF program
+ * shouldn't be executed anymore
+ */
+ close(link_fd);
+ link_fd = -1;
+
+ /* make sure there are no stragglers */
+ kern_sync_rcu();
+
+ run_cnt_before = skel->bss->run_cnt;
+ burn_cpu();
+ run_cnt_after = skel->bss->run_cnt;
+
+ ASSERT_EQ(run_cnt_before, run_cnt_after, "run_cnt_before_after");
+
+cleanup:
+ if (link_fd >= 0)
+ close(link_fd);
+ if (pfd >= 0)
+ close(pfd);
+ test_perf_link__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_perf_link.c b/tools/testing/selftests/bpf/progs/test_perf_link.c
new file mode 100644
index 000000000000..c1db9fd98d0c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_perf_link.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int run_cnt = 0;
+
+SEC("perf_event")
+int handler(struct pt_regs *ctx)
+{
+ __sync_fetch_and_add(&run_cnt, 1);
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
--
2.30.2
next prev parent reply other threads:[~2021-08-15 7:06 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-15 7:05 [PATCH v5 bpf-next 00/16] BPF perf link and user-provided bpf_cookie Andrii Nakryiko
2021-08-15 7:05 ` [PATCH v5 bpf-next 01/16] bpf: refactor BPF_PROG_RUN into a function Andrii Nakryiko
2021-08-15 7:05 ` [PATCH v5 bpf-next 02/16] bpf: refactor BPF_PROG_RUN_ARRAY family of macros into functions Andrii Nakryiko
2021-08-15 7:05 ` [PATCH v5 bpf-next 03/16] bpf: refactor perf_event_set_bpf_prog() to use struct bpf_prog input Andrii Nakryiko
2021-08-15 7:05 ` [PATCH v5 bpf-next 04/16] bpf: implement minimal BPF perf link Andrii Nakryiko
2021-08-15 7:05 ` [PATCH v5 bpf-next 05/16] bpf: allow to specify user-provided bpf_cookie for BPF perf links Andrii Nakryiko
2021-08-16 11:46 ` Peter Zijlstra
2021-08-15 7:05 ` [PATCH v5 bpf-next 06/16] bpf: add bpf_get_attach_cookie() BPF helper to access bpf_cookie value Andrii Nakryiko
2021-08-15 7:06 ` [PATCH v5 bpf-next 07/16] libbpf: re-build libbpf.so when libbpf.map changes Andrii Nakryiko
2021-08-15 7:06 ` [PATCH v5 bpf-next 08/16] libbpf: remove unused bpf_link's destroy operation, but add dealloc Andrii Nakryiko
2021-08-15 7:06 ` [PATCH v5 bpf-next 09/16] libbpf: use BPF perf link when supported by kernel Andrii Nakryiko
2021-08-15 7:06 ` [PATCH v5 bpf-next 10/16] libbpf: add bpf_cookie support to bpf_link_create() API Andrii Nakryiko
2021-08-15 7:06 ` [PATCH v5 bpf-next 11/16] libbpf: add bpf_cookie to perf_event, kprobe, uprobe, and tp attach APIs Andrii Nakryiko
2021-08-15 7:06 ` Andrii Nakryiko [this message]
2021-08-15 7:06 ` [PATCH v5 bpf-next 13/16] selftests/bpf: extract uprobe-related helpers into trace_helpers.{c,h} Andrii Nakryiko
2021-08-15 7:06 ` [PATCH v5 bpf-next 14/16] selftests/bpf: add bpf_cookie selftests for high-level APIs Andrii Nakryiko
2021-08-15 7:06 ` [PATCH v5 bpf-next 15/16] libbpf: add uprobe ref counter offset support for USDT semaphores Andrii Nakryiko
2021-08-15 7:06 ` [PATCH v5 bpf-next 16/16] selftests/bpf: add ref_ctr_offset selftests Andrii Nakryiko
2021-08-16 23:10 ` [PATCH v5 bpf-next 00/16] BPF perf link and user-provided bpf_cookie patchwork-bot+netdevbpf
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210815070609.987780-13-andrii@kernel.org \
--to=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=kernel-team@fb.com \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).