24 files changed, 219 insertions, 354 deletions

diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 0784a9420528..cadbdc90a5cb 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -116,11 +116,6 @@ struct annotation {
 	struct annotated_source *src;
 };
 
-struct sannotation {
-	struct annotation annotation;
-	struct symbol	  symbol;
-};
-
 static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
 {
 	return (((void *)&notes->src->histograms) +
@@ -129,8 +124,7 @@ static inline struct sym_hist *annotation__histogram(struct annotation *notes, i
 
 static inline struct annotation *symbol__annotation(struct symbol *sym)
 {
-	struct sannotation *a = container_of(sym, struct sannotation, symbol);
-	return &a->annotation;
+	return (void *)sym - symbol_conf.priv_size;
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e8d79e5bfaf7..0c72680a977f 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -410,21 +410,18 @@ int perf_session__cache_build_ids(struct perf_session *session)
 {
 	struct rb_node *nd;
 	int ret;
-	char debugdir[PATH_MAX];
 
 	if (no_buildid_cache)
 		return 0;
 
-	snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
-
-	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
+	if (mkdir(buildid_dir, 0755) != 0 && errno != EEXIST)
 		return -1;
 
-	ret = machine__cache_build_ids(&session->machines.host, debugdir);
+	ret = machine__cache_build_ids(&session->machines.host, buildid_dir);
 
 	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret |= machine__cache_build_ids(pos, debugdir);
+		ret |= machine__cache_build_ids(pos, buildid_dir);
 	}
 	return ret ? -1 : 0;
 }
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 5cf9e1b5989d..d04d770d90f6 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -71,7 +71,9 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
 extern char *perf_pathdup(const char *fmt, ...)
 	__attribute__((format (printf, 1, 2)));
 
+#ifndef __UCLIBC__
 /* Matches the libc/libbsd function attribute so we declare this unconditionally: */
 extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index cf524a35cc84..14e7a123d43b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -77,7 +77,7 @@ int parse_callchain_record_opt(const char *arg)
 				ret = 0;
 			} else
 				pr_err("callchain: No more arguments "
-				       "needed for -g fp\n");
+				       "needed for --call-graph fp\n");
 			break;
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
@@ -841,3 +841,33 @@ char *callchain_list__sym_name(struct callchain_list *cl,
 
 	return bf;
 }
+
+static void free_callchain_node(struct callchain_node *node)
+{
+	struct callchain_list *list, *tmp;
+	struct callchain_node *child;
+	struct rb_node *n;
+
+	list_for_each_entry_safe(list, tmp, &node->val, list) {
+		list_del(&list->list);
+		free(list);
+	}
+
+	n = rb_first(&node->rb_root_in);
+	while (n) {
+		child = container_of(n, struct callchain_node, rb_node_in);
+		n = rb_next(n);
+		rb_erase(&child->rb_node_in, &node->rb_root_in);
+
+		free_callchain_node(child);
+		free(child);
+	}
+}
+
+void free_callchain(struct callchain_root *root)
+{
+	if (!symbol_conf.use_callchain)
+		return;
+
+	free_callchain_node(&root->node);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index dbc08cf5f970..c0ec1acc38e4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -198,4 +198,6 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 char *callchain_list__sym_name(struct callchain_list *cl,
 			       char *bf, size_t bfsize, bool show_dso);
 
+void free_callchain(struct callchain_root *root);
+
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 57ff826f150b..e18f653cd7db 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -522,7 +522,7 @@ static int buildid_dir_command_config(const char *var, const char *value,
 	const char *v;
 
 	/* same dir for all commands */
-	if (!prefixcmp(var, "buildid.") && !strcmp(var + 8, "dir")) {
+	if (!strcmp(var, "buildid.dir")) {
 		v = perf_config_dirname(var, value);
 		if (!v)
 			return -1;
@@ -539,12 +539,14 @@ static void check_buildid_dir_config(void)
 	perf_config(buildid_dir_command_config, &c);
 }
 
-void set_buildid_dir(void)
+void set_buildid_dir(const char *dir)
 {
-	buildid_dir[0] = '\0';
+	if (dir)
+		scnprintf(buildid_dir, MAXPATHLEN-1, "%s", dir);
 
 	/* try config file */
-	check_buildid_dir_config();
+	if (buildid_dir[0] == '\0')
+		check_buildid_dir_config();
 
 	/* default to $HOME/.debug */
 	if (buildid_dir[0] == '\0') {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index cfbe2b99b9aa..cbab1fb77b1d 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -8,6 +8,7 @@
  */
 #include "util.h"
 #include <api/fs/debugfs.h>
+#include <api/fs/fs.h>
 #include <poll.h>
 #include "cpumap.h"
 #include "thread_map.h"
@@ -24,6 +25,7 @@
 
 #include <linux/bitops.h>
 #include <linux/hash.h>
+#include <linux/log2.h>
 
 static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx);
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx);
@@ -892,10 +894,24 @@ out_unmap:
 
 static size_t perf_evlist__mmap_size(unsigned long pages)
 {
-	/* 512 kiB: default amount of unprivileged mlocked memory */
-	if (pages == UINT_MAX)
-		pages = (512 * 1024) / page_size;
-	else if (!is_power_of_2(pages))
+	if (pages == UINT_MAX) {
+		int max;
+
+		if (sysctl__read_int("kernel/perf_event_mlock_kb", &max) < 0) {
+			/*
+			 * Pick a once upon a time good value, i.e. things look
+			 * strange since we can't read a sysctl value, but lets not
+			 * die yet...
+			 */
+			max = 512;
+		} else {
+			max -= (page_size / 1024);
+		}
+
+		pages = (max * 1024) / page_size;
+		if (!is_power_of_2(pages))
+			pages = rounddown_pow_of_two(pages);
+	} else if (!is_power_of_2(pages))
 		return 0;
 
 	return (pages + 1) * page_size;
@@ -932,7 +948,7 @@ static long parse_pages_arg(const char *str, unsigned long min,
 		/* leave number of pages at 0 */
 	} else if (!is_power_of_2(pages)) {
 		/* round pages up to next power of 2 */
-		pages = next_pow2_l(pages);
+		pages = roundup_pow_of_two(pages);
 		if (!pages)
 			return -EINVAL;
 		pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
@@ -1483,6 +1499,37 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 	return 0;
 }
 
+int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size)
+{
+	char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+	int pages_attempted = evlist->mmap_len / 1024, pages_max_per_user, printed = 0;
+
+	switch (err) {
+	case EPERM:
+		sysctl__read_int("kernel/perf_event_mlock_kb", &pages_max_per_user);
+		printed += scnprintf(buf + printed, size - printed,
+				     "Error:\t%s.\n"
+				     "Hint:\tCheck /proc/sys/kernel/perf_event_mlock_kb (%d kB) setting.\n"
+				     "Hint:\tTried using %zd kB.\n",
+				     emsg, pages_max_per_user, pages_attempted);
+
+		if (pages_attempted >= pages_max_per_user) {
+			printed += scnprintf(buf + printed, size - printed,
+					     "Hint:\tTry 'sudo sh -c \"echo %d > /proc/sys/kernel/perf_event_mlock_kb\"', or\n",
+					     pages_max_per_user + pages_attempted);
+		}
+
+		printed += scnprintf(buf + printed, size - printed,
+				     "Hint:\tTry using a smaller -m/--mmap-pages value.");
+		break;
+	default:
+		scnprintf(buf, size, "%s", emsg);
+		break;
+	}
+
+	return 0;
+}
+
 void perf_evlist__to_front(struct perf_evlist *evlist,
 			   struct perf_evsel *move_evsel)
 {
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 649b0c597283..0ba93f67ab94 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -185,6 +185,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp);
 
 int perf_evlist__strerror_tp(struct perf_evlist *evlist, int err, char *buf, size_t size);
 int perf_evlist__strerror_open(struct perf_evlist *evlist, int err, char *buf, size_t size);
+int perf_evlist__strerror_mmap(struct perf_evlist *evlist, int err, char *buf, size_t size);
 
 static inline unsigned int perf_mmap__read_head(struct perf_mmap *mm)
 {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6e88b9e395df..182395546ddc 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -6,6 +6,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "annotate.h"
+#include "ui/progress.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -303,7 +304,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 	size_t callchain_size = 0;
 	struct hist_entry *he;
 
-	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+	if (symbol_conf.use_callchain)
 		callchain_size = sizeof(struct callchain_root);
 
 	he = zalloc(sizeof(*he) + callchain_size);
@@ -736,7 +737,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
 	iter->he = he;
 	he_cache[iter->curr++] = he;
 
-	callchain_append(he->callchain, &callchain_cursor, sample->period);
+	hist_entry__append_callchain(he, sample);
 
 	/*
 	 * We need to re-initialize the cursor since callchain_append()
@@ -809,7 +810,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
 	iter->he = he;
 	he_cache[iter->curr++] = he;
 
-	callchain_append(he->callchain, &cursor, sample->period);
+	if (symbol_conf.use_callchain)
+		callchain_append(he->callchain, &cursor, sample->period);
 	return 0;
 }
 
@@ -945,6 +947,7 @@ void hist_entry__free(struct hist_entry *he)
 	zfree(&he->mem_info);
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
+	free_callchain(he->callchain);
 	free(he);
 }
 
@@ -987,6 +990,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 		else
 			p = &(*p)->rb_right;
 	}
+	hists->nr_entries++;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, root);
@@ -1024,7 +1028,10 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 	if (!sort__need_collapse)
 		return;
 
+	hists->nr_entries = 0;
+
 	root = hists__get_rotate_entries_in(hists);
+
 	next = rb_first(root);
 
 	while (next) {
@@ -1119,7 +1126,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 	rb_insert_color(&he->rb_node, entries);
 }
 
-void hists__output_resort(struct hists *hists)
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 {
 	struct rb_root *root;
 	struct rb_node *next;
@@ -1148,6 +1155,9 @@ void hists__output_resort(struct hists *hists)
 
 		if (!n->filtered)
 			hists__calc_col_len(hists, n);
+
+		if (prog)
+			ui_progress__update(prog, 1);
 	}
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d0ef9a19a744..46bd50344f85 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -121,7 +121,7 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
 			      struct hists *hists);
 void hist_entry__free(struct hist_entry *);
 
-void hists__output_resort(struct hists *hists);
+void hists__output_resort(struct hists *hists, struct ui_progress *prog);
 void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
diff --git a/tools/perf/util/hweight.c b/tools/perf/util/hweight.c
deleted file mode 100644
index 5c1d0d099f0d..000000000000
--- a/tools/perf/util/hweight.c
+++ /dev/null
@@ -1,31 +0,0 @@
-#include <linux/bitops.h>
-
-/**
- * hweightN - returns the hamming weight of a N-bit word
- * @x: the word to weigh
- *
- * The Hamming Weight of a number is the total number of bits set in it.
- */
-
-unsigned int hweight32(unsigned int w)
-{
-	unsigned int res = w - ((w >> 1) & 0x55555555);
-	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
-	res = (res + (res >> 4)) & 0x0F0F0F0F;
-	res = res + (res >> 8);
-	return (res + (res >> 16)) & 0x000000FF;
-}
-
-unsigned long hweight64(__u64 w)
-{
-#if BITS_PER_LONG == 32
-	return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
-#elif BITS_PER_LONG == 64
-	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
-	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
-	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
-	res = res + (res >> 8);
-	res = res + (res >> 16);
-	return (res + (res >> 32)) & 0x00000000000000FFul;
-#endif
-}
diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h
deleted file mode 100644
index d82b170bb216..000000000000
--- a/tools/perf/util/include/asm/hash.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_GENERIC_HASH_H
-#define __ASM_GENERIC_HASH_H
-
-/* Stub */
-
-#endif /* __ASM_GENERIC_HASH_H */
diff --git a/tools/perf/util/include/asm/hweight.h b/tools/perf/util/include/asm/hweight.h
deleted file mode 100644
index 36cf26d434a5..000000000000
--- a/tools/perf/util/include/asm/hweight.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef PERF_HWEIGHT_H
-#define PERF_HWEIGHT_H
-
-#include <linux/types.h>
-unsigned int hweight32(unsigned int w);
-unsigned long hweight64(__u64 w);
-
-#endif /* PERF_HWEIGHT_H */
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
deleted file mode 100644
index c3294163de17..000000000000
--- a/tools/perf/util/include/linux/bitops.h
+++ /dev/null
@@ -1,162 +0,0 @@
-#ifndef _PERF_LINUX_BITOPS_H_
-#define _PERF_LINUX_BITOPS_H_
-
-#include <linux/kernel.h>
-#include <linux/compiler.h>
-#include <asm/hweight.h>
-
-#ifndef __WORDSIZE
-#define __WORDSIZE (__SIZEOF_LONG__ * 8)
-#endif
-
-#define BITS_PER_LONG __WORDSIZE
-#define BITS_PER_BYTE           8
-#define BITS_TO_LONGS(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
-#define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
-#define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
-#define BIT_WORD(nr)            ((nr) / BITS_PER_LONG)
-#define BIT_MASK(nr)            (1UL << ((nr) % BITS_PER_LONG))
-
-#define for_each_set_bit(bit, addr, size) \
-	for ((bit) = find_first_bit((addr), (size));		\
-	     (bit) < (size);					\
-	     (bit) = find_next_bit((addr), (size), (bit) + 1))
-
-/* same as for_each_set_bit() but use bit as value to start with */
-#define for_each_set_bit_from(bit, addr, size) \
-	for ((bit) = find_next_bit((addr), (size), (bit));	\
-	     (bit) < (size);					\
-	     (bit) = find_next_bit((addr), (size), (bit) + 1))
-
-static inline void set_bit(int nr, unsigned long *addr)
-{
-	addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
-}
-
-static inline void clear_bit(int nr, unsigned long *addr)
-{
-	addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
-}
-
-static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
-{
-	return ((1UL << (nr % BITS_PER_LONG)) &
-		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
-}
-
-static inline unsigned long hweight_long(unsigned long w)
-{
-	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
-}
-
-#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
-
-/**
- * __ffs - find first bit in word.
- * @word: The word to search
- *
- * Undefined if no bit exists, so code should check against 0 first.
- */
-static __always_inline unsigned long __ffs(unsigned long word)
-{
-	int num = 0;
-
-#if BITS_PER_LONG == 64
-	if ((word & 0xffffffff) == 0) {
-		num += 32;
-		word >>= 32;
-	}
-#endif
-	if ((word & 0xffff) == 0) {
-		num += 16;
-		word >>= 16;
-	}
-	if ((word & 0xff) == 0) {
-		num += 8;
-		word >>= 8;
-	}
-	if ((word & 0xf) == 0) {
-		num += 4;
-		word >>= 4;
-	}
-	if ((word & 0x3) == 0) {
-		num += 2;
-		word >>= 2;
-	}
-	if ((word & 0x1) == 0)
-		num += 1;
-	return num;
-}
-
-typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;
-
-/*
- * Find the first set bit in a memory region.
- */
-static inline unsigned long
-find_first_bit(const unsigned long *addr, unsigned long size)
-{
-	long_alias_t *p = (long_alias_t *) addr;
-	unsigned long result = 0;
-	unsigned long tmp;
-
-	while (size & ~(BITS_PER_LONG-1)) {
-		if ((tmp = *(p++)))
-			goto found;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-	}
-	if (!size)
-		return result;
-
-	tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
-	if (tmp == 0UL)		/* Are any bits set? */
-		return result + size;	/* Nope. */
-found:
-	return result + __ffs(tmp);
-}
-
-/*
- * Find the next set bit in a memory region.
- */
-static inline unsigned long
-find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset)
-{
-	const unsigned long *p = addr + BITOP_WORD(offset);
-	unsigned long result = offset & ~(BITS_PER_LONG-1);
-	unsigned long tmp;
-
-	if (offset >= size)
-		return size;
-	size -= result;
-	offset %= BITS_PER_LONG;
-	if (offset) {
-		tmp = *(p++);
-		tmp &= (~0UL << offset);
-		if (size < BITS_PER_LONG)
-			goto found_first;
-		if (tmp)
-			goto found_middle;
-		size -= BITS_PER_LONG;
-		result += BITS_PER_LONG;
-	}
-	while (size & ~(BITS_PER_LONG-1)) {
-		if ((tmp = *(p++)))
-			goto found_middle;
-		result += BITS_PER_LONG;
-		size -= BITS_PER_LONG;
-	}
-	if (!size)
-		return result;
-	tmp = *p;
-
-found_first:
-	tmp &= (~0UL >> (BITS_PER_LONG - size));
-	if (tmp == 0UL)		/* Are any bits set? */
-		return result + size;	/* Nope. */
-found_middle:
-	return result + __ffs(tmp);
-}
-
-#endif
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 15dd0a9691ce..1bca3a9f2b16 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -389,7 +389,6 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
 		rb_insert_color(&th->rb_node, &machine->threads);
-		machine->last_match = th;
 
 		/*
 		 * We have to initialize map_groups separately
@@ -400,9 +399,12 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		 * leader and that would screwed the rb tree.
 		 */
 		if (thread__init_map_groups(th, machine)) {
+			rb_erase(&th->rb_node, &machine->threads);
 			thread__delete(th);
 			return NULL;
 		}
+
+		machine->last_match = th;
 	}
 
 	return th;
@@ -1385,19 +1387,46 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 static int add_callchain_ip(struct thread *thread,
 			    struct symbol **parent,
 			    struct addr_location *root_al,
-			    int cpumode,
+			    bool branch_history,
 			    u64 ip)
 {
 	struct addr_location al;
 
 	al.filtered = 0;
 	al.sym = NULL;
-	if (cpumode == -1)
+	if (branch_history)
 		thread__find_cpumode_addr_location(thread, MAP__FUNCTION,
 						   ip, &al);
-	else
+	else {
+		u8 cpumode = PERF_RECORD_MISC_USER;
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			switch (ip) {
+			case PERF_CONTEXT_HV:
+				cpumode = PERF_RECORD_MISC_HYPERVISOR;
+				break;
+			case PERF_CONTEXT_KERNEL:
+				cpumode = PERF_RECORD_MISC_KERNEL;
+				break;
+			case PERF_CONTEXT_USER:
+				cpumode = PERF_RECORD_MISC_USER;
+				break;
+			default:
+				pr_debug("invalid callchain context: "
+					 "%"PRId64"\n", (s64) ip);
+				/*
+				 * It seems the callchain is corrupted.
+				 * Discard all.
+				 */
+				callchain_cursor_reset(&callchain_cursor);
+				return 1;
+			}
+			return 0;
+		}
 		thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
 				   ip, &al);
+	}
+
 	if (al.sym != NULL) {
 		if (sort__has_parent && !*parent &&
 		    symbol__match_regex(al.sym, &parent_regex))
@@ -1480,11 +1509,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 					     struct addr_location *root_al,
 					     int max_stack)
 {
-	u8 cpumode = PERF_RECORD_MISC_USER;
 	int chain_nr = min(max_stack, (int)chain->nr);
-	int i;
-	int j;
-	int err;
+	int i, j, err;
 	int skip_idx = -1;
 	int first_call = 0;
 
@@ -1542,10 +1568,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 
 		for (i = 0; i < nr; i++) {
 			err = add_callchain_ip(thread, parent, root_al,
-					       -1, be[i].to);
+					       true, be[i].to);
 			if (!err)
 				err = add_callchain_ip(thread, parent, root_al,
-						       -1, be[i].from);
+						       true, be[i].from);
 			if (err == -EINVAL)
 				break;
 			if (err)
@@ -1574,36 +1600,10 @@ check_calls:
 #endif
 		ip = chain->ips[j];
 
-		if (ip >= PERF_CONTEXT_MAX) {
-			switch (ip) {
-			case PERF_CONTEXT_HV:
-				cpumode = PERF_RECORD_MISC_HYPERVISOR;
-				break;
-			case PERF_CONTEXT_KERNEL:
-				cpumode = PERF_RECORD_MISC_KERNEL;
-				break;
-			case PERF_CONTEXT_USER:
-				cpumode = PERF_RECORD_MISC_USER;
-				break;
-			default:
-				pr_debug("invalid callchain context: "
-					 "%"PRId64"\n", (s64) ip);
-				/*
-				 * It seems the callchain is corrupted.
-				 * Discard all.
-				 */
-				callchain_cursor_reset(&callchain_cursor);
-				return 0;
-			}
-			continue;
-		}
+		err = add_callchain_ip(thread, parent, root_al, false, ip);
 
-		err = add_callchain_ip(thread, parent, root_al,
-				       cpumode, ip);
-		if (err == -EINVAL)
-			break;
 		if (err)
-			return err;
+			return (err < 0) ? err : 0;
 	}
 
 	return 0;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 28eb1417cb2a..94a717bf007d 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -495,9 +495,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	}
 
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
-		pr_warning("Probe point '%s' not found.\n",
+		pr_warning("Probe point '%s' not found in debuginfo.\n",
 			   synthesize_perf_probe_point(&pev->point));
-		return -ENOENT;
+		if (need_dwarf)
+			return -ENOENT;
+		return 0;
 	}
 	/* Error path : ntevs < 0 */
 	pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
@@ -2050,9 +2052,11 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
 	pr_debug("Writing event: %s\n", buf);
 	if (!probe_event_dry_run) {
 		ret = write(fd, buf, strlen(buf));
-		if (ret <= 0)
+		if (ret <= 0) {
+			ret = -errno;
 			pr_warning("Failed to write event: %s\n",
 				   strerror_r(errno, sbuf, sizeof(sbuf)));
+		}
 	}
 	free(buf);
 	return ret;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c7918f83b300..b5247d777f0e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -989,8 +989,24 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 	int ret = 0;
 
 #if _ELFUTILS_PREREQ(0, 142)
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+
 	/* Get the call frame information from this dwarf */
-	pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg));
+	elf = dwarf_getelf(dbg->dbg);
+	if (elf == NULL)
+		return -EINVAL;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		return -EINVAL;
+
+	if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+	    shdr.sh_type == SHT_PROGBITS) {
+		pf->cfi = dwarf_getcfi_elf(elf);
+	} else {
+		pf->cfi = dwarf_getcfi(dbg->dbg);
+	}
 #endif
 
 	off = 0;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 16a475a7d492..6c6a6953fa93 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,7 +10,7 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
-util/hweight.c
+../../lib/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index cf69325b985f..8acd0df88b5c 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -137,16 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 
 static int get_max_rate(unsigned int *rate)
 {
-	char path[PATH_MAX];
-	const char *procfs = procfs__mountpoint();
-
-	if (!procfs)
-		return -1;
-
-	snprintf(path, PATH_MAX,
-		 "%s/sys/kernel/perf_event_max_sample_rate", procfs);
-
-	return filename__read_int(path, (int *) rate);
+	return sysctl__read_int("kernel/perf_event_max_sample_rate", (int *)rate);
 }
 
 static int record_opts__config_freq(struct record_opts *opts)
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index e73b6a5c9e0f..c93fb0c5bd0b 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -20,7 +20,7 @@
 
 struct a2l_data {
 	const char 	*input;
-	unsigned long 	addr;
+	u64	 	addr;
 
 	bool 		found;
 	const char 	*filename;
@@ -147,7 +147,7 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 	free(a2l);
 }
 
-static int addr2line(const char *dso_name, unsigned long addr,
+static int addr2line(const char *dso_name, u64 addr,
 		     char **file, unsigned int *line, struct dso *dso)
 {
 	int ret = 0;
@@ -193,7 +193,7 @@ void dso__free_a2l(struct dso *dso)
 
 #else /* HAVE_LIBBFD_SUPPORT */
 
-static int addr2line(const char *dso_name, unsigned long addr,
+static int addr2line(const char *dso_name, u64 addr,
 		     char **file, unsigned int *line_nr,
 		     struct dso *dso __maybe_unused)
 {
@@ -252,7 +252,7 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
  */
 #define A2L_FAIL_LIMIT 123
 
-char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym,
+char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		  bool show_sym)
 {
 	char *file = NULL;
@@ -293,10 +293,10 @@ out:
 		dso__free_a2l(dso);
 	}
 	if (sym) {
-		if (asprintf(&srcline, "%s+%ld", show_sym ? sym->name : "",
+		if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "",
 					addr - sym->start) < 0)
 			return SRCLINE_UNKNOWN;
-	} else if (asprintf(&srcline, "%s[%lx]", dso->short_name, addr) < 0)
+	} else if (asprintf(&srcline, "%s[%" PRIx64 "]", dso->short_name, addr) < 0)
 		return SRCLINE_UNKNOWN;
 	return srcline;
 }
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index fa585c63f56a..d7efb03b3f9a 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -129,6 +129,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 
 		for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
 			void *tmp;
+			long offset;
 
 			if (need_swap) {
 				phdr->p_type = bswap_32(phdr->p_type);
@@ -140,12 +141,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 				continue;
 
 			buf_size = phdr->p_filesz;
+			offset = phdr->p_offset;
 			tmp = realloc(buf, buf_size);
 			if (tmp == NULL)
 				goto out_free;
 
 			buf = tmp;
-			fseek(fp, phdr->p_offset, SEEK_SET);
+			fseek(fp, offset, SEEK_SET);
 			if (fread(buf, buf_size, 1, fp) != 1)
 				goto out_free;
 
@@ -178,6 +180,7 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 
 		for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
 			void *tmp;
+			long offset;
 
 			if (need_swap) {
 				phdr->p_type = bswap_32(phdr->p_type);
@@ -189,12 +192,13 @@ int filename__read_build_id(const char *filename, void *bf, size_t size)
 				continue;
 
 			buf_size = phdr->p_filesz;
+			offset = phdr->p_offset;
 			tmp = realloc(buf, buf_size);
 			if (tmp == NULL)
 				goto out_free;
 
 			buf = tmp;
-			fseek(fp, phdr->p_offset, SEEK_SET);
+			fseek(fp, offset, SEEK_SET);
 			if (fread(buf, buf_size, 1, fp) != 1)
 				goto out_free;
 
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 371219a6daf1..6edf535f65c2 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -185,6 +185,28 @@ static u64 elf_section_offset(int fd, const char *name)
 	return offset;
 }
 
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+static int elf_is_exec(int fd, const char *name)
+{
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	int retval = 0;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		return 0;
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		goto out;
+
+	retval = (ehdr.e_type == ET_EXEC);
+
+out:
+	elf_end(elf);
+	pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval);
+	return retval;
+}
+#endif
+
 struct table_entry {
 	u32 start_ip_offset;
 	u32 fde_offset;
@@ -322,8 +344,12 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
 	/* Check the .debug_frame section for unwinding info */
 	if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
+		int fd = dso__data_fd(map->dso, ui->machine);
+		int is_exec = elf_is_exec(fd, map->dso->name);
+		unw_word_t base = is_exec ? 0 : map->start;
+
 		memset(&di, 0, sizeof(di));
-		if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
+		if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
 					   map->start, map->end))
 			return dwarf_search_unwind_table(as, ip, &di, pi,
 							 need_unwind_info, arg);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index d5eab3f3323f..b86744f29eef 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -442,23 +442,6 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
 	return (unsigned long) -1;
 }
 
-int filename__read_int(const char *filename, int *value)
-{
-	char line[64];
-	int fd = open(filename, O_RDONLY), err = -1;
-
-	if (fd < 0)
-		return -1;
-
-	if (read(fd, line, sizeof(line)) > 0) {
-		*value = atoi(line);
-		err = 0;
-	}
-
-	close(fd);
-	return err;
-}
-
 int filename__read_str(const char *filename, char **buf, size_t *sizep)
 {
 	size_t size = 0, alloc_size = 0;
@@ -523,16 +506,9 @@ const char *get_filename_for_perf_kvm(void)
 
 int perf_event_paranoid(void)
 {
-	char path[PATH_MAX];
-	const char *procfs = procfs__mountpoint();
 	int value;
 
-	if (!procfs)
-		return INT_MAX;
-
-	scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs);
-
-	if (filename__read_int(path, &value))
+	if (sysctl__read_int("kernel/perf_event_paranoid", &value))
 		return INT_MAX;
 
 	return value;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 419bee030f83..027a5153495c 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -153,7 +153,7 @@ extern void warning(const char *err, ...) __attribute__((format (printf, 1, 2)))
 extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
 
 extern int prefixcmp(const char *str, const char *prefix);
-extern void set_buildid_dir(void);
+extern void set_buildid_dir(const char *dir);
 
 static inline const char *skip_prefix(const char *str, const char *prefix)
 {
@@ -269,35 +269,6 @@ void event_attr_init(struct perf_event_attr *attr);
 #define _STR(x) #x
 #define STR(x) _STR(x)
 
-/*
- *  Determine whether some value is a power of two, where zero is
- * *not* considered a power of two.
- */
-
-static inline __attribute__((const))
-bool is_power_of_2(unsigned long n)
-{
-	return (n != 0 && ((n & (n - 1)) == 0));
-}
-
-static inline unsigned next_pow2(unsigned x)
-{
-	if (!x)
-		return 1;
-	return 1ULL << (32 - __builtin_clz(x - 1));
-}
-
-static inline unsigned long next_pow2_l(unsigned long x)
-{
-#if BITS_PER_LONG == 64
-	if (x <= (1UL << 31))
-		return next_pow2(x);
-	return (unsigned long)next_pow2(x >> 32) << 32;
-#else
-	return next_pow2(x);
-#endif
-}
-
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
@@ -339,11 +310,10 @@ static inline int path__join3(char *bf, size_t size,
 struct dso;
 struct symbol;
 
-char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym,
+char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		  bool show_sym);
 void free_srcline(char *srcline);
 
-int filename__read_int(const char *filename, int *value);
 int filename__read_str(const char *filename, char **buf, size_t *sizep);
 int perf_event_paranoid(void);