Skip to contentSkip to conversation

perf updates

GIT PULL Ingo Molnar 1 participant 1 message Apr 18, 2015

Subsystems (4)
x86 perf events Tracing Page cache
lore
Share & tools
lore

Ingo Molnar

author
#0 lore raw

Linus,

Please pull the latest perf-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf-urgent-for-linus

# HEAD: 0c99241c93b8060441f3c8434848e54b5338f922 perf/x86/intel/pt: Fix and clean up error handling in pt_event_add()

This update has mostly fixes, but also other bits:

- perf tooling fixes

- PMU driver fixes

- Intel Broadwell PMU driver HW-enablement for LBR callstacks

- a late coming 'perf kmem' tool update that enables it to also analyze page allocation data. Note, this comes with MM tracepoint changes that we believe to not break anything: because it changes the formerly opaque 'struct page *' field that uniquely identifies pages to 'pfn' which identifies pages uniquely too, but isn't as opaque and can be used for other purposes as well.

Thanks,

Ingo

------------------>
He Kuang (2):
perf probe: Set retprobe flag when probe in address-based alternative mode perf probe: Fix segfault when probe with lazy_line to file

Ingo Molnar (1):
perf/x86/intel/pt: Fix and clean up error handling in pt_event_add()

Jacob Pan (1):
perf/x86/intel/rapl: Fix energy counter measurements but supporing per domain energy units

Kan Liang (1):
perf/x86/intel: Add Broadwell support for the LBR callstack

Namhyung Kim (2):
tracing, mm: Record pfn instead of pointer to struct page perf kmem: Analyze page allocator events also

Naohiro Aota (1):
perf probe: Find compilation directory path for lazy matching

Peter Zijlstra (2):
perf/x86: Fix hw_perf_event::flags collision perf/x86/intel: Fix Core2,Atom,NHM,WSM cycles:pp events

 arch/x86/kernel/cpu/perf_event.h            |  18 +-
 arch/x86/kernel/cpu/perf_event_intel.c      |   2 +-
 arch/x86/kernel/cpu/perf_event_intel_ds.c   |   8 +
 arch/x86/kernel/cpu/perf_event_intel_pt.c   |  33 +-
 arch/x86/kernel/cpu/perf_event_intel_rapl.c |  94 ++++--
 include/trace/events/filemap.h              |   8 +-
 include/trace/events/kmem.h                 |  42 +--
 include/trace/events/vmscan.h               |   8 +-
 tools/perf/Documentation/perf-kmem.txt      |   8 +-
 tools/perf/builtin-kmem.c                   | 500 +++++++++++++++++++++++++++-
 tools/perf/util/probe-event.c               |  60 +---
 tools/perf/util/probe-finder.c              |  73 +++-
 tools/perf/util/probe-finder.h              |   4 +
 13 files changed, 702 insertions(+), 156 deletions(-)
arch/x86/kernel/cpu/perf_event.h +9 -9
index 329f0356ad4a..6ac5cb7a9e14 100644
@@ -65,15 +65,15 @@ struct event_constraint {
 /*
  * struct hw_perf_event.flags flags
  */
-#define PERF_X86_EVENT_PEBS_LDLAT	0x1 /* ld+ldlat data address sampling */
-#define PERF_X86_EVENT_PEBS_ST		0x2 /* st data address sampling */
-#define PERF_X86_EVENT_PEBS_ST_HSW	0x4 /* haswell style datala, store */
-#define PERF_X86_EVENT_COMMITTED	0x8 /* event passed commit_txn */
-#define PERF_X86_EVENT_PEBS_LD_HSW	0x10 /* haswell style datala, load */
-#define PERF_X86_EVENT_PEBS_NA_HSW	0x20 /* haswell style datala, unknown */
-#define PERF_X86_EVENT_EXCL		0x40 /* HT exclusivity on counter */
-#define PERF_X86_EVENT_DYNAMIC		0x80 /* dynamic alloc'd constraint */
-#define PERF_X86_EVENT_RDPMC_ALLOWED	0x40 /* grant rdpmc permission */
+#define PERF_X86_EVENT_PEBS_LDLAT	0x0001 /* ld+ldlat data address sampling */
+#define PERF_X86_EVENT_PEBS_ST		0x0002 /* st data address sampling */
+#define PERF_X86_EVENT_PEBS_ST_HSW	0x0004 /* haswell style datala, store */
+#define PERF_X86_EVENT_COMMITTED	0x0008 /* event passed commit_txn */
+#define PERF_X86_EVENT_PEBS_LD_HSW	0x0010 /* haswell style datala, load */
+#define PERF_X86_EVENT_PEBS_NA_HSW	0x0020 /* haswell style datala, unknown */
+#define PERF_X86_EVENT_EXCL		0x0040 /* HT exclusivity on counter */
+#define PERF_X86_EVENT_DYNAMIC		0x0080 /* dynamic alloc'd constraint */
+#define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
 
 
 struct amd_nb {
arch/x86/kernel/cpu/perf_event_intel.c +1 -1
index 9da2400c2ec3..219d3fb423a1 100644
@@ -3275,7 +3275,7 @@ __init int intel_pmu_init(void)
 		hw_cache_extra_regs[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = HSW_DEMAND_WRITE|
 									      BDW_L3_MISS_LOCAL|HSW_SNOOP_DRAM;
 
-		intel_pmu_lbr_init_snb();
+		intel_pmu_lbr_init_hsw();
 
 		x86_pmu.event_constraints = intel_bdw_event_constraints;
 		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
arch/x86/kernel/cpu/perf_event_intel_ds.c +8 -0
index ca69ea56c712..813f75d71175 100644
@@ -558,6 +558,8 @@ struct event_constraint intel_core2_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
+	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01),
 	EVENT_CONSTRAINT_END
 };
 

@@ -565,6 +567,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
+	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01),
 	EVENT_CONSTRAINT_END
 };
 

@@ -588,6 +592,8 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
+	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
 	EVENT_CONSTRAINT_END
 };
 

@@ -603,6 +609,8 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
+	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
 	EVENT_CONSTRAINT_END
 };
arch/x86/kernel/cpu/perf_event_intel_pt.c +15 -18
index f2770641c0fd..ffe666c2c6b5 100644
@@ -988,39 +988,36 @@ static int pt_event_add(struct perf_event *event, int mode)
 	int ret = -EBUSY;
 
 	if (pt->handle.event)
-		goto out;
+		goto fail;
 
 	buf = perf_aux_output_begin(&pt->handle, event);
-	if (!buf) {
-		ret = -EINVAL;
-		goto out;
-	}
+	ret = -EINVAL;
+	if (!buf)
+		goto fail_stop;
 
 	pt_buffer_reset_offsets(buf, pt->handle.head);
 	if (!buf->snapshot) {
 		ret = pt_buffer_reset_markers(buf, &pt->handle);
-		if (ret) {
-			perf_aux_output_end(&pt->handle, 0, true);
-			goto out;
-		}
+		if (ret)
+			goto fail_end_stop;
 	}
 
 	if (mode & PERF_EF_START) {
 		pt_event_start(event, 0);
-		if (hwc->state == PERF_HES_STOPPED) {
-			pt_event_del(event, 0);
-			ret = -EBUSY;
-		}
+		ret = -EBUSY;
+		if (hwc->state == PERF_HES_STOPPED)
+			goto fail_end_stop;
 	} else {
 		hwc->state = PERF_HES_STOPPED;
 	}
 
-	ret = 0;
-out:
-
-	if (ret)
-		hwc->state = PERF_HES_STOPPED;
+	return 0;
 
+fail_end_stop:
+	perf_aux_output_end(&pt->handle, 0, true);
+fail_stop:
+	hwc->state = PERF_HES_STOPPED;
+fail:
 	return ret;
 }
arch/x86/kernel/cpu/perf_event_intel_rapl.c +73 -21

203 lines not on this page · raw message

include/trace/events/filemap.h +4 -4
index 0421f49a20f7..42febb6bc1d5 100644
@@ -18,14 +18,14 @@ DECLARE_EVENT_CLASS(mm_filemap_op_page_cache,
 	TP_ARGS(page),
 
 	TP_STRUCT__entry(
-		__field(struct page *, page)
+		__field(unsigned long, pfn)
 		__field(unsigned long, i_ino)
 		__field(unsigned long, index)
 		__field(dev_t, s_dev)
 	),
 
 	TP_fast_assign(
-		__entry->page = page;
+		__entry->pfn = page_to_pfn(page);
 		__entry->i_ino = page->mapping->host->i_ino;
 		__entry->index = page->index;
 		if (page->mapping->host->i_sb)

@@ -37,8 +37,8 @@ DECLARE_EVENT_CLASS(mm_filemap_op_page_cache,
 	TP_printk("dev %d:%d ino %lx page=%p pfn=%lu ofs=%lu",
 		MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
 		__entry->i_ino,
-		__entry->page,
-		page_to_pfn(__entry->page),
+		pfn_to_page(__entry->pfn),
+		__entry->pfn,
 		__entry->index << PAGE_SHIFT)
 );
include/trace/events/kmem.h +21 -21

128 lines not on this page · raw message

include/trace/events/vmscan.h +4 -4
index 69590b6ffc09..f66476b96264 100644
@@ -336,18 +336,18 @@ TRACE_EVENT(mm_vmscan_writepage,
 	TP_ARGS(page, reclaim_flags),
 
 	TP_STRUCT__entry(
-		__field(struct page *, page)
+		__field(unsigned long, pfn)
 		__field(int, reclaim_flags)
 	),
 
 	TP_fast_assign(
-		__entry->page = page;
+		__entry->pfn = page_to_pfn(page);
 		__entry->reclaim_flags = reclaim_flags;
 	),
 
 	TP_printk("page=%p pfn=%lu flags=%s",
-		__entry->page,
-		page_to_pfn(__entry->page),
+		pfn_to_page(__entry->pfn),
+		__entry->pfn,
 		show_reclaim_flags(__entry->reclaim_flags))
 );
tools/perf/Documentation/perf-kmem.txt +7 -1
index 150253cc3c97..23219c65c16f 100644
@@ -3,7 +3,7 @@ perf-kmem(1)
 
 NAME
 ----
-perf-kmem - Tool to trace/measure kernel memory(slab) properties
+perf-kmem - Tool to trace/measure kernel memory properties
 
 SYNOPSIS
 --------

@@ -46,6 +46,12 @@ OPTIONS
 --raw-ip::
 	Print raw ip instead of symbol
 
+--slab::
+	Analyze SLAB allocator events.
+
+--page::
+	Analyze page allocator events
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
tools/perf/builtin-kmem.c +484 -16

624 lines not on this page · raw message

tools/perf/util/probe-event.c +1 -59

72 lines not on this page · raw message

tools/perf/util/probe-finder.c +71 -2

92 lines not on this page · raw message

tools/perf/util/probe-finder.h +4 -0
index 92590b2c7e1c..ebf8c8c81453 100644
@@ -55,6 +55,10 @@ extern int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 					     struct variable_list **vls,
 					     int max_points, bool externs);
 
+/* Find a src file from a DWARF tag path */
+int get_real_path(const char *raw_path, const char *comp_dir,
+			 char **new_path);
+
 struct probe_finder {
 	struct perf_probe_event	*pev;		/* Target probe event */