Merge "Merge android11-5.4.233+ (4716ccc) into msm-5.4"

kernel/acct.c

@@ -331,6 +331,8 @@ static comp_t encode_comp_t(unsigned long value)
 		exp++;
 	}
 
+	if (exp > (((comp_t) ~0U) >> MANTSIZE))
+		return (comp_t) ~0U;
 	/*
 	 * Clean it up and polish it off.
 	 */

kernel/bpf/btf.c

@@ -2849,6 +2849,11 @@ static int btf_func_proto_check(struct btf_verifier_env *env,
 			break;
 		}
 
+		if (btf_type_is_resolve_source_only(arg_type)) {
+			btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1);
+			return -EINVAL;
+		}
+
 		if (args[i].name_off &&
 		    (!btf_name_offset_valid(btf, args[i].name_off) ||
 		     !btf_name_valid_identifier(btf, args[i].name_off))) {

kernel/bpf/core.c

@@ -30,6 +30,7 @@
 #include <linux/kallsyms.h>
 #include <linux/rcupdate.h>
 #include <linux/perf_event.h>
+#include <linux/nospec.h>
 
 #include <asm/barrier.h>
 #include <asm/unaligned.h>
@@ -1576,9 +1577,7 @@ out:
 		 * reuse preexisting logic from Spectre v1 mitigation that
 		 * happens to produce the required code on x86 for v4 as well.
 		 */
-#ifdef CONFIG_X86
 		barrier_nospec();
-#endif
 		CONT;
 #define LDST(SIZEOP, SIZE)						\
 	STX_MEM_##SIZEOP:						\

kernel/bpf/verifier.c

@@ -1924,7 +1924,9 @@ static int check_stack_write(struct bpf_verifier_env *env,
 		bool sanitize = reg && is_spillable_regtype(reg->type);
 
 		for (i = 0; i < size; i++) {
-			if (state->stack[spi].slot_type[i] == STACK_INVALID) {
+			u8 type = state->stack[spi].slot_type[i];
+
+			if (type != STACK_MISC && type != STACK_ZERO) {
 				sanitize = true;
 				break;
 			}
@@ -5140,6 +5142,11 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 				return err;
 			return adjust_ptr_min_max_vals(env, insn,
 						       dst_reg, src_reg);
+		} else if (dst_reg->precise) {
+			/* if dst_reg is precise, src_reg should be precise as well */
+			err = mark_chain_precision(env, insn->src_reg);
+			if (err)
+				return err;
 		}
 	} else {
 		/* Pretend the src is a reg with a known value, since we only

kernel/cgroup/cgroup-internal.h

@@ -169,7 +169,6 @@ extern struct mutex cgroup_mutex;
 extern spinlock_t css_set_lock;
 extern struct cgroup_subsys *cgroup_subsys[];
 extern struct list_head cgroup_roots;
-extern struct file_system_type cgroup_fs_type;
 
 /* iterate across the hierarchies */
 #define for_each_root(root)						\

kernel/events/core.c

@@ -10119,13 +10119,15 @@ static int pmu_dev_alloc(struct pmu *pmu)
 
 	pmu->dev->groups = pmu->attr_groups;
 	device_initialize(pmu->dev);
-	ret = dev_set_name(pmu->dev, "%s", pmu->name);
-	if (ret)
-		goto free_dev;
 
 	dev_set_drvdata(pmu->dev, pmu);
 	pmu->dev->bus = &pmu_bus;
 	pmu->dev->release = pmu_dev_release;
+
+	ret = dev_set_name(pmu->dev, "%s", pmu->name);
+	if (ret)
+		goto free_dev;
+
 	ret = device_add(pmu->dev);
 	if (ret)
 		goto free_dev;

kernel/exit.c

@@ -63,12 +63,59 @@
 #include <linux/random.h>
 #include <linux/rcuwait.h>
 #include <linux/compat.h>
+#include <linux/sysfs.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 
+/*
+ * The default value should be high enough to not crash a system that randomly
+ * crashes its kernel from time to time, but low enough to at least not permit
+ * overflowing 32-bit refcounts or the ldsem writer count.
+ */
+static unsigned int oops_limit = 10000;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table kern_exit_table[] = {
+	{
+		.procname       = "oops_limit",
+		.data           = &oops_limit,
+		.maxlen         = sizeof(oops_limit),
+		.mode           = 0644,
+		.proc_handler   = proc_douintvec,
+	},
+	{ }
+};
+
+static __init int kernel_exit_sysctls_init(void)
+{
+	register_sysctl_init("kernel", kern_exit_table);
+	return 0;
+}
+late_initcall(kernel_exit_sysctls_init);
+#endif
+
+static atomic_t oops_count = ATOMIC_INIT(0);
+
+#ifdef CONFIG_SYSFS
+static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr,
+			       char *page)
+{
+	return sysfs_emit(page, "%d\n", atomic_read(&oops_count));
+}
+
+static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count);
+
+static __init int kernel_exit_sysfs_init(void)
+{
+	sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL);
+	return 0;
+}
+late_initcall(kernel_exit_sysfs_init);
+#endif
+
 static void __unhash_process(struct task_struct *p, bool group_dead)
 {
 	nr_threads--;
@@ -864,6 +911,31 @@ void __noreturn do_exit(long code)
 }
 EXPORT_SYMBOL_GPL(do_exit);
 
+void __noreturn make_task_dead(int signr)
+{
+	/*
+	 * Take the task off the cpu after something catastrophic has
+	 * happened.
+	 */
+	unsigned int limit;
+
+	/*
+	 * Every time the system oopses, if the oops happens while a reference
+	 * to an object was held, the reference leaks.
+	 * If the oops doesn't also leak memory, repeated oopsing can cause
+	 * reference counters to wrap around (if they're not using refcount_t).
+	 * This means that repeated oopsing can make unexploitable-looking bugs
+	 * exploitable through repeated oopsing.
+	 * To make sure this can't happen, place an upper bound on how often the
+	 * kernel may oops without panic().
+	 */
+	limit = READ_ONCE(oops_limit);
+	if (atomic_inc_return(&oops_count) >= limit && limit)
+		panic("Oopsed too often (kernel.oops_limit is %d)", limit);
+
+	do_exit(signr);
+}
+
 void complete_and_exit(struct completion *comp, long code)
 {
 	if (comp)

kernel/gcov/gcc_4_7.c

@@ -85,6 +85,7 @@ struct gcov_fn_info {
  * @version: gcov version magic indicating the gcc version used for compilation
  * @next: list head for a singly-linked list
  * @stamp: uniquifying time stamp
+ * @checksum: unique object checksum
  * @filename: name of the associated gcov data file
  * @merge: merge functions (null for unused counter type)
  * @n_functions: number of instrumented functions
@@ -97,6 +98,10 @@ struct gcov_info {
 	unsigned int version;
 	struct gcov_info *next;
 	unsigned int stamp;
+ /* Since GCC 12.1 a checksum field is added. */
+#if (__GNUC__ >= 12)
+	unsigned int checksum;
+#endif
 	const char *filename;
 	void (*merge[GCOV_COUNTERS])(gcov_type *, unsigned int);
 	unsigned int n_functions;

kernel/irq/internals.h

@@ -52,6 +52,7 @@ enum {
  * IRQS_PENDING			- irq is pending and replayed later
  * IRQS_SUSPENDED		- irq is suspended
  * IRQS_NMI			- irq line is used to deliver NMIs
+ * IRQS_SYSFS			- descriptor has been added to sysfs
  */
 enum {
 	IRQS_AUTODETECT		= 0x00000001,
@@ -64,6 +65,7 @@ enum {
 	IRQS_SUSPENDED		= 0x00000800,
 	IRQS_TIMINGS		= 0x00001000,
 	IRQS_NMI		= 0x00002000,
+	IRQS_SYSFS		= 0x00004000,
 };
 
 #include "debug.h"

kernel/irq/irqdesc.c

@@ -288,22 +288,25 @@ static void irq_sysfs_add(int irq, struct irq_desc *desc)
 	if (irq_kobj_base) {
 		/*
 		 * Continue even in case of failure as this is nothing
-		 * crucial.
+		 * crucial and failures in the late irq_sysfs_init()
+		 * cannot be rolled back.
 		 */
 		if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq))
 			pr_warn("Failed to add kobject for irq %d\n", irq);
+		else
+			desc->istate |= IRQS_SYSFS;
 	}
 }
 
 static void irq_sysfs_del(struct irq_desc *desc)
 {
 	/*
-	 * If irq_sysfs_init() has not yet been invoked (early boot), then
-	 * irq_kobj_base is NULL and the descriptor was never added.
-	 * kobject_del() complains about a object with no parent, so make
-	 * it conditional.
+	 * Only invoke kobject_del() when kobject_add() was successfully
+	 * invoked for the descriptor. This covers both early boot, where
+	 * sysfs is not initialized yet, and the case of a failed
+	 * kobject_add() invocation.
 	 */
-	if (irq_kobj_base)
+	if (desc->istate & IRQS_SYSFS)
 		kobject_del(&desc->kobj);
 }
 

kernel/module.c

@@ -3666,7 +3666,8 @@ static bool finished_loading(const char *name)
 	sched_annotate_sleep();
 	mutex_lock(&module_mutex);
 	mod = find_module_all(name, strlen(name), true);
-	ret = !mod || mod->state == MODULE_STATE_LIVE;
+	ret = !mod || mod->state == MODULE_STATE_LIVE
+		|| mod->state == MODULE_STATE_GOING;
 	mutex_unlock(&module_mutex);
 
 	return ret;
@@ -3832,20 +3833,35 @@ static int add_unformed_module(struct module *mod)
 
 	mod->state = MODULE_STATE_UNFORMED;
 
-again:
 	mutex_lock(&module_mutex);
 	old = find_module_all(mod->name, strlen(mod->name), true);
 	if (old != NULL) {
-		if (old->state != MODULE_STATE_LIVE) {
+		if (old->state == MODULE_STATE_COMING
+		    || old->state == MODULE_STATE_UNFORMED) {
 			/* Wait in case it fails to load. */
 			mutex_unlock(&module_mutex);
 			err = wait_event_interruptible(module_wq,
 					       finished_loading(mod->name));
 			if (err)
 				goto out_unlocked;
-			goto again;
+
+			/* The module might have gone in the meantime. */
+			mutex_lock(&module_mutex);
+			old = find_module_all(mod->name, strlen(mod->name),
+					      true);
 		}
-		err = -EEXIST;
+
+		/*
+		 * We are here only when the same module was being loaded. Do
+		 * not try to load it again right now. It prevents long delays
+		 * caused by serialized module load failures. It might happen
+		 * when more devices of the same type trigger load of
+		 * a particular module.
+		 */
+		if (old && old->state == MODULE_STATE_LIVE)
+			err = -EEXIST;
+		else
+			err = -EBUSY;
 		goto out;
 	}
 	mod_update_bounds(mod);

kernel/panic.c

@@ -31,6 +31,7 @@
 #include <linux/bug.h>
 #include <linux/ratelimit.h>
 #include <linux/debugfs.h>
+#include <linux/sysfs.h>
 #include <asm/sections.h>
 
 #define PANIC_TIMER_STEP 100
@@ -44,6 +45,7 @@ static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
 bool crash_kexec_post_notifiers;
 int panic_on_warn __read_mostly;
+static unsigned int warn_limit __read_mostly;
 
 int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
@@ -60,6 +62,45 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
 
 EXPORT_SYMBOL(panic_notifier_list);
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table kern_panic_table[] = {
+	{
+		.procname       = "warn_limit",
+		.data           = &warn_limit,
+		.maxlen         = sizeof(warn_limit),
+		.mode           = 0644,
+		.proc_handler   = proc_douintvec,
+	},
+	{ }
+};
+
+static __init int kernel_panic_sysctls_init(void)
+{
+	register_sysctl_init("kernel", kern_panic_table);
+	return 0;
+}
+late_initcall(kernel_panic_sysctls_init);
+#endif
+
+static atomic_t warn_count = ATOMIC_INIT(0);
+
+#ifdef CONFIG_SYSFS
+static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr,
+			       char *page)
+{
+	return sysfs_emit(page, "%d\n", atomic_read(&warn_count));
+}
+
+static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count);
+
+static __init int kernel_panic_sysfs_init(void)
+{
+	sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL);
+	return 0;
+}
+late_initcall(kernel_panic_sysfs_init);
+#endif
+
 static long no_blink(int state)
 {
 	return 0;
@@ -156,6 +197,19 @@ static void panic_print_sys_info(void)
 		ftrace_dump(DUMP_ALL);
 }
 
+void check_panic_on_warn(const char *origin)
+{
+	unsigned int limit;
+
+	if (panic_on_warn)
+		panic("%s: panic_on_warn set ...\n", origin);
+
+	limit = READ_ONCE(warn_limit);
+	if (atomic_inc_return(&warn_count) >= limit && limit)
+		panic("%s: system warned too often (kernel.warn_limit is %d)",
+		      origin, limit);
+}
+
 /**
  *	panic - halt the system
  *	@fmt: The text string to print
@@ -173,6 +227,16 @@ void panic(const char *fmt, ...)
 	int old_cpu, this_cpu;
 	bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers;
 
+	if (panic_on_warn) {
+		/*
+		 * This thread may hit another WARN() in the panic path.
+		 * Resetting this prevents additional WARN() from panicking the
+		 * system on this thread.  Other threads are blocked by the
+		 * panic_mutex in panic().
+		 */
+		panic_on_warn = 0;
+	}
+
 	/*
 	 * Disable local interrupts. This will prevent panic_smp_self_stop
 	 * from deadlocking the first cpu that invokes the panic, since
@@ -571,16 +635,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 	if (args)
 		vprintk(args->fmt, args->args);
 
-	if (panic_on_warn) {
-		/*
-		 * This thread may hit another WARN() in the panic path.
-		 * Resetting this prevents additional WARN() from panicking the
-		 * system on this thread.  Other threads are blocked by the
-		 * panic_mutex in panic().
-		 */
-		panic_on_warn = 0;
-		panic("panic_on_warn set ...\n");
-	}
+	check_panic_on_warn("kernel");
 
 	print_modules();
 

kernel/power/snapshot.c

@@ -1680,8 +1680,8 @@ static unsigned long minimum_image_size(unsigned long saveable)
  * /sys/power/reserved_size, respectively).  To make this happen, we compute the
  * total number of available page frames and allocate at least
  *
- * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2
- *  + 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE)
+ * ([page frames total] - PAGES_FOR_IO - [metadata pages]) / 2
+ *  - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE)
  *
  * of them, which corresponds to the maximum size of a hibernation image.
  *

kernel/rcu/tree.c

@@ -2319,7 +2319,7 @@ void rcu_force_quiescent_state(void)
 	struct rcu_node *rnp_old = NULL;
 
 	/* Funnel through hierarchy to reduce memory contention. */
-	rnp = __this_cpu_read(rcu_data.mynode);
+	rnp = raw_cpu_read(rcu_data.mynode);
 	for (; rnp != NULL; rnp = rnp->parent) {
 		ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) ||
 		      !raw_spin_trylock(&rnp->fqslock);

kernel/relay.c

@@ -163,13 +163,13 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan)
 {
 	struct rchan_buf *buf;
 
-	if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *))
+	if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t))
 		return NULL;
 
 	buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL);
 	if (!buf)
 		return NULL;
-	buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t *),
+	buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t),
 				     GFP_KERNEL);
 	if (!buf->padding)
 		goto free_buf;

kernel/sched/core.c

@@ -4148,8 +4148,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
 		print_ip_sym(preempt_disable_ip);
 		pr_cont("\n");
 	}
-	if (panic_on_warn)
-		panic("scheduling while atomic\n");
+	check_panic_on_warn("scheduling while atomic");
 
 #ifdef CONFIG_PANIC_ON_SCHED_BUG
 	BUG();

kernel/sched/psi.c

@@ -1137,10 +1137,11 @@ void psi_trigger_destroy(struct psi_trigger *t)
 
 	group = t->group;
 	/*
-	 * Wakeup waiters to stop polling. Can happen if cgroup is deleted
-	 * from under a polling process.
+	 * Wakeup waiters to stop polling and clear the queue to prevent it from
+	 * being accessed later. Can happen if cgroup is deleted from under a
+	 * polling process.
 	 */
-	wake_up_interruptible(&t->event_wait);
+	wake_up_pollfree(&t->event_wait);
 
 	mutex_lock(&group->trigger_lock);
 

kernel/sys.c

@@ -1538,6 +1538,8 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource,
 
 	if (resource >= RLIM_NLIMITS)
 		return -EINVAL;
+	resource = array_index_nospec(resource, RLIM_NLIMITS);
+
 	if (new_rlim) {
 		if (new_rlim->rlim_cur > new_rlim->rlim_max)
 			return -EINVAL;

kernel/time/alarmtimer.c

@@ -479,11 +479,35 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval)
 }
 EXPORT_SYMBOL_GPL(alarm_forward);
 
-u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
+	ktime_t now = base->gettime();
 
-	return alarm_forward(alarm, base->gettime(), interval);
+	if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) {
+		/*
+		 * Same issue as with posix_timer_fn(). Timers which are
+		 * periodic but the signal is ignored can starve the system
+		 * with a very small interval. The real fix which was
+		 * promised in the context of posix_timer_fn() never
+		 * materialized, but someone should really work on it.
+		 *
+		 * To prevent DOS fake @now to be 1 jiffie out which keeps
+		 * the overrun accounting correct but creates an
+		 * inconsistency vs. timer_gettime(2).
+		 */
+		ktime_t kj = NSEC_PER_SEC / HZ;
+
+		if (interval < kj)
+			now = ktime_add(now, kj);
+	}
+
+	return alarm_forward(alarm, now, interval);
+}
+
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+	return __alarm_forward_now(alarm, interval, false);
 }
 EXPORT_SYMBOL_GPL(alarm_forward_now);
 
@@ -557,9 +581,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm,
 	if (posix_timer_event(ptr, si_private) && ptr->it_interval) {
 		/*
 		 * Handle ignored signals and rearm the timer. This will go
-		 * away once we handle ignored signals proper.
+		 * away once we handle ignored signals proper. Ensure that
+		 * small intervals cannot starve the system.
 		 */
-		ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval);
+		ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true);
 		++ptr->it_requeue_pending;
 		ptr->it_active = 1;
 		result = ALARMTIMER_RESTART;

kernel/trace/blktrace.c

@@ -1589,7 +1589,8 @@ blk_trace_event_print_binary(struct trace_iterator *iter, int flags,
 
 static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter)
 {
-	if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC))
+	if ((iter->ent->type != TRACE_BLK) ||
+	    !(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC))
 		return TRACE_TYPE_UNHANDLED;
 
 	return print_one_line(iter, true);

kernel/trace/bpf_trace.c

@@ -649,6 +649,9 @@ BPF_CALL_1(bpf_send_signal, u32, sig)
 		return -EPERM;
 	if (unlikely(!nmi_uaccess_okay()))
 		return -EPERM;
+	/* Task should not be pid=1 to avoid kernel panic. */
+	if (unlikely(is_global_init(current)))
+		return -EPERM;
 
 	if (irqs_disabled()) {
 		/* Do an early check on signal validity. Otherwise,

kernel/trace/trace.c

@@ -6123,7 +6123,20 @@ waitagain:
 
 		ret = print_trace_line(iter);
 		if (ret == TRACE_TYPE_PARTIAL_LINE) {
-			/* don't print partial lines */
+			/*
+			 * If one print_trace_line() fills entire trace_seq in one shot,
+			 * trace_seq_to_user() will returns -EBUSY because save_len == 0,
+			 * In this case, we need to consume it, otherwise, loop will peek
+			 * this event next time, resulting in an infinite loop.
+			 */
+			if (save_len == 0) {
+				iter->seq.full = 0;
+				trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n");
+				trace_consume(iter);
+				break;
+			}
+
+			/* In other cases, don't print partial lines */
 			iter->seq.seq.len = save_len;
 			break;
 		}
@@ -8310,9 +8323,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf,
 	if (val > 100)
 		return -EINVAL;
 
-	if (!val)
-		val = 1;
-
 	tr->buffer_percent = val;
 
 	(*ppos)++;
@@ -9398,6 +9408,8 @@ void __init early_trace_init(void)
 			static_key_enable(&tracepoint_printk_key.key);
 	}
 	tracer_alloc_buffers();
+
+	init_events();
 }
 
 void __init trace_init(void)

kernel/trace/trace.h

@@ -1613,6 +1613,7 @@ extern void trace_event_enable_cmd_record(bool enable);
 extern void trace_event_enable_tgid_record(bool enable);
 
 extern int event_trace_init(void);
+extern int init_events(void);
 extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
 extern int event_trace_del_tracer(struct trace_array *tr);
 

kernel/trace/trace_events_hist.c

@@ -481,7 +481,7 @@ struct action_data {
 	 * event param, and is passed to the synthetic event
 	 * invocation.
 	 */
-	unsigned int		var_ref_idx[TRACING_MAP_VARS_MAX];
+	unsigned int		var_ref_idx[SYNTH_FIELDS_MAX];
 	struct synth_event	*synth_event;
 	bool			use_trace_keyword;
 	char			*synth_event_name;
@@ -2564,6 +2564,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data,
 		unsigned long fl = flags & ~HIST_FIELD_FL_LOG2;
 		hist_field->fn = hist_field_log2;
 		hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL);
+		if (!hist_field->operands[0])
+			goto free;
 		hist_field->size = hist_field->operands[0]->size;
 		hist_field->type = kstrdup(hist_field->operands[0]->type, GFP_KERNEL);
 		if (!hist_field->type)
@@ -2764,7 +2766,9 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data,
 			return ref_field;
 		}
 	}
-
+	/* Sanity check to avoid out-of-bound write on 'hist_data->var_refs' */
+	if (hist_data->n_var_refs >= TRACING_MAP_VARS_MAX)
+		return NULL;
 	ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL);
 	if (ref_field) {
 		if (init_var_ref(ref_field, var_field, system, event_name)) {
@@ -4026,6 +4030,7 @@ static int parse_action_params(struct trace_array *tr, char *params,
 	while (params) {
 		if (data->n_params >= SYNTH_FIELDS_MAX) {
 			hist_err(tr, HIST_ERR_TOO_MANY_PARAMS, 0);
+			ret = -EINVAL;
 			goto out;
 		}
 
@@ -4350,6 +4355,10 @@ static int trace_action_create(struct hist_trigger_data *hist_data,
 
 	lockdep_assert_held(&event_mutex);
 
+	/* Sanity check to avoid out-of-bound write on 'data->var_ref_idx' */
+	if (data->n_params > SYNTH_FIELDS_MAX)
+		return -EINVAL;
+
 	if (data->use_trace_keyword)
 		synth_event_name = data->synth_event_name;
 	else
@@ -6445,7 +6454,7 @@ enable:
 	/* Just return zero, not the number of registered triggers */
 	ret = 0;
  out:
-	if (ret == 0)
+	if (ret == 0 && glob[0])
 		hist_err_clear();
 
 	return ret;

kernel/trace/trace_output.c

@@ -1366,7 +1366,7 @@ static struct trace_event *events[] __initdata = {
 	NULL
 };
 
-__init static int init_events(void)
+__init int init_events(void)
 {
 	struct trace_event *event;
 	int i, ret;
@@ -1384,4 +1384,3 @@ __init static int init_events(void)
 
 	return 0;
 }
-early_initcall(init_events);