igb: Support using build_skb in the case that jumbo frames are disabled

This change makes it so that we can enable the use of build_skb for cases
where jumbo frames are disabled.  The advantage to this is that we do not
have to perform a memcpy to populate the header and as a result we see a
significant performance improvement.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

drivers/net/ethernet/intel/igb/igb.h

@@ -275,10 +275,18 @@ struct igb_q_vector {
 enum e1000_ring_flags_t {
 	IGB_RING_FLAG_RX_SCTP_CSUM,
 	IGB_RING_FLAG_RX_LB_VLAN_BSWAP,
+	IGB_RING_FLAG_RX_BUILD_SKB_ENABLED,
 	IGB_RING_FLAG_TX_CTX_IDX,
 	IGB_RING_FLAG_TX_DETECT_HANG
 };
 
+#define ring_uses_build_skb(ring) \
+	test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+#define set_ring_build_skb_enabled(ring) \
+	set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+#define clear_ring_build_skb_enabled(ring) \
+	clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags)
+
 #define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS)
 
 #define IGB_RX_DESC(R, i)	    \

drivers/net/ethernet/intel/igb/igb_main.c

@@ -3354,6 +3354,20 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	wr32(E1000_RXDCTL(reg_idx), rxdctl);
 }
 
+static void igb_set_rx_buffer_len(struct igb_adapter *adapter,
+				  struct igb_ring *rx_ring)
+{
+#define IGB_MAX_BUILD_SKB_SIZE \
+	(SKB_WITH_OVERHEAD(IGB_RX_BUFSZ) - \
+	 (NET_SKB_PAD + NET_IP_ALIGN + IGB_TS_HDR_LEN))
+
+	/* set build_skb flag */
+	if (adapter->max_frame_size <= IGB_MAX_BUILD_SKB_SIZE)
+		set_ring_build_skb_enabled(rx_ring);
+	else
+		clear_ring_build_skb_enabled(rx_ring);
+}
+
 /**
  * igb_configure_rx - Configure receive Unit after Reset
  * @adapter: board private structure
@@ -3373,8 +3387,11 @@ static void igb_configure_rx(struct igb_adapter *adapter)
 
 	/* Setup the HW Rx Head and Tail Descriptor Pointers and
 	 * the Base and Length of the Rx Descriptor Ring */
-	for (i = 0; i < adapter->num_rx_queues; i++)
-		igb_configure_rx_ring(adapter, adapter->rx_ring[i]);
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct igb_ring *rx_ring = adapter->rx_ring[i];
+		igb_set_rx_buffer_len(adapter, rx_ring);
+		igb_configure_rx_ring(adapter, rx_ring);
+	}
 }
 
 /**
@@ -6097,6 +6114,41 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring,
 					 DMA_FROM_DEVICE);
 }
 
+static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
+				  struct page *page,
+				  unsigned int truesize)
+{
+	/* avoid re-using remote pages */
+	if (unlikely(page_to_nid(page) != numa_node_id()))
+		return false;
+
+#if (PAGE_SIZE < 8192)
+	/* if we are only owner of page we can reuse it */
+	if (unlikely(page_count(page) != 1))
+		return false;
+
+	/* flip page offset to other buffer */
+	rx_buffer->page_offset ^= IGB_RX_BUFSZ;
+
+	/* since we are the only owner of the page and we need to
+	 * increment it, just set the value to 2 in order to avoid
+	 * an unnecessary locked operation
+	 */
+	atomic_set(&page->_count, 2);
+#else
+	/* move offset up to the next cache line */
+	rx_buffer->page_offset += truesize;
+
+	if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ))
+		return false;
+
+	/* bump ref count on page before it is given to the stack */
+	get_page(page);
+#endif
+
+	return true;
+}
+
 /**
  * igb_add_rx_frag - Add contents of Rx buffer to sk_buff
  * @rx_ring: rx descriptor ring to transact packets on
@@ -6119,6 +6171,11 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 {
 	struct page *page = rx_buffer->page;
 	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = IGB_RX_BUFSZ;
+#else
+	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+#endif
 
 	if ((size <= IGB_RX_HDR_LEN) && !skb_is_nonlinear(skb)) {
 		unsigned char *va = page_address(page) + rx_buffer->page_offset;
@@ -6141,38 +6198,88 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 	}
 
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			rx_buffer->page_offset, size, IGB_RX_BUFSZ);
+			rx_buffer->page_offset, size, truesize);
 
-	/* avoid re-using remote pages */
-	if (unlikely(page_to_nid(page) != numa_node_id()))
-		return false;
+	return igb_can_reuse_rx_page(rx_buffer, page, truesize);
+}
 
+static struct sk_buff *igb_build_rx_buffer(struct igb_ring *rx_ring,
+					   union e1000_adv_rx_desc *rx_desc)
+{
+	struct igb_rx_buffer *rx_buffer;
+	struct sk_buff *skb;
+	struct page *page;
+	void *page_addr;
+	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
 #if (PAGE_SIZE < 8192)
-	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
-		return false;
+	unsigned int truesize = IGB_RX_BUFSZ;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+				SKB_DATA_ALIGN(NET_SKB_PAD +
+					       NET_IP_ALIGN +
+					       size);
+#endif
 
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= IGB_RX_BUFSZ;
+	/* If we spanned a buffer we have a huge mess so test for it */
+	BUG_ON(unlikely(!igb_test_staterr(rx_desc, E1000_RXD_STAT_EOP)));
 
-	/*
-	 * since we are the only owner of the page and we need to
-	 * increment it, just set the value to 2 in order to avoid
-	 * an unnecessary locked operation
-	 */
-	atomic_set(&page->_count, 2);
-#else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += SKB_DATA_ALIGN(size);
+	/* Guarantee this function can be used by verifying buffer sizes */
+	BUILD_BUG_ON(SKB_WITH_OVERHEAD(IGB_RX_BUFSZ) < (NET_SKB_PAD +
+							NET_IP_ALIGN +
+							IGB_TS_HDR_LEN +
+							ETH_FRAME_LEN +
+							ETH_FCS_LEN));
 
-	if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ))
-		return false;
+	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+	page = rx_buffer->page;
+	prefetchw(page);
 
-	/* bump ref count on page before it is given to the stack */
-	get_page(page);
+	page_addr = page_address(page) + rx_buffer->page_offset;
+
+	/* prefetch first cache line of first page */
+	prefetch(page_addr + NET_SKB_PAD + NET_IP_ALIGN);
+#if L1_CACHE_BYTES < 128
+	prefetch(page_addr + L1_CACHE_BYTES + NET_SKB_PAD + NET_IP_ALIGN);
 #endif
 
-	return true;
+	/* build an skb to around the page buffer */
+	skb = build_skb(page_addr, truesize);
+	if (unlikely(!skb)) {
+		rx_ring->rx_stats.alloc_failed++;
+		return NULL;
+	}
+
+	/* 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,
+				      IGB_RX_BUFSZ,
+				      DMA_FROM_DEVICE);
+
+	/* update pointers within the skb to store the data */
+	skb_reserve(skb, NET_IP_ALIGN + NET_SKB_PAD);
+	__skb_put(skb, size);
+
+	/* pull timestamp out of packet data */
+	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+		igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb);
+		__skb_pull(skb, IGB_TS_HDR_LEN);
+	}
+
+	if (igb_can_reuse_rx_page(rx_buffer, page, truesize)) {
+		/* hand second half of page back to the ring */
+		igb_reuse_rx_page(rx_ring, rx_buffer);
+	} else {
+		/* we are not reusing the buffer so unmap it */
+		dma_unmap_page(rx_ring->dev, rx_buffer->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
+	}
+
+	/* clear contents of buffer_info */
+	rx_buffer->dma = 0;
+	rx_buffer->page = NULL;
+
+	return skb;
 }
 
 static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
@@ -6184,13 +6291,6 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
 
 	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
 
-	/*
-	 * This memory barrier is needed to keep us from reading
-	 * any other fields out of the rx_desc until we know the
-	 * RXD_STAT_DD bit is set
-	 */
-	rmb();
-
 	page = rx_buffer->page;
 	prefetchw(page);
 
@@ -6590,7 +6690,16 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		if (!igb_test_staterr(rx_desc, E1000_RXD_STAT_DD))
 			break;
 
+		/* This memory barrier is needed to keep us from reading
+		 * any other fields out of the rx_desc until we know the
+		 * RXD_STAT_DD bit is set
+		 */
+		rmb();
+
 		/* retrieve a buffer from the ring */
+		if (ring_uses_build_skb(rx_ring))
+			skb = igb_build_rx_buffer(rx_ring, rx_desc);
+		else
 			skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb);
 
 		/* exit if we failed to retrieve a buffer */
@@ -6678,6 +6787,14 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 	return true;
 }
 
+static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring)
+{
+	if (ring_uses_build_skb(rx_ring))
+		return NET_SKB_PAD + NET_IP_ALIGN;
+	else
+		return 0;
+}
+
 /**
  * igb_alloc_rx_buffers - Replace used receive buffers; packet split
  * @adapter: address of board private structure
@@ -6704,7 +6821,9 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 		 * 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(bi->dma +
+						     bi->page_offset +
+						     igb_rx_offset(rx_ring));
 
 		rx_desc++;
 		bi++;