* [PATCHv4 bpf-next 1/5] libbpf: Add uprobe syscall feature detection
2026-02-20 10:42 [PATCHv4 bpf-next 0/5] libbpf: Make optimized uprobes backward compatible Jiri Olsa
@ 2026-02-20 10:42 ` Jiri Olsa
2026-02-20 10:42 ` [PATCHv4 bpf-next 2/5] libbpf: Add support to detect nop,nop5 instructions combo for usdt probe Jiri Olsa
` (3 subsequent siblings)
4 siblings, 0 replies; 9+ messages in thread
From: Jiri Olsa @ 2026-02-20 10:42 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: bpf, linux-kernel, Song Liu, Yonghong Song, John Fastabend
Adding uprobe syscall feature detection that will be used
in following changes.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/lib/bpf/features.c | 24 ++++++++++++++++++++++++
tools/lib/bpf/libbpf_internal.h | 2 ++
2 files changed, 26 insertions(+)
diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
index 2fa434f09cce..adcad221c601 100644
--- a/tools/lib/bpf/features.c
+++ b/tools/lib/bpf/features.c
@@ -568,6 +568,27 @@ static int probe_ldimm64_full_range_off(int token_fd)
return 1;
}
+#ifdef __x86_64__
+
+#ifndef __NR_uprobe
+#define __NR_uprobe 336
+#endif
+
+static int probe_uprobe_syscall(int token_fd)
+{
+ /*
+ * If kernel supports uprobe() syscall, it will return -ENXIO when called
+ * from the outside of a kernel-generated uprobe trampoline.
+ */
+ return syscall(__NR_uprobe) < 0 && errno == ENXIO;
+}
+#else
+static int probe_uprobe_syscall(int token_fd)
+{
+ return 0;
+}
+#endif
+
typedef int (*feature_probe_fn)(int /* token_fd */);
static struct kern_feature_cache feature_cache;
@@ -646,6 +667,9 @@ static struct kern_feature_desc {
[FEAT_LDIMM64_FULL_RANGE_OFF] = {
"full range LDIMM64 support", probe_ldimm64_full_range_off,
},
+ [FEAT_UPROBE_SYSCALL] = {
+ "kernel supports uprobe syscall", probe_uprobe_syscall,
+ },
};
bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id)
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 974147e8a8aa..4bcb6ca69bb1 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -394,6 +394,8 @@ enum kern_feature_id {
FEAT_BTF_QMARK_DATASEC,
/* Kernel supports LDIMM64 imm offsets past 512 MiB. */
FEAT_LDIMM64_FULL_RANGE_OFF,
+ /* Kernel supports uprobe syscall */
+ FEAT_UPROBE_SYSCALL,
__FEAT_CNT,
};
--
2.53.0
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCHv4 bpf-next 2/5] libbpf: Add support to detect nop,nop5 instructions combo for usdt probe
2026-02-20 10:42 [PATCHv4 bpf-next 0/5] libbpf: Make optimized uprobes backward compatible Jiri Olsa
2026-02-20 10:42 ` [PATCHv4 bpf-next 1/5] libbpf: Add uprobe syscall feature detection Jiri Olsa
@ 2026-02-20 10:42 ` Jiri Olsa
2026-02-20 11:24 ` bot+bpf-ci
2026-02-20 10:42 ` [PATCHv4 bpf-next 3/5] selftests/bpf: Emit nop,nop5 instructions combo for x86_64 arch Jiri Olsa
` (2 subsequent siblings)
4 siblings, 1 reply; 9+ messages in thread
From: Jiri Olsa @ 2026-02-20 10:42 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: bpf, linux-kernel, Song Liu, Yonghong Song, John Fastabend
Adding support to detect nop,nop5 instructions combo for usdt probe
by checking on probe's following nop5 instruction.
When the nop,nop5 combo is detected together with uprobe syscall,
we can place the probe on top of nop5 and get it optimized.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/lib/bpf/usdt.c | 47 ++++++++++++++++++++++++++++++++++++++++----
1 file changed, 43 insertions(+), 4 deletions(-)
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index d1524f6f54ae..c81e0a58caf5 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -262,6 +262,7 @@ struct usdt_manager {
bool has_bpf_cookie;
bool has_sema_refcnt;
bool has_uprobe_multi;
+ bool has_uprobe_syscall;
};
struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
@@ -301,6 +302,13 @@ struct usdt_manager *usdt_manager_new(struct bpf_object *obj)
* usdt probes.
*/
man->has_uprobe_multi = kernel_supports(obj, FEAT_UPROBE_MULTI_LINK);
+
+ /*
+ * Detect kernel support for uprobe() syscall, it's presence means we can
+ * take advantage of faster nop5 uprobe handling.
+ * Added in: 56101b69c919 ("uprobes/x86: Add uprobe syscall to speed up uprobe")
+ */
+ man->has_uprobe_syscall = kernel_supports(obj, FEAT_UPROBE_SYSCALL);
return man;
}
@@ -585,13 +593,34 @@ static int parse_usdt_note(GElf_Nhdr *nhdr, const char *data, size_t name_off,
static int parse_usdt_spec(struct usdt_spec *spec, const struct usdt_note *note, __u64 usdt_cookie);
-static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *path, pid_t pid,
- const char *usdt_provider, const char *usdt_name, __u64 usdt_cookie,
- struct usdt_target **out_targets, size_t *out_target_cnt)
+#if defined(__x86_64__)
+static bool has_nop_combo(int fd, long off)
+{
+ static unsigned char nop_combo[6] = {
+ 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 /* nop,nop5 */
+ };
+ unsigned char buf[6] = {};
+
+ if (pread(fd, buf, 6, off) != 6)
+ return false;
+ return memcmp(buf, nop_combo, 6) == 0;
+}
+#else
+static bool has_nop_combo(int fd, long off)
+{
+ return false;
+}
+#endif
+
+static int collect_usdt_targets(struct usdt_manager *man, struct elf_fd *elf_fd, const char *path,
+ pid_t pid, const char *usdt_provider, const char *usdt_name,
+ __u64 usdt_cookie, struct usdt_target **out_targets,
+ size_t *out_target_cnt)
{
size_t off, name_off, desc_off, seg_cnt = 0, vma_seg_cnt = 0, target_cnt = 0;
struct elf_seg *segs = NULL, *vma_segs = NULL;
struct usdt_target *targets = NULL, *target;
+ Elf *elf = elf_fd->elf;
long base_addr = 0;
Elf_Scn *notes_scn, *base_scn;
GElf_Shdr base_shdr, notes_shdr;
@@ -784,6 +813,16 @@ static int collect_usdt_targets(struct usdt_manager *man, Elf *elf, const char *
target = &targets[target_cnt];
memset(target, 0, sizeof(*target));
+ /*
+ * We have uprobe syscall and usdt with nop,nop5 instructions combo,
+ * so we can place the uprobe directly on nop5 (+1) and get this probe
+ * optimized.
+ */
+ if (man->has_uprobe_syscall && has_nop_combo(elf_fd->fd, usdt_rel_ip)) {
+ usdt_abs_ip++;
+ usdt_rel_ip++;
+ }
+
target->abs_ip = usdt_abs_ip;
target->rel_ip = usdt_rel_ip;
target->sema_off = usdt_sema_off;
@@ -998,7 +1037,7 @@ struct bpf_link *usdt_manager_attach_usdt(struct usdt_manager *man, const struct
/* discover USDT in given binary, optionally limiting
* activations to a given PID, if pid > 0
*/
- err = collect_usdt_targets(man, elf_fd.elf, path, pid, usdt_provider, usdt_name,
+ err = collect_usdt_targets(man, &elf_fd, path, pid, usdt_provider, usdt_name,
usdt_cookie, &targets, &target_cnt);
if (err <= 0) {
err = (err == 0) ? -ENOENT : err;
--
2.53.0
^ permalink raw reply related [flat|nested] 9+ messages in thread* Re: [PATCHv4 bpf-next 2/5] libbpf: Add support to detect nop,nop5 instructions combo for usdt probe
2026-02-20 10:42 ` [PATCHv4 bpf-next 2/5] libbpf: Add support to detect nop,nop5 instructions combo for usdt probe Jiri Olsa
@ 2026-02-20 11:24 ` bot+bpf-ci
2026-02-21 12:00 ` David Laight
0 siblings, 1 reply; 9+ messages in thread
From: bot+bpf-ci @ 2026-02-20 11:24 UTC (permalink / raw)
To: jolsa, andrii
Cc: bpf, linux-kernel, songliubraving, yhs, john.fastabend, ast,
andrii, daniel, martin.lau, eddyz87, yonghong.song, clm,
ihor.solodrai
[-- Attachment #1: Type: text/plain, Size: 1267 bytes --]
> diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
> index d1524f6f54ae..c81e0a58caf5 100644
> --- a/tools/lib/bpf/usdt.c
> +++ b/tools/lib/bpf/usdt.c
[ ... ]
> +#if defined(__x86_64__)
> +static bool has_nop_combo(int fd, long off)
> +{
> + static unsigned char nop_combo[6] = {
^^^^^^^^^^^^^^^^^^^^^^
Should nop_combo be declared const? It is a read-only lookup table
used only in the memcmp() below.
> + 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 /* nop,nop5 */
> + };
> + unsigned char buf[6] = {};
> +
> + if (pread(fd, buf, 6, off) != 6)
> + return false;
> + return memcmp(buf, nop_combo, 6) == 0;
> +}
[ ... ]
---
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/22221513473
AI-authorship-score: low
AI-authorship-explanation: Domain-specific optimization from established BPF/tracing maintainer with iterative lore review history and deep x86_64 uprobe internals knowledge.
issues-found: 1
issue-severity-score: low
issue-severity-explanation: Missing const qualifier on a static read-only byte array is a minor C best practice deviation with no runtime impact.
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [PATCHv4 bpf-next 2/5] libbpf: Add support to detect nop,nop5 instructions combo for usdt probe
2026-02-20 11:24 ` bot+bpf-ci
@ 2026-02-21 12:00 ` David Laight
2026-02-22 14:32 ` Jiri Olsa
0 siblings, 1 reply; 9+ messages in thread
From: David Laight @ 2026-02-21 12:00 UTC (permalink / raw)
To: bot+bpf-ci
Cc: jolsa, andrii, bpf, linux-kernel, songliubraving, yhs,
john.fastabend, ast, daniel, martin.lau, eddyz87, yonghong.song,
clm, ihor.solodrai
On Fri, 20 Feb 2026 11:24:45 +0000 (UTC)
bot+bpf-ci@kernel.org wrote:
> > diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
> > index d1524f6f54ae..c81e0a58caf5 100644
> > --- a/tools/lib/bpf/usdt.c
> > +++ b/tools/lib/bpf/usdt.c
>
> [ ... ]
>
> > +#if defined(__x86_64__)
> > +static bool has_nop_combo(int fd, long off)
> > +{
> > + static unsigned char nop_combo[6] = {
> ^^^^^^^^^^^^^^^^^^^^^^
>
> Should nop_combo be declared const? It is a read-only lookup table
> used only in the memcmp() below.
Actually you either want 'static const unsigned char' or just 'unsigned char'.
In either case gcc optimises away the array, the call to memcmp(), and
just compares with 32bit and 64bit constants.
>
> > + 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 /* nop,nop5 */
> > + };
> > + unsigned char buf[6] = {};
No need to initialise buf[];
David
> > +
> > + if (pread(fd, buf, 6, off) != 6)
> > + return false;
> > + return memcmp(buf, nop_combo, 6) == 0;
> > +}
>
> [ ... ]
>
>
> ---
> 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/22221513473
>
> AI-authorship-score: low
> AI-authorship-explanation: Domain-specific optimization from established BPF/tracing maintainer with iterative lore review history and deep x86_64 uprobe internals knowledge.
> issues-found: 1
> issue-severity-score: low
> issue-severity-explanation: Missing const qualifier on a static read-only byte array is a minor C best practice deviation with no runtime impact.
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [PATCHv4 bpf-next 2/5] libbpf: Add support to detect nop,nop5 instructions combo for usdt probe
2026-02-21 12:00 ` David Laight
@ 2026-02-22 14:32 ` Jiri Olsa
0 siblings, 0 replies; 9+ messages in thread
From: Jiri Olsa @ 2026-02-22 14:32 UTC (permalink / raw)
To: David Laight
Cc: bot+bpf-ci, andrii, bpf, linux-kernel, songliubraving, yhs,
john.fastabend, ast, daniel, martin.lau, eddyz87, yonghong.song,
clm, ihor.solodrai
On Sat, Feb 21, 2026 at 12:00:35PM +0000, David Laight wrote:
> On Fri, 20 Feb 2026 11:24:45 +0000 (UTC)
> bot+bpf-ci@kernel.org wrote:
>
> > > diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
> > > index d1524f6f54ae..c81e0a58caf5 100644
> > > --- a/tools/lib/bpf/usdt.c
> > > +++ b/tools/lib/bpf/usdt.c
> >
> > [ ... ]
> >
> > > +#if defined(__x86_64__)
> > > +static bool has_nop_combo(int fd, long off)
> > > +{
> > > + static unsigned char nop_combo[6] = {
> > ^^^^^^^^^^^^^^^^^^^^^^
> >
> > Should nop_combo be declared const? It is a read-only lookup table
> > used only in the memcmp() below.
>
> Actually you either want 'static const unsigned char' or just 'unsigned char'.
> In either case gcc optimises away the array, the call to memcmp(), and
> just compares with 32bit and 64bit constants.
ok, makes sense, will change
>
> >
> > > + 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 /* nop,nop5 */
> > > + };
> > > + unsigned char buf[6] = {};
>
> No need to initialise buf[];
right, thanks,
jirka
>
> David
>
> > > +
> > > + if (pread(fd, buf, 6, off) != 6)
> > > + return false;
> > > + return memcmp(buf, nop_combo, 6) == 0;
> > > +}
> >
> > [ ... ]
> >
> >
> > ---
> > 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/22221513473
> >
> > AI-authorship-score: low
> > AI-authorship-explanation: Domain-specific optimization from established BPF/tracing maintainer with iterative lore review history and deep x86_64 uprobe internals knowledge.
> > issues-found: 1
> > issue-severity-score: low
> > issue-severity-explanation: Missing const qualifier on a static read-only byte array is a minor C best practice deviation with no runtime impact.
>
^ permalink raw reply [flat|nested] 9+ messages in thread
* [PATCHv4 bpf-next 3/5] selftests/bpf: Emit nop,nop5 instructions combo for x86_64 arch
2026-02-20 10:42 [PATCHv4 bpf-next 0/5] libbpf: Make optimized uprobes backward compatible Jiri Olsa
2026-02-20 10:42 ` [PATCHv4 bpf-next 1/5] libbpf: Add uprobe syscall feature detection Jiri Olsa
2026-02-20 10:42 ` [PATCHv4 bpf-next 2/5] libbpf: Add support to detect nop,nop5 instructions combo for usdt probe Jiri Olsa
@ 2026-02-20 10:42 ` Jiri Olsa
2026-02-20 10:42 ` [PATCHv4 bpf-next 4/5] selftests/bpf: Add test for checking correct nop of optimized usdt Jiri Olsa
2026-02-20 10:42 ` [PATCHv4 bpf-next 5/5] selftests/bpf: Add usdt trigger bench Jiri Olsa
4 siblings, 0 replies; 9+ messages in thread
From: Jiri Olsa @ 2026-02-20 10:42 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: bpf, linux-kernel, Song Liu, Yonghong Song, John Fastabend
Syncing latest usdt.h change [1].
Now that we have nop5 optimization support in kernel, let's emit
nop,nop5 for usdt probe. We leave it up to the library to use
desirable nop instruction.
[1] https://github.com/libbpf/usdt/commit/c9865d158984fb2b73e3cbbdcdfb4f583ad36a73
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/testing/selftests/bpf/usdt.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/testing/selftests/bpf/usdt.h b/tools/testing/selftests/bpf/usdt.h
index 549d1f774810..c71e21df38b3 100644
--- a/tools/testing/selftests/bpf/usdt.h
+++ b/tools/testing/selftests/bpf/usdt.h
@@ -312,6 +312,8 @@ struct usdt_sema { volatile unsigned short active; };
#ifndef USDT_NOP
#if defined(__ia64__) || defined(__s390__) || defined(__s390x__)
#define USDT_NOP nop 0
+#elif defined(__x86_64__)
+#define USDT_NOP .byte 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x0 /* nop, nop5 */
#else
#define USDT_NOP nop
#endif
--
2.53.0
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCHv4 bpf-next 4/5] selftests/bpf: Add test for checking correct nop of optimized usdt
2026-02-20 10:42 [PATCHv4 bpf-next 0/5] libbpf: Make optimized uprobes backward compatible Jiri Olsa
` (2 preceding siblings ...)
2026-02-20 10:42 ` [PATCHv4 bpf-next 3/5] selftests/bpf: Emit nop,nop5 instructions combo for x86_64 arch Jiri Olsa
@ 2026-02-20 10:42 ` Jiri Olsa
2026-02-20 10:42 ` [PATCHv4 bpf-next 5/5] selftests/bpf: Add usdt trigger bench Jiri Olsa
4 siblings, 0 replies; 9+ messages in thread
From: Jiri Olsa @ 2026-02-20 10:42 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: bpf, linux-kernel, Song Liu, Yonghong Song, John Fastabend
Adding test that attaches bpf program on usdt probe in 2 scenarios;
- attach program on top of usdt_1, which is single nop instruction,
so the probe stays on nop instruction and is not optimized.
- attach program on top of usdt_2 which is probe defined on top
of nop,nop5 combo, so the probe is placed on top of nop5 and
is optimized.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/testing/selftests/bpf/.gitignore | 2 +
tools/testing/selftests/bpf/Makefile | 3 +-
tools/testing/selftests/bpf/prog_tests/usdt.c | 92 +++++++++++++++++++
tools/testing/selftests/bpf/progs/test_usdt.c | 12 +++
tools/testing/selftests/bpf/usdt_1.c | 18 ++++
tools/testing/selftests/bpf/usdt_2.c | 16 ++++
6 files changed, 142 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/usdt_1.c
create mode 100644 tools/testing/selftests/bpf/usdt_2.c
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index a3ea98211ea6..bfdc5518ecc8 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -47,3 +47,5 @@ verification_cert.h
*.BTF
*.BTF_ids
*.BTF.base
+usdt_1
+usdt_2
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 6776158f1f3e..23857d17fc5b 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -749,7 +749,8 @@ TRUNNER_EXTRA_SOURCES := test_progs.c \
$(VERIFY_SIG_HDR) \
flow_dissector_load.h \
ip_check_defrag_frags.h \
- bpftool_helpers.c
+ bpftool_helpers.c \
+ usdt_1.c usdt_2.c
TRUNNER_LIB_SOURCES := find_bit.c
TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \
$(OUTPUT)/liburandom_read.so \
diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c
index f4be5269fa90..69759b27794d 100644
--- a/tools/testing/selftests/bpf/prog_tests/usdt.c
+++ b/tools/testing/selftests/bpf/prog_tests/usdt.c
@@ -247,6 +247,96 @@ static void subtest_basic_usdt(bool optimized)
#undef TRIGGER
}
+#ifdef __x86_64__
+extern void usdt_1(void);
+extern void usdt_2(void);
+
+static unsigned char nop1[1] = { 0x90 };
+static unsigned char nop1_nop5_combo[6] = { 0x90, 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+
+static void *find_instr(void *fn, unsigned char *instr, size_t cnt)
+{
+ int i;
+
+ for (i = 0; i < 10; i++) {
+ if (!memcmp(instr, fn + i, cnt))
+ return fn + i;
+ }
+ return NULL;
+}
+
+static void subtest_optimized_attach(void)
+{
+ struct test_usdt *skel;
+ __u8 *addr_1, *addr_2;
+
+ /* usdt_1 USDT probe has single nop instruction */
+ addr_1 = find_instr(usdt_1, nop1_nop5_combo, 6);
+ if (!ASSERT_NULL(addr_1, "usdt_1_find_nop1_nop5_combo"))
+ return;
+
+ addr_1 = find_instr(usdt_1, nop1, 1);
+ if (!ASSERT_OK_PTR(addr_1, "usdt_1_find_nop1"))
+ return;
+
+ /* usdt_2 USDT probe has nop,nop5 instructions combo */
+ addr_2 = find_instr(usdt_2, nop1_nop5_combo, 6);
+ if (!ASSERT_OK_PTR(addr_2, "usdt_2_find_nop1_nop5_combo"))
+ return;
+
+ skel = test_usdt__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_usdt__open_and_load"))
+ return;
+
+ skel->bss->expected_ip = (unsigned long) addr_1;
+
+ /*
+ * Attach program on top of usdt_1 which is single nop probe,
+ * so the probe won't get optimized.
+ */
+ skel->links.usdt_executed = bpf_program__attach_usdt(skel->progs.usdt_executed,
+ 0 /*self*/, "/proc/self/exe",
+ "optimized_attach", "usdt_1", NULL);
+ if (!ASSERT_OK_PTR(skel->links.usdt_executed, "bpf_program__attach_usdt"))
+ goto cleanup;
+
+ usdt_1();
+ usdt_1();
+
+ /* int3 is on addr_1 address */
+ ASSERT_EQ(*addr_1, 0xcc, "int3");
+ ASSERT_EQ(skel->bss->executed, 2, "executed");
+
+ bpf_link__destroy(skel->links.usdt_executed);
+
+ /* we expect the nop5 ip */
+ skel->bss->expected_ip = (unsigned long) addr_2 + 1;
+
+ /*
+ * Attach program on top of usdt_2 which is probe defined on top
+ * of nop1,nop5 combo, so the probe gets optimized on top of nop5.
+ */
+ skel->links.usdt_executed = bpf_program__attach_usdt(skel->progs.usdt_executed,
+ 0 /*self*/, "/proc/self/exe",
+ "optimized_attach", "usdt_2", NULL);
+ if (!ASSERT_OK_PTR(skel->links.usdt_executed, "bpf_program__attach_usdt"))
+ goto cleanup;
+
+ usdt_2();
+ usdt_2();
+
+ /* nop stays on addr_2 address */
+ ASSERT_EQ(*addr_2, 0x90, "nop");
+
+ /* call is on addr_2 + 1 address */
+ ASSERT_EQ(*(addr_2 + 1), 0xe8, "call");
+ ASSERT_EQ(skel->bss->executed, 4, "executed");
+
+cleanup:
+ test_usdt__destroy(skel);
+}
+#endif
+
unsigned short test_usdt_100_semaphore SEC(".probes");
unsigned short test_usdt_300_semaphore SEC(".probes");
unsigned short test_usdt_400_semaphore SEC(".probes");
@@ -516,6 +606,8 @@ void test_usdt(void)
#ifdef __x86_64__
if (test__start_subtest("basic_optimized"))
subtest_basic_usdt(true);
+ if (test__start_subtest("optimized_attach"))
+ subtest_optimized_attach();
#endif
if (test__start_subtest("multispec"))
subtest_multispec_usdt();
diff --git a/tools/testing/selftests/bpf/progs/test_usdt.c b/tools/testing/selftests/bpf/progs/test_usdt.c
index a78c87537b07..f00cb52874e0 100644
--- a/tools/testing/selftests/bpf/progs/test_usdt.c
+++ b/tools/testing/selftests/bpf/progs/test_usdt.c
@@ -138,4 +138,16 @@ int usdt_sib(struct pt_regs *ctx)
return 0;
}
+#ifdef __TARGET_ARCH_x86
+int executed;
+unsigned long expected_ip;
+
+SEC("usdt")
+int usdt_executed(struct pt_regs *ctx)
+{
+ if (expected_ip == ctx->ip)
+ executed++;
+ return 0;
+}
+#endif
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/usdt_1.c b/tools/testing/selftests/bpf/usdt_1.c
new file mode 100644
index 000000000000..4f06e8bcf58b
--- /dev/null
+++ b/tools/testing/selftests/bpf/usdt_1.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#if defined(__x86_64__)
+
+/*
+ * Include usdt.h with defined USDT_NOP macro to use single
+ * nop instruction.
+ */
+#define USDT_NOP .byte 0x90
+#include "usdt.h"
+
+__attribute__((aligned(16)))
+void usdt_1(void)
+{
+ USDT(optimized_attach, usdt_1);
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/usdt_2.c b/tools/testing/selftests/bpf/usdt_2.c
new file mode 100644
index 000000000000..789883aaca4c
--- /dev/null
+++ b/tools/testing/selftests/bpf/usdt_2.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#if defined(__x86_64__)
+
+/*
+ * Include usdt.h with default nop,nop5 instructions combo.
+ */
+#include "usdt.h"
+
+__attribute__((aligned(16)))
+void usdt_2(void)
+{
+ USDT(optimized_attach, usdt_2);
+}
+
+#endif
--
2.53.0
^ permalink raw reply related [flat|nested] 9+ messages in thread* [PATCHv4 bpf-next 5/5] selftests/bpf: Add usdt trigger bench
2026-02-20 10:42 [PATCHv4 bpf-next 0/5] libbpf: Make optimized uprobes backward compatible Jiri Olsa
` (3 preceding siblings ...)
2026-02-20 10:42 ` [PATCHv4 bpf-next 4/5] selftests/bpf: Add test for checking correct nop of optimized usdt Jiri Olsa
@ 2026-02-20 10:42 ` Jiri Olsa
4 siblings, 0 replies; 9+ messages in thread
From: Jiri Olsa @ 2026-02-20 10:42 UTC (permalink / raw)
To: Andrii Nakryiko
Cc: bpf, linux-kernel, Song Liu, Yonghong Song, John Fastabend
Adding usdt trigger bench for usdt:
trig-usdt-nop - usdt on top of nop1 instruction
trig-usdt-nop5 - usdt on top of nop1/nop5 combo
Adding it to benchs/run_bench_uprobes.sh script.
Example run on x86_64 kernel with uprobe syscall:
# ./benchs/run_bench_uprobes.sh
usermode-count : 152.507 ± 0.098M/s
syscall-count : 14.309 ± 0.093M/s
uprobe-nop : 3.190 ± 0.012M/s
uprobe-push : 3.057 ± 0.004M/s
uprobe-ret : 1.095 ± 0.009M/s
uprobe-nop5 : 7.305 ± 0.034M/s
uretprobe-nop : 2.175 ± 0.005M/s
uretprobe-push : 2.109 ± 0.003M/s
uretprobe-ret : 0.945 ± 0.002M/s
uretprobe-nop5 : 3.530 ± 0.006M/s
usdt-nop : 3.235 ± 0.008M/s <-- added
usdt-nop5 : 7.511 ± 0.045M/s <-- added
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/testing/selftests/bpf/Makefile | 2 +
tools/testing/selftests/bpf/bench.c | 4 ++
.../selftests/bpf/benchs/bench_trigger.c | 60 +++++++++++++++++++
.../selftests/bpf/benchs/run_bench_uprobes.sh | 2 +-
.../selftests/bpf/progs/trigger_bench.c | 10 +++-
5 files changed, 76 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 23857d17fc5b..8196128251d5 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -874,6 +874,8 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
$(OUTPUT)/bench_bpf_crypto.o \
$(OUTPUT)/bench_sockmap.o \
$(OUTPUT)/bench_lpm_trie_map.o \
+ $(OUTPUT)/usdt_1.o \
+ $(OUTPUT)/usdt_2.o \
#
$(call msg,BINARY,,$@)
$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 8368bd3a0665..029b3e21f438 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -541,6 +541,8 @@ extern const struct bench bench_trig_uprobe_nop5;
extern const struct bench bench_trig_uretprobe_nop5;
extern const struct bench bench_trig_uprobe_multi_nop5;
extern const struct bench bench_trig_uretprobe_multi_nop5;
+extern const struct bench bench_trig_usdt_nop;
+extern const struct bench bench_trig_usdt_nop5;
#endif
extern const struct bench bench_rb_libbpf;
@@ -617,6 +619,8 @@ static const struct bench *benchs[] = {
&bench_trig_uretprobe_nop5,
&bench_trig_uprobe_multi_nop5,
&bench_trig_uretprobe_multi_nop5,
+ &bench_trig_usdt_nop,
+ &bench_trig_usdt_nop5,
#endif
/* ringbuf/perfbuf benchmarks */
&bench_rb_libbpf,
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index aeec9edd3851..2ee6a2df2c26 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -405,6 +405,23 @@ static void *uprobe_producer_nop5(void *input)
uprobe_target_nop5();
return NULL;
}
+
+void usdt_1(void);
+void usdt_2(void);
+
+static void *uprobe_producer_usdt_nop(void *input)
+{
+ while (true)
+ usdt_1();
+ return NULL;
+}
+
+static void *uprobe_producer_usdt_nop5(void *input)
+{
+ while (true)
+ usdt_2();
+ return NULL;
+}
#endif
static void usetup(bool use_retprobe, bool use_multi, void *target_addr)
@@ -542,6 +559,47 @@ static void uretprobe_multi_nop5_setup(void)
{
usetup(true, true /* use_multi */, &uprobe_target_nop5);
}
+
+static void usdt_setup(const char *name)
+{
+ struct bpf_link *link;
+ int err;
+
+ setup_libbpf();
+
+ ctx.skel = trigger_bench__open();
+ if (!ctx.skel) {
+ fprintf(stderr, "failed to open skeleton\n");
+ exit(1);
+ }
+
+ bpf_program__set_autoload(ctx.skel->progs.bench_trigger_usdt, true);
+
+ err = trigger_bench__load(ctx.skel);
+ if (err) {
+ fprintf(stderr, "failed to load skeleton\n");
+ exit(1);
+ }
+
+ link = bpf_program__attach_usdt(ctx.skel->progs.bench_trigger_usdt,
+ 0 /*self*/, "/proc/self/exe",
+ "optimized_attach", name, NULL);
+ if (libbpf_get_error(link)) {
+ fprintf(stderr, "failed to attach optimized_attach:%s usdt probe\n", name);
+ exit(1);
+ }
+ ctx.skel->links.bench_trigger_usdt = link;
+}
+
+static void usdt_nop_setup(void)
+{
+ usdt_setup("usdt_1");
+}
+
+static void usdt_nop5_setup(void)
+{
+ usdt_setup("usdt_2");
+}
#endif
const struct bench bench_trig_syscall_count = {
@@ -609,4 +667,6 @@ BENCH_TRIG_USERMODE(uprobe_nop5, nop5, "uprobe-nop5");
BENCH_TRIG_USERMODE(uretprobe_nop5, nop5, "uretprobe-nop5");
BENCH_TRIG_USERMODE(uprobe_multi_nop5, nop5, "uprobe-multi-nop5");
BENCH_TRIG_USERMODE(uretprobe_multi_nop5, nop5, "uretprobe-multi-nop5");
+BENCH_TRIG_USERMODE(usdt_nop, usdt_nop, "usdt-nop");
+BENCH_TRIG_USERMODE(usdt_nop5, usdt_nop5, "usdt-nop5");
#endif
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
index 03f55405484b..9ec59423b949 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
@@ -2,7 +2,7 @@
set -eufo pipefail
-for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop5}
+for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop5} usdt-nop usdt-nop5
do
summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
printf "%-15s: %s\n" $i "$summary"
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
index 4ea0422d1042..3225b4aee8ff 100644
--- a/tools/testing/selftests/bpf/progs/trigger_bench.c
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -1,10 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2020 Facebook
-#include <linux/bpf.h>
+#include "vmlinux.h"
#include <asm/unistd.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include "bpf_misc.h"
+#include "bpf/usdt.bpf.h"
char _license[] SEC("license") = "GPL";
@@ -180,3 +181,10 @@ int bench_trigger_rawtp(void *ctx)
handle(ctx);
return 0;
}
+
+SEC("?usdt")
+int bench_trigger_usdt(void *ctx)
+{
+ inc_counter();
+ return 0;
+}
--
2.53.0
^ permalink raw reply related [flat|nested] 9+ messages in thread