BPF List
 help / color / mirror / Atom feed
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>

  parent reply	other threads:[~2026-05-28 12:46 UTC|newest]

Thread overview: 49+ 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
2026-06-08 20:46   ` Andrii Nakryiko
2026-06-09 11:44     ` Jiri Olsa
2026-06-09 16:43       ` Andrii Nakryiko
2026-06-10  8:18         ` Jiri Olsa
2026-06-10 18:02           ` Andrii Nakryiko
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
2026-06-08 20:48   ` Andrii Nakryiko

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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox