Merge tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

Pull SCSI fixes from James Bottomley:
 "This is quite a big update because it includes a rework of the lpfc
  driver to separate the NVMe part from the FC part.

  The reason for doing this is because two separate trees (the nvme and
  scsi trees respectively) want to update the individual components and
  this separation will prevent a really nasty cross tree entanglement by
  the time we reach the next merge window.

  The rest of the fixes are the usual minor sort with no significant
  security implications"

* tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (25 commits)
  scsi: zero per-cmd private driver data for each MQ I/O
  scsi: csiostor: fix use after free in csio_hw_use_fwconfig()
  scsi: ufs: Clean up some rpm/spm level SysFS nodes upon remove
  scsi: lpfc: fix build issue if NVME_FC_TARGET is not defined
  scsi: lpfc: Fix NULL pointer dereference during PCI error recovery
  scsi: lpfc: update version to 11.2.0.14
  scsi: lpfc: Add MDS Diagnostic support.
  scsi: lpfc: Fix NVMEI's handling of NVMET's PRLI response attributes
  scsi: lpfc: Cleanup entry_repost settings on SLI4 queues
  scsi: lpfc: Fix debugfs root inode "lpfc" not getting deleted on driver unload.
  scsi: lpfc: Fix NVME I+T not registering NVME as a supported FC4 type
  scsi: lpfc: Added recovery logic for running out of NVMET IO context resources
  scsi: lpfc: Separate NVMET RQ buffer posting from IO resources SGL/iocbq/context
  scsi: lpfc: Separate NVMET data buffer pool fir ELS/CT.
  scsi: lpfc: Fix NMI watchdog assertions when running nvmet IOPS tests
  scsi: lpfc: Fix NVMEI driver not decrementing counter causing bad rport state.
  scsi: lpfc: Fix nvmet RQ resource needs for large block writes.
  scsi: lpfc: Adding additional stats counters for nvme.
  scsi: lpfc: Fix system crash when port is reset.
  scsi: lpfc: Fix used-RPI accounting problem.
  ...

23 files changed, 902 insertions, 434 deletions

diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c
index 622bdabc8894..dab195f04da7 100644
--- a/drivers/scsi/csiostor/csio_hw.c
+++ b/drivers/scsi/csiostor/csio_hw.c
@@ -1769,7 +1769,6 @@ csio_hw_use_fwconfig(struct csio_hw *hw, int reset, u32 *fw_cfg_param)
 		goto bye;
 	}
 
-	mempool_free(mbp, hw->mb_mempool);
 	if (finicsum != cfcsum) {
 		csio_warn(hw,
 		      "Config File checksum mismatch: csum=%#x, computed=%#x\n",
@@ -1780,6 +1779,10 @@ csio_hw_use_fwconfig(struct csio_hw *hw, int reset, u32 *fw_cfg_param)
 	rv = csio_hw_validate_caps(hw, mbp);
 	if (rv != 0)
 		goto bye;
+
+	mempool_free(mbp, hw->mb_mempool);
+	mbp = NULL;
+
 	/*
 	 * Note that we're operating with parameters
 	 * not supplied by the driver, rather than from hard-wired
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index b44c3136eb51..520325867e2b 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -1422,7 +1422,7 @@ static void fc_rport_recv_rtv_req(struct fc_rport_priv *rdata,
 	fp = fc_frame_alloc(lport, sizeof(*rtv));
 	if (!fp) {
 		rjt_data.reason = ELS_RJT_UNAB;
-		rjt_data.reason = ELS_EXPL_INSUF_RES;
+		rjt_data.explan = ELS_EXPL_INSUF_RES;
 		fc_seq_els_rsp_send(in_fp, ELS_LS_RJT, &rjt_data);
 		goto drop;
 	}
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 6d7840b096e6..f2c0ba6ced78 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -141,6 +141,13 @@ struct lpfc_dmabuf {
 	uint32_t   buffer_tag;	/* used for tagged queue ring */
 };
 
+struct lpfc_nvmet_ctxbuf {
+	struct list_head list;
+	struct lpfc_nvmet_rcv_ctx *context;
+	struct lpfc_iocbq *iocbq;
+	struct lpfc_sglq *sglq;
+};
+
 struct lpfc_dma_pool {
 	struct lpfc_dmabuf   *elements;
 	uint32_t    max_count;
@@ -163,9 +170,7 @@ struct rqb_dmabuf {
 	struct lpfc_dmabuf dbuf;
 	uint16_t total_size;
 	uint16_t bytes_recv;
-	void *context;
-	struct lpfc_iocbq *iocbq;
-	struct lpfc_sglq *sglq;
+	uint16_t idx;
 	struct lpfc_queue *hrq;	  /* ptr to associated Header RQ */
 	struct lpfc_queue *drq;	  /* ptr to associated Data RQ */
 };
@@ -670,6 +675,8 @@ struct lpfc_hba {
 					/* INIT_LINK mailbox command */
 #define LS_NPIV_FAB_SUPPORTED 0x2	/* Fabric supports NPIV */
 #define LS_IGNORE_ERATT       0x4	/* intr handler should ignore ERATT */
+#define LS_MDS_LINK_DOWN      0x8	/* MDS Diagnostics Link Down */
+#define LS_MDS_LOOPBACK      0x16	/* MDS Diagnostics Link Up (Loopback) */
 
 	uint32_t hba_flag;	/* hba generic flags */
 #define HBA_ERATT_HANDLED	0x1 /* This flag is set when eratt handled */
@@ -777,7 +784,6 @@ struct lpfc_hba {
 	uint32_t cfg_nvme_oas;
 	uint32_t cfg_nvme_io_channel;
 	uint32_t cfg_nvmet_mrq;
-	uint32_t cfg_nvmet_mrq_post;
 	uint32_t cfg_enable_nvmet;
 	uint32_t cfg_nvme_enable_fb;
 	uint32_t cfg_nvmet_fb_size;
@@ -943,6 +949,7 @@ struct lpfc_hba {
 	struct pci_pool *lpfc_mbuf_pool;
 	struct pci_pool *lpfc_hrb_pool;	/* header receive buffer pool */
 	struct pci_pool *lpfc_drb_pool; /* data receive buffer pool */
+	struct pci_pool *lpfc_nvmet_drb_pool; /* data receive buffer pool */
 	struct pci_pool *lpfc_hbq_pool;	/* SLI3 hbq buffer pool */
 	struct pci_pool *txrdy_payload_pool;
 	struct lpfc_dma_pool lpfc_mbuf_safety_pool;
@@ -1228,7 +1235,11 @@ lpfc_sli_read_hs(struct lpfc_hba *phba)
 static inline struct lpfc_sli_ring *
 lpfc_phba_elsring(struct lpfc_hba *phba)
 {
-	if (phba->sli_rev == LPFC_SLI_REV4)
-		return phba->sli4_hba.els_wq->pring;
+	if (phba->sli_rev == LPFC_SLI_REV4) {
+		if (phba->sli4_hba.els_wq)
+			return phba->sli4_hba.els_wq->pring;
+		else
+			return NULL;
+	}
 	return &phba->sli.sli3_ring[LPFC_ELS_RING];
 }
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 4830370bfab1..bb2d9e238225 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -60,9 +60,9 @@
 #define LPFC_MIN_DEVLOSS_TMO	1
 #define LPFC_MAX_DEVLOSS_TMO	255
 
-#define LPFC_DEF_MRQ_POST	256
-#define LPFC_MIN_MRQ_POST	32
-#define LPFC_MAX_MRQ_POST	512
+#define LPFC_DEF_MRQ_POST	512
+#define LPFC_MIN_MRQ_POST	512
+#define LPFC_MAX_MRQ_POST	2048
 
 /*
  * Write key size should be multiple of 4. If write key is changed
@@ -205,8 +205,9 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 				atomic_read(&tgtp->xmt_ls_rsp_error));
 
 		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP: Rcv %08x Drop %08x\n",
+				"FCP: Rcv %08x Release %08x Drop %08x\n",
 				atomic_read(&tgtp->rcv_fcp_cmd_in),
+				atomic_read(&tgtp->xmt_fcp_release),
 				atomic_read(&tgtp->rcv_fcp_cmd_drop));
 
 		if (atomic_read(&tgtp->rcv_fcp_cmd_in) !=
@@ -218,15 +219,12 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		}
 
 		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x\n",
+				"FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x "
+				"drop %08x\n",
 				atomic_read(&tgtp->xmt_fcp_read),
 				atomic_read(&tgtp->xmt_fcp_read_rsp),
 				atomic_read(&tgtp->xmt_fcp_write),
-				atomic_read(&tgtp->xmt_fcp_rsp));
-
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP Rsp: abort %08x drop %08x\n",
-				atomic_read(&tgtp->xmt_fcp_abort),
+				atomic_read(&tgtp->xmt_fcp_rsp),
 				atomic_read(&tgtp->xmt_fcp_drop));
 
 		len += snprintf(buf+len, PAGE_SIZE-len,
@@ -236,10 +234,22 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 				atomic_read(&tgtp->xmt_fcp_rsp_drop));
 
 		len += snprintf(buf+len, PAGE_SIZE-len,
-				"ABORT: Xmt %08x Err %08x Cmpl %08x",
+				"ABORT: Xmt %08x Cmpl %08x\n",
+				atomic_read(&tgtp->xmt_fcp_abort),
+				atomic_read(&tgtp->xmt_fcp_abort_cmpl));
+
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"ABORT: Sol %08x  Usol %08x Err %08x Cmpl %08x",
+				atomic_read(&tgtp->xmt_abort_sol),
+				atomic_read(&tgtp->xmt_abort_unsol),
 				atomic_read(&tgtp->xmt_abort_rsp),
-				atomic_read(&tgtp->xmt_abort_rsp_error),
-				atomic_read(&tgtp->xmt_abort_cmpl));
+				atomic_read(&tgtp->xmt_abort_rsp_error));
+
+		len += snprintf(buf + len, PAGE_SIZE - len,
+				"IO_CTX: %08x outstanding %08x total %x",
+				phba->sli4_hba.nvmet_ctx_cnt,
+				phba->sli4_hba.nvmet_io_wait_cnt,
+				phba->sli4_hba.nvmet_io_wait_total);
 
 		len +=  snprintf(buf+len, PAGE_SIZE-len, "\n");
 		return len;
@@ -3312,14 +3322,6 @@ LPFC_ATTR_R(nvmet_mrq,
 	    "Specify number of RQ pairs for processing NVMET cmds");
 
 /*
- * lpfc_nvmet_mrq_post: Specify number buffers to post on every MRQ
- *
- */
-LPFC_ATTR_R(nvmet_mrq_post, LPFC_DEF_MRQ_POST,
-	    LPFC_MIN_MRQ_POST, LPFC_MAX_MRQ_POST,
-	    "Specify number of buffers to post on every MRQ");
-
-/*
  * lpfc_enable_fc4_type: Defines what FC4 types are supported.
  * Supported Values:  1 - register just FCP
  *                    3 - register both FCP and NVME
@@ -5154,7 +5156,6 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_suppress_rsp,
 	&dev_attr_lpfc_nvme_io_channel,
 	&dev_attr_lpfc_nvmet_mrq,
-	&dev_attr_lpfc_nvmet_mrq_post,
 	&dev_attr_lpfc_nvme_enable_fb,
 	&dev_attr_lpfc_nvmet_fb_size,
 	&dev_attr_lpfc_enable_bg,
@@ -6194,7 +6195,6 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 
 	lpfc_enable_fc4_type_init(phba, lpfc_enable_fc4_type);
 	lpfc_nvmet_mrq_init(phba, lpfc_nvmet_mrq);
-	lpfc_nvmet_mrq_post_init(phba, lpfc_nvmet_mrq_post);
 
 	/* Initialize first burst. Target vs Initiator are different. */
 	lpfc_nvme_enable_fb_init(phba, lpfc_nvme_enable_fb);
@@ -6291,7 +6291,6 @@ lpfc_nvme_mod_param_dep(struct lpfc_hba *phba)
 		/* Not NVME Target mode.  Turn off Target parameters. */
 		phba->nvmet_support = 0;
 		phba->cfg_nvmet_mrq = 0;
-		phba->cfg_nvmet_mrq_post = 0;
 		phba->cfg_nvmet_fb_size = 0;
 	}
 
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 1c55408ac718..8912767e7bc8 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -75,6 +75,10 @@ void lpfc_init_vpi_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_cancel_all_vport_retry_delay_timer(struct lpfc_hba *);
 void lpfc_retry_pport_discovery(struct lpfc_hba *);
 void lpfc_release_rpi(struct lpfc_hba *, struct lpfc_vport *, uint16_t);
+int lpfc_init_iocb_list(struct lpfc_hba *phba, int cnt);
+void lpfc_free_iocb_list(struct lpfc_hba *phba);
+int lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hrq,
+			struct lpfc_queue *drq, int count, int idx);
 
 void lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *, LPFC_MBOXQ_t *);
 void lpfc_mbx_cmpl_reg_login(struct lpfc_hba *, LPFC_MBOXQ_t *);
@@ -246,16 +250,14 @@ struct hbq_dmabuf *lpfc_sli4_rb_alloc(struct lpfc_hba *);
 void lpfc_sli4_rb_free(struct lpfc_hba *, struct hbq_dmabuf *);
 struct rqb_dmabuf *lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba);
 void lpfc_sli4_nvmet_free(struct lpfc_hba *phba, struct rqb_dmabuf *dmab);
-void lpfc_nvmet_rq_post(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp,
-			struct lpfc_dmabuf *mp);
+void lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba,
+			    struct lpfc_nvmet_ctxbuf *ctxp);
 int lpfc_nvmet_rcv_unsol_abort(struct lpfc_vport *vport,
 			       struct fc_frame_header *fc_hdr);
 void lpfc_sli4_build_dflt_fcf_record(struct lpfc_hba *, struct fcf_record *,
 			uint16_t);
 int lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq,
 		     struct lpfc_rqe *hrqe, struct lpfc_rqe *drqe);
-int lpfc_post_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hq,
-			struct lpfc_queue *dq, int count);
 int lpfc_free_rq_buffer(struct lpfc_hba *phba, struct lpfc_queue *hq);
 void lpfc_unregister_fcf(struct lpfc_hba *);
 void lpfc_unregister_fcf_rescan(struct lpfc_hba *);
@@ -271,6 +273,7 @@ int lpfc_sli4_fcf_rr_next_proc(struct lpfc_vport *, uint16_t);
 void lpfc_sli4_clear_fcf_rr_bmask(struct lpfc_hba *);
 
 int lpfc_mem_alloc(struct lpfc_hba *, int align);
+int lpfc_nvmet_mem_alloc(struct lpfc_hba *phba);
 int lpfc_mem_alloc_active_rrq_pool_s4(struct lpfc_hba *);
 void lpfc_mem_free(struct lpfc_hba *);
 void lpfc_mem_free_all(struct lpfc_hba *);
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index c7962dae4dab..f2cd19c6c2df 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -2092,6 +2092,7 @@ lpfc_fdmi_port_attr_fc4type(struct lpfc_vport *vport,
 
 	ae->un.AttrTypes[3] = 0x02; /* Type 1 - ELS */
 	ae->un.AttrTypes[2] = 0x01; /* Type 8 - FCP */
+	ae->un.AttrTypes[6] = 0x01; /* Type 40 - NVME */
 	ae->un.AttrTypes[7] = 0x01; /* Type 32 - CT */
 	size = FOURBYTES + 32;
 	ad->AttrLen = cpu_to_be16(size);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index fce549a91911..4bcb92c844ca 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -798,21 +798,22 @@ lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size)
 				atomic_read(&tgtp->xmt_fcp_rsp));
 
 		len += snprintf(buf + len, size - len,
-				"FCP Rsp: abort %08x drop %08x\n",
-				atomic_read(&tgtp->xmt_fcp_abort),
-				atomic_read(&tgtp->xmt_fcp_drop));
-
-		len += snprintf(buf + len, size - len,
 				"FCP Rsp Cmpl: %08x err %08x drop %08x\n",
 				atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
 				atomic_read(&tgtp->xmt_fcp_rsp_error),
 				atomic_read(&tgtp->xmt_fcp_rsp_drop));
 
 		len += snprintf(buf + len, size - len,
-				"ABORT: Xmt %08x Err %08x Cmpl %08x",
+				"ABORT: Xmt %08x Cmpl %08x\n",
+				atomic_read(&tgtp->xmt_fcp_abort),
+				atomic_read(&tgtp->xmt_fcp_abort_cmpl));
+
+		len += snprintf(buf + len, size - len,
+				"ABORT: Sol %08x  Usol %08x Err %08x Cmpl %08x",
+				atomic_read(&tgtp->xmt_abort_sol),
+				atomic_read(&tgtp->xmt_abort_unsol),
 				atomic_read(&tgtp->xmt_abort_rsp),
-				atomic_read(&tgtp->xmt_abort_rsp_error),
-				atomic_read(&tgtp->xmt_abort_cmpl));
+				atomic_read(&tgtp->xmt_abort_rsp_error));
 
 		len +=  snprintf(buf + len, size - len, "\n");
 
@@ -841,6 +842,12 @@ lpfc_debugfs_nvmestat_data(struct lpfc_vport *vport, char *buf, int size)
 			}
 			spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		}
+
+		len += snprintf(buf + len, size - len,
+				"IO_CTX: %08x  outstanding %08x total %08x\n",
+				phba->sli4_hba.nvmet_ctx_cnt,
+				phba->sli4_hba.nvmet_io_wait_cnt,
+				phba->sli4_hba.nvmet_io_wait_total);
 	} else {
 		if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
 			return len;
@@ -1959,6 +1966,7 @@ lpfc_debugfs_nvmestat_write(struct file *file, const char __user *buf,
 		atomic_set(&tgtp->rcv_ls_req_out, 0);
 		atomic_set(&tgtp->rcv_ls_req_drop, 0);
 		atomic_set(&tgtp->xmt_ls_abort, 0);
+		atomic_set(&tgtp->xmt_ls_abort_cmpl, 0);
 		atomic_set(&tgtp->xmt_ls_rsp, 0);
 		atomic_set(&tgtp->xmt_ls_drop, 0);
 		atomic_set(&tgtp->xmt_ls_rsp_error, 0);
@@ -1967,19 +1975,22 @@ lpfc_debugfs_nvmestat_write(struct file *file, const char __user *buf,
 		atomic_set(&tgtp->rcv_fcp_cmd_in, 0);
 		atomic_set(&tgtp->rcv_fcp_cmd_out, 0);
 		atomic_set(&tgtp->rcv_fcp_cmd_drop, 0);
-		atomic_set(&tgtp->xmt_fcp_abort, 0);
 		atomic_set(&tgtp->xmt_fcp_drop, 0);
 		atomic_set(&tgtp->xmt_fcp_read_rsp, 0);
 		atomic_set(&tgtp->xmt_fcp_read, 0);
 		atomic_set(&tgtp->xmt_fcp_write, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp, 0);
+		atomic_set(&tgtp->xmt_fcp_release, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp_cmpl, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp_error, 0);
 		atomic_set(&tgtp->xmt_fcp_rsp_drop, 0);
 
+		atomic_set(&tgtp->xmt_fcp_abort, 0);
+		atomic_set(&tgtp->xmt_fcp_abort_cmpl, 0);
+		atomic_set(&tgtp->xmt_abort_sol, 0);
+		atomic_set(&tgtp->xmt_abort_unsol, 0);
 		atomic_set(&tgtp->xmt_abort_rsp, 0);
 		atomic_set(&tgtp->xmt_abort_rsp_error, 0);
-		atomic_set(&tgtp->xmt_abort_cmpl, 0);
 	}
 	return nbytes;
 }
@@ -3070,11 +3081,11 @@ __lpfc_idiag_print_wq(struct lpfc_queue *qp, char *wqtype,
 			qp->assoc_qid, qp->q_cnt_1,
 			(unsigned long long)qp->q_cnt_4);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
-			"\t\tWQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]",
+			"\t\tWQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
 			qp->queue_id, qp->entry_count,
 			qp->entry_size, qp->host_index,
-			qp->hba_index);
+			qp->hba_index, qp->entry_repost);
 	len +=  snprintf(pbuffer + len,
 			LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
 	return len;
@@ -3121,11 +3132,11 @@ __lpfc_idiag_print_cq(struct lpfc_queue *qp, char *cqtype,
 			qp->assoc_qid, qp->q_cnt_1, qp->q_cnt_2,
 			qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
-			"\tCQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]",
+			"\tCQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
 			qp->queue_id, qp->entry_count,
 			qp->entry_size, qp->host_index,
-			qp->hba_index);
+			qp->hba_index, qp->entry_repost);
 
 	len +=  snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
 
@@ -3143,20 +3154,20 @@ __lpfc_idiag_print_rqpair(struct lpfc_queue *qp, struct lpfc_queue *datqp,
 			"\t\t%s RQ info: ", rqtype);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
 			"AssocCQID[%02d]: RQ-STAT[nopost:x%x nobuf:x%x "
-			"trunc:x%x rcv:x%llx]\n",
+			"posted:x%x rcv:x%llx]\n",
 			qp->assoc_qid, qp->q_cnt_1, qp->q_cnt_2,
 			qp->q_cnt_3, (unsigned long long)qp->q_cnt_4);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
-			"\t\tHQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]\n",
+			"\t\tHQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]\n",
 			qp->queue_id, qp->entry_count, qp->entry_size,
-			qp->host_index, qp->hba_index);
+			qp->host_index, qp->hba_index, qp->entry_repost);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
-			"\t\tDQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]\n",
+			"\t\tDQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]\n",
 			datqp->queue_id, datqp->entry_count,
 			datqp->entry_size, datqp->host_index,
-			datqp->hba_index);
+			datqp->hba_index, datqp->entry_repost);
 	return len;
 }
 
@@ -3242,10 +3253,10 @@ __lpfc_idiag_print_eq(struct lpfc_queue *qp, char *eqtype,
 			eqtype, qp->q_cnt_1, qp->q_cnt_2, qp->q_cnt_3,
 			(unsigned long long)qp->q_cnt_4);
 	len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len,
-			"EQID[%02d], QE-CNT[%04d], QE-SIZE[%04d], "
-			"HOST-IDX[%04d], PORT-IDX[%04d]",
+			"EQID[%02d], QE-CNT[%04d], QE-SZ[%04d], "
+			"HST-IDX[%04d], PRT-IDX[%04d], PST[%03d]",
 			qp->queue_id, qp->entry_count, qp->entry_size,
-			qp->host_index, qp->hba_index);
+			qp->host_index, qp->hba_index, qp->entry_repost);
 	len +=  snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
 
 	return len;
@@ -5855,8 +5866,10 @@ lpfc_debugfs_terminate(struct lpfc_vport *vport)
 			atomic_dec(&lpfc_debugfs_hba_count);
 		}
 
-		debugfs_remove(lpfc_debugfs_root); /* lpfc */
-		lpfc_debugfs_root = NULL;
+		if (atomic_read(&lpfc_debugfs_hba_count) == 0) {
+			debugfs_remove(lpfc_debugfs_root); /* lpfc */
+			lpfc_debugfs_root = NULL;
+		}
 	}
 #endif
 	return;
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index 9d5a379f4b15..094c97b9e5f7 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -90,6 +90,7 @@ struct lpfc_nodelist {
 #define NLP_FCP_INITIATOR  0x10			/* entry is an FCP Initiator */
 #define NLP_NVME_TARGET    0x20			/* entry is a NVME Target */
 #define NLP_NVME_INITIATOR 0x40			/* entry is a NVME Initiator */
+#define NLP_NVME_DISCOVERY 0x80                 /* entry has NVME disc srvc */
 
 	uint16_t	nlp_fc4_type;		/* FC types node supports. */
 						/* Assigned from GID_FF, only
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 67827e397431..8e532b39ae93 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1047,6 +1047,13 @@ stop_rr_fcf_flogi:
 				 irsp->ulpStatus, irsp->un.ulpWord[4],
 				 irsp->ulpTimeout);
 
+
+		/* If this is not a loop open failure, bail out */
+		if (!(irsp->ulpStatus == IOSTAT_LOCAL_REJECT &&
+		      ((irsp->un.ulpWord[4] & IOERR_PARAM_MASK) ==
+					IOERR_LOOP_OPEN_FAILURE)))
+			goto flogifail;
+
 		/* FLOGI failed, so there is no fabric */
 		spin_lock_irq(shost->host_lock);
 		vport->fc_flag &= ~(FC_FABRIC | FC_PUBLIC_LOOP);
@@ -2077,16 +2084,19 @@ lpfc_cmpl_els_prli(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 	if (irsp->ulpStatus) {
 		/* Check for retry */
+		ndlp->fc4_prli_sent--;
 		if (lpfc_els_retry(phba, cmdiocb, rspiocb)) {
 			/* ELS command is being retried */
-			ndlp->fc4_prli_sent--;
 			goto out;
 		}
+
 		/* PRLI failed */
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_ELS,
-				 "2754 PRLI failure DID:%06X Status:x%x/x%x\n",
+				 "2754 PRLI failure DID:%06X Status:x%x/x%x, "
+				 "data: x%x\n",
 				 ndlp->nlp_DID, irsp->ulpStatus,
-				 irsp->un.ulpWord[4]);
+				 irsp->un.ulpWord[4], ndlp->fc4_prli_sent);
+
 		/* Do not call DSM for lpfc_els_abort'ed ELS cmds */
 		if (lpfc_error_lost_link(irsp))
 			goto out;
@@ -7441,6 +7451,13 @@ lpfc_els_flush_cmd(struct lpfc_vport *vport)
 	 */
 	spin_lock_irq(&phba->hbalock);
 	pring = lpfc_phba_elsring(phba);
+
+	/* Bail out if we've no ELS wq, like in PCI error recovery case. */
+	if (unlikely(!pring)) {
+		spin_unlock_irq(&phba->hbalock);
+		return;
+	}
+
 	if (phba->sli_rev == LPFC_SLI_REV4)
 		spin_lock(&pring->ring_lock);
 
@@ -8667,7 +8684,8 @@ lpfc_cmpl_els_fdisc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 		lpfc_do_scr_ns_plogi(phba, vport);
 	goto out;
 fdisc_failed:
-	if (vport->fc_vport->vport_state != FC_VPORT_NO_FABRIC_RSCS)
+	if (vport->fc_vport &&
+	    (vport->fc_vport->vport_state != FC_VPORT_NO_FABRIC_RSCS))
 		lpfc_vport_set_state(vport, FC_VPORT_FAILED);
 	/* Cancel discovery timer */
 	lpfc_can_disctmo(vport);
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 0482c5580331..3ffcd9215ca8 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -693,15 +693,16 @@ lpfc_work_done(struct lpfc_hba *phba)
 	pring = lpfc_phba_elsring(phba);
 	status = (ha_copy & (HA_RXMASK  << (4*LPFC_ELS_RING)));
 	status >>= (4*LPFC_ELS_RING);
-	if ((status & HA_RXMASK) ||
-	    (pring->flag & LPFC_DEFERRED_RING_EVENT) ||
-	    (phba->hba_flag & HBA_SP_QUEUE_EVT)) {
+	if (pring && (status & HA_RXMASK ||
+		      pring->flag & LPFC_DEFERRED_RING_EVENT ||
+		      phba->hba_flag & HBA_SP_QUEUE_EVT)) {
 		if (pring->flag & LPFC_STOP_IOCB_EVENT) {
 			pring->flag |= LPFC_DEFERRED_RING_EVENT;
 			/* Set the lpfc data pending flag */
 			set_bit(LPFC_DATA_READY, &phba->data_flags);
 		} else {
-			if (phba->link_state >= LPFC_LINK_UP) {
+			if (phba->link_state >= LPFC_LINK_UP ||
+			    phba->link_flag & LS_MDS_LOOPBACK) {
 				pring->flag &= ~LPFC_DEFERRED_RING_EVENT;
 				lpfc_sli_handle_slow_ring_event(phba, pring,
 								(status &
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 1d12f2be36bc..e0a5fce416ae 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1356,6 +1356,7 @@ struct lpfc_mbx_wq_destroy {
 
 #define LPFC_HDR_BUF_SIZE 128
 #define LPFC_DATA_BUF_SIZE 2048
+#define LPFC_NVMET_DATA_BUF_SIZE 128
 struct rq_context {
 	uint32_t word0;
 #define lpfc_rq_context_rqe_count_SHIFT	16	/* Version 0 Only */
@@ -4420,6 +4421,19 @@ struct fcp_treceive64_wqe {
 };
 #define TXRDY_PAYLOAD_LEN      12
 
+#define CMD_SEND_FRAME	0xE1
+
+struct send_frame_wqe {
+	struct ulp_bde64 bde;          /* words 0-2 */
+	uint32_t frame_len;            /* word 3 */
+	uint32_t fc_hdr_wd0;           /* word 4 */
+	uint32_t fc_hdr_wd1;           /* word 5 */
+	struct wqe_common wqe_com;     /* words 6-11 */
+	uint32_t fc_hdr_wd2;           /* word 12 */
+	uint32_t fc_hdr_wd3;           /* word 13 */
+	uint32_t fc_hdr_wd4;           /* word 14 */
+	uint32_t fc_hdr_wd5;           /* word 15 */
+};
 
 union lpfc_wqe {
 	uint32_t words[16];
@@ -4438,7 +4452,7 @@ union lpfc_wqe {
 	struct fcp_trsp64_wqe fcp_trsp;
 	struct fcp_tsend64_wqe fcp_tsend;
 	struct fcp_treceive64_wqe fcp_treceive;
-
+	struct send_frame_wqe send_frame;
 };
 
 union lpfc_wqe128 {
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 4b1eb98c228d..9add9473cae5 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -1099,7 +1099,7 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 
 		list_for_each_entry_safe(ctxp, ctxp_next, &nvmet_aborts, list) {
 			ctxp->flag &= ~(LPFC_NVMET_XBUSY | LPFC_NVMET_ABORT_OP);
-			lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+			lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
 		}
 	}
 
@@ -3381,7 +3381,7 @@ lpfc_sli4_nvmet_sgl_update(struct lpfc_hba *phba)
 {
 	struct lpfc_sglq *sglq_entry = NULL, *sglq_entry_next = NULL;
 	uint16_t i, lxri, xri_cnt, els_xri_cnt;
-	uint16_t nvmet_xri_cnt, tot_cnt;
+	uint16_t nvmet_xri_cnt;
 	LIST_HEAD(nvmet_sgl_list);
 	int rc;
 
@@ -3389,15 +3389,9 @@ lpfc_sli4_nvmet_sgl_update(struct lpfc_hba *phba)
 	 * update on pci function's nvmet xri-sgl list
 	 */
 	els_xri_cnt = lpfc_sli4_get_els_iocb_cnt(phba);
-	nvmet_xri_cnt = phba->cfg_nvmet_mrq * phba->cfg_nvmet_mrq_post;
-	tot_cnt = phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
-	if (nvmet_xri_cnt > tot_cnt) {
-		phba->cfg_nvmet_mrq_post = tot_cnt / phba->cfg_nvmet_mrq;
-		nvmet_xri_cnt = phba->cfg_nvmet_mrq * phba->cfg_nvmet_mrq_post;
-		lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
-				"6301 NVMET post-sgl count changed to %d\n",
-				phba->cfg_nvmet_mrq_post);
-	}
+
+	/* For NVMET, ALL remaining XRIs are dedicated for IO processing */
+	nvmet_xri_cnt = phba->sli4_hba.max_cfg_param.max_xri - els_xri_cnt;
 
 	if (nvmet_xri_cnt > phba->sli4_hba.nvmet_xri_cnt) {
 		/* els xri-sgl expanded */
@@ -4546,6 +4540,19 @@ lpfc_sli4_async_fc_evt(struct lpfc_hba *phba, struct lpfc_acqe_fc_la *acqe_fc)
 	pmb->vport = phba->pport;
 
 	if (phba->sli4_hba.link_state.status != LPFC_FC_LA_TYPE_LINK_UP) {
+		phba->link_flag &= ~(LS_MDS_LINK_DOWN | LS_MDS_LOOPBACK);
+
+		switch (phba->sli4_hba.link_state.status) {
+		case LPFC_FC_LA_TYPE_MDS_LINK_DOWN:
+			phba->link_flag |= LS_MDS_LINK_DOWN;
+			break;
+		case LPFC_FC_LA_TYPE_MDS_LOOPBACK:
+			phba->link_flag |= LS_MDS_LOOPBACK;
+			break;
+		default:
+			break;
+		}
+
 		/* Parse and translate status field */
 		mb = &pmb->u.mb;
 		mb->mbxStatus = lpfc_sli4_parse_latt_fault(phba,
@@ -5830,6 +5837,9 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		spin_lock_init(&phba->sli4_hba.abts_nvme_buf_list_lock);
 		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
 		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
+		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_ctx_list);
+		INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_io_wait_list);
+
 		/* Fast-path XRI aborted CQ Event work queue list */
 		INIT_LIST_HEAD(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue);
 	}
@@ -5837,6 +5847,7 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 	/* This abort list used by worker thread */
 	spin_lock_init(&phba->sli4_hba.sgl_list_lock);
 	spin_lock_init(&phba->sli4_hba.nvmet_io_lock);
+	spin_lock_init(&phba->sli4_hba.nvmet_io_wait_lock);
 
 	/*
 	 * Initialize driver internal slow-path work queues
@@ -5951,16 +5962,21 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
 		for (i = 0; i < lpfc_enable_nvmet_cnt; i++) {
 			if (wwn == lpfc_enable_nvmet[i]) {
 #if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
+				if (lpfc_nvmet_mem_alloc(phba))
+					break;
+
+				phba->nvmet_support = 1; /* a match */
+
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 						"6017 NVME Target %016llx\n",
 						wwn);
-				phba->nvmet_support = 1; /* a match */
 #else
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 						"6021 Can't enable NVME Target."
 						" NVME_TARGET_FC infrastructure"
 						" is not in kernel\n");
 #endif
+				break;
 			}
 		}
 	}
@@ -6269,7 +6285,7 @@ lpfc_unset_driver_resource_phase2(struct lpfc_hba *phba)
  *
  * This routine is invoked to free the driver's IOCB list and memory.
  **/
-static void
+void
 lpfc_free_iocb_list(struct lpfc_hba *phba)
 {
 	struct lpfc_iocbq *iocbq_entry = NULL, *iocbq_next = NULL;
@@ -6297,7 +6313,7 @@ lpfc_free_iocb_list(struct lpfc_hba *phba)
  *	0 - successful
  *	other values - error
  **/
-static int
+int
 lpfc_init_iocb_list(struct lpfc_hba *phba, int iocb_count)
 {
 	struct lpfc_iocbq *iocbq_entry = NULL;
@@ -6525,7 +6541,6 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 	uint16_t rpi_limit, curr_rpi_range;
 	struct lpfc_dmabuf *dmabuf;
 	struct lpfc_rpi_hdr *rpi_hdr;
-	uint32_t rpi_count;
 
 	/*
 	 * If the SLI4 port supports extents, posting the rpi header isn't
@@ -6538,8 +6553,7 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 		return NULL;
 
 	/* The limit on the logical index is just the max_rpi count. */
-	rpi_limit = phba->sli4_hba.max_cfg_param.rpi_base +
-	phba->sli4_hba.max_cfg_param.max_rpi - 1;
+	rpi_limit = phba->sli4_hba.max_cfg_param.max_rpi;
 
 	spin_lock_irq(&phba->hbalock);
 	/*
@@ -6550,18 +6564,10 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 	curr_rpi_range = phba->sli4_hba.next_rpi;
 	spin_unlock_irq(&phba->hbalock);
 
-	/*
-	 * The port has a limited number of rpis. The increment here
-	 * is LPFC_RPI_HDR_COUNT - 1 to account for the starting value
-	 * and to allow the full max_rpi range per port.
-	 */
-	if ((curr_rpi_range + (LPFC_RPI_HDR_COUNT - 1)) > rpi_limit)
-		rpi_count = rpi_limit - curr_rpi_range;
-	else
-		rpi_count = LPFC_RPI_HDR_COUNT;
-
-	if (!rpi_count)
+	/* Reached full RPI range */
+	if (curr_rpi_range == rpi_limit)
 		return NULL;
+
 	/*
 	 * First allocate the protocol header region for the port.  The
 	 * port expects a 4KB DMA-mapped memory region that is 4K aligned.
@@ -6595,13 +6601,9 @@ lpfc_sli4_create_rpi_hdr(struct lpfc_hba *phba)
 
 	/* The rpi_hdr stores the logical index only. */
 	rpi_hdr->start_rpi = curr_rpi_range;
+	rpi_hdr->next_rpi = phba->sli4_hba.next_rpi + LPFC_RPI_HDR_COUNT;
 	list_add_tail(&rpi_hdr->list, &phba->sli4_hba.lpfc_rpi_hdr_list);
 
-	/*
-	 * The next_rpi stores the next logical module-64 rpi value used
-	 * to post physical rpis in subsequent rpi postings.
-	 */
-	phba->s