Re: [RESEND PATCH V5 1/2] perf/core: Add new branch sample type for HW index of raw branch records

[Liang, Kan]

On 1/20/2020 3:24 PM, Peter Zijlstra wrote:
> On Mon, Jan 20, 2020 at 11:50:59AM -0500, Liang, Kan wrote:
> > On 1/20/2020 4:23 AM, Peter Zijlstra wrote:
> > > On Thu, Jan 16, 2020 at 07:57:56AM -0800, kan.liang@xxxxxxxxxxxxxxx wrote:
> > >
> > > >    struct perf_branch_stack {
> > > >    	__u64				nr;
> > > > +	__u64				hw_idx;
> > > >    	struct perf_branch_entry	entries[0];
> > > >    };
> > >
> > > The above and below order doesn't match.
> > >
> > > > @@ -849,7 +853,11 @@ enum perf_event_type {
> > > >    	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
> > > >    	 *
> > > >    	 *	{ u64                   nr;
> > > > -	 *        { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
> > > > +	 *        { u64 from, to, flags } lbr[nr];
> > > > +	 *
> > > > +	 *        # only available if PERF_SAMPLE_BRANCH_HW_INDEX is set
> > > > +	 *        u64			hw_idx;
> > > > +	 *      } && PERF_SAMPLE_BRANCH_STACK
> > >
> > > That wants to be written as:
> > >
> > > 		{ u64			nr;
> > > 		  { u64 from, to, flags; } entries[nr];
> > > 		  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
> > > 		} && PERF_SAMPLE_BRANCH_STACK
> > >
> > > But the big question is; why isn't it:
> > >
> > > 		{ u64			nr;
> > > 		  { u64	hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
> > > 		  { u64 from, to, flags; } entries[nr];
> > > 		} && PERF_SAMPLE_BRANCH_STACK
> > >
> > > to match the struct perf_branch_stack order. Having that variable sized
> > > entry in the middle just seems weird.
> >
> >
> > Usually, new data should be output to the end of a sample.
>
> Because.... you want old tools to read new output?

Yes, for some cases, it helps.
If no other sample types are output after PERF_SAMPLE_BRANCH_STACK,
old perf tool will ignore the hw_idx.
But, if we also have to output other sample types, e.g 
PERF_SAMPLE_DATA_SRC or PERF_SAMPLE_PHYS_ADDR, which are output after 
PERF_SAMPLE_BRANCH_STACK. The hw_idx will mess them up.
Old perf tool doesn't work anymore.


> > However, the entries[0] is sized entry, so I have to put the hw_idx before
>
> entries[0] is only in the C thing, and in C you indeed have to put
> hw_idx before.
>
> > entry. It makes the inconsistency. Sorry for the confusion caused.
>
> n/p it's clear now I think.

Should I send V6 patch to move hw_idx before entry as below?

@@ -853,7 +857,9 @@ enum perf_event_type {
         *        char                  data[size];}&& PERF_SAMPLE_RAW
         *
         *      { u64                   nr;
-        *        { u64 from, to, flags } lbr[nr];} && 
PERF_SAMPLE_BRANCH_STACK
+        *        { u64 hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX
+        *        { u64 from, to, flags } lbr[nr];
+        *      } && PERF_SAMPLE_BRANCH_STACK
         *
         *      { u64                   abi; # enum perf_sample_regs_abi
         *        u64                   regs[weight(mask)]; } && 
PERF_SAMPLE_REGS_USER

@@ -6634,6 +6639,8 @@ void perf_output_sample(struct perf_output_handle 
*handle,
                             * sizeof(struct perf_branch_entry);

                        perf_output_put(handle, data->br_stack->nr);
+                       if (perf_sample_save_hw_index(event))
+                               perf_output_put(handle, 
data->br_stack->hw_idx);
                        perf_output_copy(handle, 
data->br_stack->entries, size);
                } else {
                        /*



Thanks,
Kan