Merge tag 'v3.19-rc7' into x86/asm, to refresh the branch before pulling in new changes

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

12 files changed, 126 insertions, 57 deletions

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d6594e457a25..a64e7a207d2b 100644
--- a/kernel/bpf/core.c
+++ b/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 */
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 088ac0b1b106..536edc2be307 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -150,7 +150,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 	int ufd = attr->map_fd;
 	struct fd f = fdget(ufd);
 	struct bpf_map *map;
-	void *key, *value;
+	void *key, *value, *ptr;
 	int err;
 
 	if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
@@ -169,20 +169,29 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (copy_from_user(key, ukey, map->key_size) != 0)
 		goto free_key;
 
-	err = -ENOENT;
-	rcu_read_lock();
-	value = map->ops->map_lookup_elem(map, key);
+	err = -ENOMEM;
+	value = kmalloc(map->value_size, GFP_USER);
 	if (!value)
-		goto err_unlock;
+		goto free_key;
+
+	rcu_read_lock();
+	ptr = map->ops->map_lookup_elem(map, key);
+	if (ptr)
+		memcpy(value, ptr, map->value_size);
+	rcu_read_unlock();
+
+	err = -ENOENT;
+	if (!ptr)
+		goto free_value;
 
 	err = -EFAULT;
 	if (copy_to_user(uvalue, value, map->value_size) != 0)
-		goto err_unlock;
+		goto free_value;
 
 	err = 0;
 
-err_unlock:
-	rcu_read_unlock();
+free_value:
+	kfree(value);
 free_key:
 	kfree(key);
 err_put:
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index bb263d0caab3..04cfe8ace520 100644
--- a/kernel/cgroup.c
+++ b/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
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index f191bddf64b8..7b40c5f07dce 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/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)");
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 882f835a0d85..19efcf13375a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6776,7 +6776,6 @@ 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);
@@ -7420,7 +7419,19 @@ 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)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 06f58309fed2..ee619929cf90 100644
--- a/kernel/kprobes.c
+++ b/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 = {
diff --git a/kernel/module.c b/kernel/module.c
index 3965511ae133..d856e96a3cce 100644
--- a/kernel/module.c
+++ b/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)
diff --git a/kernel/params.c b/kernel/params.c
index 0af9b2c4e56c..728e05b167de 100644
--- a/kernel/params.c
+++ b/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++;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c0accc00566e..e628cb11b560 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7292,13 +7292,12 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 	 * since we will exit with TASK_RUNNING make sure we enter with it,
 	 * otherwise we will destroy state.
 	 */
-	if (WARN_ONCE(current->state != TASK_RUNNING,
+	WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change,
 			"do not call blocking ops when !TASK_RUNNING; "
 			"state=%lx set at [<%p>] %pS\n",
 			current->state,
 			(void *)current->task_state_change,
-			(void *)current->task_state_change))
-		__set_current_state(TASK_RUNNING);
+			(void *)current->task_state_change);
 
 	___might_sleep(file, line, preempt_offset);
 }
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 87a346fd6d61..28bf91c60a0b 100644
--- a/kernel/time/ntp.c
+++ b/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;
 }
 
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 6390517e77d4..2c85b7724af4 100644
--- a/kernel/time/time.c
+++ b/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;
 	}
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 6202b08f1933..beeeac9e0e3e 100644
--- a/kernel/workqueue.c
+++ b/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;
 }
 
 /**