Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 283 insertions, 112 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8d289697cc7a..7b3df0d518ab 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -257,16 +257,16 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	kmemcheck_annotate_variable(shinfo->destructor_arg);
 
 	if (flags & SKB_ALLOC_FCLONE) {
-		struct sk_buff *child = skb + 1;
-		atomic_t *fclone_ref = (atomic_t *) (child + 1);
+		struct sk_buff_fclones *fclones;
 
-		kmemcheck_annotate_bitfield(child, flags1);
-		kmemcheck_annotate_bitfield(child, flags2);
+		fclones = container_of(skb, struct sk_buff_fclones, skb1);
+
+		kmemcheck_annotate_bitfield(&fclones->skb2, flags1);
 		skb->fclone = SKB_FCLONE_ORIG;
-		atomic_set(fclone_ref, 1);
+		atomic_set(&fclones->fclone_ref, 1);
 
-		child->fclone = SKB_FCLONE_UNAVAILABLE;
-		child->pfmemalloc = pfmemalloc;
+		fclones->skb2.fclone = SKB_FCLONE_FREE;
+		fclones->skb2.pfmemalloc = pfmemalloc;
 	}
 out:
 	return skb;
@@ -491,32 +491,33 @@ static void skb_free_head(struct sk_buff *skb)
 
 static void skb_release_data(struct sk_buff *skb)
 {
-	if (!skb->cloned ||
-	    !atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
-			       &skb_shinfo(skb)->dataref)) {
-		if (skb_shinfo(skb)->nr_frags) {
-			int i;
-			for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
-				skb_frag_unref(skb, i);
-		}
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	int i;
 
-		/*
-		 * If skb buf is from userspace, we need to notify the caller
-		 * the lower device DMA has done;
-		 */
-		if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
-			struct ubuf_info *uarg;
+	if (skb->cloned &&
+	    atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
+			      &shinfo->dataref))
+		return;
 
-			uarg = skb_shinfo(skb)->destructor_arg;
-			if (uarg->callback)
-				uarg->callback(uarg, true);
-		}
+	for (i = 0; i < shinfo->nr_frags; i++)
+		__skb_frag_unref(&shinfo->frags[i]);
 
-		if (skb_has_frag_list(skb))
-			skb_drop_fraglist(skb);
+	/*
+	 * If skb buf is from userspace, we need to notify the caller
+	 * the lower device DMA has done;
+	 */
+	if (shinfo->tx_flags & SKBTX_DEV_ZEROCOPY) {
+		struct ubuf_info *uarg;
 
-		skb_free_head(skb);
+		uarg = shinfo->destructor_arg;
+		if (uarg->callback)
+			uarg->callback(uarg, true);
 	}
+
+	if (shinfo->frag_list)
+		kfree_skb_list(shinfo->frag_list);
+
+	skb_free_head(skb);
 }
 
 /*
@@ -524,8 +525,7 @@ static void skb_release_data(struct sk_buff *skb)
  */
 static void kfree_skbmem(struct sk_buff *skb)
 {
-	struct sk_buff *other;
-	atomic_t *fclone_ref;
+	struct sk_buff_fclones *fclones;
 
 	switch (skb->fclone) {
 	case SKB_FCLONE_UNAVAILABLE:
@@ -533,22 +533,28 @@ static void kfree_skbmem(struct sk_buff *skb)
 		break;
 
 	case SKB_FCLONE_ORIG:
-		fclone_ref = (atomic_t *) (skb + 2);
-		if (atomic_dec_and_test(fclone_ref))
-			kmem_cache_free(skbuff_fclone_cache, skb);
+		fclones = container_of(skb, struct sk_buff_fclones, skb1);
+		if (atomic_dec_and_test(&fclones->fclone_ref))
+			kmem_cache_free(skbuff_fclone_cache, fclones);
 		break;
 
 	case SKB_FCLONE_CLONE:
-		fclone_ref = (atomic_t *) (skb + 1);
-		other = skb - 1;
+		fclones = container_of(skb, struct sk_buff_fclones, skb2);
 
-		/* The clone portion is available for
-		 * fast-cloning again.
+		/* Warning : We must perform the atomic_dec_and_test() before
+		 * setting skb->fclone back to SKB_FCLONE_FREE, otherwise
+		 * skb_clone() could set clone_ref to 2 before our decrement.
+		 * Anyway, if we are going to free the structure, no need to
+		 * rewrite skb->fclone.
 		 */
-		skb->fclone = SKB_FCLONE_UNAVAILABLE;
-
-		if (atomic_dec_and_test(fclone_ref))
-			kmem_cache_free(skbuff_fclone_cache, other);
+		if (atomic_dec_and_test(&fclones->fclone_ref)) {
+			kmem_cache_free(skbuff_fclone_cache, fclones);
+		} else {
+			/* The clone portion is available for
+			 * fast-cloning again.
+			 */
+			skb->fclone = SKB_FCLONE_FREE;
+		}
 		break;
 	}
 }
@@ -566,7 +572,7 @@ static void skb_release_head_state(struct sk_buff *skb)
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	nf_conntrack_put(skb->nfct);
 #endif
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	nf_bridge_put(skb->nf_bridge);
 #endif
 /* XXX: IS this still necessary? - JHS */
@@ -674,57 +680,61 @@ void consume_skb(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(consume_skb);
 
+/* Make sure a field is enclosed inside headers_start/headers_end section */
+#define CHECK_SKB_FIELD(field) \
+	BUILD_BUG_ON(offsetof(struct sk_buff, field) <		\
+		     offsetof(struct sk_buff, headers_start));	\
+	BUILD_BUG_ON(offsetof(struct sk_buff, field) >		\
+		     offsetof(struct sk_buff, headers_end));	\
+
 static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 {
 	new->tstamp		= old->tstamp;
+	/* We do not copy old->sk */
 	new->dev		= old->dev;
-	new->transport_header	= old->transport_header;
-	new->network_header	= old->network_header;
-	new->mac_header		= old->mac_header;
-	new->inner_protocol	= old->inner_protocol;
-	new->inner_transport_header = old->inner_transport_header;
-	new->inner_network_header = old->inner_network_header;
-	new->inner_mac_header = old->inner_mac_header;
+	memcpy(new->cb, old->cb, sizeof(old->cb));
 	skb_dst_copy(new, old);
-	skb_copy_hash(new, old);
-	new->ooo_okay		= old->ooo_okay;
-	new->no_fcs		= old->no_fcs;
-	new->encapsulation	= old->encapsulation;
-	new->encap_hdr_csum	= old->encap_hdr_csum;
-	new->csum_valid		= old->csum_valid;
-	new->csum_complete_sw	= old->csum_complete_sw;
 #ifdef CONFIG_XFRM
 	new->sp			= secpath_get(old->sp);
 #endif
-	memcpy(new->cb, old->cb, sizeof(old->cb));
-	new->csum		= old->csum;
-	new->ignore_df		= old->ignore_df;
-	new->pkt_type		= old->pkt_type;
-	new->ip_summed		= old->ip_summed;
-	skb_copy_queue_mapping(new, old);
-	new->priority		= old->priority;
-#if IS_ENABLED(CONFIG_IP_VS)
-	new->ipvs_property	= old->ipvs_property;
+	__nf_copy(new, old, false);
+
+	/* Note : this field could be in headers_start/headers_end section
+	 * It is not yet because we do not want to have a 16 bit hole
+	 */
+	new->queue_mapping = old->queue_mapping;
+
+	memcpy(&new->headers_start, &old->headers_start,
+	       offsetof(struct sk_buff, headers_end) -
+	       offsetof(struct sk_buff, headers_start));
+	CHECK_SKB_FIELD(protocol);
+	CHECK_SKB_FIELD(csum);
+	CHECK_SKB_FIELD(hash);
+	CHECK_SKB_FIELD(priority);
+	CHECK_SKB_FIELD(skb_iif);
+	CHECK_SKB_FIELD(vlan_proto);
+	CHECK_SKB_FIELD(vlan_tci);
+	CHECK_SKB_FIELD(transport_header);
+	CHECK_SKB_FIELD(network_header);
+	CHECK_SKB_FIELD(mac_header);
+	CHECK_SKB_FIELD(inner_protocol);
+	CHECK_SKB_FIELD(inner_transport_header);
+	CHECK_SKB_FIELD(inner_network_header);
+	CHECK_SKB_FIELD(inner_mac_header);
+	CHECK_SKB_FIELD(mark);
+#ifdef CONFIG_NETWORK_SECMARK
+	CHECK_SKB_FIELD(secmark);
+#endif
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	CHECK_SKB_FIELD(napi_id);
 #endif
-	new->pfmemalloc		= old->pfmemalloc;
-	new->protocol		= old->protocol;
-	new->mark		= old->mark;
-	new->skb_iif		= old->skb_iif;
-	__nf_copy(new, old);
 #ifdef CONFIG_NET_SCHED
-	new->tc_index		= old->tc_index;
+	CHECK_SKB_FIELD(tc_index);
 #ifdef CONFIG_NET_CLS_ACT
-	new->tc_verd		= old->tc_verd;
+	CHECK_SKB_FIELD(tc_verd);
 #endif
 #endif
-	new->vlan_proto		= old->vlan_proto;
-	new->vlan_tci		= old->vlan_tci;
 
-	skb_copy_secmark(new, old);
-
-#ifdef CONFIG_NET_RX_BUSY_POLL
-	new->napi_id	= old->napi_id;
-#endif
 }
 
 /*
@@ -855,17 +865,22 @@ EXPORT_SYMBOL_GPL(skb_copy_ubufs);
 
 struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 {
-	struct sk_buff *n;
+	struct sk_buff_fclones *fclones = container_of(skb,
+						       struct sk_buff_fclones,
+						       skb1);
+	struct sk_buff *n = &fclones->skb2;
 
 	if (skb_orphan_frags(skb, gfp_mask))
 		return NULL;
 
-	n = skb + 1;
 	if (skb->fclone == SKB_FCLONE_ORIG &&
-	    n->fclone == SKB_FCLONE_UNAVAILABLE) {
-		atomic_t *fclone_ref = (atomic_t *) (n + 1);
+	    n->fclone == SKB_FCLONE_FREE) {
 		n->fclone = SKB_FCLONE_CLONE;
-		atomic_inc(fclone_ref);
+		/* As our fastclone was free, clone_ref must be 1 at this point.
+		 * We could use atomic_inc() here, but it is faster
+		 * to set the final value.
+		 */
+		atomic_set(&fclones->fclone_ref, 2);
 	} else {
 		if (skb_pfmemalloc(skb))
 			gfp_mask |= __GFP_MEMALLOC;
@@ -875,7 +890,6 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 			return NULL;
 
 		kmemcheck_annotate_bitfield(n, flags1);
-		kmemcheck_annotate_bitfield(n, flags2);
 		n->fclone = SKB_FCLONE_UNAVAILABLE;
 	}
 
@@ -3069,6 +3083,11 @@ perform_csum_check:
 		}
 	} while ((offset += len) < head_skb->len);
 
+	/* Some callers want to get the end of the list.
+	 * Put it in segs->prev to avoid walking the list.
+	 * (see validate_xmit_skb_list() for example)
+	 */
+	segs->prev = tail;
 	return segs;
 
 err:
@@ -3182,7 +3201,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	skb_shinfo(nskb)->frag_list = p;
 	skb_shinfo(nskb)->gso_size = pinfo->gso_size;
 	pinfo->gso_size = 0;
-	skb_header_release(p);
+	__skb_header_release(p);
 	NAPI_GRO_CB(nskb)->last = p;
 
 	nskb->data_len += p->len;
@@ -3214,7 +3233,7 @@ merge:
 	else
 		NAPI_GRO_CB(p)->last->next = skb;
 	NAPI_GRO_CB(p)->last = skb;
-	skb_header_release(skb);
+	__skb_header_release(skb);
 	lp = p;
 
 done:
@@ -3230,7 +3249,6 @@ done:
 	NAPI_GRO_CB(skb)->same_flow = 1;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(skb_gro_receive);
 
 void __init skb_init(void)
 {
@@ -3240,8 +3258,7 @@ void __init skb_init(void)
 					      SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 					      NULL);
 	skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache",
-						(2*sizeof(struct sk_buff)) +
-						sizeof(atomic_t),
+						sizeof(struct sk_buff_fclones),
 						0,
 						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 						NULL);
@@ -3494,32 +3511,66 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sock_queue_err_skb);
 
-void __skb_tstamp_tx(struct sk_buff *orig_skb,
-		     struct skb_shared_hwtstamps *hwtstamps,
-		     struct sock *sk, int tstype)
+struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
 {
-	struct sock_exterr_skb *serr;
-	struct sk_buff *skb;
-	int err;
+	struct sk_buff_head *q = &sk->sk_error_queue;
+	struct sk_buff *skb, *skb_next;
+	int err = 0;
 
-	if (!sk)
-		return;
+	spin_lock_bh(&q->lock);
+	skb = __skb_dequeue(q);
+	if (skb && (skb_next = skb_peek(q)))
+		err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
+	spin_unlock_bh(&q->lock);
 
-	if (hwtstamps) {
-		*skb_hwtstamps(orig_skb) =
-			*hwtstamps;
-	} else {
-		/*
-		 * no hardware time stamps available,
-		 * so keep the shared tx_flags and only
-		 * store software time stamp
-		 */
-		orig_skb->tstamp = ktime_get_real();
+	sk->sk_err = err;
+	if (err)
+		sk->sk_error_report(sk);
+
+	return skb;
+}
+EXPORT_SYMBOL(sock_dequeue_err_skb);
+
+/**
+ * skb_clone_sk - create clone of skb, and take reference to socket
+ * @skb: the skb to clone
+ *
+ * This function creates a clone of a buffer that holds a reference on
+ * sk_refcnt.  Buffers created via this function are meant to be
+ * returned using sock_queue_err_skb, or free via kfree_skb.
+ *
+ * When passing buffers allocated with this function to sock_queue_err_skb
+ * it is necessary to wrap the call with sock_hold/sock_put in order to
+ * prevent the socket from being released prior to being enqueued on
+ * the sk_error_queue.
+ */
+struct sk_buff *skb_clone_sk(struct sk_buff *skb)
+{
+	struct sock *sk = skb->sk;
+	struct sk_buff *clone;
+
+	if (!sk || !atomic_inc_not_zero(&sk->sk_refcnt))
+		return NULL;
+
+	clone = skb_clone(skb, GFP_ATOMIC);
+	if (!clone) {
+		sock_put(sk);
+		return NULL;
 	}
 
-	skb = skb_clone(orig_skb, GFP_ATOMIC);
-	if (!skb)
-		return;
+	clone->sk = sk;
+	clone->destructor = sock_efree;
+
+	return clone;
+}
+EXPORT_SYMBOL(skb_clone_sk);
+
+static void __skb_complete_tx_timestamp(struct sk_buff *skb,
+					struct sock *sk,
+					int tstype)
+{
+	struct sock_exterr_skb *serr;
+	int err;
 
 	serr = SKB_EXT_ERR(skb);
 	memset(serr, 0, sizeof(*serr));
@@ -3537,6 +3588,42 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	if (err)
 		kfree_skb(skb);
 }
+
+void skb_complete_tx_timestamp(struct sk_buff *skb,
+			       struct skb_shared_hwtstamps *hwtstamps)
+{
+	struct sock *sk = skb->sk;
+
+	/* take a reference to prevent skb_orphan() from freeing the socket */
+	sock_hold(sk);
+
+	*skb_hwtstamps(skb) = *hwtstamps;
+	__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND);
+
+	sock_put(sk);
+}
+EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
+
+void __skb_tstamp_tx(struct sk_buff *orig_skb,
+		     struct skb_shared_hwtstamps *hwtstamps,
+		     struct sock *sk, int tstype)
+{
+	struct sk_buff *skb;
+
+	if (!sk)
+		return;
+
+	if (hwtstamps)
+		*skb_hwtstamps(orig_skb) = *hwtstamps;
+	else
+		orig_skb->tstamp = ktime_get_real();
+
+	skb = skb_clone(orig_skb, GFP_ATOMIC);
+	if (!skb)
+		return;
+
+	__skb_complete_tx_timestamp(skb, sk, tstype);
+}
 EXPORT_SYMBOL_GPL(__skb_tstamp_tx);
 
 void skb_tstamp_tx(struct sk_buff *orig_skb,
@@ -3561,9 +3648,14 @@ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked)
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TXSTATUS;
 
+	/* take a reference to prevent skb_orphan() from freeing the socket */
+	sock_hold(sk);
+
 	err = sock_queue_err_skb(sk, skb);
 	if (err)
 		kfree_skb(skb);
+
+	sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(skb_complete_wifi_ack);
 
@@ -3864,7 +3956,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 		return false;
 
 	if (len <= skb_tailroom(to)) {
-		BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));
+		if (len)
+			BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));
 		*delta_truesize = 0;
 		return true;
 	}
@@ -4029,3 +4122,81 @@ err_free:
 	return NULL;
 }
 EXPORT_SYMBOL(skb_vlan_untag);
+
+/**
+ * alloc_skb_with_frags - allocate skb with page frags
+ *
+ * header_len: size of linear part
+ * data_len: needed length in frags
+ * max_page_order: max page order desired.
+ * errcode: pointer to error code if any
+ * gfp_mask: allocation mask
+ *
+ * This can be used to allocate a paged skb, given a maximal order for frags.
+ */
+struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
+				     unsigned long data_len,
+				     int max_page_order,
+				     int *errcode,
+				     gfp_t gfp_mask)
+{
+	int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
+	unsigned long chunk;
+	struct sk_buff *skb;
+	struct page *page;
+	gfp_t gfp_head;
+	int i;
+
+	*errcode = -EMSGSIZE;
+	/* Note this test could be relaxed, if we succeed to allocate
+	 * high order pages...
+	 */
+	if (npages > MAX_SKB_FRAGS)
+		return NULL;
+
+	gfp_head = gfp_mask;
+	if (gfp_head & __GFP_WAIT)
+		gfp_head |= __GFP_REPEAT;
+
+	*errcode = -ENOBUFS;
+	skb = alloc_skb(header_len, gfp_head);
+	if (!skb)
+		return NULL;
+
+	skb->truesize += npages << PAGE_SHIFT;
+
+	for (i = 0; npages > 0; i++) {
+		int order = max_page_order;
+
+		while (order) {
+			if (npages >= 1 << order) {
+				page = alloc_pages(gfp_mask |
+						   __GFP_COMP |
+						   __GFP_NOWARN |
+						   __GFP_NORETRY,
+						   order);
+				if (page)
+					goto fill_page;
+				/* Do not retry other high order allocations */
+				order = 1;
+				max_page_order = 0;
+			}
+			order--;
+		}
+		page = alloc_page(gfp_mask);
+		if (!page)
+			goto failure;
+fill_page:
+		chunk = min_t(unsigned long, data_len,
+			      PAGE_SIZE << order);
+		skb_fill_page_desc(skb, i, page, 0, chunk);
+		data_len -= chunk;
+		npages -= 1 << order;
+	}
+	return skb;
+
+failure:
+	kfree_skb(skb);
+	return NULL;
+}
+EXPORT_SYMBOL(alloc_skb_with_frags);