iavf: switch to Page Pool

Now that the IAVF driver simply uses dev_alloc_page() + free_page() with
no custom recycling logics, it can easily be switched to using Page
Pool / libeth API instead.
This allows to removing the whole dancing around headroom, HW buffer
size, and page order. All DMA-for-device is now done in the PP core,
for-CPU -- in the libeth helper.
Use skb_mark_for_recycle() to bring back the recycling and restore the
performance. Speaking of performance: on par with the baseline and
faster with the PP optimization series applied. But the memory usage for
1500b MTU is now almost 2x lower (x86_64) thanks to allocating a page
every second descriptor.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

1 files changed, 75 insertions, 182 deletions

diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 2ec68b51bebe..26b424fd6718 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -690,11 +690,8 @@ err:
  **/
 static void iavf_clean_rx_ring(struct iavf_ring *rx_ring)
 {
-	unsigned long bi_size;
-	u16 i;
-
 	/* ring already cleared, nothing to do */
-	if (!rx_ring->rx_bi)
+	if (!rx_ring->rx_fqes)
 		return;
 
 	if (rx_ring->skb) {
@@ -702,40 +699,16 @@ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring)
 		rx_ring->skb = NULL;
 	}
 
-	/* Free all the Rx ring sk_buffs */
-	for (i = 0; i < rx_ring->count; i++) {
-		struct iavf_rx_buffer *rx_bi = &rx_ring->rx_bi[i];
+	/* Free all the Rx ring buffers */
+	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];
 
-		if (!rx_bi->page)
-			continue;
+		page_pool_put_full_page(rx_ring->pp, rx_fqes->page, false);
 
-		/* Invalidate cache lines that may have been written to by
-		 * device so that we avoid corrupting memory.
-		 */
-		dma_sync_single_range_for_cpu(rx_ring->dev,
-					      rx_bi->dma,
-					      rx_bi->page_offset,
-					      IAVF_RXBUFFER_3072,
-					      DMA_FROM_DEVICE);
-
-		/* free resources associated with mapping */
-		dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
-				     iavf_rx_pg_size(rx_ring),
-				     DMA_FROM_DEVICE,
-				     IAVF_RX_DMA_ATTR);
-
-		__free_page(rx_bi->page);
-
-		rx_bi->page = NULL;
-		rx_bi->page_offset = 0;
+		if (unlikely(++i == rx_ring->count))
+			i = 0;
 	}
 
-	bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count;
-	memset(rx_ring->rx_bi, 0, bi_size);
-
-	/* Zero out the descriptor ring */
-	memset(rx_ring->desc, 0, rx_ring->size);
-
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
 }
@@ -748,15 +721,22 @@ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring)
  **/
 void iavf_free_rx_resources(struct iavf_ring *rx_ring)
 {
+	struct libeth_fq fq = {
+		.fqes	= rx_ring->rx_fqes,
+		.pp	= rx_ring->pp,
+	};
+
 	iavf_clean_rx_ring(rx_ring);
-	kfree(rx_ring->rx_bi);
-	rx_ring->rx_bi = NULL;
 
 	if (rx_ring->desc) {
-		dma_free_coherent(rx_ring->dev, rx_ring->size,
+		dma_free_coherent(rx_ring->pp->p.dev, rx_ring->size,
 				  rx_ring->desc, rx_ring->dma);
 		rx_ring->desc = NULL;
 	}
+
+	libeth_rx_fq_destroy(&fq);
+	rx_ring->rx_fqes = NULL;
+	rx_ring->pp = NULL;
 }
 
 /**
@@ -767,26 +747,32 @@ void iavf_free_rx_resources(struct iavf_ring *rx_ring)
  **/
 int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
-	int bi_size;
-
-	/* warn if we are about to overwrite the pointer */
-	WARN_ON(rx_ring->rx_bi);
-	bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count;
-	rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL);
-	if (!rx_ring->rx_bi)
-		goto err;
+	struct libeth_fq fq = {
+		.count		= rx_ring->count,
+		.buf_len	= LIBIE_MAX_RX_BUF_LEN,
+		.nid		= NUMA_NO_NODE,
+	};
+	int ret;
+
+	ret = libeth_rx_fq_create(&fq, &rx_ring->q_vector->napi);
+	if (ret)
+		return ret;
+
+	rx_ring->pp = fq.pp;
+	rx_ring->rx_fqes = fq.fqes;
+	rx_ring->truesize = fq.truesize;
+	rx_ring->rx_buf_len = fq.buf_len;
 
 	u64_stats_init(&rx_ring->syncp);
 
 	/* Round up to nearest 4K */
 	rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);
-	rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size,
+	rx_ring->desc = dma_alloc_coherent(fq.pp->p.dev, rx_ring->size,
 					   &rx_ring->dma, GFP_KERNEL);
 
 	if (!rx_ring->desc) {
-		dev_info(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
+		dev_info(fq.pp->p.dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n",
 			 rx_ring->size);
 		goto err;
 	}
@@ -795,9 +781,12 @@ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring)
 	rx_ring->next_to_use = 0;
 
 	return 0;
+
 err:
-	kfree(rx_ring->rx_bi);
-	rx_ring->rx_bi = NULL;
+	libeth_rx_fq_destroy(&fq);
+	rx_ring->rx_fqes = NULL;
+	rx_ring->pp = NULL;
+
 	return -ENOMEM;
 }
 
@@ -820,49 +809,6 @@ static void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val)
 }
 
 /**
- * iavf_alloc_mapped_page - recycle or make a new page
- * @rx_ring: ring to use
- * @bi: rx_buffer struct to modify
- *
- * Returns true if the page was successfully allocated or
- * reused.
- **/
-static bool iavf_alloc_mapped_page(struct iavf_ring *rx_ring,
-				   struct iavf_rx_buffer *bi)
-{
-	struct page *page = bi->page;
-	dma_addr_t dma;
-
-	/* alloc new page for storage */
-	page = dev_alloc_pages(iavf_rx_pg_order(rx_ring));
-	if (unlikely(!page)) {
-		rx_ring->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	/* map page for use */
-	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
-				 iavf_rx_pg_size(rx_ring),
-				 DMA_FROM_DEVICE,
-				 IAVF_RX_DMA_ATTR);
-
-	/* if mapping failed free memory back to system since
-	 * there isn't much point in holding memory we can't use
-	 */
-	if (dma_mapping_error(rx_ring->dev, dma)) {
-		__free_pages(page, iavf_rx_pg_order(rx_ring));
-		rx_ring->rx_stats.alloc_page_failed++;
-		return false;
-	}
-
-	bi->dma = dma;
-	bi->page = page;
-	bi->page_offset = IAVF_SKB_PAD;
-
-	return true;
-}
-
-/**
  * iavf_receive_skb - Send a completed packet up the stack
  * @rx_ring:  rx ring in play
  * @skb: packet to send up
@@ -892,38 +838,37 @@ static void iavf_receive_skb(struct iavf_ring *rx_ring,
  **/
 bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 {
+	const struct libeth_fq_fp fq = {
+		.pp		= rx_ring->pp,
+		.fqes		= rx_ring->rx_fqes,
+		.truesize	= rx_ring->truesize,
+		.count		= rx_ring->count,
+	};
 	u16 ntu = rx_ring->next_to_use;
 	union iavf_rx_desc *rx_desc;
-	struct iavf_rx_buffer *bi;
 
 	/* do nothing if no valid netdev defined */
 	if (!rx_ring->netdev || !cleaned_count)
 		return false;
 
 	rx_desc = IAVF_RX_DESC(rx_ring, ntu);
-	bi = &rx_ring->rx_bi[ntu];
 
 	do {
-		if (!iavf_alloc_mapped_page(rx_ring, bi))
-			goto no_buffers;
+		dma_addr_t addr;
 
-		/* sync the buffer for use by the device */
-		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
-						 bi->page_offset,
-						 IAVF_RXBUFFER_3072,
-						 DMA_FROM_DEVICE);
+		addr = libeth_rx_alloc(&fq, ntu);
+		if (addr == DMA_MAPPING_ERROR)
+			goto no_buffers;
 
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
-		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
+		rx_desc->read.pkt_addr = cpu_to_le64(addr);
 
 		rx_desc++;
-		bi++;
 		ntu++;
 		if (unlikely(ntu == rx_ring->count)) {
 			rx_desc = IAVF_RX_DESC(rx_ring, 0);
-			bi = rx_ring->rx_bi;
 			ntu = 0;
 		}
 
@@ -942,6 +887,8 @@ no_buffers:
 	if (rx_ring->next_to_use != ntu)
 		iavf_release_rx_desc(rx_ring, ntu);
 
+	rx_ring->rx_stats.alloc_page_failed++;
+
 	/* make sure to come back via polling to try again after
 	 * allocation failure
 	 */
@@ -1090,9 +1037,8 @@ static bool iavf_cleanup_headers(struct iavf_ring *rx_ring, struct sk_buff *skb)
 
 /**
  * iavf_add_rx_frag - Add contents of Rx buffer to sk_buff
- * @rx_ring: rx descriptor ring to transact packets on
- * @rx_buffer: buffer containing page to add
  * @skb: sk_buff to place the data into
+ * @rx_buffer: buffer containing page to add
  * @size: packet length from rx_desc
  *
  * This function will add the data contained in rx_buffer->page to the skb.
@@ -1100,106 +1046,50 @@ static bool iavf_cleanup_headers(struct iavf_ring *rx_ring, struct sk_buff *skb)
  *
  * The function will then update the page offset.
  **/
-static void iavf_add_rx_frag(struct iavf_ring *rx_ring,
-			     struct iavf_rx_buffer *rx_buffer,
-			     struct sk_buff *skb,
+static void iavf_add_rx_frag(struct sk_buff *skb,
+			     const struct libeth_fqe *rx_buffer,
 			     unsigned int size)
 {
-	unsigned int truesize = SKB_DATA_ALIGN(size + IAVF_SKB_PAD);
-
-	if (!size)
-		return;
+	u32 hr = rx_buffer->page->pp->p.offset;
 
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
-			rx_buffer->page_offset, size, truesize);
-}
-
-/**
- * iavf_get_rx_buffer - Fetch Rx buffer and synchronize data for use
- * @rx_ring: rx descriptor ring to transact packets on
- * @size: size of buffer to add to skb
- *
- * This function will pull an Rx buffer from the ring and synchronize it
- * for use by the CPU.
- */
-static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring,
-						 const unsigned int size)
-{
-	struct iavf_rx_buffer *rx_buffer;
-
-	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
-	prefetchw(rx_buffer->page);
-	if (!size)
-		return rx_buffer;
-
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      rx_buffer->dma,
-				      rx_buffer->page_offset,
-				      size,
-				      DMA_FROM_DEVICE);
-
-	return rx_buffer;
+			rx_buffer->offset + hr, size, rx_buffer->truesize);
 }
 
 /**
  * iavf_build_skb - Build skb around an existing buffer
- * @rx_ring: Rx descriptor ring to transact packets on
  * @rx_buffer: Rx buffer to pull data from
  * @size: size of buffer to add to skb
  *
  * This function builds an skb around an existing Rx buffer, taking care
  * to set up the skb correctly and avoid any memcpy overhead.
  */
-static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring,
-				      struct iavf_rx_buffer *rx_buffer,
+static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
 				      unsigned int size)
 {
-	void *va;
-	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
-				SKB_DATA_ALIGN(IAVF_SKB_PAD + size);
+	u32 hr = rx_buffer->page->pp->p.offset;
 	struct sk_buff *skb;
+	void *va;
 
-	if (!rx_buffer || !size)
-		return NULL;
 	/* prefetch first cache line of first page */
-	va = page_address(rx_buffer->page) + rx_buffer->page_offset;
-	net_prefetch(va);
+	va = page_address(rx_buffer->page) + rx_buffer->offset;
+	net_prefetch(va + hr);
 
 	/* build an skb around the page buffer */
-	skb = napi_build_skb(va - IAVF_SKB_PAD, truesize);
+	skb = napi_build_skb(va, rx_buffer->truesize);
 	if (unlikely(!skb))
 		return NULL;
 
+	skb_mark_for_recycle(skb);
+
 	/* update pointers within the skb to store the data */
-	skb_reserve(skb, IAVF_SKB_PAD);
+	skb_reserve(skb, hr);
 	__skb_put(skb, size);
 
 	return skb;
 }
 
 /**
- * iavf_put_rx_buffer - Unmap used buffer
- * @rx_ring: rx descriptor ring to transact packets on
- * @rx_buffer: rx buffer to pull data from
- *
- * This function will unmap the buffer after it's written by HW.
- */
-static void iavf_put_rx_buffer(struct iavf_ring *rx_ring,
-			       struct iavf_rx_buffer *rx_buffer)
-{
-	if (!rx_buffer)
-		return;
-
-	/* we are not reusing the buffer so unmap it */
-	dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
-			     DMA_FROM_DEVICE, IAVF_RX_DMA_ATTR);
-
-	/* clear contents of buffer_info */
-	rx_buffer->page = NULL;
-}
-
-/**
  * iavf_is_non_eop - process handling of non-EOP buffers
  * @rx_ring: Rx ring being processed
  * @rx_desc: Rx descriptor for current buffer
@@ -1252,7 +1142,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 	bool failure = false;
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
-		struct iavf_rx_buffer *rx_buffer;
+		struct libeth_fqe *rx_buffer;
 		union iavf_rx_desc *rx_desc;
 		unsigned int size;
 		u16 vlan_tag = 0;
@@ -1287,13 +1177,16 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword);
 
 		iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
-		rx_buffer = iavf_get_rx_buffer(rx_ring, size);
+
+		rx_buffer = &rx_ring->rx_fqes[rx_ring->next_to_clean];
+		if (!libeth_rx_sync_for_cpu(rx_buffer, size))
+			goto skip_data;
 
 		/* retrieve a buffer from the ring */
 		if (skb)
-			iavf_add_rx_frag(rx_ring, rx_buffer, skb, size);
+			iavf_add_rx_frag(skb, rx_buffer, size);
 		else
-			skb = iavf_build_skb(rx_ring, rx_buffer, size);
+			skb = iavf_build_skb(rx_buffer, size);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
@@ -1301,10 +1194,10 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 			break;
 		}
 
-		iavf_put_rx_buffer(rx_ring, rx_buffer);
+skip_data:
 		cleaned_count++;
 
-		if (iavf_is_non_eop(rx_ring, rx_desc, skb))
+		if (iavf_is_non_eop(rx_ring, rx_desc, skb) || unlikely(!skb))
 			continue;
 
 		/* ERR_MASK will only have valid bits if EOP set, and