[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <aFFouFEKLFsYhVOe@krava>
Date: Tue, 17 Jun 2025 15:08:08 +0200
From: Jiri Olsa <olsajiri@...il.com>
To: Oleg Nesterov <oleg@...hat.com>, Peter Zijlstra <peterz@...radead.org>,
Andrii Nakryiko <andrii@...nel.org>,
Masami Hiramatsu <mhiramat@...nel.org>
Cc: Alejandro Colomar <alx@...nel.org>, Eyal Birger <eyal.birger@...il.com>,
kees@...nel.org, bpf@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-trace-kernel@...r.kernel.org, x86@...nel.org,
Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
John Fastabend <john.fastabend@...il.com>,
Hao Luo <haoluo@...gle.com>, Steven Rostedt <rostedt@...dmis.org>,
Alan Maguire <alan.maguire@...cle.com>,
David Laight <David.Laight@...lab.com>,
Thomas Weißschuh <thomas@...ch.de>,
Ingo Molnar <mingo@...nel.org>
Subject: Re: [PATCHv3 perf/core 00/22] uprobes: Add support to optimize usdt
probes on x86_64
hi, ping
thanks,
jirka
On Thu, Jun 05, 2025 at 03:23:27PM +0200, Jiri Olsa wrote:
> hi,
> this patchset adds support to optimize usdt probes on top of 5-byte
> nop instruction.
>
> The generic approach (optimize all uprobes) is hard due to emulating
> possible multiple original instructions and its related issues. The
> usdt case, which stores 5-byte nop seems much easier, so starting
> with that.
>
> The basic idea is to replace breakpoint exception with syscall which
> is faster on x86_64. For more details please see changelog of patch 8.
>
> The run_bench_uprobes.sh benchmark triggers uprobe (on top of different
> original instructions) in a loop and counts how many of those happened
> per second (the unit below is million loops).
>
> There's big speed up if you consider current usdt implementation
> (uprobe-nop) compared to proposed usdt (uprobe-nop5):
>
> current:
> usermode-count : 152.501 ± 0.012M/s
> syscall-count : 14.463 ± 0.062M/s
> --> uprobe-nop : 3.160 ± 0.005M/s
> uprobe-push : 3.003 ± 0.003M/s
> uprobe-ret : 1.100 ± 0.003M/s
> uprobe-nop5 : 3.132 ± 0.012M/s
> uretprobe-nop : 2.103 ± 0.002M/s
> uretprobe-push : 2.027 ± 0.004M/s
> uretprobe-ret : 0.914 ± 0.002M/s
> uretprobe-nop5 : 2.115 ± 0.002M/s
>
> after the change:
> usermode-count : 152.343 ± 0.400M/s
> syscall-count : 14.851 ± 0.033M/s
> uprobe-nop : 3.204 ± 0.005M/s
> uprobe-push : 3.040 ± 0.005M/s
> uprobe-ret : 1.098 ± 0.003M/s
> --> uprobe-nop5 : 7.286 ± 0.017M/s
> uretprobe-nop : 2.144 ± 0.001M/s
> uretprobe-push : 2.069 ± 0.002M/s
> uretprobe-ret : 0.922 ± 0.000M/s
> uretprobe-nop5 : 3.487 ± 0.001M/s
>
> I see bit more speed up on Intel (above) compared to AMD. The big nop5
> speed up is partly due to emulating nop5 and partly due to optimization.
>
> The key speed up we do this for is the USDT switch from nop to nop5:
> uprobe-nop : 3.160 ± 0.005M/s
> uprobe-nop5 : 7.286 ± 0.017M/s
>
>
> Changes from v2:
> - rebased on top of tip/master + mm/mm-stable + 1 extra change [1]
> - added acks [Oleg,Andrii]
> - more details changelog for patch 1 [Masami]
> - several tests changes [Andrii]
> - add explicit PAGE_SIZE low limit to vm_unmapped_area call [Andrii]
>
>
> This patchset is adding new syscall, here are notes to check list items
> in Documentation/process/adding-syscalls.rst:
>
> - System Call Alternatives
> New syscall seems like the best way in here, because we need
> just to quickly enter kernel with no extra arguments processing,
> which we'd need to do if we decided to use another syscall.
>
> - Designing the API: Planning for Extension
> The uprobe syscall is very specific and most likely won't be
> extended in the future.
>
> - Designing the API: Other Considerations
> N/A because uprobe syscall does not return reference to kernel
> object.
>
> - Proposing the API
> Wiring up of the uprobe system call is in separate change,
> selftests and man page changes are part of the patchset.
>
> - Generic System Call Implementation
> There's no CONFIG option for the new functionality because it
> keeps the same behaviour from the user POV.
>
> - x86 System Call Implementation
> It's 64-bit syscall only.
>
> - Compatibility System Calls (Generic)
> N/A uprobe syscall has no arguments and is not supported
> for compat processes.
>
> - Compatibility System Calls (x86)
> N/A uprobe syscall is not supported for compat processes.
>
> - System Calls Returning Elsewhere
> N/A.
>
> - Other Details
> N/A.
>
> - Testing
> Adding new bpf selftests.
>
> - Man Page
> Attached.
>
> - Do not call System Calls in the Kernel
> N/A
>
> pending todo (or follow ups):
> - use PROCMAP_QUERY in tests
> - alloc 'struct uprobes_state' for mm_struct only when needed [Andrii]
> - use mm_cpumask(vma->vm_mm) in text_poke_sync
>
> thanks,
> jirka
>
>
> Cc: Alejandro Colomar <alx@...nel.org>
> Cc: Eyal Birger <eyal.birger@...il.com>
> Cc: kees@...nel.org
>
> [1] https://lore.kernel.org/linux-trace-kernel/20250514101809.2010193-1-jolsa@kernel.org/T/#u
> ---
> Jiri Olsa (21):
> uprobes: Remove breakpoint in unapply_uprobe under mmap_write_lock
> uprobes: Rename arch_uretprobe_trampoline function
> uprobes: Make copy_from_page global
> uprobes: Add uprobe_write function
> uprobes: Add nbytes argument to uprobe_write
> uprobes: Add is_register argument to uprobe_write and uprobe_write_opcode
> uprobes: Add do_ref_ctr argument to uprobe_write function
> uprobes/x86: Add mapping for optimized uprobe trampolines
> uprobes/x86: Add uprobe syscall to speed up uprobe
> uprobes/x86: Add support to optimize uprobes
> selftests/bpf: Import usdt.h from libbpf/usdt project
> selftests/bpf: Reorg the uprobe_syscall test function
> selftests/bpf: Rename uprobe_syscall_executed prog to test_uretprobe_multi
> selftests/bpf: Add uprobe/usdt syscall tests
> selftests/bpf: Add hit/attach/detach race optimized uprobe test
> selftests/bpf: Add uprobe syscall sigill signal test
> selftests/bpf: Add optimized usdt variant for basic usdt test
> selftests/bpf: Add uprobe_regs_equal test
> selftests/bpf: Change test_uretprobe_regs_change for uprobe and uretprobe
> seccomp: passthrough uprobe systemcall without filtering
> selftests/seccomp: validate uprobe syscall passes through seccomp
>
> arch/arm/probes/uprobes/core.c | 2 +-
> arch/x86/entry/syscalls/syscall_64.tbl | 1 +
> arch/x86/include/asm/uprobes.h | 7 ++
> arch/x86/kernel/uprobes.c | 525 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
> include/linux/syscalls.h | 2 +
> include/linux/uprobes.h | 20 +++-
> kernel/events/uprobes.c | 100 ++++++++++++-----
> kernel/fork.c | 1 +
> kernel/seccomp.c | 32 ++++--
> kernel/sys_ni.c | 1 +
> tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 523 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++------
> tools/testing/selftests/bpf/prog_tests/usdt.c | 38 ++++---
> tools/testing/selftests/bpf/progs/uprobe_syscall.c | 4 +-
> tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c | 60 +++++++++-
> tools/testing/selftests/bpf/test_kmods/bpf_testmod.c | 11 +-
> tools/testing/selftests/bpf/usdt.h | 545 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> tools/testing/selftests/seccomp/seccomp_bpf.c | 107 ++++++++++++++----
> 17 files changed, 1867 insertions(+), 112 deletions(-)
> create mode 100644 tools/testing/selftests/bpf/usdt.h
>
>
> Jiri Olsa (1):
> man2: Add uprobe syscall page
>
> man/man2/uprobe.2 | 1 +
> man/man2/uretprobe.2 | 36 ++++++++++++++++++++++++------------
> 2 files changed, 25 insertions(+), 12 deletions(-)
> create mode 100644 man/man2/uprobe.2
Powered by blists - more mailing lists