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>

6 files changed, 29 insertions, 18 deletions

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 699c5bc51a92..448759d4a263 100644
--- a/kernel/kprobes.c
+++ b/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);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d5038005eb5d..d4a06e714645 100644
--- a/kernel/trace/Kconfig
+++ b/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
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index e57980845549..90f2701d92a7 100644
--- a/kernel/trace/Makefile
+++ b/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
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 707445ceb7ef..0ed834d6beb0 100644
--- a/kernel/trace/trace.c
+++ b/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"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 5f688cc724f0..12fb540da0e5 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/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;
 		}
 	}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 0c0ae54d44c6..903273c93e61 100644
--- a/kernel/trace/trace_probe.h
+++ b/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;