diff options
Diffstat (limited to 'drivers/scsi/cxgbi')
-rw-r--r-- | drivers/scsi/cxgbi/Kconfig | 2 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/Makefile | 2 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/cxgb3i/Kbuild | 3 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/cxgb3i/Kconfig | 7 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/cxgb3i/cxgb3i.c | 1465 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/cxgb3i/cxgb3i.h | 51 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/cxgb4i/Kbuild | 3 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/cxgb4i/Kconfig | 7 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/cxgb4i/cxgb4i.c | 1604 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/cxgb4i/cxgb4i.h | 43 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/libcxgbi.c | 2612 | ||||
-rw-r--r-- | drivers/scsi/cxgbi/libcxgbi.h | 745 |
12 files changed, 6544 insertions, 0 deletions
diff --git a/drivers/scsi/cxgbi/Kconfig b/drivers/scsi/cxgbi/Kconfig new file mode 100644 index 000000000000..17eb5d522f42 --- /dev/null +++ b/drivers/scsi/cxgbi/Kconfig @@ -0,0 +1,2 @@ +source "drivers/scsi/cxgbi/cxgb3i/Kconfig" +source "drivers/scsi/cxgbi/cxgb4i/Kconfig" diff --git a/drivers/scsi/cxgbi/Makefile b/drivers/scsi/cxgbi/Makefile new file mode 100644 index 000000000000..86007e344955 --- /dev/null +++ b/drivers/scsi/cxgbi/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_SCSI_CXGB3_ISCSI) += libcxgbi.o cxgb3i/ +obj-$(CONFIG_SCSI_CXGB4_ISCSI) += libcxgbi.o cxgb4i/ diff --git a/drivers/scsi/cxgbi/cxgb3i/Kbuild b/drivers/scsi/cxgbi/cxgb3i/Kbuild new file mode 100644 index 000000000000..09dbf9efc8ea --- /dev/null +++ b/drivers/scsi/cxgbi/cxgb3i/Kbuild @@ -0,0 +1,3 @@ +EXTRA_CFLAGS += -I$(srctree)/drivers/net/cxgb3 + +obj-$(CONFIG_SCSI_CXGB3_ISCSI) += cxgb3i.o diff --git a/drivers/scsi/cxgbi/cxgb3i/Kconfig b/drivers/scsi/cxgbi/cxgb3i/Kconfig new file mode 100644 index 000000000000..5cf4e9831f1b --- /dev/null +++ b/drivers/scsi/cxgbi/cxgb3i/Kconfig @@ -0,0 +1,7 @@ +config SCSI_CXGB3_ISCSI + tristate "Chelsio T3 iSCSI support" + depends on CHELSIO_T3_DEPENDS + select CHELSIO_T3 + select SCSI_ISCSI_ATTRS + ---help--- + This driver supports iSCSI offload for the Chelsio T3 devices. diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c new file mode 100644 index 000000000000..a129a170b47b --- /dev/null +++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c @@ -0,0 +1,1465 @@ +/* + * cxgb3i_offload.c: Chelsio S3xx iscsi offloaded tcp connection management + * + * Copyright (C) 2003-2008 Chelsio Communications. All rights reserved. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the LICENSE file included in this + * release for licensing terms and conditions. + * + * Written by: Dimitris Michailidis (dm@chelsio.com) + * Karen Xie (kxie@chelsio.com) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__ + +#include <linux/version.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <scsi/scsi_host.h> + +#include "common.h" +#include "t3_cpl.h" +#include "t3cdev.h" +#include "cxgb3_defs.h" +#include "cxgb3_ctl_defs.h" +#include "cxgb3_offload.h" +#include "firmware_exports.h" +#include "cxgb3i.h" + +static unsigned int dbg_level; +#include "../libcxgbi.h" + +#define DRV_MODULE_NAME "cxgb3i" +#define DRV_MODULE_DESC "Chelsio T3 iSCSI Driver" +#define DRV_MODULE_VERSION "2.0.0" +#define DRV_MODULE_RELDATE "Jun. 2010" + +static char version[] = + DRV_MODULE_DESC " " DRV_MODULE_NAME + " v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; + +MODULE_AUTHOR("Chelsio Communications, Inc."); +MODULE_DESCRIPTION(DRV_MODULE_DESC); +MODULE_VERSION(DRV_MODULE_VERSION); +MODULE_LICENSE("GPL"); + +module_param(dbg_level, uint, 0644); +MODULE_PARM_DESC(dbg_level, "debug flag (default=0)"); + +static int cxgb3i_rcv_win = 256 * 1024; +module_param(cxgb3i_rcv_win, int, 0644); +MODULE_PARM_DESC(cxgb3i_rcv_win, "TCP receive window in bytes (default=256KB)"); + +static int cxgb3i_snd_win = 128 * 1024; +module_param(cxgb3i_snd_win, int, 0644); +MODULE_PARM_DESC(cxgb3i_snd_win, "TCP send window in bytes (default=128KB)"); + +static int cxgb3i_rx_credit_thres = 10 * 1024; +module_param(cxgb3i_rx_credit_thres, int, 0644); +MODULE_PARM_DESC(rx_credit_thres, + "RX credits return threshold in bytes (default=10KB)"); + +static unsigned int cxgb3i_max_connect = 8 * 1024; +module_param(cxgb3i_max_connect, uint, 0644); +MODULE_PARM_DESC(cxgb3i_max_connect, "Max. # of connections (default=8092)"); + +static unsigned int cxgb3i_sport_base = 20000; +module_param(cxgb3i_sport_base, uint, 0644); +MODULE_PARM_DESC(cxgb3i_sport_base, "starting port number (default=20000)"); + +static void cxgb3i_dev_open(struct t3cdev *); +static void cxgb3i_dev_close(struct t3cdev *); +static void cxgb3i_dev_event_handler(struct t3cdev *, u32, u32); + +static struct cxgb3_client t3_client = { + .name = DRV_MODULE_NAME, + .handlers = cxgb3i_cpl_handlers, + .add = cxgb3i_dev_open, + .remove = cxgb3i_dev_close, + .event_handler = cxgb3i_dev_event_handler, +}; + +static struct scsi_host_template cxgb3i_host_template = { + .module = THIS_MODULE, + .name = DRV_MODULE_NAME, + .proc_name = DRV_MODULE_NAME, + .can_queue = CXGB3I_SCSI_HOST_QDEPTH, + .queuecommand = iscsi_queuecommand, + .change_queue_depth = iscsi_change_queue_depth, + .sg_tablesize = SG_ALL, + .max_sectors = 0xFFFF, + .cmd_per_lun = ISCSI_DEF_CMD_PER_LUN, + .eh_abort_handler = iscsi_eh_abort, + .eh_device_reset_handler = iscsi_eh_device_reset, + .eh_target_reset_handler = iscsi_eh_recover_target, + .target_alloc = iscsi_target_alloc, + .use_clustering = DISABLE_CLUSTERING, + .this_id = -1, +}; + +static struct iscsi_transport cxgb3i_iscsi_transport = { + .owner = THIS_MODULE, + .name = DRV_MODULE_NAME, + /* owner and name should be set already */ + .caps = CAP_RECOVERY_L0 | CAP_MULTI_R2T | CAP_HDRDGST + | CAP_DATADGST | CAP_DIGEST_OFFLOAD | + CAP_PADDING_OFFLOAD, + .param_mask = ISCSI_MAX_RECV_DLENGTH | ISCSI_MAX_XMIT_DLENGTH | + ISCSI_HDRDGST_EN | ISCSI_DATADGST_EN | + ISCSI_INITIAL_R2T_EN | ISCSI_MAX_R2T | + ISCSI_IMM_DATA_EN | ISCSI_FIRST_BURST | + ISCSI_MAX_BURST | ISCSI_PDU_INORDER_EN | + ISCSI_DATASEQ_INORDER_EN | ISCSI_ERL | + ISCSI_CONN_PORT | ISCSI_CONN_ADDRESS | + ISCSI_EXP_STATSN | ISCSI_PERSISTENT_PORT | + ISCSI_PERSISTENT_ADDRESS | + ISCSI_TARGET_NAME | ISCSI_TPGT | + ISCSI_USERNAME | ISCSI_PASSWORD | + ISCSI_USERNAME_IN | ISCSI_PASSWORD_IN | + ISCSI_FAST_ABORT | ISCSI_ABORT_TMO | + ISCSI_LU_RESET_TMO | ISCSI_TGT_RESET_TMO | + ISCSI_PING_TMO | ISCSI_RECV_TMO | + ISCSI_IFACE_NAME | ISCSI_INITIATOR_NAME, + .host_param_mask = ISCSI_HOST_HWADDRESS | ISCSI_HOST_IPADDRESS | + ISCSI_HOST_INITIATOR_NAME | + ISCSI_HOST_NETDEV_NAME, + .get_host_param = cxgbi_get_host_param, + .set_host_param = cxgbi_set_host_param, + /* session management */ + .create_session = cxgbi_create_session, + .destroy_session = cxgbi_destroy_session, + .get_session_param = iscsi_session_get_param, + /* connection management */ + .create_conn = cxgbi_create_conn, + .bind_conn = cxgbi_bind_conn, + .destroy_conn = iscsi_tcp_conn_teardown, + .start_conn = iscsi_conn_start, + .stop_conn = iscsi_conn_stop, + .get_conn_param = cxgbi_get_conn_param, + .set_param = cxgbi_set_conn_param, + .get_stats = cxgbi_get_conn_stats, + /* pdu xmit req from user space */ + .send_pdu = iscsi_conn_send_pdu, + /* task */ + .init_task = iscsi_tcp_task_init, + .xmit_task = iscsi_tcp_task_xmit, + .cleanup_task = cxgbi_cleanup_task, + /* pdu */ + .alloc_pdu = cxgbi_conn_alloc_pdu, + .init_pdu = cxgbi_conn_init_pdu, + .xmit_pdu = cxgbi_conn_xmit_pdu, + .parse_pdu_itt = cxgbi_parse_pdu_itt, + /* TCP connect/disconnect */ + .ep_connect = cxgbi_ep_connect, + .ep_poll = cxgbi_ep_poll, + .ep_disconnect = cxgbi_ep_disconnect, + /* Error recovery timeout call */ + .session_recovery_timedout = iscsi_session_recovery_timedout, +}; + +static struct scsi_transport_template *cxgb3i_stt; + +/* + * CPL (Chelsio Protocol Language) defines a message passing interface between + * the host driver and Chelsio asic. + * The section below implments CPLs that related to iscsi tcp connection + * open/close/abort and data send/receive. + */ + +static int push_tx_frames(struct cxgbi_sock *csk, int req_completion); + +static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb, + const struct l2t_entry *e) +{ + unsigned int wscale = cxgbi_sock_compute_wscale(cxgb3i_rcv_win); + struct cpl_act_open_req *req = (struct cpl_act_open_req *)skb->head; + + skb->priority = CPL_PRIORITY_SETUP; + + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, csk->atid)); + req->local_port = csk->saddr.sin_port; + req->peer_port = csk->daddr.sin_port; + req->local_ip = csk->saddr.sin_addr.s_addr; + req->peer_ip = csk->daddr.sin_addr.s_addr; + + req->opt0h = htonl(V_KEEP_ALIVE(1) | F_TCAM_BYPASS | + V_WND_SCALE(wscale) | V_MSS_IDX(csk->mss_idx) | + V_L2T_IDX(e->idx) | V_TX_CHANNEL(e->smt_idx)); + req->opt0l = htonl(V_ULP_MODE(ULP2_MODE_ISCSI) | + V_RCV_BUFSIZ(cxgb3i_rcv_win>>10)); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u, %pI4:%u-%pI4:%u, %u,%u,%u.\n", + csk, csk->state, csk->flags, csk->atid, + &req->local_ip, ntohs(req->local_port), + &req->peer_ip, ntohs(req->peer_port), + csk->mss_idx, e->idx, e->smt_idx); + + l2t_send(csk->cdev->lldev, skb, csk->l2t); +} + +static inline void act_open_arp_failure(struct t3cdev *dev, struct sk_buff *skb) +{ + cxgbi_sock_act_open_req_arp_failure(NULL, skb); +} + +/* + * CPL connection close request: host -> + * + * Close a connection by sending a CPL_CLOSE_CON_REQ message and queue it to + * the write queue (i.e., after any unsent txt data). + */ +static void send_close_req(struct cxgbi_sock *csk) +{ + struct sk_buff *skb = csk->cpl_close; + struct cpl_close_con_req *req = (struct cpl_close_con_req *)skb->head; + unsigned int tid = csk->tid; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + + csk->cpl_close = NULL; + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_CLOSE_CON)); + req->wr.wr_lo = htonl(V_WR_TID(tid)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_CLOSE_CON_REQ, tid)); + req->rsvd = htonl(csk->write_seq); + + cxgbi_sock_skb_entail(csk, skb); + if (csk->state >= CTP_ESTABLISHED) + push_tx_frames(csk, 1); +} + +/* + * CPL connection abort request: host -> + * + * Send an ABORT_REQ message. Makes sure we do not send multiple ABORT_REQs + * for the same connection and also that we do not try to send a message + * after the connection has closed. + */ +static void abort_arp_failure(struct t3cdev *tdev, struct sk_buff *skb) +{ + struct cpl_abort_req *req = cplhdr(skb); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "t3dev 0x%p, tid %u, skb 0x%p.\n", + tdev, GET_TID(req), skb); + req->cmd = CPL_ABORT_NO_RST; + cxgb3_ofld_send(tdev, skb); +} + +static void send_abort_req(struct cxgbi_sock *csk) +{ + struct sk_buff *skb = csk->cpl_abort_req; + struct cpl_abort_req *req; + + if (unlikely(csk->state == CTP_ABORTING || !skb)) + return; + cxgbi_sock_set_state(csk, CTP_ABORTING); + cxgbi_sock_set_flag(csk, CTPF_ABORT_RPL_PENDING); + /* Purge the send queue so we don't send anything after an abort. */ + cxgbi_sock_purge_write_queue(csk); + + csk->cpl_abort_req = NULL; + req = (struct cpl_abort_req *)skb->head; + skb->priority = CPL_PRIORITY_DATA; + set_arp_failure_handler(skb, abort_arp_failure); + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_HOST_ABORT_CON_REQ)); + req->wr.wr_lo = htonl(V_WR_TID(csk->tid)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ABORT_REQ, csk->tid)); + req->rsvd0 = htonl(csk->snd_nxt); + req->rsvd1 = !cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT); + req->cmd = CPL_ABORT_SEND_RST; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u, snd_nxt %u, 0x%x.\n", + csk, csk->state, csk->flags, csk->tid, csk->snd_nxt, + req->rsvd1); + + l2t_send(csk->cdev->lldev, skb, csk->l2t); +} + +/* + * CPL connection abort reply: host -> + * + * Send an ABORT_RPL message in response of the ABORT_REQ received. + */ +static void send_abort_rpl(struct cxgbi_sock *csk, int rst_status) +{ + struct sk_buff *skb = csk->cpl_abort_rpl; + struct cpl_abort_rpl *rpl = (struct cpl_abort_rpl *)skb->head; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u, status %d.\n", + csk, csk->state, csk->flags, csk->tid, rst_status); + + csk->cpl_abort_rpl = NULL; + skb->priority = CPL_PRIORITY_DATA; + rpl->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_HOST_ABORT_CON_RPL)); + rpl->wr.wr_lo = htonl(V_WR_TID(csk->tid)); + OPCODE_TID(rpl) = htonl(MK_OPCODE_TID(CPL_ABORT_RPL, csk->tid)); + rpl->cmd = rst_status; + cxgb3_ofld_send(csk->cdev->lldev, skb); +} + +/* + * CPL connection rx data ack: host -> + * Send RX credits through an RX_DATA_ACK CPL message. Returns the number of + * credits sent. + */ +static u32 send_rx_credits(struct cxgbi_sock *csk, u32 credits) +{ + struct sk_buff *skb; + struct cpl_rx_data_ack *req; + u32 dack = F_RX_DACK_CHANGE | V_RX_DACK_MODE(1); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX, + "csk 0x%p,%u,0x%lx,%u, credit %u, dack %u.\n", + csk, csk->state, csk->flags, csk->tid, credits, dack); + + skb = alloc_wr(sizeof(*req), 0, GFP_ATOMIC); + if (!skb) { + pr_info("csk 0x%p, credit %u, OOM.\n", csk, credits); + return 0; + } + req = (struct cpl_rx_data_ack *)skb->head; + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_RX_DATA_ACK, csk->tid)); + req->credit_dack = htonl(F_RX_DACK_CHANGE | V_RX_DACK_MODE(1) | + V_RX_CREDITS(credits)); + skb->priority = CPL_PRIORITY_ACK; + cxgb3_ofld_send(csk->cdev->lldev, skb); + return credits; +} + +/* + * CPL connection tx data: host -> + * + * Send iscsi PDU via TX_DATA CPL message. Returns the number of + * credits sent. + * Each TX_DATA consumes work request credit (wrs), so we need to keep track of + * how many we've used so far and how many are pending (i.e., yet ack'ed by T3). + */ + +static unsigned int wrlen __read_mostly; +static unsigned int skb_wrs[SKB_WR_LIST_SIZE] __read_mostly; + +static void init_wr_tab(unsigned int wr_len) +{ + int i; + + if (skb_wrs[1]) /* already initialized */ + return; + for (i = 1; i < SKB_WR_LIST_SIZE; i++) { + int sgl_len = (3 * i) / 2 + (i & 1); + + sgl_len += 3; + skb_wrs[i] = (sgl_len <= wr_len + ? 1 : 1 + (sgl_len - 2) / (wr_len - 1)); + } + wrlen = wr_len * 8; +} + +static inline void make_tx_data_wr(struct cxgbi_sock *csk, struct sk_buff *skb, + int len, int req_completion) +{ + struct tx_data_wr *req; + struct l2t_entry *l2t = csk->l2t; + + skb_reset_transport_header(skb); + req = (struct tx_data_wr *)__skb_push(skb, sizeof(*req)); + req->wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_TX_DATA) | + (req_completion ? F_WR_COMPL : 0)); + req->wr_lo = htonl(V_WR_TID(csk->tid)); + /* len includes the length of any HW ULP additions */ + req->len = htonl(len); + /* V_TX_ULP_SUBMODE sets both the mode and submode */ + req->flags = htonl(V_TX_ULP_SUBMODE(cxgbi_skcb_ulp_mode(skb)) | + V_TX_SHOVE((skb_peek(&csk->write_queue) ? 0 : 1))); + req->sndseq = htonl(csk->snd_nxt); + req->param = htonl(V_TX_PORT(l2t->smt_idx)); + + if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) { + req->flags |= htonl(V_TX_ACK_PAGES(2) | F_TX_INIT | + V_TX_CPU_IDX(csk->rss_qid)); + /* sendbuffer is in units of 32KB. */ + req->param |= htonl(V_TX_SNDBUF(cxgb3i_snd_win >> 15)); + cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT); + } +} + +/** + * push_tx_frames -- start transmit + * @c3cn: the offloaded connection + * @req_completion: request wr_ack or not + * + * Prepends TX_DATA_WR or CPL_CLOSE_CON_REQ headers to buffers waiting in a + * connection's send queue and sends them on to T3. Must be called with the + * connection's lock held. Returns the amount of send buffer space that was + * freed as a result of sending queued data to T3. + */ + +static void arp_failure_skb_discard(struct t3cdev *dev, struct sk_buff *skb) +{ + kfree_skb(skb); +} + +static int push_tx_frames(struct cxgbi_sock *csk, int req_completion) +{ + int total_size = 0; + struct sk_buff *skb; + + if (unlikely(csk->state < CTP_ESTABLISHED || + csk->state == CTP_CLOSE_WAIT_1 || csk->state >= CTP_ABORTING)) { + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_TX, + "csk 0x%p,%u,0x%lx,%u, in closing state.\n", + csk, csk->state, csk->flags, csk->tid); + return 0; + } + + while (csk->wr_cred && (skb = skb_peek(&csk->write_queue)) != NULL) { + int len = skb->len; /* length before skb_push */ + int frags = skb_shinfo(skb)->nr_frags + (len != skb->data_len); + int wrs_needed = skb_wrs[frags]; + + if (wrs_needed > 1 && len + sizeof(struct tx_data_wr) <= wrlen) + wrs_needed = 1; + + WARN_ON(frags >= SKB_WR_LIST_SIZE || wrs_needed < 1); + + if (csk->wr_cred < wrs_needed) { + log_debug(1 << CXGBI_DBG_PDU_TX, + "csk 0x%p, skb len %u/%u, frag %u, wr %d<%u.\n", + csk, skb->len, skb->data_len, frags, + wrs_needed, csk->wr_cred); + break; + } + + __skb_unlink(skb, &csk->write_queue); + skb->priority = CPL_PRIORITY_DATA; + skb->csum = wrs_needed; /* remember this until the WR_ACK */ + csk->wr_cred -= wrs_needed; + csk->wr_una_cred += wrs_needed; + cxgbi_sock_enqueue_wr(csk, skb); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_TX, + "csk 0x%p, enqueue, skb len %u/%u, frag %u, wr %d, " + "left %u, unack %u.\n", + csk, skb->len, skb->data_len, frags, skb->csum, + csk->wr_cred, csk->wr_una_cred); + + if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR))) { + if ((req_completion && + csk->wr_una_cred == wrs_needed) || + csk->wr_una_cred >= csk->wr_max_cred / 2) { + req_completion = 1; + csk->wr_una_cred = 0; + } + len += cxgbi_ulp_extra_len(cxgbi_skcb_ulp_mode(skb)); + make_tx_data_wr(csk, skb, len, req_completion); + csk->snd_nxt += len; + cxgbi_skcb_clear_flag(skb, SKCBF_TX_NEED_HDR); + } + total_size += skb->truesize; + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_TX, + "csk 0x%p, tid 0x%x, send skb 0x%p.\n", + csk, csk->tid, skb); + set_arp_failure_handler(skb, arp_failure_skb_discard); + l2t_send(csk->cdev->lldev, skb, csk->l2t); + } + return total_size; +} + +/* + * Process a CPL_ACT_ESTABLISH message: -> host + * Updates connection state from an active establish CPL message. Runs with + * the connection lock held. + */ + +static inline void free_atid(struct cxgbi_sock *csk) +{ + if (cxgbi_sock_flag(csk, CTPF_HAS_ATID)) { + cxgb3_free_atid(csk->cdev->lldev, csk->atid); + cxgbi_sock_clear_flag(csk, CTPF_HAS_ATID); + cxgbi_sock_put(csk); + } +} + +static int do_act_establish(struct t3cdev *tdev, struct sk_buff *skb, void *ctx) +{ + struct cxgbi_sock *csk = ctx; + struct cpl_act_establish *req = cplhdr(skb); + unsigned int tid = GET_TID(req); + unsigned int atid = G_PASS_OPEN_TID(ntohl(req->tos_tid)); + u32 rcv_isn = ntohl(req->rcv_isn); /* real RCV_ISN + 1 */ + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "atid 0x%x,tid 0x%x, csk 0x%p,%u,0x%lx, isn %u.\n", + atid, atid, csk, csk->state, csk->flags, rcv_isn); + + cxgbi_sock_get(csk); + cxgbi_sock_set_flag(csk, CTPF_HAS_TID); + csk->tid = tid; + cxgb3_insert_tid(csk->cdev->lldev, &t3_client, csk, tid); + + free_atid(csk); + + csk->rss_qid = G_QNUM(ntohs(skb->csum)); + + spin_lock_bh(&csk->lock); + if (csk->retry_timer.function) { + del_timer(&csk->retry_timer); + csk->retry_timer.function = NULL; + } + + if (unlikely(csk->state != CTP_ACTIVE_OPEN)) + pr_info("csk 0x%p,%u,0x%lx,%u, got EST.\n", + csk, csk->state, csk->flags, csk->tid); + + csk->copied_seq = csk->rcv_wup = csk->rcv_nxt = rcv_isn; + if (cxgb3i_rcv_win > (M_RCV_BUFSIZ << 10)) + csk->rcv_wup -= cxgb3i_rcv_win - (M_RCV_BUFSIZ << 10); + + cxgbi_sock_established(csk, ntohl(req->snd_isn), ntohs(req->tcp_opt)); + + if (unlikely(cxgbi_sock_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED))) + /* upper layer has requested closing */ + send_abort_req(csk); + else { + if (skb_queue_len(&csk->write_queue)) + push_tx_frames(csk, 1); + cxgbi_conn_tx_open(csk); + } + + spin_unlock_bh(&csk->lock); + __kfree_skb(skb); + return 0; +} + +/* + * Process a CPL_ACT_OPEN_RPL message: -> host + * Handle active open failures. + */ +static int act_open_rpl_status_to_errno(int status) +{ + switch (status) { + case CPL_ERR_CONN_RESET: + return -ECONNREFUSED; + case CPL_ERR_ARP_MISS: + return -EHOSTUNREACH; + case CPL_ERR_CONN_TIMEDOUT: + return -ETIMEDOUT; + case CPL_ERR_TCAM_FULL: + return -ENOMEM; + case CPL_ERR_CONN_EXIST: + return -EADDRINUSE; + default: + return -EIO; + } +} + +static void act_open_retry_timer(unsigned long data) +{ + struct sk_buff *skb; + struct cxgbi_sock *csk = (struct cxgbi_sock *)data; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + + cxgbi_sock_get(csk); + spin_lock_bh(&csk->lock); + skb = alloc_wr(sizeof(struct cpl_act_open_req), 0, GFP_ATOMIC); + if (!skb) + cxgbi_sock_fail_act_open(csk, -ENOMEM); + else { + skb->sk = (struct sock *)csk; + set_arp_failure_handler(skb, act_open_arp_failure); + send_act_open_req(csk, skb, csk->l2t); + } + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); +} + +static int do_act_open_rpl(struct t3cdev *tdev, struct sk_buff *skb, void *ctx) +{ + struct cxgbi_sock *csk = ctx; + struct cpl_act_open_rpl *rpl = cplhdr(skb); + + pr_info("csk 0x%p,%u,0x%lx,%u, status %u, %pI4:%u-%pI4:%u.\n", + csk, csk->state, csk->flags, csk->atid, rpl->status, + &csk->saddr.sin_addr.s_addr, ntohs(csk->saddr.sin_port), + &csk->daddr.sin_addr.s_addr, ntohs(csk->daddr.sin_port)); + + if (rpl->status != CPL_ERR_TCAM_FULL && + rpl->status != CPL_ERR_CONN_EXIST && + rpl->status != CPL_ERR_ARP_MISS) + cxgb3_queue_tid_release(tdev, GET_TID(rpl)); + + cxgbi_sock_get(csk); + spin_lock_bh(&csk->lock); + if (rpl->status == CPL_ERR_CONN_EXIST && + csk->retry_timer.function != act_open_retry_timer) { + csk->retry_timer.function = act_open_retry_timer; + mod_timer(&csk->retry_timer, jiffies + HZ / 2); + } else + cxgbi_sock_fail_act_open(csk, + act_open_rpl_status_to_errno(rpl->status)); + + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); + __kfree_skb(skb); + return 0; +} + +/* + * Process PEER_CLOSE CPL messages: -> host + * Handle peer FIN. + */ +static int do_peer_close(struct t3cdev *cdev, struct sk_buff *skb, void *ctx) +{ + struct cxgbi_sock *csk = ctx; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + + cxgbi_sock_rcv_peer_close(csk); + __kfree_skb(skb); + return 0; +} + +/* + * Process CLOSE_CONN_RPL CPL message: -> host + * Process a peer ACK to our FIN. + */ +static int do_close_con_rpl(struct t3cdev *cdev, struct sk_buff *skb, + void *ctx) +{ + struct cxgbi_sock *csk = ctx; + struct cpl_close_con_rpl *rpl = cplhdr(skb); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u, snxt %u.\n", + csk, csk->state, csk->flags, csk->tid, ntohl(rpl->snd_nxt)); + + cxgbi_sock_rcv_close_conn_rpl(csk, ntohl(rpl->snd_nxt)); + __kfree_skb(skb); + return 0; +} + +/* + * Process ABORT_REQ_RSS CPL message: -> host + * Process abort requests. If we are waiting for an ABORT_RPL we ignore this + * request except that we need to reply to it. + */ + +static int abort_status_to_errno(struct cxgbi_sock *csk, int abort_reason, + int *need_rst) +{ + switch (abort_reason) { + case CPL_ERR_BAD_SYN: /* fall through */ + case CPL_ERR_CONN_RESET: + return csk->state > CTP_ESTABLISHED ? -EPIPE : -ECONNRESET; + case CPL_ERR_XMIT_TIMEDOUT: + case CPL_ERR_PERSIST_TIMEDOUT: + case CPL_ERR_FINWAIT2_TIMEDOUT: + case CPL_ERR_KEEPALIVE_TIMEDOUT: + return -ETIMEDOUT; + default: + return -EIO; + } +} + +static int do_abort_req(struct t3cdev *cdev, struct sk_buff *skb, void *ctx) +{ + const struct cpl_abort_req_rss *req = cplhdr(skb); + struct cxgbi_sock *csk = ctx; + int rst_status = CPL_ABORT_NO_RST; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + + if (req->status == CPL_ERR_RTX_NEG_ADVICE || + req->status == CPL_ERR_PERSIST_NEG_ADVICE) { + goto done; + } + + cxgbi_sock_get(csk); + spin_lock_bh(&csk->lock); + + if (!cxgbi_sock_flag(csk, CTPF_ABORT_REQ_RCVD)) { + cxgbi_sock_set_flag(csk, CTPF_ABORT_REQ_RCVD); + cxgbi_sock_set_state(csk, CTP_ABORTING); + goto out; + } + + cxgbi_sock_clear_flag(csk, CTPF_ABORT_REQ_RCVD); + send_abort_rpl(csk, rst_status); + + if (!cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING)) { + csk->err = abort_status_to_errno(csk, req->status, &rst_status); + cxgbi_sock_closed(csk); + } + +out: + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); +done: + __kfree_skb(skb); + return 0; +} + +/* + * Process ABORT_RPL_RSS CPL message: -> host + * Process abort replies. We only process these messages if we anticipate + * them as the coordination between SW and HW in this area is somewhat lacking + * and sometimes we get ABORT_RPLs after we are done with the connection that + * originated the ABORT_REQ. + */ +static int do_abort_rpl(struct t3cdev *cdev, struct sk_buff *skb, void *ctx) +{ + struct cpl_abort_rpl_rss *rpl = cplhdr(skb); + struct cxgbi_sock *csk = ctx; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "status 0x%x, csk 0x%p, s %u, 0x%lx.\n", + rpl->status, csk, csk ? csk->state : 0, + csk ? csk->flags : 0UL); + /* + * Ignore replies to post-close aborts indicating that the abort was + * requested too late. These connections are terminated when we get + * PEER_CLOSE or CLOSE_CON_RPL and by the time the abort_rpl_rss + * arrives the TID is either no longer used or it has been recycled. + */ + if (rpl->status == CPL_ERR_ABORT_FAILED) + goto rel_skb; + /* + * Sometimes we've already closed the connection, e.g., a post-close + * abort races with ABORT_REQ_RSS, the latter frees the connection + * expecting the ABORT_REQ will fail with CPL_ERR_ABORT_FAILED, + * but FW turns the ABORT_REQ into a regular one and so we get + * ABORT_RPL_RSS with status 0 and no connection. + */ + if (csk) + cxgbi_sock_rcv_abort_rpl(csk); +rel_skb: + __kfree_skb(skb); + return 0; +} + +/* + * Process RX_ISCSI_HDR CPL message: -> host + * Handle received PDUs, the payload could be DDP'ed. If not, the payload + * follow after the bhs. + */ +static int do_iscsi_hdr(struct t3cdev *t3dev, struct sk_buff *skb, void *ctx) +{ + struct cxgbi_sock *csk = ctx; + struct cpl_iscsi_hdr *hdr_cpl = cplhdr(skb); + struct cpl_iscsi_hdr_norss data_cpl; + struct cpl_rx_data_ddp_norss ddp_cpl; + unsigned int hdr_len, data_len, status; + unsigned int len; + int err; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX, + "csk 0x%p,%u,0x%lx,%u, skb 0x%p,%u.\n", + csk, csk->state, csk->flags, csk->tid, skb, skb->len); + + spin_lock_bh(&csk->lock); + + if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) { + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u, bad state.\n", + csk, csk->state, csk->flags, csk->tid); + if (csk->state != CTP_ABORTING) + goto abort_conn; + else + goto discard; + } + + cxgbi_skcb_tcp_seq(skb) = ntohl(hdr_cpl->seq); + cxgbi_skcb_flags(skb) = 0; + + skb_reset_transport_header(skb); + __skb_pull(skb, sizeof(struct cpl_iscsi_hdr)); + + len = hdr_len = ntohs(hdr_cpl->len); + /* msg coalesce is off or not enough data received */ + if (skb->len <= hdr_len) { + pr_err("%s: tid %u, CPL_ISCSI_HDR, skb len %u < %u.\n", + csk->cdev->ports[csk->port_id]->name, csk->tid, + skb->len, hdr_len); + goto abort_conn; + } + cxgbi_skcb_set_flag(skb, SKCBF_RX_COALESCED); + + err = skb_copy_bits(skb, skb->len - sizeof(ddp_cpl), &ddp_cpl, + sizeof(ddp_cpl)); + if (err < 0) { + pr_err("%s: tid %u, copy cpl_ddp %u-%zu failed %d.\n", + csk->cdev->ports[csk->port_id]->name, csk->tid, + skb->len, sizeof(ddp_cpl), err); + goto abort_conn; + } + + cxgbi_skcb_set_flag(skb, SKCBF_RX_STATUS); + cxgbi_skcb_rx_pdulen(skb) = ntohs(ddp_cpl.len); + cxgbi_skcb_rx_ddigest(skb) = ntohl(ddp_cpl.ulp_crc); + status = ntohl(ddp_cpl.ddp_status); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX, + "csk 0x%p, skb 0x%p,%u, pdulen %u, status 0x%x.\n", + csk, skb, skb->len, cxgbi_skcb_rx_pdulen(skb), status); + + if (status & (1 << CPL_RX_DDP_STATUS_HCRC_SHIFT)) + cxgbi_skcb_set_flag(skb, SKCBF_RX_HCRC_ERR); + if (status & (1 << CPL_RX_DDP_STATUS_DCRC_SHIFT)) + cxgbi_skcb_set_flag(skb, SKCBF_RX_DCRC_ERR); + if (status & (1 << CPL_RX_DDP_STATUS_PAD_SHIFT)) + cxgbi_skcb_set_flag(skb, SKCBF_RX_PAD_ERR); + + if (skb->len > (hdr_len + sizeof(ddp_cpl))) { + err = skb_copy_bits(skb, hdr_len, &data_cpl, sizeof(data_cpl)); + if (err < 0) { + pr_err("%s: tid %u, cp %zu/%u failed %d.\n", + csk->cdev->ports[csk->port_id]->name, + csk->tid, sizeof(data_cpl), skb->len, err); + goto abort_conn; + } + data_len = ntohs(data_cpl.len); + log_debug(1 << CXGBI_DBG_DDP | 1 << CXGBI_DBG_PDU_RX, + "skb 0x%p, pdu not ddp'ed %u/%u, status 0x%x.\n", + skb, data_len, cxgbi_skcb_rx_pdulen(skb), status); + len += sizeof(data_cpl) + data_len; + } else if (status & (1 << CPL_RX_DDP_STATUS_DDP_SHIFT)) + cxgbi_skcb_set_flag(skb, SKCBF_RX_DATA_DDPD); + + csk->rcv_nxt = ntohl(ddp_cpl.seq) + cxgbi_skcb_rx_pdulen(skb); + __pskb_trim(skb, len); + __skb_queue_tail(&csk->receive_queue, skb); + cxgbi_conn_pdu_ready(csk); + + spin_unlock_bh(&csk->lock); + return 0; + +abort_conn: + send_abort_req(csk); +discard: + spin_unlock_bh(&csk->lock); + __kfree_skb(skb); + return 0; +} + +/* + * Process TX_DATA_ACK CPL messages: -> host + * Process an acknowledgment of WR completion. Advance snd_una and send the + * next batch of work requests from the write queue. + */ +static int do_wr_ack(struct t3cdev *cdev, struct sk_buff *skb, void *ctx) +{ + struct cxgbi_sock *csk = ctx; + struct cpl_wr_ack *hdr = cplhdr(skb); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX, + "csk 0x%p,%u,0x%lx,%u, cr %u.\n", + csk, csk->state, csk->flags, csk->tid, ntohs(hdr->credits)); + + cxgbi_sock_rcv_wr_ack(csk, ntohs(hdr->credits), ntohl(hdr->snd_una), 1); + __kfree_skb(skb); + return 0; +} + +/* + * for each connection, pre-allocate skbs needed for close/abort requests. So + * that we can service the request right away. + */ +static int alloc_cpls(struct cxgbi_sock *csk) +{ + csk->cpl_close = alloc_wr(sizeof(struct cpl_close_con_req), 0, + GFP_KERNEL); + if (!csk->cpl_close) + return -ENOMEM; + csk->cpl_abort_req = alloc_wr(sizeof(struct cpl_abort_req), 0, + GFP_KERNEL); + if (!csk->cpl_abort_req) + goto free_cpl_skbs; + + csk->cpl_abort_rpl = alloc_wr(sizeof(struct cpl_abort_rpl), 0, + GFP_KERNEL); + if (!csk->cpl_abort_rpl) + goto free_cpl_skbs; + + return 0; + +free_cpl_skbs: + cxgbi_sock_free_cpl_skbs(csk); + return -ENOMEM; +} + +/** + * release_offload_resources - release offload resource + * @c3cn: the offloaded iscsi tcp connection. + * Release resources held by an offload connection (TID, L2T entry, etc.) + */ +static void l2t_put(struct cxgbi_sock *csk) +{ + struct t3cdev *t3dev = (struct t3cdev *)csk->cdev->lldev; + + if (csk->l2t) { + l2t_release(L2DATA(t3dev), csk->l2t); + csk->l2t = NULL; + cxgbi_sock_put(csk); + } +} + +static void release_offload_resources(struct cxgbi_sock *csk) +{ + struct t3cdev *t3dev = (struct t3cdev *)csk->cdev->lldev; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + + csk->rss_qid = 0; + cxgbi_sock_free_cpl_skbs(csk); + + if (csk->wr_cred != csk->wr_max_cred) { + cxgbi_sock_purge_wr_queue(csk); + cxgbi_sock_reset_wr_list(csk); + } + l2t_put(csk); + if (cxgbi_sock_flag(csk, CTPF_HAS_ATID)) + free_atid(csk); + else if (cxgbi_sock_flag(csk, CTPF_HAS_TID)) { + cxgb3_remove_tid(t3dev, (void *)csk, csk->tid); + cxgbi_sock_clear_flag(csk, CTPF_HAS_TID); + cxgbi_sock_put(csk); + } + csk->dst = NULL; + csk->cdev = NULL; +} + +static void update_address(struct cxgbi_hba *chba) +{ + if (chba->ipv4addr) { + if (chba->vdev && + chba->ipv4addr != cxgb3i_get_private_ipv4addr(chba->vdev)) { + cxgb3i_set_private_ipv4addr(chba->vdev, chba->ipv4addr); + cxgb3i_set_private_ipv4addr(chba->ndev, 0); + pr_info("%s set %pI4.\n", + chba->vdev->name, &chba->ipv4addr); + } else if (chba->ipv4addr != + cxgb3i_get_private_ipv4addr(chba->ndev)) { + cxgb3i_set_private_ipv4addr(chba->ndev, chba->ipv4addr); + pr_info("%s set %pI4.\n", + chba->ndev->name, &chba->ipv4addr); + } + } else if (cxgb3i_get_private_ipv4addr(chba->ndev)) { + if (chba->vdev) + cxgb3i_set_private_ipv4addr(chba->vdev, 0); + cxgb3i_set_private_ipv4addr(chba->ndev, 0); + } +} + +static int init_act_open(struct cxgbi_sock *csk) +{ + struct dst_entry *dst = csk->dst; + struct cxgbi_device *cdev = csk->cdev; + struct t3cdev *t3dev = (struct t3cdev *)cdev->lldev; + struct net_device *ndev = cdev->ports[csk->port_id]; + struct cxgbi_hba *chba = cdev->hbas[csk->port_id]; + struct sk_buff *skb = NULL; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx.\n", csk, csk->state, csk->flags); + + update_address(chba); + if (chba->ipv4addr) + csk->saddr.sin_addr.s_addr = chba->ipv4addr; + + csk->rss_qid = 0; + csk->l2t = t3_l2t_get(t3dev, dst->neighbour, ndev); + if (!csk->l2t) { + pr_err("NO l2t available.\n"); + return -EINVAL; + } + cxgbi_sock_get(csk); + + csk->atid = cxgb3_alloc_atid(t3dev, &t3_client, csk); + if (csk->atid < 0) { + pr_err("NO atid available.\n"); + goto rel_resource; + } + cxgbi_sock_set_flag(csk, CTPF_HAS_ATID); + cxgbi_sock_get(csk); + + skb = alloc_wr(sizeof(struct cpl_act_open_req), 0, GFP_KERNEL); + if (!skb) + goto rel_resource; + skb->sk = (struct sock *)csk; + set_arp_failure_handler(skb, act_open_arp_failure); + + csk->wr_max_cred = csk->wr_cred = T3C_DATA(t3dev)->max_wrs - 1; + csk->wr_una_cred = 0; + csk->mss_idx = cxgbi_sock_select_mss(csk, dst_mtu(dst)); + cxgbi_sock_reset_wr_list(csk); + csk->err = 0; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx, %pI4:%u-%pI4:%u.\n", + csk, csk->state, csk->flags, + &csk->saddr.sin_addr.s_addr, ntohs(csk->saddr.sin_port), + &csk->daddr.sin_addr.s_addr, ntohs(csk->daddr.sin_port)); + + cxgbi_sock_set_state(csk, CTP_ACTIVE_OPEN); + send_act_open_req(csk, skb, csk->l2t); + return 0; + +rel_resource: + if (skb) + __kfree_skb(skb); + return -EINVAL; +} + +cxgb3_cpl_handler_func cxgb3i_cpl_handlers[NUM_CPL_CMDS] = { + [CPL_ACT_ESTABLISH] = do_act_establish, + [CPL_ACT_OPEN_RPL] = do_act_open_rpl, + [CPL_PEER_CLOSE] = do_peer_close, + [CPL_ABORT_REQ_RSS] = do_abort_req, + [CPL_ABORT_RPL_RSS] = do_abort_rpl, + [CPL_CLOSE_CON_RPL] = do_close_con_rpl, + [CPL_TX_DMA_ACK] = do_wr_ack, + [CPL_ISCSI_HDR] = do_iscsi_hdr, +}; + +/** + * cxgb3i_ofld_init - allocate and initialize resources for each adapter found + * @cdev: cxgbi adapter + */ +int cxgb3i_ofld_init(struct cxgbi_device *cdev) +{ + struct t3cdev *t3dev = (struct t3cdev *)cdev->lldev; + struct adap_ports port; + struct ofld_page_info rx_page_info; + unsigned int wr_len; + int rc; + + if (t3dev->ctl(t3dev, GET_WR_LEN, &wr_len) < 0 || + t3dev->ctl(t3dev, GET_PORTS, &port) < 0 || + t3dev->ctl(t3dev, GET_RX_PAGE_INFO, &rx_page_info) < 0) { + pr_warn("t3 0x%p, offload up, ioctl failed.\n", t3dev); + return -EINVAL; + } + + if (cxgb3i_max_connect > CXGBI_MAX_CONN) + cxgb3i_max_connect = CXGBI_MAX_CONN; + + rc = cxgbi_device_portmap_create(cdev, cxgb3i_sport_base, + cxgb3i_max_connect); + if (rc < 0) + return rc; + + init_wr_tab(wr_len); + cdev->csk_release_offload_resources = release_offload_resources; + cdev->csk_push_tx_frames = push_tx_frames; + cdev->csk_send_abort_req = send_abort_req; + cdev->csk_send_close_req = send_close_req; + cdev->csk_send_rx_credits = send_rx_credits; + cdev->csk_alloc_cpls = alloc_cpls; + cdev->csk_init_act_open = init_act_open; + + pr_info("cdev 0x%p, offload up, added.\n", cdev); + return 0; +} + +/* + * functions to program the pagepod in h/w + */ +static inline void ulp_mem_io_set_hdr(struct sk_buff *skb, unsigned int addr) +{ + struct ulp_mem_io *req = (struct ulp_mem_io *)skb->head; + + memset(req, 0, sizeof(*req)); + + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_BYPASS)); + req->cmd_lock_addr = htonl(V_ULP_MEMIO_ADDR(addr >> 5) | + V_ULPTX_CMD(ULP_MEM_WRITE)); + req->len = htonl(V_ULP_MEMIO_DATA_LEN(PPOD_SIZE >> 5) | + V_ULPTX_NFLITS((PPOD_SIZE >> 3) + 1)); +} + +static int ddp_set_map(struct cxgbi_sock *csk, struct cxgbi_pagepod_hdr *hdr, + unsigned int idx, unsigned int npods, + struct cxgbi_gather_list *gl) +{ + struct cxgbi_device *cdev = csk->cdev; + struct cxgbi_ddp_info *ddp = cdev->ddp; + unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ddp->llimit; + int i; + + log_debug(1 << CXGBI_DBG_DDP, + "csk 0x%p, idx %u, npods %u, gl 0x%p.\n", + csk, idx, npods, gl); + + for (i = 0; i < npods; i++, idx++, pm_addr += PPOD_SIZE) { + struct sk_buff *skb = ddp->gl_skb[idx]; + + /* hold on to the skb until we clear the ddp mapping */ + skb_get(skb); + + ulp_mem_io_set_hdr(skb, pm_addr); + cxgbi_ddp_ppod_set((struct cxgbi_pagepod *)(skb->head + + sizeof(struct ulp_mem_io)), + hdr, gl, i * PPOD_PAGES_MAX); + skb->priority = CPL_PRIORITY_CONTROL; + cxgb3_ofld_send(cdev->lldev, skb); + } + return 0; +} + +static void ddp_clear_map(struct cxgbi_hba *chba, unsigned int tag, + unsigned int idx, unsigned int npods) +{ + struct cxgbi_device *cdev = chba->cdev; + struct cxgbi_ddp_info *ddp = cdev->ddp; + unsigned int pm_addr = (idx << PPOD_SIZE_SHIFT) + ddp->llimit; + int i; + + log_debug(1 << CXGBI_DBG_DDP, + "cdev 0x%p, idx %u, npods %u, tag 0x%x.\n", + cdev, idx, npods, tag); + + for (i = 0; i < npods; i++, idx++, pm_addr += PPOD_SIZE) { + struct sk_buff *skb = ddp->gl_skb[idx]; + + if (!skb) { + pr_err("tag 0x%x, 0x%x, %d/%u, skb NULL.\n", + tag, idx, i, npods); + continue; + } + ddp->gl_skb[idx] = NULL; + memset(skb->head + sizeof(struct ulp_mem_io), 0, PPOD_SIZE); + ulp_mem_io_set_hdr(skb, pm_addr); + skb->priority = CPL_PRIORITY_CONTROL; + cxgb3_ofld_send(cdev->lldev, skb); + } +} + +static void ddp_free_gl_skb(struct cxgbi_ddp_info *ddp, int idx, int cnt) +{ + int i; + + log_debug(1 << CXGBI_DBG_DDP, + "ddp 0x%p, idx %d, cnt %d.\n", ddp, idx, cnt); + + for (i = 0; i < cnt; i++, idx++) + if (ddp->gl_skb[idx]) { + kfree_skb(ddp->gl_skb[idx]); + ddp->gl_skb[idx] = NULL; + } +} + +static int ddp_alloc_gl_skb(struct cxgbi_ddp_info *ddp, int idx, + int cnt, gfp_t gfp) +{ + int i; + + log_debug(1 << CXGBI_DBG_DDP, + "ddp 0x%p, idx %d, cnt %d.\n", ddp, idx, cnt); + + for (i = 0; i < cnt; i++) { + struct sk_buff *skb = alloc_wr(sizeof(struct ulp_mem_io) + + PPOD_SIZE, 0, gfp); + if (skb) + ddp->gl_skb[idx + i] = skb; + else { + ddp_free_gl_skb(ddp, idx, i); + return -ENOMEM; + } + } + return 0; +} + +static int ddp_setup_conn_pgidx(struct cxgbi_sock *csk, + unsigned int tid, int pg_idx, bool reply) +{ + struct sk_buff *skb = alloc_wr(sizeof(struct cpl_set_tcb_field), 0, + GFP_KERNEL); + struct cpl_set_tcb_field *req; + u64 val = pg_idx < DDP_PGIDX_MAX ? pg_idx : 0; + + log_debug(1 << CXGBI_DBG_DDP, + "csk 0x%p, tid %u, pg_idx %d.\n", csk, tid, pg_idx); + if (!skb) + return -ENOMEM; + + /* set up ulp submode and page size */ + req = (struct cpl_set_tcb_field *)skb->head; + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, tid)); + req->reply = V_NO_REPLY(reply ? 0 : 1); + req->cpu_idx = 0; + req->word = htons(31); + req->mask = cpu_to_be64(0xF0000000); + req->val = cpu_to_be64(val << 28); + skb->priority = CPL_PRIORITY_CONTROL; + + cxgb3_ofld_send(csk->cdev->lldev, skb); + return 0; +} + +/** + * cxgb3i_setup_conn_digest - setup conn. digest setting + * @csk: cxgb tcp socket + * @tid: connection id + * @hcrc: header digest enabled + * @dcrc: data digest enabled + * @reply: request reply from h/w + * set up the iscsi digest settings for a connection identified by tid + */ +static int ddp_setup_conn_digest(struct cxgbi_sock *csk, unsigned int tid, + int hcrc, int dcrc, int reply) +{ + struct sk_buff *skb = alloc_wr(sizeof(struct cpl_set_tcb_field), 0, + GFP_KERNEL); + struct cpl_set_tcb_field *req; + u64 val = (hcrc ? 1 : 0) | (dcrc ? 2 : 0); + + log_debug(1 << CXGBI_DBG_DDP, + "csk 0x%p, tid %u, crc %d,%d.\n", csk, tid, hcrc, dcrc); + if (!skb) + return -ENOMEM; + + /* set up ulp submode and page size */ + req = (struct cpl_set_tcb_field *)skb->head; + req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD)); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, tid)); + req->reply = V_NO_REPLY(reply ? 0 : 1); + req->cpu_idx = 0; + req->word = htons(31); + req->mask = cpu_to_be64(0x0F000000); + req->val = cpu_to_be64(val << 24); + skb->priority = CPL_PRIORITY_CONTROL; + + cxgb3_ofld_send(csk->cdev->lldev, skb); + return 0; +} + +/** + * t3_ddp_cleanup - release the cxgb3 adapter's ddp resource + * @cdev: cxgb3i adapter + * release all the resource held by the ddp pagepod manager for a given + * adapter if needed + */ + +static void t3_ddp_cleanup(struct cxgbi_device *cdev) +{ + struct t3cdev *tdev = (struct t3cdev *)cdev->lldev; + + if (cxgbi_ddp_cleanup(cdev)) { + pr_info("t3dev 0x%p, ulp_iscsi no more user.\n", tdev); + tdev->ulp_iscsi = NULL; + } +} + +/** + * ddp_init - initialize the cxgb3 adapter's ddp resource + * @cdev: cxgb3i adapter + * initialize the ddp pagepod manager for a given adapter + */ +static int cxgb3i_ddp_init(struct cxgbi_device *cdev) +{ + struct t3cdev *tdev = (struct t3cdev *)cdev->lldev; + struct cxgbi_ddp_info *ddp = tdev->ulp_iscsi; + struct ulp_iscsi_info uinfo; + unsigned int pgsz_factor[4]; + int err; + + if (ddp) { + kref_get(&ddp->refcnt); + pr_warn("t3dev 0x%p, ddp 0x%p already set up.\n", + tdev, tdev->ulp_iscsi); + cdev->ddp = ddp; + return -EALREADY; + } + + err = tdev->ctl(tdev, ULP_ISCSI_GET_PARAMS, &uinfo); + if (err < 0) { + pr_err("%s, failed to get iscsi param err=%d.\n", + tdev->name, err); + return err; + } + + err = cxgbi_ddp_init(cdev, uinfo.llimit, uinfo.ulimit, + uinfo.max_txsz, uinfo.max_rxsz); + if (err < 0) + return err; + + ddp = cdev->ddp; + + uinfo.tagmask = ddp->idx_mask << PPOD_IDX_SHIFT; + cxgbi_ddp_page_size_factor(pgsz_factor); + uinfo.ulimit = uinfo.llimit + (ddp->nppods << PPOD_SIZE_SHIFT); + + err = tdev->ctl(tdev, ULP_ISCSI_SET_PARAMS, &uinfo); + if (err < 0) { + pr_warn("%s unable to set iscsi param err=%d, ddp disabled.\n", + tdev->name, err); + cxgbi_ddp_cleanup(cdev); + return err; + } + tdev->ulp_iscsi = ddp; + + cdev->csk_ddp_free_gl_skb = ddp_free_gl_skb; + cdev->csk_ddp_alloc_gl_skb = ddp_alloc_gl_skb; + cdev->csk_ddp_setup_digest = ddp_setup_conn_digest; + cdev->csk_ddp_setup_pgidx = ddp_setup_conn_pgidx; + cdev->csk_ddp_set = ddp_set_map; + cdev->csk_ddp_clear = ddp_clear_map; + + pr_info("tdev 0x%p, nppods %u, bits %u, mask 0x%x,0x%x pkt %u/%u, " + "%u/%u.\n", + tdev, ddp->nppods, ddp->idx_bits, ddp->idx_mask, + ddp->rsvd_tag_mask, ddp->max_txsz, uinfo.max_txsz, + ddp->max_rxsz, uinfo.max_rxsz); + return 0; +} + +static void cxgb3i_dev_close(struct t3cdev *t3dev) +{ + struct cxgbi_device *cdev = cxgbi_device_find_by_lldev(t3dev); + + if (!cdev || cdev->flags & CXGBI_FLAG_ADAPTER_RESET) { + pr_info("0x%p close, f 0x%x.\n", cdev, cdev ? cdev->flags : 0); + return; + } + + cxgbi_device_unregister(cdev); +} + +/** + * cxgb3i_dev_open - init a t3 adapter structure and any h/w settings + * @t3dev: t3cdev adapter + */ +static void cxgb3i_dev_open(struct t3cdev *t3dev) +{ + struct cxgbi_device *cdev = cxgbi_device_find_by_lldev(t3dev); + struct adapter *adapter = tdev2adap(t3dev); + int i, err; + + if (cdev) { + pr_info("0x%p, updating.\n", cdev); + return; + } + + cdev = cxgbi_device_register(0, adapter->params.nports); + if (!cdev) { + pr_warn("device 0x%p register failed.\n", t3dev); + return; + } + + cdev->flags = CXGBI_FLAG_DEV_T3 | CXGBI_FLAG_IPV4_SET; + cdev->lldev = t3dev; + cdev->pdev = adapter->pdev; + cdev->ports = adapter->port; + cdev->nports = adapter->params.nports; + cdev->mtus = adapter->params.mtus; + cdev->nmtus = NMTUS; + cdev->snd_win = cxgb3i_snd_win; + cdev->rcv_win = cxgb3i_rcv_win; + cdev->rx_credit_thres = cxgb3i_rx_credit_thres; + cdev->skb_tx_rsvd = CXGB3I_TX_HEADER_LEN; + cdev->skb_rx_extra = sizeof(struct cpl_iscsi_hdr_norss); + cdev->dev_ddp_cleanup = t3_ddp_cleanup; + cdev->itp = &cxgb3i_iscsi_transport; + + err = cxgb3i_ddp_init(cdev); + if (err) { + pr_info("0x%p ddp init failed\n", cdev); + goto err_out; + } + + err = cxgb3i_ofld_init(cdev); + if (err) { + pr_info("0x%p offload init failed\n", cdev); + goto err_out; + } + + err = cxgbi_hbas_add(cdev, CXGB3I_MAX_LUN, CXGBI_MAX_CONN, + &cxgb3i_host_template, cxgb3i_stt); + if (err) + goto err_out; + + for (i = 0; i < cdev->nports; i++) + cdev->hbas[i]->ipv4addr = + cxgb3i_get_private_ipv4addr(cdev->ports[i]); + + pr_info("cdev 0x%p, f 0x%x, t3dev 0x%p open, err %d.\n", + cdev, cdev ? cdev->flags : 0, t3dev, err); + return; + +err_out: + cxgbi_device_unregister(cdev); +} + +static void cxgb3i_dev_event_handler(struct t3cdev *t3dev, u32 event, u32 port) +{ + struct cxgbi_device *cdev = cxgbi_device_find_by_lldev(t3dev); + + log_debug(1 << CXGBI_DBG_TOE, + "0x%p, cdev 0x%p, event 0x%x, port 0x%x.\n", + t3dev, cdev, event, port); + if (!cdev) + return; + + switch (event) { + case OFFLOAD_STATUS_DOWN: + cdev->flags |= CXGBI_FLAG_ADAPTER_RESET; + break; + case OFFLOAD_STATUS_UP: + cdev->flags &= ~CXGBI_FLAG_ADAPTER_RESET; + break; + } +} + +/** + * cxgb3i_init_module - module init entry point + * + * initialize any driver wide global data structures and register itself + * with the cxgb3 module + */ +static int __init cxgb3i_init_module(void) +{ + int rc; + + printk(KERN_INFO "%s", version); + + rc = cxgbi_iscsi_init(&cxgb3i_iscsi_transport, &cxgb3i_stt); + if (rc < 0) + return rc; + + cxgb3_register_client(&t3_client); + return 0; +} + +/** + * cxgb3i_exit_module - module cleanup/exit entry point + * + * go through the driver hba list and for each hba, release any resource held. + * and unregisters iscsi transport and the cxgb3 module + */ +static void __exit cxgb3i_exit_module(void) +{ + cxgb3_unregister_client(&t3_client); + cxgbi_device_unregister_all(CXGBI_FLAG_DEV_T3); + cxgbi_iscsi_cleanup(&cxgb3i_iscsi_transport, &cxgb3i_stt); +} + +module_init(cxgb3i_init_module); +module_exit(cxgb3i_exit_module); diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.h b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.h new file mode 100644 index 000000000000..5f5e3394b594 --- /dev/null +++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.h @@ -0,0 +1,51 @@ +/* + * cxgb3i.h: Chelsio S3xx iSCSI driver. + * + * Copyright (c) 2008 Chelsio Communications, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + * + * Written by: Karen Xie (kxie@chelsio.com) + */ + +#ifndef __CXGB3I_H__ +#define __CXGB3I_H__ + +#define CXGB3I_SCSI_HOST_QDEPTH 1024 +#define CXGB3I_MAX_LUN 512 +#define ISCSI_PDU_NONPAYLOAD_MAX \ + (sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE + 2*ISCSI_DIGEST_SIZE) + +/*for TX: a skb must have a headroom of at least TX_HEADER_LEN bytes */ +#define CXGB3I_TX_HEADER_LEN \ + (sizeof(struct tx_data_wr) + sizeof(struct sge_opaque_hdr)) + +extern cxgb3_cpl_handler_func cxgb3i_cpl_handlers[NUM_CPL_CMDS]; + +#define cxgb3i_get_private_ipv4addr(ndev) \ + (((struct port_info *)(netdev_priv(ndev)))->iscsi_ipv4addr) +#define cxgb3i_set_private_ipv4addr(ndev, addr) \ + (((struct port_info *)(netdev_priv(ndev)))->iscsi_ipv4addr) = addr + +struct cpl_iscsi_hdr_norss { + union opcode_tid ot; + u16 pdu_len_ddp; + u16 len; + u32 seq; + u16 urg; + u8 rsvd; + u8 status; +}; + +struct cpl_rx_data_ddp_norss { + union opcode_tid ot; + u16 urg; + u16 len; + u32 seq; + u32 nxt_seq; + u32 ulp_crc; + u32 ddp_status; +}; +#endif diff --git a/drivers/scsi/cxgbi/cxgb4i/Kbuild b/drivers/scsi/cxgbi/cxgb4i/Kbuild new file mode 100644 index 000000000000..b9f4af7454b7 --- /dev/null +++ b/drivers/scsi/cxgbi/cxgb4i/Kbuild @@ -0,0 +1,3 @@ +EXTRA_CFLAGS += -I$(srctree)/drivers/net/cxgb4 + +obj-$(CONFIG_SCSI_CXGB4_ISCSI) += cxgb4i.o diff --git a/drivers/scsi/cxgbi/cxgb4i/Kconfig b/drivers/scsi/cxgbi/cxgb4i/Kconfig new file mode 100644 index 000000000000..bb94b39b17b3 --- /dev/null +++ b/drivers/scsi/cxgbi/cxgb4i/Kconfig @@ -0,0 +1,7 @@ +config SCSI_CXGB4_ISCSI + tristate "Chelsio T4 iSCSI support" + depends on CHELSIO_T4_DEPENDS + select CHELSIO_T4 + select SCSI_ISCSI_ATTRS + ---help--- + This driver supports iSCSI offload for the Chelsio T4 devices. diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c new file mode 100644 index 000000000000..99f2b8c5dd63 --- /dev/null +++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c @@ -0,0 +1,1604 @@ +/* + * cxgb4i.c: Chelsio T4 iSCSI driver. + * + * Copyright (c) 2010 Chelsio Communications, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + * + * Written by: Karen Xie (kxie@chelsio.com) + * Rakesh Ranjan (rranjan@chelsio.com) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__ + +#include <linux/version.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <scsi/scsi_host.h> +#include <net/tcp.h> +#include <net/dst.h> +#include <linux/netdevice.h> + +#include "t4_msg.h" +#include "cxgb4.h" +#include "cxgb4_uld.h" +#include "t4fw_api.h" +#include "l2t.h" +#include "cxgb4i.h" + +static unsigned int dbg_level; + +#include "../libcxgbi.h" + +#define DRV_MODULE_NAME "cxgb4i" +#define DRV_MODULE_DESC "Chelsio T4 iSCSI Driver" +#define DRV_MODULE_VERSION "0.9.1" +#define DRV_MODULE_RELDATE "Aug. 2010" + +static char version[] = + DRV_MODULE_DESC " " DRV_MODULE_NAME + " v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n"; + +MODULE_AUTHOR("Chelsio Communications, Inc."); +MODULE_DESCRIPTION(DRV_MODULE_DESC); +MODULE_VERSION(DRV_MODULE_VERSION); +MODULE_LICENSE("GPL"); + +module_param(dbg_level, uint, 0644); +MODULE_PARM_DESC(dbg_level, "Debug flag (default=0)"); + +static int cxgb4i_rcv_win = 256 * 1024; +module_param(cxgb4i_rcv_win, int, 0644); +MODULE_PARM_DESC(cxgb4i_rcv_win, "TCP reveive window in bytes"); + +static int cxgb4i_snd_win = 128 * 1024; +module_param(cxgb4i_snd_win, int, 0644); +MODULE_PARM_DESC(cxgb4i_snd_win, "TCP send window in bytes"); + +static int cxgb4i_rx_credit_thres = 10 * 1024; +module_param(cxgb4i_rx_credit_thres, int, 0644); +MODULE_PARM_DESC(cxgb4i_rx_credit_thres, + "RX credits return threshold in bytes (default=10KB)"); + +static unsigned int cxgb4i_max_connect = (8 * 1024); +module_param(cxgb4i_max_connect, uint, 0644); +MODULE_PARM_DESC(cxgb4i_max_connect, "Maximum number of connections"); + +static unsigned short cxgb4i_sport_base = 20000; +module_param(cxgb4i_sport_base, ushort, 0644); +MODULE_PARM_DESC(cxgb4i_sport_base, "Starting port number (default 20000)"); + +typedef void (*cxgb4i_cplhandler_func)(struct cxgbi_device *, struct sk_buff *); + +static void *t4_uld_add(const struct cxgb4_lld_info *); +static int t4_uld_rx_handler(void *, const __be64 *, const struct pkt_gl *); +static int t4_uld_state_change(void *, enum cxgb4_state state); + +static const struct cxgb4_uld_info cxgb4i_uld_info = { + .name = DRV_MODULE_NAME, + .add = t4_uld_add, + .rx_handler = t4_uld_rx_handler, + .state_change = t4_uld_state_change, +}; + +static struct scsi_host_template cxgb4i_host_template = { + .module = THIS_MODULE, + .name = DRV_MODULE_NAME, + .proc_name = DRV_MODULE_NAME, + .can_queue = CXGB4I_SCSI_HOST_QDEPTH, + .queuecommand = iscsi_queuecommand, + .change_queue_depth = iscsi_change_queue_depth, + .sg_tablesize = SG_ALL, + .max_sectors = 0xFFFF, + .cmd_per_lun = ISCSI_DEF_CMD_PER_LUN, + .eh_abort_handler = iscsi_eh_abort, + .eh_device_reset_handler = iscsi_eh_device_reset, + .eh_target_reset_handler = iscsi_eh_recover_target, + .target_alloc = iscsi_target_alloc, + .use_clustering = DISABLE_CLUSTERING, + .this_id = -1, +}; + +static struct iscsi_transport cxgb4i_iscsi_transport = { + .owner = THIS_MODULE, + .name = DRV_MODULE_NAME, + .caps = CAP_RECOVERY_L0 | CAP_MULTI_R2T | CAP_HDRDGST | + CAP_DATADGST | CAP_DIGEST_OFFLOAD | + CAP_PADDING_OFFLOAD, + .param_mask = ISCSI_MAX_RECV_DLENGTH | ISCSI_MAX_XMIT_DLENGTH | + ISCSI_HDRDGST_EN | ISCSI_DATADGST_EN | + ISCSI_INITIAL_R2T_EN | ISCSI_MAX_R2T | + ISCSI_IMM_DATA_EN | ISCSI_FIRST_BURST | + ISCSI_MAX_BURST | ISCSI_PDU_INORDER_EN | + ISCSI_DATASEQ_INORDER_EN | ISCSI_ERL | + ISCSI_CONN_PORT | ISCSI_CONN_ADDRESS | + ISCSI_EXP_STATSN | ISCSI_PERSISTENT_PORT | + ISCSI_PERSISTENT_ADDRESS | + ISCSI_TARGET_NAME | ISCSI_TPGT | + ISCSI_USERNAME | ISCSI_PASSWORD | + ISCSI_USERNAME_IN | ISCSI_PASSWORD_IN | + ISCSI_FAST_ABORT | ISCSI_ABORT_TMO | + ISCSI_LU_RESET_TMO | ISCSI_TGT_RESET_TMO | + ISCSI_PING_TMO | ISCSI_RECV_TMO | + ISCSI_IFACE_NAME | ISCSI_INITIATOR_NAME, + .host_param_mask = ISCSI_HOST_HWADDRESS | ISCSI_HOST_IPADDRESS | + ISCSI_HOST_INITIATOR_NAME | + ISCSI_HOST_NETDEV_NAME, + .get_host_param = cxgbi_get_host_param, + .set_host_param = cxgbi_set_host_param, + /* session management */ + .create_session = cxgbi_create_session, + .destroy_session = cxgbi_destroy_session, + .get_session_param = iscsi_session_get_param, + /* connection management */ + .create_conn = cxgbi_create_conn, + .bind_conn = cxgbi_bind_conn, + .destroy_conn = iscsi_tcp_conn_teardown, + .start_conn = iscsi_conn_start, + .stop_conn = iscsi_conn_stop, + .get_conn_param = cxgbi_get_conn_param, + .set_param = cxgbi_set_conn_param, + .get_stats = cxgbi_get_conn_stats, + /* pdu xmit req from user space */ + .send_pdu = iscsi_conn_send_pdu, + /* task */ + .init_task = iscsi_tcp_task_init, + .xmit_task = iscsi_tcp_task_xmit, + .cleanup_task = cxgbi_cleanup_task, + /* pdu */ + .alloc_pdu = cxgbi_conn_alloc_pdu, + .init_pdu = cxgbi_conn_init_pdu, + .xmit_pdu = cxgbi_conn_xmit_pdu, + .parse_pdu_itt = cxgbi_parse_pdu_itt, + /* TCP connect/disconnect */ + .ep_connect = cxgbi_ep_connect, + .ep_poll = cxgbi_ep_poll, + .ep_disconnect = cxgbi_ep_disconnect, + /* Error recovery timeout call */ + .session_recovery_timedout = iscsi_session_recovery_timedout, +}; + +static struct scsi_transport_template *cxgb4i_stt; + +/* + * CPL (Chelsio Protocol Language) defines a message passing interface between + * the host driver and Chelsio asic. + * The section below implments CPLs that related to iscsi tcp connection + * open/close/abort and data send/receive. + */ +#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) +#define RCV_BUFSIZ_MASK 0x3FFU +#define MAX_IMM_TX_PKT_LEN 128 + +static inline void set_queue(struct sk_buff *skb, unsigned int queue, + const struct cxgbi_sock *csk) +{ + skb->queue_mapping = queue; +} + +static int push_tx_frames(struct cxgbi_sock *, int); + +/* + * is_ofld_imm - check whether a packet can be sent as immediate data + * @skb: the packet + * + * Returns true if a packet can be sent as an offload WR with immediate + * data. We currently use the same limit as for Ethernet packets. + */ +static inline int is_ofld_imm(const struct sk_buff *skb) +{ + return skb->len <= (MAX_IMM_TX_PKT_LEN - + sizeof(struct fw_ofld_tx_data_wr)); +} + +static void send_act_open_req(struct cxgbi_sock *csk, struct sk_buff *skb, + struct l2t_entry *e) +{ + struct cpl_act_open_req *req; + int wscale = cxgbi_sock_compute_wscale(csk->mss_idx); + unsigned long long opt0; + unsigned int opt2; + unsigned int qid_atid = ((unsigned int)csk->atid) | + (((unsigned int)csk->rss_qid) << 14); + + opt0 = KEEP_ALIVE(1) | + WND_SCALE(wscale) | + MSS_IDX(csk->mss_idx) | + L2T_IDX(((struct l2t_entry *)csk->l2t)->idx) | + TX_CHAN(csk->tx_chan) | + SMAC_SEL(csk->smac_idx) | + ULP_MODE(ULP_MODE_ISCSI) | + RCV_BUFSIZ(cxgb4i_rcv_win >> 10); + opt2 = RX_CHANNEL(0) | + RSS_QUEUE_VALID | + (1 << 20) | (1 << 22) | + RSS_QUEUE(csk->rss_qid); + + set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->port_id); + req = (struct cpl_act_open_req *)skb->head; + + INIT_TP_WR(req, 0); + OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ, + qid_atid)); + req->local_port = csk->saddr.sin_port; + req->peer_port = csk->daddr.sin_port; + req->local_ip = csk->saddr.sin_addr.s_addr; + req->peer_ip = csk->daddr.sin_addr.s_addr; + req->opt0 = cpu_to_be64(opt0); + req->params = 0; + req->opt2 = cpu_to_be32(opt2); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p, %pI4:%u-%pI4:%u, atid %d, qid %u.\n", + csk, &req->local_ip, ntohs(req->local_port), + &req->peer_ip, ntohs(req->peer_port), + csk->atid, csk->rss_qid); + + cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t); +} + +static void send_close_req(struct cxgbi_sock *csk) +{ + struct sk_buff *skb = csk->cpl_close; + struct cpl_close_con_req *req = (struct cpl_close_con_req *)skb->head; + unsigned int tid = csk->tid; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx, tid %u.\n", + csk, csk->state, csk->flags, csk->tid); + csk->cpl_close = NULL; + set_wr_txq(skb, CPL_PRIORITY_DATA, csk->port_id); + INIT_TP_WR(req, tid); + OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_CLOSE_CON_REQ, tid)); + req->rsvd = 0; + + cxgbi_sock_skb_entail(csk, skb); + if (csk->state >= CTP_ESTABLISHED) + push_tx_frames(csk, 1); +} + +static void abort_arp_failure(void *handle, struct sk_buff *skb) +{ + struct cxgbi_sock *csk = (struct cxgbi_sock *)handle; + struct cpl_abort_req *req; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx, tid %u, abort.\n", + csk, csk->state, csk->flags, csk->tid); + req = (struct cpl_abort_req *)skb->data; + req->cmd = CPL_ABORT_NO_RST; + cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb); +} + +static void send_abort_req(struct cxgbi_sock *csk) +{ + struct cpl_abort_req *req; + struct sk_buff *skb = csk->cpl_abort_req; + + if (unlikely(csk->state == CTP_ABORTING) || !skb || !csk->cdev) + return; + cxgbi_sock_set_state(csk, CTP_ABORTING); + cxgbi_sock_set_flag(csk, CTPF_ABORT_RPL_PENDING); + cxgbi_sock_purge_write_queue(csk); + + csk->cpl_abort_req = NULL; + req = (struct cpl_abort_req *)skb->head; + set_queue(skb, CPL_PRIORITY_DATA, csk); + req->cmd = CPL_ABORT_SEND_RST; + t4_set_arp_err_handler(skb, csk, abort_arp_failure); + INIT_TP_WR(req, csk->tid); + OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_REQ, csk->tid)); + req->rsvd0 = htonl(csk->snd_nxt); + req->rsvd1 = !cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u, snd_nxt %u, 0x%x.\n", + csk, csk->state, csk->flags, csk->tid, csk->snd_nxt, + req->rsvd1); + + cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t); +} + +static void send_abort_rpl(struct cxgbi_sock *csk, int rst_status) +{ + struct sk_buff *skb = csk->cpl_abort_rpl; + struct cpl_abort_rpl *rpl = (struct cpl_abort_rpl *)skb->head; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u, status %d.\n", + csk, csk->state, csk->flags, csk->tid, rst_status); + + csk->cpl_abort_rpl = NULL; + set_queue(skb, CPL_PRIORITY_DATA, csk); + INIT_TP_WR(rpl, csk->tid); + OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_RPL, csk->tid)); + rpl->cmd = rst_status; + cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb); +} + +/* + * CPL connection rx data ack: host -> + * Send RX credits through an RX_DATA_ACK CPL message. Returns the number of + * credits sent. + */ +static u32 send_rx_credits(struct cxgbi_sock *csk, u32 credits) +{ + struct sk_buff *skb; + struct cpl_rx_data_ack *req; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX, + "csk 0x%p,%u,0x%lx,%u, credit %u.\n", + csk, csk->state, csk->flags, csk->tid, credits); + + skb = alloc_wr(sizeof(*req), 0, GFP_ATOMIC); + if (!skb) { + pr_info("csk 0x%p, credit %u, OOM.\n", csk, credits); + return 0; + } + req = (struct cpl_rx_data_ack *)skb->head; + + set_wr_txq(skb, CPL_PRIORITY_ACK, csk->port_id); + INIT_TP_WR(req, csk->tid); + OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK, + csk->tid)); + req->credit_dack = cpu_to_be32(RX_CREDITS(credits) | RX_FORCE_ACK(1)); + cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb); + return credits; +} + +/* + * sgl_len - calculates the size of an SGL of the given capacity + * @n: the number of SGL entries + * Calculates the number of flits needed for a scatter/gather list that + * can hold the given number of entries. + */ +static inline unsigned int sgl_len(unsigned int n) +{ + n--; + return (3 * n) / 2 + (n & 1) + 2; +} + +/* + * calc_tx_flits_ofld - calculate # of flits for an offload packet + * @skb: the packet + * + * Returns the number of flits needed for the given offload packet. + * These packets are already fully constructed and no additional headers + * will be added. + */ +static inline unsigned int calc_tx_flits_ofld(const struct sk_buff *skb) +{ + unsigned int flits, cnt; + + if (is_ofld_imm(skb)) + return DIV_ROUND_UP(skb->len, 8); + flits = skb_transport_offset(skb) / 8; + cnt = skb_shinfo(skb)->nr_frags; + if (skb->tail != skb->transport_header) + cnt++; + return flits + sgl_len(cnt); +} + +static inline void send_tx_flowc_wr(struct cxgbi_sock *csk) +{ + struct sk_buff *skb; + struct fw_flowc_wr *flowc; + int flowclen, i; + + flowclen = 80; + skb = alloc_wr(flowclen, 0, GFP_ATOMIC); + flowc = (struct fw_flowc_wr *)skb->head; + flowc->op_to_nparams = + htonl(FW_WR_OP(FW_FLOWC_WR) | FW_FLOWC_WR_NPARAMS(8)); + flowc->flowid_len16 = + htonl(FW_WR_LEN16(DIV_ROUND_UP(72, 16)) | + FW_WR_FLOWID(csk->tid)); + flowc->mnemval[0].mnemonic = FW_FLOWC_MNEM_PFNVFN; + flowc->mnemval[0].val = htonl(csk->cdev->pfvf); + flowc->mnemval[1].mnemonic = FW_FLOWC_MNEM_CH; + flowc->mnemval[1].val = htonl(csk->tx_chan); + flowc->mnemval[2].mnemonic = FW_FLOWC_MNEM_PORT; + flowc->mnemval[2].val = htonl(csk->tx_chan); + flowc->mnemval[3].mnemonic = FW_FLOWC_MNEM_IQID; + flowc->mnemval[3].val = htonl(csk->rss_qid); + flowc->mnemval[4].mnemonic = FW_FLOWC_MNEM_SNDNXT; + flowc->mnemval[4].val = htonl(csk->snd_nxt); + flowc->mnemval[5].mnemonic = FW_FLOWC_MNEM_RCVNXT; + flowc->mnemval[5].val = htonl(csk->rcv_nxt); + flowc->mnemval[6].mnemonic = FW_FLOWC_MNEM_SNDBUF; + flowc->mnemval[6].val = htonl(cxgb4i_snd_win); + flowc->mnemval[7].mnemonic = FW_FLOWC_MNEM_MSS; + flowc->mnemval[7].val = htonl(csk->advmss); + flowc->mnemval[8].mnemonic = 0; + flowc->mnemval[8].val = 0; + for (i = 0; i < 9; i++) { + flowc->mnemval[i].r4[0] = 0; + flowc->mnemval[i].r4[1] = 0; + flowc->mnemval[i].r4[2] = 0; + } + set_queue(skb, CPL_PRIORITY_DATA, csk); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p, tid 0x%x, %u,%u,%u,%u,%u,%u,%u.\n", + csk, csk->tid, 0, csk->tx_chan, csk->rss_qid, + csk->snd_nxt, csk->rcv_nxt, cxgb4i_snd_win, + csk->advmss); + + cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb); +} + +static inline void make_tx_data_wr(struct cxgbi_sock *csk, struct sk_buff *skb, + int dlen, int len, u32 credits, int compl) +{ + struct fw_ofld_tx_data_wr *req; + unsigned int submode = cxgbi_skcb_ulp_mode(skb) & 3; + unsigned int wr_ulp_mode = 0; + + req = (struct fw_ofld_tx_data_wr *)__skb_push(skb, sizeof(*req)); + + if (is_ofld_imm(skb)) { + req->op_to_immdlen = htonl(FW_WR_OP(FW_OFLD_TX_DATA_WR) | + FW_WR_COMPL(1) | + FW_WR_IMMDLEN(dlen)); + req->flowid_len16 = htonl(FW_WR_FLOWID(csk->tid) | + FW_WR_LEN16(credits)); + } else { + req->op_to_immdlen = + cpu_to_be32(FW_WR_OP(FW_OFLD_TX_DATA_WR) | + FW_WR_COMPL(1) | + FW_WR_IMMDLEN(0)); + req->flowid_len16 = + cpu_to_be32(FW_WR_FLOWID(csk->tid) | + FW_WR_LEN16(credits)); + } + if (submode) + wr_ulp_mode = FW_OFLD_TX_DATA_WR_ULPMODE(ULP2_MODE_ISCSI) | + FW_OFLD_TX_DATA_WR_ULPSUBMODE(submode); + req->tunnel_to_proxy = htonl(wr_ulp_mode) | + FW_OFLD_TX_DATA_WR_SHOVE(skb_peek(&csk->write_queue) ? 0 : 1); + req->plen = htonl(len); + if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) + cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT); +} + +static void arp_failure_skb_discard(void *handle, struct sk_buff *skb) +{ + kfree_skb(skb); +} + +static int push_tx_frames(struct cxgbi_sock *csk, int req_completion) +{ + int total_size = 0; + struct sk_buff *skb; + + if (unlikely(csk->state < CTP_ESTABLISHED || + csk->state == CTP_CLOSE_WAIT_1 || csk->state >= CTP_ABORTING)) { + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK | + 1 << CXGBI_DBG_PDU_TX, + "csk 0x%p,%u,0x%lx,%u, in closing state.\n", + csk, csk->state, csk->flags, csk->tid); + return 0; + } + + while (csk->wr_cred && (skb = skb_peek(&csk->write_queue)) != NULL) { + int dlen = skb->len; + int len = skb->len; + unsigned int credits_needed; + + skb_reset_transport_header(skb); + if (is_ofld_imm(skb)) + credits_needed = DIV_ROUND_UP(dlen + + sizeof(struct fw_ofld_tx_data_wr), 16); + else + credits_needed = DIV_ROUND_UP(8*calc_tx_flits_ofld(skb) + + sizeof(struct fw_ofld_tx_data_wr), + 16); + + if (csk->wr_cred < credits_needed) { + log_debug(1 << CXGBI_DBG_PDU_TX, + "csk 0x%p, skb %u/%u, wr %d < %u.\n", + csk, skb->len, skb->data_len, + credits_needed, csk->wr_cred); + break; + } + __skb_unlink(skb, &csk->write_queue); + set_queue(skb, CPL_PRIORITY_DATA, csk); + skb->csum = credits_needed; + csk->wr_cred -= credits_needed; + csk->wr_una_cred += credits_needed; + cxgbi_sock_enqueue_wr(csk, skb); + + log_debug(1 << CXGBI_DBG_PDU_TX, + "csk 0x%p, skb %u/%u, wr %d, left %u, unack %u.\n", + csk, skb->len, skb->data_len, credits_needed, + csk->wr_cred, csk->wr_una_cred); + + if (likely(cxgbi_skcb_test_flag(skb, SKCBF_TX_NEED_HDR))) { + if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) { + send_tx_flowc_wr(csk); + skb->csum += 5; + csk->wr_cred -= 5; + csk->wr_una_cred += 5; + } + len += cxgbi_ulp_extra_len(cxgbi_skcb_ulp_mode(skb)); + make_tx_data_wr(csk, skb, dlen, len, credits_needed, + req_completion); + csk->snd_nxt += len; + cxgbi_skcb_clear_flag(skb, SKCBF_TX_NEED_HDR); + } + total_size += skb->truesize; + t4_set_arp_err_handler(skb, csk, arp_failure_skb_discard); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_TX, + "csk 0x%p,%u,0x%lx,%u, skb 0x%p, %u.\n", + csk, csk->state, csk->flags, csk->tid, skb, len); + + cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t); + } + return total_size; +} + +static inline void free_atid(struct cxgbi_sock *csk) +{ + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(csk->cdev); + + if (cxgbi_sock_flag(csk, CTPF_HAS_ATID)) { + cxgb4_free_atid(lldi->tids, csk->atid); + cxgbi_sock_clear_flag(csk, CTPF_HAS_ATID); + cxgbi_sock_put(csk); + } +} + +static void do_act_establish(struct cxgbi_device *cdev, struct sk_buff *skb) +{ + struct cxgbi_sock *csk; + struct cpl_act_establish *req = (struct cpl_act_establish *)skb->data; + unsigned short tcp_opt = ntohs(req->tcp_opt); + unsigned int tid = GET_TID(req); + unsigned int atid = GET_TID_TID(ntohl(req->tos_atid)); + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct tid_info *t = lldi->tids; + u32 rcv_isn = be32_to_cpu(req->rcv_isn); + + csk = lookup_atid(t, atid); + if (unlikely(!csk)) { + pr_err("NO conn. for atid %u, cdev 0x%p.\n", atid, cdev); + goto rel_skb; + } + + if (csk->atid != atid) { + pr_err("bad conn atid %u, csk 0x%p,%u,0x%lx,tid %u, atid %u.\n", + atid, csk, csk->state, csk->flags, csk->tid, csk->atid); + goto rel_skb; + } + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx, tid %u, atid %u, rseq %u.\n", + csk, csk->state, csk->flags, tid, atid, rcv_isn); + + cxgbi_sock_get(csk); + csk->tid = tid; + cxgb4_insert_tid(lldi->tids, csk, tid); + cxgbi_sock_set_flag(csk, CTPF_HAS_TID); + + free_atid(csk); + + spin_lock_bh(&csk->lock); + if (unlikely(csk->state != CTP_ACTIVE_OPEN)) + pr_info("csk 0x%p,%u,0x%lx,%u, got EST.\n", + csk, csk->state, csk->flags, csk->tid); + + if (csk->retry_timer.function) { + del_timer(&csk->retry_timer); + csk->retry_timer.function = NULL; + } + + csk->copied_seq = csk->rcv_wup = csk->rcv_nxt = rcv_isn; + /* + * Causes the first RX_DATA_ACK to supply any Rx credits we couldn't + * pass through opt0. + */ + if (cxgb4i_rcv_win > (RCV_BUFSIZ_MASK << 10)) + csk->rcv_wup -= cxgb4i_rcv_win - (RCV_BUFSIZ_MASK << 10); + + csk->advmss = lldi->mtus[GET_TCPOPT_MSS(tcp_opt)] - 40; + if (GET_TCPOPT_TSTAMP(tcp_opt)) + csk->advmss -= 12; + if (csk->advmss < 128) + csk->advmss = 128; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p, mss_idx %u, advmss %u.\n", + csk, GET_TCPOPT_MSS(tcp_opt), csk->advmss); + + cxgbi_sock_established(csk, ntohl(req->snd_isn), ntohs(req->tcp_opt)); + + if (unlikely(cxgbi_sock_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED))) + send_abort_req(csk); + else { + if (skb_queue_len(&csk->write_queue)) + push_tx_frames(csk, 0); + cxgbi_conn_tx_open(csk); + } + spin_unlock_bh(&csk->lock); + +rel_skb: + __kfree_skb(skb); +} + +static int act_open_rpl_status_to_errno(int status) +{ + switch (status) { + case CPL_ERR_CONN_RESET: + return -ECONNREFUSED; + case CPL_ERR_ARP_MISS: + return -EHOSTUNREACH; + case CPL_ERR_CONN_TIMEDOUT: + return -ETIMEDOUT; + case CPL_ERR_TCAM_FULL: + return -ENOMEM; + case CPL_ERR_CONN_EXIST: + return -EADDRINUSE; + default: + return -EIO; + } +} + +static void csk_act_open_retry_timer(unsigned long data) +{ + struct sk_buff *skb; + struct cxgbi_sock *csk = (struct cxgbi_sock *)data; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + + cxgbi_sock_get(csk); + spin_lock_bh(&csk->lock); + skb = alloc_wr(sizeof(struct cpl_act_open_req), 0, GFP_ATOMIC); + if (!skb) + cxgbi_sock_fail_act_open(csk, -ENOMEM); + else { + skb->sk = (struct sock *)csk; + t4_set_arp_err_handler(skb, csk, + cxgbi_sock_act_open_req_arp_failure); + send_act_open_req(csk, skb, csk->l2t); + } + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); +} + +static void do_act_open_rpl(struct cxgbi_device *cdev, struct sk_buff *skb) +{ + struct cxgbi_sock *csk; + struct cpl_act_open_rpl *rpl = (struct cpl_act_open_rpl *)skb->data; + unsigned int tid = GET_TID(rpl); + unsigned int atid = + GET_TID_TID(GET_AOPEN_ATID(be32_to_cpu(rpl->atid_status))); + unsigned int status = GET_AOPEN_STATUS(be32_to_cpu(rpl->atid_status)); + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct tid_info *t = lldi->tids; + + csk = lookup_atid(t, atid); + if (unlikely(!csk)) { + pr_err("NO matching conn. atid %u, tid %u.\n", atid, tid); + goto rel_skb; + } + + pr_info("%pI4:%u-%pI4:%u, atid %u,%u, status %u, csk 0x%p,%u,0x%lx.\n", + &csk->saddr.sin_addr.s_addr, ntohs(csk->saddr.sin_port), + &csk->daddr.sin_addr.s_addr, ntohs(csk->daddr.sin_port), + atid, tid, status, csk, csk->state, csk->flags); + + if (status && status != CPL_ERR_TCAM_FULL && + status != CPL_ERR_CONN_EXIST && + status != CPL_ERR_ARP_MISS) + cxgb4_remove_tid(lldi->tids, csk->port_id, GET_TID(rpl)); + + cxgbi_sock_get(csk); + spin_lock_bh(&csk->lock); + + if (status == CPL_ERR_CONN_EXIST && + csk->retry_timer.function != csk_act_open_retry_timer) { + csk->retry_timer.function = csk_act_open_retry_timer; + mod_timer(&csk->retry_timer, jiffies + HZ / 2); + } else + cxgbi_sock_fail_act_open(csk, + act_open_rpl_status_to_errno(status)); + + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); +rel_skb: + __kfree_skb(skb); +} + +static void do_peer_close(struct cxgbi_device *cdev, struct sk_buff *skb) +{ + struct cxgbi_sock *csk; + struct cpl_peer_close *req = (struct cpl_peer_close *)skb->data; + unsigned int tid = GET_TID(req); + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct tid_info *t = lldi->tids; + + csk = lookup_tid(t, tid); + if (unlikely(!csk)) { + pr_err("can't find connection for tid %u.\n", tid); + goto rel_skb; + } + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + cxgbi_sock_rcv_peer_close(csk); +rel_skb: + __kfree_skb(skb); +} + +static void do_close_con_rpl(struct cxgbi_device *cdev, struct sk_buff *skb) +{ + struct cxgbi_sock *csk; + struct cpl_close_con_rpl *rpl = (struct cpl_close_con_rpl *)skb->data; + unsigned int tid = GET_TID(rpl); + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct tid_info *t = lldi->tids; + + csk = lookup_tid(t, tid); + if (unlikely(!csk)) { + pr_err("can't find connection for tid %u.\n", tid); + goto rel_skb; + } + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + cxgbi_sock_rcv_close_conn_rpl(csk, ntohl(rpl->snd_nxt)); +rel_skb: + __kfree_skb(skb); +} + +static int abort_status_to_errno(struct cxgbi_sock *csk, int abort_reason, + int *need_rst) +{ + switch (abort_reason) { + case CPL_ERR_BAD_SYN: /* fall through */ + case CPL_ERR_CONN_RESET: + return csk->state > CTP_ESTABLISHED ? + -EPIPE : -ECONNRESET; + case CPL_ERR_XMIT_TIMEDOUT: + case CPL_ERR_PERSIST_TIMEDOUT: + case CPL_ERR_FINWAIT2_TIMEDOUT: + case CPL_ERR_KEEPALIVE_TIMEDOUT: + return -ETIMEDOUT; + default: + return -EIO; + } +} + +static void do_abort_req_rss(struct cxgbi_device *cdev, struct sk_buff *skb) +{ + struct cxgbi_sock *csk; + struct cpl_abort_req_rss *req = (struct cpl_abort_req_rss *)skb->data; + unsigned int tid = GET_TID(req); + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct tid_info *t = lldi->tids; + int rst_status = CPL_ABORT_NO_RST; + + csk = lookup_tid(t, tid); + if (unlikely(!csk)) { + pr_err("can't find connection for tid %u.\n", tid); + goto rel_skb; + } + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx, tid %u, status 0x%x.\n", + csk, csk->state, csk->flags, csk->tid, req->status); + + if (req->status == CPL_ERR_RTX_NEG_ADVICE || + req->status == CPL_ERR_PERSIST_NEG_ADVICE) + goto rel_skb; + + cxgbi_sock_get(csk); + spin_lock_bh(&csk->lock); + + if (!cxgbi_sock_flag(csk, CTPF_ABORT_REQ_RCVD)) { + cxgbi_sock_set_flag(csk, CTPF_ABORT_REQ_RCVD); + cxgbi_sock_set_state(csk, CTP_ABORTING); + goto done; + } + + cxgbi_sock_clear_flag(csk, CTPF_ABORT_REQ_RCVD); + send_abort_rpl(csk, rst_status); + + if (!cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING)) { + csk->err = abort_status_to_errno(csk, req->status, &rst_status); + cxgbi_sock_closed(csk); + } +done: + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); +rel_skb: + __kfree_skb(skb); +} + +static void do_abort_rpl_rss(struct cxgbi_device *cdev, struct sk_buff *skb) +{ + struct cxgbi_sock *csk; + struct cpl_abort_rpl_rss *rpl = (struct cpl_abort_rpl_rss *)skb->data; + unsigned int tid = GET_TID(rpl); + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct tid_info *t = lldi->tids; + + csk = lookup_tid(t, tid); + if (!csk) + goto rel_skb; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "status 0x%x, csk 0x%p, s %u, 0x%lx.\n", + rpl->status, csk, csk ? csk->state : 0, + csk ? csk->flags : 0UL); + + if (rpl->status == CPL_ERR_ABORT_FAILED) + goto rel_skb; + + cxgbi_sock_rcv_abort_rpl(csk); +rel_skb: + __kfree_skb(skb); +} + +static void do_rx_iscsi_hdr(struct cxgbi_device *cdev, struct sk_buff *skb) +{ + struct cxgbi_sock *csk; + struct cpl_iscsi_hdr *cpl = (struct cpl_iscsi_hdr *)skb->data; + unsigned short pdu_len_ddp = be16_to_cpu(cpl->pdu_len_ddp); + unsigned int tid = GET_TID(cpl); + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct tid_info *t = lldi->tids; + + csk = lookup_tid(t, tid); + if (unlikely(!csk)) { + pr_err("can't find conn. for tid %u.\n", tid); + goto rel_skb; + } + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX, + "csk 0x%p,%u,0x%lx, tid %u, skb 0x%p,%u, 0x%x.\n", + csk, csk->state, csk->flags, csk->tid, skb, skb->len, + pdu_len_ddp); + + spin_lock_bh(&csk->lock); + + if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) { + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u, bad state.\n", + csk, csk->state, csk->flags, csk->tid); + if (csk->state != CTP_ABORTING) + goto abort_conn; + else + goto discard; + } + + cxgbi_skcb_tcp_seq(skb) = ntohl(cpl->seq); + cxgbi_skcb_flags(skb) = 0; + + skb_reset_transport_header(skb); + __skb_pull(skb, sizeof(*cpl)); + __pskb_trim(skb, ntohs(cpl->len)); + + if (!csk->skb_ulp_lhdr) { + unsigned char *bhs; + unsigned int hlen, dlen; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX, + "csk 0x%p,%u,0x%lx, tid %u, skb 0x%p header.\n", + csk, csk->state, csk->flags, csk->tid, skb); + csk->skb_ulp_lhdr = skb; + cxgbi_skcb_set_flag(skb, SKCBF_RX_HDR); + + if (cxgbi_skcb_tcp_seq(skb) != csk->rcv_nxt) { + pr_info("tid %u, CPL_ISCSI_HDR, bad seq, 0x%x/0x%x.\n", + csk->tid, cxgbi_skcb_tcp_seq(skb), + csk->rcv_nxt); + goto abort_conn; + } + + bhs = skb->data; + hlen = ntohs(cpl->len); + dlen = ntohl(*(unsigned int *)(bhs + 4)) & 0xFFFFFF; + + if ((hlen + dlen) != ISCSI_PDU_LEN(pdu_len_ddp) - 40) { + pr_info("tid 0x%x, CPL_ISCSI_HDR, pdu len " + "mismatch %u != %u + %u, seq 0x%x.\n", + csk->tid, ISCSI_PDU_LEN(pdu_len_ddp) - 40, + hlen, dlen, cxgbi_skcb_tcp_seq(skb)); + goto abort_conn; + } + + cxgbi_skcb_rx_pdulen(skb) = (hlen + dlen + 3) & (~0x3); + if (dlen) + cxgbi_skcb_rx_pdulen(skb) += csk->dcrc_len; + csk->rcv_nxt += cxgbi_skcb_rx_pdulen(skb); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX, + "csk 0x%p, skb 0x%p, 0x%x,%u+%u,0x%x,0x%x.\n", + csk, skb, *bhs, hlen, dlen, + ntohl(*((unsigned int *)(bhs + 16))), + ntohl(*((unsigned int *)(bhs + 24)))); + + } else { + struct sk_buff *lskb = csk->skb_ulp_lhdr; + + cxgbi_skcb_set_flag(lskb, SKCBF_RX_DATA); + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX, + "csk 0x%p,%u,0x%lx, skb 0x%p data, 0x%p.\n", + csk, csk->state, csk->flags, skb, lskb); + } + + __skb_queue_tail(&csk->receive_queue, skb); + spin_unlock_bh(&csk->lock); + return; + +abort_conn: + send_abort_req(csk); +discard: + spin_unlock_bh(&csk->lock); +rel_skb: + __kfree_skb(skb); +} + +static void do_rx_data_ddp(struct cxgbi_device *cdev, + struct sk_buff *skb) +{ + struct cxgbi_sock *csk; + struct sk_buff *lskb; + struct cpl_rx_data_ddp *rpl = (struct cpl_rx_data_ddp *)skb->data; + unsigned int tid = GET_TID(rpl); + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct tid_info *t = lldi->tids; + unsigned int status = ntohl(rpl->ddpvld); + + csk = lookup_tid(t, tid); + if (unlikely(!csk)) { + pr_err("can't find connection for tid %u.\n", tid); + goto rel_skb; + } + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_PDU_RX, + "csk 0x%p,%u,0x%lx, skb 0x%p,0x%x, lhdr 0x%p.\n", + csk, csk->state, csk->flags, skb, status, csk->skb_ulp_lhdr); + + spin_lock_bh(&csk->lock); + + if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) { + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u, bad state.\n", + csk, csk->state, csk->flags, csk->tid); + if (csk->state != CTP_ABORTING) + goto abort_conn; + else + goto discard; + } + + if (!csk->skb_ulp_lhdr) { + pr_err("tid 0x%x, rcv RX_DATA_DDP w/o pdu bhs.\n", csk->tid); + goto abort_conn; + } + + lskb = csk->skb_ulp_lhdr; + csk->skb_ulp_lhdr = NULL; + + cxgbi_skcb_rx_ddigest(lskb) = ntohl(rpl->ulp_crc); + + if (ntohs(rpl->len) != cxgbi_skcb_rx_pdulen(lskb)) + pr_info("tid 0x%x, RX_DATA_DDP pdulen %u != %u.\n", + csk->tid, ntohs(rpl->len), cxgbi_skcb_rx_pdulen(lskb)); + + if (status & (1 << CPL_RX_DDP_STATUS_HCRC_SHIFT)) { + pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, hcrc bad 0x%lx.\n", + csk, lskb, status, cxgbi_skcb_flags(lskb)); + cxgbi_skcb_set_flag(lskb, SKCBF_RX_HCRC_ERR); + } + if (status & (1 << CPL_RX_DDP_STATUS_DCRC_SHIFT)) { + pr_info("csk 0x%p, lhdr 0x%p, status 0x%x, dcrc bad 0x%lx.\n", + csk, lskb, status, cxgbi_skcb_flags(lskb)); + cxgbi_skcb_set_flag(lskb, SKCBF_RX_DCRC_ERR); + } + if (status & (1 << CPL_RX_DDP_STATUS_PAD_SHIFT)) { + log_debug(1 << CXGBI_DBG_PDU_RX, + "csk 0x%p, lhdr 0x%p, status 0x%x, pad bad.\n", + csk, lskb, status); + cxgbi_skcb_set_flag(lskb, SKCBF_RX_PAD_ERR); + } + if ((status & (1 << CPL_RX_DDP_STATUS_DDP_SHIFT)) && + !cxgbi_skcb_test_flag(lskb, SKCBF_RX_DATA)) { + log_debug(1 << CXGBI_DBG_PDU_RX, + "csk 0x%p, lhdr 0x%p, 0x%x, data ddp'ed.\n", + csk, lskb, status); + cxgbi_skcb_set_flag(lskb, SKCBF_RX_DATA_DDPD); + } + log_debug(1 << CXGBI_DBG_PDU_RX, + "csk 0x%p, lskb 0x%p, f 0x%lx.\n", + csk, lskb, cxgbi_skcb_flags(lskb)); + + cxgbi_skcb_set_flag(lskb, SKCBF_RX_STATUS); + cxgbi_conn_pdu_ready(csk); + spin_unlock_bh(&csk->lock); + goto rel_skb; + +abort_conn: + send_abort_req(csk); +discard: + spin_unlock_bh(&csk->lock); +rel_skb: + __kfree_skb(skb); +} + +static void do_fw4_ack(struct cxgbi_device *cdev, struct sk_buff *skb) +{ + struct cxgbi_sock *csk; + struct cpl_fw4_ack *rpl = (struct cpl_fw4_ack *)skb->data; + unsigned int tid = GET_TID(rpl); + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct tid_info *t = lldi->tids; + + csk = lookup_tid(t, tid); + if (unlikely(!csk)) + pr_err("can't find connection for tid %u.\n", tid); + else { + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + cxgbi_sock_rcv_wr_ack(csk, rpl->credits, ntohl(rpl->snd_una), + rpl->seq_vld); + } + __kfree_skb(skb); +} + +static void do_set_tcb_rpl(struct cxgbi_device *cdev, struct sk_buff *skb) +{ + struct cpl_set_tcb_rpl *rpl = (struct cpl_set_tcb_rpl *)skb->data; + unsigned int tid = GET_TID(rpl); + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct tid_info *t = lldi->tids; + struct cxgbi_sock *csk; + + csk = lookup_tid(t, tid); + if (!csk) + pr_err("can't find conn. for tid %u.\n", tid); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,%lx,%u, status 0x%x.\n", + csk, csk->state, csk->flags, csk->tid, rpl->status); + + if (rpl->status != CPL_ERR_NONE) + pr_err("csk 0x%p,%u, SET_TCB_RPL status %u.\n", + csk, tid, rpl->status); + + __kfree_skb(skb); +} + +static int alloc_cpls(struct cxgbi_sock *csk) +{ + csk->cpl_close = alloc_wr(sizeof(struct cpl_close_con_req), + 0, GFP_KERNEL); + if (!csk->cpl_close) + return -ENOMEM; + + csk->cpl_abort_req = alloc_wr(sizeof(struct cpl_abort_req), + 0, GFP_KERNEL); + if (!csk->cpl_abort_req) + goto free_cpls; + + csk->cpl_abort_rpl = alloc_wr(sizeof(struct cpl_abort_rpl), + 0, GFP_KERNEL); + if (!csk->cpl_abort_rpl) + goto free_cpls; + return 0; + +free_cpls: + cxgbi_sock_free_cpl_skbs(csk); + return -ENOMEM; +} + +static inline void l2t_put(struct cxgbi_sock *csk) +{ + if (csk->l2t) { + cxgb4_l2t_release(csk->l2t); + csk->l2t = NULL; + cxgbi_sock_put(csk); + } +} + +static void release_offload_resources(struct cxgbi_sock *csk) +{ + struct cxgb4_lld_info *lldi; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + + cxgbi_sock_free_cpl_skbs(csk); + if (csk->wr_cred != csk->wr_max_cred) { + cxgbi_sock_purge_wr_queue(csk); + cxgbi_sock_reset_wr_list(csk); + } + + l2t_put(csk); + if (cxgbi_sock_flag(csk, CTPF_HAS_ATID)) + free_atid(csk); + else if (cxgbi_sock_flag(csk, CTPF_HAS_TID)) { + lldi = cxgbi_cdev_priv(csk->cdev); + cxgb4_remove_tid(lldi->tids, 0, csk->tid); + cxgbi_sock_clear_flag(csk, CTPF_HAS_TID); + cxgbi_sock_put(csk); + } + csk->dst = NULL; + csk->cdev = NULL; +} + +static int init_act_open(struct cxgbi_sock *csk) +{ + struct cxgbi_device *cdev = csk->cdev; + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct net_device *ndev = cdev->ports[csk->port_id]; + struct port_info *pi = netdev_priv(ndev); + struct sk_buff *skb = NULL; + unsigned int step; + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u.\n", + csk, csk->state, csk->flags, csk->tid); + + csk->atid = cxgb4_alloc_atid(lldi->tids, csk); + if (csk->atid < 0) { + pr_err("%s, NO atid available.\n", ndev->name); + return -EINVAL; + } + cxgbi_sock_set_flag(csk, CTPF_HAS_ATID); + cxgbi_sock_get(csk); + + csk->l2t = cxgb4_l2t_get(lldi->l2t, csk->dst->neighbour, ndev, 0); + if (!csk->l2t) { + pr_err("%s, cannot alloc l2t.\n", ndev->name); + goto rel_resource; + } + cxgbi_sock_get(csk); + + skb = alloc_wr(sizeof(struct cpl_act_open_req), 0, GFP_KERNEL); + if (!skb) + goto rel_resource; + skb->sk = (struct sock *)csk; + t4_set_arp_err_handler(skb, csk, cxgbi_sock_act_open_req_arp_failure); + + if (!csk->mtu) + csk->mtu = dst_mtu(csk->dst); + cxgb4_best_mtu(lldi->mtus, csk->mtu, &csk->mss_idx); + csk->tx_chan = cxgb4_port_chan(ndev); + /* SMT two entries per row */ + csk->smac_idx = ((cxgb4_port_viid(ndev) & 0x7F)) << 1; + step = lldi->ntxq / lldi->nchan; + csk->txq_idx = cxgb4_port_idx(ndev) * step; + step = lldi->nrxq / lldi->nchan; + csk->rss_qid = lldi->rxq_ids[cxgb4_port_idx(ndev) * step]; + csk->wr_max_cred = csk->wr_cred = lldi->wr_cred; + csk->wr_una_cred = 0; + cxgbi_sock_reset_wr_list(csk); + csk->err = 0; + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,p%d,%s, %u,%u,%u, mss %u,%u, smac %u.\n", + csk, pi->port_id, ndev->name, csk->tx_chan, + csk->txq_idx, csk->rss_qid, csk->mtu, csk->mss_idx, + csk->smac_idx); + + cxgbi_sock_set_state(csk, CTP_ACTIVE_OPEN); + send_act_open_req(csk, skb, csk->l2t); + return 0; + +rel_resource: + if (skb) + __kfree_skb(skb); + return -EINVAL; +} + +cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = { + [CPL_ACT_ESTABLISH] = do_act_establish, + [CPL_ACT_OPEN_RPL] = do_act_open_rpl, + [CPL_PEER_CLOSE] = do_peer_close, + [CPL_ABORT_REQ_RSS] = do_abort_req_rss, + [CPL_ABORT_RPL_RSS] = do_abort_rpl_rss, + [CPL_CLOSE_CON_RPL] = do_close_con_rpl, + [CPL_FW4_ACK] = do_fw4_ack, + [CPL_ISCSI_HDR] = do_rx_iscsi_hdr, + [CPL_SET_TCB_RPL] = do_set_tcb_rpl, + [CPL_RX_DATA_DDP] = do_rx_data_ddp, +}; + +int cxgb4i_ofld_init(struct cxgbi_device *cdev) +{ + int rc; + + if (cxgb4i_max_connect > CXGB4I_MAX_CONN) + cxgb4i_max_connect = CXGB4I_MAX_CONN; + + rc = cxgbi_device_portmap_create(cdev, cxgb4i_sport_base, + cxgb4i_max_connect); + if (rc < 0) + return rc; + + cdev->csk_release_offload_resources = release_offload_resources; + cdev->csk_push_tx_frames = push_tx_frames; + cdev->csk_send_abort_req = send_abort_req; + cdev->csk_send_close_req = send_close_req; + cdev->csk_send_rx_credits = send_rx_credits; + cdev->csk_alloc_cpls = alloc_cpls; + cdev->csk_init_act_open = init_act_open; + + pr_info("cdev 0x%p, offload up, added.\n", cdev); + return 0; +} + +/* + * functions to program the pagepod in h/w + */ +#define ULPMEM_IDATA_MAX_NPPODS 4 /* 256/PPOD_SIZE */ +static inline void ulp_mem_io_set_hdr(struct ulp_mem_io *req, + unsigned int wr_len, unsigned int dlen, + unsigned int pm_addr) +{ + struct ulptx_idata *idata = (struct ulptx_idata *)(req + 1); + + INIT_ULPTX_WR(req, wr_len, 0, 0); + req->cmd = htonl(ULPTX_CMD(ULP_TX_MEM_WRITE) | (1 << 23)); + req->dlen = htonl(ULP_MEMIO_DATA_LEN(dlen >> 5)); + req->lock_addr = htonl(ULP_MEMIO_ADDR(pm_addr >> 5)); + req->len16 = htonl(DIV_ROUND_UP(wr_len - sizeof(req->wr), 16)); + + idata->cmd_more = htonl(ULPTX_CMD(ULP_TX_SC_IMM)); + idata->len = htonl(dlen); +} + +static int ddp_ppod_write_idata(struct cxgbi_device *cdev, unsigned int port_id, + struct cxgbi_pagepod_hdr *hdr, unsigned int idx, + unsigned int npods, + struct cxgbi_gather_list *gl, + unsigned int gl_pidx) +{ + struct cxgbi_ddp_info *ddp = cdev->ddp; + struct sk_buff *skb; + struct ulp_mem_io *req; + struct ulptx_idata *idata; + struct cxgbi_pagepod *ppod; + unsigned int pm_addr = idx * PPOD_SIZE + ddp->llimit; + unsigned int dlen = PPOD_SIZE * npods; + unsigned int wr_len = roundup(sizeof(struct ulp_mem_io) + + sizeof(struct ulptx_idata) + dlen, 16); + unsigned int i; + + skb = alloc_wr(wr_len, 0, GFP_ATOMIC); + if (!skb) { + pr_err("cdev 0x%p, idx %u, npods %u, OOM.\n", + cdev, idx, npods); + return -ENOMEM; + } + req = (struct ulp_mem_io *)skb->head; + set_queue(skb, CPL_PRIORITY_CONTROL, NULL); + + ulp_mem_io_set_hdr(req, wr_len, dlen, pm_addr); + idata = (struct ulptx_idata *)(req + 1); + ppod = (struct cxgbi_pagepod *)(idata + 1); + + for (i = 0; i < npods; i++, ppod++, gl_pidx += PPOD_PAGES_MAX) { + if (!hdr && !gl) + cxgbi_ddp_ppod_clear(ppod); + else + cxgbi_ddp_ppod_set(ppod, hdr, gl, gl_pidx); + } + + cxgb4_ofld_send(cdev->ports[port_id], skb); + return 0; +} + +static int ddp_set_map(struct cxgbi_sock *csk, struct cxgbi_pagepod_hdr *hdr, + unsigned int idx, unsigned int npods, + struct cxgbi_gather_list *gl) +{ + unsigned int i, cnt; + int err = 0; + + for (i = 0; i < npods; i += cnt, idx += cnt) { + cnt = npods - i; + if (cnt > ULPMEM_IDATA_MAX_NPPODS) + cnt = ULPMEM_IDATA_MAX_NPPODS; + err = ddp_ppod_write_idata(csk->cdev, csk->port_id, hdr, + idx, cnt, gl, 4 * i); + if (err < 0) + break; + } + return err; +} + +static void ddp_clear_map(struct cxgbi_hba *chba, unsigned int tag, + unsigned int idx, unsigned int npods) +{ + unsigned int i, cnt; + int err; + + for (i = 0; i < npods; i += cnt, idx += cnt) { + cnt = npods - i; + if (cnt > ULPMEM_IDATA_MAX_NPPODS) + cnt = ULPMEM_IDATA_MAX_NPPODS; + err = ddp_ppod_write_idata(chba->cdev, chba->port_id, NULL, + idx, cnt, NULL, 0); + if (err < 0) + break; + } +} + +static int ddp_setup_conn_pgidx(struct cxgbi_sock *csk, unsigned int tid, + int pg_idx, bool reply) +{ + struct sk_buff *skb; + struct cpl_set_tcb_field *req; + + if (!pg_idx || pg_idx >= DDP_PGIDX_MAX) + return 0; + + skb = alloc_wr(sizeof(*req), 0, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + /* set up ulp page size */ + req = (struct cpl_set_tcb_field *)skb->head; + INIT_TP_WR(req, csk->tid); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, csk->tid)); + req->reply_ctrl = htons(NO_REPLY(reply) | QUEUENO(csk->rss_qid)); + req->word_cookie = htons(0); + req->mask = cpu_to_be64(0x3 << 8); + req->val = cpu_to_be64(pg_idx << 8); + set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->port_id); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p, tid 0x%x, pg_idx %u.\n", csk, csk->tid, pg_idx); + + cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb); + return 0; +} + +static int ddp_setup_conn_digest(struct cxgbi_sock *csk, unsigned int tid, + int hcrc, int dcrc, int reply) +{ + struct sk_buff *skb; + struct cpl_set_tcb_field *req; + + if (!hcrc && !dcrc) + return 0; + + skb = alloc_wr(sizeof(*req), 0, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + csk->hcrc_len = (hcrc ? 4 : 0); + csk->dcrc_len = (dcrc ? 4 : 0); + /* set up ulp submode */ + req = (struct cpl_set_tcb_field *)skb->head; + INIT_TP_WR(req, tid); + OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, tid)); + req->reply_ctrl = htons(NO_REPLY(reply) | QUEUENO(csk->rss_qid)); + req->word_cookie = htons(0); + req->mask = cpu_to_be64(0x3 << 4); + req->val = cpu_to_be64(((hcrc ? ULP_CRC_HEADER : 0) | + (dcrc ? ULP_CRC_DATA : 0)) << 4); + set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->port_id); + + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p, tid 0x%x, crc %d,%d.\n", csk, csk->tid, hcrc, dcrc); + + cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb); + return 0; +} + +static int cxgb4i_ddp_init(struct cxgbi_device *cdev) +{ + struct cxgb4_lld_info *lldi = cxgbi_cdev_priv(cdev); + struct cxgbi_ddp_info *ddp = cdev->ddp; + unsigned int tagmask, pgsz_factor[4]; + int err; + + if (ddp) { + kref_get(&ddp->refcnt); + pr_warn("cdev 0x%p, ddp 0x%p already set up.\n", + cdev, cdev->ddp); + return -EALREADY; + } + + err = cxgbi_ddp_init(cdev, lldi->vr->iscsi.start, + lldi->vr->iscsi.start + lldi->vr->iscsi.size - 1, + lldi->iscsi_iolen, lldi->iscsi_iolen); + if (err < 0) + return err; + + ddp = cdev->ddp; + + tagmask = ddp->idx_mask << PPOD_IDX_SHIFT; + cxgbi_ddp_page_size_factor(pgsz_factor); + cxgb4_iscsi_init(lldi->ports[0], tagmask, pgsz_factor); + + cdev->csk_ddp_free_gl_skb = NULL; + cdev->csk_ddp_alloc_gl_skb = NULL; + cdev->csk_ddp_setup_digest = ddp_setup_conn_digest; + cdev->csk_ddp_setup_pgidx = ddp_setup_conn_pgidx; + cdev->csk_ddp_set = ddp_set_map; + cdev->csk_ddp_clear = ddp_clear_map; + + pr_info("cxgb4i 0x%p tag: sw %u, rsvd %u,%u, mask 0x%x.\n", + cdev, cdev->tag_format.sw_bits, cdev->tag_format.rsvd_bits, + cdev->tag_format.rsvd_shift, cdev->tag_format.rsvd_mask); + pr_info("cxgb4i 0x%p, nppods %u, bits %u, mask 0x%x,0x%x pkt %u/%u, " + " %u/%u.\n", + cdev, ddp->nppods, ddp->idx_bits, ddp->idx_mask, + ddp->rsvd_tag_mask, ddp->max_txsz, lldi->iscsi_iolen, + ddp->max_rxsz, lldi->iscsi_iolen); + pr_info("cxgb4i 0x%p max payload size: %u/%u, %u/%u.\n", + cdev, cdev->tx_max_size, ddp->max_txsz, cdev->rx_max_size, + ddp->max_rxsz); + return 0; +} + +static void *t4_uld_add(const struct cxgb4_lld_info *lldi) +{ + struct cxgbi_device *cdev; + struct port_info *pi; + int i, rc; + + cdev = cxgbi_device_register(sizeof(*lldi), lldi->nports); + if (!cdev) { + pr_info("t4 device 0x%p, register failed.\n", lldi); + return NULL; + } + pr_info("0x%p,0x%x, ports %u,%s, chan %u, q %u,%u, wr %u.\n", + cdev, lldi->adapter_type, lldi->nports, + lldi->ports[0]->name, lldi->nchan, lldi->ntxq, + lldi->nrxq, lldi->wr_cred); + for (i = 0; i < lldi->nrxq; i++) + log_debug(1 << CXGBI_DBG_DEV, + "t4 0x%p, rxq id #%d: %u.\n", + cdev, i, lldi->rxq_ids[i]); + + memcpy(cxgbi_cdev_priv(cdev), lldi, sizeof(*lldi)); + cdev->flags = CXGBI_FLAG_DEV_T4; + cdev->pdev = lldi->pdev; + cdev->ports = lldi->ports; + cdev->nports = lldi->nports; + cdev->mtus = lldi->mtus; + cdev->nmtus = NMTUS; + cdev->snd_win = cxgb4i_snd_win; + cdev->rcv_win = cxgb4i_rcv_win; + cdev->rx_credit_thres = cxgb4i_rx_credit_thres; + cdev->skb_tx_rsvd = CXGB4I_TX_HEADER_LEN; + cdev->skb_rx_extra = sizeof(struct cpl_iscsi_hdr); + cdev->itp = &cxgb4i_iscsi_transport; + + cdev->pfvf = FW_VIID_PFN_GET(cxgb4_port_viid(lldi->ports[0])) << 8; + pr_info("cdev 0x%p,%s, pfvf %u.\n", + cdev, lldi->ports[0]->name, cdev->pfvf); + + rc = cxgb4i_ddp_init(cdev); + if (rc) { + pr_info("t4 0x%p ddp init failed.\n", cdev); + goto err_out; + } + rc = cxgb4i_ofld_init(cdev); + if (rc) { + pr_info("t4 0x%p ofld init failed.\n", cdev); + goto err_out; + } + + rc = cxgbi_hbas_add(cdev, CXGB4I_MAX_LUN, CXGBI_MAX_CONN, + &cxgb4i_host_template, cxgb4i_stt); + if (rc) + goto err_out; + + for (i = 0; i < cdev->nports; i++) { + pi = netdev_priv(lldi->ports[i]); + cdev->hbas[i]->port_id = pi->port_id; + } + return cdev; + +err_out: + cxgbi_device_unregister(cdev); + return ERR_PTR(-ENOMEM); +} + +#define RX_PULL_LEN 128 +static int t4_uld_rx_handler(void *handle, const __be64 *rsp, + const struct pkt_gl *pgl) +{ + const struct cpl_act_establish *rpl; + struct sk_buff *skb; + unsigned int opc; + struct cxgbi_device *cdev = handle; + + if (pgl == NULL) { + unsigned int len = 64 - sizeof(struct rsp_ctrl) - 8; + + skb = alloc_wr(len, 0, GFP_ATOMIC); + if (!skb) + goto nomem; + skb_copy_to_linear_data(skb, &rsp[1], len); + } else { + if (unlikely(*(u8 *)rsp != *(u8 *)pgl->va)) { + pr_info("? FL 0x%p,RSS%#llx,FL %#llx,len %u.\n", + pgl->va, be64_to_cpu(*rsp), + be64_to_cpu(*(u64 *)pgl->va), + pgl->tot_len); + return 0; + } + skb = cxgb4_pktgl_to_skb(pgl, RX_PULL_LEN, RX_PULL_LEN); + if (unlikely(!skb)) + goto nomem; + } + + rpl = (struct cpl_act_establish *)skb->data; + opc = rpl->ot.opcode; + log_debug(1 << CXGBI_DBG_TOE, + "cdev %p, opcode 0x%x(0x%x,0x%x), skb %p.\n", + cdev, opc, rpl->ot.opcode_tid, ntohl(rpl->ot.opcode_tid), skb); + if (cxgb4i_cplhandlers[opc]) + cxgb4i_cplhandlers[opc](cdev, skb); + else { + pr_err("No handler for opcode 0x%x.\n", opc); + __kfree_skb(skb); + } + return 0; +nomem: + log_debug(1 << CXGBI_DBG_TOE, "OOM bailing out.\n"); + return 1; +} + +static int t4_uld_state_change(void *handle, enum cxgb4_state state) +{ + struct cxgbi_device *cdev = handle; + + switch (state) { + case CXGB4_STATE_UP: + pr_info("cdev 0x%p, UP.\n", cdev); + /* re-initialize */ + break; + case CXGB4_STATE_START_RECOVERY: + pr_info("cdev 0x%p, RECOVERY.\n", cdev); + /* close all connections */ + break; + case CXGB4_STATE_DOWN: + pr_info("cdev 0x%p, DOWN.\n", cdev); + break; + case CXGB4_STATE_DETACH: + pr_info("cdev 0x%p, DETACH.\n", cdev); + break; + default: + pr_info("cdev 0x%p, unknown state %d.\n", cdev, state); + break; + } + return 0; +} + +static int __init cxgb4i_init_module(void) +{ + int rc; + + printk(KERN_INFO "%s", version); + + rc = cxgbi_iscsi_init(&cxgb4i_iscsi_transport, &cxgb4i_stt); + if (rc < 0) + return rc; + cxgb4_register_uld(CXGB4_ULD_ISCSI, &cxgb4i_uld_info); + return 0; +} + +static void __exit cxgb4i_exit_module(void) +{ + cxgb4_unregister_uld(CXGB4_ULD_ISCSI); + cxgbi_device_unregister_all(CXGBI_FLAG_DEV_T4); + cxgbi_iscsi_cleanup(&cxgb4i_iscsi_transport, &cxgb4i_stt); +} + +module_init(cxgb4i_init_module); +module_exit(cxgb4i_exit_module); diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.h b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.h new file mode 100644 index 000000000000..1096026ba241 --- /dev/null +++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.h @@ -0,0 +1,43 @@ +/* + * cxgb4i.h: Chelsio T4 iSCSI driver. + * + * Copyright (c) 2010 Chelsio Communications, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + * + * Written by: Karen Xie (kxie@chelsio.com) + * Written by: Rakesh Ranjan (rranjan@chelsio.com) + */ + +#ifndef __CXGB4I_H__ +#define __CXGB4I_H__ + +#define CXGB4I_SCSI_HOST_QDEPTH 1024 +#define CXGB4I_MAX_CONN 16384 +#define CXGB4I_MAX_TARGET CXGB4I_MAX_CONN +#define CXGB4I_MAX_LUN 0x1000 + +/* for TX: a skb must have a headroom of at least TX_HEADER_LEN bytes */ +#define CXGB4I_TX_HEADER_LEN \ + (sizeof(struct fw_ofld_tx_data_wr) + sizeof(struct sge_opaque_hdr)) + +struct ulptx_idata { + __be32 cmd_more; + __be32 len; +}; + +struct cpl_rx_data_ddp { + union opcode_tid ot; + __be16 urg; + __be16 len; + __be32 seq; + union { + __be32 nxt_seq; + __be32 ddp_report; + }; + __be32 ulp_crc; + __be32 ddpvld; +}; +#endif /* __CXGB4I_H__ */ diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c new file mode 100644 index 000000000000..be5661707dfa --- /dev/null +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -0,0 +1,2612 @@ +/* + * libcxgbi.c: Chelsio common library for T3/T4 iSCSI driver. + * + * Copyright (c) 2010 Chelsio Communications, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + * + * Written by: Karen Xie (kxie@chelsio.com) + * Written by: Rakesh Ranjan (rranjan@chelsio.com) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__ + +#include <linux/skbuff.h> +#include <linux/crypto.h> +#include <linux/scatterlist.h> +#include <linux/pci.h> +#include <scsi/scsi.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_host.h> +#include <linux/if_vlan.h> +#include <linux/inet.h> +#include <net/dst.h> +#include <net/route.h> +#include <linux/inetdevice.h> /* ip_dev_find */ +#include <net/tcp.h> + +static unsigned int dbg_level; + +#include "libcxgbi.h" + +#define DRV_MODULE_NAME "libcxgbi" +#define DRV_MODULE_DESC "Chelsio iSCSI driver library" +#define DRV_MODULE_VERSION "0.9.0" +#define DRV_MODULE_RELDATE "Jun. 2010" + +MODULE_AUTHOR("Chelsio Communications, Inc."); +MODULE_DESCRIPTION(DRV_MODULE_DESC); +MODULE_VERSION(DRV_MODULE_VERSION); +MODULE_LICENSE("GPL"); + +module_param(dbg_level, uint, 0644); +MODULE_PARM_DESC(dbg_level, "libiscsi debug level (default=0)"); + + +/* + * cxgbi device management + * maintains a list of the cxgbi devices + */ +static LIST_HEAD(cdev_list); +static DEFINE_MUTEX(cdev_mutex); + +int cxgbi_device_portmap_create(struct cxgbi_device *cdev, unsigned int base, + unsigned int max_conn) +{ + struct cxgbi_ports_map *pmap = &cdev->pmap; + + pmap->port_csk = cxgbi_alloc_big_mem(max_conn * + sizeof(struct cxgbi_sock *), + GFP_KERNEL); + if (!pmap->port_csk) { + pr_warn("cdev 0x%p, portmap OOM %u.\n", cdev, max_conn); + return -ENOMEM; + } + + pmap->max_connect = max_conn; + pmap->sport_base = base; + spin_lock_init(&pmap->lock); + return 0; +} +EXPORT_SYMBOL_GPL(cxgbi_device_portmap_create); + +void cxgbi_device_portmap_cleanup(struct cxgbi_device *cdev) +{ + struct cxgbi_ports_map *pmap = &cdev->pmap; + struct cxgbi_sock *csk; + int i; + + for (i = 0; i < pmap->max_connect; i++) { + if (pmap->port_csk[i]) { + csk = pmap->port_csk[i]; + pmap->port_csk[i] = NULL; + log_debug(1 << CXGBI_DBG_SOCK, + "csk 0x%p, cdev 0x%p, offload down.\n", + csk, cdev); + spin_lock_bh(&csk->lock); + cxgbi_sock_set_flag(csk, CTPF_OFFLOAD_DOWN); + cxgbi_sock_closed(csk); + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); + } + } +} +EXPORT_SYMBOL_GPL(cxgbi_device_portmap_cleanup); + +static inline void cxgbi_device_destroy(struct cxgbi_device *cdev) +{ + log_debug(1 << CXGBI_DBG_DEV, + "cdev 0x%p, p# %u.\n", cdev, cdev->nports); + cxgbi_hbas_remove(cdev); + cxgbi_device_portmap_cleanup(cdev); + if (cdev->dev_ddp_cleanup) + cdev->dev_ddp_cleanup(cdev); + else + cxgbi_ddp_cleanup(cdev); + if (cdev->ddp) + cxgbi_ddp_cleanup(cdev); + if (cdev->pmap.max_connect) + cxgbi_free_big_mem(cdev->pmap.port_csk); + kfree(cdev); +} + +struct cxgbi_device *cxgbi_device_register(unsigned int extra, + unsigned int nports) +{ + struct cxgbi_device *cdev; + + cdev = kzalloc(sizeof(*cdev) + extra + nports * + (sizeof(struct cxgbi_hba *) + + sizeof(struct net_device *)), + GFP_KERNEL); + if (!cdev) { + pr_warn("nport %d, OOM.\n", nports); + return NULL; + } + cdev->ports = (struct net_device **)(cdev + 1); + cdev->hbas = (struct cxgbi_hba **)(((char*)cdev->ports) + nports * + sizeof(struct net_device *)); + if (extra) + cdev->dd_data = ((char *)cdev->hbas) + + nports * sizeof(struct cxgbi_hba *); + spin_lock_init(&cdev->pmap.lock); + + mutex_lock(&cdev_mutex); + list_add_tail(&cdev->list_head, &cdev_list); + mutex_unlock(&cdev_mutex); + + log_debug(1 << CXGBI_DBG_DEV, + "cdev 0x%p, p# %u.\n", cdev, nports); + return cdev; +} +EXPORT_SYMBOL_GPL(cxgbi_device_register); + +void cxgbi_device_unregister(struct cxgbi_device *cdev) +{ + log_debug(1 << CXGBI_DBG_DEV, + "cdev 0x%p, p# %u,%s.\n", + cdev, cdev->nports, cdev->nports ? cdev->ports[0]->name : ""); + mutex_lock(&cdev_mutex); + list_del(&cdev->list_head); + mutex_unlock(&cdev_mutex); + cxgbi_device_destroy(cdev); +} +EXPORT_SYMBOL_GPL(cxgbi_device_unregister); + +void cxgbi_device_unregister_all(unsigned int flag) +{ + struct cxgbi_device *cdev, *tmp; + + mutex_lock(&cdev_mutex); + list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) { + if ((cdev->flags & flag) == flag) { + log_debug(1 << CXGBI_DBG_DEV, + "cdev 0x%p, p# %u,%s.\n", + cdev, cdev->nports, cdev->nports ? + cdev->ports[0]->name : ""); + list_del(&cdev->list_head); + cxgbi_device_destroy(cdev); + } + } + mutex_unlock(&cdev_mutex); +} +EXPORT_SYMBOL_GPL(cxgbi_device_unregister_all); + +struct cxgbi_device *cxgbi_device_find_by_lldev(void *lldev) +{ + struct cxgbi_device *cdev, *tmp; + + mutex_lock(&cdev_mutex); + list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) { + if (cdev->lldev == lldev) { + mutex_unlock(&cdev_mutex); + return cdev; + } + } + mutex_unlock(&cdev_mutex); + log_debug(1 << CXGBI_DBG_DEV, + "lldev 0x%p, NO match found.\n", lldev); + return NULL; +} +EXPORT_SYMBOL_GPL(cxgbi_device_find_by_lldev); + +static struct cxgbi_device *cxgbi_device_find_by_netdev(struct net_device *ndev, + int *port) +{ + struct net_device *vdev = NULL; + struct cxgbi_device *cdev, *tmp; + int i; + + if (ndev->priv_flags & IFF_802_1Q_VLAN) { + vdev = ndev; + ndev = vlan_dev_real_dev(ndev); + log_debug(1 << CXGBI_DBG_DEV, + "vlan dev %s -> %s.\n", vdev->name, ndev->name); + } + + mutex_lock(&cdev_mutex); + list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) { + for (i = 0; i < cdev->nports; i++) { + if (ndev == cdev->ports[i]) { + cdev->hbas[i]->vdev = vdev; + mutex_unlock(&cdev_mutex); + if (port) + *port = i; + return cdev; + } + } + } + mutex_unlock(&cdev_mutex); + log_debug(1 << CXGBI_DBG_DEV, + "ndev 0x%p, %s, NO match found.\n", ndev, ndev->name); + return NULL; +} + +void cxgbi_hbas_remove(struct cxgbi_device *cdev) +{ + int i; + struct cxgbi_hba *chba; + + log_debug(1 << CXGBI_DBG_DEV, + "cdev 0x%p, p#%u.\n", cdev, cdev->nports); + + for (i = 0; i < cdev->nports; i++) { + chba = cdev->hbas[i]; + if (chba) { + cdev->hbas[i] = NULL; + iscsi_host_remove(chba->shost); + pci_dev_put(cdev->pdev); + iscsi_host_free(chba->shost); + } + } +} +EXPORT_SYMBOL_GPL(cxgbi_hbas_remove); + +int cxgbi_hbas_add(struct cxgbi_device *cdev, unsigned int max_lun, + unsigned int max_id, struct scsi_host_template *sht, + struct scsi_transport_template *stt) +{ + struct cxgbi_hba *chba; + struct Scsi_Host *shost; + int i, err; + + log_debug(1 << CXGBI_DBG_DEV, "cdev 0x%p, p#%u.\n", cdev, cdev->nports); + + for (i = 0; i < cdev->nports; i++) { + shost = iscsi_host_alloc(sht, sizeof(*chba), 1); + if (!shost) { + pr_info("0x%p, p%d, %s, host alloc failed.\n", + cdev, i, cdev->ports[i]->name); + err = -ENOMEM; + goto err_out; + } + + shost->transportt = stt; + shost->max_lun = max_lun; + shost->max_id = max_id; + shost->max_channel = 0; + shost->max_cmd_len = 16; + + chba = iscsi_host_priv(shost); + chba->cdev = cdev; + chba->ndev = cdev->ports[i]; + chba->shost = shost; + + log_debug(1 << CXGBI_DBG_DEV, + "cdev 0x%p, p#%d %s: chba 0x%p.\n", + cdev, i, cdev->ports[i]->name, chba); + + pci_dev_get(cdev->pdev); + err = iscsi_host_add(shost, &cdev->pdev->dev); + if (err) { + pr_info("cdev 0x%p, p#%d %s, host add failed.\n", + cdev, i, cdev->ports[i]->name); + pci_dev_put(cdev->pdev); + scsi_host_put(shost); + goto err_out; + } + + cdev->hbas[i] = chba; + } + + return 0; + +err_out: + cxgbi_hbas_remove(cdev); + return err; +} +EXPORT_SYMBOL_GPL(cxgbi_hbas_add); + +/* + * iSCSI offload + * + * - source port management + * To find a free source port in the port allocation map we use a very simple + * rotor scheme to look for the next free port. + * + * If a source port has been specified make sure that it doesn't collide with + * our normal source port allocation map. If it's outside the range of our + * allocation/deallocation scheme just let them use it. + * + * If the source port is outside our allocation range, the caller is + * responsible for keeping track of their port usage. + */ +static int sock_get_port(struct cxgbi_sock *csk) +{ + struct cxgbi_device *cdev = csk->cdev; + struct cxgbi_ports_map *pmap = &cdev->pmap; + unsigned int start; + int idx; + + if (!pmap->max_connect) { + pr_err("cdev 0x%p, p#%u %s, NO port map.\n", + cdev, csk->port_id, cdev->ports[csk->port_id]->name); + return -EADDRNOTAVAIL; + } + + if (csk->saddr.sin_port) { + pr_err("source port NON-ZERO %u.\n", + ntohs(csk->saddr.sin_port)); + return -EADDRINUSE; + } + + spin_lock_bh(&pmap->lock); + if (pmap->used >= pmap->max_connect) { + spin_unlock_bh(&pmap->lock); + pr_info("cdev 0x%p, p#%u %s, ALL ports used.\n", + cdev, csk->port_id, cdev->ports[csk->port_id]->name); + return -EADDRNOTAVAIL; + } + + start = idx = pmap->next; + do { + if (++idx >= pmap->max_connect) + idx = 0; + if (!pmap->port_csk[idx]) { + pmap->used++; + csk->saddr.sin_port = + htons(pmap->sport_base + idx); + pmap->next = idx; + pmap->port_csk[idx] = csk; + spin_unlock_bh(&pmap->lock); + cxgbi_sock_get(csk); + log_debug(1 << CXGBI_DBG_SOCK, + "cdev 0x%p, p#%u %s, p %u, %u.\n", + cdev, csk->port_id, + cdev->ports[csk->port_id]->name, + pmap->sport_base + idx, pmap->next); + return 0; + } + } while (idx != start); + spin_unlock_bh(&pmap->lock); + + /* should not happen */ + pr_warn("cdev 0x%p, p#%u %s, next %u?\n", + cdev, csk->port_id, cdev->ports[csk->port_id]->name, + pmap->next); + return -EADDRNOTAVAIL; +} + +static void sock_put_port(struct cxgbi_sock *csk) +{ + struct cxgbi_device *cdev = csk->cdev; + struct cxgbi_ports_map *pmap = &cdev->pmap; + + if (csk->saddr.sin_port) { + int idx = ntohs(csk->saddr.sin_port) - pmap->sport_base; + + csk->saddr.sin_port = 0; + if (idx < 0 || idx >= pmap->max_connect) { + pr_err("cdev 0x%p, p#%u %s, port %u OOR.\n", + cdev, csk->port_id, + cdev->ports[csk->port_id]->name, + ntohs(csk->saddr.sin_port)); + return; + } + + spin_lock_bh(&pmap->lock); + pmap->port_csk[idx] = NULL; + pmap->used--; + spin_unlock_bh(&pmap->lock); + + log_debug(1 << CXGBI_DBG_SOCK, + "cdev 0x%p, p#%u %s, release %u.\n", + cdev, csk->port_id, cdev->ports[csk->port_id]->name, + pmap->sport_base + idx); + + cxgbi_sock_put(csk); + } +} + +/* + * iscsi tcp connection + */ +void cxgbi_sock_free_cpl_skbs(struct cxgbi_sock *csk) +{ + if (csk->cpl_close) { + kfree_skb(csk->cpl_close); + csk->cpl_close = NULL; + } + if (csk->cpl_abort_req) { + kfree_skb(csk->cpl_abort_req); + csk->cpl_abort_req = NULL; + } + if (csk->cpl_abort_rpl) { + kfree_skb(csk->cpl_abort_rpl); + csk->cpl_abort_rpl = NULL; + } +} +EXPORT_SYMBOL_GPL(cxgbi_sock_free_cpl_skbs); + +static struct cxgbi_sock *cxgbi_sock_create(struct cxgbi_device *cdev) +{ + struct cxgbi_sock *csk = kzalloc(sizeof(*csk), GFP_NOIO); + + if (!csk) { + pr_info("alloc csk %zu failed.\n", sizeof(*csk)); + return NULL; + } + + if (cdev->csk_alloc_cpls(csk) < 0) { + pr_info("csk 0x%p, alloc cpls failed.\n", csk); + kfree(csk); + return NULL; + } + + spin_lock_init(&csk->lock); + kref_init(&csk->refcnt); + skb_queue_head_init(&csk->receive_queue); + skb_queue_head_init(&csk->write_queue); + setup_timer(&csk->retry_timer, NULL, (unsigned long)csk); + rwlock_init(&csk->callback_lock); + csk->cdev = cdev; + csk->flags = 0; + cxgbi_sock_set_state(csk, CTP_CLOSED); + + log_debug(1 << CXGBI_DBG_SOCK, "cdev 0x%p, new csk 0x%p.\n", cdev, csk); + + return csk; +} + +static struct rtable *find_route_ipv4(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport, u8 tos) +{ + struct rtable *rt; + struct flowi fl = { + .oif = 0, + .nl_u = { + .ip4_u = { + .daddr = daddr, + .saddr = saddr, + .tos = tos } + }, + .proto = IPPROTO_TCP, + .uli_u = { + .ports = { + .sport = sport, + .dport = dport } + } + }; + + if (ip_route_output_flow(&init_net, &rt, &fl, NULL, 0)) + return NULL; + + return rt; +} + +static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr) +{ + struct sockaddr_in *daddr = (struct sockaddr_in *)dst_addr; + struct dst_entry *dst; + struct net_device *ndev; + struct cxgbi_device *cdev; + struct rtable *rt = NULL; + struct cxgbi_sock *csk = NULL; + unsigned int mtu = 0; + int port = 0xFFFF; + int err = 0; + + if (daddr->sin_family != AF_INET) { + pr_info("address family 0x%x NOT supported.\n", + daddr->sin_family); + err = -EAFNOSUPPORT; + goto err_out; + } + + rt = find_route_ipv4(0, daddr->sin_addr.s_addr, 0, daddr->sin_port, 0); + if (!rt) { + pr_info("no route to ipv4 0x%x, port %u.\n", + daddr->sin_addr.s_addr, daddr->sin_port); + err = -ENETUNREACH; + goto err_out; + } + dst = &rt->dst; + ndev = dst->neighbour->dev; + + if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { + pr_info("multi-cast route %pI4, port %u, dev %s.\n", + &daddr->sin_addr.s_addr, ntohs(daddr->sin_port), + ndev->name); + err = -ENETUNREACH; + goto rel_rt; + } + + if (ndev->flags & IFF_LOOPBACK) { + ndev = ip_dev_find(&init_net, daddr->sin_addr.s_addr); + mtu = ndev->mtu; + pr_info("rt dev %s, loopback -> %s, mtu %u.\n", + dst->neighbour->dev->name, ndev->name, mtu); + } + + cdev = cxgbi_device_find_by_netdev(ndev, &port); + if (!cdev) { + pr_info("dst %pI4, %s, NOT cxgbi device.\n", + &daddr->sin_addr.s_addr, ndev->name); + err = -ENETUNREACH; + goto rel_rt; + } + log_debug(1 << CXGBI_DBG_SOCK, + "route to %pI4 :%u, ndev p#%d,%s, cdev 0x%p.\n", + &daddr->sin_addr.s_addr, ntohs(daddr->sin_port), + port, ndev->name, cdev); + + csk = cxgbi_sock_create(cdev); + if (!csk) { + err = -ENOMEM; + goto rel_rt; + } + csk->cdev = cdev; + csk->port_id = port; + csk->mtu = mtu; + csk->dst = dst; + csk->daddr.sin_addr.s_addr = daddr->sin_addr.s_addr; + csk->daddr.sin_port = daddr->sin_port; + csk->saddr.sin_addr.s_addr = rt->rt_src; + + return csk; + +rel_rt: + ip_rt_put(rt); + if (csk) + cxgbi_sock_closed(csk); +err_out: + return ERR_PTR(err); +} + +void cxgbi_sock_established(struct cxgbi_sock *csk, unsigned int snd_isn, + unsigned int opt) +{ + csk->write_seq = csk->snd_nxt = csk->snd_una = snd_isn; + dst_confirm(csk->dst); + smp_mb(); + cxgbi_sock_set_state(csk, CTP_ESTABLISHED); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_established); + +static void cxgbi_inform_iscsi_conn_closing(struct cxgbi_sock *csk) +{ + log_debug(1 << CXGBI_DBG_SOCK, + "csk 0x%p, state %u, flags 0x%lx, conn 0x%p.\n", + csk, csk->state, csk->flags, csk->user_data); + + if (csk->state != CTP_ESTABLISHED) { + read_lock_bh(&csk->callback_lock); + if (csk->user_data) + iscsi_conn_failure(csk->user_data, + ISCSI_ERR_CONN_FAILED); + read_unlock_bh(&csk->callback_lock); + } +} + +void cxgbi_sock_closed(struct cxgbi_sock *csk) +{ + log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n", + csk, (csk)->state, (csk)->flags, (csk)->tid); + cxgbi_sock_set_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED); + if (csk->state == CTP_ACTIVE_OPEN || csk->state == CTP_CLOSED) + return; + if (csk->saddr.sin_port) + sock_put_port(csk); + if (csk->dst) + dst_release(csk->dst); + csk->cdev->csk_release_offload_resources(csk); + cxgbi_sock_set_state(csk, CTP_CLOSED); + cxgbi_inform_iscsi_conn_closing(csk); + cxgbi_sock_put(csk); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_closed); + +static void need_active_close(struct cxgbi_sock *csk) +{ + int data_lost; + int close_req = 0; + + log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n", + csk, (csk)->state, (csk)->flags, (csk)->tid); + spin_lock_bh(&csk->lock); + dst_confirm(csk->dst); + data_lost = skb_queue_len(&csk->receive_queue); + __skb_queue_purge(&csk->receive_queue); + + if (csk->state == CTP_ACTIVE_OPEN) + cxgbi_sock_set_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED); + else if (csk->state == CTP_ESTABLISHED) { + close_req = 1; + cxgbi_sock_set_state(csk, CTP_ACTIVE_CLOSE); + } else if (csk->state == CTP_PASSIVE_CLOSE) { + close_req = 1; + cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_2); + } + + if (close_req) { + if (data_lost) + csk->cdev->csk_send_abort_req(csk); + else + csk->cdev->csk_send_close_req(csk); + } + + spin_unlock_bh(&csk->lock); +} + +void cxgbi_sock_fail_act_open(struct cxgbi_sock *csk, int errno) +{ + pr_info("csk 0x%p,%u,%lx, %pI4:%u-%pI4:%u, err %d.\n", + csk, csk->state, csk->flags, + &csk->saddr.sin_addr.s_addr, csk->saddr.sin_port, + &csk->daddr.sin_addr.s_addr, csk->daddr.sin_port, + errno); + + cxgbi_sock_set_state(csk, CTP_CONNECTING); + csk->err = errno; + cxgbi_sock_closed(csk); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_fail_act_open); + +void cxgbi_sock_act_open_req_arp_failure(void *handle, struct sk_buff *skb) +{ + struct cxgbi_sock *csk = (struct cxgbi_sock *)skb->sk; + + log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n", + csk, (csk)->state, (csk)->flags, (csk)->tid); + cxgbi_sock_get(csk); + spin_lock_bh(&csk->lock); + if (csk->state == CTP_ACTIVE_OPEN) + cxgbi_sock_fail_act_open(csk, -EHOSTUNREACH); + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); + __kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_act_open_req_arp_failure); + +void cxgbi_sock_rcv_abort_rpl(struct cxgbi_sock *csk) +{ + cxgbi_sock_get(csk); + spin_lock_bh(&csk->lock); + if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING)) { + if (!cxgbi_sock_flag(csk, CTPF_ABORT_RPL_RCVD)) + cxgbi_sock_set_flag(csk, CTPF_ABORT_RPL_RCVD); + else { + cxgbi_sock_clear_flag(csk, CTPF_ABORT_RPL_RCVD); + cxgbi_sock_clear_flag(csk, CTPF_ABORT_RPL_PENDING); + if (cxgbi_sock_flag(csk, CTPF_ABORT_REQ_RCVD)) + pr_err("csk 0x%p,%u,0x%lx,%u,ABT_RPL_RSS.\n", + csk, csk->state, csk->flags, csk->tid); + cxgbi_sock_closed(csk); + } + } + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_abort_rpl); + +void cxgbi_sock_rcv_peer_close(struct cxgbi_sock *csk) +{ + log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n", + csk, (csk)->state, (csk)->flags, (csk)->tid); + cxgbi_sock_get(csk); + spin_lock_bh(&csk->lock); + + if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING)) + goto done; + + switch (csk->state) { + case CTP_ESTABLISHED: + cxgbi_sock_set_state(csk, CTP_PASSIVE_CLOSE); + break; + case CTP_ACTIVE_CLOSE: + cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_2); + break; + case CTP_CLOSE_WAIT_1: + cxgbi_sock_closed(csk); + break; + case CTP_ABORTING: + break; + default: + pr_err("csk 0x%p,%u,0x%lx,%u, bad state.\n", + csk, csk->state, csk->flags, csk->tid); + } + cxgbi_inform_iscsi_conn_closing(csk); +done: + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_peer_close); + +void cxgbi_sock_rcv_close_conn_rpl(struct cxgbi_sock *csk, u32 snd_nxt) +{ + log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n", + csk, (csk)->state, (csk)->flags, (csk)->tid); + cxgbi_sock_get(csk); + spin_lock_bh(&csk->lock); + + csk->snd_una = snd_nxt - 1; + if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING)) + goto done; + + switch (csk->state) { + case CTP_ACTIVE_CLOSE: + cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_1); + break; + case CTP_CLOSE_WAIT_1: + case CTP_CLOSE_WAIT_2: + cxgbi_sock_closed(csk); + break; + case CTP_ABORTING: + break; + default: + pr_err("csk 0x%p,%u,0x%lx,%u, bad state.\n", + csk, csk->state, csk->flags, csk->tid); + } +done: + spin_unlock_bh(&csk->lock); + cxgbi_sock_put(csk); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_close_conn_rpl); + +void cxgbi_sock_rcv_wr_ack(struct cxgbi_sock *csk, unsigned int credits, + unsigned int snd_una, int seq_chk) +{ + log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx,%u, cr %u,%u+%u, snd_una %u,%d.\n", + csk, csk->state, csk->flags, csk->tid, credits, + csk->wr_cred, csk->wr_una_cred, snd_una, seq_chk); + + spin_lock_bh(&csk->lock); + + csk->wr_cred += credits; + if (csk->wr_una_cred > csk->wr_max_cred - csk->wr_cred) + csk->wr_una_cred = csk->wr_max_cred - csk->wr_cred; + + while (credits) { + struct sk_buff *p = cxgbi_sock_peek_wr(csk); + + if (unlikely(!p)) { + pr_err("csk 0x%p,%u,0x%lx,%u, cr %u,%u+%u, empty.\n", + csk, csk->state, csk->flags, csk->tid, credits, + csk->wr_cred, csk->wr_una_cred); + break; + } + + if (unlikely(credits < p->csum)) { + pr_warn("csk 0x%p,%u,0x%lx,%u, cr %u,%u+%u, < %u.\n", + csk, csk->state, csk->flags, csk->tid, + credits, csk->wr_cred, csk->wr_una_cred, + p->csum); + p->csum -= credits; + break; + } else { + cxgbi_sock_dequeue_wr(csk); + credits -= p->csum; + kfree_skb(p); + } + } + + cxgbi_sock_check_wr_invariants(csk); + + if (seq_chk) { + if (unlikely(before(snd_una, csk->snd_una))) { + pr_warn("csk 0x%p,%u,0x%lx,%u, snd_una %u/%u.", + csk, csk->state, csk->flags, csk->tid, snd_una, + csk->snd_una); + goto done; + } + + if (csk->snd_una != snd_una) { + csk->snd_una = snd_una; + dst_confirm(csk->dst); + } + } + + if (skb_queue_len(&csk->write_queue)) { + if (csk->cdev->csk_push_tx_frames(csk, 0)) + cxgbi_conn_tx_open(csk); + } else + cxgbi_conn_tx_open(csk); +done: + spin_unlock_bh(&csk->lock); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_rcv_wr_ack); + +static unsigned int cxgbi_sock_find_best_mtu(struct cxgbi_sock *csk, + unsigned short mtu) +{ + int i = 0; + + while (i < csk->cdev->nmtus - 1 && csk->cdev->mtus[i + 1] <= mtu) + ++i; + + return i; +} + +unsigned int cxgbi_sock_select_mss(struct cxgbi_sock *csk, unsigned int pmtu) +{ + unsigned int idx; + struct dst_entry *dst = csk->dst; + + csk->advmss = dst_metric(dst, RTAX_ADVMSS); + + if (csk->advmss > pmtu - 40) + csk->advmss = pmtu - 40; + if (csk->advmss < csk->cdev->mtus[0] - 40) + csk->advmss = csk->cdev->mtus[0] - 40; + idx = cxgbi_sock_find_best_mtu(csk, csk->advmss + 40); + + return idx; +} +EXPORT_SYMBOL_GPL(cxgbi_sock_select_mss); + +void cxgbi_sock_skb_entail(struct cxgbi_sock *csk, struct sk_buff *skb) +{ + cxgbi_skcb_tcp_seq(skb) = csk->write_seq; + __skb_queue_tail(&csk->write_queue, skb); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_skb_entail); + +void cxgbi_sock_purge_wr_queue(struct cxgbi_sock *csk) +{ + struct sk_buff *skb; + + while ((skb = cxgbi_sock_dequeue_wr(csk)) != NULL) + kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_purge_wr_queue); + +void cxgbi_sock_check_wr_invariants(const struct cxgbi_sock *csk) +{ + int pending = cxgbi_sock_count_pending_wrs(csk); + + if (unlikely(csk->wr_cred + pending != csk->wr_max_cred)) + pr_err("csk 0x%p, tid %u, credit %u + %u != %u.\n", + csk, csk->tid, csk->wr_cred, pending, csk->wr_max_cred); +} +EXPORT_SYMBOL_GPL(cxgbi_sock_check_wr_invariants); + +static int cxgbi_sock_send_pdus(struct cxgbi_sock *csk, struct sk_buff *skb) +{ + struct cxgbi_device *cdev = csk->cdev; + struct sk_buff *next; + int err, copied = 0; + + spin_lock_bh(&csk->lock); + + if (csk->state != CTP_ESTABLISHED) { + log_debug(1 << CXGBI_DBG_PDU_TX, + "csk 0x%p,%u,0x%lx,%u, EAGAIN.\n", + csk, csk->state, csk->flags, csk->tid); + err = -EAGAIN; + goto out_err; + } + + if (csk->err) { + log_debug(1 << CXGBI_DBG_PDU_TX, + "csk 0x%p,%u,0x%lx,%u, EPIPE %d.\n", + csk, csk->state, csk->flags, csk->tid, csk->err); + err = -EPIPE; + goto out_err; + } + + if (csk->write_seq - csk->snd_una >= cdev->snd_win) { + log_debug(1 << CXGBI_DBG_PDU_TX, + "csk 0x%p,%u,0x%lx,%u, FULL %u-%u >= %u.\n", + csk, csk->state, csk->flags, csk->tid, csk->write_seq, + csk->snd_una, cdev->snd_win); + err = -ENOBUFS; + goto out_err; + } + + while (skb) { + int frags = skb_shinfo(skb)->nr_frags + + (skb->len != skb->data_len); + + if (unlikely(skb_headroom(skb) < cdev->skb_tx_rsvd)) { + pr_err("csk 0x%p, skb head %u < %u.\n", + csk, skb_headroom(skb), cdev->skb_tx_rsvd); + err = -EINVAL; + goto out_err; + } + + if (frags >= SKB_WR_LIST_SIZE) { + pr_err("csk 0x%p, frags %d, %u,%u >%u.\n", + csk, skb_shinfo(skb)->nr_frags, skb->len, + skb->data_len, (uint)(SKB_WR_LIST_SIZE)); + err = -EINVAL; + goto out_err; + } + + next = skb->next; + skb->next = NULL; + cxgbi_skcb_set_flag(skb, SKCBF_TX_NEED_HDR); + cxgbi_sock_skb_entail(csk, skb); + copied += skb->len; + csk->write_seq += skb->len + + cxgbi_ulp_extra_len(cxgbi_skcb_ulp_mode(skb)); + skb = next; + } +done: + if (likely(skb_queue_len(&csk->write_queue))) + cdev->csk_push_tx_frames(csk, 1); + spin_unlock_bh(&csk->lock); + return copied; + +out_err: + if (copied == 0 && err == -EPIPE) + copied = csk->err ? csk->err : -EPIPE; + else + copied = err; + goto done; +} + +/* + * Direct Data Placement - + * Directly place the iSCSI Data-In or Data-Out PDU's payload into pre-posted + * final destination host-memory buffers based on the Initiator Task Tag (ITT) + * in Data-In or Target Task Tag (TTT) in Data-Out PDUs. + * The host memory address is programmed into h/w in the format of pagepod + * entries. + * The location of the pagepod entry is encoded into ddp tag which is used as + * the base for ITT/TTT. + */ + +static unsigned char ddp_page_order[DDP_PGIDX_MAX] = {0, 1, 2, 4}; +static unsigned char ddp_page_shift[DDP_PGIDX_MAX] = {12, 13, 14, 16}; +static unsigned char page_idx = DDP_PGIDX_MAX; + +static unsigned char sw_tag_idx_bits; +static unsigned char sw_tag_age_bits; + +/* + * Direct-Data Placement page size adjustment + */ +static int ddp_adjust_page_table(void) +{ + int i; + unsigned int base_order, order; + + if (PAGE_SIZE < (1UL << ddp_page_shift[0])) { + pr_info("PAGE_SIZE 0x%lx too small, min 0x%lx\n", + PAGE_SIZE, 1UL << ddp_page_shift[0]); + return -EINVAL; + } + + base_order = get_order(1UL << ddp_page_shift[0]); + order = get_order(1UL << PAGE_SHIFT); + + for (i = 0; i < DDP_PGIDX_MAX; i++) { + /* first is the kernel page size, then just doubling */ + ddp_page_order[i] = order - base_order + i; + ddp_page_shift[i] = PAGE_SHIFT + i; + } + return 0; +} + +static int ddp_find_page_index(unsigned long pgsz) +{ + int i; + + for (i = 0; i < DDP_PGIDX_MAX; i++) { + if (pgsz == (1UL << ddp_page_shift[i])) + return i; + } + pr_info("ddp page size %lu not supported.\n", pgsz); + return DDP_PGIDX_MAX; +} + +static void ddp_setup_host_page_size(void) +{ + if (page_idx == DDP_PGIDX_MAX) { + page_idx = ddp_find_page_index(PAGE_SIZE); + + if (page_idx == DDP_PGIDX_MAX) { + pr_info("system PAGE %lu, update hw.\n", PAGE_SIZE); + if (ddp_adjust_page_table() < 0) { + pr_info("PAGE %lu, disable ddp.\n", PAGE_SIZE); + return; + } + page_idx = ddp_find_page_index(PAGE_SIZE); + } + pr_info("system PAGE %lu, ddp idx %u.\n", PAGE_SIZE, page_idx); + } +} + +void cxgbi_ddp_page_size_factor(int *pgsz_factor) +{ + int i; + + for (i = 0; i < DDP_PGIDX_MAX; i++) + pgsz_factor[i] = ddp_page_order[i]; +} +EXPORT_SYMBOL_GPL(cxgbi_ddp_page_size_factor); + +/* + * DDP setup & teardown + */ + +void cxgbi_ddp_ppod_set(struct cxgbi_pagepod *ppod, + struct cxgbi_pagepod_hdr *hdr, + struct cxgbi_gather_list *gl, unsigned int gidx) +{ + int i; + + memcpy(ppod, hdr, sizeof(*hdr)); + for (i = 0; i < (PPOD_PAGES_MAX + 1); i++, gidx++) { + ppod->addr[i] = gidx < gl->nelem ? + cpu_to_be64(gl->phys_addr[gidx]) : 0ULL; + } +} +EXPORT_SYMBOL_GPL(cxgbi_ddp_ppod_set); + +void cxgbi_ddp_ppod_clear(struct cxgbi_pagepod *ppod) +{ + memset(ppod, 0, sizeof(*ppod)); +} +EXPORT_SYMBOL_GPL(cxgbi_ddp_ppod_clear); + +static inline int ddp_find_unused_entries(struct cxgbi_ddp_info *ddp, + unsigned int start, unsigned int max, + unsigned int count, + struct cxgbi_gather_list *gl) +{ + unsigned int i, j, k; + + /* not enough entries */ + if ((max - start) < count) { + log_debug(1 << CXGBI_DBG_DDP, + "NOT enough entries %u+%u < %u.\n", start, count, max); + return -EBUSY; + } + + max -= count; + spin_lock(&ddp->map_lock); + for (i = start; i < max;) { + for (j = 0, k = i; j < count; j++, k++) { + if (ddp->gl_map[k]) + break; + } + if (j == count) { + for (j = 0, k = i; j < count; j++, k++) + ddp->gl_map[k] = gl; + spin_unlock(&ddp->map_lock); + return i; + } + i += j + 1; + } + spin_unlock(&ddp->map_lock); + log_debug(1 << CXGBI_DBG_DDP, + "NO suitable entries %u available.\n", count); + return -EBUSY; +} + +static inline void ddp_unmark_entries(struct cxgbi_ddp_info *ddp, + int start, int count) +{ + spin_lock(&ddp->map_lock); + memset(&ddp->gl_map[start], 0, + count * sizeof(struct cxgbi_gather_list *)); + spin_unlock(&ddp->map_lock); +} + +static inline void ddp_gl_unmap(struct pci_dev *pdev, + struct cxgbi_gather_list *gl) +{ + int i; + + for (i = 0; i < gl->nelem; i++) + dma_unmap_page(&pdev->dev, gl->phys_addr[i], PAGE_SIZE, + PCI_DMA_FROMDEVICE); +} + +static inline int ddp_gl_map(struct pci_dev *pdev, + struct cxgbi_gather_list *gl) +{ + int i; + + for (i = 0; i < gl->nelem; i++) { + gl->phys_addr[i] = dma_map_page(&pdev->dev, gl->pages[i], 0, + PAGE_SIZE, + PCI_DMA_FROMDEVICE); + if (unlikely(dma_mapping_error(&pdev->dev, gl->phys_addr[i]))) { + log_debug(1 << CXGBI_DBG_DDP, + "page %d 0x%p, 0x%p dma mapping err.\n", + i, gl->pages[i], pdev); + goto unmap; + } + } + return i; +unmap: + if (i) { + unsigned int nelem = gl->nelem; + + gl->nelem = i; + ddp_gl_unmap(pdev, gl); + gl->nelem = nelem; + } + return -EINVAL; +} + +static void ddp_release_gl(struct cxgbi_gather_list *gl, + struct pci_dev *pdev) +{ + ddp_gl_unmap(pdev, gl); + kfree(gl); +} + +static struct cxgbi_gather_list *ddp_make_gl(unsigned int xferlen, + struct scatterlist *sgl, + unsigned int sgcnt, + struct pci_dev *pdev, + gfp_t gfp) +{ + struct cxgbi_gather_list *gl; + struct scatterlist *sg = sgl; + struct page *sgpage = sg_page(sg); + unsigned int sglen = sg->length; + unsigned int sgoffset = sg->offset; + unsigned int npages = (xferlen + sgoffset + PAGE_SIZE - 1) >> + PAGE_SHIFT; + int i = 1, j = 0; + + if (xferlen < DDP_THRESHOLD) { + log_debug(1 << CXGBI_DBG_DDP, + "xfer %u < threshold %u, no ddp.\n", + xferlen, DDP_THRESHOLD); + return NULL; + } + + gl = kzalloc(sizeof(struct cxgbi_gather_list) + + npages * (sizeof(dma_addr_t) + + sizeof(struct page *)), gfp); + if (!gl) { + log_debug(1 << CXGBI_DBG_DDP, + "xfer %u, %u pages, OOM.\n", xferlen, npages); + return NULL; + } + + log_debug(1 << CXGBI_DBG_DDP, + "xfer %u, sgl %u, gl max %u.\n", xferlen, sgcnt, npages); + + gl->pages = (struct page **)&gl->phys_addr[npages]; + gl->nelem = npages; + gl->length = xferlen; + gl->offset = sgoffset; + gl->pages[0] = sgpage; + + for (i = 1, sg = sg_next(sgl), j = 0; i < sgcnt; + i++, sg = sg_next(sg)) { + struct page *page = sg_page(sg); + + if (sgpage == page && sg->offset == sgoffset + sglen) + sglen += sg->length; + else { + /* make sure the sgl is fit for ddp: + * each has the same page size, and + * all of the middle pages are used completely + */ + if ((j && sgoffset) || ((i != sgcnt - 1) && + ((sglen + sgoffset) & ~PAGE_MASK))) { + log_debug(1 << CXGBI_DBG_DDP, + "page %d/%u, %u + %u.\n", + i, sgcnt, sgoffset, sglen); + goto error_out; + } + + j++; + if (j == gl->nelem || sg->offset) { + log_debug(1 << CXGBI_DBG_DDP, + "page %d/%u, offset %u.\n", + j, gl->nelem, sg->offset); + goto error_out; + } + gl->pages[j] = page; + sglen = sg->length; + sgoffset = sg->offset; + sgpage = page; + } + } + gl->nelem = ++j; + + if (ddp_gl_map(pdev, gl) < 0) + goto error_out; + + return gl; + +error_out: + kfree(gl); + return NULL; +} + +static void ddp_tag_release(struct cxgbi_hba *chba, u32 tag) +{ + struct cxgbi_device *cdev = chba->cdev; + struct cxgbi_ddp_info *ddp = cdev->ddp; + u32 idx; + + idx = (tag >> PPOD_IDX_SHIFT) & ddp->idx_mask; + if (idx < ddp->nppods) { + struct cxgbi_gather_list *gl = ddp->gl_map[idx]; + unsigned int npods; + + if (!gl || !gl->nelem) { + pr_warn("tag 0x%x, idx %u, gl 0x%p, %u.\n", + tag, idx, gl, gl ? gl->nelem : 0); + return; + } + npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT; + log_debug(1 << CXGBI_DBG_DDP, + "tag 0x%x, release idx %u, npods %u.\n", + tag, idx, npods); + cdev->csk_ddp_clear(chba, tag, idx, npods); + ddp_unmark_entries(ddp, idx, npods); + ddp_release_gl(gl, ddp->pdev); + } else + pr_warn("tag 0x%x, idx %u > max %u.\n", tag, idx, ddp->nppods); +} + +static int ddp_tag_reserve(struct cxgbi_sock *csk, unsigned int tid, + u32 sw_tag, u32 *tagp, struct cxgbi_gather_list *gl, + gfp_t gfp) +{ + struct cxgbi_device *cdev = csk->cdev; + struct cxgbi_ddp_info *ddp = cdev->ddp; + struct cxgbi_tag_format *tformat = &cdev->tag_format; + struct cxgbi_pagepod_hdr hdr; + unsigned int npods; + int idx = -1; + int err = -ENOMEM; + u32 tag; + + npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT; + if (ddp->idx_last == ddp->nppods) + idx = ddp_find_unused_entries(ddp, 0, ddp->nppods, + npods, gl); + else { + idx = ddp_find_unused_entries(ddp, ddp->idx_last + 1, + ddp->nppods, npods, + gl); + if (idx < 0 && ddp->idx_last >= npods) { + idx = ddp_find_unused_entries(ddp, 0, + min(ddp->idx_last + npods, ddp->nppods), + npods, gl); + } + } + if (idx < 0) { + log_debug(1 << CXGBI_DBG_DDP, + "xferlen %u, gl %u, npods %u NO DDP.\n", + gl->length, gl->nelem, npods); + return idx; + } + + if (cdev->csk_ddp_alloc_gl_skb) { + err = cdev->csk_ddp_alloc_gl_skb(ddp, idx, npods, gfp); + if (err < 0) + goto unmark_entries; + } + + tag = cxgbi_ddp_tag_base(tformat, sw_tag); + tag |= idx << PPOD_IDX_SHIFT; + + hdr.rsvd = 0; + hdr.vld_tid = htonl(PPOD_VALID_FLAG | PPOD_TID(tid)); + hdr.pgsz_tag_clr = htonl(tag & ddp->rsvd_tag_mask); + hdr.max_offset = htonl(gl->length); + hdr.page_offset = htonl(gl->offset); + + err = cdev->csk_ddp_set(csk, &hdr, idx, npods, gl); + if (err < 0) { + if (cdev->csk_ddp_free_gl_skb) + cdev->csk_ddp_free_gl_skb(ddp, idx, npods); + goto unmark_entries; + } + + ddp->idx_last = idx; + log_debug(1 << CXGBI_DBG_DDP, + "xfer %u, gl %u,%u, tid 0x%x, tag 0x%x->0x%x(%u,%u).\n", + gl->length, gl->nelem, gl->offset, tid, sw_tag, tag, idx, + npods); + *tagp = tag; + return 0; + +unmark_entries: + ddp_unmark_entries(ddp, idx, npods); + return err; +} + +int cxgbi_ddp_reserve(struct cxgbi_sock *csk, unsigned int *tagp, + unsigned int sw_tag, unsigned int xferlen, + struct scatterlist *sgl, unsigned int sgcnt, gfp_t gfp) +{ + struct cxgbi_device *cdev = csk->cdev; + struct cxgbi_tag_format *tformat = &cdev->tag_format; + struct cxgbi_gather_list *gl; + int err; + + if (page_idx >= DDP_PGIDX_MAX || !cdev->ddp || + xferlen < DDP_THRESHOLD) { + log_debug(1 << CXGBI_DBG_DDP, + "pgidx %u, xfer %u, NO ddp.\n", page_idx, xferlen); + return -EINVAL; + } + + if (!cxgbi_sw_tag_usable(tformat, sw_tag)) { + log_debug(1 << CXGBI_DBG_DDP, + "sw_tag 0x%x NOT usable.\n", sw_tag); + return -EINVAL; + } + + gl = ddp_make_gl(xferlen, sgl, sgcnt, cdev->pdev, gfp); + if (!gl) + return -ENOMEM; + + err = ddp_tag_reserve(csk, csk->tid, sw_tag, tagp, gl, gfp); + if (err < 0) + ddp_release_gl(gl, cdev->pdev); + + return err; +} + +static void ddp_destroy(struct kref *kref) +{ + struct cxgbi_ddp_info *ddp = container_of(kref, + struct cxgbi_ddp_info, + refcnt); + struct cxgbi_device *cdev = ddp->cdev; + int i = 0; + + pr_info("kref 0, destroy ddp 0x%p, cdev 0x%p.\n", ddp, cdev); + + while (i < ddp->nppods) { + struct cxgbi_gather_list *gl = ddp->gl_map[i]; + + if (gl) { + int npods = (gl->nelem + PPOD_PAGES_MAX - 1) + >> PPOD_PAGES_SHIFT; + pr_info("cdev 0x%p, ddp %d + %d.\n", cdev, i, npods); + kfree(gl); + if (cdev->csk_ddp_free_gl_skb) + cdev->csk_ddp_free_gl_skb(ddp, i, npods); + i += npods; + } else + i++; + } + cxgbi_free_big_mem(ddp); +} + +int cxgbi_ddp_cleanup(struct cxgbi_device *cdev) +{ + struct cxgbi_ddp_info *ddp = cdev->ddp; + + log_debug(1 << CXGBI_DBG_DDP, + "cdev 0x%p, release ddp 0x%p.\n", cdev, ddp); + cdev->ddp = NULL; + if (ddp) + return kref_put(&ddp->refcnt, ddp_destroy); + return 0; +} +EXPORT_SYMBOL_GPL(cxgbi_ddp_cleanup); + +int cxgbi_ddp_init(struct cxgbi_device *cdev, + unsigned int llimit, unsigned int ulimit, + unsigned int max_txsz, unsigned int max_rxsz) +{ + struct cxgbi_ddp_info *ddp; + unsigned int ppmax, bits; + + ppmax = (ulimit - llimit + 1) >> PPOD_SIZE_SHIFT; + bits = __ilog2_u32(ppmax) + 1; + if (bits > PPOD_IDX_MAX_SIZE) + bits = PPOD_IDX_MAX_SIZE; + ppmax = (1 << (bits - 1)) - 1; + + ddp = cxgbi_alloc_big_mem(sizeof(struct cxgbi_ddp_info) + + ppmax * (sizeof(struct cxgbi_gather_list *) + + sizeof(struct sk_buff *)), + GFP_KERNEL); + if (!ddp) { + pr_warn("cdev 0x%p, ddp ppmax %u OOM.\n", cdev, ppmax); + return -ENOMEM; + } + ddp->gl_map = (struct cxgbi_gather_list **)(ddp + 1); + ddp->gl_skb = (struct sk_buff **)(((char *)ddp->gl_map) + + ppmax * sizeof(struct cxgbi_gather_list *)); + cdev->ddp = ddp; + + spin_lock_init(&ddp->map_lock); + kref_init(&ddp->refcnt); + + ddp->cdev = cdev; + ddp->pdev = cdev->pdev; + ddp->llimit = llimit; + ddp->ulimit = ulimit; + ddp->max_txsz = min_t(unsigned int, max_txsz, ULP2_MAX_PKT_SIZE); + ddp->max_rxsz = min_t(unsigned int, max_rxsz, ULP2_MAX_PKT_SIZE); + ddp->nppods = ppmax; + ddp->idx_last = ppmax; + ddp->idx_bits = bits; + ddp->idx_mask = (1 << bits) - 1; + ddp->rsvd_tag_mask = (1 << (bits + PPOD_IDX_SHIFT)) - 1; + + cdev->tag_format.sw_bits = sw_tag_idx_bits + sw_tag_age_bits; + cdev->tag_format.rsvd_bits = ddp->idx_bits; + cdev->tag_format.rsvd_shift = PPOD_IDX_SHIFT; + cdev->tag_format.rsvd_mask = (1 << cdev->tag_format.rsvd_bits) - 1; + + pr_info("%s tag format, sw %u, rsvd %u,%u, mask 0x%x.\n", + cdev->ports[0]->name, cdev->tag_format.sw_bits, + cdev->tag_format.rsvd_bits, cdev->tag_format.rsvd_shift, + cdev->tag_format.rsvd_mask); + + cdev->tx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD, + ddp->max_txsz - ISCSI_PDU_NONPAYLOAD_LEN); + cdev->rx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD, + ddp->max_rxsz - ISCSI_PDU_NONPAYLOAD_LEN); + + log_debug(1 << CXGBI_DBG_DDP, + "%s max payload size: %u/%u, %u/%u.\n", + cdev->ports[0]->name, cdev->tx_max_size, ddp->max_txsz, + cdev->rx_max_size, ddp->max_rxsz); + return 0; +} +EXPORT_SYMBOL_GPL(cxgbi_ddp_init); + +/* + * APIs interacting with open-iscsi libraries + */ + +static unsigned char padding[4]; + +static void task_release_itt(struct iscsi_task *task, itt_t hdr_itt) +{ + struct scsi_cmnd *sc = task->sc; + struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data; + struct cxgbi_conn *cconn = tcp_conn->dd_data; + struct cxgbi_hba *chba = cconn->chba; + struct cxgbi_tag_format *tformat = &chba->cdev->tag_format; + u32 tag = ntohl((__force u32)hdr_itt); + + log_debug(1 << CXGBI_DBG_DDP, + "cdev 0x%p, release tag 0x%x.\n", chba->cdev, tag); + if (sc && + (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE) && + cxgbi_is_ddp_tag(tformat, tag)) + ddp_tag_release(chba, tag); +} + +static int task_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt) +{ + struct scsi_cmnd *sc = task->sc; + struct iscsi_conn *conn = task->conn; + struct iscsi_session *sess = conn->session; + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgbi_conn *cconn = tcp_conn->dd_data; + struct cxgbi_hba *chba = cconn->chba; + struct cxgbi_tag_format *tformat = &chba->cdev->tag_format; + u32 sw_tag = (sess->age << cconn->task_idx_bits) | task->itt; + u32 tag = 0; + int err = -EINVAL; + + if (sc && + (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_FROM_DEVICE)) { + err = cxgbi_ddp_reserve(cconn->cep->csk, &tag, sw_tag, + scsi_in(sc)->length, + scsi_in(sc)->table.sgl, + scsi_in(sc)->table.nents, + GFP_ATOMIC); + if (err < 0) + log_debug(1 << CXGBI_DBG_DDP, + "csk 0x%p, R task 0x%p, %u,%u, no ddp.\n", + cconn->cep->csk, task, scsi_in(sc)->length, + scsi_in(sc)->table.nents); + } + + if (err < 0) + tag = cxgbi_set_non_ddp_tag(tformat, sw_tag); + /* the itt need to sent in big-endian order */ + *hdr_itt = (__force itt_t)htonl(tag); + + log_debug(1 << CXGBI_DBG_DDP, + "cdev 0x%p, task 0x%p, 0x%x(0x%x,0x%x)->0x%x/0x%x.\n", + chba->cdev, task, sw_tag, task->itt, sess->age, tag, *hdr_itt); + return 0; +} + +void cxgbi_parse_pdu_itt(struct iscsi_conn *conn, itt_t itt, int *idx, int *age) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgbi_conn *cconn = tcp_conn->dd_data; + struct cxgbi_device *cdev = cconn->chba->cdev; + u32 tag = ntohl((__force u32) itt); + u32 sw_bits; + + sw_bits = cxgbi_tag_nonrsvd_bits(&cdev->tag_format, tag); + if (idx) + *idx = sw_bits & ((1 << cconn->task_idx_bits) - 1); + if (age) + *age = (sw_bits >> cconn->task_idx_bits) & ISCSI_AGE_MASK; + + log_debug(1 << CXGBI_DBG_DDP, + "cdev 0x%p, tag 0x%x/0x%x, -> 0x%x(0x%x,0x%x).\n", + cdev, tag, itt, sw_bits, idx ? *idx : 0xFFFFF, + age ? *age : 0xFF); +} +EXPORT_SYMBOL_GPL(cxgbi_parse_pdu_itt); + +void cxgbi_conn_tx_open(struct cxgbi_sock *csk) +{ + struct iscsi_conn *conn = csk->user_data; + + if (conn) { + log_debug(1 << CXGBI_DBG_SOCK, + "csk 0x%p, cid %d.\n", csk, conn->id); + iscsi_conn_queue_work(conn); + } +} +EXPORT_SYMBOL_GPL(cxgbi_conn_tx_open); + +/* + * pdu receive, interact with libiscsi_tcp + */ +static inline int read_pdu_skb(struct iscsi_conn *conn, + struct sk_buff *skb, + unsigned int offset, + int offloaded) +{ + int status = 0; + int bytes_read; + + bytes_read = iscsi_tcp_recv_skb(conn, skb, offset, offloaded, &status); + switch (status) { + case ISCSI_TCP_CONN_ERR: + pr_info("skb 0x%p, off %u, %d, TCP_ERR.\n", + skb, offset, offloaded); + return -EIO; + case ISCSI_TCP_SUSPENDED: + log_debug(1 << CXGBI_DBG_PDU_RX, + "skb 0x%p, off %u, %d, TCP_SUSPEND, rc %d.\n", + skb, offset, offloaded, bytes_read); + /* no transfer - just have caller flush queue */ + return bytes_read; + case ISCSI_TCP_SKB_DONE: + pr_info("skb 0x%p, off %u, %d, TCP_SKB_DONE.\n", + skb, offset, offloaded); + /* + * pdus should always fit in the skb and we should get + * segment done notifcation. + */ + iscsi_conn_printk(KERN_ERR, conn, "Invalid pdu or skb."); + return -EFAULT; + case ISCSI_TCP_SEGMENT_DONE: + log_debug(1 << CXGBI_DBG_PDU_RX, + "skb 0x%p, off %u, %d, TCP_SEG_DONE, rc %d.\n", + skb, offset, offloaded, bytes_read); + return bytes_read; + default: + pr_info("skb 0x%p, off %u, %d, invalid status %d.\n", + skb, offset, offloaded, status); + return -EINVAL; + } +} + +static int skb_read_pdu_bhs(struct iscsi_conn *conn, struct sk_buff *skb) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + + log_debug(1 << CXGBI_DBG_PDU_RX, + "conn 0x%p, skb 0x%p, len %u, flag 0x%lx.\n", + conn, skb, skb->len, cxgbi_skcb_flags(skb)); + + if (!iscsi_tcp_recv_segment_is_hdr(tcp_conn)) { + pr_info("conn 0x%p, skb 0x%p, not hdr.\n", conn, skb); + iscsi_conn_failure(conn, ISCSI_ERR_PROTO); + return -EIO; + } + + if (conn->hdrdgst_en && + cxgbi_skcb_test_flag(skb, SKCBF_RX_HCRC_ERR)) { + pr_info("conn 0x%p, skb 0x%p, hcrc.\n", conn, skb); + iscsi_conn_failure(conn, ISCSI_ERR_HDR_DGST); + return -EIO; + } + + return read_pdu_skb(conn, skb, 0, 0); +} + +static int skb_read_pdu_data(struct iscsi_conn *conn, struct sk_buff *lskb, + struct sk_buff *skb, unsigned int offset) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + bool offloaded = 0; + int opcode = tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK; + + log_debug(1 << CXGBI_DBG_PDU_RX, + "conn 0x%p, skb 0x%p, len %u, flag 0x%lx.\n", + conn, skb, skb->len, cxgbi_skcb_flags(skb)); + + if (conn->datadgst_en && + cxgbi_skcb_test_flag(lskb, SKCBF_RX_DCRC_ERR)) { + pr_info("conn 0x%p, skb 0x%p, dcrc 0x%lx.\n", + conn, lskb, cxgbi_skcb_flags(lskb)); + iscsi_conn_failure(conn, ISCSI_ERR_DATA_DGST); + return -EIO; + } + + if (iscsi_tcp_recv_segment_is_hdr(tcp_conn)) + return 0; + + /* coalesced, add header digest length */ + if (lskb == skb && conn->hdrdgst_en) + offset += ISCSI_DIGEST_SIZE; + + if (cxgbi_skcb_test_flag(lskb, SKCBF_RX_DATA_DDPD)) + offloaded = 1; + + if (opcode == ISCSI_OP_SCSI_DATA_IN) + log_debug(1 << CXGBI_DBG_PDU_RX, + "skb 0x%p, op 0x%x, itt 0x%x, %u %s ddp'ed.\n", + skb, opcode, ntohl(tcp_conn->in.hdr->itt), + tcp_conn->in.datalen, offloaded ? "is" : "not"); + + return read_pdu_skb(conn, skb, offset, offloaded); +} + +static void csk_return_rx_credits(struct cxgbi_sock *csk, int copied) +{ + struct cxgbi_device *cdev = csk->cdev; + int must_send; + u32 credits; + + log_debug(1 << CXGBI_DBG_PDU_RX, + "csk 0x%p,%u,0x%lu,%u, seq %u, wup %u, thre %u, %u.\n", + csk, csk->state, csk->flags, csk->tid, csk->copied_seq, + csk->rcv_wup, cdev->rx_credit_thres, + cdev->rcv_win); + + if (csk->state != CTP_ESTABLISHED) + return; + + credits = csk->copied_seq - csk->rcv_wup; + if (unlikely(!credits)) + return; + if (unlikely(cdev->rx_credit_thres == 0)) + return; + + must_send = credits + 16384 >= cdev->rcv_win; + if (must_send || credits >= cdev->rx_credit_thres) + csk->rcv_wup += cdev->csk_send_rx_credits(csk, credits); +} + +void cxgbi_conn_pdu_ready(struct cxgbi_sock *csk) +{ + struct cxgbi_device *cdev = csk->cdev; + struct iscsi_conn *conn = csk->user_data; + struct sk_buff *skb; + unsigned int read = 0; + int err = 0; + + log_debug(1 << CXGBI_DBG_PDU_RX, + "csk 0x%p, conn 0x%p.\n", csk, conn); + + if (unlikely(!conn || conn->suspend_rx)) { + log_debug(1 << CXGBI_DBG_PDU_RX, + "csk 0x%p, conn 0x%p, id %d, suspend_rx %lu!\n", + csk, conn, conn ? conn->id : 0xFF, + conn ? conn->suspend_rx : 0xFF); + return; + } + + while (!err) { + skb = skb_peek(&csk->receive_queue); + if (!skb || + !(cxgbi_skcb_test_flag(skb, SKCBF_RX_STATUS))) { + if (skb) + log_debug(1 << CXGBI_DBG_PDU_RX, + "skb 0x%p, NOT ready 0x%lx.\n", + skb, cxgbi_skcb_flags(skb)); + break; + } + __skb_unlink(skb, &csk->receive_queue); + + read += cxgbi_skcb_rx_pdulen(skb); + log_debug(1 << CXGBI_DBG_PDU_RX, + "csk 0x%p, skb 0x%p,%u,f 0x%lx, pdu len %u.\n", + csk, skb, skb->len, cxgbi_skcb_flags(skb), + cxgbi_skcb_rx_pdulen(skb)); + + if (cxgbi_skcb_test_flag(skb, SKCBF_RX_COALESCED)) { + err = skb_read_pdu_bhs(conn, skb); + if (err < 0) { + pr_err("coalesced bhs, csk 0x%p, skb 0x%p,%u, " + "f 0x%lx, plen %u.\n", + csk, skb, skb->len, + cxgbi_skcb_flags(skb), + cxgbi_skcb_rx_pdulen(skb)); + goto skb_done; + } + err = skb_read_pdu_data(conn, skb, skb, + err + cdev->skb_rx_extra); + if (err < 0) + pr_err("coalesced data, csk 0x%p, skb 0x%p,%u, " + "f 0x%lx, plen %u.\n", + csk, skb, skb->len, + cxgbi_skcb_flags(skb), + cxgbi_skcb_rx_pdulen(skb)); + } else { + err = skb_read_pdu_bhs(conn, skb); + if (err < 0) { + pr_err("bhs, csk 0x%p, skb 0x%p,%u, " + "f 0x%lx, plen %u.\n", + csk, skb, skb->len, + cxgbi_skcb_flags(skb), + cxgbi_skcb_rx_pdulen(skb)); + goto skb_done; + } + + if (cxgbi_skcb_test_flag(skb, SKCBF_RX_DATA)) { + struct sk_buff *dskb; + + dskb = skb_peek(&csk->receive_queue); + if (!dskb) { + pr_err("csk 0x%p, skb 0x%p,%u, f 0x%lx," + " plen %u, NO data.\n", + csk, skb, skb->len, + cxgbi_skcb_flags(skb), + cxgbi_skcb_rx_pdulen(skb)); + err = -EIO; + goto skb_done; + } + __skb_unlink(dskb, &csk->receive_queue); + + err = skb_read_pdu_data(conn, skb, dskb, 0); + if (err < 0) + pr_err("data, csk 0x%p, skb 0x%p,%u, " + "f 0x%lx, plen %u, dskb 0x%p," + "%u.\n", + csk, skb, skb->len, + cxgbi_skcb_flags(skb), + cxgbi_skcb_rx_pdulen(skb), + dskb, dskb->len); + __kfree_skb(dskb); + } else + err = skb_read_pdu_data(conn, skb, skb, 0); + } +skb_done: + __kfree_skb(skb); + + if (err < 0) + break; + } + + log_debug(1 << CXGBI_DBG_PDU_RX, "csk 0x%p, read %u.\n", csk, read); + if (read) { + csk->copied_seq += read; + csk_return_rx_credits(csk, read); + conn->rxdata_octets += read; + } + + if (err < 0) { + pr_info("csk 0x%p, 0x%p, rx failed %d, read %u.\n", + csk, conn, err, read); + iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED); + } +} +EXPORT_SYMBOL_GPL(cxgbi_conn_pdu_ready); + +static int sgl_seek_offset(struct scatterlist *sgl, unsigned int sgcnt, + unsigned int offset, unsigned int *off, + struct scatterlist **sgp) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sgl, sg, sgcnt, i) { + if (offset < sg->length) { + *off = offset; + *sgp = sg; + return 0; + } + offset -= sg->length; + } + return -EFAULT; +} + +static int sgl_read_to_frags(struct scatterlist *sg, unsigned int sgoffset, + unsigned int dlen, skb_frag_t *frags, + int frag_max) +{ + unsigned int datalen = dlen; + unsigned int sglen = sg->length - sgoffset; + struct page *page = sg_page(sg); + int i; + + i = 0; + do { + unsigned int copy; + + if (!sglen) { + sg = sg_next(sg); + if (!sg) { + pr_warn("sg %d NULL, len %u/%u.\n", + i, datalen, dlen); + return -EINVAL; + } + sgoffset = 0; + sglen = sg->length; + page = sg_page(sg); + + } + copy = min(datalen, sglen); + if (i && page == frags[i - 1].page && + sgoffset + sg->offset == + frags[i - 1].page_offset + frags[i - 1].size) { + frags[i - 1].size += copy; + } else { + if (i >= frag_max) { + pr_warn("too many pages %u, dlen %u.\n", + frag_max, dlen); + return -EINVAL; + } + + frags[i].page = page; + frags[i].page_offset = sg->offset + sgoffset; + frags[i].size = copy; + i++; + } + datalen -= copy; + sgoffset += copy; + sglen -= copy; + } while (datalen); + + return i; +} + +int cxgbi_conn_alloc_pdu(struct iscsi_task *task, u8 opcode) +{ + struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data; + struct cxgbi_conn *cconn = tcp_conn->dd_data; + struct cxgbi_device *cdev = cconn->chba->cdev; + struct iscsi_conn *conn = task->conn; + struct iscsi_tcp_task *tcp_task = task->dd_data; + struct cxgbi_task_data *tdata = iscsi_task_cxgbi_data(task); + struct scsi_cmnd *sc = task->sc; + int headroom = SKB_TX_ISCSI_PDU_HEADER_MAX; + + tcp_task->dd_data = tdata; + task->hdr = NULL; + + if (SKB_MAX_HEAD(cdev->skb_tx_rsvd) > (512 * MAX_SKB_FRAGS) && + (opcode == ISCSI_OP_SCSI_DATA_OUT || + (opcode == ISCSI_OP_SCSI_CMD && + (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_TO_DEVICE)))) + /* data could goes into skb head */ + headroom += min_t(unsigned int, + SKB_MAX_HEAD(cdev->skb_tx_rsvd), + conn->max_xmit_dlength); + + tdata->skb = alloc_skb(cdev->skb_tx_rsvd + headroom, GFP_ATOMIC); + if (!tdata->skb) { + pr_warn("alloc skb %u+%u, opcode 0x%x failed.\n", + cdev->skb_tx_rsvd, headroom, opcode); + return -ENOMEM; + } + + skb_reserve(tdata->skb, cdev->skb_tx_rsvd); + task->hdr = (struct iscsi_hdr *)tdata->skb->data; + task->hdr_max = SKB_TX_ISCSI_PDU_HEADER_MAX; /* BHS + AHS */ + + /* data_out uses scsi_cmd's itt */ + if (opcode != ISCSI_OP_SCSI_DATA_OUT) + task_reserve_itt(task, &task->hdr->itt); + + log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX, + "task 0x%p, op 0x%x, skb 0x%p,%u+%u/%u, itt 0x%x.\n", + task, opcode, tdata->skb, cdev->skb_tx_rsvd, headroom, + conn->max_xmit_dlength, ntohl(task->hdr->itt)); + + return 0; +} +EXPORT_SYMBOL_GPL(cxgbi_conn_alloc_pdu); + +static inline void tx_skb_setmode(struct sk_buff *skb, int hcrc, int dcrc) +{ + u8 submode = 0; + + if (hcrc) + submode |= 1; + if (dcrc) + submode |= 2; + cxgbi_skcb_ulp_mode(skb) = (ULP2_MODE_ISCSI << 4) | submode; +} + +int cxgbi_conn_init_pdu(struct iscsi_task *task, unsigned int offset, + unsigned int count) +{ + struct iscsi_conn *conn = task->conn; + struct cxgbi_task_data *tdata = iscsi_task_cxgbi_data(task); + struct sk_buff *skb = tdata->skb; + unsigned int datalen = count; + int i, padlen = iscsi_padding(count); + struct page *pg; + + log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX, + "task 0x%p,0x%p, skb 0x%p, 0x%x,0x%x,0x%x, %u+%u.\n", + task, task->sc, skb, (*skb->data) & ISCSI_OPCODE_MASK, + ntohl(task->cmdsn), ntohl(task->hdr->itt), offset, count); + + skb_put(skb, task->hdr_len); + tx_skb_setmode(skb, conn->hdrdgst_en, datalen ? conn->datadgst_en : 0); + if (!count) + return 0; + + if (task->sc) { + struct scsi_data_buffer *sdb = scsi_out(task->sc); + struct scatterlist *sg = NULL; + int err; + + tdata->offset = offset; + tdata->count = count; + err = sgl_seek_offset( + sdb->table.sgl, sdb->table.nents, + tdata->offset, &tdata->sgoffset, &sg); + if (err < 0) { + pr_warn("tpdu, sgl %u, bad offset %u/%u.\n", + sdb->table.nents, tdata->offset, sdb->length); + return err; + } + err = sgl_read_to_frags(sg, tdata->sgoffset, tdata->count, + tdata->frags, MAX_PDU_FRAGS); + if (err < 0) { + pr_warn("tpdu, sgl %u, bad offset %u + %u.\n", + sdb->table.nents, tdata->offset, tdata->count); + return err; + } + tdata->nr_frags = err; + + if (tdata->nr_frags > MAX_SKB_FRAGS || + (padlen && tdata->nr_frags == MAX_SKB_FRAGS)) { + char *dst = skb->data + task->hdr_len; + skb_frag_t *frag = tdata->frags; + + /* data fits in the skb's headroom */ + for (i = 0; i < tdata->nr_frags; i++, frag++) { + char *src = kmap_atomic(frag->page, + KM_SOFTIRQ0); + + memcpy(dst, src+frag->page_offset, frag->size); + dst += frag->size; + kunmap_atomic(src, KM_SOFTIRQ0); + } + if (padlen) { + memset(dst, 0, padlen); + padlen = 0; + } + skb_put(skb, count + padlen); + } else { + /* data fit into frag_list */ + for (i = 0; i < tdata->nr_frags; i++) + get_page(tdata->frags[i].page); + + memcpy(skb_shinfo(skb)->frags, tdata->frags, + sizeof(skb_frag_t) * tdata->nr_frags); + skb_shinfo(skb)->nr_frags = tdata->nr_frags; + skb->len += count; + skb->data_len += count; + skb->truesize += count; + } + + } else { + pg = virt_to_page(task->data); + + get_page(pg); + skb_fill_page_desc(skb, 0, pg, offset_in_page(task->data), + count); + skb->len += count; + skb->data_len += count; + skb->truesize += count; + } + + if (padlen) { + i = skb_shinfo(skb)->nr_frags; + skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, + virt_to_page(padding), offset_in_page(padding), + padlen); + + skb->data_len += padlen; + skb->truesize += padlen; + skb->len += padlen; + } + + return 0; +} +EXPORT_SYMBOL_GPL(cxgbi_conn_init_pdu); + +int cxgbi_conn_xmit_pdu(struct iscsi_task *task) +{ + struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data; + struct cxgbi_conn *cconn = tcp_conn->dd_data; + struct cxgbi_task_data *tdata = iscsi_task_cxgbi_data(task); + struct sk_buff *skb = tdata->skb; + unsigned int datalen; + int err; + + if (!skb) { + log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX, + "task 0x%p, skb NULL.\n", task); + return 0; + } + + datalen = skb->data_len; + tdata->skb = NULL; + err = cxgbi_sock_send_pdus(cconn->cep->csk, skb); + if (err > 0) { + int pdulen = err; + + log_debug(1 << CXGBI_DBG_PDU_TX, + "task 0x%p,0x%p, skb 0x%p, len %u/%u, rv %d.\n", + task, task->sc, skb, skb->len, skb->data_len, err); + + if (task->conn->hdrdgst_en) + pdulen += ISCSI_DIGEST_SIZE; + + if (datalen && task->conn->datadgst_en) + pdulen += ISCSI_DIGEST_SIZE; + + task->conn->txdata_octets += pdulen; + return 0; + } + + if (err == -EAGAIN || err == -ENOBUFS) { + log_debug(1 << CXGBI_DBG_PDU_TX, + "task 0x%p, skb 0x%p, len %u/%u, %d EAGAIN.\n", + task, skb, skb->len, skb->data_len, err); + /* reset skb to send when we are called again */ + tdata->skb = skb; + return err; + } + + kfree_skb(skb); + log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_PDU_TX, + "itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n", + task->itt, skb, skb->len, skb->data_len, err); + iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err); + iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED); + return err; +} +EXPORT_SYMBOL_GPL(cxgbi_conn_xmit_pdu); + +void cxgbi_cleanup_task(struct iscsi_task *task) +{ + struct cxgbi_task_data *tdata = iscsi_task_cxgbi_data(task); + + log_debug(1 << CXGBI_DBG_ISCSI, + "task 0x%p, skb 0x%p, itt 0x%x.\n", + task, tdata->skb, task->hdr_itt); + + /* never reached the xmit task callout */ + if (tdata->skb) + __kfree_skb(tdata->skb); + memset(tdata, 0, sizeof(*tdata)); + + task_release_itt(task, task->hdr_itt); + iscsi_tcp_cleanup_task(task); +} +EXPORT_SYMBOL_GPL(cxgbi_cleanup_task); + +void cxgbi_get_conn_stats(struct iscsi_cls_conn *cls_conn, + struct iscsi_stats *stats) +{ + struct iscsi_conn *conn = cls_conn->dd_data; + + stats->txdata_octets = conn->txdata_octets; + stats->rxdata_octets = conn->rxdata_octets; + stats->scsicmd_pdus = conn->scsicmd_pdus_cnt; + stats->dataout_pdus = conn->dataout_pdus_cnt; + stats->scsirsp_pdus = conn->scsirsp_pdus_cnt; + stats->datain_pdus = conn->datain_pdus_cnt; + stats->r2t_pdus = conn->r2t_pdus_cnt; + stats->tmfcmd_pdus = conn->tmfcmd_pdus_cnt; + stats->tmfrsp_pdus = conn->tmfrsp_pdus_cnt; + stats->digest_err = 0; + stats->timeout_err = 0; + stats->custom_length = 1; + strcpy(stats->custom[0].desc, "eh_abort_cnt"); + stats->custom[0].value = conn->eh_abort_cnt; +} +EXPORT_SYMBOL_GPL(cxgbi_get_conn_stats); + +static int cxgbi_conn_max_xmit_dlength(struct iscsi_conn *conn) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgbi_conn *cconn = tcp_conn->dd_data; + struct cxgbi_device *cdev = cconn->chba->cdev; + unsigned int headroom = SKB_MAX_HEAD(cdev->skb_tx_rsvd); + unsigned int max_def = 512 * MAX_SKB_FRAGS; + unsigned int max = max(max_def, headroom); + + max = min(cconn->chba->cdev->tx_max_size, max); + if (conn->max_xmit_dlength) + conn->max_xmit_dlength = min(conn->max_xmit_dlength, max); + else + conn->max_xmit_dlength = max; + cxgbi_align_pdu_size(conn->max_xmit_dlength); + + return 0; +} + +static int cxgbi_conn_max_recv_dlength(struct iscsi_conn *conn) +{ + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgbi_conn *cconn = tcp_conn->dd_data; + unsigned int max = cconn->chba->cdev->rx_max_size; + + cxgbi_align_pdu_size(max); + + if (conn->max_recv_dlength) { + if (conn->max_recv_dlength > max) { + pr_err("MaxRecvDataSegmentLength %u > %u.\n", + conn->max_recv_dlength, max); + return -EINVAL; + } + conn->max_recv_dlength = min(conn->max_recv_dlength, max); + cxgbi_align_pdu_size(conn->max_recv_dlength); + } else + conn->max_recv_dlength = max; + + return 0; +} + +int cxgbi_set_conn_param(struct iscsi_cls_conn *cls_conn, + enum iscsi_param param, char *buf, int buflen) +{ + struct iscsi_conn *conn = cls_conn->dd_data; + struct iscsi_session *session = conn->session; + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgbi_conn *cconn = tcp_conn->dd_data; + struct cxgbi_sock *csk = cconn->cep->csk; + int value, err = 0; + + log_debug(1 << CXGBI_DBG_ISCSI, + "cls_conn 0x%p, param %d, buf(%d) %s.\n", + cls_conn, param, buflen, buf); + + switch (param) { + case ISCSI_PARAM_HDRDGST_EN: + err = iscsi_set_param(cls_conn, param, buf, buflen); + if (!err && conn->hdrdgst_en) + err = csk->cdev->csk_ddp_setup_digest(csk, csk->tid, + conn->hdrdgst_en, + conn->datadgst_en, 0); + break; + case ISCSI_PARAM_DATADGST_EN: + err = iscsi_set_param(cls_conn, param, buf, buflen); + if (!err && conn->datadgst_en) + err = csk->cdev->csk_ddp_setup_digest(csk, csk->tid, + conn->hdrdgst_en, + conn->datadgst_en, 0); + break; + case ISCSI_PARAM_MAX_R2T: + sscanf(buf, "%d", &value); + if (value <= 0 || !is_power_of_2(value)) + return -EINVAL; + if (session->max_r2t == value) + break; + iscsi_tcp_r2tpool_free(session); + err = iscsi_set_param(cls_conn, param, buf, buflen); + if (!err && iscsi_tcp_r2tpool_alloc(session)) + return -ENOMEM; + case ISCSI_PARAM_MAX_RECV_DLENGTH: + err = iscsi_set_param(cls_conn, param, buf, buflen); + if (!err) + err = cxgbi_conn_max_recv_dlength(conn); + break; + case ISCSI_PARAM_MAX_XMIT_DLENGTH: + err = iscsi_set_param(cls_conn, param, buf, buflen); + if (!err) + err = cxgbi_conn_max_xmit_dlength(conn); + break; + default: + return iscsi_set_param(cls_conn, param, buf, buflen); + } + return err; +} +EXPORT_SYMBOL_GPL(cxgbi_set_conn_param); + +int cxgbi_get_conn_param(struct iscsi_cls_conn *cls_conn, + enum iscsi_param param, char *buf) +{ + struct iscsi_conn *iconn = cls_conn->dd_data; + int len; + + log_debug(1 << CXGBI_DBG_ISCSI, + "cls_conn 0x%p, param %d.\n", cls_conn, param); + + switch (param) { + case ISCSI_PARAM_CONN_PORT: + spin_lock_bh(&iconn->session->lock); + len = sprintf(buf, "%hu\n", iconn->portal_port); + spin_unlock_bh(&iconn->session->lock); + break; + case ISCSI_PARAM_CONN_ADDRESS: + spin_lock_bh(&iconn->session->lock); + len = sprintf(buf, "%s\n", iconn->portal_address); + spin_unlock_bh(&iconn->session->lock); + break; + default: + return iscsi_conn_get_param(cls_conn, param, buf); + } + return len; +} +EXPORT_SYMBOL_GPL(cxgbi_get_conn_param); + +struct iscsi_cls_conn * +cxgbi_create_conn(struct iscsi_cls_session *cls_session, u32 cid) +{ + struct iscsi_cls_conn *cls_conn; + struct iscsi_conn *conn; + struct iscsi_tcp_conn *tcp_conn; + struct cxgbi_conn *cconn; + + cls_conn = iscsi_tcp_conn_setup(cls_session, sizeof(*cconn), cid); + if (!cls_conn) + return NULL; + + conn = cls_conn->dd_data; + tcp_conn = conn->dd_data; + cconn = tcp_conn->dd_data; + cconn->iconn = conn; + + log_debug(1 << CXGBI_DBG_ISCSI, + "cid %u(0x%x), cls 0x%p,0x%p, conn 0x%p,0x%p,0x%p.\n", + cid, cid, cls_session, cls_conn, conn, tcp_conn, cconn); + + return cls_conn; +} +EXPORT_SYMBOL_GPL(cxgbi_create_conn); + +int cxgbi_bind_conn(struct iscsi_cls_session *cls_session, + struct iscsi_cls_conn *cls_conn, + u64 transport_eph, int is_leading) +{ + struct iscsi_conn *conn = cls_conn->dd_data; + struct iscsi_tcp_conn *tcp_conn = conn->dd_data; + struct cxgbi_conn *cconn = tcp_conn->dd_data; + struct iscsi_endpoint *ep; + struct cxgbi_endpoint *cep; + struct cxgbi_sock *csk; + int err; + + ep = iscsi_lookup_endpoint(transport_eph); + if (!ep) + return -EINVAL; + + /* setup ddp pagesize */ + cep = ep->dd_data; + csk = cep->csk; + err = csk->cdev->csk_ddp_setup_pgidx(csk, csk->tid, page_idx, 0); + if (err < 0) + return err; + + err = iscsi_conn_bind(cls_session, cls_conn, is_leading); + if (err) + return -EINVAL; + + /* calculate the tag idx bits needed for this conn based on cmds_max */ + cconn->task_idx_bits = (__ilog2_u32(conn->session->cmds_max - 1)) + 1; + + write_lock_bh(&csk->callback_lock); + csk->user_data = conn; + cconn->chba = cep->chba; + cconn->cep = cep; + cep->cconn = cconn; + write_unlock_bh(&csk->callback_lock); + + cxgbi_conn_max_xmit_dlength(conn); + cxgbi_conn_max_recv_dlength(conn); + + spin_lock_bh(&conn->session->lock); + sprintf(conn->portal_address, "%pI4", &csk->daddr.sin_addr.s_addr); + conn->portal_port = ntohs(csk->daddr.sin_port); + spin_unlock_bh(&conn->session->lock); + + log_debug(1 << CXGBI_DBG_ISCSI, + "cls 0x%p,0x%p, ep 0x%p, cconn 0x%p, csk 0x%p.\n", + cls_session, cls_conn, ep, cconn, csk); + /* init recv engine */ + iscsi_tcp_hdr_recv_prep(tcp_conn); + + return 0; +} +EXPORT_SYMBOL_GPL(cxgbi_bind_conn); + +struct iscsi_cls_session *cxgbi_create_session(struct iscsi_endpoint *ep, + u16 cmds_max, u16 qdepth, + u32 initial_cmdsn) +{ + struct cxgbi_endpoint *cep; + struct cxgbi_hba *chba; + struct Scsi_Host *shost; + struct iscsi_cls_session *cls_session; + struct iscsi_session *session; + + if (!ep) { + pr_err("missing endpoint.\n"); + return NULL; + } + + cep = ep->dd_data; + chba = cep->chba; + shost = chba->shost; + + BUG_ON(chba != iscsi_host_priv(shost)); + + cls_session = iscsi_session_setup(chba->cdev->itp, shost, + cmds_max, 0, + sizeof(struct iscsi_tcp_task) + + sizeof(struct cxgbi_task_data), + initial_cmdsn, ISCSI_MAX_TARGET); + if (!cls_session) + return NULL; + + session = cls_session->dd_data; + if (iscsi_tcp_r2tpool_alloc(session)) + goto remove_session; + + log_debug(1 << CXGBI_DBG_ISCSI, + "ep 0x%p, cls sess 0x%p.\n", ep, cls_session); + return cls_session; + +remove_session: + iscsi_session_teardown(cls_session); + return NULL; +} +EXPORT_SYMBOL_GPL(cxgbi_create_session); + +void cxgbi_destroy_session(struct iscsi_cls_session *cls_session) +{ + log_debug(1 << CXGBI_DBG_ISCSI, + "cls sess 0x%p.\n", cls_session); + + iscsi_tcp_r2tpool_free(cls_session->dd_data); + iscsi_session_teardown(cls_session); +} +EXPORT_SYMBOL_GPL(cxgbi_destroy_session); + +int cxgbi_set_host_param(struct Scsi_Host *shost, enum iscsi_host_param param, + char *buf, int buflen) +{ + struct cxgbi_hba *chba = iscsi_host_priv(shost); + + if (!chba->ndev) { + shost_printk(KERN_ERR, shost, "Could not get host param. " + "netdev for host not set.\n"); + return -ENODEV; + } + + log_debug(1 << CXGBI_DBG_ISCSI, + "shost 0x%p, hba 0x%p,%s, param %d, buf(%d) %s.\n", + shost, chba, chba->ndev->name, param, buflen, buf); + + switch (param) { + case ISCSI_HOST_PARAM_IPADDRESS: + { + __be32 addr = in_aton(buf); + log_debug(1 << CXGBI_DBG_ISCSI, + "hba %s, req. ipv4 %pI4.\n", chba->ndev->name, &addr); + cxgbi_set_iscsi_ipv4(chba, addr); + return 0; + } + case ISCSI_HOST_PARAM_HWADDRESS: + case ISCSI_HOST_PARAM_NETDEV_NAME: + return 0; + default: + return iscsi_host_set_param(shost, param, buf, buflen); + } +} +EXPORT_SYMBOL_GPL(cxgbi_set_host_param); + +int cxgbi_get_host_param(struct Scsi_Host *shost, enum iscsi_host_param param, + char *buf) +{ + struct cxgbi_hba *chba = iscsi_host_priv(shost); + int len = 0; + + if (!chba->ndev) { + shost_printk(KERN_ERR, shost, "Could not get host param. " + "netdev for host not set.\n"); + return -ENODEV; + } + + log_debug(1 << CXGBI_DBG_ISCSI, + "shost 0x%p, hba 0x%p,%s, param %d.\n", + shost, chba, chba->ndev->name, param); + + switch (param) { + case ISCSI_HOST_PARAM_HWADDRESS: + len = sysfs_format_mac(buf, chba->ndev->dev_addr, 6); + break; + case ISCSI_HOST_PARAM_NETDEV_NAME: + len = sprintf(buf, "%s\n", chba->ndev->name); + break; + case ISCSI_HOST_PARAM_IPADDRESS: + { + __be32 addr; + + addr = cxgbi_get_iscsi_ipv4(chba); + len = sprintf(buf, "%pI4", &addr); + log_debug(1 << CXGBI_DBG_ISCSI, + "hba %s, ipv4 %pI4.\n", chba->ndev->name, &addr); + break; + } + default: + return iscsi_host_get_param(shost, param, buf); + } + + return len; +} +EXPORT_SYMBOL_GPL(cxgbi_get_host_param); + +struct iscsi_endpoint *cxgbi_ep_connect(struct Scsi_Host *shost, + struct sockaddr *dst_addr, + int non_blocking) +{ + struct iscsi_endpoint *ep; + struct cxgbi_endpoint *cep; + struct cxgbi_hba *hba = NULL; + struct cxgbi_sock *csk; + int err = -EINVAL; + + log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_SOCK, + "shost 0x%p, non_blocking %d, dst_addr 0x%p.\n", + shost, non_blocking, dst_addr); + + if (shost) { + hba = iscsi_host_priv(shost); + if (!hba) { + pr_info("shost 0x%p, priv NULL.\n", shost); + goto err_out; + } + } + + csk = cxgbi_check_route(dst_addr); + if (IS_ERR(csk)) + return (struct iscsi_endpoint *)csk; + cxgbi_sock_get(csk); + + if (!hba) + hba = csk->cdev->hbas[csk->port_id]; + else if (hba != csk->cdev->hbas[csk->port_id]) { + pr_info("Could not connect through requested host %u" + "hba 0x%p != 0x%p (%u).\n", + shost->host_no, hba, + csk->cdev->hbas[csk->port_id], csk->port_id); + err = -ENOSPC; + goto release_conn; + } + + err = sock_get_port(csk); + if (err) + goto release_conn; + + cxgbi_sock_set_state(csk, CTP_CONNECTING); + err = csk->cdev->csk_init_act_open(csk); + if (err) + goto release_conn; + + if (cxgbi_sock_is_closing(csk)) { + err = -ENOSPC; + pr_info("csk 0x%p is closing.\n", csk); + goto release_conn; + } + + ep = iscsi_create_endpoint(sizeof(*cep)); + if (!ep) { + err = -ENOMEM; + pr_info("iscsi alloc ep, OOM.\n"); + goto release_conn; + } + + cep = ep->dd_data; + cep->csk = csk; + cep->chba = hba; + + log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_SOCK, + "ep 0x%p, cep 0x%p, csk 0x%p, hba 0x%p,%s.\n", + ep, cep, csk, hba, hba->ndev->name); + return ep; + +release_conn: + cxgbi_sock_put(csk); + cxgbi_sock_closed(csk); +err_out: + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(cxgbi_ep_connect); + +int cxgbi_ep_poll(struct iscsi_endpoint *ep, int timeout_ms) +{ + struct cxgbi_endpoint *cep = ep->dd_data; + struct cxgbi_sock *csk = cep->csk; + + if (!cxgbi_sock_is_established(csk)) + return 0; + return 1; +} +EXPORT_SYMBOL_GPL(cxgbi_ep_poll); + +void cxgbi_ep_disconnect(struct iscsi_endpoint *ep) +{ + struct cxgbi_endpoint *cep = ep->dd_data; + struct cxgbi_conn *cconn = cep->cconn; + struct cxgbi_sock *csk = cep->csk; + + log_debug(1 << CXGBI_DBG_ISCSI | 1 << CXGBI_DBG_SOCK, + "ep 0x%p, cep 0x%p, cconn 0x%p, csk 0x%p,%u,0x%lx.\n", + ep, cep, cconn, csk, csk->state, csk->flags); + + if (cconn && cconn->iconn) { + iscsi_suspend_tx(cconn->iconn); + write_lock_bh(&csk->callback_lock); + cep->csk->user_data = NULL; + cconn->cep = NULL; + write_unlock_bh(&csk->callback_lock); + } + iscsi_destroy_endpoint(ep); + + if (likely(csk->state >= CTP_ESTABLISHED)) + need_active_close(csk); + else + cxgbi_sock_closed(csk); + + cxgbi_sock_put(csk); +} +EXPORT_SYMBOL_GPL(cxgbi_ep_disconnect); + +int cxgbi_iscsi_init(struct iscsi_transport *itp, + struct scsi_transport_template **stt) +{ + *stt = iscsi_register_transport(itp); + if (*stt == NULL) { + pr_err("unable to register %s transport 0x%p.\n", + itp->name, itp); + return -ENODEV; + } + log_debug(1 << CXGBI_DBG_ISCSI, + "%s, registered iscsi transport 0x%p.\n", + itp->name, stt); + return 0; +} +EXPORT_SYMBOL_GPL(cxgbi_iscsi_init); + +void cxgbi_iscsi_cleanup(struct iscsi_transport *itp, + struct scsi_transport_template **stt) +{ + if (*stt) { + log_debug(1 << CXGBI_DBG_ISCSI, + "de-register transport 0x%p, %s, stt 0x%p.\n", + itp, itp->name, *stt); + *stt = NULL; + iscsi_unregister_transport(itp); + } +} +EXPORT_SYMBOL_GPL(cxgbi_iscsi_cleanup); + +static int __init libcxgbi_init_module(void) +{ + sw_tag_idx_bits = (__ilog2_u32(ISCSI_ITT_MASK)) + 1; + sw_tag_age_bits = (__ilog2_u32(ISCSI_AGE_MASK)) + 1; + + pr_info("tag itt 0x%x, %u bits, age 0x%x, %u bits.\n", + ISCSI_ITT_MASK, sw_tag_idx_bits, + ISCSI_AGE_MASK, sw_tag_age_bits); + + ddp_setup_host_page_size(); + return 0; +} + +static void __exit libcxgbi_exit_module(void) +{ + cxgbi_device_unregister_all(0xFF); + return; +} + +module_init(libcxgbi_init_module); +module_exit(libcxgbi_exit_module); diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h new file mode 100644 index 000000000000..c57d59db000c --- /dev/null +++ b/drivers/scsi/cxgbi/libcxgbi.h @@ -0,0 +1,745 @@ +/* + * libcxgbi.h: Chelsio common library for T3/T4 iSCSI driver. + * + * Copyright (c) 2010 Chelsio Communications, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + * + * Written by: Karen Xie (kxie@chelsio.com) + * Written by: Rakesh Ranjan (rranjan@chelsio.com) + */ + +#ifndef __LIBCXGBI_H__ +#define __LIBCXGBI_H__ + +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/debugfs.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/if_vlan.h> +#include <linux/scatterlist.h> +#include <linux/skbuff.h> +#include <linux/vmalloc.h> +#include <scsi/scsi_device.h> +#include <scsi/libiscsi_tcp.h> + +enum cxgbi_dbg_flag { + CXGBI_DBG_ISCSI, + CXGBI_DBG_DDP, + CXGBI_DBG_TOE, + CXGBI_DBG_SOCK, + + CXGBI_DBG_PDU_TX, + CXGBI_DBG_PDU_RX, + CXGBI_DBG_DEV, +}; + +#define log_debug(level, fmt, ...) \ + do { \ + if (dbg_level & (level)) \ + pr_info(fmt, ##__VA_ARGS__); \ + } while (0) + +/* max. connections per adapter */ +#define CXGBI_MAX_CONN 16384 + +/* always allocate rooms for AHS */ +#define SKB_TX_ISCSI_PDU_HEADER_MAX \ + (sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE) + +#define ISCSI_PDU_NONPAYLOAD_LEN 312 /* bhs(48) + ahs(256) + digest(8)*/ + +/* + * align pdu size to multiple of 512 for better performance + */ +#define cxgbi_align_pdu_size(n) do { n = (n) & (~511); } while (0) + +#define ULP2_MODE_ISCSI 2 + +#define ULP2_MAX_PKT_SIZE 16224 +#define ULP2_MAX_PDU_PAYLOAD \ + (ULP2_MAX_PKT_SIZE - ISCSI_PDU_NONPAYLOAD_LEN) + +/* + * For iscsi connections HW may inserts digest bytes into the pdu. Those digest + * bytes are not sent by the host but are part of the TCP payload and therefore + * consume TCP sequence space. + */ +static const unsigned int ulp2_extra_len[] = { 0, 4, 4, 8 }; +static inline unsigned int cxgbi_ulp_extra_len(int submode) +{ + return ulp2_extra_len[submode & 3]; +} + +/* + * struct pagepod_hdr, pagepod - pagepod format + */ + +#define CPL_RX_DDP_STATUS_DDP_SHIFT 16 /* ddp'able */ +#define CPL_RX_DDP_STATUS_PAD_SHIFT 19 /* pad error */ +#define CPL_RX_DDP_STATUS_HCRC_SHIFT 20 /* hcrc error */ +#define CPL_RX_DDP_STATUS_DCRC_SHIFT 21 /* dcrc error */ + +struct cxgbi_pagepod_hdr { + u32 vld_tid; + u32 pgsz_tag_clr; + u32 max_offset; + u32 page_offset; + u64 rsvd; +}; + +#define PPOD_PAGES_MAX 4 +struct cxgbi_pagepod { + struct cxgbi_pagepod_hdr hdr; + u64 addr[PPOD_PAGES_MAX + 1]; +}; + +struct cxgbi_tag_format { + unsigned char sw_bits; + unsigned char rsvd_bits; + unsigned char rsvd_shift; + unsigned char filler[1]; + u32 rsvd_mask; +}; + +struct cxgbi_gather_list { + unsigned int tag; + unsigned int length; + unsigned int offset; + unsigned int nelem; + struct page **pages; + dma_addr_t phys_addr[0]; +}; + +struct cxgbi_ddp_info { + struct kref refcnt; + struct cxgbi_device *cdev; + struct pci_dev *pdev; + unsigned int max_txsz; + unsigned int max_rxsz; + unsigned int llimit; + unsigned int ulimit; + unsigned int nppods; + unsigned int idx_last; + unsigned char idx_bits; + unsigned char filler[3]; + unsigned int idx_mask; + unsigned int rsvd_tag_mask; + spinlock_t map_lock; + struct cxgbi_gather_list **gl_map; + struct sk_buff **gl_skb; +}; + +#define DDP_PGIDX_MAX 4 +#define DDP_THRESHOLD 2048 + +#define PPOD_PAGES_SHIFT 2 /* 4 pages per pod */ + +#define PPOD_SIZE sizeof(struct cxgbi_pagepod) /* 64 */ +#define PPOD_SIZE_SHIFT 6 + +#define ULPMEM_DSGL_MAX_NPPODS 16 /* 1024/PPOD_SIZE */ +#define ULPMEM_IDATA_MAX_NPPODS 4 /* 256/PPOD_SIZE */ +#define PCIE_MEMWIN_MAX_NPPODS 16 /* 1024/PPOD_SIZE */ + +#define PPOD_COLOR_SHIFT 0 +#define PPOD_COLOR(x) ((x) << PPOD_COLOR_SHIFT) + +#define PPOD_IDX_SHIFT 6 +#define PPOD_IDX_MAX_SIZE 24 + +#define PPOD_TID_SHIFT 0 +#define PPOD_TID(x) ((x) << PPOD_TID_SHIFT) + +#define PPOD_TAG_SHIFT 6 +#define PPOD_TAG(x) ((x) << PPOD_TAG_SHIFT) + +#define PPOD_VALID_SHIFT 24 +#define PPOD_VALID(x) ((x) << PPOD_VALID_SHIFT) +#define PPOD_VALID_FLAG PPOD_VALID(1U) + +/* + * sge_opaque_hdr - + * Opaque version of structure the SGE stores at skb->head of TX_DATA packets + * and for which we must reserve space. + */ +struct sge_opaque_hdr { + void *dev; + dma_addr_t addr[MAX_SKB_FRAGS + 1]; +}; + +struct cxgbi_sock { + struct cxgbi_device *cdev; + + int tid; + int atid; + unsigned long flags; + unsigned int mtu; + unsigned short rss_qid; + unsigned short txq_idx; + unsigned short advmss; + unsigned int tx_chan; + unsigned int rx_chan; + unsigned int mss_idx; + unsigned int smac_idx; + unsigned char port_id; + int wr_max_cred; + int wr_cred; + int wr_una_cred; + unsigned char hcrc_len; + unsigned char dcrc_len; + + void *l2t; + struct sk_buff *wr_pending_head; + struct sk_buff *wr_pending_tail; + struct sk_buff *cpl_close; + struct sk_buff *cpl_abort_req; + struct sk_buff *cpl_abort_rpl; + struct sk_buff *skb_ulp_lhdr; + spinlock_t lock; + struct kref refcnt; + unsigned int state; + struct sockaddr_in saddr; + struct sockaddr_in daddr; + struct dst_entry *dst; + struct sk_buff_head receive_queue; + struct sk_buff_head write_queue; + struct timer_list retry_timer; + int err; + rwlock_t callback_lock; + void *user_data; + + u32 rcv_nxt; + u32 copied_seq; + u32 rcv_wup; + u32 snd_nxt; + u32 snd_una; + u32 write_seq; +}; + +/* + * connection states + */ +enum cxgbi_sock_states{ + CTP_CLOSED, + CTP_CONNECTING, + CTP_ACTIVE_OPEN, + CTP_ESTABLISHED, + CTP_ACTIVE_CLOSE, + CTP_PASSIVE_CLOSE, + CTP_CLOSE_WAIT_1, + CTP_CLOSE_WAIT_2, + CTP_ABORTING, +}; + +/* + * Connection flags -- many to track some close related events. + */ +enum cxgbi_sock_flags { + CTPF_ABORT_RPL_RCVD, /*received one ABORT_RPL_RSS message */ + CTPF_ABORT_REQ_RCVD, /*received one ABORT_REQ_RSS message */ + CTPF_ABORT_RPL_PENDING, /* expecting an abort reply */ + CTPF_TX_DATA_SENT, /* already sent a TX_DATA WR */ + CTPF_ACTIVE_CLOSE_NEEDED,/* need to be closed */ + CTPF_HAS_ATID, /* reserved atid */ + CTPF_HAS_TID, /* reserved hw tid */ + CTPF_OFFLOAD_DOWN, /* offload function off */ +}; + +struct cxgbi_skb_rx_cb { + __u32 ddigest; + __u32 pdulen; +}; + +struct cxgbi_skb_tx_cb { + void *l2t; + struct sk_buff *wr_next; +}; + +enum cxgbi_skcb_flags { + SKCBF_TX_NEED_HDR, /* packet needs a header */ + SKCBF_RX_COALESCED, /* received whole pdu */ + SKCBF_RX_HDR, /* recieved pdu header */ + SKCBF_RX_DATA, /* recieved pdu payload */ + SKCBF_RX_STATUS, /* recieved ddp status */ + SKCBF_RX_DATA_DDPD, /* pdu payload ddp'd */ + SKCBF_RX_HCRC_ERR, /* header digest error */ + SKCBF_RX_DCRC_ERR, /* data digest error */ + SKCBF_RX_PAD_ERR, /* padding byte error */ +}; + +struct cxgbi_skb_cb { + unsigned char ulp_mode; + unsigned long flags; + unsigned int seq; + union { + struct cxgbi_skb_rx_cb rx; + struct cxgbi_skb_tx_cb tx; + }; +}; + +#define CXGBI_SKB_CB(skb) ((struct cxgbi_skb_cb *)&((skb)->cb[0])) +#define cxgbi_skcb_flags(skb) (CXGBI_SKB_CB(skb)->flags) +#define cxgbi_skcb_ulp_mode(skb) (CXGBI_SKB_CB(skb)->ulp_mode) +#define cxgbi_skcb_tcp_seq(skb) (CXGBI_SKB_CB(skb)->seq) +#define cxgbi_skcb_rx_ddigest(skb) (CXGBI_SKB_CB(skb)->rx.ddigest) +#define cxgbi_skcb_rx_pdulen(skb) (CXGBI_SKB_CB(skb)->rx.pdulen) +#define cxgbi_skcb_tx_wr_next(skb) (CXGBI_SKB_CB(skb)->tx.wr_next) + +static inline void cxgbi_skcb_set_flag(struct sk_buff *skb, + enum cxgbi_skcb_flags flag) +{ + __set_bit(flag, &(cxgbi_skcb_flags(skb))); +} + +static inline void cxgbi_skcb_clear_flag(struct sk_buff *skb, + enum cxgbi_skcb_flags flag) +{ + __clear_bit(flag, &(cxgbi_skcb_flags(skb))); +} + +static inline int cxgbi_skcb_test_flag(struct sk_buff *skb, + enum cxgbi_skcb_flags flag) +{ + return test_bit(flag, &(cxgbi_skcb_flags(skb))); +} + +static inline void cxgbi_sock_set_flag(struct cxgbi_sock *csk, + enum cxgbi_sock_flags flag) +{ + __set_bit(flag, &csk->flags); + log_debug(1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx, bit %d.\n", + csk, csk->state, csk->flags, flag); +} + +static inline void cxgbi_sock_clear_flag(struct cxgbi_sock *csk, + enum cxgbi_sock_flags flag) +{ + __clear_bit(flag, &csk->flags); + log_debug(1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx, bit %d.\n", + csk, csk->state, csk->flags, flag); +} + +static inline int cxgbi_sock_flag(struct cxgbi_sock *csk, + enum cxgbi_sock_flags flag) +{ + if (csk == NULL) + return 0; + return test_bit(flag, &csk->flags); +} + +static inline void cxgbi_sock_set_state(struct cxgbi_sock *csk, int state) +{ + log_debug(1 << CXGBI_DBG_SOCK, + "csk 0x%p,%u,0x%lx, state -> %u.\n", + csk, csk->state, csk->flags, state); + csk->state = state; +} + +static inline void cxgbi_sock_free(struct kref *kref) +{ + struct cxgbi_sock *csk = container_of(kref, + struct cxgbi_sock, + refcnt); + if (csk) { + log_debug(1 << CXGBI_DBG_SOCK, + "free csk 0x%p, state %u, flags 0x%lx\n", + csk, csk->state, csk->flags); + kfree(csk); + } +} + +static inline void __cxgbi_sock_put(const char *fn, struct cxgbi_sock *csk) +{ + log_debug(1 << CXGBI_DBG_SOCK, + "%s, put csk 0x%p, ref %u-1.\n", + fn, csk, atomic_read(&csk->refcnt.refcount)); + kref_put(&csk->refcnt, cxgbi_sock_free); +} +#define cxgbi_sock_put(csk) __cxgbi_sock_put(__func__, csk) + +static inline void __cxgbi_sock_get(const char *fn, struct cxgbi_sock *csk) +{ + log_debug(1 << CXGBI_DBG_SOCK, + "%s, get csk 0x%p, ref %u+1.\n", + fn, csk, atomic_read(&csk->refcnt.refcount)); + kref_get(&csk->refcnt); +} +#define cxgbi_sock_get(csk) __cxgbi_sock_get(__func__, csk) + +static inline int cxgbi_sock_is_closing(struct cxgbi_sock *csk) +{ + return csk->state >= CTP_ACTIVE_CLOSE; +} + +static inline int cxgbi_sock_is_established(struct cxgbi_sock *csk) +{ + return csk->state == CTP_ESTABLISHED; +} + +static inline void cxgbi_sock_purge_write_queue(struct cxgbi_sock *csk) +{ + struct sk_buff *skb; + + while ((skb = __skb_dequeue(&csk->write_queue))) + __kfree_skb(skb); +} + +static inline unsigned int cxgbi_sock_compute_wscale(unsigned int win) +{ + unsigned int wscale = 0; + + while (wscale < 14 && (65535 << wscale) < win) + wscale++; + return wscale; +} + +static inline struct sk_buff *alloc_wr(int wrlen, int dlen, gfp_t gfp) +{ + struct sk_buff *skb = alloc_skb(wrlen + dlen, gfp); + + if (skb) { + __skb_put(skb, wrlen); + memset(skb->head, 0, wrlen + dlen); + } else + pr_info("alloc cpl wr skb %u+%u, OOM.\n", wrlen, dlen); + return skb; +} + + +/* + * The number of WRs needed for an skb depends on the number of fragments + * in the skb and whether it has any payload in its main body. This maps the + * length of the gather list represented by an skb into the # of necessary WRs. + * The extra two fragments are for iscsi bhs and payload padding. + */ +#define SKB_WR_LIST_SIZE (MAX_SKB_FRAGS + 2) + +static inline void cxgbi_sock_reset_wr_list(struct cxgbi_sock *csk) +{ + csk->wr_pending_head = csk->wr_pending_tail = NULL; +} + +static inline void cxgbi_sock_enqueue_wr(struct cxgbi_sock *csk, + struct sk_buff *skb) +{ + cxgbi_skcb_tx_wr_next(skb) = NULL; + /* + * We want to take an extra reference since both us and the driver + * need to free the packet before it's really freed. We know there's + * just one user currently so we use atomic_set rather than skb_get + * to avoid the atomic op. + */ + atomic_set(&skb->users, 2); + + if (!csk->wr_pending_head) + csk->wr_pending_head = skb; + else + cxgbi_skcb_tx_wr_next(csk->wr_pending_tail) = skb; + csk->wr_pending_tail = skb; +} + +static inline int cxgbi_sock_count_pending_wrs(const struct cxgbi_sock *csk) +{ + int n = 0; + const struct sk_buff *skb = csk->wr_pending_head; + + while (skb) { + n += skb->csum; + skb = cxgbi_skcb_tx_wr_next(skb); + } + return n; +} + +static inline struct sk_buff *cxgbi_sock_peek_wr(const struct cxgbi_sock *csk) +{ + return csk->wr_pending_head; +} + +static inline struct sk_buff *cxgbi_sock_dequeue_wr(struct cxgbi_sock *csk) +{ + struct sk_buff *skb = csk->wr_pending_head; + + if (likely(skb)) { + csk->wr_pending_head = cxgbi_skcb_tx_wr_next(skb); + cxgbi_skcb_tx_wr_next(skb) = NULL; + } + return skb; +} + +void cxgbi_sock_check_wr_invariants(const struct cxgbi_sock *); +void cxgbi_sock_purge_wr_queue(struct cxgbi_sock *); +void cxgbi_sock_skb_entail(struct cxgbi_sock *, struct sk_buff *); +void cxgbi_sock_fail_act_open(struct cxgbi_sock *, int); +void cxgbi_sock_act_open_req_arp_failure(void *, struct sk_buff *); +void cxgbi_sock_closed(struct cxgbi_sock *); +void cxgbi_sock_established(struct cxgbi_sock *, unsigned int, unsigned int); +void cxgbi_sock_rcv_abort_rpl(struct cxgbi_sock *); +void cxgbi_sock_rcv_peer_close(struct cxgbi_sock *); +void cxgbi_sock_rcv_close_conn_rpl(struct cxgbi_sock *, u32); +void cxgbi_sock_rcv_wr_ack(struct cxgbi_sock *, unsigned int, unsigned int, + int); +unsigned int cxgbi_sock_select_mss(struct cxgbi_sock *, unsigned int); +void cxgbi_sock_free_cpl_skbs(struct cxgbi_sock *); + +struct cxgbi_hba { + struct net_device *ndev; + struct net_device *vdev; /* vlan dev */ + struct Scsi_Host *shost; + struct cxgbi_device *cdev; + __be32 ipv4addr; + unsigned char port_id; +}; + +struct cxgbi_ports_map { + unsigned int max_connect; + unsigned int used; + unsigned short sport_base; + spinlock_t lock; + unsigned int next; + struct cxgbi_sock **port_csk; +}; + +#define CXGBI_FLAG_DEV_T3 0x1 +#define CXGBI_FLAG_DEV_T4 0x2 +#define CXGBI_FLAG_ADAPTER_RESET 0x4 +#define CXGBI_FLAG_IPV4_SET 0x10 +struct cxgbi_device { + struct list_head list_head; + unsigned int flags; + struct net_device **ports; + void *lldev; + struct cxgbi_hba **hbas; + const unsigned short *mtus; + unsigned char nmtus; + unsigned char nports; + struct pci_dev *pdev; + struct dentry *debugfs_root; + struct iscsi_transport *itp; + + unsigned int pfvf; + unsigned int snd_win; + unsigned int rcv_win; + unsigned int rx_credit_thres; + unsigned int skb_tx_rsvd; + unsigned int skb_rx_extra; /* for msg coalesced mode */ + unsigned int tx_max_size; + unsigned int rx_max_size; + struct cxgbi_ports_map pmap; + struct cxgbi_tag_format tag_format; + struct cxgbi_ddp_info *ddp; + + void (*dev_ddp_cleanup)(struct cxgbi_device *); + void (*csk_ddp_free_gl_skb)(struct cxgbi_ddp_info *, int, int); + int (*csk_ddp_alloc_gl_skb)(struct cxgbi_ddp_info *, int, int, gfp_t); + int (*csk_ddp_set)(struct cxgbi_sock *, struct cxgbi_pagepod_hdr *, + unsigned int, unsigned int, + struct cxgbi_gather_list *); + void (*csk_ddp_clear)(struct cxgbi_hba *, + unsigned int, unsigned int, unsigned int); + int (*csk_ddp_setup_digest)(struct cxgbi_sock *, + unsigned int, int, int, int); + int (*csk_ddp_setup_pgidx)(struct cxgbi_sock *, + unsigned int, int, bool); + + void (*csk_release_offload_resources)(struct cxgbi_sock *); + int (*csk_rx_pdu_ready)(struct cxgbi_sock *, struct sk_buff *); + u32 (*csk_send_rx_credits)(struct cxgbi_sock *, u32); + int (*csk_push_tx_frames)(struct cxgbi_sock *, int); + void (*csk_send_abort_req)(struct cxgbi_sock *); + void (*csk_send_close_req)(struct cxgbi_sock *); + int (*csk_alloc_cpls)(struct cxgbi_sock *); + int (*csk_init_act_open)(struct cxgbi_sock *); + + void *dd_data; +}; +#define cxgbi_cdev_priv(cdev) ((cdev)->dd_data) + +struct cxgbi_conn { + struct cxgbi_endpoint *cep; + struct iscsi_conn *iconn; + struct cxgbi_hba *chba; + u32 task_idx_bits; +}; + +struct cxgbi_endpoint { + struct cxgbi_conn *cconn; + struct cxgbi_hba *chba; + struct cxgbi_sock *csk; +}; + +#define MAX_PDU_FRAGS ((ULP2_MAX_PDU_PAYLOAD + 512 - 1) / 512) +struct cxgbi_task_data { + unsigned short nr_frags; + skb_frag_t frags[MAX_PDU_FRAGS]; + struct sk_buff *skb; + unsigned int offset; + unsigned int count; + unsigned int sgoffset; +}; +#define iscsi_task_cxgbi_data(task) \ + ((task)->dd_data + sizeof(struct iscsi_tcp_task)) + +static inline int cxgbi_is_ddp_tag(struct cxgbi_tag_format *tformat, u32 tag) +{ + return !(tag & (1 << (tformat->rsvd_bits + tformat->rsvd_shift - 1))); +} + +static inline int cxgbi_sw_tag_usable(struct cxgbi_tag_format *tformat, + u32 sw_tag) +{ + sw_tag >>= (32 - tformat->rsvd_bits); + return !sw_tag; +} + +static inline u32 cxgbi_set_non_ddp_tag(struct cxgbi_tag_format *tformat, + u32 sw_tag) +{ + unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1; + u32 mask = (1 << shift) - 1; + + if (sw_tag && (sw_tag & ~mask)) { + u32 v1 = sw_tag & ((1 << shift) - 1); + u32 v2 = (sw_tag >> (shift - 1)) << shift; + + return v2 | v1 | 1 << shift; + } + + return sw_tag | 1 << shift; +} + +static inline u32 cxgbi_ddp_tag_base(struct cxgbi_tag_format *tformat, + u32 sw_tag) +{ + u32 mask = (1 << tformat->rsvd_shift) - 1; + + if (sw_tag && (sw_tag & ~mask)) { + u32 v1 = sw_tag & mask; + u32 v2 = sw_tag >> tformat->rsvd_shift; + + v2 <<= tformat->rsvd_bits + tformat->rsvd_shift; + + return v2 | v1; + } + + return sw_tag; +} + +static inline u32 cxgbi_tag_rsvd_bits(struct cxgbi_tag_format *tformat, + u32 tag) +{ + if (cxgbi_is_ddp_tag(tformat, tag)) + return (tag >> tformat->rsvd_shift) & tformat->rsvd_mask; + + return 0; +} + +static inline u32 cxgbi_tag_nonrsvd_bits(struct cxgbi_tag_format *tformat, + u32 tag) +{ + unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1; + u32 v1, v2; + + if (cxgbi_is_ddp_tag(tformat, tag)) { + v1 = tag & ((1 << tformat->rsvd_shift) - 1); + v2 = (tag >> (shift + 1)) << tformat->rsvd_shift; + } else { + u32 mask = (1 << shift) - 1; + tag &= ~(1 << shift); + v1 = tag & mask; + v2 = (tag >> 1) & ~mask; + } + return v1 | v2; +} + +static inline void *cxgbi_alloc_big_mem(unsigned int size, + gfp_t gfp) +{ + void *p = kmalloc(size, gfp); + if (!p) + p = vmalloc(size); + if (p) + memset(p, 0, size); + return p; +} + +static inline void cxgbi_free_big_mem(void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} + +static inline void cxgbi_set_iscsi_ipv4(struct cxgbi_hba *chba, __be32 ipaddr) +{ + if (chba->cdev->flags & CXGBI_FLAG_IPV4_SET) + chba->ipv4addr = ipaddr; + else + pr_info("set iscsi ipv4 NOT supported, using %s ipv4.\n", + chba->ndev->name); +} + +static inline __be32 cxgbi_get_iscsi_ipv4(struct cxgbi_hba *chba) +{ + return chba->ipv4addr; +} + +struct cxgbi_device *cxgbi_device_register(unsigned int, unsigned int); +void cxgbi_device_unregister(struct cxgbi_device *); +void cxgbi_device_unregister_all(unsigned int flag); +struct cxgbi_device *cxgbi_device_find_by_lldev(void *); +int cxgbi_hbas_add(struct cxgbi_device *, unsigned int, unsigned int, + struct scsi_host_template *, + struct scsi_transport_template *); +void cxgbi_hbas_remove(struct cxgbi_device *); + +int cxgbi_device_portmap_create(struct cxgbi_device *cdev, unsigned int base, + unsigned int max_conn); +void cxgbi_device_portmap_cleanup(struct cxgbi_device *cdev); + +void cxgbi_conn_tx_open(struct cxgbi_sock *); +void cxgbi_conn_pdu_ready(struct cxgbi_sock *); +int cxgbi_conn_alloc_pdu(struct iscsi_task *, u8); +int cxgbi_conn_init_pdu(struct iscsi_task *, unsigned int , unsigned int); +int cxgbi_conn_xmit_pdu(struct iscsi_task *); + +void cxgbi_cleanup_task(struct iscsi_task *task); + +void cxgbi_get_conn_stats(struct iscsi_cls_conn *, struct iscsi_stats *); +int cxgbi_set_conn_param(struct iscsi_cls_conn *, + enum iscsi_param, char *, int); +int cxgbi_get_conn_param(struct iscsi_cls_conn *, enum iscsi_param, char *); +struct iscsi_cls_conn *cxgbi_create_conn(struct iscsi_cls_session *, u32); +int cxgbi_bind_conn(struct iscsi_cls_session *, + struct iscsi_cls_conn *, u64, int); +void cxgbi_destroy_session(struct iscsi_cls_session *); +struct iscsi_cls_session *cxgbi_create_session(struct iscsi_endpoint *, + u16, u16, u32); +int cxgbi_set_host_param(struct Scsi_Host *, + enum iscsi_host_param, char *, int); +int cxgbi_get_host_param(struct Scsi_Host *, enum iscsi_host_param, char *); +struct iscsi_endpoint *cxgbi_ep_connect(struct Scsi_Host *, + struct sockaddr *, int); +int cxgbi_ep_poll(struct iscsi_endpoint *, int); +void cxgbi_ep_disconnect(struct iscsi_endpoint *); + +int cxgbi_iscsi_init(struct iscsi_transport *, + struct scsi_transport_template **); +void cxgbi_iscsi_cleanup(struct iscsi_transport *, + struct scsi_transport_template **); +void cxgbi_parse_pdu_itt(struct iscsi_conn *, itt_t, int *, int *); +int cxgbi_ddp_init(struct cxgbi_device *, unsigned int, unsigned int, + unsigned int, unsigned int); +int cxgbi_ddp_cleanup(struct cxgbi_device *); +void cxgbi_ddp_page_size_factor(int *); +void cxgbi_ddp_ppod_clear(struct cxgbi_pagepod *); +void cxgbi_ddp_ppod_set(struct cxgbi_pagepod *, struct cxgbi_pagepod_hdr *, + struct cxgbi_gather_list *, unsigned int); +#endif /*__LIBCXGBI_H__*/ |