From: Michael Neuling <mikey@neuling.org> To: Peter Zijlstra <peterz@infradead.org> Cc: anshuman Stephane Eranian <eranian@google.com>, Ingo Molnar <mingo@kernel.org>, LKML <linux-kernel@vger.kernel.org>, "ak@linux.intel.com" <ak@linux.intel.com>, Michael Ellerman <michael@ellerman.id.au>, "benh@kernel.crashing.org" <benh@kernel.crashing.org>, Linux PPC dev <linuxppc-dev@ozlabs.org> Subject: Re: [PATCH 3/3] perf, x86, lbr: Demand proper privileges for PERF_SAMPLE_BRANCH_KERNEL Date: Tue, 21 May 2013 15:41:35 +1000 [thread overview] Message-ID: <10224.1369114895@ale.ozlabs.ibm.com> (raw) In-Reply-To: <20130517111232.GE5162@dyad.programming.kicks-ass.net> Peter Zijlstra <peterz@infradead.org> wrote: > On Thu, May 16, 2013 at 05:36:11PM +0200, Stephane Eranian wrote: > > On Thu, May 16, 2013 at 1:16 PM, Peter Zijlstra <peterz@infradead.org> wrote: > > > On Thu, May 16, 2013 at 08:15:17PM +1000, Michael Neuling wrote: > > >> Peter, > > >> > > >> BTW PowerPC also has the ability to filter on conditional branches. Any > > >> chance we could add something like the follow to perf also? > > >> > > > > > > I don't see an immediate problem with that except that we on x86 need to > > > implement that in the software filter. Stephane do you see any > > > fundamental issue with that? > > > > > On X86, the LBR cannot filter on conditional in HW. Thus as Peter said, it would > > have to be done in SW. I did not add that because I think those branches are > > not necessarily useful for tools. > > Wouldn't it be mostly conditional branches that are the primary control flow > and can get predicted wrong? I mean, I'm sure someone will miss-predict an > unconditional branch but its not like we care about people with such > afflictions do we? > > Anyway, since PPC people thought it worth baking into hardware, presumably they > have a compelling use case. Mikey could you see if you can retrieve that from > someone in the know? It might be interesting. > > Also, it looks like its trivial to add to x86, you seem to have already done > all the hard work by having X86_BR_JCC. > > The only missing piece would be: Peter, Can we add your signed-off-by on this? We are cleaning up our series for conditional branches and would like to add this as part of the post. Mikey > > --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c > +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c > @@ -337,6 +337,10 @@ static int intel_pmu_setup_sw_lbr_filter > > if (br_type & PERF_SAMPLE_BRANCH_IND_CALL) > mask |= X86_BR_IND_CALL; > + > + if (br_type & PERF_SAMPLE_BRANCH_CONDITIONAL) > + mask |= X86_BR_JCC; > + > /* > * stash actual user request into reg, it may > * be used by fixup code for some CPU >
WARNING: multiple messages have this Message-ID (diff)
From: Michael Neuling <mikey@neuling.org> To: Peter Zijlstra <peterz@infradead.org> Cc: "ak@linux.intel.com" <ak@linux.intel.com>, LKML <linux-kernel@vger.kernel.org>, anshuman Stephane Eranian <eranian@google.com>, Linux PPC dev <linuxppc-dev@ozlabs.org>, Ingo Molnar <mingo@kernel.org> Subject: Re: [PATCH 3/3] perf, x86, lbr: Demand proper privileges for PERF_SAMPLE_BRANCH_KERNEL Date: Tue, 21 May 2013 15:41:35 +1000 [thread overview] Message-ID: <10224.1369114895@ale.ozlabs.ibm.com> (raw) In-Reply-To: <20130517111232.GE5162@dyad.programming.kicks-ass.net> Peter Zijlstra <peterz@infradead.org> wrote: > On Thu, May 16, 2013 at 05:36:11PM +0200, Stephane Eranian wrote: > > On Thu, May 16, 2013 at 1:16 PM, Peter Zijlstra <peterz@infradead.org> wrote: > > > On Thu, May 16, 2013 at 08:15:17PM +1000, Michael Neuling wrote: > > >> Peter, > > >> > > >> BTW PowerPC also has the ability to filter on conditional branches. Any > > >> chance we could add something like the follow to perf also? > > >> > > > > > > I don't see an immediate problem with that except that we on x86 need to > > > implement that in the software filter. Stephane do you see any > > > fundamental issue with that? > > > > > On X86, the LBR cannot filter on conditional in HW. Thus as Peter said, it would > > have to be done in SW. I did not add that because I think those branches are > > not necessarily useful for tools. > > Wouldn't it be mostly conditional branches that are the primary control flow > and can get predicted wrong? I mean, I'm sure someone will miss-predict an > unconditional branch but its not like we care about people with such > afflictions do we? > > Anyway, since PPC people thought it worth baking into hardware, presumably they > have a compelling use case. Mikey could you see if you can retrieve that from > someone in the know? It might be interesting. > > Also, it looks like its trivial to add to x86, you seem to have already done > all the hard work by having X86_BR_JCC. > > The only missing piece would be: Peter, Can we add your signed-off-by on this? We are cleaning up our series for conditional branches and would like to add this as part of the post. Mikey > > --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c > +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c > @@ -337,6 +337,10 @@ static int intel_pmu_setup_sw_lbr_filter > > if (br_type & PERF_SAMPLE_BRANCH_IND_CALL) > mask |= X86_BR_IND_CALL; > + > + if (br_type & PERF_SAMPLE_BRANCH_CONDITIONAL) > + mask |= X86_BR_JCC; > + > /* > * stash actual user request into reg, it may > * be used by fixup code for some CPU >
next prev parent reply other threads:[~2013-05-21 5:41 UTC|newest] Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top 2013-05-03 12:11 [PATCH 0/3] Various perf patches Peter Zijlstra 2013-05-03 12:11 ` [PATCH 1/3] perf, x86: Blacklist all MEM_*_RETIRED events for IVB Peter Zijlstra 2013-05-03 14:35 ` Andi Kleen 2013-05-03 17:00 ` Peter Zijlstra 2013-05-15 14:20 ` Stephane Eranian 2013-05-15 16:51 ` Peter Zijlstra 2013-05-16 15:42 ` Stephane Eranian 2013-05-16 16:07 ` Andi Kleen 2013-05-16 16:26 ` Stephane Eranian 2013-05-04 8:20 ` [tip:perf/urgent] perf/x86: Blacklist all MEM_*_RETIRED events for Ivy Bridge tip-bot for Peter Zijlstra 2013-05-03 12:11 ` [PATCH 2/3] perf, x86, lbr: Fix LBR filter Peter Zijlstra 2013-05-03 14:34 ` Andi Kleen 2013-05-04 6:34 ` Ingo Molnar 2013-05-04 8:21 ` [tip:perf/urgent] perf/x86/intel/lbr: " tip-bot for Peter Zijlstra 2013-05-03 12:11 ` [PATCH 3/3] perf, x86, lbr: Demand proper privileges for PERF_SAMPLE_BRANCH_KERNEL Peter Zijlstra 2013-05-03 14:41 ` Andi Kleen 2013-05-04 8:22 ` [tip:perf/urgent] perf/x86/intel/lbr: " tip-bot for Peter Zijlstra 2013-05-04 11:19 ` Borislav Petkov 2013-05-05 9:05 ` Ingo Molnar 2013-05-06 8:07 ` Peter Zijlstra 2013-05-06 9:42 ` Ingo Molnar 2013-05-15 13:37 ` [PATCH 3/3] perf, x86, lbr: " Stephane Eranian 2013-05-15 14:30 ` Peter Zijlstra 2013-05-16 9:09 ` Peter Zijlstra 2013-05-16 9:17 ` Peter Zijlstra 2013-05-16 10:09 ` Michael Neuling 2013-05-16 10:09 ` Michael Neuling 2013-05-16 10:15 ` Michael Neuling 2013-05-16 10:15 ` Michael Neuling 2013-05-16 11:16 ` Peter Zijlstra 2013-05-16 11:16 ` Peter Zijlstra 2013-05-16 15:36 ` Stephane Eranian 2013-05-16 15:36 ` Stephane Eranian 2013-05-17 11:12 ` Peter Zijlstra 2013-05-17 11:12 ` Peter Zijlstra 2013-05-17 11:32 ` Michael Neuling 2013-05-17 11:32 ` Michael Neuling 2013-05-17 11:39 ` Peter Zijlstra 2013-05-17 11:39 ` Peter Zijlstra 2013-05-17 21:39 ` Stephane Eranian 2013-05-17 21:39 ` Stephane Eranian 2013-05-17 22:14 ` Michael Neuling 2013-05-17 22:14 ` Michael Neuling 2013-05-17 22:59 ` Stephane Eranian 2013-05-17 22:59 ` Stephane Eranian 2013-05-21 5:41 ` Michael Neuling [this message] 2013-05-21 5:41 ` Michael Neuling 2013-05-21 8:50 ` Peter Zijlstra 2013-05-21 8:50 ` Peter Zijlstra 2013-05-21 13:46 ` Stephane Eranian 2013-05-21 13:46 ` Stephane Eranian 2013-05-21 13:55 ` Stephane Eranian 2013-05-21 13:55 ` Stephane Eranian 2013-05-22 6:43 ` Anshuman Khandual 2013-05-22 12:23 ` Stephane Eranian 2013-05-22 14:51 ` Anshuman Khandual
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=10224.1369114895@ale.ozlabs.ibm.com \ --to=mikey@neuling.org \ --cc=ak@linux.intel.com \ --cc=benh@kernel.crashing.org \ --cc=eranian@google.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linuxppc-dev@ozlabs.org \ --cc=michael@ellerman.id.au \ --cc=mingo@kernel.org \ --cc=peterz@infradead.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.