mirrors/linux
2
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-05-11 01:53:20 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'perf-s390-regression-move-uid-filtering-to-bpf-filters'

Browse Source 
Ilya Leoshkevich says:

====================
perf/s390: Regression: Move uid filtering to BPF filters

v4: https://lore.kernel.org/bpf/20250806114227.14617-1-iii@linux.ibm.com/
v4 -> v5: Fix a typo in the commit message (Yonghong).

v3: https://lore.kernel.org/bpf/20250805130346.1225535-1-iii@linux.ibm.com/
v3 -> v4: Rename the new field to dont_enable (Alexei, Eduard).
          Switch the Fixes: tag in patch 2 (Alexander, Thomas).
          Fix typos in the cover letter (Thomas).

v2: https://lore.kernel.org/bpf/20250728144340.711196-1-tmricht@linux.ibm.com/
v2 -> v3: Use no_ioctl_enable in perf.

v1: https://lore.kernel.org/bpf/20250725093405.3629253-1-tmricht@linux.ibm.com/
v1 -> v2: Introduce no_ioctl_enable (Jiri).

Hi,

This series fixes a regression caused by moving UID filtering to BPF.
The regression affects all events that support auxiliary data, most
notably, "cycles" events on s390, but also PT events on Intel. The
symptom is missing events when UID filtering is enabled.

Patch 1 introduces a new option for the
bpf_program__attach_perf_event_opts() function.
Patch 2 makes use of it in perf, and also contains a lot of technical
details of why exactly the problem is occurring.

Thanks to Thomas Richter for the investigation and the initial version
of this fix, and to Jiri Olsa for suggestions.

Best regards,
Ilya
====================

Link: https://patch.msgid.link/20250806162417.19666-1-iii@linux.ibm.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This commit is contained in:
Alexei Starovoitov
2025-08-07 09:01:41 -07:00
parent 1b30d44417 5e2ac8e857
commit 0e260fc798
3 changed files with 15 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
tools/lib/bpf/libbpf.c
View File

@@ -10965,11 +10965,14 @@ struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *p
}
link->link.fd = pfd;
}
if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
err = -errno;
pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n",
prog->name, pfd, errstr(err));
goto err_out;
if (!OPTS_GET(opts, dont_enable, false)) {
if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) {
err = -errno;
pr_warn("prog '%s': failed to enable perf_event FD %d: %s\n",
prog->name, pfd, errstr(err));
goto err_out;
}
}
return &link->link;

4
tools/lib/bpf/libbpf.h
View File

@@ -499,9 +499,11 @@ struct bpf_perf_event_opts {
__u64 bpf_cookie;
/* don't use BPF link when attach BPF program */
bool force_ioctl_attach;
/* don't automatically enable the event */
bool dont_enable;
size_t :0;
};
#define bpf_perf_event_opts__last_field force_ioctl_attach
#define bpf_perf_event_opts__last_field dont_enable
LIBBPF_API struct bpf_link *
bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd);

5
tools/perf/util/bpf-filter.c
View File

@@ -451,6 +451,8 @@ int perf_bpf_filter__prepare(struct evsel *evsel, struct target *target)
struct bpf_link *link;
struct perf_bpf_filter_entry *entry;
bool needs_idx_hash = !target__has_cpu(target);
DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts,
.dont_enable = true);
entry = calloc(MAX_FILTERS, sizeof(*entry));
if (entry == NULL)
@@ -522,7 +524,8 @@ int perf_bpf_filter__prepare(struct evsel *evsel, struct target *target)
prog = skel->progs.perf_sample_filter;
for (x = 0; x < xyarray__max_x(evsel->core.fd); x++) {
for (y = 0; y < xyarray__max_y(evsel->core.fd); y++) {
link = bpf_program__attach_perf_event(prog, FD(evsel, x, y));
link = bpf_program__attach_perf_event_opts(prog, FD(evsel, x, y),
&pe_opts);
if (IS_ERR(link)) {
pr_err("Failed to attach perf sample-filter program\n");
ret = PTR_ERR(link);