Merge tag 'v5.0.17' into toradex_5.0.y

This is the 5.0.17 stable release

22 files changed, 356 insertions, 184 deletions

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8974b3755670..3c18260403dd 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -162,10 +162,14 @@ static void cpu_map_kthread_stop(struct work_struct *work)
 static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 					 struct xdp_frame *xdpf)
 {
+	unsigned int hard_start_headroom;
 	unsigned int frame_size;
 	void *pkt_data_start;
 	struct sk_buff *skb;
 
+	/* Part of headroom was reserved to xdpf */
+	hard_start_headroom = sizeof(struct xdp_frame) +  xdpf->headroom;
+
 	/* build_skb need to place skb_shared_info after SKB end, and
 	 * also want to know the memory "truesize".  Thus, need to
 	 * know the memory frame size backing xdp_buff.
@@ -183,15 +187,15 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 	 * is not at a fixed memory location, with mixed length
 	 * packets, which is bad for cache-line hotness.
 	 */
-	frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) +
+	frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
-	pkt_data_start = xdpf->data - xdpf->headroom;
+	pkt_data_start = xdpf->data - hard_start_headroom;
 	skb = build_skb(pkt_data_start, frame_size);
 	if (!skb)
 		return NULL;
 
-	skb_reserve(skb, xdpf->headroom);
+	skb_reserve(skb, hard_start_headroom);
 	__skb_put(skb, xdpf->len);
 	if (xdpf->metasize)
 		skb_metadata_set(skb, xdpf->metasize);
@@ -205,6 +209,9 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 	 * - RX ring dev queue index	(skb_record_rx_queue)
 	 */
 
+	/* Allow SKB to reuse area used by xdp_frame */
+	xdp_scrub_frame(xdpf);
+
 	return skb;
 }
 
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 2ada5e21dfa6..4a8f390a2b82 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -554,19 +554,6 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ
 }
 EXPORT_SYMBOL(bpf_prog_get_type_path);
 
-static void bpf_evict_inode(struct inode *inode)
-{
-	enum bpf_type type;
-
-	truncate_inode_pages_final(&inode->i_data);
-	clear_inode(inode);
-
-	if (S_ISLNK(inode->i_mode))
-		kfree(inode->i_link);
-	if (!bpf_inode_type(inode, &type))
-		bpf_any_put(inode->i_private, type);
-}
-
 /*
  * Display the mount options in /proc/mounts.
  */
@@ -579,11 +566,28 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+static void bpf_destroy_inode_deferred(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	enum bpf_type type;
+
+	if (S_ISLNK(inode->i_mode))
+		kfree(inode->i_link);
+	if (!bpf_inode_type(inode, &type))
+		bpf_any_put(inode->i_private, type);
+	free_inode_nonrcu(inode);
+}
+
+static void bpf_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, bpf_destroy_inode_deferred);
+}
+
 static const struct super_operations bpf_super_ops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= generic_delete_inode,
 	.show_options	= bpf_show_options,
-	.evict_inode	= bpf_evict_inode,
+	.destroy_inode	= bpf_destroy_inode,
 };
 
 enum {
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6754f3ecfd94..43e741e88691 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2304,3 +2304,18 @@ void __init boot_cpu_hotplug_init(void)
 #endif
 	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
 }
+
+enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
+
+static int __init mitigations_parse_cmdline(char *arg)
+{
+	if (!strcmp(arg, "off"))
+		cpu_mitigations = CPU_MITIGATIONS_OFF;
+	else if (!strcmp(arg, "auto"))
+		cpu_mitigations = CPU_MITIGATIONS_AUTO;
+	else if (!strcmp(arg, "auto,nosmt"))
+		cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT;
+
+	return 0;
+}
+early_param("mitigations", mitigations_parse_cmdline);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 26d6edab051a..124e1e3d06b9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2007,8 +2007,8 @@ event_sched_out(struct perf_event *event,
 	event->pmu->del(event, 0);
 	event->oncpu = -1;
 
-	if (event->pending_disable) {
-		event->pending_disable = 0;
+	if (READ_ONCE(event->pending_disable) >= 0) {
+		WRITE_ONCE(event->pending_disable, -1);
 		state = PERF_EVENT_STATE_OFF;
 	}
 	perf_event_set_state(event, state);
@@ -2196,7 +2196,8 @@ EXPORT_SYMBOL_GPL(perf_event_disable);
 
 void perf_event_disable_inatomic(struct perf_event *event)
 {
-	event->pending_disable = 1;
+	WRITE_ONCE(event->pending_disable, smp_processor_id());
+	/* can fail, see perf_pending_event_disable() */
 	irq_work_queue(&event->pending);
 }
 
@@ -5803,10 +5804,45 @@ void perf_event_wakeup(struct perf_event *event)
 	}
 }
 
+static void perf_pending_event_disable(struct perf_event *event)
+{
+	int cpu = READ_ONCE(event->pending_disable);
+
+	if (cpu < 0)
+		return;
+
+	if (cpu == smp_processor_id()) {
+		WRITE_ONCE(event->pending_disable, -1);
+		perf_event_disable_local(event);
+		return;
+	}
+
+	/*
+	 *  CPU-A			CPU-B
+	 *
+	 *  perf_event_disable_inatomic()
+	 *    @pending_disable = CPU-A;
+	 *    irq_work_queue();
+	 *
+	 *  sched-out
+	 *    @pending_disable = -1;
+	 *
+	 *				sched-in
+	 *				perf_event_disable_inatomic()
+	 *				  @pending_disable = CPU-B;
+	 *				  irq_work_queue(); // FAILS
+	 *
+	 *  irq_work_run()
+	 *    perf_pending_event()
+	 *
+	 * But the event runs on CPU-B and wants disabling there.
+	 */
+	irq_work_queue_on(&event->pending, cpu);
+}
+
 static void perf_pending_event(struct irq_work *entry)
 {
-	struct perf_event *event = container_of(entry,
-			struct perf_event, pending);
+	struct perf_event *event = container_of(entry, struct perf_event, pending);
 	int rctx;
 
 	rctx = perf_swevent_get_recursion_context();
@@ -5815,10 +5851,7 @@ static void perf_pending_event(struct irq_work *entry)
 	 * and we won't recurse 'further'.
 	 */
 
-	if (event->pending_disable) {
-		event->pending_disable = 0;
-		perf_event_disable_local(event);
-	}
+	perf_pending_event_disable(event);
 
 	if (event->pending_wakeup) {
 		event->pending_wakeup = 0;
@@ -7178,6 +7211,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
 	int size = mmap_event->event_id.header.size;
+	u32 type = mmap_event->event_id.header.type;
 	int ret;
 
 	if (!perf_event_mmap_match(event, data))
@@ -7221,6 +7255,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 	perf_output_end(&handle);
 out:
 	mmap_event->event_id.header.size = size;
+	mmap_event->event_id.header.type = type;
 }
 
 static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
@@ -9996,6 +10031,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 
 	init_waitqueue_head(&event->waitq);
+	event->pending_disable = -1;
 	init_irq_work(&event->pending, perf_pending_event);
 
 	mutex_init(&event->mmap_mutex);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 878c62ec0190..a5fc56a654fd 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -393,7 +393,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 		 * store that will be enabled on successful return
 		 */
 		if (!handle->size) { /* A, matches D */
-			event->pending_disable = 1;
+			event->pending_disable = smp_processor_id();
 			perf_output_wakeup(handle);
 			local_set(&rb->aux_nest, 0);
 			goto err_put;
@@ -456,24 +456,21 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 		rb->aux_head += size;
 	}
 
-	if (size || handle->aux_flags) {
-		/*
-		 * Only send RECORD_AUX if we have something useful to communicate
-		 *
-		 * Note: the OVERWRITE records by themselves are not considered
-		 * useful, as they don't communicate any *new* information,
-		 * aside from the short-lived offset, that becomes history at
-		 * the next event sched-in and therefore isn't useful.
-		 * The userspace that needs to copy out AUX data in overwrite
-		 * mode should know to use user_page::aux_head for the actual
-		 * offset. So, from now on we don't output AUX records that
-		 * have *only* OVERWRITE flag set.
-		 */
-
-		if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
-			perf_event_aux_event(handle->event, aux_head, size,
-			                     handle->aux_flags);
-	}
+	/*
+	 * Only send RECORD_AUX if we have something useful to communicate
+	 *
+	 * Note: the OVERWRITE records by themselves are not considered
+	 * useful, as they don't communicate any *new* information,
+	 * aside from the short-lived offset, that becomes history at
+	 * the next event sched-in and therefore isn't useful.
+	 * The userspace that needs to copy out AUX data in overwrite
+	 * mode should know to use user_page::aux_head for the actual
+	 * offset. So, from now on we don't output AUX records that
+	 * have *only* OVERWRITE flag set.
+	 */
+	if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE))
+		perf_event_aux_event(handle->event, aux_head, size,
+				     handle->aux_flags);
 
 	rb->user_page->aux_head = rb->aux_head;
 	if (rb_need_aux_wakeup(rb))
@@ -481,7 +478,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 
 	if (wakeup) {
 		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
-			handle->event->pending_disable = 1;
+			handle->event->pending_disable = smp_processor_id();
 		perf_output_wakeup(handle);
 	}
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 52668d44e07b..4eafa8ec76a4 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1314,13 +1314,15 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
 
 static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
 {
+	int err;
 	u32 uninitialized_var(curval);
 
 	if (unlikely(should_fail_futex(true)))
 		return -EFAULT;
 
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
-		return -EFAULT;
+	err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+	if (unlikely(err))
+		return err;
 
 	/* If user space value changed, let the caller retry */
 	return curval != uval ? -EAGAIN : 0;
@@ -1506,10 +1508,8 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 	if (unlikely(should_fail_futex(true)))
 		ret = -EFAULT;
 
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
-		ret = -EFAULT;
-
-	} else if (curval != uval) {
+	ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+	if (!ret && (curval != uval)) {
 		/*
 		 * If a unconditional UNLOCK_PI operation (user space did not
 		 * try the TID->0 transition) raced with a waiter setting the
@@ -1704,32 +1704,32 @@ retry_private:
 	double_lock_hb(hb1, hb2);
 	op_ret = futex_atomic_op_inuser(op, uaddr2);
 	if (unlikely(op_ret < 0)) {
-
 		double_unlock_hb(hb1, hb2);
 
-#ifndef CONFIG_MMU
-		/*
-		 * we don't get EFAULT from MMU faults if we don't have an MMU,
-		 * but we might get them from range checking
-		 */
-		ret = op_ret;
-		goto out_put_keys;
-#endif
-
-		if (unlikely(op_ret != -EFAULT)) {
+		if (!IS_ENABLED(CONFIG_MMU) ||
+		    unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) {
+			/*
+			 * we don't get EFAULT from MMU faults if we don't have
+			 * an MMU, but we might get them from range checking
+			 */
 			ret = op_ret;
 			goto out_put_keys;
 		}
 
-		ret = fault_in_user_writeable(uaddr2);
-		if (ret)
-			goto out_put_keys;
+		if (op_ret == -EFAULT) {
+			ret = fault_in_user_writeable(uaddr2);
+			if (ret)
+				goto out_put_keys;
+		}
 
-		if (!(flags & FLAGS_SHARED))
+		if (!(flags & FLAGS_SHARED)) {
+			cond_resched();
 			goto retry_private;
+		}
 
 		put_futex_key(&key2);
 		put_futex_key(&key1);
+		cond_resched();
 		goto retry;
 	}
 
@@ -2354,7 +2354,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	u32 uval, uninitialized_var(curval), newval;
 	struct task_struct *oldowner, *newowner;
 	u32 newtid;
-	int ret;
+	int ret, err = 0;
 
 	lockdep_assert_held(q->lock_ptr);
 
@@ -2425,14 +2425,17 @@ retry:
 	if (!pi_state->owner)
 		newtid |= FUTEX_OWNER_DIED;
 
-	if (get_futex_value_locked(&uval, uaddr))
-		goto handle_fault;
+	err = get_futex_value_locked(&uval, uaddr);
+	if (err)
+		goto handle_err;
 
 	for (;;) {
 		newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
-		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
-			goto handle_fault;
+		err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+		if (err)
+			goto handle_err;
+
 		if (curval == uval)
 			break;
 		uval = curval;
@@ -2460,23 +2463,37 @@ retry:
 	return 0;
 
 	/*
-	 * To handle the page fault we need to drop the locks here. That gives
-	 * the other task (either the highest priority waiter itself or the
-	 * task which stole the rtmutex) the chance to try the fixup of the
-	 * pi_state. So once we are back from handling the fault we need to
-	 * check the pi_state after reacquiring the locks and before trying to
-	 * do another fixup. When the fixup has been done already we simply
-	 * return.
+	 * In order to reschedule or handle a page fault, we need to drop the
+	 * locks here. In the case of a fault, this gives the other task
+	 * (either the highest priority waiter itself or the task which stole
+	 * the rtmutex) the chance to try the fixup of the pi_state. So once we
+	 * are back from handling the fault we need to check the pi_state after
+	 * reacquiring the locks and before trying to do another fixup. When
+	 * the fixup has been done already we simply return.
 	 *
 	 * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
 	 * drop hb->lock since the caller owns the hb -> futex_q relation.
 	 * Dropping the pi_mutex->wait_lock requires the state revalidate.
 	 */
-handle_fault:
+handle_err:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	spin_unlock(q->lock_ptr);
 
-	ret = fault_in_user_writeable(uaddr);
+	switch (err) {
+	case -EFAULT:
+		ret = fault_in_user_writeable(uaddr);
+		break;
+
+	case -EAGAIN:
+		cond_resched();
+		ret = 0;
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+		ret = err;
+		break;
+	}
 
 	spin_lock(q->lock_ptr);
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
@@ -3045,10 +3062,8 @@ retry:
 		 * A unconditional UNLOCK_PI op raced against a waiter
 		 * setting the FUTEX_WAITERS bit. Try again.
 		 */
-		if (ret == -EAGAIN) {
-			put_futex_key(&key);
-			goto retry;
-		}
+		if (ret == -EAGAIN)
+			goto pi_retry;
 		/*
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
@@ -3063,9 +3078,19 @@ retry:
 	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
 	 * owner.
 	 */
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
+	if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) {
 		spin_unlock(&hb->lock);
-		goto pi_faulted;
+		switch (ret) {
+		case -EFAULT:
+			goto pi_faulted;
+
+		case -EAGAIN:
+			goto pi_retry;
+
+		default:
+			WARN_ON_ONCE(1);
+			goto out_putkey;
+		}
 	}
 
 	/*
@@ -3079,6 +3104,11 @@ out_putkey:
 	put_futex_key(&key);
 	return ret;
 
+pi_retry:
+	put_futex_key(&key);
+	cond_resched();
+	goto retry;
+
 pi_faulted:
 	put_futex_key(&key);
 
@@ -3439,6 +3469,7 @@ err_unlock:
 static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
 {
 	u32 uval, uninitialized_var(nval), mval;
+	int err;
 
 	/* Futex address must be 32bit aligned */
 	if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)
@@ -3448,42 +3479,57 @@ retry:
 	if (get_user(uval, uaddr))
 		return -1;
 
-	if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) {
-		/*
-		 * Ok, this dying thread is truly holding a futex
-		 * of interest. Set the OWNER_DIED bit atomically
-		 * via cmpxchg, and if the value had FUTEX_WAITERS
-		 * set, wake up a waiter (if any). (We have to do a
-		 * futex_wake() even if OWNER_DIED is already set -
-		 * to handle the rare but possible case of recursive
-		 * thread-death.) The rest of the cleanup is done in
-		 * userspace.
-		 */
-		mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
-		/*
-		 * We are not holding a lock here, but we want to have
-		 * the pagefault_disable/enable() protection because
-		 * we want to handle the fault gracefully. If the
-		 * access fails we try to fault in the futex with R/W
-		 * verification via get_user_pages. get_user() above
-		 * does not guarantee R/W access. If that fails we
-		 * give up and leave the futex locked.
-		 */
-		if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr))
+		return 0;
+
+	/*
+	 * Ok, this dying thread is truly holding a futex
+	 * of interest. Set the OWNER_DIED bit atomically
+	 * via cmpxchg, and if the value had FUTEX_WAITERS
+	 * set, wake up a waiter (if any). (We have to do a
+	 * futex_wake() even if OWNER_DIED is already set -
+	 * to handle the rare but possible case of recursive
+	 * thread-death.) The rest of the cleanup is done in
+	 * userspace.
+	 */
+	mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
+
+	/*
+	 * We are not holding a lock here, but we want to have
+	 * the pagefault_disable/enable() protection because
+	 * we want to handle the fault gracefully. If the
+	 * access fails we try to fault in the futex with R/W
+	 * verification via get_user_pages. get_user() above
+	 * does not guarantee R/W access. If that fails we
+	 * give up and leave the futex locked.
+	 */
+	if ((err = cmpxchg_futex_value_locked(&nval, uaddr, uval, mval))) {
+		switch (err) {
+		case -EFAULT:
 			if (fault_in_user_writeable(uaddr))
 				return -1;
 			goto retry;
-		}
-		if (nval != uval)
+
+		case -EAGAIN:
+			cond_resched();
 			goto retry;
 
-		/*
-		 * Wake robust non-PI futexes here. The wakeup of
-		 * PI futexes happens in exit_pi_state():
-		 */
-		if (!pi && (uval & FUTEX_WAITERS))
-			futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+		default:
+			WARN_ON_ONCE(1);
+			return err;
+		}
 	}
+
+	if (nval != uval)
+		goto retry;
+
+	/*
+	 * Wake robust non-PI futexes here. The wakeup of
+	 * PI futexes happens in exit_pi_state():
+	 */
+	if (!pi && (uval & FUTEX_WAITERS))
+		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+
 	return 0;
 }
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 84b54a17b95d..df557ec20a6f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -356,8 +356,10 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 	desc->affinity_notify = notify;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
-	if (old_notify)
+	if (old_notify) {
+		cancel_work_sync(&old_notify->work);
 		kref_put(&old_notify->kref, old_notify->release);
+	}
 
 	return 0;
 }
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index f4ddfdd2d07e..de78d1b998f8 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -709,7 +709,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force)
 static int reuse_unused_kprobe(struct kprobe *ap)
 {
 	struct optimized_kprobe *op;
-	int ret;
 
 	/*
 	 * Unused kprobe MUST be on the way of delayed unoptimizing (means
@@ -720,9 +719,8 @@ static int reuse_unused_kprobe(struct kprobe *ap)
 	/* Enable the probe again */
 	ap->flags &= ~KPROBE_FLAG_DISABLED;
 	/* Optimize it again (remove from op->list) */
-	ret = kprobe_optready(ap);
-	if (ret)
-		return ret;
+	if (!kprobe_optready(ap))
+		return -EINVAL;
 
 	optimize_kprobe(ap);
 	return 0;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 771e93f9c43f..6f357f4fc859 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -29,6 +29,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/cn_proc.h>
 #include <linux/compat.h>
+#include <linux/sched/signal.h>
 
 /*
  * Access another process' address space via ptrace.
@@ -924,18 +925,26 @@ int ptrace_request(struct task_struct *child, long request,
 			ret = ptrace_setsiginfo(child, &siginfo);
 		break;
 
-	case PTRACE_GETSIGMASK:
+	case PTRACE_GETSIGMASK: {
+		sigset_t *mask;
+
 		if (addr != sizeof(sigset_t)) {
 			ret = -EINVAL;
 			break;
 		}
 
-		if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t)))
+		if (test_tsk_restore_sigmask(child))
+			mask = &child->saved_sigmask;
+		else
+			mask = &child->blocked;
+
+		if (copy_to_user(datavp, mask, sizeof(sigset_t)))
 			ret = -EFAULT;
 		else
 			ret = 0;
 
 		break;
+	}
 
 	case PTRACE_SETSIGMASK: {
 		sigset_t new_set;
@@ -961,6 +970,8 @@ int ptrace_request(struct task_struct *child, long request,
 		child->blocked = new_set;
 		spin_unlock_irq(&child->sighand->siglock);
 
+		clear_tsk_restore_sigmask(child);
+
 		ret = 0;
 		break;
 	}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 01a2489de94e..62cc29364fba 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6942,7 +6942,7 @@ static int __maybe_unused cpu_period_quota_parse(char *buf,
 {
 	char tok[21];	/* U64_MAX */
 
-	if (!sscanf(buf, "%s %llu", tok, periodp))
+	if (sscanf(buf, "%20s %llu", tok, periodp) < 1)
 		return -EINVAL;
 
 	*periodp *= NSEC_PER_USEC;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 033ec7c45f13..1ccf77f6d346 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -48,10 +48,10 @@ struct sugov_cpu {
 
 	bool			iowait_boost_pending;
 	unsigned int		iowait_boost;
-	unsigned int		iowait_boost_max;
 	u64			last_update;
 
 	unsigned long		bw_dl;
+	unsigned long		min;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -303,8 +303,7 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
 	if (delta_ns <= TICK_NSEC)
 		return false;
 
-	sg_cpu->iowait_boost = set_iowait_boost
-		? sg_cpu->sg_policy->policy->min : 0;
+	sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->min : 0;
 	sg_cpu->iowait_boost_pending = set_iowait_boost;
 
 	return true;
@@ -344,14 +343,13 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
 
 	/* Double the boost at each request */
 	if (sg_cpu->iowait_boost) {
-		sg_cpu->iowait_boost <<= 1;
-		if (sg_cpu->iowait_boost > sg_cpu->iowait_boost_max)
-			sg_cpu->iowait_boost = sg_cpu->iowait_boost_max;
+		sg_cpu->iowait_boost =
+			min_t(unsigned int, sg_cpu->iowait_boost << 1, SCHED_CAPACITY_SCALE);
 		return;
 	}
 
 	/* First wakeup after IO: start with minimum boost */
-	sg_cpu->iowait_boost = sg_cpu->sg_policy->policy->min;
+	sg_cpu->iowait_boost = sg_cpu->min;
 }
 
 /**
@@ -373,47 +371,38 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  * This mechanism is designed to boost high frequently IO waiting tasks, while
  * being more conservative on tasks which does sporadic IO operations.
  */
-static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
-			       unsigned long *util, unsigned long *max)
+static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
+					unsigned long util, unsigned long max)
 {
-	unsigned int boost_util, boost_max;
+	unsigned long boost;
 
 	/* No boost currently required */
 	if (!sg_cpu->iowait_boost)
-		return;
+		return util;
 
 	/* Reset boost if the CPU appears to have been idle enough */
 	if (sugov_iowait_reset(sg_cpu, time, false))
-		return;
+		return util;
 
-	/*
-	 * An IO waiting task has just woken up:
-	 * allow to further double the boost value
-	 */
-	if (sg_cpu->iowait_boost_pending) {
-		sg_cpu->iowait_boost_pending = false;
-	} else {
+	if (!sg_cpu->iowait_boost_pending) {
 		/*
-		 * Otherwise: reduce the boost value and disable it when we
-		 * reach the minimum.
+		 * No boost pending; reduce the boost value.
 		 */
 		sg_cpu->iowait_boost >>= 1;
-		if (sg_cpu->iowait_boost < sg_cpu->sg_policy->policy->min) {
+		if (sg_cpu->iowait_boost < sg_cpu->min) {
 			sg_cpu->iowait_boost = 0;
-			return;
+			return util;
 		}
 	}
 
+	sg_cpu->iowait_boost_pending = false;
+
 	/*
-	 * Apply the current boost value: a CPU is boosted only if its current
-	 * utilization is smaller then the current IO boost level.
+	 * @util is already in capacity scale; convert iowait_boost
+	 * into the same scale so we can compare.
 	 */
-	boost_util = sg_cpu->iowait_boost;
-	boost_max = sg_cpu->iowait_boost_max;
-	if (*util * boost_max < *max * boost_util) {
-		*util = boost_util;
-		*max = boost_max;
-	}
+	boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT;
+	return max(boost, util);
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -460,7 +449,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 
 	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
-	sugov_iowait_apply(sg_cpu, time, &util, &max);
+	util = sugov_iowait_apply(sg_cpu, time, util, max);
 	next_f = get_next_freq(sg_policy, util, max);
 	/*
 	 * Do not reduce the frequency if the CPU has not been idle
@@ -500,7 +489,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 
 		j_util = sugov_get_util(j_sg_cpu);
 		j_max = j_sg_cpu->max;
-		sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
+		j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max);
 
 		if (j_util * max > j_max * util) {
 			util = j_util;
@@ -837,7 +826,9 @@ static int sugov_start(struct cpufreq_policy *policy)
 		memset(sg_cpu, 0, sizeof(*sg_cpu));
 		sg_cpu->cpu			= cpu;
 		sg_cpu->sg_policy		= sg_policy;
-		sg_cpu->iowait_boost_max	= policy->cpuinfo.max_freq;
+		sg_cpu->min			=
+			(SCHED_CAPACITY_SCALE * policy->cpuinfo.min_freq) /
+			policy->cpuinfo.max_freq;
 	}
 
 	for_each_cpu(cpu, policy->cpus) {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fb8b7b5d745d..451b1f9e80a6 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -252,7 +252,6 @@ static void task_non_contending(struct task_struct *p)
 	if (dl_entity_is_special(dl_se))
 		return;
 
-	WARN_ON(hrtimer_active(&dl_se->inactive_timer));
 	WARN_ON(dl_se->dl_non_contending);
 
 	zerolag_time = dl_se->deadline -
@@ -269,7 +268,7 @@ static void task_non_contending(struct task_struct *p)
 	 * If the "0-lag time" already passed, decrease the active
 	 * utilization now, instead of starting a timer
 	 */
-	if (zerolag_time < 0) {
+	if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
 		if (dl_task(p))
 			sub_running_bw(dl_se, dl_rq);
 		if (!dl_task(p) || p->state == TASK_DEAD) {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5e61a1a99e38..be55a64748ba 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1994,6 +1994,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
 	if (p->last_task_numa_placement) {
 		delta = runtime - p->last_sum_exec_runtime;
 		*period = now - p->last_task_numa_placement;
+
+		/* Avoid time going backwards, prevent potential divide error: */
+		if (unlikely((s64)*period < 0))
+			*period = 0;
 	} else {
 		delta = p->se.avg.load_sum;
 		*period = LOAD_AVG_MAX;
@@ -4859,12 +4863,15 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
+extern const u64 max_cfs_quota_period;
+
 static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
 		container_of(timer, struct cfs_bandwidth, period_timer);
 	int overrun;
 	int idle = 0;
+	int count = 0;
 
 	raw_spin_lock(&cfs_b->lock);
 	for (;;) {
@@ -4872,6 +4879,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 		if (!overrun)
 			break;
 
+		if (++count > 3) {
+			u64 new, old = ktime_to_ns(cfs_b->period);
+
+			new = (old * 147) / 128; /* ~115% */
+			new = min(new, max_cfs_quota_period);
+
+			cfs_b->period = ns_to_ktime(new);
+
+			/* since max is 1s, this is limited to 1e9^2, which fits in u64 */
+			cfs_b->quota *= new;
+			cfs_b->quota = div64_u64(cfs_b->quota, old);
+
+			pr_warn_ratelimited(
+        "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
+	                        smp_processor_id(),
+	                        div_u64(new, NSEC_PER_USEC),
+                                div_u64(cfs_b->quota, NSEC_PER_USEC));
+
+			/* reset count so we don't come right back in here */
+			count = 0;
+		}
+
 		idle = do_sched_cfs_period_timer(cfs_b, overrun);
 	}
 	if (idle)
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index e815781ed751..181e72718434 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -500,7 +500,10 @@ out:
  *
  * Caller must be holding current->sighand->siglock lock.
  *
- * Returns 0 on success, -ve on error.
+ * Returns 0 on success, -ve on error, or
+ *   - in TSYNC mode: the pid of a thread which was either not in the correct
+ *     seccomp mode or did not have an ancestral seccomp filter
+ *   - in NEW_LISTENER mode: the fd of the new listener
  */
 static long seccomp_attach_filter(unsigned int flags,
 				  struct seccomp_filter *filter)
@@ -1256,6 +1259,16 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	if (flags & ~SECCOMP_FILTER_FLAG_MASK)
 		return -EINVAL;
 
+	/*
+	 * In the successful case, NEW_LISTENER returns the new listener fd.
+	 * But in the failure case, TSYNC returns the thread that died. If you
+	 * combine these two flags, there's no way to tell whether something
+	 * succeeded or failed. So, let's disallow this combination.
+	 */
+	if ((flags & SECCOMP_FILTER_FLAG_TSYNC) &&
+	    (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER))
+		return -EINVAL;
+
 	/* Prepare the new filter before holding any locks. */
 	prepared = seccomp_prepare_user_filter(filter);
 	if (IS_ERR(prepared))
@@ -1302,7 +1315,7 @@ out:
 		mutex_unlock(&current->signal->cred_guard_mutex);
 out_put_fd:
 	if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) {
-		if (ret < 0) {
+		if (ret) {
 			listener_f->private_data = NULL;
 			fput(listener_f);
 			put_unused_fd(listener);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 28ec71d914c7..f50f1471c119 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -126,6 +126,7 @@ static int zero;
 static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
 static int __maybe_unused four = 4;
+static unsigned long zero_ul;
 static unsigned long one_ul = 1;
 static unsigned long long_max = LONG_MAX;
 static int one_hundred = 100;
@@ -1723,7 +1724,7 @@ static struct ctl_table fs_table[] = {
 		.maxlen		= sizeof(files_stat.max_files),
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
-		.extra1		= &zero,
+		.extra1		= &zero_ul,
 		.extra2		= &long_max,
 	},
 	{
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 094b82ca95e5..930113b9799a 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -272,7 +272,7 @@ static u64 notrace suspended_sched_clock_read(void)
 	return cd.read_data[seq & 1].epoch_cyc;
 }
 
-static int sched_clock_suspend(void)
+int sched_clock_suspend(void)
 {
 	struct clock_read_data *rd = &cd.read_data[0];
 
@@ -283,7 +283,7 @@ static int sched_clock_suspend(void)
 	return 0;
 }
 
-static void sched_clock_resume(void)
+void sched_clock_resume(void)
 {
 	struct clock_read_data *rd = &cd.read_data[0];
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 529143b4c8d2..df401463a191 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -487,6 +487,7 @@ void tick_freeze(void)
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), true);
 		system_state = SYSTEM_SUSPEND;
+		sched_clock_suspend();
 		timekeeping_suspend();
 	} else {
 		tick_suspend_local();
@@ -510,6 +511,7 @@ void tick_unfreeze(void)
 
 	if (tick_freeze_depth == num_online_cpus()) {
 		timekeeping_resume();
+		sched_clock_resume();
 		system_state = SYSTEM_RUNNING;
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), false);
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 7a9b4eb7a1d5..141ab3ab0354 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -14,6 +14,13 @@ extern u64 timekeeping_max_deferment(void);
 extern void timekeeping_warp_clock(void);
 extern int timekeeping_suspend(void);
 extern void timekeeping_resume(void);
+#ifdef CONFIG_GENERIC_SCHED_CLOCK
+extern int sched_clock_suspend(void);
+extern void sched_clock_resume(void);
+#else
+static inline int sched_clock_suspend(void) { return 0; }
+static inline void sched_clock_resume(void) { }
+#endif
 
 extern void do_timer(unsigned long ticks);
 extern void update_wall_time(void);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index aac7847c0214..f546ae5102e0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -33,6 +33,7 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <linux/rcupdate.h>
+#include <linux/kprobes.h>
 
 #include <trace/events/sched.h>
 
@@ -6216,7 +6217,7 @@ void ftrace_reset_array_ops(struct trace_array *tr)
 	tr->ops->func = ftrace_stub;
 }
 
-static inline void
+static nokprobe_inline void
 __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *ignored, struct pt_regs *regs)
 {
@@ -6276,11 +6277,13 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, regs);
 }
+NOKPROBE_SYMBOL(ftrace_ops_list_func);
 #else
 static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
 }
+NOKPROBE_SYMBOL(ftrace_ops_no_ops);
 #endif
 
 /*
@@ -6307,6 +6310,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 	preempt_enable_notrace();
 	trace_clear_recursion(bit);
 }
+NOKPROBE_SYMBOL(ftrace_ops_assist_func);
 
 /**
  * ftrace_ops_get_func - get the function a trampoline should call
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b49affb4666b..4463ae28bf1a 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -776,7 +776,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
 
 	preempt_disable_notrace();
 	time = rb_time_stamp(buffer);
-	preempt_enable_no_resched_notrace();
+	preempt_enable_notrace();
 
 	return time;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 89158aa93fa6..3842773b8aee 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -496,8 +496,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	 * not modified.
 	 */
 	pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
-	if (!pid_list)
+	if (!pid_list) {
+		trace_parser_put(&parser);
 		return -ENOMEM;
+	}
 
 	pid_list->pid_max = READ_ONCE(pid_max);
 
@@ -507,6 +509,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 
 	pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
 	if (!pid_list->pids) {
+		trace_parser_put(&parser);
 		kfree(pid_list);
 		return -ENOMEM;
 	}
@@ -6820,28 +6823,36 @@ struct buffer_ref {
 	struct ring_buffer	*buffer;
 	void			*page;
 	int			cpu;
-	int			ref;
+	refcount_t		refcount;
 };
 
+static void buffer_ref_release(struct buffer_ref *ref)
+{
+	if (!refcount_dec_and_test(&ref->refcount))
+		return;
+	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
+	kfree(ref);
+}
+
 static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
 				    struct pipe_buffer *buf)
 {
 	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
 
-	if (--ref->ref)
-		return;
-
-	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
-	kfree(ref);
+	buffer_ref_release(ref);
 	buf->private = 0;
 }
 
-static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
+static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 				struct pipe_buffer *buf)
 {
 	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
 
-	ref->ref++;
+	if (refcount_read(&ref->refcount) > INT_MAX/2)
+		return false;
+
+	refcount_inc(&ref->refcount);
+	return true;
 }
 
 /* Pipe buffer operations for a buffer. */
@@ -6849,7 +6860,7 @@ static const struct pipe_buf_operations buffer_pipe_buf_ops = {
 	.can_merge		= 0,
 	.confirm		= generic_pipe_buf_confirm,
 	.release		= buffer_pipe_buf_release,
-	.steal			= generic_pipe_buf_steal,
+	.steal			= generic_pipe_buf_nosteal,
 	.get			= buffer_pipe_buf_get,
 };
 
@@ -6862,11 +6873,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i)
 	struct buffer_ref *ref =
 		(struct buffer_ref *)spd->partial[i].private;
 
-	if (--ref->ref)
-		return;
-
-	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
-	kfree(ref);
+	buffer_ref_release(ref);
 	spd->partial[i].private = 0;
 }
 
@@ -6921,7 +6928,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 		}
 
-		ref->ref = 1;
+		refcount_set(&ref->refcount, 1);
 		ref->buffer = iter->trace_buffer->buffer;
 		ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
 		if (IS_ERR(ref->page)) {
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index fc5d23d752a5..e94d2b6bee7f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2931,6 +2931,9 @@ static bool __flush_work(struct work_struct *work, bool from_cancel)
 	if (WARN_ON(!wq_online))
 		return false;
 
+	if (WARN_ON(!work->func))
+		return false;
+
 	if (!from_cancel) {
 		lock_map_acquire(&work->lockdep_map);
 		lock_map_release(&work->lockdep_map);