Commit 42bbabed authored by Kan Liang's avatar Kan Liang Committed by Arnaldo Carvalho de Melo
Browse files

perf tools: Add hw_idx in struct branch_stack 



The low level index of raw branch records for the most recent branch can
be recorded in a sample with PERF_SAMPLE_BRANCH_HW_INDEX
branch_sample_type. Extend struct branch_stack to support it.

However, if the PERF_SAMPLE_BRANCH_HW_INDEX is not applied, only nr and
entries[] will be output by kernel. The pointer of entries[] could be
wrong, since the output format is different with new struct
branch_stack.  Add a variable no_hw_idx in struct perf_sample to
indicate whether the hw_idx is output.  Add get_branch_entry() to return
corresponding pointer of entries[0].

To make dummy branch sample consistent as new branch sample, add hw_idx
in struct dummy_branch_stack for cs-etm and intel-pt.

Apply the new struct branch_stack for synthetic events as well.

Extend test case sample-parsing to support new struct branch_stack.

Committer notes:

Renamed get_branch_entries() to perf_sample__branch_entries() to have
proper namespacing and pave the way for this to be moved to libperf,
eventually.

Add 'static' to that inline as it is in a header.

Add 'hw_idx' to 'struct dummy_branch_stack' in cs-etm.c to fix the build
on arm64.

Signed-off-by: default avatarKan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pavel Gerasimov <pavel.gerasimov@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com>
Link: http://lore.kernel.org/lkml/20200228163011.19358-2-kan.liang@linux.intel.com


Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent 6339998d

tools/perf/builtin-script.c

+37 −33
Original line number Diff line number Diff line
@@ -735,6 +735,7 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, 
					struct perf_event_attr *attr, FILE *fp)

{

	struct branch_stack *br = sample->branch_stack;

	struct branch_entry *entries = perf_sample__branch_entries(sample);

	struct addr_location alf, alt;

	u64 i, from, to;

	int printed = 0;
@@ -743,8 +744,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, 
		return 0;



	for (i = 0; i < br->nr; i++) {

		from = br->entries[i].from;

		to   = br->entries[i].to;

		from = entries[i].from;

		to   = entries[i].to;



		if (PRINT_FIELD(DSO)) {

			memset(&alf, 0, sizeof(alf));
@@ -768,10 +769,10 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample, 
		}



		printed += fprintf(fp, "/%c/%c/%c/%d ",

			mispred_str( br->entries + i),

			br->entries[i].flags.in_tx? 'X' : '-',

			br->entries[i].flags.abort? 'A' : '-',

			br->entries[i].flags.cycles);

			mispred_str(entries + i),

			entries[i].flags.in_tx ? 'X' : '-',

			entries[i].flags.abort ? 'A' : '-',

			entries[i].flags.cycles);

	}



	return printed;
@@ -782,6 +783,7 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, 
					   struct perf_event_attr *attr, FILE *fp)

{

	struct branch_stack *br = sample->branch_stack;

	struct branch_entry *entries = perf_sample__branch_entries(sample);

	struct addr_location alf, alt;

	u64 i, from, to;

	int printed = 0;
@@ -793,8 +795,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, 


		memset(&alf, 0, sizeof(alf));

		memset(&alt, 0, sizeof(alt));

		from = br->entries[i].from;

		to   = br->entries[i].to;

		from = entries[i].from;

		to   = entries[i].to;



		thread__find_symbol_fb(thread, sample->cpumode, from, &alf);

		thread__find_symbol_fb(thread, sample->cpumode, to, &alt);
@@ -813,10 +815,10 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample, 
			printed += fprintf(fp, ")");

		}

		printed += fprintf(fp, "/%c/%c/%c/%d ",

			mispred_str( br->entries + i),

			br->entries[i].flags.in_tx? 'X' : '-',

			br->entries[i].flags.abort? 'A' : '-',

			br->entries[i].flags.cycles);

			mispred_str(entries + i),

			entries[i].flags.in_tx ? 'X' : '-',

			entries[i].flags.abort ? 'A' : '-',

			entries[i].flags.cycles);

	}



	return printed;
@@ -827,6 +829,7 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, 
					   struct perf_event_attr *attr, FILE *fp)

{

	struct branch_stack *br = sample->branch_stack;

	struct branch_entry *entries = perf_sample__branch_entries(sample);

	struct addr_location alf, alt;

	u64 i, from, to;

	int printed = 0;
@@ -838,8 +841,8 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, 


		memset(&alf, 0, sizeof(alf));

		memset(&alt, 0, sizeof(alt));

		from = br->entries[i].from;

		to   = br->entries[i].to;

		from = entries[i].from;

		to   = entries[i].to;



		if (thread__find_map_fb(thread, sample->cpumode, from, &alf) &&

		    !alf.map->dso->adjust_symbols)
@@ -862,10 +865,10 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample, 
			printed += fprintf(fp, ")");

		}

		printed += fprintf(fp, "/%c/%c/%c/%d ",

			mispred_str(br->entries + i),

			br->entries[i].flags.in_tx ? 'X' : '-',

			br->entries[i].flags.abort ? 'A' : '-',

			br->entries[i].flags.cycles);

			mispred_str(entries + i),

			entries[i].flags.in_tx ? 'X' : '-',

			entries[i].flags.abort ? 'A' : '-',

			entries[i].flags.cycles);

	}



	return printed;
@@ -1053,6 +1056,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, 
					    struct machine *machine, FILE *fp)

{

	struct branch_stack *br = sample->branch_stack;

	struct branch_entry *entries = perf_sample__branch_entries(sample);

	u64 start, end;

	int i, insn, len, nr, ilen, printed = 0;

	struct perf_insn x;
@@ -1073,31 +1077,31 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, 
	printed += fprintf(fp, "%c", '\n');



	/* Handle first from jump, of which we don't know the entry. */

	len = grab_bb(buffer, br->entries[nr-1].from,

			br->entries[nr-1].from,

	len = grab_bb(buffer, entries[nr-1].from,

			entries[nr-1].from,

			machine, thread, &x.is64bit, &x.cpumode, false);

	if (len > 0) {

		printed += ip__fprintf_sym(br->entries[nr - 1].from, thread,

		printed += ip__fprintf_sym(entries[nr - 1].from, thread,

					   x.cpumode, x.cpu, &lastsym, attr, fp);

		printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1],

		printed += ip__fprintf_jump(entries[nr - 1].from, &entries[nr - 1],

					    &x, buffer, len, 0, fp, &total_cycles);

		if (PRINT_FIELD(SRCCODE))

			printed += print_srccode(thread, x.cpumode, br->entries[nr - 1].from);

			printed += print_srccode(thread, x.cpumode, entries[nr - 1].from);

	}



	/* Print all blocks */

	for (i = nr - 2; i >= 0; i--) {

		if (br->entries[i].from || br->entries[i].to)

		if (entries[i].from || entries[i].to)

			pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i,

				 br->entries[i].from,

				 br->entries[i].to);

		start = br->entries[i + 1].to;

		end   = br->entries[i].from;

				 entries[i].from,

				 entries[i].to);

		start = entries[i + 1].to;

		end   = entries[i].from;



		len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);

		/* Patch up missing kernel transfers due to ring filters */

		if (len == -ENXIO && i > 0) {

			end = br->entries[--i].from;

			end = entries[--i].from;

			pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end);

			len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);

		}
@@ -1110,7 +1114,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, 


			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);

			if (ip == end) {

				printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, ++insn, fp,

				printed += ip__fprintf_jump(ip, &entries[i], &x, buffer + off, len - off, ++insn, fp,

							    &total_cycles);

				if (PRINT_FIELD(SRCCODE))

					printed += print_srccode(thread, x.cpumode, ip);
@@ -1134,9 +1138,9 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, 
	 * Hit the branch? In this case we are already done, and the target

	 * has not been executed yet.

	 */

	if (br->entries[0].from == sample->ip)

	if (entries[0].from == sample->ip)

		goto out;

	if (br->entries[0].flags.abort)

	if (entries[0].flags.abort)

		goto out;



	/*
@@ -1147,7 +1151,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, 
	 * between final branch and sample. When this happens just

	 * continue walking after the last TO until we hit a branch.

	 */

	start = br->entries[0].to;

	start = entries[0].to;

	end = sample->ip;

	if (end < start) {

		/* Missing jump. Scan 128 bytes for the next branch */

tools/perf/tests/sample-parsing.c

+6 −1
Original line number Diff line number Diff line
@@ -99,6 +99,7 @@ static bool samples_same(const struct perf_sample *s1, 


	if (type & PERF_SAMPLE_BRANCH_STACK) {

		COMP(branch_stack->nr);

		COMP(branch_stack->hw_idx);

		for (i = 0; i < s1->branch_stack->nr; i++)

			MCOMP(branch_stack->entries[i]);

	}
@@ -186,7 +187,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) 
		u64 data[64];

	} branch_stack = {

		/* 1 branch_entry */

		.data = {1, 211, 212, 213},

		.data = {1, -1ULL, 211, 212, 213},

	};

	u64 regs[64];

	const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
@@ -208,6 +209,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) 
		.transaction	= 112,

		.raw_data	= (void *)raw_data,

		.callchain	= &callchain.callchain,

		.no_hw_idx      = false,

		.branch_stack	= &branch_stack.branch_stack,

		.user_regs	= {

			.abi	= PERF_SAMPLE_REGS_ABI_64,
@@ -244,6 +246,9 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format) 
	if (sample_type & PERF_SAMPLE_REGS_INTR)

		evsel.core.attr.sample_regs_intr = sample_regs;



	if (sample_type & PERF_SAMPLE_BRANCH_STACK)

		evsel.core.attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;



	for (i = 0; i < sizeof(regs); i++)

		*(i + (u8 *)regs) = i & 0xfe;

tools/perf/util/branch.h

+22 −0
Original line number Diff line number Diff line
@@ -12,6 +12,7 @@ 
#include <linux/stddef.h>

#include <linux/perf_event.h>

#include <linux/types.h>

#include "event.h"



struct branch_flags {

	u64 mispred:1;
@@ -39,9 +40,30 @@ struct branch_entry { 


struct branch_stack {

	u64			nr;

	u64			hw_idx;

	struct branch_entry	entries[0];

};



/*

 * The hw_idx is only available when PERF_SAMPLE_BRANCH_HW_INDEX is applied.

 * Otherwise, the output format of a sample with branch stack is

 * struct branch_stack {

 *	u64			nr;

 *	struct branch_entry	entries[0];

 * }

 * Check whether the hw_idx is available,

 * and return the corresponding pointer of entries[0].

 */

static inline struct branch_entry *perf_sample__branch_entries(struct perf_sample *sample)

{

	u64 *entry = (u64 *)sample->branch_stack;



	entry++;

	if (sample->no_hw_idx)

		return (struct branch_entry *)entry;

	return (struct branch_entry *)(++entry);

}



struct branch_type_stat {

	bool	branch_to;

	u64	counts[PERF_BR_MAX];

tools/perf/util/cs-etm.c

+2 −0
Original line number Diff line number Diff line
@@ -1172,6 +1172,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq, 
	union perf_event *event = tidq->event_buf;

	struct dummy_branch_stack {

		u64			nr;

		u64			hw_idx;

		struct branch_entry	entries;

	} dummy_bs;

	u64 ip;
@@ -1202,6 +1203,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq, 
	if (etm->synth_opts.last_branch) {

		dummy_bs = (struct dummy_branch_stack){

			.nr = 1,

			.hw_idx = -1ULL,

			.entries = {

				.from = sample.ip,

				.to = sample.addr,

tools/perf/util/event.h

+1 −0
Original line number Diff line number Diff line
@@ -139,6 +139,7 @@ struct perf_sample { 
	u16 insn_len;

	u8  cpumode;

	u16 misc;

	bool no_hw_idx;		/* No hw_idx collected in branch_stack */

	char insn[MAX_INSN];

	void *raw_data;

	struct ip_callchain *callchain;

CRA Git | Maintained and supported by SUSTech CRA and CCSE