Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Conflict resolution of ice_virtchnl_pf.c based upon work by
Stephen Rothwell.

Signed-off-by: David S. Miller <davem@davemloft.net>

13 files changed, 230 insertions, 225 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 805c43b083e9..787140095e58 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4142,9 +4142,9 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
  * EFAULT - verifier bug
  * 0 - 99% match. The last 1% is validated by the verifier.
  */
-int btf_check_func_type_match(struct bpf_verifier_log *log,
-			      struct btf *btf1, const struct btf_type *t1,
-			      struct btf *btf2, const struct btf_type *t2)
+static int btf_check_func_type_match(struct bpf_verifier_log *log,
+				     struct btf *btf1, const struct btf_type *t1,
+				     struct btf *btf2, const struct btf_type *t2)
 {
 	const struct btf_param *args1, *args2;
 	const char *fn1, *fn2, *s1, *s2;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 2d182c4ee9d9..a1468e3f5af2 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -56,6 +56,7 @@ struct htab_elem {
 			union {
 				struct bpf_htab *htab;
 				struct pcpu_freelist_node fnode;
+				struct htab_elem *batch_flink;
 			};
 		};
 	};
@@ -126,6 +127,17 @@ free_elems:
 	bpf_map_area_free(htab->elems);
 }
 
+/* The LRU list has a lock (lru_lock). Each htab bucket has a lock
+ * (bucket_lock). If both locks need to be acquired together, the lock
+ * order is always lru_lock -> bucket_lock and this only happens in
+ * bpf_lru_list.c logic. For example, certain code path of
+ * bpf_lru_pop_free(), which is called by function prealloc_lru_pop(),
+ * will acquire lru_lock first followed by acquiring bucket_lock.
+ *
+ * In hashtab.c, to avoid deadlock, lock acquisition of
+ * bucket_lock followed by lru_lock is not allowed. In such cases,
+ * bucket_lock needs to be released first before acquiring lru_lock.
+ */
 static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
 					  u32 hash)
 {
@@ -1256,10 +1268,12 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map,
 	void __user *ukeys = u64_to_user_ptr(attr->batch.keys);
 	void *ubatch = u64_to_user_ptr(attr->batch.in_batch);
 	u32 batch, max_count, size, bucket_size;
+	struct htab_elem *node_to_free = NULL;
 	u64 elem_map_flags, map_flags;
 	struct hlist_nulls_head *head;
 	struct hlist_nulls_node *n;
-	unsigned long flags;
+	unsigned long flags = 0;
+	bool locked = false;
 	struct htab_elem *l;
 	struct bucket *b;
 	int ret = 0;
@@ -1319,15 +1333,25 @@ again_nocopy:
 	dst_val = values;
 	b = &htab->buckets[batch];
 	head = &b->head;
-	raw_spin_lock_irqsave(&b->lock, flags);
+	/* do not grab the lock unless need it (bucket_cnt > 0). */
+	if (locked)
+		raw_spin_lock_irqsave(&b->lock, flags);
 
 	bucket_cnt = 0;
 	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
 		bucket_cnt++;
 
+	if (bucket_cnt && !locked) {
+		locked = true;
+		goto again_nocopy;
+	}
+
 	if (bucket_cnt > (max_count - total)) {
 		if (total == 0)
 			ret = -ENOSPC;
+		/* Note that since bucket_cnt > 0 here, it is implicit
+		 * that the locked was grabbed, so release it.
+		 */
 		raw_spin_unlock_irqrestore(&b->lock, flags);
 		rcu_read_unlock();
 		this_cpu_dec(bpf_prog_active);
@@ -1337,6 +1361,9 @@ again_nocopy:
 
 	if (bucket_cnt > bucket_size) {
 		bucket_size = bucket_cnt;
+		/* Note that since bucket_cnt > 0 here, it is implicit
+		 * that the locked was grabbed, so release it.
+		 */
 		raw_spin_unlock_irqrestore(&b->lock, flags);
 		rcu_read_unlock();
 		this_cpu_dec(bpf_prog_active);
@@ -1346,6 +1373,10 @@ again_nocopy:
 		goto alloc;
 	}
 
+	/* Next block is only safe to run if you have grabbed the lock */
+	if (!locked)
+		goto next_batch;
+
 	hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
 		memcpy(dst_key, l->key, key_size);
 
@@ -1370,16 +1401,33 @@ again_nocopy:
 		}
 		if (do_delete) {
 			hlist_nulls_del_rcu(&l->hash_node);
-			if (is_lru_map)
-				bpf_lru_push_free(&htab->lru, &l->lru_node);
-			else
+
+			/* bpf_lru_push_free() will acquire lru_lock, which
+			 * may cause deadlock. See comments in function
+			 * prealloc_lru_pop(). Let us do bpf_lru_push_free()
+			 * after releasing the bucket lock.
+			 */
+			if (is_lru_map) {
+				l->batch_flink = node_to_free;
+				node_to_free = l;
+			} else {
 				free_htab_elem(htab, l);
+			}
 		}
 		dst_key += key_size;
 		dst_val += value_size;
 	}
 
 	raw_spin_unlock_irqrestore(&b->lock, flags);
+	locked = false;
+
+	while (node_to_free) {
+		l = node_to_free;
+		node_to_free = node_to_free->batch_flink;
+		bpf_lru_push_free(&htab->lru, &l->lru_node);
+	}
+
+next_batch:
 	/* If we are not copying data, we can go to next bucket and avoid
 	 * unlocking the rcu.
 	 */
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 2c5dc6541ece..bd09290e3648 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -321,7 +321,7 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
 
 	ulen = info->jited_prog_len;
 	info->jited_prog_len = aux->offload->jited_len;
-	if (info->jited_prog_len & ulen) {
+	if (info->jited_prog_len && ulen) {
 		uinsns = u64_to_user_ptr(info->jited_prog_insns);
 		ulen = min_t(u32, info->jited_prog_len, ulen);
 		if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) {
diff --git a/kernel/compat.c b/kernel/compat.c
index 95005f849c68..843dd17e6078 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -26,70 +26,6 @@
 
 #include <linux/uaccess.h>
 
-static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv)
-{
-	return (!access_ok(ctv, sizeof(*ctv)) ||
-			__get_user(tv->tv_sec, &ctv->tv_sec) ||
-			__get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
-}
-
-static int __compat_put_timeval(const struct timeval *tv, struct old_timeval32 __user *ctv)
-{
-	return (!access_ok(ctv, sizeof(*ctv)) ||
-			__put_user(tv->tv_sec, &ctv->tv_sec) ||
-			__put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
-}
-
-static int __compat_get_timespec(struct timespec *ts, const struct old_timespec32 __user *cts)
-{
-	return (!access_ok(cts, sizeof(*cts)) ||
-			__get_user(ts->tv_sec, &cts->tv_sec) ||
-			__get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
-}
-
-static int __compat_put_timespec(const struct timespec *ts, struct old_timespec32 __user *cts)
-{
-	return (!access_ok(cts, sizeof(*cts)) ||
-			__put_user(ts->tv_sec, &cts->tv_sec) ||
-			__put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
-}
-
-int compat_get_timeval(struct timeval *tv, const void __user *utv)
-{
-	if (COMPAT_USE_64BIT_TIME)
-		return copy_from_user(tv, utv, sizeof(*tv)) ? -EFAULT : 0;
-	else
-		return __compat_get_timeval(tv, utv);
-}
-EXPORT_SYMBOL_GPL(compat_get_timeval);
-
-int compat_put_timeval(const struct timeval *tv, void __user *utv)
-{
-	if (COMPAT_USE_64BIT_TIME)
-		return copy_to_user(utv, tv, sizeof(*tv)) ? -EFAULT : 0;
-	else
-		return __compat_put_timeval(tv, utv);
-}
-EXPORT_SYMBOL_GPL(compat_put_timeval);
-
-int compat_get_timespec(struct timespec *ts, const void __user *uts)
-{
-	if (COMPAT_USE_64BIT_TIME)
-		return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0;
-	else
-		return __compat_get_timespec(ts, uts);
-}
-EXPORT_SYMBOL_GPL(compat_get_timespec);
-
-int compat_put_timespec(const struct timespec *ts, void __user *uts)
-{
-	if (COMPAT_USE_64BIT_TIME)
-		return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0;
-	else
-		return __compat_put_timespec(ts, uts);
-}
-EXPORT_SYMBOL_GPL(compat_put_timespec);
-
 #ifdef __ARCH_WANT_SYS_SIGPROCMASK
 
 /*
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index daa4e6eefdde..8bc6f2d670f9 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -302,9 +302,16 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 	phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
 	phys_addr_t mask = align - 1;
 	unsigned long node = rmem->fdt_node;
+	bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL);
 	struct cma *cma;
 	int err;
 
+	if (size_cmdline != -1 && default_cma) {
+		pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n",
+			rmem->name);
+		return -EBUSY;
+	}
+
 	if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
 	    of_get_flat_dt_prop(node, "no-map", NULL))
 		return -EINVAL;
@@ -322,7 +329,7 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 	/* Architecture specific contiguous memory fixup. */
 	dma_contiguous_early_fixup(rmem->base, rmem->size);
 
-	if (of_get_flat_dt_prop(node, "linux,cma-default", NULL))
+	if (default_cma)
 		dma_contiguous_set_default(cma);
 
 	rmem->ops = &rmem_cma_ops;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 6af7ae83c4ad..ac7956c38f69 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -23,18 +23,6 @@
  */
 unsigned int zone_dma_bits __ro_after_init = 24;
 
-static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
-{
-	if (!dev->dma_mask) {
-		dev_err_once(dev, "DMA map on device without dma_mask\n");
-	} else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_limit) {
-		dev_err_once(dev,
-			"overflow %pad+%zu of DMA mask %llx bus limit %llx\n",
-			&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-	}
-	WARN_ON_ONCE(1);
-}
-
 static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 		phys_addr_t phys)
 {
@@ -357,13 +345,6 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 EXPORT_SYMBOL(dma_direct_unmap_sg);
 #endif
 
-static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
-		size_t size)
-{
-	return swiotlb_force != SWIOTLB_FORCE &&
-		dma_capable(dev, dma_addr, size, true);
-}
-
 dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir,
 		unsigned long attrs)
@@ -371,9 +352,16 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 	phys_addr_t phys = page_to_phys(page) + offset;
 	dma_addr_t dma_addr = phys_to_dma(dev, phys);
 
-	if (unlikely(!dma_direct_possible(dev, dma_addr, size)) &&
-	    !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) {
-		report_addr(dev, dma_addr, size);
+	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_map(dev, phys, size, dir, attrs);
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (swiotlb_force != SWIOTLB_NO_FORCE)
+			return swiotlb_map(dev, phys, size, dir, attrs);
+
+		dev_WARN_ONCE(dev, 1,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
 		return DMA_MAPPING_ERROR;
 	}
 
@@ -411,7 +399,10 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 	dma_addr_t dma_addr = paddr;
 
 	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
-		report_addr(dev, dma_addr, size);
+		dev_err_once(dev,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		WARN_ON_ONCE(1);
 		return DMA_MAPPING_ERROR;
 	}
 
@@ -472,28 +463,26 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 }
 #endif /* CONFIG_MMU */
 
-/*
- * Because 32-bit DMA masks are so common we expect every architecture to be
- * able to satisfy them - either by not supporting more physical memory, or by
- * providing a ZONE_DMA32.  If neither is the case, the architecture needs to
- * use an IOMMU instead of the direct mapping.
- */
 int dma_direct_supported(struct device *dev, u64 mask)
 {
-	u64 min_mask;
+	u64 min_mask = (max_pfn - 1) << PAGE_SHIFT;
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		min_mask = DMA_BIT_MASK(zone_dma_bits);
-	else
-		min_mask = DMA_BIT_MASK(32);
-
-	min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT);
+	/*
+	 * Because 32-bit DMA masks are so common we expect every architecture
+	 * to be able to satisfy them - either by not supporting more physical
+	 * memory, or by providing a ZONE_DMA32.  If neither is the case, the
+	 * architecture needs to use an IOMMU instead of the direct mapping.
+	 */
+	if (mask >= DMA_BIT_MASK(32))
+		return 1;
 
 	/*
 	 * This check needs to be against the actual bit mask value, so
 	 * use __phys_to_dma() here so that the SME encryption mask isn't
 	 * part of the check.
 	 */
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
 	return mask >= __phys_to_dma(dev, min_mask);
 }
 
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 9280d6f8271e..c19379fabd20 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -22,6 +22,7 @@
 
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
@@ -656,35 +657,38 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 }
 
 /*
- * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing
+ * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing
  * to the device copy the data into it as well.
  */
-bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
+dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
-	trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force);
+	phys_addr_t swiotlb_addr;
+	dma_addr_t dma_addr;
 
-	if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) {
-		dev_warn_ratelimited(dev,
-			"Cannot do DMA to address %pa\n", phys);
-		return false;
-	}
+	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
+			      swiotlb_force);
 
-	/* Oh well, have to allocate and map a bounce buffer. */
-	*phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
-			*phys, size, size, dir, attrs);
-	if (*phys == (phys_addr_t)DMA_MAPPING_ERROR)
-		return false;
+	swiotlb_addr = swiotlb_tbl_map_single(dev,
+			__phys_to_dma(dev, io_tlb_start),
+			paddr, size, size, dir, attrs);
+	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
+		return DMA_MAPPING_ERROR;
 
 	/* Ensure that the address returned is DMA'ble */
-	*dma_addr = __phys_to_dma(dev, *phys);
-	if (unlikely(!dma_capable(dev, *dma_addr, size, true))) {
-		swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
+	dma_addr = __phys_to_dma(dev, swiotlb_addr);
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
-		return false;
+		dev_WARN_ONCE(dev, 1,
+			"swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		return DMA_MAPPING_ERROR;
 	}
 
-	return true;
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(swiotlb_addr, size, dir);
+	return dma_addr;
 }
 
 size_t swiotlb_max_mapping_size(struct device *dev)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fc1dfc007604..1a9983da4408 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -552,27 +552,32 @@ void resched_cpu(int cpu)
  */
 int get_nohz_timer_target(void)
 {
-	int i, cpu = smp_processor_id();
+	int i, cpu = smp_processor_id(), default_cpu = -1;
 	struct sched_domain *sd;
 
-	if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER))
-		return cpu;
+	if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
+		if (!idle_cpu(cpu))
+			return cpu;
+		default_cpu = cpu;
+	}
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
-		for_each_cpu(i, sched_domain_span(sd)) {
+		for_each_cpu_and(i, sched_domain_span(sd),
+			housekeeping_cpumask(HK_FLAG_TIMER)) {
 			if (cpu == i)
 				continue;
 
-			if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) {
+			if (!idle_cpu(i)) {
 				cpu = i;
 				goto unlock;
 			}
 		}
 	}
 
-	if (!housekeeping_cpu(cpu, HK_FLAG_TIMER))
-		cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+	if (default_cpu == -1)
+		default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+	cpu = default_cpu;
 unlock:
 	rcu_read_unlock();
 	return cpu;
@@ -1442,17 +1447,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 
 #ifdef CONFIG_SMP
 
-static inline bool is_per_cpu_kthread(struct task_struct *p)
-{
-	if (!(p->flags & PF_KTHREAD))
-		return false;
-
-	if (p->nr_cpus_allowed != 1)
-		return false;
-
-	return true;
-}
-
 /*
  * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
@@ -3669,28 +3663,32 @@ static void sched_tick_remote(struct work_struct *work)
 	 * statistics and checks timeslices in a time-independent way, regardless
 	 * of when exactly it is running.
 	 */
-	if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+	if (!tick_nohz_tick_stopped_cpu(cpu))
 		goto out_requeue;
 
 	rq_lock_irq(rq, &rf);
 	curr = rq->curr;
-	if (is_idle_task(curr) || cpu_is_offline(cpu))
+	if (cpu_is_offline(cpu))
 		goto out_unlock;
 
+	curr = rq->curr;
 	update_rq_clock(rq);
-	delta = rq_clock_task(rq) - curr->se.exec_start;
 
-	/*
-	 * Make sure the next tick runs within a reasonable
-	 * amount of time.
-	 */
-	WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+	if (!is_idle_task(curr)) {
+		/*
+		 * Make sure the next tick runs within a reasonable
+		 * amount of time.
+		 */
+		delta = rq_clock_task(rq) - curr->se.exec_start;
+		WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+	}
 	curr->sched_class->task_tick(rq, curr, 0);
 
+	calc_load_nohz_remote(rq);
 out_unlock:
 	rq_unlock_irq(rq, &rf);
-
 out_requeue:
+
 	/*
 	 * Run the remote tick once per second (1Hz). This arbitrary
 	 * frequency is large enough to avoid overload but short enough
@@ -7063,8 +7061,15 @@ void sched_move_task(struct task_struct *tsk)
 
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
-	if (running)
+	if (running) {
 		set_next_task(rq, tsk);
+		/*
+		 * After changing group, the running task may have joined a
+		 * throttled one but it's still the running task. Trigger a
+		 * resched to make sure that task can still run.
+		 */
+		resched_curr(rq);
+	}
 
 	task_rq_unlock(rq, tsk, &rf);
 }
@@ -7260,7 +7265,7 @@ capacity_from_percent(char *buf)
 					     &req.percent);
 		if (req.ret)
 			return req;
-		if (req.percent > UCLAMP_PERCENT_SCALE) {
+		if ((u64)req.percent > UCLAMP_PERCENT_SCALE) {
 			req.ret = -ERANGE;
 			return req;
 		}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fe4e0d775375..3c8a379c357e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3516,7 +3516,6 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
  * attach_entity_load_avg - attach this entity to its cfs_rq load avg
  * @cfs_rq: cfs_rq to attach to
  * @se: sched_entity to attach
- * @flags: migration hints
  *
  * Must call update_cfs_rq_load_avg() before this, since we rely on
  * cfs_rq->avg.last_update_time being current.
@@ -5912,6 +5911,20 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    (available_idle_cpu(prev) || sched_idle_cpu(prev)))
 		return prev;
 
+	/*
+	 * Allow a per-cpu kthread to stack with the wakee if the
+	 * kworker thread and the tasks previous CPUs are the same.
+	 * The assumption is that the wakee queued work for the
+	 * per-cpu kthread that is now complete and the wakeup is
+	 * essentially a sync wakeup. An obvious example of this
+	 * pattern is IO completions.
+	 */
+	if (is_per_cpu_kthread(current) &&
+	    prev == smp_processor_id() &&
+	    this_rq()->nr_running <= 1) {
+		return prev;
+	}
+
 	/* Check a recently used CPU as a potential idle candidate: */
 	recent_used_cpu = p->recent_used_cpu;
 	if (recent_used_cpu != prev &&
@@ -8658,10 +8671,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	/*
 	 * Try to use spare capacity of local group without overloading it or
 	 * emptying busiest.
-	 * XXX Spreading tasks across NUMA nodes is not always the best policy
-	 * and special care should be taken for SD_NUMA domain level before
-	 * spreading the tasks. For now, load_balance() fully relies on
-	 * NUMA_BALANCING and fbq_classify_group/rq to override the decision.
 	 */
 	if (local->group_type == group_has_spare) {
 		if (busiest->group_type > group_fully_busy) {
@@ -8701,16 +8710,37 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 			env->migration_type = migrate_task;
 			lsub_positive(&nr_diff, local->sum_nr_running);
 			env->imbalance = nr_diff >> 1;
-			return;
-		}
+		} else {
 
-		/*
-		 * If there is no overload, we just want to even the number of
-		 * idle cpus.
-		 */
-		env->migration_type = migrate_task;
-		env->imbalance = max_t(long, 0, (local->idle_cpus -
+			/*
+			 * If there is no overload, we just want to even the number of
+			 * idle cpus.
+			 */
+			env->migration_type = migrate_task;
+			env->imbalance = max_t(long, 0, (local->idle_cpus -
 						 busiest->idle_cpus) >> 1);
+		}
+
+		/* Consider allowing a small imbalance between NUMA groups */
+		if (env->sd->flags & SD_NUMA) {
+			unsigned int imbalance_min;
+
+			/*
+			 * Compute an allowed imbalance based on a simple
+			 * pair of communicating tasks that should remain
+			 * local and ignore them.
+			 *
+			 * NOTE: Generally this would have been based on
+			 * the domain size and this was evaluated. However,
+			 * the benefit is similar across a range of workloads
+			 * and machines but scaling by the domain size adds
+			 * the risk that lower domains have to be rebalanced.
+			 */
+			imbalance_min = 2;
+			if (busiest->sum_nr_running <= imbalance_min)
+				env->imbalance = 0;
+		}
+
 		return;
 	}
 
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 28a516575c18..de22da666ac7 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -231,16 +231,11 @@ static inline int calc_load_read_idx(void)
 	return calc_load_idx & 1;
 }
 
-void calc_load_nohz_start(void)
+static void calc_load_nohz_fold(struct rq *rq)
 {
-	struct rq *this_rq = this_rq();
 	long delta;
 
-	/*
-	 * We're going into NO_HZ mode, if there's any pending delta, fold it
-	 * into the pending NO_HZ delta.
-	 */
-	delta = calc_load_fold_active(this_rq, 0);
+	delta = calc_load_fold_active(rq, 0);
 	if (delta) {
 		int idx = calc_load_write_idx();
 
@@ -248,6 +243,24 @@ void calc_load_nohz_start(void)
 	}
 }
 
+void calc_load_nohz_start(void)
+{
+	/*
+	 * We're going into NO_HZ mode, if there's any pending delta, fold it
+	 * into the pending NO_HZ delta.
+	 */
+	calc_load_nohz_fold(this_rq());
+}
+
+/*
+ * Keep track of the load for NOHZ_FULL, must be called between
+ * calc_load_nohz_{start,stop}().
+ */
+void calc_load_nohz_remote(struct rq *rq)
+{
+	calc_load_nohz_fold(rq);
+}
+
 void calc_load_nohz_stop(void)
 {
 	struct rq *this_rq = this_rq();
@@ -268,7 +281,7 @@ void calc_load_nohz_stop(void)
 		this_rq->calc_load_update += LOAD_FREQ;
 }
 
-static long calc_load_nohz_fold(void)
+static long calc_load_nohz_read(void)
 {
 	int idx = calc_load_read_idx();
 	long delta = 0;
@@ -323,7 +336,7 @@ static void calc_global_nohz(void)
 }
 #else /* !CONFIG_NO_HZ_COMMON */
 
-static inline long calc_load_nohz_fold(void) { return 0; }
+static inline long calc_load_nohz_read(void) { return 0; }
 static inline void calc_global_nohz(void) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
@@ -346,7 +359,7 @@ void calc_global_load(unsigned long ticks)
 	/*
 	 * Fold the 'old' NO_HZ-delta to include all NO_HZ CPUs.
 	 */
-	delta = calc_load_nohz_fold();
+	delta = calc_load_nohz_read();
 	if (delta)
 		atomic_long_add(delta, &calc_load_tasks);
 
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index ac4bd0ca11cc..028520702717 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1199,6 +1199,9 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 	if (static_branch_likely(&psi_disabled))
 		return -EOPNOTSUPP;
 
+	if (!nbytes)
+		return -EINVAL;
+
 	buf_size = min(nbytes, sizeof(buf));
 	if (copy_from_user(buf, user_buf, buf_size))
 		return -EFAULT;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1a88dc8ad11b..9ea647835fd6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -896,7 +896,7 @@ struct rq {
 	 */
 	unsigned long		nr_uninterruptible;
 
-	struct task_struct	*curr;
+	struct task_struct __rcu	*curr;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
 	unsigned long		next_balance;
@@ -2479,3 +2479,16 @@ static inline void membarrier_switch_mm(struct rq *rq,
 {
 }
 #endif
+
+#ifdef CONFIG_SMP
+static inline bool is_per_cpu_kthread(struct task_struct *p)
+{
+	if (!(p->flags & PF_KTHREAD))
+		return false;
+
+	if (p->nr_cpus_allowed != 1)
+		return false;
+
+	return true;
+}
+#endif
diff --git a/kernel/time/time.c b/kernel/time/time.c
index cdd7386115ff..3985b2b32d08 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -449,49 +449,6 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0,
 }
 EXPORT_SYMBOL(mktime64);
 
-/**
- * ns_to_timespec - Convert nanoseconds to timespec
- * @nsec:       the nanoseconds value to be converted
- *
- * Returns the timespec representation of the nsec parameter.
- */
-struct timespec ns_to_timespec(const s64 nsec)
-{
-	struct timespec ts;
-	s32 rem;
-
-	if (!nsec)
-		return (struct timespec) {0, 0};
-
-	ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem);
-	if (unlikely(rem < 0)) {
-		ts.tv_sec--;
-		rem += NSEC_PER_SEC;
-	}
-	ts.tv_nsec = rem;
-
-	return ts;
-}
-EXPORT_SYMBOL(ns_to_timespec);
-
-/**
- * ns_to_timeval - Convert nanoseconds to timeval
- * @nsec:       the nanoseconds value to be converted
- *
- * Returns the timeval representation of the nsec parameter.
- */
-struct timeval ns_to_timeval(const s64 nsec)
-{
-	struct timespec ts = ns_to_timespec(nsec);
-	struct timeval tv;
-
-	tv.tv_sec = ts.tv_sec;
-	tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000;
-
-	return tv;
-}
-EXPORT_SYMBOL(ns_to_timeval);
-
 struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec)
 {
 	struct timespec64 ts = ns_to_timespec64(nsec);