summaryrefslogtreecommitdiffstats
path: root/tools/perf/builtin-report.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-04-30 16:41:01 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2013-04-30 16:41:01 +0200
commite0972916e8fe943f342b0dd1c9d43dbf5bc261c2 (patch)
tree690c436f1f9b839c4ba34d17ab3efa63b97a2dce /tools/perf/builtin-report.c
parentMerge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kerne... (diff)
parentperf/x86/intel/P4: Robistify P4 PMU types (diff)
downloadlinux-e0972916e8fe943f342b0dd1c9d43dbf5bc261c2.tar.xz
linux-e0972916e8fe943f342b0dd1c9d43dbf5bc261c2.zip
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Ingo Molnar: "Features: - Add "uretprobes" - an optimization to uprobes, like kretprobes are an optimization to kprobes. "perf probe -x file sym%return" now works like kretprobes. By Oleg Nesterov. - Introduce per core aggregation in 'perf stat', from Stephane Eranian. - Add memory profiling via PEBS, from Stephane Eranian. - Event group view for 'annotate' in --stdio, --tui and --gtk, from Namhyung Kim. - Add support for AMD NB and L2I "uncore" counters, by Jacob Shin. - Add Ivy Bridge-EP uncore support, by Zheng Yan - IBM zEnterprise EC12 oprofile support patchlet from Robert Richter. - Add perf test entries for checking breakpoint overflow signal handler issues, from Jiri Olsa. - Add perf test entry for for checking number of EXIT events, from Namhyung Kim. - Add perf test entries for checking --cpu in record and stat, from Jiri Olsa. - Introduce perf stat --repeat forever, from Frederik Deweerdt. - Add --no-demangle to report/top, from Namhyung Kim. - PowerPC fixes plus a couple of cleanups/optimizations in uprobes and trace_uprobes, by Oleg Nesterov. Various fixes and refactorings: - Fix dependency of the python binding wrt libtraceevent, from Naohiro Aota. - Simplify some perf_evlist methods and to allow 'stat' to share code with 'record' and 'trace', by Arnaldo Carvalho de Melo. - Remove dead code in related to libtraceevent integration, from Namhyung Kim. - Revert "perf sched: Handle PERF_RECORD_EXIT events" to get 'perf sched lat' back working, by Arnaldo Carvalho de Melo - We don't use Newt anymore, just plain libslang, by Arnaldo Carvalho de Melo. - Kill a bunch of die() calls, from Namhyung Kim. - Fix build on non-glibc systems due to libio.h absence, from Cody P Schafer. - Remove some perf_session and tracing dead code, from David Ahern. - Honor parallel jobs, fix from Borislav Petkov - Introduce tools/lib/lk library, initially just removing duplication among tools/perf and tools/vm. from Borislav Petkov ... and many more I missed to list, see the shortlog and git log for more details." * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (136 commits) perf/x86/intel/P4: Robistify P4 PMU types perf/x86/amd: Fix AMD NB and L2I "uncore" support perf/x86/amd: Remove old-style NB counter support from perf_event_amd.c perf/x86: Check all MSRs before passing hw check perf/x86/amd: Add support for AMD NB and L2I "uncore" counters perf/x86/intel: Add Ivy Bridge-EP uncore support perf/x86/intel: Fix SNB-EP CBO and PCU uncore PMU filter management perf/x86: Avoid kfree() in CPU_{STARTING,DYING} uprobes/perf: Avoid perf_trace_buf_prepare/submit if ->perf_events is empty uprobes/tracing: Don't pass addr=ip to perf_trace_buf_submit() uprobes/tracing: Change create_trace_uprobe() to support uretprobes uprobes/tracing: Make seq_printf() code uretprobe-friendly uprobes/tracing: Make register_uprobe_event() paths uretprobe-friendly uprobes/tracing: Make uprobe_{trace,perf}_print() uretprobe-friendly uprobes/tracing: Introduce is_ret_probe() and uretprobe_dispatcher() uprobes/tracing: Introduce uprobe_{trace,perf}_print() helpers uprobes/tracing: Generalize struct uprobe_trace_entry_head uprobes/tracing: Kill the pointless local_save_flags/preempt_count calls uprobes/tracing: Kill the pointless seq_print_ip_sym() call uprobes/tracing: Kill the pointless task_pt_regs() calls ...
Diffstat (limited to 'tools/perf/builtin-report.c')
-rw-r--r--tools/perf/builtin-report.c150
1 files changed, 140 insertions, 10 deletions
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 96b5a7fee4bb..bd0ca81eeaca 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -13,7 +13,6 @@
#include "util/annotate.h"
#include "util/color.h"
#include <linux/list.h>
-#include "util/cache.h"
#include <linux/rbtree.h>
#include "util/symbol.h"
#include "util/callchain.h"
@@ -47,6 +46,7 @@ struct perf_report {
bool show_full_info;
bool show_threads;
bool inverted_callchain;
+ bool mem_mode;
struct perf_read_values show_threads_values;
const char *pretty_printing_style;
symbol_filter_t annotate_init;
@@ -65,6 +65,99 @@ static int perf_report_config(const char *var, const char *value, void *cb)
return perf_default_config(var, value, cb);
}
+static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
+ struct addr_location *al,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine,
+ union perf_event *event)
+{
+ struct perf_report *rep = container_of(tool, struct perf_report, tool);
+ struct symbol *parent = NULL;
+ u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+ int err = 0;
+ struct hist_entry *he;
+ struct mem_info *mi, *mx;
+ uint64_t cost;
+
+ if ((sort__has_parent || symbol_conf.use_callchain) &&
+ sample->callchain) {
+ err = machine__resolve_callchain(machine, evsel, al->thread,
+ sample, &parent);
+ if (err)
+ return err;
+ }
+
+ mi = machine__resolve_mem(machine, al->thread, sample, cpumode);
+ if (!mi)
+ return -ENOMEM;
+
+ if (rep->hide_unresolved && !al->sym)
+ return 0;
+
+ cost = sample->weight;
+ if (!cost)
+ cost = 1;
+
+ /*
+ * must pass period=weight in order to get the correct
+ * sorting from hists__collapse_resort() which is solely
+ * based on periods. We want sorting be done on nr_events * weight
+ * and this is indirectly achieved by passing period=weight here
+ * and the he_stat__add_period() function.
+ */
+ he = __hists__add_mem_entry(&evsel->hists, al, parent, mi, cost, cost);
+ if (!he)
+ return -ENOMEM;
+
+ /*
+ * In the TUI browser, we are doing integrated annotation,
+ * so we don't allocate the extra space needed because the stdio
+ * code will not use it.
+ */
+ if (sort__has_sym && he->ms.sym && use_browser > 0) {
+ struct annotation *notes = symbol__annotation(he->ms.sym);
+
+ assert(evsel != NULL);
+
+ if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
+ goto out;
+
+ err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+ if (err)
+ goto out;
+ }
+
+ if (sort__has_sym && he->mem_info->daddr.sym && use_browser > 0) {
+ struct annotation *notes;
+
+ mx = he->mem_info;
+
+ notes = symbol__annotation(mx->daddr.sym);
+ if (notes->src == NULL && symbol__alloc_hist(mx->daddr.sym) < 0)
+ goto out;
+
+ err = symbol__inc_addr_samples(mx->daddr.sym,
+ mx->daddr.map,
+ evsel->idx,
+ mx->daddr.al_addr);
+ if (err)
+ goto out;
+ }
+
+ evsel->hists.stats.total_period += cost;
+ hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+ err = 0;
+
+ if (symbol_conf.use_callchain) {
+ err = callchain_append(he->callchain,
+ &callchain_cursor,
+ sample->period);
+ }
+out:
+ return err;
+}
+
static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
struct addr_location *al,
struct perf_sample *sample,
@@ -99,7 +192,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
* and not events sampled. Thus we use a pseudo period of 1.
*/
he = __hists__add_branch_entry(&evsel->hists, al, parent,
- &bi[i], 1);
+ &bi[i], 1, 1);
if (he) {
struct annotation *notes;
err = -ENOMEM;
@@ -157,7 +250,8 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
return err;
}
- he = __hists__add_entry(&evsel->hists, al, parent, sample->period);
+ he = __hists__add_entry(&evsel->hists, al, parent, sample->period,
+ sample->weight);
if (he == NULL)
return -ENOMEM;
@@ -169,7 +263,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
return err;
}
/*
- * Only in the newt browser we are doing integrated annotation,
+ * Only in the TUI browser we are doing integrated annotation,
* so we don't allocated the extra space needed because the stdio
* code will not use it.
*/
@@ -220,6 +314,12 @@ static int process_sample_event(struct perf_tool *tool,
pr_debug("problem adding lbr entry, skipping event\n");
return -1;
}
+ } else if (rep->mem_mode == 1) {
+ if (perf_report__add_mem_hist_entry(tool, &al, sample,
+ evsel, machine, event)) {
+ pr_debug("problem adding mem entry, skipping event\n");
+ return -1;
+ }
} else {
if (al.map != NULL)
al.map->dso->hit = 1;
@@ -303,7 +403,8 @@ static void sig_handler(int sig __maybe_unused)
session_done = 1;
}
-static size_t hists__fprintf_nr_sample_events(struct hists *self,
+static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
+ struct hists *self,
const char *evname, FILE *fp)
{
size_t ret;
@@ -314,7 +415,7 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self,
char buf[512];
size_t size = sizeof(buf);
- if (symbol_conf.event_group && evsel->nr_members > 1) {
+ if (perf_evsel__is_group_event(evsel)) {
struct perf_evsel *pos;
perf_evsel__group_desc(evsel, buf, size);
@@ -331,7 +432,11 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self,
if (evname != NULL)
ret += fprintf(fp, " of event '%s'", evname);
- ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
+ if (rep->mem_mode) {
+ ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events);
+ ret += fprintf(fp, "\n# Sort order : %s", sort_order);
+ } else
+ ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
return ret + fprintf(fp, "\n#\n");
}
@@ -349,7 +454,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
!perf_evsel__is_group_leader(pos))
continue;
- hists__fprintf_nr_sample_events(hists, evname, stdout);
+ hists__fprintf_nr_sample_events(rep, hists, evname, stdout);
hists__fprintf(hists, true, 0, 0, stdout);
fprintf(stdout, "\n\n");
}
@@ -645,7 +750,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
"Use the stdio interface"),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
- " dso_to, dso_from, symbol_to, symbol_from, mispredict"),
+ " dso_to, dso_from, symbol_to, symbol_from, mispredict,"
+ " weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, "
+ "snoop, locked"),
OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
"Show sample percentage for different cpu modes"),
OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -693,6 +800,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
"use branch records for histogram filling", parse_branch_mode),
OPT_STRING(0, "objdump", &objdump_path, "path",
"objdump binary to use for disassembly and annotations"),
+ OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
+ "Disable symbol demangling"),
+ OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
OPT_END()
};
@@ -750,12 +860,24 @@ repeat:
"dso_to,symbol_to";
}
+ if (report.mem_mode) {
+ if (sort__branch_mode == 1) {
+ fprintf(stderr, "branch and mem mode incompatible\n");
+ goto error;
+ }
+ /*
+ * if no sort_order is provided, then specify
+ * branch-mode specific order
+ */
+ if (sort_order == default_sort_order)
+ sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
+ }
if (setup_sorting() < 0)
usage_with_options(report_usage, options);
/*
- * Only in the newt browser we are doing integrated annotation,
+ * Only in the TUI browser we are doing integrated annotation,
* so don't allocate extra space that won't be used in the stdio
* implementation.
*/
@@ -815,6 +937,14 @@ repeat:
sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
} else {
+ if (report.mem_mode) {
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "symbol_daddr", stdout);
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso_daddr", stdout);
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "mem", stdout);
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "local_weight", stdout);
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "tlb", stdout);
+ sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "snoop", stdout);
+ }
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
}