Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-24 Thread Andy Lutomirski
On Thu, May 24, 2018 at 7:37 AM Alexey Budankov < alexey.budan...@linux.intel.com> wrote: > Hi, > On 23.05.2018 16:09, Peter Zijlstra wrote: > > On Wed, May 23, 2018 at 01:06:58PM +0300, Alexey Budankov wrote: > > > >> Is the patch ready to be up streamed now? > > > > Please post a new one where

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-24 Thread Alexey Budankov
Hi, On 23.05.2018 16:09, Peter Zijlstra wrote: > On Wed, May 23, 2018 at 01:06:58PM +0300, Alexey Budankov wrote: > >> Is the patch ready to be up streamed now? > > Please post a new one where you modify the comment about the syscalls > not saving registers and ideally find the commit that made

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-23 Thread Peter Zijlstra
On Wed, May 23, 2018 at 01:06:58PM +0300, Alexey Budankov wrote: > Is the patch ready to be up streamed now? Please post a new one where you modify the comment about the syscalls not saving registers and ideally find the commit that made it so. Also; I think Andy would appreciate a comment near

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-23 Thread Alexey Budankov
Hi Peter, On 10.05.2018 13:14, Peter Zijlstra wrote: > On Thu, May 10, 2018 at 12:42:38PM +0300, Alexey Budankov wrote: >>> The Changelog needs to state that user_regs->bp is in fact valid and >> >> That actually was tested on binaries compiled without and with BP exposed >> and in the latter cas

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-21 Thread Alexey Budankov
Hi, On 21.05.2018 20:23, Andy Lutomirski wrote: > >> On May 21, 2018, at 9:51 AM, Alexey Budankov >> wrote: >> >> >> Hi Andy, >>> On 21.05.2018 17:14, Andy Lutomirski wrote: >>> On May 21, 2018, at 5:44 AM, Alexey Budankov wrote: Hi Peter, > On 10.05.2018 13:14, P

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-21 Thread Andy Lutomirski
> On May 21, 2018, at 9:51 AM, Alexey Budankov > wrote: > > > Hi Andy, >> On 21.05.2018 17:14, Andy Lutomirski wrote: >> >>> On May 21, 2018, at 5:44 AM, Alexey Budankov >>> wrote: >>> >>> Hi Peter, >>> On 10.05.2018 13:14, Peter Zijlstra wrote: On Thu, May 10, 2018 at 12:42:38P

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-21 Thread Alexey Budankov
Hi Andy, On 21.05.2018 17:14, Andy Lutomirski wrote: > >> On May 21, 2018, at 5:44 AM, Alexey Budankov >> wrote: >> >> Hi Peter, >> >>> On 10.05.2018 13:14, Peter Zijlstra wrote: >>> On Thu, May 10, 2018 at 12:42:38PM +0300, Alexey Budankov wrote: > The Changelog needs to state that user_re

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-21 Thread Andy Lutomirski
> On May 21, 2018, at 5:44 AM, Alexey Budankov > wrote: > > Hi Peter, > >> On 10.05.2018 13:14, Peter Zijlstra wrote: >> On Thu, May 10, 2018 at 12:42:38PM +0300, Alexey Budankov wrote: The Changelog needs to state that user_regs->bp is in fact valid and >>> >>> That actually was tested

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-21 Thread Alexey Budankov
Hi Peter, On 10.05.2018 13:14, Peter Zijlstra wrote: > On Thu, May 10, 2018 at 12:42:38PM +0300, Alexey Budankov wrote: >>> The Changelog needs to state that user_regs->bp is in fact valid and >> >> That actually was tested on binaries compiled without and with BP exposed >> and in the latter cas

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-18 Thread Alexey Budankov
Hi, On 16.05.2018 11:42, Alexey Budankov wrote: > Hi, > On 15.05.2018 19:30, Andy Lutomirski wrote: >> >>> On May 15, 2018, at 1:08 AM, Alexey Budankov >>> wrote: >>> >>> >>> Hi Andy, >>> On 09.05.2018 17:54, Peter Zijlstra wrote: > On Tue, May 08, 2018 at 06:21:36PM +0300, Alexey Budan

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-16 Thread Alexey Budankov
Hi, On 15.05.2018 19:30, Andy Lutomirski wrote: > >> On May 15, 2018, at 1:08 AM, Alexey Budankov >> wrote: >> >> >> Hi Andy, >> >>> On 09.05.2018 17:54, Peter Zijlstra wrote: On Tue, May 08, 2018 at 06:21:36PM +0300, Alexey Budankov wrote: Store user space frame-pointer value (BP

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-15 Thread Andy Lutomirski
> On May 15, 2018, at 1:08 AM, Alexey Budankov > wrote: > > > Hi Andy, > >> On 09.05.2018 17:54, Peter Zijlstra wrote: >>> On Tue, May 08, 2018 at 06:21:36PM +0300, Alexey Budankov wrote: >>> >>> Store user space frame-pointer value (BP register) into Perf trace >>> on a sample for a proces

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-15 Thread Alexey Budankov
Hi Andy, On 09.05.2018 17:54, Peter Zijlstra wrote: > On Tue, May 08, 2018 at 06:21:36PM +0300, Alexey Budankov wrote: >> >> Store user space frame-pointer value (BP register) into Perf trace >> on a sample for a process so the value becomes available when >> unwinding call stacks for functions

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-10 Thread Alexey Budankov
Hi, On 10.05.2018 13:14, Peter Zijlstra wrote: > On Thu, May 10, 2018 at 12:42:38PM +0300, Alexey Budankov wrote: >>> The Changelog needs to state that user_regs->bp is in fact valid and >> >> That actually was tested on binaries compiled without and with BP exposed >> and in the latter case prov

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-10 Thread Peter Zijlstra
On Thu, May 10, 2018 at 12:42:38PM +0300, Alexey Budankov wrote: > > The Changelog needs to state that user_regs->bp is in fact valid and > > That actually was tested on binaries compiled without and with BP exposed > and in the latter case proved the value of that change. Mostly works is not th

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-10 Thread Alexey Budankov
Hi, On 09.05.2018 17:54, Peter Zijlstra wrote: > On Tue, May 08, 2018 at 06:21:36PM +0300, Alexey Budankov wrote: >> >> Store user space frame-pointer value (BP register) into Perf trace >> on a sample for a process so the value becomes available when >> unwinding call stacks for functions gaini

Re: [PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-09 Thread Peter Zijlstra
On Tue, May 08, 2018 at 06:21:36PM +0300, Alexey Budankov wrote: > > Store user space frame-pointer value (BP register) into Perf trace > on a sample for a process so the value becomes available when > unwinding call stacks for functions gaining event samples. > > Signed-off-by: Alexey Budankov

[PATCH v2]: perf/x86: store user space frame-pointer value on a sample

2018-05-08 Thread Alexey Budankov
Store user space frame-pointer value (BP register) into Perf trace on a sample for a process so the value becomes available when unwinding call stacks for functions gaining event samples. Signed-off-by: Alexey Budankov --- arch/x86/kernel/perf_regs.c | 8 +++- 1 file changed, 7 insertions