Merge: CNB97: skbuff: Optimize SKB coalescing for page pool

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6972

JIRA: https://issues.redhat.com/browse/RHEL-91107

Commits
```
aaf153a ("page_pool: halve BIAS_MAX for multiple user references of a fragment")
f7dc324 ("skbuff: Optimization of SKB coalescing for page pool")
```

Signed-off-by: Ivan Vecera <ivecera@redhat.com>

Approved-by: Davide Caratti <dcaratti@redhat.com>
Approved-by: José Ignacio Tornos Martínez <jtornosm@redhat.com>
Approved-by: Petr Oros <poros@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Augusto Caringi <acaringi@redhat.com>

Author: caringi

include/net/page_pool/helpers.h

@@ -279,6 +279,11 @@ static inline long page_pool_unref_page(struct page *page, long nr)
 	return ret;
 }
 
+static inline void page_pool_ref_page(struct page *page)
+{
+	atomic_long_inc(&page->pp_ref_count);
+}
+
 static inline bool page_pool_is_last_ref(struct page *page)
 {
 	/* If page_pool_unref_page() returns 0, we were the last user */

net/core/page_pool.c

@@ -29,7 +29,7 @@
 #define DEFER_TIME (msecs_to_jiffies(1000))
 #define DEFER_WARN_INTERVAL (60 * HZ)
 
-#define BIAS_MAX	LONG_MAX
+#define BIAS_MAX	(LONG_MAX >> 1)
 
 #ifdef CONFIG_PAGE_POOL_STATS
 static DEFINE_PER_CPU(struct page_pool_recycle_stats, pp_system_recycle_stats);

net/core/skbuff.c

@@ -877,6 +877,37 @@ 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(page_pool_page_is_pp(head_page)))
+			page_pool_ref_page(head_page);
+		else
+			page_ref_inc(head_page);
+	}
+	return 0;
+}
+
 static void skb_free_head(struct sk_buff *skb)
 {
 	unsigned char *head = skb->head;
@@ -5654,17 +5685,12 @@ 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)) {
@@ -5721,8 +5747,10 @@ 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;