Merge tag 'v4.13-rc7' into for-4.14/block-postmerge

Linux 4.13-rc7

Signed-off-by: Jens Axboe <axboe@kernel.dk>

kernel/audit_watch.c

@@ -66,7 +66,7 @@ static struct fsnotify_group *audit_watch_group;
 
 /* fsnotify events we care about. */
 #define AUDIT_FS_WATCH (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF |\
-			FS_MOVE_SELF | FS_EVENT_ON_CHILD)
+			FS_MOVE_SELF | FS_EVENT_ON_CHILD | FS_UNMOUNT)
 
 static void audit_free_parent(struct audit_parent *parent)
 {
@@ -457,13 +457,15 @@ void audit_remove_watch_rule(struct audit_krule *krule)
 	list_del(&krule->rlist);
 
 	if (list_empty(&watch->rules)) {
+		/*
+		 * audit_remove_watch() drops our reference to 'parent' which
+		 * can get freed. Grab our own reference to be safe.
+		 */
+		audit_get_parent(parent);
 		audit_remove_watch(watch);
-
-		if (list_empty(&parent->watches)) {
-			audit_get_parent(parent);
+		if (list_empty(&parent->watches))
 			fsnotify_destroy_mark(&parent->mark, audit_watch_group);
-			audit_put_parent(parent);
-		}
+		audit_put_parent(parent);
 	}
 }
 

kernel/bpf/syscall.c

@@ -1289,7 +1289,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	info_len = min_t(u32, sizeof(info), info_len);
 
 	if (copy_from_user(&info, uinfo, info_len))
-		return err;
+		return -EFAULT;
 
 	info.type = prog->type;
 	info.id = prog->aux->id;
@@ -1312,7 +1312,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	}
 
 	ulen = info.xlated_prog_len;
-	info.xlated_prog_len = bpf_prog_size(prog->len);
+	info.xlated_prog_len = bpf_prog_insn_size(prog);
 	if (info.xlated_prog_len && ulen) {
 		uinsns = u64_to_user_ptr(info.xlated_prog_insns);
 		ulen = min_t(u32, info.xlated_prog_len, ulen);

kernel/bpf/verifier.c

@@ -1865,10 +1865,12 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	 * do our normal operations to the register, we need to set the values
 	 * to the min/max since they are undefined.
 	 */
-	if (min_val == BPF_REGISTER_MIN_RANGE)
-		dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-	if (max_val == BPF_REGISTER_MAX_RANGE)
-		dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+	if (opcode != BPF_SUB) {
+		if (min_val == BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+		if (max_val == BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+	}
 
 	switch (opcode) {
 	case BPF_ADD:
@@ -1879,10 +1881,17 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		dst_reg->min_align = min(src_align, dst_align);
 		break;
 	case BPF_SUB:
+		/* If one of our values was at the end of our ranges, then the
+		 * _opposite_ value in the dst_reg goes to the end of our range.
+		 */
+		if (min_val == BPF_REGISTER_MIN_RANGE)
+			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+		if (max_val == BPF_REGISTER_MAX_RANGE)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
-			dst_reg->min_value -= min_val;
+			dst_reg->min_value -= max_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
-			dst_reg->max_value -= max_val;
+			dst_reg->max_value -= min_val;
 		dst_reg->min_align = min(src_align, dst_align);
 		break;
 	case BPF_MUL:

kernel/cgroup/cgroup-internal.h

@@ -33,6 +33,9 @@ struct cgroup_taskset {
 	struct list_head	src_csets;
 	struct list_head	dst_csets;
 
+	/* the number of tasks in the set */
+	int			nr_tasks;
+
 	/* the subsys currently being processed */
 	int			ssid;
 

kernel/cgroup/cgroup.c

@@ -2007,6 +2007,8 @@ static void cgroup_migrate_add_task(struct task_struct *task,
 	if (!cset->mg_src_cgrp)
 		return;
 
+	mgctx->tset.nr_tasks++;
+
 	list_move_tail(&task->cg_list, &cset->mg_tasks);
 	if (list_empty(&cset->mg_node))
 		list_add_tail(&cset->mg_node,
@@ -2095,21 +2097,19 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
 	struct css_set *cset, *tmp_cset;
 	int ssid, failed_ssid, ret;
 
-	/* methods shouldn't be called if no task is actually migrating */
-	if (list_empty(&tset->src_csets))
-		return 0;
-
 	/* check that we can legitimately attach to the cgroup */
-	do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
-		if (ss->can_attach) {
-			tset->ssid = ssid;
-			ret = ss->can_attach(tset);
-			if (ret) {
-				failed_ssid = ssid;
-				goto out_cancel_attach;
+	if (tset->nr_tasks) {
+		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+			if (ss->can_attach) {
+				tset->ssid = ssid;
+				ret = ss->can_attach(tset);
+				if (ret) {
+					failed_ssid = ssid;
+					goto out_cancel_attach;
+				}
 			}
-		}
-	} while_each_subsys_mask();
+		} while_each_subsys_mask();
+	}
 
 	/*
 	 * Now that we're guaranteed success, proceed to move all tasks to
@@ -2138,25 +2138,29 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
 	 */
 	tset->csets = &tset->dst_csets;
 
-	do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
-		if (ss->attach) {
-			tset->ssid = ssid;
-			ss->attach(tset);
-		}
-	} while_each_subsys_mask();
+	if (tset->nr_tasks) {
+		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+			if (ss->attach) {
+				tset->ssid = ssid;
+				ss->attach(tset);
+			}
+		} while_each_subsys_mask();
+	}
 
 	ret = 0;
 	goto out_release_tset;
 
 out_cancel_attach:
-	do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
-		if (ssid == failed_ssid)
-			break;
-		if (ss->cancel_attach) {
-			tset->ssid = ssid;
-			ss->cancel_attach(tset);
-		}
-	} while_each_subsys_mask();
+	if (tset->nr_tasks) {
+		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+			if (ssid == failed_ssid)
+				break;
+			if (ss->cancel_attach) {
+				tset->ssid = ssid;
+				ss->cancel_attach(tset);
+			}
+		} while_each_subsys_mask();
+	}
 out_release_tset:
 	spin_lock_irq(&css_set_lock);
 	list_splice_init(&tset->dst_csets, &tset->src_csets);
@@ -2998,11 +3002,11 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 	cgrp->subtree_control &= ~disable;
 
 	ret = cgroup_apply_control(cgrp);
-
 	cgroup_finalize_control(cgrp, ret);
+	if (ret)
+		goto out_unlock;
 
 	kernfs_activate(cgrp->kn);
-	ret = 0;
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
@@ -4670,6 +4674,10 @@ int __init cgroup_init(void)
 
 		if (ss->bind)
 			ss->bind(init_css_set.subsys[ssid]);
+
+		mutex_lock(&cgroup_mutex);
+		css_populate_dir(init_css_set.subsys[ssid]);
+		mutex_unlock(&cgroup_mutex);
 	}
 
 	/* init_css_set.subsys[] has been updated, re-hash */

kernel/cgroup/cpuset.c

@@ -63,6 +63,7 @@
 #include <linux/cgroup.h>
 #include <linux/wait.h>
 
+DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
 DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
 
 /* See "Frequency meter" comments, below. */

kernel/events/core.c

@@ -2217,6 +2217,33 @@ static int group_can_go_on(struct perf_event *event,
 	return can_add_hw;
 }
 
+/*
+ * Complement to update_event_times(). This computes the tstamp_* values to
+ * continue 'enabled' state from @now, and effectively discards the time
+ * between the prior tstamp_stopped and now (as we were in the OFF state, or
+ * just switched (context) time base).
+ *
+ * This further assumes '@event->state == INACTIVE' (we just came from OFF) and
+ * cannot have been scheduled in yet. And going into INACTIVE state means
+ * '@event->tstamp_stopped = @now'.
+ *
+ * Thus given the rules of update_event_times():
+ *
+ *   total_time_enabled = tstamp_stopped - tstamp_enabled
+ *   total_time_running = tstamp_stopped - tstamp_running
+ *
+ * We can insert 'tstamp_stopped == now' and reverse them to compute new
+ * tstamp_* values.
+ */
+static void __perf_event_enable_time(struct perf_event *event, u64 now)
+{
+	WARN_ON_ONCE(event->state != PERF_EVENT_STATE_INACTIVE);
+
+	event->tstamp_stopped = now;
+	event->tstamp_enabled = now - event->total_time_enabled;
+	event->tstamp_running = now - event->total_time_running;
+}
+
 static void add_event_to_ctx(struct perf_event *event,
 			       struct perf_event_context *ctx)
 {
@@ -2224,9 +2251,12 @@ static void add_event_to_ctx(struct perf_event *event,
 
 	list_add_event(event, ctx);
 	perf_group_attach(event);
-	event->tstamp_enabled = tstamp;
-	event->tstamp_running = tstamp;
-	event->tstamp_stopped = tstamp;
+	/*
+	 * We can be called with event->state == STATE_OFF when we create with
+	 * .disabled = 1. In that case the IOC_ENABLE will call this function.
+	 */
+	if (event->state == PERF_EVENT_STATE_INACTIVE)
+		__perf_event_enable_time(event, tstamp);
 }
 
 static void ctx_sched_out(struct perf_event_context *ctx,
@@ -2471,10 +2501,11 @@ static void __perf_event_mark_enabled(struct perf_event *event)
 	u64 tstamp = perf_event_time(event);
 
 	event->state = PERF_EVENT_STATE_INACTIVE;
-	event->tstamp_enabled = tstamp - event->total_time_enabled;
+	__perf_event_enable_time(event, tstamp);
 	list_for_each_entry(sub, &event->sibling_list, group_entry) {
+		/* XXX should not be > INACTIVE if event isn't */
 		if (sub->state >= PERF_EVENT_STATE_INACTIVE)
-			sub->tstamp_enabled = tstamp - sub->total_time_enabled;
+			__perf_event_enable_time(sub, tstamp);
 	}
 }
 
@@ -5090,7 +5121,7 @@ static void perf_mmap_open(struct vm_area_struct *vma)
 		atomic_inc(&event->rb->aux_mmap_count);
 
 	if (event->pmu->event_mapped)
-		event->pmu->event_mapped(event);
+		event->pmu->event_mapped(event, vma->vm_mm);
 }
 
 static void perf_pmu_output_stop(struct perf_event *event);
@@ -5113,7 +5144,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	unsigned long size = perf_data_size(rb);
 
 	if (event->pmu->event_unmapped)
-		event->pmu->event_unmapped(event);
+		event->pmu->event_unmapped(event, vma->vm_mm);
 
 	/*
 	 * rb->aux_mmap_count will always drop before rb->mmap_count and
@@ -5411,7 +5442,7 @@ aux_unlock:
 	vma->vm_ops = &perf_mmap_vmops;
 
 	if (event->pmu->event_mapped)
-		event->pmu->event_mapped(event);
+		event->pmu->event_mapped(event, vma->vm_mm);
 
 	return ret;
 }
@@ -10001,28 +10032,27 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_context;
 
 		/*
-		 * Do not allow to attach to a group in a different
-		 * task or CPU 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 (move_group) {
-			/*
-			 * Make sure we're both on the same task, or both
-			 * per-cpu events.
-			 */
-			if (group_leader->ctx->task != ctx->task)
-				goto err_context;
+		if (group_leader->cpu != event->cpu)
+			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)
-				goto err_context;
-		}
+		/*
+		 * Make sure we're both on the same task, or both
+		 * per-CPU events.
+		 */
+		if (group_leader->ctx->task != ctx->task)
+			goto err_context;
+
+		/*
+		 * Do not allow to attach to a group in a different task
+		 * or CPU context. If we're moving SW events, we'll fix
+		 * this up later, so allow that.
+		 */
+		if (!move_group && group_leader->ctx != ctx)
+			goto err_context;
 
 		/*
 		 * Only a group leader can be exclusive or pinned

kernel/fork.c

@@ -806,8 +806,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm_init_cpumask(mm);
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
+	RCU_INIT_POINTER(mm->exe_file, NULL);
 	mmu_notifier_mm_init(mm);
-	clear_tlb_flush_pending(mm);
+	init_tlb_flush_pending(mm);
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	mm->pmd_huge_pte = NULL;
 #endif

kernel/futex.c

@@ -670,13 +670,14 @@ again:
 		 * this reference was taken by ihold under the page lock
 		 * pinning the inode in place so i_lock was unnecessary. The
 		 * only way for this check to fail is if the inode was
-		 * truncated in parallel so warn for now if this happens.
+		 * truncated in parallel which is almost certainly an
+		 * application bug. In such a case, just retry.
 		 *
 		 * We are not calling into get_futex_key_refs() in file-backed
 		 * cases, therefore a successful atomic_inc return below will
 		 * guarantee that get_futex_key() will still imply smp_mb(); (B).
 		 */
-		if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) {
+		if (!atomic_inc_not_zero(&inode->i_count)) {
 			rcu_read_unlock();
 			put_page(page);
 

kernel/irq/chip.c

@@ -1000,7 +1000,7 @@ EXPORT_SYMBOL_GPL(irq_set_chip_and_handler_name);
 
 void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 {
-	unsigned long flags;
+	unsigned long flags, trigger, tmp;
 	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
 
 	if (!desc)
@@ -1014,6 +1014,8 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 
 	irq_settings_clr_and_set(desc, clr, set);
 
+	trigger = irqd_get_trigger_type(&desc->irq_data);
+
 	irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU |
 		   IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT);
 	if (irq_settings_has_no_balance_set(desc))
@@ -1025,7 +1027,11 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 	if (irq_settings_is_level(desc))
 		irqd_set(&desc->irq_data, IRQD_LEVEL);
 
-	irqd_set(&desc->irq_data, irq_settings_get_trigger_mask(desc));
+	tmp = irq_settings_get_trigger_mask(desc);
+	if (tmp != IRQ_TYPE_NONE)
+		trigger = tmp;
+
+	irqd_set(&desc->irq_data, trigger);
 
 	irq_put_desc_unlock(desc, flags);
 }

kernel/irq/cpuhotplug.c

@@ -95,8 +95,13 @@ static bool migrate_one_irq(struct irq_desc *desc)
 		affinity = cpu_online_mask;
 		brokeaff = true;
 	}
-
-	err = irq_do_set_affinity(d, affinity, true);
+	/*
+	 * Do not set the force argument of irq_do_set_affinity() as this
+	 * disables the masking of offline CPUs from the supplied affinity
+	 * mask and therefore might keep/reassign the irq to the outgoing
+	 * CPU.
+	 */
+	err = irq_do_set_affinity(d, affinity, false);
 	if (err) {
 		pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n",
 				    d->irq, err);

kernel/irq/ipi.c

@@ -165,7 +165,7 @@ irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu)
 	struct irq_data *data = irq_get_irq_data(irq);
 	struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL;
 
-	if (!data || !ipimask || cpu > nr_cpu_ids)
+	if (!data || !ipimask || cpu >= nr_cpu_ids)
 		return INVALID_HWIRQ;
 
 	if (!cpumask_test_cpu(cpu, ipimask))
@@ -195,7 +195,7 @@ static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data,
 	if (!chip->ipi_send_single && !chip->ipi_send_mask)
 		return -EINVAL;
 
-	if (cpu > nr_cpu_ids)
+	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
 	if (dest) {

kernel/kmod.c

@@ -70,6 +70,18 @@ static DECLARE_RWSEM(umhelper_sem);
 static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT);
 static DECLARE_WAIT_QUEUE_HEAD(kmod_wq);
 
+/*
+ * This is a restriction on having *all* MAX_KMOD_CONCURRENT threads
+ * running at the same time without returning. When this happens we
+ * believe you've somehow ended up with a recursive module dependency
+ * creating a loop.
+ *
+ * We have no option but to fail.
+ *
+ * Userspace should proactively try to detect and prevent these.
+ */
+#define MAX_KMOD_ALL_BUSY_TIMEOUT 5
+
 /*
 	modprobe_path is set via /proc/sys.
 */
@@ -167,8 +179,17 @@ int __request_module(bool wait, const char *fmt, ...)
 		pr_warn_ratelimited("request_module: kmod_concurrent_max (%u) close to 0 (max_modprobes: %u), for module %s, throttling...",
 				    atomic_read(&kmod_concurrent_max),
 				    MAX_KMOD_CONCURRENT, module_name);
-		wait_event_interruptible(kmod_wq,
-					 atomic_dec_if_positive(&kmod_concurrent_max) >= 0);
+		ret = wait_event_killable_timeout(kmod_wq,
+						  atomic_dec_if_positive(&kmod_concurrent_max) >= 0,
+						  MAX_KMOD_ALL_BUSY_TIMEOUT * HZ);
+		if (!ret) {
+			pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now",
+					    module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT);
+			return -ETIME;
+		} else if (ret == -ERESTARTSYS) {
+			pr_warn_ratelimited("request_module: sigkill sent for modprobe %s, giving up", module_name);
+			return ret;
+		}
 	}
 
 	trace_module_request(module_name, wait, _RET_IP_);

kernel/pid.c

@@ -527,8 +527,11 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 	if (!ns)
 		ns = task_active_pid_ns(current);
 	if (likely(pid_alive(task))) {
-		if (type != PIDTYPE_PID)
+		if (type != PIDTYPE_PID) {
+			if (type == __PIDTYPE_TGID)
+				type = PIDTYPE_PID;
 			task = task->group_leader;
+		}
 		nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
 	}
 	rcu_read_unlock();
@@ -537,12 +540,6 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 }
 EXPORT_SYMBOL(__task_pid_nr_ns);
 
-pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return pid_nr_ns(task_tgid(tsk), ns);
-}
-EXPORT_SYMBOL(task_tgid_nr_ns);
-
 struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
 {
 	return ns_of_pid(task_pid(tsk));
@@ -575,13 +572,10 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
  */
 void __init pidhash_init(void)
 {
-	unsigned int pidhash_size;
-
 	pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
 					   HASH_EARLY | HASH_SMALL | HASH_ZERO,
 					   &pidhash_shift, NULL,
 					   0, 4096);
-	pidhash_size = 1U << pidhash_shift;
 }
 
 void __init pidmap_init(void)

kernel/power/snapshot.c

@@ -1650,7 +1650,7 @@ static unsigned long minimum_image_size(unsigned long saveable)
 {
 	unsigned long size;
 
-	size = global_page_state(NR_SLAB_RECLAIMABLE)
+	size = global_node_page_state(NR_SLAB_RECLAIMABLE)
 		+ global_node_page_state(NR_ACTIVE_ANON)
 		+ global_node_page_state(NR_INACTIVE_ANON)
 		+ global_node_page_state(NR_ACTIVE_FILE)

kernel/sched/core.c

@@ -2069,7 +2069,7 @@ out:
 /**
  * try_to_wake_up_local - try to wake up a local task with rq lock held
  * @p: the thread to be awakened
- * @cookie: context's cookie for pinning
+ * @rf: request-queue flags for pinning
  *
  * Put @p on the run-queue if it's not already there. The caller must
  * ensure that this_rq() is locked, @p is bound to this_rq() and not

kernel/sched/wait.c

@@ -70,9 +70,10 @@ static void __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
 
 	list_for_each_entry_safe(curr, next, &wq_head->head, entry) {
 		unsigned flags = curr->flags;
-
-		if (curr->func(curr, mode, wake_flags, key) &&
-				(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
+		int ret = curr->func(curr, mode, wake_flags, key);
+		if (ret < 0)
+			break;
+		if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
 			break;
 	}
 }

kernel/signal.c

@@ -1194,7 +1194,11 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
 			recalc_sigpending_and_wake(t);
 		}
 	}
-	if (action->sa.sa_handler == SIG_DFL)
+	/*
+	 * Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect
+	 * debugging to leave init killable.
+	 */
+	if (action->sa.sa_handler == SIG_DFL && !t->ptrace)
 		t->signal->flags &= ~SIGNAL_UNKILLABLE;
 	ret = specific_send_sig_info(sig, info, t);
 	spin_unlock_irqrestore(&t->sighand->siglock, flags);
@@ -3303,12 +3307,15 @@ SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set)
 #ifdef CONFIG_COMPAT
 COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set32)
 {
+#ifdef __BIG_ENDIAN
 	sigset_t set;
-	int err = do_sigpending(&set, sizeof(old_sigset_t)); 
-	if (err == 0)
-		if (copy_to_user(set32, &set, sizeof(old_sigset_t)))
-			err = -EFAULT;
+	int err = do_sigpending(&set, sizeof(set.sig[0]));
+	if (!err)
+		err = put_user(set.sig[0], set32);
 	return err;
+#else
+	return sys_rt_sigpending((sigset_t __user *)set32, sizeof(*set32));
+#endif
 }
 #endif
 

kernel/time/timer.c

@@ -203,6 +203,7 @@ struct timer_base {
 	bool			migration_enabled;
 	bool			nohz_active;
 	bool			is_idle;
+	bool			must_forward_clk;
 	DECLARE_BITMAP(pending_map, WHEEL_SIZE);
 	struct hlist_head	vectors[WHEEL_SIZE];
 } ____cacheline_aligned;
@@ -856,13 +857,19 @@ get_target_base(struct timer_base *base, unsigned tflags)
 
 static inline void forward_timer_base(struct timer_base *base)
 {
-	unsigned long jnow = READ_ONCE(jiffies);
+	unsigned long jnow;
 
 	/*
-	 * We only forward the base when it's idle and we have a delta between
-	 * base clock and jiffies.
+	 * We only forward the base when we are idle or have just come out of
+	 * idle (must_forward_clk logic), and have a delta between base clock
+	 * and jiffies. In the common case, run_timers will take care of it.
 	 */
-	if (!base->is_idle || (long) (jnow - base->clk) < 2)
+	if (likely(!base->must_forward_clk))
+		return;
+
+	jnow = READ_ONCE(jiffies);
+	base->must_forward_clk = base->is_idle;
+	if ((long)(jnow - base->clk) < 2)
 		return;
 
 	/*
@@ -938,6 +945,11 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 	 * same array bucket then just return:
 	 */
 	if (timer_pending(timer)) {
+		/*
+		 * The downside of this optimization is that it can result in
+		 * larger granularity than you would get from adding a new
+		 * timer with this expiry.
+		 */
 		if (timer->expires == expires)
 			return 1;
 
@@ -948,6 +960,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		 * dequeue/enqueue dance.
 		 */
 		base = lock_timer_base(timer, &flags);
+		forward_timer_base(base);
 
 		clk = base->clk;
 		idx = calc_wheel_index(expires, clk);
@@ -964,6 +977,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		}
 	} else {
 		base = lock_timer_base(timer, &flags);
+		forward_timer_base(base);
 	}
 
 	ret = detach_if_pending(timer, base, false);
@@ -991,12 +1005,10 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 			raw_spin_lock(&base->lock);
 			WRITE_ONCE(timer->flags,
 				   (timer->flags & ~TIMER_BASEMASK) | base->cpu);
+			forward_timer_base(base);
 		}
 	}
 
-	/* Try to forward a stale timer base clock */
-	forward_timer_base(base);
-
 	timer->expires = expires;
 	/*
 	 * If 'idx' was calculated above and the base time did not advance
@@ -1112,6 +1124,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
 		WRITE_ONCE(timer->flags,
 			   (timer->flags & ~TIMER_BASEMASK) | cpu);
 	}
+	forward_timer_base(base);
 
 	debug_activate(timer, timer->expires);
 	internal_add_timer(base, timer);
@@ -1495,12 +1508,18 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		base->is_idle = false;
 	} else {
 		if (!is_max_delta)
-			expires = basem + (nextevt - basej) * TICK_NSEC;
+			expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 		/*
-		 * If we expect to sleep more than a tick, mark the base idle:
+		 * If we expect to sleep more than a tick, mark the base idle.
+		 * Also the tick is stopped so any added timer must forward
+		 * the base clk itself to keep granularity small. This idle
+		 * logic is only maintained for the BASE_STD base, deferrable
+		 * timers may still see large granularity skew (by design).
 		 */
-		if ((expires - basem) > TICK_NSEC)
+		if ((expires - basem) > TICK_NSEC) {
+			base->must_forward_clk = true;
 			base->is_idle = true;
+		}
 	}
 	raw_spin_unlock(&base->lock);
 
@@ -1611,6 +1630,19 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 {
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
+	/*
+	 * must_forward_clk must be cleared before running timers so that any
+	 * timer functions that call mod_timer will not try to forward the
+	 * base. idle trcking / clock forwarding logic is only used with
+	 * BASE_STD timers.
+	 *
+	 * The deferrable base does not do idle tracking at all, so we do
+	 * not forward it. This can result in very large variations in
+	 * granularity for deferrable timers, but they can be deferred for
+	 * long periods due to idle.
+	 */
+	base->must_forward_clk = false;
+
 	__run_timers(base);
 	if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));

kernel/trace/bpf_trace.c

@@ -204,10 +204,36 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1,
 		fmt_cnt++;
 	}
 
-	return __trace_printk(1/* fake ip will not be printed */, fmt,
-			      mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1,
-			      mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2,
-			      mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3);
+/* Horrid workaround for getting va_list handling working with different
+ * argument type combinations generically for 32 and 64 bit archs.
+ */
+#define __BPF_TP_EMIT()	__BPF_ARG3_TP()
+#define __BPF_TP(...)							\
+	__trace_printk(1 /* Fake ip will not be printed. */,		\
+		       fmt, ##__VA_ARGS__)
+
+#define __BPF_ARG1_TP(...)						\
+	((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_TP(arg1, ##__VA_ARGS__)				\
+	  : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_TP((long)arg1, ##__VA_ARGS__)			\
+	      : __BPF_TP((u32)arg1, ##__VA_ARGS__)))
+
+#define __BPF_ARG2_TP(...)						\
+	((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__)				\
+	  : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__)		\
+	      : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__)))
+
+#define __BPF_ARG3_TP(...)						\
+	((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64))	\
+	  ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__)				\
+	  : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32))	\
+	      ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__)		\
+	      : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__)))
+
+	return __BPF_TP_EMIT();
 }
 
 static const struct bpf_func_proto bpf_trace_printk_proto = {