Merge tag 'perf-core-for-mingo-4.11-20170306' of...

Merge tag 'perf-core-for-mingo-4.11-20170306' 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:

New features:

- Allow sorting by symbol_size in 'perf report' and 'perf top' (Charles Baylis)

  E.g.:

  # perf report -s symbol_size,symbol

  Samples: 9K of event 'cycles:k', Event count (approx.): 2870461623
  Overhead  Symbol size  Symbol
    14.55%          326  [k] flush_tlb_mm_range
     7.20%         1045  [k] filemap_map_pages
     5.82%          124  [k] vma_interval_tree_insert
     5.18%         2430  [k] unmap_page_range
     2.57%          571  [k] vma_interval_tree_remove
     1.94%          494  [k] page_add_file_rmap
     1.82%          740  [k] page_remove_rmap
     1.66%         1017  [k] release_pages
     1.57%         1636  [k] update_blocked_averages
     1.57%           76  [k] unlock_page

- Add support for -p/--pid, -a/--all-cpus and -C/--cpu in 'perf ftrace' (Namhyung Kim)

Change in behaviour:

- Make system wide (-a) the default option if no target was specified and one
  of following conditions is met:

  - No workload specified (current behaviour)

  - A workload is specified but all requested events are system wide ones,
    like uncore ones. (Jiri Olsa)

Fixes:

- Add missing initialization to the instruction decoder used in the
  intel PT/BTS code, which was causing lots of failures in 'perf test',
  looking for a value when there was none (Adrian Hunter)

Infrastructure changes:

- Add arch code needed to adopt the kernel's refcount_t to aid in
  catching bugs when using atomic_t as a reference counter, basically
  cmpxchg related functions (Arnaldo Carvalho de Melo)

- Convert the code using atomic_t as reference counts to refcount_t
  (Elena Rashetova)

- Add feature test for sched_getcpu() to more easily check for its
  presence in the many libc implementations and accross different
  versions of such C libraries (Arnaldo Carvalho de Melo)

- Issue a HW watchdog disable hint in 'perf stat' for when some of the
  requested events can't get counted because a PMU counter is taken by that
  watchdog (Borislav Petkov).

- Add mapping for Intel's KnightsMill PMU events (Karol Wachowski)

Documentation changes:

- Clarify the term 'convergence' in:

   perf bench numa numa-mem -h --show_convergence (Jiri Olsa)

Kernel code changes:

- Ensure probe location is at function entry in kretprobes (Naveen N. Rao)

- Allow return probes with offsets and absolute addresses (Naveen N. Rao)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/trace/kprobetrace.txt

@@ -12,7 +12,7 @@ kprobes can probe (this means, all functions body except for __kprobes
 functions). Unlike the Tracepoint based event, this can be added and removed
 dynamically, on the fly.
 
-To enable this feature, build your kernel with CONFIG_KPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
 
 Similar to the events tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via

Documentation/trace/uprobetracer.txt

@@ -7,7 +7,7 @@
 Overview
 --------
 Uprobe based trace events are similar to kprobe based trace events.
-To enable this feature, build your kernel with CONFIG_UPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
 
 Similar to the kprobe-event tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via

arch/s390/configs/default_defconfig

@@ -609,7 +609,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y

arch/s390/configs/gcov_defconfig

@@ -560,7 +560,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y

arch/s390/configs/performance_defconfig

@@ -558,7 +558,7 @@ CONFIG_SCHED_TRACER=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y

arch/s390/defconfig

@@ -179,7 +179,7 @@ CONFIG_FTRACE_SYSCALLS=y
 CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
 CONFIG_KPROBES_SANITY_TEST=y

arch/x86/kernel/kprobes/common.h

@@ -67,7 +67,7 @@
 #endif
 
 /* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction);
+extern int can_boost(kprobe_opcode_t *instruction, void *addr);
 /* Recover instruction if given address is probed */
 extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
 					 unsigned long addr);

arch/x86/kernel/kprobes/core.c

@@ -167,12 +167,12 @@ NOKPROBE_SYMBOL(skip_prefixes);
  * Returns non-zero if opcode is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-int can_boost(kprobe_opcode_t *opcodes)
+int can_boost(kprobe_opcode_t *opcodes, void *addr)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
 
-	if (search_exception_tables((unsigned long)opcodes))
+	if (search_exception_tables((unsigned long)addr))
 		return 0;	/* Page fault may occur on this address. */
 
 retry:
@@ -417,7 +417,7 @@ static int arch_copy_kprobe(struct kprobe *p)
 	 * __copy_instruction can modify the displacement of the instruction,
 	 * but it doesn't affect boostable check.
 	 */
-	if (can_boost(p->ainsn.insn))
+	if (can_boost(p->ainsn.insn, p->addr))
 		p->ainsn.boostable = 0;
 	else
 		p->ainsn.boostable = -1;

arch/x86/kernel/kprobes/opt.c

@@ -178,7 +178,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src)
 
 	while (len < RELATIVEJUMP_SIZE) {
 		ret = __copy_instruction(dest + len, src + len);
-		if (!ret || !can_boost(dest + len))
+		if (!ret || !can_boost(dest + len, src + len))
 			return -EINVAL;
 		len += ret;
 	}

include/linux/kprobes.h

@@ -267,6 +267,7 @@ extern int arch_init_kprobes(void);
 extern void show_registers(struct pt_regs *regs);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
 extern bool arch_within_kprobe_blacklist(unsigned long addr);
+extern bool arch_function_offset_within_entry(unsigned long offset);
 
 extern bool within_kprobe_blacklist(unsigned long addr);
 

kernel/kprobes.c

@@ -1875,12 +1875,25 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(pre_handler_kretprobe);
 
+bool __weak arch_function_offset_within_entry(unsigned long offset)
+{
+	return !offset;
+}
+
 int register_kretprobe(struct kretprobe *rp)
 {
 	int ret = 0;
 	struct kretprobe_instance *inst;
 	int i;
 	void *addr;
+	unsigned long offset;
+
+	addr = kprobe_addr(&rp->kp);
+	if (!kallsyms_lookup_size_offset((unsigned long)addr, NULL, &offset))
+		return -EINVAL;
+
+	if (!arch_function_offset_within_entry(offset))
+		return -EINVAL;
 
 	if (kretprobe_blacklist_size) {
 		addr = kprobe_addr(&rp->kp);

kernel/trace/Kconfig

@@ -429,7 +429,7 @@ config BLK_DEV_IO_TRACE
 
 	  If unsure, say N.
 
-config KPROBE_EVENT
+config KPROBE_EVENTS
 	depends on KPROBES
 	depends on HAVE_REGS_AND_STACK_ACCESS_API
 	bool "Enable kprobes-based dynamic events"
@@ -447,7 +447,7 @@ config KPROBE_EVENT
 	  This option is also required by perf-probe subcommand of perf tools.
 	  If you want to use perf tools, this option is strongly recommended.
 
-config UPROBE_EVENT
+config UPROBE_EVENTS
 	bool "Enable uprobes-based dynamic events"
 	depends on ARCH_SUPPORTS_UPROBES
 	depends on MMU
@@ -466,7 +466,7 @@ config UPROBE_EVENT
 
 config BPF_EVENTS
 	depends on BPF_SYSCALL
-	depends on (KPROBE_EVENT || UPROBE_EVENT) && PERF_EVENTS
+	depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
 	bool
 	default y
 	help

kernel/trace/Makefile

@@ -57,7 +57,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
-obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
 ifeq ($(CONFIG_PM),y)
 obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
@@ -66,7 +66,7 @@ ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
-obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 

kernel/trace/trace.c

@@ -4341,22 +4341,23 @@ static const char readme_msg[] =
 	"\t\t\t  traces\n"
 #endif
 #endif /* CONFIG_STACK_TRACER */
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 	"  kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
 	"  uprobe_events\t\t- Add/remove/show the userspace dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#if defined(CONFIG_KPROBE_EVENT) || defined(CONFIG_UPROBE_EVENT)
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
 	"\t  accepts: event-definitions (one definition per line)\n"
 	"\t   Format: p|r[:[<group>/]<event>] <place> [<args>]\n"
 	"\t           -:[<group>/]<event>\n"
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 	"\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
+  "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
 	"\t    place: <path>:<offset>\n"
 #endif
 	"\t     args: <name>=fetcharg[:type]\n"

kernel/trace/trace_kprobe.c

@@ -681,10 +681,6 @@ static int create_trace_kprobe(int argc, char **argv)
 		return -EINVAL;
 	}
 	if (isdigit(argv[1][0])) {
-		if (is_return) {
-			pr_info("Return probe point must be a symbol.\n");
-			return -EINVAL;
-		}
 		/* an address specified */
 		ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr);
 		if (ret) {
@@ -700,8 +696,9 @@ static int create_trace_kprobe(int argc, char **argv)
 			pr_info("Failed to parse symbol.\n");
 			return ret;
 		}
-		if (offset && is_return) {
-			pr_info("Return probe must be used without offset.\n");
+		if (offset && is_return &&
+		    !arch_function_offset_within_entry(offset)) {
+			pr_info("Given offset is not valid for return probe.\n");
 			return -EINVAL;
 		}
 	}

kernel/trace/trace_probe.h

@@ -248,7 +248,7 @@ ASSIGN_FETCH_FUNC(file_offset, ftype),			\
 #define FETCH_TYPE_STRING	0
 #define FETCH_TYPE_STRSIZE	1
 
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 struct symbol_cache;
 unsigned long update_symbol_cache(struct symbol_cache *sc);
 void free_symbol_cache(struct symbol_cache *sc);
@@ -278,7 +278,7 @@ alloc_symbol_cache(const char *sym, long offset)
 {
 	return NULL;
 }
-#endif /* CONFIG_KPROBE_EVENT */
+#endif /* CONFIG_KPROBE_EVENTS */
 
 struct probe_arg {
 	struct fetch_param	fetch;

tools/arch/x86/include/asm/atomic.h

@@ -7,6 +7,8 @@
 
 #define LOCK_PREFIX "\n\tlock; "
 
+#include <asm/cmpxchg.h>
+
 /*
  * Atomic operations that C can't guarantee us.  Useful for
  * resource counting etc..
@@ -62,4 +64,9 @@ static inline int atomic_dec_and_test(atomic_t *v)
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
 }
 
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	return cmpxchg(&v->counter, old, new);
+}
+
 #endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */

tools/arch/x86/include/asm/cmpxchg.h

+#ifndef TOOLS_ASM_X86_CMPXCHG_H
+#define TOOLS_ASM_X86_CMPXCHG_H
+
+#include <linux/compiler.h>
+
+/*
+ * Non-existant functions to indicate usage errors at link time
+ * (or compile-time if the compiler implements __compiletime_error().
+ */
+extern void __cmpxchg_wrong_size(void)
+	__compiletime_error("Bad argument size for cmpxchg");
+
+/*
+ * Constants for operation sizes. On 32-bit, the 64-bit size it set to
+ * -1 because sizeof will never return -1, thereby making those switch
+ * case statements guaranteeed dead code which the compiler will
+ * eliminate, and allowing the "missing symbol in the default case" to
+ * indicate a usage error.
+ */
+#define __X86_CASE_B	1
+#define __X86_CASE_W	2
+#define __X86_CASE_L	4
+#ifdef __x86_64__
+#define __X86_CASE_Q	8
+#else
+#define	__X86_CASE_Q	-1		/* sizeof will never return -1 */
+#endif
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+#define __raw_cmpxchg(ptr, old, new, size, lock)			\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	__typeof__(*(ptr)) __old = (old);				\
+	__typeof__(*(ptr)) __new = (new);				\
+	switch (size) {							\
+	case __X86_CASE_B:						\
+	{								\
+		volatile u8 *__ptr = (volatile u8 *)(ptr);		\
+		asm volatile(lock "cmpxchgb %2,%1"			\
+			     : "=a" (__ret), "+m" (*__ptr)		\
+			     : "q" (__new), "0" (__old)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	case __X86_CASE_W:						\
+	{								\
+		volatile u16 *__ptr = (volatile u16 *)(ptr);		\
+		asm volatile(lock "cmpxchgw %2,%1"			\
+			     : "=a" (__ret), "+m" (*__ptr)		\
+			     : "r" (__new), "0" (__old)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	case __X86_CASE_L:						\
+	{								\
+		volatile u32 *__ptr = (volatile u32 *)(ptr);		\
+		asm volatile(lock "cmpxchgl %2,%1"			\
+			     : "=a" (__ret), "+m" (*__ptr)		\
+			     : "r" (__new), "0" (__old)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	case __X86_CASE_Q:						\
+	{								\
+		volatile u64 *__ptr = (volatile u64 *)(ptr);		\
+		asm volatile(lock "cmpxchgq %2,%1"			\
+			     : "=a" (__ret), "+m" (*__ptr)		\
+			     : "r" (__new), "0" (__old)			\
+			     : "memory");				\
+		break;							\
+	}								\
+	default:							\
+		__cmpxchg_wrong_size();					\
+	}								\
+	__ret;								\
+})
+
+#define __cmpxchg(ptr, old, new, size)					\
+	__raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
+
+#define cmpxchg(ptr, old, new)						\
+	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
+
+
+#endif	/* TOOLS_ASM_X86_CMPXCHG_H */

tools/build/Makefile.feature

@@ -63,6 +63,7 @@ FEATURE_TESTS_BASIC :=                  \
         lzma                            \
         get_cpuid                       \
         bpf                             \
+        sched_getcpu			\
         sdt
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list

tools/build/feature/Makefile

@@ -48,12 +48,13 @@ FILES=                                          \
          test-get_cpuid.bin                     \
          test-sdt.bin                           \
          test-cxx.bin                           \
-         test-jvmti.bin
+         test-jvmti.bin				\
+         test-sched_getcpu.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
-CC := $(CROSS_COMPILE)gcc -MD
-CXX := $(CROSS_COMPILE)g++ -MD
+CC ?= $(CROSS_COMPILE)gcc -MD
+CXX ?= $(CROSS_COMPILE)g++ -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
 LLVM_CONFIG ?= llvm-config
 
@@ -91,6 +92,9 @@ $(OUTPUT)test-libelf.bin:
 $(OUTPUT)test-glibc.bin:
 	$(BUILD)
 
+$(OUTPUT)test-sched_getcpu.bin:
+	$(BUILD)
+
 DWARFLIBS := -ldw
 ifeq ($(findstring -static,${LDFLAGS}),-static)
 DWARFLIBS += -lelf -lebl -lz -llzma -lbz2