eth: mpnic: add a NAPI depletion check

The Rx path can wedge if page pool allocations fail in
__mpnic_fill_bdq(). The problematic sequence is: page pool allocations
fail, bdq rings are empty, device receives packet from the network, but
drops it for lack of buffer space and does not raise interrupt,
mpnic_poll() does not run, so page pool allocations are not retried.

To break out of this cycle, we can add a depletion check to our service
task. The depletion check checks if posted buffers are under a low
watermark, and raises a completion queue interrupt, so that mpnic_poll
will run on the corresponding napi vector.

A note about the lock free reads: We don't bother synchronizing the ring
head and tail reads with mpnic_poll(), because a false positive signal
would simply raise a spurious interrupt scheduling mpnic_poll(), and a
false negative signal will result in a retry, where if mpnic_poll() has
truly not been running, should then report accurately whether or not
posted Rx buffers are low.

Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Link: https://patch.msgid.link/20261001-linux-mpnic-v1-4-6422ee74233a@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 36 insertions, 0 deletions

diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_pci.c b/drivers/net/ethernet/meta/mpnic/mpnic_pci.c
index 17eae5a9ba16..125fb26edf93 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_pci.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_pci.c
@@ -11,6 +11,7 @@
 
 #include "mpnic.h"
 #include "mpnic_netdev.h"
+#include "mpnic_txrx.h"
 
 #define PCI_DEVICE_ID_META_MPNIC	0x0014
 
@@ -61,6 +62,9 @@ static void mpnic_service_task(struct work_struct *work)
 
 	netdev_lock(netdev);
 
+	if (netif_carrier_ok(netdev))
+		mpnic_napi_depletion_check(netdev_priv(netdev));
+
 	if (netif_running(netdev))
 		schedule_delayed_work(&mpd->service_task, HZ);
 
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
index 49061c7316d5..5495e9a9aa65 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.c
@@ -55,6 +55,12 @@ static unsigned int mpnic_desc_unused(struct mpnic_ring *ring)
 	return (ring->head - ring->tail - 1) & ring->size_mask;
 }
 
+static unsigned int mpnic_desc_used(struct mpnic_ring *ring)
+{
+	return (READ_ONCE(ring->tail) - READ_ONCE(ring->head)) &
+	       ring->size_mask;
+}
+
 static struct netdev_queue *mpnic_txring_txq(const struct net_device *dev,
 					     const struct mpnic_ring *ring)
 {
@@ -1393,3 +1399,28 @@ void mpnic_napi_enable(struct mpnic_net *mpn)
 
 	mpnic_wrfl(mpn->mpd);
 }
+
+void mpnic_napi_depletion_check(struct mpnic_net *mpn)
+{
+	int i, j, t;
+
+	for (i = 0; i < mpn->num_napi; i++) {
+		struct mpnic_napi_vector *nv = mpn->napi[i];
+
+		for (t = nv->txt_count, j = 0; j < nv->rxt_count; j++, t++) {
+			/* Check if BDs posted covers a max sized frame
+			 *  + 1 BD held by RDE as a spare
+			 *  + 1 BD of extra safety margin
+			 */
+			if (mpnic_desc_used(&nv->qt[t].sub0) <
+			    MPNIC_RX_HPQ_DROP_THRS + 2 ||
+			    mpnic_desc_used(&nv->qt[t].sub1) <
+			    MPNIC_RX_PPQ_DROP_THRS + 2) {
+				mpnic_nv_irq_trigger(nv);
+				break;
+			}
+		}
+	}
+
+	mpnic_wrfl(mpn->mpd);
+}
diff --git a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
index 9397010557eb..767d87a36c35 100644
--- a/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
+++ b/drivers/net/ethernet/meta/mpnic/mpnic_txrx.h
@@ -148,6 +148,7 @@ int mpnic_set_netif_queues(struct mpnic_net *mpn);
 void mpnic_reset_netif_queues(struct mpnic_net *mpn);
 void mpnic_napi_enable(struct mpnic_net *mpn);
 void mpnic_napi_disable(struct mpnic_net *mpn);
+void mpnic_napi_depletion_check(struct mpnic_net *mpn);
 void mpnic_enable(struct mpnic_net *mpn);
 void mpnic_disable(struct mpnic_net *mpn);
 void mpnic_wait_all_queues_idle(struct mpnic_dev *mpd);