Merge tag 'perf-core-for-mingo-20160718' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

 - Properly report when a function wildcard produces no matches in 'perf probe'
   (Masami Hiramatsu)

 - Balance opening and reading events in 'perf stat', which could cause
   it to get stuck trying to close invalid file descriptors (Mark Rutland)

Infrastructure changes:

 - Copy more headers from the kernel, this time for headers that
   were just including the contents of its kernel counterparts, should
   help resolving the problems with linux-next, where some uapi related
   patches seem to be breaking tools/object/ build. (Arnaldo Carvalho de Melo)

   Some more combing will be done, but at least it is possible to build
   perf out of tree, via a detached tarball (make help | grep perf),
   without including kernel files in its MANIFEST (Arnaldo Carvalho de Melo)

 - Fix smatch found errors that were not causing problems, but are
   mistakes nonetheless (Dan Carpenter)

 - Fix string vs. byte array resolving in the python script code (Jiri Olsa)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

26 files changed, 512 insertions, 57 deletions

diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h
index 494c9c615d1c..a60a7ccb6782 100644
--- a/tools/include/asm-generic/bitops/__fls.h
+++ b/tools/include/asm-generic/bitops/__fls.h
@@ -1 +1,43 @@
-#include "../../../../include/asm-generic/bitops/__fls.h"
+#ifndef _ASM_GENERIC_BITOPS___FLS_H_
+#define _ASM_GENERIC_BITOPS___FLS_H_
+
+#include <asm/types.h>
+
+/**
+ * __fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __fls(unsigned long word)
+{
+	int num = BITS_PER_LONG - 1;
+
+#if BITS_PER_LONG == 64
+	if (!(word & (~0ul << 32))) {
+		num -= 32;
+		word <<= 32;
+	}
+#endif
+	if (!(word & (~0ul << (BITS_PER_LONG-16)))) {
+		num -= 16;
+		word <<= 16;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-8)))) {
+		num -= 8;
+		word <<= 8;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-4)))) {
+		num -= 4;
+		word <<= 4;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-2)))) {
+		num -= 2;
+		word <<= 2;
+	}
+	if (!(word & (~0ul << (BITS_PER_LONG-1))))
+		num -= 1;
+	return num;
+}
+
+#endif /* _ASM_GENERIC_BITOPS___FLS_H_ */
diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h
index 318bb2b202b0..6a211f40665c 100644
--- a/tools/include/asm-generic/bitops/arch_hweight.h
+++ b/tools/include/asm-generic/bitops/arch_hweight.h
@@ -1 +1,25 @@
-#include "../../../../include/asm-generic/bitops/arch_hweight.h"
+#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+
+#include <asm/types.h>
+
+static inline unsigned int __arch_hweight32(unsigned int w)
+{
+	return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+	return __sw_hweight16(w);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+	return __sw_hweight8(w);
+}
+
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+	return __sw_hweight64(w);
+}
+#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h
index 0afd644aff83..0a7e06623470 100644
--- a/tools/include/asm-generic/bitops/const_hweight.h
+++ b/tools/include/asm-generic/bitops/const_hweight.h
@@ -1 +1,43 @@
-#include "../../../../include/asm-generic/bitops/const_hweight.h"
+#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+
+/*
+ * Compile time versions of __arch_hweightN()
+ */
+#define __const_hweight8(w)		\
+	((unsigned int)			\
+	 ((!!((w) & (1ULL << 0))) +	\
+	  (!!((w) & (1ULL << 1))) +	\
+	  (!!((w) & (1ULL << 2))) +	\
+	  (!!((w) & (1ULL << 3))) +	\
+	  (!!((w) & (1ULL << 4))) +	\
+	  (!!((w) & (1ULL << 5))) +	\
+	  (!!((w) & (1ULL << 6))) +	\
+	  (!!((w) & (1ULL << 7)))))
+
+#define __const_hweight16(w) (__const_hweight8(w)  + __const_hweight8((w)  >> 8 ))
+#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16))
+#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32))
+
+/*
+ * Generic interface.
+ */
+#define hweight8(w)  (__builtin_constant_p(w) ? __const_hweight8(w)  : __arch_hweight8(w))
+#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w))
+#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w))
+#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w))
+
+/*
+ * Interface for known constant arguments
+ */
+#define HWEIGHT8(w)  (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w))
+#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w))
+#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w))
+#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w))
+
+/*
+ * Type invariant interface to the compile time constant hweight functions.
+ */
+#define HWEIGHT(w)   HWEIGHT64((u64)w)
+
+#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */
diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h
index 0e4995fa0248..0576d1f42f43 100644
--- a/tools/include/asm-generic/bitops/fls.h
+++ b/tools/include/asm-generic/bitops/fls.h
@@ -1 +1,41 @@
-#include "../../../../include/asm-generic/bitops/fls.h"
+#ifndef _ASM_GENERIC_BITOPS_FLS_H_
+#define _ASM_GENERIC_BITOPS_FLS_H_
+
+/**
+ * fls - find last (most-significant) bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
+ */
+
+static __always_inline int fls(int x)
+{
+	int r = 32;
+
+	if (!x)
+		return 0;
+	if (!(x & 0xffff0000u)) {
+		x <<= 16;
+		r -= 16;
+	}
+	if (!(x & 0xff000000u)) {
+		x <<= 8;
+		r -= 8;
+	}
+	if (!(x & 0xf0000000u)) {
+		x <<= 4;
+		r -= 4;
+	}
+	if (!(x & 0xc0000000u)) {
+		x <<= 2;
+		r -= 2;
+	}
+	if (!(x & 0x80000000u)) {
+		x <<= 1;
+		r -= 1;
+	}
+	return r;
+}
+
+#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */
diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h
index 35bee0071e78..b097cf8444e3 100644
--- a/tools/include/asm-generic/bitops/fls64.h
+++ b/tools/include/asm-generic/bitops/fls64.h
@@ -1 +1,36 @@
-#include "../../../../include/asm-generic/bitops/fls64.h"
+#ifndef _ASM_GENERIC_BITOPS_FLS64_H_
+#define _ASM_GENERIC_BITOPS_FLS64_H_
+
+#include <asm/types.h>
+
+/**
+ * fls64 - find last set bit in a 64-bit word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as the libc and compiler builtin
+ * ffsll, but returns the position of the most significant set bit.
+ *
+ * fls64(value) returns 0 if value is 0 or the position of the last
+ * set bit if value is nonzero. The last (most significant) bit is
+ * at position 64.
+ */
+#if BITS_PER_LONG == 32
+static __always_inline int fls64(__u64 x)
+{
+	__u32 h = x >> 32;
+	if (h)
+		return fls(h) + 32;
+	return fls(x);
+}
+#elif BITS_PER_LONG == 64
+static __always_inline int fls64(__u64 x)
+{
+	if (x == 0)
+		return 0;
+	return __fls(x) + 1;
+}
+#else
+#error BITS_PER_LONG not 32 or 64
+#endif
+
+#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */
diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h
index d026c6573018..ad6fa21d977b 100644
--- a/tools/include/linux/hash.h
+++ b/tools/include/linux/hash.h
@@ -1,5 +1,104 @@
-#include "../../../include/linux/hash.h"
+#ifndef _LINUX_HASH_H
+#define _LINUX_HASH_H
+/* Fast hashing routine for ints,  longs and pointers.
+   (C) 2002 Nadia Yvette Chambers, IBM */
 
-#ifndef _TOOLS_LINUX_HASH_H
-#define _TOOLS_LINUX_HASH_H
+#include <asm/types.h>
+#include <linux/compiler.h>
+
+/*
+ * The "GOLDEN_RATIO_PRIME" is used in ifs/btrfs/brtfs_inode.h and
+ * fs/inode.c.  It's not actually prime any more (the previous primes
+ * were actively bad for hashing), but the name remains.
+ */
+#if BITS_PER_LONG == 32
+#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_32
+#define hash_long(val, bits) hash_32(val, bits)
+#elif BITS_PER_LONG == 64
+#define hash_long(val, bits) hash_64(val, bits)
+#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_64
+#else
+#error Wordsize not 32 or 64
+#endif
+
+/*
+ * This hash multiplies the input by a large odd number and takes the
+ * high bits.  Since multiplication propagates changes to the most
+ * significant end only, it is essential that the high bits of the
+ * product be used for the hash value.
+ *
+ * Chuck Lever verified the effectiveness of this technique:
+ * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf
+ *
+ * Although a random odd number will do, it turns out that the golden
+ * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice
+ * properties.  (See Knuth vol 3, section 6.4, exercise 9.)
+ *
+ * These are the negative, (1 - phi) = phi**2 = (3 - sqrt(5))/2,
+ * which is very slightly easier to multiply by and makes no
+ * difference to the hash distribution.
+ */
+#define GOLDEN_RATIO_32 0x61C88647
+#define GOLDEN_RATIO_64 0x61C8864680B583EBull
+
+#ifdef CONFIG_HAVE_ARCH_HASH
+/* This header may use the GOLDEN_RATIO_xx constants */
+#include <asm/hash.h>
+#endif
+
+/*
+ * The _generic versions exist only so lib/test_hash.c can compare
+ * the arch-optimized versions with the generic.
+ *
+ * Note that if you change these, any <asm/hash.h> that aren't updated
+ * to match need to have their HAVE_ARCH_* define values updated so the
+ * self-test will not false-positive.
+ */
+#ifndef HAVE_ARCH__HASH_32
+#define __hash_32 __hash_32_generic
+#endif
+static inline u32 __hash_32_generic(u32 val)
+{
+	return val * GOLDEN_RATIO_32;
+}
+
+#ifndef HAVE_ARCH_HASH_32
+#define hash_32 hash_32_generic
 #endif
+static inline u32 hash_32_generic(u32 val, unsigned int bits)
+{
+	/* High bits are more random, so use them. */
+	return __hash_32(val) >> (32 - bits);
+}
+
+#ifndef HAVE_ARCH_HASH_64
+#define hash_64 hash_64_generic
+#endif
+static __always_inline u32 hash_64_generic(u64 val, unsigned int bits)
+{
+#if BITS_PER_LONG == 64
+	/* 64x64-bit multiply is efficient on all 64-bit processors */
+	return val * GOLDEN_RATIO_64 >> (64 - bits);
+#else
+	/* Hash 64 bits using only 32x32-bit multiply. */
+	return hash_32((u32)val ^ __hash_32(val >> 32), bits);
+#endif
+}
+
+static inline u32 hash_ptr(const void *ptr, unsigned int bits)
+{
+	return hash_long((unsigned long)ptr, bits);
+}
+
+/* This really should be called fold32_ptr; it does no hashing to speak of. */
+static inline u32 hash32_ptr(const void *ptr)
+{
+	unsigned long val = (unsigned long)ptr;
+
+#if BITS_PER_LONG == 64
+	val ^= (val >> 32);
+#endif
+	return (u32)val;
+}
+
+#endif /* _LINUX_HASH_H */
diff --git a/tools/include/linux/poison.h b/tools/include/linux/poison.h
index 0c27bdf14233..51334edec506 100644
--- a/tools/include/linux/poison.h
+++ b/tools/include/linux/poison.h
@@ -1 +1,90 @@
-#include "../../../include/linux/poison.h"
+#ifndef _LINUX_POISON_H
+#define _LINUX_POISON_H
+
+/********** include/linux/list.h **********/
+
+/*
+ * Architectures might want to move the poison pointer offset
+ * into some well-recognized area such as 0xdead000000000000,
+ * that is also not mappable by user-space exploits:
+ */
+#ifdef CONFIG_ILLEGAL_POINTER_VALUE
+# define POISON_POINTER_DELTA _AC(CONFIG_ILLEGAL_POINTER_VALUE, UL)
+#else
+# define POISON_POINTER_DELTA 0
+#endif
+
+/*
+ * These are non-NULL pointers that will result in page faults
+ * under normal circumstances, used to verify that nobody uses
+ * non-initialized list entries.
+ */
+#define LIST_POISON1  ((void *) 0x100 + POISON_POINTER_DELTA)
+#define LIST_POISON2  ((void *) 0x200 + POISON_POINTER_DELTA)
+
+/********** include/linux/timer.h **********/
+/*
+ * Magic number "tsta" to indicate a static timer initializer
+ * for the object debugging code.
+ */
+#define TIMER_ENTRY_STATIC	((void *) 0x300 + POISON_POINTER_DELTA)
+
+/********** mm/debug-pagealloc.c **********/
+#ifdef CONFIG_PAGE_POISONING_ZERO
+#define PAGE_POISON 0x00
+#else
+#define PAGE_POISON 0xaa
+#endif
+
+/********** mm/page_alloc.c ************/
+
+#define TAIL_MAPPING	((void *) 0x400 + POISON_POINTER_DELTA)
+
+/********** mm/slab.c **********/
+/*
+ * Magic nums for obj red zoning.
+ * Placed in the first word before and the first word after an obj.
+ */
+#define	RED_INACTIVE	0x09F911029D74E35BULL	/* when obj is inactive */
+#define	RED_ACTIVE	0xD84156C5635688C0ULL	/* when obj is active */
+
+#define SLUB_RED_INACTIVE	0xbb
+#define SLUB_RED_ACTIVE		0xcc
+
+/* ...and for poisoning */
+#define	POISON_INUSE	0x5a	/* for use-uninitialised poisoning */
+#define POISON_FREE	0x6b	/* for use-after-free poisoning */
+#define	POISON_END	0xa5	/* end-byte of poisoning */
+
+/********** arch/$ARCH/mm/init.c **********/
+#define POISON_FREE_INITMEM	0xcc
+
+/********** arch/ia64/hp/common/sba_iommu.c **********/
+/*
+ * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a
+ * value of "SBAIOMMU POISON\0" for spill-over poisoning.
+ */
+
+/********** fs/jbd/journal.c **********/
+#define JBD_POISON_FREE		0x5b
+#define JBD2_POISON_FREE	0x5c
+
+/********** drivers/base/dmapool.c **********/
+#define	POOL_POISON_FREED	0xa7	/* !inuse */
+#define	POOL_POISON_ALLOCATED	0xa9	/* !initted */
+
+/********** drivers/atm/ **********/
+#define ATM_POISON_FREE		0x12
+#define ATM_POISON		0xdeadbeef
+
+/********** kernel/mutexes **********/
+#define MUTEX_DEBUG_INIT	0x11
+#define MUTEX_DEBUG_FREE	0x22
+
+/********** lib/flex_array.c **********/
+#define FLEX_ARRAY_FREE	0x6c	/* for use-after-free poisoning */
+
+/********** security/ **********/
+#define KEY_DESTROY		0xbd
+
+#endif
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 923eda2e7d52..ad2534df4ba6 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -77,17 +77,4 @@ tools/include/linux/stringify.h
 tools/include/linux/types.h
 tools/include/linux/err.h
 tools/include/linux/bitmap.h
-include/asm-generic/bitops/arch_hweight.h
-include/asm-generic/bitops/const_hweight.h
-include/asm-generic/bitops/fls64.h
-include/asm-generic/bitops/__fls.h
-include/asm-generic/bitops/fls.h
-include/linux/list.h
-include/linux/hash.h
-include/linux/swab.h
-arch/*/include/asm/unistd*.h
-arch/*/include/uapi/asm/unistd*.h
 tools/arch/*/include/uapi/asm/perf_regs.h
-include/linux/poison.h
-include/uapi/linux/const.h
-include/uapi/linux/swab.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index a129fbc1ed37..6641abb97f0a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -351,6 +351,9 @@ $(PERF_IN): prepare FORCE
 	@(test -f ../../include/uapi/linux/perf_event.h && ( \
         (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \
         || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/linux/hash.h && ( \
+        (diff -B ../include/linux/hash.h ../../include/linux/hash.h >/dev/null) \
+        || echo "Warning: tools/include/linux/hash.h differs from kernel" >&2 )) || true
 	@(test -f ../../include/uapi/linux/hw_breakpoint.h && ( \
         (diff -B ../include/uapi/linux/hw_breakpoint.h ../../include/uapi/linux/hw_breakpoint.h >/dev/null) \
         || echo "Warning: tools/include/uapi/linux/hw_breakpoint.h differs from kernel" >&2 )) || true
@@ -411,6 +414,21 @@ $(PERF_IN): prepare FORCE
 	@(test -f ../../arch/arm64/include/uapi/asm/kvm.h && ( \
         (diff -B ../arch/arm64/include/uapi/asm/kvm.h ../../arch/arm64/include/uapi/asm/kvm.h >/dev/null) \
         || echo "Warning: tools/arch/arm64/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/asm-generic/bitops/arch_hweight.h && ( \
+        (diff -B ../include/asm-generic/bitops/arch_hweight.h ../../include/asm-generic/bitops/arch_hweight.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/arch_hweight.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/asm-generic/bitops/const_hweight.h && ( \
+        (diff -B ../include/asm-generic/bitops/const_hweight.h ../../include/asm-generic/bitops/const_hweight.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/const_hweight.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/asm-generic/bitops/__fls.h && ( \
+        (diff -B ../include/asm-generic/bitops/__fls.h ../../include/asm-generic/bitops/__fls.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/__fls.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/asm-generic/bitops/fls.h && ( \
+        (diff -B ../include/asm-generic/bitops/fls.h ../../include/asm-generic/bitops/fls.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/fls.h differs from kernel" >&2 )) || true
+	@(test -f ../../include/asm-generic/bitops/fls64.h && ( \
+        (diff -B ../include/asm-generic/bitops/fls64.h ../../include/asm-generic/bitops/fls64.h >/dev/null) \
+        || echo "Warning: tools/include/asm-generic/bitops/fls64.h differs from kernel" >&2 )) || true
 	$(Q)$(MAKE) $(build)=perf
 
 $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8c5a3bfdfdd7..0c16d20d7e32 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -290,8 +290,12 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
 static int read_counter(struct perf_evsel *counter)
 {
 	int nthreads = thread_map__nr(evsel_list->threads);
-	int ncpus = perf_evsel__nr_cpus(counter);
-	int cpu, thread;
+	int ncpus, cpu, thread;
+
+	if (target__has_cpu(&target))
+		ncpus = perf_evsel__nr_cpus(counter);
+	else
+		ncpus = 1;
 
 	if (!counter->supported)
 		return -ENOENT;
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index 3573f315f955..55daefff0d54 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -59,7 +59,6 @@ static int get_e_machine(struct jitheader *hdr)
 	ssize_t sret;
 	char id[16];
 	int fd, ret = -1;
-	int m = -1;
 	struct {
 		uint16_t e_type;
 		uint16_t e_machine;
@@ -81,11 +80,7 @@ static int get_e_machine(struct jitheader *hdr)
 	if (sret != sizeof(info))
 		goto error;
 
-	m = info.e_machine;
-	if (m < 0)
-		m = 0; /* ELF EM_NONE */
-
-	hdr->elf_mach = m;
+	hdr->elf_mach = info.e_machine;
 	ret = 0;
 error:
 	close(fd);
@@ -491,10 +486,11 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
 		if (sret != 1)
 			goto error;
 	}
-	if (padding_count)
+	if (padding_count) {
 		sret = fwrite_unlocked(pad_bytes, padding_count, 1, fp);
 		if (sret != 1)
 			goto error;
+	}
 
 	funlockfile(fp);
 	return 0;
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 5cee8a3d0455..7ed72a475c57 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -5,6 +5,7 @@
 #include <sys/types.h>
 #include <sys/syscall.h>
 #include <linux/types.h>
+#include <linux/compiler.h>
 #include <linux/perf_event.h>
 #include <asm/barrier.h>
 
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 4158422cc2a6..cb20ae1c0d35 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -40,6 +40,7 @@ perf-y += event_update.o
 perf-y += event-times.o
 perf-y += backward-ring-buffer.o
 perf-y += sdt.o
+perf-y += is_printable_array.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 4dd2d050788a..10eb30686c9c 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -222,6 +222,10 @@ static struct test generic_tests[] = {
 		.func = test__sdt_event,
 	},
 	{
+		.desc = "Test is_printable_array function",
+		.func = test__is_printable_array,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/is_printable_array.c b/tools/perf/tests/is_printable_array.c
new file mode 100644
index 000000000000..42e13393e502
--- /dev/null
+++ b/tools/perf/tests/is_printable_array.c
@@ -0,0 +1,36 @@
+#include <linux/compiler.h>
+#include "tests.h"
+#include "debug.h"
+#include "util.h"
+
+int test__is_printable_array(int subtest __maybe_unused)
+{
+	char buf1[] = { 'k', 'r', 4, 'v', 'a', 0 };
+	char buf2[] = { 'k', 'r', 'a', 'v', 4, 0 };
+	struct {
+		char		*buf;
+		unsigned int	 len;
+		int		 ret;
+	} t[] = {
+		{ (char *) "krava",	sizeof("krava"),	1 },
+		{ (char *) "krava",	sizeof("krava") - 1,	0 },
+		{ (char *) "",		sizeof(""),		1 },
+		{ (char *) "",		0,			0 },
+		{ NULL,			0,			0 },
+		{ buf1,			sizeof(buf1),		0 },
+		{ buf2,			sizeof(buf2),		0 },
+	};
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(t); i++) {
+		int ret;
+
+		ret = is_printable_array((char *) t[i].buf, t[i].len);
+		if (ret != t[i].ret) {
+			pr_err("failed: test %u\n", i);
+			return TEST_FAIL;
+		}
+	}
+
+	return TEST_OK;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a0288f8092b2..9bfc0e06c61a 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -89,6 +89,7 @@ int test__event_times(int subtest);
 int test__backward_ring_buffer(int subtest);
 int test__cpu_map_print(int subtest);
 int test__sdt_event(int subtest);
+int test__is_printable_array(int subtest);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 15f83acac1b8..2c0b52264a46 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -589,14 +589,24 @@ int cpu__setup_cpunode_map(void)
 
 bool cpu_map__has(struct cpu_map *cpus, int cpu)
 {
+	return cpu_map__idx(cpus, cpu) != -1;
+}
+
+int cpu_map__idx(struct cpu_map *cpus, int cpu)
+{
 	int i;
 
 	for (i = 0; i < cpus->nr; ++i) {
 		if (cpus->map[i] == cpu)
-			return true;
+			return i;
 	}
 
-	return false;
+	return -1;
+}
+
+int cpu_map__cpu(struct cpu_map *cpus, int idx)
+{
+	return cpus->map[idx];
 }
 
 size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size)
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 206dc550354a..06bd689f5989 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -68,5 +68,7 @@ int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 		       int (*f)(struct cpu_map *map, int cpu, void *data),
 		       void *data);
 
+int cpu_map__cpu(struct cpu_map *cpus, int idx);
 bool cpu_map__has(struct cpu_map *cpus, int cpu);
+int cpu_map__idx(struct cpu_map *cpus, int cpu);
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/include/asm/byteorder.h b/tools/perf/util/include/asm/byteorder.h
deleted file mode 100644
index 2a9bdc066307..000000000000
--- a/tools/perf/util/include/asm/byteorder.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#include <asm/types.h>
-#include "../../../../include/uapi/linux/swab.h"
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
deleted file mode 100644
index c10a35e1afb8..000000000000
--- a/tools/perf/util/include/linux/const.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../../include/uapi/linux/const.h"
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index b39b12a1208d..728129ac653a 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -312,6 +312,9 @@ int map__load(struct map *map, symbol_filter_t filter)
 			pr_warning("%.*s was updated (is prelink enabled?). "
 				"Restart the long running apps that use it!\n",
 				   (int)real_len, name);
+		} else if (filter) {
+			pr_warning("no symbols passed the given filter.\n");
+			return -2;	/* Empty but maybe by the filter */
 		} else {
 			pr_warning("no symbols found in %s, maybe install "
 				   "a debug package?\n", name);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d4f8835c0a27..953dc1ab2ed7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -3312,8 +3312,16 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 
 	/* Load symbols with given filter */
 	available_func_filter = _filter;
-	if (map__load(map, filter_available_functions)) {
-		pr_err("Failed to load symbols in %s\n", (target) ? : "kernel");
+	ret = map__load(map, filter_available_functions);
+	if (ret) {
+		if (ret == -2) {
+			char *str = strfilter__string(_filter);
+			pr_err("Failed to find symbols matched to \"%s\"\n",
+			       str);
+			free(str);
+		} else
+			pr_err("Failed to load symbols in %s\n",
+			       (target) ? : "kernel");
 		goto end;
 	}
 	if (!dso__sorted_by_name(map->dso, map->type))
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index d32f97033718..a5fbc012e3df 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -295,18 +295,6 @@ static bool is_tracepoint(struct pyrf_event *pevent)
 	return pevent->evsel->attr.type == PERF_TYPE_TRACEPOINT;
 }
 
-static int is_printable_array(char *p, unsigned int len)
-{
-	unsigned int i;
-
-	for (i = 0; i < len; i++) {
-		if (!isprint(p[i]) && !isspace(p[i]))
-			return 0;
-	}
-
-	return 1;
-}
-
 static PyObject*
 tracepoint_field(struct pyrf_event *pe, struct format_field *field)
 {
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 6ac6b7a33f42..e0203b979474 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -386,7 +386,6 @@ exit:
 	return pylist;
 }
 
-
 static void python_process_tracepoint(struct perf_sample *sample,
 				      struct perf_evsel *evsel,
 				      struct addr_location *al)
@@ -457,14 +456,26 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		pydict_set_item_string_decref(dict, "common_callchain", callchain);
 	}
 	for (field = event->format.fields; field; field = field->next) {
-		if (field->flags & FIELD_IS_STRING) {
-			int offset;
+		unsigned int offset, len;
+		unsigned long long val;
+
+		if (field->flags & FIELD_IS_ARRAY) {
+			offset = field->offset;
+			len    = field->size;
 			if (field->flags & FIELD_IS_DYNAMIC) {
-				offset = *(int *)(data + field->offset);
+				val     = pevent_read_number(scripting_context->pevent,
+							     data + offset, len);
+				offset  = val;
+				len     = offset >> 16;
 				offset &= 0xffff;
-			} else
-				offset = field->offset;
-			obj = PyString_FromString((char *)data + offset);
+			}
+			if (field->flags & FIELD_IS_STRING &&
+			    is_printable_array(data + offset, len)) {
+				obj = PyString_FromString((char *) data + offset);
+			} else {
+				obj = PyByteArray_FromStringAndSize((const char *) data + offset, len);
+				field->flags &= ~FIELD_IS_STRING;
+			}
 		} else { /* FIELD_IS_NUMERIC */
 			obj = get_field_numeric_entry(event, field, data);
 		}
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 5f44a21955cd..cee559d8c9e8 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -746,3 +746,19 @@ void print_binary(unsigned char *data, size_t len,
 	}
 	printer(BINARY_PRINT_DATA_END, -1, extra);
 }
+
+int is_printable_array(char *p, unsigned int len)
+{
+	unsigned int i;
+
+	if (!p || !len || p[len - 1] != 0)
+		return 0;
+
+	len--;
+
+	for (i = 0; i < len; i++) {
+		if (!isprint(p[i]) && !isspace(p[i]))
+			return 0;
+	}
+	return 1;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 843cbba8f9d3..e5f55477491d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -364,4 +364,5 @@ void print_binary(unsigned char *data, size_t len,
 extern int sched_getcpu(void);
 #endif
 
+int is_printable_array(char *p, unsigned int len);
 #endif /* GIT_COMPAT_UTIL_H */