16 files changed, 233 insertions, 95 deletions

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 93f222d66716..df43bfe6d573 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -421,6 +421,7 @@ struct lpfc_vport {
         uint32_t cfg_enable_da_id;
         uint32_t cfg_max_scsicmpl_time;
         uint32_t cfg_tgt_queue_depth;
+        uint32_t cfg_first_burst_size;
 
         uint32_t dev_loss_tmo_changed;
 
@@ -710,8 +711,6 @@ struct lpfc_hba {
         uint32_t cfg_use_msi;
         uint32_t cfg_fcp_imax;
         uint32_t cfg_fcp_cpu_map;
-        uint32_t cfg_fcp_wq_count;
-        uint32_t cfg_fcp_eq_count;
         uint32_t cfg_fcp_io_channel;
         uint32_t cfg_total_seg_cnt;
         uint32_t cfg_sg_seg_cnt;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index f4360c5ea6a9..16498e030c70 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -674,9 +674,6 @@ lpfc_do_offline(struct lpfc_hba *phba, uint32_t type)
         int i;
         int rc;
 
-        if (phba->pport->fc_flag & FC_OFFLINE_MODE)
-                return 0;
-
         init_completion(&online_compl);
         rc = lpfc_workq_post_event(phba, &status, &online_compl,
                               LPFC_EVT_OFFLINE_PREP);
@@ -744,14 +741,15 @@ lpfc_selective_reset(struct lpfc_hba *phba)
         int status = 0;
         int rc;
 
-        if ((!phba->cfg_enable_hba_reset) ||
-            (phba->pport->fc_flag & FC_OFFLINE_MODE))
+        if (!phba->cfg_enable_hba_reset)
                 return -EACCES;
 
-        status = lpfc_do_offline(phba, LPFC_EVT_OFFLINE);
+        if (!(phba->pport->fc_flag & FC_OFFLINE_MODE)) {
+                status = lpfc_do_offline(phba, LPFC_EVT_OFFLINE);
 
-        if (status != 0)
-                return status;
+                if (status != 0)
+                        return status;
+        }
 
         init_completion(&online_compl);
         rc = lpfc_workq_post_event(phba, &status, &online_compl,
@@ -2591,9 +2589,12 @@ LPFC_VPORT_ATTR_R(enable_da_id, 1, 0, 1,
 
 /*
 # lun_queue_depth:  This parameter is used to limit the number of outstanding
-# commands per FCP LUN. Value range is [1,128]. Default value is 30.
+# commands per FCP LUN. Value range is [1,512]. Default value is 30.
+# If this parameter value is greater than 1/8th the maximum number of exchanges
+# supported by the HBA port, then the lun queue depth will be reduced to
+# 1/8th the maximum number of exchanges.
 */
-LPFC_VPORT_ATTR_R(lun_queue_depth, 30, 1, 128,
+LPFC_VPORT_ATTR_R(lun_queue_depth, 30, 1, 512,
                   "Max number of FCP commands we can queue to a specific LUN");
 
 /*
@@ -2601,7 +2602,7 @@ LPFC_VPORT_ATTR_R(lun_queue_depth, 30, 1, 128,
 # commands per target port. Value range is [10,65535]. Default value is 65535.
 */
 LPFC_VPORT_ATTR_R(tgt_queue_depth, 65535, 10, 65535,
-        "Max number of FCP commands we can queue to a specific target port");
+                  "Max number of FCP commands we can queue to a specific target port");
 
 /*
 # hba_queue_depth:  This parameter is used to limit the number of outstanding
@@ -3949,6 +3950,14 @@ LPFC_VPORT_ATTR_RW(use_adisc, 0, 0, 1,
                    "Use ADISC on rediscovery to authenticate FCP devices");
 
 /*
+# lpfc_first_burst_size: First burst size to use on the NPorts
+# that support first burst.
+# Value range is [0,65536]. Default value is 0.
+*/
+LPFC_VPORT_ATTR_RW(first_burst_size, 0, 0, 65536,
+                   "First burst size for Targets that support first burst");
+
+/*
 # lpfc_max_scsicmpl_time: Use scsi command completion time to control I/O queue
 # depth. Default value is 0. When the value of this parameter is zero the
 # SCSI command completion time is not used for controlling I/O queue depth. When
@@ -4112,25 +4121,6 @@ LPFC_ATTR_R(use_msi, 2, 0, 2, "Use Message Signaled Interrupts (1) or "
             "MSI-X (2), if possible");
 
 /*
-# lpfc_fcp_wq_count: Set the number of fast-path FCP work queues
-# This parameter is ignored and will eventually be depricated
-#
-# Value range is [1,7]. Default value is 4.
-*/
-LPFC_ATTR_R(fcp_wq_count, LPFC_FCP_IO_CHAN_DEF, LPFC_FCP_IO_CHAN_MIN,
-            LPFC_FCP_IO_CHAN_MAX,
-            "Set the number of fast-path FCP work queues, if possible");
-
-/*
-# lpfc_fcp_eq_count: Set the number of FCP EQ/CQ/WQ IO channels
-#
-# Value range is [1,7]. Default value is 4.
-*/
-LPFC_ATTR_R(fcp_eq_count, LPFC_FCP_IO_CHAN_DEF, LPFC_FCP_IO_CHAN_MIN,
-            LPFC_FCP_IO_CHAN_MAX,
-            "Set the number of fast-path FCP event queues, if possible");
-
-/*
 # lpfc_fcp_io_channel: Set the number of FCP EQ/CQ/WQ IO channels
 #
 # Value range is [1,7]. Default value is 4.
@@ -4276,6 +4266,7 @@ struct device_attribute *lpfc_hba_attrs[] = {
         &dev_attr_lpfc_devloss_tmo,
         &dev_attr_lpfc_fcp_class,
         &dev_attr_lpfc_use_adisc,
+        &dev_attr_lpfc_first_burst_size,
         &dev_attr_lpfc_ack0,
         &dev_attr_lpfc_topology,
         &dev_attr_lpfc_scan_down,
@@ -4307,8 +4298,6 @@ struct device_attribute *lpfc_hba_attrs[] = {
         &dev_attr_lpfc_use_msi,
         &dev_attr_lpfc_fcp_imax,
         &dev_attr_lpfc_fcp_cpu_map,
-        &dev_attr_lpfc_fcp_wq_count,
-        &dev_attr_lpfc_fcp_eq_count,
         &dev_attr_lpfc_fcp_io_channel,
         &dev_attr_lpfc_enable_bg,
         &dev_attr_lpfc_soft_wwnn,
@@ -4352,6 +4341,7 @@ struct device_attribute *lpfc_vport_attrs[] = {
         &dev_attr_lpfc_restrict_login,
         &dev_attr_lpfc_fcp_class,
         &dev_attr_lpfc_use_adisc,
+        &dev_attr_lpfc_first_burst_size,
         &dev_attr_lpfc_fdmi_on,
         &dev_attr_lpfc_max_luns,
         &dev_attr_nport_evt_cnt,
@@ -5290,8 +5280,6 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
         lpfc_use_msi_init(phba, lpfc_use_msi);
         lpfc_fcp_imax_init(phba, lpfc_fcp_imax);
         lpfc_fcp_cpu_map_init(phba, lpfc_fcp_cpu_map);
-        lpfc_fcp_wq_count_init(phba, lpfc_fcp_wq_count);
-        lpfc_fcp_eq_count_init(phba, lpfc_fcp_eq_count);
         lpfc_fcp_io_channel_init(phba, lpfc_fcp_io_channel);
         lpfc_enable_hba_reset_init(phba, lpfc_enable_hba_reset);
         lpfc_enable_hba_heartbeat_init(phba, lpfc_enable_hba_heartbeat);
@@ -5331,6 +5319,7 @@ lpfc_get_vport_cfgparam(struct lpfc_vport *vport)
         lpfc_restrict_login_init(vport, lpfc_restrict_login);
         lpfc_fcp_class_init(vport, lpfc_fcp_class);
         lpfc_use_adisc_init(vport, lpfc_use_adisc);
+        lpfc_first_burst_size_init(vport, lpfc_first_burst_size);
         lpfc_max_scsicmpl_time_init(vport, lpfc_max_scsicmpl_time);
         lpfc_fdmi_on_init(vport, lpfc_fdmi_on);
         lpfc_discovery_threads_init(vport, lpfc_discovery_threads);
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index fcbedd6053c4..79c13c3263f1 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -2498,7 +2498,7 @@ static int lpfcdiag_loop_get_xri(struct lpfc_hba *phba, uint16_t rpi,
         struct lpfc_sli_ct_request *ctreq = NULL;
         int ret_val = 0;
         int time_left;
-        int iocb_stat = 0;
+        int iocb_stat = IOCB_SUCCESS;
         unsigned long flags;
 
         *txxri = 0;
@@ -2574,6 +2574,7 @@ static int lpfcdiag_loop_get_xri(struct lpfc_hba *phba, uint16_t rpi,
 
         cmdiocbq->iocb_flag |= LPFC_IO_LIBDFC;
         cmdiocbq->vport = phba->pport;
+        cmdiocbq->iocb_cmpl = NULL;
 
         iocb_stat = lpfc_sli_issue_iocb_wait(phba, LPFC_ELS_RING, cmdiocbq,
                                 rspiocbq,
@@ -2963,7 +2964,7 @@ lpfc_bsg_diag_loopback_run(struct fc_bsg_job *job)
         uint8_t *ptr = NULL, *rx_databuf = NULL;
         int rc = 0;
         int time_left;
-        int iocb_stat;
+        int iocb_stat = IOCB_SUCCESS;
         unsigned long flags;
         void *dataout = NULL;
         uint32_t total_mem;
@@ -3149,6 +3150,7 @@ lpfc_bsg_diag_loopback_run(struct fc_bsg_job *job)
         }
         cmdiocbq->iocb_flag |= LPFC_IO_LIBDFC;
         cmdiocbq->vport = phba->pport;
+        cmdiocbq->iocb_cmpl = NULL;
         iocb_stat = lpfc_sli_issue_iocb_wait(phba, LPFC_ELS_RING, cmdiocbq,
                                              rspiocbq, (phba->fc_ratov * 2) +
                                              LPFC_DRVR_TIMEOUT);
@@ -3209,7 +3211,7 @@ err_loopback_test_exit:
         lpfc_bsg_event_unref(evt); /* delete */
         spin_unlock_irqrestore(&phba->ct_ev_lock, flags);
 
-        if (cmdiocbq != NULL)
+        if ((cmdiocbq != NULL) && (iocb_stat != IOCB_TIMEDOUT))
                 lpfc_sli_release_iocbq(phba, cmdiocbq);
 
         if (rspiocbq != NULL)
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 68391177432b..02e8cd923d0a 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -895,7 +895,7 @@ lpfc_cmpl_ct(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
         if (irsp->ulpStatus) {
                 lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY,
-                                 "0268 NS cmd %x Error (%d %d)\n",
+                                 "0268 NS cmd x%x Error (x%x x%x)\n",
                                  cmdcode, irsp->ulpStatus, irsp->un.ulpWord[4]);
 
                 if ((irsp->ulpStatus == IOSTAT_LOCAL_REJECT) &&
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index af49fb03dbb8..e409ba5f728c 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2008 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -154,6 +154,7 @@ struct lpfc_node_rrq {
 #define NLP_NODEV_REMOVE   0x08000000   /* Defer removal till discovery ends */
 #define NLP_TARGET_REMOVE  0x10000000   /* Target remove in process */
 #define NLP_SC_REQ         0x20000000   /* Target requires authentication */
+#define NLP_FIRSTBURST     0x40000000   /* Target supports FirstBurst */
 #define NLP_RPI_REGISTERED 0x80000000   /* nlp_rpi is valid */
 
 /* ndlp usage management macros */
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 6b8ee7449f16..110445f0c58d 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -2122,6 +2122,8 @@ lpfc_issue_els_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
         }
         npr->estabImagePair = 1;
         npr->readXferRdyDis = 1;
+         if (vport->cfg_first_burst_size)
+                npr->writeXferRdyDis = 1;
 
         /* For FCP support */
         npr->prliType = PRLI_FCP_TYPE;
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 4ec3d7c044c2..086c3f28caa6 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -234,6 +234,9 @@ struct ulp_bde64 {
         uint32_t addrHigh;
 };
 
+/* Maximun size of immediate data that can fit into a 128 byte WQE */
+#define LPFC_MAX_BDE_IMM_SIZE   64
+
 struct lpfc_sli4_flags {
         uint32_t word0;
 #define lpfc_idx_rsrc_rdy_SHIFT         0
@@ -2585,6 +2588,9 @@ struct lpfc_sli4_parameters {
 #define cfg_mqv_WORD                            word6
         uint32_t word7;
         uint32_t word8;
+#define cfg_wqsize_SHIFT                        8
+#define cfg_wqsize_MASK                         0x0000000f
+#define cfg_wqsize_WORD                         word8
 #define cfg_wqv_SHIFT                           14
 #define cfg_wqv_MASK                            0x00000003
 #define cfg_wqv_WORD                            word8
@@ -3622,6 +3628,13 @@ union lpfc_wqe {
         struct gen_req64_wqe gen_req;
 };
 
+union lpfc_wqe128 {
+        uint32_t words[32];
+        struct lpfc_wqe_generic generic;
+        struct xmit_seq64_wqe xmit_sequence;
+        struct gen_req64_wqe gen_req;
+};
+
 #define LPFC_GROUP_OJECT_MAGIC_NUM              0xfeaa0001
 #define LPFC_FILE_TYPE_GROUP                    0xf7
 #define LPFC_FILE_ID_GROUP                      0xa2
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index e0b20fad8502..501147c4a147 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -472,10 +472,22 @@ lpfc_config_port_post(struct lpfc_hba *phba)
         lpfc_sli_read_link_ste(phba);
 
         /* Reset the DFT_HBA_Q_DEPTH to the max xri  */
-        if (phba->cfg_hba_queue_depth > (mb->un.varRdConfig.max_xri+1))
-                phba->cfg_hba_queue_depth =
-                        (mb->un.varRdConfig.max_xri + 1) -
-                                        lpfc_sli4_get_els_iocb_cnt(phba);
+        i = (mb->un.varRdConfig.max_xri + 1);
+        if (phba->cfg_hba_queue_depth > i) {
+                lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+                                "3359 HBA queue depth changed from %d to %d\n",
+                                phba->cfg_hba_queue_depth, i);
+                phba->cfg_hba_queue_depth = i;
+        }
+
+        /* Reset the DFT_LUN_Q_DEPTH to (max xri >> 3)  */
+        i = (mb->un.varRdConfig.max_xri >> 3);
+        if (phba->pport->cfg_lun_queue_depth > i) {
+                lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+                                "3360 LUN queue depth changed from %d to %d\n",
+                                phba->pport->cfg_lun_queue_depth, i);
+                phba->pport->cfg_lun_queue_depth = i;
+        }
 
         phba->lmt = mb->un.varRdConfig.lmt;
 
@@ -4901,9 +4913,6 @@ lpfc_sli4_driver_resource_setup(struct lpfc_hba *phba)
         lpfc_get_cfgparam(phba);
         phba->max_vpi = LPFC_MAX_VPI;
 
-        /* Eventually cfg_fcp_eq_count / cfg_fcp_wq_count will be depricated */
-        phba->cfg_fcp_io_channel = phba->cfg_fcp_eq_count;
-
         /* This will be set to correct value after the read_config mbox */
         phba->max_vports = 0;
 
@@ -6664,12 +6673,14 @@ lpfc_sli4_read_config(struct lpfc_hba *phba)
                 goto read_cfg_out;
 
         /* Reset the DFT_HBA_Q_DEPTH to the max xri  */
-        if (phba->cfg_hba_queue_depth >
-                (phba->sli4_hba.max_cfg_param.max_xri -
-                        lpfc_sli4_get_els_iocb_cnt(phba)))
-                phba->cfg_hba_queue_depth =
-                        phba->sli4_hba.max_cfg_param.max_xri -
-                                lpfc_sli4_get_els_iocb_cnt(phba);
+        length = phba->sli4_hba.max_cfg_param.max_xri -
+                        lpfc_sli4_get_els_iocb_cnt(phba);
+        if (phba->cfg_hba_queue_depth > length) {
+                lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+                                "3361 HBA queue depth changed from %d to %d\n",
+                                phba->cfg_hba_queue_depth, length);
+                phba->cfg_hba_queue_depth = length;
+        }
 
         if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
             LPFC_SLI_INTF_IF_TYPE_2)
@@ -6859,11 +6870,7 @@ lpfc_sli4_queue_verify(struct lpfc_hba *phba)
                 cfg_fcp_io_channel = phba->sli4_hba.max_cfg_param.max_eq;
         }
 
-        /* Eventually cfg_fcp_eq_count / cfg_fcp_wq_count will be depricated */
-
         /* The actual number of FCP event queues adopted */
-        phba->cfg_fcp_eq_count = cfg_fcp_io_channel;
-        phba->cfg_fcp_wq_count = cfg_fcp_io_channel;
         phba->cfg_fcp_io_channel = cfg_fcp_io_channel;
 
         /* Get EQ depth from module parameter, fake the default for now */
@@ -9154,6 +9161,7 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
         sli4_params->mqv = bf_get(cfg_mqv, mbx_sli4_parameters);
         sli4_params->wqv = bf_get(cfg_wqv, mbx_sli4_parameters);
         sli4_params->rqv = bf_get(cfg_rqv, mbx_sli4_parameters);
+        sli4_params->wqsize = bf_get(cfg_wqsize, mbx_sli4_parameters);
         sli4_params->sgl_pages_max = bf_get(cfg_sgl_page_cnt,
                                             mbx_sli4_parameters);
         sli4_params->sgl_pp_align = bf_get(cfg_sgl_pp_align,
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index b1c510f6b8f0..1f292e29d566 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -178,7 +178,8 @@ lpfc_dump_wakeup_param(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
         mb->mbxOwner = OWN_HOST;
         mb->un.varDmp.cv = 1;
         mb->un.varDmp.type = DMP_NV_PARAMS;
-        mb->un.varDmp.entry_index = 0;
+        if (phba->sli_rev < LPFC_SLI_REV4)
+                mb->un.varDmp.entry_index = 0;
         mb->un.varDmp.region_id = WAKE_UP_PARMS_REGION_ID;
         mb->un.varDmp.word_cnt = WAKE_UP_PARMS_WORD_SIZE;
         mb->un.varDmp.co = 0;
@@ -361,7 +362,7 @@ lpfc_config_link(struct lpfc_hba * phba, LPFC_MBOXQ_t * pmb)
         /* NEW_FEATURE
          * SLI-2, Coalescing Response Feature.
          */
-        if (phba->cfg_cr_delay) {
+        if (phba->cfg_cr_delay && (phba->sli_rev < LPFC_SLI_REV4)) {
                 mb->un.varCfgLnk.cr = 1;
                 mb->un.varCfgLnk.ci = 1;
                 mb->un.varCfgLnk.cr_delay = phba->cfg_cr_delay;
@@ -377,7 +378,7 @@ lpfc_config_link(struct lpfc_hba * phba, LPFC_MBOXQ_t * pmb)
         mb->un.varCfgLnk.crtov = phba->fc_crtov;
         mb->un.varCfgLnk.citov = phba->fc_citov;
 
-        if (phba->cfg_ack0)
+        if (phba->cfg_ack0 && (phba->sli_rev < LPFC_SLI_REV4))
                 mb->un.varCfgLnk.ack0_enable = 1;
 
         mb->mbxCommand = MBX_CONFIG_LINK;
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 6aaf39a1f1c5..abc361259d6d 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -690,11 +690,15 @@ lpfc_rcv_prli(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 
         ndlp->nlp_type &= ~(NLP_FCP_TARGET | NLP_FCP_INITIATOR);
         ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
+        ndlp->nlp_flag &= ~NLP_FIRSTBURST;
         if (npr->prliType == PRLI_FCP_TYPE) {
                 if (npr->initiatorFunc)
                         ndlp->nlp_type |= NLP_FCP_INITIATOR;
-                if (npr->targetFunc)
+                if (npr->targetFunc) {
                         ndlp->nlp_type |= NLP_FCP_TARGET;
+                        if (npr->writeXferRdyDis)
+                                ndlp->nlp_flag |= NLP_FIRSTBURST;
+                }
                 if (npr->Retry)
                         ndlp->nlp_fcp_info |= NLP_FCP_2_DEVICE;
         }
@@ -1676,12 +1680,16 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
         /* Check out PRLI rsp */
         ndlp->nlp_type &= ~(NLP_FCP_TARGET | NLP_FCP_INITIATOR);
         ndlp->nlp_fcp_info &= ~NLP_FCP_2_DEVICE;
+        ndlp->nlp_flag &= ~NLP_FIRSTBURST;
         if ((npr->acceptRspCode == PRLI_REQ_EXECUTED) &&
             (npr->prliType == PRLI_FCP_TYPE)) {
                 if (npr->initiatorFunc)
                         ndlp->nlp_type |= NLP_FCP_INITIATOR;
-                if (npr->targetFunc)
+                if (npr->targetFunc) {
                         ndlp->nlp_type |= NLP_FCP_TARGET;
+                        if (npr->writeXferRdyDis)
+                                ndlp->nlp_flag |= NLP_FIRSTBURST;
+                }
                 if (npr->Retry)
                         ndlp->nlp_fcp_info |= NLP_FCP_2_DEVICE;
         }
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 243de1d324b7..1242b6c4308b 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -4386,11 +4386,11 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
         if (scsi_sg_count(scsi_cmnd)) {
                 if (datadir == DMA_TO_DEVICE) {
                         iocb_cmd->ulpCommand = CMD_FCP_IWRITE64_CR;
-                        if (sli4)
-                                iocb_cmd->ulpPU = PARM_READ_CHECK;
-                        else {
-                                iocb_cmd->un.fcpi.fcpi_parm = 0;
-                                iocb_cmd->ulpPU = 0;
+                        iocb_cmd->ulpPU = PARM_READ_CHECK;
+                        if (vport->cfg_first_burst_size &&
+                            (pnode->nlp_flag & NLP_FIRSTBURST)) {
+                                piocbq->iocb.un.fcpi.fcpi_XRdy =
+                                        vport->cfg_first_burst_size;
                         }
                         fcp_cmnd->fcpCntl3 = WRITE_DATA;
                         phba->fc4OutputRequests++;
@@ -5022,6 +5022,7 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct lpfc_rport_data *rdata,
                 lpfc_release_scsi_buf(phba, lpfc_cmd);
                 return FAILED;
         }
+        iocbq->iocb_cmpl = lpfc_tskmgmt_def_cmpl;
 
         lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP,
                          "0702 Issue %s to TGT %d LUN %d "
@@ -5034,7 +5035,6 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct lpfc_rport_data *rdata,
                                           iocbq, iocbqrsp, lpfc_cmd->timeout);
         if (status != IOCB_SUCCESS) {
                 if (status == IOCB_TIMEDOUT) {
-                        iocbq->iocb_cmpl = lpfc_tskmgmt_def_cmpl;
                         ret = TIMEOUT_ERROR;
                 } else
                         ret = FAILED;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 43440ca16f46..0392e114531c 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -6163,6 +6163,7 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
                 kfree(vpd);
                 goto out_free_mbox;
         }
+
         mqe = &mboxq->u.mqe;
         phba->sli_rev = bf_get(lpfc_mbx_rd_rev_sli_lvl, &mqe->un.read_rev);
         if (bf_get(lpfc_mbx_rd_rev_fcoe, &mqe->un.read_rev))
@@ -6249,6 +6250,16 @@ lpfc_sli4_hba_setup(struct lpfc_hba *phba)
                         phba->vpd.rev.fcphHigh, phba->vpd.rev.fcphLow,
                         phba->vpd.rev.feaLevelHigh, phba->vpd.rev.feaLevelLow);
 
+        /* Reset the DFT_LUN_Q_DEPTH to (max xri >> 3)  */
+        rc = (phba->sli4_hba.max_cfg_param.max_xri >> 3);
+        if (phba->pport->cfg_lun_queue_depth > rc) {
+                lpfc_printf_log(phba, KERN_WARNING, LOG_INIT,
+                                "3362 LUN queue depth changed from %d to %d\n",
+                                phba->pport->cfg_lun_queue_depth, rc);
+                phba->pport->cfg_lun_queue_depth = rc;
+        }
+
+
         /*
          * Discover the port's supported feature set and match it against the
          * hosts requests.
@@ -9889,6 +9900,24 @@ lpfc_sli_wake_iocb_wait(struct lpfc_hba *phba,
         struct lpfc_scsi_buf *lpfc_cmd;
 
         spin_lock_irqsave(&phba->hbalock, iflags);
+        if (cmdiocbq->iocb_flag & LPFC_IO_WAKE_TMO) {
+
+                /*
+                 * A time out has occurred for the iocb.  If a time out
+                 * completion handler has been supplied, call it.  Otherwise,
+                 * just free the iocbq.
+                 */
+
+                spin_unlock_irqrestore(&phba->hbalock, iflags);
+                cmdiocbq->iocb_cmpl = cmdiocbq->wait_iocb_cmpl;
+                cmdiocbq->wait_iocb_cmpl = NULL;
+                if (cmdiocbq->iocb_cmpl)
+                        (cmdiocbq->iocb_cmpl)(phba, cmdiocbq, NULL);
+                else
+                        lpfc_sli_release_iocbq(phba, cmdiocbq);
+                return;
+        }
+
         cmdiocbq->iocb_flag |= LPFC_IO_WAKE;
         if (cmdiocbq->context2 && rspiocbq)
                 memcpy(&((struct lpfc_iocbq *)cmdiocbq->context2)->iocb,
@@ -9944,10 +9973,16 @@ lpfc_chk_iocb_flg(struct lpfc_hba *phba,
  * @timeout: Timeout in number of seconds.
  *
  * This function issues the iocb to firmware and waits for the
- * iocb to complete. If the iocb command is not
- * completed within timeout seconds, it returns IOCB_TIMEDOUT.
- * Caller should not free the iocb resources if this function
- * returns IOCB_TIMEDOUT.
+ * iocb to complete. The iocb_cmpl field of the shall be used
+ * to handle iocbs which time out. If the field is NULL, the
+ * function shall free the iocbq structure.  If more clean up is
+ * needed, the caller is expected to provide a completion function
+ * that will provide the needed clean up.  If the iocb command is
+ * not completed within timeout seconds, the function will either
+ * free the iocbq structure (if iocb_cmpl == NULL) or execute the
+ * completion function set in the iocb_cmpl field and then return
+ * a status of IOCB_TIMEDOUT.  The caller should not free the iocb
+ * resources if this function returns IOCB_TIMEDOUT.
  * The function waits for the iocb completion using an
  * non-interruptible wait.
  * This function will sleep while waiting for iocb completion.
@@ -9980,6 +10015,9 @@ lpfc_sli_issue_iocb_wait(struct lpfc_hba *phba,
         int txq_cnt = 0;
         int txcmplq_cnt = 0;
         struct lpfc_sli_ring *pring = &phba->sli.ring[LPFC_ELS_RING];
+        unsigned long iflags;
+        bool iocb_completed = true;
+
         /*
          * If the caller has provided a response iocbq buffer, then context2
          * is NULL or its an error.
@@ -9990,9 +10028,10 @@ lpfc_sli_issue_iocb_wait(struct lpfc_hba *phba,
                 piocb->context2 = prspiocbq;
         }
 
+        piocb->wait_iocb_cmpl = piocb->iocb_cmpl;
         piocb->iocb_cmpl = lpfc_sli_wake_iocb_wait;
         piocb->context_un.wait_queue = &done_q;
-        piocb->iocb_flag &= ~LPFC_IO_WAKE;
+        piocb->iocb_flag &= ~(LPFC_IO_WAKE | LPFC_IO_WAKE_TMO);
 
         if (phba->cfg_poll & DISABLE_FCP_RING_INT) {
                 if (lpfc_readl(phba->HCregaddr, &creg_val))
@@ -10009,8 +10048,19 @@ lpfc_sli_issue_iocb_wait(struct lpfc_hba *phba,
                 timeleft = wait_event_timeout(done_q,
                                 lpfc_chk_iocb_flg(phba, piocb, LPFC_IO_WAKE),
                                 timeout_req);
+                spin_lock_irqsave(&phba->hbalock, iflags);
+                if (!(piocb->iocb_flag & LPFC_IO_WAKE)) {
 
-                if (piocb->iocb_flag & LPFC_IO_WAKE) {
+                        /*
+                         * IOCB timed out.  Inform the wake iocb wait
+                         * completion function and set local status
+                         */
+
+                        iocb_completed = false;
+                        piocb->iocb_flag |= LPFC_IO_WAKE_TMO;
+                }
+                spin_unlock_irqrestore(&phba->hbalock, iflags);
+                if (iocb_completed) {
                         lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
                                         "0331 IOCB wake signaled\n");
                 } else if (timeleft == 0) {
@@ -10122,7 +10172,6 @@ lpfc_sli_issue_mbox_wait(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmboxq,
                  */
                 if (pmboxq->mbox_flag & LPFC_MBX_WAKE) {
                         retval = MBX_SUCCESS;
-                        lpfc_sli4_swap_str(phba, pmboxq);
                 } else {
                         retval = MBX_TIMEOUT;
                         pmboxq->mbox_cmpl = lpfc_sli_def_mbox_cmpl;
@@ -12820,10 +12869,44 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
                     wq->page_count);
         bf_set(lpfc_mbx_wq_create_cq_id, &wq_create->u.request,
                     cq->queue_id);
+
+        /* wqv is the earliest version supported, NOT the latest */
         bf_set(lpfc_mbox_hdr_version, &shdr->request,
                phba->sli4_hba.pc_sli4_params.wqv);
 
-        if (phba->sli4_hba.pc_sli4_params.wqv == LPFC_Q_CREATE_VERSION_1) {
+        switch (phba->sli4_hba.pc_sli4_params.wqv) {
+        case LPFC_Q_CREATE_VERSION_0:
+                switch (wq->entry_size) {
+                default:
+                case 64:
+                        /* Nothing to do, version 0 ONLY supports 64 byte */
+                        page = wq_create->u.request.page;
+                        break;
+                case 128:
+                        if (!(phba->sli4_hba.pc_sli4_params.wqsize &
+                            LPFC_WQ_SZ128_SUPPORT)) {
+                                status = -ERANGE;
+                                goto out;
+                        }
+                        /* If we get here the HBA MUST also support V1 and
+                         * we MUST use it
+                         */
+                        bf_set(lpfc_mbox_hdr_version, &shdr->request,
+                               LPFC_Q_CREATE_VERSION_1);
+
+                        bf_set(lpfc_mbx_wq_create_wqe_count,
+                               &wq_create->u.request_1, wq->entry_count);
+                        bf_set(lpfc_mbx_wq_create_wqe_size,
+                               &wq_create->u.request_1,
+                               LPFC_WQ_WQE_SIZE_128);
+                        bf_set(lpfc_mbx_wq_create_page_size,
+                               &wq_create->u.request_1,
+                               (PAGE_SIZE/SLI4_PAGE_SIZE));
+                        page = wq_create->u.request_1.page;
+                        break;
+                }
+                break;
+        case LPFC_Q_CREATE_VERSION_1:
                 bf_set(lpfc_mbx_wq_create_wqe_count, &wq_create->u.request_1,
                        wq->entry_count);
                 switch (wq->entry_size) {
@@ -12834,6 +12917,11 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
                                LPFC_WQ_WQE_SIZE_64);
                         break;
                 case 128:
+                        if (!(phba->sli4_hba.pc_sli4_params.wqsize &
+                                LPFC_WQ_SZ128_SUPPORT)) {
+                                status = -ERANGE;
+                                goto out;
+                        }
                         bf_set(lpfc_mbx_wq_create_wqe_size,
                                &wq_create->u.request_1,
                                LPFC_WQ_WQE_SIZE_128);
@@ -12842,9 +12930,12 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq,
                 bf_set(lpfc_mbx_wq_create_page_size, &wq_create->u.request_1,
                        (PAGE_SIZE/SLI4_PAGE_SIZE));
                 page = wq_create->u.request_1.page;
-        } else {
-                page = wq_create->u.request.page;
+                break;
+        default:
+                status = -ERANGE;
+                goto out;
         }
+
         list_for_each_entry(dmabuf, &wq->page_list, list) {
                 memset(dmabuf->virt, 0, hw_page_size);
                 page[dmabuf->buffer_tag].addr_lo = putPaddrLow(dmabuf->phys);
@@ -14665,14 +14756,20 @@ lpfc_prep_seq(struct lpfc_vport *vport, struct hbq_dmabuf *seq_dmabuf)
                 first_iocbq->iocb.unsli3.rcvsli3.vpi =
                         vport->phba->vpi_ids[vport->vpi];
                 /* put the first buffer into the first IOCBq */
+                tot_len = bf_get(lpfc_rcqe_length,
+                                       &seq_dmabuf->cq_event.cqe.rcqe_cmpl);
+
                 first_iocbq->context2 = &seq_dmabuf->dbuf;
                 first_iocbq->context3 = NULL;
                 first_iocbq->iocb.ulpBdeCount = 1;
-                first_iocbq->iocb.un.cont64[0].tus.f.bdeSize =
+                if (tot_len > LPFC_DATA_BUF_SIZE)
+                        first_iocbq->iocb.un.cont64[0].tus.f.bdeSize =
                                                         LPFC_DATA_BUF_SIZE;
+                else
+                        first_iocbq->iocb.un.cont64[0].tus.f.bdeSize = tot_len;
+
                 first_iocbq->iocb.un.rcvels.remoteID = sid;
-                tot_len = bf_get(lpfc_rcqe_length,
-                                       &seq_dmabuf->cq_event.cqe.rcqe_cmpl);
+
                 first_iocbq->iocb.unsli3.rcvsli3.acc_len = tot_len;
         }
         iocbq = first_iocbq;
@@ -14688,14 +14785,17 @@ lpfc_prep_seq(struct lpfc_vport *vport, struct hbq_dmabuf *seq_dmabuf)
                 if (!iocbq->context3) {
                         iocbq->context3 = d_buf;
                         iocbq->iocb.ulpBdeCount++;
-                        pbde = (struct ulp_bde64 *)
-                                        &iocbq->iocb.unsli3.sli3Words[4];
-                        pbde->tus.f.bdeSize = LPFC_DATA_BUF_SIZE;
-
                         /* We need to get the size out of the right CQE */
                         hbq_buf = container_of(d_buf, struct hbq_dmabuf, dbuf);
                         len = bf_get(lpfc_rcqe_length,
                                        &hbq_buf->cq_event.cqe.rcqe_cmpl);
+                        pbde = (struct ulp_bde64 *)
+                                        &iocbq->iocb.unsli3.sli3Words[4];
+                        if (len > LPFC_DATA_BUF_SIZE)
+                                pbde->tus.f.bdeSize = LPFC_DATA_BUF_SIZE;
+                        else
+                                pbde->tus.f.bdeSize = len;
+
                         iocbq->iocb.unsli3.rcvsli3.acc_len += len;
                         tot_len += len;
                 } else {
@@ -14710,16 +14810,19 @@ lpfc_prep_seq(struct lpfc_vport *vport, struct hbq_dmabuf *seq_dmabuf)
                                 lpfc_in_buf_free(vport->phba, d_buf);
                                 continue;
                         }
+                        /* We need to get the size out of the right CQE */
+                        hbq_buf = container_of(d_buf, struct hbq_dmabuf, dbuf);
+                        len = bf_get(lpfc_rcqe_length,
+                                       &hbq_buf->cq_event.cqe.rcqe_cmpl);
                         iocbq->context2 = d_buf;
                         iocbq->context3 = NULL;
                         iocbq->iocb.ulpBdeCount = 1;
-                        iocbq->iocb.un.cont64[0].tus.f.bdeSize =
+                        if (len > LPFC_DATA_BUF_SIZE)
+                                iocbq->iocb.un.cont64[0].tus.f.bdeSize =
                                                         LPFC_DATA_BUF_SIZE;
+                        else
+                                iocbq->iocb.un.cont64[0].tus.f.bdeSize = len;
 
-                        /* We need to get the size out of the right CQE */
-                        hbq_buf = container_of(d_buf, struct hbq_dmabuf, dbuf);
-                        len = bf_get(lpfc_rcqe_length,
-                                       &hbq_buf->cq_event.cqe.rcqe_cmpl);
                         tot_len += len;
                         iocbq->iocb.unsli3.rcvsli3.acc_len = tot_len;
 
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 9d2e0c6fe334..97617996206d 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2007 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -60,7 +60,8 @@ struct lpfc_iocbq {
         uint8_t retry;          /* retry counter for IOCB cmd - if needed */
         uint16_t iocb_flag;
 #define LPFC_IO_LIBDFC          1       /* libdfc iocb */
-#define LPFC_IO_WAKE            2       /* High Priority Queue signal flag */
+#define LPFC_IO_WAKE            2       /* Synchronous I/O completed */
+#define LPFC_IO_WAKE_TMO        LPFC_IO_WAKE /* Synchronous I/O timed out */
 #define LPFC_IO_FCP             4       /* FCP command -- iocbq in scsi_buf */
 #define LPFC_DRIVER_ABORTED     8       /* driver aborted this request */
 #define LPFC_IO_FABRIC          0x10    /* Iocb send using fabric scheduler */
@@ -93,6 +94,8 @@ struct lpfc_iocbq {
 
         void (*fabric_iocb_cmpl) (struct lpfc_hba *, struct lpfc_iocbq *,
                            struct lpfc_iocbq *);
+        void (*wait_iocb_cmpl) (struct lpfc_hba *, struct lpfc_iocbq *,
+                           struct lpfc_iocbq *);
         void (*iocb_cmpl) (struct lpfc_hba *, struct lpfc_iocbq *,
                            struct lpfc_iocbq *);
 };
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index d710b87a4417..5bcc38223ac9 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -117,6 +117,7 @@ union sli4_qe {
         struct lpfc_rcqe_complete *rcqe_complete;
         struct lpfc_mqe *mqe;
         union  lpfc_wqe *wqe;
+        union  lpfc_wqe128 *wqe128;
         struct lpfc_rqe *rqe;
 };
 
@@ -325,12 +326,14 @@ struct lpfc_bmbx {
 #define LPFC_EQE_SIZE_16B       16
 #define LPFC_CQE_SIZE           16
 #define LPFC_WQE_SIZE           64
+#define LPFC_WQE128_SIZE        128
 #define LPFC_MQE_SIZE           256
 #define LPFC_RQE_SIZE           8
 
 #define LPFC_EQE_DEF_COUNT      1024
 #define LPFC_CQE_DEF_COUNT      1024
 #define LPFC_WQE_DEF_COUNT      256
+#define LPFC_WQE128_DEF_COUNT   128
 #define LPFC_MQE_DEF_COUNT      16
 #define LPFC_RQE_DEF_COUNT      512
 
@@ -416,6 +419,9 @@ struct lpfc_pc_sli4_params {
         uint8_t mqv;
         uint8_t wqv;
         uint8_t rqv;
+        uint8_t wqsize;
+#define LPFC_WQ_SZ64_SUPPORT    1
+#define LPFC_WQ_SZ128_SUPPORT   2
 };
 
 struct lpfc_iov {
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index c6c32eebf3dd..21859d2006ce 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -18,7 +18,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "8.3.40"
+#define LPFC_DRIVER_VERSION "8.3.41"
 #define LPFC_DRIVER_NAME                "lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index e28e431564b0..a87ee33f4f2a 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2008 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -387,6 +387,9 @@ lpfc_vport_create(struct fc_vport *fc_vport, bool disable)
         /* Create binary sysfs attribute for vport */
         lpfc_alloc_sysfs_attr(vport);
 
+        /* Set the DFT_LUN_Q_DEPTH accordingly */
+        vport->cfg_lun_queue_depth  = phba->pport->cfg_lun_queue_depth;
+
         *(struct lpfc_vport **)fc_vport->dd_data = vport;
         vport->fc_vport = fc_vport;