1 files changed, 154 insertions, 101 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6cbf77bc61fc..ee0274417948 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -64,6 +64,7 @@
 #include <linux/mpls.h>
 #include <linux/kcov.h>
 #include <linux/iov_iter.h>
+#include <linux/crc32.h>
 
 #include <net/protocol.h>
 #include <net/dst.h>
@@ -89,6 +90,7 @@
 #include <linux/textsearch.h>
 
 #include "dev.h"
+#include "devmem.h"
 #include "netmem_priv.h"
 #include "sock_destructor.h"
 
@@ -382,8 +384,7 @@ static inline void __finalize_skb_around(struct sk_buff *skb, void *data,
 	skb_set_kcov_handle(skb, kcov_common_handle());
 }
 
-static inline void *__slab_build_skb(struct sk_buff *skb, void *data,
-				     unsigned int *size)
+static inline void *__slab_build_skb(void *data, unsigned int *size)
 {
 	void *resized;
 
@@ -416,7 +417,7 @@ struct sk_buff *slab_build_skb(void *data)
 		return NULL;
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
-	data = __slab_build_skb(skb, data, &size);
+	data = __slab_build_skb(data, &size);
 	__finalize_skb_around(skb, data, size);
 
 	return skb;
@@ -433,7 +434,7 @@ static void __build_skb_around(struct sk_buff *skb, void *data,
 	 * using slab buffer should use slab_build_skb() instead.
 	 */
 	if (WARN_ONCE(size == 0, "Use slab_build_skb() instead"))
-		data = __slab_build_skb(skb, data, &size);
+		data = __slab_build_skb(data, &size);
 
 	__finalize_skb_around(skb, data, size);
 }
@@ -893,11 +894,6 @@ static void skb_clone_fraglist(struct sk_buff *skb)
 		skb_get(list);
 }
 
-static bool is_pp_netmem(netmem_ref netmem)
-{
-	return (netmem_get_pp_magic(netmem) & ~0x3UL) == PP_SIGNATURE;
-}
-
 int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
 		    unsigned int headroom)
 {
@@ -995,14 +991,7 @@ bool napi_pp_put_page(netmem_ref netmem)
 {
 	netmem = netmem_compound_head(netmem);
 
-	/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
-	 * in order to preserve any existing bits, such as bit 0 for the
-	 * head page of compound page and bit 1 for pfmemalloc page, so
-	 * mask those bits for freeing side when doing below checking,
-	 * and page_is_pfmemalloc() is checked in __page_pool_put_page()
-	 * to avoid recycling the pfmemalloc page.
-	 */
-	if (unlikely(!is_pp_netmem(netmem)))
+	if (unlikely(!netmem_is_pp(netmem)))
 		return false;
 
 	page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false);
@@ -1042,7 +1031,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb)
 
 	for (i = 0; i < shinfo->nr_frags; i++) {
 		head_netmem = netmem_compound_head(shinfo->frags[i].netmem);
-		if (likely(is_pp_netmem(head_netmem)))
+		if (likely(netmem_is_pp(head_netmem)))
 			page_pool_ref_netmem(head_netmem);
 		else
 			page_ref_inc(netmem_to_page(head_netmem));
@@ -1666,7 +1655,8 @@ void mm_unaccount_pinned_pages(struct mmpin *mmp)
 }
 EXPORT_SYMBOL_GPL(mm_unaccount_pinned_pages);
 
-static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
+static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size,
+					    bool devmem)
 {
 	struct ubuf_info_msgzc *uarg;
 	struct sk_buff *skb;
@@ -1681,7 +1671,7 @@ static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size)
 	uarg = (void *)skb->cb;
 	uarg->mmp.user = NULL;
 
-	if (mm_account_pinned_pages(&uarg->mmp, size)) {
+	if (likely(!devmem) && mm_account_pinned_pages(&uarg->mmp, size)) {
 		kfree_skb(skb);
 		return NULL;
 	}
@@ -1704,7 +1694,7 @@ static inline struct sk_buff *skb_from_uarg(struct ubuf_info_msgzc *uarg)
 }
 
 struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
-				       struct ubuf_info *uarg)
+				       struct ubuf_info *uarg, bool devmem)
 {
 	if (uarg) {
 		struct ubuf_info_msgzc *uarg_zc;
@@ -1734,7 +1724,8 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 
 		next = (u32)atomic_read(&sk->sk_zckey);
 		if ((u32)(uarg_zc->id + uarg_zc->len) == next) {
-			if (mm_account_pinned_pages(&uarg_zc->mmp, size))
+			if (likely(!devmem) &&
+			    mm_account_pinned_pages(&uarg_zc->mmp, size))
 				return NULL;
 			uarg_zc->len++;
 			uarg_zc->bytelen = bytelen;
@@ -1749,7 +1740,7 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
 	}
 
 new_alloc:
-	return msg_zerocopy_alloc(sk, size);
+	return msg_zerocopy_alloc(sk, size, devmem);
 }
 EXPORT_SYMBOL_GPL(msg_zerocopy_realloc);
 
@@ -1853,7 +1844,8 @@ EXPORT_SYMBOL_GPL(msg_zerocopy_ubuf_ops);
 
 int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 			     struct msghdr *msg, int len,
-			     struct ubuf_info *uarg)
+			     struct ubuf_info *uarg,
+			     struct net_devmem_dmabuf_binding *binding)
 {
 	int err, orig_len = skb->len;
 
@@ -1872,7 +1864,8 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
 			return -EEXIST;
 	}
 
-	err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len);
+	err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len,
+				      binding);
 	if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) {
 		struct sock *save_sk = skb->sk;
 
@@ -3066,10 +3059,8 @@ static bool spd_can_coalesce(const struct splice_pipe_desc *spd,
 /*
  * Fill page/offset/length into spd, if it can hold more pages.
  */
-static bool spd_fill_page(struct splice_pipe_desc *spd,
-			  struct pipe_inode_info *pipe, struct page *page,
-			  unsigned int *len, unsigned int offset,
-			  bool linear,
+static bool spd_fill_page(struct splice_pipe_desc *spd, struct page *page,
+			  unsigned int *len, unsigned int offset, bool linear,
 			  struct sock *sk)
 {
 	if (unlikely(spd->nr_pages == MAX_SKB_FRAGS))
@@ -3097,8 +3088,7 @@ static bool __splice_segment(struct page *page, unsigned int poff,
 			     unsigned int plen, unsigned int *off,
 			     unsigned int *len,
 			     struct splice_pipe_desc *spd, bool linear,
-			     struct sock *sk,
-			     struct pipe_inode_info *pipe)
+			     struct sock *sk)
 {
 	if (!*len)
 		return true;
@@ -3117,8 +3107,7 @@ static bool __splice_segment(struct page *page, unsigned int poff,
 	do {
 		unsigned int flen = min(*len, plen);
 
-		if (spd_fill_page(spd, pipe, page, &flen, poff,
-				  linear, sk))
+		if (spd_fill_page(spd, page, &flen, poff, linear, sk))
 			return true;
 		poff += flen;
 		plen -= flen;
@@ -3136,8 +3125,8 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
 			      unsigned int *offset, unsigned int *len,
 			      struct splice_pipe_desc *spd, struct sock *sk)
 {
-	int seg;
 	struct sk_buff *iter;
+	int seg;
 
 	/* map the linear part :
 	 * If skb->head_frag is set, this 'linear' part is backed by a
@@ -3149,7 +3138,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
 			     skb_headlen(skb),
 			     offset, len, spd,
 			     skb_head_is_locked(skb),
-			     sk, pipe))
+			     sk))
 		return true;
 
 	/*
@@ -3166,7 +3155,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
 
 		if (__splice_segment(skb_frag_page(f),
 				     skb_frag_off(f), skb_frag_size(f),
-				     offset, len, spd, false, sk, pipe))
+				     offset, len, spd, false, sk))
 			return true;
 	}
 
@@ -3239,8 +3228,9 @@ static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg)
 
 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)
+			   int len, sendmsg_func sendmsg, int flags)
 {
+	int more_hint = sk_is_tcp(sk) ? MSG_MORE : 0;
 	unsigned int orig_len = len;
 	struct sk_buff *head = skb;
 	unsigned short fragidx;
@@ -3257,7 +3247,9 @@ do_frag_list:
 		kv.iov_base = skb->data + offset;
 		kv.iov_len = slen;
 		memset(&msg, 0, sizeof(msg));
-		msg.msg_flags = MSG_DONTWAIT;
+		msg.msg_flags = MSG_DONTWAIT | flags;
+		if (slen < len)
+			msg.msg_flags |= more_hint;
 
 		iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen);
 		ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
@@ -3294,9 +3286,12 @@ do_frag_list:
 		while (slen) {
 			struct bio_vec bvec;
 			struct msghdr msg = {
-				.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT,
+				.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT |
+					     flags,
 			};
 
+			if (slen < len)
+				msg.msg_flags |= more_hint;
 			bvec_set_page(&bvec, skb_frag_page(frag), slen,
 				      skb_frag_off(frag) + offset);
 			iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1,
@@ -3340,14 +3335,21 @@ 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, sendmsg_locked);
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, 0);
 }
 EXPORT_SYMBOL_GPL(skb_send_sock_locked);
 
+int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb,
+				    int offset, int len, int flags)
+{
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, flags);
+}
+EXPORT_SYMBOL_GPL(skb_send_sock_locked_with_flags);
+
 /* 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);
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked, 0);
 }
 
 /**
@@ -3443,8 +3445,7 @@ fault:
 EXPORT_SYMBOL(skb_store_bits);
 
 /* Checksum skb data. */
-__wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
-		      __wsum csum, const struct skb_checksum_ops *ops)
+__wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
@@ -3455,8 +3456,7 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		csum = INDIRECT_CALL_1(ops->update, csum_partial_ext,
-				       skb->data + offset, copy, csum);
+		csum = csum_partial(skb->data + offset, copy, csum);
 		if ((len -= copy) == 0)
 			return csum;
 		offset += copy;
@@ -3486,13 +3486,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 					      skb_frag_off(frag) + offset - start,
 					      copy, p, p_off, p_len, copied) {
 				vaddr = kmap_atomic(p);
-				csum2 = INDIRECT_CALL_1(ops->update,
-							csum_partial_ext,
-							vaddr + p_off, p_len, 0);
+				csum2 = csum_partial(vaddr + p_off, p_len, 0);
 				kunmap_atomic(vaddr);
-				csum = INDIRECT_CALL_1(ops->combine,
-						       csum_block_add_ext, csum,
-						       csum2, pos, p_len);
+				csum = csum_block_add(csum, csum2, pos);
 				pos += p_len;
 			}
 
@@ -3513,10 +3509,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 			__wsum csum2;
 			if (copy > len)
 				copy = len;
-			csum2 = __skb_checksum(frag_iter, offset - start,
-					       copy, 0, ops);
-			csum = INDIRECT_CALL_1(ops->combine, csum_block_add_ext,
-					       csum, csum2, pos, copy);
+			csum2 = skb_checksum(frag_iter, offset - start, copy,
+					     0);
+			csum = csum_block_add(csum, csum2, pos);
 			if ((len -= copy) == 0)
 				return csum;
 			offset += copy;
@@ -3528,18 +3523,6 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 
 	return csum;
 }
-EXPORT_SYMBOL(__skb_checksum);
-
-__wsum skb_checksum(const struct sk_buff *skb, int offset,
-		    int len, __wsum csum)
-{
-	const struct skb_checksum_ops ops = {
-		.update  = csum_partial_ext,
-		.combine = csum_block_add_ext,
-	};
-
-	return __skb_checksum(skb, offset, len, csum, &ops);
-}
 EXPORT_SYMBOL(skb_checksum);
 
 /* Both of above in one bottle. */
@@ -3632,6 +3615,78 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
 }
 EXPORT_SYMBOL(skb_copy_and_csum_bits);
 
+#ifdef CONFIG_NET_CRC32C
+u32 skb_crc32c(const struct sk_buff *skb, int offset, int len, u32 crc)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+
+	if (copy > 0) {
+		copy = min(copy, len);
+		crc = crc32c(crc, skb->data + offset, copy);
+		len -= copy;
+		if (len == 0)
+			return crc;
+		offset += copy;
+	}
+
+	if (WARN_ON_ONCE(!skb_frags_readable(skb)))
+		return 0;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_frag_size(frag);
+		copy = end - offset;
+		if (copy > 0) {
+			u32 p_off, p_len, copied;
+			struct page *p;
+			u8 *vaddr;
+
+			copy = min(copy, len);
+			skb_frag_foreach_page(frag,
+					      skb_frag_off(frag) + offset - start,
+					      copy, p, p_off, p_len, copied) {
+				vaddr = kmap_atomic(p);
+				crc = crc32c(crc, vaddr + p_off, p_len);
+				kunmap_atomic(vaddr);
+			}
+			len -= copy;
+			if (len == 0)
+				return crc;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		copy = end - offset;
+		if (copy > 0) {
+			copy = min(copy, len);
+			crc = skb_crc32c(frag_iter, offset - start, copy, crc);
+			len -= copy;
+			if (len == 0)
+				return crc;
+			offset += copy;
+		}
+		start = end;
+	}
+	BUG_ON(len);
+
+	return crc;
+}
+EXPORT_SYMBOL(skb_crc32c);
+#endif /* CONFIG_NET_CRC32C */
+
 __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 {
 	__sum16 sum;
@@ -3691,32 +3746,6 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(__skb_checksum_complete);
 
-static __wsum warn_crc32c_csum_update(const void *buff, int len, __wsum sum)
-{
-	net_warn_ratelimited(
-		"%s: attempt to compute crc32c without libcrc32c.ko\n",
-		__func__);
-	return 0;
-}
-
-static __wsum warn_crc32c_csum_combine(__wsum csum, __wsum csum2,
-				       int offset, int len)
-{
-	net_warn_ratelimited(
-		"%s: attempt to compute crc32c without libcrc32c.ko\n",
-		__func__);
-	return 0;
-}
-
-static const struct skb_checksum_ops default_crc32c_ops = {
-	.update  = warn_crc32c_csum_update,
-	.combine = warn_crc32c_csum_combine,
-};
-
-const struct skb_checksum_ops *crc32c_csum_stub __read_mostly =
-	&default_crc32c_ops;
-EXPORT_SYMBOL(crc32c_csum_stub);
-
  /**
  *	skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy()
  *	@from: source buffer
@@ -6232,9 +6261,6 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
 	if (!pskb_may_pull(skb, write_len))
 		return -ENOMEM;
 
-	if (!skb_frags_readable(skb))
-		return -EFAULT;
-
 	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
 		return 0;
 
@@ -6737,8 +6763,7 @@ static int pskb_carve(struct sk_buff *skb, const u32 off, gfp_t gfp);
 /* carve out the first eat bytes from skb's frag_list. May recurse into
  * pskb_carve()
  */
-static int pskb_carve_frag_list(struct sk_buff *skb,
-				struct skb_shared_info *shinfo, int eat,
+static int pskb_carve_frag_list(struct skb_shared_info *shinfo, int eat,
 				gfp_t gfp_mask)
 {
 	struct sk_buff *list = shinfo->frag_list;
@@ -6843,7 +6868,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off,
 		skb_clone_fraglist(skb);
 
 	/* split line is in frag list */
-	if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) {
+	if (k == 0 && pskb_carve_frag_list(shinfo, off - pos, gfp_mask)) {
 		/* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */
 		if (skb_has_frag_list(skb))
 			kfree_skb_list(skb_shinfo(skb)->frag_list);
@@ -7208,7 +7233,6 @@ static void skb_splice_csum_page(struct sk_buff *skb, struct page *page,
  * @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
@@ -7219,7 +7243,7 @@ static void skb_splice_csum_page(struct sk_buff *skb, struct page *page,
  * 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)
+			     ssize_t maxsize)
 {
 	size_t frag_limit = READ_ONCE(net_hotdata.sysctl_max_skb_frags);
 	struct page *pages[8], **ppages = pages;
@@ -7317,3 +7341,32 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes,
 	return false;
 }
 EXPORT_SYMBOL(csum_and_copy_from_iter_full);
+
+void get_netmem(netmem_ref netmem)
+{
+	struct net_iov *niov;
+
+	if (netmem_is_net_iov(netmem)) {
+		niov = netmem_to_net_iov(netmem);
+		if (net_is_devmem_iov(niov))
+			net_devmem_get_net_iov(netmem_to_net_iov(netmem));
+		return;
+	}
+	get_page(netmem_to_page(netmem));
+}
+EXPORT_SYMBOL(get_netmem);
+
+void put_netmem(netmem_ref netmem)
+{
+	struct net_iov *niov;
+
+	if (netmem_is_net_iov(netmem)) {
+		niov = netmem_to_net_iov(netmem);
+		if (net_is_devmem_iov(niov))
+			net_devmem_put_net_iov(netmem_to_net_iov(netmem));
+		return;
+	}
+
+	put_page(netmem_to_page(netmem));
+}
+EXPORT_SYMBOL(put_netmem);