Re: [PATCH v6 1/7] perf/core: Define the common branch type classification

From: Michael Ellerman <mpe@ellerman.id.au>
To: Peter Zijlstra <peterz@infradead.org>, Jin Yao <yao.jin@linux.intel.com>
Cc: ak@linux.intel.com, maddy@linux.vnet.ibm.com,
	alexander.shishkin@linux.intel.com, kan.liang@intel.com,
	linuxppc-dev@lists.ozlabs.org, Linux-kernel@vger.kernel.org,
	acme@kernel.org, mingo@redhat.com, jolsa@kernel.org,
	yao.jin@intel.com
Subject: Re: [PATCH v6 1/7] perf/core: Define the common branch type classification
Date: Mon, 10 Jul 2017 15:19:57 +1000	[thread overview]
Message-ID: <87tw2kj2bm.fsf@concordia.ellerman.id.au> (raw)
In-Reply-To: <20170707084201.zglggi2sfziirjio@hirez.programming.kicks-ass.net>

Peter Zijlstra <peterz@infradead.org> writes:

> PPC folks, maddy, does this work for you guys?

It think it works for us, but I have some comments, I'll reply to the original.

cheers

> On Thu, Apr 20, 2017 at 08:07:49PM +0800, Jin Yao wrote:
>> It is often useful to know the branch types while analyzing branch
>> data. For example, a call is very different from a conditional branch.
>> 
>> Currently we have to look it up in binary while the binary may later
>> not be available and even the binary is available but user has to take
>> some time. It is very useful for user to check it directly in perf
>> report.
>> 
>> Perf already has support for disassembling the branch instruction
>> to get the x86 branch type.
>> 
>> To keep consistent on kernel and userspace and make the classification
>> more common, the patch adds the common branch type classification
>> in perf_event.h.
>> 
>> PERF_BR_NONE      : unknown
>> PERF_BR_JCC       : conditional jump
>> PERF_BR_JMP       : jump
>> PERF_BR_IND_JMP   : indirect jump
>> PERF_BR_CALL      : call
>> PERF_BR_IND_CALL  : indirect call
>> PERF_BR_RET       : return
>> PERF_BR_SYSCALL   : syscall
>> PERF_BR_SYSRET    : syscall return
>> PERF_BR_IRQ       : hw interrupt/trap/fault
>> PERF_BR_INT       : sw interrupt
>> PERF_BR_IRET      : return from interrupt
>> PERF_BR_FAR_BRANCH: not generic far branch type
>> 
>> The patch also adds a new field type (4 bits) in perf_branch_entry
>> to record the branch type.
>> 
>> Since the disassembling of branch instruction needs some overhead,
>> a new PERF_SAMPLE_BRANCH_TYPE_SAVE is introduced to indicate if it
>> needs to disassemble the branch instruction and record the branch
>> type.
>> 
>> Change log
>> ----------
>> 
>> v6: Not changed.
>> 
>> v5: Not changed. The v5 patch series just change the userspace.
>> 
>> v4: Comparing to previous version, the major changes are:
>> 
>> 1. Remove the PERF_BR_JCC_FWD/PERF_BR_JCC_BWD, they will be
>>    computed later in userspace.
>> 
>> 2. Remove the "cross" field in perf_branch_entry. The cross page
>>    computing will be done later in userspace.
>> 
>> Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
>> ---
>>  include/uapi/linux/perf_event.h       | 29 ++++++++++++++++++++++++++++-
>>  tools/include/uapi/linux/perf_event.h | 29 ++++++++++++++++++++++++++++-
>>  2 files changed, 56 insertions(+), 2 deletions(-)
>> 
>> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
>> index d09a9cd..69af012 100644
>> --- a/include/uapi/linux/perf_event.h
>> +++ b/include/uapi/linux/perf_event.h
>> @@ -174,6 +174,8 @@ enum perf_branch_sample_type_shift {
>>  	PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT	= 14, /* no flags */
>>  	PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT	= 15, /* no cycles */
>>  
>> +	PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT	= 16, /* save branch type */
>> +
>>  	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
>>  };
>>  
>> @@ -198,9 +200,32 @@ enum perf_branch_sample_type {
>>  	PERF_SAMPLE_BRANCH_NO_FLAGS	= 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
>>  	PERF_SAMPLE_BRANCH_NO_CYCLES	= 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
>>  
>> +	PERF_SAMPLE_BRANCH_TYPE_SAVE	=
>> +		1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
>> +
>>  	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
>>  };
>>  
>> +/*
>> + * Common flow change classification
>> + */
>> +enum {
>> +	PERF_BR_NONE		= 0,	/* unknown */
>> +	PERF_BR_JCC		= 1,	/* conditional jump */
>> +	PERF_BR_JMP		= 2,	/* jump */
>> +	PERF_BR_IND_JMP		= 3,	/* indirect jump */
>> +	PERF_BR_CALL		= 4,	/* call */
>> +	PERF_BR_IND_CALL	= 5,	/* indirect call */
>> +	PERF_BR_RET		= 6,	/* return */
>> +	PERF_BR_SYSCALL		= 7,	/* syscall */
>> +	PERF_BR_SYSRET		= 8,	/* syscall return */
>> +	PERF_BR_IRQ		= 9,	/* hw interrupt/trap/fault */
>> +	PERF_BR_INT		= 10,	/* sw interrupt */
>> +	PERF_BR_IRET		= 11,	/* return from interrupt */
>> +	PERF_BR_FAR_BRANCH	= 12,	/* not generic far branch type */
>> +	PERF_BR_MAX,
>> +};
>> +
>>  #define PERF_SAMPLE_BRANCH_PLM_ALL \
>>  	(PERF_SAMPLE_BRANCH_USER|\
>>  	 PERF_SAMPLE_BRANCH_KERNEL|\
>> @@ -999,6 +1024,7 @@ union perf_mem_data_src {
>>   *     in_tx: running in a hardware transaction
>>   *     abort: aborting a hardware transaction
>>   *    cycles: cycles from last branch (or 0 if not supported)
>> + *      type: branch type
>>   */
>>  struct perf_branch_entry {
>>  	__u64	from;
>> @@ -1008,7 +1034,8 @@ struct perf_branch_entry {
>>  		in_tx:1,    /* in transaction */
>>  		abort:1,    /* transaction abort */
>>  		cycles:16,  /* cycle count to last branch */
>> -		reserved:44;
>> +		type:4,     /* branch type */
>> +		reserved:40;
>>  };
>>  
>>  #endif /* _UAPI_LINUX_PERF_EVENT_H */
>> diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
>> index d09a9cd..69af012 100644
>> --- a/tools/include/uapi/linux/perf_event.h
>> +++ b/tools/include/uapi/linux/perf_event.h
>> @@ -174,6 +174,8 @@ enum perf_branch_sample_type_shift {
>>  	PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT	= 14, /* no flags */
>>  	PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT	= 15, /* no cycles */
>>  
>> +	PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT	= 16, /* save branch type */
>> +
>>  	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
>>  };
>>  
>> @@ -198,9 +200,32 @@ enum perf_branch_sample_type {
>>  	PERF_SAMPLE_BRANCH_NO_FLAGS	= 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT,
>>  	PERF_SAMPLE_BRANCH_NO_CYCLES	= 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT,
>>  
>> +	PERF_SAMPLE_BRANCH_TYPE_SAVE	=
>> +		1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT,
>> +
>>  	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
>>  };
>>  
>> +/*
>> + * Common flow change classification
>> + */
>> +enum {
>> +	PERF_BR_NONE		= 0,	/* unknown */
>> +	PERF_BR_JCC		= 1,	/* conditional jump */
>> +	PERF_BR_JMP		= 2,	/* jump */
>> +	PERF_BR_IND_JMP		= 3,	/* indirect jump */
>> +	PERF_BR_CALL		= 4,	/* call */
>> +	PERF_BR_IND_CALL	= 5,	/* indirect call */
>> +	PERF_BR_RET		= 6,	/* return */
>> +	PERF_BR_SYSCALL		= 7,	/* syscall */
>> +	PERF_BR_SYSRET		= 8,	/* syscall return */
>> +	PERF_BR_IRQ		= 9,	/* hw interrupt/trap/fault */
>> +	PERF_BR_INT		= 10,	/* sw interrupt */
>> +	PERF_BR_IRET		= 11,	/* return from interrupt */
>> +	PERF_BR_FAR_BRANCH	= 12,	/* not generic far branch type */
>> +	PERF_BR_MAX,
>> +};
>> +
>>  #define PERF_SAMPLE_BRANCH_PLM_ALL \
>>  	(PERF_SAMPLE_BRANCH_USER|\
>>  	 PERF_SAMPLE_BRANCH_KERNEL|\
>> @@ -999,6 +1024,7 @@ union perf_mem_data_src {
>>   *     in_tx: running in a hardware transaction
>>   *     abort: aborting a hardware transaction
>>   *    cycles: cycles from last branch (or 0 if not supported)
>> + *      type: branch type
>>   */
>>  struct perf_branch_entry {
>>  	__u64	from;
>> @@ -1008,7 +1034,8 @@ struct perf_branch_entry {
>>  		in_tx:1,    /* in transaction */
>>  		abort:1,    /* transaction abort */
>>  		cycles:16,  /* cycle count to last branch */
>> -		reserved:44;
>> +		type:4,     /* branch type */
>> +		reserved:40;
>>  };
>>  
>>  #endif /* _UAPI_LINUX_PERF_EVENT_H */
>> -- 
>> 2.7.4
>> 