Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next

Jeff Kirsher says:

====================
Intel Wired LAN Driver Updates 2014-11-20

This series contains updates to ixgbevf, i40e and i40evf.

Emil updates ixgbevf with much of the work that Alex Duyck did while at
Intel.  First updates the driver to clear the status bits on allocation
instead of in the cleanup routine, this way we can leave the recieve
descriptor rings as a read only memory block until we actually have
buffers to give back to the hardware.  Clean up ixgbevf_clean_rx_irq()
by creating ixgbevf_process_skb_field() to merge several similar
operations into this new function.  Cleanup temporary variables within
the receive hot-path and reducing the scope of variables that do not
need to exist outside the main loop.  Save on stack space by just
storing our updated values back in next_to_clean instead of using
a stack variable, which also collapses the size the function.  Improve
performace on IOMMU enabled systems and reduce cache misses by changing
the basic receive patch for ixgbevf so that instead of receiving the
data into an skb, it is received into a double buffered page.  Add
netpoll support by creating ixgbevf_netpoll(), which is a callback for
.ndo_poll_controller to allow for the VF interface to be used with
netconsole.

Mitch provides several cleanups and trivial fixes for i40e and i40evf.
First is a fix the overloading of the msg_size field in the
arq_event_info struct by splitting the field into two and renaming to
indicate the actual function of each field.  Updates code comments
to match the actual function.  Cleanup several checkpatch.pl warnings
by adding or removing blank lines, aligning function parameters, and
correcting over-long lines (which makes the code more readable).

Shannon provides a patch for i40e to write the extra bits that will
turn off the ITR wait for the interrupt, since we want the SW INT to
go off as soon as possible.

v2: updated patch 07 based on feedback from Alex Duyck by
 - adding pfmemalloc check to a new function for reusable page
 - moved atomic_inc outside of #if/else in ixgbevf_add_rx_frag()
 - reverted the removal of the API check in ixgbevf_change_mtu()
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/i40e/i40e_adminq.c

@@ -980,10 +980,10 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw,
 
 	e->desc = *desc;
 	datalen = le16_to_cpu(desc->datalen);
-	e->msg_size = min(datalen, e->msg_size);
-	if (e->msg_buf != NULL && (e->msg_size != 0))
+	e->msg_len = min(datalen, e->buf_len);
+	if (e->msg_buf != NULL && (e->msg_len != 0))
 		memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va,
-		       e->msg_size);
+		       e->msg_len);
 
 	i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n");
 	i40e_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf,

drivers/net/ethernet/intel/i40e/i40e_adminq.h

@@ -76,7 +76,8 @@ struct i40e_asq_cmd_details {
 /* ARQ event information */
 struct i40e_arq_event_info {
 	struct i40e_aq_desc desc;
-	u16 msg_size;
+	u16 msg_len;
+	u16 buf_len;
 	u8 *msg_buf;
 };
 

drivers/net/ethernet/intel/i40e/i40e_ethtool.c

@@ -1400,7 +1400,10 @@ static int i40e_intr_test(struct net_device *netdev, u64 *data)
 	netif_info(pf, hw, netdev, "interrupt test\n");
 	wr32(&pf->hw, I40E_PFINT_DYN_CTL0,
 	     (I40E_PFINT_DYN_CTL0_INTENA_MASK |
-	      I40E_PFINT_DYN_CTL0_SWINT_TRIG_MASK));
+	      I40E_PFINT_DYN_CTL0_SWINT_TRIG_MASK |
+	      I40E_PFINT_DYN_CTL0_ITR_INDX_MASK |
+	      I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_MASK |
+	      I40E_PFINT_DYN_CTL0_SW_ITR_INDX_MASK));
 	usleep_range(1000, 2000);
 	*data = (swc_old == pf->sw_int_count);
 

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -5565,11 +5565,17 @@ static void i40e_check_hang_subtask(struct i40e_pf *pf)
 			if (!(pf->flags & I40E_FLAG_MSIX_ENABLED)) {
 				wr32(&vsi->back->hw, I40E_PFINT_DYN_CTL0,
 				     (I40E_PFINT_DYN_CTL0_INTENA_MASK |
-				      I40E_PFINT_DYN_CTL0_SWINT_TRIG_MASK));
+				      I40E_PFINT_DYN_CTL0_SWINT_TRIG_MASK |
+				      I40E_PFINT_DYN_CTL0_ITR_INDX_MASK |
+				      I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_MASK |
+				      I40E_PFINT_DYN_CTL0_SW_ITR_INDX_MASK));
 			} else {
 				u16 vec = vsi->base_vector - 1;
 				u32 val = (I40E_PFINT_DYN_CTLN_INTENA_MASK |
-					   I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK);
+				      I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
+				      I40E_PFINT_DYN_CTLN_ITR_INDX_MASK |
+				      I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK |
+				      I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK);
 				for (i = 0; i < vsi->num_q_vectors; i++, vec++)
 					wr32(&vsi->back->hw,
 					     I40E_PFINT_DYN_CTLN(vec), val);
@@ -5750,13 +5756,12 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 	if (oldval != val)
 		wr32(&pf->hw, pf->hw.aq.asq.len, val);
 
-	event.msg_size = I40E_MAX_AQ_BUF_SIZE;
-	event.msg_buf = kzalloc(event.msg_size, GFP_KERNEL);
+	event.buf_len = I40E_MAX_AQ_BUF_SIZE;
+	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
 	if (!event.msg_buf)
 		return;
 
 	do {
-		event.msg_size = I40E_MAX_AQ_BUF_SIZE; /* reinit each time */
 		ret = i40e_clean_arq_element(hw, &event, &pending);
 		if (ret == I40E_ERR_ADMIN_QUEUE_NO_WORK)
 			break;
@@ -5777,7 +5782,7 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 					le32_to_cpu(event.desc.cookie_high),
 					le32_to_cpu(event.desc.cookie_low),
 					event.msg_buf,
-					event.msg_size);
+					event.msg_len);
 			break;
 		case i40e_aqc_opc_lldp_update_mib:
 			dev_dbg(&pf->pdev->dev, "ARQ: Update LLDP MIB event received\n");

drivers/net/ethernet/intel/i40evf/i40e_adminq.c

@@ -929,10 +929,10 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw,
 
 	e->desc = *desc;
 	datalen = le16_to_cpu(desc->datalen);
-	e->msg_size = min(datalen, e->msg_size);
-	if (e->msg_buf != NULL && (e->msg_size != 0))
+	e->msg_len = min(datalen, e->buf_len);
+	if (e->msg_buf != NULL && (e->msg_len != 0))
 		memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va,
-		       e->msg_size);
+		       e->msg_len);
 
 	if (i40e_is_nvm_update_op(&e->desc))
 		hw->aq.nvm_busy = false;

drivers/net/ethernet/intel/i40evf/i40e_adminq.h

@@ -76,7 +76,8 @@ struct i40e_asq_cmd_details {
 /* ARQ event information */
 struct i40e_arq_event_info {
 	struct i40e_aq_desc desc;
-	u16 msg_size;
+	u16 msg_len;
+	u16 buf_len;
 	u8 *msg_buf;
 };
 

drivers/net/ethernet/intel/i40evf/i40evf.h

@@ -244,7 +244,7 @@ struct i40evf_adapter {
 	struct i40e_hw hw; /* defined in i40e_type.h */
 
 	enum i40evf_state_t state;
-	volatile unsigned long crit_section;
+	unsigned long crit_section;
 
 	struct work_struct watchdog_task;
 	bool netdev_registered;

drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c

@@ -58,7 +58,7 @@ static const struct i40evf_stats i40evf_gstrings_stats[] = {
 
 #define I40EVF_GLOBAL_STATS_LEN ARRAY_SIZE(i40evf_gstrings_stats)
 #define I40EVF_QUEUE_STATS_LEN(_dev) \
-	(((struct i40evf_adapter *) \
+	(((struct i40evf_adapter *)\
 		netdev_priv(_dev))->num_active_queues \
 		  * 2 * (sizeof(struct i40e_queue_stats) / sizeof(u64)))
 #define I40EVF_STATS_LEN(_dev) \
@@ -175,6 +175,7 @@ static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 static u32 i40evf_get_msglevel(struct net_device *netdev)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
+
 	return adapter->msg_enable;
 }
 
@@ -189,6 +190,7 @@ static u32 i40evf_get_msglevel(struct net_device *netdev)
 static void i40evf_set_msglevel(struct net_device *netdev, u32 data)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
+
 	adapter->msg_enable = data;
 }
 
@@ -621,7 +623,7 @@ static u32 i40evf_get_rxfh_indir_size(struct net_device *netdev)
  * i40evf_get_rxfh - get the rx flow hash indirection table
  * @netdev: network interface device structure
  * @indir: indirection table
- * @key: hash key (will be %NULL until get_rxfh_key_size is implemented)
+ * @key: hash key
  *
  * Reads the indirection table directly from the hardware. Always returns 0.
  **/
@@ -646,7 +648,7 @@ static int i40evf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key)
  * i40evf_set_rxfh - set the rx flow hash indirection table
  * @netdev: network interface device structure
  * @indir: indirection table
- * @key: hash key (will be %NULL until get_rxfh_key_size is implemented)
+ * @key: hash key
  *
  * Returns -EINVAL if the table specifies an inavlid queue id, otherwise
  * returns 0 after programming the table.

drivers/net/ethernet/intel/i40evf/i40evf_main.c

@@ -185,6 +185,7 @@ static void i40evf_tx_timeout(struct net_device *netdev)
 static void i40evf_misc_irq_disable(struct i40evf_adapter *adapter)
 {
 	struct i40e_hw *hw = &adapter->hw;
+
 	wr32(hw, I40E_VFINT_DYN_CTL01, 0);
 
 	/* read flush */
@@ -200,6 +201,7 @@ static void i40evf_misc_irq_disable(struct i40evf_adapter *adapter)
 static void i40evf_misc_irq_enable(struct i40evf_adapter *adapter)
 {
 	struct i40e_hw *hw = &adapter->hw;
+
 	wr32(hw, I40E_VFINT_DYN_CTL01, I40E_VFINT_DYN_CTL01_INTENA_MASK |
 				       I40E_VFINT_DYN_CTL01_ITR_INDX_MASK);
 	wr32(hw, I40E_VFINT_ICR0_ENA1, I40E_VFINT_ICR0_ENA_ADMINQ_MASK);
@@ -226,7 +228,6 @@ static void i40evf_irq_disable(struct i40evf_adapter *adapter)
 	}
 	/* read flush */
 	rd32(hw, I40E_VFGEN_RSTAT);
-
 }
 
 /**
@@ -253,8 +254,7 @@ void i40evf_irq_enable_queues(struct i40evf_adapter *adapter, u32 mask)
  * @adapter: board private structure
  * @mask: bitmap of vectors to trigger
  **/
-static void i40evf_fire_sw_int(struct i40evf_adapter *adapter,
-					    u32 mask)
+static void i40evf_fire_sw_int(struct i40evf_adapter *adapter, u32 mask)
 {
 	struct i40e_hw *hw = &adapter->hw;
 	int i;
@@ -551,6 +551,7 @@ static void i40evf_free_traffic_irqs(struct i40evf_adapter *adapter)
 {
 	int i;
 	int q_vectors;
+
 	q_vectors = adapter->num_msix_vectors - NONQ_VECS;
 
 	for (i = 0; i < q_vectors; i++) {
@@ -584,6 +585,7 @@ static void i40evf_configure_tx(struct i40evf_adapter *adapter)
 {
 	struct i40e_hw *hw = &adapter->hw;
 	int i;
+
 	for (i = 0; i < adapter->num_active_queues; i++)
 		adapter->tx_rings[i]->tail = hw->hw_addr + I40E_QTX_TAIL1(i);
 }
@@ -667,9 +669,9 @@ i40evf_vlan_filter *i40evf_add_vlan(struct i40evf_adapter *adapter, u16 vlan)
 	struct i40evf_vlan_filter *f;
 
 	f = i40evf_find_vlan(adapter, vlan);
-	if (NULL == f) {
+	if (!f) {
 		f = kzalloc(sizeof(*f), GFP_ATOMIC);
-		if (NULL == f)
+		if (!f)
 			return NULL;
 
 		f->vlan = vlan;
@@ -772,9 +774,9 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter,
 		udelay(1);
 
 	f = i40evf_find_filter(adapter, macaddr);
-	if (NULL == f) {
+	if (!f) {
 		f = kzalloc(sizeof(*f), GFP_ATOMIC);
-		if (NULL == f) {
+		if (!f) {
 			clear_bit(__I40EVF_IN_CRITICAL_TASK,
 				  &adapter->crit_section);
 			return NULL;
@@ -881,6 +883,7 @@ static void i40evf_napi_enable_all(struct i40evf_adapter *adapter)
 
 	for (q_idx = 0; q_idx < q_vectors; q_idx++) {
 		struct napi_struct *napi;
+
 		q_vector = adapter->q_vector[q_idx];
 		napi = &q_vector->napi;
 		napi_enable(napi);
@@ -920,6 +923,7 @@ static void i40evf_configure(struct i40evf_adapter *adapter)
 
 	for (i = 0; i < adapter->num_active_queues; i++) {
 		struct i40e_ring *ring = adapter->rx_rings[i];
+
 		i40evf_alloc_rx_buffers(ring, ring->count);
 		ring->next_to_use = ring->count - 1;
 		writel(ring->next_to_use, ring->tail);
@@ -1088,7 +1092,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		struct i40e_ring *tx_ring;
 		struct i40e_ring *rx_ring;
 
-		tx_ring = kzalloc(sizeof(struct i40e_ring) * 2, GFP_KERNEL);
+		tx_ring = kzalloc(sizeof(*tx_ring) * 2, GFP_KERNEL);
 		if (!tx_ring)
 			goto err_out;
 
@@ -1172,7 +1176,7 @@ static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter)
 	num_q_vectors = adapter->num_msix_vectors - NONQ_VECS;
 
 	for (q_idx = 0; q_idx < num_q_vectors; q_idx++) {
-		q_vector = kzalloc(sizeof(struct i40e_q_vector), GFP_KERNEL);
+		q_vector = kzalloc(sizeof(*q_vector), GFP_KERNEL);
 		if (!q_vector)
 			goto err_out;
 		q_vector->adapter = adapter;
@@ -1265,8 +1269,8 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter)
 	}
 
 	dev_info(&adapter->pdev->dev, "Multiqueue %s: Queue pair count = %u",
-		(adapter->num_active_queues > 1) ? "Enabled" :
-		"Disabled", adapter->num_active_queues);
+		 (adapter->num_active_queues > 1) ? "Enabled" : "Disabled",
+		 adapter->num_active_queues);
 
 	return 0;
 err_alloc_queues:
@@ -1284,6 +1288,7 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter)
 static void i40evf_watchdog_timer(unsigned long data)
 {
 	struct i40evf_adapter *adapter = (struct i40evf_adapter *)data;
+
 	schedule_work(&adapter->watchdog_task);
 	/* timer will be rescheduled in watchdog task */
 }
@@ -1508,7 +1513,6 @@ static void i40evf_reset_task(struct work_struct *work)
 		if ((rstat_val != I40E_VFR_VFACTIVE) &&
 		    (rstat_val != I40E_VFR_COMPLETED))
 			break;
-		else
 		msleep(I40EVF_RESET_WAIT_MS);
 	}
 	if (i == I40EVF_RESET_WAIT_COUNT) {
@@ -1523,7 +1527,6 @@ static void i40evf_reset_task(struct work_struct *work)
 		if ((rstat_val == I40E_VFR_VFACTIVE) ||
 		    (rstat_val == I40E_VFR_COMPLETED))
 			break;
-		else
 		msleep(I40EVF_RESET_WAIT_MS);
 	}
 	if (i == I40EVF_RESET_WAIT_COUNT) {
@@ -1632,8 +1635,8 @@ static void i40evf_adminq_task(struct work_struct *work)
 	if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED)
 		return;
 
-	event.msg_size = I40EVF_MAX_AQ_BUF_SIZE;
-	event.msg_buf = kzalloc(event.msg_size, GFP_KERNEL);
+	event.buf_len = I40EVF_MAX_AQ_BUF_SIZE;
+	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
 	if (!event.msg_buf)
 		return;
 
@@ -1645,11 +1648,9 @@ static void i40evf_adminq_task(struct work_struct *work)
 
 		i40evf_virtchnl_completion(adapter, v_msg->v_opcode,
 					   v_msg->v_retval, event.msg_buf,
-					   event.msg_size);
-		if (pending != 0) {
+					   event.msg_len);
+		if (pending != 0)
 			memset(event.msg_buf, 0, I40EVF_MAX_AQ_BUF_SIZE);
-			event.msg_size = I40EVF_MAX_AQ_BUF_SIZE;
-		}
 	} while (pending);
 
 	/* check for error indications */
@@ -1706,7 +1707,6 @@ static void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter)
 	for (i = 0; i < adapter->num_active_queues; i++)
 		if (adapter->tx_rings[i]->desc)
 			i40evf_free_tx_resources(adapter->tx_rings[i]);
-
 }
 
 /**
@@ -2136,7 +2136,7 @@ static void i40evf_init_task(struct work_struct *work)
 	ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
 
 	f = kzalloc(sizeof(*f), GFP_ATOMIC);
-	if (NULL == f)
+	if (!f)
 		goto err_sw_init;
 
 	ether_addr_copy(f->macaddr, adapter->hw.mac.addr);
@@ -2501,6 +2501,7 @@ static struct pci_driver i40evf_driver = {
 static int __init i40evf_init_module(void)
 {
 	int ret;
+
 	pr_info("i40evf: %s - version %s\n", i40evf_driver_string,
 		i40evf_driver_version);
 

drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c

@@ -92,8 +92,8 @@ int i40evf_verify_api_ver(struct i40evf_adapter *adapter)
 	enum i40e_virtchnl_ops op;
 	i40e_status err;
 
-	event.msg_size = I40EVF_MAX_AQ_BUF_SIZE;
-	event.msg_buf = kzalloc(event.msg_size, GFP_KERNEL);
+	event.buf_len = I40EVF_MAX_AQ_BUF_SIZE;
+	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
 	if (!event.msg_buf) {
 		err = -ENOMEM;
 		goto out;
@@ -169,15 +169,14 @@ int i40evf_get_vf_config(struct i40evf_adapter *adapter)
 
 	len =  sizeof(struct i40e_virtchnl_vf_resource) +
 		I40E_MAX_VF_VSI * sizeof(struct i40e_virtchnl_vsi_resource);
-	event.msg_size = len;
-	event.msg_buf = kzalloc(event.msg_size, GFP_KERNEL);
+	event.buf_len = len;
+	event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL);
 	if (!event.msg_buf) {
 		err = -ENOMEM;
 		goto out;
 	}
 
 	while (1) {
-		event.msg_size = len;
 		/* When the AQ is empty, i40evf_clean_arq_element will return
 		 * nonzero and this loop will terminate.
 		 */
@@ -191,7 +190,7 @@ int i40evf_get_vf_config(struct i40evf_adapter *adapter)
 	}
 
 	err = (i40e_status)le32_to_cpu(event.desc.cookie_low);
-	memcpy(adapter->vf_res, event.msg_buf, min(event.msg_size, len));
+	memcpy(adapter->vf_res, event.msg_buf, min(event.msg_len, len));
 
 	i40e_vf_parse_hw_config(hw, adapter->vf_res);
 out_alloc:
@@ -638,6 +637,7 @@ void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags)
 void i40evf_request_stats(struct i40evf_adapter *adapter)
 {
 	struct i40e_virtchnl_queue_select vqs;
+
 	if (adapter->current_op != I40E_VIRTCHNL_OP_UNKNOWN) {
 		/* no error message, this isn't crucial */
 		return;
@@ -712,7 +712,6 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 				"%s: Unknown event %d from pf\n",
 				__func__, vpe->event);
 			break;
-
 		}
 		return;
 	}

drivers/net/ethernet/intel/ixgbevf/ixgbevf.h

@@ -58,8 +58,9 @@ struct ixgbevf_tx_buffer {
 };
 
 struct ixgbevf_rx_buffer {
-	struct sk_buff *skb;
 	dma_addr_t dma;
+	struct page *page;
+	unsigned int page_offset;
 };
 
 struct ixgbevf_stats {
@@ -79,7 +80,6 @@ struct ixgbevf_tx_queue_stats {
 };
 
 struct ixgbevf_rx_queue_stats {
-	u64 non_eop_descs;
 	u64 alloc_rx_page_failed;
 	u64 alloc_rx_buff_failed;
 	u64 csum_err;
@@ -92,9 +92,10 @@ struct ixgbevf_ring {
 	void *desc;			/* descriptor ring memory */
 	dma_addr_t dma;			/* phys. address of descriptor ring */
 	unsigned int size;		/* length in bytes */
-	unsigned int count;		/* amount of descriptors */
-	unsigned int next_to_use;
-	unsigned int next_to_clean;
+	u16 count;			/* amount of descriptors */
+	u16 next_to_use;
+	u16 next_to_clean;
+	u16 next_to_alloc;
 
 	union {
 		struct ixgbevf_tx_buffer *tx_buffer_info;
@@ -110,12 +111,11 @@ struct ixgbevf_ring {
 
 	u64 hw_csum_rx_error;
 	u8 __iomem *tail;
+	struct sk_buff *skb;
 
 	u16 reg_idx; /* holds the special value that gets the hardware register
 		      * offset associated with this ring, which is different
 		      * for DCB and RSS modes */
-
-	u16 rx_buf_len;
 	int queue_index; /* needed for multiqueue queue management */
 };
 
@@ -134,12 +134,10 @@ struct ixgbevf_ring {
 
 /* Supported Rx Buffer Sizes */
 #define IXGBEVF_RXBUFFER_256   256    /* Used for packet split */
-#define IXGBEVF_RXBUFFER_2K    2048
-#define IXGBEVF_RXBUFFER_4K    4096
-#define IXGBEVF_RXBUFFER_8K    8192
-#define IXGBEVF_RXBUFFER_10K   10240
+#define IXGBEVF_RXBUFFER_2048  2048
 
 #define IXGBEVF_RX_HDR_SIZE IXGBEVF_RXBUFFER_256
+#define IXGBEVF_RX_BUFSZ    IXGBEVF_RXBUFFER_2048
 
 #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
 
@@ -307,6 +305,13 @@ static inline bool ixgbevf_qv_disable(struct ixgbevf_q_vector *q_vector)
 	((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8)
 #define EITR_REG_TO_INTS_PER_SEC EITR_INTS_PER_SEC_TO_REG
 
+/* ixgbevf_test_staterr - tests bits in Rx descriptor status and error fields */
+static inline __le32 ixgbevf_test_staterr(union ixgbe_adv_rx_desc *rx_desc,
+					  const u32 stat_err_bits)
+{
+	return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits);
+}
+
 static inline u16 ixgbevf_desc_unused(struct ixgbevf_ring *ring)
 {
 	u16 ntc = ring->next_to_clean;
@@ -339,8 +344,10 @@ static inline void ixgbevf_write_tail(struct ixgbevf_ring *ring, u32 value)
 
 /* board specific private data structure */
 struct ixgbevf_adapter {
-	struct timer_list watchdog_timer;
+	/* this field must be first, see ixgbevf_process_skb_fields */
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
+
+	struct timer_list watchdog_timer;
 	struct work_struct reset_task;
 	struct ixgbevf_q_vector *q_vector[MAX_MSIX_Q_VECTORS];
 
@@ -363,7 +370,6 @@ struct ixgbevf_adapter {
 	struct ixgbevf_ring *rx_ring[MAX_TX_QUEUES]; /* One per active queue */
 	u64 hw_csum_rx_error;
 	u64 hw_rx_no_dma_resources;
-	u64 non_eop_descs;
 	int num_msix_vectors;
 	u32 alloc_rx_page_failed;
 	u32 alloc_rx_buff_failed;
@@ -373,7 +379,7 @@ struct ixgbevf_adapter {
 	 */
 	u32 flags;
 #define IXGBE_FLAG_IN_WATCHDOG_TASK             (u32)(1)
-#define IXGBE_FLAG_IN_NETPOLL                   (u32)(1 << 1)
+
 #define IXGBEVF_FLAG_QUEUE_RESET_REQUESTED	(u32)(1 << 2)
 
 	struct msix_entry *msix_entries;
@@ -423,11 +429,6 @@ enum ixbgevf_state_t {
 	__IXGBEVF_WORK_INIT,
 };
 
-struct ixgbevf_cb {
-	struct sk_buff *prev;
-};
-#define IXGBE_CB(skb) ((struct ixgbevf_cb *)(skb)->cb)
-
 enum ixgbevf_boards {
 	board_82599_vf,
 	board_X540_vf,

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -143,21 +143,6 @@ u32 ixgbevf_read_reg(struct ixgbe_hw *hw, u32 reg)
 	return value;
 }
 
-static inline void ixgbevf_release_rx_desc(struct ixgbevf_ring *rx_ring,
-					   u32 val)
-{
-	rx_ring->next_to_use = val;
-
-	/*
-	 * Force memory writes to complete before letting h/w
-	 * know there are new descriptors to fetch.  (Only
-	 * applicable for weak-ordered memory model archs,
-	 * such as IA-64).
-	 */
-	wmb();
-	ixgbevf_write_tail(rx_ring, val);
-}
-
 /**
  * ixgbevf_set_ivar - set IVAR registers - maps interrupt causes to vectors
  * @adapter: pointer to adapter struct
@@ -342,40 +327,13 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector,
 	return !!budget;
 }
 
-/**
- * ixgbevf_receive_skb - Send a completed packet up the stack
- * @q_vector: structure containing interrupt and ring information
- * @skb: packet to send up
- * @status: hardware indication of status of receive
- * @rx_desc: rx descriptor
- **/
-static void ixgbevf_receive_skb(struct ixgbevf_q_vector *q_vector,
-				struct sk_buff *skb, u8 status,
-				union ixgbe_adv_rx_desc *rx_desc)
-{
-	struct ixgbevf_adapter *adapter = q_vector->adapter;
-	bool is_vlan = (status & IXGBE_RXD_STAT_VP);
-	u16 tag = le16_to_cpu(rx_desc->wb.upper.vlan);
-
-	if (is_vlan && test_bit(tag & VLAN_VID_MASK, adapter->active_vlans))
-		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tag);
-
-	if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL))
-		napi_gro_receive(&q_vector->napi, skb);
-	else
-		netif_rx(skb);
-}
-
 /**
  * ixgbevf_rx_skb - Helper function to determine proper Rx method
  * @q_vector: structure containing interrupt and ring information
  * @skb: packet to send up
- * @status: hardware indication of status of receive
- * @rx_desc: rx descriptor
  **/
 static void ixgbevf_rx_skb(struct ixgbevf_q_vector *q_vector,
-			   struct sk_buff *skb, u8 status,
-			   union ixgbe_adv_rx_desc *rx_desc)
+			   struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	skb_mark_napi_id(skb, &q_vector->napi);
@@ -387,17 +345,17 @@ static void ixgbevf_rx_skb(struct ixgbevf_q_vector *q_vector,
 	}
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
-	ixgbevf_receive_skb(q_vector, skb, status, rx_desc);
+	napi_gro_receive(&q_vector->napi, skb);
 }
 
-/**
- * ixgbevf_rx_checksum - indicate in skb if hw indicated a good cksum
- * @ring: pointer to Rx descriptor ring structure
- * @status_err: hardware indication of status of receive
+/* ixgbevf_rx_checksum - indicate in skb if hw indicated a good cksum
+ * @ring: structure containig ring specific data
+ * @rx_desc: current Rx descriptor being processed
  * @skb: skb currently being received and modified
- **/
+ */
 static inline void ixgbevf_rx_checksum(struct ixgbevf_ring *ring,
-				       u32 status_err, struct sk_buff *skb)
+				       union ixgbe_adv_rx_desc *rx_desc,
+				       struct sk_buff *skb)
 {
 	skb_checksum_none_assert(skb);
 
@@ -406,16 +364,16 @@ static inline void ixgbevf_rx_checksum(struct ixgbevf_ring *ring,
 		return;
 
 	/* if IP and error */
-	if ((status_err & IXGBE_RXD_STAT_IPCS) &&
-	    (status_err & IXGBE_RXDADV_ERR_IPE)) {
+	if (ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_IPCS) &&
+	    ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_ERR_IPE)) {
 		ring->rx_stats.csum_err++;
 		return;
 	}
 
-	if (!(status_err & IXGBE_RXD_STAT_L4CS))
+	if (!ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_L4CS))
 		return;
 
-	if (status_err & IXGBE_RXDADV_ERR_TCPE) {
+	if (ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_ERR_TCPE)) {
 		ring->rx_stats.csum_err++;
 		return;
 	}
@@ -424,52 +382,413 @@ static inline void ixgbevf_rx_checksum(struct ixgbevf_ring *ring,
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 }
 
+/* ixgbevf_process_skb_fields - Populate skb header fields from Rx descriptor
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_desc: pointer to the EOP Rx descriptor
+ * @skb: pointer to current skb being populated
+ *
+ * This function checks the ring, descriptor, and packet information in
+ * order to populate the checksum, VLAN, protocol, and other fields within
+ * the skb.
+ */
+static void ixgbevf_process_skb_fields(struct ixgbevf_ring *rx_ring,
+				       union ixgbe_adv_rx_desc *rx_desc,
+				       struct sk_buff *skb)
+{
+	ixgbevf_rx_checksum(rx_ring, rx_desc, skb);
+
+	if (ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) {
+		u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan);
+		unsigned long *active_vlans = netdev_priv(rx_ring->netdev);
+
+		if (test_bit(vid & VLAN_VID_MASK, active_vlans))
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid);
+	}
+
+	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
+}
+
+/**
+ * ixgbevf_is_non_eop - process handling of non-EOP buffers
+ * @rx_ring: Rx ring being processed
+ * @rx_desc: Rx descriptor for current buffer
+ * @skb: current socket buffer containing buffer in progress
+ *
+ * This function updates next to clean.  If the buffer is an EOP buffer
+ * this function exits returning false, otherwise it will place the
+ * sk_buff in the next buffer to be chained and return true indicating
+ * that this is in fact a non-EOP buffer.
+ **/
+static bool ixgbevf_is_non_eop(struct ixgbevf_ring *rx_ring,
+			       union ixgbe_adv_rx_desc *rx_desc)
+{
+	u32 ntc = rx_ring->next_to_clean + 1;
+
+	/* fetch, update, and store next to clean */
+	ntc = (ntc < rx_ring->count) ? ntc : 0;
+	rx_ring->next_to_clean = ntc;
+
+	prefetch(IXGBEVF_RX_DESC(rx_ring, ntc));
+
+	if (likely(ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)))
+		return false;
+
+	return true;
+}
+
+static bool ixgbevf_alloc_mapped_page(struct ixgbevf_ring *rx_ring,
+				      struct ixgbevf_rx_buffer *bi)
+{
+	struct page *page = bi->page;
+	dma_addr_t dma = bi->dma;
+
+	/* since we are recycling buffers we should seldom need to alloc */
+	if (likely(page))
+		return true;
+
+	/* alloc new page for storage */
+	page = dev_alloc_page();
+	if (unlikely(!page)) {
+		rx_ring->rx_stats.alloc_rx_page_failed++;
+		return false;
+	}
+
+	/* map page for use */
+	dma = dma_map_page(rx_ring->dev, page, 0,
+			   PAGE_SIZE, DMA_FROM_DEVICE);
+
+	/* 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_page(page);
+
+		rx_ring->rx_stats.alloc_rx_buff_failed++;
+		return false;
+	}
+
+	bi->dma = dma;
+	bi->page = page;
+	bi->page_offset = 0;
+
+	return true;
+}
+
 /**
  * ixgbevf_alloc_rx_buffers - Replace used receive buffers; packet split
  * @rx_ring: rx descriptor ring (for a specific queue) to setup buffers on
+ * @cleaned_count: number of buffers to replace
  **/
 static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring,
-				     int cleaned_count)
+				     u16 cleaned_count)
 {
 	union ixgbe_adv_rx_desc *rx_desc;
 	struct ixgbevf_rx_buffer *bi;
 	unsigned int i = rx_ring->next_to_use;
 
-	while (cleaned_count--) {
+	/* nothing to do or no valid netdev defined */
+	if (!cleaned_count || !rx_ring->netdev)
+		return;
+
 	rx_desc = IXGBEVF_RX_DESC(rx_ring, i);
 	bi = &rx_ring->rx_buffer_info[i];
+	i -= rx_ring->count;
 
-		if (!bi->skb) {
-			struct sk_buff *skb;
+	do {
+		if (!ixgbevf_alloc_mapped_page(rx_ring, bi))
+			break;
 
-			skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
-							rx_ring->rx_buf_len);
-			if (!skb)
-				goto no_buffers;
+		/* Refresh the desc even if pkt_addr didn't change
+		 * because each write-back erases this info.
+		 */
+		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
 
-			bi->skb = skb;
+		rx_desc++;
+		bi++;
+		i++;
+		if (unlikely(!i)) {
+			rx_desc = IXGBEVF_RX_DESC(rx_ring, 0);
+			bi = rx_ring->rx_buffer_info;
+			i -= rx_ring->count;
+		}
 
-			bi->dma = dma_map_single(rx_ring->dev, skb->data,
-						 rx_ring->rx_buf_len,
-						 DMA_FROM_DEVICE);
-			if (dma_mapping_error(rx_ring->dev, bi->dma)) {
-				dev_kfree_skb(skb);
-				bi->skb = NULL;
-				dev_err(rx_ring->dev, "Rx DMA map failed\n");
-				break;
+		/* clear the hdr_addr for the next_to_use descriptor */
+		rx_desc->read.hdr_addr = 0;
+
+		cleaned_count--;
+	} while (cleaned_count);
+
+	i += rx_ring->count;
+
+	if (rx_ring->next_to_use != i) {
+		/* record the next descriptor to use */
+		rx_ring->next_to_use = i;
+
+		/* update next to alloc since we have filled the ring */
+		rx_ring->next_to_alloc = i;
+
+		/* Force memory writes to complete before letting h/w
+		 * know there are new descriptors to fetch.  (Only
+		 * applicable for weak-ordered memory model archs,
+		 * such as IA-64).
+		 */
+		wmb();
+		ixgbevf_write_tail(rx_ring, i);
+	}
+}
+
+/* ixgbevf_pull_tail - ixgbevf specific version of skb_pull_tail
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @skb: pointer to current skb being adjusted
+ *
+ * This function is an ixgbevf specific version of __pskb_pull_tail.  The
+ * main difference between this version and the original function is that
+ * this function can make several assumptions about the state of things
+ * that allow for significant optimizations versus the standard function.
+ * As a result we can do things like drop a frag and maintain an accurate
+ * truesize for the skb.
+ */
+static void ixgbevf_pull_tail(struct ixgbevf_ring *rx_ring,
+			      struct sk_buff *skb)
+{
+	struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0];
+	unsigned char *va;
+	unsigned int pull_len;
+
+	/* it is valid to use page_address instead of kmap since we are
+	 * working with pages allocated out of the lomem pool per
+	 * alloc_page(GFP_ATOMIC)
+	 */
+	va = skb_frag_address(frag);
+
+	/* 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, IXGBEVF_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
+
+	/* update all of the pointers */
+	skb_frag_size_sub(frag, pull_len);
+	frag->page_offset += pull_len;
+	skb->data_len -= pull_len;
+	skb->tail += pull_len;
+}
+
+/* ixgbevf_cleanup_headers - Correct corrupted or empty headers
+ * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_desc: pointer to the EOP Rx descriptor
+ * @skb: pointer to current skb being fixed
+ *
+ * Check for corrupted packet headers caused by senders on the local L2
+ * embedded NIC switch not setting up their Tx Descriptors right.  These
+ * should be very rare.
+ *
+ * Also address the case where we are pulling data in on pages only
+ * and as such no data is present in the skb header.
+ *
+ * In addition if skb is not at least 60 bytes we need to pad it so that
+ * it is large enough to qualify as a valid Ethernet frame.
+ *
+ * Returns true if an error was encountered and skb was freed.
+ */
+static bool ixgbevf_cleanup_headers(struct ixgbevf_ring *rx_ring,
+				    union ixgbe_adv_rx_desc *rx_desc,
+				    struct sk_buff *skb)
+{
+	/* verify that the packet does not have any known errors */
+	if (unlikely(ixgbevf_test_staterr(rx_desc,
+					  IXGBE_RXDADV_ERR_FRAME_ERR_MASK))) {
+		struct net_device *netdev = rx_ring->netdev;
+
+		if (!(netdev->features & NETIF_F_RXALL)) {
+			dev_kfree_skb_any(skb);
+			return true;
 		}
 	}
-		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma);
 
-		i++;
-		if (i == rx_ring->count)
-			i = 0;
+	/* place header in linear portion of buffer */
+	if (skb_is_nonlinear(skb))
+		ixgbevf_pull_tail(rx_ring, skb);
+
+	/* if skb_pad returns an error the skb was freed */
+	if (unlikely(skb->len < 60)) {
+		int pad_len = 60 - skb->len;
+
+		if (skb_pad(skb, pad_len))
+			return true;
+		__skb_put(skb, pad_len);
 	}
 
-no_buffers:
+	return false;
+}
+
+/* ixgbevf_reuse_rx_page - page flip buffer and store it back on the ring
+ * @rx_ring: rx descriptor ring to store buffers on
+ * @old_buff: donor buffer to have page reused
+ *
+ * Synchronizes page for reuse by the adapter
+ */
+static void ixgbevf_reuse_rx_page(struct ixgbevf_ring *rx_ring,
+				  struct ixgbevf_rx_buffer *old_buff)
+{
+	struct ixgbevf_rx_buffer *new_buff;
+	u16 nta = rx_ring->next_to_alloc;
+
+	new_buff = &rx_ring->rx_buffer_info[nta];
+
+	/* update, and store next to alloc */
+	nta++;
+	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
+
+	/* transfer page from old buffer to new buffer */
+	new_buff->page = old_buff->page;
+	new_buff->dma = old_buff->dma;
+	new_buff->page_offset = old_buff->page_offset;
+
+	/* sync the buffer for use by the device */
+	dma_sync_single_range_for_device(rx_ring->dev, new_buff->dma,
+					 new_buff->page_offset,
+					 IXGBEVF_RX_BUFSZ,
+					 DMA_FROM_DEVICE);
+}
+
+static inline bool ixgbevf_page_is_reserved(struct page *page)
+{
+	return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc;
+}
+
+/* ixgbevf_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
+ * @rx_desc: descriptor containing length of buffer written by hardware
+ * @skb: sk_buff to place the data into
+ *
+ * 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.
+ *
+ * The function will then update the page offset if necessary and return
+ * true if the buffer can be reused by the adapter.
+ */
+static bool ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring,
+				struct ixgbevf_rx_buffer *rx_buffer,
+				union ixgbe_adv_rx_desc *rx_desc,
+				struct sk_buff *skb)
+{
+	struct page *page = rx_buffer->page;
+	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = IXGBEVF_RX_BUFSZ;
+#else
+	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+#endif
+
+	if ((size <= IXGBEVF_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) {
+		unsigned char *va = page_address(page) + rx_buffer->page_offset;
+
+		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
+
+		/* page is not reserved, we can reuse buffer as is */
+		if (likely(!ixgbevf_page_is_reserved(page)))
+			return true;
+
+		/* this page cannot be reused so discard it */
+		put_page(page);
+		return false;
+	}
+
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+			rx_buffer->page_offset, size, truesize);
+
+	/* avoid re-using remote pages */
+	if (unlikely(ixgbevf_page_is_reserved(page)))
+		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 ^= IXGBEVF_RX_BUFSZ;
+
+#else
+	/* move offset up to the next cache line */
+	rx_buffer->page_offset += truesize;
+
+	if (rx_buffer->page_offset > (PAGE_SIZE - IXGBEVF_RX_BUFSZ))
+		return false;
+
+#endif
+	/* Even if we own the page, we are not allowed to use atomic_set()
+	 * This would break get_page_unless_zero() users.
+	 */
+	atomic_inc(&page->_count);
+
+	return true;
+}
+
+static struct sk_buff *ixgbevf_fetch_rx_buffer(struct ixgbevf_ring *rx_ring,
+					       union ixgbe_adv_rx_desc *rx_desc,
+					       struct sk_buff *skb)
+{
+	struct ixgbevf_rx_buffer *rx_buffer;
+	struct page *page;
+
+	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+	page = rx_buffer->page;
+	prefetchw(page);
+
+	if (likely(!skb)) {
+		void *page_addr = page_address(page) +
+				  rx_buffer->page_offset;
+
+		/* prefetch first cache line of first page */
+		prefetch(page_addr);
+#if L1_CACHE_BYTES < 128
+		prefetch(page_addr + L1_CACHE_BYTES);
+#endif
+
+		/* allocate a skb to store the frags */
+		skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
+						IXGBEVF_RX_HDR_SIZE);
+		if (unlikely(!skb)) {
 			rx_ring->rx_stats.alloc_rx_buff_failed++;
-	if (rx_ring->next_to_use != i)
-		ixgbevf_release_rx_desc(rx_ring, i);
+			return NULL;
+		}
+
+		/* 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);
+	}
+
+	/* 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,
+				      IXGBEVF_RX_BUFSZ,
+				      DMA_FROM_DEVICE);
+
+	/* pull page into skb */
+	if (ixgbevf_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) {
+		/* hand second half of page back to the ring */
+		ixgbevf_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 inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter,
@@ -484,78 +803,51 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 				struct ixgbevf_ring *rx_ring,
 				int budget)
 {
-	union ixgbe_adv_rx_desc *rx_desc, *next_rxd;
-	struct ixgbevf_rx_buffer *rx_buffer_info, *next_buffer;
-	struct sk_buff *skb;
-	unsigned int i;
-	u32 len, staterr;
-	int cleaned_count = 0;
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+	u16 cleaned_count = ixgbevf_desc_unused(rx_ring);
+	struct sk_buff *skb = rx_ring->skb;
 
-	i = rx_ring->next_to_clean;
-	rx_desc = IXGBEVF_RX_DESC(rx_ring, i);
-	staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
-	rx_buffer_info = &rx_ring->rx_buffer_info[i];
+	while (likely(total_rx_packets < budget)) {
+		union ixgbe_adv_rx_desc *rx_desc;
 
-	while (staterr & IXGBE_RXD_STAT_DD) {
-		if (!budget)
-			break;
-		budget--;
+		/* return some buffers to hardware, one at a time is too slow */
+		if (cleaned_count >= IXGBEVF_RX_BUFFER_WRITE) {
+			ixgbevf_alloc_rx_buffers(rx_ring, cleaned_count);
+			cleaned_count = 0;
+		}
 
-		rmb(); /* read descriptor and rx_buffer_info after status DD */
-		len = le16_to_cpu(rx_desc->wb.upper.length);
-		skb = rx_buffer_info->skb;
-		prefetch(skb->data - NET_IP_ALIGN);
-		rx_buffer_info->skb = NULL;
+		rx_desc = IXGBEVF_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
-		if (rx_buffer_info->dma) {
-			dma_unmap_single(rx_ring->dev, rx_buffer_info->dma,
-					 rx_ring->rx_buf_len,
-					 DMA_FROM_DEVICE);
-			rx_buffer_info->dma = 0;
-			skb_put(skb, len);
-		}
+		if (!ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_DD))
+			break;
 
-		i++;
-		if (i == rx_ring->count)
-			i = 0;
+		/* 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();
 
-		next_rxd = IXGBEVF_RX_DESC(rx_ring, i);
-		prefetch(next_rxd);
-		cleaned_count++;
+		/* retrieve a buffer from the ring */
+		skb = ixgbevf_fetch_rx_buffer(rx_ring, rx_desc, skb);
 
-		next_buffer = &rx_ring->rx_buffer_info[i];
+		/* exit if we failed to retrieve a buffer */
+		if (!skb)
+			break;
 
-		if (!(staterr & IXGBE_RXD_STAT_EOP)) {
-			skb->next = next_buffer->skb;
-			IXGBE_CB(skb->next)->prev = skb;
-			rx_ring->rx_stats.non_eop_descs++;
-			goto next_desc;
-		}
+		cleaned_count++;
 
-		/* we should not be chaining buffers, if we did drop the skb */
-		if (IXGBE_CB(skb)->prev) {
-			do {
-				struct sk_buff *this = skb;
-				skb = IXGBE_CB(skb)->prev;
-				dev_kfree_skb(this);
-			} while (skb);
-			goto next_desc;
-		}
+		/* fetch next buffer in frame if non-eop */
+		if (ixgbevf_is_non_eop(rx_ring, rx_desc))
+			continue;
 
-		/* ERR_MASK will only have valid bits if EOP set */
-		if (unlikely(staterr & IXGBE_RXDADV_ERR_FRAME_ERR_MASK)) {
-			dev_kfree_skb_irq(skb);
-			goto next_desc;
+		/* verify the packet layout is correct */
+		if (ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) {
+			skb = NULL;
+			continue;
 		}
 
-		ixgbevf_rx_checksum(rx_ring, staterr, skb);
-
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
-		total_rx_packets++;
-
-		skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 
 		/* Workaround hardware that can't do proper VEPA multicast
 		 * source pruning.
@@ -565,32 +857,23 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		    ether_addr_equal(rx_ring->netdev->dev_addr,
 				     eth_hdr(skb)->h_source)) {
 			dev_kfree_skb_irq(skb);
-			goto next_desc;
+			continue;
 		}
 
-		ixgbevf_rx_skb(q_vector, skb, staterr, rx_desc);
-
-next_desc:
-		rx_desc->wb.upper.status_error = 0;
+		/* populate checksum, VLAN, and protocol */
+		ixgbevf_process_skb_fields(rx_ring, rx_desc, skb);
 
-		/* return some buffers to hardware, one at a time is too slow */
-		if (cleaned_count >= IXGBEVF_RX_BUFFER_WRITE) {
-			ixgbevf_alloc_rx_buffers(rx_ring, cleaned_count);
-			cleaned_count = 0;
-		}
+		ixgbevf_rx_skb(q_vector, skb);
 
-		/* use prefetched values */
-		rx_desc = next_rxd;
-		rx_buffer_info = &rx_ring->rx_buffer_info[i];
+		/* reset skb pointer */
+		skb = NULL;
 
-		staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
+		/* update budget accounting */
+		total_rx_packets++;
 	}
 
-	rx_ring->next_to_clean = i;
-	cleaned_count = ixgbevf_desc_unused(rx_ring);
-
-	if (cleaned_count)
-		ixgbevf_alloc_rx_buffers(rx_ring, cleaned_count);
+	/* place incomplete frames back on ring for completion */
+	rx_ring->skb = skb;
 
 	u64_stats_update_begin(&rx_ring->syncp);
 	rx_ring->stats.packets += total_rx_packets;
@@ -634,12 +917,10 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget)
 	else
 		per_ring_budget = budget;
 
-	adapter->flags |= IXGBE_FLAG_IN_NETPOLL;
 	ixgbevf_for_each_ring(ring, q_vector->rx)
 		clean_complete &= (ixgbevf_clean_rx_irq(q_vector, ring,
 							per_ring_budget)
 				   < per_ring_budget);
-	adapter->flags &= ~IXGBE_FLAG_IN_NETPOLL;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	ixgbevf_qv_unlock_napi(q_vector);
@@ -1229,19 +1510,15 @@ static void ixgbevf_configure_tx(struct ixgbevf_adapter *adapter)
 
 static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, int index)
 {
-	struct ixgbevf_ring *rx_ring;
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 srrctl;
 
-	rx_ring = adapter->rx_ring[index];
-
 	srrctl = IXGBE_SRRCTL_DROP_EN;
 
+	srrctl |= IXGBEVF_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT;
+	srrctl |= IXGBEVF_RX_BUFSZ >> IXGBE_SRRCTL_BSIZEPKT_SHIFT;
 	srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF;
 
-	srrctl |= ALIGN(rx_ring->rx_buf_len, 1024) >>
-		  IXGBE_SRRCTL_BSIZEPKT_SHIFT;
-
 	IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl);
 }
 
@@ -1260,40 +1537,6 @@ static void ixgbevf_setup_psrtype(struct ixgbevf_adapter *adapter)
 	IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, psrtype);
 }
 
-static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	struct net_device *netdev = adapter->netdev;
-	int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
-	int i;
-	u16 rx_buf_len;
-
-	/* notify the PF of our intent to use this size of frame */
-	ixgbevf_rlpml_set_vf(hw, max_frame);
-
-	/* PF will allow an extra 4 bytes past for vlan tagged frames */
-	max_frame += VLAN_HLEN;
-
-	/*
-	 * Allocate buffer sizes that fit well into 32K and
-	 * take into account max frame size of 9.5K
-	 */
-	if ((hw->mac.type == ixgbe_mac_X540_vf) &&
-	    (max_frame <= MAXIMUM_ETHERNET_VLAN_SIZE))
-		rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
-	else if (max_frame <= IXGBEVF_RXBUFFER_2K)
-		rx_buf_len = IXGBEVF_RXBUFFER_2K;
-	else if (max_frame <= IXGBEVF_RXBUFFER_4K)
-		rx_buf_len = IXGBEVF_RXBUFFER_4K;
-	else if (max_frame <= IXGBEVF_RXBUFFER_8K)
-		rx_buf_len = IXGBEVF_RXBUFFER_8K;
-	else
-		rx_buf_len = IXGBEVF_RXBUFFER_10K;
-
-	for (i = 0; i < adapter->num_rx_queues; i++)
-		adapter->rx_ring[i]->rx_buf_len = rx_buf_len;
-}
-
 #define IXGBEVF_MAX_RX_DESC_POLL 10
 static void ixgbevf_disable_rx_queue(struct ixgbevf_adapter *adapter,
 				     struct ixgbevf_ring *ring)
@@ -1371,12 +1614,13 @@ static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter,
 	/* reset ntu and ntc to place SW in sync with hardwdare */
 	ring->next_to_clean = 0;
 	ring->next_to_use = 0;
+	ring->next_to_alloc = 0;
 
 	ixgbevf_configure_srrctl(adapter, reg_idx);
 
-	/* prevent DMA from exceeding buffer space available */
-	rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK;
-	rxdctl |= ring->rx_buf_len | IXGBE_RXDCTL_RLPML_EN;
+	/* allow any size packet since we can handle overflow */
+	rxdctl &= ~IXGBE_RXDCTL_RLPML_EN;
+
 	rxdctl |= IXGBE_RXDCTL_ENABLE | IXGBE_RXDCTL_VME;
 	IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(reg_idx), rxdctl);
 
@@ -1393,11 +1637,13 @@ static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter,
 static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter)
 {
 	int i;
+	struct ixgbe_hw *hw = &adapter->hw;
+	struct net_device *netdev = adapter->netdev;
 
 	ixgbevf_setup_psrtype(adapter);
 
-	/* set_rx_buffer_len must be called before ring initialization */
-	ixgbevf_set_rx_buffer_len(adapter);
+	/* notify the PF of our intent to use this size of frame */
+	ixgbevf_rlpml_set_vf(hw, netdev->mtu + ETH_HLEN + ETH_FCS_LEN);
 
 	/* Setup the HW Rx Head and Tail Descriptor Pointers and
 	 * the Base and Length of the Rx Descriptor Ring */
@@ -1702,32 +1948,32 @@ void ixgbevf_up(struct ixgbevf_adapter *adapter)
  **/
 static void ixgbevf_clean_rx_ring(struct ixgbevf_ring *rx_ring)
 {
+	struct device *dev = rx_ring->dev;
 	unsigned long size;
 	unsigned int i;
 
+	/* Free Rx ring sk_buff */
+	if (rx_ring->skb) {
+		dev_kfree_skb(rx_ring->skb);
+		rx_ring->skb = NULL;
+	}
+
+	/* ring already cleared, nothing to do */
 	if (!rx_ring->rx_buffer_info)
 		return;
 
-	/* Free all the Rx ring sk_buffs */
+	/* Free all the Rx ring pages */
 	for (i = 0; i < rx_ring->count; i++) {
-		struct ixgbevf_rx_buffer *rx_buffer_info;
+		struct ixgbevf_rx_buffer *rx_buffer;
 
-		rx_buffer_info = &rx_ring->rx_buffer_info[i];
-		if (rx_buffer_info->dma) {
-			dma_unmap_single(rx_ring->dev, rx_buffer_info->dma,
-					 rx_ring->rx_buf_len,
-					 DMA_FROM_DEVICE);
-			rx_buffer_info->dma = 0;
-		}
-		if (rx_buffer_info->skb) {
-			struct sk_buff *skb = rx_buffer_info->skb;
-			rx_buffer_info->skb = NULL;
-			do {
-				struct sk_buff *this = skb;
-				skb = IXGBE_CB(skb)->prev;
-				dev_kfree_skb(this);
-			} while (skb);
-		}
+		rx_buffer = &rx_ring->rx_buffer_info[i];
+		if (rx_buffer->dma)
+			dma_unmap_page(dev, rx_buffer->dma,
+				       PAGE_SIZE, DMA_FROM_DEVICE);
+		rx_buffer->dma = 0;
+		if (rx_buffer->page)
+			__free_page(rx_buffer->page);
+		rx_buffer->page = NULL;
 	}
 
 	size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count;
@@ -3274,6 +3520,7 @@ static int ixgbevf_set_mac(struct net_device *netdev, void *p)
 static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
 	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
 	int max_possible_frame = MAXIMUM_ETHERNET_VLAN_SIZE;
 
@@ -3291,17 +3538,35 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu)
 	if ((new_mtu < 68) || (max_frame > max_possible_frame))
 		return -EINVAL;
 
-	hw_dbg(&adapter->hw, "changing MTU from %d to %d\n",
+	hw_dbg(hw, "changing MTU from %d to %d\n",
 	       netdev->mtu, new_mtu);
 	/* must set new MTU before calling down or up */
 	netdev->mtu = new_mtu;
 
-	if (netif_running(netdev))
-		ixgbevf_reinit_locked(adapter);
+	/* notify the PF of our intent to use this size of frame */
+	ixgbevf_rlpml_set_vf(hw, max_frame);
 
 	return 0;
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/* Polling 'interrupt' - used by things like netconsole to send skbs
+ * without having to re-enable interrupts. It's not called while
+ * the interrupt routine is executing.
+ */
+static void ixgbevf_netpoll(struct net_device *netdev)
+{
+	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
+	int i;
+
+	/* if interface is down do nothing */
+	if (test_bit(__IXGBEVF_DOWN, &adapter->state))
+		return;
+	for (i = 0; i < adapter->num_rx_queues; i++)
+		ixgbevf_msix_clean_rings(0, adapter->q_vector[i]);
+}
+#endif /* CONFIG_NET_POLL_CONTROLLER */
+
 static int ixgbevf_suspend(struct pci_dev *pdev, pm_message_t state)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -3438,6 +3703,9 @@ static const struct net_device_ops ixgbevf_netdev_ops = {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	.ndo_busy_poll		= ixgbevf_busy_poll_recv,
 #endif
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= ixgbevf_netpoll,
+#endif
 };
 
 static void ixgbevf_assign_netdev_ops(struct net_device *dev)