From: Jakub Sitnicki <jakub@cloudflare.com>
To: Jiri Olsa <jolsa@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@kernel.org>,
Masami Hiramatsu <mhiramat@kernel.org>,
Andrii Nakryiko <andrii@kernel.org>,
bpf@vger.kernel.org, linux-trace-kernel@vger.kernel.org
Subject: Re: [PATCHv4 12/13] selftests/bpf: Add tests for uprobe nop10 red zone clobbering
Date: Thu, 28 May 2026 14:46:48 +0200 [thread overview]
Message-ID: <87pl2f66rr.fsf@cloudflare.com> (raw)
In-Reply-To: <20260526205840.173790-13-jolsa@kernel.org> (Jiri Olsa's message of "Tue, 26 May 2026 22:58:39 +0200")
On Tue, May 26, 2026 at 10:58 PM +02, Jiri Olsa wrote:
> From: Andrii Nakryiko <andrii@kernel.org>
>
> The uprobe nop5 optimization used to replace a 5-byte NOP with a 5-byte
> CALL to a trampoline. The CALL pushes a return address onto the stack at
> [rsp-8], clobbering whatever was stored there.
>
> On x86-64, the red zone is the 128 bytes below rsp that user code may use
> for temporary storage without adjusting rsp. Compilers can place USDT
> argument operands there, generating specs like "8@-8(%rbp)" when rbp ==
> rsp. With the CALL-based optimization, the return address overwrites that
> argument before the BPF-side USDT argument fetch runs.
>
> Add two tests for this case. The uprobe_syscall subtest stores known values
> at -8(%rsp), -16(%rsp), and -24(%rsp), executes an optimized nop10 uprobe,
> and verifies the red-zone data is still intact. The USDT subtest triggers a
> probe in a function where the compiler places three USDT operands in the
> red zone and verifies that all 10 optimized invocations deliver the expected
> argument values to BPF.
>
> On an unfixed kernel, the first hit goes through the INT3 path and later
> hits use the optimized CALL path, so the red-zone checks fail after
> optimization.
>
> Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
> [ updates to use nop10 ]
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
> .../selftests/bpf/prog_tests/uprobe_syscall.c | 75 +++++++++++++++++++
> tools/testing/selftests/bpf/prog_tests/usdt.c | 49 ++++++++++++
> tools/testing/selftests/bpf/progs/test_usdt.c | 25 +++++++
> tools/testing/selftests/bpf/usdt_2.c | 13 ++++
> 4 files changed, 162 insertions(+)
>
> diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
> index 969f4deba9fd..efff0c515184 100644
> --- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
> +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
[...]
> @@ -855,6 +897,37 @@ static void test_uprobe_race(void)
> #define __NR_uprobe 336
> #endif
>
> +static void test_uprobe_red_zone(void)
> +{
> + struct uprobe_syscall_executed *skel;
> + struct bpf_link *link;
> + void *nop10_addr;
> + size_t offset;
> + int i;
> +
> + nop10_addr = find_nop10(uprobe_red_zone_test);
> + if (!ASSERT_NEQ(nop10_addr, NULL, "find_nop10"))
Nit: ASSERT_OK_PTR would have worked as well. Dealer's choice.
> + return;
> +
> + skel = uprobe_syscall_executed__open_and_load();
> + if (!ASSERT_OK_PTR(skel, "open_and_load"))
> + return;
> +
> + offset = get_uprobe_offset(nop10_addr);
> + link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
> + 0, "/proc/self/exe", offset, NULL);
> + if (!ASSERT_OK_PTR(link, "attach_uprobe"))
> + goto cleanup;
> +
> + for (i = 0; i < 10; i++)
> + ASSERT_EQ(uprobe_red_zone_test(), 0, "red_zone_intact");
> +
> + bpf_link__destroy(link);
> +
> +cleanup:
> + uprobe_syscall_executed__destroy(skel);
> +}
> +
> static void test_uprobe_error(void)
> {
> long err = syscall(__NR_uprobe);
[...]
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
next prev parent reply other threads:[~2026-05-28 12:46 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-26 20:58 [PATCHv4 00/13] uprobes/x86: Fix red zone issue for optimized uprobes Jiri Olsa
2026-05-26 20:58 ` [PATCHv4 01/13] uprobes/x86: Use proper mm_struct in __in_uprobe_trampoline Jiri Olsa
2026-05-26 20:58 ` [PATCHv4 02/13] uprobes/x86: Remove struct uprobe_trampoline object Jiri Olsa
2026-05-26 21:46 ` bot+bpf-ci
2026-05-27 9:58 ` Jiri Olsa
2026-06-01 8:31 ` Jiri Olsa
2026-05-26 20:58 ` [PATCHv4 03/13] uprobes/x86: Allow to copy uprobe trampolines on fork Jiri Olsa
2026-05-26 21:46 ` bot+bpf-ci
2026-05-27 9:58 ` Jiri Olsa
2026-05-26 20:58 ` [PATCHv4 04/13] uprobes/x86: Unmap trampoline vma object in case it's unused Jiri Olsa
2026-05-26 21:46 ` bot+bpf-ci
2026-05-27 9:57 ` Jiri Olsa
2026-05-26 20:58 ` [PATCHv4 05/13] uprobes/x86: Move optimized uprobe from nop5 to nop10 Jiri Olsa
2026-05-26 20:58 ` [PATCHv4 06/13] libbpf: Change has_nop_combo to work on top of nop10 Jiri Olsa
2026-05-26 21:28 ` sashiko-bot
2026-05-27 9:57 ` Jiri Olsa
2026-05-26 21:46 ` bot+bpf-ci
2026-05-27 9:57 ` Jiri Olsa
2026-05-26 20:58 ` [PATCHv4 07/13] libbpf: Detect uprobe syscall with new error Jiri Olsa
2026-05-26 21:36 ` sashiko-bot
2026-05-26 21:46 ` bot+bpf-ci
2026-05-26 20:58 ` [PATCHv4 08/13] selftests/bpf: Emit nop,nop10 instructions combo for x86_64 arch Jiri Olsa
2026-05-26 21:19 ` sashiko-bot
2026-05-26 21:46 ` bot+bpf-ci
2026-05-26 20:58 ` [PATCHv4 09/13] selftests/bpf: Change uprobe syscall tests to use nop10 Jiri Olsa
2026-05-26 21:15 ` sashiko-bot
2026-05-27 9:58 ` Jiri Olsa
2026-05-26 21:46 ` bot+bpf-ci
2026-05-27 9:58 ` Jiri Olsa
2026-05-27 10:30 ` Jakub Sitnicki
2026-05-26 20:58 ` [PATCHv4 10/13] selftests/bpf: Change uprobe/usdt trigger bench code " Jiri Olsa
2026-05-27 10:46 ` Jakub Sitnicki
2026-05-26 20:58 ` [PATCHv4 11/13] selftests/bpf: Add reattach tests for uprobe syscall Jiri Olsa
2026-05-27 11:32 ` Jakub Sitnicki
2026-05-28 11:10 ` Jiri Olsa
2026-05-26 20:58 ` [PATCHv4 12/13] selftests/bpf: Add tests for uprobe nop10 red zone clobbering Jiri Olsa
2026-05-26 21:46 ` bot+bpf-ci
2026-05-27 10:26 ` Jiri Olsa
2026-05-28 12:46 ` Jakub Sitnicki [this message]
2026-05-26 20:58 ` [PATCHv4 13/13] selftests/bpf: Add tests for forked/cloned optimized uprobes Jiri Olsa
2026-05-28 13:00 ` Jakub Sitnicki
2026-06-01 8:31 ` Jiri Olsa
2026-06-04 6:59 ` [PATCHv4 00/13] uprobes/x86: Fix red zone issue for " Jiri Olsa
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87pl2f66rr.fsf@cloudflare.com \
--to=jakub@cloudflare.com \
--cc=andrii@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=jolsa@kernel.org \
--cc=linux-trace-kernel@vger.kernel.org \
--cc=mhiramat@kernel.org \
--cc=mingo@kernel.org \
--cc=oleg@redhat.com \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.