Merge branch 'qed-doorbell-overflow-recovery'

Denis Bolotin says:

====================
qed: Fix the Doorbell Overflow Recovery mechanism

This patch series fixes and improves the doorbell recovery mechanism.
The main goals of this series are to fix missing attentions from the
doorbells block (DORQ) or not handling them properly, and execute the
recovery from periodic handler instead of the attention handler.

Please consider applying the series to net.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 63 insertions, 20 deletions

diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index e23980e301b6..8848d5bed6e5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -378,6 +378,9 @@ static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn,
 	u32 count = QED_DB_REC_COUNT;
 	u32 usage = 1;
 
+	/* Flush any pending (e)dpms as they may never arrive */
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
+
 	/* wait for usage to zero or count to run out. This is necessary since
 	 * EDPM doorbell transactions can take multiple 64b cycles, and as such
 	 * can "split" over the pci. Possibly, the doorbell drop can happen with
@@ -406,51 +409,74 @@ static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn,
 
 int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	u32 overflow;
+	u32 attn_ovfl, cur_ovfl;
 	int rc;
 
-	overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
-	DP_NOTICE(p_hwfn, "PF Overflow sticky 0x%x\n", overflow);
-	if (!overflow) {
-		qed_db_recovery_execute(p_hwfn, DB_REC_ONCE);
+	attn_ovfl = test_and_clear_bit(QED_OVERFLOW_BIT,
+				       &p_hwfn->db_recovery_info.overflow);
+	cur_ovfl = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+	if (!cur_ovfl && !attn_ovfl)
 		return 0;
-	}
 
-	if (qed_edpm_enabled(p_hwfn)) {
+	DP_NOTICE(p_hwfn, "PF Overflow sticky: attn %u current %u\n",
+		  attn_ovfl, cur_ovfl);
+
+	if (cur_ovfl && !p_hwfn->db_bar_no_edpm) {
 		rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
 		if (rc)
 			return rc;
 	}
 
-	/* Flush any pending (e)dpm as they may never arrive */
-	qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
-
 	/* Release overflow sticky indication (stop silently dropping everything) */
 	qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
 
 	/* Repeat all last doorbells (doorbell drop recovery) */
-	qed_db_recovery_execute(p_hwfn, DB_REC_REAL_DEAL);
+	qed_db_recovery_execute(p_hwfn);
 
 	return 0;
 }
 
-static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+static void qed_dorq_attn_overflow(struct qed_hwfn *p_hwfn)
 {
-	u32 int_sts, first_drop_reason, details, address, all_drops_reason;
 	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
+	u32 overflow;
 	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);
+	overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+	if (!overflow)
+		goto out;
+
+	/* Run PF doorbell recovery in next periodic handler */
+	set_bit(QED_OVERFLOW_BIT, &p_hwfn->db_recovery_info.overflow);
+
+	if (!p_hwfn->db_bar_no_edpm) {
+		rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
+		if (rc)
+			goto out;
+	}
+
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
+out:
+	/* Schedule the handler even if overflow was not detected */
+	qed_periodic_db_rec_start(p_hwfn);
+}
+
+static int qed_dorq_attn_int_sts(struct qed_hwfn *p_hwfn)
+{
+	u32 int_sts, first_drop_reason, details, address, all_drops_reason;
+	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
 
 	/* 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)) {
@@ -477,11 +503,6 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
 			  GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4,
 			  first_drop_reason, all_drops_reason);
 
-		rc = qed_db_rec_handler(p_hwfn, p_ptt);
-		qed_periodic_db_rec_start(p_hwfn);
-		if (rc)
-			return rc;
-
 		/* Clear the doorbell drop details and prepare for next drop */
 		qed_wr(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS_REL, 0);
 
@@ -507,6 +528,25 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
 	return -EINVAL;
 }
 
+static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+{
+	p_hwfn->db_recovery_info.dorq_attn = true;
+	qed_dorq_attn_overflow(p_hwfn);
+
+	return qed_dorq_attn_int_sts(p_hwfn);
+}
+
+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.
  */
@@ -1080,6 +1120,9 @@ 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 +