forcedeth: irq data path optimization
This patch optimizes the irq data paths and cleans up the code.
Signed-Off-By: Ayaz Abdulla <aabdulla@nvidia.com>
Signed-off-by: Jeff Garzik <jeff@garzik.org>
diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c
index fd91071..7c0f0cc 100644
--- a/drivers/net/forcedeth.c
+++ b/drivers/net/forcedeth.c
@@ -2777,7 +2777,6 @@
events = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQSTAT_MASK;
writel(NVREG_IRQSTAT_MASK, base + NvRegMSIXIrqStatus);
}
- pci_push(base);
dprintk(KERN_DEBUG "%s: irq: %08x\n", dev->name, events);
if (!(events & np->irqmask))
break;
@@ -2786,22 +2785,46 @@
nv_tx_done(dev);
spin_unlock(&np->lock);
- if (events & NVREG_IRQ_LINK) {
+#ifdef CONFIG_FORCEDETH_NAPI
+ if (events & NVREG_IRQ_RX_ALL) {
+ netif_rx_schedule(dev);
+
+ /* Disable furthur receive irq's */
+ spin_lock(&np->lock);
+ np->irqmask &= ~NVREG_IRQ_RX_ALL;
+
+ if (np->msi_flags & NV_MSI_X_ENABLED)
+ writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
+ else
+ writel(np->irqmask, base + NvRegIrqMask);
+ spin_unlock(&np->lock);
+ }
+#else
+ if (nv_rx_process(dev, dev->weight)) {
+ if (unlikely(nv_alloc_rx(dev))) {
+ spin_lock(&np->lock);
+ if (!np->in_shutdown)
+ mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
+ spin_unlock(&np->lock);
+ }
+ }
+#endif
+ if (unlikely(events & NVREG_IRQ_LINK)) {
spin_lock(&np->lock);
nv_link_irq(dev);
spin_unlock(&np->lock);
}
- if (np->need_linktimer && time_after(jiffies, np->link_timeout)) {
+ if (unlikely(np->need_linktimer && time_after(jiffies, np->link_timeout))) {
spin_lock(&np->lock);
nv_linkchange(dev);
spin_unlock(&np->lock);
np->link_timeout = jiffies + LINK_TIMEOUT;
}
- if (events & (NVREG_IRQ_TX_ERR)) {
+ if (unlikely(events & (NVREG_IRQ_TX_ERR))) {
dprintk(KERN_DEBUG "%s: received irq with events 0x%x. Probably TX fail.\n",
dev->name, events);
}
- if (events & (NVREG_IRQ_UNKNOWN)) {
+ if (unlikely(events & (NVREG_IRQ_UNKNOWN))) {
printk(KERN_DEBUG "%s: received irq with unknown events 0x%x. Please report\n",
dev->name, events);
}
@@ -2822,30 +2845,7 @@
spin_unlock(&np->lock);
break;
}
-#ifdef CONFIG_FORCEDETH_NAPI
- if (events & NVREG_IRQ_RX_ALL) {
- netif_rx_schedule(dev);
-
- /* Disable furthur receive irq's */
- spin_lock(&np->lock);
- np->irqmask &= ~NVREG_IRQ_RX_ALL;
-
- if (np->msi_flags & NV_MSI_X_ENABLED)
- writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
- else
- writel(np->irqmask, base + NvRegIrqMask);
- spin_unlock(&np->lock);
- }
-#else
- nv_rx_process(dev, dev->weight);
- if (nv_alloc_rx(dev)) {
- spin_lock(&np->lock);
- if (!np->in_shutdown)
- mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
- spin_unlock(&np->lock);
- }
-#endif
- if (i > max_interrupt_work) {
+ if (unlikely(i > max_interrupt_work)) {
spin_lock(&np->lock);
/* disable interrupts on the nic */
if (!(np->msi_flags & NV_MSI_X_ENABLED))
@@ -2869,6 +2869,13 @@
return IRQ_RETVAL(i);
}
+#define TX_WORK_PER_LOOP 64
+#define RX_WORK_PER_LOOP 64
+/**
+ * All _optimized functions are used to help increase performance
+ * (reduce CPU and increase throughput). They use descripter version 3,
+ * compiler directives, and reduce memory accesses.
+ */
static irqreturn_t nv_nic_irq_optimized(int foo, void *data)
{
struct net_device *dev = (struct net_device *) data;
@@ -2887,7 +2894,6 @@
events = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQSTAT_MASK;
writel(NVREG_IRQSTAT_MASK, base + NvRegMSIXIrqStatus);
}
- pci_push(base);
dprintk(KERN_DEBUG "%s: irq: %08x\n", dev->name, events);
if (!(events & np->irqmask))
break;
@@ -2896,22 +2902,46 @@
nv_tx_done_optimized(dev);
spin_unlock(&np->lock);
- if (events & NVREG_IRQ_LINK) {
+#ifdef CONFIG_FORCEDETH_NAPI
+ if (events & NVREG_IRQ_RX_ALL) {
+ netif_rx_schedule(dev);
+
+ /* Disable furthur receive irq's */
+ spin_lock(&np->lock);
+ np->irqmask &= ~NVREG_IRQ_RX_ALL;
+
+ if (np->msi_flags & NV_MSI_X_ENABLED)
+ writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
+ else
+ writel(np->irqmask, base + NvRegIrqMask);
+ spin_unlock(&np->lock);
+ }
+#else
+ if (nv_rx_process_optimized(dev, dev->weight)) {
+ if (unlikely(nv_alloc_rx_optimized(dev))) {
+ spin_lock(&np->lock);
+ if (!np->in_shutdown)
+ mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
+ spin_unlock(&np->lock);
+ }
+ }
+#endif
+ if (unlikely(events & NVREG_IRQ_LINK)) {
spin_lock(&np->lock);
nv_link_irq(dev);
spin_unlock(&np->lock);
}
- if (np->need_linktimer && time_after(jiffies, np->link_timeout)) {
+ if (unlikely(np->need_linktimer && time_after(jiffies, np->link_timeout))) {
spin_lock(&np->lock);
nv_linkchange(dev);
spin_unlock(&np->lock);
np->link_timeout = jiffies + LINK_TIMEOUT;
}
- if (events & (NVREG_IRQ_TX_ERR)) {
+ if (unlikely(events & (NVREG_IRQ_TX_ERR))) {
dprintk(KERN_DEBUG "%s: received irq with events 0x%x. Probably TX fail.\n",
dev->name, events);
}
- if (events & (NVREG_IRQ_UNKNOWN)) {
+ if (unlikely(events & (NVREG_IRQ_UNKNOWN))) {
printk(KERN_DEBUG "%s: received irq with unknown events 0x%x. Please report\n",
dev->name, events);
}
@@ -2933,30 +2963,7 @@
break;
}
-#ifdef CONFIG_FORCEDETH_NAPI
- if (events & NVREG_IRQ_RX_ALL) {
- netif_rx_schedule(dev);
-
- /* Disable furthur receive irq's */
- spin_lock(&np->lock);
- np->irqmask &= ~NVREG_IRQ_RX_ALL;
-
- if (np->msi_flags & NV_MSI_X_ENABLED)
- writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
- else
- writel(np->irqmask, base + NvRegIrqMask);
- spin_unlock(&np->lock);
- }
-#else
- nv_rx_process_optimized(dev, dev->weight);
- if (nv_alloc_rx_optimized(dev)) {
- spin_lock(&np->lock);
- if (!np->in_shutdown)
- mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
- spin_unlock(&np->lock);
- }
-#endif
- if (i > max_interrupt_work) {
+ if (unlikely(i > max_interrupt_work)) {
spin_lock(&np->lock);
/* disable interrupts on the nic */
if (!(np->msi_flags & NV_MSI_X_ENABLED))
@@ -2994,7 +3001,6 @@
for (i=0; ; i++) {
events = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQ_TX_ALL;
writel(NVREG_IRQ_TX_ALL, base + NvRegMSIXIrqStatus);
- pci_push(base);
dprintk(KERN_DEBUG "%s: tx irq: %08x\n", dev->name, events);
if (!(events & np->irqmask))
break;
@@ -3003,11 +3009,11 @@
nv_tx_done_optimized(dev);
spin_unlock_irqrestore(&np->lock, flags);
- if (events & (NVREG_IRQ_TX_ERR)) {
+ if (unlikely(events & (NVREG_IRQ_TX_ERR))) {
dprintk(KERN_DEBUG "%s: received irq with events 0x%x. Probably TX fail.\n",
dev->name, events);
}
- if (i > max_interrupt_work) {
+ if (unlikely(i > max_interrupt_work)) {
spin_lock_irqsave(&np->lock, flags);
/* disable interrupts on the nic */
writel(NVREG_IRQ_TX_ALL, base + NvRegIrqMask);
@@ -3105,20 +3111,20 @@
for (i=0; ; i++) {
events = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQ_RX_ALL;
writel(NVREG_IRQ_RX_ALL, base + NvRegMSIXIrqStatus);
- pci_push(base);
dprintk(KERN_DEBUG "%s: rx irq: %08x\n", dev->name, events);
if (!(events & np->irqmask))
break;
- nv_rx_process_optimized(dev, dev->weight);
- if (nv_alloc_rx_optimized(dev)) {
- spin_lock_irqsave(&np->lock, flags);
- if (!np->in_shutdown)
- mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
- spin_unlock_irqrestore(&np->lock, flags);
+ if (nv_rx_process_optimized(dev, dev->weight)) {
+ if (unlikely(nv_alloc_rx_optimized(dev))) {
+ spin_lock_irqsave(&np->lock, flags);
+ if (!np->in_shutdown)
+ mod_timer(&np->oom_kick, jiffies + OOM_REFILL);
+ spin_unlock_irqrestore(&np->lock, flags);
+ }
}
- if (i > max_interrupt_work) {
+ if (unlikely(i > max_interrupt_work)) {
spin_lock_irqsave(&np->lock, flags);
/* disable interrupts on the nic */
writel(NVREG_IRQ_RX_ALL, base + NvRegIrqMask);
@@ -3153,7 +3159,6 @@
for (i=0; ; i++) {
events = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQ_OTHER;
writel(NVREG_IRQ_OTHER, base + NvRegMSIXIrqStatus);
- pci_push(base);
dprintk(KERN_DEBUG "%s: irq: %08x\n", dev->name, events);
if (!(events & np->irqmask))
break;
@@ -3187,7 +3192,7 @@
printk(KERN_DEBUG "%s: received irq with unknown events 0x%x. Please report\n",
dev->name, events);
}
- if (i > max_interrupt_work) {
+ if (unlikely(i > max_interrupt_work)) {
spin_lock_irqsave(&np->lock, flags);
/* disable interrupts on the nic */
writel(NVREG_IRQ_OTHER, base + NvRegIrqMask);
@@ -4969,7 +4974,7 @@
#ifdef CONFIG_NET_POLL_CONTROLLER
dev->poll_controller = nv_poll_controller;
#endif
- dev->weight = 64;
+ dev->weight = RX_WORK_PER_LOOP;
#ifdef CONFIG_FORCEDETH_NAPI
dev->poll = nv_napi_poll;
#endif