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

Pull perf updates from Ingo Molnar:
 "The tooling changes maintained by Jiri Olsa until Arnaldo is on
  vacation:

  User visible changes:
   - Add -F option for specifying output fields (Namhyung Kim)
   - Propagate exit status of a command line workload for record command
     (Namhyung Kim)
   - Use tid for finding thread (Namhyung Kim)
   - Clarify the output of perf sched map plus small sched command
     fixes (Dongsheng Yang)
   - Wire up perf_regs and unwind support for ARM64 (Jean Pihet)
   - Factor hists statistics counts processing which in turn also fixes
     several bugs in TUI report command (Namhyung Kim)
   - Add --percentage option to control absolute/relative percentage
     output (Namhyung Kim)
   - Add --list-cmds to 'kmem', 'mem', 'lock' and 'sched', for use by
     completion scripts (Ramkumar Ramachandra)

  Development/infrastructure changes and fixes:
   - Android related fixes for pager and map dso resolving (Michael
     Lentine)
   - Add libdw DWARF post unwind support for ARM (Jean Pihet)
   - Consolidate types.h for ARM and ARM64 (Jean Pihet)
   - Fix possible null pointer dereference in session.c (Masanari Iida)
   - Cleanup, remove unused variables in map_switch_event() (Dongsheng
     Yang)
   - Remove nr_state_machine_bugs in perf latency (Dongsheng Yang)
   - Remove usage of trace_sched_wakeup(.success) (Peter Zijlstra)
   - Cleanups for perf.h header (Jiri Olsa)
   - Consolidate types.h and export.h within tools (Borislav Petkov)
   - Move u64_swap union to its single user's header, evsel.h (Borislav
     Petkov)
   - Fix for s390 to properly parse tracepoints plus test code
     (Alexander Yarygin)
   - Handle EINTR error for readn/writen (Namhyung Kim)
   - Add a test case for hists filtering (Namhyung Kim)
   - Share map_groups among threads of the same group (Arnaldo Carvalho
     de Melo, Jiri Olsa)
   - Making some code (cpu node map and report parse callchain callback)
     global to be usable by upcomming changes (Don Zickus)
   - Fix pmu object compilation error (Jiri Olsa)

  Kernel side changes:
   - intrusive uprobes fixes from Oleg Nesterov.  Since the interface is
     admin-only, and the bug only affects user-space ("any probed
     jmp/call can kill the application"), we queued these fixes via the
     development tree, as a special exception.
   - more fuzzer motivated race fixes and related refactoring and
     robustization.
   - allow PMU drivers to be built as modules.  (No actual module yet,
     because the x86 Intel uncore module wasn't ready in time for this)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (114 commits)
  perf tools: Add automatic remapping of Android libraries
  perf tools: Add cat as fallback pager
  perf tests: Add a testcase for histogram output sorting
  perf tests: Factor out print_hists_*()
  perf tools: Introduce reset_output_field()
  perf tools: Get rid of obsolete hist_entry__sort_list
  perf hists: Reset width of output fields with header length
  perf tools: Skip elided sort entries
  perf top: Add --fields option to specify output fields
  perf report/tui: Fix a bug when --fields/sort is given
  perf tools: Add ->sort() member to struct sort_entry
  perf report: Add -F option to specify output fields
  perf tools: Call perf_hpp__init() before setting up GUI browsers
  perf tools: Consolidate management of default sort orders
  perf tools: Allow hpp fields to be sort keys
  perf ui: Get rid of callback from __hpp__fmt()
  perf tools: Consolidate output field handling to hpp format routines
  perf tools: Use hpp formats to sort final output
  perf tools: Support event grouping in hpp ->sort()
  perf tools: Use hpp formats to sort hist entries
  ...

kernel/events/core.c

@@ -39,6 +39,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/mm_types.h>
 #include <linux/cgroup.h>
+#include <linux/module.h>
 
 #include "internal.h"
 
@@ -1677,6 +1678,8 @@ event_sched_in(struct perf_event *event,
 	u64 tstamp = perf_event_time(event);
 	int ret = 0;
 
+	lockdep_assert_held(&ctx->lock);
+
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
 
@@ -3244,9 +3247,13 @@ static void __free_event(struct perf_event *event)
 	if (event->ctx)
 		put_ctx(event->ctx);
 
+	if (event->pmu)
+		module_put(event->pmu->module);
+
 	call_rcu(&event->rcu_head, free_event_rcu);
 }
-static void free_event(struct perf_event *event)
+
+static void _free_event(struct perf_event *event)
 {
 	irq_work_sync(&event->pending);
 
@@ -3267,42 +3274,31 @@ static void free_event(struct perf_event *event)
 	if (is_cgroup_event(event))
 		perf_detach_cgroup(event);
 
-
 	__free_event(event);
 }
 
-int perf_event_release_kernel(struct perf_event *event)
+/*
+ * Used to free events which have a known refcount of 1, such as in error paths
+ * where the event isn't exposed yet and inherited events.
+ */
+static void free_event(struct perf_event *event)
 {
-	struct perf_event_context *ctx = event->ctx;
+	if (WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1,
+				"unexpected event refcount: %ld; ptr=%p\n",
+				atomic_long_read(&event->refcount), event)) {
+		/* leak to avoid use-after-free */
+		return;
+	}
 
-	WARN_ON_ONCE(ctx->parent_ctx);
-	/*
-	 * There are two ways this annotation is useful:
-	 *
-	 *  1) there is a lock recursion from perf_event_exit_task
-	 *     see the comment there.
-	 *
-	 *  2) there is a lock-inversion with mmap_sem through
-	 *     perf_event_read_group(), which takes faults while
-	 *     holding ctx->mutex, however this is called after
-	 *     the last filedesc died, so there is no possibility
-	 *     to trigger the AB-BA case.
-	 */
-	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
-	perf_remove_from_context(event, true);
-	mutex_unlock(&ctx->mutex);
-
-	free_event(event);
-
-	return 0;
+	_free_event(event);
 }
-EXPORT_SYMBOL_GPL(perf_event_release_kernel);
 
 /*
  * Called when the last reference to the file is gone.
  */
 static void put_event(struct perf_event *event)
 {
+	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *owner;
 
 	if (!atomic_long_dec_and_test(&event->refcount))
@@ -3341,9 +3337,33 @@ static void put_event(struct perf_event *event)
 		put_task_struct(owner);
 	}
 
-	perf_event_release_kernel(event);
+	WARN_ON_ONCE(ctx->parent_ctx);
+	/*
+	 * There are two ways this annotation is useful:
+	 *
+	 *  1) there is a lock recursion from perf_event_exit_task
+	 *     see the comment there.
+	 *
+	 *  2) there is a lock-inversion with mmap_sem through
+	 *     perf_event_read_group(), which takes faults while
+	 *     holding ctx->mutex, however this is called after
+	 *     the last filedesc died, so there is no possibility
+	 *     to trigger the AB-BA case.
+	 */
+	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
+	perf_remove_from_context(event, true);
+	mutex_unlock(&ctx->mutex);
+
+	_free_event(event);
 }
 
+int perf_event_release_kernel(struct perf_event *event)
+{
+	put_event(event);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(perf_event_release_kernel);
+
 static int perf_release(struct inode *inode, struct file *file)
 {
 	put_event(file->private_data);
@@ -6578,6 +6598,7 @@ free_pdc:
 	free_percpu(pmu->pmu_disable_count);
 	goto unlock;
 }
+EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
@@ -6599,6 +6620,7 @@ void perf_pmu_unregister(struct pmu *pmu)
 	put_device(pmu->dev);
 	free_pmu_context(pmu);
 }
+EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 
 struct pmu *perf_init_event(struct perf_event *event)
 {
@@ -6612,6 +6634,10 @@ struct pmu *perf_init_event(struct perf_event *event)
 	pmu = idr_find(&pmu_idr, event->attr.type);
 	rcu_read_unlock();
 	if (pmu) {
+		if (!try_module_get(pmu->module)) {
+			pmu = ERR_PTR(-ENODEV);
+			goto unlock;
+		}
 		event->pmu = pmu;
 		ret = pmu->event_init(event);
 		if (ret)
@@ -6620,6 +6646,10 @@ struct pmu *perf_init_event(struct perf_event *event)
 	}
 
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
+		if (!try_module_get(pmu->module)) {
+			pmu = ERR_PTR(-ENODEV);
+			goto unlock;
+		}
 		event->pmu = pmu;
 		ret = pmu->event_init(event);
 		if (!ret)
@@ -6798,6 +6828,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 err_pmu:
 	if (event->destroy)
 		event->destroy(event);
+	module_put(pmu->module);
 err_ns:
 	if (event->ns)
 		put_pid_ns(event->ns);
@@ -7067,20 +7098,26 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
+	if (task && group_leader &&
+	    group_leader->attr.inherit != attr.inherit) {
+		err = -EINVAL;
+		goto err_task;
+	}
+
 	get_online_cpus();
 
 	event = perf_event_alloc(&attr, cpu, task, group_leader, NULL,
 				 NULL, NULL);
 	if (IS_ERR(event)) {
 		err = PTR_ERR(event);
-		goto err_task;
+		goto err_cpus;
 	}
 
 	if (flags & PERF_FLAG_PID_CGROUP) {
 		err = perf_cgroup_connect(pid, event, &attr, group_leader);
 		if (err) {
 			__free_event(event);
-			goto err_task;
+			goto err_cpus;
 		}
 	}
 
@@ -7242,8 +7279,9 @@ err_context:
 	put_ctx(ctx);
 err_alloc:
 	free_event(event);
-err_task:
+err_cpus:
 	put_online_cpus();
+err_task:
 	if (task)
 		put_task_struct(task);
 err_group_fd:
@@ -7379,7 +7417,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 			 struct perf_event_context *child_ctx,
 			 struct task_struct *child)
 {
-	perf_remove_from_context(child_event, !!child_event->parent);
+	perf_remove_from_context(child_event, true);
 
 	/*
 	 * It can happen that the parent exits first, and has events
@@ -7394,7 +7432,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 
 static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 {
-	struct perf_event *child_event, *tmp;
+	struct perf_event *child_event;
 	struct perf_event_context *child_ctx;
 	unsigned long flags;
 
@@ -7448,24 +7486,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 */
 	mutex_lock(&child_ctx->mutex);
 
-again:
-	list_for_each_entry_safe(child_event, tmp, &child_ctx->pinned_groups,
-				 group_entry)
+	list_for_each_entry_rcu(child_event, &child_ctx->event_list, event_entry)
 		__perf_event_exit_task(child_event, child_ctx, child);
 
-	list_for_each_entry_safe(child_event, tmp, &child_ctx->flexible_groups,
-				 group_entry)
-		__perf_event_exit_task(child_event, child_ctx, child);
-
-	/*
-	 * If the last event was a group event, it will have appended all
-	 * its siblings to the list, but we obtained 'tmp' before that which
-	 * will still point to the list head terminating the iteration.
-	 */
-	if (!list_empty(&child_ctx->pinned_groups) ||
-	    !list_empty(&child_ctx->flexible_groups))
-		goto again;
-
 	mutex_unlock(&child_ctx->mutex);
 
 	put_ctx(child_ctx);

kernel/events/uprobes.c

@@ -60,8 +60,6 @@ static struct percpu_rw_semaphore dup_mmap_sem;
 
 /* Have a copy of original instruction */
 #define UPROBE_COPY_INSN	0
-/* Can skip singlestep */
-#define UPROBE_SKIP_SSTEP	1
 
 struct uprobe {
 	struct rb_node		rb_node;	/* node in the rb tree */
@@ -491,12 +489,9 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset)
 	uprobe->offset = offset;
 	init_rwsem(&uprobe->register_rwsem);
 	init_rwsem(&uprobe->consumer_rwsem);
-	/* For now assume that the instruction need not be single-stepped */
-	__set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
 
 	/* add to uprobes_tree, sorted on inode:offset */
 	cur_uprobe = insert_uprobe(uprobe);
-
 	/* a uprobe exists for this inode:offset combination */
 	if (cur_uprobe) {
 		kfree(uprobe);
@@ -1628,20 +1623,6 @@ bool uprobe_deny_signal(void)
 	return true;
 }
 
-/*
- * Avoid singlestepping the original instruction if the original instruction
- * is a NOP or can be emulated.
- */
-static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs)
-{
-	if (test_bit(UPROBE_SKIP_SSTEP, &uprobe->flags)) {
-		if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
-			return true;
-		clear_bit(UPROBE_SKIP_SSTEP, &uprobe->flags);
-	}
-	return false;
-}
-
 static void mmf_recalc_uprobes(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;
@@ -1868,13 +1849,13 @@ static void handle_swbp(struct pt_regs *regs)
 
 	handler_chain(uprobe, regs);
 
-	if (can_skip_sstep(uprobe, regs))
+	if (arch_uprobe_skip_sstep(&uprobe->arch, regs))
 		goto out;
 
 	if (!pre_ssout(uprobe, regs, bp_vaddr))
 		return;
 
-	/* can_skip_sstep() succeeded, or restart if can't singlestep */
+	/* arch_uprobe_skip_sstep() succeeded, or restart if can't singlestep */
 out:
 	put_uprobe(uprobe);
 }
@@ -1886,10 +1867,11 @@ out:
 static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
 {
 	struct uprobe *uprobe;
+	int err = 0;
 
 	uprobe = utask->active_uprobe;
 	if (utask->state == UTASK_SSTEP_ACK)
-		arch_uprobe_post_xol(&uprobe->arch, regs);
+		err = arch_uprobe_post_xol(&uprobe->arch, regs);
 	else if (utask->state == UTASK_SSTEP_TRAPPED)
 		arch_uprobe_abort_xol(&uprobe->arch, regs);
 	else
@@ -1903,6 +1885,11 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs)
 	spin_lock_irq(&current->sighand->siglock);
 	recalc_sigpending(); /* see uprobe_deny_signal() */
 	spin_unlock_irq(&current->sighand->siglock);
+
+	if (unlikely(err)) {
+		uprobe_warn(current, "execute the probed insn, sending SIGILL.");
+		force_sig_info(SIGILL, SEND_SIG_FORCED, current);
+	}
 }
 
 /*

kernel/hrtimer.c

@@ -1039,6 +1039,7 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(__hrtimer_start_range_ns);
 
 /**
  * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU