Merge tag 'perf-core-for-mingo-4.20-20180905' of git://git.kernel.org…

…/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo:

perf trace:

- Augment the payload of syscall entry/exit tracepoints with the contents
  of pointer arguments, such as the "filename" argument to the "open"
  syscall or the 'struct sockaddr *' argument to the 'connect' syscall.

  This is done using a BPF program that gets compiled and attached to
  various syscalls:sys_enter_NAME tracepoints, copying via a BPF map and
  "bpf-output" perf event the raw_syscalls:sys_enter tracepoint payload +
  the contents of pointer arguments using the "probe_read", "probe_read_str"
  and "perf_event_output" BPF functions.

  The 'perf trace' codebase now just processes these augmented tracepoints
  using the existing beautifiers that now check if there is more in the
  perf_sample->raw_data than what is expected for a normal syscall enter
  tracepoint (the common preamble, syscall id, up to six parameters),
  using that with hand crafted struct beautifiers.

  This is just to show how to augment the existing tracepoints, work will
  be done to use DWARF or BTF info to do the pretty-printing and to create
  the collectors.

  For now this is done using an example restricted C BPF program, but the
  end goal is to have this all autogenerated and done transparently.

  Its still useful to have this example as one can use it as an skeleton and
  write more involved filters, see the etcsnoop.c BPF example, for instance.

  E.g.:

  # cd tools/perf/examples/bpf/
  # perf trace -e augmented_syscalls.c ping -c 1 ::1
     0.000 ( 0.008 ms): openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
     0.020 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libcap.so.2, flags: CLOEXEC) = 3
     0.051 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libidn.so.11, flags: CLOEXEC) = 3
     0.076 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libcrypto.so.1.1, flags: CLOEXEC) = 3
     0.106 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libresolv.so.2, flags: CLOEXEC) = 3
     0.136 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libm.so.6, flags: CLOEXEC) = 3
     0.194 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
     0.224 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libz.so.1, flags: CLOEXEC) = 3
     0.252 ( 0.004 ms): openat(dfd: CWD, filename: /lib64/libdl.so.2, flags: CLOEXEC) = 3
     0.275 ( 0.003 ms): openat(dfd: CWD, filename: /lib64/libpthread.so.0, flags: CLOEXEC) = 3
     0.730 ( 0.007 ms): open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
  PING ::1(::1) 56 data bytes
     0.834 ( 0.008 ms): connect(fd: 5, uservaddr: { .family: INET6, port: 1025, addr: ::1 }, addrlen: 28) = 0
  64 bytes from ::1: icmp_seq=1 ttl=64 time=0.032 ms

  --- ::1 ping statistics ---
  1 packets transmitted, 1 received, 0% packet loss, time 0ms
  rtt min/avg/max/mdev = 0.032/0.032/0.032/0.000 ms
     0.914 ( 0.036 ms): sendto(fd: 4<socket:[843044]>, buff: 0x55b5e52e9720, len: 64, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
  #

  Use 'perf trace -e augmented_syscalls.c,close ping -c 1 ::1' to see the
  'close' calls as well, as it is not one of the syscalls augmented in that .c
  file.

  (Arnaldo Carvalho de Melo)

- Alias 'umount' to 'umount2' (Benjamin Peterson)

perf stat: (Jiri Olsa)

- Make many builtin-stat.c functions generic, moving display functions
  to a separate file, prep work for adding the ability to store/display
  stat data in perf record/top.

perf annotate: (Kim Phillips)

- Handle arm64 move instructions

perf report: (Thomas Richter):

- Create auxiliary trace data files for s390

libtraceevent: (Tzvetomir Stoyanov (VMware)):

- Split trace-seq related APIs in a separate header file.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

kernel/events/core.c

@@ -2867,16 +2867,11 @@ static int perf_event_modify_breakpoint(struct perf_event *bp,
 	_perf_event_disable(bp);
 
 	err = modify_user_hw_breakpoint_check(bp, attr, true);
-	if (err) {
-		if (!bp->attr.disabled)
-			_perf_event_enable(bp);
 
-		return err;
-	}
-
-	if (!attr->disabled)
+	if (!bp->attr.disabled)
 		_perf_event_enable(bp);
-	return 0;
+
+	return err;
 }
 
 static int perf_event_modify_attr(struct perf_event *event,

kernel/events/hw_breakpoint.c

@@ -509,6 +509,8 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a
  */
 int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
 {
+	int err;
+
 	/*
 	 * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
 	 * will not be possible to raise IPIs that invoke __perf_event_disable.
@@ -520,15 +522,12 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att
 	else
 		perf_event_disable(bp);
 
-	if (!attr->disabled) {
-		int err = modify_user_hw_breakpoint_check(bp, attr, false);
+	err = modify_user_hw_breakpoint_check(bp, attr, false);
 
-		if (err)
-			return err;
+	if (!bp->attr.disabled)
 		perf_event_enable(bp);
-		bp->attr.disabled = 0;
-	}
-	return 0;
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
 

tools/lib/traceevent/event-parse.c

@@ -24,6 +24,7 @@
 #include <netinet/in.h>
 #include "event-parse.h"
 #include "event-utils.h"
+#include "trace-seq.h"
 
 static const char *input_buf;
 static unsigned long long input_buf_ptr;

tools/lib/traceevent/event-parse.h

@@ -26,17 +26,12 @@
 #include <regex.h>
 #include <string.h>
 
+#include "trace-seq.h"
+
 #ifndef __maybe_unused
 #define __maybe_unused __attribute__((unused))
 #endif
 
-/* ----------------------- trace_seq ----------------------- */
-
-
-#ifndef TRACE_SEQ_BUF_SIZE
-#define TRACE_SEQ_BUF_SIZE 4096
-#endif
-
 #ifndef DEBUG_RECORD
 #define DEBUG_RECORD 0
 #endif
@@ -59,43 +54,6 @@ struct tep_record {
 #endif
 };
 
-enum trace_seq_fail {
-	TRACE_SEQ__GOOD,
-	TRACE_SEQ__BUFFER_POISONED,
-	TRACE_SEQ__MEM_ALLOC_FAILED,
-};
-
-/*
- * Trace sequences are used to allow a function to call several other functions
- * to create a string of data to use (up to a max of PAGE_SIZE).
- */
-
-struct trace_seq {
-	char			*buffer;
-	unsigned int		buffer_size;
-	unsigned int		len;
-	unsigned int		readpos;
-	enum trace_seq_fail	state;
-};
-
-void trace_seq_init(struct trace_seq *s);
-void trace_seq_reset(struct trace_seq *s);
-void trace_seq_destroy(struct trace_seq *s);
-
-extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
-	__attribute__ ((format (printf, 2, 3)));
-extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
-	__attribute__ ((format (printf, 2, 0)));
-
-extern int trace_seq_puts(struct trace_seq *s, const char *str);
-extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-
-extern void trace_seq_terminate(struct trace_seq *s);
-
-extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
-extern int trace_seq_do_printf(struct trace_seq *s);
-
-
 /* ----------------------- pevent ----------------------- */
 
 struct tep_handle;

tools/lib/traceevent/event-plugin.c

@@ -15,6 +15,7 @@
 #include <dirent.h>
 #include "event-parse.h"
 #include "event-utils.h"
+#include "trace-seq.h"
 
 #define LOCAL_PLUGIN_DIR ".traceevent/plugins"
 

tools/lib/traceevent/plugin_function.c

@@ -23,6 +23,7 @@
 
 #include "event-parse.h"
 #include "event-utils.h"
+#include "trace-seq.h"
 
 static struct func_stack {
 	int size;

tools/lib/traceevent/plugin_hrtimer.c

@@ -23,6 +23,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 static int timer_expire_handler(struct trace_seq *s,
 				struct tep_record *record,

tools/lib/traceevent/plugin_jbd2.c

@@ -22,6 +22,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #define MINORBITS	20
 #define MINORMASK	((1U << MINORBITS) - 1)

tools/lib/traceevent/plugin_kmem.c

@@ -22,6 +22,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 static int call_site_handler(struct trace_seq *s, struct tep_record *record,
 			     struct event_format *event, void *context)

tools/lib/traceevent/plugin_kvm.c

@@ -23,6 +23,7 @@
 #include <stdint.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #ifdef HAVE_UDIS86
 

tools/lib/traceevent/plugin_mac80211.c

@@ -22,6 +22,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #define INDENT 65
 

tools/lib/traceevent/plugin_sched_switch.c

@@ -22,6 +22,7 @@
 #include <string.h>
 
 #include "event-parse.h"
+#include "trace-seq.h"
 
 static void write_state(struct trace_seq *s, int val)
 {

tools/lib/traceevent/plugin_scsi.c

@@ -3,6 +3,7 @@
 #include <string.h>
 #include <inttypes.h>
 #include "event-parse.h"
+#include "trace-seq.h"
 
 typedef unsigned long sector_t;
 typedef uint64_t u64;

tools/lib/traceevent/plugin_xen.c

@@ -3,6 +3,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include "event-parse.h"
+#include "trace-seq.h"
 
 #define __HYPERVISOR_set_trap_table			0
 #define __HYPERVISOR_mmu_update				1

tools/lib/traceevent/trace-seq.c

@@ -3,6 +3,8 @@
  * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
  *
  */
+#include "trace-seq.h"
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>

tools/lib/traceevent/trace-seq.h

@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+
+#ifndef _TRACE_SEQ_H
+#define _TRACE_SEQ_H
+
+#include <stdarg.h>
+#include <stdio.h>
+
+/* ----------------------- trace_seq ----------------------- */
+
+#ifndef TRACE_SEQ_BUF_SIZE
+#define TRACE_SEQ_BUF_SIZE 4096
+#endif
+
+enum trace_seq_fail {
+	TRACE_SEQ__GOOD,
+	TRACE_SEQ__BUFFER_POISONED,
+	TRACE_SEQ__MEM_ALLOC_FAILED,
+};
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE).
+ */
+
+struct trace_seq {
+	char			*buffer;
+	unsigned int		buffer_size;
+	unsigned int		len;
+	unsigned int		readpos;
+	enum trace_seq_fail	state;
+};
+
+void trace_seq_init(struct trace_seq *s);
+void trace_seq_reset(struct trace_seq *s);
+void trace_seq_destroy(struct trace_seq *s);
+
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+	__attribute__ ((format (printf, 2, 0)));
+
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+
+extern void trace_seq_terminate(struct trace_seq *s);
+
+extern int trace_seq_do_fprintf(struct trace_seq *s, FILE *fp);
+extern int trace_seq_do_printf(struct trace_seq *s);
+
+#endif /* _TRACE_SEQ_H */

tools/perf/Makefile.perf

@@ -777,14 +777,14 @@ endif
 	$(call QUIET_INSTALL, libexec) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBBPF
-	$(call QUIET_INSTALL, lib) \
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, include/bpf) \
-		$(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, lib) \
-		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
-	$(call QUIET_INSTALL, examples/bpf) \
-		$(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, bpf-headers) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'; \
+		$(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \
+		$(INSTALL) include/bpf/linux/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf/linux'
+	$(call QUIET_INSTALL, bpf-examples) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \
+		$(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
 endif
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'

tools/perf/arch/arm64/Makefile

@@ -11,15 +11,16 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 
 out    := $(OUTPUT)arch/arm64/include/generated/asm
 header := $(out)/syscalls.c
-sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
+incpath := $(srctree)/tools
+sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h
 sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
 systbl := $(sysprf)/mksyscalltbl
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header): $(sysdef) $(systbl)
-	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@
 
 clean::
 	$(call QUIET_CLEAN, arm64) $(RM) $(header)

tools/perf/arch/arm64/annotate/instructions.c

@@ -8,6 +8,63 @@ struct arm64_annotate {
 		jump_insn;
 };
 
+static int arm64_mov__parse(struct arch *arch __maybe_unused,
+			    struct ins_operands *ops,
+			    struct map_symbol *ms __maybe_unused)
+{
+	char *s = strchr(ops->raw, ','), *target, *endptr;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+
+	if (ops->source.raw == NULL)
+		return -1;
+
+	target = ++s;
+	ops->target.raw = strdup(target);
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	ops->target.addr = strtoull(target, &endptr, 16);
+	if (endptr == target)
+		goto out_free_target;
+
+	s = strchr(endptr, '<');
+	if (s == NULL)
+		goto out_free_target;
+	endptr = strchr(s + 1, '>');
+	if (endptr == NULL)
+		goto out_free_target;
+
+	*endptr = '\0';
+	*s = ' ';
+	ops->target.name = strdup(s);
+	*s = '<';
+	*endptr = '>';
+	if (ops->target.name == NULL)
+		goto out_free_target;
+
+	return 0;
+
+out_free_target:
+	zfree(&ops->target.raw);
+out_free_source:
+	zfree(&ops->source.raw);
+	return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+			  struct ins_operands *ops);
+
+static struct ins_ops arm64_mov_ops = {
+	.parse	   = arm64_mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
 static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const char *name)
 {
 	struct arm64_annotate *arm = arch->priv;
@@ -21,7 +78,7 @@ static struct ins_ops *arm64__associate_instruction_ops(struct arch *arch, const
 	else if (!strcmp(name, "ret"))
 		ops = &ret_ops;
 	else
-		return NULL;
+		ops = &arm64_mov_ops;
 
 	arch__associate_ins_ops(arch, name, ops);
 	return ops;