-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'bpf_read_branch_records'
Daniel Xu says: ==================== Branch records are a CPU feature that can be configured to record certain branches that are taken during code execution. This data is particularly interesting for profile guided optimizations. perf has had branch record support for a while but the data collection can be a bit coarse grained. We (Facebook) have seen in experiments that associating metadata with branch records can improve results (after postprocessing). We generally use bpf_probe_read_*() to get metadata out of userspace. That's why bpf support for branch records is useful. Aside from this particular use case, having branch data available to bpf progs can be useful to get stack traces out of userspace applications that omit frame pointers. Changes in v8: - Use globals instead of perf buffer - Call test_perf_branches__detach() before destroying skeleton - Fix typo in docs Changes in v7: - Const-ify and static-ify local var - Documentation formatting Changes in v6: - Move #ifdef a little to avoid unused variable warnings on !x86 - Test negative condition in selftest (-EINVAL on improperly configured perf event) - Skip positive condition selftest on setups that don't support branch records Changes in v5: - Rename bpf_perf_prog_read_branches() -> bpf_read_branch_records() - Rename BPF_F_GET_BR_SIZE -> BPF_F_GET_BRANCH_RECORDS_SIZE - Squash tools/ bpf.h sync into selftest commit Changes in v4: - Add BPF_F_GET_BR_SIZE flag - Return -ENOENT on unsupported architectures - Only accept initialized memory in helper - Check buffer size is multiple of sizeof(struct perf_branch_entry) - Use bpf skeleton in selftest - Add commit messages - Spelling and formatting Changes in v3: - Document filling unused buffer with zero - Formatting fixes - Rebase Changes in v2: - Change to a bpf helper instead of context access - Avoid mentioning Intel specific things ==================== Signed-off-by: Alexei Starovoitov <ast@kernel.org>
- Loading branch information
Showing
5 changed files
with
309 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,170 @@ | ||
| // SPDX-License-Identifier: GPL-2.0 | ||
| #define _GNU_SOURCE | ||
| #include <pthread.h> | ||
| #include <sched.h> | ||
| #include <sys/socket.h> | ||
| #include <test_progs.h> | ||
| #include "bpf/libbpf_internal.h" | ||
| #include "test_perf_branches.skel.h" | ||
|
|
||
| static void check_good_sample(struct test_perf_branches *skel) | ||
| { | ||
| int written_global = skel->bss->written_global_out; | ||
| int required_size = skel->bss->required_size_out; | ||
| int written_stack = skel->bss->written_stack_out; | ||
| int pbe_size = sizeof(struct perf_branch_entry); | ||
| int duration = 0; | ||
|
|
||
| if (CHECK(!skel->bss->valid, "output not valid", | ||
| "no valid sample from prog")) | ||
| return; | ||
|
|
||
| /* | ||
| * It's hard to validate the contents of the branch entries b/c it | ||
| * would require some kind of disassembler and also encoding the | ||
| * valid jump instructions for supported architectures. So just check | ||
| * the easy stuff for now. | ||
| */ | ||
| CHECK(required_size <= 0, "read_branches_size", "err %d\n", required_size); | ||
| CHECK(written_stack < 0, "read_branches_stack", "err %d\n", written_stack); | ||
| CHECK(written_stack % pbe_size != 0, "read_branches_stack", | ||
| "stack bytes written=%d not multiple of struct size=%d\n", | ||
| written_stack, pbe_size); | ||
| CHECK(written_global < 0, "read_branches_global", "err %d\n", written_global); | ||
| CHECK(written_global % pbe_size != 0, "read_branches_global", | ||
| "global bytes written=%d not multiple of struct size=%d\n", | ||
| written_global, pbe_size); | ||
| CHECK(written_global < written_stack, "read_branches_size", | ||
| "written_global=%d < written_stack=%d\n", written_global, written_stack); | ||
| } | ||
|
|
||
| static void check_bad_sample(struct test_perf_branches *skel) | ||
| { | ||
| int written_global = skel->bss->written_global_out; | ||
| int required_size = skel->bss->required_size_out; | ||
| int written_stack = skel->bss->written_stack_out; | ||
| int duration = 0; | ||
|
|
||
| if (CHECK(!skel->bss->valid, "output not valid", | ||
| "no valid sample from prog")) | ||
| return; | ||
|
|
||
| CHECK((required_size != -EINVAL && required_size != -ENOENT), | ||
| "read_branches_size", "err %d\n", required_size); | ||
| CHECK((written_stack != -EINVAL && written_stack != -ENOENT), | ||
| "read_branches_stack", "written %d\n", written_stack); | ||
| CHECK((written_global != -EINVAL && written_global != -ENOENT), | ||
| "read_branches_global", "written %d\n", written_global); | ||
| } | ||
|
|
||
| static void test_perf_branches_common(int perf_fd, | ||
| void (*cb)(struct test_perf_branches *)) | ||
| { | ||
| struct test_perf_branches *skel; | ||
| int err, i, duration = 0; | ||
| bool detached = false; | ||
| struct bpf_link *link; | ||
| volatile int j = 0; | ||
| cpu_set_t cpu_set; | ||
|
|
||
| skel = test_perf_branches__open_and_load(); | ||
| if (CHECK(!skel, "test_perf_branches_load", | ||
| "perf_branches skeleton failed\n")) | ||
| return; | ||
|
|
||
| /* attach perf_event */ | ||
| link = bpf_program__attach_perf_event(skel->progs.perf_branches, perf_fd); | ||
| if (CHECK(IS_ERR(link), "attach_perf_event", "err %ld\n", PTR_ERR(link))) | ||
| goto out_destroy_skel; | ||
|
|
||
| /* 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); | ||
| if (CHECK(err, "set_affinity", "cpu #0, err %d\n", err)) | ||
| goto out_destroy; | ||
| /* spin the loop for a while (random high number) */ | ||
| for (i = 0; i < 1000000; ++i) | ||
| ++j; | ||
|
|
||
| test_perf_branches__detach(skel); | ||
| detached = true; | ||
|
|
||
| cb(skel); | ||
| out_destroy: | ||
| bpf_link__destroy(link); | ||
| out_destroy_skel: | ||
| if (!detached) | ||
| test_perf_branches__detach(skel); | ||
| test_perf_branches__destroy(skel); | ||
| } | ||
|
|
||
| static void test_perf_branches_hw(void) | ||
| { | ||
| struct perf_event_attr attr = {0}; | ||
| int duration = 0; | ||
| int pfd; | ||
|
|
||
| /* create perf event */ | ||
| attr.size = sizeof(attr); | ||
| attr.type = PERF_TYPE_HARDWARE; | ||
| attr.config = PERF_COUNT_HW_CPU_CYCLES; | ||
| attr.freq = 1; | ||
| attr.sample_freq = 4000; | ||
| attr.sample_type = PERF_SAMPLE_BRANCH_STACK; | ||
| attr.branch_sample_type = PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY; | ||
| pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); | ||
|
|
||
| /* | ||
| * Some setups don't support branch records (virtual machines, !x86), | ||
| * so skip test in this case. | ||
| */ | ||
| if (pfd == -1) { | ||
| if (errno == ENOENT || errno == EOPNOTSUPP) { | ||
| printf("%s:SKIP:no PERF_SAMPLE_BRANCH_STACK\n", | ||
| __func__); | ||
| test__skip(); | ||
| return; | ||
| } | ||
| if (CHECK(pfd < 0, "perf_event_open", "err %d errno %d\n", | ||
| pfd, errno)) | ||
| return; | ||
| } | ||
|
|
||
| test_perf_branches_common(pfd, check_good_sample); | ||
|
|
||
| close(pfd); | ||
| } | ||
|
|
||
| /* | ||
| * Tests negative case -- run bpf_read_branch_records() on improperly configured | ||
| * perf event. | ||
| */ | ||
| static void test_perf_branches_no_hw(void) | ||
| { | ||
| struct perf_event_attr attr = {0}; | ||
| int duration = 0; | ||
| int pfd; | ||
|
|
||
| /* create perf event */ | ||
| 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 (CHECK(pfd < 0, "perf_event_open", "err %d\n", pfd)) | ||
| return; | ||
|
|
||
| test_perf_branches_common(pfd, check_bad_sample); | ||
|
|
||
| close(pfd); | ||
| } | ||
|
|
||
| void test_perf_branches(void) | ||
| { | ||
| if (test__start_subtest("perf_branches_hw")) | ||
| test_perf_branches_hw(); | ||
| if (test__start_subtest("perf_branches_no_hw")) | ||
| test_perf_branches_no_hw(); | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,50 @@ | ||
| // SPDX-License-Identifier: GPL-2.0 | ||
| // Copyright (c) 2019 Facebook | ||
|
|
||
| #include <stddef.h> | ||
| #include <linux/ptrace.h> | ||
| #include <linux/bpf.h> | ||
| #include <bpf/bpf_helpers.h> | ||
| #include "bpf_trace_helpers.h" | ||
|
|
||
| int valid = 0; | ||
| int required_size_out = 0; | ||
| int written_stack_out = 0; | ||
| int written_global_out = 0; | ||
|
|
||
| struct { | ||
| __u64 _a; | ||
| __u64 _b; | ||
| __u64 _c; | ||
| } fpbe[30] = {0}; | ||
|
|
||
| SEC("perf_event") | ||
| int perf_branches(void *ctx) | ||
| { | ||
| __u64 entries[4 * 3] = {0}; | ||
| int required_size, written_stack, written_global; | ||
|
|
||
| /* write to stack */ | ||
| written_stack = bpf_read_branch_records(ctx, entries, sizeof(entries), 0); | ||
| /* ignore spurious events */ | ||
| if (!written_stack) | ||
| return 1; | ||
|
|
||
| /* get required size */ | ||
| required_size = bpf_read_branch_records(ctx, NULL, 0, | ||
| BPF_F_GET_BRANCH_RECORDS_SIZE); | ||
|
|
||
| written_global = bpf_read_branch_records(ctx, fpbe, sizeof(fpbe), 0); | ||
| /* ignore spurious events */ | ||
| if (!written_global) | ||
| return 1; | ||
|
|
||
| required_size_out = required_size; | ||
| written_stack_out = written_stack; | ||
| written_global_out = written_global; | ||
| valid = 1; | ||
|
|
||
| return 0; | ||
| } | ||
|
|
||
| char _license[] SEC("license") = "GPL"; |