sfc: Rework IRQ enable/disable

There are many problems with the current efx_stop_interrupts() and
efx_start_interrupts():

1. On Siena, it is unsafe to disable the master IRQ enable bit
(DRV_INT_EN_KER) while any IRQ sources are enabled.

2. On EF10 there is no master IRQ enable bit, so we cannot expect to
defer IRQs without tearing down event queues.  (Though I don't think
we will need to keep any event queues around while the device is down,
as we do for VFDI on Siena.)

3. synchronize_irq() only waits for a running IRQ handler to finish,
not for any propagation through IRQ controllers.  Therefore an IRQ may
still be received and handled after efx_stop_interrupts() returns.
IRQ handlers can then race with channel reallocation.

To fix this:

a. Introduce a software IRQ enable flag.  So long as this is clear,
IRQ handlers will only acknowledge IRQs and not touch the channel
structures.

b. Define a new struct efx_msi_context as the context for MSIs.  This
is never reallocated and is sufficient to find the software enable
flag and the channel structure.  It also includes the channel/IRQ
name, which was previously separated out as it must also not be
reallocated.

c. Split efx_{start,stop}_interrupts() into
efx_{,soft_}_{enable,disable}_interrupts().  The 'soft' functions
don't touch the hardware master enable flag (if it exists) and don't
reinitialise or tear down channels with the keep_eventq flag set.

Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>

1 files changed, 28 insertions, 25 deletions

diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index f758333b4d85..c17d659f4525 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -1567,6 +1567,7 @@ irqreturn_t efx_nic_fatal_interrupt(struct efx_nic *efx)
 static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id)
 {
 	struct efx_nic *efx = dev_id;
+	bool soft_enabled = ACCESS_ONCE(efx->irq_soft_enabled);
 	efx_oword_t *int_ker = efx->irq_status.addr;
 	irqreturn_t result = IRQ_NONE;
 	struct efx_channel *channel;
@@ -1574,12 +1575,6 @@ static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id)
 	u32 queues;
 	int syserr;
 
-	/* Could this be ours?  If interrupts are disabled then the
-	 * channel state may not be valid.
-	 */
-	if (!efx->legacy_irq_enabled)
-		return result;
-
 	/* Read the ISR which also ACKs the interrupts */
 	efx_readd(efx, &reg, FR_BZ_INT_ISR0);
 	queues = EFX_EXTRACT_DWORD(reg, 0, 31);
@@ -1595,7 +1590,7 @@ static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id)
 	}
 
 	/* Handle non-event-queue sources */
-	if (queues & (1U << efx->irq_level)) {
+	if (queues & (1U << efx->irq_level) && soft_enabled) {
 		syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
 		if (unlikely(syserr))
 			return efx_nic_fatal_interrupt(efx);
@@ -1607,10 +1602,12 @@ static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id)
 			efx->irq_zero_count = 0;
 
 		/* Schedule processing of any interrupting queues */
-		efx_for_each_channel(channel, efx) {
-			if (queues & 1)
-				efx_schedule_channel_irq(channel);
-			queues >>= 1;
+		if (likely(soft_enabled)) {
+			efx_for_each_channel(channel, efx) {
+				if (queues & 1)
+					efx_schedule_channel_irq(channel);
+				queues >>= 1;
+			}
 		}
 		result = IRQ_HANDLED;
 
@@ -1623,12 +1620,15 @@ static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id)
 			result = IRQ_HANDLED;
 
 		/* Ensure we schedule or rearm all event queues */
-		efx_for_each_channel(channel, efx) {
-			event = efx_event(channel, channel->eventq_read_ptr);
-			if (efx_event_present(event))
-				efx_schedule_channel_irq(channel);
-			else
-				efx_nic_eventq_read_ack(channel);
+		if (likely(soft_enabled)) {
+			efx_for_each_channel(channel, efx) {
+				event = efx_event(channel,
+						  channel->eventq_read_ptr);
+				if (efx_event_present(event))
+					efx_schedule_channel_irq(channel);
+				else
+					efx_nic_eventq_read_ack(channel);
+			}
 		}
 	}
 
@@ -1649,8 +1649,8 @@ static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id)
  */
 static irqreturn_t efx_msi_interrupt(int irq, void *dev_id)
 {
-	struct efx_channel *channel = *(struct efx_channel **)dev_id;
-	struct efx_nic *efx = channel->efx;
+	struct efx_msi_context *context = dev_id;
+	struct efx_nic *efx = context->efx;
 	efx_oword_t *int_ker = efx->irq_status.addr;
 	int syserr;
 
@@ -1658,8 +1658,11 @@ static irqreturn_t efx_msi_interrupt(int irq, void *dev_id)
 		   "IRQ %d on CPU %d status " EFX_OWORD_FMT "\n",
 		   irq, raw_smp_processor_id(), EFX_OWORD_VAL(*int_ker));
 
+	if (!likely(ACCESS_ONCE(efx->irq_soft_enabled)))
+		return IRQ_HANDLED;
+
 	/* Handle non-event-queue sources */
-	if (channel->channel == efx->irq_level) {
+	if (context->index == efx->irq_level) {
 		syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
 		if (unlikely(syserr))
 			return efx_nic_fatal_interrupt(efx);
@@ -1667,7 +1670,7 @@ static irqreturn_t efx_msi_interrupt(int irq, void *dev_id)
 	}
 
 	/* Schedule processing of the channel */
-	efx_schedule_channel_irq(channel);
+	efx_schedule_channel_irq(efx->channel[context->index]);
 
 	return IRQ_HANDLED;
 }
@@ -1739,8 +1742,8 @@ int efx_nic_init_interrupt(struct efx_nic *efx)
 	efx_for_each_channel(channel, efx) {
 		rc = request_irq(channel->irq, efx_msi_interrupt,
 				 IRQF_PROBE_SHARED, /* Not shared */
-				 efx->channel_name[channel->channel],
-				 &efx->channel[channel->channel]);
+				 efx->msi_context[channel->channel].name,
+				 &efx->msi_context[channel->channel]);
 		if (rc) {
 			netif_err(efx, drv, efx->net_dev,
 				  "failed to hook IRQ %d\n", channel->irq);
@@ -1769,7 +1772,7 @@ int efx_nic_init_interrupt(struct efx_nic *efx)
 	efx_for_each_channel(channel, efx) {
 		if (n_irqs-- == 0)
 			break;
-		free_irq(channel->irq, &efx->channel[channel->channel]);
+		free_irq(channel->irq, &efx->msi_context[channel->channel]);
 	}
  fail1:
 	return rc;
@@ -1787,7 +1790,7 @@ void efx_nic_fini_interrupt(struct efx_nic *efx)
 
 	/* Disable MSI/MSI-X interrupts */
 	efx_for_each_channel(channel, efx)
-		free_irq(channel->irq, &efx->channel[channel->channel]);
+		free_irq(channel->irq, &efx->msi_context[channel->channel]);
 
 	/* ACK legacy interrupt */
 	if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0)