Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2017-02-01

1) Some typo fixes, from Alexander Alemayhu.

2) Don't acquire state lock in get_mtu functions.
   The only rece against a dead state does not matter.
   From Florian Westphal.

3) Remove xfrm4_state_fini, it is unused for more than
   10 years. From Florian Westphal.

4) Various rcu usage improvements. From Florian Westphal.

5) Properly handle crypto arrors in ah4/ah6.
   From Gilad Ben-Yossef.

6) Try to avoid skb linearization in esp4 and esp6.

7) The esp trailer is now set up in different places,
   add a helper for this.

8) With the upcomming usage of gro_cells in IPsec,
   a gro merged skb can have a secpath. Drop it
   before freeing or reusing the skb.

9) Add a xfrm dummy network device for napi. With
   this we can use gro_cells from within xfrm,
   it allows IPsec GRO without impact on the generic
   networking code.

Please pull or let me know if there are problems.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/xfrm.h

@@ -213,6 +213,8 @@ struct xfrm_state {
 	/* Last used time */
 	unsigned long		lastused;
 
+	struct page_frag xfrag;
+
 	/* Reference to data common to all the instances of this
 	 * transformer. */
 	const struct xfrm_type	*type;
@@ -343,7 +345,7 @@ struct xfrm_state_afinfo {
 int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo);
 int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo);
 struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
-void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);
+struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family);
 
 struct xfrm_input_afinfo {
 	unsigned int		family;

net/core/dev.c

@@ -4593,6 +4593,7 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 	case GRO_MERGED_FREE:
 		if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) {
 			skb_dst_drop(skb);
+			secpath_reset(skb);
 			kmem_cache_free(skbuff_head_cache, skb);
 		} else {
 			__kfree_skb(skb);
@@ -4633,6 +4634,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->encapsulation = 0;
 	skb_shinfo(skb)->gso_type = 0;
 	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
+	secpath_reset(skb);
 
 	napi->skb = skb;
 }

net/ipv4/ah4.c

@@ -270,6 +270,9 @@ static void ah_input_done(struct crypto_async_request *base, int err)
 	int ihl = ip_hdrlen(skb);
 	int ah_hlen = (ah->hdrlen + 2) << 2;
 
+	if (err)
+		goto out;
+
 	work_iph = AH_SKB_CB(skb)->tmp;
 	auth_data = ah_tmp_auth(work_iph, ihl);
 	icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len);

net/ipv4/esp4.c

@@ -18,6 +18,8 @@
 #include <net/protocol.h>
 #include <net/udp.h>
 
+#include <linux/highmem.h>
+
 struct esp_skb_cb {
 	struct xfrm_skb_cb xfrm;
 	void *tmp;
@@ -92,11 +94,40 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
 			     __alignof__(struct scatterlist));
 }
 
+static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
+{
+	struct esp_output_extra *extra = esp_tmp_extra(tmp);
+	struct crypto_aead *aead = x->data;
+	int extralen = 0;
+	u8 *iv;
+	struct aead_request *req;
+	struct scatterlist *sg;
+
+	if (x->props.flags & XFRM_STATE_ESN)
+		extralen += sizeof(*extra);
+
+	extra = esp_tmp_extra(tmp);
+	iv = esp_tmp_iv(aead, tmp, extralen);
+	req = esp_tmp_req(aead, iv);
+
+	/* Unref skb_frag_pages in the src scatterlist if necessary.
+	 * Skip the first sg which comes from skb->data.
+	 */
+	if (req->src != req->dst)
+		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
+			put_page(sg_page(sg));
+}
+
 static void esp_output_done(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
+	void *tmp;
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_state *x = dst->xfrm;
 
-	kfree(ESP_SKB_CB(skb)->tmp);
+	tmp = ESP_SKB_CB(skb)->tmp;
+	esp_ssg_unref(x, tmp);
+	kfree(tmp);
 	xfrm_output_resume(skb, err);
 }
 
@@ -120,6 +151,29 @@ static void esp_output_restore_header(struct sk_buff *skb)
 				sizeof(__be32));
 }
 
+static struct ip_esp_hdr *esp_output_set_extra(struct sk_buff *skb,
+					       struct ip_esp_hdr *esph,
+					       struct esp_output_extra *extra)
+{
+	struct xfrm_state *x = skb_dst(skb)->xfrm;
+
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * encryption.
+	 */
+	if ((x->props.flags & XFRM_STATE_ESN)) {
+		extra->esphoff = (unsigned char *)esph -
+				 skb_transport_header(skb);
+		esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
+		extra->seqhi = esph->spi;
+		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+	}
+
+	esph->spi = x->id.spi;
+
+	return esph;
+}
+
 static void esp_output_done_esn(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
@@ -128,18 +182,36 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
 	esp_output_done(base, err);
 }
 
+static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
+{
+	/* Fill padding... */
+	if (tfclen) {
+		memset(tail, 0, tfclen);
+		tail += tfclen;
+	}
+	do {
+		int i;
+		for (i = 0; i < plen - 2; i++)
+			tail[i] = i + 1;
+	} while (0);
+	tail[plen - 2] = plen - 2;
+	tail[plen - 1] = proto;
+}
+
 static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 {
-	int err;
 	struct esp_output_extra *extra;
+	int err = -ENOMEM;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
 	struct aead_request *req;
-	struct scatterlist *sg;
+	struct scatterlist *sg, *dsg;
 	struct sk_buff *trailer;
+	struct page *page;
 	void *tmp;
 	u8 *iv;
 	u8 *tail;
+	u8 *vaddr;
 	int blksize;
 	int clen;
 	int alen;
@@ -149,7 +221,9 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	int nfrags;
 	int assoclen;
 	int extralen;
+	int tailen;
 	__be64 seqno;
+	__u8 proto = *skb_mac_header(skb);
 
 	/* skb is pure payload to encrypt */
 
@@ -169,12 +243,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
 	clen = ALIGN(skb->len + 2 + tfclen, blksize);
 	plen = clen - skb->len - tfclen;
-
-	err = skb_cow_data(skb, tfclen + plen + alen, &trailer);
-	if (err < 0)
-		goto error;
-	nfrags = err;
-
+	tailen = tfclen + plen + alen;
 	assoclen = sizeof(*esph);
 	extralen = 0;
 
@@ -183,35 +252,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 		assoclen += sizeof(__be32);
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags, extralen);
-	if (!tmp) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	extra = esp_tmp_extra(tmp);
-	iv = esp_tmp_iv(aead, tmp, extralen);
-	req = esp_tmp_req(aead, iv);
-	sg = esp_req_sg(aead, req);
-
-	/* Fill padding... */
-	tail = skb_tail_pointer(trailer);
-	if (tfclen) {
-		memset(tail, 0, tfclen);
-		tail += tfclen;
-	}
-	do {
-		int i;
-		for (i = 0; i < plen - 2; i++)
-			tail[i] = i + 1;
-	} while (0);
-	tail[plen - 2] = plen - 2;
-	tail[plen - 1] = *skb_mac_header(skb);
-	pskb_put(skb, trailer, clen - skb->len + alen);
-
-	skb_push(skb, -skb_network_offset(skb));
-	esph = ip_esp_hdr(skb);
 	*skb_mac_header(skb) = IPPROTO_ESP;
+	esph = ip_esp_hdr(skb);
 
 	/* this is non-NULL only with UDP Encapsulation */
 	if (x->encap) {
@@ -230,7 +272,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 		uh = (struct udphdr *)esph;
 		uh->source = sport;
 		uh->dest = dport;
-		uh->len = htons(skb->len - skb_transport_offset(skb));
+		uh->len = htons(skb->len + tailen
+				- skb_transport_offset(skb));
 		uh->check = 0;
 
 		switch (encap_type) {
@@ -248,31 +291,148 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 		*skb_mac_header(skb) = IPPROTO_UDP;
 	}
 
-	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+	if (!skb_cloned(skb)) {
+		if (tailen <= skb_availroom(skb)) {
+			nfrags = 1;
+			trailer = skb;
+			tail = skb_tail_pointer(trailer);
 
-	aead_request_set_callback(req, 0, esp_output_done, skb);
+			goto skip_cow;
+		} else if ((skb_shinfo(skb)->nr_frags < MAX_SKB_FRAGS)
+			   && !skb_has_frag_list(skb)) {
+			int allocsize;
+			struct sock *sk = skb->sk;
+			struct page_frag *pfrag = &x->xfrag;
 
-	/* For ESN we move the header forward by 4 bytes to
-	 * accomodate the high bits.  We will move it back after
-	 * encryption.
-	 */
-	if ((x->props.flags & XFRM_STATE_ESN)) {
-		extra->esphoff = (unsigned char *)esph -
-				 skb_transport_header(skb);
-		esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
-		extra->seqhi = esph->spi;
-		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
-		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
+			allocsize = ALIGN(tailen, L1_CACHE_BYTES);
+
+			spin_lock_bh(&x->lock);
+
+			if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
+				spin_unlock_bh(&x->lock);
+				goto cow;
+			}
+
+			page = pfrag->page;
+			get_page(page);
+
+			vaddr = kmap_atomic(page);
+
+			tail = vaddr + pfrag->offset;
+
+			esp_output_fill_trailer(tail, tfclen, plen, proto);
+
+			kunmap_atomic(vaddr);
+
+			nfrags = skb_shinfo(skb)->nr_frags;
+
+			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
+					     tailen);
+			skb_shinfo(skb)->nr_frags = ++nfrags;
+
+			pfrag->offset = pfrag->offset + allocsize;
+			nfrags++;
+
+			skb->len += tailen;
+			skb->data_len += tailen;
+			skb->truesize += tailen;
+			if (sk)
+				atomic_add(tailen, &sk->sk_wmem_alloc);
+
+			skb_push(skb, -skb_network_offset(skb));
+
+			esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+			esph->spi = x->id.spi;
+
+			tmp = esp_alloc_tmp(aead, nfrags + 2, extralen);
+			if (!tmp) {
+				spin_unlock_bh(&x->lock);
+				err = -ENOMEM;
+				goto error;
+			}
+
+			extra = esp_tmp_extra(tmp);
+			iv = esp_tmp_iv(aead, tmp, extralen);
+			req = esp_tmp_req(aead, iv);
+			sg = esp_req_sg(aead, req);
+			dsg = &sg[nfrags];
+
+			esph = esp_output_set_extra(skb, esph, extra);
+
+			sg_init_table(sg, nfrags);
+			skb_to_sgvec(skb, sg,
+				     (unsigned char *)esph - skb->data,
+				     assoclen + ivlen + clen + alen);
+
+			allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES);
+
+			if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
+				spin_unlock_bh(&x->lock);
+				err = -ENOMEM;
+				goto error;
+			}
+
+			skb_shinfo(skb)->nr_frags = 1;
+
+			page = pfrag->page;
+			get_page(page);
+			/* replace page frags in skb with new page */
+			__skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len);
+			pfrag->offset = pfrag->offset + allocsize;
+
+			sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1);
+			skb_to_sgvec(skb, dsg,
+				     (unsigned char *)esph - skb->data,
+				     assoclen + ivlen + clen + alen);
+
+			spin_unlock_bh(&x->lock);
+
+			goto skip_cow2;
+		}
 	}
 
+cow:
+	err = skb_cow_data(skb, tailen, &trailer);
+	if (err < 0)
+		goto error;
+	nfrags = err;
+	tail = skb_tail_pointer(trailer);
+	esph = ip_esp_hdr(skb);
+
+skip_cow:
+	esp_output_fill_trailer(tail, tfclen, plen, proto);
+
+	pskb_put(skb, trailer, clen - skb->len + alen);
+	skb_push(skb, -skb_network_offset(skb));
+	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
 	esph->spi = x->id.spi;
 
+	tmp = esp_alloc_tmp(aead, nfrags, extralen);
+	if (!tmp) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	extra = esp_tmp_extra(tmp);
+	iv = esp_tmp_iv(aead, tmp, extralen);
+	req = esp_tmp_req(aead, iv);
+	sg = esp_req_sg(aead, req);
+	dsg = sg;
+
+	esph = esp_output_set_extra(skb, esph, extra);
+
 	sg_init_table(sg, nfrags);
 	skb_to_sgvec(skb, sg,
 		     (unsigned char *)esph - skb->data,
 		     assoclen + ivlen + clen + alen);
 
-	aead_request_set_crypt(req, sg, sg, ivlen + clen, iv);
+skip_cow2:
+	if ((x->props.flags & XFRM_STATE_ESN))
+		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
+	else
+		aead_request_set_callback(req, 0, esp_output_done, skb);
+
+	aead_request_set_crypt(req, sg, dsg, ivlen + clen, iv);
 	aead_request_set_ad(req, assoclen);
 
 	seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
@@ -298,6 +458,8 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 			esp_output_restore_header(skb);
 	}
 
+	if (sg != dsg)
+		esp_ssg_unref(x, tmp);
 	kfree(tmp);
 
 error:
@@ -401,6 +563,23 @@ static void esp_input_restore_header(struct sk_buff *skb)
 	__skb_pull(skb, 4);
 }
 
+static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi)
+{
+	struct xfrm_state *x = xfrm_input_state(skb);
+	struct ip_esp_hdr *esph = (struct ip_esp_hdr *)skb->data;
+
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * decryption.
+	 */
+	if ((x->props.flags & XFRM_STATE_ESN)) {
+		esph = (void *)skb_push(skb, 4);
+		*seqhi = esph->spi;
+		esph->spi = esph->seq_no;
+		esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
+	}
+}
+
 static void esp_input_done_esn(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
@@ -437,12 +616,6 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 	if (elen <= 0)
 		goto out;
 
-	err = skb_cow_data(skb, 0, &trailer);
-	if (err < 0)
-		goto out;
-
-	nfrags = err;
-
 	assoclen = sizeof(*esph);
 	seqhilen = 0;
 
@@ -451,6 +624,26 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 		assoclen += seqhilen;
 	}
 
+	if (!skb_cloned(skb)) {
+		if (!skb_is_nonlinear(skb)) {
+			nfrags = 1;
+
+			goto skip_cow;
+		} else if (!skb_has_frag_list(skb)) {
+			nfrags = skb_shinfo(skb)->nr_frags;
+			nfrags++;
+
+			goto skip_cow;
+		}
+	}
+
+	err = skb_cow_data(skb, 0, &trailer);
+	if (err < 0)
+		goto out;
+
+	nfrags = err;
+
+skip_cow:
 	err = -ENOMEM;
 	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
 	if (!tmp)
@@ -462,26 +655,17 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
 
-	skb->ip_summed = CHECKSUM_NONE;
+	esp_input_set_header(skb, seqhi);
 
-	esph = (struct ip_esp_hdr *)skb->data;
+	sg_init_table(sg, nfrags);
+	skb_to_sgvec(skb, sg, 0, skb->len);
 
-	aead_request_set_callback(req, 0, esp_input_done, skb);
+	skb->ip_summed = CHECKSUM_NONE;
 
-	/* For ESN we move the header forward by 4 bytes to
-	 * accomodate the high bits.  We will move it back after
-	 * decryption.
-	 */
-	if ((x->props.flags & XFRM_STATE_ESN)) {
-		esph = (void *)skb_push(skb, 4);
-		*seqhi = esph->spi;
-		esph->spi = esph->seq_no;
-		esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
+	if ((x->props.flags & XFRM_STATE_ESN))
 		aead_request_set_callback(req, 0, esp_input_done_esn, skb);
-	}
-
-	sg_init_table(sg, nfrags);
-	skb_to_sgvec(skb, sg, 0, skb->len);
+	else
+		aead_request_set_callback(req, 0, esp_input_done, skb);
 
 	aead_request_set_crypt(req, sg, sg, elen + ivlen, iv);
 	aead_request_set_ad(req, assoclen);

net/ipv4/xfrm4_state.c

@@ -90,11 +90,3 @@ void __init xfrm4_state_init(void)
 {
 	xfrm_state_register_afinfo(&xfrm4_state_afinfo);
 }
-
-#if 0
-void __exit xfrm4_state_fini(void)
-{
-	xfrm_state_unregister_afinfo(&xfrm4_state_afinfo);
-}
-#endif  /*  0  */
-

net/ipv6/ah6.c

@@ -474,6 +474,9 @@ static void ah6_input_done(struct crypto_async_request *base, int err)
 	int hdr_len = skb_network_header_len(skb);
 	int ah_hlen = (ah->hdrlen + 2) << 2;
 
+	if (err)
+		goto out;
+
 	work_iph = AH_SKB_CB(skb)->tmp;
 	auth_data = ah_tmp_auth(work_iph, hdr_len);
 	icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len);

net/ipv6/esp6.c

@@ -44,6 +44,8 @@
 #include <net/protocol.h>
 #include <linux/icmpv6.h>
 
+#include <linux/highmem.h>
+
 struct esp_skb_cb {
 	struct xfrm_skb_cb xfrm;
 	void *tmp;
@@ -114,11 +116,40 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
 			     __alignof__(struct scatterlist));
 }
 
+static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
+{
+	__be32 *seqhi;
+	struct crypto_aead *aead = x->data;
+	int seqhilen = 0;
+	u8 *iv;
+	struct aead_request *req;
+	struct scatterlist *sg;
+
+	if (x->props.flags & XFRM_STATE_ESN)
+		seqhilen += sizeof(__be32);
+
+	seqhi = esp_tmp_seqhi(tmp);
+	iv = esp_tmp_iv(aead, tmp, seqhilen);
+	req = esp_tmp_req(aead, iv);
+
+	/* Unref skb_frag_pages in the src scatterlist if necessary.
+	 * Skip the first sg which comes from skb->data.
+	 */
+	if (req->src != req->dst)
+		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
+			put_page(sg_page(sg));
+}
+
 static void esp_output_done(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
+	void *tmp;
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_state *x = dst->xfrm;
 
-	kfree(ESP_SKB_CB(skb)->tmp);
+	tmp = ESP_SKB_CB(skb)->tmp;
+	esp_ssg_unref(x, tmp);
+	kfree(tmp);
 	xfrm_output_resume(skb, err);
 }
 
@@ -138,6 +169,27 @@ static void esp_output_restore_header(struct sk_buff *skb)
 	esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
 }
 
+static struct ip_esp_hdr *esp_output_set_esn(struct sk_buff *skb,
+					     struct ip_esp_hdr *esph,
+					     __be32 *seqhi)
+{
+	struct xfrm_state *x = skb_dst(skb)->xfrm;
+
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * encryption.
+	 */
+	if ((x->props.flags & XFRM_STATE_ESN)) {
+		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
+		*seqhi = esph->spi;
+		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+	}
+
+	esph->spi = x->id.spi;
+
+	return esph;
+}
+
 static void esp_output_done_esn(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
@@ -146,14 +198,31 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
 	esp_output_done(base, err);
 }
 
+static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
+{
+	/* Fill padding... */
+	if (tfclen) {
+		memset(tail, 0, tfclen);
+		tail += tfclen;
+	}
+	do {
+		int i;
+		for (i = 0; i < plen - 2; i++)
+			tail[i] = i + 1;
+	} while (0);
+	tail[plen - 2] = plen - 2;
+	tail[plen - 1] = proto;
+}
+
 static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err;
 	struct ip_esp_hdr *esph;
 	struct crypto_aead *aead;
 	struct aead_request *req;
-	struct scatterlist *sg;
+	struct scatterlist *sg, *dsg;
 	struct sk_buff *trailer;
+	struct page *page;
 	void *tmp;
 	int blksize;
 	int clen;
@@ -164,10 +233,13 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 	int nfrags;
 	int assoclen;
 	int seqhilen;
+	int tailen;
 	u8 *iv;
 	u8 *tail;
+	u8 *vaddr;
 	__be32 *seqhi;
 	__be64 seqno;
+	__u8 proto = *skb_mac_header(skb);
 
 	/* skb is pure payload to encrypt */
 	aead = x->data;
@@ -186,11 +258,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
 	clen = ALIGN(skb->len + 2 + tfclen, blksize);
 	plen = clen - skb->len - tfclen;
-
-	err = skb_cow_data(skb, tfclen + plen + alen, &trailer);
-	if (err < 0)
-		goto error;
-	nfrags = err;
+	tailen = tfclen + plen + alen;
 
 	assoclen = sizeof(*esph);
 	seqhilen = 0;
@@ -200,59 +268,152 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 		assoclen += seqhilen;
 	}
 
-	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
-	if (!tmp) {
-		err = -ENOMEM;
-		goto error;
+	*skb_mac_header(skb) = IPPROTO_ESP;
+	esph = ip_esp_hdr(skb);
+
+	if (!skb_cloned(skb)) {
+		if (tailen <= skb_availroom(skb)) {
+			nfrags = 1;
+			trailer = skb;
+			tail = skb_tail_pointer(trailer);
+
+			goto skip_cow;
+		} else if ((skb_shinfo(skb)->nr_frags < MAX_SKB_FRAGS)
+			   && !skb_has_frag_list(skb)) {
+			int allocsize;
+			struct sock *sk = skb->sk;
+			struct page_frag *pfrag = &x->xfrag;
+
+			allocsize = ALIGN(tailen, L1_CACHE_BYTES);
+
+			spin_lock_bh(&x->lock);
+
+			if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
+				spin_unlock_bh(&x->lock);
+				goto cow;
+			}
+
+			page = pfrag->page;
+			get_page(page);
+
+			vaddr = kmap_atomic(page);
+
+			tail = vaddr + pfrag->offset;
+
+			esp_output_fill_trailer(tail, tfclen, plen, proto);
+
+			kunmap_atomic(vaddr);
+
+			nfrags = skb_shinfo(skb)->nr_frags;
+
+			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
+					     tailen);
+			skb_shinfo(skb)->nr_frags = ++nfrags;
+
+			pfrag->offset = pfrag->offset + allocsize;
+			nfrags++;
+
+			skb->len += tailen;
+			skb->data_len += tailen;
+			skb->truesize += tailen;
+			if (sk)
+				atomic_add(tailen, &sk->sk_wmem_alloc);
+
+			skb_push(skb, -skb_network_offset(skb));
+
+			esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+			esph->spi = x->id.spi;
+
+			tmp = esp_alloc_tmp(aead, nfrags + 2, seqhilen);
+			if (!tmp) {
+				spin_unlock_bh(&x->lock);
+				err = -ENOMEM;
+				goto error;
+			}
+			seqhi = esp_tmp_seqhi(tmp);
+			iv = esp_tmp_iv(aead, tmp, seqhilen);
+			req = esp_tmp_req(aead, iv);
+			sg = esp_req_sg(aead, req);
+			dsg = &sg[nfrags];
+
+			esph = esp_output_set_esn(skb, esph, seqhi);
+
+			sg_init_table(sg, nfrags);
+			skb_to_sgvec(skb, sg,
+				     (unsigned char *)esph - skb->data,
+				     assoclen + ivlen + clen + alen);
+
+			allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES);
+
+			if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
+				spin_unlock_bh(&x->lock);
+				err = -ENOMEM;
+				goto error;
+			}
+
+			skb_shinfo(skb)->nr_frags = 1;
+
+			page = pfrag->page;
+			get_page(page);
+			/* replace page frags in skb with new page */
+			__skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len);
+			pfrag->offset = pfrag->offset + allocsize;
+
+			sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1);
+			skb_to_sgvec(skb, dsg,
+				     (unsigned char *)esph - skb->data,
+				     assoclen + ivlen + clen + alen);
+
+			spin_unlock_bh(&x->lock);
+
+			goto skip_cow2;
+		}
 	}
 
-	seqhi = esp_tmp_seqhi(tmp);
-	iv = esp_tmp_iv(aead, tmp, seqhilen);
-	req = esp_tmp_req(aead, iv);
-	sg = esp_req_sg(aead, req);
+cow:
+	err = skb_cow_data(skb, tailen, &trailer);
+	if (err < 0)
+		goto error;
+	nfrags = err;
 
-	/* Fill padding... */
 	tail = skb_tail_pointer(trailer);
-	if (tfclen) {
-		memset(tail, 0, tfclen);
-		tail += tfclen;
-	}
-	do {
-		int i;
-		for (i = 0; i < plen - 2; i++)
-			tail[i] = i + 1;
-	} while (0);
-	tail[plen - 2] = plen - 2;
-	tail[plen - 1] = *skb_mac_header(skb);
-	pskb_put(skb, trailer, clen - skb->len + alen);
+	esph = ip_esp_hdr(skb);
 
+skip_cow:
+	esp_output_fill_trailer(tail, tfclen, plen, proto);
+
+	pskb_put(skb, trailer, clen - skb->len + alen);
 	skb_push(skb, -skb_network_offset(skb));
-	esph = ip_esp_hdr(skb);
-	*skb_mac_header(skb) = IPPROTO_ESP;
 
 	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
+	esph->spi = x->id.spi;
 
-	aead_request_set_callback(req, 0, esp_output_done, skb);
-
-	/* For ESN we move the header forward by 4 bytes to
-	 * accomodate the high bits.  We will move it back after
-	 * encryption.
-	 */
-	if ((x->props.flags & XFRM_STATE_ESN)) {
-		esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
-		*seqhi = esph->spi;
-		esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
-		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
+	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
+	if (!tmp) {
+		err = -ENOMEM;
+		goto error;
 	}
 
-	esph->spi = x->id.spi;
+	seqhi = esp_tmp_seqhi(tmp);
+	iv = esp_tmp_iv(aead, tmp, seqhilen);
+	req = esp_tmp_req(aead, iv);
+	sg = esp_req_sg(aead, req);
+	dsg = sg;
+
+	esph = esp_output_set_esn(skb, esph, seqhi);
 
 	sg_init_table(sg, nfrags);
 	skb_to_sgvec(skb, sg,
 		     (unsigned char *)esph - skb->data,
 		     assoclen + ivlen + clen + alen);
 
-	aead_request_set_crypt(req, sg, sg, ivlen + clen, iv);
+skip_cow2:
+	if ((x->props.flags & XFRM_STATE_ESN))
+		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
+	else
+		aead_request_set_callback(req, 0, esp_output_done, skb);
+
+	aead_request_set_crypt(req, sg, dsg, ivlen + clen, iv);
 	aead_request_set_ad(req, assoclen);
 
 	seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
@@ -278,6 +439,8 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 			esp_output_restore_header(skb);
 	}
 
+	if (sg != dsg)
+		esp_ssg_unref(x, tmp);
 	kfree(tmp);
 
 error:
@@ -343,6 +506,23 @@ static void esp_input_restore_header(struct sk_buff *skb)
 	__skb_pull(skb, 4);
 }
 
+static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi)
+{
+	struct xfrm_state *x = xfrm_input_state(skb);
+	struct ip_esp_hdr *esph = (struct ip_esp_hdr *)skb->data;
+
+	/* For ESN we move the header forward by 4 bytes to
+	 * accomodate the high bits.  We will move it back after
+	 * decryption.
+	 */
+	if ((x->props.flags & XFRM_STATE_ESN)) {
+		esph = (void *)skb_push(skb, 4);
+		*seqhi = esph->spi;
+		esph->spi = esph->seq_no;
+		esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
+	}
+}
+
 static void esp_input_done_esn(struct crypto_async_request *base, int err)
 {
 	struct sk_buff *skb = base->data;
@@ -378,14 +558,6 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 		goto out;
 	}
 
-	nfrags = skb_cow_data(skb, 0, &trailer);
-	if (nfrags < 0) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	ret = -ENOMEM;
-
 	assoclen = sizeof(*esph);
 	seqhilen = 0;
 
@@ -394,6 +566,27 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 		assoclen += seqhilen;
 	}
 
+	if (!skb_cloned(skb)) {
+		if (!skb_is_nonlinear(skb)) {
+			nfrags = 1;
+
+			goto skip_cow;
+		} else if (!skb_has_frag_list(skb)) {
+			nfrags = skb_shinfo(skb)->nr_frags;
+			nfrags++;
+
+			goto skip_cow;
+		}
+	}
+
+	nfrags = skb_cow_data(skb, 0, &trailer);
+	if (nfrags < 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+skip_cow:
+	ret = -ENOMEM;
 	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
 	if (!tmp)
 		goto out;
@@ -404,26 +597,17 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 	req = esp_tmp_req(aead, iv);
 	sg = esp_req_sg(aead, req);
 
-	skb->ip_summed = CHECKSUM_NONE;
+	esp_input_set_header(skb, seqhi);
 
-	esph = (struct ip_esp_hdr *)skb->data;
+	sg_init_table(sg, nfrags);
+	skb_to_sgvec(skb, sg, 0, skb->len);
 
-	aead_request_set_callback(req, 0, esp_input_done, skb);
+	skb->ip_summed = CHECKSUM_NONE;
 
-	/* For ESN we move the header forward by 4 bytes to
-	 * accomodate the high bits.  We will move it back after
-	 * decryption.
-	 */
-	if ((x->props.flags & XFRM_STATE_ESN)) {
-		esph = (void *)skb_push(skb, 4);
-		*seqhi = esph->spi;
-		esph->spi = esph->seq_no;
-		esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
+	if ((x->props.flags & XFRM_STATE_ESN))
 		aead_request_set_callback(req, 0, esp_input_done_esn, skb);
-	}
-
-	sg_init_table(sg, nfrags);
-	skb_to_sgvec(skb, sg, 0, skb->len);
+	else
+		aead_request_set_callback(req, 0, esp_input_done, skb);
 
 	aead_request_set_crypt(req, sg, sg, elen + ivlen, iv);
 	aead_request_set_ad(req, assoclen);

net/xfrm/xfrm_input.c

@@ -21,6 +21,9 @@ static struct kmem_cache *secpath_cachep __read_mostly;
 static DEFINE_SPINLOCK(xfrm_input_afinfo_lock);
 static struct xfrm_input_afinfo __rcu *xfrm_input_afinfo[NPROTO];
 
+static struct gro_cells gro_cells;
+static struct net_device xfrm_napi_dev;
+
 int xfrm_input_register_afinfo(struct xfrm_input_afinfo *afinfo)
 {
 	int err = 0;
@@ -371,7 +374,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 	if (decaps) {
 		skb_dst_drop(skb);
-		netif_rx(skb);
+		gro_cells_receive(&gro_cells, skb);
 		return 0;
 	} else {
 		return x->inner_mode->afinfo->transport_finish(skb, async);
@@ -394,6 +397,13 @@ EXPORT_SYMBOL(xfrm_input_resume);
 
 void __init xfrm_input_init(void)
 {
+	int err;
+
+	init_dummy_netdev(&xfrm_napi_dev);
+	err = gro_cells_init(&gro_cells, &xfrm_napi_dev);
+	if (err)
+		gro_cells.cells = NULL;
+
 	secpath_cachep = kmem_cache_create("secpath_cache",
 					   sizeof(struct sec_path),
 					   0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,

net/xfrm/xfrm_output.c

@@ -246,10 +246,8 @@ void xfrm_local_error(struct sk_buff *skb, int mtu)
 		return;
 
 	afinfo = xfrm_state_get_afinfo(proto);
-	if (!afinfo)
-		return;
-
-	afinfo->local_error(skb, mtu);
-	xfrm_state_put_afinfo(afinfo);
+	if (afinfo)
+		afinfo->local_error(skb, mtu);
+	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(xfrm_local_error);

net/xfrm/xfrm_policy.c

@@ -330,7 +330,7 @@ void xfrm_policy_destroy(struct xfrm_policy *policy)
 }
 EXPORT_SYMBOL(xfrm_policy_destroy);
 
-/* Rule must be locked. Release descentant resources, announce
+/* Rule must be locked. Release descendant resources, announce
  * entry dead. The rule must be unlinked from lists to the moment.
  */
 

net/xfrm/xfrm_state.c

@@ -192,7 +192,7 @@ int xfrm_register_type(const struct xfrm_type *type, unsigned short family)
 	else
 		err = -EEXIST;
 	spin_unlock_bh(&xfrm_type_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_register_type);
@@ -213,7 +213,7 @@ int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family)
 	else
 		typemap[type->proto] = NULL;
 	spin_unlock_bh(&xfrm_type_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_unregister_type);
@@ -231,17 +231,18 @@ static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family)
 		return NULL;
 	typemap = afinfo->type_map;
 
-	type = typemap[proto];
+	type = READ_ONCE(typemap[proto]);
 	if (unlikely(type && !try_module_get(type->owner)))
 		type = NULL;
+
+	rcu_read_unlock();
+
 	if (!type && !modload_attempted) {
-		xfrm_state_put_afinfo(afinfo);
 		request_module("xfrm-type-%d-%d", family, proto);
 		modload_attempted = 1;
 		goto retry;
 	}
 
-	xfrm_state_put_afinfo(afinfo);
 	return type;
 }
 
@@ -280,7 +281,7 @@ int xfrm_register_mode(struct xfrm_mode *mode, int family)
 
 out:
 	spin_unlock_bh(&xfrm_mode_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_register_mode);
@@ -308,7 +309,7 @@ int xfrm_unregister_mode(struct xfrm_mode *mode, int family)
 	}
 
 	spin_unlock_bh(&xfrm_mode_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_unregister_mode);
@@ -327,17 +328,17 @@ static struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
 	if (unlikely(afinfo == NULL))
 		return NULL;
 
-	mode = afinfo->mode_map[encap];
+	mode = READ_ONCE(afinfo->mode_map[encap]);
 	if (unlikely(mode && !try_module_get(mode->owner)))
 		mode = NULL;
+
+	rcu_read_unlock();
 	if (!mode && !modload_attempted) {
-		xfrm_state_put_afinfo(afinfo);
 		request_module("xfrm-mode-%d-%d", family, encap);
 		modload_attempted = 1;
 		goto retry;
 	}
 
-	xfrm_state_put_afinfo(afinfo);
 	return mode;
 }
 
@@ -409,7 +410,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 			if (x->xflags & XFRM_SOFT_EXPIRE) {
 				/* enter hard expire without soft expire first?!
 				 * setting a new date could trigger this.
-				 * workarbound: fix x->curflt.add_time by below:
+				 * workaround: fix x->curflt.add_time by below:
 				 */
 				x->curlft.add_time = now - x->saved_tmo - 1;
 				tmo = x->lft.hard_add_expires_seconds - x->saved_tmo;
@@ -639,26 +640,25 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
 }
 EXPORT_SYMBOL(xfrm_sad_getinfo);
 
-static int
+static void
 xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
 		    const struct xfrm_tmpl *tmpl,
 		    const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		    unsigned short family)
 {
-	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
+	struct xfrm_state_afinfo *afinfo = xfrm_state_afinfo_get_rcu(family);
+
 	if (!afinfo)
-		return -1;
+		return;
+
 	afinfo->init_tempsel(&x->sel, fl);
 
 	if (family != tmpl->encap_family) {
-		xfrm_state_put_afinfo(afinfo);
-		afinfo = xfrm_state_get_afinfo(tmpl->encap_family);
+		afinfo = xfrm_state_afinfo_get_rcu(tmpl->encap_family);
 		if (!afinfo)
-			return -1;
+			return;
 	}
 	afinfo->init_temprop(x, tmpl, daddr, saddr);
-	xfrm_state_put_afinfo(afinfo);
-	return 0;
 }
 
 static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
@@ -1474,7 +1474,7 @@ xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
 	if (afinfo->tmpl_sort)
 		err = afinfo->tmpl_sort(dst, src, n);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_tmpl_sort);
@@ -1494,7 +1494,7 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
 	if (afinfo->state_sort)
 		err = afinfo->state_sort(dst, src, n);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_state_sort);
@@ -1932,10 +1932,10 @@ EXPORT_SYMBOL(xfrm_unregister_km);
 int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo)
 {
 	int err = 0;
-	if (unlikely(afinfo == NULL))
-		return -EINVAL;
-	if (unlikely(afinfo->family >= NPROTO))
+
+	if (WARN_ON(afinfo->family >= NPROTO))
 		return -EAFNOSUPPORT;
+
 	spin_lock_bh(&xfrm_state_afinfo_lock);
 	if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL))
 		err = -EEXIST;
@@ -1948,14 +1948,14 @@ EXPORT_SYMBOL(xfrm_state_register_afinfo);
 
 int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo)
 {
-	int err = 0;
-	if (unlikely(afinfo == NULL))
-		return -EINVAL;
-	if (unlikely(afinfo->family >= NPROTO))
+	int err = 0, family = afinfo->family;
+
+	if (WARN_ON(family >= NPROTO))
 		return -EAFNOSUPPORT;
+
 	spin_lock_bh(&xfrm_state_afinfo_lock);
 	if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) {
-		if (unlikely(xfrm_state_afinfo[afinfo->family] != afinfo))
+		if (rcu_access_pointer(xfrm_state_afinfo[family]) != afinfo)
 			err = -EINVAL;
 		else
 			RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL);
@@ -1966,6 +1966,14 @@ int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo)
 }
 EXPORT_SYMBOL(xfrm_state_unregister_afinfo);
 
+struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family)
+{
+	if (unlikely(family >= NPROTO))
+		return NULL;
+
+	return rcu_dereference(xfrm_state_afinfo[family]);
+}
+
 struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
 {
 	struct xfrm_state_afinfo *afinfo;
@@ -1978,11 +1986,6 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
 	return afinfo;
 }
 
-void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo)
-{
-	rcu_read_unlock();
-}
-
 /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
 void xfrm_state_delete_tunnel(struct xfrm_state *x)
 {
@@ -2000,16 +2003,13 @@ EXPORT_SYMBOL(xfrm_state_delete_tunnel);
 
 int xfrm_state_mtu(struct xfrm_state *x, int mtu)
 {
-	int res;
+	const struct xfrm_type *type = READ_ONCE(x->type);
 
-	spin_lock_bh(&x->lock);
 	if (x->km.state == XFRM_STATE_VALID &&
-	    x->type && x->type->get_mtu)
-		res = x->type->get_mtu(x, mtu);
-	else
-		res = mtu - x->props.header_len;
-	spin_unlock_bh(&x->lock);
-	return res;
+	    type && type->get_mtu)
+		return type->get_mtu(x, mtu);
+
+	return mtu - x->props.header_len;
 }
 
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay)
@@ -2028,7 +2028,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay)
 	if (afinfo->init_flags)
 		err = afinfo->init_flags(x);
 
-	xfrm_state_put_afinfo(afinfo);
+	rcu_read_unlock();
 
 	if (err)
 		goto error;