octeontx2-pf: Fix page pool cache index corruption.

The access to page pool `cache' array and the `count' variable
is not locked. Page pool cache access is fine as long as there
is only one consumer per pool.

octeontx2 driver fills in rx buffers from page pool in NAPI context.
If system is stressed and could not allocate buffers, refiiling work
will be delegated to a delayed workqueue. This means that there are
two cosumers to the page pool cache.

Either workqueue or IRQ/NAPI can be run on other CPU. This will lead
to lock less access, hence corruption of cache pool indexes.

To fix this issue, NAPI is rescheduled from workqueue context to refill
rx buffers.

Fixes: b2e3406a38f0 ("octeontx2-pf: Add support for page pool")
Signed-off-by: Ratheesh Kannoth <rkannoth@marvell.com>
Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 25 insertions, 5 deletions

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index e369baf11530..e77d43848955 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -424,9 +424,10 @@ process_cqe:
 	return processed_cqe;
 }
 
-void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
+int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 {
 	struct otx2_nic *pfvf = dev;
+	int cnt = cq->pool_ptrs;
 	dma_addr_t bufptr;
 
 	while (cq->pool_ptrs) {
@@ -435,6 +436,8 @@ void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 		otx2_aura_freeptr(pfvf, cq->cq_idx, bufptr + OTX2_HEAD_ROOM);
 		cq->pool_ptrs--;
 	}
+
+	return cnt - cq->pool_ptrs;
 }
 
 static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
@@ -521,6 +524,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 	struct otx2_cq_queue *cq;
 	struct otx2_qset *qset;
 	struct otx2_nic *pfvf;
+	int filled_cnt = -1;
 
 	cq_poll = container_of(napi, struct otx2_cq_poll, napi);
 	pfvf = (struct otx2_nic *)cq_poll->dev;
@@ -541,7 +545,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 	}
 
 	if (rx_cq && rx_cq->pool_ptrs)
-		pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq);
+		filled_cnt = pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq);
 	/* Clear the IRQ */
 	otx2_write64(pfvf, NIX_LF_CINTX_INT(cq_poll->cint_idx), BIT_ULL(0));
 
@@ -561,9 +565,25 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 				otx2_config_irq_coalescing(pfvf, i);
 		}
 
-		/* Re-enable interrupts */
-		otx2_write64(pfvf, NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx),
-			     BIT_ULL(0));
+		if (unlikely(!filled_cnt)) {
+			struct refill_work *work;
+			struct delayed_work *dwork;
+
+			work = &pfvf->refill_wrk[cq->cq_idx];
+			dwork = &work->pool_refill_work;
+			/* Schedule a task if no other task is running */
+			if (!cq->refill_task_sched) {
+				work->napi = napi;
+				cq->refill_task_sched = true;
+				schedule_delayed_work(dwork,
+						      msecs_to_jiffies(100));
+			}
+		} else {
+			/* Re-enable interrupts */
+			otx2_write64(pfvf,
+				     NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx),
+				     BIT_ULL(0));
+		}
 	}
 	return workdone;
 }