Deriving a netmem's page pool from the ref requires loading a pointer
from the netmem_desc, which may not be cached. The driver may already
have a cached reference to the correct page pool, so add a bypass.

No functional change for existing callers.

Signed-off-by: Matt Vollrath <tactii@gmail.com>
Assisted-by: Claude:claude-5-fable
---
 include/net/libeth/rx.h | 37 ++++++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 11 deletions(-)

diff --git a/include/net/libeth/rx.h b/include/net/libeth/rx.h
index 5d991404845e..fddac084e001 100644
--- a/include/net/libeth/rx.h
+++ b/include/net/libeth/rx.h
@@ -118,36 +118,51 @@ static inline dma_addr_t libeth_rx_alloc(const struct libeth_fq_fp *fq, u32 i)
 void libeth_rx_recycle_slow(netmem_ref netmem);
 
 /**
- * libeth_rx_sync_for_cpu - synchronize or recycle buffer post DMA
+ * __libeth_rx_sync_for_cpu - synchronize or recycle buffer post DMA
+ * @pool: &page_pool the buffer was allocated from
  * @fqe: buffer to process
  * @len: frame length from the descriptor
  *
- * Process the buffer after it's written by HW. The regular path is to
- * synchronize DMA for CPU, but in case of no data it will be immediately
- * recycled back to its PP.
+ * Variant for callers which already know the buffer's pool, typically
+ * their Rx queue's fill queue pool.
  *
  * Return: true when there's data to process, false otherwise.
  */
-static inline bool libeth_rx_sync_for_cpu(const struct libeth_fqe *fqe,
-					  u32 len)
+static inline bool __libeth_rx_sync_for_cpu(const struct page_pool *pool,
+					    const struct libeth_fqe *fqe,
+					    u32 len)
 {
-	netmem_ref netmem = fqe->netmem;
-
 	/* Very rare, but possible case. The most common reason:
 	 * the last fragment contained FCS only, which was then
 	 * stripped by the HW.
 	 */
 	if (unlikely(!len)) {
-		libeth_rx_recycle_slow(netmem);
+		libeth_rx_recycle_slow(fqe->netmem);
 		return false;
 	}
 
-	page_pool_dma_sync_netmem_for_cpu(netmem_get_pp(netmem), netmem,
-					  fqe->offset, len);
+	page_pool_dma_sync_netmem_for_cpu(pool, fqe->netmem, fqe->offset, len);
 
 	return true;
 }
 
+/**
+ * libeth_rx_sync_for_cpu - synchronize or recycle buffer post DMA
+ * @fqe: buffer to process
+ * @len: frame length from the descriptor
+ *
+ * Process the buffer after it's written by HW. The regular path is to
+ * synchronize DMA for CPU, but in case of no data it will be immediately
+ * recycled back to its PP.
+ *
+ * Return: true when there's data to process, false otherwise.
+ */
+static inline bool libeth_rx_sync_for_cpu(const struct libeth_fqe *fqe,
+					  u32 len)
+{
+	return __libeth_rx_sync_for_cpu(netmem_get_pp(fqe->netmem), fqe, len);
+}
+
 /* Converting abstract packet type numbers into a software structure with
  * the packet parameters to do O(1) lookup on Rx.
  */
-- 
2.43.0