Merge branch 'master' into for-linus

4 files changed, 193 insertions, 232 deletions

diff --git a/drivers/net/qlge/qlge.h b/drivers/net/qlge/qlge.h
index 6ed5317ab1c..a9845a2f243 100644
--- a/drivers/net/qlge/qlge.h
+++ b/drivers/net/qlge/qlge.h
@@ -1287,12 +1287,11 @@ struct rx_ring {
 	u32 sbq_free_cnt;	/* free buffer desc cnt */
 
 	/* Misc. handler elements. */
-	u32 type;		/* Type of queue, tx, rx, or default. */
+	u32 type;		/* Type of queue, tx, rx. */
 	u32 irq;		/* Which vector this ring is assigned. */
 	u32 cpu;		/* Which CPU this should run on. */
 	char name[IFNAMSIZ + 5];
 	struct napi_struct napi;
-	struct delayed_work rx_work;
 	u8 reserved;
 	struct ql_adapter *qdev;
 };
@@ -1366,6 +1365,7 @@ struct nic_stats {
 struct intr_context {
 	struct ql_adapter *qdev;
 	u32 intr;
+	u32 irq_mask;		/* Mask of which rings the vector services. */
 	u32 hooked;
 	u32 intr_en_mask;	/* value/mask used to enable this intr */
 	u32 intr_dis_mask;	/* value/mask used to disable this intr */
@@ -1486,13 +1486,11 @@ struct ql_adapter {
 	struct intr_context intr_context[MAX_RX_RINGS];
 
 	int tx_ring_count;	/* One per online CPU. */
-	u32 rss_ring_first_cq_id;/* index of first inbound (rss) rx_ring */
-	u32 rss_ring_count;	/* One per online CPU.  */
+	u32 rss_ring_count;	/* One per irq vector.  */
 	/*
 	 * rx_ring_count =
-	 *  one default queue +
 	 *  (CPU count * outbound completion rx_ring) +
-	 *  (CPU count * inbound (RSS) completion rx_ring)
+	 *  (irq_vector_cnt * inbound (RSS) completion rx_ring)
 	 */
 	int rx_ring_count;
 	int ring_mem_size;
@@ -1519,7 +1517,6 @@ struct ql_adapter {
 	union flash_params flash;
 
 	struct net_device_stats stats;
-	struct workqueue_struct *q_workqueue;
 	struct workqueue_struct *workqueue;
 	struct delayed_work asic_reset_work;
 	struct delayed_work mpi_reset_work;
diff --git a/drivers/net/qlge/qlge_dbg.c b/drivers/net/qlge/qlge_dbg.c
index 40a70c36f5a..aa88cb3f41c 100644
--- a/drivers/net/qlge/qlge_dbg.c
+++ b/drivers/net/qlge/qlge_dbg.c
@@ -418,8 +418,6 @@ void ql_dump_qdev(struct ql_adapter *qdev)
 	printk(KERN_ERR PFX "qdev->intr_count 	= %d.\n", qdev->intr_count);
 	printk(KERN_ERR PFX "qdev->tx_ring		= %p.\n",
 	       qdev->tx_ring);
-	printk(KERN_ERR PFX "qdev->rss_ring_first_cq_id 	= %d.\n",
-	       qdev->rss_ring_first_cq_id);
 	printk(KERN_ERR PFX "qdev->rss_ring_count 	= %d.\n",
 	       qdev->rss_ring_count);
 	printk(KERN_ERR PFX "qdev->rx_ring	= %p.\n", qdev->rx_ring);
diff --git a/drivers/net/qlge/qlge_ethtool.c b/drivers/net/qlge/qlge_ethtool.c
index eb6a9ee640e..68f9bd280f8 100644
--- a/drivers/net/qlge/qlge_ethtool.c
+++ b/drivers/net/qlge/qlge_ethtool.c
@@ -49,10 +49,11 @@ static int ql_update_ring_coalescing(struct ql_adapter *qdev)
 	/* Skip the default queue, and update the outbound handler
 	 * queues if they changed.
 	 */
-	cqicb = (struct cqicb *)&qdev->rx_ring[1];
+	cqicb = (struct cqicb *)&qdev->rx_ring[qdev->rss_ring_count];
 	if (le16_to_cpu(cqicb->irq_delay) != qdev->tx_coalesce_usecs ||
-	    le16_to_cpu(cqicb->pkt_delay) != qdev->tx_max_coalesced_frames) {
-		for (i = 1; i < qdev->rss_ring_first_cq_id; i++, rx_ring++) {
+		le16_to_cpu(cqicb->pkt_delay) !=
+				qdev->tx_max_coalesced_frames) {
+		for (i = qdev->rss_ring_count; i < qdev->rx_ring_count; i++) {
 			rx_ring = &qdev->rx_ring[i];
 			cqicb = (struct cqicb *)rx_ring;
 			cqicb->irq_delay = cpu_to_le16(qdev->tx_coalesce_usecs);
@@ -70,12 +71,11 @@ static int ql_update_ring_coalescing(struct ql_adapter *qdev)
 	}
 
 	/* Update the inbound (RSS) handler queues if they changed. */
-	cqicb = (struct cqicb *)&qdev->rx_ring[qdev->rss_ring_first_cq_id];
+	cqicb = (struct cqicb *)&qdev->rx_ring[0];
 	if (le16_to_cpu(cqicb->irq_delay) != qdev->rx_coalesce_usecs ||
-	    le16_to_cpu(cqicb->pkt_delay) != qdev->rx_max_coalesced_frames) {
-		for (i = qdev->rss_ring_first_cq_id;
-		     i <= qdev->rss_ring_first_cq_id + qdev->rss_ring_count;
-		     i++) {
+		le16_to_cpu(cqicb->pkt_delay) !=
+					qdev->rx_max_coalesced_frames) {
+		for (i = 0; i < qdev->rss_ring_count; i++, rx_ring++) {
 			rx_ring = &qdev->rx_ring[i];
 			cqicb = (struct cqicb *)rx_ring;
 			cqicb->irq_delay = cpu_to_le16(qdev->rx_coalesce_usecs);
diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c
index 5768af17f16..22052925782 100644
--- a/drivers/net/qlge/qlge_main.c
+++ b/drivers/net/qlge/qlge_main.c
@@ -370,9 +370,7 @@ static int ql_set_mac_addr_reg(struct ql_adapter *qdev, u8 *addr, u32 type,
 				cam_output = (CAM_OUT_ROUTE_NIC |
 					      (qdev->
 					       func << CAM_OUT_FUNC_SHIFT) |
-					      (qdev->
-					       rss_ring_first_cq_id <<
-					       CAM_OUT_CQ_ID_SHIFT));
+						(0 << CAM_OUT_CQ_ID_SHIFT));
 				if (qdev->vlgrp)
 					cam_output |= CAM_OUT_RV;
 				/* route to NIC core */
@@ -1649,8 +1647,7 @@ static void ql_process_mac_rx_intr(struct ql_adapter *qdev,
 
 	qdev->stats.rx_packets++;
 	qdev->stats.rx_bytes += skb->len;
-	skb_record_rx_queue(skb,
-		rx_ring->cq_id - qdev->rss_ring_first_cq_id);
+	skb_record_rx_queue(skb, rx_ring->cq_id);
 	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
 		if (qdev->vlgrp &&
 			(ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_V) &&
@@ -1862,11 +1859,41 @@ static int ql_napi_poll_msix(struct napi_struct *napi, int budget)
 {
 	struct rx_ring *rx_ring = container_of(napi, struct rx_ring, napi);
 	struct ql_adapter *qdev = rx_ring->qdev;
-	int work_done = ql_clean_inbound_rx_ring(rx_ring, budget);
+	struct rx_ring *trx_ring;
+	int i, work_done = 0;
+	struct intr_context *ctx = &qdev->intr_context[rx_ring->cq_id];
 
 	QPRINTK(qdev, RX_STATUS, DEBUG, "Enter, NAPI POLL cq_id = %d.\n",
 		rx_ring->cq_id);
 
+	/* Service the TX rings first.  They start
+	 * right after the RSS rings. */
+	for (i = qdev->rss_ring_count; i < qdev->rx_ring_count; i++) {
+		trx_ring = &qdev->rx_ring[i];
+		/* If this TX completion ring belongs to this vector and
+		 * it's not empty then service it.
+		 */
+		if ((ctx->irq_mask & (1 << trx_ring->cq_id)) &&
+			(ql_read_sh_reg(trx_ring->prod_idx_sh_reg) !=
+					trx_ring->cnsmr_idx)) {
+			QPRINTK(qdev, INTR, DEBUG,
+				"%s: Servicing TX completion ring %d.\n",
+				__func__, trx_ring->cq_id);
+			ql_clean_outbound_rx_ring(trx_ring);
+		}
+	}
+
+	/*
+	 * Now service the RSS ring if it's active.
+	 */
+	if (ql_read_sh_reg(rx_ring->prod_idx_sh_reg) !=
+					rx_ring->cnsmr_idx) {
+		QPRINTK(qdev, INTR, DEBUG,
+			"%s: Servicing RX completion ring %d.\n",
+			__func__, rx_ring->cq_id);
+		work_done = ql_clean_inbound_rx_ring(rx_ring, budget);
+	}
+
 	if (work_done < budget) {
 		napi_complete(napi);
 		ql_enable_completion_interrupt(qdev, rx_ring->irq);
@@ -1928,38 +1955,6 @@ static void ql_vlan_rx_kill_vid(struct net_device *ndev, u16 vid)
 
 }
 
-/* Worker thread to process a given rx_ring that is dedicated
- * to outbound completions.
- */
-static void ql_tx_clean(struct work_struct *work)
-{
-	struct rx_ring *rx_ring =
-	    container_of(work, struct rx_ring, rx_work.work);
-	ql_clean_outbound_rx_ring(rx_ring);
-	ql_enable_completion_interrupt(rx_ring->qdev, rx_ring->irq);
-
-}
-
-/* Worker thread to process a given rx_ring that is dedicated
- * to inbound completions.
- */
-static void ql_rx_clean(struct work_struct *work)
-{
-	struct rx_ring *rx_ring =
-	    container_of(work, struct rx_ring, rx_work.work);
-	ql_clean_inbound_rx_ring(rx_ring, 64);
-	ql_enable_completion_interrupt(rx_ring->qdev, rx_ring->irq);
-}
-
-/* MSI-X Multiple Vector Interrupt Handler for outbound completions. */
-static irqreturn_t qlge_msix_tx_isr(int irq, void *dev_id)
-{
-	struct rx_ring *rx_ring = dev_id;
-	queue_delayed_work_on(rx_ring->cpu, rx_ring->qdev->q_workqueue,
-			      &rx_ring->rx_work, 0);
-	return IRQ_HANDLED;
-}
-
 /* MSI-X Multiple Vector Interrupt Handler for inbound completions. */
 static irqreturn_t qlge_msix_rx_isr(int irq, void *dev_id)
 {
@@ -1979,7 +1974,6 @@ static irqreturn_t qlge_isr(int irq, void *dev_id)
 	struct ql_adapter *qdev = rx_ring->qdev;
 	struct intr_context *intr_context = &qdev->intr_context[0];
 	u32 var;
-	int i;
 	int work_done = 0;
 
 	spin_lock(&qdev->hw_lock);
@@ -2020,41 +2014,18 @@ static irqreturn_t qlge_isr(int irq, void *dev_id)
 	}
 
 	/*
-	 * Check the default queue and wake handler if active.
+	 * Get the bit-mask that shows the active queues for this
+	 * pass.  Compare it to the queues that this irq services
+	 * and call napi if there's a match.
 	 */
-	rx_ring = &qdev->rx_ring[0];
-	if (ql_read_sh_reg(rx_ring->prod_idx_sh_reg) != rx_ring->cnsmr_idx) {
-		QPRINTK(qdev, INTR, INFO, "Waking handler for rx_ring[0].\n");
-		ql_disable_completion_interrupt(qdev, intr_context->intr);
-		queue_delayed_work_on(smp_processor_id(), qdev->q_workqueue,
-				      &rx_ring->rx_work, 0);
-		work_done++;
-	}
-
-	if (!test_bit(QL_MSIX_ENABLED, &qdev->flags)) {
-		/*
-		 * Start the DPC for each active queue.
-		 */
-		for (i = 1; i < qdev->rx_ring_count; i++) {
-			rx_ring = &qdev->rx_ring[i];
-			if (ql_read_sh_reg(rx_ring->prod_idx_sh_reg) !=
-			    rx_ring->cnsmr_idx) {
+	var = ql_read32(qdev, ISR1);
+	if (var & intr_context->irq_mask) {
 				QPRINTK(qdev, INTR, INFO,
-					"Waking handler for rx_ring[%d].\n", i);
-				ql_disable_completion_interrupt(qdev,
-								intr_context->
-								intr);
-				if (i < qdev->rss_ring_first_cq_id)
-					queue_delayed_work_on(rx_ring->cpu,
-							      qdev->q_workqueue,
-							      &rx_ring->rx_work,
-							      0);
-				else
+			"Waking handler for rx_ring[0].\n");
+		ql_disable_completion_interrupt(qdev, intr_context->intr);
 					napi_schedule(&rx_ring->napi);
 				work_done++;
 			}
-		}
-	}
 	ql_enable_completion_interrupt(qdev, intr_context->intr);
 	return work_done ? IRQ_HANDLED : IRQ_NONE;
 }
@@ -2132,7 +2103,7 @@ static void ql_hw_csum_setup(struct sk_buff *skb,
 				    iph->daddr, len, iph->protocol, 0);
 }
 
-static int qlge_send(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t qlge_send(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct tx_ring_desc *tx_ring_desc;
 	struct ob_mac_iocb_req *mac_iocb_ptr;
@@ -2706,35 +2677,9 @@ static int ql_start_rx_ring(struct ql_adapter *qdev, struct rx_ring *rx_ring)
 	}
 	switch (rx_ring->type) {
 	case TX_Q:
-		/* If there's only one interrupt, then we use
-		 * worker threads to process the outbound
-		 * completion handling rx_rings. We do this so
-		 * they can be run on multiple CPUs. There is
-		 * room to play with this more where we would only
-		 * run in a worker if there are more than x number
-		 * of outbound completions on the queue and more
-		 * than one queue active.  Some threshold that
-		 * would indicate a benefit in spite of the cost
-		 * of a context switch.
-		 * If there's more than one interrupt, then the
-		 * outbound completions are processed in the ISR.
-		 */
-		if (!test_bit(QL_MSIX_ENABLED, &qdev->flags))
-			INIT_DELAYED_WORK(&rx_ring->rx_work, ql_tx_clean);
-		else {
-			/* With all debug warnings on we see a WARN_ON message
-			 * when we free the skb in the interrupt context.
-			 */
-			INIT_DELAYED_WORK(&rx_ring->rx_work, ql_tx_clean);
-		}
 		cqicb->irq_delay = cpu_to_le16(qdev->tx_coalesce_usecs);
 		cqicb->pkt_delay = cpu_to_le16(qdev->tx_max_coalesced_frames);
 		break;
-	case DEFAULT_Q:
-		INIT_DELAYED_WORK(&rx_ring->rx_work, ql_rx_clean);
-		cqicb->irq_delay = 0;
-		cqicb->pkt_delay = 0;
-		break;
 	case RX_Q:
 		/* Inbound completion handling rx_rings run in
 		 * separate NAPI contexts.
@@ -2818,17 +2763,20 @@ static void ql_disable_msix(struct ql_adapter *qdev)
 	}
 }
 
+/* We start by trying to get the number of vectors
+ * stored in qdev->intr_count. If we don't get that
+ * many then we reduce the count and try again.
+ */
 static void ql_enable_msix(struct ql_adapter *qdev)
 {
-	int i;
+	int i, err;
 
-	qdev->intr_count = 1;
 	/* Get the MSIX vectors. */
 	if (irq_type == MSIX_IRQ) {
 		/* Try to alloc space for the msix struct,
 		 * if it fails then go to MSI/legacy.
 		 */
-		qdev->msi_x_entry = kcalloc(qdev->rx_ring_count,
+		qdev->msi_x_entry = kcalloc(qdev->intr_count,
 					    sizeof(struct msix_entry),
 					    GFP_KERNEL);
 		if (!qdev->msi_x_entry) {
@@ -2836,26 +2784,36 @@ static void ql_enable_msix(struct ql_adapter *qdev)
 			goto msi;
 		}
 
-		for (i = 0; i < qdev->rx_ring_count; i++)
+		for (i = 0; i < qdev->intr_count; i++)
 			qdev->msi_x_entry[i].entry = i;
 
-		if (!pci_enable_msix
-		    (qdev->pdev, qdev->msi_x_entry, qdev->rx_ring_count)) {
-			set_bit(QL_MSIX_ENABLED, &qdev->flags);
-			qdev->intr_count = qdev->rx_ring_count;
-			QPRINTK(qdev, IFUP, DEBUG,
-				"MSI-X Enabled, got %d vectors.\n",
-				qdev->intr_count);
-			return;
-		} else {
+		/* Loop to get our vectors.  We start with
+		 * what we want and settle for what we get.
+		 */
+		do {
+			err = pci_enable_msix(qdev->pdev,
+				qdev->msi_x_entry, qdev->intr_count);
+			if (err > 0)
+				qdev->intr_count = err;
+		} while (err > 0);
+
+		if (err < 0) {
 			kfree(qdev->msi_x_entry);
 			qdev->msi_x_entry = NULL;
 			QPRINTK(qdev, IFUP, WARNING,
 				"MSI-X Enable failed, trying MSI.\n");
+			qdev->intr_count = 1;
 			irq_type = MSI_IRQ;
+		} else if (err == 0) {
+			set_bit(QL_MSIX_ENABLED, &qdev->flags);
+			QPRINTK(qdev, IFUP, INFO,
+				"MSI-X Enabled, got %d vectors.\n",
+				qdev->intr_count);
+			return;
 		}
 	}
 msi:
+	qdev->intr_count = 1;
 	if (irq_type == MSI_IRQ) {
 		if (!pci_enable_msi(qdev->pdev)) {
 			set_bit(QL_MSI_ENABLED, &qdev->flags);
@@ -2868,6 +2826,71 @@ msi:
 	QPRINTK(qdev, IFUP, DEBUG, "Running with legacy interrupts.\n");
 }
 
+/* Each vector services 1 RSS ring and and 1 or more
+ * TX completion rings.  This function loops through
+ * the TX completion rings and assigns the vector that
+ * will service it.  An example would be if there are
+ * 2 vectors (so 2 RSS rings) and 8 TX completion rings.
+ * This would mean that vector 0 would service RSS ring 0
+ * and TX competion rings 0,1,2 and 3.  Vector 1 would
+ * service RSS ring 1 and TX completion rings 4,5,6 and 7.
+ */
+static void ql_set_tx_vect(struct ql_adapter *qdev)
+{
+	int i, j, vect;
+	u32 tx_rings_per_vector = qdev->tx_ring_count / qdev->intr_count;
+
+	if (likely(test_bit(QL_MSIX_ENABLED, &qdev->flags))) {
+		/* Assign irq vectors to TX rx_rings.*/
+		for (vect = 0, j = 0, i = qdev->rss_ring_count;
+					 i < qdev->rx_ring_count; i++) {
+			if (j == tx_rings_per_vector) {
+				vect++;
+				j = 0;
+			}
+			qdev->rx_ring[i].irq = vect;
+			j++;
+		}
+	} else {
+		/* For single vector all rings have an irq
+		 * of zero.
+		 */
+		for (i = 0; i < qdev->rx_ring_count; i++)
+			qdev->rx_ring[i].irq = 0;
+	}
+}
+
+/* Set the interrupt mask for this vector.  Each vector
+ * will service 1 RSS ring and 1 or more TX completion
+ * rings.  This function sets up a bit mask per vector
+ * that indicates which rings it services.
+ */
+static void ql_set_irq_mask(struct ql_adapter *qdev, struct intr_context *ctx)
+{
+	int j, vect = ctx->intr;
+	u32 tx_rings_per_vector = qdev->tx_ring_count / qdev->intr_count;
+
+	if (likely(test_bit(QL_MSIX_ENABLED, &qdev->flags))) {
+		/* Add the RSS ring serviced by this vector
+		 * to the mask.
+		 */
+		ctx->irq_mask = (1 << qdev->rx_ring[vect].cq_id);
+		/* Add the TX ring(s) serviced by this vector
+		 * to the mask. */
+		for (j = 0; j < tx_rings_per_vector; j++) {
+			ctx->irq_mask |=
+			(1 << qdev->rx_ring[qdev->rss_ring_count +
+			(vect * tx_rings_per_vector) + j].cq_id);
+		}
+	} else {
+		/* For single vector we just shift each queue's
+		 * ID into the mask.
+		 */
+		for (j = 0; j < qdev->rx_ring_count; j++)
+			ctx->irq_mask |= (1 << qdev->rx_ring[j].cq_id);
+	}
+}
+
 /*
  * Here we build the intr_context structures based on
  * our rx_ring count and intr vector count.
@@ -2879,18 +2902,19 @@ static void ql_resolve_queues_to_irqs(struct ql_adapter *qdev)
 	int i = 0;
 	struct intr_context *intr_context = &qdev->intr_context[0];
 
-	ql_enable_msix(qdev);
-
 	if (likely(test_bit(QL_MSIX_ENABLED, &qdev->flags))) {
 		/* Each rx_ring has it's
 		 * own intr_context since we have separate
 		 * vectors for each queue.
-		 * This only true when MSI-X is enabled.
 		 */
 		for (i = 0; i < qdev->intr_count; i++, intr_context++) {
 			qdev->rx_ring[i].irq = i;
 			intr_context->intr = i;
 			intr_context->qdev = qdev;
+			/* Set up this vector's bit-mask that indicates
+			 * which queues it services.
+			 */
+			ql_set_irq_mask(qdev, intr_context);
 			/*
 			 * We set up each vectors enable/disable/read bits so
 			 * there's no bit/mask calculations in the critical path.
@@ -2907,21 +2931,14 @@ static void ql_resolve_queues_to_irqs(struct ql_adapter *qdev)
 			    INTR_EN_TYPE_MASK | INTR_EN_INTR_MASK |
 			    INTR_EN_TYPE_READ | INTR_EN_IHD_MASK | INTR_EN_IHD |
 			    i;
-
 			if (i == 0) {
-				/*
-				 * Default queue handles bcast/mcast plus
-				 * async events.  Needs buffers.
+				/* The first vector/queue handles
+				 * broadcast/multicast, fatal errors,
+				 * and firmware events.  This in addition
+				 * to normal inbound NAPI processing.
 				 */
 				intr_context->handler = qlge_isr;
-				sprintf(intr_context->name, "%s-default-queue",
-					qdev->ndev->name);
-			} else if (i < qdev->rss_ring_first_cq_id) {
-				/*
-				 * Outbound queue is for outbound completions only.
-				 */
-				intr_context->handler = qlge_msix_tx_isr;
-				sprintf(intr_context->name, "%s-tx-%d",
+				sprintf(intr_context->name, "%s-rx-%d",
 					qdev->ndev->name, i);
 			} else {
 				/*
@@ -2955,9 +2972,17 @@ static void ql_resolve_queues_to_irqs(struct ql_adapter *qdev)
 		 */
 		intr_context->handler = qlge_isr;
 		sprintf(intr_context->name, "%s-single_irq", qdev->ndev->name);
-		for (i = 0; i < qdev->rx_ring_count; i++)
-			qdev->rx_ring[i].irq = 0;
+		/* Set up this vector's bit-mask that indicates
+		 * which queues it services. In this case there is
+		 * a single vector so it will service all RSS and
+		 * TX completion rings.
+		 */
+		ql_set_irq_mask(qdev, intr_context);
 	}
+	/* Tell the TX completion rings which MSIx vector
+	 * they will be using.
+	 */
+	ql_set_tx_vect(qdev);
 }
 
 static void ql_free_irq(struct ql_adapter *qdev)
@@ -3062,7 +3087,7 @@ static int ql_start_rss(struct ql_adapter *qdev)
 
 	memset((void *)ricb, 0, sizeof(*ricb));
 
-	ricb->base_cq = qdev->rss_ring_first_cq_id | RSS_L4K;
+	ricb->base_cq = RSS_L4K;
 	ricb->flags =
 	    (RSS_L6K | RSS_LI | RSS_LB | RSS_LM | RSS_RI4 | RSS_RI6 | RSS_RT4 |
 	     RSS_RT6);
@@ -3264,7 +3289,7 @@ static int ql_adapter_initialize(struct ql_adapter *qdev)
 	}
 
 	/* Start NAPI for the RSS queues. */
-	for (i = qdev->rss_ring_first_cq_id; i < qdev->rx_ring_count; i++) {
+	for (i = 0; i < qdev->rss_ring_count; i++) {
 		QPRINTK(qdev, IFUP, DEBUG, "Enabling NAPI for rx_ring[%d].\n",
 			i);
 		napi_enable(&qdev->rx_ring[i].napi);
@@ -3326,7 +3351,6 @@ static void ql_display_dev_info(struct net_device *ndev)
 static int ql_adapter_down(struct ql_adapter *qdev)
 {
 	int i, status = 0;
-	struct rx_ring *rx_ring;
 
 	ql_link_off(qdev);
 
@@ -3340,27 +3364,8 @@ static int ql_adapter_down(struct ql_adapter *qdev)
 	cancel_delayed_work_sync(&qdev->mpi_idc_work);
 	cancel_delayed_work_sync(&qdev->mpi_port_cfg_work);
 
-	/* The default queue at index 0 is always processed in
-	 * a workqueue.
-	 */
-	cancel_delayed_work_sync(&qdev->rx_ring[0].rx_work);
-
-	/* The rest of the rx_rings are processed in
-	 * a workqueue only if it's a single interrupt
-	 * environment (MSI/Legacy).
-	 */
-	for (i = 1; i < qdev->rx_ring_count; i++) {
-		rx_ring = &qdev->rx_ring[i];
-		/* Only the RSS rings use NAPI on multi irq
-		 * environment.  Outbound completion processing
-		 * is done in interrupt context.
-		 */
-		if (i >= qdev->rss_ring_first_cq_id) {
-			napi_disable(&rx_ring->napi);
-		} else {
-			cancel_delayed_work_sync(&rx_ring->rx_work);
-		}
-	}
+	for (i = 0; i < qdev->rss_ring_count; i++)
+		napi_disable(&qdev->rx_ring[i].napi);
 
 	clear_bit(QL_ADAPTER_UP, &qdev->flags);
 
@@ -3370,7 +3375,7 @@ static int ql_adapter_down(struct ql_adapter *qdev)
 
 	/* Call netif_napi_del() from common point.
 	 */
-	for (i = qdev->rss_ring_first_cq_id; i < qdev->rx_ring_count; i++)
+	for (i = 0; i < qdev->rss_ring_count; i++)
 		netif_napi_del(&qdev->rx_ring[i].napi);
 
 	ql_free_rx_buffers(qdev);
@@ -3449,43 +3454,21 @@ static int ql_configure_rings(struct ql_adapter *qdev)
 	int i;
 	struct rx_ring *rx_ring;
 	struct tx_ring *tx_ring;
-	int cpu_cnt = num_online_cpus();
-
-	/*
-	 * For each processor present we allocate one
-	 * rx_ring for outbound completions, and one
-	 * rx_ring for inbound completions.  Plus there is
-	 * always the one default queue.  For the CPU
-	 * counts we end up with the following rx_rings:
-	 * rx_ring count =
-	 *  one default queue +
-	 *  (CPU count * outbound completion rx_ring) +
-	 *  (CPU count * inbound (RSS) completion rx_ring)
-	 * To keep it simple we limit the total number of
-	 * queues to < 32, so we truncate CPU to 8.
-	 * This limitation can be removed when requested.
+	int cpu_cnt = min(MAX_CPUS, (int)num_online_cpus());
+
+	/* In a perfect world we have one RSS ring for each CPU
+	 * and each has it's own vector.  To do that we ask for
+	 * cpu_cnt vectors.  ql_enable_msix() will adjust the
+	 * vector count to what we actually get.  We then
+	 * allocate an RSS ring for each.
+	 * Essentially, we are doing min(cpu_count, msix_vector_count).
 	 */
-
-	if (cpu_cnt > MAX_CPUS)
-		cpu_cnt = MAX_CPUS;
-
-	/*
-	 * rx_ring[0] is always the default queue.
-	 */
-	/* Allocate outbound completion ring for each CPU. */
+	qdev->intr_count = cpu_cnt;
+	ql_enable_msix(qdev);
+	/* Adjust the RSS ring count to the actual vector count. */
+	qdev->rss_ring_count = qdev->intr_count;
 	qdev->tx_ring_count = cpu_cnt;
-	/* Allocate inbound completion (RSS) ring for each CPU. */
-	qdev->rss_ring_count = cpu_cnt;
-	/* cq_id for the first inbound ring handler. */
-	qdev->rss_ring_first_cq_id = cpu_cnt + 1;
-	/*
-	 * qdev->rx_ring_count:
-	 * Total number of rx_rings.  This includes the one
-	 * default queue, a number of outbound completion
-	 * handler rx_rings, and the number of inbound
-	 * completion handler rx_rings.
-	 */
-	qdev->rx_ring_count = qdev->tx_ring_count + qdev->rss_ring_count + 1;
+	qdev->rx_ring_count = qdev->tx_ring_count + qdev->rss_ring_count;
 
 	for (i = 0; i < qdev->tx_ring_count; i++) {
 		tx_ring = &qdev->tx_ring[i];
@@ -3498,9 +3481,9 @@ static int ql_configure_rings(struct ql_adapter *qdev)
 
 		/*
 		 * The completion queue ID for the tx rings start
-		 * immediately after the default Q ID, which is zero.
+		 * immediately after the rss rings.
 		 */
-		tx_ring->cq_id = i + 1;
+		tx_ring->cq_id = qdev->rss_ring_count + i;
 	}
 
 	for (i = 0; i < qdev->rx_ring_count; i++) {
@@ -3509,10 +3492,9 @@ static int ql_configure_rings(struct ql_adapter *qdev)
 		rx_ring->qdev = qdev;
 		rx_ring->cq_id = i;
 		rx_ring->cpu = i % cpu_cnt;	/* CPU to run handler on. */
-		if (i == 0) {	/* Default queue at index 0. */
+		if (i < qdev->rss_ring_count) {
 			/*
-			 * Default queue handles bcast/mcast plus
-			 * async events.  Needs buffers.
+			 * Inbound (RSS) queues.
 			 */
 			rx_ring->cq_len = qdev->rx_ring_size;
 			rx_ring->cq_size =
@@ -3525,8 +3507,8 @@ static int ql_configure_rings(struct ql_adapter *qdev)
 			rx_ring->sbq_size =
 			    rx_ring->sbq_len * sizeof(__le64);
 			rx_ring->sbq_buf_size = SMALL_BUFFER_SIZE * 2;
-			rx_ring->type = DEFAULT_Q;
-		} else if (i < qdev->rss_ring_first_cq_id) {
+			rx_ring->type = RX_Q;
+		} else {
 			/*
 			 * Outbound queue handles outbound completions only.
 			 */
@@ -3541,22 +3523,6 @@ static int ql_configure_rings(struct ql_adapter *qdev)
 			rx_ring->sbq_size = 0;
 			rx_ring->sbq_buf_size = 0;
 			rx_ring->type = TX_Q;
-		} else {	/* Inbound completions (RSS) queues */
-			/*
-			 * Inbound queues handle unicast frames only.
-			 */
-			rx_ring->cq_len = qdev->rx_ring_size;
-			rx_ring->cq_size =
-			    rx_ring->cq_len * sizeof(struct ql_net_rsp_iocb);
-			rx_ring->lbq_len = NUM_LARGE_BUFFERS;
-			rx_ring->lbq_size =
-			    rx_ring->lbq_len * sizeof(__le64);
-			rx_ring->lbq_buf_size = LARGE_BUFFER_SIZE;
-			rx_ring->sbq_len = NUM_SMALL_BUFFERS;
-			rx_ring->sbq_size =
-			    rx_ring->sbq_len * sizeof(__le64);
-			rx_ring->sbq_buf_size = SMALL_BUFFER_SIZE * 2;
-			rx_ring->type = RX_Q;
 		}
 	}
 	return 0;
@@ -3845,10 +3811,7 @@ static void ql_release_all(struct pci_dev *pdev)
 		destroy_workqueue(qdev->workqueue);
 		qdev->workqueue = NULL;
 	}
-	if (qdev->q_workqueue) {
-		destroy_workqueue(qdev->q_workqueue);
-		qdev->q_workqueue = NULL;
-	}
+
 	if (qdev->reg_base)
 		iounmap(qdev->reg_base);
 	if (qdev->doorbell_area)
@@ -3961,8 +3924,6 @@ static int __devinit ql_init_device(struct pci_dev *pdev,
 	 * Set up the operating parameters.
 	 */
 	qdev->rx_csum = 1;
-
-	qdev->q_workqueue = create_workqueue(ndev->name);
 	qdev->workqueue = create_singlethread_workqueue(ndev->name);
 	INIT_DELAYED_WORK(&qdev->asic_reset_work, ql_asic_reset_work);
 	INIT_DELAYED_WORK(&qdev->mpi_reset_work, ql_mpi_reset_work);
@@ -4076,6 +4037,11 @@ static pci_ers_result_t qlge_io_error_detected(struct pci_dev *pdev,
 	struct net_device *ndev = pci_get_drvdata(pdev);
 	struct ql_adapter *qdev = netdev_priv(ndev);
 
+	netif_device_detach(ndev);
+
+	if (state == pci_channel_io_perm_failure)
+		return PCI_ERS_RESULT_DISCONNECT;
+
 	if (netif_running(ndev))
 		ql_adapter_down(qdev);