linux-kernel - Re: [PATCH 2/3] perf tools: allow user to specify hardware breakpoint bp

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] [day] [month] [year] [list]

Date:	Sun, 28 Apr 2013 18:12:45 +0200
From:	Oleg Nesterov <oleg@...hat.com>
To:	"H. Peter Anvin" <hpa@...or.com>
Cc:	Jacob Shin <jacob.shin@....com>, Ingo Molnar <mingo@...hat.com>,
	Frederic Weisbecker <fweisbec@...il.com>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Arnaldo Carvalho de Melo <acme@...stprotocols.net>,
	Thomas Gleixner <tglx@...utronix.de>, x86@...nel.org,
	Stephane Eranian <eranian@...gle.com>,
	Jiri Olsa <jolsa@...hat.com>, linux-kernel@...r.kernel.org,
	Will Deacon <will.deacon@....com>
Subject: Re: [PATCH 2/3] perf tools: allow user to specify hardware
	breakpoint bp_len

On 04/27, H. Peter Anvin wrote:
>
> On 04/27/2013 09:58 AM, Oleg Nesterov wrote:
> >
> > Stupid question... So X86_FEATURE_BPEXT only works for r/w? I mean, it
> > doesn't allow to specify the mask for an execute breakpoint?
>
> x86 execute breakpoints in general are only a single byte, which has to
> be the first byte of the instruction.

OK, thanks, but this new X86_FEATURE_BPEXT allows to specify the range
even for HW_BREAKPOINT_X... But lets ignore this series for the moment.

If execute breakpoints are only a single byte, then why
arch_build_bp_info() requires ->bp_len = sizeof(long) but not 1?

And note that it sets info->len = X86_BREAKPOINT_LEN_X. The comment says

	x86 inst breakpoints need to have a specific undefined len

but despite its "special" name LEN_X is simply LEN_1, and other code
relies on this fact.

And, otoh, ptrace requires DR_LEN_1. Then arch_bp_generic_fields()
translates this into "gen_len = sizeof(long)" for validate. Which
is translated to LEN_1 later.

This looks confusing, imho. And imho X86_BREAKPOINT_LEN_X should die...

But I guess we can't change arch_build_bp_info() to require bp_len = 1,
this can break userspace...

And it is not clear to me how we can change this code to support a
range for the execute breakpoints, perhaps something like below.

Oleg.

--- x/arch/x86/kernel/hw_breakpoint.c
+++ x/arch/x86/kernel/hw_breakpoint.c
@@ -270,10 +270,11 @@ static int arch_build_bp_info(struct per
 		 * But we still need to check userspace is not trying to setup
 		 * an unsupported length, to get a range breakpoint for example.
 		 */
-		if (bp->attr.bp_len == sizeof(long)) {
-			info->len = X86_BREAKPOINT_LEN_X;
-			return 0;
-		}
+		if (bp->attr.bp_len == sizeof(long))
+			bp->attr.bp_len = HW_BREAKPOINT_LEN_1;
+		else if (!cpu_has_bpext)
+			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/