Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main updates in this cycle were:

   - Lots of perf tooling changes too voluminous to list (big perf trace
     and perf stat improvements, lots of libtraceevent reorganization,
     etc.), so I'll list the authors and refer to the changelog for
     details:

       Benjamin Peterson, Jérémie Galarneau, Kim Phillips, Peter
       Zijlstra, Ravi Bangoria, Sangwon Hong, Sean V Kelley, Steven
       Rostedt, Thomas Gleixner, Ding Xiang, Eduardo Habkost, Thomas
       Richter, Andi Kleen, Sanskriti Sharma, Adrian Hunter, Tzvetomir
       Stoyanov, Arnaldo Carvalho de Melo, Jiri Olsa.

     ... with the bulk of the changes written by Jiri Olsa, Tzvetomir
     Stoyanov and Arnaldo Carvalho de Melo.

   - Continued intel_rdt work with a focus on playing well with perf
     events. This also imported some non-perf RDT work due to
     dependencies. (Reinette Chatre)

   - Implement counter freezing for Arch Perfmon v4 (Skylake and newer).
     This allows to speed up the PMI handler by avoiding unnecessary MSR
     writes and make it more accurate. (Andi Kleen)

   - kprobes cleanups and simplification (Masami Hiramatsu)

   - Intel Goldmont PMU updates (Kan Liang)

   - ... plus misc other fixes and updates"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (155 commits)
  kprobes/x86: Use preempt_enable() in optimized_callback()
  x86/intel_rdt: Prevent pseudo-locking from using stale pointers
  kprobes, x86/ptrace.h: Make regs_get_kernel_stack_nth() not fault on bad stack
  perf/x86/intel: Export mem events only if there's PEBS support
  x86/cpu: Drop pointless static qualifier in punit_dev_state_show()
  x86/intel_rdt: Fix initial allocation to consider CDP
  x86/intel_rdt: CBM overlap should also check for overlap with CDP peer
  x86/intel_rdt: Introduce utility to obtain CDP peer
  tools lib traceevent, perf tools: Move struct tep_handler definition in a local header file
  tools lib traceevent: Separate out tep_strerror() for strerror_r() issues
  perf python: More portable way to make CFLAGS work with clang
  perf python: Make clang_has_option() work on Python 3
  perf tools: Free temporary 'sys' string in read_event_files()
  perf tools: Avoid double free in read_event_file()
  perf tools: Free 'printk' string in parse_ftrace_printk()
  perf tools: Cleanup trace-event-info 'tdata' leak
  perf strbuf: Match va_{add,copy} with va_end
  perf test: S390 does not support watchpoints in test 22
  perf auxtrace: Include missing asm/bitsperlong.h to get BITS_PER_LONG
  tools include: Adopt linux/bits.h
  ...

2 files changed, 39 insertions, 14 deletions

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 5d3cf407e374..4a9937076331 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -459,10 +459,20 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 	if (size || handle->aux_flags) {
 		/*
 		 * Only send RECORD_AUX if we have something useful to communicate
+		 *
+		 * Note: the OVERWRITE records by themselves are not considered
+		 * useful, as they don't communicate any *new* information,
+		 * aside from the short-lived offset, that becomes history at
+		 * the next event sched-in and therefore isn't useful.
+		 * The userspace that needs to copy out AUX data in overwrite
+		 * mode should know to use user_page::aux_head for the actual
+		 * offset. So, from now on we don't output AUX records that
+		 * have *only* OVERWRITE flag set.
 		 */
 
-		perf_event_aux_event(handle->event, aux_head, size,
-		                     handle->aux_flags);
+		if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
+			perf_event_aux_event(handle->event, aux_head, size,
+			                     handle->aux_flags);
 	}
 
 	rb->user_page->aux_head = rb->aux_head;
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ab257be4d924..90e98e233647 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -546,8 +546,14 @@ static void do_free_cleaned_kprobes(void)
 	struct optimized_kprobe *op, *tmp;
 
 	list_for_each_entry_safe(op, tmp, &freeing_list, list) {
-		BUG_ON(!kprobe_unused(&op->kp));
 		list_del_init(&op->list);
+		if (WARN_ON_ONCE(!kprobe_unused(&op->kp))) {
+			/*
+			 * This must not happen, but if there is a kprobe
+			 * still in use, keep it on kprobes hash list.
+			 */
+			continue;
+		}
 		free_aggr_kprobe(&op->kp);
 	}
 }
@@ -700,11 +706,11 @@ static void unoptimize_kprobe(struct kprobe *p, bool force)
 }
 
 /* Cancel unoptimizing for reusing */
-static void reuse_unused_kprobe(struct kprobe *ap)
+static int reuse_unused_kprobe(struct kprobe *ap)
 {
 	struct optimized_kprobe *op;
+	int ret;
 
-	BUG_ON(!kprobe_unused(ap));
 	/*
 	 * Unused kprobe MUST be on the way of delayed unoptimizing (means
 	 * there is still a relative jump) and disabled.
@@ -714,8 +720,12 @@ static void reuse_unused_kprobe(struct kprobe *ap)
 	/* Enable the probe again */
 	ap->flags &= ~KPROBE_FLAG_DISABLED;
 	/* Optimize it again (remove from op->list) */
-	BUG_ON(!kprobe_optready(ap));
+	ret = kprobe_optready(ap);
+	if (ret)
+		return ret;
+
 	optimize_kprobe(ap);
+	return 0;
 }
 
 /* Remove optimized instructions */
@@ -940,11 +950,16 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt)
 #define kprobe_disarmed(p)			kprobe_disabled(p)
 #define wait_for_kprobe_optimizer()		do {} while (0)
 
-/* There should be no unused kprobes can be reused without optimization */
-static void reuse_unused_kprobe(struct kprobe *ap)
+static int reuse_unused_kprobe(struct kprobe *ap)
 {
+	/*
+	 * If the optimized kprobe is NOT supported, the aggr kprobe is
+	 * released at the same time that the last aggregated kprobe is
+	 * unregistered.
+	 * Thus there should be no chance to reuse unused kprobe.
+	 */
 	printk(KERN_ERR "Error: There should be no unused kprobe here.\n");
-	BUG_ON(kprobe_unused(ap));
+	return -EINVAL;
 }
 
 static void free_aggr_kprobe(struct kprobe *p)
@@ -1259,8 +1274,6 @@ NOKPROBE_SYMBOL(cleanup_rp_inst);
 /* Add the new probe to ap->list */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
-	BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
-
 	if (p->post_handler)
 		unoptimize_kprobe(ap, true);	/* Fall back to normal kprobe */
 
@@ -1318,9 +1331,12 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
 			goto out;
 		}
 		init_aggr_kprobe(ap, orig_p);
-	} else if (kprobe_unused(ap))
+	} else if (kprobe_unused(ap)) {
 		/* This probe is going to die. Rescue it */
-		reuse_unused_kprobe(ap);
+		ret = reuse_unused_kprobe(ap);
+		if (ret)
+			goto out;
+	}
 
 	if (kprobe_gone(ap)) {
 		/*
@@ -1704,7 +1720,6 @@ noclean:
 	return 0;
 
 disarmed:
-	BUG_ON(!kprobe_disarmed(ap));
 	hlist_del_rcu(&ap->hlist);
 	return 0;
 }