Re: [PATCH 2/3] perf tools: allow user to specify hardwarebreakpoint bp_len

From: Oleg Nesterov
Date: Sun Apr 28 2013 - 12:16:24 EST

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.


--- 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;
return -EINVAL;

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at