Merging upstream version 6.8.9.

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

1 files changed, 77 insertions, 17 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 78cb3304fb..71dee435d5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -337,7 +337,7 @@ static struct sk_buff *napi_skb_cache_get(void)
 	}
 
 	skb = nc->skb_cache[--nc->skb_count];
-	kasan_unpoison_object_data(skbuff_cache, skb);
+	kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache));
 
 	return skb;
 }
@@ -890,6 +890,11 @@ static void skb_clone_fraglist(struct sk_buff *skb)
 		skb_get(list);
 }
 
+static bool is_pp_page(struct page *page)
+{
+	return (page->pp_magic & ~0x3UL) == PP_SIGNATURE;
+}
+
 #if IS_ENABLED(CONFIG_PAGE_POOL)
 bool napi_pp_put_page(struct page *page, bool napi_safe)
 {
@@ -905,7 +910,7 @@ bool napi_pp_put_page(struct page *page, bool napi_safe)
 	 * and page_is_pfmemalloc() is checked in __page_pool_put_page()
 	 * to avoid recycling the pfmemalloc page.
 	 */
-	if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE))
+	if (unlikely(!is_pp_page(page)))
 		return false;
 
 	pp = page->pp;
@@ -942,6 +947,37 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe)
 	return napi_pp_put_page(virt_to_page(data), napi_safe);
 }
 
+/**
+ * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb
+ * @skb:	page pool aware skb
+ *
+ * Increase the fragment reference count (pp_ref_count) of a skb. This is
+ * intended to gain fragment references only for page pool aware skbs,
+ * i.e. when skb->pp_recycle is true, and not for fragments in a
+ * non-pp-recycling skb. It has a fallback to increase references on normal
+ * pages, as page pool aware skbs may also have normal page fragments.
+ */
+static int skb_pp_frag_ref(struct sk_buff *skb)
+{
+	struct skb_shared_info *shinfo;
+	struct page *head_page;
+	int i;
+
+	if (!skb->pp_recycle)
+		return -EINVAL;
+
+	shinfo = skb_shinfo(skb);
+
+	for (i = 0; i < shinfo->nr_frags; i++) {
+		head_page = compound_head(skb_frag_page(&shinfo->frags[i]));
+		if (likely(is_pp_page(head_page)))
+			page_pool_ref_page(head_page);
+		else
+			page_ref_inc(head_page);
+	}
+	return 0;
+}
+
 static void skb_kfree_head(void *head, unsigned int end_offset)
 {
 	if (end_offset == SKB_SMALL_HEAD_HEADROOM)
@@ -1309,13 +1345,15 @@ static void napi_skb_cache_put(struct sk_buff *skb)
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 	u32 i;
 
-	kasan_poison_object_data(skbuff_cache, skb);
+	if (!kasan_mempool_poison_object(skb))
+		return;
+
 	nc->skb_cache[nc->skb_count++] = skb;
 
 	if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {
 		for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++)
-			kasan_unpoison_object_data(skbuff_cache,
-						   nc->skb_cache[i]);
+			kasan_mempool_unpoison_object(nc->skb_cache[i],
+						kmem_cache_size(skbuff_cache));
 
 		kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF,
 				     nc->skb_cache + NAPI_SKB_CACHE_HALF);
@@ -5767,17 +5805,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 		return false;
 
 	/* In general, avoid mixing page_pool and non-page_pool allocated
-	 * pages within the same SKB. Additionally avoid dealing with clones
-	 * with page_pool pages, in case the SKB is using page_pool fragment
-	 * references (page_pool_alloc_frag()). Since we only take full page
-	 * references for cloned SKBs at the moment that would result in
-	 * inconsistent reference counts.
-	 * In theory we could take full references if @from is cloned and
-	 * !@to->pp_recycle but its tricky (due to potential race with
-	 * the clone disappearing) and rare, so not worth dealing with.
+	 * pages within the same SKB. In theory we could take full
+	 * references if @from is cloned and !@to->pp_recycle but its
+	 * tricky (due to potential race with the clone disappearing) and
+	 * rare, so not worth dealing with.
 	 */
-	if (to->pp_recycle != from->pp_recycle ||
-	    (from->pp_recycle && skb_cloned(from)))
+	if (to->pp_recycle != from->pp_recycle)
 		return false;
 
 	if (len <= skb_tailroom(to)) {
@@ -5834,8 +5867,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	/* if the skb is not cloned this does nothing
 	 * since we set nr_frags to 0.
 	 */
-	for (i = 0; i < from_shinfo->nr_frags; i++)
-		__skb_frag_ref(&from_shinfo->frags[i]);
+	if (skb_pp_frag_ref(from)) {
+		for (i = 0; i < from_shinfo->nr_frags; i++)
+			__skb_frag_ref(&from_shinfo->frags[i]);
+	}
 
 	to->truesize += delta;
 	to->len += len;
@@ -5962,6 +5997,31 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
 }
 EXPORT_SYMBOL(skb_ensure_writable);
 
+int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev)
+{
+	int needed_headroom = dev->needed_headroom;
+	int needed_tailroom = dev->needed_tailroom;
+
+	/* For tail taggers, we need to pad short frames ourselves, to ensure
+	 * that the tail tag does not fail at its role of being at the end of
+	 * the packet, once the conduit interface pads the frame. Account for
+	 * that pad length here, and pad later.
+	 */
+	if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
+		needed_tailroom += ETH_ZLEN - skb->len;
+	/* skb_headroom() returns unsigned int... */
+	needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
+	needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
+
+	if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb)))
+		/* No reallocation needed, yay! */
+		return 0;
+
+	return pskb_expand_head(skb, needed_headroom, needed_tailroom,
+				GFP_ATOMIC);
+}
+EXPORT_SYMBOL(skb_ensure_writable_head_tail);
+
 /* remove VLAN header from packet and update csum accordingly.
  * expects a non skb_vlan_tag_present skb with a vlan tag payload
  */