Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 98a3b32c authored by Stephane Eranian's avatar Stephane Eranian Committed by Arnaldo Carvalho de Melo
Browse files

perf tools: Add mem access sampling core support 



This patch adds the sorting and histogram support
functions to enable profiling of memory accesses.

The following sorting orders are added:
 - symbol_daddr: data address symbol (or raw address)
 - dso_daddr: data address shared object
 - locked: access uses locked transaction
 - tlb : TLB access
 - mem : memory level of the access (L1, L2, L3, RAM, ...)
 - snoop: access snoop mode

Signed-off-by: default avatarStephane Eranian <eranian@google.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1359040242-8269-12-git-send-email-eranian@google.com


[ committer note: changed to cope with fc5871ed, the move of methods to
  machine.[ch], and the rename of dsrc to data_src, to match the change
  made in the PERF_SAMPLE_DSRC in a previous patch. ]
Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent 05484298

tools/perf/util/event.h

+8 −0
Original line number Diff line number Diff line
@@ -91,6 +91,7 @@ struct perf_sample { 
	u64 weight;

	u32 cpu;

	u32 raw_size;

	u64 data_src;

	void *raw_data;

	struct ip_callchain *callchain;

	struct branch_stack *branch_stack;
@@ -98,6 +99,13 @@ struct perf_sample { 
	struct stack_dump user_stack;

};



#define PERF_MEM_DATA_SRC_NONE \

	(PERF_MEM_S(OP, NA) |\

	 PERF_MEM_S(LVL, NA) |\

	 PERF_MEM_S(SNOOP, NA) |\

	 PERF_MEM_S(LOCK, NA) |\

	 PERF_MEM_S(TLB, NA))



struct build_id_event {

	struct perf_event_header header;

	pid_t			 pid;

tools/perf/util/evsel.c

+6 −0
Original line number Diff line number Diff line
@@ -1177,6 +1177,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event, 
		array++;

	}



	data->data_src = PERF_MEM_DATA_SRC_NONE;

	if (type & PERF_SAMPLE_DATA_SRC) {

		data->data_src = *array;

		array++;

	}



	return 0;

}

tools/perf/util/hist.c

+83 −3
Original line number Diff line number Diff line
@@ -67,12 +67,16 @@ static void hists__set_unres_dso_col_len(struct hists *hists, int dso) 
void hists__calc_col_len(struct hists *hists, struct hist_entry *h)

{

	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;

	int symlen;

	u16 len;



	if (h->ms.sym)

		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);

	else

	else {

		symlen = unresolved_col_width + 4 + 2;

		hists__new_col_len(hists, HISTC_SYMBOL, symlen);

		hists__set_unres_dso_col_len(hists, HISTC_DSO);

	}



	len = thread__comm_len(h->thread);

	if (hists__new_col_len(hists, HISTC_COMM, len))
@@ -87,7 +91,6 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) 
		hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen);



	if (h->branch_info) {

		int symlen;

		/*

		 * +4 accounts for '[x] ' priv level info

		 * +2 account of 0x prefix on raw addresses
@@ -116,6 +119,42 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) 
			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);

		}

	}



	if (h->mem_info) {

		/*

		 * +4 accounts for '[x] ' priv level info

		 * +2 account of 0x prefix on raw addresses

		 */

		if (h->mem_info->daddr.sym) {

			symlen = (int)h->mem_info->daddr.sym->namelen + 4

			       + unresolved_col_width + 2;

			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,

					   symlen);

		} else {

			symlen = unresolved_col_width + 4 + 2;

			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,

					   symlen);

		}

		if (h->mem_info->daddr.map) {

			symlen = dso__name_len(h->mem_info->daddr.map->dso);

			hists__new_col_len(hists, HISTC_MEM_DADDR_DSO,

					   symlen);

		} else {

			symlen = unresolved_col_width + 4 + 2;

			hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);

		}

	} else {

		symlen = unresolved_col_width + 4 + 2;

		hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);

		hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);

	}



	hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);

	hists__new_col_len(hists, HISTC_MEM_TLB, 22);

	hists__new_col_len(hists, HISTC_MEM_SNOOP, 12);

	hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3);

	hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);

	hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);

}



void hists__output_recalc_col_len(struct hists *hists, int max_rows)
@@ -158,6 +197,7 @@ static void hist_entry__add_cpumode_period(struct hist_entry *he, 
static void he_stat__add_period(struct he_stat *he_stat, u64 period,

				u64 weight)

{



	he_stat->period		+= period;

	he_stat->weight		+= weight;

	he_stat->nr_events	+= 1;
@@ -243,7 +283,7 @@ void hists__decay_entries_threaded(struct hists *hists, 
static struct hist_entry *hist_entry__new(struct hist_entry *template)

{

	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;

	struct hist_entry *he = malloc(sizeof(*he) + callchain_size);

	struct hist_entry *he = zalloc(sizeof(*he) + callchain_size);



	if (he != NULL) {

		*he = *template;
@@ -258,6 +298,13 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template) 
				he->branch_info->to.map->referenced = true;

		}



		if (he->mem_info) {

			if (he->mem_info->iaddr.map)

				he->mem_info->iaddr.map->referenced = true;

			if (he->mem_info->daddr.map)

				he->mem_info->daddr.map->referenced = true;

		}



		if (symbol_conf.use_callchain)

			callchain_init(he->callchain);
@@ -346,6 +393,36 @@ static struct hist_entry *add_hist_entry(struct hists *hists, 
	return he;

}



struct hist_entry *__hists__add_mem_entry(struct hists *self,

					  struct addr_location *al,

					  struct symbol *sym_parent,

					  struct mem_info *mi,

					  u64 period,

					  u64 weight)

{

	struct hist_entry entry = {

		.thread	= al->thread,

		.ms = {

			.map	= al->map,

			.sym	= al->sym,

		},

		.stat = {

			.period	= period,

			.weight = weight,

			.nr_events = 1,

		},

		.cpu	= al->cpu,

		.ip	= al->addr,

		.level	= al->level,

		.parent = sym_parent,

		.filtered = symbol__parent_filter(sym_parent),

		.hists = self,

		.mem_info = mi,

		.branch_info = NULL,

	};

	return add_hist_entry(self, &entry, al, period, weight);

}



struct hist_entry *__hists__add_branch_entry(struct hists *self,

					     struct addr_location *al,

					     struct symbol *sym_parent,
@@ -371,6 +448,7 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self, 
		.filtered = symbol__parent_filter(sym_parent),

		.branch_info = bi,

		.hists	= self,

		.mem_info = NULL,

	};



	return add_hist_entry(self, &entry, al, period, weight);
@@ -398,6 +476,8 @@ struct hist_entry *__hists__add_entry(struct hists *self, 
		.parent = sym_parent,

		.filtered = symbol__parent_filter(sym_parent),

		.hists	= self,

		.branch_info = NULL,

		.mem_info = NULL,

	};



	return add_hist_entry(self, &entry, al, period, weight);

tools/perf/util/hist.h

+13 −0
Original line number Diff line number Diff line
@@ -51,6 +51,12 @@ enum hist_column { 
	HISTC_SRCLINE,

	HISTC_LOCAL_WEIGHT,

	HISTC_GLOBAL_WEIGHT,

	HISTC_MEM_DADDR_SYMBOL,

	HISTC_MEM_DADDR_DSO,

	HISTC_MEM_LOCKED,

	HISTC_MEM_TLB,

	HISTC_MEM_LVL,

	HISTC_MEM_SNOOP,

	HISTC_NR_COLS, /* Last entry */

};
@@ -90,6 +96,13 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self, 
					     u64 period,

					     u64 weight);



struct hist_entry *__hists__add_mem_entry(struct hists *self,

					  struct addr_location *al,

					  struct symbol *sym_parent,

					  struct mem_info *mi,

					  u64 period,

					  u64 weight);



void hists__output_resort(struct hists *self);

void hists__output_resort_threaded(struct hists *hists);

void hists__collapse_resort(struct hists *self);

tools/perf/util/machine.c

+32 −0
Original line number Diff line number Diff line
@@ -1097,6 +1097,38 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread, 
	ams->map = al.map;

}



static void ip__resolve_data(struct machine *machine, struct thread *thread,

			     u8 m, struct addr_map_symbol *ams, u64 addr)

{

	struct addr_location al;



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



	thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, &al,

				   NULL);

	ams->addr = addr;

	ams->al_addr = al.addr;

	ams->sym = al.sym;

	ams->map = al.map;

}



struct mem_info *machine__resolve_mem(struct machine *machine,

				      struct thread *thr,

				      struct perf_sample *sample,

				      u8 cpumode)

{

	struct mem_info *mi = zalloc(sizeof(*mi));



	if (!mi)

		return NULL;



	ip__resolve_ams(machine, thr, &mi->iaddr, sample->ip);

	ip__resolve_data(machine, thr, cpumode, &mi->daddr, sample->addr);

	mi->data_src.val = sample->data_src;



	return mi;

}



struct branch_info *machine__resolve_bstack(struct machine *machine,

					    struct thread *thr,

					    struct branch_stack *bs)