iser-target: Add iSCSI Extensions for RDMA (iSER) target driver

This patch adds support for iSCSI Extensions for RDMA target mode,
and includes CQ pooling per isert_device context distributed across
multiple active iser target sessions.

It also uses cmwq process context for RX / TX ib_post_cq() polling
via isert_cq_desc->cq_[rx,tx]_work invoked by isert_cq_[rx,tx]_callback()
hardIRQ context callbacks.

v5 changes:

- Use ISER_RECV_DATA_SEG_LEN instead of hardcoded value in ISER_RX_PAD_SIZE (Or)
- Fix make W=1 warnings (Or)
- Add missing depends on NET && INFINIBAND_ADDR_TRANS in Kconfig (Randy + Or)
- Make isert_device_find_by_ib_dev() return proper ERR_PTR (Wei Yongjun)
- Properly setup iscsi_np->np_sockaddr in isert_setup_np() (Shlomi + nab)
- Add special case for early ISCSI_OP_SCSI_CMD exception handling (nab)

v4 changes:
- Mark isert_cq_rx_work as static (Or)
- Drop unnecessary ib_dma_sync_single_for_cpu + ib_dma_sync_single_for_device
  calls for isert_cmd->sense_buf_dma from isert_put_response (Or)
- Use 12288 for ISER_RX_PAD_SIZE base to save extra page per
  struct iser_rx_desc (Or + nab)
- Drop now unnecessary isert_rx_desc usage, and convert RX users to
  iser_rx_desc (Or + nab)
- Move isert_[alloc,free]_rx_descriptors() ahead of
  isert_create_device_ib_res() usage (nab)
- Mark isert_cq_[rx,tx]_callback() + prototypes as static
- Fix 'warning: 'ret' may be used uninitialized' warning for
  isert_create_device_ib_res on powerpc allmodconfig (fengguang + nab)
- Fix 'warning: 'ret' may be used uninitialized' warning for
  isert_connect_request on i386 allyesconfig (fengguang + nab)
- Fix pr_debug conversion specification in isert_rx_completion()
  (fengguang + nab)
- Drop unnecessary isert_conn->conn_cm_id != NULL check in
  isert_connect_release causing the build warning:
  "variable dereferenced before check 'isert_conn->conn_cm_id'"
- Fix isert_lid + isert_np leak in isert_setup_np failure path
- Add isert_conn->conn_wait_comp_err usage in isert_free_conn()
  for isert_cq_comp_err completion path
- Add isert_conn->logout_posted bit to determine decrement of
  isert_conn->post_send_buf_count from logout response completion
- Always set ISER_CONN_DOWN from isert_disconnect_work() callback

v3 changes:

- Convert to use per isert_cq_desc->cq_[rx,tx]_work + drop tasklets (Or + nab)
- Move IB_EVENT_QP_LAST_WQE_REACHED warn into correct
  isert_qp_event_callback (Or)
- Drop unnecessary IB_ACCESS_REMOTE_* access flag usage in
  isert_create_device_ib_res (Or)
- Add common isert_init_send_wr(), and convert isert_put_* calls (Or)
- Move to verbs+core logic to single ib_isert.[c,h]  (Or + nab)
- Add kmem_cache isert_cmd_cache usage for descriptor allocation (nab)
- Move common ib_post_send() logic used by isert_put_*() to
  isert_post_response() (nab)
- Add isert_put_reject call in isert_response_queue() for posting
  ISCSI_REJECT response. (nab)
- Add ISTATE_SEND_REJECT checking in isert_do_control_comp. (nab)

v2 changes:

- Drop unused ISERT_ADDR_ROUTE_TIMEOUT define
- Add rdma_notify() call for IB_EVENT_COMM_EST in isert_qp_event_callback()
- Make isert_query_device() less verbose
- Drop unused RDMA_CM_EVENT_ADDR_ERROR and RDMA_CM_EVENT_ROUTE_ERROR
  cases from isert_cma_handler()
- Drop unused rdma/ib_fmr_pool.h include
- Update isert_conn_setup_qp() to assign cq based upon least used
- Add isert_create_device_ib_res() to setup PD, CQs and MRs for each
  underlying struct ib_device, instead of using per isert_conn resources.
- Add isert_free_device_ib_res() to release PD, CQs and MRs for each
  underlying struct ib_device.
- Add isert_device_find_by_ib_dev()
- Change isert_connect_request() to drop PD, CQs and MRs allocation,
  and use isert_device_find_by_ib_dev() instead.
- Add isert_device_try_release()
- Change isert_connect_release() to decrement cq_active_qps, and drop
  PD, CQs and MRs resource release.
- Update isert_connect_release() to call isert_device_try_release()
- Make isert_create_device_ib_res() determine device->cqs_used based
  upon num_online_cpus()
- Drop misleading isert_dump_ib_wc() usage
- Drop unused rdma/ib_fmr_pool.h include
- Use proper xfer_len for login PDUs in isert_rx_completion()
- Add isert_release_cmd() usage
- Change isert_alloc_cmd() to setup iscsi_cmd.release_cmd() pointer
- Change isert_put_cmd() to perform per iscsi_opcode specific release
  logic
- Add isert_unmap_cmd() call for ISCSI_OP_SCSI_CMD from isert_put_cmd()
- Change isert_send_completion() to call
  atomic_dec(&isert_conn->post_send_buf_count)
  based upon per iscsi_opcode logic
- Drop ISTATE_REMOVE processing from isert_immediate_queue()
- Drop ISTATE_SEND_DATAIN processing from isert_response_queue()
- Drop ISTATE_SEND_STATUS processing from isert_response_queue()
- Drop iscsit_transport->iscsit_unmap_cmd() and ->iscsit_free_cmd()
- Convert iser_cq_tx_tasklet() to use struct isert_cq_desc pooling logic
- Convert isert_cq_tx_callback() to use struct isert_cq_desc pooling
  logic
- Convert iser_cq_rx_tasklet() to use struct isert_cq_desc pooling logic
- Convert isert_cq_rx_callback() to use struct isert_cq_desc pooling
  logic
- Add explict iscsit_stop_dataout_timer() call to
  isert_do_rdma_read_comp()
- Use isert_get_dataout() for iscsit_transport->iscsit_get_dataout()
  caller
- Drop ISTATE_SEND_R2T processing from isert_immediate_queue()
- Drop unused rdma/ib_fmr_pool.h include
- Drop isert_cmd->cmd_kref in favor of se_cmd->cmd_kref usage
- Add struct isert_device in order to support multiple EQs + CQ pooling
- Add struct isert_cq_desc
- Drop tasklets and cqs from isert_conn
- Bump ISERT_MAX_CQ to 64
- Various minor checkpatch fixes

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Nicholas Bellinger <nab@linux-iscsi.org>

drivers/infiniband/Kconfig

@@ -59,5 +59,6 @@ source "drivers/infiniband/ulp/srp/Kconfig"
 source "drivers/infiniband/ulp/srpt/Kconfig"
 
 source "drivers/infiniband/ulp/iser/Kconfig"
+source "drivers/infiniband/ulp/isert/Kconfig"
 
 endif # INFINIBAND

drivers/infiniband/Makefile

@@ -13,3 +13,4 @@ obj-$(CONFIG_INFINIBAND_IPOIB)		+= ulp/ipoib/
 obj-$(CONFIG_INFINIBAND_SRP)		+= ulp/srp/
 obj-$(CONFIG_INFINIBAND_SRPT)		+= ulp/srpt/
 obj-$(CONFIG_INFINIBAND_ISER)		+= ulp/iser/
+obj-$(CONFIG_INFINIBAND_ISERT)		+= ulp/isert/

drivers/infiniband/ulp/isert/Kconfig

@@ -0,0 +1,5 @@
+config INFINIBAND_ISERT
+	tristate "iSCSI Extentions for RDMA (iSER) target support"
+	depends on INET && INFINIBAND_ADDR_TRANS && TARGET_CORE && ISCSI_TARGET
+	---help---
+	Support for iSCSI Extentions for RDMA (iSER) Target on Infiniband fabrics.

drivers/infiniband/ulp/isert/Makefile

@@ -0,0 +1,2 @@
+ccflags-y		:= -Idrivers/target -Idrivers/target/iscsi
+obj-$(CONFIG_INFINIBAND_ISERT)	+= ib_isert.o

drivers/infiniband/ulp/isert/ib_isert.h

@@ -0,0 +1,138 @@
+#include <linux/socket.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+
+#define ISERT_RDMA_LISTEN_BACKLOG	10
+
+enum isert_desc_type {
+	ISCSI_TX_CONTROL,
+	ISCSI_TX_DATAIN
+};
+
+enum iser_ib_op_code {
+	ISER_IB_RECV,
+	ISER_IB_SEND,
+	ISER_IB_RDMA_WRITE,
+	ISER_IB_RDMA_READ,
+};
+
+enum iser_conn_state {
+	ISER_CONN_INIT,
+	ISER_CONN_UP,
+	ISER_CONN_TERMINATING,
+	ISER_CONN_DOWN,
+};
+
+struct iser_rx_desc {
+	struct iser_hdr iser_header;
+	struct iscsi_hdr iscsi_header;
+	char		data[ISER_RECV_DATA_SEG_LEN];
+	u64		dma_addr;
+	struct ib_sge	rx_sg;
+	char		pad[ISER_RX_PAD_SIZE];
+} __packed;
+
+struct iser_tx_desc {
+	struct iser_hdr iser_header;
+	struct iscsi_hdr iscsi_header;
+	enum isert_desc_type type;
+	u64		dma_addr;
+	struct ib_sge	tx_sg[2];
+	int		num_sge;
+	struct isert_cmd *isert_cmd;
+	struct ib_send_wr send_wr;
+} __packed;
+
+struct isert_rdma_wr {
+	struct list_head	wr_list;
+	struct isert_cmd	*isert_cmd;
+	enum iser_ib_op_code	iser_ib_op;
+	struct ib_sge		*ib_sge;
+	int			num_sge;
+	struct scatterlist	*sge;
+	int			send_wr_num;
+	struct ib_send_wr	*send_wr;
+};
+
+struct isert_cmd {
+	uint32_t		read_stag;
+	uint32_t		write_stag;
+	uint64_t		read_va;
+	uint64_t		write_va;
+	u64			sense_buf_dma;
+	u32			sense_buf_len;
+	u32			read_va_off;
+	u32			write_va_off;
+	u32			rdma_wr_num;
+	struct isert_conn	*conn;
+	struct iscsi_cmd	iscsi_cmd;
+	struct ib_sge		*ib_sge;
+	struct iser_tx_desc	tx_desc;
+	struct isert_rdma_wr	rdma_wr;
+	struct work_struct	comp_work;
+};
+
+struct isert_device;
+
+struct isert_conn {
+	enum iser_conn_state	state;
+	bool			logout_posted;
+	int			post_recv_buf_count;
+	atomic_t		post_send_buf_count;
+	u32			responder_resources;
+	u32			initiator_depth;
+	u32			max_sge;
+	char			*login_buf;
+	char			*login_req_buf;
+	char			*login_rsp_buf;
+	u64			login_req_dma;
+	u64			login_rsp_dma;
+	unsigned int		conn_rx_desc_head;
+	struct iser_rx_desc	*conn_rx_descs;
+	struct ib_recv_wr	conn_rx_wr[ISERT_MIN_POSTED_RX];
+	struct iscsi_conn	*conn;
+	struct list_head	conn_accept_node;
+	struct completion	conn_login_comp;
+	struct iser_tx_desc	conn_login_tx_desc;
+	struct rdma_cm_id	*conn_cm_id;
+	struct ib_pd		*conn_pd;
+	struct ib_mr		*conn_mr;
+	struct ib_qp		*conn_qp;
+	struct isert_device	*conn_device;
+	struct work_struct	conn_logout_work;
+	wait_queue_head_t	conn_wait;
+	wait_queue_head_t	conn_wait_comp_err;
+	struct kref		conn_kref;
+};
+
+#define ISERT_MAX_CQ 64
+
+struct isert_cq_desc {
+	struct isert_device	*device;
+	int			cq_index;
+	struct work_struct	cq_rx_work;
+	struct work_struct	cq_tx_work;
+};
+
+struct isert_device {
+	int			cqs_used;
+	int			refcount;
+	int			cq_active_qps[ISERT_MAX_CQ];
+	struct ib_device	*ib_device;
+	struct ib_pd		*dev_pd;
+	struct ib_mr		*dev_mr;
+	struct ib_cq		*dev_rx_cq[ISERT_MAX_CQ];
+	struct ib_cq		*dev_tx_cq[ISERT_MAX_CQ];
+	struct isert_cq_desc	*cq_desc;
+	struct list_head	dev_node;
+};
+
+struct isert_np {
+	wait_queue_head_t	np_accept_wq;
+	struct rdma_cm_id	*np_cm_id;
+	struct mutex		np_accept_mutex;
+	struct list_head	np_accept_list;
+	struct completion	np_login_comp;
+};

drivers/infiniband/ulp/isert/isert_proto.h

@@ -0,0 +1,47 @@
+/* From iscsi_iser.h */
+
+struct iser_hdr {
+	u8	flags;
+	u8	rsvd[3];
+	__be32	write_stag; /* write rkey */
+	__be64	write_va;
+	__be32	read_stag;  /* read rkey */
+	__be64	read_va;
+} __packed;
+
+/*Constant PDU lengths calculations */
+#define ISER_HEADERS_LEN  (sizeof(struct iser_hdr) + sizeof(struct iscsi_hdr))
+
+#define ISER_RECV_DATA_SEG_LEN  8192
+#define ISER_RX_PAYLOAD_SIZE    (ISER_HEADERS_LEN + ISER_RECV_DATA_SEG_LEN)
+#define ISER_RX_LOGIN_SIZE      (ISER_HEADERS_LEN + ISCSI_DEF_MAX_RECV_SEG_LEN)
+
+/* QP settings */
+/* Maximal bounds on received asynchronous PDUs */
+#define ISERT_MAX_TX_MISC_PDUS	4 /* NOOP_IN(2) , ASYNC_EVENT(2)   */
+
+#define ISERT_MAX_RX_MISC_PDUS	6 /* NOOP_OUT(2), TEXT(1),         *
+				   * SCSI_TMFUNC(2), LOGOUT(1) */
+
+#define ISCSI_DEF_XMIT_CMDS_MAX 128 /* from libiscsi.h, must be power of 2 */
+
+#define ISERT_QP_MAX_RECV_DTOS	(ISCSI_DEF_XMIT_CMDS_MAX)
+
+#define ISERT_MIN_POSTED_RX	(ISCSI_DEF_XMIT_CMDS_MAX >> 2)
+
+#define ISERT_INFLIGHT_DATAOUTS	8
+
+#define ISERT_QP_MAX_REQ_DTOS	(ISCSI_DEF_XMIT_CMDS_MAX *    \
+				(1 + ISERT_INFLIGHT_DATAOUTS) + \
+				ISERT_MAX_TX_MISC_PDUS	+ \
+				ISERT_MAX_RX_MISC_PDUS)
+
+#define ISER_RX_PAD_SIZE	(ISER_RECV_DATA_SEG_LEN + 4096 - \
+		(ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge)))
+
+#define ISER_VER	0x10
+#define ISER_WSV	0x08
+#define ISER_RSV	0x04
+#define ISCSI_CTRL	0x10
+#define ISER_HELLO	0x20
+#define ISER_HELLORPLY	0x30