perf/core improvements and fixes

new file mode 100644
index 0000000..c9de001
@@ -0,0 +1,19 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include "debug.h"
+#include "symbol.h"
+
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+	return ehdr.e_type == ET_EXEC ||
+	       ehdr.e_type == ET_REL ||
+	       ehdr.e_type == ET_DYN;
+}
+#endif

index a7ab606..54347ba 100644
@@ -630,6 +630,11 @@ void symsrc__destroy(struct symsrc *ss)
 	close(ss->fd);
 }
 
+bool __weak elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+	return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL;
+}
+
 int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		 enum dso_binary_type type)
 {

@@ -711,8 +716,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 						     ".gnu.prelink_undo",
 						     NULL) != NULL);
 	} else {
-		ss->adjust_symbols = ehdr.e_type == ET_EXEC ||
-				     ehdr.e_type == ET_REL;
+		ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
 	}
 
 	ss->name   = strdup(name);

index 0956150..8cb0af4 100644
@@ -303,4 +303,8 @@ int setup_list(struct strlist **list, const char *list_str,
 int setup_intlist(struct intlist **list, const char *list_str,
 		  const char *list_name);
 
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
+#endif
+
 #endif /* __PERF_SYMBOL */

index c9de001..5522a40 100644
@@ -17,3 +17,23 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
 	       ehdr.e_type == ET_DYN;
 }
 #endif
+
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+int arch__choose_best_symbol(struct symbol *syma,
+			     struct symbol *symb __maybe_unused)
+{
+	char *sym = syma->name;
+
+	/* Skip over any initial dot */
+	if (*sym == '.')
+		sym++;
+
+	/* Avoid "SyS" kernel syscall aliases */
+	if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3))
+		return SYMBOL_B;
+	if (strlen(sym) >= 10 && !strncmp(sym, "compat_SyS", 10))
+		return SYMBOL_B;
+
+	return SYMBOL_A;
+}
+#endif

index 201f6c4c..f805757 100644
@@ -85,8 +85,17 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
-#define SYMBOL_A 0
-#define SYMBOL_B 1
+int __weak arch__choose_best_symbol(struct symbol *syma,
+				    struct symbol *symb __maybe_unused)
+{
+	/* Avoid "SyS" kernel syscall aliases */
+	if (strlen(syma->name) >= 3 && !strncmp(syma->name, "SyS", 3))
+		return SYMBOL_B;
+	if (strlen(syma->name) >= 10 && !strncmp(syma->name, "compat_SyS", 10))
+		return SYMBOL_B;
+
+	return SYMBOL_A;
+}
 
 static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 {

@@ -134,13 +143,7 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 	else if (na < nb)
 		return SYMBOL_B;
 
-	/* Avoid "SyS" kernel syscall aliases */
-	if (na >= 3 && !strncmp(syma->name, "SyS", 3))
-		return SYMBOL_B;
-	if (na >= 10 && !strncmp(syma->name, "compat_SyS", 10))
-		return SYMBOL_B;
-
-	return SYMBOL_A;
+	return arch__choose_best_symbol(syma, symb);
 }
 
 void symbols__fixup_duplicate(struct rb_root *symbols)

index 8cb0af4..bd50ba0 100644
@@ -307,4 +307,9 @@ int setup_intlist(struct intlist **list, const char *list_str,
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
 #endif
 
+#define SYMBOL_A 0
+#define SYMBOL_B 1
+
+int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
+
 #endif /* __PERF_SYMBOL */

index 5522a40..2de2cc4 100644
@@ -8,6 +8,7 @@
 
 #include "debug.h"
 #include "symbol.h"
+#include "map.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)

@@ -36,4 +37,16 @@ int arch__choose_best_symbol(struct symbol *syma,
 
 	return SYMBOL_A;
 }
+
+/* Allow matching against dot variants */
+int arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+	/* Skip over initial dot */
+	if (*namea == '.')
+		namea++;
+	if (*nameb == '.')
+		nameb++;
+
+	return strcmp(namea, nameb);
+}
 #endif

index a14f08f..cd0e335 100644
@@ -292,6 +292,11 @@ int map__load(struct map *map, symbol_filter_t filter)
 	return 0;
 }
 
+int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+	return strcmp(namea, nameb);
+}
+
 struct symbol *map__find_symbol(struct map *map, u64 addr,
 				symbol_filter_t filter)
 {

index ec19c59..4e0c729 100644
@@ -124,7 +124,7 @@ struct thread;
  */
 #define __map__for_each_symbol_by_name(map, sym_name, pos, filter)	\
 	for (pos = map__find_symbol_by_name(map, sym_name, filter);	\
-	     pos && strcmp(pos->name, sym_name) == 0;		\
+	     pos && arch__compare_symbol_names(pos->name, sym_name) == 0;	\
 	     pos = symbol__next_by_name(pos))
 
 #define map__for_each_symbol_by_name(map, sym_name, pos)		\

@@ -132,6 +132,7 @@ struct thread;
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
+int arch__compare_symbol_names(const char *namea, const char *nameb);
 void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct machine *machine, u64 start, u64 len,

index f805757..45ba48a 100644
@@ -411,7 +411,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 		int cmp;
 
 		s = rb_entry(n, struct symbol_name_rb_node, rb_node);
-		cmp = strcmp(name, s->sym.name);
+		cmp = arch__compare_symbol_names(name, s->sym.name);
 
 		if (cmp < 0)
 			n = n->rb_left;

@@ -429,7 +429,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 		struct symbol_name_rb_node *tmp;
 
 		tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
-		if (strcmp(tmp->sym.name, s->sym.name))
+		if (arch__compare_symbol_names(tmp->sym.name, s->sym.name))
 			break;
 
 		s = tmp;

index 2de2cc4..012a0f8 100644
@@ -17,6 +17,13 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
 	       ehdr.e_type == ET_REL ||
 	       ehdr.e_type == ET_DYN;
 }
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+void arch__elf_sym_adjust(GElf_Sym *sym)
+{
+	sym->st_value += PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
+}
+#endif
 #endif
 
 #if !defined(_CALL_ELF) || _CALL_ELF != 2

index 54347ba..d99b442 100644
@@ -775,6 +775,8 @@ static bool want_demangle(bool is_kernel_sym)
 	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
 }
 
+void __weak arch__elf_sym_adjust(GElf_Sym *sym __maybe_unused) { }
+
 int dso__load_sym(struct dso *dso, struct map *map,
 		  struct symsrc *syms_ss, struct symsrc *runtime_ss,
 		  symbol_filter_t filter, int kmodule)

@@ -939,6 +941,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 		    (sym.st_value & 1))
 			--sym.st_value;
 
+		arch__elf_sym_adjust(&sym);
+
 		if (dso->kernel || kmodule) {
 			char dso_name[PATH_MAX];
 

index bd50ba0..9096529 100644
@@ -305,6 +305,7 @@ int setup_intlist(struct intlist **list, const char *list_str,
 
 #ifdef HAVE_LIBELF_SUPPORT
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
+void arch__elf_sym_adjust(GElf_Sym *sym);
 #endif
 
 #define SYMBOL_A 0

index 012a0f8..a170060 100644
@@ -9,6 +9,7 @@
 #include "debug.h"
 #include "symbol.h"
 #include "map.h"
+#include "probe-event.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)

@@ -57,3 +58,10 @@ int arch__compare_symbol_names(const char *namea, const char *nameb)
 	return strcmp(namea, nameb);
 }
 #endif
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+bool arch__prefers_symtab(void)
+{
+	return true;
+}
+#endif

index 291bf23..4dfb412 100644
@@ -2567,6 +2567,8 @@ err_out:
 	goto out;
 }
 
+bool __weak arch__prefers_symtab(void) { return false; }
+
 static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 					  struct probe_trace_event **tevs,
 					  int max_tevs, const char *target)

@@ -2582,6 +2584,12 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 		}
 	}
 
+	if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
+		ret = find_probe_trace_events_from_map(pev, tevs, max_tevs, target);
+		if (ret > 0)
+			return ret; /* Found in symbol table */
+	}
+
 	/* Convert perf_probe_event with debuginfo */
 	ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
 	if (ret != 0)

index d6b7834..52bca4b 100644
@@ -135,6 +135,7 @@ extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
 			       struct strfilter *filter, bool externs);
 extern int show_available_funcs(const char *module, struct strfilter *filter,
 				bool user);
+bool arch__prefers_symtab(void);
 
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX	1024

index a170060..bbc1a50 100644
@@ -64,4 +64,19 @@ bool arch__prefers_symtab(void)
 {
 	return true;
 }
+
+#define PPC64LE_LEP_OFFSET	8
+
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+			     struct probe_trace_event *tev, struct map *map)
+{
+	/*
+	 * ppc64 ABIv2 local entry point is currently always 2 instructions
+	 * (8 bytes) after the global entry point.
+	 */
+	if (!pev->uprobes && map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
+		tev->point.address += PPC64LE_LEP_OFFSET;
+		tev->point.offset += PPC64LE_LEP_OFFSET;
+	}
+}
 #endif

index 4dfb412..eb75a5e 100644
@@ -2447,6 +2447,10 @@ static int find_probe_functions(struct map *map, char *name)
 #define strdup_or_goto(str, label)	\
 	({ char *__p = strdup(str); if (!__p) goto label; __p; })
 
+void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
+				struct probe_trace_event *tev __maybe_unused,
+				struct map *map __maybe_unused) { }
+
 /*
  * Find probe function addresses from map.
  * Return an error or the number of found probe_trace_event

@@ -2553,6 +2557,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 					strdup_or_goto(pev->args[i].type,
 							nomem_out);
 		}
+		arch__fix_tev_from_maps(pev, tev, map);
 	}
 
 out:

index 52bca4b..180f142 100644
@@ -136,6 +136,8 @@ extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
 extern int show_available_funcs(const char *module, struct strfilter *filter,
 				bool user);
 bool arch__prefers_symtab(void);
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+			     struct probe_trace_event *tev, struct map *map);
 
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX	1024

index 0ec8c3b..7ec1bf9 100644
@@ -695,7 +695,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 
 static bool perf_mmap__empty(struct perf_mmap *md)
 {
-	return perf_mmap__read_head(md) == md->prev;
+	return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
 }
 
 static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)

index cd2f38b..6805098 100644
@@ -148,9 +148,10 @@ static const char *output_field2str(enum perf_output_field field)
 
 #define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
 
-static int perf_evsel__check_stype(struct perf_evsel *evsel,
-				   u64 sample_type, const char *sample_msg,
-				   enum perf_output_field field)
+static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
+				      u64 sample_type, const char *sample_msg,
+				      enum perf_output_field field,
+				      bool allow_user_set)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	int type = attr->type;

@@ -160,6 +161,8 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 		return 0;
 
 	if (output[type].user_set) {
+		if (allow_user_set)
+			return 0;
 		evname = perf_evsel__name(evsel);
 		pr_err("Samples for '%s' event do not have %s attribute set. "
 		       "Cannot print '%s' field.\n",

@@ -177,10 +180,22 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 	return 0;
 }
 
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+				   u64 sample_type, const char *sample_msg,
+				   enum perf_output_field field)
+{
+	return perf_evsel__do_check_stype(evsel, sample_type, sample_msg, field,
+					  false);
+}
+
 static int perf_evsel__check_attr(struct perf_evsel *evsel,
 				  struct perf_session *session)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	bool allow_user_set;
+
+	allow_user_set = perf_header__has_feat(&session->header,
+					       HEADER_AUXTRACE);
 
 	if (PRINT_FIELD(TRACE) &&
 		!perf_session__has_traces(session, "record -R"))

@@ -193,8 +208,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 	}
 
 	if (PRINT_FIELD(ADDR) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
-					PERF_OUTPUT_ADDR))
+		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
+					   PERF_OUTPUT_ADDR, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {

@@ -231,8 +246,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		return -EINVAL;
 
 	if (PRINT_FIELD(CPU) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
-					PERF_OUTPUT_CPU))
+		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
+					   PERF_OUTPUT_CPU, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(PERIOD) &&

index 476cdf7..18cb0ff 100644
@@ -36,6 +36,8 @@
 #include "util/data.h"
 #include "arch/common.h"
 
+#include "util/auxtrace.h"
+
 #include <dlfcn.h>
 #include <linux/bitmap.h>
 

@@ -585,6 +587,7 @@ parse_percent_limit(const struct option *opt, const char *str,
 int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_session *session;
+	struct itrace_synth_opts itrace_synth_opts = { .set = 0, };
 	struct stat st;
 	bool has_br_stack = false;
 	int branch_mode = -1;

@@ -607,6 +610,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = perf_event__process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
+			.id_index	 = perf_event__process_id_index,
+			.auxtrace_info	 = perf_event__process_auxtrace_info,
+			.auxtrace	 = perf_event__process_auxtrace,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},

@@ -717,6 +723,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "how to display percentage of filtered entries", parse_filter_percentage),
+	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+			    "Instruction Tracing options",
+			    itrace_parse_synth_opts),
 	OPT_END()
 	};
 	struct perf_data_file file = {

@@ -761,6 +770,8 @@ repeat:
 					       report.queue_size);
 	}
 
+	session->itrace_synth_opts = &itrace_synth_opts;
+
 	report.session = session;
 
 	has_br_stack = perf_header__has_feat(&session->header,

index d99b442..9d526a5 100644
@@ -683,6 +683,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		}
 
 		if (!dso__build_id_equal(dso, build_id)) {
+			pr_debug("%s: build id mismatch for %s.\n", __func__, name);
 			dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID;
 			goto out_elf_end;
 		}

index eb75a5e..416c10f 100644
@@ -1077,6 +1077,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	struct perf_probe_point *pp = &pev->point;
 	char *ptr, *tmp;
 	char c, nc = 0;
+	bool file_spec = false;
 	/*
 	 * <Syntax>
 	 * perf probe [EVENT=]SRC[:LN|;PTN]

@@ -1105,6 +1106,23 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 		arg = tmp;
 	}
 
+	/*
+	 * Check arg is function or file name and copy it.
+	 *
+	 * We consider arg to be a file spec if and only if it satisfies
+	 * all of the below criteria::
+	 * - it does not include any of "+@%",
+	 * - it includes one of ":;", and
+	 * - it has a period '.' in the name.
+	 *
+	 * Otherwise, we consider arg to be a function specification.
+	 */
+	if (!strpbrk(arg, "+@%") && (ptr = strpbrk(arg, ";:")) != NULL) {
+		/* This is a file spec if it includes a '.' before ; or : */
+		if (memchr(arg, '.', ptr - arg))
+			file_spec = true;
+	}
+
 	ptr = strpbrk(arg, ";:+@%");
 	if (ptr) {
 		nc = *ptr;

@@ -1115,10 +1133,9 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	if (tmp == NULL)
 		return -ENOMEM;
 
-	/* Check arg is function or file and copy it */
-	if (strchr(tmp, '.'))	/* File */
+	if (file_spec)
 		pp->file = tmp;
-	else			/* Function */
+	else
 		pp->function = tmp;
 
 	/* Parse other options */

@@ -2265,6 +2282,9 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 {
 	int i, ret;
 
+	if (*base == '.')
+		base++;
+
 	/* Try no suffix */
 	ret = e_snprintf(buf, len, "%s", base);
 	if (ret < 0) {

@@ -2766,6 +2786,9 @@ int del_perf_probe_events(struct strlist *dellist)
 			event = str;
 		}
 
+		if (event && *event == '.')
+			event++;
+
 		ret = e_snprintf(buf, 128, "%s:%s", group, event);
 		if (ret < 0) {
 			pr_err("Failed to copy event.");

index 79a757a..f3429cd 100644
@@ -170,6 +170,46 @@ struct strfilter *strfilter__new(const char *rules, const char **err)
 	return filter;
 }
 
+static int strfilter__append(struct strfilter *filter, bool _or,
+			     const char *rules, const char **err)
+{
+	struct strfilter_node *right, *root;
+	const char *ep = NULL;
+
+	if (!filter || !rules)
+		return -EINVAL;
+
+	right = strfilter_node__new(rules, &ep);
+	if (!right || *ep != '\0') {
+		if (err)
+			*err = ep;
+		goto error;
+	}
+	root = strfilter_node__alloc(_or ? OP_or : OP_and, filter->root, right);
+	if (!root) {
+		ep = NULL;
+		goto error;
+	}
+
+	filter->root = root;
+	return 0;
+
+error:
+	strfilter_node__delete(right);
+	return ep ? -EINVAL : -ENOMEM;
+}
+
+int strfilter__or(struct strfilter *filter, const char *rules, const char **err)
+{
+	return strfilter__append(filter, true, rules, err);
+}
+
+int strfilter__and(struct strfilter *filter, const char *rules,
+		   const char **err)
+{
+	return strfilter__append(filter, false, rules, err);
+}
+
 static bool strfilter_node__compare(struct strfilter_node *node,
 				    const char *str)
 {

index fe611f3..d007cdc 100644
@@ -29,6 +29,32 @@ struct strfilter {
 struct strfilter *strfilter__new(const char *rules, const char **err);
 
 /**
+ * strfilter__or - Append an additional rule by logical-or
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ *         @filter by using logical-or.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-or.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__or(struct strfilter *filter,
+		  const char *rules, const char **err);
+
+/**
+ * strfilter__add - Append an additional rule by logical-and
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ *         @filter by using logical-and.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-and.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__and(struct strfilter *filter,
+		   const char *rules, const char **err);
+
+/**
  * strfilter__compare - compare given string and a string filter
  * @filter: String filter
  * @str: target string

index f3429cd..bcae659 100644
@@ -237,3 +237,70 @@ bool strfilter__compare(struct strfilter *filter, const char *str)
 		return false;
 	return strfilter_node__compare(filter->root, str);
 }
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf);
+
+/* sprint node in parenthesis if needed */
+static int strfilter_node__sprint_pt(struct strfilter_node *node, char *buf)
+{
+	int len;
+	int pt = node->r ? 2 : 0;	/* don't need to check node->l */
+
+	if (buf && pt)
+		*buf++ = '(';
+	len = strfilter_node__sprint(node, buf);
+	if (len < 0)
+		return len;
+	if (buf && pt)
+		*(buf + len) = ')';
+	return len + pt;
+}
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf)
+{
+	int len = 0, rlen;
+
+	if (!node || !node->p)
+		return -EINVAL;
+
+	switch (*node->p) {
+	case '|':
+	case '&':
+		len = strfilter_node__sprint_pt(node->l, buf);
+		if (len < 0)
+			return len;
+	case '!':
+		if (buf) {
+			*(buf + len++) = *node->p;
+			buf += len;
+		} else
+			len++;
+		rlen = strfilter_node__sprint_pt(node->r, buf);
+		if (rlen < 0)
+			return rlen;
+		len += rlen;
+		break;
+	default:
+		len = strlen(node->p);
+		if (buf)
+			strcpy(buf, node->p);
+	}
+
+	return len;
+}
+
+char *strfilter__string(struct strfilter *filter)
+{
+	int len;
+	char *ret = NULL;
+
+	len = strfilter_node__sprint(filter->root, NULL);
+	if (len < 0)
+		return NULL;
+
+	ret = malloc(len + 1);
+	if (ret)
+		strfilter_node__sprint(filter->root, ret);
+
+	return ret;
+}

index d007cdc..cff5eda 100644
@@ -71,4 +71,13 @@ bool strfilter__compare(struct strfilter *filter, const char *str);
  */
 void strfilter__delete(struct strfilter *filter);
 
+/**
+ * strfilter__string - Reconstruct a rule string from filter
+ * @filter: String filter to reconstruct
+ *
+ * Reconstruct a rule string from @filter. This will be good for
+ * debug messages. Note that returning string must be freed afterward.
+ */
+char *strfilter__string(struct strfilter *filter);
+
 #endif

index 92dcce0..be17075 100644
@@ -262,21 +262,25 @@ static int opt_set_filter(const struct option *opt __maybe_unused,
 			  const char *str, int unset __maybe_unused)
 {
 	const char *err;
+	int ret = 0;
 
 	if (str) {
 		pr_debug2("Set filter: %s\n", str);
-		if (params.filter)
-			strfilter__delete(params.filter);
-		params.filter = strfilter__new(str, &err);
 		if (!params.filter) {
+			params.filter = strfilter__new(str, &err);
+			if (!params.filter)
+				ret = err ? -EINVAL : -ENOMEM;
+		} else
+			ret = strfilter__or(params.filter, str, &err);
+
+		if (ret == -EINVAL) {
 			pr_err("Filter parse error at %td.\n", err - str + 1);
 			pr_err("Source: \"%s\"\n", str);
 			pr_err("         %*c\n", (int)(err - str + 1), '^');
-			return -EINVAL;
 		}
 	}
 
-	return 0;
+	return ret;
 }
 
 static int init_params(void)

118 lines not on this page · raw message

index 416c10f..5995d81 100644
@@ -2146,7 +2146,23 @@ static int show_perf_probe_event(struct perf_probe_event *pev,
 	return ret;
 }
 
-static int __show_perf_probe_events(int fd, bool is_kprobe)
+static bool filter_probe_trace_event(struct probe_trace_event *tev,
+				     struct strfilter *filter)
+{
+	char tmp[128];
+
+	/* At first, check the event name itself */
+	if (strfilter__compare(filter, tev->event))
+		return true;
+
+	/* Next, check the combination of name and group */
+	if (e_snprintf(tmp, 128, "%s:%s", tev->group, tev->event) < 0)
+		return false;
+	return strfilter__compare(filter, tmp);
+}
+
+static int __show_perf_probe_events(int fd, bool is_kprobe,
+				    struct strfilter *filter)
 {
 	int ret = 0;
 	struct probe_trace_event tev;

@@ -2164,12 +2180,15 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 	strlist__for_each(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret >= 0) {
+			if (!filter_probe_trace_event(&tev, filter))
+				goto next;
 			ret = convert_to_perf_probe_event(&tev, &pev,
 								is_kprobe);
 			if (ret >= 0)
 				ret = show_perf_probe_event(&pev,
 							    tev.point.module);
 		}
+next:
 		clear_perf_probe_event(&pev);
 		clear_probe_trace_event(&tev);
 		if (ret < 0)

@@ -2181,7 +2200,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 }
 
 /* List up current perf-probe events */
-int show_perf_probe_events(void)
+int show_perf_probe_events(struct strfilter *filter)
 {
 	int kp_fd, up_fd, ret;
 

@@ -2193,7 +2212,7 @@ int show_perf_probe_events(void)
 
 	kp_fd = open_kprobe_events(false);
 	if (kp_fd >= 0) {
-		ret = __show_perf_probe_events(kp_fd, true);
+		ret = __show_perf_probe_events(kp_fd, true, filter);
 		close(kp_fd);
 		if (ret < 0)
 			goto out;

@@ -2207,7 +2226,7 @@ int show_perf_probe_events(void)
 	}
 
 	if (up_fd >= 0) {
-		ret = __show_perf_probe_events(up_fd, false);
+		ret = __show_perf_probe_events(up_fd, false, filter);
 		close(up_fd);
 	}
 out:

index 180f142..ec13362 100644
@@ -127,7 +127,7 @@ extern const char *kernel_get_module_path(const char *module);
 extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
 				 int max_probe_points, bool force_add);
 extern int del_perf_probe_events(struct strlist *dellist);
-extern int show_perf_probe_events(void);
+extern int show_perf_probe_events(struct strfilter *filter);
 extern int show_line_range(struct line_range *lr, const char *module,
 			   bool user);
 extern int show_available_vars(struct perf_probe_event *pevs, int npevs,

index 4f0f384..3649eec 100644
@@ -10,6 +10,7 @@
 #include "util/header.h"
 #include "util/session.h"
 #include "util/tool.h"
+#include "util/callchain.h"
 
 #include "util/parse-options.h"
 #include "util/trace-event.h"

@@ -21,6 +22,7 @@
 #include <linux/rbtree.h>
 #include <linux/string.h>
 #include <locale.h>
+#include <regex.h>
 
 static int	kmem_slab;
 static int	kmem_page;

@@ -241,6 +243,7 @@ static unsigned long nr_page_fails;
 static unsigned long nr_page_nomatch;
 
 static bool use_pfn;
+static struct perf_session *kmem_session;
 
 #define MAX_MIGRATE_TYPES  6
 #define MAX_PAGE_ORDER     11

@@ -250,6 +253,7 @@ static int order_stats[MAX_PAGE_ORDER][MAX_MIGRATE_TYPES];
 struct page_stat {
 	struct rb_node 	node;
 	u64 		page;
+	u64 		callsite;
 	int 		order;
 	unsigned 	gfp_flags;
 	unsigned 	migrate_type;

@@ -262,8 +266,144 @@ struct page_stat {
 static struct rb_root page_tree;
 static struct rb_root page_alloc_tree;
 static struct rb_root page_alloc_sorted;
+static struct rb_root page_caller_tree;
+static struct rb_root page_caller_sorted;
 
-static struct page_stat *search_page(unsigned long page, bool create)
+struct alloc_func {
+	u64 start;
+	u64 end;
+	char *name;
+};
+
+static int nr_alloc_funcs;
+static struct alloc_func *alloc_func_list;
+
+static int funcmp(const void *a, const void *b)
+{
+	const struct alloc_func *fa = a;
+	const struct alloc_func *fb = b;
+
+	if (fa->start > fb->start)
+		return 1;
+	else
+		return -1;
+}
+
+static int callcmp(const void *a, const void *b)
+{
+	const struct alloc_func *fa = a;
+	const struct alloc_func *fb = b;
+
+	if (fb->start <= fa->start && fa->end < fb->end)
+		return 0;
+
+	if (fa->start > fb->start)
+		return 1;
+	else
+		return -1;
+}
+
+static int build_alloc_func_list(void)
+{
+	int ret;
+	struct map *kernel_map;
+	struct symbol *sym;
+	struct rb_node *node;
+	struct alloc_func *func;
+	struct machine *machine = &kmem_session->machines.host;
+	regex_t alloc_func_regex;
+	const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?";
+
+	ret = regcomp(&alloc_func_regex, pattern, REG_EXTENDED);
+	if (ret) {
+		char err[BUFSIZ];
+
+		regerror(ret, &alloc_func_regex, err, sizeof(err));
+		pr_err("Invalid regex: %s\n%s", pattern, err);
+		return -EINVAL;
+	}
+
+	kernel_map = machine->vmlinux_maps[MAP__FUNCTION];
+	if (map__load(kernel_map, NULL) < 0) {
+		pr_err("cannot load kernel map\n");
+		return -ENOENT;
+	}
+
+	map__for_each_symbol(kernel_map, sym, node) {
+		if (regexec(&alloc_func_regex, sym->name, 0, NULL, 0))
+			continue;
+
+		func = realloc(alloc_func_list,
+			       (nr_alloc_funcs + 1) * sizeof(*func));
+		if (func == NULL)
+			return -ENOMEM;
+
+		pr_debug("alloc func: %s\n", sym->name);
+		func[nr_alloc_funcs].start = sym->start;
+		func[nr_alloc_funcs].end   = sym->end;
+		func[nr_alloc_funcs].name  = sym->name;
+
+		alloc_func_list = func;
+		nr_alloc_funcs++;
+	}
+
+	qsort(alloc_func_list, nr_alloc_funcs, sizeof(*func), funcmp);
+
+	regfree(&alloc_func_regex);
+	return 0;
+}
+
+/*
+ * Find first non-memory allocation function from callchain.
+ * The allocation functions are in the 'alloc_func_list'.
+ */
+static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample)
+{
+	struct addr_location al;
+	struct machine *machine = &kmem_session->machines.host;
+	struct callchain_cursor_node *node;
+
+	if (alloc_func_list == NULL) {
+		if (build_alloc_func_list() < 0)
+			goto out;
+	}
+
+	al.thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+	sample__resolve_callchain(sample, NULL, evsel, &al, 16);
+
+	callchain_cursor_commit(&callchain_cursor);
+	while (true) {
+		struct alloc_func key, *caller;
+		u64 addr;
+
+		node = callchain_cursor_current(&callchain_cursor);
+		if (node == NULL)
+			break;
+
+		key.start = key.end = node->ip;
+		caller = bsearch(&key, alloc_func_list, nr_alloc_funcs,
+				 sizeof(key), callcmp);
+		if (!caller) {
+			/* found */
+			if (node->map)
+				addr = map__unmap_ip(node->map, node->ip);
+			else
+				addr = node->ip;
+
+			return addr;
+		} else
+			pr_debug3("skipping alloc function: %s\n", caller->name);
+
+		callchain_cursor_advance(&callchain_cursor);
+	}
+
+out:
+	pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip);
+	return sample->ip;
+}
+
+static struct page_stat *
+__page_stat__findnew_page(u64 page, bool create)
 {
 	struct rb_node **node = &page_tree.rb_node;
 	struct rb_node *parent = NULL;

@@ -298,6 +438,16 @@ static struct page_stat *search_page(unsigned long page, bool create)
 	return data;
 }
 
+static struct page_stat *page_stat__find_page(u64 page)
+{
+	return __page_stat__findnew_page(page, false);
+}
+
+static struct page_stat *page_stat__findnew_page(u64 page)
+{
+	return __page_stat__findnew_page(page, true);
+}
+
 static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
 {
 	if (a->page > b->page)

@@ -319,7 +469,8 @@ static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
 	return 0;
 }
 
-static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool create)
+static struct page_stat *
+__page_stat__findnew_alloc(struct page_stat *pstat, bool create)
 {
 	struct rb_node **node = &page_alloc_tree.rb_node;
 	struct rb_node *parent = NULL;

@@ -357,6 +508,62 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool cr
 	return data;
 }
 
+static struct page_stat *page_stat__find_alloc(struct page_stat *pstat)
+{
+	return __page_stat__findnew_alloc(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_alloc(struct page_stat *pstat)
+{
+	return __page_stat__findnew_alloc(pstat, true);
+}
+
+static struct page_stat *
+__page_stat__findnew_caller(u64 callsite, bool create)
+{
+	struct rb_node **node = &page_caller_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct page_stat *data;
+
+	while (*node) {
+		s64 cmp;
+
+		parent = *node;
+		data = rb_entry(*node, struct page_stat, node);
+
+		cmp = data->callsite - callsite;
+		if (cmp < 0)
+			node = &parent->rb_left;
+		else if (cmp > 0)
+			node = &parent->rb_right;
+		else
+			return data;
+	}
+
+	if (!create)
+		return NULL;
+
+	data = zalloc(sizeof(*data));
+	if (data != NULL) {
+		data->callsite = callsite;
+
+		rb_link_node(&data->node, parent, node);
+		rb_insert_color(&data->node, &page_caller_tree);
+	}
+
+	return data;
+}
+
+static struct page_stat *page_stat__find_caller(u64 callsite)
+{
+	return __page_stat__findnew_caller(callsite, false);
+}
+
+static struct page_stat *page_stat__findnew_caller(u64 callsite)
+{
+	return __page_stat__findnew_caller(callsite, true);
+}
+
 static bool valid_page(u64 pfn_or_page)
 {
 	if (use_pfn && pfn_or_page == -1UL)

@@ -375,6 +582,7 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	unsigned int migrate_type = perf_evsel__intval(evsel, sample,
 						       "migratetype");
 	u64 bytes = kmem_page_size << order;
+	u64 callsite;
 	struct page_stat *pstat;
 	struct page_stat this = {
 		.order = order,

@@ -397,25 +605,40 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 		return 0;
 	}
 
+	callsite = find_callsite(evsel, sample);
+
 	/*
 	 * This is to find the current page (with correct gfp flags and
 	 * migrate type) at free event.
 	 */
-	pstat = search_page(page, true);
+	pstat = page_stat__findnew_page(page);
 	if (pstat == NULL)
 		return -ENOMEM;
 
 	pstat->order = order;
 	pstat->gfp_flags = gfp_flags;
 	pstat->migrate_type = migrate_type;
+	pstat->callsite = callsite;
 
 	this.page = page;
-	pstat = search_page_alloc_stat(&this, true);
+	pstat = page_stat__findnew_alloc(&this);
 	if (pstat == NULL)
 		return -ENOMEM;
 
 	pstat->nr_alloc++;
 	pstat->alloc_bytes += bytes;
+	pstat->callsite = callsite;
+
+	pstat = page_stat__findnew_caller(callsite);
+	if (pstat == NULL)
+		return -ENOMEM;
+
+	pstat->order = order;
+	pstat->gfp_flags = gfp_flags;
+	pstat->migrate_type = migrate_type;
+
+	pstat->nr_alloc++;
+	pstat->alloc_bytes += bytes;
 
 	order_stats[order][migrate_type]++;
 

@@ -441,7 +664,7 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	nr_page_frees++;
 	total_page_free_bytes += bytes;
 
-	pstat = search_page(page, false);
+	pstat = page_stat__find_page(page);
 	if (pstat == NULL) {
 		pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
 			  page, order);

@@ -455,11 +678,19 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	this.page = page;
 	this.gfp_flags = pstat->gfp_flags;
 	this.migrate_type = pstat->migrate_type;
+	this.callsite = pstat->callsite;
 
 	rb_erase(&pstat->node, &page_tree);
 	free(pstat);
 
-	pstat = search_page_alloc_stat(&this, false);
+	pstat = page_stat__find_alloc(&this);
+	if (pstat == NULL)
+		return -ENOENT;
+
+	pstat->nr_free++;
+	pstat->free_bytes += bytes;
+
+	pstat = page_stat__find_caller(this.callsite);
 	if (pstat == NULL)
 		return -ENOENT;
 

@@ -576,41 +807,89 @@ static const char * const migrate_type_str[] = {
 	"UNKNOWN",
 };
 
-static void __print_page_result(struct rb_root *root,
-				struct perf_session *session __maybe_unused,
-				int n_lines)
+static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 {
-	struct rb_node *next = rb_first(root);
+	struct rb_node *next = rb_first(&page_alloc_sorted);
+	struct machine *machine = &session->machines.host;
 	const char *format;
 
-	printf("\n%.80s\n", graph_dotted_line);
-	printf(" %-16s | Total alloc (KB) | Hits      | Order | Mig.type | GFP flags\n",
+	printf("\n%.105s\n", graph_dotted_line);
+	printf(" %-16s | Total alloc (KB) | Hits      | Order | Mig.type | GFP flags | Callsite\n",
 	       use_pfn ? "PFN" : "Page");
-	printf("%.80s\n", graph_dotted_line);
+	printf("%.105s\n", graph_dotted_line);
 
 	if (use_pfn)
-		format = " %16llu | %'16llu | %'9d | %5d | %8s |  %08lx\n";
+		format = " %16llu | %'16llu | %'9d | %5d | %8s |  %08lx | %s\n";
 	else
-		format = " %016llx | %'16llu | %'9d | %5d | %8s |  %08lx\n";
+		format = " %016llx | %'16llu | %'9d | %5d | %8s |  %08lx | %s\n";
 
 	while (next && n_lines--) {
 		struct page_stat *data;
+		struct symbol *sym;
+		struct map *map;
+		char buf[32];
+		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
+		sym = machine__find_kernel_function(machine, data->callsite,
+						    &map, NULL);
+		if (sym && sym->name)
+			caller = sym->name;
+		else
+			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
 
 		printf(format, (unsigned long long)data->page,
 		       (unsigned long long)data->alloc_bytes / 1024,
 		       data->nr_alloc, data->order,
 		       migrate_type_str[data->migrate_type],
-		       (unsigned long)data->gfp_flags);
+		       (unsigned long)data->gfp_flags, caller);
 
 		next = rb_next(next);
 	}
 
 	if (n_lines == -1)
-		printf(" ...              | ...              | ...       | ...   | ...      | ...     \n");
+		printf(" ...              | ...              | ...       | ...   | ...      | ...       | ...\n");
 
-	printf("%.80s\n", graph_dotted_line);
+	printf("%.105s\n", graph_dotted_line);
+}
+
+static void __print_page_caller_result(struct perf_session *session, int n_lines)
+{
+	struct rb_node *next = rb_first(&page_caller_sorted);
+	struct machine *machine = &session->machines.host;
+
+	printf("\n%.105s\n", graph_dotted_line);
+	printf(" Total alloc (KB) | Hits      | Order | Mig.type | GFP flags | Callsite\n");
+	printf("%.105s\n", graph_dotted_line);
+
+	while (next && n_lines--) {
+		struct page_stat *data;
+		struct symbol *sym;
+		struct map *map;
+		char buf[32];
+		char *caller = buf;
+
+		data = rb_entry(next, struct page_stat, node);
+		sym = machine__find_kernel_function(machine, data->callsite,
+						    &map, NULL);
+		if (sym && sym->name)
+			caller = sym->name;
+		else
+			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
+
+		printf(" %'16llu | %'9d | %5d | %8s |  %08lx | %s\n",
+		       (unsigned long long)data->alloc_bytes / 1024,
+		       data->nr_alloc, data->order,
+		       migrate_type_str[data->migrate_type],
+		       (unsigned long)data->gfp_flags, caller);
+
+		next = rb_next(next);
+	}
+
+	if (n_lines == -1)
+		printf(" ...              | ...       | ...   | ...      | ...       | ...\n");
+
+	printf("%.105s\n", graph_dotted_line);
 }
 
 static void print_slab_summary(void)

@@ -682,8 +961,10 @@ static void print_slab_result(struct perf_session *session)
 
 static void print_page_result(struct perf_session *session)
 {
+	if (caller_flag)
+		__print_page_caller_result(session, caller_lines);
 	if (alloc_flag)
-		__print_page_result(&page_alloc_sorted, session, alloc_lines);
+		__print_page_alloc_result(session, alloc_lines);
 	print_page_summary();
 }
 

@@ -802,6 +1083,7 @@ static void sort_result(void)
 	}
 	if (kmem_page) {
 		__sort_page_result(&page_alloc_tree, &page_alloc_sorted);
+		__sort_page_result(&page_caller_tree, &page_caller_sorted);
 	}
 }
 

@@ -1084,7 +1366,7 @@ static int __cmd_record(int argc, const char **argv)
 	if (kmem_slab)
 		rec_argc += ARRAY_SIZE(slab_events);
 	if (kmem_page)
-		rec_argc += ARRAY_SIZE(page_events);
+		rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
 
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 

@@ -1099,6 +1381,8 @@ static int __cmd_record(int argc, const char **argv)
 			rec_argv[i] = strdup(slab_events[j]);
 	}
 	if (kmem_page) {
+		rec_argv[i++] = strdup("-g");
+
 		for (j = 0; j < ARRAY_SIZE(page_events); j++, i++)
 			rec_argv[i] = strdup(page_events[j]);
 	}

@@ -1159,7 +1443,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	file.path = input_name;
 
-	session = perf_session__new(&file, false, &perf_kmem);
+	kmem_session = session = perf_session__new(&file, false, &perf_kmem);
 	if (session == NULL)
 		return -1;
 

@@ -1172,6 +1456,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 
 		kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
+		symbol_conf.use_callchain = true;
 	}
 
 	symbol__init(&session->header.env);

616 lines not on this page · raw message

217 lines not on this page · raw message

index 7ead942..1c66895 100644
@@ -581,6 +581,176 @@ static bool valid_page(u64 pfn_or_page)
 	return true;
 }
 
+struct gfp_flag {
+	unsigned int flags;
+	char *compact_str;
+	char *human_readable;
+};
+
+static struct gfp_flag *gfps;
+static int nr_gfps;
+
+static int gfpcmp(const void *a, const void *b)
+{
+	const struct gfp_flag *fa = a;
+	const struct gfp_flag *fb = b;
+
+	return fa->flags - fb->flags;
+}
+
+/* see include/trace/events/gfpflags.h */
+static const struct {
+	const char *original;
+	const char *compact;
+} gfp_compact_table[] = {
+	{ "GFP_TRANSHUGE",		"THP" },
+	{ "GFP_HIGHUSER_MOVABLE",	"HUM" },
+	{ "GFP_HIGHUSER",		"HU" },
+	{ "GFP_USER",			"U" },
+	{ "GFP_TEMPORARY",		"TMP" },
+	{ "GFP_KERNEL",			"K" },
+	{ "GFP_NOFS",			"NF" },
+	{ "GFP_ATOMIC",			"A" },
+	{ "GFP_NOIO",			"NI" },
+	{ "GFP_HIGH",			"H" },
+	{ "GFP_WAIT",			"W" },
+	{ "GFP_IO",			"I" },
+	{ "GFP_COLD",			"CO" },
+	{ "GFP_NOWARN",			"NWR" },
+	{ "GFP_REPEAT",			"R" },
+	{ "GFP_NOFAIL",			"NF" },
+	{ "GFP_NORETRY",		"NR" },
+	{ "GFP_COMP",			"C" },
+	{ "GFP_ZERO",			"Z" },
+	{ "GFP_NOMEMALLOC",		"NMA" },
+	{ "GFP_MEMALLOC",		"MA" },
+	{ "GFP_HARDWALL",		"HW" },
+	{ "GFP_THISNODE",		"TN" },
+	{ "GFP_RECLAIMABLE",		"RC" },
+	{ "GFP_MOVABLE",		"M" },
+	{ "GFP_NOTRACK",		"NT" },
+	{ "GFP_NO_KSWAPD",		"NK" },
+	{ "GFP_OTHER_NODE",		"ON" },
+	{ "GFP_NOWAIT",			"NW" },
+};
+
+static size_t max_gfp_len;
+
+static char *compact_gfp_flags(char *gfp_flags)
+{
+	char *orig_flags = strdup(gfp_flags);
+	char *new_flags = NULL;
+	char *str, *pos;
+	size_t len = 0;
+
+	if (orig_flags == NULL)
+		return NULL;
+
+	str = strtok_r(orig_flags, "|", &pos);
+	while (str) {
+		size_t i;
+		char *new;
+		const char *cpt;
+
+		for (i = 0; i < ARRAY_SIZE(gfp_compact_table); i++) {
+			if (strcmp(gfp_compact_table[i].original, str))
+				continue;
+
+			cpt = gfp_compact_table[i].compact;
+			new = realloc(new_flags, len + strlen(cpt) + 2);
+			if (new == NULL) {
+				free(new_flags);
+				return NULL;
+			}
+
+			new_flags = new;
+
+			if (!len) {
+				strcpy(new_flags, cpt);
+			} else {
+				strcat(new_flags, "|");
+				strcat(new_flags, cpt);
+				len++;
+			}
+
+			len += strlen(cpt);
+		}
+
+		str = strtok_r(NULL, "|", &pos);
+	}
+
+	if (max_gfp_len < len)
+		max_gfp_len = len;
+
+	free(orig_flags);
+	return new_flags;
+}
+
+static char *compact_gfp_string(unsigned long gfp_flags)
+{
+	struct gfp_flag key = {
+		.flags = gfp_flags,
+	};
+	struct gfp_flag *gfp;
+
+	gfp = bsearch(&key, gfps, nr_gfps, sizeof(*gfps), gfpcmp);
+	if (gfp)
+		return gfp->compact_str;
+
+	return NULL;
+}
+
+static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample,
+			   unsigned int gfp_flags)
+{
+	struct pevent_record record = {
+		.cpu = sample->cpu,
+		.data = sample->raw_data,
+		.size = sample->raw_size,
+	};
+	struct trace_seq seq;
+	char *str, *pos;
+
+	if (nr_gfps) {
+		struct gfp_flag key = {
+			.flags = gfp_flags,
+		};
+
+		if (bsearch(&key, gfps, nr_gfps, sizeof(*gfps), gfpcmp))
+			return 0;
+	}
+
+	trace_seq_init(&seq);
+	pevent_event_info(&seq, evsel->tp_format, &record);
+
+	str = strtok_r(seq.buffer, " ", &pos);
+	while (str) {
+		if (!strncmp(str, "gfp_flags=", 10)) {
+			struct gfp_flag *new;
+
+			new = realloc(gfps, (nr_gfps + 1) * sizeof(*gfps));
+			if (new == NULL)
+				return -ENOMEM;
+
+			gfps = new;
+			new += nr_gfps++;
+
+			new->flags = gfp_flags;
+			new->human_readable = strdup(str + 10);
+			new->compact_str = compact_gfp_flags(str + 10);
+			if (!new->human_readable || !new->compact_str)
+				return -ENOMEM;
+
+			qsort(gfps, nr_gfps, sizeof(*gfps), gfpcmp);
+		}
+
+		str = strtok_r(NULL, " ", &pos);
+	}
+
+	trace_seq_destroy(&seq);
+	return 0;
+}
+
 static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 						struct perf_sample *sample)
 {

@@ -613,6 +783,9 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 		return 0;
 	}
 
+	if (parse_gfp_flags(evsel, sample, gfp_flags) < 0)
+		return -1;
+
 	callsite = find_callsite(evsel, sample);
 
 	/*

@@ -832,16 +1005,18 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 	struct rb_node *next = rb_first(&page_alloc_sorted);
 	struct machine *machine = &session->machines.host;
 	const char *format;
+	int gfp_len = max(strlen("GFP flags"), max_gfp_len);
 
 	printf("\n%.105s\n", graph_dotted_line);
-	printf(" %-16s | %5s alloc (KB) | Hits      | Order | Mig.type | GFP flags | Callsite\n",
-	       use_pfn ? "PFN" : "Page", live_page ? "Live" : "Total");
+	printf(" %-16s | %5s alloc (KB) | Hits      | Order | Mig.type | %-*s | Callsite\n",
+	       use_pfn ? "PFN" : "Page", live_page ? "Live" : "Total",
+	       gfp_len, "GFP flags");
 	printf("%.105s\n", graph_dotted_line);
 
 	if (use_pfn)
-		format = " %16llu | %'16llu | %'9d | %5d | %8s |  %08lx | %s\n";
+		format = " %16llu | %'16llu | %'9d | %5d | %8s | %-*s | %s\n";
 	else
-		format = " %016llx | %'16llu | %'9d | %5d | %8s |  %08lx | %s\n";
+		format = " %016llx | %'16llu | %'9d | %5d | %8s | %-*s | %s\n";
 
 	while (next && n_lines--) {
 		struct page_stat *data;

@@ -862,13 +1037,15 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 		       (unsigned long long)data->alloc_bytes / 1024,
 		       data->nr_alloc, data->order,
 		       migrate_type_str[data->migrate_type],
-		       (unsigned long)data->gfp_flags, caller);
+		       gfp_len, compact_gfp_string(data->gfp_flags), caller);
 
 		next = rb_next(next);
 	}
 
-	if (n_lines == -1)
-		printf(" ...              | ...              | ...       | ...   | ...      | ...       | ...\n");
+	if (n_lines == -1) {
+		printf(" ...              | ...              | ...       | ...   | ...      | %-*s | ...\n",
+		       gfp_len, "...");
+	}
 
 	printf("%.105s\n", graph_dotted_line);
 }

@@ -877,10 +1054,11 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
 {
 	struct rb_node *next = rb_first(&page_caller_sorted);
 	struct machine *machine = &session->machines.host;
+	int gfp_len = max(strlen("GFP flags"), max_gfp_len);
 
 	printf("\n%.105s\n", graph_dotted_line);
-	printf(" %5s alloc (KB) | Hits      | Order | Mig.type | GFP flags | Callsite\n",
-	       live_page ? "Live" : "Total");
+	printf(" %5s alloc (KB) | Hits      | Order | Mig.type | %-*s | Callsite\n",
+	       live_page ? "Live" : "Total", gfp_len, "GFP flags");
 	printf("%.105s\n", graph_dotted_line);
 
 	while (next && n_lines--) {

@@ -898,21 +1076,37 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
 		else
 			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
 
-		printf(" %'16llu | %'9d | %5d | %8s |  %08lx | %s\n",
+		printf(" %'16llu | %'9d | %5d | %8s | %-*s | %s\n",
 		       (unsigned long long)data->alloc_bytes / 1024,
 		       data->nr_alloc, data->order,
 		       migrate_type_str[data->migrate_type],
-		       (unsigned long)data->gfp_flags, caller);
+		       gfp_len, compact_gfp_string(data->gfp_flags), caller);
 
 		next = rb_next(next);
 	}
 
-	if (n_lines == -1)
-		printf(" ...              | ...       | ...   | ...      | ...       | ...\n");
+	if (n_lines == -1) {
+		printf(" ...              | ...       | ...   | ...      | %-*s | ...\n",
+		       gfp_len, "...");
+	}
 
 	printf("%.105s\n", graph_dotted_line);
 }
 
+static void print_gfp_flags(void)
+{
+	int i;
+
+	printf("#\n");
+	printf("# GFP flags\n");
+	printf("# ---------\n");
+	for (i = 0; i < nr_gfps; i++) {
+		printf("# %08x: %*s: %s\n", gfps[i].flags,
+		       (int) max_gfp_len, gfps[i].compact_str,
+		       gfps[i].human_readable);
+	}
+}
+
 static void print_slab_summary(void)
 {
 	printf("\nSUMMARY (SLAB allocator)");

@@ -982,6 +1176,8 @@ static void print_slab_result(struct perf_session *session)
 
 static void print_page_result(struct perf_session *session)
 {
+	if (caller_flag || alloc_flag)
+		print_gfp_flags();
 	if (caller_flag)
 		__print_page_caller_result(session, caller_lines);
 	if (alloc_flag)

index 1c66895..828b728 100644
@@ -28,6 +28,10 @@ static int	kmem_slab;
 static int	kmem_page;
 
 static long	kmem_page_size;
+static enum {
+	KMEM_SLAB,
+	KMEM_PAGE,
+} kmem_default = KMEM_SLAB;  /* for backward compatibility */
 
 struct alloc_stat;
 typedef int (*sort_fn_t)(void *, void *);

@@ -1710,7 +1714,8 @@ static int parse_sort_opt(const struct option *opt __maybe_unused,
 	if (!arg)
 		return -1;
 
-	if (kmem_page > kmem_slab) {
+	if (kmem_page > kmem_slab ||
+	    (kmem_page == 0 && kmem_slab == 0 && kmem_default == KMEM_PAGE)) {
 		if (caller_flag > alloc_flag)
 			return setup_page_sorting(&page_caller_sort, arg);
 		else

@@ -1826,6 +1831,22 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
+static int kmem_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "kmem.default")) {
+		if (!strcmp(value, "slab"))
+			kmem_default = KMEM_SLAB;
+		else if (!strcmp(value, "page"))
+			kmem_default = KMEM_PAGE;
+		else
+			pr_err("invalid default value ('slab' or 'page' required): %s\n",
+			       value);
+		return 0;
+	}
+
+	return perf_default_config(var, value, cb);
+}
+
 int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const char * const default_slab_sort = "frag,hit,bytes";

@@ -1862,14 +1883,19 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	struct perf_session *session;
 	int ret = -1;
 
+	perf_config(kmem_config, NULL);
 	argc = parse_options_subcommand(argc, argv, kmem_options,
 					kmem_subcommands, kmem_usage, 0);
 
 	if (!argc)
 		usage_with_options(kmem_usage, kmem_options);
 
-	if (kmem_slab == 0 && kmem_page == 0)
-		kmem_slab = 1;  /* for backward compatibility */
+	if (kmem_slab == 0 && kmem_page == 0) {
+		if (kmem_default == KMEM_SLAB)
+			kmem_slab = 1;
+		else
+			kmem_page = 1;
+	}
 
 	if (!strncmp(argv[0], "rec", 3)) {
 		symbol__init(NULL);