qed: Fix missing DORQ attentions

When the DORQ (doorbell block) is overflowed, all PFs get attentions at the
same time. If one PF finished handling the attention before another PF even
started, the second PF might miss the DORQ's attention bit and not handle
the attention at all.
If the DORQ attention is missed and the issue is not resolved, another
attention will not be sent, therefore each attention is treated as a
potential DORQ attention.
As a result, the attention callback is called more frequently so the debug
print was moved to reduce its quantity.
The number of periodic doorbell recovery handler schedules was reduced
because it was the previous way to mitigating the missed attention issue.

Signed-off-by: Denis Bolotin <dbolotin@marvell.com>
Signed-off-by: Michal Kalderon <mkalderon@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 20 insertions, 3 deletions

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 1514ec93b989..fcc2d745c375 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -436,6 +436,7 @@ struct qed_db_recovery_info {
 
 	/* Lock to protect the doorbell recovery mechanism list */
 	spinlock_t lock;
+	bool dorq_attn;
 	u32 db_recovery_counter;
 };
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index 3546e253c75f..fe3286fc956b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -438,17 +438,19 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
 	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
 	int rc;
 
-	int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
-	DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+	p_hwfn->db_recovery_info.dorq_attn = true;
 
 	/* int_sts may be zero since all PFs were interrupted for doorbell
 	 * overflow but another one already handled it. Can abort here. If
 	 * This PF also requires overflow recovery we will be interrupted again.
 	 * The masked almost full indication may also be set. Ignoring.
 	 */
+	int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
 	if (!(int_sts & ~DORQ_REG_INT_STS_DORQ_FIFO_AFULL))
 		return 0;
 
+	DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+
 	/* check if db_drop or overflow happened */
 	if (int_sts & (DORQ_REG_INT_STS_DB_DROP |
 		       DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR)) {
@@ -505,6 +507,17 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
 	return -EINVAL;
 }
 
+static void qed_dorq_attn_handler(struct qed_hwfn *p_hwfn)
+{
+	if (p_hwfn->db_recovery_info.dorq_attn)
+		goto out;
+
+	/* Call DORQ callback if the attention was missed */
+	qed_dorq_attn_cb(p_hwfn);
+out:
+	p_hwfn->db_recovery_info.dorq_attn = false;
+}
+
 /* Instead of major changes to the data-structure, we have a some 'special'
  * identifiers for sources that changed meaning between adapters.
  */
@@ -1078,6 +1091,9 @@ static int qed_int_deassertion(struct qed_hwfn  *p_hwfn,
 		}
 	}
 
+	/* Handle missed DORQ attention */
+	qed_dorq_attn_handler(p_hwfn);
+
 	/* Clear IGU indication for the deasserted bits */
 	DIRECT_REG_WR((u8 __iomem *)p_hwfn->regview +
 				    GTT_BAR0_MAP_REG_IGU_CMD +
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index f164d4acebcb..6de23b56b294 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -970,7 +970,7 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 	}
 }
 
-#define QED_PERIODIC_DB_REC_COUNT		100
+#define QED_PERIODIC_DB_REC_COUNT		10
 #define QED_PERIODIC_DB_REC_INTERVAL_MS		100
 #define QED_PERIODIC_DB_REC_INTERVAL \
 	msecs_to_jiffies(QED_PERIODIC_DB_REC_INTERVAL_MS)