scsi: lpfc: NVME Initiator: Base modifications

NVME Initiator: Base modifications

This patch adds base modifications for NVME initiator support.

The base modifications consist of:
- Formal split of SLI3 rings from SLI-4 WQs (sometimes referred to as
  rings as well) as implementation now widely varies between the two.
- Addition of configuration modes:
   SCSI initiator only; NVME initiator only; NVME target only; and
   SCSI and NVME initiator.
   The configuration mode drives overall adapter configuration,
   offloads enabled, and resource splits.
   NVME support is only available on SLI-4 devices and newer fw.
- Implements the following based on configuration mode:
  - Exchange resources are split by protocol; Obviously, if only
     1 mode, then no split occurs. Default is 50/50. module attribute
     allows tuning.
  - Pools and config parameters are separated per-protocol
  - Each protocol has it's own set of queues, but share interrupt
    vectors.
     SCSI:
       SLI3 devices have few queues and the original style of queue
         allocation remains.
       SLI4 devices piggy back on an "io-channel" concept that
         eventually needs to merge with scsi-mq/blk-mq support (it is
	 underway).  For now, the paradigm continues as it existed
	 prior. io channel allocates N msix and N WQs (N=4 default)
	 and either round robins or uses cpu # modulo N for scheduling.
	 A bunch of module parameters allow the configuration to be
	 tuned.
     NVME (initiator):
       Allocates an msix per cpu (or whatever pci_alloc_irq_vectors
         gets)
       Allocates a WQ per cpu, and maps the WQs to msix on a WQ #
         modulo msix vector count basis.
       Module parameters exist to cap/control the config if desired.
  - Each protocol has its own buffer and dma pools.

I apologize for the size of the patch.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>

----
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/lpfc/lpfc_hw4.h

@@ -108,6 +108,7 @@ struct lpfc_sli_intf {
 #define LPFC_MAX_MQ_PAGE		8
 #define LPFC_MAX_WQ_PAGE_V0		4
 #define LPFC_MAX_WQ_PAGE		8
+#define LPFC_MAX_RQ_PAGE		8
 #define LPFC_MAX_CQ_PAGE		4
 #define LPFC_MAX_EQ_PAGE		8
 
@@ -198,7 +199,7 @@ struct lpfc_sli_intf {
 /* Configuration of Interrupts / sec for entire HBA port */
 #define LPFC_MIN_IMAX          5000
 #define LPFC_MAX_IMAX          5000000
-#define LPFC_DEF_IMAX          50000
+#define LPFC_DEF_IMAX          150000
 
 #define LPFC_MIN_CPU_MAP       0
 #define LPFC_MAX_CPU_MAP       2
@@ -348,6 +349,7 @@ struct lpfc_cqe {
 #define CQE_CODE_RECEIVE		0x4
 #define CQE_CODE_XRI_ABORTED		0x5
 #define CQE_CODE_RECEIVE_V1		0x9
+#define CQE_CODE_NVME_ERSP		0xd
 
 /*
  * Define mask value for xri_aborted and wcqe completed CQE extended status.
@@ -367,6 +369,9 @@ struct lpfc_wcqe_complete {
 #define lpfc_wcqe_c_hw_status_SHIFT	0
 #define lpfc_wcqe_c_hw_status_MASK	0x000000FF
 #define lpfc_wcqe_c_hw_status_WORD	word0
+#define lpfc_wcqe_c_ersp0_SHIFT		0
+#define lpfc_wcqe_c_ersp0_MASK		0x0000FFFF
+#define lpfc_wcqe_c_ersp0_WORD		word0
 	uint32_t total_data_placed;
 	uint32_t parameter;
 #define lpfc_wcqe_c_bg_edir_SHIFT	5
@@ -400,6 +405,9 @@ struct lpfc_wcqe_complete {
 #define lpfc_wcqe_c_code_SHIFT		lpfc_cqe_code_SHIFT
 #define lpfc_wcqe_c_code_MASK		lpfc_cqe_code_MASK
 #define lpfc_wcqe_c_code_WORD		lpfc_cqe_code_WORD
+#define lpfc_wcqe_c_sqhead_SHIFT	0
+#define lpfc_wcqe_c_sqhead_MASK		0x0000FFFF
+#define lpfc_wcqe_c_sqhead_WORD		word3
 };
 
 /* completion queue entry for wqe release */
@@ -2841,12 +2849,18 @@ struct lpfc_sli4_parameters {
 #define cfg_mqv_WORD				word6
 	uint32_t word7;
 	uint32_t word8;
+#define cfg_wqpcnt_SHIFT			0
+#define cfg_wqpcnt_MASK				0x0000000f
+#define cfg_wqpcnt_WORD				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
+#define cfg_wqpsize_SHIFT			16
+#define cfg_wqpsize_MASK			0x000000ff
+#define cfg_wqpsize_WORD			word8
 	uint32_t word9;
 	uint32_t word10;
 #define cfg_rqv_SHIFT				14
@@ -2897,6 +2911,12 @@ struct lpfc_sli4_parameters {
 #define cfg_mds_diags_SHIFT			1
 #define cfg_mds_diags_MASK			0x00000001
 #define cfg_mds_diags_WORD			word19
+#define cfg_nvme_SHIFT				3
+#define cfg_nvme_MASK				0x00000001
+#define cfg_nvme_WORD				word19
+#define cfg_xib_SHIFT				4
+#define cfg_xib_MASK				0x00000001
+#define cfg_xib_WORD				word19
 };
 
 #define LPFC_SET_UE_RECOVERY		0x10
@@ -3659,6 +3679,9 @@ struct wqe_common {
 #define wqe_ebde_cnt_SHIFT    0
 #define wqe_ebde_cnt_MASK     0x0000000f
 #define wqe_ebde_cnt_WORD     word10
+#define wqe_nvme_SHIFT        4
+#define wqe_nvme_MASK         0x00000001
+#define wqe_nvme_WORD         word10
 #define wqe_oas_SHIFT         6
 #define wqe_oas_MASK          0x00000001
 #define wqe_oas_WORD          word10
@@ -4017,11 +4040,39 @@ struct lpfc_grp_hdr {
 	uint8_t revision[32];
 };
 
-#define FCP_COMMAND 0x0
-#define FCP_COMMAND_DATA_OUT 0x1
-#define ELS_COMMAND_NON_FIP 0xC
-#define ELS_COMMAND_FIP 0xD
-#define OTHER_COMMAND 0x8
+/* Defines for WQE command type */
+#define FCP_COMMAND		0x0
+#define NVME_READ_CMD		0x0
+#define FCP_COMMAND_DATA_OUT	0x1
+#define NVME_WRITE_CMD		0x1
+#define FCP_COMMAND_TRECEIVE	0x2
+#define FCP_COMMAND_TRSP	0x3
+#define FCP_COMMAND_TSEND	0x7
+#define OTHER_COMMAND		0x8
+#define ELS_COMMAND_NON_FIP	0xC
+#define ELS_COMMAND_FIP		0xD
+
+#define LPFC_NVME_EMBED_CMD	0x0
+#define LPFC_NVME_EMBED_WRITE	0x1
+#define LPFC_NVME_EMBED_READ	0x2
+
+/* WQE Commands */
+#define CMD_ABORT_XRI_WQE       0x0F
+#define CMD_XMIT_SEQUENCE64_WQE 0x82
+#define CMD_XMIT_BCAST64_WQE    0x84
+#define CMD_ELS_REQUEST64_WQE   0x8A
+#define CMD_XMIT_ELS_RSP64_WQE  0x95
+#define CMD_XMIT_BLS_RSP64_WQE  0x97
+#define CMD_FCP_IWRITE64_WQE    0x98
+#define CMD_FCP_IREAD64_WQE     0x9A
+#define CMD_FCP_ICMND64_WQE     0x9C
+#define CMD_FCP_TSEND64_WQE     0x9F
+#define CMD_FCP_TRECEIVE64_WQE  0xA1
+#define CMD_FCP_TRSP64_WQE      0xA3
+#define CMD_GEN_REQUEST64_WQE   0xC2
+
+#define CMD_WQE_MASK            0xff
+
 
 #define LPFC_FW_DUMP	1
 #define LPFC_FW_RESET	2