Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/gi…

…t/jkirsher/net-next

Jeff Kirsher says:

====================
This series contains updates to ixgbe and igb.

Alexander Duyck (13):
  ixgbe: Initialize q_vector cpu and affinity masks correctly
  ixgbe: Enable jumbo frames support w/ SR-IOV
  ixgbe: Move message handling routines into their own functions
  ixgbe: Add mailbox API version negotiation support to ixgbe PF
  igb: Split Rx timestamping into two separate functions
  igb: Do not use header split, instead receive all frames into a
    single buffer
  igb: Combine post-processing of skb into a single function
  igb: Map entire page and sync half instead of mapping and unmapping
    half pages
  igb: Move rx_buffer related code in Rx cleanup path into separate
    function
  igb: Lock buffer size at 2K even on systems with larger pages
  igb: Combine q_vector and ring allocation into a single function
  igb: Move the calls to set the Tx and Rx queues into igb_open
  igb: Split igb_update_dca into separate Tx and Rx functions

Tushar Dave (1):
  igb: Correcting and improving small packet check and padding
====================

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

drivers/net/ethernet/intel/igb/e1000_82575.h

@@ -172,10 +172,13 @@ struct e1000_adv_tx_context_desc {
 #define E1000_DCA_RXCTRL_DESC_DCA_EN (1 << 5) /* DCA Rx Desc enable */
 #define E1000_DCA_RXCTRL_HEAD_DCA_EN (1 << 6) /* DCA Rx Desc header enable */
 #define E1000_DCA_RXCTRL_DATA_DCA_EN (1 << 7) /* DCA Rx Desc payload enable */
+#define E1000_DCA_RXCTRL_DESC_RRO_EN (1 << 9) /* DCA Rx rd Desc Relax Order */
 
 #define E1000_DCA_TXCTRL_CPUID_MASK 0x0000001F /* Tx CPUID Mask */
 #define E1000_DCA_TXCTRL_DESC_DCA_EN (1 << 5) /* DCA Tx Desc enable */
+#define E1000_DCA_TXCTRL_DESC_RRO_EN (1 << 9) /* Tx rd Desc Relax Order */
 #define E1000_DCA_TXCTRL_TX_WB_RO_EN (1 << 11) /* Tx Desc writeback RO bit */
+#define E1000_DCA_TXCTRL_DATA_RRO_EN (1 << 13) /* Tx rd data Relax Order */
 
 /* Additional DCA related definitions, note change in position of CPUID */
 #define E1000_DCA_TXCTRL_CPUID_MASK_82576 0xFF000000 /* Tx CPUID Mask */

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

@@ -132,9 +132,10 @@ struct vf_data_storage {
 #define MAXIMUM_ETHERNET_VLAN_SIZE 1522
 
 /* Supported Rx Buffer Sizes */
-#define IGB_RXBUFFER_256   256
-#define IGB_RXBUFFER_16384 16384
-#define IGB_RX_HDR_LEN     IGB_RXBUFFER_256
+#define IGB_RXBUFFER_256	256
+#define IGB_RXBUFFER_2048	2048
+#define IGB_RX_HDR_LEN		IGB_RXBUFFER_256
+#define IGB_RX_BUFSZ		IGB_RXBUFFER_2048
 
 /* How many Tx Descriptors do we need to call netif_wake_queue ? */
 #define IGB_TX_QUEUE_WAKE	16
@@ -174,11 +175,9 @@ struct igb_tx_buffer {
 };
 
 struct igb_rx_buffer {
-	struct sk_buff *skb;
 	dma_addr_t dma;
 	struct page *page;
-	dma_addr_t page_dma;
-	u32 page_offset;
+	unsigned int page_offset;
 };
 
 struct igb_tx_queue_stats {
@@ -205,22 +204,6 @@ struct igb_ring_container {
 	u8 itr;				/* current ITR setting for ring */
 };
 
-struct igb_q_vector {
-	struct igb_adapter *adapter;	/* backlink */
-	int cpu;			/* CPU for DCA */
-	u32 eims_value;			/* EIMS mask value */
-
-	struct igb_ring_container rx, tx;
-
-	struct napi_struct napi;
-
-	u16 itr_val;
-	u8 set_itr;
-	void __iomem *itr_register;
-
-	char name[IFNAMSIZ + 9];
-};
-
 struct igb_ring {
 	struct igb_q_vector *q_vector;	/* backlink to q_vector */
 	struct net_device *netdev;	/* back pointer to net_device */
@@ -232,15 +215,17 @@ struct igb_ring {
 	void *desc;			/* descriptor ring memory */
 	unsigned long flags;		/* ring specific flags */
 	void __iomem *tail;		/* pointer to ring tail register */
+	dma_addr_t dma;			/* phys address of the ring */
+	unsigned int  size;		/* length of desc. ring in bytes */
 
 	u16 count;			/* number of desc. in the ring */
 	u8 queue_index;			/* logical index of the ring*/
 	u8 reg_idx;			/* physical index of the ring */
-	u32 size;			/* length of desc. ring in bytes */
 
 	/* everything past this point are written often */
-	u16 next_to_clean ____cacheline_aligned_in_smp;
+	u16 next_to_clean;
 	u16 next_to_use;
+	u16 next_to_alloc;
 
 	union {
 		/* TX */
@@ -251,12 +236,30 @@ struct igb_ring {
 		};
 		/* RX */
 		struct {
+			struct sk_buff *skb;
 			struct igb_rx_queue_stats rx_stats;
 			struct u64_stats_sync rx_syncp;
 		};
 	};
-	/* Items past this point are only used during ring alloc / free */
-	dma_addr_t dma;                /* phys address of the ring */
+} ____cacheline_internodealigned_in_smp;
+
+struct igb_q_vector {
+	struct igb_adapter *adapter;	/* backlink */
+	int cpu;			/* CPU for DCA */
+	u32 eims_value;			/* EIMS mask value */
+
+	u16 itr_val;
+	u8 set_itr;
+	void __iomem *itr_register;
+
+	struct igb_ring_container rx, tx;
+
+	struct napi_struct napi;
+	struct rcu_head rcu;	/* to avoid race with update stats on free */
+	char name[IFNAMSIZ + 9];
+
+	/* for dynamic allocation of rings associated with this q_vector */
+	struct igb_ring ring[0] ____cacheline_internodealigned_in_smp;
 };
 
 enum e1000_ring_flags_t {
@@ -442,9 +445,20 @@ extern void igb_ptp_stop(struct igb_adapter *adapter);
 extern void igb_ptp_reset(struct igb_adapter *adapter);
 extern void igb_ptp_tx_work(struct work_struct *work);
 extern void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter);
-extern void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector,
-				union e1000_adv_rx_desc *rx_desc,
+extern void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector,
 				struct sk_buff *skb);
+extern void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector,
+				unsigned char *va,
+				struct sk_buff *skb);
+static inline void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector,
+				       union e1000_adv_rx_desc *rx_desc,
+				       struct sk_buff *skb)
+{
+	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TS) &&
+	    !igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))
+		igb_ptp_rx_rgtstamp(q_vector, skb);
+}
+
 extern int igb_ptp_hwtstamp_ioctl(struct net_device *netdev,
 				  struct ifreq *ifr, int cmd);
 #endif /* CONFIG_IGB_PTP */

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

@@ -37,6 +37,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
+#include <linux/highmem.h>
 
 #include "igb.h"
 
@@ -1685,16 +1686,24 @@ static void igb_create_lbtest_frame(struct sk_buff *skb,
 	memset(&skb->data[frame_size + 12], 0xAF, 1);
 }
 
-static int igb_check_lbtest_frame(struct sk_buff *skb, unsigned int frame_size)
+static int igb_check_lbtest_frame(struct igb_rx_buffer *rx_buffer,
+				  unsigned int frame_size)
 {
-	frame_size /= 2;
-	if (*(skb->data + 3) == 0xFF) {
-		if ((*(skb->data + frame_size + 10) == 0xBE) &&
-		   (*(skb->data + frame_size + 12) == 0xAF)) {
-			return 0;
-		}
-	}
-	return 13;
+	unsigned char *data;
+	bool match = true;
+
+	frame_size >>= 1;
+
+	data = kmap(rx_buffer->page);
+
+	if (data[3] != 0xFF ||
+	    data[frame_size + 10] != 0xBE ||
+	    data[frame_size + 12] != 0xAF)
+		match = false;
+
+	kunmap(rx_buffer->page);
+
+	return match;
 }
 
 static int igb_clean_test_rings(struct igb_ring *rx_ring,
@@ -1704,9 +1713,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
 	union e1000_adv_rx_desc *rx_desc;
 	struct igb_rx_buffer *rx_buffer_info;
 	struct igb_tx_buffer *tx_buffer_info;
-	struct netdev_queue *txq;
 	u16 rx_ntc, tx_ntc, count = 0;
-	unsigned int total_bytes = 0, total_packets = 0;
 
 	/* initialize next to clean and descriptor values */
 	rx_ntc = rx_ring->next_to_clean;
@@ -1717,21 +1724,24 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
 		/* check rx buffer */
 		rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc];
 
-		/* unmap rx buffer, will be remapped by alloc_rx_buffers */
-		dma_unmap_single(rx_ring->dev,
-				 rx_buffer_info->dma,
-				 IGB_RX_HDR_LEN,
-				 DMA_FROM_DEVICE);
-		rx_buffer_info->dma = 0;
+		/* sync Rx buffer for CPU read */
+		dma_sync_single_for_cpu(rx_ring->dev,
+					rx_buffer_info->dma,
+					IGB_RX_BUFSZ,
+					DMA_FROM_DEVICE);
 
 		/* verify contents of skb */
-		if (!igb_check_lbtest_frame(rx_buffer_info->skb, size))
+		if (igb_check_lbtest_frame(rx_buffer_info, size))
 			count++;
 
+		/* sync Rx buffer for device write */
+		dma_sync_single_for_device(rx_ring->dev,
+					   rx_buffer_info->dma,
+					   IGB_RX_BUFSZ,
+					   DMA_FROM_DEVICE);
+
 		/* unmap buffer on tx side */
 		tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc];
-		total_bytes += tx_buffer_info->bytecount;
-		total_packets += tx_buffer_info->gso_segs;
 		igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info);
 
 		/* increment rx/tx next to clean counters */
@@ -1746,8 +1756,7 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring,
 		rx_desc = IGB_RX_DESC(rx_ring, rx_ntc);
 	}
 
-	txq = netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index);
-	netdev_tx_completed_queue(txq, total_packets, total_bytes);
+	netdev_tx_reset_queue(txring_txq(tx_ring));
 
 	/* re-map buffers to ring, store next to clean values */
 	igb_alloc_rx_buffers(rx_ring, count);