Merge branch 'perf/urgent' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/bpf/core.c

@@ -163,7 +163,7 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 
 void bpf_jit_binary_free(struct bpf_binary_header *hdr)
 {
-	module_free(NULL, hdr);
+	module_memfree(hdr);
 }
 #endif /* CONFIG_BPF_JIT */
 

kernel/cgroup.c

@@ -1909,7 +1909,7 @@ static void cgroup_kill_sb(struct super_block *sb)
 	 *
 	 * And don't kill the default root.
 	 */
-	if (css_has_online_children(&root->cgrp.self) ||
+	if (!list_empty(&root->cgrp.self.children) ||
 	    root == &cgrp_dfl_root)
 		cgroup_put(&root->cgrp);
 	else

kernel/debug/kdb/kdb_main.c

@@ -2023,7 +2023,7 @@ static int kdb_lsmod(int argc, const char **argv)
 		kdb_printf("%-20s%8u  0x%p ", mod->name,
 			   mod->core_size, (void *)mod);
 #ifdef CONFIG_MODULE_UNLOAD
-		kdb_printf("%4ld ", module_refcount(mod));
+		kdb_printf("%4d ", module_refcount(mod));
 #endif
 		if (mod->state == MODULE_STATE_GOING)
 			kdb_printf(" (Unloading)");

kernel/events/core.c

@@ -6787,7 +6787,6 @@ skip_type:
 		__perf_event_init_context(&cpuctx->ctx);
 		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
-		cpuctx->ctx.type = cpu_context;
 		cpuctx->ctx.pmu = pmu;
 
 		__perf_cpu_hrtimer_init(cpuctx, cpu);
@@ -7431,7 +7430,19 @@ SYSCALL_DEFINE5(perf_event_open,
 		 * task or CPU context:
 		 */
 		if (move_group) {
-			if (group_leader->ctx->type != ctx->type)
+			/*
+			 * Make sure we're both on the same task, or both
+			 * per-cpu events.
+			 */
+			if (group_leader->ctx->task != ctx->task)
+				goto err_context;
+
+			/*
+			 * Make sure we're both events for the same CPU;
+			 * grouping events for different CPUs is broken; since
+			 * you can never concurrently schedule them anyhow.
+			 */
+			if (group_leader->cpu != event->cpu)
 				goto err_context;
 		} else {
 			if (group_leader->ctx != ctx)

kernel/kprobes.c

@@ -127,7 +127,7 @@ static void *alloc_insn_page(void)
 
 static void free_insn_page(void *page)
 {
-	module_free(NULL, page);
+	module_memfree(page);
 }
 
 struct kprobe_insn_cache kprobe_insn_slots = {

kernel/module.c

@@ -772,9 +772,18 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 	return 0;
 }
 
-unsigned long module_refcount(struct module *mod)
+/**
+ * module_refcount - return the refcount or -1 if unloading
+ *
+ * @mod:	the module we're checking
+ *
+ * Returns:
+ *	-1 if the module is in the process of unloading
+ *	otherwise the number of references in the kernel to the module
+ */
+int module_refcount(struct module *mod)
 {
-	return (unsigned long)atomic_read(&mod->refcnt) - MODULE_REF_BASE;
+	return atomic_read(&mod->refcnt) - MODULE_REF_BASE;
 }
 EXPORT_SYMBOL(module_refcount);
 
@@ -856,7 +865,7 @@ static inline void print_unload_info(struct seq_file *m, struct module *mod)
 	struct module_use *use;
 	int printed_something = 0;
 
-	seq_printf(m, " %lu ", module_refcount(mod));
+	seq_printf(m, " %i ", module_refcount(mod));
 
 	/*
 	 * Always include a trailing , so userspace can differentiate
@@ -908,7 +917,7 @@ EXPORT_SYMBOL_GPL(symbol_put_addr);
 static ssize_t show_refcnt(struct module_attribute *mattr,
 			   struct module_kobject *mk, char *buffer)
 {
-	return sprintf(buffer, "%lu\n", module_refcount(mk->mod));
+	return sprintf(buffer, "%i\n", module_refcount(mk->mod));
 }
 
 static struct module_attribute modinfo_refcnt =
@@ -1795,7 +1804,7 @@ static void unset_module_core_ro_nx(struct module *mod) { }
 static void unset_module_init_ro_nx(struct module *mod) { }
 #endif
 
-void __weak module_free(struct module *mod, void *module_region)
+void __weak module_memfree(void *module_region)
 {
 	vfree(module_region);
 }
@@ -1804,6 +1813,10 @@ void __weak module_arch_cleanup(struct module *mod)
 {
 }
 
+void __weak module_arch_freeing_init(struct module *mod)
+{
+}
+
 /* Free a module, remove from lists, etc. */
 static void free_module(struct module *mod)
 {
@@ -1841,7 +1854,8 @@ static void free_module(struct module *mod)
 
 	/* This may be NULL, but that's OK */
 	unset_module_init_ro_nx(mod);
-	module_free(mod, mod->module_init);
+	module_arch_freeing_init(mod);
+	module_memfree(mod->module_init);
 	kfree(mod->args);
 	percpu_modfree(mod);
 
@@ -1850,7 +1864,7 @@ static void free_module(struct module *mod)
 
 	/* Finally, free the core (containing the module structure) */
 	unset_module_core_ro_nx(mod);
-	module_free(mod, mod->module_core);
+	module_memfree(mod->module_core);
 
 #ifdef CONFIG_MPU
 	update_protections(current->mm);
@@ -2785,7 +2799,7 @@ static int move_module(struct module *mod, struct load_info *info)
 		 */
 		kmemleak_ignore(ptr);
 		if (!ptr) {
-			module_free(mod, mod->module_core);
+			module_memfree(mod->module_core);
 			return -ENOMEM;
 		}
 		memset(ptr, 0, mod->init_size);
@@ -2930,8 +2944,9 @@ static struct module *layout_and_allocate(struct load_info *info, int flags)
 static void module_deallocate(struct module *mod, struct load_info *info)
 {
 	percpu_modfree(mod);
-	module_free(mod, mod->module_init);
-	module_free(mod, mod->module_core);
+	module_arch_freeing_init(mod);
+	module_memfree(mod->module_init);
+	module_memfree(mod->module_core);
 }
 
 int __weak module_finalize(const Elf_Ehdr *hdr,
@@ -2983,10 +2998,31 @@ static void do_mod_ctors(struct module *mod)
 #endif
 }
 
+/* For freeing module_init on success, in case kallsyms traversing */
+struct mod_initfree {
+	struct rcu_head rcu;
+	void *module_init;
+};
+
+static void do_free_init(struct rcu_head *head)
+{
+	struct mod_initfree *m = container_of(head, struct mod_initfree, rcu);
+	module_memfree(m->module_init);
+	kfree(m);
+}
+
 /* This is where the real work happens */
 static int do_init_module(struct module *mod)
 {
 	int ret = 0;
+	struct mod_initfree *freeinit;
+
+	freeinit = kmalloc(sizeof(*freeinit), GFP_KERNEL);
+	if (!freeinit) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+	freeinit->module_init = mod->module_init;
 
 	/*
 	 * We want to find out whether @mod uses async during init.  Clear
@@ -2999,18 +3035,7 @@ static int do_init_module(struct module *mod)
 	if (mod->init != NULL)
 		ret = do_one_initcall(mod->init);
 	if (ret < 0) {
-		/*
-		 * Init routine failed: abort.  Try to protect us from
-		 * buggy refcounters.
-		 */
-		mod->state = MODULE_STATE_GOING;
-		synchronize_sched();
-		module_put(mod);
-		blocking_notifier_call_chain(&module_notify_list,
-					     MODULE_STATE_GOING, mod);
-		free_module(mod);
-		wake_up_all(&module_wq);
-		return ret;
+		goto fail_free_freeinit;
 	}
 	if (ret > 0) {
 		pr_warn("%s: '%s'->init suspiciously returned %d, it should "
@@ -3055,15 +3080,35 @@ static int do_init_module(struct module *mod)
 	mod->strtab = mod->core_strtab;
 #endif
 	unset_module_init_ro_nx(mod);
-	module_free(mod, mod->module_init);
+	module_arch_freeing_init(mod);
 	mod->module_init = NULL;
 	mod->init_size = 0;
 	mod->init_ro_size = 0;
 	mod->init_text_size = 0;
+	/*
+	 * We want to free module_init, but be aware that kallsyms may be
+	 * walking this with preempt disabled.  In all the failure paths,
+	 * we call synchronize_rcu/synchronize_sched, but we don't want
+	 * to slow down the success path, so use actual RCU here.
+	 */
+	call_rcu(&freeinit->rcu, do_free_init);
 	mutex_unlock(&module_mutex);
 	wake_up_all(&module_wq);
 
 	return 0;
+
+fail_free_freeinit:
+	kfree(freeinit);
+fail:
+	/* Try to protect us from buggy refcounters. */
+	mod->state = MODULE_STATE_GOING;
+	synchronize_sched();
+	module_put(mod);
+	blocking_notifier_call_chain(&module_notify_list,
+				     MODULE_STATE_GOING, mod);
+	free_module(mod);
+	wake_up_all(&module_wq);
+	return ret;
 }
 
 static int may_init_module(void)

kernel/params.c

@@ -642,12 +642,15 @@ static __modinit int add_sysfs_param(struct module_kobject *mk,
 	mk->mp->grp.attrs = new_attrs;
 
 	/* Tack new one on the end. */
+	memset(&mk->mp->attrs[mk->mp->num], 0, sizeof(mk->mp->attrs[0]));
 	sysfs_attr_init(&mk->mp->attrs[mk->mp->num].mattr.attr);
 	mk->mp->attrs[mk->mp->num].param = kp;
 	mk->mp->attrs[mk->mp->num].mattr.show = param_attr_show;
 	/* Do not allow runtime DAC changes to make param writable. */
 	if ((kp->perm & (S_IWUSR | S_IWGRP | S_IWOTH)) != 0)
 		mk->mp->attrs[mk->mp->num].mattr.store = param_attr_store;
+	else
+		mk->mp->attrs[mk->mp->num].mattr.store = NULL;
 	mk->mp->attrs[mk->mp->num].mattr.attr.name = (char *)name;
 	mk->mp->attrs[mk->mp->num].mattr.attr.mode = kp->perm;
 	mk->mp->num++;

kernel/range.c

@@ -113,12 +113,12 @@ static int cmp_range(const void *x1, const void *x2)
 {
 	const struct range *r1 = x1;
 	const struct range *r2 = x2;
-	s64 start1, start2;
 
-	start1 = r1->start;
-	start2 = r2->start;
-
-	return start1 - start2;
+	if (r1->start < r2->start)
+		return -1;
+	if (r1->start > r2->start)
+		return 1;
+	return 0;
 }
 
 int clean_sort_range(struct range *range, int az)

kernel/sys.c

@@ -2210,9 +2210,13 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		up_write(&me->mm->mmap_sem);
 		break;
 	case PR_MPX_ENABLE_MANAGEMENT:
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
 		error = MPX_ENABLE_MANAGEMENT(me);
 		break;
 	case PR_MPX_DISABLE_MANAGEMENT:
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
 		error = MPX_DISABLE_MANAGEMENT(me);
 		break;
 	default:

kernel/time/ntp.c

@@ -633,6 +633,13 @@ int ntp_validate_timex(struct timex *txc)
 	if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
 		return -EPERM;
 
+	if (txc->modes & ADJ_FREQUENCY) {
+		if (LONG_MIN / PPM_SCALE > txc->freq)
+			return -EINVAL;
+		if (LONG_MAX / PPM_SCALE < txc->freq)
+			return -EINVAL;
+	}
+
 	return 0;
 }
 

kernel/time/time.c

@@ -196,6 +196,10 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
 	if (tv) {
 		if (copy_from_user(&user_tv, tv, sizeof(*tv)))
 			return -EFAULT;
+
+		if (!timeval_valid(&user_tv))
+			return -EINVAL;
+
 		new_ts.tv_sec = user_tv.tv_sec;
 		new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
 	}

kernel/trace/ftrace.c

@@ -2497,12 +2497,14 @@ static void ftrace_run_update_code(int command)
 }
 
 static void ftrace_run_modify_code(struct ftrace_ops *ops, int command,
-				   struct ftrace_hash *old_hash)
+				   struct ftrace_ops_hash *old_hash)
 {
 	ops->flags |= FTRACE_OPS_FL_MODIFYING;
-	ops->old_hash.filter_hash = old_hash;
+	ops->old_hash.filter_hash = old_hash->filter_hash;
+	ops->old_hash.notrace_hash = old_hash->notrace_hash;
 	ftrace_run_update_code(command);
 	ops->old_hash.filter_hash = NULL;
+	ops->old_hash.notrace_hash = NULL;
 	ops->flags &= ~FTRACE_OPS_FL_MODIFYING;
 }
 
@@ -3579,7 +3581,7 @@ static struct ftrace_ops trace_probe_ops __read_mostly =
 
 static int ftrace_probe_registered;
 
-static void __enable_ftrace_function_probe(struct ftrace_hash *old_hash)
+static void __enable_ftrace_function_probe(struct ftrace_ops_hash *old_hash)
 {
 	int ret;
 	int i;
@@ -3637,6 +3639,7 @@ int
 register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 			      void *data)
 {
+	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_func_probe *entry;
 	struct ftrace_hash **orig_hash = &trace_probe_ops.func_hash->filter_hash;
 	struct ftrace_hash *old_hash = *orig_hash;
@@ -3658,6 +3661,10 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	mutex_lock(&trace_probe_ops.func_hash->regex_lock);
 
+	old_hash_ops.filter_hash = old_hash;
+	/* Probes only have filters */
+	old_hash_ops.notrace_hash = NULL;
+
 	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash);
 	if (!hash) {
 		count = -ENOMEM;
@@ -3718,7 +3725,7 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 
 	ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
 
-	__enable_ftrace_function_probe(old_hash);
+	__enable_ftrace_function_probe(&old_hash_ops);
 
 	if (!ret)
 		free_ftrace_hash_rcu(old_hash);
@@ -4006,10 +4013,34 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 }
 
 static void ftrace_ops_update_code(struct ftrace_ops *ops,
-				   struct ftrace_hash *old_hash)
+				   struct ftrace_ops_hash *old_hash)
 {
-	if (ops->flags & FTRACE_OPS_FL_ENABLED && ftrace_enabled)
+	struct ftrace_ops *op;
+
+	if (!ftrace_enabled)
+		return;
+
+	if (ops->flags & FTRACE_OPS_FL_ENABLED) {
 		ftrace_run_modify_code(ops, FTRACE_UPDATE_CALLS, old_hash);
+		return;
+	}
+
+	/*
+	 * If this is the shared global_ops filter, then we need to
+	 * check if there is another ops that shares it, is enabled.
+	 * If so, we still need to run the modify code.
+	 */
+	if (ops->func_hash != &global_ops.local_hash)
+		return;
+
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+		if (op->func_hash == &global_ops.local_hash &&
+		    op->flags & FTRACE_OPS_FL_ENABLED) {
+			ftrace_run_modify_code(op, FTRACE_UPDATE_CALLS, old_hash);
+			/* Only need to do this once */
+			return;
+		}
+	} while_for_each_ftrace_op(op);
 }
 
 static int
@@ -4017,6 +4048,7 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 		unsigned long ip, int remove, int reset, int enable)
 {
 	struct ftrace_hash **orig_hash;
+	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_hash *old_hash;
 	struct ftrace_hash *hash;
 	int ret;
@@ -4053,9 +4085,11 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 
 	mutex_lock(&ftrace_lock);
 	old_hash = *orig_hash;
+	old_hash_ops.filter_hash = ops->func_hash->filter_hash;
+	old_hash_ops.notrace_hash = ops->func_hash->notrace_hash;
 	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
 	if (!ret) {
-		ftrace_ops_update_code(ops, old_hash);
+		ftrace_ops_update_code(ops, &old_hash_ops);
 		free_ftrace_hash_rcu(old_hash);
 	}
 	mutex_unlock(&ftrace_lock);
@@ -4267,6 +4301,7 @@ static void __init set_ftrace_early_filters(void)
 int ftrace_regex_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = (struct seq_file *)file->private_data;
+	struct ftrace_ops_hash old_hash_ops;
 	struct ftrace_iterator *iter;
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *old_hash;
@@ -4300,10 +4335,12 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 
 		mutex_lock(&ftrace_lock);
 		old_hash = *orig_hash;
+		old_hash_ops.filter_hash = iter->ops->func_hash->filter_hash;
+		old_hash_ops.notrace_hash = iter->ops->func_hash->notrace_hash;
 		ret = ftrace_hash_move(iter->ops, filter_hash,
 				       orig_hash, iter->hash);
 		if (!ret) {
-			ftrace_ops_update_code(iter->ops, old_hash);
+			ftrace_ops_update_code(iter->ops, &old_hash_ops);
 			free_ftrace_hash_rcu(old_hash);
 		}
 		mutex_unlock(&ftrace_lock);

kernel/trace/trace.c

@@ -6918,7 +6918,6 @@ void __init trace_init(void)
 			tracepoint_printk = 0;
 	}
 	tracer_alloc_buffers();
-	init_ftrace_syscalls();
 	trace_event_init();	
 }
 

kernel/trace/trace_events.c

@@ -2429,12 +2429,39 @@ static __init int event_trace_memsetup(void)
 	return 0;
 }
 
+static __init void
+early_enable_events(struct trace_array *tr, bool disable_first)
+{
+	char *buf = bootup_event_buf;
+	char *token;
+	int ret;
+
+	while (true) {
+		token = strsep(&buf, ",");
+
+		if (!token)
+			break;
+		if (!*token)
+			continue;
+
+		/* Restarting syscalls requires that we stop them first */
+		if (disable_first)
+			ftrace_set_clr_event(tr, token, 0);
+
+		ret = ftrace_set_clr_event(tr, token, 1);
+		if (ret)
+			pr_warn("Failed to enable trace event: %s\n", token);
+
+		/* Put back the comma to allow this to be called again */
+		if (buf)
+			*(buf - 1) = ',';
+	}
+}
+
 static __init int event_trace_enable(void)
 {
 	struct trace_array *tr = top_trace_array();
 	struct ftrace_event_call **iter, *call;
-	char *buf = bootup_event_buf;
-	char *token;
 	int ret;
 
 	if (!tr)
@@ -2456,18 +2483,7 @@ static __init int event_trace_enable(void)
 	 */
 	__trace_early_add_events(tr);
 
-	while (true) {
-		token = strsep(&buf, ",");
-
-		if (!token)
-			break;
-		if (!*token)
-			continue;
-
-		ret = ftrace_set_clr_event(tr, token, 1);
-		if (ret)
-			pr_warn("Failed to enable trace event: %s\n", token);
-	}
+	early_enable_events(tr, false);
 
 	trace_printk_start_comm();
 
@@ -2478,6 +2494,31 @@ static __init int event_trace_enable(void)
 	return 0;
 }
 
+/*
+ * event_trace_enable() is called from trace_event_init() first to
+ * initialize events and perhaps start any events that are on the
+ * command line. Unfortunately, there are some events that will not
+ * start this early, like the system call tracepoints that need
+ * to set the TIF_SYSCALL_TRACEPOINT flag of pid 1. But event_trace_enable()
+ * is called before pid 1 starts, and this flag is never set, making
+ * the syscall tracepoint never get reached, but the event is enabled
+ * regardless (and not doing anything).
+ */
+static __init int event_trace_enable_again(void)
+{
+	struct trace_array *tr;
+
+	tr = top_trace_array();
+	if (!tr)
+		return -ENODEV;
+
+	early_enable_events(tr, true);
+
+	return 0;
+}
+
+early_initcall(event_trace_enable_again);
+
 static __init int event_trace_init(void)
 {
 	struct trace_array *tr;

kernel/workqueue.c

@@ -1841,17 +1841,11 @@ static void pool_mayday_timeout(unsigned long __pool)
  * spin_lock_irq(pool->lock) which may be released and regrabbed
  * multiple times.  Does GFP_KERNEL allocations.  Called only from
  * manager.
- *
- * Return:
- * %false if no action was taken and pool->lock stayed locked, %true
- * otherwise.
  */
-static bool maybe_create_worker(struct worker_pool *pool)
+static void maybe_create_worker(struct worker_pool *pool)
 __releases(&pool->lock)
 __acquires(&pool->lock)
 {
-	if (!need_to_create_worker(pool))
-		return false;
 restart:
 	spin_unlock_irq(&pool->lock);
 
@@ -1877,7 +1871,6 @@ restart:
 	 */
 	if (need_to_create_worker(pool))
 		goto restart;
-	return true;
 }
 
 /**
@@ -1897,16 +1890,14 @@ restart:
  * multiple times.  Does GFP_KERNEL allocations.
  *
  * Return:
- * %false if the pool don't need management and the caller can safely start
- * processing works, %true indicates that the function released pool->lock
- * and reacquired it to perform some management function and that the
- * conditions that the caller verified while holding the lock before
- * calling the function might no longer be true.
+ * %false if the pool doesn't need management and the caller can safely
+ * start processing works, %true if management function was performed and
+ * the conditions that the caller verified before calling the function may
+ * no longer be true.
  */
 static bool manage_workers(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
-	bool ret = false;
 
 	/*
 	 * Anyone who successfully grabs manager_arb wins the arbitration
@@ -1919,12 +1910,12 @@ static bool manage_workers(struct worker *worker)
 	 * actual management, the pool may stall indefinitely.
 	 */
 	if (!mutex_trylock(&pool->manager_arb))
-		return ret;
+		return false;
 
-	ret |= maybe_create_worker(pool);
+	maybe_create_worker(pool);
 
 	mutex_unlock(&pool->manager_arb);
-	return ret;
+	return true;
 }
 
 /**