Revert "net: mirror skb frag ref/unref helpers"

This reverts commit a580ea994fd37f4105028f5a85c38ff6508a2b25.

This revert is to resolve Dragos's report of page_pool leak here:
https://lore.kernel.org/lkml/20240424165646.1625690-2-dtatulea@nvidia.com/

The reverted patch interacts very badly with commit 2cc3aeb5eccc ("skbuff:
Fix a potential race while recycling page_pool packets"). The reverted
commit hopes that the pp_recycle + is_pp_page variables do not change
between the skb_frag_ref and skb_frag_unref operation. If such a change
occurs, the skb_frag_ref/unref will not operate on the same reference type.
In the case of Dragos's report, the grabbed ref was a pp ref, but the unref
was a page ref, because the pp_recycle setting on the skb was changed.

Attempting to fix this issue on the fly is risky. Lets revert and I hope
to reland this with better understanding and testing to ensure we don't
regress some edge case while streamlining skb reffing.

Fixes: a580ea994fd3 ("net: mirror skb frag ref/unref helpers")
Reported-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Link: https://lore.kernel.org/r/20240502175423.2456544-1-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 42 insertions, 4 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 28cd640a6ea9..466999a7515e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -904,6 +904,11 @@ 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;
+}
+
 int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
 		    unsigned int headroom)
 {
@@ -1025,6 +1030,37 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data)
 	return napi_pp_put_page(virt_to_page(data));
 }
 
+/**
+ * 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)
@@ -4160,7 +4196,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
 			to++;
 
 		} else {
-			__skb_frag_ref(fragfrom, skb->pp_recycle);
+			__skb_frag_ref(fragfrom);
 			skb_frag_page_copy(fragto, fragfrom);
 			skb_frag_off_copy(fragto, fragfrom);
 			skb_frag_size_set(fragto, todo);
@@ -4810,7 +4846,7 @@ normal:
 			}
 
 			*nskb_frag = (i < 0) ? skb_head_frag_to_page_desc(frag_skb) : *frag;
-			__skb_frag_ref(nskb_frag, nskb->pp_recycle);
+			__skb_frag_ref(nskb_frag);
 			size = skb_frag_size(nskb_frag);
 
 			if (pos < offset) {
@@ -5941,8 +5977,10 @@ 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], from->pp_recycle);
+	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;