mlx4_en: map entire pages to increase throughput

In its receive path, mlx4_en driver maps each page chunk that it pushes
to the hardware and unmaps it when pushing it up the stack. This limits
throughput to about 3Gbps on a Power7 8-core machine.

One solution is to map the entire allocated page at once. However, this
requires that we keep track of every page fragment we give to a
descriptor. We also need to work with the discipline that all fragments will
be released (in the sense that it will not be reused by the driver
anymore) in the order they are allocated to the driver.

This requires that we don't reuse any fragments, every single one of
them must be reallocated. We do that by releasing all the fragments that
are processed and only after finished processing the descriptors, we
start the refill.

We also must somehow guarantee that we either refill all fragments in a
descriptor or none at all, without resorting to giving up a page
fragment that we would have already given. Otherwise, we would break the
discipline of only releasing the fragments in the order they were
allocated.

This has passed page allocation fault injections (restricted to the
driver by using required-start and required-end) and device hotplug
while 16 TCP streams were able to deliver more than 9Gbps.

Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -41,41 +41,75 @@
 
 #include "mlx4_en.h"
 
-
-static int mlx4_en_alloc_frag(struct mlx4_en_priv *priv,
-			      struct mlx4_en_rx_desc *rx_desc,
-			      struct page_frag *skb_frags,
-			      struct mlx4_en_rx_alloc *ring_alloc,
-			      int i)
+static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
+			       struct mlx4_en_rx_desc *rx_desc,
+			       struct mlx4_en_rx_alloc *frags,
+			       struct mlx4_en_rx_alloc *ring_alloc)
 {
-	struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
-	struct mlx4_en_rx_alloc *page_alloc = &ring_alloc[i];
+	struct mlx4_en_rx_alloc page_alloc[MLX4_EN_MAX_RX_FRAGS];
+	struct mlx4_en_frag_info *frag_info;
 	struct page *page;
 	dma_addr_t dma;
+	int i;
 
-	if (page_alloc->offset == frag_info->last_offset) {
-		/* Allocate new page */
-		page = alloc_pages(GFP_ATOMIC | __GFP_COMP, MLX4_EN_ALLOC_ORDER);
-		if (!page)
-			return -ENOMEM;
-
-		skb_frags[i].page = page_alloc->page;
-		skb_frags[i].offset = page_alloc->offset;
-		page_alloc->page = page;
-		page_alloc->offset = frag_info->frag_align;
-	} else {
-		page = page_alloc->page;
-		get_page(page);
+	for (i = 0; i < priv->num_frags; i++) {
+		frag_info = &priv->frag_info[i];
+		if (ring_alloc[i].offset == frag_info->last_offset) {
+			page = alloc_pages(GFP_ATOMIC | __GFP_COMP,
+					MLX4_EN_ALLOC_ORDER);
+			if (!page)
+				goto out;
+			dma = dma_map_page(priv->ddev, page, 0,
+				MLX4_EN_ALLOC_SIZE, PCI_DMA_FROMDEVICE);
+			if (dma_mapping_error(priv->ddev, dma)) {
+				put_page(page);
+				goto out;
+			}
+			page_alloc[i].page = page;
+			page_alloc[i].dma = dma;
+			page_alloc[i].offset = frag_info->frag_align;
+		} else {
+			page_alloc[i].page = ring_alloc[i].page;
+			get_page(ring_alloc[i].page);
+			page_alloc[i].dma = ring_alloc[i].dma;
+			page_alloc[i].offset = ring_alloc[i].offset +
+						frag_info->frag_stride;
+		}
+	}
 
-		skb_frags[i].page = page;
-		skb_frags[i].offset = page_alloc->offset;
-		page_alloc->offset += frag_info->frag_stride;
+	for (i = 0; i < priv->num_frags; i++) {
+		frags[i] = ring_alloc[i];
+		dma = ring_alloc[i].dma + ring_alloc[i].offset;
+		ring_alloc[i] = page_alloc[i];
+		rx_desc->data[i].addr = cpu_to_be64(dma);
 	}
-	dma = dma_map_single(priv->ddev, page_address(skb_frags[i].page) +
-			     skb_frags[i].offset, frag_info->frag_size,
-			     PCI_DMA_FROMDEVICE);
-	rx_desc->data[i].addr = cpu_to_be64(dma);
+
 	return 0;
+
+
+out:
+	while (i--) {
+		frag_info = &priv->frag_info[i];
+		if (ring_alloc[i].offset == frag_info->last_offset)
+			dma_unmap_page(priv->ddev, page_alloc[i].dma,
+				MLX4_EN_ALLOC_SIZE, PCI_DMA_FROMDEVICE);
+		put_page(page_alloc[i].page);
+	}
+	return -ENOMEM;
+}
+
+static void mlx4_en_free_frag(struct mlx4_en_priv *priv,
+			      struct mlx4_en_rx_alloc *frags,
+			      int i)
+{
+	struct mlx4_en_frag_info *frag_info = &priv->frag_info[i];
+
+	if (frags[i].offset == frag_info->last_offset) {
+		dma_unmap_page(priv->ddev, frags[i].dma, MLX4_EN_ALLOC_SIZE,
+					 PCI_DMA_FROMDEVICE);
+	}
+	if (frags[i].page)
+		put_page(frags[i].page);
 }
 
 static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
@@ -91,6 +125,13 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
 		if (!page_alloc->page)
 			goto out;
 
+		page_alloc->dma = dma_map_page(priv->ddev, page_alloc->page, 0,
+					MLX4_EN_ALLOC_SIZE, PCI_DMA_FROMDEVICE);
+		if (dma_mapping_error(priv->ddev, page_alloc->dma)) {
+			put_page(page_alloc->page);
+			page_alloc->page = NULL;
+			goto out;
+		}
 		page_alloc->offset = priv->frag_info[i].frag_align;
 		en_dbg(DRV, priv, "Initialized allocator:%d with page:%p\n",
 		       i, page_alloc->page);
@@ -100,6 +141,8 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
 out:
 	while (i--) {
 		page_alloc = &ring->page_alloc[i];
+		dma_unmap_page(priv->ddev, page_alloc->dma,
+				MLX4_EN_ALLOC_SIZE, PCI_DMA_FROMDEVICE);
 		put_page(page_alloc->page);
 		page_alloc->page = NULL;
 	}
@@ -117,24 +160,22 @@ static void mlx4_en_destroy_allocator(struct mlx4_en_priv *priv,
 		en_dbg(DRV, priv, "Freeing allocator:%d count:%d\n",
 		       i, page_count(page_alloc->page));
 
+		dma_unmap_page(priv->ddev, page_alloc->dma,
+				MLX4_EN_ALLOC_SIZE, PCI_DMA_FROMDEVICE);
 		put_page(page_alloc->page);
 		page_alloc->page = NULL;
 	}
 }
 
-
 static void mlx4_en_init_rx_desc(struct mlx4_en_priv *priv,
 				 struct mlx4_en_rx_ring *ring, int index)
 {
 	struct mlx4_en_rx_desc *rx_desc = ring->buf + ring->stride * index;
-	struct skb_frag_struct *skb_frags = ring->rx_info +
-					    (index << priv->log_rx_info);
 	int possible_frags;
 	int i;
 
 	/* Set size and memtype fields */
 	for (i = 0; i < priv->num_frags; i++) {
-		skb_frag_size_set(&skb_frags[i], priv->frag_info[i].frag_size);
 		rx_desc->data[i].byte_count =
 			cpu_to_be32(priv->frag_info[i].frag_size);
 		rx_desc->data[i].lkey = cpu_to_be32(priv->mdev->mr.key);
@@ -151,29 +192,14 @@ static void mlx4_en_init_rx_desc(struct mlx4_en_priv *priv,
 	}
 }
 
-
 static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 				   struct mlx4_en_rx_ring *ring, int index)
 {
 	struct mlx4_en_rx_desc *rx_desc = ring->buf + (index * ring->stride);
-	struct page_frag *skb_frags = ring->rx_info +
-				      (index << priv->log_rx_info);
-	int i;
+	struct mlx4_en_rx_alloc *frags = ring->rx_info +
+					(index << priv->log_rx_info);
 
-	for (i = 0; i < priv->num_frags; i++)
-		if (mlx4_en_alloc_frag(priv, rx_desc, skb_frags, ring->page_alloc, i))
-			goto err;
-
-	return 0;
-
-err:
-	while (i--) {
-		dma_addr_t dma = be64_to_cpu(rx_desc->data[i].addr);
-		pci_unmap_single(priv->mdev->pdev, dma, skb_frags[i].size,
-				 PCI_DMA_FROMDEVICE);
-		put_page(skb_frags[i].page);
-	}
-	return -ENOMEM;
+	return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc);
 }
 
 static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring)
@@ -185,20 +211,13 @@ static void mlx4_en_free_rx_desc(struct mlx4_en_priv *priv,
 				 struct mlx4_en_rx_ring *ring,
 				 int index)
 {
-	struct page_frag *skb_frags;
-	struct mlx4_en_rx_desc *rx_desc = ring->buf + (index << ring->log_stride);
-	dma_addr_t dma;
+	struct mlx4_en_rx_alloc *frags;
 	int nr;
 
-	skb_frags = ring->rx_info + (index << priv->log_rx_info);
+	frags = ring->rx_info + (index << priv->log_rx_info);
 	for (nr = 0; nr < priv->num_frags; nr++) {
 		en_dbg(DRV, priv, "Freeing fragment:%d\n", nr);
-		dma = be64_to_cpu(rx_desc->data[nr].addr);
-
-		en_dbg(DRV, priv, "Unmapping buffer at dma:0x%llx\n", (u64) dma);
-		dma_unmap_single(priv->ddev, dma, skb_frags[nr].size,
-				 PCI_DMA_FROMDEVICE);
-		put_page(skb_frags[nr].page);
+		mlx4_en_free_frag(priv, frags, nr);
 	}
 }
 
@@ -268,10 +287,9 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_rx_ring *ring, u32 size, u16 stride)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
-	int err;
+	int err = -ENOMEM;
 	int tmp;
 
-
 	ring->prod = 0;
 	ring->cons = 0;
 	ring->size = size;
@@ -281,7 +299,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 	ring->buf_size = ring->size * ring->stride + TXBB_SIZE;
 
 	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
-					sizeof(struct skb_frag_struct));
+					sizeof(struct mlx4_en_rx_alloc));
 	ring->rx_info = vmalloc(tmp);
 	if (!ring->rx_info)
 		return -ENOMEM;
@@ -338,7 +356,7 @@ int mlx4_en_activate_rx_rings(struct mlx4_en_priv *priv)
 		memset(ring->buf, 0, ring->buf_size);
 		mlx4_en_update_rx_prod_db(ring);
 
-		/* Initailize all descriptors */
+		/* Initialize all descriptors */
 		for (i = 0; i < ring->size; i++)
 			mlx4_en_init_rx_desc(priv, ring, i);
 
@@ -404,12 +422,10 @@ void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
 }
 
 
-/* Unmap a completed descriptor and free unused pages */
 static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 				    struct mlx4_en_rx_desc *rx_desc,
-				    struct page_frag *skb_frags,
+				    struct mlx4_en_rx_alloc *frags,
 				    struct sk_buff *skb,
-				    struct mlx4_en_rx_alloc *page_alloc,
 				    int length)
 {
 	struct skb_frag_struct *skb_frags_rx = skb_shinfo(skb)->frags;
@@ -417,26 +433,24 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 	int nr;
 	dma_addr_t dma;
 
-	/* Collect used fragments while replacing them in the HW descirptors */
+	/* Collect used fragments while replacing them in the HW descriptors */
 	for (nr = 0; nr < priv->num_frags; nr++) {
 		frag_info = &priv->frag_info[nr];
 		if (length <= frag_info->frag_prefix_size)
 			break;
+		if (!frags[nr].page)
+			goto fail;
 
-		/* Save page reference in skb */
-		__skb_frag_set_page(&skb_frags_rx[nr], skb_frags[nr].page);
-		skb_frag_size_set(&skb_frags_rx[nr], skb_frags[nr].size);
-		skb_frags_rx[nr].page_offset = skb_frags[nr].offset;
-		skb->truesize += frag_info->frag_stride;
 		dma = be64_to_cpu(rx_desc->data[nr].addr);
+		dma_sync_single_for_cpu(priv->ddev, dma, frag_info->frag_size,
+					DMA_FROM_DEVICE);
 
-		/* Allocate a replacement page */
-		if (mlx4_en_alloc_frag(priv, rx_desc, skb_frags, page_alloc, nr))
-			goto fail;
-
-		/* Unmap buffer */
-		dma_unmap_single(priv->ddev, dma, skb_frag_size(&skb_frags_rx[nr]),
-				 PCI_DMA_FROMDEVICE);
+		/* Save page reference in skb */
+		get_page(frags[nr].page);
+		__skb_frag_set_page(&skb_frags_rx[nr], frags[nr].page);
+		skb_frag_size_set(&skb_frags_rx[nr], frag_info->frag_size);
+		skb_frags_rx[nr].page_offset = frags[nr].offset;
+		skb->truesize += frag_info->frag_stride;
 	}
 	/* Adjust size of last fragment to match actual length */
 	if (nr > 0)
@@ -445,8 +459,6 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 	return nr;
 
 fail:
-	/* Drop all accumulated fragments (which have already been replaced in
-	 * the descriptor) of this packet; remaining fragments are reused... */
 	while (nr > 0) {
 		nr--;
 		__skb_frag_unref(&skb_frags_rx[nr]);
@@ -457,8 +469,7 @@ fail:
 
 static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv,
 				      struct mlx4_en_rx_desc *rx_desc,
-				      struct page_frag *skb_frags,
-				      struct mlx4_en_rx_alloc *page_alloc,
+				      struct mlx4_en_rx_alloc *frags,
 				      unsigned int length)
 {
 	struct sk_buff *skb;
@@ -476,23 +487,20 @@ static struct sk_buff *mlx4_en_rx_skb(struct mlx4_en_priv *priv,
 
 	/* Get pointer to first fragment so we could copy the headers into the
 	 * (linear part of the) skb */
-	va = page_address(skb_frags[0].page) + skb_frags[0].offset;
+	va = page_address(frags[0].page) + frags[0].offset;
 
 	if (length <= SMALL_PACKET_SIZE) {
 		/* We are copying all relevant data to the skb - temporarily
-		 * synch buffers for the copy */
+		 * sync buffers for the copy */
 		dma = be64_to_cpu(rx_desc->data[0].addr);
 		dma_sync_single_for_cpu(priv->ddev, dma, length,
 					DMA_FROM_DEVICE);
 		skb_copy_to_linear_data(skb, va, length);
-		dma_sync_single_for_device(priv->ddev, dma, length,
-					   DMA_FROM_DEVICE);
 		skb->tail += length;
 	} else {
-
 		/* Move relevant fragments to skb */
-		used_frags = mlx4_en_complete_rx_desc(priv, rx_desc, skb_frags,
-						      skb, page_alloc, length);
+		used_frags = mlx4_en_complete_rx_desc(priv, rx_desc, frags,
+							skb, length);
 		if (unlikely(!used_frags)) {
 			kfree_skb(skb);
 			return NULL;
@@ -529,12 +537,25 @@ out_loopback:
 	dev_kfree_skb_any(skb);
 }
 
+static void mlx4_en_refill_rx_buffers(struct mlx4_en_priv *priv,
+				     struct mlx4_en_rx_ring *ring)
+{
+	int index = ring->prod & ring->size_mask;
+
+	while ((u32) (ring->prod - ring->cons) < ring->actual_size) {
+		if (mlx4_en_prepare_rx_desc(priv, ring, index))
+			break;
+		ring->prod++;
+		index = ring->prod & ring->size_mask;
+	}
+}
+
 int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int budget)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_cqe *cqe;
 	struct mlx4_en_rx_ring *ring = &priv->rx_ring[cq->ring];
-	struct page_frag *skb_frags;
+	struct mlx4_en_rx_alloc *frags;
 	struct mlx4_en_rx_desc *rx_desc;
 	struct sk_buff *skb;
 	int index;
@@ -543,6 +564,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	int polled = 0;
 	int ip_summed;
 	struct ethhdr *ethh;
+	dma_addr_t dma;
 	u64 s_mac;
 
 	if (!priv->port_up)
@@ -558,7 +580,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
 		    cq->mcq.cons_index & cq->size)) {
 
-		skb_frags = ring->rx_info + (index << priv->log_rx_info);
+		frags = ring->rx_info + (index << priv->log_rx_info);
 		rx_desc = ring->buf + (index << ring->log_stride);
 
 		/*
@@ -582,8 +604,11 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 
 		/* Get pointer to first fragment since we haven't skb yet and
 		 * cast it to ethhdr struct */
-		ethh = (struct ethhdr *)(page_address(skb_frags[0].page) +
-					 skb_frags[0].offset);
+		dma = be64_to_cpu(rx_desc->data[0].addr);
+		dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh),
+					DMA_FROM_DEVICE);
+		ethh = (struct ethhdr *)(page_address(frags[0].page) +
+					 frags[0].offset);
 		s_mac = mlx4_en_mac_to_u64(ethh->h_source);
 
 		/* If source MAC is equal to our own MAC and not performing
@@ -615,10 +640,9 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 					if (!gro_skb)
 						goto next;
 
-					nr = mlx4_en_complete_rx_desc(
-						priv, rx_desc,
-						skb_frags, gro_skb,
-						ring->page_alloc, length);
+					nr = mlx4_en_complete_rx_desc(priv,
+						rx_desc, frags, gro_skb,
+						length);
 					if (!nr)
 						goto next;
 
@@ -654,8 +678,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			ring->csum_none++;
 		}
 
-		skb = mlx4_en_rx_skb(priv, rx_desc, skb_frags,
-				     ring->page_alloc, length);
+		skb = mlx4_en_rx_skb(priv, rx_desc, frags, length);
 		if (!skb) {
 			priv->stats.rx_dropped++;
 			goto next;
@@ -681,6 +704,9 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		netif_receive_skb(skb);
 
 next:
+		for (nr = 0; nr < priv->num_frags; nr++)
+			mlx4_en_free_frag(priv, frags, nr);
+
 		++cq->mcq.cons_index;
 		index = (cq->mcq.cons_index) & ring->size_mask;
 		cqe = &cq->buf[index];
@@ -696,7 +722,7 @@ out:
 	mlx4_cq_set_ci(&cq->mcq);
 	wmb(); /* ensure HW sees CQ consumer before we post new buffers */
 	ring->cons = cq->mcq.cons_index;
-	ring->prod += polled; /* Polled descriptors were realocated in place */
+	mlx4_en_refill_rx_buffers(priv, ring);
 	mlx4_en_update_rx_prod_db(ring);
 	return polled;
 }
@@ -785,7 +811,7 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
 
 	priv->num_frags = i;
 	priv->rx_skb_size = eff_mtu;
-	priv->log_rx_info = ROUNDUP_LOG2(i * sizeof(struct skb_frag_struct));
+	priv->log_rx_info = ROUNDUP_LOG2(i * sizeof(struct mlx4_en_rx_alloc));
 
 	en_dbg(DRV, priv, "Rx buffer scatter-list (effective-mtu:%d "
 		  "num_frags:%d):\n", eff_mtu, priv->num_frags);
@@ -987,8 +1013,3 @@ void mlx4_en_release_rss_steer(struct mlx4_en_priv *priv)
 	}
 	mlx4_qp_release_range(mdev->dev, rss_map->base_qpn, priv->rx_ring_num);
 }
-
-
-
-
-

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -111,7 +111,7 @@ enum {
 #define MLX4_EN_MAX_TX_SIZE	8192
 #define MLX4_EN_MAX_RX_SIZE	8192
 
-/* Minimum ring size for our page-allocation sceme to work */
+/* Minimum ring size for our page-allocation scheme to work */
 #define MLX4_EN_MIN_RX_SIZE	(MLX4_EN_ALLOC_SIZE / SMP_CACHE_BYTES)
 #define MLX4_EN_MIN_TX_SIZE	(4096 / TXBB_SIZE)
 
@@ -232,6 +232,7 @@ struct mlx4_en_tx_desc {
 
 struct mlx4_en_rx_alloc {
 	struct page *page;
+	dma_addr_t dma;
 	u16 offset;
 };