[PATCH rdma-next v2 02/11] RDMA/erdma: Add the hardware related definitions

[Cheng Xu <chengyou@linux.alibaba.com>]

ERDMA is a PCIe device, and this file provides ERDMA hardware related
definitions, mainly including PCIe device capabilities restrictions,
device registers definitions, doorbell space, doorbell structure
definitions and WQE definitions.

Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
---
 drivers/infiniband/hw/erdma/erdma_hw.h | 476 +++++++++++++++++++++++++
 1 file changed, 476 insertions(+)
 create mode 100644 drivers/infiniband/hw/erdma/erdma_hw.h

diff --git a/drivers/infiniband/hw/erdma/erdma_hw.h b/drivers/infiniband/hw/erdma/erdma_hw.h
new file mode 100644
index 000000000000..02640f64cc26
--- /dev/null
+++ b/drivers/infiniband/hw/erdma/erdma_hw.h
@@ -0,0 +1,476 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+
+/* Authors: Cheng Xu <chengyou@linux.alibaba.com> */
+/*          Kai Shen <kaishen@linux.alibaba.com> */
+/* Copyright (c) 2020-2022, Alibaba Group. */
+
+#ifndef __ERDMA_HW_H__
+#define __ERDMA_HW_H__
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+/* PCIe device related definition. */
+#define PCI_VENDOR_ID_ALIBABA 0x1ded
+
+#define ERDMA_FUNC_BAR     0
+#define ERDMA_MISX_BAR     2
+
+#define ERDMA_BAR_MASK (BIT(ERDMA_FUNC_BAR) | BIT(ERDMA_MISX_BAR))
+
+/* MSI-X related. */
+#define ERDMA_NUM_MSIX_VEC        32
+#define ERDMA_MSIX_VECTOR_CMDQ    0
+
+/* PCIe Bar0 Registers. */
+#define ERDMA_REGS_VERSION_REG             0x0
+#define ERDMA_REGS_DEV_CTRL_REG            0x10
+#define ERDMA_REGS_DEV_ST_REG              0x14
+#define ERDMA_REGS_NETDEV_MAC_L_REG        0x18
+#define ERDMA_REGS_NETDEV_MAC_H_REG        0x1C
+#define ERDMA_REGS_CMDQ_SQ_ADDR_L_REG      0x20
+#define ERDMA_REGS_CMDQ_SQ_ADDR_H_REG      0x24
+#define ERDMA_REGS_CMDQ_CQ_ADDR_L_REG      0x28
+#define ERDMA_REGS_CMDQ_CQ_ADDR_H_REG      0x2C
+#define ERDMA_REGS_CMDQ_DEPTH_REG          0x30
+#define ERDMA_REGS_CMDQ_EQ_DEPTH_REG       0x34
+#define ERDMA_REGS_CMDQ_EQ_ADDR_L_REG      0x38
+#define ERDMA_REGS_CMDQ_EQ_ADDR_H_REG      0x3C
+#define ERDMA_REGS_AEQ_ADDR_L_REG          0x40
+#define ERDMA_REGS_AEQ_ADDR_H_REG          0x44
+#define ERDMA_REGS_AEQ_DEPTH_REG           0x48
+#define ERDMA_REGS_GRP_NUM_REG             0x4c
+#define ERDMA_REGS_AEQ_DB_REG              0x50
+#define ERDMA_CMDQ_SQ_DB_HOST_ADDR_REG     0x60
+#define ERDMA_CMDQ_CQ_DB_HOST_ADDR_REG     0x68
+#define ERDMA_CMDQ_EQ_DB_HOST_ADDR_REG     0x70
+#define ERDMA_AEQ_DB_HOST_ADDR_REG         0x78
+#define ERDMA_REGS_CEQ_DB_BASE_REG         0x100
+#define ERDMA_CMDQ_SQDB_REG                0x200
+#define ERDMA_CMDQ_CQDB_REG                0x300
+
+/* DEV_CTRL_REG details. */
+#define ERDMA_REG_DEV_CTRL_RESET_MASK       0x00000001
+#define ERDMA_REG_DEV_CTRL_INIT_MASK        0x00000002
+
+/* DEV_ST_REG details. */
+#define ERDMA_REG_DEV_ST_RESET_DONE_MASK    0x00000001U
+#define ERDMA_REG_DEV_ST_INIT_DONE_MASK     0x00000002U
+
+/* eRDMA PCIe DBs definition. */
+#define ERDMA_BAR_DB_SPACE_BASE     4096
+
+#define ERDMA_BAR_SQDB_SPACE_OFFSET 0
+#define ERDMA_BAR_SQDB_SPACE_SIZE   (384 * 1024)
+
+#define ERDMA_BAR_RQDB_SPACE_OFFSET (ERDMA_BAR_SQDB_SPACE_OFFSET + ERDMA_BAR_SQDB_SPACE_SIZE)
+#define ERDMA_BAR_RQDB_SPACE_SIZE   (96 * 1024)
+
+#define ERDMA_BAR_CQDB_SPACE_OFFSET (ERDMA_BAR_RQDB_SPACE_OFFSET + ERDMA_BAR_RQDB_SPACE_SIZE)
+
+/* Doorbell page resources related. */
+/*
+ * Max # of parallelly issued directSQE is 3072 per device,
+ * hardware organizes this into 24 group, per group has 128 credits.
+ */
+#define ERDMA_DWQE_MAX_GRP_CNT          24
+#define ERDMA_DWQE_NUM_PER_GRP          128
+
+#define ERDMA_DWQE_TYPE0_CNT            64
+#define ERDMA_DWQE_TYPE1_CNT            496
+#define ERDMA_DWQE_TYPE1_CNT_PER_PAGE   16  /* type1 DB contains 2 DBs, takes 256Byte. */
+
+#define ERDMA_SDB_SHARED_PAGE_INDEX     95
+
+/* Doorbell related. */
+#define ERDMA_CQDB_EQN_MASK              GENMASK_ULL(63, 56)
+#define ERDMA_CQDB_CQN_MASK              GENMASK_ULL(55, 32)
+#define ERDMA_CQDB_ARM_MASK              BIT_ULL(31)
+#define ERDMA_CQDB_SOL_MASK              BIT_ULL(30)
+#define ERDMA_CQDB_CMDSN_MASK            GENMASK_ULL(29, 28)
+#define ERDMA_CQDB_CI_MASK               GENMASK_ULL(23, 0)
+
+#define ERDMA_EQDB_ARM_MASK              BIT(31)
+#define ERDMA_EQDB_CI_MASK               GENMASK_ULL(23, 0)
+
+#define ERDMA_PAGE_SIZE_SUPPORT          0x7FFFF000
+
+
+/* WQE related. */
+#define EQE_SIZE 16
+#define EQE_SHIFT 4
+#define RQE_SIZE 32
+#define RQE_SHIFT 5
+#define CQE_SIZE 32
+#define CQE_SHIFT 5
+#define SQEBB_SIZE 32
+#define SQEBB_SHIFT 5
+#define SQEBB_MASK (~(SQEBB_SIZE - 1))
+#define SQEBB_ALIGN(size) ((size + SQEBB_SIZE - 1) & SQEBB_MASK)
+#define SQEBB_COUNT(size) (SQEBB_ALIGN(size) >> SQEBB_SHIFT)
+
+#define ERDMA_MAX_SQE_SIZE 128
+#define ERDMA_MAX_WQEBB_PER_SQE 4
+
+/* CMDQ related. */
+#define ERDMA_CMDQ_MAX_OUTSTANDING      128
+#define ERDMA_CMDQ_SQE_SIZE             64
+
+/* cmdq sub module definition. */
+enum CMDQ_WQE_SUB_MOD {
+	CMDQ_SUBMOD_RDMA    = 0,
+	CMDQ_SUBMOD_COMMON  = 1
+};
+
+enum CMDQ_RDMA_OPCODE {
+	CMDQ_OPCODE_QUERY_DEVICE = 0,
+	CMDQ_OPCODE_CREATE_QP    = 1,
+	CMDQ_OPCODE_DESTROY_QP   = 2,
+	CMDQ_OPCODE_MODIFY_QP    = 3,
+	CMDQ_OPCODE_CREATE_CQ    = 4,
+	CMDQ_OPCODE_DESTROY_CQ   = 5,
+	CMDQ_OPCODE_REG_MR       = 8,
+	CMDQ_OPCODE_DEREG_MR     = 9
+};
+
+enum CMDQ_COMMON_OPCODE {
+	CMDQ_OPCODE_CREATE_EQ  = 0,
+	CMDQ_OPCODE_DESTROY_EQ = 1
+};
+
+/* cmdq-SQE HDR */
+#define ERDMA_CMD_HDR_WQEBB_CNT_MASK     GENMASK_ULL(54, 52)
+#define ERDMA_CMD_HDR_CONTEXT_COOKIE     GENMASK_ULL(47, 32)
+#define ERDMA_CMD_HDR_SUB_MOD_MASK       GENMASK_ULL(25, 24)
+#define ERDMA_CMD_HDR_OPCODE_MASK        GENMASK_ULL(23, 16)
+#define ERDMA_CMD_HDR_WQEBB_INDEX_MASK   GENMASK_ULL(15, 0)
+
+struct erdma_cmdq_destroy_cq_req {
+	u64 hdr;
+	u32 cqn;
+};
+
+struct erdma_cmdq_create_eq_req {
+	u64 hdr;
+	u64 qbuf_addr;
+	u8  vector_idx;
+	u8  eqn;
+	u8  depth;
+	u8  qtype;
+	u32 db_dma_addr_l;
+	u32 db_dma_addr_h;
+};
+
+struct erdma_cmdq_destroy_eq_req {
+	u64 hdr;
+	u64 rsvd0;
+	u8  vector_idx;
+	u8  eqn;
+	u8  rsvd1;
+	u8  qtype;
+};
+
+/* create_cq cfg0 */
+#define ERDMA_CMD_CREATE_CQ_DEPTH_MASK      GENMASK(31, 24)
+#define ERDMA_CMD_CREATE_CQ_PAGESIZE_MASK   GENMASK(23, 20)
+#define ERDMA_CMD_CREATE_CQ_CQN_MASK        GENMASK(19, 0)
+
+/* create_cq cfg1 */
+#define ERDMA_CMD_CREATE_CQ_MTT_CNT_MASK    GENMASK(31, 16)
+#define ERDMA_CMD_CREATE_CQ_MTT_TYPE_MASK   BIT(15)
+#define ERDMA_CMD_CREATE_CQ_EQN_MASK        GENMASK(9, 0)
+
+struct erdma_cmdq_create_cq_req {
+	u64 hdr;
+	u32 cfg0;
+	u32 qbuf_addr_l;
+	u32 qbuf_addr_h;
+	u32 cfg1;
+	u64 cq_db_info_addr;
+	u32 first_page_offset;
+};
+
+/* regmr/deregmr cfg0 */
+#define ERDMA_CMD_MR_VALID_MASK    BIT(31)
+#define ERDMA_CMD_MR_KEY_MASK      GENMASK(27, 20)
+#define ERDMA_CMD_MR_MPT_IDX_MASK  GENMASK(19, 0)
+
+/* regmr cfg1 */
+#define ERDMA_CMD_REGMR_PD_MASK       GENMASK(31, 12)
+#define ERDMA_CMD_REGMR_TYPE_MASK     GENMASK(7, 6)
+#define ERDMA_CMD_REGMR_RIGHT_MASK    GENMASK(5, 2)
+#define ERDMA_CMD_REGMR_ACC_MODE_MASK GENMASK(1, 0)
+
+/* regmr cfg2 */
+#define ERDMA_CMD_REGMR_PAGESIZE_MASK GENMASK(31, 27)
+#define ERDMA_CMD_REGMR_MTT_TYPE_MASK GENMASK(21, 20)
+#define ERDMA_CMD_REGMR_MTT_CNT_MASK  GENMASK(19, 0)
+
+struct erdma_cmdq_reg_mr_req {
+	u64 hdr;
+	u32 cfg0;
+	u32 cfg1;
+	u64 start_va;
+	u32 size;
+	u32 cfg2;
+	u64 phy_addr[4];
+};
+
+struct erdma_cmdq_dereg_mr_req {
+	u64 hdr;
+	u32 cfg0;
+};
+
+/* modify qp cfg0 */
+#define ERDMA_CMD_MODIFY_QP_STATE_MASK  GENMASK(31, 24)
+#define ERDMA_CMD_MODIFY_QP_CC_MASK     GENMASK(23, 20)
+#define ERDMA_CMD_MODIFY_QP_QPN_MASK    GENMASK(19, 0)
+
+struct erdma_cmdq_modify_qp_req {
+	u64 hdr;
+	u32 cfg0;
+	u32 cookie;
+	u32 dip;
+	u32 sip;
+	u16 sport;
+	u16 dport;
+	u32 send_nxt;
+	u32 recv_nxt;
+};
+
+/* create qp cfg0 */
+#define ERDMA_CMD_CREATE_QP_SQ_DEPTH_MASK   GENMASK(31, 20)
+#define ERDMA_CMD_CREATE_QP_QPN_MASK        GENMASK(19, 0)
+
+/* create qp cfg1 */
+#define ERDMA_CMD_CREATE_QP_RQ_DEPTH_MASK   GENMASK(31, 20)
+#define ERDMA_CMD_CREATE_QP_PD_MASK         GENMASK(19, 0)
+
+/* cqn_mtt_cfg */
+#define ERDMA_CMD_CREATE_QP_PAGE_SIZE_MASK  GENMASK(31, 28)
+#define ERDMA_CMD_CREATE_QP_CQN_MASK        GENMASK(23, 0)
+
+/* mtt_cfg */
+#define ERDMA_CMD_CREATE_QP_PAGE_OFFSET_MASK GENMASK(31, 12)
+#define ERDMA_CMD_CREATE_QP_MTT_CNT_MASK     GENMASK(11, 1)
+#define ERDMA_CMD_CREATE_QP_MTT_TYPE_MASK    BIT(0)
+
+struct erdma_cmdq_create_qp_req {
+	u64 hdr;
+	u32 cfg0;
+	u32 cfg1;
+	u32 sq_cqn_mtt_cfg;
+	u32 rq_cqn_mtt_cfg;
+	u64 sq_buf_addr;
+	u64 rq_buf_addr;
+	u32 sq_mtt_cfg;
+	u32 rq_mtt_cfg;
+	u64 sq_db_info_dma_addr;
+	u64 rq_db_info_dma_addr;
+};
+
+struct erdma_cmdq_destroy_qp_req {
+	u64 hdr;
+	u32 qpn;
+};
+
+#define ERDMA_CMD_DEV_CAP0_MAX_CQE_MASK      GENMASK_ULL(47, 40)
+#define ERDMA_CMD_DEV_CAP0_MAX_RECV_WR_MASK  GENMASK_ULL(23, 16)
+#define ERDMA_CMD_DEV_CAP0_MAX_MR_SIZE_MASK  GENMASK_ULL(7, 0)
+
+#define ERDMA_CMD_DEV_CAP1_DMA_LOCAL_KEY_MASK GENMASK_ULL(63, 32)
+#define ERDMA_CMD_DEV_CAP1_DEFAULT_CC_MASK    GENMASK_ULL(31, 28)
+#define ERDMA_CMD_DEV_CAP1_QBLOCK_MASK        GENMASK_ULL(27, 16)
+#define ERDMA_CMD_DEV_CAP1_MAX_MW_MASK        GENMASK_ULL(7, 0)
+
+#define ERDMA_NQP_PER_QBLOCK 1024
+
+/* CQE hdr */
+#define ERDMA_CQE_HDR_OWNER_MASK         BIT(31)
+#define ERDMA_CQE_HDR_OPCODE_MASK        GENMASK(23, 16)
+#define ERDMA_CQE_HDR_QTYPE_MASK         GENMASK(15, 8)
+#define ERDMA_CQE_HDR_SYNDROME_MASK      GENMASK(7, 0)
+
+#define ERDMA_CQE_QTYPE_SQ    0
+#define ERDMA_CQE_QTYPE_RQ    1
+#define ERDMA_CQE_QTYPE_CMDQ  2
+
+struct erdma_cqe {
+	__be32 hdr;
+	__be32 qe_idx;
+	__be32 qpn;
+	__be32 imm_data;
+	__be32 size;
+	__be32 rsvd[3];
+};
+
+struct erdma_sge {
+	__aligned_le64 laddr;
+	__le32         length;
+	__le32         lkey;
+};
+
+/* Receive Queue Element */
+struct erdma_rqe {
+	__le16 qe_idx;
+	__le16 rsvd;
+	__le32 qpn;
+	__le32 rsvd2;
+	__le32 rsvd3;
+	__le64 to;
+	__le32 length;
+	__le32 stag;
+};
+
+/* SQE */
+#define ERDMA_SQE_HDR_SGL_LEN_MASK       GENMASK_ULL(63, 56)
+#define ERDMA_SQE_HDR_WQEBB_CNT_MASK     GENMASK_ULL(54, 52)
+#define ERDMA_SQE_HDR_QPN_MASK           GENMASK_ULL(51, 32)
+#define ERDMA_SQE_HDR_OPCODE_MASK        GENMASK_ULL(31, 27)
+#define ERDMA_SQE_HDR_DWQE_MASK          BIT_ULL(26)
+#define ERDMA_SQE_HDR_INLINE_MASK        BIT_ULL(25)
+#define ERDMA_SQE_HDR_FENCE_MASK         BIT_ULL(24)
+#define ERDMA_SQE_HDR_SE_MASK            BIT_ULL(23)
+#define ERDMA_SQE_HDR_CE_MASK            BIT_ULL(22)
+#define ERDMA_SQE_HDR_WQEBB_INDEX_MASK   GENMASK_ULL(15, 0)
+
+/* REG MR attrs */
+#define ERDMA_SQE_MR_ACCESS_MODE_MASK	GENMASK_ULL(1, 0)
+#define ERDMA_SQE_MR_ACCESS_RIGHT_MASK	GENMASK_ULL(5, 2)
+#define ERDMA_SQE_MR_MTT_TYPE_MASK		GENMASK_ULL(7, 6)
+#define ERDMA_SQE_MR_MTT_COUNT_MASK		GENMASK_ULL(31, 12)
+
+struct erdma_write_sqe {
+	__le64 hdr;
+	__le32 imm_data;
+	__le32 length;
+
+	__le32 sink_stag;
+	__le32 sink_to_low;
+	__le32 sink_to_high;
+
+	__le32 rsvd;
+
+	struct erdma_sge sgl[0];
+};
+
+struct erdma_send_sqe {
+	__le64 hdr;
+	__le32 imm_data;
+	__le32 length;
+	struct erdma_sge sgl[0];
+};
+
+struct erdma_readreq_sqe {
+	__le64 hdr;
+	__le32 invalid_stag;
+	__le32 length;
+	__le32 sink_stag;
+	__le32 sink_to_low;
+	__le32 sink_to_high;
+	__le32 rsvd0;
+};
+
+struct erdma_reg_mr_sqe {
+	__le64 hdr;
+	__le64 addr;
+	__le32 length;
+	__le32 stag;
+	__le32 attrs;
+	__le32 reserved;
+	__u64 inline_addr[0];
+};
+
+/* EQ related. */
+#define ERDMA_DEFAULT_EQ_DEPTH 256
+
+/* ceqe */
+#define ERDMA_CEQE_HDR_DB_MASK  BIT_ULL(63)
+#define ERDMA_CEQE_HDR_PI_MASK  GENMASK_ULL(55, 32)
+#define ERDMA_CEQE_HDR_O_MASK   BIT_ULL(31)
+#define ERDMA_CEQE_HDR_CQN_MASK GENMASK_ULL(19, 0)
+
+/* aeqe */
+#define ERDMA_AEQE_HDR_O_MASK       BIT(31)
+#define ERDMA_AEQE_HDR_TYPE_MASK    GENMASK(23, 16)
+#define ERDMA_AEQE_HDR_SUBTYPE_MASK GENMASK(7, 0)
+
+#define ERDMA_AE_TYPE_QP_FATAL_EVENT     0
+#define ERDMA_AE_TYPE_QP_ERQ_ERR_EVENT   1
+#define ERDMA_AE_TYPE_ACC_ERR_EVENT      2
+#define ERDMA_AE_TYPE_CQ_ERR             3
+#define ERDMA_AE_TYPE_OTHER_ERROR        4
+
+struct erdma_aeqe {
+	__le32   hdr;
+	__le32   event_data0;
+	__le32   event_data1;
+	__le32   rsvd2;
+};
+
+enum erdma_opcode {
+	ERDMA_OP_WRITE           = 0,
+	ERDMA_OP_READ            = 1,
+	ERDMA_OP_SEND            = 2,
+	ERDMA_OP_SEND_WITH_IMM   = 3,
+
+	ERDMA_OP_RECEIVE         = 4,
+	ERDMA_OP_RECV_IMM        = 5,
+	ERDMA_OP_RECV_INV        = 6,
+
+	ERDMA_OP_REQ_ERR         = 7,
+	ERDNA_OP_READ_RESPONSE   = 8,
+	ERDMA_OP_WRITE_WITH_IMM  = 9,
+
+	ERDMA_OP_RECV_ERR        = 10,
+
+	ERDMA_OP_INVALIDATE     = 11,
+	ERDMA_OP_RSP_SEND_IMM   = 12,
+	ERDMA_OP_SEND_WITH_INV  = 13,
+
+	ERDMA_OP_REG_MR         = 14,
+	ERDMA_OP_LOCAL_INV      = 15,
+	ERDMA_OP_READ_WITH_INV  = 16,
+	ERDMA_NUM_OPCODES       = 17,
+	ERDMA_OP_INVALID        = ERDMA_NUM_OPCODES + 1
+};
+
+enum erdma_wc_status {
+	ERDMA_WC_SUCCESS = 0,
+	ERDMA_WC_GENERAL_ERR = 1,
+	ERDMA_WC_RECV_WQE_FORMAT_ERR = 2,
+	ERDMA_WC_RECV_STAG_INVALID_ERR = 3,
+	ERDMA_WC_RECV_ADDR_VIOLATION_ERR = 4,
+	ERDMA_WC_RECV_RIGHT_VIOLATION_ERR = 5,
+	ERDMA_WC_RECV_PDID_ERR = 6,
+	ERDMA_WC_RECV_WARRPING_ERR = 7,
+	ERDMA_WC_SEND_WQE_FORMAT_ERR = 8,
+	ERDMA_WC_SEND_WQE_ORD_EXCEED = 9,
+	ERDMA_WC_SEND_STAG_INVALID_ERR = 10,
+	ERDMA_WC_SEND_ADDR_VIOLATION_ERR = 11,
+	ERDMA_WC_SEND_RIGHT_VIOLATION_ERR = 12,
+	ERDMA_WC_SEND_PDID_ERR = 13,
+	ERDMA_WC_SEND_WARRPING_ERR = 14,
+	ERDMA_WC_FLUSH_ERR = 15,
+	ERDMA_WC_RETRY_EXC_ERR = 16,
+	ERDMA_NUM_WC_STATUS
+};
+
+enum erdma_vendor_err {
+	ERDMA_WC_VENDOR_NO_ERR = 0,
+	ERDMA_WC_VENDOR_INVALID_RQE = 1,
+	ERDMA_WC_VENDOR_RQE_INVALID_STAG = 2,
+	ERDMA_WC_VENDOR_RQE_ADDR_VIOLATION = 3,
+	ERDMA_WC_VENDOR_RQE_ACCESS_RIGHT_ERR = 4,
+	ERDMA_WC_VENDOR_RQE_INVALID_PD = 5,
+	ERDMA_WC_VENDOR_RQE_WRAP_ERR = 6,
+	ERDMA_WC_VENDOR_INVALID_SQE = 0x20,
+	ERDMA_WC_VENDOR_ZERO_ORD = 0x21,
+	ERDMA_WC_VENDOR_SQE_INVALID_STAG = 0x30,
+	ERDMA_WC_VENDOR_SQE_ADDR_VIOLATION = 0x31,
+	ERDMA_WC_VENDOR_SQE_ACCESS_ERR = 0x32,
+	ERDMA_WC_VENDOR_SQE_INVALID_PD = 0x33,
+	ERDMA_WC_VENDOR_SQE_WARP_ERR = 0x34
+};
+
+#endif
-- 
2.27.0