1 files changed, 125 insertions, 187 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 515ec5cdc79c..6c5915efbc17 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -67,6 +67,7 @@
 #include <net/dst.h>
 #include <net/sock.h>
 #include <net/checksum.h>
+#include <net/gso.h>
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
 #include <net/mpls.h>
@@ -92,15 +93,7 @@ static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
 static struct kmem_cache *skbuff_ext_cache __ro_after_init;
 #endif
 
-/* skb_small_head_cache and related code is only supported
- * for CONFIG_SLAB and CONFIG_SLUB.
- * As soon as SLOB is removed from the kernel, we can clean up this.
- */
-#if !defined(CONFIG_SLOB)
-# define HAVE_SKB_SMALL_HEAD_CACHE 1
-#endif
 
-#ifdef HAVE_SKB_SMALL_HEAD_CACHE
 static struct kmem_cache *skb_small_head_cache __ro_after_init;
 
 #define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER)
@@ -117,7 +110,6 @@ static struct kmem_cache *skb_small_head_cache __ro_after_init;
 
 #define SKB_SMALL_HEAD_HEADROOM						\
 	SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE)
-#endif /* HAVE_SKB_SMALL_HEAD_CACHE */
 
 int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS;
 EXPORT_SYMBOL(sysctl_max_skb_frags);
@@ -562,7 +554,6 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 	void *obj;
 
 	obj_size = SKB_HEAD_ALIGN(*size);
-#ifdef HAVE_SKB_SMALL_HEAD_CACHE
 	if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE &&
 	    !(flags & KMALLOC_NOT_NORMAL_BITS)) {
 		obj = kmem_cache_alloc_node(skb_small_head_cache,
@@ -576,7 +567,6 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node,
 		obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node);
 		goto out;
 	}
-#endif
 	*size = obj_size = kmalloc_size_roundup(obj_size);
 	/*
 	 * Try a regular allocation, when that fails and we're not entitled
@@ -898,11 +888,9 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe)
 
 static void skb_kfree_head(void *head, unsigned int end_offset)
 {
-#ifdef HAVE_SKB_SMALL_HEAD_CACHE
 	if (end_offset == SKB_SMALL_HEAD_HEADROOM)
 		kmem_cache_free(skb_small_head_cache, head);
 	else
-#endif
 		kfree(head);
 }
 
@@ -2160,7 +2148,6 @@ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
 	if (likely(skb_end_offset(skb) == saved_end_offset))
 		return 0;
 
-#ifdef HAVE_SKB_SMALL_HEAD_CACHE
 	/* We can not change skb->end if the original or new value
 	 * is SKB_SMALL_HEAD_HEADROOM, as it might break skb_kfree_head().
 	 */
@@ -2174,7 +2161,6 @@ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri)
 		WARN_ON_ONCE(1);
 		return 0;
 	}
-#endif
 
 	shinfo = skb_shinfo(skb);
 
@@ -3003,32 +2989,32 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
 }
 EXPORT_SYMBOL_GPL(skb_splice_bits);
 
-static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg,
-			    struct kvec *vec, size_t num, size_t size)
+static int sendmsg_locked(struct sock *sk, struct msghdr *msg)
 {
 	struct socket *sock = sk->sk_socket;
+	size_t size = msg_data_left(msg);
 
 	if (!sock)
 		return -EINVAL;
-	return kernel_sendmsg(sock, msg, vec, num, size);
+
+	if (!sock->ops->sendmsg_locked)
+		return sock_no_sendmsg_locked(sk, msg, size);
+
+	return sock->ops->sendmsg_locked(sk, msg, size);
 }
 
-static int sendpage_unlocked(struct sock *sk, struct page *page, int offset,
-			     size_t size, int flags)
+static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg)
 {
 	struct socket *sock = sk->sk_socket;
 
 	if (!sock)
 		return -EINVAL;
-	return kernel_sendpage(sock, page, offset, size, flags);
+	return sock_sendmsg(sock, msg);
 }
 
-typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg,
-			    struct kvec *vec, size_t num, size_t size);
-typedef int (*sendpage_func)(struct sock *sk, struct page *page, int offset,
-			     size_t size, int flags);
+typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg);
 static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
-			   int len, sendmsg_func sendmsg, sendpage_func sendpage)
+			   int len, sendmsg_func sendmsg)
 {
 	unsigned int orig_len = len;
 	struct sk_buff *head = skb;
@@ -3048,8 +3034,9 @@ do_frag_list:
 		memset(&msg, 0, sizeof(msg));
 		msg.msg_flags = MSG_DONTWAIT;
 
-		ret = INDIRECT_CALL_2(sendmsg, kernel_sendmsg_locked,
-				      sendmsg_unlocked, sk, &msg, &kv, 1, slen);
+		iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen);
+		ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
+				      sendmsg_unlocked, sk, &msg);
 		if (ret <= 0)
 			goto error;
 
@@ -3080,11 +3067,18 @@ do_frag_list:
 		slen = min_t(size_t, len, skb_frag_size(frag) - offset);
 
 		while (slen) {
-			ret = INDIRECT_CALL_2(sendpage, kernel_sendpage_locked,
-					      sendpage_unlocked, sk,
-					      skb_frag_page(frag),
-					      skb_frag_off(frag) + offset,
-					      slen, MSG_DONTWAIT);
+			struct bio_vec bvec;
+			struct msghdr msg = {
+				.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT,
+			};
+
+			bvec_set_page(&bvec, skb_frag_page(frag), slen,
+				      skb_frag_off(frag) + offset);
+			iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1,
+				      slen);
+
+			ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
+					      sendmsg_unlocked, sk, &msg);
 			if (ret <= 0)
 				goto error;
 
@@ -3121,16 +3115,14 @@ error:
 int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
 			 int len)
 {
-	return __skb_send_sock(sk, skb, offset, len, kernel_sendmsg_locked,
-			       kernel_sendpage_locked);
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_locked);
 }
 EXPORT_SYMBOL_GPL(skb_send_sock_locked);
 
 /* Send skb data on a socket. Socket must be unlocked. */
 int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len)
 {
-	return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked,
-			       sendpage_unlocked);
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked);
 }
 
 /**
@@ -4203,13 +4195,13 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
 EXPORT_SYMBOL(skb_find_text);
 
 int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
-			 int offset, size_t size)
+			 int offset, size_t size, size_t max_frags)
 {
 	int i = skb_shinfo(skb)->nr_frags;
 
 	if (skb_can_coalesce(skb, i, page, offset)) {
 		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size);
-	} else if (i < MAX_SKB_FRAGS) {
+	} else if (i < max_frags) {
 		skb_zcopy_downgrade_managed(skb);
 		get_page(page);
 		skb_fill_page_desc_noacc(skb, i, page, offset, size);
@@ -4249,10 +4241,9 @@ static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb)
 	struct page *page;
 
 	page = virt_to_head_page(frag_skb->head);
-	__skb_frag_set_page(&head_frag, page);
-	skb_frag_off_set(&head_frag, frag_skb->data -
-			 (unsigned char *)page_address(page));
-	skb_frag_size_set(&head_frag, skb_headlen(frag_skb));
+	skb_frag_fill_page_desc(&head_frag, page, frag_skb->data -
+				(unsigned char *)page_address(page),
+				skb_headlen(frag_skb));
 	return head_frag;
 }
 
@@ -4768,7 +4759,6 @@ void __init skb_init(void)
 						0,
 						SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 						NULL);
-#ifdef HAVE_SKB_SMALL_HEAD_CACHE
 	/* usercopy should only access first SKB_SMALL_HEAD_HEADROOM bytes.
 	 * struct skb_shared_info is located at the end of skb->head,
 	 * and should not be copied to/from user.
@@ -4780,7 +4770,6 @@ void __init skb_init(void)
 						0,
 						SKB_SMALL_HEAD_HEADROOM,
 						NULL);
-#endif
 	skb_extensions_init();
 }
 
@@ -5224,8 +5213,10 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	} else {
 		skb = skb_clone(orig_skb, GFP_ATOMIC);
 
-		if (skb_orphan_frags_rx(skb, GFP_ATOMIC))
+		if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) {
+			kfree_skb(skb);
 			return;
+		}
 	}
 	if (!skb)
 		return;
@@ -5782,147 +5773,6 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 }
 EXPORT_SYMBOL_GPL(skb_scrub_packet);
 
-/**
- * skb_gso_transport_seglen - Return length of individual segments of a gso packet
- *
- * @skb: GSO skb
- *
- * skb_gso_transport_seglen is used to determine the real size of the
- * individual segments, including Layer4 headers (TCP/UDP).
- *
- * The MAC/L2 or network (IP, IPv6) headers are not accounted for.
- */
-static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
-{
-	const struct skb_shared_info *shinfo = skb_shinfo(skb);
-	unsigned int thlen = 0;
-
-	if (skb->encapsulation) {
-		thlen = skb_inner_transport_header(skb) -
-			skb_transport_header(skb);
-
-		if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
-			thlen += inner_tcp_hdrlen(skb);
-	} else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
-		thlen = tcp_hdrlen(skb);
-	} else if (unlikely(skb_is_gso_sctp(skb))) {
-		thlen = sizeof(struct sctphdr);
-	} else if (shinfo->gso_type & SKB_GSO_UDP_L4) {
-		thlen = sizeof(struct udphdr);
-	}
-	/* UFO sets gso_size to the size of the fragmentation
-	 * payload, i.e. the size of the L4 (UDP) header is already
-	 * accounted for.
-	 */
-	return thlen + shinfo->gso_size;
-}
-
-/**
- * skb_gso_network_seglen - Return length of individual segments of a gso packet
- *
- * @skb: GSO skb
- *
- * skb_gso_network_seglen is used to determine the real size of the
- * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP).
- *
- * The MAC/L2 header is not accounted for.
- */
-static unsigned int skb_gso_network_seglen(const struct sk_buff *skb)
-{
-	unsigned int hdr_len = skb_transport_header(skb) -
-			       skb_network_header(skb);
-
-	return hdr_len + skb_gso_transport_seglen(skb);
-}
-
-/**
- * skb_gso_mac_seglen - Return length of individual segments of a gso packet
- *
- * @skb: GSO skb
- *
- * skb_gso_mac_seglen is used to determine the real size of the
- * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4
- * headers (TCP/UDP).
- */
-static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
-{
-	unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
-
-	return hdr_len + skb_gso_transport_seglen(skb);
-}
-
-/**
- * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS
- *
- * There are a couple of instances where we have a GSO skb, and we
- * want to determine what size it would be after it is segmented.
- *
- * We might want to check:
- * -    L3+L4+payload size (e.g. IP forwarding)
- * - L2+L3+L4+payload size (e.g. sanity check before passing to driver)
- *
- * This is a helper to do that correctly considering GSO_BY_FRAGS.
- *
- * @skb: GSO skb
- *
- * @seg_len: The segmented length (from skb_gso_*_seglen). In the
- *           GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS].
- *
- * @max_len: The maximum permissible length.
- *
- * Returns true if the segmented length <= max length.
- */
-static inline bool skb_gso_size_check(const struct sk_buff *skb,
-				      unsigned int seg_len,
-				      unsigned int max_len) {
-	const struct skb_shared_info *shinfo = skb_shinfo(skb);
-	const struct sk_buff *iter;
-
-	if (shinfo->gso_size != GSO_BY_FRAGS)
-		return seg_len <= max_len;
-
-	/* Undo this so we can re-use header sizes */
-	seg_len -= GSO_BY_FRAGS;
-
-	skb_walk_frags(skb, iter) {
-		if (seg_len + skb_headlen(iter) > max_len)
-			return false;
-	}
-
-	return true;
-}
-
-/**
- * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU?
- *
- * @skb: GSO skb
- * @mtu: MTU to validate against
- *
- * skb_gso_validate_network_len validates if a given skb will fit a
- * wanted MTU once split. It considers L3 headers, L4 headers, and the
- * payload.
- */
-bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu)
-{
-	return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu);
-}
-EXPORT_SYMBOL_GPL(skb_gso_validate_network_len);
-
-/**
- * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length?
- *
- * @skb: GSO skb
- * @len: length to validate against
- *
- * skb_gso_validate_mac_len validates if a given skb will fit a wanted
- * length once split, including L2, L3 and L4 headers and the payload.
- */
-bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len)
-{
-	return skb_gso_size_check(skb, skb_gso_mac_seglen(skb), len);
-}
-EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len);
-
 static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 {
 	int mac_len, meta_len;
@@ -6910,3 +6760,91 @@ nodefer:	__kfree_skb(skb);
 	if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1))
 		smp_call_function_single_async(cpu, &sd->defer_csd);
 }
+
+static void skb_splice_csum_page(struct sk_buff *skb, struct page *page,
+				 size_t offset, size_t len)
+{
+	const char *kaddr;
+	__wsum csum;
+
+	kaddr = kmap_local_page(page);
+	csum = csum_partial(kaddr + offset, len, 0);
+	kunmap_local(kaddr);
+	skb->csum = csum_block_add(skb->csum, csum, skb->len);
+}
+
+/**
+ * skb_splice_from_iter - Splice (or copy) pages to skbuff
+ * @skb: The buffer to add pages to
+ * @iter: Iterator representing the pages to be added
+ * @maxsize: Maximum amount of pages to be added
+ * @gfp: Allocation flags
+ *
+ * This is a common helper function for supporting MSG_SPLICE_PAGES.  It
+ * extracts pages from an iterator and adds them to the socket buffer if
+ * possible, copying them to fragments if not possible (such as if they're slab
+ * pages).
+ *
+ * Returns the amount of data spliced/copied or -EMSGSIZE if there's
+ * insufficient space in the buffer to transfer anything.
+ */
+ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
+			     ssize_t maxsize, gfp_t gfp)
+{
+	size_t frag_limit = READ_ONCE(sysctl_max_skb_frags);
+	struct page *pages[8], **ppages = pages;
+	ssize_t spliced = 0, ret = 0;
+	unsigned int i;
+
+	while (iter->count > 0) {
+		ssize_t space, nr, len;
+		size_t off;
+
+		ret = -EMSGSIZE;
+		space = frag_limit - skb_shinfo(skb)->nr_frags;
+		if (space < 0)
+			break;
+
+		/* We might be able to coalesce without increasing nr_frags */
+		nr = clamp_t(size_t, space, 1, ARRAY_SIZE(pages));
+
+		len = iov_iter_extract_pages(iter, &ppages, maxsize, nr, 0, &off);
+		if (len <= 0) {
+			ret = len ?: -EIO;
+			break;
+		}
+
+		i = 0;
+		do {
+			struct page *page = pages[i++];
+			size_t part = min_t(size_t, PAGE_SIZE - off, len);
+
+			ret = -EIO;
+			if (WARN_ON_ONCE(!sendpage_ok(page)))
+				goto out;
+
+			ret = skb_append_pagefrags(skb, page, off, part,
+						   frag_limit);
+			if (ret < 0) {
+				iov_iter_revert(iter, len);
+				goto out;
+			}
+
+			if (skb->ip_summed == CHECKSUM_NONE)
+				skb_splice_csum_page(skb, page, off, part);
+
+			off = 0;
+			spliced += part;
+			maxsize -= part;
+			len -= part;
+		} while (len > 0);
+
+		if (maxsize <= 0)
+			break;
+	}
+
+out:
+	skb_len_add(skb, spliced);
+	return spliced ?: ret;
+}
+EXPORT_SYMBOL(skb_splice_from_iter);