#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/skbuff.h>
-#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
#include <linux/delay.h>
#include <linux/mm.h>
{
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);
status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK);
if (status)
return;
- spin_lock(&qdev->hw_lock);
if (ql_set_mac_addr_reg
(qdev, (u8 *) &enable_bit, MAC_ADDR_TYPE_VLAN, vid)) {
QPRINTK(qdev, IFUP, ERR, "Failed to init vlan address.\n");
}
- spin_unlock(&qdev->hw_lock);
ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK);
}
if (status)
return;
- spin_lock(&qdev->hw_lock);
if (ql_set_mac_addr_reg
(qdev, (u8 *) &enable_bit, MAC_ADDR_TYPE_VLAN, vid)) {
QPRINTK(qdev, IFUP, ERR, "Failed to clear vlan address.\n");
}
- spin_unlock(&qdev->hw_lock);
ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK);
}
-/* 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)
{
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);
/*
* Check MPI processor activity.
*/
- if (var & STS_PI) {
+ if ((var & STS_PI) &&
+ (ql_read32(qdev, INTR_MASK) & INTR_MASK_PI)) {
/*
* We've got an async event or mailbox completion.
* Handle it and clear the source of the interrupt.
*/
QPRINTK(qdev, INTR, ERR, "Got MPI processor interrupt.\n");
ql_disable_completion_interrupt(qdev, intr_context->intr);
- queue_delayed_work_on(smp_processor_id(), qdev->workqueue,
- &qdev->mpi_work, 0);
+ ql_write32(qdev, INTR_MASK, (INTR_MASK_PI << 16));
+ queue_delayed_work_on(smp_processor_id(),
+ qdev->workqueue, &qdev->mpi_work, 0);
work_done++;
}
/*
- * 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_count)
- 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;
}
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;
FLAGS_LI; /* Load irq delay values */
if (rx_ring->lbq_len) {
cqicb->flags |= FLAGS_LL; /* Load lbq values */
- tmp = (u64)rx_ring->lbq_base_dma;;
+ tmp = (u64)rx_ring->lbq_base_dma;
base_indirect_ptr = (__le64 *) rx_ring->lbq_base_indirect;
page_entries = 0;
do {
}
if (rx_ring->sbq_len) {
cqicb->flags |= FLAGS_LS; /* Load sbq values */
- tmp = (u64)rx_ring->sbq_base_dma;;
+ tmp = (u64)rx_ring->sbq_base_dma;
base_indirect_ptr = (__le64 *) rx_ring->sbq_base_indirect;
page_entries = 0;
do {
}
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.
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.
/* 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.
INTR_EN_TYPE_MASK | INTR_EN_INTR_MASK |
INTR_EN_TYPE_READ | INTR_EN_IHD_MASK | INTR_EN_IHD |
i;
-
- if (i < qdev->rss_ring_count) {
- /*
- * Inbound queues handle unicast frames only.
+ if (i == 0) {
+ /* The first vector/queue handles
+ * broadcast/multicast, fatal errors,
+ * and firmware events. This in addition
+ * to normal inbound NAPI processing.
*/
- intr_context->handler = qlge_msix_rx_isr;
+ intr_context->handler = qlge_isr;
sprintf(intr_context->name, "%s-rx-%d",
qdev->ndev->name, i);
} else {
/*
- * Outbound queue is for outbound completions only.
+ * Inbound queues handle unicast frames only.
*/
- intr_context->handler = qlge_msix_tx_isr;
- sprintf(intr_context->name, "%s-tx-%d",
+ intr_context->handler = qlge_msix_rx_isr;
+ sprintf(intr_context->name, "%s-rx-%d",
qdev->ndev->name, i);
}
}
*/
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)
{
int status = 0;
- status = ql_sem_spinlock(qdev, SEM_RT_IDX_MASK);
+ /* Clear all the entries in the routing table. */
+ status = ql_clear_routing_entries(qdev);
if (status)
return status;
- /* Clear all the entries in the routing table. */
- status = ql_clear_routing_entries(qdev);
+ status = ql_sem_spinlock(qdev, SEM_RT_IDX_MASK);
if (status)
- goto exit;
+ return status;
status = ql_set_routing_reg(qdev, RT_IDX_ALL_ERR_SLOT, RT_IDX_ERR, 1);
if (status) {
static int ql_adapter_down(struct ql_adapter *qdev)
{
int i, status = 0;
- struct rx_ring *rx_ring;
ql_link_off(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_count) {
- 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);
ql_free_rx_buffers(qdev);
- spin_lock(&qdev->hw_lock);
status = ql_adapter_reset(qdev);
if (status)
QPRINTK(qdev, IFDOWN, ERR, "reset(func #%d) FAILED!\n",
qdev->func);
- spin_unlock(&qdev->hw_lock);
return status;
}
/*
* 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 + qdev->rss_ring_count;
+ tx_ring->cq_id = qdev->rss_ring_count + i;
}
for (i = 0; i < qdev->rx_ring_count; i++) {
rx_ring->cq_id = i;
rx_ring->cpu = i % cpu_cnt; /* CPU to run handler on. */
if (i < qdev->rss_ring_count) {
- /* Inbound completions (RSS) queues */
+ /*
+ * Inbound (RSS) queues.
+ */
rx_ring->cq_len = qdev->rx_ring_size;
rx_ring->cq_size =
rx_ring->cq_len * sizeof(struct ql_net_rsp_iocb);
status = ql_sem_spinlock(qdev, SEM_RT_IDX_MASK);
if (status)
return;
- spin_lock(&qdev->hw_lock);
/*
* Set or clear promiscuous mode if a
* transition is taking place.
}
}
exit:
- spin_unlock(&qdev->hw_lock);
ql_sem_unlock(qdev, SEM_RT_IDX_MASK);
}
status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK);
if (status)
return status;
- spin_lock(&qdev->hw_lock);
status = ql_set_mac_addr_reg(qdev, (u8 *) ndev->dev_addr,
MAC_ADDR_TYPE_CAM_MAC, qdev->func * MAX_CQ);
- spin_unlock(&qdev->hw_lock);
if (status)
QPRINTK(qdev, HW, ERR, "Failed to load MAC address.\n");
ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK);
struct ql_adapter *qdev =
container_of(work, struct ql_adapter, asic_reset_work.work);
int status;
-
+ rtnl_lock();
status = ql_adapter_down(qdev);
if (status)
goto error;
status = ql_adapter_up(qdev);
if (status)
goto error;
-
+ rtnl_unlock();
return;
error:
QPRINTK(qdev, IFUP, ALERT,
"Driver up/down cycle failed, closing device\n");
- rtnl_lock();
+
set_bit(QL_ADAPTER_UP, &qdev->flags);
dev_close(qdev->ndev);
rtnl_unlock();
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)
return err;
}
+ qdev->ndev = ndev;
+ qdev->pdev = pdev;
+ pci_set_drvdata(pdev, ndev);
pos = pci_find_capability(pdev, PCI_CAP_ID_EXP);
if (pos <= 0) {
dev_err(&pdev->dev, PFX "Cannot find PCI Express capability, "
"aborting.\n");
- goto err_out;
+ return pos;
} else {
pci_read_config_word(pdev, pos + PCI_EXP_DEVCTL, &val16);
val16 &= ~PCI_EXP_DEVCTL_NOSNOOP_EN;
err = pci_request_regions(pdev, DRV_NAME);
if (err) {
dev_err(&pdev->dev, "PCI region request failed.\n");
- goto err_out;
+ return err;
}
pci_set_master(pdev);
goto err_out;
}
- pci_set_drvdata(pdev, ndev);
qdev->reg_base =
ioremap_nocache(pci_resource_start(pdev, 1),
pci_resource_len(pdev, 1));
goto err_out;
}
- qdev->ndev = ndev;
- qdev->pdev = pdev;
err = ql_get_board_info(qdev);
if (err) {
dev_err(&pdev->dev, "Register access failed.\n");
* 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);
INIT_DELAYED_WORK(&qdev->mpi_work, ql_mpi_work);
INIT_DELAYED_WORK(&qdev->mpi_port_cfg_work, ql_mpi_port_cfg_work);
INIT_DELAYED_WORK(&qdev->mpi_idc_work, ql_mpi_idc_work);
- mutex_init(&qdev->mpi_mutex);
init_completion(&qdev->ide_completion);
if (!cards_found) {