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

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

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;
 }
 

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 {

kernel/bpf/verifier.c

@@ -1897,8 +1897,9 @@ continue_func:
 		}
 		frame++;
 		if (frame >= MAX_CALL_FRAMES) {
-			WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
-			return -EFAULT;
+			verbose(env, "the call stack of %d frames is too deep !\n",
+				frame);
+			return -E2BIG;
 		}
 		goto process_func;
 	}

kernel/dma/debug.c

@@ -706,7 +706,7 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 #ifdef CONFIG_STACKTRACE
 	entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
 	entry->stacktrace.entries = entry->st_entries;
-	entry->stacktrace.skip = 2;
+	entry->stacktrace.skip = 1;
 	save_stack_trace(&entry->stacktrace);
 #endif
 

kernel/events/core.c

@@ -2009,8 +2009,8 @@ 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);
@@ -2198,7 +2198,8 @@ 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);
 }
 
@@ -5810,10 +5811,45 @@ 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();
@@ -5822,10 +5858,7 @@ 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;
@@ -10236,6 +10269,7 @@ 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);

kernel/events/ring_buffer.c

@@ -392,7 +392,7 @@ 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;
@@ -480,7 +480,7 @@ 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);
 	}
 

kernel/irq/chip.c

@@ -1449,6 +1449,10 @@ int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info)
 int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on)
 {
 	data = data->parent_data;
+
+	if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE)
+		return 0;
+
 	if (data->chip->irq_set_wake)
 		return data->chip->irq_set_wake(data, on);
 

kernel/irq/irqdesc.c

@@ -558,6 +558,7 @@ int __init early_irq_init(void)
 		alloc_masks(&desc[i], node);
 		raw_spin_lock_init(&desc[i].lock);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+		mutex_init(&desc[i].request_mutex);
 		desc_set_defaults(i, &desc[i], node, NULL, NULL);
 	}
 	return arch_early_irq_init();

kernel/locking/lockdep.c

@@ -4689,8 +4689,8 @@ static void free_zapped_rcu(struct rcu_head *ch)
 		return;
 
 	raw_local_irq_save(flags);
-	if (!graph_lock())
-		goto out_irq;
+	arch_spin_lock(&lockdep_lock);
+	current->lockdep_recursion = 1;
 
 	/* closed head */
 	pf = delayed_free.pf + (delayed_free.index ^ 1);
@@ -4702,8 +4702,8 @@ static void free_zapped_rcu(struct rcu_head *ch)
 	 */
 	call_rcu_zapped(delayed_free.pf + delayed_free.index);
 
-	graph_unlock();
-out_irq:
+	current->lockdep_recursion = 0;
+	arch_spin_unlock(&lockdep_lock);
 	raw_local_irq_restore(flags);
 }
 
@@ -4744,21 +4744,17 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size)
 {
 	struct pending_free *pf;
 	unsigned long flags;
-	int locked;
 
 	init_data_structures_once();
 
 	raw_local_irq_save(flags);
-	locked = graph_lock();
-	if (!locked)
-		goto out_irq;
-
+	arch_spin_lock(&lockdep_lock);
+	current->lockdep_recursion = 1;
 	pf = get_pending_free();
 	__lockdep_free_key_range(pf, start, size);
 	call_rcu_zapped(pf);
-
-	graph_unlock();
-out_irq:
+	current->lockdep_recursion = 0;
+	arch_spin_unlock(&lockdep_lock);
 	raw_local_irq_restore(flags);
 
 	/*
@@ -4911,9 +4907,8 @@ void lockdep_unregister_key(struct lock_class_key *key)
 		return;
 
 	raw_local_irq_save(flags);
-	if (!graph_lock())
-		goto out_irq;
-
+	arch_spin_lock(&lockdep_lock);
+	current->lockdep_recursion = 1;
 	pf = get_pending_free();
 	hlist_for_each_entry_rcu(k, hash_head, hash_entry) {
 		if (k == key) {
@@ -4925,8 +4920,8 @@ void lockdep_unregister_key(struct lock_class_key *key)
 	WARN_ON_ONCE(!found);
 	__lockdep_free_key_range(pf, key, 1);
 	call_rcu_zapped(pf);
-	graph_unlock();
-out_irq:
+	current->lockdep_recursion = 0;
+	arch_spin_unlock(&lockdep_lock);
 	raw_local_irq_restore(flags);
 
 	/* Wait until is_dynamic_key() has finished accessing k->hash_entry. */

kernel/sched/fair.c

@@ -7784,10 +7784,10 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 	if (cfs_rq->last_h_load_update == now)
 		return;
 
-	cfs_rq->h_load_next = NULL;
+	WRITE_ONCE(cfs_rq->h_load_next, NULL);
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		cfs_rq->h_load_next = se;
+		WRITE_ONCE(cfs_rq->h_load_next, se);
 		if (cfs_rq->last_h_load_update == now)
 			break;
 	}
@@ -7797,7 +7797,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 		cfs_rq->last_h_load_update = now;
 	}
 
-	while ((se = cfs_rq->h_load_next) != NULL) {
+	while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) {
 		load = cfs_rq->h_load;
 		load = div64_ul(load * se->avg.load_avg,
 			cfs_rq_load_avg(cfs_rq) + 1);

kernel/seccomp.c

@@ -149,7 +149,7 @@ static void populate_seccomp_data(struct seccomp_data *sd)
 
 	sd->nr = syscall_get_nr(task, regs);
 	sd->arch = syscall_get_arch();
-	syscall_get_arguments(task, regs, 0, 6, args);
+	syscall_get_arguments(task, regs, args);
 	sd->args[0] = args[0];
 	sd->args[1] = args[1];
 	sd->args[2] = args[2];

kernel/signal.c

@@ -3605,16 +3605,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 		if (unlikely(sig != kinfo.si_signo))
 			goto err;
 
+		/* Only allow sending arbitrary signals to yourself. */
+		ret = -EPERM;
 		if ((task_pid(current) != pid) &&
-		    (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) {
-			/* Only allow sending arbitrary signals to yourself. */
-			ret = -EPERM;
-			if (kinfo.si_code != SI_USER)
-				goto err;
-
-			/* Turn this into a regular kill signal. */
-			prepare_kill_siginfo(sig, &kinfo);
-		}
+		    (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL))
+			goto err;
 	} else {
 		prepare_kill_siginfo(sig, &kinfo);
 	}

kernel/sysctl.c

@@ -128,6 +128,7 @@ 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;
@@ -1750,7 +1751,7 @@ 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,
 	},
 	{

kernel/time/alarmtimer.c

@@ -594,7 +594,7 @@ static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now)
 {
 	struct alarm *alarm = &timr->it.alarm.alarmtimer;
 
-	return ktime_sub(now, alarm->node.expires);
+	return ktime_sub(alarm->node.expires, now);
 }
 
 /**

kernel/trace/trace.c

@@ -7041,12 +7041,16 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
 	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;
 
+	if (ref->ref > INT_MAX/2)
+		return false;
+
 	ref->ref++;
+	return true;
 }
 
 /* Pipe buffer operations for a buffer. */

kernel/trace/trace_syscalls.c

@@ -314,6 +314,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
 	unsigned long irq_flags;
+	unsigned long args[6];
 	int pc;
 	int syscall_nr;
 	int size;
@@ -347,7 +348,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 
 	entry = ring_buffer_event_data(event);
 	entry->nr = syscall_nr;
-	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
+	syscall_get_arguments(current, regs, args);
+	memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
 	event_trigger_unlock_commit(trace_file, buffer, event, entry,
 				    irq_flags, pc);
@@ -583,6 +585,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
 	struct hlist_head *head;
+	unsigned long args[6];
 	bool valid_prog_array;
 	int syscall_nr;
 	int rctx;
@@ -613,8 +616,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 		return;
 
 	rec->nr = syscall_nr;
-	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
-			       (unsigned long *)&rec->args);
+	syscall_get_arguments(current, regs, args);
+	memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
 	if ((valid_prog_array &&
 	     !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||