linux-kernel - Re: [PATCH perf/core 08/22] uprobes/x86: Add mapping for optimized uprobe trampolines

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: <aA-HQ3YfLz28MnhZ@krava>
Date: Mon, 28 Apr 2025 15:48:51 +0200
From: Jiri Olsa <olsajiri@...il.com>
To: Oleg Nesterov <oleg@...hat.com>
Cc: Peter Zijlstra <peterz@...radead.org>,
	Andrii Nakryiko <andrii@...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>,
	Masami Hiramatsu <mhiramat@...nel.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: [PATCH perf/core 08/22] uprobes/x86: Add mapping for optimized
 uprobe trampolines

On Sun, Apr 27, 2025 at 07:34:56PM +0200, Oleg Nesterov wrote:
> On 04/27, Oleg Nesterov wrote:
> >
> > On 04/21, Jiri Olsa wrote:
> > >
> > > +static unsigned long find_nearest_page(unsigned long vaddr)
> > > +{
> > > +	struct vm_area_struct *vma, *prev = NULL;
> > > +	unsigned long prev_vm_end = PAGE_SIZE;
> > > +	VMA_ITERATOR(vmi, current->mm, 0);
> > > +
> > > +	vma = vma_next(&vmi);
> > > +	while (vma) {
> > > +		if (prev)
> > > +			prev_vm_end = prev->vm_end;
> > > +		if (vma->vm_start - prev_vm_end  >= PAGE_SIZE) {
> > > +			if (is_reachable_by_call(prev_vm_end, vaddr))
> > > +				return prev_vm_end;
> > > +			if (is_reachable_by_call(vma->vm_start - PAGE_SIZE, vaddr))
> > > +				return vma->vm_start - PAGE_SIZE;
> > > +		}
> > > +		prev = vma;
> > > +		vma = vma_next(&vmi);
> > > +	}
> > > +
> > > +	return 0;
> > > +}
> >
> > This can be simplified afaics... We don't really need prev, and we can
> > use for_each_vma(),
> >
> > 	static unsigned long find_nearest_page(unsigned long vaddr)
> > 	{
> > 		struct vm_area_struct *vma;
> > 		unsigned long prev_vm_end = PAGE_SIZE;
> > 		VMA_ITERATOR(vmi, current->mm, 0);
> >
> > 		for_each_vma(vmi, vma) {
> > 			if (vma->vm_start - prev_vm_end  >= PAGE_SIZE) {
> > 				if (is_reachable_by_call(prev_vm_end, vaddr))
> > 					return prev_vm_end;
> > 				if (is_reachable_by_call(vma->vm_start - PAGE_SIZE, vaddr))
> > 					return vma->vm_start - PAGE_SIZE;
> > 			}
> > 			prev_vm_end = vma->vm_end;
> > 		}
> >
> > 		return 0;
> > 	}
> 
> Either way it doesn't look nice. If nothing else, we should respect
> vm_start/end_gap(vma).
> 
> Can't we do something like
> 
> 	struct vm_unmapped_area_info info = {};
> 
> 	info.length = PAGE_SIZE;
> 	info.low_limit  = vaddr - INT_MIN + 5;
> 	info.high_limit = vaddr + INT_MAX;
> 	
> 	info.flags = VM_UNMAPPED_AREA_TOPDOWN; // makes sense?

so this would return highest available space right? current code goes from
bottom now, not sure what's preffered

> 
> 	return vm_unmapped_area(&info);
> 
> instead ?

yes, I did not realize we could use this, looks better, will try that

thanks,
jirka