Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 13 Sep 2021 16:53:31 -0300
From:   Arnaldo Carvalho de Melo <acme@kernel.org>
To:     "Jin, Yao" <yao.jin@linux.intel.com>
Cc:     Ravi Bangoria <ravi.bangoria@amd.com>, mark.rutland@arm.com,
        alexander.shishkin@linux.intel.com, jolsa@redhat.com,
        namhyung@kernel.org, kim.phillips@amd.com,
        linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 1/2] perf annotate: Fix fused instr logic for assembly
 functions
Message-ID: <YT+sOxJeEplSm2pl@kernel.org>
References: <20210911043854.8373-1-ravi.bangoria@amd.com>
 <YTz9nfyXOSXDdpSE@kernel.org>
 <211bb79d-80ff-e9b6-1851-1aaed987301d@linux.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <211bb79d-80ff-e9b6-1851-1aaed987301d@linux.intel.com>
Precedence: bulk

Em Mon, Sep 13, 2021 at 09:54:00AM +0800, Jin, Yao escreveu:
> Hi Arnaldo, Ravi
> 
> On 9/12/2021 3:03 AM, Arnaldo Carvalho de Melo wrote:
> > Em Sat, Sep 11, 2021 at 10:08:53AM +0530, Ravi Bangoria escreveu:
> > > Some x86 microarchitectures fuse a subset of cmp/test/ALU instructions
> > > with branch instructions, and thus perf annotate highlight such valid
> > > pairs as fused.
> > 
> > Jin, are you ok with this? Can I have your reviewed-by?
> > 
> > - Arnaldo
> 
> Oh, my original patch could only handle the case like:
> 
> cmp xxx
> je  aaa
> 
> But it didn't consider Ravi's case something like:
> 
> cmp xxx
> cmp yyy
> je  aaa
> je  bbb
> 
> Thanks for Ravi fixing this issue! Backward searching is probably a better solution.
> 
> Frankly I can't reproduce Ravi's case, but for my test suite, Ravi's patch works as well.
> 
> Reviewed-by: Jin Yao <yao.jin@linux.intel.com>

Thanks, applied.

- Arnaldo