Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 36 insertions, 16 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index bd0694275..5bafcfe18 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -566,6 +566,15 @@ struct ubuf_info_msgzc {
 int mm_account_pinned_pages(struct mmpin *mmp, size_t size);
 void mm_unaccount_pinned_pages(struct mmpin *mmp);
 
+/* Preserve some data across TX submission and completion.
+ *
+ * Note, this state is stored in the driver. Extending the layout
+ * might need some special care.
+ */
+struct xsk_tx_metadata_compl {
+	__u64 *tx_timestamp;
+};
+
 /* This data is invariant across clones and lives at
  * the end of the header data, ie. at skb->end.
  */
@@ -578,7 +587,10 @@ struct skb_shared_info {
 	/* Warning: this field is not always filled in (UFO)! */
 	unsigned short	gso_segs;
 	struct sk_buff	*frag_list;
-	struct skb_shared_hwtstamps hwtstamps;
+	union {
+		struct skb_shared_hwtstamps hwtstamps;
+		struct xsk_tx_metadata_compl xsk_meta;
+	};
 	unsigned int	gso_type;
 	u32		tskey;
 
@@ -736,13 +748,10 @@ typedef unsigned char *sk_buff_data_t;
  *	@list: queue head
  *	@ll_node: anchor in an llist (eg socket defer_list)
  *	@sk: Socket we are owned by
- *	@ip_defrag_offset: (aka @sk) alternate use of @sk, used in
- *		fragmentation management
  *	@dev: Device we arrived on/are leaving by
  *	@dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL
  *	@cb: Control buffer. Free for use by every layer. Put private vars here
  *	@_skb_refdst: destination entry (with norefcount bit)
- *	@sp: the security path, used for xfrm
  *	@len: Length of actual data
  *	@data_len: Data length
  *	@mac_len: Length of link layer header
@@ -776,7 +785,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue)
  *	@_sk_redir: socket redirection information for skmsg
  *	@_nfct: Associated connection, if any (with nfctinfo bits)
- *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
  *	@skb_iif: ifindex of device we arrived on
  *	@tc_index: Traffic control index
  *	@hash: the packet hash
@@ -860,10 +868,7 @@ struct sk_buff {
 		struct llist_node	ll_node;
 	};
 
-	union {
-		struct sock		*sk;
-		int			ip_defrag_offset;
-	};
+	struct sock		*sk;
 
 	union {
 		ktime_t		tstamp;
@@ -1057,7 +1062,7 @@ struct sk_buff {
 	refcount_t		users;
 
 #ifdef CONFIG_SKB_EXTENSIONS
-	/* only useable after checking ->active_extensions != 0 */
+	/* only usable after checking ->active_extensions != 0 */
 	struct skb_ext		*extensions;
 #endif
 };
@@ -2632,6 +2637,8 @@ static inline void skb_put_u8(struct sk_buff *skb, u8 val)
 void *skb_push(struct sk_buff *skb, unsigned int len);
 static inline void *__skb_push(struct sk_buff *skb, unsigned int len)
 {
+	DEBUG_NET_WARN_ON_ONCE(len > INT_MAX);
+
 	skb->data -= len;
 	skb->len  += len;
 	return skb->data;
@@ -2640,6 +2647,8 @@ static inline void *__skb_push(struct sk_buff *skb, unsigned int len)
 void *skb_pull(struct sk_buff *skb, unsigned int len);
 static inline void *__skb_pull(struct sk_buff *skb, unsigned int len)
 {
+	DEBUG_NET_WARN_ON_ONCE(len > INT_MAX);
+
 	skb->len -= len;
 	if (unlikely(skb->len < skb->data_len)) {
 #if defined(CONFIG_DEBUG_NET)
@@ -2664,6 +2673,8 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta);
 static inline enum skb_drop_reason
 pskb_may_pull_reason(struct sk_buff *skb, unsigned int len)
 {
+	DEBUG_NET_WARN_ON_ONCE(len > INT_MAX);
+
 	if (likely(len <= skb_headlen(skb)))
 		return SKB_NOT_DROPPED_YET;
 
@@ -2836,6 +2847,11 @@ static inline void skb_set_inner_network_header(struct sk_buff *skb,
 	skb->inner_network_header += offset;
 }
 
+static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb)
+{
+	return skb->inner_network_header > 0;
+}
+
 static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb)
 {
 	return skb->head + skb->inner_mac_header;
@@ -3299,7 +3315,7 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask,
 					     unsigned int order)
 {
 	/* This piece of code contains several assumptions.
-	 * 1.  This is for device Rx, therefor a cold page is preferred.
+	 * 1.  This is for device Rx, therefore a cold page is preferred.
 	 * 2.  The expectation is the user wants a compound page.
 	 * 3.  If requesting a order 0 page it will not be compound
 	 *     due to the check to see if order has a value in prep_new_page
@@ -4007,6 +4023,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features
 				 unsigned int offset);
 struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
 int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len);
+int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev);
 int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
@@ -4245,10 +4262,13 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
 {
 	const void *a = skb_metadata_end(skb_a);
 	const void *b = skb_metadata_end(skb_b);
-	/* Using more efficient varaiant than plain call to memcmp(). */
-#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
 	u64 diffs = 0;
 
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    BITS_PER_LONG != 64)
+		goto slow;
+
+	/* Using more efficient variant than plain call to memcmp(). */
 	switch (meta_len) {
 #define __it(x, op) (x -= sizeof(u##op))
 #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op))
@@ -4268,11 +4288,11 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
 		fallthrough;
 	case  4: diffs |= __it_diff(a, b, 32);
 		break;
+	default:
+slow:
+		return memcmp(a - meta_len, b - meta_len, meta_len);
 	}
 	return diffs;
-#else
-	return memcmp(a - meta_len, b - meta_len, meta_len);
-#endif
 }
 
 static inline bool skb_metadata_differs(const struct sk_buff *skb_a,