Revision 9c29bcd189f4ab1644b7125713602532d0aefdb7 authored by Eric Dumazet on 21 September 2018, 22:27:48 UTC, committed by David S. Miller on 24 September 2018, 04:55:25 UTC
As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

mlx5 uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent a24b66c
Raw File
builtin-annotate.c
// SPDX-License-Identifier: GPL-2.0
/*
 * builtin-annotate.c
 *
 * Builtin annotate command: Analyze the perf.data input file,
 * look up and read DSOs and symbol information and display
 * a histogram of results, along various sorting keys.
 */
#include "builtin.h"

#include "util/util.h"
#include "util/color.h"
#include <linux/list.h>
#include "util/cache.h"
#include <linux/rbtree.h>
#include "util/symbol.h"

#include "perf.h"
#include "util/debug.h"

#include "util/evlist.h"
#include "util/evsel.h"
#include "util/annotate.h"
#include "util/event.h"
#include <subcmd/parse-options.h>
#include "util/parse-events.h"
#include "util/thread.h"
#include "util/sort.h"
#include "util/hist.h"
#include "util/session.h"
#include "util/tool.h"
#include "util/data.h"
#include "arch/common.h"
#include "util/block-range.h"

#include <dlfcn.h>
#include <errno.h>
#include <linux/bitmap.h>

struct perf_annotate {
	struct perf_tool tool;
	struct perf_session *session;
	struct annotation_options opts;
	bool	   use_tui, use_stdio, use_stdio2, use_gtk;
	bool	   skip_missing;
	bool	   has_br_stack;
	bool	   group_set;
	const char *sym_hist_filter;
	const char *cpu_list;
	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
};

/*
 * Given one basic block:
 *
 *	from	to		branch_i
 *	* ----> *
 *		|
 *		| block
 *		v
 *		* ----> *
 *		from	to	branch_i+1
 *
 * where the horizontal are the branches and the vertical is the executed
 * block of instructions.
 *
 * We count, for each 'instruction', the number of blocks that covered it as
 * well as count the ratio each branch is taken.
 *
 * We can do this without knowing the actual instruction stream by keeping
 * track of the address ranges. We break down ranges such that there is no
 * overlap and iterate from the start until the end.
 *
 * @acme: once we parse the objdump output _before_ processing the samples,
 * we can easily fold the branch.cycles IPC bits in.
 */
static void process_basic_block(struct addr_map_symbol *start,
				struct addr_map_symbol *end,
				struct branch_flags *flags)
{
	struct symbol *sym = start->sym;
	struct annotation *notes = sym ? symbol__annotation(sym) : NULL;
	struct block_range_iter iter;
	struct block_range *entry;

	/*
	 * Sanity; NULL isn't executable and the CPU cannot execute backwards
	 */
	if (!start->addr || start->addr > end->addr)
		return;

	iter = block_range__create(start->addr, end->addr);
	if (!block_range_iter__valid(&iter))
		return;

	/*
	 * First block in range is a branch target.
	 */
	entry = block_range_iter(&iter);
	assert(entry->is_target);
	entry->entry++;

	do {
		entry = block_range_iter(&iter);

		entry->coverage++;
		entry->sym = sym;

		if (notes)
			notes->max_coverage = max(notes->max_coverage, entry->coverage);

	} while (block_range_iter__next(&iter));

	/*
	 * Last block in rage is a branch.
	 */
	entry = block_range_iter(&iter);
	assert(entry->is_branch);
	entry->taken++;
	if (flags->predicted)
		entry->pred++;
}

static void process_branch_stack(struct branch_stack *bs, struct addr_location *al,
				 struct perf_sample *sample)
{
	struct addr_map_symbol *prev = NULL;
	struct branch_info *bi;
	int i;

	if (!bs || !bs->nr)
		return;

	bi = sample__resolve_bstack(sample, al);
	if (!bi)
		return;

	for (i = bs->nr - 1; i >= 0; i--) {
		/*
		 * XXX filter against symbol
		 */
		if (prev)
			process_basic_block(prev, &bi[i].from, &bi[i].flags);
		prev = &bi[i].to;
	}

	free(bi);
}

static int hist_iter__branch_callback(struct hist_entry_iter *iter,
				      struct addr_location *al __maybe_unused,
				      bool single __maybe_unused,
				      void *arg __maybe_unused)
{
	struct hist_entry *he = iter->he;
	struct branch_info *bi;
	struct perf_sample *sample = iter->sample;
	struct perf_evsel *evsel = iter->evsel;
	int err;

	hist__account_cycles(sample->branch_stack, al, sample, false);

	bi = he->branch_info;
	err = addr_map_symbol__inc_samples(&bi->from, sample, evsel);

	if (err)
		goto out;

	err = addr_map_symbol__inc_samples(&bi->to, sample, evsel);

out:
	return err;
}

static int process_branch_callback(struct perf_evsel *evsel,
				   struct perf_sample *sample,
				   struct addr_location *al __maybe_unused,
				   struct perf_annotate *ann,
				   struct machine *machine)
{
	struct hist_entry_iter iter = {
		.evsel		= evsel,
		.sample		= sample,
		.add_entry_cb	= hist_iter__branch_callback,
		.hide_unresolved	= symbol_conf.hide_unresolved,
		.ops		= &hist_iter_branch,
	};

	struct addr_location a;
	int ret;

	if (machine__resolve(machine, &a, sample) < 0)
		return -1;

	if (a.sym == NULL)
		return 0;

	if (a.map != NULL)
		a.map->dso->hit = 1;

	ret = hist_entry_iter__add(&iter, &a, PERF_MAX_STACK_DEPTH, ann);
	return ret;
}

static bool has_annotation(struct perf_annotate *ann)
{
	return ui__has_annotation() || ann->use_stdio2;
}

static int perf_evsel__add_sample(struct perf_evsel *evsel,
				  struct perf_sample *sample,
				  struct addr_location *al,
				  struct perf_annotate *ann,
				  struct machine *machine)
{
	struct hists *hists = evsel__hists(evsel);
	struct hist_entry *he;
	int ret;

	if ((!ann->has_br_stack || !has_annotation(ann)) &&
	    ann->sym_hist_filter != NULL &&
	    (al->sym == NULL ||
	     strcmp(ann->sym_hist_filter, al->sym->name) != 0)) {
		/* We're only interested in a symbol named sym_hist_filter */
		/*
		 * FIXME: why isn't this done in the symbol_filter when loading
		 * the DSO?
		 */
		if (al->sym != NULL) {
			rb_erase(&al->sym->rb_node,
				 &al->map->dso->symbols);
			symbol__delete(al->sym);
			dso__reset_find_symbol_cache(al->map->dso);
		}
		return 0;
	}

	/*
	 * XXX filtered samples can still have branch entires pointing into our
	 * symbol and are missed.
	 */
	process_branch_stack(sample->branch_stack, al, sample);

	if (ann->has_br_stack && has_annotation(ann))
		return process_branch_callback(evsel, sample, al, ann, machine);

	he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
	if (he == NULL)
		return -ENOMEM;

	ret = hist_entry__inc_addr_samples(he, sample, evsel, al->addr);
	hists__inc_nr_samples(hists, true);
	return ret;
}

static int process_sample_event(struct perf_tool *tool,
				union perf_event *event,
				struct perf_sample *sample,
				struct perf_evsel *evsel,
				struct machine *machine)
{
	struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool);
	struct addr_location al;
	int ret = 0;

	if (machine__resolve(machine, &al, sample) < 0) {
		pr_warning("problem processing %d event, skipping it.\n",
			   event->header.type);
		return -1;
	}

	if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
		goto out_put;

	if (!al.filtered &&
	    perf_evsel__add_sample(evsel, sample, &al, ann, machine)) {
		pr_warning("problem incrementing symbol count, "
			   "skipping event\n");
		ret = -1;
	}
out_put:
	addr_location__put(&al);
	return ret;
}

static int process_feature_event(struct perf_tool *tool,
				 union perf_event *event,
				 struct perf_session *session)
{
	if (event->feat.feat_id < HEADER_LAST_FEATURE)
		return perf_event__process_feature(tool, event, session);
	return 0;
}

static int hist_entry__tty_annotate(struct hist_entry *he,
				    struct perf_evsel *evsel,
				    struct perf_annotate *ann)
{
	if (!ann->use_stdio2)
		return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel, &ann->opts);

	return symbol__tty_annotate2(he->ms.sym, he->ms.map, evsel, &ann->opts);
}

static void hists__find_annotations(struct hists *hists,
				    struct perf_evsel *evsel,
				    struct perf_annotate *ann)
{
	struct rb_node *nd = rb_first(&hists->entries), *next;
	int key = K_RIGHT;

	while (nd) {
		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
		struct annotation *notes;

		if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned)
			goto find_next;

		if (ann->sym_hist_filter &&
		    (strcmp(he->ms.sym->name, ann->sym_hist_filter) != 0))
			goto find_next;

		notes = symbol__annotation(he->ms.sym);
		if (notes->src == NULL) {
find_next:
			if (key == K_LEFT)
				nd = rb_prev(nd);
			else
				nd = rb_next(nd);
			continue;
		}

		if (use_browser == 2) {
			int ret;
			int (*annotate)(struct hist_entry *he,
					struct perf_evsel *evsel,
					struct hist_browser_timer *hbt);

			annotate = dlsym(perf_gtk_handle,
					 "hist_entry__gtk_annotate");
			if (annotate == NULL) {
				ui__error("GTK browser not found!\n");
				return;
			}

			ret = annotate(he, evsel, NULL);
			if (!ret || !ann->skip_missing)
				return;

			/* skip missing symbols */
			nd = rb_next(nd);
		} else if (use_browser == 1) {
			key = hist_entry__tui_annotate(he, evsel, NULL, &ann->opts);

			switch (key) {
			case -1:
				if (!ann->skip_missing)
					return;
				/* fall through */
			case K_RIGHT:
				next = rb_next(nd);
				break;
			case K_LEFT:
				next = rb_prev(nd);
				break;
			default:
				return;
			}

			if (next != NULL)
				nd = next;
		} else {
			hist_entry__tty_annotate(he, evsel, ann);
			nd = rb_next(nd);
			/*
			 * Since we have a hist_entry per IP for the same
			 * symbol, free he->ms.sym->src to signal we already
			 * processed this symbol.
			 */
			zfree(&notes->src->cycles_hist);
			zfree(&notes->src);
		}
	}
}

static int __cmd_annotate(struct perf_annotate *ann)
{
	int ret;
	struct perf_session *session = ann->session;
	struct perf_evsel *pos;
	u64 total_nr_samples;

	if (ann->cpu_list) {
		ret = perf_session__cpu_bitmap(session, ann->cpu_list,
					       ann->cpu_bitmap);
		if (ret)
			goto out;
	}

	if (!ann->opts.objdump_path) {
		ret = perf_env__lookup_objdump(&session->header.env,
					       &ann->opts.objdump_path);
		if (ret)
			goto out;
	}

	ret = perf_session__process_events(session);
	if (ret)
		goto out;

	if (dump_trace) {
		perf_session__fprintf_nr_events(session, stdout);
		perf_evlist__fprintf_nr_events(session->evlist, stdout);
		goto out;
	}

	if (verbose > 3)
		perf_session__fprintf(session, stdout);

	if (verbose > 2)
		perf_session__fprintf_dsos(session, stdout);

	total_nr_samples = 0;
	evlist__for_each_entry(session->evlist, pos) {
		struct hists *hists = evsel__hists(pos);
		u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];

		if (nr_samples > 0) {
			total_nr_samples += nr_samples;
			hists__collapse_resort(hists, NULL);
			/* Don't sort callchain */
			perf_evsel__reset_sample_bit(pos, CALLCHAIN);
			perf_evsel__output_resort(pos, NULL);

			if (symbol_conf.event_group &&
			    !perf_evsel__is_group_leader(pos))
				continue;

			hists__find_annotations(hists, pos, ann);
		}
	}

	if (total_nr_samples == 0) {
		ui__error("The %s file has no samples!\n", session->data->file.path);
		goto out;
	}

	if (use_browser == 2) {
		void (*show_annotations)(void);

		show_annotations = dlsym(perf_gtk_handle,
					 "perf_gtk__show_annotations");
		if (show_annotations == NULL) {
			ui__error("GTK browser not found!\n");
			goto out;
		}
		show_annotations();
	}

out:
	return ret;
}

static const char * const annotate_usage[] = {
	"perf annotate [<options>]",
	NULL
};

int cmd_annotate(int argc, const char **argv)
{
	struct perf_annotate annotate = {
		.tool = {
			.sample	= process_sample_event,
			.mmap	= perf_event__process_mmap,
			.mmap2	= perf_event__process_mmap2,
			.comm	= perf_event__process_comm,
			.exit	= perf_event__process_exit,
			.fork	= perf_event__process_fork,
			.namespaces = perf_event__process_namespaces,
			.attr	= perf_event__process_attr,
			.build_id = perf_event__process_build_id,
			.tracing_data   = perf_event__process_tracing_data,
			.feature	= process_feature_event,
			.ordered_events = true,
			.ordering_requires_timestamps = true,
		},
		.opts = annotation__default_options,
	};
	struct perf_data data = {
		.mode  = PERF_DATA_MODE_READ,
	};
	struct option options[] = {
	OPT_STRING('i', "input", &input_name, "file",
		    "input file name"),
	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
		   "only consider symbols in these dsos"),
	OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol",
		    "symbol to annotate"),
	OPT_BOOLEAN('f', "force", &data.force, "don't complain, do it"),
	OPT_INCR('v', "verbose", &verbose,
		    "be more verbose (show symbol address, etc)"),
	OPT_BOOLEAN('q', "quiet", &quiet, "do now show any message"),
	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
		    "dump raw trace in ASCII"),
	OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"),
	OPT_BOOLEAN(0, "tui", &annotate.use_tui, "Use the TUI interface"),
	OPT_BOOLEAN(0, "stdio", &annotate.use_stdio, "Use the stdio interface"),
	OPT_BOOLEAN(0, "stdio2", &annotate.use_stdio2, "Use the stdio interface"),
	OPT_BOOLEAN(0, "ignore-vmlinux", &symbol_conf.ignore_vmlinux,
                    "don't load vmlinux even if found"),
	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
		   "file", "vmlinux pathname"),
	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
		    "load module symbols - WARNING: use only with -k and LIVE kernel"),
	OPT_BOOLEAN('l', "print-line", &annotate.opts.print_lines,
		    "print matching source lines (may be slow)"),
	OPT_BOOLEAN('P', "full-paths", &annotate.opts.full_path,
		    "Don't shorten the displayed pathnames"),
	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
		    "Skip symbols that cannot be annotated"),
	OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group,
			&annotate.group_set,
			"Show event group information together"),
	OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
	OPT_CALLBACK(0, "symfs", NULL, "directory",
		     "Look for files with symbols relative to this directory",
		     symbol__config_symfs),
	OPT_BOOLEAN(0, "source", &annotate.opts.annotate_src,
		    "Interleave source code with assembly code (default)"),
	OPT_BOOLEAN(0, "asm-raw", &annotate.opts.show_asm_raw,
		    "Display raw encoding of assembly instructions (default)"),
	OPT_STRING('M', "disassembler-style", &annotate.opts.disassembler_style, "disassembler style",
		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
	OPT_STRING(0, "objdump", &annotate.opts.objdump_path, "path",
		   "objdump binary to use for disassembly and annotations"),
	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
		    "Show event group information together"),
	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
		    "Show a column with the sum of periods"),
	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
		    "Show a column with the number of samples"),
	OPT_CALLBACK_DEFAULT(0, "stdio-color", NULL, "mode",
			     "'always' (default), 'never' or 'auto' only applicable to --stdio mode",
			     stdio__config_color, "always"),
	OPT_CALLBACK(0, "percent-type", &annotate.opts, "local-period",
		     "Set percent type local/global-period/hits",
		     annotate_parse_percent_type),

	OPT_END()
	};
	int ret;

	set_option_flag(options, 0, "show-total-period", PARSE_OPT_EXCLUSIVE);
	set_option_flag(options, 0, "show-nr-samples", PARSE_OPT_EXCLUSIVE);


	ret = hists__init();
	if (ret < 0)
		return ret;

	argc = parse_options(argc, argv, options, annotate_usage, 0);
	if (argc) {
		/*
		 * Special case: if there's an argument left then assume that
		 * it's a symbol filter:
		 */
		if (argc > 1)
			usage_with_options(annotate_usage, options);

		annotate.sym_hist_filter = argv[0];
	}

	if (symbol_conf.show_nr_samples && annotate.use_gtk) {
		pr_err("--show-nr-samples is not available in --gtk mode at this time\n");
		return ret;
	}

	if (quiet)
		perf_quiet_option();

	data.file.path = input_name;

	annotate.session = perf_session__new(&data, false, &annotate.tool);
	if (annotate.session == NULL)
		return -1;

	annotate.has_br_stack = perf_header__has_feat(&annotate.session->header,
						      HEADER_BRANCH_STACK);

	if (annotate.group_set)
		perf_evlist__force_leader(annotate.session->evlist);

	ret = symbol__annotation_init();
	if (ret < 0)
		goto out_delete;

	annotation_config__init();

	symbol_conf.try_vmlinux_path = true;

	ret = symbol__init(&annotate.session->header.env);
	if (ret < 0)
		goto out_delete;

	if (annotate.use_stdio || annotate.use_stdio2)
		use_browser = 0;
	else if (annotate.use_tui)
		use_browser = 1;
	else if (annotate.use_gtk)
		use_browser = 2;

	setup_browser(true);

	if ((use_browser == 1 || annotate.use_stdio2) && annotate.has_br_stack) {
		sort__mode = SORT_MODE__BRANCH;
		if (setup_sorting(annotate.session->evlist) < 0)
			usage_with_options(annotate_usage, options);
	} else {
		if (setup_sorting(NULL) < 0)
			usage_with_options(annotate_usage, options);
	}

	ret = __cmd_annotate(&annotate);

out_delete:
	/*
	 * Speed up the exit process, for large files this can
	 * take quite a while.
	 *
	 * XXX Enable this when using valgrind or if we ever
	 * librarize this command.
	 *
	 * Also experiment with obstacks to see how much speed
	 * up we'll get here.
	 *
	 * perf_session__delete(session);
	 */
	return ret;
}
back to top