mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Cc: "Jiri Olsa" <olsajiri@gmail.com>,
	"Oleg Nesterov" <oleg@redhat.com>,
	"Andrii Nakryiko" <andrii@kernel.org>, bpf <bpf@vger.kernel.org>,
	"open list" <linux-kernel@vger.kernel.org>,
	"Linux trace kernel" <linux-trace-kernel@vger.kernel.org>,
	"X86 ML" <x86@kernel.org>, "Song Liu" <songliubraving@fb.com>,
	"Yonghong Song" <yhs@fb.com>,
	"John Fastabend" <john.fastabend@gmail.com>,
	"Hao Luo" <haoluo@google.com>,
	"Steven Rostedt" <rostedt@goodmis.org>,
	"Masami Hiramatsu" <mhiramat@kernel.org>,
	"Alan Maguire" <alan.maguire@oracle.com>,
	"David Laight" <David.Laight@aculab.com>,
	"Thomas Weißschuh" <thomas@t-8ch.de>,
	"Ingo Molnar" <mingo@kernel.org>
Subject: Re: nop5-optimized USDTs WAS: Re: [PATCHv6 perf/core 09/22] uprobes/x86: Add uprobe syscall to speed up uprobe
Date: Fri, 5 Sep 2025 10:38:33 +0200	[thread overview]
Message-ID: <20250905083833.GR4068168@noisy.programming.kicks-ass.net> (raw)
In-Reply-To: <20250905082447.GQ4068168@noisy.programming.kicks-ass.net>

On Fri, Sep 05, 2025 at 10:24:47AM +0200, Peter Zijlstra wrote:
> +bool insn_is_nop(struct insn *insn)
> +{
> +	u8 rex, rex_b = 0, rex_x = 0, rex_r = 0, rex_w = 0;
> +	u8 modrm, modrm_mod, modrm_reg, modrm_rm;
> +	u8 sib = 0, sib_scale, sib_index, sib_base;
> +
> +	if (insn->rex_prefix.nbytes) {
> +		rex = insn->rex_prefix.bytes[0];
> +		rex_w = !!X86_REX_W(rex);
> +		rex_r = !!X86_REX_R(rex);
> +		rex_x = !!X86_REX_X(rex);
> +		rex_b = !!X86_REX_B(rex);
> +	}
> +
> +	if (insn->modrm.nbytes) {
> +		modrm = insn->modrm.bytes[0];
> +		modrm_mod = X86_MODRM_MOD(modrm);
> +		modrm_reg = X86_MODRM_REG(modrm) + 8*rex_r;
> +		modrm_rm  = X86_MODRM_RM(modrm)  + 8*rex_b;
> +	}
> +
> +	if (insn->sib.nbytes) {
> +		sib = insn->sib.bytes[0];
> +		sib_scale = X86_SIB_SCALE(sib);
> +		sib_index = X86_SIB_INDEX(sib) + 8*rex_x;
> +		sib_base  = X86_SIB_BASE(sib)  + 8*rex_b;
> +
> +		modrm_rm = sib_base;
> +	}
> +
> +	switch (insn->opcode.bytes[0]) {
> +	case 0x0f: /* 2nd byte */
> +		break;
> +
> +	case 0x89: /* MOV */
> +		if (modrm_mod != 3) /* register-direct */
> +			return false;
> +
> +		if (insn->x86_64 && !rex_w) /* native size */
> +			return false;
> +
> +		for (int i = 0; i < insn->prefixes.nbytes; i++) {
> +			if (insn->prefixes.bytes[i] == 0x66) /* OSP */
> +				return false;
> +		}
> +
> +		return modrm_reg == modrm_rm; /* MOV %reg, %reg */
> +
> +	case 0x8d: /* LEA */
> +		if (modrm_mod == 0 || modrm_mod == 3) /* register-indirect with disp */
> +			return false;
> +
> +		if (insn->x86_64 && !rex_w) /* native size */
> +			return false;
> +
> +		if (insn->displacement.value != 0)
> +			return false;
> +
> +		if (sib & (sib_scale != 0 || sib_index != 4)) /* (%reg, %eiz, 1) */

Argh, that should obviously be: &&

> +			return false;
> +
> +		for (int i = 0; i < insn->prefixes.nbytes; i++) {
> +			if (insn->prefixes.bytes[i] != 0x3e) /* DS */
> +				return false;
> +		}
> +
> +		return modrm_reg == modrm_rm; /* LEA 0(%reg), %reg */
> +
> +	case 0x90: /* NOP */
> +		for (int i = 0; i < insn->prefixes.nbytes; i++) {
> +			if (insn->prefixes.bytes[i] == 0xf3) /* REP */
> +				return false; /* REP NOP -- PAUSE */
> +		}
> +		return true;
> +
> +	case 0xe9: /* JMP.d32 */
> +	case 0xeb: /* JMP.d8 */
> +		return insn->immediate.value == 0; /* JMP +0 */
> +
> +	default:
> +		return false;
> +	}
> +
> +	switch (insn->opcode.bytes[1]) {
> +	case 0x1f:
> +		return modrm_reg == 0; /* 0f 1f /0 -- NOPL */
> +
> +	default:
> +		return false;
> +	}
> +}

  reply	other threads:[~2025-09-05  8:38 UTC|newest]

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-20 11:21 [PATCHv6 perf/core 00/22] uprobes: Add support to optimize usdt probes on x86_64 Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 01/22] uprobes: Remove breakpoint in unapply_uprobe under mmap_write_lock Jiri Olsa
2025-08-25 10:25   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 02/22] uprobes: Rename arch_uretprobe_trampoline function Jiri Olsa
2025-08-25 10:25   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 03/22] uprobes: Make copy_from_page global Jiri Olsa
2025-08-25 10:25   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 04/22] uprobes: Add uprobe_write function Jiri Olsa
2025-08-25 10:25   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 05/22] uprobes: Add nbytes argument to uprobe_write Jiri Olsa
2025-08-25 10:25   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 06/22] uprobes: Add is_register argument to uprobe_write and uprobe_write_opcode Jiri Olsa
2025-08-25 10:25   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 07/22] uprobes: Add do_ref_ctr argument to uprobe_write function Jiri Olsa
2025-08-25 10:25   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 08/22] uprobes/x86: Add mapping for optimized uprobe trampolines Jiri Olsa
2025-08-19 14:53   ` Peter Zijlstra
2025-08-20 12:18     ` Jiri Olsa
2025-08-25 10:25   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 09/22] uprobes/x86: Add uprobe syscall to speed up uprobe Jiri Olsa
2025-07-20 11:38   ` Oleg Nesterov
2025-07-25 10:11   ` Masami Hiramatsu
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-09-03 18:24   ` [PATCHv6 perf/core 09/22] " Andrii Nakryiko
2025-09-03 20:56     ` Jiri Olsa
2025-09-03 21:01       ` Peter Zijlstra
2025-09-03 23:12         ` Andrii Nakryiko
2025-09-04  7:56           ` Jiri Olsa
2025-09-04  9:39             ` Jann Horn
2025-09-04 14:03               ` Jiri Olsa
2025-09-04 18:32                 ` Andrii Nakryiko
2025-09-05 10:46                   ` Jiri Olsa
2025-09-05 18:44                     ` Andrii Nakryiko
2025-09-04  8:13     ` Jiri Olsa
2025-09-04 18:27       ` nop5-optimized USDTs WAS: " Andrii Nakryiko
2025-09-04 20:35         ` Peter Zijlstra
2025-09-04 20:49           ` Andrii Nakryiko
2025-09-04 20:52             ` Peter Zijlstra
2025-09-04 21:44               ` Andrii Nakryiko
2025-09-04 21:56                 ` Peter Zijlstra
2025-09-04 21:58                   ` Peter Zijlstra
2025-09-05  8:24                     ` Peter Zijlstra
2025-09-05  8:38                       ` Peter Zijlstra [this message]
2025-09-10 14:30                       ` Andrii Nakryiko
2025-07-20 11:21 ` [PATCHv6 perf/core 10/22] uprobes/x86: Add support to optimize uprobes Jiri Olsa
2025-07-25 10:13   ` Masami Hiramatsu
2025-07-28 21:34     ` Jiri Olsa
2025-08-08 17:44       ` Jiri Olsa
2025-08-19 19:17       ` Peter Zijlstra
2025-08-20 12:19         ` Jiri Olsa
2025-08-19 19:15   ` Peter Zijlstra
2025-08-20 12:19     ` Jiri Olsa
2025-08-20 13:01       ` Peter Zijlstra
2025-08-20 12:30     ` Peter Zijlstra
2025-08-20 15:58       ` Edgecombe, Rick P
2025-08-20 17:12         ` Peter Zijlstra
2025-08-20 17:26           ` Edgecombe, Rick P
2025-08-20 17:43             ` Peter Zijlstra
2025-08-20 18:04               ` Edgecombe, Rick P
2025-08-20 21:38       ` Jiri Olsa
2025-09-03  6:48     ` Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 11/22] selftests/bpf: Import usdt.h from libbpf/usdt project Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 12/22] selftests/bpf: Reorg the uprobe_syscall test function Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 13/22] selftests/bpf: Rename uprobe_syscall_executed prog to test_uretprobe_multi Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 14/22] selftests/bpf: Add uprobe/usdt syscall tests Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 15/22] selftests/bpf: Add hit/attach/detach race optimized uprobe test Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 16/22] selftests/bpf: Add uprobe syscall sigill signal test Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 17/22] selftests/bpf: Add optimized usdt variant for basic usdt test Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 18/22] selftests/bpf: Add uprobe_regs_equal test Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 19/22] selftests/bpf: Change test_uretprobe_regs_change for uprobe and uretprobe Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 20/22] seccomp: passthrough uprobe systemcall without filtering Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv6 perf/core 21/22] selftests/seccomp: validate uprobe syscall passes through seccomp Jiri Olsa
2025-08-25 10:24   ` [tip: perf/core] " tip-bot2 for Jiri Olsa
2025-07-20 11:21 ` [PATCHv5 22/22] man2: Add uprobe syscall page 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=20250905083833.GR4068168@noisy.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=David.Laight@aculab.com \
    --cc=alan.maguire@oracle.com \
    --cc=andrii.nakryiko@gmail.com \
    --cc=andrii@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=haoluo@google.com \
    --cc=john.fastabend@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-trace-kernel@vger.kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=mingo@kernel.org \
    --cc=oleg@redhat.com \
    --cc=olsajiri@gmail.com \
    --cc=rostedt@goodmis.org \
    --cc=songliubraving@fb.com \
    --cc=thomas@t-8ch.de \
    --cc=x86@kernel.org \
    --cc=yhs@fb.com \
    /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

all inboxes | Powered by JetHome®