Merge remote-tracking branch 'net-next/master' into mac80211-next

Bring in net-next which had pulled in net, so I have the changes
from mac80211 and can apply a patch that would otherwise conflict.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>

14 files changed, 921 insertions, 332 deletions

diff --git a/lib/dma-direct.c b/lib/dma-direct.c
index c0bba30fef0a..bbfb229aa067 100644
--- a/lib/dma-direct.c
+++ b/lib/dma-direct.c
@@ -84,7 +84,8 @@ again:
 		__free_pages(page, page_order);
 		page = NULL;
 
-		if (dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
+		if (IS_ENABLED(CONFIG_ZONE_DMA) &&
+		    dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
 		    !(gfp & GFP_DMA)) {
 			gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
 			goto again;
diff --git a/lib/errseq.c b/lib/errseq.c
index df782418b333..81f9e33aa7e7 100644
--- a/lib/errseq.c
+++ b/lib/errseq.c
@@ -111,27 +111,22 @@ EXPORT_SYMBOL(errseq_set);
  * errseq_sample() - Grab current errseq_t value.
  * @eseq: Pointer to errseq_t to be sampled.
  *
- * This function allows callers to sample an errseq_t value, marking it as
- * "seen" if required.
+ * This function allows callers to initialise their errseq_t variable.
+ * If the error has been "seen", new callers will not see an old error.
+ * If there is an unseen error in @eseq, the caller of this function will
+ * see it the next time it checks for an error.
  *
+ * Context: Any context.
  * Return: The current errseq value.
  */
 errseq_t errseq_sample(errseq_t *eseq)
 {
 	errseq_t old = READ_ONCE(*eseq);
-	errseq_t new = old;
 
-	/*
-	 * For the common case of no errors ever having been set, we can skip
-	 * marking the SEEN bit. Once an error has been set, the value will
-	 * never go back to zero.
-	 */
-	if (old != 0) {
-		new |= ERRSEQ_SEEN;
-		if (old != new)
-			cmpxchg(eseq, old, new);
-	}
-	return new;
+	/* If nobody has seen this error yet, then we can be the first. */
+	if (!(old & ERRSEQ_SEEN))
+		old = 0;
+	return old;
 }
 EXPORT_SYMBOL(errseq_sample);
 
diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c
index 5985a25e6cbc..5367ffa5c18f 100644
--- a/lib/find_bit_benchmark.c
+++ b/lib/find_bit_benchmark.c
@@ -132,7 +132,12 @@ static int __init find_bit_test(void)
 	test_find_next_bit(bitmap, BITMAP_LEN);
 	test_find_next_zero_bit(bitmap, BITMAP_LEN);
 	test_find_last_bit(bitmap, BITMAP_LEN);
-	test_find_first_bit(bitmap, BITMAP_LEN);
+
+	/*
+	 * test_find_first_bit() may take some time, so
+	 * traverse only part of bitmap to avoid soft lockup.
+	 */
+	test_find_first_bit(bitmap, BITMAP_LEN / 10);
 	test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN);
 
 	pr_err("\nStart testing find_bit() with sparse bitmap\n");
diff --git a/lib/kobject.c b/lib/kobject.c
index e1d1f290bf35..18989b5b3b56 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -233,13 +233,12 @@ static int kobject_add_internal(struct kobject *kobj)
 
 		/* be noisy on error issues */
 		if (error == -EEXIST)
-			WARN(1,
-			     "%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n",
-			     __func__, kobject_name(kobj));
+			pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n",
+			       __func__, kobject_name(kobj));
 		else
-			WARN(1, "%s failed for %s (error: %d parent: %s)\n",
-			     __func__, kobject_name(kobj), error,
-			     parent ? kobject_name(parent) : "'none'");
+			pr_err("%s failed for %s (error: %d parent: %s)\n",
+			       __func__, kobject_name(kobj), error,
+			       parent ? kobject_name(parent) : "'none'");
 	} else
 		kobj->state_in_sysfs = 1;
 
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 15ea216a67ce..63d0816ab23b 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -22,6 +22,7 @@
 #include <linux/socket.h>
 #include <linux/skbuff.h>
 #include <linux/netlink.h>
+#include <linux/uidgid.h>
 #include <linux/uuid.h>
 #include <linux/ctype.h>
 #include <net/sock.h>
@@ -231,30 +232,6 @@ out:
 	return r;
 }
 
-#ifdef CONFIG_NET
-static int kobj_bcast_filter(struct sock *dsk, struct sk_buff *skb, void *data)
-{
-	struct kobject *kobj = data, *ksobj;
-	const struct kobj_ns_type_operations *ops;
-
-	ops = kobj_ns_ops(kobj);
-	if (!ops && kobj->kset) {
-		ksobj = &kobj->kset->kobj;
-		if (ksobj->parent != NULL)
-			ops = kobj_ns_ops(ksobj->parent);
-	}
-
-	if (ops && ops->netlink_ns && kobj->ktype->namespace) {
-		const void *sock_ns, *ns;
-		ns = kobj->ktype->namespace(kobj);
-		sock_ns = ops->netlink_ns(dsk);
-		return sock_ns != ns;
-	}
-
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_UEVENT_HELPER
 static int kobj_usermode_filter(struct kobject *kobj)
 {
@@ -296,15 +273,44 @@ static void cleanup_uevent_env(struct subprocess_info *info)
 }
 #endif
 
-static int kobject_uevent_net_broadcast(struct kobject *kobj,
-					struct kobj_uevent_env *env,
+#ifdef CONFIG_NET
+static struct sk_buff *alloc_uevent_skb(struct kobj_uevent_env *env,
 					const char *action_string,
 					const char *devpath)
 {
-	int retval = 0;
-#if defined(CONFIG_NET)
+	struct netlink_skb_parms *parms;
+	struct sk_buff *skb = NULL;
+	char *scratch;
+	size_t len;
+
+	/* allocate message with maximum possible size */
+	len = strlen(action_string) + strlen(devpath) + 2;
+	skb = alloc_skb(len + env->buflen, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	/* add header */
+	scratch = skb_put(skb, len);
+	sprintf(scratch, "%s@%s", action_string, devpath);
+
+	skb_put_data(skb, env->buf, env->buflen);
+
+	parms = &NETLINK_CB(skb);
+	parms->creds.uid = GLOBAL_ROOT_UID;
+	parms->creds.gid = GLOBAL_ROOT_GID;
+	parms->dst_group = 1;
+	parms->portid = 0;
+
+	return skb;
+}
+
+static int uevent_net_broadcast_untagged(struct kobj_uevent_env *env,
+					 const char *action_string,
+					 const char *devpath)
+{
 	struct sk_buff *skb = NULL;
 	struct uevent_sock *ue_sk;
+	int retval = 0;
 
 	/* send netlink message */
 	list_for_each_entry(ue_sk, &uevent_sock_list, list) {
@@ -314,37 +320,99 @@ static int kobject_uevent_net_broadcast(struct kobject *kobj,
 			continue;
 
 		if (!skb) {
-			/* allocate message with the maximum possible size */
-			size_t len = strlen(action_string) + strlen(devpath) + 2;
-			char *scratch;
-
 			retval = -ENOMEM;
-			skb = alloc_skb(len + env->buflen, GFP_KERNEL);
+			skb = alloc_uevent_skb(env, action_string, devpath);
 			if (!skb)
 				continue;
-
-			/* add header */
-			scratch = skb_put(skb, len);
-			sprintf(scratch, "%s@%s", action_string, devpath);
-
-			skb_put_data(skb, env->buf, env->buflen);
-
-			NETLINK_CB(skb).dst_group = 1;
 		}
 
-		retval = netlink_broadcast_filtered(uevent_sock, skb_get(skb),
-						    0, 1, GFP_KERNEL,
-						    kobj_bcast_filter,
-						    kobj);
+		retval = netlink_broadcast(uevent_sock, skb_get(skb), 0, 1,
+					   GFP_KERNEL);
 		/* ENOBUFS should be handled in userspace */
 		if (retval == -ENOBUFS || retval == -ESRCH)
 			retval = 0;
 	}
 	consume_skb(skb);
-#endif
+
 	return retval;
 }
 
+static int uevent_net_broadcast_tagged(struct sock *usk,
+				       struct kobj_uevent_env *env,
+				       const char *action_string,
+				       const char *devpath)
+{
+	struct user_namespace *owning_user_ns = sock_net(usk)->user_ns;
+	struct sk_buff *skb = NULL;
+	int ret = 0;
+
+	skb = alloc_uevent_skb(env, action_string, devpath);
+	if (!skb)
+		return -ENOMEM;
+
+	/* fix credentials */
+	if (owning_user_ns != &init_user_ns) {
+		struct netlink_skb_parms *parms = &NETLINK_CB(skb);
+		kuid_t root_uid;
+		kgid_t root_gid;
+
+		/* fix uid */
+		root_uid = make_kuid(owning_user_ns, 0);
+		if (uid_valid(root_uid))
+			parms->creds.uid = root_uid;
+
+		/* fix gid */
+		root_gid = make_kgid(owning_user_ns, 0);
+		if (gid_valid(root_gid))
+			parms->creds.gid = root_gid;
+	}
+
+	ret = netlink_broadcast(usk, skb, 0, 1, GFP_KERNEL);
+	/* ENOBUFS should be handled in userspace */
+	if (ret == -ENOBUFS || ret == -ESRCH)
+		ret = 0;
+
+	return ret;
+}
+#endif
+
+static int kobject_uevent_net_broadcast(struct kobject *kobj,
+					struct kobj_uevent_env *env,
+					const char *action_string,
+					const char *devpath)
+{
+	int ret = 0;
+
+#ifdef CONFIG_NET
+	const struct kobj_ns_type_operations *ops;
+	const struct net *net = NULL;
+
+	ops = kobj_ns_ops(kobj);
+	if (!ops && kobj->kset) {
+		struct kobject *ksobj = &kobj->kset->kobj;
+		if (ksobj->parent != NULL)
+			ops = kobj_ns_ops(ksobj->parent);
+	}
+
+	/* kobjects currently only carry network namespace tags and they
+	 * are the only tag relevant here since we want to decide which
+	 * network namespaces to broadcast the uevent into.
+	 */
+	if (ops && ops->netlink_ns && kobj->ktype->namespace)
+		if (ops->type == KOBJ_NS_TYPE_NET)
+			net = kobj->ktype->namespace(kobj);
+
+	if (!net)
+		ret = uevent_net_broadcast_untagged(env, action_string,
+						    devpath);
+	else
+		ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env,
+						  action_string, devpath);
+#endif
+
+	return ret;
+}
+
 static void zap_modalias_env(struct kobj_uevent_env *env)
 {
 	static const char modalias_prefix[] = "MODALIAS=";
@@ -703,9 +771,13 @@ static int uevent_net_init(struct net *net)
 
 	net->uevent_sock = ue_sk;
 
-	mutex_lock(&uevent_sock_mutex);
-	list_add_tail(&ue_sk->list, &uevent_sock_list);
-	mutex_unlock(&uevent_sock_mutex);
+	/* Restrict uevents to initial user namespace. */
+	if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) {
+		mutex_lock(&uevent_sock_mutex);
+		list_add_tail(&ue_sk->list, &uevent_sock_list);
+		mutex_unlock(&uevent_sock_mutex);
+	}
+
 	return 0;
 }
 
@@ -713,9 +785,11 @@ static void uevent_net_exit(struct net *net)
 {
 	struct uevent_sock *ue_sk = net->uevent_sock;
 
-	mutex_lock(&uevent_sock_mutex);
-	list_del(&ue_sk->list);
-	mutex_unlock(&uevent_sock_mutex);
+	if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) {
+		mutex_lock(&uevent_sock_mutex);
+		list_del(&ue_sk->list);
+		mutex_unlock(&uevent_sock_mutex);
+	}
 
 	netlink_kernel_release(ue_sk->sk);
 	kfree(ue_sk);
diff --git a/lib/lockref.c b/lib/lockref.c
index 47169ed7e964..3d468b53d4c9 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -81,6 +81,34 @@ int lockref_get_not_zero(struct lockref *lockref)
 EXPORT_SYMBOL(lockref_get_not_zero);
 
 /**
+ * lockref_put_not_zero - Decrements count unless count <= 1 before decrement
+ * @lockref: pointer to lockref structure
+ * Return: 1 if count updated successfully or 0 if count would become zero
+ */
+int lockref_put_not_zero(struct lockref *lockref)
+{
+	int retval;
+
+	CMPXCHG_LOOP(
+		new.count--;
+		if (old.count <= 1)
+			return 0;
+	,
+		return 1;
+	);
+
+	spin_lock(&lockref->lock);
+	retval = 0;
+	if (lockref->count > 1) {
+		lockref->count--;
+		retval = 1;
+	}
+	spin_unlock(&lockref->lock);
+	return retval;
+}
+EXPORT_SYMBOL(lockref_put_not_zero);
+
+/**
  * lockref_get_or_lock - Increments count unless the count is 0 or dead
  * @lockref: pointer to lockref structure
  * Return: 1 if count updated successfully or 0 if count was zero
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index da9e10c827df..43e0cbedc3a0 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1612,11 +1612,9 @@ static void set_iter_tags(struct radix_tree_iter *iter,
 static void __rcu **skip_siblings(struct radix_tree_node **nodep,
 			void __rcu **slot, struct radix_tree_iter *iter)
 {
-	void *sib = node_to_entry(slot - 1);
-
 	while (iter->index < iter->next_index) {
 		*nodep = rcu_dereference_raw(*slot);
-		if (*nodep && *nodep != sib)
+		if (*nodep && !is_sibling_entry(iter->node, *nodep))
 			return slot;
 		slot++;
 		iter->index = __radix_tree_iter_add(iter, 1);
@@ -1631,7 +1629,7 @@ void __rcu **__radix_tree_next_slot(void __rcu **slot,
 				struct radix_tree_iter *iter, unsigned flags)
 {
 	unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK;
-	struct radix_tree_node *node = rcu_dereference_raw(*slot);
+	struct radix_tree_node *node;
 
 	slot = skip_siblings(&node, slot, iter);
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 2b2b79974b61..9427b5766134 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -668,8 +668,9 @@ EXPORT_SYMBOL_GPL(rhashtable_insert_slow);
  * For a completely stable walk you should construct your own data
  * structure outside the hash table.
  *
- * This function may sleep so you must not call it from interrupt
- * context or with spin locks held.
+ * This function may be called from any process context, including
+ * non-preemptable context, but cannot be called from softirq or
+ * hardirq context.
  *
  * You must call rhashtable_walk_exit after this function returns.
  */
@@ -726,6 +727,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter)
 	__acquires(RCU)
 {
 	struct rhashtable *ht = iter->ht;
+	bool rhlist = ht->rhlist;
 
 	rcu_read_lock();
 
@@ -734,11 +736,52 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter)
 		list_del(&iter->walker.list);
 	spin_unlock(&ht->lock);
 
-	if (!iter->walker.tbl && !iter->end_of_table) {
+	if (iter->end_of_table)
+		return 0;
+	if (!iter->walker.tbl) {
 		iter->walker.tbl = rht_dereference_rcu(ht->tbl, ht);
+		iter->slot = 0;
+		iter->skip = 0;
 		return -EAGAIN;
 	}
 
+	if (iter->p && !rhlist) {
+		/*
+		 * We need to validate that 'p' is still in the table, and
+		 * if so, update 'skip'
+		 */
+		struct rhash_head *p;
+		int skip = 0;
+		rht_for_each_rcu(p, iter->walker.tbl, iter->slot) {
+			skip++;
+			if (p == iter->p) {
+				iter->skip = skip;
+				goto found;
+			}
+		}
+		iter->p = NULL;
+	} else if (iter->p && rhlist) {
+		/* Need to validate that 'list' is still in the table, and
+		 * if so, update 'skip' and 'p'.
+		 */
+		struct rhash_head *p;
+		struct rhlist_head *list;
+		int skip = 0;
+		rht_for_each_rcu(p, iter->walker.tbl, iter->slot) {
+			for (list = container_of(p, struct rhlist_head, rhead);
+			     list;
+			     list = rcu_dereference(list->next)) {
+				skip++;
+				if (list == iter->list) {
+					iter->p = p;
+					skip = skip;
+					goto found;
+				}
+			}
+		}
+		iter->p = NULL;
+	}
+found:
 	return 0;
 }
 EXPORT_SYMBOL_GPL(rhashtable_walk_start_check);
@@ -914,8 +957,6 @@ void rhashtable_walk_stop(struct rhashtable_iter *iter)
 		iter->walker.tbl = NULL;
 	spin_unlock(&ht->lock);
 
-	iter->p = NULL;
-
 out:
 	rcu_read_unlock();
 }
diff --git a/lib/sha256.c b/lib/sha256.c
new file mode 100644
index 000000000000..4400c832e2aa
--- /dev/null
+++ b/lib/sha256.c
@@ -0,0 +1,283 @@
+/*
+ * SHA-256, as specified in
+ * http://csrc.nist.gov/groups/STM/cavp/documents/shs/sha256-384-512.pdf
+ *
+ * SHA-256 code by Jean-Luc Cooke <jlcooke@certainkey.com>.
+ *
+ * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com>
+ * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
+ * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
+ * Copyright (c) 2014 Red Hat Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/bitops.h>
+#include <linux/sha256.h>
+#include <linux/string.h>
+#include <asm/byteorder.h>
+
+static inline u32 Ch(u32 x, u32 y, u32 z)
+{
+	return z ^ (x & (y ^ z));
+}
+
+static inline u32 Maj(u32 x, u32 y, u32 z)
+{
+	return (x & y) | (z & (x | y));
+}
+
+#define e0(x)       (ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22))
+#define e1(x)       (ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25))
+#define s0(x)       (ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3))
+#define s1(x)       (ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10))
+
+static inline void LOAD_OP(int I, u32 *W, const u8 *input)
+{
+	W[I] = __be32_to_cpu(((__be32 *)(input))[I]);
+}
+
+static inline void BLEND_OP(int I, u32 *W)
+{
+	W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16];
+}
+
+static void sha256_transform(u32 *state, const u8 *input)
+{
+	u32 a, b, c, d, e, f, g, h, t1, t2;
+	u32 W[64];
+	int i;
+
+	/* load the input */
+	for (i = 0; i < 16; i++)
+		LOAD_OP(i, W, input);
+
+	/* now blend */
+	for (i = 16; i < 64; i++)
+		BLEND_OP(i, W);
+
+	/* load the state into our registers */
+	a = state[0];  b = state[1];  c = state[2];  d = state[3];
+	e = state[4];  f = state[5];  g = state[6];  h = state[7];
+
+	/* now iterate */
+	t1 = h + e1(e) + Ch(e, f, g) + 0x428a2f98 + W[0];
+	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1 + t2;
+	t1 = g + e1(d) + Ch(d, e, f) + 0x71374491 + W[1];
+	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1 + t2;
+	t1 = f + e1(c) + Ch(c, d, e) + 0xb5c0fbcf + W[2];
+	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1 + t2;
+	t1 = e + e1(b) + Ch(b, c, d) + 0xe9b5dba5 + W[3];
+	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1 + t2;
+	t1 = d + e1(a) + Ch(a, b, c) + 0x3956c25b + W[4];
+	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1 + t2;
+	t1 = c + e1(h) + Ch(h, a, b) + 0x59f111f1 + W[5];
+	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1 + t2;
+	t1 = b + e1(g) + Ch(g, h, a) + 0x923f82a4 + W[6];
+	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1 + t2;
+	t1 = a + e1(f) + Ch(f, g, h) + 0xab1c5ed5 + W[7];
+	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1 + t2;
+
+	t1 = h + e1(e) + Ch(e, f, g) + 0xd807aa98 + W[8];
+	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1 + t2;
+	t1 = g + e1(d) + Ch(d, e, f) + 0x12835b01 + W[9];
+	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1 + t2;
+	t1 = f + e1(c) + Ch(c, d, e) + 0x243185be + W[10];
+	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1 + t2;
+	t1 = e + e1(b) + Ch(b, c, d) + 0x550c7dc3 + W[11];
+	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1 + t2;
+	t1 = d + e1(a) + Ch(a, b, c) + 0x72be5d74 + W[12];
+	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1 + t2;
+	t1 = c + e1(h) + Ch(h, a, b) + 0x80deb1fe + W[13];
+	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1 + t2;
+	t1 = b + e1(g) + Ch(g, h, a) + 0x9bdc06a7 + W[14];
+	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1 + t2;
+	t1 = a + e1(f) + Ch(f, g, h) + 0xc19bf174 + W[15];
+	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1+t2;
+
+	t1 = h + e1(e) + Ch(e, f, g) + 0xe49b69c1 + W[16];
+	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1+t2;
+	t1 = g + e1(d) + Ch(d, e, f) + 0xefbe4786 + W[17];
+	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1+t2;
+	t1 = f + e1(c) + Ch(c, d, e) + 0x0fc19dc6 + W[18];
+	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1+t2;
+	t1 = e + e1(b) + Ch(b, c, d) + 0x240ca1cc + W[19];
+	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1+t2;
+	t1 = d + e1(a) + Ch(a, b, c) + 0x2de92c6f + W[20];
+	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1+t2;
+	t1 = c + e1(h) + Ch(h, a, b) + 0x4a7484aa + W[21];
+	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1+t2;
+	t1 = b + e1(g) + Ch(g, h, a) + 0x5cb0a9dc + W[22];
+	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1+t2;
+	t1 = a + e1(f) + Ch(f, g, h) + 0x76f988da + W[23];
+	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1+t2;
+
+	t1 = h + e1(e) + Ch(e, f, g) + 0x983e5152 + W[24];
+	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1+t2;
+	t1 = g + e1(d) + Ch(d, e, f) + 0xa831c66d + W[25];
+	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1+t2;
+	t1 = f + e1(c) + Ch(c, d, e) + 0xb00327c8 + W[26];
+	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1+t2;
+	t1 = e + e1(b) + Ch(b, c, d) + 0xbf597fc7 + W[27];
+	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1+t2;
+	t1 = d + e1(a) + Ch(a, b, c) + 0xc6e00bf3 + W[28];
+	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1+t2;
+	t1 = c + e1(h) + Ch(h, a, b) + 0xd5a79147 + W[29];
+	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1+t2;
+	t1 = b + e1(g) + Ch(g, h, a) + 0x06ca6351 + W[30];
+	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1+t2;
+	t1 = a + e1(f) + Ch(f, g, h) + 0x14292967 + W[31];
+	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1+t2;
+
+	t1 = h + e1(e) + Ch(e, f, g) + 0x27b70a85 + W[32];
+	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1+t2;
+	t1 = g + e1(d) + Ch(d, e, f) + 0x2e1b2138 + W[33];
+	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1+t2;
+	t1 = f + e1(c) + Ch(c, d, e) + 0x4d2c6dfc + W[34];
+	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1+t2;
+	t1 = e + e1(b) + Ch(b, c, d) + 0x53380d13 + W[35];
+	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1+t2;
+	t1 = d + e1(a) + Ch(a, b, c) + 0x650a7354 + W[36];
+	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1+t2;
+	t1 = c + e1(h) + Ch(h, a, b) + 0x766a0abb + W[37];
+	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1+t2;
+	t1 = b + e1(g) + Ch(g, h, a) + 0x81c2c92e + W[38];
+	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1+t2;
+	t1 = a + e1(f) + Ch(f, g, h) + 0x92722c85 + W[39];
+	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1+t2;
+
+	t1 = h + e1(e) + Ch(e, f, g) + 0xa2bfe8a1 + W[40];
+	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1+t2;
+	t1 = g + e1(d) + Ch(d, e, f) + 0xa81a664b + W[41];
+	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1+t2;
+	t1 = f + e1(c) + Ch(c, d, e) + 0xc24b8b70 + W[42];
+	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1+t2;
+	t1 = e + e1(b) + Ch(b, c, d) + 0xc76c51a3 + W[43];
+	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1+t2;
+	t1 = d + e1(a) + Ch(a, b, c) + 0xd192e819 + W[44];
+	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1+t2;
+	t1 = c + e1(h) + Ch(h, a, b) + 0xd6990624 + W[45];
+	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1+t2;
+	t1 = b + e1(g) + Ch(g, h, a) + 0xf40e3585 + W[46];
+	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1+t2;
+	t1 = a + e1(f) + Ch(f, g, h) + 0x106aa070 + W[47];
+	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1+t2;
+
+	t1 = h + e1(e) + Ch(e, f, g) + 0x19a4c116 + W[48];
+	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1+t2;
+	t1 = g + e1(d) + Ch(d, e, f) + 0x1e376c08 + W[49];
+	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1+t2;
+	t1 = f + e1(c) + Ch(c, d, e) + 0x2748774c + W[50];
+	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1+t2;
+	t1 = e + e1(b) + Ch(b, c, d) + 0x34b0bcb5 + W[51];
+	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1+t2;
+	t1 = d + e1(a) + Ch(a, b, c) + 0x391c0cb3 + W[52];
+	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1+t2;
+	t1 = c + e1(h) + Ch(h, a, b) + 0x4ed8aa4a + W[53];
+	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1+t2;
+	t1 = b + e1(g) + Ch(g, h, a) + 0x5b9cca4f + W[54];
+	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1+t2;
+	t1 = a + e1(f) + Ch(f, g, h) + 0x682e6ff3 + W[55];
+	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1+t2;
+
+	t1 = h + e1(e) + Ch(e, f, g) + 0x748f82ee + W[56];
+	t2 = e0(a) + Maj(a, b, c);    d += t1;    h = t1+t2;
+	t1 = g + e1(d) + Ch(d, e, f) + 0x78a5636f + W[57];
+	t2 = e0(h) + Maj(h, a, b);    c += t1;    g = t1+t2;
+	t1 = f + e1(c) + Ch(c, d, e) + 0x84c87814 + W[58];
+	t2 = e0(g) + Maj(g, h, a);    b += t1;    f = t1+t2;
+	t1 = e + e1(b) + Ch(b, c, d) + 0x8cc70208 + W[59];
+	t2 = e0(f) + Maj(f, g, h);    a += t1;    e = t1+t2;
+	t1 = d + e1(a) + Ch(a, b, c) + 0x90befffa + W[60];
+	t2 = e0(e) + Maj(e, f, g);    h += t1;    d = t1+t2;
+	t1 = c + e1(h) + Ch(h, a, b) + 0xa4506ceb + W[61];
+	t2 = e0(d) + Maj(d, e, f);    g += t1;    c = t1+t2;
+	t1 = b + e1(g) + Ch(g, h, a) + 0xbef9a3f7 + W[62];
+	t2 = e0(c) + Maj(c, d, e);    f += t1;    b = t1+t2;
+	t1 = a + e1(f) + Ch(f, g, h) + 0xc67178f2 + W[63];
+	t2 = e0(b) + Maj(b, c, d);    e += t1;    a = t1+t2;
+
+	state[0] += a; state[1] += b; state[2] += c; state[3] += d;
+	state[4] += e; state[5] += f; state[6] += g; state[7] += h;
+
+	/* clear any sensitive info... */
+	a = b = c = d = e = f = g = h = t1 = t2 = 0;
+	memset(W, 0, 64 * sizeof(u32));
+}
+
+int sha256_init(struct sha256_state *sctx)
+{
+	sctx->state[0] = SHA256_H0;
+	sctx->state[1] = SHA256_H1;
+	sctx->state[2] = SHA256_H2;
+	sctx->state[3] = SHA256_H3;
+	sctx->state[4] = SHA256_H4;
+	sctx->state[5] = SHA256_H5;
+	sctx->state[6] = SHA256_H6;
+	sctx->state[7] = SHA256_H7;
+	sctx->count = 0;
+
+	return 0;
+}
+
+int sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len)
+{
+	unsigned int partial, done;
+	const u8 *src;
+
+	partial = sctx->count & 0x3f;
+	sctx->count += len;
+	done = 0;
+	src = data;
+
+	if ((partial + len) > 63) {
+		if (partial) {
+			done = -partial;
+			memcpy(sctx->buf + partial, data, done + 64);
+			src = sctx->buf;
+		}
+
+		do {
+			sha256_transform(sctx->state, src);
+			done += 64;
+			src = data + done;
+		} while (done + 63 < len);
+
+		partial = 0;
+	}
+	memcpy(sctx->buf + partial, src, len - done);
+
+	return 0;
+}
+
+int sha256_final(struct sha256_state *sctx, u8 *out)
+{
+	__be32 *dst = (__be32 *)out;
+	__be64 bits;
+	unsigned int index, pad_len;
+	int i;
+	static const u8 padding[64] = { 0x80, };
+
+	/* Save number of bits */
+	bits = cpu_to_be64(sctx->count << 3);
+
+	/* Pad out to 56 mod 64. */
+	index = sctx->count & 0x3f;
+	pad_len = (index < 56) ? (56 - index) : ((64+56) - index);
+	sha256_update(sctx, padding, pad_len);
+
+	/* Append length (before padding) */
+	sha256_update(sctx, (const u8 *)&bits, sizeof(bits));
+
+	/* Store state in digest */
+	for (i = 0; i < 8; i++)
+		dst[i] = cpu_to_be32(sctx->state[i]);
+
+	/* Zeroize sensitive information. */
+	memset(sctx, 0, sizeof(*sctx));
+
+	return 0;
+}
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index de7cc540450f..cc640588f145 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -714,7 +714,7 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
 
 	phys_addr = swiotlb_tbl_map_single(dev,
 			__phys_to_dma(dev, io_tlb_start),
-			0, size, DMA_FROM_DEVICE, 0);
+			0, size, DMA_FROM_DEVICE, attrs);
 	if (phys_addr == SWIOTLB_MAP_ERROR)
 		goto out_warn;
 
@@ -737,7 +737,7 @@ out_unmap:
 	swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
 			DMA_ATTR_SKIP_CPU_SYNC);
 out_warn:
-	if ((attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
+	if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
 		dev_warn(dev,
 			"swiotlb: coherent allocation failed, size=%zu\n",
 			size);
@@ -1087,6 +1087,6 @@ const struct dma_map_ops swiotlb_dma_ops = {
 	.unmap_sg		= swiotlb_unmap_sg_attrs,
 	.map_page		= swiotlb_map_page,
 	.unmap_page		= swiotlb_unmap_page,
-	.dma_supported		= swiotlb_dma_supported,
+	.dma_supported		= dma_direct_supported,
 };
 #endif /* CONFIG_DMA_DIRECT_OPS */
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index de16f7869fb1..6cd7d0740005 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -331,23 +331,32 @@ static void noinline __init test_mem_optimisations(void)
 	unsigned int start, nbits;
 
 	for (start = 0; start < 1024; start += 8) {
-		memset(bmap1, 0x5a, sizeof(bmap1));
-		memset(bmap2, 0x5a, sizeof(bmap2));
 		for (nbits = 0; nbits < 1024 - start; nbits += 8) {
+			memset(bmap1, 0x5a, sizeof(bmap1));
+			memset(bmap2, 0x5a, sizeof(bmap2));
+
 			bitmap_set(bmap1, start, nbits);
 			__bitmap_set(bmap2, start, nbits);
-			if (!bitmap_equal(bmap1, bmap2, 1024))
+			if (!bitmap_equal(bmap1, bmap2, 1024)) {
 				printk("set not equal %d %d\n", start, nbits);
-			if (!__bitmap_equal(bmap1, bmap2, 1024))
+				failed_tests++;
+			}
+			if (!__bitmap_equal(bmap1, bmap2, 1024)) {
 				printk("set not __equal %d %d\n", start, nbits);
+				failed_tests++;
+			}
 
 			bitmap_clear(bmap1, start, nbits);
 			__bitmap_clear(bmap2, start, nbits);
-			if (!bitmap_equal(bmap1, bmap2, 1024))
+			if (!bitmap_equal(bmap1, bmap2, 1024)) {
 				printk("clear not equal %d %d\n", start, nbits);
-			if (!__bitmap_equal(bmap1, bmap2, 1024))
+				failed_tests++;
+			}
+			if (!__bitmap_equal(bmap1, bmap2, 1024)) {
 				printk("clear not __equal %d %d\n", start,
 									nbits);
+				failed_tests++;
+			}
 		}
 	}
 }
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 8e157806df7a..317f231462d4 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -386,116 +386,6 @@ static int bpf_fill_ld_abs_get_processor_id(struct bpf_test *self)
 	return 0;
 }
 
-#define PUSH_CNT 68
-/* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
-static int bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
-{
-	unsigned int len = BPF_MAXINSNS;
-	struct bpf_insn *insn;
-	int i = 0, j, k = 0;
-
-	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
-	if (!insn)
-		return -ENOMEM;
-
-	insn[i++] = BPF_MOV64_REG(R6, R1);
-loop:
-	for (j = 0; j < PUSH_CNT; j++) {
-		insn[i++] = BPF_LD_ABS(BPF_B, 0);
-		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2);
-		i++;
-		insn[i++] = BPF_MOV64_REG(R1, R6);
-		insn[i++] = BPF_MOV64_IMM(R2, 1);
-		insn[i++] = BPF_MOV64_IMM(R3, 2);
-		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-					 bpf_skb_vlan_push_proto.func - __bpf_call_base);
-		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2);
-		i++;
-	}
-
-	for (j = 0; j < PUSH_CNT; j++) {
-		insn[i++] = BPF_LD_ABS(BPF_B, 0);
-		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2);
-		i++;
-		insn[i++] = BPF_MOV64_REG(R1, R6);
-		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-					 bpf_skb_vlan_pop_proto.func - __bpf_call_base);
-		insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2);
-		i++;
-	}
-	if (++k < 5)
-		goto loop;
-
-	for (; i < len - 1; i++)
-		insn[i] = BPF_ALU32_IMM(BPF_MOV, R0, 0xbef);
-
-	insn[len - 1] = BPF_EXIT_INSN();
-
-	self->u.ptr.insns = insn;
-	self->u.ptr.len = len;
-
-	return 0;
-}
-
-static int bpf_fill_ld_abs_vlan_push_pop2(struct bpf_test *self)
-{
-	struct bpf_insn *insn;
-
-	insn = kmalloc_array(16, sizeof(*insn), GFP_KERNEL);
-	if (!insn)
-		return -ENOMEM;
-
-	/* Due to func address being non-const, we need to
-	 * assemble this here.
-	 */
-	insn[0] = BPF_MOV64_REG(R6, R1);
-	insn[1] = BPF_LD_ABS(BPF_B, 0);
-	insn[2] = BPF_LD_ABS(BPF_H, 0);
-	insn[3] = BPF_LD_ABS(BPF_W, 0);
-	insn[4] = BPF_MOV64_REG(R7, R6);
-	insn[5] = BPF_MOV64_IMM(R6, 0);
-	insn[6] = BPF_MOV64_REG(R1, R7);
-	insn[7] = BPF_MOV64_IMM(R2, 1);
-	insn[8] = BPF_MOV64_IMM(R3, 2);
-	insn[9] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			       bpf_skb_vlan_push_proto.func - __bpf_call_base);
-	insn[10] = BPF_MOV64_REG(R6, R7);
-	insn[11] = BPF_LD_ABS(BPF_B, 0);
-	insn[12] = BPF_LD_ABS(BPF_H, 0);
-	insn[13] = BPF_LD_ABS(BPF_W, 0);
-	insn[14] = BPF_MOV64_IMM(R0, 42);
-	insn[15] = BPF_EXIT_INSN();
-
-	self->u.ptr.insns = insn;
-	self->u.ptr.len = 16;
-
-	return 0;
-}
-
-static int bpf_fill_jump_around_ld_abs(struct bpf_test *self)
-{
-	unsigned int len = BPF_MAXINSNS;
-	struct bpf_insn *insn;
-	int i = 0;
-
-	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
-	if (!insn)
-		return -ENOMEM;
-
-	insn[i++] = BPF_MOV64_REG(R6, R1);
-	insn[i++] = BPF_LD_ABS(BPF_B, 0);
-	insn[i] = BPF_JMP_IMM(BPF_JEQ, R0, 10, len - i - 2);
-	i++;
-	while (i < len - 1)
-		insn[i++] = BPF_LD_ABS(BPF_B, 1);
-	insn[i] = BPF_EXIT_INSN();
-
-	self->u.ptr.insns = insn;
-	self->u.ptr.len = len;
-
-	return 0;
-}
-
 static int __bpf_fill_stxdw(struct bpf_test *self, int size)
 {
 	unsigned int len = BPF_MAXINSNS;
@@ -1988,40 +1878,6 @@ static struct bpf_test tests[] = {
 		{ { 0, -1 } }
 	},
 	{
-		"INT: DIV + ABS",
-		.u.insns_int = {
-			BPF_ALU64_REG(BPF_MOV, R6, R1),
-			BPF_LD_ABS(BPF_B, 3),
-			BPF_ALU64_IMM(BPF_MOV, R2, 2),
-			BPF_ALU32_REG(BPF_DIV, R0, R2),
-			BPF_ALU64_REG(BPF_MOV, R8, R0),
-			BPF_LD_ABS(BPF_B, 4),
-			BPF_ALU64_REG(BPF_ADD, R8, R0),
-			BPF_LD_IND(BPF_B, R8, -70),
-			BPF_EXIT_INSN(),
-		},
-		INTERNAL,
-		{ 10, 20, 30, 40, 50 },
-		{ { 4, 0 }, { 5, 10 } }
-	},
-	{
-		/* This one doesn't go through verifier, but is just raw insn
-		 * as opposed to cBPF tests from here. Thus div by 0 tests are
-		 * done in test_verifier in BPF kselftests.
-		 */
-		"INT: DIV by -1",
-		.u.insns_int = {
-			BPF_ALU64_REG(BPF_MOV, R6, R1),
-			BPF_ALU64_IMM(BPF_MOV, R7, -1),
-			BPF_LD_ABS(BPF_B, 3),
-			BPF_ALU32_REG(BPF_DIV, R0, R7),
-			BPF_EXIT_INSN(),
-		},
-		INTERNAL,
-		{ 10, 20, 30, 40, 50 },
-		{ { 3, 0 }, { 4, 0 } }
-	},
-	{
 		"check: missing ret",
 		.u.insns = {
 			BPF_STMT(BPF_LD | BPF_IMM, 1),
@@ -2383,50 +2239,6 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 1 } }
 	},
-	{
-		"nmap reduced",
-		.u.insns_int = {
-			BPF_MOV64_REG(R6, R1),
-			BPF_LD_ABS(BPF_H, 12),
-			BPF_JMP_IMM(BPF_JNE, R0, 0x806, 28),
-			BPF_LD_ABS(BPF_H, 12),
-			BPF_JMP_IMM(BPF_JNE, R0, 0x806, 26),
-			BPF_MOV32_IMM(R0, 18),
-			BPF_STX_MEM(BPF_W, R10, R0, -64),
-			BPF_LDX_MEM(BPF_W, R7, R10, -64),
-			BPF_LD_IND(BPF_W, R7, 14),
-			BPF_STX_MEM(BPF_W, R10, R0, -60),
-			BPF_MOV32_IMM(R0, 280971478),
-			BPF_STX_MEM(BPF_W, R10, R0, -56),
-			BPF_LDX_MEM(BPF_W, R7, R10, -56),
-			BPF_LDX_MEM(BPF_W, R0, R10, -60),
-			BPF_ALU32_REG(BPF_SUB, R0, R7),
-			BPF_JMP_IMM(BPF_JNE, R0, 0, 15),
-			BPF_LD_ABS(BPF_H, 12),
-			BPF_JMP_IMM(BPF_JNE, R0, 0x806, 13),
-			BPF_MOV32_IMM(R0, 22),
-			BPF_STX_MEM(BPF_W, R10, R0, -56),
-			BPF_LDX_MEM(BPF_W, R7, R10, -56),
-			BPF_LD_IND(BPF_H, R7, 14),
-			BPF_STX_MEM(BPF_W, R10, R0, -52),
-			BPF_MOV32_IMM(R0, 17366),
-			BPF_STX_MEM(BPF_W, R10, R0, -48),
-			BPF_LDX_MEM(BPF_W, R7, R10, -48),
-			BPF_LDX_MEM(BPF_W, R0, R10, -52),
-			BPF_ALU32_REG(BPF_SUB, R0, R7),
-			BPF_JMP_IMM(BPF_JNE, R0, 0, 2),
-			BPF_MOV32_IMM(R0, 256),
-			BPF_EXIT_INSN(),
-			BPF_MOV32_IMM(R0, 0),
-			BPF_EXIT_INSN(),
-		},
-		INTERNAL,
-		{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0, 0,
-		  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-		  0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6},
-		{ { 38, 256 } },
-		.stack_depth = 64,
-	},
 	/* BPF_ALU | BPF_MOV | BPF_X */
 	{
 		"ALU_MOV_X: dst = 2",
@@ -5485,22 +5297,6 @@ static struct bpf_test tests[] = {
 		{ { 1, 0xbee } },
 		.fill_helper = bpf_fill_ld_abs_get_processor_id,
 	},
-	{
-		"BPF_MAXINSNS: ld_abs+vlan_push/pop",
-		{ },
-		INTERNAL,
-		{ 0x34 },
-		{ { ETH_HLEN, 0xbef } },
-		.fill_helper = bpf_fill_ld_abs_vlan_push_pop,
-	},
-	{
-		"BPF_MAXINSNS: jump around ld_abs",
-		{ },
-		INTERNAL,
-		{ 10, 11 },
-		{ { 2, 10 } },
-		.fill_helper = bpf_fill_jump_around_ld_abs,
-	},
 	/*
 	 * LD_IND / LD_ABS on fragmented SKBs
 	 */
@@ -5683,6 +5479,53 @@ static struct bpf_test tests[] = {
 		{ {0x40, 0x05 } },
 	},
 	{
+		"LD_IND byte positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xff } },
+	},
+	{
+		"LD_IND byte positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_IND byte negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, -0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 } },
+	},
+	{
+		"LD_IND byte negative offset, multiple calls",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3b),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 1),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 2),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 3),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 4),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x82 }, },
+	},
+	{
 		"LD_IND halfword positive offset",
 		.u.insns = {
 			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
@@ -5731,6 +5574,39 @@ static struct bpf_test tests[] = {
 		{ {0x40, 0x66cc } },
 	},
 	{
+		"LD_IND halfword positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3d),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xffff } },
+	},
+	{
+		"LD_IND halfword positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_IND halfword negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_H, -0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 } },
+	},
+	{
 		"LD_IND word positive offset",
 		.u.insns = {
 			BPF_STMT(BPF_LDX | BPF_IMM, 0x20),
@@ -5821,6 +5697,39 @@ static struct bpf_test tests[] = {
 		{ {0x40, 0x66cc77dd } },
 	},
 	{
+		"LD_IND word positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3b),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xffffffff } },
+	},
+	{
+		"LD_IND word positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_IND word negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0x3e),
+			BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 } },
+	},
+	{
 		"LD_ABS byte",
 		.u.insns = {
 			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x20),
@@ -5838,6 +5747,68 @@ static struct bpf_test tests[] = {
 		{ {0x40, 0xcc } },
 	},
 	{
+		"LD_ABS byte positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xff } },
+	},
+	{
+		"LD_ABS byte positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_ABS byte negative offset, out of bounds load",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, -1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_EXPECTED_FAIL,
+		.expected_errcode = -EINVAL,
+	},
+	{
+		"LD_ABS byte negative offset, in bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x82 }, },
+	},
+	{
+		"LD_ABS byte negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_ABS byte negative offset, multiple calls",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3c),
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3d),
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3e),
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x82 }, },
+	},
+	{
 		"LD_ABS halfword",
 		.u.insns = {
 			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x22),
@@ -5872,6 +5843,55 @@ static struct bpf_test tests[] = {
 		{ {0x40, 0x99ff } },
 	},
 	{
+		"LD_ABS halfword positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x3e),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xffff } },
+	},
+	{
+		"LD_ABS halfword positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_ABS halfword negative offset, out of bounds load",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, -1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_EXPECTED_FAIL,
+		.expected_errcode = -EINVAL,
+	},
+	{
+		"LD_ABS halfword negative offset, in bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, SKF_LL_OFF + 0x3e),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x1982 }, },
+	},
+	{
+		"LD_ABS halfword negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_H, SKF_LL_OFF + 0x3e),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
 		"LD_ABS word",
 		.u.insns = {
 			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x1c),
@@ -5939,6 +5959,140 @@ static struct bpf_test tests[] = {
 		},
 		{ {0x40, 0x88ee99ff } },
 	},
+	{
+		"LD_ABS word positive offset, all ff",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x3c),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0xff, [0x3d] = 0xff,  [0x3e] = 0xff, [0x3f] = 0xff },
+		{ {0x40, 0xffffffff } },
+	},
+	{
+		"LD_ABS word positive offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LD_ABS word negative offset, out of bounds load",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, -1),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC | FLAG_EXPECTED_FAIL,
+		.expected_errcode = -EINVAL,
+	},
+	{
+		"LD_ABS word negative offset, in bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, SKF_LL_OFF + 0x3c),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x25051982 }, },
+	},
+	{
+		"LD_ABS word negative offset, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_ABS | BPF_W, SKF_LL_OFF + 0x3c),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x3f, 0 }, },
+	},
+	{
+		"LDX_MSH standalone, preserved A",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0xffeebbaa }, },
+	},
+	{
+		"LDX_MSH standalone, preserved A 2",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0x175e9d63),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3d),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3e),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3f),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x175e9d63 }, },
+	},
+	{
+		"LDX_MSH standalone, test result 1",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x14 }, },
+	},
+	{
+		"LDX_MSH standalone, test result 2",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3e),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x24 }, },
+	},
+	{
+		"LDX_MSH standalone, negative offset",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, -1),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0 }, },
+	},
+	{
+		"LDX_MSH standalone, negative offset 2",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, SKF_LL_OFF + 0x3e),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0x24 }, },
+	},
+	{
+		"LDX_MSH standalone, out of bounds",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x40),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0x0),
+		},
+		CLASSIC,
+		{ [0x3c] = 0x25, [0x3d] = 0x05,  [0x3e] = 0x19, [0x3f] = 0x82 },
+		{ {0x40, 0 }, },
+	},
 	/*
 	 * verify that the interpreter or JIT correctly sets A and X
 	 * to 0.
@@ -6127,14 +6281,6 @@ static struct bpf_test tests[] = {
 		{},
 		{ {0x1, 0x42 } },
 	},
-	{
-		"LD_ABS with helper changing skb data",
-		{ },
-		INTERNAL,
-		{ 0x34 },
-		{ { ETH_HLEN, 42 } },
-		.fill_helper = bpf_fill_ld_abs_vlan_push_pop2,
-	},
 	/* Checking interpreter vs JIT wrt signed extended imms. */
 	{
 		"JNE signed compare, test 1",
diff --git a/lib/textsearch.c b/lib/textsearch.c
index 0b79908dfe89..5939549c0e7b 100644
--- a/lib/textsearch.c
+++ b/lib/textsearch.c
@@ -10,7 +10,10 @@
  * 		Pablo Neira Ayuso <pablo@netfilter.org>
  *
  * ==========================================================================
- *
+ */
+
+/**
+ * DOC: ts_intro
  * INTRODUCTION
  *
  *   The textsearch infrastructure provides text searching facilities for
@@ -19,7 +22,9 @@
  *
  * ARCHITECTURE
  *
- *      User
+ * .. code-block:: none
+ *
+ *     User
  *     +----------------+
  *     |        finish()|<--------------(6)-----------------+
  *     |get_next_block()|<--------------(5)---------------+ |
@@ -33,21 +38,21 @@
  *     |             (3)|----->| find()/next() |-----------+          |
  *     |             (7)|----->| destroy()     |----------------------+
  *     +----------------+      +---------------+
- *  
- *   (1) User configures a search by calling _prepare() specifying the
- *       search parameters such as the pattern and algorithm name.
+ *
+ *   (1) User configures a search by calling textsearch_prepare() specifying
+ *       the search parameters such as the pattern and algorithm name.
  *   (2) Core requests the algorithm to allocate and initialize a search
  *       configuration according to the specified parameters.
- *   (3) User starts the search(es) by calling _find() or _next() to
- *       fetch subsequent occurrences. A state variable is provided
- *       to the algorithm to store persistent variables.
+ *   (3) User starts the search(es) by calling textsearch_find() or
+ *       textsearch_next() to fetch subsequent occurrences. A state variable
+ *       is provided to the algorithm to store persistent variables.
  *   (4) Core eventually resets the search offset and forwards the find()
  *       request to the algorithm.
  *   (5) Algorithm calls get_next_block() provided by the user continuously
  *       to fetch the data to be searched in block by block.
  *   (6) Algorithm invokes finish() after the last call to get_next_block
  *       to clean up any leftovers from get_next_block. (Optional)
- *   (7) User destroys the configuration by calling _destroy().
+ *   (7) User destroys the configuration by calling textsearch_destroy().
  *   (8) Core notifies the algorithm to destroy algorithm specific
  *       allocations. (Optional)
  *
@@ -62,9 +67,10 @@
  *   amount of times and even in parallel as long as a separate struct
  *   ts_state variable is provided to every instance.
  *
- *   The actual search is performed by either calling textsearch_find_-
- *   continuous() for linear data or by providing an own get_next_block()
- *   implementation and calling textsearch_find(). Both functions return
+ *   The actual search is performed by either calling
+ *   textsearch_find_continuous() for linear data or by providing
+ *   an own get_next_block() implementation and
+ *   calling textsearch_find(). Both functions return
  *   the position of the first occurrence of the pattern or UINT_MAX if
  *   no match was found. Subsequent occurrences can be found by calling
  *   textsearch_next() regardless of the linearity of the data.
@@ -72,7 +78,7 @@
  *   Once you're done using a configuration it must be given back via
  *   textsearch_destroy.
  *
- * EXAMPLE
+ * EXAMPLE::
  *
  *   int pos;
  *   struct ts_config *conf;
@@ -87,13 +93,13 @@
  *       goto errout;
  *   }
  *
- *   pos = textsearch_find_continuous(conf, &state, example, strlen(example));
+ *   pos = textsearch_find_continuous(conf, \&state, example, strlen(example));
  *   if (pos != UINT_MAX)
- *       panic("Oh my god, dancing chickens at %d\n", pos);
+ *       panic("Oh my god, dancing chickens at \%d\n", pos);
  *
  *   textsearch_destroy(conf);
- * ==========================================================================
  */
+/* ========================================================================== */
 
 #include <linux/module.h>
 #include <linux/types.h>
@@ -225,7 +231,7 @@ static unsigned int get_linear_data(unsigned int consumed, const u8 **dst,
  *
  * Returns the position of first occurrence of the pattern or
  * %UINT_MAX if no occurrence was found.
- */ 
+ */
 unsigned int textsearch_find_continuous(struct ts_config *conf,
 					struct ts_state *state,
 					const void *data, unsigned int len)
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 30c0cb8cc9bc..23920c5ff728 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1669,19 +1669,22 @@ char *pointer_string(char *buf, char *end, const void *ptr,
 	return number(buf, end, (unsigned long int)ptr, spec);
 }
 
-static bool have_filled_random_ptr_key __read_mostly;
+static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key);
 static siphash_key_t ptr_key __read_mostly;
 
-static void fill_random_ptr_key(struct random_ready_callback *unused)
+static void enable_ptr_key_workfn(struct work_struct *work)
 {
 	get_random_bytes(&ptr_key, sizeof(ptr_key));
-	/*
-	 * have_filled_random_ptr_key==true is dependent on get_random_bytes().
-	 * ptr_to_id() needs to see have_filled_random_ptr_key==true
-	 * after get_random_bytes() returns.
-	 */
-	smp_mb();
-	WRITE_ONCE(have_filled_random_ptr_key, true);
+	/* Needs to run from preemptible context */
+	static_branch_disable(&not_filled_random_ptr_key);
+}
+
+static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn);
+
+static void fill_random_ptr_key(struct random_ready_callback *unused)
+{
+	/* This may be in an interrupt handler. */
+	queue_work(system_unbound_wq, &enable_ptr_key_work);
 }
 
 static struct random_ready_callback random_ready = {
@@ -1695,7 +1698,8 @@ static int __init initialize_ptr_random(void)
 	if (!ret) {
 		return 0;
 	} else if (ret == -EALREADY) {
-		fill_random_ptr_key(&random_ready);
+		/* This is in preemptible context */
+		enable_ptr_key_workfn(&enable_ptr_key_work);
 		return 0;
 	}
 
@@ -1709,7 +1713,7 @@ static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec)
 	unsigned long hashval;
 	const int default_width = 2 * sizeof(ptr);
 
-	if (unlikely(!have_filled_random_ptr_key)) {
+	if (static_branch_unlikely(&not_filled_random_ptr_key)) {
 		spec.field_width = default_width;
 		/* string length must be less than default_width */
 		return string(buf, end, "(ptrval)", spec);