Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue

Jeff Kirsher says:

====================
40GbE Intel Wired LAN Driver Updates 2017-04-08

This series contains updates to i40e and i40evf only.

Mitch fixes an issue where the client driver (i40iw) was attempting to
load on x710 devices (which do not support iWARP), so only register with
the client if iWARP is supported.

Jake fixes up error messages to better clarify to the user when adding a
invalid flow type.  Updates the driver to look up the MAC address from
eth_get_platform_mac_address() first before checking what the firmware
provides.  Cleans up code so we are not repeating a duplicate loop, by
checking both transmit and receive queues in a single loop.  Also cleans
up flags never used, so remove the definitions.

Alex does cleanup so that we are always updating pf->flags when a change
is made to the private flags.  Adds support for 3K buffers to the receive
path so that we can provide the additional padding needed in the event
of NET_IP_ALIGN being non-zero or a cache line being greater than 64.
Adds support for build_skb() to i40e/i40evf.

Maciej adjusts the scope of the rtnl lock held during reset because it
was stopping other PFs from running their reset procedures.

Alan reduces code complexity in i40e_detect_recover_hung_queue().
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 84 insertions, 32 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index ebffca0cefac..20691d2bf113 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -533,14 +533,15 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi,
 			break;
 		default:
 			/* We cannot support masking based on protocol */
-			goto unsupported_flow;
+			dev_info(&pf->pdev->dev, "Unsupported IPv4 protocol 0x%02x\n",
+				 input->ip4_proto);
+			return -EINVAL;
 		}
 		break;
 	default:
-unsupported_flow:
-		dev_info(&pf->pdev->dev, "Could not specify spec type %d\n",
+		dev_info(&pf->pdev->dev, "Unsupported flow type 0x%02x\n",
 			 input->flow_type);
-		ret = -EINVAL;
+		return -EINVAL;
 	}
 
 	/* The buffer allocated here will be normally be freed by
@@ -710,19 +711,15 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring)
 /**
  * i40e_get_tx_pending - how many tx descriptors not processed
  * @tx_ring: the ring of descriptors
- * @in_sw: is tx_pending being checked in SW or HW
  *
  * Since there is no access to the ring head register
  * in XL710, we need to use our local copies
  **/
-u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw)
+u32 i40e_get_tx_pending(struct i40e_ring *ring)
 {
 	u32 head, tail;
 
-	if (!in_sw)
-		head = i40e_get_head(ring);
-	else
-		head = ring->next_to_clean;
+	head = i40e_get_head(ring);
 	tail = readl(ring->tail);
 
 	if (head != tail)
@@ -845,7 +842,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		 * them to be written back in case we stay in NAPI.
 		 * In this mode on X722 we do not enable Interrupt.
 		 */
-		unsigned int j = i40e_get_tx_pending(tx_ring, false);
+		unsigned int j = i40e_get_tx_pending(tx_ring);
 
 		if (budget &&
 		    ((j / WB_STRIDE) == 0) && (j > 0) &&
@@ -1141,14 +1138,15 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring)
 		dma_sync_single_range_for_cpu(rx_ring->dev,
 					      rx_bi->dma,
 					      rx_bi->page_offset,
-					      I40E_RXBUFFER_2048,
+					      rx_ring->rx_buf_len,
 					      DMA_FROM_DEVICE);
 
 		/* free resources associated with mapping */
 		dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma,
-				     PAGE_SIZE,
+				     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;
@@ -1250,6 +1248,17 @@ 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
@@ -1270,7 +1279,7 @@ 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;
@@ -1278,7 +1287,7 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 
 	/* map page for use */
 	dma = dma_map_page_attrs(rx_ring->dev, page, 0,
-				 PAGE_SIZE,
+				 i40e_rx_pg_size(rx_ring),
 				 DMA_FROM_DEVICE,
 				 I40E_RX_DMA_ATTR);
 
@@ -1286,14 +1295,14 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring,
 	 * 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;
@@ -1346,7 +1355,7 @@ bool i40e_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count)
 		/* sync the buffer for use by the device */
 		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
 						 bi->page_offset,
-						 I40E_RXBUFFER_2048,
+						 rx_ring->rx_buf_len,
 						 DMA_FROM_DEVICE);
 
 		/* Refresh the desc even if buffer_addrs didn't change
@@ -1648,9 +1657,6 @@ static inline bool i40e_page_is_reusable(struct page *page)
  **/
 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;
 
@@ -1663,7 +1669,9 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer)
 	if (unlikely((page_count(page) - pagecnt_bias) > 1))
 		return false;
 #else
-	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
 
@@ -1697,9 +1705,9 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring,
 			     unsigned int size)
 {
 #if (PAGE_SIZE < 8192)
-	unsigned int truesize = I40E_RXBUFFER_2048;
+	unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2;
 #else
-	unsigned int truesize = SKB_DATA_ALIGN(size);
+	unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring));
 #endif
 
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page,
@@ -1758,7 +1766,7 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 {
 	void *va = page_address(rx_buffer->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 = SKB_DATA_ALIGN(size);
 #endif
@@ -1808,6 +1816,51 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring,
 }
 
 /**
+ * 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(va);
+#if L1_CACHE_BYTES < 128
+	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;
+
+	/* update pointers within the skb to store the data */
+	skb_reserve(skb, I40E_SKB_PAD);
+	__skb_put(skb, size);
+
+	/* buffer is used by skb, update page_offset */
+#if (PAGE_SIZE < 8192)
+	rx_buffer->page_offset ^= truesize;
+#else
+	rx_buffer->page_offset += truesize;
+#endif
+
+	return 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
@@ -1824,7 +1877,8 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring,
 		rx_ring->rx_stats.page_reuse_count++;
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE,
+		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);
@@ -1930,6 +1984,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* 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);
 
@@ -2125,8 +2181,6 @@ int i40e_napi_poll(struct napi_struct *napi, int budget)
 		return 0;
 	}
 
-	/* Clear hung_detected bit */
-	clear_bit(I40E_Q_VECTOR_HUNG_DETECT, &q_vector->hung_detected);
 	/* Since the actual Tx work is minimal, we can give the Tx a larger
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
@@ -2262,8 +2316,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	/* Due to lack of space, no more new filters can be programmed */
 	if (th->syn && (pf->hw_disabled_flags & I40E_FLAG_FD_ATR_ENABLED))
 		return;
-	if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
-	    (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE))) {
+	if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) {
 		/* HW ATR eviction will take care of removing filters on FIN
 		 * and RST packets.
 		 */
@@ -2325,8 +2378,7 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 			I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
 			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
 
-	if ((pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) &&
-	    (!(pf->hw_disabled_flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)))
+	if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE)
 		dtype_cmd |= I40E_TXD_FLTR_QW1_ATR_MASK;
 
 	fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);