Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

1 files changed, 266 insertions, 204 deletions

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index c91fcf43ccbc..dfe241a12ad0 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -28,6 +28,7 @@
 #include <net/busy_poll.h>
 
 #include "i40evf.h"
+#include "i40e_trace.h"
 #include "i40e_prototype.h"
 
 static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
@@ -137,10 +138,7 @@ u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw)
 {
 	u32 head, tail;
 
-	if (!in_sw)
-		head = i40e_get_head(ring);
-	else
-		head = ring->next_to_clean;
+	head = ring->next_to_clean;
 	tail = readl(ring->tail);
 
 	if (head != tail)
@@ -165,7 +163,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 {
 	u16 i = tx_ring->next_to_clean;
 	struct i40e_tx_buffer *tx_buf;
-	struct i40e_tx_desc *tx_head;
 	struct i40e_tx_desc *tx_desc;
 	unsigned int total_bytes = 0, total_packets = 0;
 	unsigned int budget = vsi->work_limit;
@@ -174,8 +171,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 	tx_desc = I40E_TX_DESC(tx_ring, i);
 	i -= tx_ring->count;
 
-	tx_head = I40E_TX_DESC(tx_ring, i40e_get_head(tx_ring));
-
 	do {
 		struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch;
 
@@ -186,8 +181,10 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		/* prevent any other reads prior to eop_desc */
 		read_barrier_depends();
 
-		/* we have caught up to head, no work left to do */
-		if (tx_head == tx_desc)
+		i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
+		/* if the descriptor isn't done, no work yet to do */
+		if (!(eop_desc->cmd_type_offset_bsz &
+		      cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE)))
 			break;
 
 		/* clear next_to_watch to prevent false hangs */
@@ -212,6 +209,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 
 		/* unmap remaining buffers */
 		while (tx_desc != eop_desc) {
+			i40e_trace(clean_tx_irq_unmap,
+				   tx_ring, tx_desc, tx_buf);
 
 			tx_buf++;
 			tx_desc++;
@@ -267,7 +266,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 
 		if (budget &&
 		    ((j / WB_STRIDE) == 0) && (j > 0) &&
-		    !test_bit(__I40E_DOWN, &vsi->state) &&
+		    !test_bit(__I40E_VSI_DOWN, vsi->state) &&
 		    (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
 			tx_ring->arm_wb = true;
 	}
@@ -285,7 +284,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		smp_mb();
 		if (__netif_subqueue_stopped(tx_ring->netdev,
 					     tx_ring->queue_index) &&
-		   !test_bit(__I40E_DOWN, &vsi->state)) {
+		   !test_bit(__I40E_VSI_DOWN, vsi->state)) {
 			netif_wake_subqueue(tx_ring->netdev,
 					    tx_ring->queue_index);
 			++tx_ring->tx_stats.restart_queue;
@@ -464,10 +463,6 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring)
 
 	/* round up to nearest 4K */
 	tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc);
-	/* add u32 for head writeback, align after this takes care of
-	 * guaranteeing this is at least one cache line in size
-	 */
-	tx_ring->size += sizeof(u32);
 	tx_ring->size = ALIGN(tx_ring->size, 4096);
 	tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size,
 					   &tx_ring->dma, GFP_KERNEL);
@@ -493,7 +488,6 @@ err:
  **/
 void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
 {
-	struct device *dev = rx_ring->dev;
 	unsigned long bi_size;
 	u16 i;
 
@@ -513,8 +507,22 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring)
 		if (!rx_bi->page)
 			continue;
 
-		dma_unmap_page(dev, rx_bi->dma, PAGE_SIZE, DMA_FROM_DEVICE);
-		__free_pages(rx_bi->page, 0);
+		/* 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,
+					      rx_ring->rx_buf_len,
+					      DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
+				     i40e_rx_pg_size(rx_ring),
+				     DMA_FROM_DEVICE,
+				     I40E_RX_DMA_ATTR);
+
+		__page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias);
 
 		rx_bi->page = NULL;
 		rx_bi->page_offset = 0;
@@ -615,6 +623,17 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
 }
 
 /**
+ * i40e_rx_offset - Return expected offset into page to access data
+ * @rx_ring: Ring we are requesting offset of
+ *
+ * Returns the offset value for ring into the data buffer.
+ */
+static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
+{
+	return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
+}
+
+/**
  * i40e_alloc_mapped_page - recycle or make a new page
  * @rx_ring: ring to use
  * @bi: rx_buffer struct to modify
@@ -635,27 +654,33 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	}
 
 	/* alloc new page for storage */
-	page = dev_alloc_page();
+	page = dev_alloc_pages(i40e_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(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
+				 i40e_rx_pg_size(rx_ring),
+				 DMA_FROM_DEVICE,
+				 I40E_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, 0);
+		__free_pages(page, i40e_rx_pg_order(rx_ring));
 		rx_ring->rx_stats.alloc_page_failed++;
 		return false;
 	}
 
 	bi->dma = dma;
 	bi->page = page;
-	bi->page_offset = 0;
+	bi->page_offset = i40e_rx_offset(rx_ring);
+
+	/* initialize pagecnt_bias to 1 representing we fully own page */
+	bi->pagecnt_bias = 1;
 
 	return true;
 }
@@ -702,6 +727,12 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		if (!i40e_alloc_mapped_page(rx_ring, bi))
 			goto no_buffers;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 rx_ring->rx_buf_len,
+						 DMA_FROM_DEVICE);
+
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
@@ -742,8 +773,6 @@ no_buffers:
  * @vsi: the VSI we care about
  * @skb: skb currently being received and modified
  * @rx_desc: the receive descriptor
- *
- * skb->protocol must be set before this function is called
  **/
 static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    struct sk_buff *skb,
@@ -806,13 +835,6 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
 
-	/* If there is an outer header present that might contain a checksum
-	 * we need to bump the checksum level by 1 to reflect the fact that
-	 * we are indicating we validated the inner checksum.
-	 */
-	if (decoded.tunnel_type >= I40E_RX_PTYPE_TUNNEL_IP_GRENAT)
-		skb->csum_level = 1;
-
 	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
 	switch (decoded.inner_prot) {
 	case I40E_RX_PTYPE_INNER_PROT_TCP:
@@ -895,12 +917,12 @@ void i40evf_process_skb_fields(struct i40e_ring *rx_ring,
 {
 	i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
 
-	/* modifies the skb - consumes the enet header */
-	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
-
 	i40e_rx_checksum(rx_ring->vsi, skb, rx_desc);
 
 	skb_record_rx_queue(skb, rx_ring->queue_index);
+
+	/* modifies the skb - consumes the enet header */
+	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 }
 
 /**
@@ -945,7 +967,10 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring,
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
 	/* transfer page from old buffer to new buffer */
-	*new_buff = *old_buff;
+	new_buff->dma		= old_buff->dma;
+	new_buff->page		= old_buff->page;
+	new_buff->page_offset	= old_buff->page_offset;
+	new_buff->pagecnt_bias	= old_buff->pagecnt_bias;
 }
 
 /**
@@ -966,8 +991,6 @@ static inline bool i40e_page_is_reusable(struct page *page)
  * the adapter for another receive
  *
  * @rx_buffer: buffer containing the page
- * @page: page address from rx_buffer
- * @truesize: actual size of the buffer in this page
  *
  * If page is reusable, rx_buffer->page_offset is adjusted to point to
  * an unused region in the page.
@@ -990,13 +1013,10 @@ static inline bool i40e_page_is_reusable(struct page *page)
  *
  * In either case, if the page is reusable its refcount is increased.
  **/
-static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
-				   struct page *page,
-				   const unsigned int truesize)
+static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
 {
-#if (PAGE_SIZE >= 8192)
-	unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048;
-#endif
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
+	struct page *page = rx_buffer->page;
 
 	/* Is any reuse possible? */
 	if (unlikely(!i40e_page_is_reusable(page)))
@@ -1004,21 +1024,23 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely((page_count(page) - pagecnt_bias) > 1))
 		return false;
-
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= truesize;
 #else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += truesize;
-
-	if (rx_buffer->page_offset > last_offset)
+#define I40E_LAST_OFFSET \
+	(SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048)
+	if (rx_buffer->page_offset > I40E_LAST_OFFSET)
 		return false;
 #endif
 
-	/* Inc ref count on page before passing it up to the stack */
-	get_page(page);
+	/* If we have drained the page fragment pool we need to update
+	 * the pagecnt_bias and page count so that we fully restock the
+	 * number of references the driver holds.
+	 */
+	if (unlikely(!pagecnt_bias)) {
+		page_ref_add(page, USHRT_MAX);
+		rx_buffer->pagecnt_bias = USHRT_MAX;
+	}
 
 	return true;
 }
@@ -1027,145 +1049,201 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer,
  * i40e_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
- * @size: packet length from rx_desc
  * @skb: sk_buff to place the data into
+ * @size: packet length from rx_desc
  *
  * This function will add the data contained in rx_buffer->page to the skb.
- * This is done either through a direct copy if the data in the buffer is
- * less than the skb header size, otherwise it will just attach the page as
- * a frag to the skb.
+ * It will just attach the page as a frag to the skb.
  *
- * The function will then update the page offset if necessary and return
- * true if the buffer can be reused by the adapter.
+ * The function will then update the page offset.
  **/
-static bool i40e_add_rx_frag(struct i40e_ring *rx_ring,
+static void i40e_add_rx_frag(struct i40e_ring *rx_ring,
 			     struct i40e_rx_buffer *rx_buffer,
-			     unsigned int size,
-			     struct sk_buff *skb)
+			     struct sk_buff *skb,
+			     unsigned int size)
 {
-	struct page *page = rx_buffer->page;
-	unsigned char *va = page_address(page) + rx_buffer->page_offset;
 #if (PAGE_SIZE < 8192)
-	unsigned int truesize = I40E_RXBUFFER_2048;
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
 #else
-	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+	unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring));
 #endif
-	unsigned int pull_len;
-
-	if (unlikely(skb_is_nonlinear(skb)))
-		goto add_tail_frag;
 
-	/* will the data fit in the skb we allocated? if so, just
-	 * copy it as it is pretty small anyway
-	 */
-	if (size <= I40E_RX_HDR_SIZE) {
-		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
-
-		/* page is reusable, we can reuse buffer as-is */
-		if (likely(i40e_page_is_reusable(page)))
-			return true;
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
+			rx_buffer->page_offset, size, truesize);
 
-		/* this page cannot be reused so discard it */
-		__free_pages(page, 0);
-		return false;
-	}
+	/* page is being used so we must update the page offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+}
 
-	/* we need the header to contain the greater of either
-	 * ETH_HLEN or 60 bytes if the skb->len is less than
-	 * 60 for skb_pad.
-	 */
-	pull_len = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+/**
+ * i40e_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 i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring,
+						 const unsigned int size)
+{
+	struct i40e_rx_buffer *rx_buffer;
 
-	/* align pull length to size of long to optimize
-	 * memcpy performance
-	 */
-	memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long)));
+	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
+	prefetchw(rx_buffer->page);
 
-	/* update all of the pointers */
-	va += pull_len;
-	size -= pull_len;
+	/* 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);
 
-add_tail_frag:
-	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			(unsigned long)va & ~PAGE_MASK, size, truesize);
+	/* We have pulled a buffer for use, so decrement pagecnt_bias */
+	rx_buffer->pagecnt_bias--;
 
-	return i40e_can_reuse_rx_page(rx_buffer, page, truesize);
+	return rx_buffer;
 }
 
 /**
- * i40evf_fetch_rx_buffer - Allocate skb and populate it
+ * i40e_construct_skb - Allocate skb and populate it
  * @rx_ring: rx descriptor ring to transact packets on
- * @rx_desc: descriptor containing info written by hardware
+ * @rx_buffer: rx buffer to pull data from
+ * @size: size of buffer to add to skb
  *
- * This function allocates an skb on the fly, and populates it with the page
- * data from the current receive descriptor, taking care to set up the skb
- * correctly, as well as handling calling the page recycle function if
- * necessary.
+ * This function allocates an skb.  It then populates it with the page
+ * data from the current receive descriptor, taking care to set up the
+ * skb correctly.
  */
-static inline
-struct sk_buff *i40evf_fetch_rx_buffer(struct i40e_ring *rx_ring,
-				       union i40e_rx_desc *rx_desc,
-				       struct sk_buff *skb)
+static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
+					  struct i40e_rx_buffer *rx_buffer,
+					  unsigned int size)
 {
-	u64 local_status_error_len =
-		le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	unsigned int size =
-		(local_status_error_len & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
-		I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
-	struct i40e_rx_buffer *rx_buffer;
-	struct page *page;
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+	unsigned int headlen;
+	struct sk_buff *skb;
 
-	rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean];
-	page = rx_buffer->page;
-	prefetchw(page);
+	/* prefetch first cache line of first page */
+	prefetch(va);
+#if L1_CACHE_BYTES < 128
+	prefetch(va + L1_CACHE_BYTES);
+#endif
+
+	/* allocate a skb to store the frags */
+	skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+			       I40E_RX_HDR_SIZE,
+			       GFP_ATOMIC | __GFP_NOWARN);
+	if (unlikely(!skb))
+		return NULL;
+
+	/* Determine available headroom for copy */
+	headlen = size;
+	if (headlen > I40E_RX_HDR_SIZE)
+		headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long)));
+
+	/* update all of the pointers */
+	size -= headlen;
+	if (size) {
+		skb_add_rx_frag(skb, 0, rx_buffer->page,
+				rx_buffer->page_offset + headlen,
+				size, truesize);
+
+		/* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+		rx_buffer->page_offset ^= truesize;
+#else
+		rx_buffer->page_offset += truesize;
+#endif
+	} else {
+		/* buffer is unused, reset bias back to rx_buffer */
+		rx_buffer->pagecnt_bias++;
+	}
+
+	return skb;
+}
 
-	if (likely(!skb)) {
-		void *page_addr = page_address(page) + rx_buffer->page_offset;
+/**
+ * i40e_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 *i40e_build_skb(struct i40e_ring *rx_ring,
+				      struct i40e_rx_buffer *rx_buffer,
+				      unsigned int size)
+{
+	void *va = page_address(rx_buffer->page) + rx_buffer->page_offset;
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(size);
+#endif
+	struct sk_buff *skb;
 
-		/* prefetch first cache line of first page */
-		prefetch(page_addr);
+	/* prefetch first cache line of first page */
+	prefetch(va);
 #if L1_CACHE_BYTES < 128
-		prefetch(page_addr + L1_CACHE_BYTES);
+	prefetch(va + L1_CACHE_BYTES);
 #endif
+	/* build an skb around the page buffer */
+	skb = build_skb(va - I40E_SKB_PAD, truesize);
+	if (unlikely(!skb))
+		return NULL;
 
-		/* allocate a skb to store the frags */
-		skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
-				       I40E_RX_HDR_SIZE,
-				       GFP_ATOMIC | __GFP_NOWARN);
-		if (unlikely(!skb)) {
-			rx_ring->rx_stats.alloc_buff_failed++;
-			return NULL;
-		}
+	/* update pointers within the skb to store the data */
+	skb_reserve(skb, I40E_SKB_PAD);
+	__skb_put(skb, size);
 
-		/* we will be copying header into skb->data in
-		 * pskb_may_pull so it is in our interest to prefetch
-		 * it now to avoid a possible cache miss
-		 */
-		prefetchw(skb->data);
-	}
+	/* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
 
-	/* 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 skb;
+}
 
-	/* pull page into skb */
-	if (i40e_add_rx_frag(rx_ring, rx_buffer, size, skb)) {
+/**
+ * i40e_put_rx_buffer - Clean up used buffer and either recycle or free
+ * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_buffer: rx buffer to pull data from
+ *
+ * This function will clean up the contents of the rx_buffer.  It will
+ * either recycle the bufer or unmap it and free the associated resources.
+ */
+static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
+			       struct i40e_rx_buffer *rx_buffer)
+{
+	if (i40e_can_reuse_rx_page(rx_buffer)) {
 		/* hand second half of page back to the ring */
 		i40e_reuse_rx_page(rx_ring, rx_buffer);
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
-			       DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+				     i40e_rx_pg_size(rx_ring),
+				     DMA_FROM_DEVICE, I40E_RX_DMA_ATTR);
+		__page_frag_cache_drain(rx_buffer->page,
+					rx_buffer->pagecnt_bias);
 	}
 
 	/* clear contents of buffer_info */
 	rx_buffer->page = NULL;
-
-	return skb;
 }
 
 /**
@@ -1221,7 +1299,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	bool failure = false;
 
 	while (likely(total_rx_packets < budget)) {
+		struct i40e_rx_buffer *rx_buffer;
 		union i40e_rx_desc *rx_desc;
+		unsigned int size;
 		u16 vlan_tag;
 		u8 rx_ptype;
 		u64 qword;
@@ -1238,22 +1318,40 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* status_error_len will always be zero for unused descriptors
 		 * because it's cleared in cleanup, and overlaps with hdr_addr
 		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then it will be non-zero
+		 * hardware wrote DD then the length will be non-zero
 		 */
-		if (!i40e_test_staterr(rx_desc,
-				       BIT(I40E_RX_DESC_STATUS_DD_SHIFT)))
-			break;
+		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
 
 		/* This memory barrier is needed to keep us from reading
-		 * any other fields out of the rx_desc until we know the
-		 * DD bit is set.
+		 * any other fields out of the rx_desc until we have
+		 * verified the descriptor has been written back.
 		 */
 		dma_rmb();
 
-		skb = i40evf_fetch_rx_buffer(rx_ring, rx_desc, skb);
-		if (!skb)
+		size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >>
+		       I40E_RXD_QW1_LENGTH_PBUF_SHIFT;
+		if (!size)
 			break;
 
+		i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb);
+		rx_buffer = i40e_get_rx_buffer(rx_ring, size);
+
+		/* retrieve a buffer from the ring */
+		if (skb)
+			i40e_add_rx_frag(rx_ring, rx_buffer, skb, size);
+		else if (ring_uses_build_skb(rx_ring))
+			skb = i40e_build_skb(rx_ring, rx_buffer, size);
+		else
+			skb = i40e_construct_skb(rx_ring, rx_buffer, size);
+
+		/* exit if we failed to retrieve a buffer */
+		if (!skb) {
+			rx_ring->rx_stats.alloc_buff_failed++;
+			rx_buffer->pagecnt_bias++;
+			break;
+		}
+
+		i40e_put_rx_buffer(rx_ring, rx_buffer);
 		cleaned_count++;
 
 		if (i40e_is_non_eop(rx_ring, rx_desc, skb))
@@ -1266,6 +1364,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		 */
 		if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) {
 			dev_kfree_skb_any(skb);
+			skb = NULL;
 			continue;
 		}
 
@@ -1288,6 +1387,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ?
 			   le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0;
 
+		i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
 		i40e_receive_skb(rx_ring, skb, vlan_tag);
 		skb = NULL;
 
@@ -1408,7 +1508,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi,
 	}
 
 enable_int:
-	if (!test_bit(__I40E_DOWN, &vsi->state))
+	if (!test_bit(__I40E_VSI_DOWN, vsi->state))
 		wr32(hw, INTREG(vector - 1), txval);
 
 	if (q_vector->itr_countdown)
@@ -1437,7 +1537,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget)
 	int budget_per_ring;
 	int work_done = 0;
 
-	if (test_bit(__I40E_DOWN, &vsi->state)) {
+	if (test_bit(__I40E_VSI_DOWN, vsi->state)) {
 		napi_complete(napi);
 		return 0;
 	}
@@ -1980,7 +2080,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	u16 i = tx_ring->next_to_use;
 	u32 td_tag = 0;
 	dma_addr_t dma;
-	u16 desc_count = 1;
 
 	if (tx_flags & I40E_TX_FLAGS_HW_VLAN) {
 		td_cmd |= I40E_TX_DESC_CMD_IL2TAG1;
@@ -2016,7 +2115,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 			tx_desc++;
 			i++;
-			desc_count++;
 
 			if (i == tx_ring->count) {
 				tx_desc = I40E_TX_DESC(tx_ring, 0);
@@ -2038,7 +2136,6 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 		tx_desc++;
 		i++;
-		desc_count++;
 
 		if (i == tx_ring->count) {
 			tx_desc = I40E_TX_DESC(tx_ring, 0);
@@ -2064,46 +2161,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	i40e_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
-	/* write last descriptor with EOP bit */
-	td_cmd |= I40E_TX_DESC_CMD_EOP;
-
-	/* We can OR these values together as they both are checked against
-	 * 4 below and at this point desc_count will be used as a boolean value
-	 * after this if/else block.
-	 */
-	desc_count |= ++tx_ring->packet_stride;
-
-	/* Algorithm to optimize tail and RS bit setting:
-	 * if queue is stopped
-	 *	mark RS bit
-	 *	reset packet counter
-	 * else if xmit_more is supported and is true
-	 *	advance packet counter to 4
-	 *	reset desc_count to 0
-	 *
-	 * if desc_count >= 4
-	 *	mark RS bit
-	 *	reset packet counter
-	 * if desc_count > 0
-	 *	update tail
-	 *
-	 * Note: If there are less than 4 descriptors
-	 * pending and interrupts were disabled the service task will
-	 * trigger a force WB.
-	 */
-	if (netif_xmit_stopped(txring_txq(tx_ring))) {
-		goto do_rs;
-	} else if (skb->xmit_more) {
-		/* set stride to arm on next packet and reset desc_count */
-		tx_ring->packet_stride = WB_STRIDE;
-		desc_count = 0;
-	} else if (desc_count >= WB_STRIDE) {
-do_rs:
-		/* write last descriptor with RS bit set */
-		td_cmd |= I40E_TX_DESC_CMD_RS;
-		tx_ring->packet_stride = 0;
-	}
-
+	/* write last descriptor with RS and EOP bits */
+	td_cmd |= I40E_TXD_CMD;
 	tx_desc->cmd_type_offset_bsz =
 			build_ctob(td_cmd, td_offset, size, td_tag);
 
@@ -2119,7 +2178,7 @@ do_rs:
 	first->next_to_watch = tx_desc;
 
 	/* notify HW of packet */
-	if (desc_count) {
+	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
@@ -2170,6 +2229,8 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	/* prefetch the data, we'll need it later */
 	prefetch(skb->data);
 
+	i40e_trace(xmit_frame_ring, skb, tx_ring);
+
 	count = i40e_xmit_descriptor_count(skb);
 	if (i40e_chk_linearize(skb, count)) {
 		if (__skb_linearize(skb)) {
@@ -2237,6 +2298,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 out_drop:
+	i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring);
 	dev_kfree_skb_any(first->skb);
 	first->skb = NULL;
 	return NETDEV_TX_OK;