scsi: qedi: Add support for fastpath doorbell recovery

Driver fastpath employs doorbells to indicate to the device that work is
available. Each doorbell translates to a message sent to the device over
PCI. These messages are queued by the doorbell queue HW block, and handled
by the HW.

If a sufficient amount of CPU cores are sending messages at a sufficient
rate, the queue can overflow, and messages can be dropped. There are many
entities in the driver which can send doorbell messages.  When overflow
happens, a fatal HW attention is indicated, and the Doorbell HW block stops
accepting new doorbell messages until recovery procedure is done.

When overflow occurs, all doorbells are dropped. Since doorbells are
aggregatives, if more doorbells are sent nothing has to be done.  But if
the "last" doorbell is dropped, the doorbelling entity doesn’t know this
happened, and may wait forever for the device to perform the action.  The
doorbell recovery mechanism addresses just that - it sends the last
doorbell of every entity.

[mkp: fix missing brackets reported by Guenter Roeck]

Link: https://lore.kernel.org/r/20210804221412.5048-1-smalin@marvell.com
Co-developed-by: Manish Rangankar <mrangankar@marvell.com>
Signed-off-by: Manish Rangankar <mrangankar@marvell.com>
Signed-off-by: Shai Malin <smalin@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

3 files changed, 39 insertions, 12 deletions

diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
index ac99e980bb31..d01cd829ef97 100644
--- a/drivers/scsi/qedi/qedi_fw.c
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -929,17 +929,11 @@ exit_fp_process:
 
 static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
 {
-	struct iscsi_db_data dbell = { 0 };
+	qedi_conn->ep->db_data.sq_prod = qedi_conn->ep->fw_sq_prod_idx;
 
-	dbell.agg_flags = 0;
-
-	dbell.params |= DB_DEST_XCM << ISCSI_DB_DATA_DEST_SHIFT;
-	dbell.params |= DB_AGG_CMD_SET << ISCSI_DB_DATA_AGG_CMD_SHIFT;
-	dbell.params |=
-		   DQ_XCM_ISCSI_SQ_PROD_CMD << ISCSI_DB_DATA_AGG_VAL_SEL_SHIFT;
-
-	dbell.sq_prod = qedi_conn->ep->fw_sq_prod_idx;
-	writel(*(u32 *)&dbell, qedi_conn->ep->p_doorbell);
+	/* wmb - Make sure fw idx is coherent */
+	wmb();
+	writel(*(u32 *)&qedi_conn->ep->db_data, qedi_conn->ep->p_doorbell);
 
 	/* Make sure fw write idx is coherent, and include both memory barriers
 	 * as a failsafe as for some architectures the call is the same but on
diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c
index 97f83760da88..c5260429c637 100644
--- a/drivers/scsi/qedi/qedi_iscsi.c
+++ b/drivers/scsi/qedi/qedi_iscsi.c
@@ -499,8 +499,8 @@ static u16 qedi_calc_mss(u16 pmtu, u8 is_ipv6, u8 tcp_ts_en, u8 vlan_en)
 
 static int qedi_iscsi_offload_conn(struct qedi_endpoint *qedi_ep)
 {
-	struct qedi_ctx *qedi = qedi_ep->qedi;
 	struct qed_iscsi_params_offload *conn_info;
+	struct qedi_ctx *qedi = qedi_ep->qedi;
 	int rval;
 	int i;
 
@@ -577,10 +577,37 @@ static int qedi_iscsi_offload_conn(struct qedi_endpoint *qedi_ep)
 		  "Default cq index [%d], mss [%d]\n",
 		  conn_info->default_cq, conn_info->mss);
 
+	/* Prepare the doorbell parameters */
+	qedi_ep->db_data.agg_flags = 0;
+	qedi_ep->db_data.params = 0;
+	SET_FIELD(qedi_ep->db_data.params, ISCSI_DB_DATA_DEST, DB_DEST_XCM);
+	SET_FIELD(qedi_ep->db_data.params, ISCSI_DB_DATA_AGG_CMD,
+		  DB_AGG_CMD_MAX);
+	SET_FIELD(qedi_ep->db_data.params, ISCSI_DB_DATA_AGG_VAL_SEL,
+		  DQ_XCM_ISCSI_SQ_PROD_CMD);
+	SET_FIELD(qedi_ep->db_data.params, ISCSI_DB_DATA_BYPASS_EN, 1);
+
+	/* Register doorbell with doorbell recovery mechanism */
+	rval = qedi_ops->common->db_recovery_add(qedi->cdev,
+						 qedi_ep->p_doorbell,
+						 &qedi_ep->db_data,
+						 DB_REC_WIDTH_32B,
+						 DB_REC_KERNEL);
+	if (rval) {
+		kfree(conn_info);
+		return rval;
+	}
+
 	rval = qedi_ops->offload_conn(qedi->cdev, qedi_ep->handle, conn_info);
-	if (rval)
+	if (rval) {
+		/* delete doorbell from doorbell recovery mechanism */
+		rval = qedi_ops->common->db_recovery_del(qedi->cdev,
+							 qedi_ep->p_doorbell,
+							 &qedi_ep->db_data);
+
 		QEDI_ERR(&qedi->dbg_ctx, "offload_conn returned %d, ep=%p\n",
 			 rval, qedi_ep);
+	}
 
 	kfree(conn_info);
 	return rval;
@@ -1109,6 +1136,11 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep)
 	    test_bit(QEDI_IN_RECOVERY, &qedi->flags))
 		goto ep_release_conn;
 
+	/* Delete doorbell from doorbell recovery mechanism */
+	ret = qedi_ops->common->db_recovery_del(qedi->cdev,
+					       qedi_ep->p_doorbell,
+					       &qedi_ep->db_data);
+
 	ret = qedi_ops->destroy_conn(qedi->cdev, qedi_ep->handle, abrt_conn);
 	if (ret) {
 		QEDI_WARN(&qedi->dbg_ctx,
diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h
index 758735209e15..a31c5de74754 100644
--- a/drivers/scsi/qedi/qedi_iscsi.h
+++ b/drivers/scsi/qedi/qedi_iscsi.h
@@ -80,6 +80,7 @@ struct qedi_endpoint {
 	u32 handle;
 	u32 fw_cid;
 	void __iomem *p_doorbell;
+	struct iscsi_db_data db_data;
 
 	/* Send queue management */
 	struct iscsi_wqe *sq;