* [PATCHv3 bpf-next 22/24] selftests/bpf: Add tracing multi attach fails test
From: Jiri Olsa @ 2026-03-16 7:51 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260316075138.465430-1-jolsa@kernel.org>
Adding tests for attach fails on tracing multi link.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
.../selftests/bpf/prog_tests/tracing_multi.c | 74 +++++++++++++++++++
.../selftests/bpf/progs/tracing_multi_fail.c | 19 +++++
2 files changed, 93 insertions(+)
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_fail.c
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_multi.c b/tools/testing/selftests/bpf/prog_tests/tracing_multi.c
index 04d83c37495b..9f4c5af88e21 100644
--- a/tools/testing/selftests/bpf/prog_tests/tracing_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_multi.c
@@ -8,6 +8,7 @@
#include "tracing_multi_module.skel.h"
#include "tracing_multi_intersect.skel.h"
#include "tracing_multi_session.skel.h"
+#include "tracing_multi_fail.skel.h"
#include "trace_helpers.h"
static __u64 bpf_fentry_test_cookies[] = {
@@ -480,6 +481,77 @@ static void test_session(void)
tracing_multi_session__destroy(skel);
}
+static void test_attach_api_fails(void)
+{
+ LIBBPF_OPTS(bpf_tracing_multi_opts, opts);
+ static const char * const func[] = {
+ "bpf_fentry_test2",
+ };
+ struct tracing_multi_fail *skel = NULL;
+ __u32 ids[2], *ids2;
+ __u64 cookies[2];
+
+ skel = tracing_multi_fail__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "tracing_multi_fail__open_and_load"))
+ return;
+
+ /* fail#1 pattern and opts NULL */
+ skel->links.test_fentry = bpf_program__attach_tracing_multi(skel->progs.test_fentry,
+ NULL, NULL);
+ if (!ASSERT_ERR_PTR(skel->links.test_fentry, "bpf_program__attach_tracing_multi"))
+ goto cleanup;
+
+ /* fail#2 pattern and ids */
+ opts.ids = ids;
+ opts.cnt = 2;
+
+ skel->links.test_fentry = bpf_program__attach_tracing_multi(skel->progs.test_fentry,
+ "bpf_fentry_test*", &opts);
+ if (!ASSERT_ERR_PTR(skel->links.test_fentry, "bpf_program__attach_tracing_multi"))
+ goto cleanup;
+
+ /* fail#3 pattern and cookies */
+ opts.ids = NULL;
+ opts.cnt = 2;
+ opts.cookies = cookies;
+
+ skel->links.test_fentry = bpf_program__attach_tracing_multi(skel->progs.test_fentry,
+ "bpf_fentry_test*", &opts);
+ if (!ASSERT_ERR_PTR(skel->links.test_fentry, "bpf_program__attach_tracing_multi"))
+ goto cleanup;
+
+ /* fail#4 bogus pattern */
+ skel->links.test_fentry = bpf_program__attach_tracing_multi(skel->progs.test_fentry,
+ "bpf_not_really_a_function*", NULL);
+ if (!ASSERT_ERR_PTR(skel->links.test_fentry, "bpf_program__attach_tracing_multi"))
+ goto cleanup;
+
+ /* fail#5 abnormal cnt */
+ opts.ids = ids;
+ opts.cnt = INT_MAX;
+
+ skel->links.test_fentry = bpf_program__attach_tracing_multi(skel->progs.test_fentry,
+ NULL, &opts);
+ if (!ASSERT_ERR_PTR(skel->links.test_fentry, "bpf_program__attach_tracing_multi"))
+ goto cleanup;
+
+ /* fail#6 attach sleepable program to not-allowed function */
+ ids2 = get_ids(func, 1, NULL);
+ if (!ASSERT_OK_PTR(ids, "get_ids"))
+ goto cleanup;
+
+ opts.ids = ids2;
+ opts.cnt = 1;
+
+ skel->links.test_fentry_s = bpf_program__attach_tracing_multi(skel->progs.test_fentry_s,
+ NULL, &opts);
+ ASSERT_ERR_PTR(skel->links.test_fentry, "bpf_program__attach_tracing_multi");
+ free(ids2);
+
+cleanup:
+ tracing_multi_fail__destroy(skel);
+}
+
void test_tracing_multi_test(void)
{
#ifndef __x86_64__
@@ -505,4 +577,6 @@ void test_tracing_multi_test(void)
test_link_api_ids(true);
if (test__start_subtest("session"))
test_session();
+ if (test__start_subtest("attach_api_fails"))
+ test_attach_api_fails();
}
diff --git a/tools/testing/selftests/bpf/progs/tracing_multi_fail.c b/tools/testing/selftests/bpf/progs/tracing_multi_fail.c
new file mode 100644
index 000000000000..8f769ddb9136
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tracing_multi_fail.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fentry.multi")
+int BPF_PROG(test_fentry)
+{
+ return 0;
+}
+
+SEC("fentry.multi.s")
+int BPF_PROG(test_fentry_s)
+{
+ return 0;
+}
--
2.53.0
^ permalink raw reply related
* [PATCHv3 bpf-next 23/24] selftests/bpf: Add tracing multi attach benchmark test
From: Jiri Olsa @ 2026-03-16 7:51 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260316075138.465430-1-jolsa@kernel.org>
Adding benchmark test that attaches to (almost) all allowed tracing
functions and display attach/detach times.
# ./test_progs -t tracing_multi_bench_attach -v
bpf_testmod.ko is already unloaded.
Loading bpf_testmod.ko...
Successfully loaded bpf_testmod.ko.
serial_test_tracing_multi_bench_attach:PASS:btf__load_vmlinux_btf 0 nsec
serial_test_tracing_multi_bench_attach:PASS:tracing_multi_bench__open_and_load 0 nsec
serial_test_tracing_multi_bench_attach:PASS:get_syms 0 nsec
serial_test_tracing_multi_bench_attach:PASS:bpf_program__attach_tracing_multi 0 nsec
serial_test_tracing_multi_bench_attach: found 51186 functions
serial_test_tracing_multi_bench_attach: attached in 1.295s
serial_test_tracing_multi_bench_attach: detached in 0.243s
#507 tracing_multi_bench_attach:OK
Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED
Successfully unloaded bpf_testmod.ko.
Exporting skip_entry as is_unsafe_function and usign it in the test.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
.../selftests/bpf/prog_tests/tracing_multi.c | 97 +++++++++++++++++++
.../selftests/bpf/progs/tracing_multi_bench.c | 13 +++
tools/testing/selftests/bpf/trace_helpers.c | 6 +-
tools/testing/selftests/bpf/trace_helpers.h | 1 +
4 files changed, 114 insertions(+), 3 deletions(-)
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_bench.c
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_multi.c b/tools/testing/selftests/bpf/prog_tests/tracing_multi.c
index 9f4c5af88e21..a0fcda51bb6c 100644
--- a/tools/testing/selftests/bpf/prog_tests/tracing_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_multi.c
@@ -9,6 +9,7 @@
#include "tracing_multi_intersect.skel.h"
#include "tracing_multi_session.skel.h"
#include "tracing_multi_fail.skel.h"
+#include "tracing_multi_bench.skel.h"
#include "trace_helpers.h"
static __u64 bpf_fentry_test_cookies[] = {
@@ -552,6 +553,102 @@ static void test_attach_api_fails(void)
tracing_multi_fail__destroy(skel);
}
+void serial_test_tracing_multi_bench_attach(void)
+{
+ LIBBPF_OPTS(bpf_tracing_multi_opts, opts);
+ struct tracing_multi_bench *skel = NULL;
+ long attach_start_ns, attach_end_ns;
+ long detach_start_ns, detach_end_ns;
+ double attach_delta, detach_delta;
+ struct bpf_link *link = NULL;
+ size_t i, cap = 0, cnt = 0;
+ struct ksyms *ksyms = NULL;
+ void *root = NULL;
+ __u32 *ids = NULL;
+ __u32 nr, type_id;
+ struct btf *btf;
+ int err;
+
+#ifndef __x86_64__
+ test__skip();
+ return;
+#endif
+
+ btf = btf__load_vmlinux_btf();
+ if (!ASSERT_OK_PTR(btf, "btf__load_vmlinux_btf"))
+ return;
+
+ skel = tracing_multi_bench__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "tracing_multi_bench__open_and_load"))
+ goto cleanup;
+
+ if (!ASSERT_OK(bpf_get_ksyms(&ksyms, true), "get_syms"))
+ goto cleanup;
+
+ /* Get all ftrace 'safe' symbols.. */
+ for (i = 0; i < ksyms->filtered_cnt; i++) {
+ if (is_unsafe_function(ksyms->filtered_syms[i]))
+ continue;
+ tsearch(&ksyms->filtered_syms[i], &root, compare);
+ }
+
+ /* ..and filter them through BTF and btf_type_is_traceable_func. */
+ nr = btf__type_cnt(btf);
+ for (type_id = 1; type_id < nr; type_id++) {
+ const struct btf_type *type;
+ const char *str;
+
+ type = btf__type_by_id(btf, type_id);
+ if (!type)
+ break;
+
+ if (BTF_INFO_KIND(type->info) != BTF_KIND_FUNC)
+ continue;
+
+ str = btf__name_by_offset(btf, type->name_off);
+ if (!str)
+ break;
+
+ if (!tfind(&str, &root, compare))
+ continue;
+
+ if (!btf_type_is_traceable_func(btf, type))
+ continue;
+
+ err = libbpf_ensure_mem((void **) &ids, &cap, sizeof(*ids), cnt + 1);
+ if (err)
+ goto cleanup;
+
+ ids[cnt++] = type_id;
+ }
+
+ opts.ids = ids;
+ opts.cnt = cnt;
+
+ attach_start_ns = get_time_ns();
+ link = bpf_program__attach_tracing_multi(skel->progs.bench, NULL, &opts);
+ attach_end_ns = get_time_ns();
+
+ if (!ASSERT_OK_PTR(link, "bpf_program__attach_tracing_multi"))
+ goto cleanup;
+
+ detach_start_ns = get_time_ns();
+ bpf_link__destroy(link);
+ detach_end_ns = get_time_ns();
+
+ attach_delta = (attach_end_ns - attach_start_ns) / 1000000000.0;
+ detach_delta = (detach_end_ns - detach_start_ns) / 1000000000.0;
+
+ printf("%s: found %lu functions\n", __func__, cnt);
+ printf("%s: attached in %7.3lfs\n", __func__, attach_delta);
+ printf("%s: detached in %7.3lfs\n", __func__, detach_delta);
+
+cleanup:
+ tracing_multi_bench__destroy(skel);
+ free_kallsyms_local(ksyms);
+ free(ids);
+}
+
void test_tracing_multi_test(void)
{
#ifndef __x86_64__
diff --git a/tools/testing/selftests/bpf/progs/tracing_multi_bench.c b/tools/testing/selftests/bpf/progs/tracing_multi_bench.c
new file mode 100644
index 000000000000..067ba668489b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tracing_multi_bench.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("fentry.multi")
+int BPF_PROG(bench)
+{
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 0e63daf83ed5..3bf600f3271b 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -548,7 +548,7 @@ static const char * const trace_blacklist[] = {
"bpf_get_numa_node_id",
};
-static bool skip_entry(char *name)
+bool is_unsafe_function(char *name)
{
int i;
@@ -651,7 +651,7 @@ int bpf_get_ksyms(struct ksyms **ksymsp, bool kernel)
free(name);
if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1)
continue;
- if (skip_entry(name))
+ if (is_unsafe_function(name))
continue;
ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare);
@@ -728,7 +728,7 @@ int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel)
free(name);
if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2)
continue;
- if (skip_entry(name))
+ if (is_unsafe_function(name))
continue;
if (cnt == max_cnt) {
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index d5bf1433675d..d93be322675d 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -63,4 +63,5 @@ int read_build_id(const char *path, char *build_id, size_t size);
int bpf_get_ksyms(struct ksyms **ksymsp, bool kernel);
int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel);
+bool is_unsafe_function(char *name);
#endif
--
2.53.0
^ permalink raw reply related
* [PATCHv3 bpf-next 24/24] selftests/bpf: Add tracing multi attach rollback tests
From: Jiri Olsa @ 2026-03-16 7:51 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: bpf, linux-trace-kernel, Martin KaFai Lau, Eduard Zingerman,
Song Liu, Yonghong Song, Menglong Dong, Steven Rostedt
In-Reply-To: <20260316075138.465430-1-jolsa@kernel.org>
Adding tests for the rollback code when the tracing_multi
link won't get attached, covering 2 reasons:
- wrong btf id passed by user, where all previously allocated
trampolines will be released
- trampoline for requested function is fully attached (has already
maximum programs attached) and the link fails, the rollback code
needs to release all previously link-ed trampolines and release
them
We need the bpf_fentry_test* unattached for the tests to pass,
so the rollback tests are serial.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
.../selftests/bpf/prog_tests/tracing_multi.c | 181 ++++++++++++++++++
.../bpf/progs/tracing_multi_rollback.c | 38 ++++
2 files changed, 219 insertions(+)
create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_rollback.c
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_multi.c b/tools/testing/selftests/bpf/prog_tests/tracing_multi.c
index a0fcda51bb6c..10b8cc6b368b 100644
--- a/tools/testing/selftests/bpf/prog_tests/tracing_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_multi.c
@@ -10,6 +10,7 @@
#include "tracing_multi_session.skel.h"
#include "tracing_multi_fail.skel.h"
#include "tracing_multi_bench.skel.h"
+#include "tracing_multi_rollback.skel.h"
#include "trace_helpers.h"
static __u64 bpf_fentry_test_cookies[] = {
@@ -649,6 +650,186 @@ void serial_test_tracing_multi_bench_attach(void)
free(ids);
}
+static void tracing_multi_rollback_run(struct tracing_multi_rollback *skel)
+{
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ int err, prog_fd;
+
+ prog_fd = bpf_program__fd(skel->progs.test_fentry);
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+ ASSERT_OK(err, "test_run");
+
+ /* make sure the rollback code did not leave any program attached */
+ ASSERT_EQ(skel->bss->test_result_fentry, 0, "test_result_fentry");
+ ASSERT_EQ(skel->bss->test_result_fexit, 0, "test_result_fexit");
+}
+
+static void test_rollback_put(void)
+{
+ LIBBPF_OPTS(bpf_tracing_multi_opts, opts);
+ struct tracing_multi_rollback *skel = NULL;
+ size_t cnt = FUNCS_CNT;
+ __u32 *ids = NULL;
+ int err;
+
+ skel = tracing_multi_rollback__open();
+ if (!ASSERT_OK_PTR(skel, "tracing_multi_rollback__open"))
+ return;
+
+ bpf_program__set_autoload(skel->progs.test_fentry, true);
+ bpf_program__set_autoload(skel->progs.test_fexit, true);
+
+ err = tracing_multi_rollback__load(skel);
+ if (!ASSERT_OK(err, "tracing_multi_rollback__load"))
+ goto cleanup;
+
+ ids = get_ids(bpf_fentry_test, cnt, NULL);
+ if (!ASSERT_OK_PTR(ids, "get_ids"))
+ goto cleanup;
+
+ /*
+ * Mangle last id to trigger rollback, which needs to do put
+ * on get-ed trampolines.
+ */
+ ids[9] = 0;
+
+ opts.ids = ids;
+ opts.cnt = cnt;
+
+ skel->bss->pid = getpid();
+
+ skel->links.test_fentry = bpf_program__attach_tracing_multi(skel->progs.test_fentry,
+ NULL, &opts);
+ if (!ASSERT_ERR_PTR(skel->links.test_fentry, "bpf_program__attach_tracing_multi"))
+ goto cleanup;
+
+ skel->links.test_fexit = bpf_program__attach_tracing_multi(skel->progs.test_fexit,
+ NULL, &opts);
+ if (!ASSERT_ERR_PTR(skel->links.test_fexit, "bpf_program__attach_tracing_multi"))
+ goto cleanup;
+
+ /* We don't really attach any program, but let's make sure. */
+ tracing_multi_rollback_run(skel);
+
+cleanup:
+ tracing_multi_rollback__destroy(skel);
+ free(ids);
+}
+
+
+static void fillers_cleanup(struct tracing_multi_rollback **skels, int cnt)
+{
+ int i;
+
+ for (i = 0; i < cnt; i++)
+ tracing_multi_rollback__destroy(skels[i]);
+
+ free(skels);
+}
+
+static struct tracing_multi_rollback **fillers_load_and_link(int max)
+{
+ struct tracing_multi_rollback **skels, *skel;
+ int i, err;
+
+ skels = calloc(max + 1, sizeof(*skels));
+ if (!ASSERT_OK_PTR(skels, "calloc"))
+ return NULL;
+
+ for (i = 0; i < max; i++) {
+ skel = skels[i] = tracing_multi_rollback__open();
+ if (!ASSERT_OK_PTR(skels[i], "tracing_multi_rollback__open"))
+ goto cleanup;
+
+ bpf_program__set_autoload(skel->progs.filler, true);
+
+ err = tracing_multi_rollback__load(skel);
+ if (!ASSERT_OK(err, "tracing_multi_rollback__load"))
+ goto cleanup;
+
+ skel->links.filler = bpf_program__attach_trace(skel->progs.filler);
+ if (!ASSERT_OK_PTR(skels[i]->links.filler, "bpf_program__attach_trace"))
+ goto cleanup;
+ }
+
+ return skels;
+
+cleanup:
+ fillers_cleanup(skels, i);
+ return NULL;
+}
+
+static void test_rollback_unlink(void)
+{
+ LIBBPF_OPTS(bpf_tracing_multi_opts, opts);
+ struct tracing_multi_rollback **fillers;
+ struct tracing_multi_rollback *skel;
+ size_t cnt = FUNCS_CNT;
+ __u32 *ids = NULL;
+ int err, max;
+
+ max = get_bpf_max_tramp_links();
+ if (!ASSERT_GE(max, 1, "bpf_max_tramp_links"))
+ return;
+
+ /* Attach maximum allowed programs to bpf_fentry_test10 */
+ fillers = fillers_load_and_link(max);
+ if (!ASSERT_OK_PTR(fillers, "fillers_load_and_link"))
+ return;
+
+ skel = tracing_multi_rollback__open();
+ if (!ASSERT_OK_PTR(skel, "tracing_multi_rollback__open"))
+ goto cleanup;
+
+ bpf_program__set_autoload(skel->progs.test_fentry, true);
+ bpf_program__set_autoload(skel->progs.test_fexit, true);
+
+ /*
+ * Attach tracing_multi link on bpf_fentry_test1-10, which will
+ * fail on bpf_fentry_test10 function, because it already has
+ * maximum allowed programs attached.
+ *
+ * The rollback needs to unlink already link-ed trampolines and
+ * put all of them.
+ */
+ err = tracing_multi_rollback__load(skel);
+ if (!ASSERT_OK(err, "tracing_multi_rollback__load"))
+ goto cleanup;
+
+ ids = get_ids(bpf_fentry_test, cnt, NULL);
+ if (!ASSERT_OK_PTR(ids, "get_ids"))
+ goto cleanup;
+
+ opts.ids = ids;
+ opts.cnt = cnt;
+
+ skel->bss->pid = getpid();
+
+ skel->links.test_fentry = bpf_program__attach_tracing_multi(skel->progs.test_fentry,
+ NULL, &opts);
+ if (!ASSERT_ERR_PTR(skel->links.test_fentry, "bpf_program__attach_tracing_multi"))
+ goto cleanup;
+
+ skel->links.test_fexit = bpf_program__attach_tracing_multi(skel->progs.test_fexit,
+ NULL, &opts);
+ if (!ASSERT_ERR_PTR(skel->links.test_fexit, "bpf_program__attach_tracing_multi"))
+ goto cleanup;
+
+ tracing_multi_rollback_run(skel);
+
+cleanup:
+ fillers_cleanup(fillers, max);
+ free(ids);
+}
+
+void serial_test_tracing_multi_attach_rollback(void)
+{
+ if (test__start_subtest("put"))
+ test_rollback_put();
+ if (test__start_subtest("unlink"))
+ test_rollback_unlink();
+}
+
void test_tracing_multi_test(void)
{
#ifndef __x86_64__
diff --git a/tools/testing/selftests/bpf/progs/tracing_multi_rollback.c b/tools/testing/selftests/bpf/progs/tracing_multi_rollback.c
new file mode 100644
index 000000000000..eb27869f551a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tracing_multi_rollback.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+
+__u64 test_result_fentry = 0;
+__u64 test_result_fexit = 0;
+
+SEC("?fentry.multi")
+int BPF_PROG(test_fentry)
+{
+ if (bpf_get_current_pid_tgid() >> 32 != pid)
+ return 0;
+
+ test_result_fentry++;
+ return 0;
+}
+
+SEC("?fexit.multi")
+int BPF_PROG(test_fexit)
+{
+ if (bpf_get_current_pid_tgid() >> 32 != pid)
+ return 0;
+
+ test_result_fexit++;
+ return 0;
+}
+
+SEC("?fentry/bpf_fentry_test10")
+int BPF_PROG(filler)
+{
+ return 0;
+}
--
2.53.0
^ permalink raw reply related
* Re: [PATCHv3 bpf-next 14/24] libbpf: Add bpf_link_create support for tracing_multi link
From: bot+bpf-ci @ 2026-03-16 8:35 UTC (permalink / raw)
To: jolsa, ast, daniel, andrii
Cc: bpf, linux-trace-kernel, kafai, eddyz87, songliubraving, yhs,
menglong8.dong, rostedt, ast, andrii, daniel, martin.lau, eddyz87,
yonghong.song, clm, ihor.solodrai
In-Reply-To: <20260316075138.465430-15-jolsa@kernel.org>
[-- Attachment #1: Type: text/plain, Size: 1156 bytes --]
> diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
> --- a/tools/lib/bpf/bpf.h
> +++ b/tools/lib/bpf/bpf.h
> @@ -454,6 +454,11 @@ struct bpf_link_create_opts {
> __u64 expected_revision;
> } cgroup;
> + struct {
> + __u32 *ids;
> + __u64 *cookies;
> + __u32 cnt;
> + } tracing_multi;
> };
Should the ids and cookies pointers be const-qualified here?
Every other multi-attach member in this union uses const for
its pointer fields, for example in kprobe_multi:
const char **syms;
const unsigned long *addrs;
const __u64 *cookies;
and in uprobe_multi:
const unsigned long *offsets;
const unsigned long *ref_ctr_offsets;
const __u64 *cookies;
These arrays are input-only (passed straight through to the
kernel via ptr_to_u64), so marking them const would be
consistent with the existing convention and would avoid
compiler warnings for callers passing const arrays.
---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/23133791558
^ permalink raw reply
* Re: [PATCHv3 bpf-next 16/24] libbpf: Add support to create tracing multi link
From: bot+bpf-ci @ 2026-03-16 8:35 UTC (permalink / raw)
To: jolsa, ast, daniel, andrii
Cc: bpf, linux-trace-kernel, kafai, eddyz87, songliubraving, yhs,
menglong8.dong, rostedt, ast, andrii, daniel, martin.lau, eddyz87,
yonghong.song, clm, ihor.solodrai
In-Reply-To: <20260316075138.465430-17-jolsa@kernel.org>
[-- Attachment #1: Type: text/plain, Size: 565 bytes --]
> The provided <pattern> is used as 'pattern' argument in
> bpf_program__attach_kprobe_multi_opts function.
Should this say bpf_program__attach_tracing_multi instead of
bpf_program__attach_kprobe_multi_opts? The auto-attach path in
attach_tracing_multi() calls bpf_program__attach_tracing_multi(),
not the kprobe variant.
---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/23133791558
^ permalink raw reply
* Re: [PATCHv3 bpf-next 02/24] bpf: Use mutex lock pool for bpf trampolines
From: bot+bpf-ci @ 2026-03-16 8:35 UTC (permalink / raw)
To: jolsa, ast, daniel, andrii
Cc: bpf, linux-trace-kernel, kafai, eddyz87, songliubraving, yhs,
menglong8.dong, rostedt, ast, andrii, daniel, martin.lau, eddyz87,
yonghong.song, clm, ihor.solodrai
In-Reply-To: <20260316075138.465430-3-jolsa@kernel.org>
[-- Attachment #1: Type: text/plain, Size: 1366 bytes --]
> diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
> index f02254a21585..9923703a1544 100644
> --- a/kernel/bpf/trampoline.c
> +++ b/kernel/bpf/trampoline.c
[ ... ]
> +/*
> + * We keep 32 trampoline locks (5 bits) in the pool, because there
> + * is 48 (MAX_LOCK_DEPTH) locks limit allowed to be simultaneously
> + * held by task.
> + */
> +#define TRAMPOLINE_LOCKS_BITS 5
> +#define TRAMPOLINE_LOCKS_TABLE_SIZE (1 << TRAMPOLINE_LOCKS_BITS)
> +
> +static struct {
> + struct mutex mutex;
> + struct lock_class_key key;
> +} trampoline_locks[TRAMPOLINE_LOCKS_TABLE_SIZE];
During v1 review, Alexei asked to add a comment explaining both the
pool size of 32 and why per-lock class keys are needed:
https://lore.kernel.org/bpf/CAADnVQL_Jpe_7a55HTn5CyYoxWcHahiK3+CDeOeURqZAuf+teA@mail.gmail.com/
The comment explains the 32 count (MAX_LOCK_DEPTH limit), but does
it also need to mention why each lock has its own lock_class_key?
Without that, it is not obvious that distinct keys are required to
avoid lockdep "recursive locking" warnings when
trampoline_lock_all() acquires all 32 pool mutexes simultaneously.
---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/23133791558
^ permalink raw reply
* Re: [PATCHv3 bpf-next 08/24] bpf: Add bpf_trampoline_multi_attach/detach functions
From: bot+bpf-ci @ 2026-03-16 8:35 UTC (permalink / raw)
To: jolsa, ast, daniel, andrii
Cc: bpf, linux-trace-kernel, kafai, eddyz87, songliubraving, yhs,
menglong8.dong, rostedt, ast, andrii, daniel, martin.lau, eddyz87,
yonghong.song, clm, ihor.solodrai
In-Reply-To: <20260316075138.465430-9-jolsa@kernel.org>
[-- Attachment #1: Type: text/plain, Size: 4562 bytes --]
> The detach works as follows:
> - we lock all the needed trampolines
> - remove the program from each (__bpf_trampoline_unlink_prog)
> - the trampoline_multi_ops passed in __bpf_trampoline_link_prog gathers
> ftrace_hash (ip -> trampoline) objects
The detach description references __bpf_trampoline_link_prog, but the
detach path calls __bpf_trampoline_unlink_prog.
> diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
> index d55651b13511..9331cca8c0b4 100644
> --- a/kernel/bpf/trampoline.c
> +++ b/kernel/bpf/trampoline.c
[ ... ]
> +static int modify_fentry_multi(struct bpf_trampoline *tr, u32 orig_flags, void *old_addr,
> + void *new_addr, bool lock_direct_mutex, void *ptr)
> +{
> + unsigned long addr = (unsigned long) new_addr;
> + unsigned long ip = ftrace_location(tr->ip);
> + struct fentry_multi_data *data = ptr;
> +
> + if (bpf_trampoline_use_jmp(tr->flags))
> + addr = ftrace_jmp_set(addr);
> + return add_ftrace_hash_entry_direct(data->modify, ip, addr) ? 0 : -ENOMEM;
> +}
Unlike the standard modify_fentry() which calls direct_ops_mod() ->
update_ftrace_direct_mod() to update ftrace immediately,
modify_fentry_multi() only adds a hash entry. The actual ftrace
update is deferred until after the link loop.
This matters because bpf_trampoline_update() unconditionally calls
bpf_tramp_image_put() on the old cur_image after a successful
modify_fentry callback:
bpf_trampoline_update() {
...
err = ops->modify_fentry(tr, ...);
...
if (tr->cur_image)
bpf_tramp_image_put(tr->cur_image);
tr->cur_image = im;
}
With the standard ops, the old image is already unreachable when put.
With multi ops, ftrace still points to the old image when it is put.
bpf_tramp_image_put() text-pokes the old image to skip fexit programs
and starts deferred freeing.
In the success path, the window between image_put and the batched
update_ftrace_direct_mod is brief (bounded by trampoline_lock_all).
However, in the rollback path below, ftrace is never updated at all:
[ ... ]
> + trampoline_lock_all();
> +
> + for (i = 0; i < cnt; i++) {
> + mnode = &link->nodes[i];
> + err = __bpf_trampoline_link_prog(&mnode->node, mnode->trampoline, NULL,
> + &trampoline_multi_ops, &data);
> + if (err)
> + goto rollback_unlink;
> + }
[ ... ]
> +rollback_unlink:
> + for (j = 0; j < i; j++) {
> + mnode = &link->nodes[j];
> + WARN_ON_ONCE(__bpf_trampoline_unlink_prog(&mnode->node, mnode->trampoline,
> + NULL, &trampoline_multi_ops, &data));
> + }
> + trampoline_unlock_all();
> +
> + i = cnt;
If a trampoline at index 0 already had programs attached through the
standard single-trampoline path, and __bpf_trampoline_link_prog
succeeds for it but fails for a later trampoline, the rollback path
restores tr->cur_image to a correct new image but never calls
update_ftrace_direct_mod.
At that point, ftrace still routes calls through the old image that
was put during the link phase. bpf_tramp_image_put() has already
patched that old image to skip fexit programs and started the deferred
freeing sequence (percpu_ref_kill).
Could this leave existing fexit/fmod_ret programs on that trampoline
non-functional? And once the percpu_ref drains during a quiet period,
would the old image be freed while ftrace still references it?
[ ... ]
> +int bpf_trampoline_multi_detach(struct bpf_prog *prog, struct bpf_tracing_multi_link *link)
> +{
> + struct bpf_tracing_multi_node *mnode;
> + struct fentry_multi_data data = {};
> + int i, cnt = link->nodes_cnt;
> +
> + data.unreg = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
> + data.modify = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
> +
> + if (!data.unreg || !data.modify) {
> + free_fentry_multi_data(&data);
> + return -ENOMEM;
> + }
bpf_trampoline_multi_detach can return -ENOMEM here without detaching
anything. In e80a839e3d2c ("bpf: Add support for tracing multi
link"), this is called from bpf_tracing_multi_link_release():
WARN_ON_ONCE(bpf_trampoline_multi_detach(link->prog, tr_link));
If detach fails, the programs remain linked to the trampolines via
mnode->node.tramp_hlist, but the link (and its embedded nodes array)
is freed by bpf_tracing_multi_link_dealloc(). Would this leave
dangling hlist entries in each trampoline's progs_hlist?
---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/23133791558
^ permalink raw reply
* [PATCH v3] tracing: Generate undef symbols allowlist for simple_ring_buffer
From: Vincent Donnefort @ 2026-03-16 9:28 UTC (permalink / raw)
To: maz
Cc: rostedt, arnd, nathan, linux-trace-kernel, kvmarm, kernel-team,
Vincent Donnefort
Compiler and tooling-generated symbols are difficult to maintain
across all supported architectures. Make the allowlist more robust by
replacing the harcoded list with a mechanism that automatically detects
these symbols.
This mechanism generates a C function designed to trigger common
compiler-inserted symbols.
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
---
Changes in v3:
- Enforce KASAN to ensure FORTIFY_SOURCE isn't disabled on some arch (Nathan)
Changes in v2:
- Use filechk (Nathan)
- Removed deprecated extra-y (Nathan)
- Added simple_ring_buffer in allowlist (Nathan)
- Added memcpy() to generate more symbols (Nathan)
- Added __sancov
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index beb15936829d..f4503a001d4c 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -136,17 +136,47 @@ obj-$(CONFIG_TRACE_REMOTE_TEST) += remote_test.o
# simple_ring_buffer is used by the pKVM hypervisor which does not have access
# to all kernel symbols. Fail the build if forbidden symbols are found.
#
-UNDEFINED_ALLOWLIST := memset alt_cb_patch_nops __x86 __ubsan __asan __kasan __gcov __aeabi_unwind
-UNDEFINED_ALLOWLIST += __stack_chk_fail stackleak_track_stack __ref_stack __sanitizer llvm_gcda llvm_gcov
-UNDEFINED_ALLOWLIST += .TOC\. __clear_pages_unrolled __memmove copy_page warn_slowpath_fmt
-UNDEFINED_ALLOWLIST += ftrace_likely_update __hwasan_load __hwasan_store __hwasan_tag_memory
-UNDEFINED_ALLOWLIST += warn_bogus_irq_restore __stack_chk_guard
-UNDEFINED_ALLOWLIST := $(addprefix -e , $(UNDEFINED_ALLOWLIST))
+# undefsyms_base generates a set of compiler and tooling-generated symbols that can
+# safely be ignored for simple_ring_buffer.
+#
+filechk_undefsyms_base = \
+ echo '$(pound)include <linux/atomic.h>'; \
+ echo '$(pound)include <linux/string.h>'; \
+ echo '$(pound)include <asm/page.h>'; \
+ echo 'static char page[PAGE_SIZE] __aligned(PAGE_SIZE);'; \
+ echo 'void undefsyms_base(void *p, int n);'; \
+ echo 'void undefsyms_base(void *p, int n) {'; \
+ echo ' char buffer[256] = { 0 };'; \
+ echo ' u32 u = 0;'; \
+ echo ' memset((char * volatile)page, 8, PAGE_SIZE);'; \
+ echo ' memset((char * volatile)buffer, 8, sizeof(buffer));'; \
+ echo ' memcpy((void * volatile)p, buffer, sizeof(buffer));'; \
+ echo ' cmpxchg((u32 * volatile)&u, 0, 8);'; \
+ echo ' WARN_ON(n == 0xdeadbeef);'; \
+ echo '}'
+
+$(obj)/undefsyms_base.c: FORCE
+ $(call filechk,undefsyms_base)
+
+clean-files += undefsyms_base.c
+
+$(obj)/undefsyms_base.o: $(obj)/undefsyms_base.c
+
+targets += undefsyms_base.o
+
+# Ensure KASAN is enabled to avoid logic that may disable FORTIFY_SOURCE when
+# KASAN is not enabled. undefsyms_base.o does not automatically get KASAN flags
+# because it is not linked into vmlinux.
+KASAN_SANITIZE_undefsyms_base.o := y
+
+UNDEFINED_ALLOWLIST = __asan __gcov __kasan __kcsan __hwasan __sancov __sanitizer __tsan __ubsan __x86_indirect_thunk \
+ simple_ring_buffer \
+ $(shell $(NM) -u $(obj)/undefsyms_base.o 2>/dev/null | awk '{print $$2}')
quiet_cmd_check_undefined = NM $<
- cmd_check_undefined = test -z "`$(NM) -u $< | grep -v $(UNDEFINED_ALLOWLIST)`"
+ cmd_check_undefined = test -z "`$(NM) -u $< | grep -v $(addprefix -e , $(UNDEFINED_ALLOWLIST))`"
-$(obj)/%.o.checked: $(obj)/%.o FORCE
+$(obj)/%.o.checked: $(obj)/%.o $(obj)/undefsyms_base.o FORCE
$(call if_changed,check_undefined)
always-$(CONFIG_SIMPLE_RING_BUFFER) += simple_ring_buffer.o.checked
base-commit: 33f2e266515717c4b2df585dadefa0525557726c
--
2.53.0.851.ga537e3e6e9-goog
^ permalink raw reply related
* Re: [PATCH v2] tracing: Generate undef symbols allowlist for simple_ring_buffer
From: Vincent Donnefort @ 2026-03-16 9:31 UTC (permalink / raw)
To: Nathan Chancellor
Cc: maz, rostedt, arnd, linux-trace-kernel, kvmarm, kernel-team
In-Reply-To: <20260313163724.GA2573924@ax162>
On Fri, Mar 13, 2026 at 09:37:24AM -0700, Nathan Chancellor wrote:
> On Fri, Mar 13, 2026 at 10:58:29AM +0000, Vincent Donnefort wrote:
> > Compiler and tooling-generated symbols are difficult to maintain
> > across all supported architectures. Make the allowlist more robust by
> > replacing the harcoded list with a mechanism that automatically detects
> > these symbols.
> >
> > This mechanism generates a C function designed to trigger common
> > compiler-inserted symbols.
> >
> > Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
> >
> > ---
> >
> > Changes in v2:
> >
> > - Use filechk (Nathan)
> > - Removed deprecated extra-y (Nathan)
> > - Added simple_ring_buffer in allowlist (Nathan)
> > - Added memcpy() to generate more symbols (Nathan)
> > - Added __sancov
> >
> > diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
> > index beb15936829d..96627a909ecc 100644
> > --- a/kernel/trace/Makefile
> > +++ b/kernel/trace/Makefile
> > @@ -136,17 +136,42 @@ obj-$(CONFIG_TRACE_REMOTE_TEST) += remote_test.o
> > # simple_ring_buffer is used by the pKVM hypervisor which does not have access
> > # to all kernel symbols. Fail the build if forbidden symbols are found.
> > #
> > -UNDEFINED_ALLOWLIST := memset alt_cb_patch_nops __x86 __ubsan __asan __kasan __gcov __aeabi_unwind
> > -UNDEFINED_ALLOWLIST += __stack_chk_fail stackleak_track_stack __ref_stack __sanitizer llvm_gcda llvm_gcov
> > -UNDEFINED_ALLOWLIST += .TOC\. __clear_pages_unrolled __memmove copy_page warn_slowpath_fmt
> > -UNDEFINED_ALLOWLIST += ftrace_likely_update __hwasan_load __hwasan_store __hwasan_tag_memory
> > -UNDEFINED_ALLOWLIST += warn_bogus_irq_restore __stack_chk_guard
> > -UNDEFINED_ALLOWLIST := $(addprefix -e , $(UNDEFINED_ALLOWLIST))
> > +# undefsyms_base generates a set of compiler and tooling-generated symbols that can
> > +# safely be ignored for simple_ring_buffer.
> > +#
> > +filechk_undefsyms_base = \
> > + echo '$(pound)include <linux/atomic.h>'; \
> > + echo '$(pound)include <linux/string.h>'; \
> > + echo '$(pound)include <asm/page.h>'; \
> > + echo 'static char page[PAGE_SIZE] __aligned(PAGE_SIZE);'; \
> > + echo 'void undefsyms_base(void *p, int n);'; \
> > + echo 'void undefsyms_base(void *p, int n) {'; \
> > + echo ' char buffer[256] = { 0 };'; \
> > + echo ' u32 u = 0;'; \
> > + echo ' memset((char * volatile)page, 8, PAGE_SIZE);'; \
> > + echo ' memset((char * volatile)buffer, 8, sizeof(buffer));'; \
> > + echo ' memcpy((void * volatile)p, buffer, sizeof(buffer));'; \
> > + echo ' cmpxchg((u32 * volatile)&u, 0, 8);'; \
> > + echo ' WARN_ON(n == 0xdeadbeef);'; \
> > + echo '}'
> > +
> > +$(obj)/undefsyms_base.c: FORCE
> > + $(call filechk,undefsyms_base)
> > +
> > +clean-files += undefsyms_base.c
> > +
> > +$(obj)/undefsyms_base.o: $(obj)/undefsyms_base.c
> > +
> > +targets += undefsyms_base.o
> > +
> > +UNDEFINED_ALLOWLIST = __asan __gcov __kasan __kcsan __hwasan __sancov __sanitizer __tsan __ubsan __x86_indirect_thunk \
> > + simple_ring_buffer \
> > + $(shell $(NM) -u $(obj)/undefsyms_base.o 2>/dev/null | awk '{print $$2}')
> >
> > quiet_cmd_check_undefined = NM $<
> > - cmd_check_undefined = test -z "`$(NM) -u $< | grep -v $(UNDEFINED_ALLOWLIST)`"
> > + cmd_check_undefined = test -z "`$(NM) -u $< | grep -v $(addprefix -e , $(UNDEFINED_ALLOWLIST))`"
> >
> > -$(obj)/%.o.checked: $(obj)/%.o FORCE
> > +$(obj)/%.o.checked: $(obj)/%.o $(obj)/undefsyms_base.o FORCE
> > $(call if_changed,check_undefined)
> >
> > always-$(CONFIG_SIMPLE_RING_BUFFER) += simple_ring_buffer.o.checked
> >
> > base-commit: 33f2e266515717c4b2df585dadefa0525557726c
> > --
> > 2.53.0.851.ga537e3e6e9-goog
> >
>
> Thanks! This is almost perfect for my tests, one final thing that I
> noticed as a result of my full overnight builds. For ARCH=riscv (and
> some other architectures from a quick grep), there is some logic in
> their include/asm/string.h files to avoid FORTIFY_SOURCE when KASAN is
> enabled for the entire build but not enabled for the particular file. As
> undefsyms_base.o is not linked into vmlinux or modules, it does not
> automatically have KASAN enabled.
>
> $ cat allmod.config
> CONFIG_GCOV_KERNEL=n
> CONFIG_LTO_CLANG_THIN=y
> CONFIG_WERROR=n
>
> $ make -skj"$(nproc)" ARCH=riscv KCONFIG_ALLCONFIG=1 LLVM=1 mrproper allmodconfig kernel/trace/
> Unexpected symbols in kernel/trace/simple_ring_buffer.o:
> U __fortify_panic
> U __write_overflow_field
> ...
>
> This cures that for me.
>
> diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
> index 260382f62dbf..55af887a90e2 100644
> --- a/kernel/trace/Makefile
> +++ b/kernel/trace/Makefile
> @@ -164,6 +164,11 @@ $(obj)/undefsyms_base.o: $(obj)/undefsyms_base.c
>
> targets += undefsyms_base.o
>
> +# ensure KASAN is enabled to avoid logic that may disable FORTIFY_SOURCE when
> +# KASAN is not enabled. undefsyms_base.o does not automatically get KASAN flags
> +# because it is not linked into vmlinux.
> +KASAN_SANITIZE_undefsyms_base.o := y
> +
> UNDEFINED_ALLOWLIST = __asan __gcov __kasan __kcsan __hwasan __sancov __sanitizer __tsan __ubsan __x86_indirect_thunk \
> simple_ring_buffer \
> $(shell $(NM) -u $(obj)/undefsyms_base.o 2>/dev/null | awk '{print $$2}')
> --
>
> With that addressed:
>
> Reviewed-by: Nathan Chancellor <nathan@kernel.org>
> Tested-by: Nathan Chancellor <nathan@kernel.org>
I've just sent a v3 with all that. I have tested locally with allmodconfig and
many architectures with both clang and gcc.
Thanks a lot for your help!
--
Vincent
>
> Cheers,
> Nathan
^ permalink raw reply
* Re: [PATCH net-next v2 05/14] tcp: grow rcvbuf to back scaled-window quantization slack
From: Paolo Abeni @ 2026-03-16 11:04 UTC (permalink / raw)
To: atwellwea, netdev, davem, kuba, edumazet, ncardwell
Cc: linux-kernel, linux-api, linux-doc, linux-kselftest,
linux-trace-kernel, mptcp, dsahern, horms, kuniyu, andrew+netdev,
willemdebruijn.kernel, jasowang, skhan, corbet, matttbe,
martineau, geliang, rostedt, mhiramat, mathieu.desnoyers,
0x7f454c46
In-Reply-To: <20260314201348.1786972-6-atwellwea@gmail.com>
On 3/14/26 9:13 PM, atwellwea@gmail.com wrote:
> From: Wesley Atwell <atwellwea@gmail.com>
>
> Teach TCP to grow sk_rcvbuf when scale rounding would otherwise expose
> more sender-visible window than the current hard receive-memory backing
> can cover.
>
> The new helper keeps backlog and memory-pressure limits in the same
> units as the rest of the receive path, while __tcp_select_window()
> backs any rounding slack before advertising it.
>
> Signed-off-by: Wesley Atwell <atwellwea@gmail.com>
> ---
> include/net/tcp.h | 12 ++++++++++++
> net/ipv4/tcp_input.c | 36 ++++++++++++++++++++++++++++++++++--
> net/ipv4/tcp_output.c | 15 +++++++++++++--
> 3 files changed, 59 insertions(+), 4 deletions(-)
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index fc22ab6b80d5..5b479ad44f89 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -397,6 +397,7 @@ int tcp_ioctl(struct sock *sk, int cmd, int *karg);
> enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb);
> void tcp_rcv_established(struct sock *sk, struct sk_buff *skb);
> void tcp_rcvbuf_grow(struct sock *sk, u32 newval);
> +bool tcp_try_grow_rcvbuf(struct sock *sk, int needed);
> void tcp_rcv_space_adjust(struct sock *sk);
> int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
> void tcp_twsk_destructor(struct sock *sk);
> @@ -1844,6 +1845,17 @@ static inline int tcp_rwnd_avail(const struct sock *sk)
> return tcp_rmem_avail(sk) - READ_ONCE(sk->sk_backlog.len);
> }
>
> +/* Passive children clone the listener's sk_socket until accept() grafts
> + * their own struct socket, so only sockets that point back to themselves
> + * should autotune receive-buffer backing.
> + */
> +static inline bool tcp_rcvbuf_grow_allowed(const struct sock *sk)
> +{
> + struct socket *sock = READ_ONCE(sk->sk_socket);
> +
> + return sock && READ_ONCE(sock->sk) == sk;
This is executed under the sk socket lock, ONCE annotation not needed.
> +}
> +
> /* Note: caller must be prepared to deal with negative returns */
> static inline int tcp_space(const struct sock *sk)
> {
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index 352f814a4ff6..32256519a085 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -774,6 +774,38 @@ static void tcp_init_buffer_space(struct sock *sk)
> (u32)TCP_INIT_CWND * tp->advmss);
> }
>
> +/* Try to grow sk_rcvbuf so the hard receive-memory limit covers @needed
> + * bytes beyond sk_rmem_alloc while preserving sender-visible headroom
> + * already consumed by sk_backlog.len.
> + */
> +bool tcp_try_grow_rcvbuf(struct sock *sk, int needed)
> +{
> + struct net *net = sock_net(sk);
> + int backlog;
> + int rmem2;
> + int target;
> +
> + needed = max(needed, 0);
> + backlog = READ_ONCE(sk->sk_backlog.len);
> + target = tcp_rmem_used(sk) + backlog + needed;
> +
> + if (target <= READ_ONCE(sk->sk_rcvbuf))
> + return true;
> +
> + rmem2 = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
> + if (READ_ONCE(sk->sk_rcvbuf) >= rmem2 ||
> + (sk->sk_userlocks & SOCK_RCVBUF_LOCK) ||
> + tcp_under_memory_pressure(sk) ||
> + sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0))
> + return false;
> +
> + WRITE_ONCE(sk->sk_rcvbuf,
> + min_t(int, rmem2,
> + max_t(int, READ_ONCE(sk->sk_rcvbuf), target)));
> +
> + return target <= READ_ONCE(sk->sk_rcvbuf);
Same here, and more cases below.
/P
^ permalink raw reply
* Re: [PATCH v3] tracing: Generate undef symbols allowlist for simple_ring_buffer
From: Arnd Bergmann @ 2026-03-16 11:06 UTC (permalink / raw)
To: Vincent Donnefort, Marc Zyngier
Cc: Steven Rostedt, Nathan Chancellor, linux-trace-kernel, kvmarm,
kernel-team
In-Reply-To: <20260316092845.3367411-1-vdonnefort@google.com>
On Mon, Mar 16, 2026, at 10:28, Vincent Donnefort wrote:
> Compiler and tooling-generated symbols are difficult to maintain
> across all supported architectures. Make the allowlist more robust by
> replacing the harcoded list with a mechanism that automatically detects
> these symbols.
>
> This mechanism generates a C function designed to trigger common
> compiler-inserted symbols.
>
> Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
> Reviewed-by: Nathan Chancellor <nathan@kernel.org>
> Tested-by: Nathan Chancellor <nathan@kernel.org>
Added to my randconfig build setup now, I'll let you know if
any regressions remain.
Arnd
^ permalink raw reply
* Re: [PATCH net-next v2 00/14] tcp: preserve receive-window accounting across ratio drift
From: Paolo Abeni @ 2026-03-16 11:09 UTC (permalink / raw)
To: atwellwea, netdev, davem, kuba, edumazet, ncardwell
Cc: linux-kernel, linux-api, linux-doc, linux-kselftest,
linux-trace-kernel, mptcp, dsahern, horms, kuniyu, andrew+netdev,
willemdebruijn.kernel, jasowang, skhan, corbet, matttbe,
martineau, geliang, rostedt, mhiramat, mathieu.desnoyers,
0x7f454c46
In-Reply-To: <20260314201348.1786972-1-atwellwea@gmail.com>
On 3/14/26 9:13 PM, atwellwea@gmail.com wrote:
> From: Wesley Atwell <atwellwea@gmail.com>
>
> This series keeps sender-visible TCP receive-window accounting tied to the
> scaling basis that was in force when the window was advertised, even if
> later receive-side truesize inflation lowers scaling_ratio or the live
> receive window retracts below the largest right edge already exposed to the
> sender.
>
> After the receive-window retraction changes, the receive path needs to keep
> track of two related pieces of sender-visible state:
>
> 1. the live advertised receive window
> 2. the maximum advertised right edge and the basis it was exposed with
>
> This repost snapshots both, uses them to repair receive-buffer backing when
> ratio drift would otherwise strand sender-visible space, extends
> TCP_REPAIR_WINDOW so repair/restore can round-trip the new state, and adds
> truesize-drift coverage through TUN packetdrill tests and netdevsim-based
> selftests.
The series is IMHO significantly not trivial. Can the end-user meet the
relevant condition in practice? How? What is the net benefit in
practice? Is that observable under usual conditions or require
exceptional circumstances?
I think we need a strong motivation to merge this kind of changes.
/P
^ permalink raw reply
* Re: [PATCH net-next v2 05/14] tcp: grow rcvbuf to back scaled-window quantization slack
From: Paolo Abeni @ 2026-03-16 11:24 UTC (permalink / raw)
To: atwellwea, netdev, davem, kuba, edumazet, ncardwell
Cc: linux-kernel, linux-api, linux-doc, linux-kselftest,
linux-trace-kernel, mptcp, dsahern, horms, kuniyu, andrew+netdev,
willemdebruijn.kernel, jasowang, skhan, corbet, matttbe,
martineau, geliang, rostedt, mhiramat, mathieu.desnoyers,
0x7f454c46
In-Reply-To: <20260314201348.1786972-6-atwellwea@gmail.com>
On 3/14/26 9:13 PM, atwellwea@gmail.com wrote:
> From: Wesley Atwell <atwellwea@gmail.com>
>
> Teach TCP to grow sk_rcvbuf when scale rounding would otherwise expose
> more sender-visible window than the current hard receive-memory backing
> can cover.
>
> The new helper keeps backlog and memory-pressure limits in the same
> units as the rest of the receive path, while __tcp_select_window()
> backs any rounding slack before advertising it.
>
> Signed-off-by: Wesley Atwell <atwellwea@gmail.com>
> ---
> include/net/tcp.h | 12 ++++++++++++
> net/ipv4/tcp_input.c | 36 ++++++++++++++++++++++++++++++++++--
> net/ipv4/tcp_output.c | 15 +++++++++++++--
> 3 files changed, 59 insertions(+), 4 deletions(-)
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index fc22ab6b80d5..5b479ad44f89 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -397,6 +397,7 @@ int tcp_ioctl(struct sock *sk, int cmd, int *karg);
> enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb);
> void tcp_rcv_established(struct sock *sk, struct sk_buff *skb);
> void tcp_rcvbuf_grow(struct sock *sk, u32 newval);
> +bool tcp_try_grow_rcvbuf(struct sock *sk, int needed);
> void tcp_rcv_space_adjust(struct sock *sk);
> int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);
> void tcp_twsk_destructor(struct sock *sk);
> @@ -1844,6 +1845,17 @@ static inline int tcp_rwnd_avail(const struct sock *sk)
> return tcp_rmem_avail(sk) - READ_ONCE(sk->sk_backlog.len);
> }
>
> +/* Passive children clone the listener's sk_socket until accept() grafts
> + * their own struct socket,
AFAICS, the above statement is false, see sk_set_socket() in sk_clone()
> so only sockets that point back to themselves
> + * should autotune receive-buffer backing.
> + */
> +static inline bool tcp_rcvbuf_grow_allowed(const struct sock *sk)
> +{
> + struct socket *sock = READ_ONCE(sk->sk_socket);
You can just check `sk->sk_socket`. Also you could re-use this helper in
tcp_data_queue_ofo().
/P
^ permalink raw reply
* Re: [PATCH net-next v2 05/14] tcp: grow rcvbuf to back scaled-window quantization slack
From: Paolo Abeni @ 2026-03-16 11:31 UTC (permalink / raw)
To: atwellwea, netdev, davem, kuba, edumazet, ncardwell
Cc: linux-kernel, linux-api, linux-doc, linux-kselftest,
linux-trace-kernel, mptcp, dsahern, horms, kuniyu, andrew+netdev,
willemdebruijn.kernel, jasowang, skhan, corbet, matttbe,
martineau, geliang, rostedt, mhiramat, mathieu.desnoyers,
0x7f454c46
In-Reply-To: <20260314201348.1786972-6-atwellwea@gmail.com>
On 3/14/26 9:13 PM, atwellwea@gmail.com wrote:
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index 57a2a6daaad3..53781cf591d2 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -3375,13 +3375,24 @@ u32 __tcp_select_window(struct sock *sk)
> * scaled window will not line up with the MSS boundary anyway.
> */
> if (tp->rx_opt.rcv_wscale) {
> + int rcv_wscale = 1 << tp->rx_opt.rcv_wscale;
> +
> window = free_space;
>
> /* Advertise enough space so that it won't get scaled away.
> - * Import case: prevent zero window announcement if
> + * Important case: prevent zero-window announcement if
> * 1<<rcv_wscale > mss.
> */
> - window = ALIGN(window, (1 << tp->rx_opt.rcv_wscale));
> + window = ALIGN(window, rcv_wscale);
> +
> + /* Back any scale-quantization slack before we expose it.
> + * Otherwise tcp_can_ingest() can reject data which is still
> + * within the sender-visible window.
> + */
> + if (window > free_space &&
> + (!tcp_rcvbuf_grow_allowed(sk) ||
> + !tcp_try_grow_rcvbuf(sk, tcp_space_from_win(sk, window))))
> + window = round_down(free_space, rcv_wscale);
It looks like this can cause the advertised window to shrink even if we
are in the 'do not allow window to shrink' branch.
Also why the other branch (shrinking allowed) is not touched?
/P
^ permalink raw reply
* Re: [PATCH net-next v2 07/14] tcp: honor the maximum advertised window after live retraction
From: Paolo Abeni @ 2026-03-16 11:44 UTC (permalink / raw)
To: atwellwea, netdev, davem, kuba, edumazet, ncardwell
Cc: linux-kernel, linux-api, linux-doc, linux-kselftest,
linux-trace-kernel, mptcp, dsahern, horms, kuniyu, andrew+netdev,
willemdebruijn.kernel, jasowang, skhan, corbet, matttbe,
martineau, geliang, rostedt, mhiramat, mathieu.desnoyers,
0x7f454c46
In-Reply-To: <20260314201348.1786972-8-atwellwea@gmail.com>
On 3/14/26 9:13 PM, atwellwea@gmail.com wrote:
> +/* Sender-visible window rescue does not relax hard receive-memory admission.
> + * If growth did not make room, fall back to the established prune/collapse
> + * path.
> + */
> static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb,
> unsigned int size)
> {
> - if (!tcp_can_ingest(sk, skb) ||
> - !sk_rmem_schedule(sk, skb, size)) {
> + bool can_ingest = tcp_can_ingest(sk, skb);
> + bool scheduled = can_ingest && sk_rmem_schedule(sk, skb, size);
> +
> + if (!scheduled) {
> + int pruned = tcp_prune_queue(sk, skb);
>
> - if (tcp_prune_queue(sk, skb) < 0)
> + if (pruned < 0)
> return -1;
>
> while (!sk_rmem_schedule(sk, skb, size)) {
> - if (!tcp_prune_ofo_queue(sk, skb))
> + bool pruned_ofo = tcp_prune_ofo_queue(sk, skb);
> +
> + if (!pruned_ofo)
> return -1;
> }
> }
The above chunk is AFAICS pure noise. Please have a more careful local
review of this series before any next revision.
/P
^ permalink raw reply
* Re: [PATCH v3 17/17] tools/bootconfig: fix fd leak in load_xbc_file() on fstat failure
From: Markus Elfring @ 2026-03-16 12:15 UTC (permalink / raw)
To: Josh Law, linux-trace-kernel, Andrew Morton, Masami Hiramatsu; +Cc: LKML
In-Reply-To: <20260314223425.142966-18-objecting@objecting.org>
> If fstat() fails after open() succeeds, load_xbc_file() returns
> -errno without closing the file descriptor. Add the missing close()
> call on the error path.
https://elixir.bootlin.com/linux/v7.0-rc3/source/tools/bootconfig/main.c#L139-L153
How do you think about to use a corresponding goto chain?
Would you like to add any tags (like “Fixes” and “Cc”) accordingly?
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/process/submitting-patches.rst?h=v7.0-rc4#n145
Regards,
Markus
^ permalink raw reply
* Re: [PATCH 50/61] iommu: Prefer IS_ERR_OR_NULL over manual NULL check
From: Robin Murphy @ 2026-03-16 13:30 UTC (permalink / raw)
To: Philipp Hahn, amd-gfx, apparmor, bpf, ceph-devel, cocci, dm-devel,
dri-devel, gfs2, intel-gfx, intel-wired-lan, iommu, kvm,
linux-arm-kernel, linux-block, linux-bluetooth, linux-btrfs,
linux-cifs, linux-clk, linux-erofs, linux-ext4, linux-fsdevel,
linux-gpio, linux-hyperv, linux-input, linux-kernel, linux-leds,
linux-media, linux-mips, linux-mm, linux-modules, linux-mtd,
linux-nfs, linux-omap, linux-phy, linux-pm, linux-rockchip,
linux-s390, linux-scsi, linux-sctp, linux-security-module,
linux-sh, linux-sound, linux-stm32, linux-trace-kernel, linux-usb,
linux-wireless, netdev, ntfs3, samba-technical, sched-ext,
target-devel, tipc-discussion, v9fs
Cc: Joerg Roedel, Will Deacon
In-Reply-To: <20260310-b4-is_err_or_null-v1-50-bd63b656022d@avm.de>
On 2026-03-10 11:49 am, Philipp Hahn wrote:
> Prefer using IS_ERR_OR_NULL() over using IS_ERR() and a manual NULL
> check.
AFAICS it doesn't look possible for the argument to be anything other
than valid at both callsites, so *both* conditions here seem in fact to
be entirely redundant.
> Change generated with coccinelle.
Please use coccinelle responsibly. Mechanical changes are great for
scripted API updates, but for cleanup, whilst it's ideal for *finding*
areas of code that are worth looking at, the code then wants actually
looking at, in its whole context, because meaningful cleanup often goes
deeper than trivial replacement.
In particular, anywhere IS_ERR_OR_NULL() is genuinely relevant is
usually a sign of bad interface design, so if you're looking at this
then you really should be looking first and foremost to remove any
checks that are already unnecessary, and for the remainder, to see if
the thing being checked can be improved to not mix the two different
styles. That would be constructive and (usually) welcome cleanup. Simply
churning a bunch of code with this ugly macro that's arguably less
readable than what it replaces, not so much.
Thanks,
Robin.
> To: Joerg Roedel <joro@8bytes.org>
> To: Will Deacon <will@kernel.org>
> To: Robin Murphy <robin.murphy@arm.com>
> Cc: iommu@lists.linux.dev
> Cc: linux-kernel@vger.kernel.org
> Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
> ---
> drivers/iommu/omap-iommu.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
> index 8231d7d6bb6a9202025643639a6b28e6faa84659..500a42b57a997696ff37c76f028a717ab71d01f9 100644
> --- a/drivers/iommu/omap-iommu.c
> +++ b/drivers/iommu/omap-iommu.c
> @@ -881,7 +881,7 @@ static int omap_iommu_attach(struct omap_iommu *obj, u32 *iopgd)
> **/
> static void omap_iommu_detach(struct omap_iommu *obj)
> {
> - if (!obj || IS_ERR(obj))
> + if (IS_ERR_OR_NULL(obj))
> return;
>
> spin_lock(&obj->iommu_lock);
>
^ permalink raw reply
* Re: [PATCH V2] tracing: Revert "tracing: Remove pid in task_rename tracing output"
From: Steven Rostedt @ 2026-03-16 13:54 UTC (permalink / raw)
To: Xuewen Yan
Cc: Xuewen Yan, mhiramat, mathieu.desnoyers, elver, kees,
lorenzo.stoakes, brauner, schuster.simon, david, linux-kernel,
linux-trace-kernel, guohua.yan, ke.wang, jing.xia
In-Reply-To: <CAB8ipk8M=Uij65LZCbSAjJPPPsXWYY4kGBQwMm1WqJHHEb33eQ@mail.gmail.com>
On Mon, 16 Mar 2026 10:00:13 +0800
Xuewen Yan <xuewen.yan94@gmail.com> wrote:
> Unless there are any further comments, could you please help to take
> this through the tracing tree?
I guess this file doesn't really have an owner, so yeah, I'll take it.
-- Steve
^ permalink raw reply
* Re: [PATCH v3] tracing: Generate undef symbols allowlist for simple_ring_buffer
From: Steven Rostedt @ 2026-03-16 14:09 UTC (permalink / raw)
To: Vincent Donnefort
Cc: maz, arnd, nathan, linux-trace-kernel, kvmarm, kernel-team
In-Reply-To: <20260316092845.3367411-1-vdonnefort@google.com>
On Mon, 16 Mar 2026 09:28:45 +0000
Vincent Donnefort <vdonnefort@google.com> wrote:
> Compiler and tooling-generated symbols are difficult to maintain
> across all supported architectures. Make the allowlist more robust by
> replacing the harcoded list with a mechanism that automatically detects
> these symbols.
>
> This mechanism generates a C function designed to trigger common
> compiler-inserted symbols.
>
> Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
> Reviewed-by: Nathan Chancellor <nathan@kernel.org>
> Tested-by: Nathan Chancellor <nathan@kernel.org>
I take it that Marc will take this?
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
-- Steve
^ permalink raw reply
* Re: [PATCH v3 17/17] tools/bootconfig: fix fd leak in load_xbc_file() on fstat failure
From: Josh Law @ 2026-03-16 15:14 UTC (permalink / raw)
To: Markus Elfring, linux-trace-kernel, Andrew Morton,
Masami Hiramatsu; +Cc: LKML
In-Reply-To: <ecb34439-8695-4562-a9e7-9fac74323adb@web.de>
On 16 March 2026 12:15:08 GMT, Markus Elfring <Markus.Elfring@web.de> wrote:
>> If fstat() fails after open() succeeds, load_xbc_file() returns
>> -errno without closing the file descriptor. Add the missing close()
>> call on the error path.
>
>https://elixir.bootlin.com/linux/v7.0-rc3/source/tools/bootconfig/main.c#L139-L153
>
>How do you think about to use a corresponding goto chain?
>
>
>Would you like to add any tags (like “Fixes” and “Cc”) accordingly?
>https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/process/submitting-patches.rst?h=v7.0-rc4#n145
>
>Regards,
>Markus
Hello markus, i submitted a V6 (yes a v6) that responds to all that, and includes extra patches to fix some warnings under W123 (maximum GCC warning level)
Thanks.
V/R
Josh Law
^ permalink raw reply
* Re: [PATCH v2 2/2] locking: Add contended_release tracepoint
From: Dmitry Ilvokhin @ 2026-03-16 15:32 UTC (permalink / raw)
To: Usama Arif
Cc: Dennis Zhou, Tejun Heo, Christoph Lameter, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Peter Zijlstra, Ingo Molnar,
Will Deacon, Boqun Feng, Waiman Long, linux-mm, linux-kernel,
linux-trace-kernel, kernel-team
In-Reply-To: <20260312113815.2107882-1-usama.arif@linux.dev>
On Thu, Mar 12, 2026 at 04:38:14AM -0700, Usama Arif wrote:
> On Tue, 10 Mar 2026 17:49:39 +0000 Dmitry Ilvokhin <d@ilvokhin.com> wrote:
>
> > Add the contended_release trace event. This tracepoint fires on the
> > holder side when a contended lock is released, complementing the
> > existing contention_begin/contention_end tracepoints which fire on the
> > waiter side.
> >
> > This enables correlating lock hold time under contention with waiter
> > events by lock address.
> >
> > Add trace_contended_release() calls to the slowpath unlock paths of
> > sleepable locks: mutex, rtmutex, semaphore, rwsem, percpu-rwsem, and
> > RT-specific rwbase locks. Each call site fires only when there are
> > blocked waiters being woken, except percpu_up_write() which always wakes
> > via __wake_up().
> >
> > Signed-off-by: Dmitry Ilvokhin <d@ilvokhin.com>
> > ---
> > include/trace/events/lock.h | 17 +++++++++++++++++
> > kernel/locking/mutex.c | 1 +
> > kernel/locking/percpu-rwsem.c | 3 +++
> > kernel/locking/rtmutex.c | 1 +
> > kernel/locking/rwbase_rt.c | 8 +++++++-
> > kernel/locking/rwsem.c | 9 +++++++--
> > kernel/locking/semaphore.c | 4 +++-
> > 7 files changed, 39 insertions(+), 4 deletions(-)
> >
[...]
> > diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
> > index f3ee7a0d6047..1eee51766aaf 100644
> > --- a/kernel/locking/percpu-rwsem.c
> > +++ b/kernel/locking/percpu-rwsem.c
> > @@ -263,6 +263,8 @@ void percpu_up_write(struct percpu_rw_semaphore *sem)
> > {
> > rwsem_release(&sem->dep_map, _RET_IP_);
> >
> > + trace_contended_release(sem);
> > +
>
> Hello!
>
> I saw that you mentioned in the commmit message that you do this for only
> blocked waiters except for percpu_up_write(). We can use
> waitqueue_active(&sem->waiters) to check for this over here so that
> its consistent with every other call?
Thanks for the feedback, Usama.
I thought about it and even mentioned in the comment, but I forgot what
was the reason. Now, I think you are correct. I added wq_has_sleeper()
locally instead of waitqueue_active() locally, since we are not holding
the lock here and waitqueue_active() requires a barrier based on the
comment. It might be not very important here, but I'd rather make it
correct even for tracepoint.
Note that __percpu_up_read() doesn't need this guard. Maybe I was
thinking at __percpu_up_read() part before and just made it symmetric.
Anyway, thanks for suggestion.
>
>
> > /*
> > * Signal the writer is done, no fast path yet.
> > *
> > @@ -297,6 +299,7 @@ void __percpu_up_read(struct percpu_rw_semaphore *sem)
> > * writer.
> > */
> > smp_mb(); /* B matches C */
> > + trace_contended_release(sem);
>
> Should we do this after this_cpu_dec(*sem->read_count)?
Good point. I moved it after this_cpu_dec() so the tracepoint fires
after the lock is released but before rcuwait_wake_up(). I also went
through all other call sites and made the placement consistent where
possible: after release, before wake. It should be fixed in v3.
^ permalink raw reply
* [PATCH v8 0/3] mm: vmscan: add PID and cgroup ID to vmscan tracepoints
From: Thomas Ballasi @ 2026-03-16 16:09 UTC (permalink / raw)
To: tballasi
Cc: akpm, axelrasmussen, david, hannes, linux-mm, linux-trace-kernel,
lorenzo.stoakes, mhiramat, mhocko, rostedt, shakeel.butt, weixugc,
yuanchu, zhengqi.arch
In-Reply-To: <20260223171544.4750-1-tballasi@linux.microsoft.com>
Changes in v8:
- Removed in_task() mention in PID commit message
- Moved __entry->pid to __entry->ent.pid
Link to v7:
https://lore.kernel.org/linux-trace-kernel/20260223171544.4750-1-tballasi@linux.microsoft.com/
Signed-off-by: Thomas Ballasi <tballasi@linux.microsoft.com>
Steven Rostedt (1):
tracing: Add __event_in_*irq() helpers
Thomas Ballasi (2):
mm: vmscan: add cgroup IDs to vmscan tracepoints
mm: vmscan: add PIDs to vmscan tracepoints
include/trace/events/vmscan.h | 95 +++++++++++++---------
include/trace/stages/stage3_trace_output.h | 8 ++
include/trace/stages/stage7_class_define.h | 19 +++++
mm/shrinker.c | 6 +-
mm/vmscan.c | 17 ++--
5 files changed, 98 insertions(+), 47 deletions(-)
--
2.45.3
^ permalink raw reply
* [PATCH v8 1/3] tracing: Add __event_in_*irq() helpers
From: Thomas Ballasi @ 2026-03-16 16:09 UTC (permalink / raw)
To: tballasi
Cc: akpm, axelrasmussen, david, hannes, linux-mm, linux-trace-kernel,
lorenzo.stoakes, mhiramat, mhocko, rostedt, shakeel.butt, weixugc,
yuanchu, zhengqi.arch
In-Reply-To: <20260316160908.42727-1-tballasi@linux.microsoft.com>
From: Steven Rostedt <rostedt@goodmis.org>
Some trace events want to expose in their output if they were triggered in
an interrupt or softirq context. Instead of recording this in the event
structure itself, as this information is stored in the flags portion of
the event header, add helper macros that can be used in the print format:
TP_printk("val=%d %s", __entry->val, __event_in_irq() ? "(in-irq)" : "")
This will output "(in-irq)" for the event in the trace data if the event
was triggered in hard or soft interrupt context.
Link: https://lore.kernel.org/all/20251229132942.31a2b583@gandalf.local.home/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Thomas Ballasi <tballasi@linux.microsoft.com>
---
include/trace/stages/stage3_trace_output.h | 8 ++++++++
include/trace/stages/stage7_class_define.h | 19 +++++++++++++++++++
2 files changed, 27 insertions(+)
diff --git a/include/trace/stages/stage3_trace_output.h b/include/trace/stages/stage3_trace_output.h
index 1e7b0bef95f52..53a23988a3b8a 100644
--- a/include/trace/stages/stage3_trace_output.h
+++ b/include/trace/stages/stage3_trace_output.h
@@ -150,3 +150,11 @@
#undef __get_buf
#define __get_buf(len) trace_seq_acquire(p, (len))
+
+#undef __event_in_hardirq
+#undef __event_in_softirq
+#undef __event_in_irq
+
+#define __event_in_hardirq() (__entry->ent.flags & TRACE_FLAG_HARDIRQ)
+#define __event_in_softirq() (__entry->ent.flags & TRACE_FLAG_SOFTIRQ)
+#define __event_in_irq() (__entry->ent.flags & (TRACE_FLAG_HARDIRQ | TRACE_FLAG_SOFTIRQ))
diff --git a/include/trace/stages/stage7_class_define.h b/include/trace/stages/stage7_class_define.h
index fcd564a590f43..47008897a7956 100644
--- a/include/trace/stages/stage7_class_define.h
+++ b/include/trace/stages/stage7_class_define.h
@@ -26,6 +26,25 @@
#undef __print_hex_dump
#undef __get_buf
+#undef __event_in_hardirq
+#undef __event_in_softirq
+#undef __event_in_irq
+
+/*
+ * The TRACE_FLAG_* are enums. Instead of using TRACE_DEFINE_ENUM(),
+ * use their hardcoded values. These values are parsed by user space
+ * tooling elsewhere so they will never change.
+ *
+ * See "enum trace_flag_type" in linux/trace_events.h:
+ * TRACE_FLAG_HARDIRQ
+ * TRACE_FLAG_SOFTIRQ
+ */
+
+/* This is what is displayed in the format files */
+#define __event_in_hardirq() (REC->common_flags & 0x8)
+#define __event_in_softirq() (REC->common_flags & 0x10)
+#define __event_in_irq() (REC->common_flags & 0x18)
+
/*
* The below is not executed in the kernel. It is only what is
* displayed in the print format for userspace to parse.
--
2.45.3
^ permalink raw reply related
* [PATCH v8 2/3] mm: vmscan: add cgroup IDs to vmscan tracepoints
From: Thomas Ballasi @ 2026-03-16 16:09 UTC (permalink / raw)
To: tballasi
Cc: akpm, axelrasmussen, david, hannes, linux-mm, linux-trace-kernel,
lorenzo.stoakes, mhiramat, mhocko, rostedt, shakeel.butt, weixugc,
yuanchu, zhengqi.arch
In-Reply-To: <20260316160908.42727-1-tballasi@linux.microsoft.com>
Memory reclaim events are currently difficult to attribute to
specific cgroups, making debugging memory pressure issues
challenging. This patch adds memory cgroup ID (memcg_id) to key
vmscan tracepoints to enable better correlation and analysis.
For operations not associated with a specific cgroup, the field
is defaulted to 0.
Signed-off-by: Thomas Ballasi <tballasi@linux.microsoft.com>
---
include/trace/events/vmscan.h | 83 ++++++++++++++++++++---------------
mm/shrinker.c | 6 ++-
mm/vmscan.c | 17 +++----
3 files changed, 61 insertions(+), 45 deletions(-)
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 490958fa10dee..1212f6a7c223e 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -114,85 +114,92 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd,
DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
- TP_PROTO(int order, gfp_t gfp_flags),
+ TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
- TP_ARGS(order, gfp_flags),
+ TP_ARGS(gfp_flags, order, memcg),
TP_STRUCT__entry(
- __field( int, order )
__field( unsigned long, gfp_flags )
+ __field( u64, memcg_id )
+ __field( int, order )
),
TP_fast_assign(
- __entry->order = order;
__entry->gfp_flags = (__force unsigned long)gfp_flags;
+ __entry->order = order;
+ __entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("order=%d gfp_flags=%s",
+ TP_printk("order=%d gfp_flags=%s memcg_id=%llu",
__entry->order,
- show_gfp_flags(__entry->gfp_flags))
+ show_gfp_flags(__entry->gfp_flags),
+ __entry->memcg_id)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
- TP_PROTO(int order, gfp_t gfp_flags),
+ TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
- TP_ARGS(order, gfp_flags)
+ TP_ARGS(gfp_flags, order, memcg)
);
#ifdef CONFIG_MEMCG
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
- TP_PROTO(int order, gfp_t gfp_flags),
+ TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
- TP_ARGS(order, gfp_flags)
+ TP_ARGS(gfp_flags, order, memcg)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin,
- TP_PROTO(int order, gfp_t gfp_flags),
+ TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
- TP_ARGS(order, gfp_flags)
+ TP_ARGS(gfp_flags, order, memcg)
);
#endif /* CONFIG_MEMCG */
DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template,
- TP_PROTO(unsigned long nr_reclaimed),
+ TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg),
- TP_ARGS(nr_reclaimed),
+ TP_ARGS(nr_reclaimed, memcg),
TP_STRUCT__entry(
__field( unsigned long, nr_reclaimed )
+ __field( u64, memcg_id )
),
TP_fast_assign(
__entry->nr_reclaimed = nr_reclaimed;
+ __entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed)
+ TP_printk("nr_reclaimed=%lu memcg_id=%llu",
+ __entry->nr_reclaimed,
+ __entry->memcg_id)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end,
- TP_PROTO(unsigned long nr_reclaimed),
+ TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg),
- TP_ARGS(nr_reclaimed)
+ TP_ARGS(nr_reclaimed, memcg)
);
#ifdef CONFIG_MEMCG
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end,
- TP_PROTO(unsigned long nr_reclaimed),
+ TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg),
- TP_ARGS(nr_reclaimed)
+ TP_ARGS(nr_reclaimed, memcg)
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end,
- TP_PROTO(unsigned long nr_reclaimed),
+ TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg),
- TP_ARGS(nr_reclaimed)
+ TP_ARGS(nr_reclaimed, memcg)
);
#endif /* CONFIG_MEMCG */
@@ -200,39 +207,42 @@ TRACE_EVENT(mm_shrink_slab_start,
TP_PROTO(struct shrinker *shr, struct shrink_control *sc,
long nr_objects_to_shrink, unsigned long cache_items,
unsigned long long delta, unsigned long total_scan,
- int priority),
+ int priority, struct mem_cgroup *memcg),
TP_ARGS(shr, sc, nr_objects_to_shrink, cache_items, delta, total_scan,
- priority),
+ priority, memcg),
TP_STRUCT__entry(
__field(struct shrinker *, shr)
__field(void *, shrink)
- __field(int, nid)
__field(long, nr_objects_to_shrink)
__field(unsigned long, gfp_flags)
__field(unsigned long, cache_items)
__field(unsigned long long, delta)
__field(unsigned long, total_scan)
__field(int, priority)
+ __field(int, nid)
+ __field(u64, memcg_id)
),
TP_fast_assign(
__entry->shr = shr;
__entry->shrink = shr->scan_objects;
- __entry->nid = sc->nid;
__entry->nr_objects_to_shrink = nr_objects_to_shrink;
__entry->gfp_flags = (__force unsigned long)sc->gfp_mask;
__entry->cache_items = cache_items;
__entry->delta = delta;
__entry->total_scan = total_scan;
__entry->priority = priority;
+ __entry->nid = sc->nid;
+ __entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("%pS %p: nid: %d objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d",
+ TP_printk("%pS %p: nid: %d memcg_id: %llu objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d",
__entry->shrink,
__entry->shr,
__entry->nid,
+ __entry->memcg_id,
__entry->nr_objects_to_shrink,
show_gfp_flags(__entry->gfp_flags),
__entry->cache_items,
@@ -243,35 +253,38 @@ TRACE_EVENT(mm_shrink_slab_start,
TRACE_EVENT(mm_shrink_slab_end,
TP_PROTO(struct shrinker *shr, int nid, int shrinker_retval,
- long unused_scan_cnt, long new_scan_cnt, long total_scan),
+ long unused_scan_cnt, long new_scan_cnt, long total_scan, struct mem_cgroup *memcg),
TP_ARGS(shr, nid, shrinker_retval, unused_scan_cnt, new_scan_cnt,
- total_scan),
+ total_scan, memcg),
TP_STRUCT__entry(
__field(struct shrinker *, shr)
- __field(int, nid)
__field(void *, shrink)
__field(long, unused_scan)
__field(long, new_scan)
- __field(int, retval)
__field(long, total_scan)
+ __field(int, nid)
+ __field(int, retval)
+ __field(u64, memcg_id)
),
TP_fast_assign(
__entry->shr = shr;
- __entry->nid = nid;
__entry->shrink = shr->scan_objects;
__entry->unused_scan = unused_scan_cnt;
__entry->new_scan = new_scan_cnt;
- __entry->retval = shrinker_retval;
__entry->total_scan = total_scan;
+ __entry->nid = nid;
+ __entry->retval = shrinker_retval;
+ __entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("%pS %p: nid: %d unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d",
+ TP_printk("%pS %p: nid: %d memcg_id: %llu unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d",
__entry->shrink,
__entry->shr,
__entry->nid,
+ __entry->memcg_id,
__entry->unused_scan,
__entry->new_scan,
__entry->total_scan,
@@ -504,9 +517,9 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin,
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_node_reclaim_end,
- TP_PROTO(unsigned long nr_reclaimed),
+ TP_PROTO(unsigned long nr_reclaimed, struct mem_cgroup *memcg),
- TP_ARGS(nr_reclaimed)
+ TP_ARGS(nr_reclaimed, memcg)
);
TRACE_EVENT(mm_vmscan_throttled,
diff --git a/mm/shrinker.c b/mm/shrinker.c
index 4a93fd433689a..ddf784f996a59 100644
--- a/mm/shrinker.c
+++ b/mm/shrinker.c
@@ -410,7 +410,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
total_scan = min(total_scan, (2 * freeable));
trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
- freeable, delta, total_scan, priority);
+ freeable, delta, total_scan, priority,
+ shrinkctl->memcg);
/*
* Normally, we should not scan less than batch_size objects in one
@@ -461,7 +462,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
*/
new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl);
- trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan);
+ trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan,
+ shrinkctl->memcg);
return freed;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 05d9354a59c65..b3117814ec436 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6652,11 +6652,11 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
return 1;
set_task_reclaim_state(current, &sc.reclaim_state);
- trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask);
+ trace_mm_vmscan_direct_reclaim_begin(sc.gfp_mask, order, 0);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
- trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
+ trace_mm_vmscan_direct_reclaim_end(nr_reclaimed, 0);
set_task_reclaim_state(current, NULL);
return nr_reclaimed;
@@ -6685,8 +6685,9 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
- trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
- sc.gfp_mask);
+ trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.gfp_mask,
+ sc.order,
+ memcg);
/*
* NOTE: Although we can get the priority field, using it
@@ -6697,7 +6698,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
*/
shrink_lruvec(lruvec, &sc);
- trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
+ trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed, memcg);
*nr_scanned = sc.nr_scanned;
@@ -6733,13 +6734,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
set_task_reclaim_state(current, &sc.reclaim_state);
- trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask);
+ trace_mm_vmscan_memcg_reclaim_begin(sc.gfp_mask, 0, memcg);
noreclaim_flag = memalloc_noreclaim_save();
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
memalloc_noreclaim_restore(noreclaim_flag);
- trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
+ trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed, memcg);
set_task_reclaim_state(current, NULL);
return nr_reclaimed;
@@ -7685,7 +7686,7 @@ static unsigned long __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask,
delayacct_freepages_end();
psi_memstall_leave(&pflags);
- trace_mm_vmscan_node_reclaim_end(sc->nr_reclaimed);
+ trace_mm_vmscan_node_reclaim_end(sc->nr_reclaimed, 0);
return sc->nr_reclaimed;
}
--
2.45.3
^ permalink raw reply related
* [PATCH v8 3/3] mm: vmscan: add PIDs to vmscan tracepoints
From: Thomas Ballasi @ 2026-03-16 16:09 UTC (permalink / raw)
To: tballasi
Cc: akpm, axelrasmussen, david, hannes, linux-mm, linux-trace-kernel,
lorenzo.stoakes, mhiramat, mhocko, rostedt, shakeel.butt, weixugc,
yuanchu, zhengqi.arch
In-Reply-To: <20260316160908.42727-1-tballasi@linux.microsoft.com>
The changes aims at adding additionnal tracepoints variables to help
debuggers attribute them to specific processes.
Signed-off-by: Thomas Ballasi <tballasi@linux.microsoft.com>
---
include/trace/events/vmscan.h | 24 ++++++++++++++++--------
1 file changed, 16 insertions(+), 8 deletions(-)
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 1212f6a7c223e..645b036572707 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -130,10 +130,12 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
__entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("order=%d gfp_flags=%s memcg_id=%llu",
+ TP_printk("order=%d gfp_flags=%s pid=%d memcg_id=%llu %s",
__entry->order,
show_gfp_flags(__entry->gfp_flags),
- __entry->memcg_id)
+ __entry->ent.pid,
+ __entry->memcg_id,
+ __event_in_irq() ? "(in-irq)" : "")
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
@@ -175,9 +177,11 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template,
__entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("nr_reclaimed=%lu memcg_id=%llu",
+ TP_printk("nr_reclaimed=%lu pid=%d memcg_id=%llu %s",
__entry->nr_reclaimed,
- __entry->memcg_id)
+ __entry->ent.pid,
+ __entry->memcg_id,
+ __event_in_irq() ? "(in-irq)" : "")
);
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end,
@@ -238,17 +242,19 @@ TRACE_EVENT(mm_shrink_slab_start,
__entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("%pS %p: nid: %d memcg_id: %llu objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d",
+ TP_printk("%pS %p: nid: %d pid: %d memcg_id: %llu objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d %s",
__entry->shrink,
__entry->shr,
__entry->nid,
+ __entry->ent.pid,
__entry->memcg_id,
__entry->nr_objects_to_shrink,
show_gfp_flags(__entry->gfp_flags),
__entry->cache_items,
__entry->delta,
__entry->total_scan,
- __entry->priority)
+ __entry->priority,
+ __event_in_irq() ? "(in-irq)" : "")
);
TRACE_EVENT(mm_shrink_slab_end,
@@ -280,15 +286,17 @@ TRACE_EVENT(mm_shrink_slab_end,
__entry->memcg_id = mem_cgroup_id(memcg);
),
- TP_printk("%pS %p: nid: %d memcg_id: %llu unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d",
+ TP_printk("%pS %p: nid: %d pid: %d memcg_id: %llu unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d %s",
__entry->shrink,
__entry->shr,
__entry->nid,
+ __entry->ent.pid,
__entry->memcg_id,
__entry->unused_scan,
__entry->new_scan,
__entry->total_scan,
- __entry->retval)
+ __entry->retval,
+ __event_in_irq() ? "(in-irq)" : "")
);
TRACE_EVENT(mm_vmscan_lru_isolate,
--
2.45.3
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox