Merge tag 'noinstr-lds-2020-05-19' into core/rcu

Get the noinstr section and annotation markers to base the RCU parts on.

19 files changed, 139 insertions, 51 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index b69c8b460341..87f31bf1f0a0 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1326,6 +1326,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 	case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2:
 		if (!audit_enabled && msg_type != AUDIT_USER_AVC)
 			return 0;
+		/* exit early if there isn't at least one character to print */
+		if (data_len < 2)
+			return -EINVAL;
 
 		err = audit_filter(msg_type, AUDIT_FILTER_USER);
 		if (err == 1) { /* match or error */
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 70f71b154fa5..3fe0b006d2d2 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -469,7 +469,7 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
 		return -EOVERFLOW;
 
 	/* Make sure CPU is a valid possible cpu */
-	if (!cpu_possible(key_cpu))
+	if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu))
 		return -ENODEV;
 
 	if (qsize == 0) {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d85f37239540..7626b8024471 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2283,7 +2283,7 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp)
 }
 #endif
 
-const struct file_operations bpf_link_fops = {
+static const struct file_operations bpf_link_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_link_show_fdinfo,
 #endif
@@ -3628,8 +3628,10 @@ static int link_update(union bpf_attr *attr)
 		return PTR_ERR(link);
 
 	new_prog = bpf_prog_get(attr->link_update.new_prog_fd);
-	if (IS_ERR(new_prog))
-		return PTR_ERR(new_prog);
+	if (IS_ERR(new_prog)) {
+		ret = PTR_ERR(new_prog);
+		goto out_put_link;
+	}
 
 	if (flags & BPF_F_REPLACE) {
 		old_prog = bpf_prog_get(attr->link_update.old_prog_fd);
@@ -3638,6 +3640,9 @@ static int link_update(union bpf_attr *attr)
 			old_prog = NULL;
 			goto out_put_progs;
 		}
+	} else if (attr->link_update.old_prog_fd) {
+		ret = -EINVAL;
+		goto out_put_progs;
 	}
 
 #ifdef CONFIG_CGROUP_BPF
@@ -3653,6 +3658,8 @@ out_put_progs:
 		bpf_prog_put(old_prog);
 	if (ret)
 		bpf_prog_put(new_prog);
+out_put_link:
+	bpf_link_put(link);
 	return ret;
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 38cfcf701eeb..fa1d8245b925 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2118,6 +2118,15 @@ static bool register_is_const(struct bpf_reg_state *reg)
 	return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
 }
 
+static bool __is_pointer_value(bool allow_ptr_leaks,
+			       const struct bpf_reg_state *reg)
+{
+	if (allow_ptr_leaks)
+		return false;
+
+	return reg->type != SCALAR_VALUE;
+}
+
 static void save_register_state(struct bpf_func_state *state,
 				int spi, struct bpf_reg_state *reg)
 {
@@ -2308,6 +2317,16 @@ static int check_stack_read(struct bpf_verifier_env *env,
 			 * which resets stack/reg liveness for state transitions
 			 */
 			state->regs[value_regno].live |= REG_LIVE_WRITTEN;
+		} else if (__is_pointer_value(env->allow_ptr_leaks, reg)) {
+			/* If value_regno==-1, the caller is asking us whether
+			 * it is acceptable to use this value as a SCALAR_VALUE
+			 * (e.g. for XADD).
+			 * We must not allow unprivileged callers to do that
+			 * with spilled pointers.
+			 */
+			verbose(env, "leaking pointer from stack off %d\n",
+				off);
+			return -EACCES;
 		}
 		mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
 	} else {
@@ -2673,15 +2692,6 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
 	return -EACCES;
 }
 
-static bool __is_pointer_value(bool allow_ptr_leaks,
-			       const struct bpf_reg_state *reg)
-{
-	if (allow_ptr_leaks)
-		return false;
-
-	return reg->type != SCALAR_VALUE;
-}
-
 static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
 {
 	return cur_regs(env) + regno;
@@ -3089,7 +3099,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 	if (ret < 0)
 		return ret;
 
-	if (atype == BPF_READ) {
+	if (atype == BPF_READ && value_regno >= 0) {
 		if (ret == SCALAR_VALUE) {
 			mark_reg_unknown(env, regs, value_regno);
 			return 0;
@@ -10487,6 +10497,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 				return -EINVAL;
 			}
 			env->ops = bpf_verifier_ops[tgt_prog->type];
+			prog->expected_attach_type = tgt_prog->expected_attach_type;
 		}
 		if (!tgt_prog->jited) {
 			verbose(env, "Can attach to only JITed progs\n");
@@ -10831,6 +10842,13 @@ err_release_maps:
 		 * them now. Otherwise free_used_maps() will release them.
 		 */
 		release_maps(env);
+
+	/* extension progs temporarily inherit the attach_type of their targets
+	   for verification purposes, so set it back to zero before returning
+	 */
+	if (env->prog->type == BPF_PROG_TYPE_EXT)
+		env->prog->expected_attach_type = 0;
+
 	*prog = env->prog;
 err_unlock:
 	if (!is_priv)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bc9b98a9af9a..633b4ae72ed5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7491,10 +7491,17 @@ static void perf_event_task_output(struct perf_event *event,
 		goto out;
 
 	task_event->event_id.pid = perf_event_pid(event, task);
-	task_event->event_id.ppid = perf_event_pid(event, current);
-
 	task_event->event_id.tid = perf_event_tid(event, task);
-	task_event->event_id.ptid = perf_event_tid(event, current);
+
+	if (task_event->event_id.header.type == PERF_RECORD_EXIT) {
+		task_event->event_id.ppid = perf_event_pid(event,
+							task->real_parent);
+		task_event->event_id.ptid = perf_event_pid(event,
+							task->real_parent);
+	} else {  /* PERF_RECORD_FORK */
+		task_event->event_id.ppid = perf_event_pid(event, current);
+		task_event->event_id.ptid = perf_event_tid(event, current);
+	}
 
 	task_event->event_id.time = perf_event_clock(event);
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 389a88cb3081..ce2a75bc0ade 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -219,6 +219,7 @@ repeat:
 
 	write_unlock_irq(&tasklist_lock);
 	proc_flush_pid(thread_pid);
+	put_pid(thread_pid);
 	release_thread(p);
 	put_task_struct_rcu_user(p);
 
diff --git a/kernel/kcov.c b/kernel/kcov.c
index f50354202dbe..8accc9722a81 100644
--- a/kernel/kcov.c
+++ b/kernel/kcov.c
@@ -740,8 +740,8 @@ static const struct file_operations kcov_fops = {
  * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an
  * arbitrary 4-byte non-zero number as the instance id). This common handle
  * then gets saved into the task_struct of the process that issued the
- * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn
- * kernel threads, the common handle must be retrived via kcov_common_handle()
+ * KCOV_REMOTE_ENABLE ioctl. When this process issues system calls that spawn
+ * kernel threads, the common handle must be retrieved via kcov_common_handle()
  * and passed to the spawned threads via custom annotations. Those kernel
  * threads must in turn be annotated with kcov_remote_start(common_handle) and
  * kcov_remote_stop(). All of the threads that are spawned by the same process
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 86aba8706b16..30bd28d1d418 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -898,6 +898,13 @@ static int software_resume(void)
 	error = freeze_processes();
 	if (error)
 		goto Close_Finish;
+
+	error = freeze_kernel_threads();
+	if (error) {
+		thaw_processes();
+		goto Close_Finish;
+	}
+
 	error = load_image_and_restore();
 	thaw_processes();
  Finish:
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5ca567adfcb9..a05b85b3e0f7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1232,13 +1232,8 @@ static void uclamp_fork(struct task_struct *p)
 		return;
 
 	for_each_clamp_id(clamp_id) {
-		unsigned int clamp_value = uclamp_none(clamp_id);
-
-		/* By default, RT tasks always get 100% boost */
-		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
-			clamp_value = uclamp_none(UCLAMP_MAX);
-
-		uclamp_se_set(&p->uclamp_req[clamp_id], clamp_value, false);
+		uclamp_se_set(&p->uclamp_req[clamp_id],
+			      uclamp_none(clamp_id), false);
 	}
 }
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 713104884414..284fc1600063 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1989,8 +1989,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 		if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN)
 			sig = 0;
 	}
+	/*
+	 * Send with __send_signal as si_pid and si_uid are in the
+	 * parent's namespaces.
+	 */
 	if (valid_signal(sig) && sig)
-		__group_send_sig_info(sig, &info, tsk->parent);
+		__send_signal(sig, &info, tsk->parent, PIDTYPE_TGID, false);
 	__wake_up_parent(tsk, tsk->parent);
 	spin_unlock_irqrestore(&psig->siglock, flags);
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index ae69010d521a..1e9a8f9a3459 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -467,7 +467,6 @@ config PROFILE_ANNOTATED_BRANCHES
 config PROFILE_ALL_BRANCHES
 	bool "Profile all if conditionals" if !FORTIFY_SOURCE
 	select TRACE_BRANCH_PROFILING
-	imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED  # avoid false positives
 	help
 	  This tracer profiles all branch conditions. Every if ()
 	  taken in the kernel is recorded whether it hit or miss.
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 771eace959f3..b5765aeea698 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5154,6 +5154,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr)
 			list_del_rcu(&direct->next);
 			synchronize_rcu_tasks();
 			kfree(direct);
+			kfree(entry);
 			ftrace_direct_func_count--;
 		}
 	}
diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c
index 31c0fad4cb9e..c4c86de63cf9 100644
--- a/kernel/trace/preemptirq_delay_test.c
+++ b/kernel/trace/preemptirq_delay_test.c
@@ -113,22 +113,42 @@ static int preemptirq_delay_run(void *data)
 
 	for (i = 0; i < s; i++)
 		(testfuncs[i])(i);
+
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+
+	__set_current_state(TASK_RUNNING);
+
 	return 0;
 }
 
-static struct task_struct *preemptirq_start_test(void)
+static int preemptirq_run_test(void)
 {
+	struct task_struct *task;
+
 	char task_name[50];
 
 	snprintf(task_name, sizeof(task_name), "%s_test", test_mode);
-	return kthread_run(preemptirq_delay_run, NULL, task_name);
+	task =  kthread_run(preemptirq_delay_run, NULL, task_name);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	if (task)
+		kthread_stop(task);
+	return 0;
 }
 
 
 static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr,
 			 const char *buf, size_t count)
 {
-	preemptirq_start_test();
+	ssize_t ret;
+
+	ret = preemptirq_run_test();
+	if (ret)
+		return ret;
 	return count;
 }
 
@@ -148,11 +168,9 @@ static struct kobject *preemptirq_delay_kobj;
 
 static int __init preemptirq_delay_init(void)
 {
-	struct task_struct *test_task;
 	int retval;
 
-	test_task = preemptirq_start_test();
-	retval = PTR_ERR_OR_ZERO(test_task);
+	retval = preemptirq_run_test();
 	if (retval != 0)
 		return retval;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8d2b98812625..29615f15a820 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -947,7 +947,8 @@ int __trace_bputs(unsigned long ip, const char *str)
 EXPORT_SYMBOL_GPL(__trace_bputs);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data)
+static void tracing_snapshot_instance_cond(struct trace_array *tr,
+					   void *cond_data)
 {
 	struct tracer *tracer = tr->current_trace;
 	unsigned long flags;
@@ -8525,6 +8526,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	 */
 	allocate_snapshot = false;
 #endif
+
+	/*
+	 * Because of some magic with the way alloc_percpu() works on
+	 * x86_64, we need to synchronize the pgd of all the tables,
+	 * otherwise the trace events that happen in x86_64 page fault
+	 * handlers can't cope with accessing the chance that a
+	 * alloc_percpu()'d memory might be touched in the page fault trace
+	 * event. Oh, and we need to audit all other alloc_percpu() and vmalloc()
+	 * calls in tracing, because something might get triggered within a
+	 * page fault trace event!
+	 */
+	vmalloc_sync_mappings();
+
 	return 0;
 }
 
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 06d7feb5255f..9de29bb45a27 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -95,24 +95,20 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event)
 	struct xbc_node *anode;
 	char buf[MAX_BUF_LEN];
 	const char *val;
-	int ret;
+	int ret = 0;
 
-	kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
+	xbc_node_for_each_array_value(node, "probes", anode, val) {
+		kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN);
 
-	ret = kprobe_event_gen_cmd_start(&cmd, event, NULL);
-	if (ret)
-		return ret;
+		ret = kprobe_event_gen_cmd_start(&cmd, event, val);
+		if (ret)
+			break;
 
-	xbc_node_for_each_array_value(node, "probes", anode, val) {
-		ret = kprobe_event_add_field(&cmd, val);
+		ret = kprobe_event_gen_cmd_end(&cmd);
 		if (ret)
-			return ret;
+			pr_err("Failed to add probe: %s\n", buf);
 	}
 
-	ret = kprobe_event_gen_cmd_end(&cmd);
-	if (ret)
-		pr_err("Failed to add probe: %s\n", buf);
-
 	return ret;
 }
 #else
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 5f6834a2bf41..fcab11cc6833 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3320,6 +3320,9 @@ static void __destroy_hist_field(struct hist_field *hist_field)
 	kfree(hist_field->name);
 	kfree(hist_field->type);
 
+	kfree(hist_field->system);
+	kfree(hist_field->event_name);
+
 	kfree(hist_field);
 }
 
@@ -4382,6 +4385,7 @@ static struct hist_field *create_var(struct hist_trigger_data *hist_data,
 		goto out;
 	}
 
+	var->ref = 1;
 	var->flags = HIST_FIELD_FL_VAR;
 	var->var.idx = idx;
 	var->var.hist_data = var->hist_data = hist_data;
@@ -5011,6 +5015,9 @@ static void destroy_field_vars(struct hist_trigger_data *hist_data)
 
 	for (i = 0; i < hist_data->n_field_vars; i++)
 		destroy_field_var(hist_data->field_vars[i]);
+
+	for (i = 0; i < hist_data->n_save_vars; i++)
+		destroy_field_var(hist_data->save_vars[i]);
 }
 
 static void save_field_var(struct hist_trigger_data *hist_data,
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index d0568af4a0ef..35989383ae11 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -453,7 +453,7 @@ static bool __within_notrace_func(unsigned long addr)
 
 static bool within_notrace_func(struct trace_kprobe *tk)
 {
-	unsigned long addr = addr = trace_kprobe_address(tk);
+	unsigned long addr = trace_kprobe_address(tk);
 	char symname[KSYM_NAME_LEN], *p;
 
 	if (!__within_notrace_func(addr))
@@ -940,6 +940,9 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init);
  * complete command or only the first part of it; in the latter case,
  * kprobe_event_add_fields() can be used to add more fields following this.
  *
+ * Unlikely the synth_event_gen_cmd_start(), @loc must be specified. This
+ * returns -EINVAL if @loc == NULL.
+ *
  * Return: 0 if successful, error otherwise.
  */
 int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe,
@@ -953,6 +956,9 @@ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe,
 	if (cmd->type != DYNEVENT_TYPE_KPROBE)
 		return -EINVAL;
 
+	if (!loc)
+		return -EINVAL;
+
 	if (kretprobe)
 		snprintf(buf, MAX_EVENT_NAME_LEN, "r:kprobes/%s", name);
 	else
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 9e31bfc818ff..74738c9856f1 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -283,7 +283,7 @@ int tracing_map_add_key_field(struct tracing_map *map,
 	return idx;
 }
 
-void tracing_map_array_clear(struct tracing_map_array *a)
+static void tracing_map_array_clear(struct tracing_map_array *a)
 {
 	unsigned int i;
 
@@ -294,7 +294,7 @@ void tracing_map_array_clear(struct tracing_map_array *a)
 		memset(a->pages[i], 0, PAGE_SIZE);
 }
 
-void tracing_map_array_free(struct tracing_map_array *a)
+static void tracing_map_array_free(struct tracing_map_array *a)
 {
 	unsigned int i;
 
@@ -316,7 +316,7 @@ void tracing_map_array_free(struct tracing_map_array *a)
 	kfree(a);
 }
 
-struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
+static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
 						  unsigned int entry_size)
 {
 	struct tracing_map_array *a;
diff --git a/kernel/umh.c b/kernel/umh.c
index 7f255b5a8845..11bf5eea474c 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -544,6 +544,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob);
  * Runs a user-space application.  The application is started
  * asynchronously if wait is not set, and runs as a child of system workqueues.
  * (ie. it runs with full root capabilities and optimized affinity).
+ *
+ * Note: successful return value does not guarantee the helper was called at
+ * all. You can't rely on sub_info->{init,cleanup} being called even for
+ * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers
+ * into a successful no-op.
  */
 int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 {