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

Cross-merge networking fixes after downstream PR (net-6.13-rc3).

No conflicts or adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

17 files changed, 163 insertions, 91 deletions

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 279ba5c420a4..561d96affe9f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2728,8 +2728,8 @@ void __audit_ptrace(struct task_struct *t)
 	context->target_auid = audit_get_loginuid(t);
 	context->target_uid = task_uid(t);
 	context->target_sessionid = audit_get_sessionid(t);
-	security_task_getlsmprop_obj(t, &context->target_ref);
 	strscpy(context->target_comm, t->comm);
+	security_task_getlsmprop_obj(t, &context->target_ref);
 }
 
 /**
@@ -2755,8 +2755,8 @@ int audit_signal_info_syscall(struct task_struct *t)
 		ctx->target_auid = audit_get_loginuid(t);
 		ctx->target_uid = t_uid;
 		ctx->target_sessionid = audit_get_sessionid(t);
-		security_task_getlsmprop_obj(t, &ctx->target_ref);
 		strscpy(ctx->target_comm, t->comm);
+		security_task_getlsmprop_obj(t, &ctx->target_ref);
 		return 0;
 	}
 
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index 3bc61628ab25..967492b65185 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -375,8 +375,6 @@ BTF_ID(func, bpf_lsm_socket_socketpair)
 
 BTF_ID(func, bpf_lsm_syslog)
 BTF_ID(func, bpf_lsm_task_alloc)
-BTF_ID(func, bpf_lsm_current_getsecid_subj)
-BTF_ID(func, bpf_lsm_task_getsecid_obj)
 BTF_ID(func, bpf_lsm_task_prctl)
 BTF_ID(func, bpf_lsm_task_setscheduler)
 BTF_ID(func, bpf_lsm_task_to_inode)
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index effde52bc857..482d284a1553 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -184,7 +184,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 static void dev_map_free(struct bpf_map *map)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
-	int i;
+	u32 i;
 
 	/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
 	 * so the programs (can be more than one that used this map) were
@@ -821,7 +821,7 @@ static long dev_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *old_dev;
-	int k = *(u32 *)key;
+	u32 k = *(u32 *)key;
 
 	if (k >= map->max_entries)
 		return -EINVAL;
@@ -838,7 +838,7 @@ static long dev_map_hash_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
 	struct bpf_dtab_netdev *old_dev;
-	int k = *(u32 *)key;
+	u32 k = *(u32 *)key;
 	unsigned long flags;
 	int ret = -ENOENT;
 
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 9b60eda0f727..f8bc1e096182 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -15,6 +15,7 @@
 #include <net/ipv6.h>
 #include <uapi/linux/btf.h>
 #include <linux/btf_ids.h>
+#include <linux/bpf_mem_alloc.h>
 
 /* Intermediate node */
 #define LPM_TREE_NODE_FLAG_IM BIT(0)
@@ -22,7 +23,6 @@
 struct lpm_trie_node;
 
 struct lpm_trie_node {
-	struct rcu_head rcu;
 	struct lpm_trie_node __rcu	*child[2];
 	u32				prefixlen;
 	u32				flags;
@@ -32,10 +32,11 @@ struct lpm_trie_node {
 struct lpm_trie {
 	struct bpf_map			map;
 	struct lpm_trie_node __rcu	*root;
+	struct bpf_mem_alloc		ma;
 	size_t				n_entries;
 	size_t				max_prefixlen;
 	size_t				data_size;
-	spinlock_t			lock;
+	raw_spinlock_t			lock;
 };
 
 /* This trie implements a longest prefix match algorithm that can be used to
@@ -287,17 +288,18 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key)
 	return found->data + trie->data_size;
 }
 
-static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie,
-						 const void *value)
+static struct lpm_trie_node *lpm_trie_node_alloc(struct lpm_trie *trie,
+						 const void *value,
+						 bool disable_migration)
 {
 	struct lpm_trie_node *node;
-	size_t size = sizeof(struct lpm_trie_node) + trie->data_size;
 
-	if (value)
-		size += trie->map.value_size;
+	if (disable_migration)
+		migrate_disable();
+	node = bpf_mem_cache_alloc(&trie->ma);
+	if (disable_migration)
+		migrate_enable();
 
-	node = bpf_map_kmalloc_node(&trie->map, size, GFP_NOWAIT | __GFP_NOWARN,
-				    trie->map.numa_node);
 	if (!node)
 		return NULL;
 
@@ -310,12 +312,22 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie,
 	return node;
 }
 
+static int trie_check_add_elem(struct lpm_trie *trie, u64 flags)
+{
+	if (flags == BPF_EXIST)
+		return -ENOENT;
+	if (trie->n_entries == trie->map.max_entries)
+		return -ENOSPC;
+	trie->n_entries++;
+	return 0;
+}
+
 /* Called from syscall or from eBPF program */
 static long trie_update_elem(struct bpf_map *map,
 			     void *_key, void *value, u64 flags)
 {
 	struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
-	struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL;
+	struct lpm_trie_node *node, *im_node, *new_node;
 	struct lpm_trie_node *free_node = NULL;
 	struct lpm_trie_node __rcu **slot;
 	struct bpf_lpm_trie_key_u8 *key = _key;
@@ -330,22 +342,14 @@ static long trie_update_elem(struct bpf_map *map,
 	if (key->prefixlen > trie->max_prefixlen)
 		return -EINVAL;
 
-	spin_lock_irqsave(&trie->lock, irq_flags);
-
-	/* Allocate and fill a new node */
-
-	if (trie->n_entries == trie->map.max_entries) {
-		ret = -ENOSPC;
-		goto out;
-	}
-
-	new_node = lpm_trie_node_alloc(trie, value);
-	if (!new_node) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	/* Allocate and fill a new node. Need to disable migration before
+	 * invoking bpf_mem_cache_alloc().
+	 */
+	new_node = lpm_trie_node_alloc(trie, value, true);
+	if (!new_node)
+		return -ENOMEM;
 
-	trie->n_entries++;
+	raw_spin_lock_irqsave(&trie->lock, irq_flags);
 
 	new_node->prefixlen = key->prefixlen;
 	RCU_INIT_POINTER(new_node->child[0], NULL);
@@ -364,8 +368,7 @@ static long trie_update_elem(struct bpf_map *map,
 		matchlen = longest_prefix_match(trie, node, key);
 
 		if (node->prefixlen != matchlen ||
-		    node->prefixlen == key->prefixlen ||
-		    node->prefixlen == trie->max_prefixlen)
+		    node->prefixlen == key->prefixlen)
 			break;
 
 		next_bit = extract_bit(key->data, node->prefixlen);
@@ -376,6 +379,10 @@ static long trie_update_elem(struct bpf_map *map,
 	 * simply assign the @new_node to that slot and be done.
 	 */
 	if (!node) {
+		ret = trie_check_add_elem(trie, flags);
+		if (ret)
+			goto out;
+
 		rcu_assign_pointer(*slot, new_node);
 		goto out;
 	}
@@ -384,18 +391,30 @@ static long trie_update_elem(struct bpf_map *map,
 	 * which already has the correct data array set.
 	 */
 	if (node->prefixlen == matchlen) {
+		if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) {
+			if (flags == BPF_NOEXIST) {
+				ret = -EEXIST;
+				goto out;
+			}
+		} else {
+			ret = trie_check_add_elem(trie, flags);
+			if (ret)
+				goto out;
+		}
+
 		new_node->child[0] = node->child[0];
 		new_node->child[1] = node->child[1];
 
-		if (!(node->flags & LPM_TREE_NODE_FLAG_IM))
-			trie->n_entries--;
-
 		rcu_assign_pointer(*slot, new_node);
 		free_node = node;
 
 		goto out;
 	}
 
+	ret = trie_check_add_elem(trie, flags);
+	if (ret)
+		goto out;
+
 	/* If the new node matches the prefix completely, it must be inserted
 	 * as an ancestor. Simply insert it between @node and *@slot.
 	 */
@@ -406,8 +425,10 @@ static long trie_update_elem(struct bpf_map *map,
 		goto out;
 	}
 
-	im_node = lpm_trie_node_alloc(trie, NULL);
+	/* migration is disabled within the locked scope */
+	im_node = lpm_trie_node_alloc(trie, NULL, false);
 	if (!im_node) {
+		trie->n_entries--;
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -429,16 +450,13 @@ static long trie_update_elem(struct bpf_map *map,
 	rcu_assign_pointer(*slot, im_node);
 
 out:
-	if (ret) {
-		if (new_node)
-			trie->n_entries--;
+	raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
 
-		kfree(new_node);
-		kfree(im_node);
-	}
-
-	spin_unlock_irqrestore(&trie->lock, irq_flags);
-	kfree_rcu(free_node, rcu);
+	migrate_disable();
+	if (ret)
+		bpf_mem_cache_free(&trie->ma, new_node);
+	bpf_mem_cache_free_rcu(&trie->ma, free_node);
+	migrate_enable();
 
 	return ret;
 }
@@ -459,7 +477,7 @@ static long trie_delete_elem(struct bpf_map *map, void *_key)
 	if (key->prefixlen > trie->max_prefixlen)
 		return -EINVAL;
 
-	spin_lock_irqsave(&trie->lock, irq_flags);
+	raw_spin_lock_irqsave(&trie->lock, irq_flags);
 
 	/* Walk the tree looking for an exact key/length match and keeping
 	 * track of the path we traverse.  We will need to know the node
@@ -535,9 +553,12 @@ static long trie_delete_elem(struct bpf_map *map, void *_key)
 	free_node = node;
 
 out:
-	spin_unlock_irqrestore(&trie->lock, irq_flags);
-	kfree_rcu(free_parent, rcu);
-	kfree_rcu(free_node, rcu);
+	raw_spin_unlock_irqrestore(&trie->lock, irq_flags);
+
+	migrate_disable();
+	bpf_mem_cache_free_rcu(&trie->ma, free_parent);
+	bpf_mem_cache_free_rcu(&trie->ma, free_node);
+	migrate_enable();
 
 	return ret;
 }
@@ -559,6 +580,8 @@ out:
 static struct bpf_map *trie_alloc(union bpf_attr *attr)
 {
 	struct lpm_trie *trie;
+	size_t leaf_size;
+	int err;
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 ||
@@ -581,9 +604,19 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 			  offsetof(struct bpf_lpm_trie_key_u8, data);
 	trie->max_prefixlen = trie->data_size * 8;
 
-	spin_lock_init(&trie->lock);
+	raw_spin_lock_init(&trie->lock);
 
+	/* Allocate intermediate and leaf nodes from the same allocator */
+	leaf_size = sizeof(struct lpm_trie_node) + trie->data_size +
+		    trie->map.value_size;
+	err = bpf_mem_alloc_init(&trie->ma, leaf_size, false);
+	if (err)
+		goto free_out;
 	return &trie->map;
+
+free_out:
+	bpf_map_area_free(trie);
+	return ERR_PTR(err);
 }
 
 static void trie_free(struct bpf_map *map)
@@ -615,13 +648,17 @@ static void trie_free(struct bpf_map *map)
 				continue;
 			}
 
-			kfree(node);
+			/* No bpf program may access the map, so freeing the
+			 * node without waiting for the extra RCU GP.
+			 */
+			bpf_mem_cache_raw_free(node);
 			RCU_INIT_POINTER(*slot, NULL);
 			break;
 		}
 	}
 
 out:
+	bpf_mem_alloc_destroy(&trie->ma);
 	bpf_map_area_free(trie);
 }
 
@@ -633,7 +670,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)
 	struct lpm_trie_node **node_stack = NULL;
 	int err = 0, stack_ptr = -1;
 	unsigned int next_bit;
-	size_t matchlen;
+	size_t matchlen = 0;
 
 	/* The get_next_key follows postorder. For the 4 node example in
 	 * the top of this file, the trie_get_next_key() returns the following
@@ -672,7 +709,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)
 		next_bit = extract_bit(key->data, node->prefixlen);
 		node = rcu_dereference(node->child[next_bit]);
 	}
-	if (!node || node->prefixlen != key->prefixlen ||
+	if (!node || node->prefixlen != matchlen ||
 	    (node->flags & LPM_TREE_NODE_FLAG_IM))
 		goto find_leftmost;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1c4ebb326785..01fbef9576e0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1202,14 +1202,17 @@ static bool is_spilled_scalar_reg64(const struct bpf_stack_state *stack)
 /* Mark stack slot as STACK_MISC, unless it is already STACK_INVALID, in which
  * case they are equivalent, or it's STACK_ZERO, in which case we preserve
  * more precise STACK_ZERO.
- * Note, in uprivileged mode leaving STACK_INVALID is wrong, so we take
- * env->allow_ptr_leaks into account and force STACK_MISC, if necessary.
+ * Regardless of allow_ptr_leaks setting (i.e., privileged or unprivileged
+ * mode), we won't promote STACK_INVALID to STACK_MISC. In privileged case it is
+ * unnecessary as both are considered equivalent when loading data and pruning,
+ * in case of unprivileged mode it will be incorrect to allow reads of invalid
+ * slots.
  */
 static void mark_stack_slot_misc(struct bpf_verifier_env *env, u8 *stype)
 {
 	if (*stype == STACK_ZERO)
 		return;
-	if (env->allow_ptr_leaks && *stype == STACK_INVALID)
+	if (*stype == STACK_INVALID)
 		return;
 	*stype = STACK_MISC;
 }
@@ -4700,6 +4703,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 	 */
 	if (!env->allow_ptr_leaks &&
 	    is_spilled_reg(&state->stack[spi]) &&
+	    !is_spilled_scalar_reg(&state->stack[spi]) &&
 	    size != BPF_REG_SIZE) {
 		verbose(env, "attempt to corrupt spilled pointer on stack\n");
 		return -EACCES;
@@ -8071,7 +8075,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
 	if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) {
 		verbose(env,
 			"arg#%d expected pointer to stack or const struct bpf_dynptr\n",
-			regno);
+			regno - 1);
 		return -EINVAL;
 	}
 
@@ -8125,7 +8129,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
 		if (!is_dynptr_reg_valid_init(env, reg)) {
 			verbose(env,
 				"Expected an initialized dynptr as arg #%d\n",
-				regno);
+				regno - 1);
 			return -EINVAL;
 		}
 
@@ -8133,7 +8137,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
 		if (!is_dynptr_type_expected(env, reg, arg_type & ~MEM_RDONLY)) {
 			verbose(env,
 				"Expected a dynptr of type %s as arg #%d\n",
-				dynptr_type_str(arg_to_dynptr_type(arg_type)), regno);
+				dynptr_type_str(arg_to_dynptr_type(arg_type)), regno - 1);
 			return -EINVAL;
 		}
 
@@ -8189,6 +8193,11 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
 	const struct btf_type *t;
 	int spi, err, i, nr_slots, btf_id;
 
+	if (reg->type != PTR_TO_STACK) {
+		verbose(env, "arg#%d expected pointer to an iterator on stack\n", regno - 1);
+		return -EINVAL;
+	}
+
 	/* For iter_{new,next,destroy} functions, btf_check_iter_kfuncs()
 	 * ensures struct convention, so we wouldn't need to do any BTF
 	 * validation here. But given iter state can be passed as a parameter
@@ -8197,7 +8206,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
 	 */
 	btf_id = btf_check_iter_arg(meta->btf, meta->func_proto, regno - 1);
 	if (btf_id < 0) {
-		verbose(env, "expected valid iter pointer as arg #%d\n", regno);
+		verbose(env, "expected valid iter pointer as arg #%d\n", regno - 1);
 		return -EINVAL;
 	}
 	t = btf_type_by_id(meta->btf, btf_id);
@@ -8207,7 +8216,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
 		/* bpf_iter_<type>_new() expects pointer to uninit iter state */
 		if (!is_iter_reg_valid_uninit(env, reg, nr_slots)) {
 			verbose(env, "expected uninitialized iter_%s as arg #%d\n",
-				iter_type_str(meta->btf, btf_id), regno);
+				iter_type_str(meta->btf, btf_id), regno - 1);
 			return -EINVAL;
 		}
 
@@ -8231,7 +8240,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
 			break;
 		case -EINVAL:
 			verbose(env, "expected an initialized iter_%s as arg #%d\n",
-				iter_type_str(meta->btf, btf_id), regno);
+				iter_type_str(meta->btf, btf_id), regno - 1);
 			return err;
 		case -EPROTO:
 			verbose(env, "expected an RCU CS when using %s\n", meta->func_name);
diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h
index 618ce1fe870e..99b32e728c4a 100644
--- a/kernel/futex/futex.h
+++ b/kernel/futex/futex.h
@@ -265,11 +265,11 @@ static __always_inline int futex_read_inatomic(u32 *dest, u32 __user *from)
 	else if (!user_read_access_begin(from, sizeof(*from)))
 		return -EFAULT;
 	unsafe_get_user(val, from, Efault);
-	user_access_end();
+	user_read_access_end();
 	*dest = val;
 	return 0;
 Efault:
-	user_access_end();
+	user_read_access_end();
 	return -EFAULT;
 }
 
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index f36c33bd2da4..8e29809de38d 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -501,17 +501,18 @@ int show_interrupts(struct seq_file *p, void *v)
 
 		seq_put_decimal_ull_width(p, " ", cnt, 10);
 	}
+	seq_putc(p, ' ');
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	if (desc->irq_data.chip) {
 		if (desc->irq_data.chip->irq_print_chip)
 			desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
 		else if (desc->irq_data.chip->name)
-			seq_printf(p, " %8s", desc->irq_data.chip->name);
+			seq_printf(p, "%8s", desc->irq_data.chip->name);
 		else
-			seq_printf(p, " %8s", "-");
+			seq_printf(p, "%8s", "-");
 	} else {
-		seq_printf(p, " %8s", "None");
+		seq_printf(p, "%8s", "None");
 	}
 	if (desc->irq_data.domain)
 		seq_printf(p, " %*lu", prec, desc->irq_data.hwirq);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index ac1365afcc4a..e858de203eb6 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1248,10 +1248,7 @@ static int __sched task_blocks_on_rt_mutex(struct rt_mutex_base *lock,
 
 		/* Check whether the waiter should back out immediately */
 		rtm = container_of(lock, struct rt_mutex, rtmutex);
-		preempt_disable();
 		res = __ww_mutex_add_waiter(waiter, rtm, ww_ctx, wake_q);
-		wake_up_q(wake_q);
-		preempt_enable();
 		if (res) {
 			raw_spin_lock(&task->pi_lock);
 			rt_mutex_dequeue(lock, waiter);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 95e40895a519..c6d8232ad9ee 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1283,9 +1283,9 @@ static void nohz_csd_func(void *info)
 	WARN_ON(!(flags & NOHZ_KICK_MASK));
 
 	rq->idle_balance = idle_cpu(cpu);
-	if (rq->idle_balance && !need_resched()) {
+	if (rq->idle_balance) {
 		rq->nohz_idle_balance = flags;
-		raise_softirq_irqoff(SCHED_SOFTIRQ);
+		__raise_softirq_irqoff(SCHED_SOFTIRQ);
 	}
 }
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index d9d5a702f1a6..db47f33cb7d2 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -781,7 +781,7 @@ static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
 	 * If it is a deferred reservation, and the server
 	 * is not handling an starvation case, defer it.
 	 */
-	if (dl_se->dl_defer & !dl_se->dl_defer_running) {
+	if (dl_se->dl_defer && !dl_se->dl_defer_running) {
 		dl_se->dl_throttled = 1;
 		dl_se->dl_defer_armed = 1;
 	}
@@ -2042,6 +2042,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 	} else if (flags & ENQUEUE_REPLENISH) {
 		replenish_dl_entity(dl_se);
 	} else if ((flags & ENQUEUE_RESTORE) &&
+		   !is_dl_boosted(dl_se) &&
 		   dl_time_before(dl_se->deadline, rq_clock(rq_of_dl_se(dl_se)))) {
 		setup_new_dl_entity(dl_se);
 	}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fbdca89c677f..aa0238ee4857 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3399,10 +3399,16 @@ retry_pids:
 
 		/* Initialise new per-VMA NUMAB state. */
 		if (!vma->numab_state) {
-			vma->numab_state = kzalloc(sizeof(struct vma_numab_state),
-				GFP_KERNEL);
-			if (!vma->numab_state)
+			struct vma_numab_state *ptr;
+
+			ptr = kzalloc(sizeof(*ptr), GFP_KERNEL);
+			if (!ptr)
+				continue;
+
+			if (cmpxchg(&vma->numab_state, NULL, ptr)) {
+				kfree(ptr);
 				continue;
+			}
 
 			vma->numab_state->start_scan_seq = mm->numa_scan_seq;
 
@@ -12568,7 +12574,7 @@ static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags)
 		 * work being done for other CPUs. Next load
 		 * balancing owner will pick it up.
 		 */
-		if (need_resched()) {
+		if (!idle_cpu(this_cpu) && need_resched()) {
 			if (flags & NOHZ_STATS_KICK)
 				has_blocked_load = true;
 			if (flags & NOHZ_NEXT_KICK)
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 0d71fcbaf1e3..ff0e5ab4e37c 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -1200,7 +1200,7 @@ int __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
 			bool empty = !cpumask_and(new_mask, new_mask,
 						  ctx->user_mask);
 
-			if (WARN_ON_ONCE(empty))
+			if (empty)
 				cpumask_copy(new_mask, cpus_allowed);
 		}
 		__set_cpus_allowed_ptr(p, ctx);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 8b41bd13cc3d..4dae6ac2e83f 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -280,17 +280,24 @@ static inline void invoke_softirq(void)
 		wakeup_softirqd();
 }
 
+#define SCHED_SOFTIRQ_MASK	BIT(SCHED_SOFTIRQ)
+
 /*
  * flush_smp_call_function_queue() can raise a soft interrupt in a function
- * call. On RT kernels this is undesired and the only known functionality
- * in the block layer which does this is disabled on RT. If soft interrupts
- * get raised which haven't been raised before the flush, warn so it can be
+ * call. On RT kernels this is undesired and the only known functionalities
+ * are in the block layer which is disabled on RT, and in the scheduler for
+ * idle load balancing. If soft interrupts get raised which haven't been
+ * raised before the flush, warn if it is not a SCHED_SOFTIRQ so it can be
  * investigated.
  */
 void do_softirq_post_smp_call_flush(unsigned int was_pending)
 {
-	if (WARN_ON_ONCE(was_pending != local_softirq_pending()))
+	unsigned int is_pending = local_softirq_pending();
+
+	if (unlikely(was_pending != is_pending)) {
+		WARN_ON_ONCE(was_pending != (is_pending & ~SCHED_SOFTIRQ_MASK));
 		invoke_softirq();
+	}
 }
 
 #else /* CONFIG_PREEMPT_RT */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index aab6472853fa..7304d7cf47f2 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -24,7 +24,7 @@ static void clocksource_enqueue(struct clocksource *cs);
 
 static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end)
 {
-	u64 delta = clocksource_delta(end, start, cs->mask);
+	u64 delta = clocksource_delta(end, start, cs->mask, cs->max_raw_delta);
 
 	if (likely(delta < cs->max_cycles))
 		return clocksource_cyc2ns(delta, cs->mult, cs->shift);
@@ -993,6 +993,15 @@ static inline void clocksource_update_max_deferment(struct clocksource *cs)
 	cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift,
 						cs->maxadj, cs->mask,
 						&cs->max_cycles);
+
+	/*
+	 * Threshold for detecting negative motion in clocksource_delta().
+	 *
+	 * Allow for 0.875 of the counter width so that overly long idle
+	 * sleeps, which go slightly over mask/2, do not trigger the
+	 * negative motion detection.
+	 */
+	cs->max_raw_delta = (cs->mask >> 1) + (cs->mask >> 2) + (cs->mask >> 3);
 }
 
 static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 0ca85ff4fbb4..3d128825d343 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -755,7 +755,8 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 	u64 cycle_now, delta;
 
 	cycle_now = tk_clock_read(&tk->tkr_mono);
-	delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
+	delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
+				  tk->tkr_mono.clock->max_raw_delta);
 	tk->tkr_mono.cycle_last = cycle_now;
 	tk->tkr_raw.cycle_last  = cycle_now;
 
@@ -2230,7 +2231,8 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode)
 		return false;
 
 	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
-				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
+				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask,
+				   tk->tkr_mono.clock->max_raw_delta);
 
 	/* Check if there's really nothing to do */
 	if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index 63e600e943a7..8c9079108ffb 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -30,15 +30,15 @@ static inline void timekeeping_inc_mg_floor_swaps(void)
 
 #endif
 
-static inline u64 clocksource_delta(u64 now, u64 last, u64 mask)
+static inline u64 clocksource_delta(u64 now, u64 last, u64 mask, u64 max_delta)
 {
 	u64 ret = (now - last) & mask;
 
 	/*
-	 * Prevent time going backwards by checking the MSB of mask in
-	 * the result. If set, return 0.
+	 * Prevent time going backwards by checking the result against
+	 * @max_delta. If greater, return 0.
 	 */
-	return ret & ~(mask >> 1) ? 0 : ret;
+	return ret > max_delta ? 0 : ret;
 }
 
 /* Semi public for serialization of non timekeeper VDSO updates. */
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index ebda68ee9abf..be8be0c1aaf0 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -963,6 +963,11 @@ static int __trace_eprobe_create(int argc, const char *argv[])
 		goto error;
 	}
 	ret = dyn_event_add(&ep->devent, &ep->tp.event->call);
+	if (ret < 0) {
+		trace_probe_unregister_event_call(&ep->tp);
+		mutex_unlock(&event_mutex);
+		goto error;
+	}
 	mutex_unlock(&event_mutex);
 	return ret;
 parse_error: