linux-kernel - Re: [PATCH bpf-next 08/13] uprobes/x86: Add support to optimize uprobes

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20241213104907.GA35539@noisy.programming.kicks-ass.net>
Date: Fri, 13 Dec 2024 11:49:07 +0100
From: Peter Zijlstra <peterz@...radead.org>
To: Jiri Olsa <jolsa@...nel.org>
Cc: Oleg Nesterov <oleg@...hat.com>, Andrii Nakryiko <andrii@...nel.org>,
	bpf@...r.kernel.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>,
	Masami Hiramatsu <mhiramat@...nel.org>,
	Alan Maguire <alan.maguire@...cle.com>,
	linux-kernel@...r.kernel.org, linux-trace-kernel@...r.kernel.org
Subject: Re: [PATCH bpf-next 08/13] uprobes/x86: Add support to optimize
 uprobes

On Wed, Dec 11, 2024 at 02:33:57PM +0100, Jiri Olsa wrote:
> diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
> index cdea97f8cd39..b2420eeee23a 100644
> --- a/arch/x86/kernel/uprobes.c
> +++ b/arch/x86/kernel/uprobes.c

> @@ -1306,3 +1339,132 @@ bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
>  	else
>  		return regs->sp <= ret->stack;
>  }
> +
> +int arch_uprobe_verify_opcode(struct arch_uprobe *auprobe, struct page *page,
> +			      unsigned long vaddr, uprobe_opcode_t *new_opcode,
> +			      int nbytes)
> +{
> +	uprobe_opcode_t old_opcode[5];
> +	bool is_call, is_swbp, is_nop5;
> +
> +	if (!test_bit(ARCH_UPROBE_FLAG_CAN_OPTIMIZE, &auprobe->flags))
> +		return uprobe_verify_opcode(page, vaddr, new_opcode);
> +
> +	/*
> +	 * The ARCH_UPROBE_FLAG_CAN_OPTIMIZE flag guarantees the following
> +	 * 5 bytes read won't cross the page boundary.
> +	 */
> +	uprobe_copy_from_page(page, vaddr, (uprobe_opcode_t *) &old_opcode, 5);
> +	is_call = is_call_insn((uprobe_opcode_t *) &old_opcode);
> +	is_swbp = is_swbp_insn((uprobe_opcode_t *) &old_opcode);
> +	is_nop5 = is_nop5_insn((uprobe_opcode_t *) &old_opcode);
> +
> +	/*
> +	 * We allow following trasitions for optimized uprobes:
> +	 *
> +	 *   nop5 -> swbp -> call
> +	 *   ||      |       |
> +	 *   |'--<---'       |
> +	 *   '---<-----------'
> +	 *
> +	 * We return 1 to ack the write, 0 to do nothing, -1 to fail write.
> +	 *
> +	 * If the current opcode (old_opcode) has already desired value,
> +	 * we do nothing, because we are racing with another thread doing
> +	 * the update.
> +	 */
> +	switch (nbytes) {
> +	case 5:
> +		if (is_call_insn(new_opcode)) {
> +			if (is_swbp)
> +				return 1;
> +			if (is_call && !memcmp(new_opcode, &old_opcode, 5))
> +				return 0;
> +		} else {
> +			if (is_call || is_swbp)
> +				return 1;
> +			if (is_nop5)
> +				return 0;
> +		}
> +		break;
> +	case 1:
> +		if (is_swbp_insn(new_opcode)) {
> +			if (is_nop5)
> +				return 1;
> +			if (is_swbp || is_call)
> +				return 0;
> +		} else {
> +			if (is_swbp || is_call)
> +				return 1;
> +			if (is_nop5)
> +				return 0;
> +		}
> +	}
> +	return -1;
> +}
> +
> +bool arch_uprobe_is_register(uprobe_opcode_t *insn, int nbytes)
> +{
> +	return nbytes == 5 ? is_call_insn(insn) : is_swbp_insn(insn);
> +}
> +
> +static void __arch_uprobe_optimize(struct arch_uprobe *auprobe, struct mm_struct *mm,
> +				   unsigned long vaddr)
> +{
> +	struct uprobe_trampoline *tramp;
> +	char call[5];
> +
> +	tramp = uprobe_trampoline_get(vaddr);
> +	if (!tramp)
> +		goto fail;
> +
> +	relative_call(call, (void *) vaddr, (void *) tramp->vaddr);
> +	if (uprobe_write_opcode(auprobe, mm, vaddr, call, 5))
> +		goto fail;
> +
> +	set_bit(ARCH_UPROBE_FLAG_OPTIMIZED, &auprobe->flags);
> +	return;
> +
> +fail:
> +	/* Once we fail we never try again. */
> +	clear_bit(ARCH_UPROBE_FLAG_CAN_OPTIMIZE, &auprobe->flags);
> +	uprobe_trampoline_put(tramp);
> +}
> +
> +static bool should_optimize(struct arch_uprobe *auprobe)
> +{
> +	if (!test_bit(ARCH_UPROBE_FLAG_CAN_OPTIMIZE, &auprobe->flags))
> +		return false;
> +	if (test_bit(ARCH_UPROBE_FLAG_OPTIMIZED, &auprobe->flags))
> +		return false;
> +	return true;
> +}
> +
> +void arch_uprobe_optimize(struct arch_uprobe *auprobe, unsigned long vaddr)
> +{
> +	struct mm_struct *mm = current->mm;
> +
> +	if (!should_optimize(auprobe))
> +		return;
> +
> +	mmap_write_lock(mm);
> +	if (should_optimize(auprobe))
> +		__arch_uprobe_optimize(auprobe, mm, vaddr);
> +	mmap_write_unlock(mm);
> +}
> +
> +int set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
> +{
> +	uprobe_opcode_t *insn = (uprobe_opcode_t *) auprobe->insn;
> +
> +	if (test_bit(ARCH_UPROBE_FLAG_OPTIMIZED, &auprobe->flags))
> +		return uprobe_write_opcode(auprobe, mm, vaddr, insn, 5);
> +
> +	return uprobe_write_opcode(auprobe, mm, vaddr, insn, UPROBE_SWBP_INSN_SIZE);
> +}
> +
> +bool arch_uprobe_is_callable(unsigned long vtramp, unsigned long vaddr)
> +{
> +	long delta = (long)(vaddr + 5 - vtramp);
> +	return delta >= INT_MIN && delta <= INT_MAX;
> +}

All this code is useless on 32bit, right?