I've been meaning to do this for a long time.
This adds tagged status support. With this, we don't need to
poke the chip 10 times per second via the timer to keep from
losing interrupts.
Michael, I didn't know what needs to be done wrt. MSI here.
So I didn't touch the MSI code until I understand things better,
which likely means that this patch breaks MSI (actually, I think
it will cause the MSI case to generate interrupts endlessly).
My best hunch is that all MSI supporting chips support tagged
status, therefore I should just make the tg3_msi() interrupt
handler do the tp->last_tag stuff.
We should also integrate the coalescing tweaks we did last week
after we smoothe this patch out.
I noticed that we were doing the 5705 status block fetch 10 times
per second instead of once per second. That's fixed here too.
I also removed the MAILBOX readback in the normal interrupt handling
paths. Network processing overhead minded folks, particular the SGI
NUMA people (hint hint) should really really check out this patch :-)
It is against current 2.6.x sources.
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
--- 1/drivers/net/tg3.c.~1~ 2005-05-05 17:15:59.000000000 -0700
+++ 2/drivers/net/tg3.c 2005-05-05 21:11:41.000000000 -0700
@@ -420,7 +420,8 @@ static void tg3_enable_ints(struct tg3 *
{
tw32(TG3PCI_MISC_HOST_CTRL,
(tp->misc_host_ctrl & ~MISC_HOST_CTRL_MASK_PCI_INT));
- tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW, 0x00000000);
+ tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW,
+ (tp->last_tag << 24));
tr32(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW);
tg3_cond_int(tp);
@@ -455,7 +456,8 @@ static void tg3_restart_ints(struct tg3
{
tw32(TG3PCI_MISC_HOST_CTRL,
(tp->misc_host_ctrl & ~MISC_HOST_CTRL_MASK_PCI_INT));
- tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW, 0x00000000);
+ tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW,
+ tp->last_tag << 24);
mmiowb();
if (tg3_has_work(tp))
@@ -2977,11 +2979,56 @@ static irqreturn_t tg3_interrupt(int irq
*/
tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW,
0x00000001);
+ sblk->status &= ~SD_STATUS_UPDATED;
+
+ if (likely(tg3_has_work(tp)))
+ netif_rx_schedule(dev); /* schedule NAPI poll */
+ else {
+ /* no work, shared interrupt perhaps? re-enable
+ * interrupts, and flush that PCI write
+ */
+ tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW,
+ 0x00000000);
+ tr32(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW);
+ }
+ } else { /* shared interrupt */
+ handled = 0;
+ }
+
+ spin_unlock_irqrestore(&tp->lock, flags);
+
+ return IRQ_RETVAL(handled);
+}
+
+static irqreturn_t tg3_interrupt_tagged(int irq, void *dev_id, struct pt_regs
*regs)
+{
+ struct net_device *dev = dev_id;
+ struct tg3 *tp = netdev_priv(dev);
+ struct tg3_hw_status *sblk = tp->hw_status;
+ unsigned long flags;
+ unsigned int handled = 1;
+
+ spin_lock_irqsave(&tp->lock, flags);
+
+ /* In INTx mode, it is possible for the interrupt to arrive at
+ * the CPU before the status block posted prior to the interrupt.
+ * Reading the PCI State register will confirm whether the
+ * interrupt is ours and will flush the status block.
+ */
+ if ((sblk->status & SD_STATUS_UPDATED) ||
+ !(tr32(TG3PCI_PCISTATE) & PCISTATE_INT_NOT_ACTIVE)) {
/*
- * Flush PCI write. This also guarantees that our
- * status block has been flushed to host memory.
+ * writing any value to intr-mbox-0 clears PCI INTA# and
+ * chip-internal interrupt pending events.
+ * writing non-zero to intr-mbox-0 additional tells the
+ * NIC to stop sending us irqs, engaging "in-intr-handler"
+ * event coalescing.
*/
- tr32(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW);
+ tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW,
+ 0x00000001);
+
+ tp->last_tag = sblk->status_tag;
+
sblk->status &= ~SD_STATUS_UPDATED;
if (likely(tg3_has_work(tp)))
@@ -2991,7 +3038,7 @@ static irqreturn_t tg3_interrupt(int irq
* interrupts, and flush that PCI write
*/
tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW,
- 0x00000000);
+ tp->last_tag << 24);
tr32(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW);
}
} else { /* shared interrupt */
@@ -5446,6 +5493,7 @@ static int tg3_reset_hw(struct tg3 *tp)
tw32_mailbox(MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW, 0);
tr32(MAILBOX_INTERRUPT_0);
+ tp->last_tag = 0;
if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS)) {
tw32_f(DMAC_MODE, DMAC_MODE_ENABLE);
@@ -5723,31 +5771,33 @@ static void tg3_timer(unsigned long __op
spin_lock_irqsave(&tp->lock, flags);
spin_lock(&tp->tx_lock);
- /* All of this garbage is because when using non-tagged
- * IRQ status the mailbox/status_block protocol the chip
- * uses with the cpu is race prone.
- */
- if (tp->hw_status->status & SD_STATUS_UPDATED) {
- tw32(GRC_LOCAL_CTRL,
- tp->grc_local_ctrl | GRC_LCLCTRL_SETINT);
- } else {
- tw32(HOSTCC_MODE, tp->coalesce_mode |
- (HOSTCC_MODE_ENABLE | HOSTCC_MODE_NOW));
- }
+ if (!(tp->tg3_flags & TG3_FLAG_TAGGED_STATUS)) {
+ /* All of this garbage is because when using non-tagged
+ * IRQ status the mailbox/status_block protocol the chip
+ * uses with the cpu is race prone.
+ */
+ if (tp->hw_status->status & SD_STATUS_UPDATED) {
+ tw32(GRC_LOCAL_CTRL,
+ tp->grc_local_ctrl | GRC_LCLCTRL_SETINT);
+ } else {
+ tw32(HOSTCC_MODE, tp->coalesce_mode |
+ (HOSTCC_MODE_ENABLE | HOSTCC_MODE_NOW));
+ }
- if (!(tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) {
- tp->tg3_flags2 |= TG3_FLG2_RESTART_TIMER;
- spin_unlock(&tp->tx_lock);
- spin_unlock_irqrestore(&tp->lock, flags);
- schedule_work(&tp->reset_task);
- return;
+ if (!(tr32(WDMAC_MODE) & WDMAC_MODE_ENABLE)) {
+ tp->tg3_flags2 |= TG3_FLG2_RESTART_TIMER;
+ spin_unlock(&tp->tx_lock);
+ spin_unlock_irqrestore(&tp->lock, flags);
+ schedule_work(&tp->reset_task);
+ return;
+ }
}
- if (tp->tg3_flags2 & TG3_FLG2_5705_PLUS)
- tg3_periodic_fetch_stats(tp);
-
/* This part only runs once per second. */
if (!--tp->timer_counter) {
+ if (tp->tg3_flags2 & TG3_FLG2_5705_PLUS)
+ tg3_periodic_fetch_stats(tp);
+
if (tp->tg3_flags & TG3_FLAG_USE_LINKCHG_REG) {
u32 mac_stat;
int phy_event;
@@ -5846,9 +5896,13 @@ static int tg3_test_interrupt(struct tg3
if (tp->tg3_flags2 & TG3_FLG2_USING_MSI)
err = request_irq(tp->pdev->irq, tg3_msi,
SA_SAMPLE_RANDOM, dev->name, dev);
- else
- err = request_irq(tp->pdev->irq, tg3_interrupt,
+ else {
+ irqreturn_t (*fn)(int, void *, struct pt_regs *)=tg3_interrupt;
+ if (tp->tg3_flags & TG3_FLAG_TAGGED_STATUS)
+ fn = tg3_interrupt_tagged;
+ err = request_irq(tp->pdev->irq, fn,
SA_SHIRQ | SA_SAMPLE_RANDOM, dev->name, dev);
+ }
if (err)
return err;
@@ -5900,9 +5954,14 @@ static int tg3_test_msi(struct tg3 *tp)
tp->tg3_flags2 &= ~TG3_FLG2_USING_MSI;
- err = request_irq(tp->pdev->irq, tg3_interrupt,
- SA_SHIRQ | SA_SAMPLE_RANDOM, dev->name, dev);
+ {
+ irqreturn_t (*fn)(int, void *, struct pt_regs *)=tg3_interrupt;
+ if (tp->tg3_flags & TG3_FLAG_TAGGED_STATUS)
+ fn = tg3_interrupt_tagged;
+ err = request_irq(tp->pdev->irq, fn,
+ SA_SHIRQ | SA_SAMPLE_RANDOM, dev->name, dev);
+ }
if (err)
return err;
@@ -5959,9 +6018,14 @@ static int tg3_open(struct net_device *d
if (tp->tg3_flags2 & TG3_FLG2_USING_MSI)
err = request_irq(tp->pdev->irq, tg3_msi,
SA_SAMPLE_RANDOM, dev->name, dev);
- else
- err = request_irq(tp->pdev->irq, tg3_interrupt,
+ else {
+ irqreturn_t (*fn)(int, void *, struct pt_regs *)=tg3_interrupt;
+ if (tp->tg3_flags & TG3_FLAG_TAGGED_STATUS)
+ fn = tg3_interrupt_tagged;
+
+ err = request_irq(tp->pdev->irq, fn,
SA_SHIRQ | SA_SAMPLE_RANDOM, dev->name, dev);
+ }
if (err) {
if (tp->tg3_flags2 & TG3_FLG2_USING_MSI) {
@@ -5980,9 +6044,16 @@ static int tg3_open(struct net_device *d
tg3_halt(tp, 1);
tg3_free_rings(tp);
} else {
- tp->timer_offset = HZ / 10;
- tp->timer_counter = tp->timer_multiplier = 10;
- tp->asf_counter = tp->asf_multiplier = (10 * 120);
+ if (tp->tg3_flags & TG3_FLAG_TAGGED_STATUS)
+ tp->timer_offset = HZ;
+ else
+ tp->timer_offset = HZ / 10;
+
+ BUG_ON(tp->timer_offset > HZ);
+ tp->timer_counter = tp->timer_multiplier =
+ (HZ / tp->timer_offset);
+ tp->asf_counter = tp->asf_multiplier =
+ ((HZ / tp->timer_offset) * 120);
init_timer(&tp->timer);
tp->timer.expires = jiffies + tp->timer_offset;
@@ -8422,15 +8493,7 @@ static int __devinit tg3_get_invariants(
if (tp->tg3_flags2 & TG3_FLG2_5705_PLUS)
tp->tg3_flags2 |= TG3_FLG2_PHY_BER_BUG;
- /* Only 5701 and later support tagged irq status mode.
- * Also, 5788 chips cannot use tagged irq status.
- *
- * However, since we are using NAPI avoid tagged irq status
- * because the interrupt condition is more difficult to
- * fully clear in that mode.
- */
tp->coalesce_mode = 0;
-
if (GET_CHIP_REV(tp->pci_chip_rev_id) != CHIPREV_5700_AX &&
GET_CHIP_REV(tp->pci_chip_rev_id) != CHIPREV_5700_BX)
tp->coalesce_mode |= HOSTCC_MODE_32BYTE;
@@ -8494,6 +8557,18 @@ static int __devinit tg3_get_invariants(
grc_misc_cfg == GRC_MISC_CFG_BOARD_ID_5788M))
tp->tg3_flags2 |= TG3_FLG2_IS_5788;
+ if (!(tp->tg3_flags2 & TG3_FLG2_IS_5788) &&
+ (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5700))
+ tp->tg3_flags |= TG3_FLAG_TAGGED_STATUS;
+ if (tp->tg3_flags & TG3_FLAG_TAGGED_STATUS) {
+ tp->coalesce_mode |= (HOSTCC_MODE_CLRTICK_RXBD |
+ HOSTCC_MODE_CLRTICK_TXBD);
+
+ tp->misc_host_ctrl |= MISC_HOST_CTRL_TAGGED_STATUS;
+ pci_write_config_dword(tp->pdev, TG3PCI_MISC_HOST_CTRL,
+ tp->misc_host_ctrl);
+ }
+
/* these are limited to 10/100 only */
if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5703 &&
(grc_misc_cfg == 0x8000 || grc_misc_cfg == 0x4000)) ||
--- 1/drivers/net/tg3.h.~1~ 2005-05-05 17:15:59.000000000 -0700
+++ 2/drivers/net/tg3.h 2005-05-05 20:58:56.000000000 -0700
@@ -2023,6 +2023,7 @@ struct tg3 {
struct tg3_hw_status *hw_status;
dma_addr_t status_mapping;
+ u32 last_tag;
u32 msg_enable;
@@ -2068,6 +2069,7 @@ struct tg3 {
u32 rx_offset;
u32 tg3_flags;
+#define TG3_FLAG_TAGGED_STATUS 0x00000001
#define TG3_FLAG_TXD_MBOX_HWBUG 0x00000002
#define TG3_FLAG_RX_CHECKSUMS 0x00000004
#define TG3_FLAG_USE_LINKCHG_REG 0x00000008
|