On Tue, Jul 11, 2017 at 8:32 AM, Kyle Huey wrote:
> On Tue, Jul 11, 2017 at 2:03 AM, Ingo Molnar wrote:
>>
>> * Kyle Huey wrote:
>>
>>> On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan
>>> wrote:
>>> > On Tue, Jul
On Tue, Jul 11, 2017 at 8:32 AM, Kyle Huey wrote:
> On Tue, Jul 11, 2017 at 2:03 AM, Ingo Molnar wrote:
>>
>> * Kyle Huey wrote:
>>
>>> On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan
>>> wrote:
>>> > On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
>>> >> Should any of those be moved
* Jin, Yao wrote:
> Could we provide 2 options in user space when enabling the event sampling?
>
> One option is for the use case like rr debugger which only cares the PMI
> interrupt but doesn't care the skid. The skid samples doesn't need to be
> dropped.
Since
* Jin, Yao wrote:
> Could we provide 2 options in user space when enabling the event sampling?
>
> One option is for the use case like rr debugger which only cares the PMI
> interrupt but doesn't care the skid. The skid samples doesn't need to be
> dropped.
Since it's an information leak,
On Tue, Jul 11, 2017 at 2:03 AM, Ingo Molnar wrote:
>
> * Kyle Huey wrote:
>
>> On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan
>> wrote:
>> > On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
>> >> Should
On Tue, Jul 11, 2017 at 2:03 AM, Ingo Molnar wrote:
>
> * Kyle Huey wrote:
>
>> On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan
>> wrote:
>> > On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
>> >> Should any of those be moved into the "should be dropped" pile?
>> >
>> > Why not be
On Tue, Jul 11, 2017 at 11:03:58AM +0200, Ingo Molnar wrote:
>
> * Kyle Huey wrote:
>
> > On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan
> > wrote:
> > > On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
> > >> Should any
On Tue, Jul 11, 2017 at 11:03:58AM +0200, Ingo Molnar wrote:
>
> * Kyle Huey wrote:
>
> > On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan
> > wrote:
> > > On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
> > >> Should any of those be moved into the "should be dropped" pile?
> > >
> > >
On 7/11/2017 5:03 PM, Ingo Molnar wrote:
* Kyle Huey wrote:
On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan wrote:
On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
Should any of those be moved into the "should be
On 7/11/2017 5:03 PM, Ingo Molnar wrote:
* Kyle Huey wrote:
On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan wrote:
On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
Should any of those be moved into the "should be dropped" pile?
Why not be conservative and clear every sample
* Kyle Huey wrote:
> On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan
> wrote:
> > On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
> >> Should any of those be moved into the "should be dropped" pile?
> >
> > Why not be
* Kyle Huey wrote:
> On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan
> wrote:
> > On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
> >> Should any of those be moved into the "should be dropped" pile?
> >
> > Why not be conservative and clear every sample you're not sure about?
> >
> >
On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan wrote:
> On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
>> Should any of those be moved into the "should be dropped" pile?
>
> Why not be conservative and clear every sample you're not sure about?
On Wed, Jul 5, 2017 at 10:07 PM, Robert O'Callahan wrote:
> On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
>> Should any of those be moved into the "should be dropped" pile?
>
> Why not be conservative and clear every sample you're not sure about?
>
> We'd appreciate a fix sooner rather
On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
> Should any of those be moved into the "should be dropped" pile?
Why not be conservative and clear every sample you're not sure about?
We'd appreciate a fix sooner rather than later here, since rr is
currently broken on
On Tue, Jul 4, 2017 at 3:21 AM, Mark Rutland wrote:
> Should any of those be moved into the "should be dropped" pile?
Why not be conservative and clear every sample you're not sure about?
We'd appreciate a fix sooner rather than later here, since rr is
currently broken on every stable Linux
On Tue, Jul 04, 2017 at 10:33:45AM +0100, Mark Rutland wrote:
> On Tue, Jul 04, 2017 at 11:03:13AM +0200, Peter Zijlstra wrote:
> > Faking data gets a wee bit tricky in how much data we need to clear
> > through, its not only IP, pretty much everything we get from the
> > interrupt context, like
On Tue, Jul 04, 2017 at 10:33:45AM +0100, Mark Rutland wrote:
> On Tue, Jul 04, 2017 at 11:03:13AM +0200, Peter Zijlstra wrote:
> > Faking data gets a wee bit tricky in how much data we need to clear
> > through, its not only IP, pretty much everything we get from the
> > interrupt context, like
* Peter Zijlstra wrote:
> On Thu, Jun 29, 2017 at 10:12:33AM +0200, Ingo Molnar wrote:
> >
> > * Mark Rutland wrote:
> >
> > > It still seems wrong to make up data, though.
> >
> > So what we have here is a hardware quirk: we asked for user-space
* Peter Zijlstra wrote:
> On Thu, Jun 29, 2017 at 10:12:33AM +0200, Ingo Molnar wrote:
> >
> > * Mark Rutland wrote:
> >
> > > It still seems wrong to make up data, though.
> >
> > So what we have here is a hardware quirk: we asked for user-space samples,
> > but
> > didn't get them and
On Tue, Jul 04, 2017 at 10:33:45AM +0100, Mark Rutland wrote:
> > That said, with a per-cpu event the TID sample value is indeed subject
> > to skid like you describe.
>
> For per-cpu events, does that matter? Those don't have TID filters in
> the first place, no?
eBPF can do all sorts I
On Tue, Jul 04, 2017 at 10:33:45AM +0100, Mark Rutland wrote:
> > That said, with a per-cpu event the TID sample value is indeed subject
> > to skid like you describe.
>
> For per-cpu events, does that matter? Those don't have TID filters in
> the first place, no?
eBPF can do all sorts I
On Tue, Jul 04, 2017 at 11:03:13AM +0200, Peter Zijlstra wrote:
> On Wed, Jun 28, 2017 at 03:55:07PM -0700, Kyle Huey wrote:
>
> > > Having thought about this some more, I think Vince does make a good
> > > point that throwing away samples is liable to break stuff, e.g. that
> > > which only
On Tue, Jul 04, 2017 at 11:03:13AM +0200, Peter Zijlstra wrote:
> On Wed, Jun 28, 2017 at 03:55:07PM -0700, Kyle Huey wrote:
>
> > > Having thought about this some more, I think Vince does make a good
> > > point that throwing away samples is liable to break stuff, e.g. that
> > > which only
On Thu, Jun 29, 2017 at 10:12:33AM +0200, Ingo Molnar wrote:
>
> * Mark Rutland wrote:
>
> > It still seems wrong to make up data, though.
>
> So what we have here is a hardware quirk: we asked for user-space samples,
> but
> didn't get them and we cannot expose the
On Thu, Jun 29, 2017 at 10:12:33AM +0200, Ingo Molnar wrote:
>
> * Mark Rutland wrote:
>
> > It still seems wrong to make up data, though.
>
> So what we have here is a hardware quirk: we asked for user-space samples,
> but
> didn't get them and we cannot expose the kernel-internal address.
On Wed, Jun 28, 2017 at 03:55:07PM -0700, Kyle Huey wrote:
> > Having thought about this some more, I think Vince does make a good
> > point that throwing away samples is liable to break stuff, e.g. that
> > which only relies on (non-sensitive) samples.
> >
> > It still seems wrong to make up
On Wed, Jun 28, 2017 at 03:55:07PM -0700, Kyle Huey wrote:
> > Having thought about this some more, I think Vince does make a good
> > point that throwing away samples is liable to break stuff, e.g. that
> > which only relies on (non-sensitive) samples.
> >
> > It still seems wrong to make up
On Wed, Jun 28, 2017 at 3:55 PM, Kyle Huey wrote:
> On Wed, Jun 28, 2017 at 10:49 AM, Mark Rutland wrote:
>> On Wed, Jun 28, 2017 at 09:48:27AM -0700, Kyle Huey wrote:
>>> On Wed, Jun 28, 2017 at 3:56 AM, Mark Rutland wrote:
>>> >
On Wed, Jun 28, 2017 at 3:55 PM, Kyle Huey wrote:
> On Wed, Jun 28, 2017 at 10:49 AM, Mark Rutland wrote:
>> On Wed, Jun 28, 2017 at 09:48:27AM -0700, Kyle Huey wrote:
>>> On Wed, Jun 28, 2017 at 3:56 AM, Mark Rutland wrote:
>>> > @@ -6101,6 +6116,12 @@ void perf_prepare_sample(struct
On 29.06.2017 11:13, Alexey Budankov wrote:
> Hi Folks,
>
> On 28.06.2017 16:07, Mark Rutland wrote:
>> On Wed, Jun 28, 2017 at 08:40:30AM -0400, Vince Weaver wrote:
>>> On Wed, 28 Jun 2017, Mark Rutland wrote:
>>>
On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
>>>
On 29.06.2017 11:13, Alexey Budankov wrote:
> Hi Folks,
>
> On 28.06.2017 16:07, Mark Rutland wrote:
>> On Wed, Jun 28, 2017 at 08:40:30AM -0400, Vince Weaver wrote:
>>> On Wed, 28 Jun 2017, Mark Rutland wrote:
>>>
On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
>>>
Hi Folks,
On 28.06.2017 16:07, Mark Rutland wrote:
> On Wed, Jun 28, 2017 at 08:40:30AM -0400, Vince Weaver wrote:
>> On Wed, 28 Jun 2017, Mark Rutland wrote:
>>
>>> On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
>>
>>> Instead of bailing out early in perf_event_overflow, we can
Hi Folks,
On 28.06.2017 16:07, Mark Rutland wrote:
> On Wed, Jun 28, 2017 at 08:40:30AM -0400, Vince Weaver wrote:
>> On Wed, 28 Jun 2017, Mark Rutland wrote:
>>
>>> On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
>>
>>> Instead of bailing out early in perf_event_overflow, we can
* Mark Rutland wrote:
> It still seems wrong to make up data, though.
So what we have here is a hardware quirk: we asked for user-space samples, but
didn't get them and we cannot expose the kernel-internal address.
The question is, how do we handle the hardware quirk.
* Mark Rutland wrote:
> It still seems wrong to make up data, though.
So what we have here is a hardware quirk: we asked for user-space samples, but
didn't get them and we cannot expose the kernel-internal address.
The question is, how do we handle the hardware quirk. Since we cannot fix the
On 6/29/2017 6:55 AM, Kyle Huey wrote:
On Wed, Jun 28, 2017 at 10:49 AM, Mark Rutland wrote:
On Wed, Jun 28, 2017 at 09:48:27AM -0700, Kyle Huey wrote:
On Wed, Jun 28, 2017 at 3:56 AM, Mark Rutland wrote:
@@ -6101,6 +6116,12 @@ void
On 6/29/2017 6:55 AM, Kyle Huey wrote:
On Wed, Jun 28, 2017 at 10:49 AM, Mark Rutland wrote:
On Wed, Jun 28, 2017 at 09:48:27AM -0700, Kyle Huey wrote:
On Wed, Jun 28, 2017 at 3:56 AM, Mark Rutland wrote:
@@ -6101,6 +6116,12 @@ void perf_prepare_sample(struct perf_event_header
*header,
On Wed, Jun 28, 2017 at 10:49 AM, Mark Rutland wrote:
> On Wed, Jun 28, 2017 at 09:48:27AM -0700, Kyle Huey wrote:
>> On Wed, Jun 28, 2017 at 3:56 AM, Mark Rutland wrote:
>> > @@ -6101,6 +6116,12 @@ void perf_prepare_sample(struct perf_event_header
>>
On Wed, Jun 28, 2017 at 10:49 AM, Mark Rutland wrote:
> On Wed, Jun 28, 2017 at 09:48:27AM -0700, Kyle Huey wrote:
>> On Wed, Jun 28, 2017 at 3:56 AM, Mark Rutland wrote:
>> > @@ -6101,6 +6116,12 @@ void perf_prepare_sample(struct perf_event_header
>> > *header,
>> > struct
On Wed, Jun 28, 2017 at 09:48:27AM -0700, Kyle Huey wrote:
> On Wed, Jun 28, 2017 at 3:56 AM, Mark Rutland wrote:
> > @@ -6101,6 +6116,12 @@ void perf_prepare_sample(struct perf_event_header
> > *header,
> > struct perf_output_handle handle;
> > struct
On Wed, Jun 28, 2017 at 09:48:27AM -0700, Kyle Huey wrote:
> On Wed, Jun 28, 2017 at 3:56 AM, Mark Rutland wrote:
> > @@ -6101,6 +6116,12 @@ void perf_prepare_sample(struct perf_event_header
> > *header,
> > struct perf_output_handle handle;
> > struct perf_event_header header;
>
On Wed, Jun 28, 2017 at 3:56 AM, Mark Rutland wrote:
> On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
>> On Tue, Jun 27, 2017 at 09:51:00PM -0700, Kyle Huey wrote:
>
>> As we're trying to avoid smapling state, I think we can move the check
>> into
On Wed, Jun 28, 2017 at 3:56 AM, Mark Rutland wrote:
> On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
>> On Tue, Jun 27, 2017 at 09:51:00PM -0700, Kyle Huey wrote:
>
>> As we're trying to avoid smapling state, I think we can move the check
>> into perf_prepare_sample() or
On Wed, Jun 28, 2017 at 08:40:30AM -0400, Vince Weaver wrote:
> On Wed, 28 Jun 2017, Mark Rutland wrote:
>
> > On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
>
> > Instead of bailing out early in perf_event_overflow, we can bail prior
> > to performing the actual sampling in
On Wed, Jun 28, 2017 at 08:40:30AM -0400, Vince Weaver wrote:
> On Wed, 28 Jun 2017, Mark Rutland wrote:
>
> > On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
>
> > Instead of bailing out early in perf_event_overflow, we can bail prior
> > to performing the actual sampling in
On Wed, 28 Jun 2017, Mark Rutland wrote:
> On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
> Instead of bailing out early in perf_event_overflow, we can bail prior
> to performing the actual sampling in __perf_event_output(). This avoids
> the information leak, but preserves the
On Wed, 28 Jun 2017, Mark Rutland wrote:
> On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
> Instead of bailing out early in perf_event_overflow, we can bail prior
> to performing the actual sampling in __perf_event_output(). This avoids
> the information leak, but preserves the
On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
> On Tue, Jun 27, 2017 at 09:51:00PM -0700, Kyle Huey wrote:
> As we're trying to avoid smapling state, I think we can move the check
> into perf_prepare_sample() or __perf_event_output(), where that state is
> actually sampled. I'll
On Wed, Jun 28, 2017 at 11:12:48AM +0100, Mark Rutland wrote:
> On Tue, Jun 27, 2017 at 09:51:00PM -0700, Kyle Huey wrote:
> As we're trying to avoid smapling state, I think we can move the check
> into perf_prepare_sample() or __perf_event_output(), where that state is
> actually sampled. I'll
50 matches
Mail list logo