Merge tag 'kvmarm-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for Linux 5.11

- PSCI relay at EL2 when "protected KVM" is enabled
- New exception injection code
- Simplification of AArch32 system register handling
- Fix PMU accesses when no PMU is enabled
- Expose CSV3 on non-Meltdown hosts
- Cache hierarchy discovery fixes
- PV steal-time cleanups
- Allow function pointers at EL2
- Various host EL2 entry cleanups
- Simplification of the EL2 vector allocation

11 files changed, 124 insertions, 112 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5a29ab09e72d..dc568ca295bd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2312,9 +2312,6 @@ group_sched_out(struct perf_event *group_event,
 		event_sched_out(event, cpuctx, ctx);
 
 	perf_pmu_enable(ctx->pmu);
-
-	if (group_event->attr.exclusive)
-		cpuctx->exclusive = 0;
 }
 
 #define DETACH_GROUP	0x01UL
@@ -2583,11 +2580,8 @@ group_sched_in(struct perf_event *group_event,
 
 	pmu->start_txn(pmu, PERF_PMU_TXN_ADD);
 
-	if (event_sched_in(group_event, cpuctx, ctx)) {
-		pmu->cancel_txn(pmu);
-		perf_mux_hrtimer_restart(cpuctx);
-		return -EAGAIN;
-	}
+	if (event_sched_in(group_event, cpuctx, ctx))
+		goto error;
 
 	/*
 	 * Schedule in siblings as one group (if any):
@@ -2616,10 +2610,8 @@ group_error:
 	}
 	event_sched_out(group_event, cpuctx, ctx);
 
+error:
 	pmu->cancel_txn(pmu);
-
-	perf_mux_hrtimer_restart(cpuctx);
-
 	return -EAGAIN;
 }
 
@@ -2645,7 +2637,7 @@ static int group_can_go_on(struct perf_event *event,
 	 * If this group is exclusive and there are already
 	 * events on the CPU, it can't go on.
 	 */
-	if (event->attr.exclusive && cpuctx->active_oncpu)
+	if (event->attr.exclusive && !list_empty(get_event_list(event)))
 		return 0;
 	/*
 	 * Otherwise, try to add it if all previous groups were able
@@ -3679,6 +3671,7 @@ static int merge_sched_in(struct perf_event *event, void *data)
 
 		*can_add_hw = 0;
 		ctx->rotate_necessary = 1;
+		perf_mux_hrtimer_restart(cpuctx);
 	}
 
 	return 0;
@@ -6374,14 +6367,13 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 }
 
 static void perf_sample_regs_user(struct perf_regs *regs_user,
-				  struct pt_regs *regs,
-				  struct pt_regs *regs_user_copy)
+				  struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		regs_user->abi = perf_reg_abi(current);
 		regs_user->regs = regs;
 	} else if (!(current->flags & PF_KTHREAD)) {
-		perf_get_regs_user(regs_user, regs, regs_user_copy);
+		perf_get_regs_user(regs_user, regs);
 	} else {
 		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
 		regs_user->regs = NULL;
@@ -7083,8 +7075,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 
 	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
-		perf_sample_regs_user(&data->regs_user, regs,
-				      &data->regs_user_copy);
+		perf_sample_regs_user(&data->regs_user, regs);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
@@ -7186,6 +7177,7 @@ __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
 		    struct pt_regs *regs,
 		    int (*output_begin)(struct perf_output_handle *,
+					struct perf_sample_data *,
 					struct perf_event *,
 					unsigned int))
 {
@@ -7198,7 +7190,7 @@ __perf_event_output(struct perf_event *event,
 
 	perf_prepare_sample(&header, data, event, regs);
 
-	err = output_begin(&handle, event, header.size);
+	err = output_begin(&handle, data, event, header.size);
 	if (err)
 		goto exit;
 
@@ -7264,7 +7256,7 @@ perf_event_read_event(struct perf_event *event,
 	int ret;
 
 	perf_event_header__init_id(&read_event.header, &sample, event);
-	ret = perf_output_begin(&handle, event, read_event.header.size);
+	ret = perf_output_begin(&handle, &sample, event, read_event.header.size);
 	if (ret)
 		return;
 
@@ -7533,7 +7525,7 @@ static void perf_event_task_output(struct perf_event *event,
 
 	perf_event_header__init_id(&task_event->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				task_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7636,7 +7628,7 @@ static void perf_event_comm_output(struct perf_event *event,
 		return;
 
 	perf_event_header__init_id(&comm_event->event_id.header, &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				comm_event->event_id.header.size);
 
 	if (ret)
@@ -7736,7 +7728,7 @@ static void perf_event_namespaces_output(struct perf_event *event,
 
 	perf_event_header__init_id(&namespaces_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				namespaces_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7863,7 +7855,7 @@ static void perf_event_cgroup_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&cgroup_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				cgroup_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -7989,7 +7981,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 	}
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				mmap_event->event_id.header.size);
 	if (ret)
 		goto out;
@@ -8299,7 +8291,7 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head,
 	int ret;
 
 	perf_event_header__init_id(&rec.header, &sample, event);
-	ret = perf_output_begin(&handle, event, rec.header.size);
+	ret = perf_output_begin(&handle, &sample, event, rec.header.size);
 
 	if (ret)
 		return;
@@ -8333,7 +8325,7 @@ void perf_log_lost_samples(struct perf_event *event, u64 lost)
 
 	perf_event_header__init_id(&lost_samples_event.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				lost_samples_event.header.size);
 	if (ret)
 		return;
@@ -8388,7 +8380,7 @@ static void perf_event_switch_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&se->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event, se->event_id.header.size);
+	ret = perf_output_begin(&handle, &sample, event, se->event_id.header.size);
 	if (ret)
 		return;
 
@@ -8463,7 +8455,7 @@ static void perf_log_throttle(struct perf_event *event, int enable)
 
 	perf_event_header__init_id(&throttle_event.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				throttle_event.header.size);
 	if (ret)
 		return;
@@ -8506,7 +8498,7 @@ static void perf_event_ksymbol_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&ksymbol_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, &sample, event,
 				ksymbol_event->event_id.header.size);
 	if (ret)
 		return;
@@ -8596,7 +8588,7 @@ static void perf_event_bpf_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&bpf_event->event_id.header,
 				   &sample, event);
-	ret = perf_output_begin(&handle, event,
+	ret = perf_output_begin(&handle, data, event,
 				bpf_event->event_id.header.size);
 	if (ret)
 		return;
@@ -8705,7 +8697,8 @@ static void perf_event_text_poke_output(struct perf_event *event, void *data)
 
 	perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event);
 
-	ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size);
+	ret = perf_output_begin(&handle, &sample, event,
+				text_poke_event->event_id.header.size);
 	if (ret)
 		return;
 
@@ -8786,7 +8779,7 @@ static void perf_log_itrace_start(struct perf_event *event)
 	rec.tid	= perf_event_tid(event, current);
 
 	perf_event_header__init_id(&rec.header, &sample, event);
-	ret = perf_output_begin(&handle, event, rec.header.size);
+	ret = perf_output_begin(&handle, &sample, event, rec.header.size);
 
 	if (ret)
 		return;
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index fcbf5616a441..228801e20788 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -205,16 +205,12 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
 
 static inline int get_recursion_context(int *recursion)
 {
-	int rctx;
-
-	if (unlikely(in_nmi()))
-		rctx = 3;
-	else if (in_irq())
-		rctx = 2;
-	else if (in_softirq())
-		rctx = 1;
-	else
-		rctx = 0;
+	unsigned int pc = preempt_count();
+	unsigned char rctx = 0;
+
+	rctx += !!(pc & (NMI_MASK));
+	rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK));
+	rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET));
 
 	if (recursion[rctx])
 		return -1;
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 192b8abc6330..ef91ae75ca56 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -147,6 +147,7 @@ ring_buffer_has_space(unsigned long head, unsigned long tail,
 
 static __always_inline int
 __perf_output_begin(struct perf_output_handle *handle,
+		    struct perf_sample_data *data,
 		    struct perf_event *event, unsigned int size,
 		    bool backward)
 {
@@ -237,18 +238,16 @@ __perf_output_begin(struct perf_output_handle *handle,
 	handle->size = (1UL << page_shift) - offset;
 
 	if (unlikely(have_lost)) {
-		struct perf_sample_data sample_data;
-
 		lost_event.header.size = sizeof(lost_event);
 		lost_event.header.type = PERF_RECORD_LOST;
 		lost_event.header.misc = 0;
 		lost_event.id          = event->id;
 		lost_event.lost        = local_xchg(&rb->lost, 0);
 
-		perf_event_header__init_id(&lost_event.header,
-					   &sample_data, event);
+		/* XXX mostly redundant; @data is already fully initializes */
+		perf_event_header__init_id(&lost_event.header, data, event);
 		perf_output_put(handle, lost_event);
-		perf_event__output_id_sample(event, handle, &sample_data);
+		perf_event__output_id_sample(event, handle, data);
 	}
 
 	return 0;
@@ -263,22 +262,25 @@ out:
 }
 
 int perf_output_begin_forward(struct perf_output_handle *handle,
-			     struct perf_event *event, unsigned int size)
+			      struct perf_sample_data *data,
+			      struct perf_event *event, unsigned int size)
 {
-	return __perf_output_begin(handle, event, size, false);
+	return __perf_output_begin(handle, data, event, size, false);
 }
 
 int perf_output_begin_backward(struct perf_output_handle *handle,
+			       struct perf_sample_data *data,
 			       struct perf_event *event, unsigned int size)
 {
-	return __perf_output_begin(handle, event, size, true);
+	return __perf_output_begin(handle, data, event, size, true);
 }
 
 int perf_output_begin(struct perf_output_handle *handle,
+		      struct perf_sample_data *data,
 		      struct perf_event *event, unsigned int size)
 {
 
-	return __perf_output_begin(handle, event, size,
+	return __perf_output_begin(handle, data, event, size,
 				   unlikely(is_write_backward(event)));
 }
 
diff --git a/kernel/futex.c b/kernel/futex.c
index ac328874f6e5..00259c7e288e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -788,8 +788,9 @@ static void put_pi_state(struct futex_pi_state *pi_state)
 	 */
 	if (pi_state->owner) {
 		struct task_struct *owner;
+		unsigned long flags;
 
-		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+		raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags);
 		owner = pi_state->owner;
 		if (owner) {
 			raw_spin_lock(&owner->pi_lock);
@@ -797,7 +798,7 @@ static void put_pi_state(struct futex_pi_state *pi_state)
 			raw_spin_unlock(&owner->pi_lock);
 		}
 		rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
-		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+		raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags);
 	}
 
 	if (current->pi_state_cache) {
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index b71ad8d9f1c9..d9fb9e19d2ed 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2765,7 +2765,9 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
  * (Note that this has to be done separately, because the graph cannot
  * detect such classes of deadlocks.)
  *
- * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read
+ * Returns: 0 on deadlock detected, 1 on OK, 2 if another lock with the same
+ * lock class is held but nest_lock is also held, i.e. we rely on the
+ * nest_lock to avoid the deadlock.
  */
 static int
 check_deadlock(struct task_struct *curr, struct held_lock *next)
@@ -2788,7 +2790,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next)
 		 * lock class (i.e. read_lock(lock)+read_lock(lock)):
 		 */
 		if ((next->read == 2) && prev->read)
-			return 2;
+			continue;
 
 		/*
 		 * We're holding the nest_lock, which serializes this lock's
@@ -3593,15 +3595,12 @@ static int validate_chain(struct task_struct *curr,
 		if (!ret)
 			return 0;
 		/*
-		 * Mark recursive read, as we jump over it when
-		 * building dependencies (just like we jump over
-		 * trylock entries):
-		 */
-		if (ret == 2)
-			hlock->read = 2;
-		/*
 		 * Add dependency only if this lock is not the head
-		 * of the chain, and if it's not a secondary read-lock:
+		 * of the chain, and if the new lock introduces no more
+		 * lock dependency (because we already hold a lock with the
+		 * same lock class) nor deadlock (because the nest_lock
+		 * serializes nesting locks), see the comments for
+		 * check_deadlock().
 		 */
 		if (!chain_head && ret != 2) {
 			if (!check_prevs_add(curr, hlock))
diff --git a/kernel/panic.c b/kernel/panic.c
index 396142ee43fd..332736a72a58 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -605,7 +605,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 		panic("panic_on_warn set ...\n");
 	}
 
-	dump_stack();
+	if (!regs)
+		dump_stack();
 
 	print_irqtrace_events(current);
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 2a52f42f64b6..bd04b09b84b3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -4077,7 +4077,6 @@ void rcu_cpu_starting(unsigned int cpu)
 	smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
 /*
  * The outgoing function has no further need of RCU, so remove it from
  * the rcu_node tree's ->qsmaskinitnext bit masks.
@@ -4117,6 +4116,7 @@ void rcu_report_dead(unsigned int cpu)
 	rdp->cpu_started = false;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * The outgoing CPU has just passed through the dying-idle state, and we
  * are being invoked from the CPU that was IPIed to continue the offline
diff --git a/kernel/reboot.c b/kernel/reboot.c
index e7b78d5ae1ab..af6f23d8bea1 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -551,22 +551,22 @@ static int __init reboot_setup(char *str)
 			break;
 
 		case 's':
-		{
-			int rc;
-
-			if (isdigit(*(str+1))) {
-				rc = kstrtoint(str+1, 0, &reboot_cpu);
-				if (rc)
-					return rc;
-			} else if (str[1] == 'm' && str[2] == 'p' &&
-				   isdigit(*(str+3))) {
-				rc = kstrtoint(str+3, 0, &reboot_cpu);
-				if (rc)
-					return rc;
-			} else
+			if (isdigit(*(str+1)))
+				reboot_cpu = simple_strtoul(str+1, NULL, 0);
+			else if (str[1] == 'm' && str[2] == 'p' &&
+							isdigit(*(str+3)))
+				reboot_cpu = simple_strtoul(str+3, NULL, 0);
+			else
 				*mode = REBOOT_SOFT;
+			if (reboot_cpu >= num_possible_cpus()) {
+				pr_err("Ignoring the CPU number in reboot= option. "
+				       "CPU %d exceeds possible cpu number %d\n",
+				       reboot_cpu, num_possible_cpus());
+				reboot_cpu = 0;
+				break;
+			}
 			break;
-		}
+
 		case 'g':
 			*mode = REBOOT_GPIO;
 			break;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 0655524700d2..2357921580f9 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -251,7 +251,7 @@ static int sd_ctl_doflags(struct ctl_table *table, int write,
 	unsigned long flags = *(unsigned long *)table->data;
 	size_t data_size = 0;
 	size_t len = 0;
-	char *tmp;
+	char *tmp, *buf;
 	int idx;
 
 	if (write)
@@ -269,17 +269,17 @@ static int sd_ctl_doflags(struct ctl_table *table, int write,
 		return 0;
 	}
 
-	tmp = kcalloc(data_size + 1, sizeof(*tmp), GFP_KERNEL);
-	if (!tmp)
+	buf = kcalloc(data_size + 1, sizeof(*buf), GFP_KERNEL);
+	if (!buf)
 		return -ENOMEM;
 
 	for_each_set_bit(idx, &flags, __SD_FLAG_CNT) {
 		char *name = sd_flag_debug[idx].name;
 
-		len += snprintf(tmp + len, strlen(name) + 2, "%s ", name);
+		len += snprintf(buf + len, strlen(name) + 2, "%s ", name);
 	}
 
-	tmp += *ppos;
+	tmp = buf + *ppos;
 	len -= *ppos;
 
 	if (len > *lenp)
@@ -294,7 +294,7 @@ static int sd_ctl_doflags(struct ctl_table *table, int write,
 	*lenp = len;
 	*ppos += len;
 
-	kfree(tmp);
+	kfree(buf);
 
 	return 0;
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 290f9e38378c..8917d2d715ef 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6172,21 +6172,21 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 static int
 select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 {
-	unsigned long best_cap = 0;
+	unsigned long task_util, best_cap = 0;
 	int cpu, best_cpu = -1;
 	struct cpumask *cpus;
 
-	sync_entity_load_avg(&p->se);
-
 	cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
 	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
 
+	task_util = uclamp_task_util(p);
+
 	for_each_cpu_wrap(cpu, cpus, target) {
 		unsigned long cpu_cap = capacity_of(cpu);
 
 		if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
 			continue;
-		if (task_fits_capacity(p, cpu_cap))
+		if (fits_capacity(task_util, cpu_cap))
 			return cpu;
 
 		if (cpu_cap > best_cap) {
@@ -6198,44 +6198,42 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 	return best_cpu;
 }
 
+static inline bool asym_fits_capacity(int task_util, int cpu)
+{
+	if (static_branch_unlikely(&sched_asym_cpucapacity))
+		return fits_capacity(task_util, capacity_of(cpu));
+
+	return true;
+}
+
 /*
  * Try and locate an idle core/thread in the LLC cache domain.
  */
 static int select_idle_sibling(struct task_struct *p, int prev, int target)
 {
 	struct sched_domain *sd;
+	unsigned long task_util;
 	int i, recent_used_cpu;
 
 	/*
-	 * For asymmetric CPU capacity systems, our domain of interest is
-	 * sd_asym_cpucapacity rather than sd_llc.
+	 * On asymmetric system, update task utilization because we will check
+	 * that the task fits with cpu's capacity.
 	 */
 	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
-		sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
-		/*
-		 * On an asymmetric CPU capacity system where an exclusive
-		 * cpuset defines a symmetric island (i.e. one unique
-		 * capacity_orig value through the cpuset), the key will be set
-		 * but the CPUs within that cpuset will not have a domain with
-		 * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
-		 * capacity path.
-		 */
-		if (!sd)
-			goto symmetric;
-
-		i = select_idle_capacity(p, sd, target);
-		return ((unsigned)i < nr_cpumask_bits) ? i : target;
+		sync_entity_load_avg(&p->se);
+		task_util = uclamp_task_util(p);
 	}
 
-symmetric:
-	if (available_idle_cpu(target) || sched_idle_cpu(target))
+	if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
+	    asym_fits_capacity(task_util, target))
 		return target;
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:
 	 */
 	if (prev != target && cpus_share_cache(prev, target) &&
-	    (available_idle_cpu(prev) || sched_idle_cpu(prev)))
+	    (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
+	    asym_fits_capacity(task_util, prev))
 		return prev;
 
 	/*
@@ -6258,7 +6256,8 @@ symmetric:
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
 	    (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
-	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
+	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
+	    asym_fits_capacity(task_util, recent_used_cpu)) {
 		/*
 		 * Replace recent_used_cpu with prev as it is a potential
 		 * candidate for the next wake:
@@ -6267,6 +6266,26 @@ symmetric:
 		return recent_used_cpu;
 	}
 
+	/*
+	 * For asymmetric CPU capacity systems, our domain of interest is
+	 * sd_asym_cpucapacity rather than sd_llc.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity)) {
+		sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target));
+		/*
+		 * On an asymmetric CPU capacity system where an exclusive
+		 * cpuset defines a symmetric island (i.e. one unique
+		 * capacity_orig value through the cpuset), the key will be set
+		 * but the CPUs within that cpuset will not have a domain with
+		 * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric
+		 * capacity path.
+		 */
+		if (sd) {
+			i = select_idle_capacity(p, sd, target);
+			return ((unsigned)i < nr_cpumask_bits) ? i : target;
+		}
+	}
+
 	sd = rcu_dereference(per_cpu(sd_llc, target));
 	if (!sd)
 		return target;
@@ -9031,7 +9050,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 * emptying busiest.
 	 */
 	if (local->group_type == group_has_spare) {
-		if (busiest->group_type > group_fully_busy) {
+		if ((busiest->group_type > group_fully_busy) &&
+		    !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) {
 			/*
 			 * If busiest is overloaded, try to fill spare
 			 * capacity. This might end up creating spare capacity
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 5abb5b22ad13..71109065bd8e 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -44,8 +44,6 @@ int __read_mostly soft_watchdog_user_enabled = 1;
 int __read_mostly watchdog_thresh = 10;
 static int __read_mostly nmi_watchdog_available;
 
-static struct cpumask watchdog_allowed_mask __read_mostly;
-
 struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
@@ -162,6 +160,8 @@ static void lockup_detector_update_enable(void)
 int __read_mostly sysctl_softlockup_all_cpu_backtrace;
 #endif
 
+static struct cpumask watchdog_allowed_mask __read_mostly;
+
 /* Global variables, exported for sysctl */
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;