libeth: convert to netmem

Back when the libeth Rx core was initially written, devmem was a draft
and netmem_ref didn't exist in the mainline. Now that it's here, make
libeth MP-agnostic before introducing any new code or any new library
users.
When it's known that the created PP/FQ is for header buffers, use faster
"unsafe" underscored netmem <--> virt accessors as netmem_is_net_iov()
is always false in that case, but consumes some cycles (bit test +
true branch).

Reviewed-by: Mina Almasry <[e-mail]>
Signed-off-by: Alexander Lobakin <[e-mail]>
Signed-off-by: Tony Nguyen <[e-mail]>

drivers/net/ethernet/intel/iavf/iavf_txrx.c

···
 	for (u32 i = rx_ring->next_to_clean; i != rx_ring->next_to_use; ) {
 		const struct libeth_fqe *rx_fqes = &rx_ring->rx_fqes[i];
 
-		page_pool_put_full_page(rx_ring->pp, rx_fqes->page, false);
+		libeth_rx_recycle_slow(rx_fqes->netmem);
 
 		if (unlikely(++i == rx_ring->count))
 			i = 0;
···
 			     const struct libeth_fqe *rx_buffer,
 			     unsigned int size)
 {
-	u32 hr = rx_buffer->page->pp->p.offset;
+	u32 hr = netmem_get_pp(rx_buffer->netmem)->p.offset;
 
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
-			rx_buffer->offset + hr, size, rx_buffer->truesize);
+	skb_add_rx_frag_netmem(skb, skb_shinfo(skb)->nr_frags,
+			       rx_buffer->netmem, rx_buffer->offset + hr,
+			       size, rx_buffer->truesize);
 }
 
 /**
···
 static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
 				      unsigned int size)
 {
-	u32 hr = rx_buffer->page->pp->p.offset;
+	struct page *buf_page = __netmem_to_page(rx_buffer->netmem);
+	u32 hr = buf_page->pp->p.offset;
 	struct sk_buff *skb;
 	void *va;
 
 	/* prefetch first cache line of first page */
-	va = page_address(rx_buffer->page) + rx_buffer->offset;
+	va = page_address(buf_page) + rx_buffer->offset;
 	net_prefetch(va + hr);
 
 	/* build an skb around the page buffer */

drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c

···
 			break;
 
 skip_data:
-		rx_buf->page = NULL;
+		rx_buf->netmem = 0;
 
 		IDPF_SINGLEQ_BUMP_RING_IDX(rx_q, ntc);
 		cleaned_count++;

drivers/net/ethernet/intel/idpf/idpf_txrx.c

···
  */
 static void idpf_rx_page_rel(struct libeth_fqe *rx_buf)
 {
-	if (unlikely(!rx_buf->page))
+	if (unlikely(!rx_buf->netmem))
 		return;
 
-	page_pool_put_full_page(rx_buf->page->pp, rx_buf->page, false);
+	libeth_rx_recycle_slow(rx_buf->netmem);
 
-	rx_buf->page = NULL;
+	rx_buf->netmem = 0;
 	rx_buf->offset = 0;
 }
 
···
 void idpf_rx_add_frag(struct idpf_rx_buf *rx_buf, struct sk_buff *skb,
 		      unsigned int size)
 {
-	u32 hr = rx_buf->page->pp->p.offset;
+	u32 hr = netmem_get_pp(rx_buf->netmem)->p.offset;
 
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page,
-			rx_buf->offset + hr, size, rx_buf->truesize);
+	skb_add_rx_frag_netmem(skb, skb_shinfo(skb)->nr_frags, rx_buf->netmem,
+			       rx_buf->offset + hr, size, rx_buf->truesize);
 }
 
 /**
···
 			     struct libeth_fqe *buf, u32 data_len)
 {
 	u32 copy = data_len <= L1_CACHE_BYTES ? data_len : ETH_HLEN;
+	struct page *hdr_page, *buf_page;
 	const void *src;
 	void *dst;
 
-	if (!libeth_rx_sync_for_cpu(buf, copy))
+	if (unlikely(netmem_is_net_iov(buf->netmem)) ||
+	    !libeth_rx_sync_for_cpu(buf, copy))
 		return 0;
 
-	dst = page_address(hdr->page) + hdr->offset + hdr->page->pp->p.offset;
-	src = page_address(buf->page) + buf->offset + buf->page->pp->p.offset;
-	memcpy(dst, src, LARGEST_ALIGN(copy));
+	hdr_page = __netmem_to_page(hdr->netmem);
+	buf_page = __netmem_to_page(buf->netmem);
+	dst = page_address(hdr_page) + hdr->offset + hdr_page->pp->p.offset;
+	src = page_address(buf_page) + buf->offset + buf_page->pp->p.offset;
 
+	memcpy(dst, src, LARGEST_ALIGN(copy));
 	buf->offset += copy;
 
 	return copy;
···
  */
 struct sk_buff *idpf_rx_build_skb(const struct libeth_fqe *buf, u32 size)
 {
-	u32 hr = buf->page->pp->p.offset;
+	struct page *buf_page = __netmem_to_page(buf->netmem);
+	u32 hr = buf_page->pp->p.offset;
 	struct sk_buff *skb;
 	void *va;
 
-	va = page_address(buf->page) + buf->offset;
+	va = page_address(buf_page) + buf->offset;
 	prefetch(va + hr);
 
 	skb = napi_build_skb(va, buf->truesize);
···
 
 		if (unlikely(!hdr_len && !skb)) {
 			hdr_len = idpf_rx_hsplit_wa(hdr, rx_buf, pkt_len);
-			pkt_len -= hdr_len;
+			/* If failed, drop both buffers by setting len to 0 */
+			pkt_len -= hdr_len ? : pkt_len;
 
 			u64_stats_update_begin(&rxq->stats_sync);
 			u64_stats_inc(&rxq->q_stats.hsplit_buf_ovf);
···
 			u64_stats_update_end(&rxq->stats_sync);
 		}
 
-		hdr->page = NULL;
+		hdr->netmem = 0;
 
 payload:
 		if (!libeth_rx_sync_for_cpu(rx_buf, pkt_len))
···
 			break;
 
 skip_data:
-		rx_buf->page = NULL;
+		rx_buf->netmem = 0;
 
 		idpf_rx_post_buf_refill(refillq, buf_id);
 		IDPF_RX_BUMP_NTC(rxq, ntc);

drivers/net/ethernet/intel/libeth/rx.c

···
 EXPORT_SYMBOL_GPL(libeth_rx_fq_destroy);
 
 /**
- * libeth_rx_recycle_slow - recycle a libeth page from the NAPI context
- * @page: page to recycle
+ * libeth_rx_recycle_slow - recycle libeth netmem
+ * @netmem: network memory to recycle
  *
  * To be used on exceptions or rare cases not requiring fast inline recycling.
  */
-void libeth_rx_recycle_slow(struct page *page)
+void __cold libeth_rx_recycle_slow(netmem_ref netmem)
 {
-	page_pool_recycle_direct(page->pp, page);
+	page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false);
 }
 EXPORT_SYMBOL_GPL(libeth_rx_recycle_slow);
 

include/net/libeth/rx.h

···
 /* SPDX-License-Identifier: GPL-2.0-only */
-/* Copyright (C) 2024 Intel Corporation */
+/* Copyright (C) 2024-2025 Intel Corporation */
 
 #ifndef __LIBETH_RX_H
 #define __LIBETH_RX_H
···
 
 /**
  * struct libeth_fqe - structure representing an Rx buffer (fill queue element)
- * @page: page holding the buffer
+ * @netmem: network memory reference holding the buffer
  * @offset: offset from the page start (to the headroom)
  * @truesize: total space occupied by the buffer (w/ headroom and tailroom)
  *
···
  * former, @offset is always 0 and @truesize is always ```PAGE_SIZE```.
  */
 struct libeth_fqe {
-	struct page		*page;
+	netmem_ref		netmem;
 	u32			offset;
 	u32			truesize;
 } __aligned_largest;
···
 	struct libeth_fqe *buf = &fq->fqes[i];
 
 	buf->truesize = fq->truesize;
-	buf->page = page_pool_dev_alloc(fq->pp, &buf->offset, &buf->truesize);
-	if (unlikely(!buf->page))
+	buf->netmem = page_pool_dev_alloc_netmem(fq->pp, &buf->offset,
+						 &buf->truesize);
+	if (unlikely(!buf->netmem))
 		return DMA_MAPPING_ERROR;
 
-	return page_pool_get_dma_addr(buf->page) + buf->offset +
+	return page_pool_get_dma_addr_netmem(buf->netmem) + buf->offset +
 	       fq->pp->p.offset;
 }
 
-void libeth_rx_recycle_slow(struct page *page);
+void libeth_rx_recycle_slow(netmem_ref netmem);
 
 /**
  * libeth_rx_sync_for_cpu - synchronize or recycle buffer post DMA
···
 static inline bool libeth_rx_sync_for_cpu(const struct libeth_fqe *fqe,
 					  u32 len)
 {
-	struct page *page = fqe->page;
+	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(page);
+		libeth_rx_recycle_slow(netmem);
 		return false;
 	}
 
-	page_pool_dma_sync_for_cpu(page->pp, page, fqe->offset, len);
+	page_pool_dma_sync_netmem_for_cpu(netmem_get_pp(netmem), netmem,
+					  fqe->offset, len);
 
 	return true;
 }