scsi: lpfc: Fix nvmet async receive buffer replenishment

Under circustances with high load, the driver is running out of async
receive buffers which may result in one of the following messages:

0:6401 RQE Error x13, posted 226 err_cnt 0: 925c6050 925c604e 925c5d54

or

0:2885 Port Status Event: port status reg 0x81800000,
       port smphr reg 0xc000, error 1=0x52004a01, error 2=0x0

The driver is waiting for full io completion before returning receive
buffers to the adapter. There is no need for such a relationship.

Whenever a new command is received from the wire, the driver will have two
contexts - an io context (ctxp) and a receive buffer context.  In current
code, the receive buffer context stays 1:1 with the io and won't be
reposted to the hardware until the io completes. There is no need for such
a relationship.

Change the driver so that up on successful handing of the command to the
transport, where the transport has copied what it needed thus the buffer is
returned to the driver, have the driver immediately repost the buffer to
the hardware. If the command cannot be successfully handed to the transport
as transport resources are temporarily busy, have the driver allocate a new
and separate receive buffer and post it to the hardware so that hardware
can continue while the command is queued for the transport.

When an io is complete, the transport returns the io context to the driver,
and the driver may be waiting for more contexts, thus immediately reuse the
io context. In this path, there was a buffer posted when the receive buffer
was queued waiting for an io context so a replacement is not needed in the
new code additions. Thus, exempt this the context reuse case from the
buffer reposting.
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/lpfc/lpfc_nvmet.c

@@ -1843,7 +1843,7 @@ lpfc_nvmet_process_rcv_fcp_req(struct lpfc_nvmet_ctxbuf *ctx_buf)
 	struct lpfc_hba *phba = ctxp->phba;
 	struct rqb_dmabuf *nvmebuf = ctxp->rqb_buffer;
 	struct lpfc_nvmet_tgtport *tgtp;
-	uint32_t *payload;
+	uint32_t *payload, qno;
 	uint32_t rc;
 	unsigned long iflags;
 
@@ -1876,6 +1876,15 @@ lpfc_nvmet_process_rcv_fcp_req(struct lpfc_nvmet_ctxbuf *ctx_buf)
 	/* Process FCP command */
 	if (rc == 0) {
 		atomic_inc(&tgtp->rcv_fcp_cmd_out);
+		spin_lock_irqsave(&ctxp->ctxlock, iflags);
+		if ((ctxp->flag & LPFC_NVMET_CTX_REUSE_WQ) ||
+		    (nvmebuf != ctxp->rqb_buffer)) {
+			spin_unlock_irqrestore(&ctxp->ctxlock, iflags);
+			return;
+		}
+		ctxp->rqb_buffer = NULL;
+		spin_unlock_irqrestore(&ctxp->ctxlock, iflags);
+		lpfc_rq_buf_free(phba, &nvmebuf->hbuf); /* repost */
 		return;
 	}
 
@@ -1886,6 +1895,20 @@ lpfc_nvmet_process_rcv_fcp_req(struct lpfc_nvmet_ctxbuf *ctx_buf)
 				 ctxp->oxid, ctxp->size, ctxp->sid);
 		atomic_inc(&tgtp->rcv_fcp_cmd_out);
 		atomic_inc(&tgtp->defer_fod);
+		spin_lock_irqsave(&ctxp->ctxlock, iflags);
+		if (ctxp->flag & LPFC_NVMET_CTX_REUSE_WQ) {
+			spin_unlock_irqrestore(&ctxp->ctxlock, iflags);
+			return;
+		}
+		spin_unlock_irqrestore(&ctxp->ctxlock, iflags);
+		/*
+		 * Post a replacement DMA buffer to RQ and defer
+		 * freeing rcv buffer till .defer_rcv callback
+		 */
+		qno = nvmebuf->idx;
+		lpfc_post_rq_buffer(
+			phba, phba->sli4_hba.nvmet_mrq_hdr[qno],
+			phba->sli4_hba.nvmet_mrq_data[qno], 1, qno);
 		return;
 	}
 	atomic_inc(&tgtp->rcv_fcp_cmd_drop);