diff options
Diffstat (limited to 'drivers/scsi/libiscsi.c')
| -rw-r--r-- | drivers/scsi/libiscsi.c | 1674 |
1 files changed, 1060 insertions, 614 deletions
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index ae69dfcc7834..c9f410c50978 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * iSCSI lib functions * @@ -6,28 +7,15 @@ * Copyright (C) 2004 - 2005 Dmitry Yusupov * Copyright (C) 2004 - 2005 Alex Aizman * maintained by open-iscsi@googlegroups.com - * - * 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; either version 2 of the License, or - * (at your option) any later version. - * - * 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 - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ #include <linux/types.h> #include <linux/kfifo.h> #include <linux/delay.h> #include <linux/log2.h> #include <linux/slab.h> +#include <linux/sched/signal.h> #include <linux/module.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <net/tcp.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_device.h> @@ -39,6 +27,7 @@ #include <scsi/scsi_transport.h> #include <scsi/scsi_transport_iscsi.h> #include <scsi/libiscsi.h> +#include <trace/events/iscsi.h> static int iscsi_dbg_lib_conn; module_param_named(debug_libiscsi_conn, iscsi_dbg_lib_conn, int, @@ -67,6 +56,9 @@ MODULE_PARM_DESC(debug_libiscsi_eh, iscsi_conn_printk(KERN_INFO, _conn, \ "%s " dbg_fmt, \ __func__, ##arg); \ + iscsi_dbg_trace(trace_iscsi_dbg_conn, \ + &(_conn)->cls_conn->dev, \ + "%s " dbg_fmt, __func__, ##arg);\ } while (0); #define ISCSI_DBG_SESSION(_session, dbg_fmt, arg...) \ @@ -75,6 +67,9 @@ MODULE_PARM_DESC(debug_libiscsi_eh, iscsi_session_printk(KERN_INFO, _session, \ "%s " dbg_fmt, \ __func__, ##arg); \ + iscsi_dbg_trace(trace_iscsi_dbg_session, \ + &(_session)->cls_session->dev, \ + "%s " dbg_fmt, __func__, ##arg); \ } while (0); #define ISCSI_DBG_EH(_session, dbg_fmt, arg...) \ @@ -83,9 +78,14 @@ MODULE_PARM_DESC(debug_libiscsi_eh, iscsi_session_printk(KERN_INFO, _session, \ "%s " dbg_fmt, \ __func__, ##arg); \ + iscsi_dbg_trace(trace_iscsi_dbg_eh, \ + &(_session)->cls_session->dev, \ + "%s " dbg_fmt, __func__, ##arg); \ } while (0); -inline void iscsi_conn_queue_work(struct iscsi_conn *conn) +#define ISCSI_CMD_COMPL_WAIT 5 + +inline void iscsi_conn_queue_xmit(struct iscsi_conn *conn) { struct Scsi_Host *shost = conn->session->host; struct iscsi_host *ihost = shost_priv(shost); @@ -93,7 +93,17 @@ inline void iscsi_conn_queue_work(struct iscsi_conn *conn) if (ihost->workq) queue_work(ihost->workq, &conn->xmitwork); } -EXPORT_SYMBOL_GPL(iscsi_conn_queue_work); +EXPORT_SYMBOL_GPL(iscsi_conn_queue_xmit); + +inline void iscsi_conn_queue_recv(struct iscsi_conn *conn) +{ + struct Scsi_Host *shost = conn->session->host; + struct iscsi_host *ihost = shost_priv(shost); + + if (ihost->workq && !test_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags)) + queue_work(ihost->workq, &conn->recvwork); +} +EXPORT_SYMBOL_GPL(iscsi_conn_queue_recv); static void __iscsi_update_cmdsn(struct iscsi_session *session, uint32_t exp_cmdsn, uint32_t max_cmdsn) @@ -110,16 +120,8 @@ static void __iscsi_update_cmdsn(struct iscsi_session *session, session->exp_cmdsn = exp_cmdsn; if (max_cmdsn != session->max_cmdsn && - !iscsi_sna_lt(max_cmdsn, session->max_cmdsn)) { + !iscsi_sna_lt(max_cmdsn, session->max_cmdsn)) session->max_cmdsn = max_cmdsn; - /* - * if the window closed with IO queued, then kick the - * xmit thread - */ - if (!list_empty(&session->leadconn->cmdqueue) || - !list_empty(&session->leadconn->mgmtqueue)) - iscsi_conn_queue_work(session->leadconn); - } } void iscsi_update_cmdsn(struct iscsi_session *session, struct iscsi_nopin *hdr) @@ -225,32 +227,6 @@ static int iscsi_prep_ecdb_ahs(struct iscsi_task *task) return 0; } -static int iscsi_prep_bidi_ahs(struct iscsi_task *task) -{ - struct scsi_cmnd *sc = task->sc; - struct iscsi_rlength_ahdr *rlen_ahdr; - int rc; - - rlen_ahdr = iscsi_next_hdr(task); - rc = iscsi_add_hdr(task, sizeof(*rlen_ahdr)); - if (rc) - return rc; - - rlen_ahdr->ahslength = - cpu_to_be16(sizeof(rlen_ahdr->read_length) + - sizeof(rlen_ahdr->reserved)); - rlen_ahdr->ahstype = ISCSI_AHSTYPE_RLENGTH; - rlen_ahdr->reserved = 0; - rlen_ahdr->read_length = cpu_to_be32(scsi_in(sc)->length); - - ISCSI_DBG_SESSION(task->conn->session, - "bidi-in rlen_ahdr->read_length(%d) " - "rlen_ahdr->ahslength(%d)\n", - be32_to_cpu(rlen_ahdr->read_length), - be16_to_cpu(rlen_ahdr->ahslength)); - return 0; -} - /** * iscsi_check_tmf_restrictions - check if a task is affected by TMF * @task: iscsi task @@ -266,11 +242,11 @@ static int iscsi_prep_bidi_ahs(struct iscsi_task *task) */ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode) { - struct iscsi_conn *conn = task->conn; - struct iscsi_tm *tmf = &conn->tmhdr; - unsigned int hdr_lun; + struct iscsi_session *session = task->conn->session; + struct iscsi_tm *tmf = &session->tmhdr; + u64 hdr_lun; - if (conn->tmf_state == TMF_INITIAL) + if (session->tmf_state == TMF_INITIAL) return 0; if ((tmf->opcode & ISCSI_OPCODE_MASK) != ISCSI_OP_SCSI_TMFUNC) @@ -284,30 +260,25 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode) hdr_lun = scsilun_to_int(&tmf->lun); if (hdr_lun != task->sc->device->lun) return 0; - /* fall through */ + fallthrough; case ISCSI_TM_FUNC_TARGET_WARM_RESET: /* * Fail all SCSI cmd PDUs */ if (opcode != ISCSI_OP_SCSI_DATA_OUT) { - iscsi_conn_printk(KERN_INFO, conn, - "task [op %x/%x itt " - "0x%x/0x%x] " - "rejected.\n", - task->hdr->opcode, opcode, - task->itt, task->hdr_itt); + iscsi_session_printk(KERN_INFO, session, + "task [op %x itt 0x%x/0x%x] rejected.\n", + opcode, task->itt, task->hdr_itt); return -EACCES; } /* * And also all data-out PDUs in response to R2T * if fast_abort is set. */ - if (conn->session->fast_abort) { - iscsi_conn_printk(KERN_INFO, conn, - "task [op %x/%x itt " - "0x%x/0x%x] fast abort.\n", - task->hdr->opcode, opcode, - task->itt, task->hdr_itt); + if (session->fast_abort) { + iscsi_session_printk(KERN_INFO, session, + "task [op %x itt 0x%x/0x%x] fast abort.\n", + opcode, task->itt, task->hdr_itt); return -EACCES; } break; @@ -320,7 +291,7 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode) */ if (opcode == ISCSI_OP_SCSI_DATA_OUT && task->hdr_itt == tmf->rtt) { - ISCSI_DBG_SESSION(conn->session, + ISCSI_DBG_SESSION(session, "Preventing task %x/%x from sending " "data-out due to abort task in " "progress\n", task->itt, @@ -346,7 +317,7 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task) struct iscsi_session *session = conn->session; struct scsi_cmnd *sc = task->sc; struct iscsi_scsi_req *hdr; - unsigned hdrlength, cmd_len; + unsigned hdrlength, cmd_len, transfer_length; itt_t itt; int rc; @@ -389,17 +360,14 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task) memcpy(hdr->cdb, sc->cmnd, cmd_len); task->imm_count = 0; - if (scsi_bidi_cmnd(sc)) { - hdr->flags |= ISCSI_FLAG_CMD_READ; - rc = iscsi_prep_bidi_ahs(task); - if (rc) - return rc; - } + if (scsi_get_prot_op(sc) != SCSI_PROT_NORMAL) + task->protected = true; + + transfer_length = scsi_transfer_length(sc); + hdr->data_length = cpu_to_be32(transfer_length); if (sc->sc_data_direction == DMA_TO_DEVICE) { - unsigned out_len = scsi_out(sc)->length; struct iscsi_r2t_info *r2t = &task->unsol_r2t; - hdr->data_length = cpu_to_be32(out_len); hdr->flags |= ISCSI_FLAG_CMD_WRITE; /* * Write counters: @@ -418,18 +386,19 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task) memset(r2t, 0, sizeof(*r2t)); if (session->imm_data_en) { - if (out_len >= session->first_burst) + if (transfer_length >= session->first_burst) task->imm_count = min(session->first_burst, conn->max_xmit_dlength); else - task->imm_count = min(out_len, - conn->max_xmit_dlength); + task->imm_count = min(transfer_length, + conn->max_xmit_dlength); hton24(hdr->dlength, task->imm_count); } else zero_data(hdr->dlength); if (!session->initial_r2t_en) { - r2t->data_length = min(session->first_burst, out_len) - + r2t->data_length = min(session->first_burst, + transfer_length) - task->imm_count; r2t->data_offset = task->imm_count; r2t->ttt = cpu_to_be32(ISCSI_RESERVED_TAG); @@ -442,7 +411,6 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task) } else { hdr->flags |= ISCSI_FLAG_CMD_FINAL; zero_data(hdr->dlength); - hdr->data_length = cpu_to_be32(scsi_in(sc)->length); if (sc->sc_data_direction == DMA_FROM_DEVICE) hdr->flags |= ISCSI_FLAG_CMD_READ; @@ -466,12 +434,10 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task) conn->scsicmd_pdus_cnt++; ISCSI_DBG_SESSION(session, "iscsi prep [%s cid %d sc %p cdb 0x%x " - "itt 0x%x len %d bidi_len %d cmdsn %d win %d]\n", - scsi_bidi_cmnd(sc) ? "bidirectional" : + "itt 0x%x len %d cmdsn %d win %d]\n", sc->sc_data_direction == DMA_TO_DEVICE ? "write" : "read", conn->id, sc, sc->cmnd[0], - task->itt, scsi_bufflen(sc), - scsi_bidi_cmnd(sc) ? scsi_in(sc)->length : 0, + task->itt, transfer_length, session->cmdsn, session->max_cmdsn - session->exp_cmdsn + 1); return 0; @@ -481,7 +447,7 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task) * iscsi_free_task - free a task * @task: iscsi cmd task * - * Must be called with session lock. + * Must be called with session back_lock. * This function returns the scsi command to scsi-ml or cleans * up mgmt tasks then returns the task to the pool. */ @@ -508,25 +474,31 @@ static void iscsi_free_task(struct iscsi_task *task) if (sc) { /* SCSI eh reuses commands to verify us */ - sc->SCp.ptr = NULL; + iscsi_cmd(sc)->task = NULL; /* * queue command may call this to free the task, so * it will decide how to return sc to scsi-ml. */ if (oldstate != ISCSI_TASK_REQUEUE_SCSIQ) - sc->scsi_done(sc); + scsi_done(sc); } } -void __iscsi_get_task(struct iscsi_task *task) +bool iscsi_get_task(struct iscsi_task *task) { - atomic_inc(&task->refcount); + return refcount_inc_not_zero(&task->refcount); } -EXPORT_SYMBOL_GPL(__iscsi_get_task); +EXPORT_SYMBOL_GPL(iscsi_get_task); +/** + * __iscsi_put_task - drop the refcount on a task + * @task: iscsi_task to drop the refcount on + * + * The back_lock must be held when calling in case it frees the task. + */ void __iscsi_put_task(struct iscsi_task *task) { - if (atomic_dec_and_test(&task->refcount)) + if (refcount_dec_and_test(&task->refcount)) iscsi_free_task(task); } EXPORT_SYMBOL_GPL(__iscsi_put_task); @@ -535,9 +507,11 @@ void iscsi_put_task(struct iscsi_task *task) { struct iscsi_session *session = task->conn->session; - spin_lock_bh(&session->lock); - __iscsi_put_task(task); - spin_unlock_bh(&session->lock); + if (refcount_dec_and_test(&task->refcount)) { + spin_lock_bh(&session->back_lock); + iscsi_free_task(task); + spin_unlock_bh(&session->back_lock); + } } EXPORT_SYMBOL_GPL(iscsi_put_task); @@ -546,7 +520,7 @@ EXPORT_SYMBOL_GPL(iscsi_put_task); * @task: iscsi cmd task * @state: state to complete task with * - * Must be called with session lock. + * Must be called with session back_lock. */ static void iscsi_complete_task(struct iscsi_task *task, int state) { @@ -563,14 +537,8 @@ static void iscsi_complete_task(struct iscsi_task *task, int state) WARN_ON_ONCE(task->state == ISCSI_TASK_FREE); task->state = state; - if (!list_empty(&task->running)) - list_del_init(&task->running); - - if (conn->task == task) - conn->task = NULL; - - if (conn->ping_task == task) - conn->ping_task = NULL; + if (READ_ONCE(conn->ping_task) == task) + WRITE_ONCE(conn->ping_task, NULL); /* release get from queueing */ __iscsi_put_task(task); @@ -585,7 +553,7 @@ static void iscsi_complete_task(struct iscsi_task *task, int state) * This is used when drivers do not need or cannot perform * lower level pdu processing. * - * Called with session lock + * Called with session back_lock */ void iscsi_complete_scsi_task(struct iscsi_task *task, uint32_t exp_cmdsn, uint32_t max_cmdsn) @@ -600,25 +568,57 @@ void iscsi_complete_scsi_task(struct iscsi_task *task, } EXPORT_SYMBOL_GPL(iscsi_complete_scsi_task); +/* + * Must be called with back and frwd lock + */ +static bool cleanup_queued_task(struct iscsi_task *task) +{ + struct iscsi_conn *conn = task->conn; + bool early_complete = false; + + /* + * We might have raced where we handled a R2T early and got a response + * but have not yet taken the task off the requeue list, then a TMF or + * recovery happened and so we can still see it here. + */ + if (task->state == ISCSI_TASK_COMPLETED) + early_complete = true; + + if (!list_empty(&task->running)) { + list_del_init(&task->running); + /* + * If it's on a list but still running this could be cleanup + * from a TMF or session recovery. + */ + if (task->state == ISCSI_TASK_RUNNING || + task->state == ISCSI_TASK_COMPLETED) + __iscsi_put_task(task); + } + + if (conn->session->running_aborted_task == task) { + conn->session->running_aborted_task = NULL; + __iscsi_put_task(task); + } + + if (conn->task == task) { + conn->task = NULL; + __iscsi_put_task(task); + } + + return early_complete; +} /* - * session lock must be held and if not called for a task that is - * still pending or from the xmit thread, then xmit thread must - * be suspended. + * session back and frwd lock must be held and if not called for a task that + * is still pending or from the xmit thread, then xmit thread must be suspended */ -static void fail_scsi_task(struct iscsi_task *task, int err) +static void __fail_scsi_task(struct iscsi_task *task, int err) { struct iscsi_conn *conn = task->conn; struct scsi_cmnd *sc; int state; - /* - * if a command completes and we get a successful tmf response - * we will hit this because the scsi eh abort code does not take - * a ref to the task. - */ - sc = task->sc; - if (!sc) + if (cleanup_queued_task(task)) return; if (task->state == ISCSI_TASK_PENDING) { @@ -634,17 +634,21 @@ static void fail_scsi_task(struct iscsi_task *task, int err) else state = ISCSI_TASK_ABRT_TMF; + sc = task->sc; sc->result = err << 16; - if (!scsi_bidi_cmnd(sc)) - scsi_set_resid(sc, scsi_bufflen(sc)); - else { - scsi_out(sc)->resid = scsi_out(sc)->length; - scsi_in(sc)->resid = scsi_in(sc)->length; - } - + scsi_set_resid(sc, scsi_bufflen(sc)); iscsi_complete_task(task, state); } +static void fail_scsi_task(struct iscsi_task *task, int err) +{ + struct iscsi_session *session = task->conn->session; + + spin_lock_bh(&session->back_lock); + __fail_scsi_task(task, err); + spin_unlock_bh(&session->back_lock); +} + static int iscsi_prep_mgmt_task(struct iscsi_conn *conn, struct iscsi_task *task) { @@ -691,17 +695,24 @@ static int iscsi_prep_mgmt_task(struct iscsi_conn *conn, return 0; } +/** + * iscsi_alloc_mgmt_task - allocate and setup a mgmt task. + * @conn: iscsi conn that the task will be sent on. + * @hdr: iscsi pdu that will be sent. + * @data: buffer for data segment if needed. + * @data_size: length of data in bytes. + */ static struct iscsi_task * -__iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, +iscsi_alloc_mgmt_task(struct iscsi_conn *conn, struct iscsi_hdr *hdr, char *data, uint32_t data_size) { struct iscsi_session *session = conn->session; - struct iscsi_host *ihost = shost_priv(session->host); uint8_t opcode = hdr->opcode & ISCSI_OPCODE_MASK; struct iscsi_task *task; itt_t itt; - if (session->state == ISCSI_STATE_TERMINATE) + if (session->state == ISCSI_STATE_TERMINATE || + !test_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags)) return NULL; if (opcode == ISCSI_OP_LOGIN || opcode == ISCSI_OP_TEXT) { @@ -717,11 +728,21 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, return NULL; } + if (data_size > ISCSI_DEF_MAX_RECV_SEG_LEN) { + iscsi_conn_printk(KERN_ERR, conn, "Invalid buffer len of %u for login task. Max len is %u\n", data_size, ISCSI_DEF_MAX_RECV_SEG_LEN); + return NULL; + } + task = conn->login_task; } else { if (session->state != ISCSI_STATE_LOGGED_IN) return NULL; + if (data_size != 0) { + iscsi_conn_printk(KERN_ERR, conn, "Can not send data buffer of len %u for op 0x%x\n", data_size, opcode); + return NULL; + } + BUG_ON(conn->c_stage == ISCSI_CONN_INITIAL_STAGE); BUG_ON(conn->c_stage == ISCSI_CONN_STOPPED); @@ -734,7 +755,7 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, * released by the lld when it has transmitted the task for * pdus we do not expect a response for. */ - atomic_set(&task->refcount, 1); + refcount_set(&task->refcount, 1); task->conn = conn; task->sc = NULL; INIT_LIST_HEAD(&task->running); @@ -766,22 +787,57 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, task->conn->session->age); } + return task; + +free_task: + iscsi_put_task(task); + return NULL; +} + +/** + * iscsi_send_mgmt_task - Send task created with iscsi_alloc_mgmt_task. + * @task: iscsi task to send. + * + * On failure this returns a non-zero error code, and the driver must free + * the task with iscsi_put_task; + */ +static int iscsi_send_mgmt_task(struct iscsi_task *task) +{ + struct iscsi_conn *conn = task->conn; + struct iscsi_session *session = conn->session; + struct iscsi_host *ihost = shost_priv(conn->session->host); + int rc = 0; + if (!ihost->workq) { - if (iscsi_prep_mgmt_task(conn, task)) - goto free_task; + rc = iscsi_prep_mgmt_task(conn, task); + if (rc) + return rc; - if (session->tt->xmit_task(task)) - goto free_task; + rc = session->tt->xmit_task(task); + if (rc) + return rc; } else { list_add_tail(&task->running, &conn->mgmtqueue); - iscsi_conn_queue_work(conn); + iscsi_conn_queue_xmit(conn); } - return task; + return 0; +} -free_task: - __iscsi_put_task(task); - return NULL; +static int __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, + char *data, uint32_t data_size) +{ + struct iscsi_task *task; + int rc; + + task = iscsi_alloc_mgmt_task(conn, hdr, data, data_size); + if (!task) + return -ENOMEM; + + rc = iscsi_send_mgmt_task(task); + if (rc) + iscsi_put_task(task); + return rc; } int iscsi_conn_send_pdu(struct iscsi_cls_conn *cls_conn, struct iscsi_hdr *hdr, @@ -791,16 +847,16 @@ int iscsi_conn_send_pdu(struct iscsi_cls_conn *cls_conn, struct iscsi_hdr *hdr, struct iscsi_session *session = conn->session; int err = 0; - spin_lock_bh(&session->lock); - if (!__iscsi_conn_send_pdu(conn, hdr, data, data_size)) + spin_lock_bh(&session->frwd_lock); + if (__iscsi_conn_send_pdu(conn, hdr, data, data_size)) err = -EPERM; - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); return err; } EXPORT_SYMBOL_GPL(iscsi_conn_send_pdu); /** - * iscsi_cmd_rsp - SCSI Command Response processing + * iscsi_scsi_cmd_rsp - SCSI Command Response processing * @conn: iscsi connection * @hdr: iscsi header * @task: scsi command task @@ -808,7 +864,7 @@ EXPORT_SYMBOL_GPL(iscsi_conn_send_pdu); * @datalen: len of buffer * * iscsi_cmd_rsp sets up the scsi_cmnd fields based on the PDU and - * then completes the command and task. + * then completes the command and task. called under back_lock **/ static void iscsi_scsi_cmd_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr, struct iscsi_task *task, char *data, @@ -823,6 +879,27 @@ static void iscsi_scsi_cmd_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr, sc->result = (DID_OK << 16) | rhdr->cmd_status; + if (task->protected) { + sector_t sector; + u8 ascq; + + /** + * Transports that didn't implement check_protection + * callback but still published T10-PI support to scsi-mid + * deserve this BUG_ON. + **/ + BUG_ON(!session->tt->check_protection); + + ascq = session->tt->check_protection(task, §or); + if (ascq) { + scsi_build_sense(sc, 1, ILLEGAL_REQUEST, 0x10, ascq); + scsi_set_sense_information(sc->sense_buffer, + SCSI_SENSE_BUFFERSIZE, + sector); + goto out; + } + } + if (rhdr->response != ISCSI_STATUS_CMD_COMPLETED) { sc->result = DID_ERROR << 16; goto out; @@ -853,14 +930,7 @@ invalid_datalen: if (rhdr->flags & (ISCSI_FLAG_CMD_BIDI_UNDERFLOW | ISCSI_FLAG_CMD_BIDI_OVERFLOW)) { - int res_count = be32_to_cpu(rhdr->bi_residual_count); - - if (scsi_bidi_cmnd(sc) && res_count > 0 && - (rhdr->flags & ISCSI_FLAG_CMD_BIDI_OVERFLOW || - res_count <= scsi_in(sc)->length)) - scsi_in(sc)->resid = res_count; - else - sc->result = (DID_BAD_TARGET << 16) | rhdr->cmd_status; + sc->result = (DID_BAD_TARGET << 16) | rhdr->cmd_status; } if (rhdr->flags & (ISCSI_FLAG_CMD_UNDERFLOW | @@ -887,6 +957,9 @@ out: * @conn: iscsi connection * @hdr: iscsi pdu * @task: scsi command task + * + * iscsi_data_in_rsp sets up the scsi_cmnd fields based on the data received + * then completes the command and task. called under back_lock **/ static void iscsi_data_in_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr, @@ -907,8 +980,8 @@ iscsi_data_in_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr, if (res_count > 0 && (rhdr->flags & ISCSI_FLAG_CMD_OVERFLOW || - res_count <= scsi_in(sc)->length)) - scsi_in(sc)->resid = res_count; + res_count <= sc->sdb.length)) + scsi_set_resid(sc, res_count); else sc->result = (DID_BAD_TARGET << 16) | rhdr->cmd_status; } @@ -923,29 +996,32 @@ iscsi_data_in_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr, static void iscsi_tmf_rsp(struct iscsi_conn *conn, struct iscsi_hdr *hdr) { struct iscsi_tm_rsp *tmf = (struct iscsi_tm_rsp *)hdr; + struct iscsi_session *session = conn->session; conn->exp_statsn = be32_to_cpu(hdr->statsn) + 1; conn->tmfrsp_pdus_cnt++; - if (conn->tmf_state != TMF_QUEUED) + if (session->tmf_state != TMF_QUEUED) return; if (tmf->response == ISCSI_TMF_RSP_COMPLETE) - conn->tmf_state = TMF_SUCCESS; + session->tmf_state = TMF_SUCCESS; else if (tmf->response == ISCSI_TMF_RSP_NO_TASK) - conn->tmf_state = TMF_NOT_FOUND; + session->tmf_state = TMF_NOT_FOUND; else - conn->tmf_state = TMF_FAILED; - wake_up(&conn->ehwait); + session->tmf_state = TMF_FAILED; + wake_up(&session->ehwait); } -static void iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) +static int iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) { struct iscsi_nopout hdr; struct iscsi_task *task; - if (!rhdr && conn->ping_task) - return; + if (!rhdr) { + if (READ_ONCE(conn->ping_task)) + return -EINVAL; + } memset(&hdr, 0, sizeof(struct iscsi_nopout)); hdr.opcode = ISCSI_OP_NOOP_OUT | ISCSI_OP_IMMEDIATE; @@ -958,23 +1034,45 @@ static void iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr) } else hdr.ttt = RESERVED_ITT; - task = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)&hdr, NULL, 0); + task = iscsi_alloc_mgmt_task(conn, (struct iscsi_hdr *)&hdr, NULL, 0); if (!task) + return -ENOMEM; + + if (!rhdr) + WRITE_ONCE(conn->ping_task, task); + + if (iscsi_send_mgmt_task(task)) { + if (!rhdr) + WRITE_ONCE(conn->ping_task, NULL); + iscsi_put_task(task); + iscsi_conn_printk(KERN_ERR, conn, "Could not send nopout\n"); - else if (!rhdr) { + return -EIO; + } else if (!rhdr) { /* only track our nops */ - conn->ping_task = task; conn->last_ping = jiffies; } + + return 0; } +/** + * iscsi_nop_out_rsp - SCSI NOP Response processing + * @task: scsi command task + * @nop: the nop structure + * @data: where to put the data + * @datalen: length of data + * + * iscsi_nop_out_rsp handles nop response from use or + * from user space. called under back_lock + **/ static int iscsi_nop_out_rsp(struct iscsi_task *task, struct iscsi_nopin *nop, char *data, int datalen) { struct iscsi_conn *conn = task->conn; int rc = 0; - if (conn->ping_task != task) { + if (READ_ONCE(conn->ping_task) != task) { /* * If this is not in response to one of our * nops then it must be from userspace. @@ -1013,13 +1111,13 @@ static int iscsi_handle_reject(struct iscsi_conn *conn, struct iscsi_hdr *hdr, iscsi_conn_printk(KERN_ERR, conn, "pdu (op 0x%x itt 0x%x) rejected " "due to DataDigest error.\n", - rejected_pdu.itt, opcode); + opcode, rejected_pdu.itt); break; case ISCSI_REASON_IMM_CMD_REJECT: iscsi_conn_printk(KERN_ERR, conn, "pdu (op 0x%x itt 0x%x) rejected. Too many " "immediate commands.\n", - rejected_pdu.itt, opcode); + opcode, rejected_pdu.itt); /* * We only send one TMF at a time so if the target could not * handle it, then it should get fixed (RFC mandates that @@ -1031,14 +1129,19 @@ static int iscsi_handle_reject(struct iscsi_conn *conn, struct iscsi_hdr *hdr, if (opcode != ISCSI_OP_NOOP_OUT) return 0; - if (rejected_pdu.itt == cpu_to_be32(ISCSI_RESERVED_TAG)) + if (rejected_pdu.itt == cpu_to_be32(ISCSI_RESERVED_TAG)) { /* * nop-out in response to target's nop-out rejected. * Just resend. */ + /* In RX path we are under back lock */ + spin_unlock(&conn->session->back_lock); + spin_lock(&conn->session->frwd_lock); iscsi_send_nopout(conn, (struct iscsi_nopin*)&rejected_pdu); - else { + spin_unlock(&conn->session->frwd_lock); + spin_lock(&conn->session->back_lock); + } else { struct iscsi_task *task; /* * Our nop as ping got dropped. We know the target @@ -1059,8 +1162,8 @@ static int iscsi_handle_reject(struct iscsi_conn *conn, struct iscsi_hdr *hdr, default: iscsi_conn_printk(KERN_ERR, conn, "pdu (op 0x%x itt 0x%x) rejected. Reason " - "code 0x%x\n", rejected_pdu.itt, - rejected_pdu.opcode, reject->reason); + "code 0x%x\n", rejected_pdu.opcode, + rejected_pdu.itt, reject->reason); break; } return rc; @@ -1074,7 +1177,7 @@ static int iscsi_handle_reject(struct iscsi_conn *conn, struct iscsi_hdr *hdr, * This should be used for mgmt tasks like login and nops, or if * the LDD's itt space does not include the session age. * - * The session lock must be held. + * The session back_lock must be held. */ struct iscsi_task *iscsi_itt_to_task(struct iscsi_conn *conn, itt_t itt) { @@ -1103,7 +1206,7 @@ EXPORT_SYMBOL_GPL(iscsi_itt_to_task); * @datalen: len of data buffer * * Completes pdu processing by freeing any resources allocated at - * queuecommand or send generic. session lock must be held and verify + * queuecommand or send generic. session back_lock must be held and verify * itt must have been called. */ int __iscsi_complete_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, @@ -1140,7 +1243,12 @@ int __iscsi_complete_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, if (hdr->ttt == cpu_to_be32(ISCSI_RESERVED_TAG)) break; + /* In RX path we are under back lock */ + spin_unlock(&session->back_lock); + spin_lock(&session->frwd_lock); iscsi_send_nopout(conn, (struct iscsi_nopin*)hdr); + spin_unlock(&session->frwd_lock); + spin_lock(&session->back_lock); break; case ISCSI_OP_REJECT: rc = iscsi_handle_reject(conn, hdr, data, datalen); @@ -1247,9 +1355,9 @@ int iscsi_complete_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, { int rc; - spin_lock(&conn->session->lock); + spin_lock(&conn->session->back_lock); rc = __iscsi_complete_pdu(conn, hdr, data, datalen); - spin_unlock(&conn->session->lock); + spin_unlock(&conn->session->back_lock); return rc; } EXPORT_SYMBOL_GPL(iscsi_complete_pdu); @@ -1293,7 +1401,7 @@ EXPORT_SYMBOL_GPL(iscsi_verify_itt); * * This should be used for cmd tasks. * - * The session lock must be held. + * The session back_lock must be held. */ struct iscsi_task *iscsi_itt_to_ctask(struct iscsi_conn *conn, itt_t itt) { @@ -1306,10 +1414,10 @@ struct iscsi_task *iscsi_itt_to_ctask(struct iscsi_conn *conn, itt_t itt) if (!task || !task->sc) return NULL; - if (task->sc->SCp.phase != conn->session->age) { + if (iscsi_cmd(task->sc)->age != conn->session->age) { iscsi_session_printk(KERN_ERR, conn->session, "task's session age %d, expected %d\n", - task->sc->SCp.phase, conn->session->age); + iscsi_cmd(task->sc)->age, conn->session->age); return NULL; } @@ -1321,19 +1429,16 @@ void iscsi_session_failure(struct iscsi_session *session, enum iscsi_err err) { struct iscsi_conn *conn; - struct device *dev; - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); conn = session->leadconn; if (session->state == ISCSI_STATE_TERMINATE || !conn) { - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); return; } - dev = get_device(&conn->cls_conn->dev); - spin_unlock_bh(&session->lock); - if (!dev) - return; + iscsi_get_conn(conn->cls_conn); + spin_unlock_bh(&session->frwd_lock); /* * if the host is being removed bypass the connection * recovery initialization because we are going to kill @@ -1343,27 +1448,36 @@ void iscsi_session_failure(struct iscsi_session *session, iscsi_conn_error_event(conn->cls_conn, err); else iscsi_conn_failure(conn, err); - put_device(dev); + iscsi_put_conn(conn->cls_conn); } EXPORT_SYMBOL_GPL(iscsi_session_failure); -void iscsi_conn_failure(struct iscsi_conn *conn, enum iscsi_err err) +static bool iscsi_set_conn_failed(struct iscsi_conn *conn) { struct iscsi_session *session = conn->session; - spin_lock_bh(&session->lock); - if (session->state == ISCSI_STATE_FAILED) { - spin_unlock_bh(&session->lock); - return; - } + if (session->state == ISCSI_STATE_FAILED) + return false; if (conn->stop_stage == 0) session->state = ISCSI_STATE_FAILED; - spin_unlock_bh(&session->lock); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); - iscsi_conn_error_event(conn->cls_conn, err); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); + set_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); + return true; +} + +void iscsi_conn_failure(struct iscsi_conn *conn, enum iscsi_err err) +{ + struct iscsi_session *session = conn->session; + bool needs_evt; + + spin_lock_bh(&session->frwd_lock); + needs_evt = iscsi_set_conn_failed(conn); + spin_unlock_bh(&session->frwd_lock); + + if (needs_evt) + iscsi_conn_error_event(conn->cls_conn, err); } EXPORT_SYMBOL_GPL(iscsi_conn_failure); @@ -1384,24 +1498,63 @@ static int iscsi_check_cmdsn_window_closed(struct iscsi_conn *conn) return 0; } -static int iscsi_xmit_task(struct iscsi_conn *conn) +static int iscsi_xmit_task(struct iscsi_conn *conn, struct iscsi_task *task, + bool was_requeue) { - struct iscsi_task *task = conn->task; int rc; - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) + if (!conn->task) { + /* + * Take a ref so we can access it after xmit_task(). + * + * This should never fail because the failure paths will have + * stopped the xmit thread. + */ + if (!iscsi_get_task(task)) { + WARN_ON_ONCE(1); + return 0; + } + } else { + /* Already have a ref from when we failed to send it last call */ + conn->task = NULL; + } + + /* + * If this was a requeue for a R2T we have an extra ref on the task in + * case a bad target sends a cmd rsp before we have handled the task. + */ + if (was_requeue) + iscsi_put_task(task); + + /* + * Do this after dropping the extra ref because if this was a requeue + * it's removed from that list and cleanup_queued_task would miss it. + */ + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { + /* + * Save the task and ref in case we weren't cleaning up this + * task and get woken up again. + */ + conn->task = task; return -ENODATA; + } - __iscsi_get_task(task); - spin_unlock_bh(&conn->session->lock); + spin_unlock_bh(&conn->session->frwd_lock); rc = conn->session->tt->xmit_task(task); - spin_lock_bh(&conn->session->lock); + spin_lock_bh(&conn->session->frwd_lock); if (!rc) { /* done with this task */ task->last_xfer = jiffies; - conn->task = NULL; + } else { + /* + * get an extra ref that is released next time we access it + * as conn->task above. + */ + iscsi_get_task(task); + conn->task = task; } - __iscsi_put_task(task); + + iscsi_put_task(task); return rc; } @@ -1409,9 +1562,7 @@ static int iscsi_xmit_task(struct iscsi_conn *conn) * iscsi_requeue_task - requeue task to run from session workqueue * @task: task to requeue * - * LLDs that need to run a task from the session workqueue should call - * this. The session lock must be held. This should only be called - * by software drivers. + * Callers must have taken a ref to the task that is going to be requeued. */ void iscsi_requeue_task(struct iscsi_task *task) { @@ -1421,9 +1572,18 @@ void iscsi_requeue_task(struct iscsi_task *task) * this may be on the requeue list already if the xmit_task callout * is handling the r2ts while we are adding new ones */ - if (list_empty(&task->running)) + spin_lock_bh(&conn->session->frwd_lock); + if (list_empty(&task->running)) { list_add_tail(&task->running, &conn->requeue); - iscsi_conn_queue_work(conn); + } else { + /* + * Don't need the extra ref since it's already requeued and + * has a ref. + */ + iscsi_put_task(task); + } + iscsi_conn_queue_xmit(conn); + spin_unlock_bh(&conn->session->frwd_lock); } EXPORT_SYMBOL_GPL(iscsi_requeue_task); @@ -1441,15 +1601,15 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) struct iscsi_task *task; int rc = 0; - spin_lock_bh(&conn->session->lock); - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + spin_lock_bh(&conn->session->frwd_lock); + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { ISCSI_DBG_SESSION(conn->session, "Tx suspended!\n"); - spin_unlock_bh(&conn->session->lock); + spin_unlock_bh(&conn->session->frwd_lock); return -ENODATA; } if (conn->task) { - rc = iscsi_xmit_task(conn); + rc = iscsi_xmit_task(conn, conn->task, false); if (rc) goto done; } @@ -1461,40 +1621,61 @@ static int iscsi_data_xmit(struct iscsi_conn *conn) */ check_mgmt: while (!list_empty(&conn->mgmtqueue)) { - conn->task = list_entry(conn->mgmtqueue.next, - struct iscsi_task, running); - list_del_init(&conn->task->running); - if (iscsi_prep_mgmt_task(conn, conn->task)) { - __iscsi_put_task(conn->task); - conn->task = NULL; + task = list_entry(conn->mgmtqueue.next, struct iscsi_task, + running); + list_del_init(&task->running); + if (iscsi_prep_mgmt_task(conn, task)) { + /* regular RX path uses back_lock */ + spin_lock_bh(&conn->session->back_lock); + __iscsi_put_task(task); + spin_unlock_bh(&conn->session->back_lock); continue; } - rc = iscsi_xmit_task(conn); + rc = iscsi_xmit_task(conn, task, false); + if (rc) + goto done; + } + +check_requeue: + while (!list_empty(&conn->requeue)) { + /* + * we always do fastlogout - conn stop code will clean up. + */ + if (conn->session->state == ISCSI_STATE_LOGGING_OUT) + break; + + task = list_entry(conn->requeue.next, struct iscsi_task, + running); + + if (iscsi_check_tmf_restrictions(task, ISCSI_OP_SCSI_DATA_OUT)) + break; + + list_del_init(&task->running); + rc = iscsi_xmit_task(conn, task, true); if (rc) goto done; + if (!list_empty(&conn->mgmtqueue)) + goto check_mgmt; } /* process pending command queue */ while (!list_empty(&conn->cmdqueue)) { - conn->task = list_entry(conn->cmdqueue.next, struct iscsi_task, - running); - list_del_init(&conn->task->running); + task = list_entry(conn->cmdqueue.next, struct iscsi_task, + running); + list_del_init(&task->running); if (conn->session->state == ISCSI_STATE_LOGGING_OUT) { - fail_scsi_task(conn->task, DID_IMM_RETRY); + fail_scsi_task(task, DID_IMM_RETRY); continue; } - rc = iscsi_prep_scsi_cmd_pdu(conn->task); + rc = iscsi_prep_scsi_cmd_pdu(task); if (rc) { - if (rc == -ENOMEM || rc == -EACCES) { - list_add_tail(&conn->task->running, - &conn->cmdqueue); - conn->task = NULL; - goto done; - } else - fail_scsi_task(conn->task, DID_ABORT); + if (rc == -ENOMEM || rc == -EACCES) + fail_scsi_task(task, DID_IMM_RETRY); + else + fail_scsi_task(task, DID_ABORT); continue; } - rc = iscsi_xmit_task(conn); + rc = iscsi_xmit_task(conn, task, false); if (rc) goto done; /* @@ -1504,34 +1685,15 @@ check_mgmt: */ if (!list_empty(&conn->mgmtqueue)) goto check_mgmt; + if (!list_empty(&conn->requeue)) + goto check_requeue; } - while (!list_empty(&conn->requeue)) { - /* - * we always do fastlogout - conn stop code will clean up. - */ - if (conn->session->state == ISCSI_STATE_LOGGING_OUT) - break; - - task = list_entry(conn->requeue.next, struct iscsi_task, - running); - if (iscsi_check_tmf_restrictions(task, ISCSI_OP_SCSI_DATA_OUT)) - break; - - conn->task = task; - list_del_init(&conn->task->running); - conn->task->state = ISCSI_TASK_RUNNING; - rc = iscsi_xmit_task(conn); - if (rc) - goto done; - if (!list_empty(&conn->mgmtqueue)) - goto check_mgmt; - } - spin_unlock_bh(&conn->session->lock); + spin_unlock_bh(&conn->session->frwd_lock); return -ENODATA; done: - spin_unlock_bh(&conn->session->lock); + spin_unlock_bh(&conn->session->frwd_lock); return rc; } @@ -1557,16 +1719,17 @@ static inline struct iscsi_task *iscsi_alloc_task(struct iscsi_conn *conn, (void *) &task, sizeof(void *))) return NULL; - sc->SCp.phase = conn->session->age; - sc->SCp.ptr = (char *) task; + iscsi_cmd(sc)->age = conn->session->age; + iscsi_cmd(sc)->task = task; - atomic_set(&task->refcount, 1); + refcount_set(&task->refcount, 1); task->state = ISCSI_TASK_PENDING; task->conn = conn; task->sc = sc; task->have_checked_conn = false; task->last_timeout = jiffies; task->last_xfer = jiffies; + task->protected = false; INIT_LIST_HEAD(&task->running); return task; } @@ -1594,13 +1757,13 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) struct iscsi_task *task = NULL; sc->result = 0; - sc->SCp.ptr = NULL; + iscsi_cmd(sc)->task = NULL; ihost = shost_priv(host); cls_session = starget_to_session(scsi_target(sc->device)); session = cls_session->dd_data; - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); reason = iscsi_session_chkready(cls_session); if (reason) { @@ -1617,6 +1780,16 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) */ switch (session->state) { case ISCSI_STATE_FAILED: + /* + * cmds should fail during shutdown, if the session + * state is bad, allowing completion to happen + */ + if (unlikely(system_state != SYSTEM_RUNNING)) { + reason = FAILURE_SESSION_FAILED; + sc->result = DID_NO_CONNECT << 16; + break; + } + fallthrough; case ISCSI_STATE_IN_RECOVERY: reason = FAILURE_SESSION_IN_RECOVERY; sc->result = DID_IMM_RETRY << 16; @@ -1647,9 +1820,9 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) goto fault; } - if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { + if (test_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags)) { reason = FAILURE_SESSION_IN_RECOVERY; - sc->result = DID_REQUEUE; + sc->result = DID_REQUEUE << 16; goto fault; } @@ -1682,57 +1855,37 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc) } } else { list_add_tail(&task->running, &conn->cmdqueue); - iscsi_conn_queue_work(conn); + iscsi_conn_queue_xmit(conn); } session->queued_cmdsn++; - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); return 0; prepd_reject: + spin_lock_bh(&session->back_lock); iscsi_complete_task(task, ISCSI_TASK_REQUEUE_SCSIQ); + spin_unlock_bh(&session->back_lock); reject: - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); ISCSI_DBG_SESSION(session, "cmd 0x%x rejected (%d)\n", sc->cmnd[0], reason); return SCSI_MLQUEUE_TARGET_BUSY; prepd_fault: + spin_lock_bh(&session->back_lock); iscsi_complete_task(task, ISCSI_TASK_REQUEUE_SCSIQ); + spin_unlock_bh(&session->back_lock); fault: - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); ISCSI_DBG_SESSION(session, "iscsi: cmd 0x%x is not queued (%d)\n", sc->cmnd[0], reason); - if (!scsi_bidi_cmnd(sc)) - scsi_set_resid(sc, scsi_bufflen(sc)); - else { - scsi_out(sc)->resid = scsi_out(sc)->length; - scsi_in(sc)->resid = scsi_in(sc)->length; - } - sc->scsi_done(sc); + scsi_set_resid(sc, scsi_bufflen(sc)); + scsi_done(sc); return 0; } EXPORT_SYMBOL_GPL(iscsi_queuecommand); -int iscsi_change_queue_depth(struct scsi_device *sdev, int depth, int reason) -{ - switch (reason) { - case SCSI_QDEPTH_DEFAULT: - scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth); - break; - case SCSI_QDEPTH_QFULL: - scsi_track_queue_full(sdev, depth); - break; - case SCSI_QDEPTH_RAMP_UP: - scsi_adjust_queue_depth(sdev, scsi_get_tag_type(sdev), depth); - break; - default: - return -EOPNOTSUPP; - } - return sdev->queue_depth; -} -EXPORT_SYMBOL_GPL(iscsi_change_queue_depth); - int iscsi_target_alloc(struct scsi_target *starget) { struct iscsi_cls_session *cls_session = starget_to_session(starget); @@ -1743,45 +1896,41 @@ int iscsi_target_alloc(struct scsi_target *starget) } EXPORT_SYMBOL_GPL(iscsi_target_alloc); -static void iscsi_tmf_timedout(unsigned long data) +static void iscsi_tmf_timedout(struct timer_list *t) { - struct iscsi_conn *conn = (struct iscsi_conn *)data; - struct iscsi_session *session = conn->session; + struct iscsi_session *session = timer_container_of(session, t, + tmf_timer); - spin_lock(&session->lock); - if (conn->tmf_state == TMF_QUEUED) { - conn->tmf_state = TMF_TIMEDOUT; + spin_lock(&session->frwd_lock); + if (session->tmf_state == TMF_QUEUED) { + session->tmf_state = TMF_TIMEDOUT; ISCSI_DBG_EH(session, "tmf timedout\n"); /* unblock eh_abort() */ - wake_up(&conn->ehwait); + wake_up(&session->ehwait); } - spin_unlock(&session->lock); + spin_unlock(&session->frwd_lock); } static int iscsi_exec_task_mgmt_fn(struct iscsi_conn *conn, struct iscsi_tm *hdr, int age, int timeout) + __must_hold(&session->frwd_lock) { struct iscsi_session *session = conn->session; - struct iscsi_task *task; - task = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)hdr, - NULL, 0); - if (!task) { - spin_unlock_bh(&session->lock); + if (__iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)hdr, NULL, 0)) { + spin_unlock_bh(&session->frwd_lock); iscsi_conn_printk(KERN_ERR, conn, "Could not send TMF.\n"); iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); return -EPERM; } conn->tmfcmd_pdus_cnt++; - conn->tmf_timer.expires = timeout * HZ + jiffies; - conn->tmf_timer.function = iscsi_tmf_timedout; - conn->tmf_timer.data = (unsigned long)conn; - add_timer(&conn->tmf_timer); + session->tmf_timer.expires = timeout * HZ + jiffies; + add_timer(&session->tmf_timer); ISCSI_DBG_EH(session, "tmf set timeout\n"); - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); mutex_unlock(&session->eh_mutex); /* @@ -1792,15 +1941,15 @@ static int iscsi_exec_task_mgmt_fn(struct iscsi_conn *conn, * 3) session is terminated or restarted or userspace has * given up on recovery */ - wait_event_interruptible(conn->ehwait, age != session->age || + wait_event_interruptible(session->ehwait, age != session->age || session->state != ISCSI_STATE_LOGGED_IN || - conn->tmf_state != TMF_QUEUED); + session->tmf_state != TMF_QUEUED); if (signal_pending(current)) flush_signals(current); - del_timer_sync(&conn->tmf_timer); + timer_delete_sync(&session->tmf_timer); mutex_lock(&session->eh_mutex); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); /* if the session drops it will clean up the task */ if (age != session->age || session->state != ISCSI_STATE_LOGGED_IN) @@ -1809,35 +1958,50 @@ static int iscsi_exec_task_mgmt_fn(struct iscsi_conn *conn, } /* - * Fail commands. session lock held and recv side suspended and xmit - * thread flushed + * Fail commands. session frwd lock held and xmit thread flushed. */ -static void fail_scsi_tasks(struct iscsi_conn *conn, unsigned lun, - int error) +static void fail_scsi_tasks(struct iscsi_conn *conn, u64 lun, int error) { + struct iscsi_session *session = conn->session; struct iscsi_task *task; int i; - for (i = 0; i < conn->session->cmds_max; i++) { - task = conn->session->cmds[i]; +restart_cmd_loop: + spin_lock_bh(&session->back_lock); + for (i = 0; i < session->cmds_max; i++) { + task = session->cmds[i]; if (!task->sc || task->state == ISCSI_TASK_FREE) continue; if (lun != -1 && lun != task->sc->device->lun) continue; + /* + * The cmd is completing but if this is called from an eh + * callout path then when we return scsi-ml owns the cmd. Wait + * for the completion path to finish freeing the cmd. + */ + if (!iscsi_get_task(task)) { + spin_unlock_bh(&session->back_lock); + spin_unlock_bh(&session->frwd_lock); + udelay(ISCSI_CMD_COMPL_WAIT); + spin_lock_bh(&session->frwd_lock); + goto restart_cmd_loop; + } - ISCSI_DBG_SESSION(conn->session, + ISCSI_DBG_SESSION(session, "failing sc %p itt 0x%x state %d\n", task->sc, task->itt, task->state); - fail_scsi_task(task, error); + __fail_scsi_task(task, error); + __iscsi_put_task(task); } + spin_unlock_bh(&session->back_lock); } /** * iscsi_suspend_queue - suspend iscsi_queuecommand * @conn: iscsi conn to stop queueing IO on * - * This grabs the session lock to make sure no one is in + * This grabs the session frwd_lock to make sure no one is in * xmit_task/queuecommand, and then sets suspend to prevent * new commands from being queued. This only needs to be called * by offload drivers that need to sync a path like ep disconnect @@ -1846,15 +2010,15 @@ static void fail_scsi_tasks(struct iscsi_conn *conn, unsigned lun, */ void iscsi_suspend_queue(struct iscsi_conn *conn) { - spin_lock_bh(&conn->session->lock); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); - spin_unlock_bh(&conn->session->lock); + spin_lock_bh(&conn->session->frwd_lock); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); + spin_unlock_bh(&conn->session->frwd_lock); } EXPORT_SYMBOL_GPL(iscsi_suspend_queue); /** * iscsi_suspend_tx - suspend iscsi_data_xmit - * @conn: iscsi conn tp stop processing IO on. + * @conn: iscsi conn to stop processing IO on. * * This function sets the suspend bit to prevent iscsi_data_xmit * from sending new IO, and if work is queued on the xmit thread @@ -1865,17 +2029,32 @@ void iscsi_suspend_tx(struct iscsi_conn *conn) struct Scsi_Host *shost = conn->session->host; struct iscsi_host *ihost = shost_priv(shost); - set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + set_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); if (ihost->workq) - flush_workqueue(ihost->workq); + flush_work(&conn->xmitwork); } EXPORT_SYMBOL_GPL(iscsi_suspend_tx); static void iscsi_start_tx(struct iscsi_conn *conn) { - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); - iscsi_conn_queue_work(conn); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); + iscsi_conn_queue_xmit(conn); +} + +/** + * iscsi_suspend_rx - Prevent recvwork from running again. + * @conn: iscsi conn to stop. + */ +void iscsi_suspend_rx(struct iscsi_conn *conn) +{ + struct Scsi_Host *shost = conn->session->host; + struct iscsi_host *ihost = shost_priv(shost); + + set_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); + if (ihost->workq) + flush_work(&conn->recvwork); } +EXPORT_SYMBOL_GPL(iscsi_suspend_rx); /* * We want to make sure a ping is in flight. It has timed out. @@ -1885,7 +2064,7 @@ static void iscsi_start_tx(struct iscsi_conn *conn) */ static int iscsi_has_ping_timed_out(struct iscsi_conn *conn) { - if (conn->ping_task && + if (READ_ONCE(conn->ping_task) && time_before_eq(conn->last_recv + (conn->recv_timeout * HZ) + (conn->ping_timeout * HZ), jiffies)) return 1; @@ -1893,9 +2072,9 @@ static int iscsi_has_ping_timed_out(struct iscsi_conn *conn) return 0; } -static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) +enum scsi_timeout_action iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) { - enum blk_eh_timer_return rc = BLK_EH_NOT_HANDLED; + enum scsi_timeout_action rc = SCSI_EH_NOT_HANDLED; struct iscsi_task *task = NULL, *running_task; struct iscsi_cls_session *cls_session; struct iscsi_session *session; @@ -1907,30 +2086,56 @@ static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) ISCSI_DBG_EH(session, "scsi cmd %p timedout\n", sc); - spin_lock(&session->lock); - task = (struct iscsi_task *)sc->SCp.ptr; + spin_lock_bh(&session->frwd_lock); + spin_lock(&session->back_lock); + task = iscsi_cmd(sc)->task; if (!task) { /* * Raced with completion. Blk layer has taken ownership * so let timeout code complete it now. */ - rc = BLK_EH_HANDLED; + rc = SCSI_EH_NOT_HANDLED; + spin_unlock(&session->back_lock); goto done; } + if (!iscsi_get_task(task)) { + /* + * Racing with the completion path right now, so give it more + * time so that path can complete it like normal. + */ + rc = SCSI_EH_RESET_TIMER; + task = NULL; + spin_unlock(&session->back_lock); + goto done; + } + spin_unlock(&session->back_lock); if (session->state != ISCSI_STATE_LOGGED_IN) { /* + * During shutdown, if session is prematurely disconnected, + * recovery won't happen and there will be hung cmds. Not + * handling cmds would trigger EH, also bad in this case. + * Instead, handle cmd, allow completion to happen and let + * upper layer to deal with the result. + */ + if (unlikely(system_state != SYSTEM_RUNNING)) { + sc->result = DID_NO_CONNECT << 16; + ISCSI_DBG_EH(session, "sc on shutdown, handled\n"); + rc = SCSI_EH_NOT_HANDLED; + goto done; + } + /* * We are probably in the middle of iscsi recovery so let * that complete and handle the error. */ - rc = BLK_EH_RESET_TIMER; + rc = SCSI_EH_RESET_TIMER; goto done; } conn = session->leadconn; if (!conn) { /* In the middle of shuting down */ - rc = BLK_EH_RESET_TIMER; + rc = SCSI_EH_RESET_TIMER; goto done; } @@ -1947,7 +2152,7 @@ static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) "Last data xfer at %lu. Last timeout was at " "%lu\n.", task->last_xfer, task->last_timeout); task->have_checked_conn = false; - rc = BLK_EH_RESET_TIMER; + rc = SCSI_EH_RESET_TIMER; goto done; } @@ -1958,10 +2163,11 @@ static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) * and can let the iscsi eh handle it */ if (iscsi_has_ping_timed_out(conn)) { - rc = BLK_EH_RESET_TIMER; + rc = SCSI_EH_RESET_TIMER; goto done; } + spin_lock(&session->back_lock); for (i = 0; i < conn->session->cmds_max; i++) { running_task = conn->session->cmds[i]; if (!running_task->sc || running_task == task || @@ -1994,10 +2200,12 @@ static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) "last xfer %lu/%lu. Last check %lu.\n", task->last_xfer, running_task->last_xfer, task->last_timeout); - rc = BLK_EH_RESET_TIMER; + spin_unlock(&session->back_lock); + rc = SCSI_EH_RESET_TIMER; goto done; } } + spin_unlock(&session->back_lock); /* Assumes nop timeout is shorter than scsi cmd timeout */ if (task->have_checked_conn) @@ -2007,33 +2215,37 @@ static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc) * Checking the transport already or nop from a cmd timeout still * running */ - if (conn->ping_task) { + if (READ_ONCE(conn->ping_task)) { task->have_checked_conn = true; - rc = BLK_EH_RESET_TIMER; + rc = SCSI_EH_RESET_TIMER; goto done; } /* Make sure there is a transport check done */ iscsi_send_nopout(conn, NULL); task->have_checked_conn = true; - rc = BLK_EH_RESET_TIMER; + rc = SCSI_EH_RESET_TIMER; done: - if (task) + spin_unlock_bh(&session->frwd_lock); + + if (task) { task->last_timeout = jiffies; - spin_unlock(&session->lock); - ISCSI_DBG_EH(session, "return %s\n", rc == BLK_EH_RESET_TIMER ? - "timer reset" : "nh"); + iscsi_put_task(task); + } + ISCSI_DBG_EH(session, "return %s\n", rc == SCSI_EH_RESET_TIMER ? + "timer reset" : "shutdown or nh"); return rc; } +EXPORT_SYMBOL_GPL(iscsi_eh_cmd_timed_out); -static void iscsi_check_transport_timeouts(unsigned long data) +static void iscsi_check_transport_timeouts(struct timer_list *t) { - struct iscsi_conn *conn = (struct iscsi_conn *)data; + struct iscsi_conn *conn = timer_container_of(conn, t, transport_timer); struct iscsi_session *session = conn->session; unsigned long recv_timeout, next_timeout = 0, last_recv; - spin_lock(&session->lock); + spin_lock(&session->frwd_lock); if (session->state != ISCSI_STATE_LOGGED_IN) goto done; @@ -2050,24 +2262,73 @@ static void iscsi_check_transport_timeouts(unsigned long data) "last ping %lu, now %lu\n", conn->ping_timeout, conn->recv_timeout, last_recv, conn->last_ping, jiffies); - spin_unlock(&session->lock); - iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED); + spin_unlock(&session->frwd_lock); + iscsi_conn_failure(conn, ISCSI_ERR_NOP_TIMEDOUT); return; } if (time_before_eq(last_recv + recv_timeout, jiffies)) { /* send a ping to try to provoke some traffic */ ISCSI_DBG_CONN(conn, "Sending nopout as ping\n"); - iscsi_send_nopout(conn, NULL); - next_timeout = conn->last_ping + (conn->ping_timeout * HZ); + if (iscsi_send_nopout(conn, NULL)) + next_timeout = jiffies + (1 * HZ); + else + next_timeout = conn->last_ping + (conn->ping_timeout * HZ); } else next_timeout = last_recv + recv_timeout; ISCSI_DBG_CONN(conn, "Setting next tmo %lu\n", next_timeout); mod_timer(&conn->transport_timer, next_timeout); done: - spin_unlock(&session->lock); + spin_unlock(&session->frwd_lock); +} + +/** + * iscsi_conn_unbind - prevent queueing to conn. + * @cls_conn: iscsi conn ep is bound to. + * @is_active: is the conn in use for boot or is this for EH/termination + * + * This must be called by drivers implementing the ep_disconnect callout. + * It disables queueing to the connection from libiscsi in preparation for + * an ep_disconnect call. + */ +void iscsi_conn_unbind(struct iscsi_cls_conn *cls_conn, bool is_active) +{ + struct iscsi_session *session; + struct iscsi_conn *conn; + + if (!cls_conn) + return; + + conn = cls_conn->dd_data; + session = conn->session; + /* + * Wait for iscsi_eh calls to exit. We don't wait for the tmf to + * complete or timeout. The caller just wants to know what's running + * is everything that needs to be cleaned up, and no cmds will be + * queued. + */ + mutex_lock(&session->eh_mutex); + + iscsi_suspend_queue(conn); + iscsi_suspend_tx(conn); + + spin_lock_bh(&session->frwd_lock); + clear_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags); + + if (!is_active) { + /* + * if logout timed out before userspace could even send a PDU + * the state might still be in ISCSI_STATE_LOGGED_IN and + * allowing new cmds and TMFs. + */ + if (session->state == ISCSI_STATE_LOGGED_IN) + iscsi_set_conn_failed(conn); + } + spin_unlock_bh(&session->frwd_lock); + mutex_unlock(&session->eh_mutex); } +EXPORT_SYMBOL_GPL(iscsi_conn_unbind); static void iscsi_prep_abort_task_pdu(struct iscsi_task *task, struct iscsi_tm *hdr) @@ -2088,23 +2349,24 @@ int iscsi_eh_abort(struct scsi_cmnd *sc) struct iscsi_conn *conn; struct iscsi_task *task; struct iscsi_tm *hdr; - int rc, age; + int age; cls_session = starget_to_session(scsi_target(sc->device)); session = cls_session->dd_data; ISCSI_DBG_EH(session, "aborting sc %p\n", sc); +completion_check: mutex_lock(&session->eh_mutex); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); /* * if session was ISCSI_STATE_IN_RECOVERY then we may not have * got the command. */ - if (!sc->SCp.ptr) { + if (!iscsi_cmd(sc)->task) { ISCSI_DBG_EH(session, "sc never reached iscsi layer or " "it completed.\n"); - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); mutex_unlock(&session->eh_mutex); return SUCCESS; } @@ -2114,49 +2376,61 @@ int iscsi_eh_abort(struct scsi_cmnd *sc) * then let the host reset code handle this */ if (!session->leadconn || session->state != ISCSI_STATE_LOGGED_IN || - sc->SCp.phase != session->age) { - spin_unlock_bh(&session->lock); + iscsi_cmd(sc)->age != session->age) { + spin_unlock_bh(&session->frwd_lock); mutex_unlock(&session->eh_mutex); ISCSI_DBG_EH(session, "failing abort due to dropped " "session.\n"); return FAILED; } - conn = session->leadconn; - conn->eh_abort_cnt++; - age = session->age; + spin_lock(&session->back_lock); + task = iscsi_cmd(sc)->task; + if (!task || !task->sc) { + /* task completed before time out */ + ISCSI_DBG_EH(session, "sc completed while abort in progress\n"); - task = (struct iscsi_task *)sc->SCp.ptr; - ISCSI_DBG_EH(session, "aborting [sc %p itt 0x%x]\n", - sc, task->itt); + spin_unlock(&session->back_lock); + spin_unlock_bh(&session->frwd_lock); + mutex_unlock(&session->eh_mutex); + return SUCCESS; + } - /* task completed before time out */ - if (!task->sc) { - ISCSI_DBG_EH(session, "sc completed while abort in progress\n"); - goto success; + if (!iscsi_get_task(task)) { + spin_unlock(&session->back_lock); + spin_unlock_bh(&session->frwd_lock); + mutex_unlock(&session->eh_mutex); + /* We are just about to call iscsi_free_task so wait for it. */ + udelay(ISCSI_CMD_COMPL_WAIT); + goto completion_check; } + ISCSI_DBG_EH(session, "aborting [sc %p itt 0x%x]\n", sc, task->itt); + conn = session->leadconn; + iscsi_get_conn(conn->cls_conn); + conn->eh_abort_cnt++; + age = session->age; + spin_unlock(&session->back_lock); + if (task->state == ISCSI_TASK_PENDING) { fail_scsi_task(task, DID_ABORT); goto success; } /* only have one tmf outstanding at a time */ - if (conn->tmf_state != TMF_INITIAL) + if (session->tmf_state != TMF_INITIAL) goto failed; - conn->tmf_state = TMF_QUEUED; + session->tmf_state = TMF_QUEUED; - hdr = &conn->tmhdr; + hdr = &session->tmhdr; iscsi_prep_abort_task_pdu(task, hdr); - if (iscsi_exec_task_mgmt_fn(conn, hdr, age, session->abort_timeout)) { - rc = FAILED; + if (iscsi_exec_task_mgmt_fn(conn, hdr, age, session->abort_timeout)) goto failed; - } - switch (conn->tmf_state) { + switch (session->tmf_state) { case TMF_SUCCESS: - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); /* * stop tx side incase the target had sent a abort rsp but * the initiator was still writing out data. @@ -2167,45 +2441,57 @@ int iscsi_eh_abort(struct scsi_cmnd *sc) * good and have never sent us a successful tmf response * then sent more data for the cmd. */ - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); fail_scsi_task(task, DID_ABORT); - conn->tmf_state = TMF_INITIAL; + session->tmf_state = TMF_INITIAL; memset(hdr, 0, sizeof(*hdr)); - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); iscsi_start_tx(conn); goto success_unlocked; case TMF_TIMEDOUT: - spin_unlock_bh(&session->lock); + session->running_aborted_task = task; + spin_unlock_bh(&session->frwd_lock); iscsi_conn_failure(conn, ISCSI_ERR_SCSI_EH_SESSION_RST); goto failed_unlocked; case TMF_NOT_FOUND: - if (!sc->SCp.ptr) { - conn->tmf_state = TMF_INITIAL; + if (iscsi_task_is_completed(task)) { + session->tmf_state = TMF_INITIAL; memset(hdr, 0, sizeof(*hdr)); /* task completed before tmf abort response */ ISCSI_DBG_EH(session, "sc completed while abort in " "progress\n"); goto success; } - /* fall through */ + fallthrough; default: - conn->tmf_state = TMF_INITIAL; + session->tmf_state = TMF_INITIAL; goto failed; } success: - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); success_unlocked: ISCSI_DBG_EH(session, "abort success [sc %p itt 0x%x]\n", sc, task->itt); + iscsi_put_task(task); + iscsi_put_conn(conn->cls_conn); mutex_unlock(&session->eh_mutex); return SUCCESS; failed: - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); failed_unlocked: ISCSI_DBG_EH(session, "abort failed [sc %p itt 0x%x]\n", sc, task ? task->itt : 0); + /* + * The driver might be accessing the task so hold the ref. The conn + * stop cleanup will drop the ref after ep_disconnect so we know the + * driver's no longer touching the task. + */ + if (!session->running_aborted_task) + iscsi_put_task(task); + + iscsi_put_conn(conn->cls_conn); mutex_unlock(&session->eh_mutex); return FAILED; } @@ -2232,10 +2518,11 @@ int iscsi_eh_device_reset(struct scsi_cmnd *sc) cls_session = starget_to_session(scsi_target(sc->device)); session = cls_session->dd_data; - ISCSI_DBG_EH(session, "LU Reset [sc %p lun %u]\n", sc, sc->device->lun); + ISCSI_DBG_EH(session, "LU Reset [sc %p lun %llu]\n", sc, + sc->device->lun); mutex_lock(&session->eh_mutex); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); /* * Just check if we are not logged in. We cannot check for * the phase because the reset could come from a ioctl. @@ -2245,11 +2532,11 @@ int iscsi_eh_device_reset(struct scsi_cmnd *sc) conn = session->leadconn; /* only have one tmf outstanding at a time */ - if (conn->tmf_state != TMF_INITIAL) + if (session->tmf_state != TMF_INITIAL) goto unlock; - conn->tmf_state = TMF_QUEUED; + session->tmf_state = TMF_QUEUED; - hdr = &conn->tmhdr; + hdr = &session->tmhdr; iscsi_prep_lun_reset_pdu(sc, hdr); if (iscsi_exec_task_mgmt_fn(conn, hdr, session->age, @@ -2258,34 +2545,34 @@ int iscsi_eh_device_reset(struct scsi_cmnd *sc) goto unlock; } - switch (conn->tmf_state) { + switch (session->tmf_state) { case TMF_SUCCESS: break; case TMF_TIMEDOUT: - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); iscsi_conn_failure(conn, ISCSI_ERR_SCSI_EH_SESSION_RST); goto done; default: - conn->tmf_state = TMF_INITIAL; + session->tmf_state = TMF_INITIAL; goto unlock; } rc = SUCCESS; - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); iscsi_suspend_tx(conn); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); memset(hdr, 0, sizeof(*hdr)); fail_scsi_tasks(conn, sc->device->lun, DID_ERROR); - conn->tmf_state = TMF_INITIAL; - spin_unlock_bh(&session->lock); + session->tmf_state = TMF_INITIAL; + spin_unlock_bh(&session->frwd_lock); iscsi_start_tx(conn); goto done; unlock: - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); done: ISCSI_DBG_EH(session, "dev reset result = %s\n", rc == SUCCESS ? "SUCCESS" : "FAILED"); @@ -2298,13 +2585,12 @@ void iscsi_session_recovery_timedout(struct iscsi_cls_session *cls_session) { struct iscsi_session *session = cls_session->dd_data; - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); if (session->state != ISCSI_STATE_LOGGED_IN) { session->state = ISCSI_STATE_RECOVERY_FAILED; - if (session->leadconn) - wake_up(&session->leadconn->ehwait); + wake_up(&session->ehwait); } - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); } EXPORT_SYMBOL_GPL(iscsi_session_recovery_timedout); @@ -2323,31 +2609,31 @@ int iscsi_eh_session_reset(struct scsi_cmnd *sc) cls_session = starget_to_session(scsi_target(sc->device)); session = cls_session->dd_data; - conn = session->leadconn; mutex_lock(&session->eh_mutex); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); if (session->state == ISCSI_STATE_TERMINATE) { failed: ISCSI_DBG_EH(session, "failing session reset: Could not log back into " - "%s, %s [age %d]\n", session->targetname, - conn->persistent_address, session->age); - spin_unlock_bh(&session->lock); + "%s [age %d]\n", session->targetname, + session->age); + spin_unlock_bh(&session->frwd_lock); mutex_unlock(&session->eh_mutex); return FAILED; } - spin_unlock_bh(&session->lock); + conn = session->leadconn; + iscsi_get_conn(conn->cls_conn); + + spin_unlock_bh(&session->frwd_lock); mutex_unlock(&session->eh_mutex); - /* - * we drop the lock here but the leadconn cannot be destoyed while - * we are in the scsi eh - */ + iscsi_conn_failure(conn, ISCSI_ERR_SCSI_EH_SESSION_RST); + iscsi_put_conn(conn->cls_conn); ISCSI_DBG_EH(session, "wait for relogin\n"); - wait_event_interruptible(conn->ehwait, + wait_event_interruptible(session->ehwait, session->state == ISCSI_STATE_TERMINATE || session->state == ISCSI_STATE_LOGGED_IN || session->state == ISCSI_STATE_RECOVERY_FAILED); @@ -2355,14 +2641,14 @@ failed: flush_signals(current); mutex_lock(&session->eh_mutex); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); if (session->state == ISCSI_STATE_LOGGED_IN) { ISCSI_DBG_EH(session, "session reset succeeded for %s,%s\n", session->targetname, conn->persistent_address); } else goto failed; - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); mutex_unlock(&session->eh_mutex); return SUCCESS; } @@ -2383,7 +2669,7 @@ static void iscsi_prep_tgt_reset_pdu(struct scsi_cmnd *sc, struct iscsi_tm *hdr) * * This will attempt to send a warm target reset. */ -int iscsi_eh_target_reset(struct scsi_cmnd *sc) +static int iscsi_eh_target_reset(struct scsi_cmnd *sc) { struct iscsi_cls_session *cls_session; struct iscsi_session *session; @@ -2398,7 +2684,7 @@ int iscsi_eh_target_reset(struct scsi_cmnd *sc) session->targetname); mutex_lock(&session->eh_mutex); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); /* * Just check if we are not logged in. We cannot check for * the phase because the reset could come from a ioctl. @@ -2408,11 +2694,11 @@ int iscsi_eh_target_reset(struct scsi_cmnd *sc) conn = session->leadconn; /* only have one tmf outstanding at a time */ - if (conn->tmf_state != TMF_INITIAL) + if (session->tmf_state != TMF_INITIAL) goto unlock; - conn->tmf_state = TMF_QUEUED; + session->tmf_state = TMF_QUEUED; - hdr = &conn->tmhdr; + hdr = &session->tmhdr; iscsi_prep_tgt_reset_pdu(sc, hdr); if (iscsi_exec_task_mgmt_fn(conn, hdr, session->age, @@ -2421,41 +2707,40 @@ int iscsi_eh_target_reset(struct scsi_cmnd *sc) goto unlock; } - switch (conn->tmf_state) { + switch (session->tmf_state) { case TMF_SUCCESS: break; case TMF_TIMEDOUT: - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); iscsi_conn_failure(conn, ISCSI_ERR_SCSI_EH_SESSION_RST); goto done; default: - conn->tmf_state = TMF_INITIAL; + session->tmf_state = TMF_INITIAL; goto unlock; } rc = SUCCESS; - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); iscsi_suspend_tx(conn); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); memset(hdr, 0, sizeof(*hdr)); fail_scsi_tasks(conn, -1, DID_ERROR); - conn->tmf_state = TMF_INITIAL; - spin_unlock_bh(&session->lock); + session->tmf_state = TMF_INITIAL; + spin_unlock_bh(&session->frwd_lock); iscsi_start_tx(conn); goto done; unlock: - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); done: ISCSI_DBG_EH(session, "tgt %s reset result = %s\n", session->targetname, rc == SUCCESS ? "SUCCESS" : "FAILED"); mutex_unlock(&session->eh_mutex); return rc; } -EXPORT_SYMBOL_GPL(iscsi_eh_target_reset); /** * iscsi_eh_recover_target - reset target and possibly the session @@ -2494,7 +2779,7 @@ iscsi_pool_init(struct iscsi_pool *q, int max, void ***items, int item_size) * the array. */ if (items) num_arrays++; - q->pool = kzalloc(num_arrays * max * sizeof(void*), GFP_KERNEL); + q->pool = kvcalloc(num_arrays * max, sizeof(void *), GFP_KERNEL); if (q->pool == NULL) return -ENOMEM; @@ -2528,10 +2813,60 @@ void iscsi_pool_free(struct iscsi_pool *q) for (i = 0; i < q->max; i++) kfree(q->pool[i]); - kfree(q->pool); + kvfree(q->pool); } EXPORT_SYMBOL_GPL(iscsi_pool_free); +int iscsi_host_get_max_scsi_cmds(struct Scsi_Host *shost, + uint16_t requested_cmds_max) +{ + int scsi_cmds, total_cmds = requested_cmds_max; + +check: + if (!total_cmds) + total_cmds = ISCSI_DEF_XMIT_CMDS_MAX; + /* + * The iscsi layer needs some tasks for nop handling and tmfs, + * so the cmds_max must at least be greater than ISCSI_MGMT_CMDS_MAX + * + 1 command for scsi IO. + */ + if (total_cmds < ISCSI_TOTAL_CMDS_MIN) { + printk(KERN_ERR "iscsi: invalid max cmds of %d. Must be a power of two that is at least %d.\n", + total_cmds, ISCSI_TOTAL_CMDS_MIN); + return -EINVAL; + } + + if (total_cmds > ISCSI_TOTAL_CMDS_MAX) { + printk(KERN_INFO "iscsi: invalid max cmds of %d. Must be a power of 2 less than or equal to %d. Using %d.\n", + requested_cmds_max, ISCSI_TOTAL_CMDS_MAX, + ISCSI_TOTAL_CMDS_MAX); + total_cmds = ISCSI_TOTAL_CMDS_MAX; + } + + if (!is_power_of_2(total_cmds)) { + total_cmds = rounddown_pow_of_two(total_cmds); + if (total_cmds < ISCSI_TOTAL_CMDS_MIN) { + printk(KERN_ERR "iscsi: invalid max cmds of %d. Must be a power of 2 greater than %d.\n", requested_cmds_max, ISCSI_TOTAL_CMDS_MIN); + return -EINVAL; + } + + printk(KERN_INFO "iscsi: invalid max cmds %d. Must be a power of 2. Rounding max cmds down to %d.\n", + requested_cmds_max, total_cmds); + } + + scsi_cmds = total_cmds - ISCSI_MGMT_CMDS_MAX; + if (shost->can_queue && scsi_cmds > shost->can_queue) { + total_cmds = shost->can_queue; + + printk(KERN_INFO "iscsi: requested max cmds %u is higher than driver limit. Using driver limit %u\n", + requested_cmds_max, shost->can_queue); + goto check; + } + + return scsi_cmds; +} +EXPORT_SYMBOL_GPL(iscsi_host_get_max_scsi_cmds); + /** * iscsi_host_add - add host to system * @shost: scsi host @@ -2548,8 +2883,6 @@ int iscsi_host_add(struct Scsi_Host *shost, struct device *pdev) if (!shost->cmd_per_lun) shost->cmd_per_lun = ISCSI_DEF_CMD_PER_LUN; - if (!shost->transportt->eh_timed_out) - shost->transportt->eh_timed_out = iscsi_eh_cmd_timed_out; return scsi_add_host(shost, pdev); } EXPORT_SYMBOL_GPL(iscsi_host_add); @@ -2563,7 +2896,7 @@ EXPORT_SYMBOL_GPL(iscsi_host_add); * This should be called by partial offload and software iscsi drivers. * To access the driver specific memory use the iscsi_host_priv() macro. */ -struct Scsi_Host *iscsi_host_alloc(struct scsi_host_template *sht, +struct Scsi_Host *iscsi_host_alloc(const struct scsi_host_template *sht, int dd_data_size, bool xmit_can_sleep) { struct Scsi_Host *shost; @@ -2575,9 +2908,9 @@ struct Scsi_Host *iscsi_host_alloc(struct scsi_host_template *sht, ihost = shost_priv(shost); if (xmit_can_sleep) { - snprintf(ihost->workq_name, sizeof(ihost->workq_name), - "iscsi_q_%d", shost->host_no); - ihost->workq = create_singlethread_workqueue(ihost->workq_name); + ihost->workq = alloc_workqueue("iscsi_q_%d", + WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND, + 1, shost->host_no); if (!ihost->workq) goto free_host; } @@ -2602,11 +2935,12 @@ static void iscsi_notify_host_removed(struct iscsi_cls_session *cls_session) /** * iscsi_host_remove - remove host and sessions * @shost: scsi host + * @is_shutdown: true if called from a driver shutdown callout * * If there are any sessions left, this will initiate the removal and wait * for the completion. */ -void iscsi_host_remove(struct Scsi_Host *shost) +void iscsi_host_remove(struct Scsi_Host *shost, bool is_shutdown) { struct iscsi_host *ihost = shost_priv(shost); unsigned long flags; @@ -2615,15 +2949,17 @@ void iscsi_host_remove(struct Scsi_Host *shost) ihost->state = ISCSI_HOST_REMOVED; spin_unlock_irqrestore(&ihost->lock, flags); - iscsi_host_for_each_session(shost, iscsi_notify_host_removed); + if (!is_shutdown) + iscsi_host_for_each_session(shost, iscsi_notify_host_removed); + else + iscsi_host_for_each_session(shost, iscsi_force_destroy_session); + wait_event_interruptible(ihost->session_removal_wq, ihost->num_sessions == 0); if (signal_pending(current)) flush_signals(current); scsi_remove_host(shost); - if (ihost->workq) - destroy_workqueue(ihost->workq); } EXPORT_SYMBOL_GPL(iscsi_host_remove); @@ -2631,6 +2967,9 @@ void iscsi_host_free(struct Scsi_Host *shost) { struct iscsi_host *ihost = shost_priv(shost); + if (ihost->workq) + destroy_workqueue(ihost->workq); + kfree(ihost->netdev); kfree(ihost->hwaddress); kfree(ihost->initiatorname); @@ -2664,8 +3003,10 @@ static void iscsi_host_dec_session_cnt(struct Scsi_Host *shost) * @iscsit: iscsi transport template * @shost: scsi host * @cmds_max: session can queue + * @dd_size: private driver data size, added to session allocation size * @cmd_task_size: LLD task private data size * @initial_cmdsn: initial CmdSN + * @id: target ID to add to this session * * This can be used by software iscsi_transports that allocate * a session per scsi host. @@ -2682,7 +3023,7 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost, struct iscsi_host *ihost = shost_priv(shost); struct iscsi_session *session; struct iscsi_cls_session *cls_session; - int cmd_i, scsi_cmds, total_cmds = cmds_max; + int cmd_i, scsi_cmds; unsigned long flags; spin_lock_irqsave(&ihost->lock, flags); @@ -2693,37 +3034,9 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost, ihost->num_sessions++; spin_unlock_irqrestore(&ihost->lock, flags); - if (!total_cmds) - total_cmds = ISCSI_DEF_XMIT_CMDS_MAX; - /* - * The iscsi layer needs some tasks for nop handling and tmfs, - * so the cmds_max must at least be greater than ISCSI_MGMT_CMDS_MAX - * + 1 command for scsi IO. - */ - if (total_cmds < ISCSI_TOTAL_CMDS_MIN) { - printk(KERN_ERR "iscsi: invalid can_queue of %d. can_queue " - "must be a power of two that is at least %d.\n", - total_cmds, ISCSI_TOTAL_CMDS_MIN); + scsi_cmds = iscsi_host_get_max_scsi_cmds(shost, cmds_max); + if (scsi_cmds < 0) goto dec_session_count; - } - - if (total_cmds > ISCSI_TOTAL_CMDS_MAX) { - printk(KERN_ERR "iscsi: invalid can_queue of %d. can_queue " - "must be a power of 2 less than or equal to %d.\n", - cmds_max, ISCSI_TOTAL_CMDS_MAX); - total_cmds = ISCSI_TOTAL_CMDS_MAX; - } - - if (!is_power_of_2(total_cmds)) { - printk(KERN_ERR "iscsi: invalid can_queue of %d. can_queue " - "must be a power of 2.\n", total_cmds); - total_cmds = rounddown_pow_of_two(total_cmds); - if (total_cmds < ISCSI_TOTAL_CMDS_MIN) - return NULL; - printk(KERN_INFO "iscsi: Rounding can_queue to %d.\n", - total_cmds); - } - scsi_cmds = total_cmds - ISCSI_MGMT_CMDS_MAX; cls_session = iscsi_alloc_session(shost, iscsit, sizeof(struct iscsi_session) + @@ -2739,15 +3052,21 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost, session->lu_reset_timeout = 15; session->abort_timeout = 10; session->scsi_cmds_max = scsi_cmds; - session->cmds_max = total_cmds; + session->cmds_max = scsi_cmds + ISCSI_MGMT_CMDS_MAX; session->queued_cmdsn = session->cmdsn = initial_cmdsn; session->exp_cmdsn = initial_cmdsn + 1; session->max_cmdsn = initial_cmdsn + 1; session->max_r2t = 1; session->tt = iscsit; session->dd_data = cls_session->dd_data + sizeof(*session); + + session->tmf_state = TMF_INITIAL; + timer_setup(&session->tmf_timer, iscsi_tmf_timedout, 0); mutex_init(&session->eh_mutex); - spin_lock_init(&session->lock); + init_waitqueue_head(&session->ehwait); + + spin_lock_init(&session->frwd_lock); + spin_lock_init(&session->back_lock); /* initialize SCSI PDU commands pool */ if (iscsi_pool_init(&session->cmdpool, session->cmds_max, @@ -2786,21 +3105,34 @@ dec_session_count: } EXPORT_SYMBOL_GPL(iscsi_session_setup); +/* + * issi_session_remove - Remove session from iSCSI class. + */ +void iscsi_session_remove(struct iscsi_cls_session *cls_session) +{ + struct iscsi_session *session = cls_session->dd_data; + struct Scsi_Host *shost = session->host; + + iscsi_remove_session(cls_session); + /* + * host removal only has to wait for its children to be removed from + * sysfs, and iscsi_tcp needs to do iscsi_host_remove before freeing + * the session, so drop the session count here. + */ + iscsi_host_dec_session_cnt(shost); +} +EXPORT_SYMBOL_GPL(iscsi_session_remove); + /** - * iscsi_session_teardown - destroy session, host, and cls_session + * iscsi_session_free - Free iscsi session and it's resources * @cls_session: iscsi session - * - * The driver must have called iscsi_remove_session before - * calling this. */ -void iscsi_session_teardown(struct iscsi_cls_session *cls_session) +void iscsi_session_free(struct iscsi_cls_session *cls_session) { struct iscsi_session *session = cls_session->dd_data; struct module *owner = cls_session->transport->owner; - struct Scsi_Host *shost = session->host; iscsi_pool_free(&session->cmdpool); - kfree(session->password); kfree(session->password_in); kfree(session->username); @@ -2812,11 +3144,23 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) kfree(session->boot_nic); kfree(session->boot_target); kfree(session->ifacename); + kfree(session->portal_type); + kfree(session->discovery_parent_type); - iscsi_destroy_session(cls_session); - iscsi_host_dec_session_cnt(shost); + iscsi_free_session(cls_session); module_put(owner); } +EXPORT_SYMBOL_GPL(iscsi_session_free); + +/** + * iscsi_session_teardown - destroy session and cls_session + * @cls_session: iscsi session + */ +void iscsi_session_teardown(struct iscsi_cls_session *cls_session) +{ + iscsi_session_remove(cls_session); + iscsi_session_free(cls_session); +} EXPORT_SYMBOL_GPL(iscsi_session_teardown); /** @@ -2833,25 +3177,23 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, struct iscsi_conn *conn; struct iscsi_cls_conn *cls_conn; char *data; + int err; - cls_conn = iscsi_create_conn(cls_session, sizeof(*conn) + dd_size, + cls_conn = iscsi_alloc_conn(cls_session, sizeof(*conn) + dd_size, conn_idx); if (!cls_conn) return NULL; conn = cls_conn->dd_data; - memset(conn, 0, sizeof(*conn) + dd_size); - conn->dd_data = cls_conn->dd_data + sizeof(*conn); + if (dd_size) + conn->dd_data = cls_conn->dd_data + sizeof(*conn); conn->session = session; conn->cls_conn = cls_conn; conn->c_stage = ISCSI_CONN_INITIAL_STAGE; conn->id = conn_idx; conn->exp_statsn = 0; - conn->tmf_state = TMF_INITIAL; - init_timer(&conn->transport_timer); - conn->transport_timer.data = (unsigned long)conn; - conn->transport_timer.function = iscsi_check_transport_timeouts; + timer_setup(&conn->transport_timer, iscsi_check_transport_timeouts, 0); INIT_LIST_HEAD(&conn->mgmtqueue); INIT_LIST_HEAD(&conn->cmdqueue); @@ -2859,14 +3201,14 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, INIT_WORK(&conn->xmitwork, iscsi_xmitworker); /* allocate login_task used for the login/text sequences */ - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); if (!kfifo_out(&session->cmdpool.queue, (void*)&conn->login_task, sizeof(void*))) { - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); goto login_task_alloc_fail; } - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); data = (char *) __get_free_pages(GFP_KERNEL, get_order(ISCSI_DEF_MAX_RECV_SEG_LEN)); @@ -2874,23 +3216,28 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, goto login_task_data_alloc_fail; conn->login_task->data = conn->data = data; - init_timer(&conn->tmf_timer); - init_waitqueue_head(&conn->ehwait); + err = iscsi_add_conn(cls_conn); + if (err) + goto login_task_add_dev_fail; return cls_conn; +login_task_add_dev_fail: + free_pages((unsigned long) conn->data, + get_order(ISCSI_DEF_MAX_RECV_SEG_LEN)); + login_task_data_alloc_fail: kfifo_in(&session->cmdpool.queue, (void*)&conn->login_task, sizeof(void*)); login_task_alloc_fail: - iscsi_destroy_conn(cls_conn); + iscsi_put_conn(cls_conn); return NULL; } EXPORT_SYMBOL_GPL(iscsi_conn_setup); /** * iscsi_conn_teardown - teardown iscsi connection - * cls_conn: iscsi class connection + * @cls_conn: iscsi class connection * * TODO: we may need to make this into a two step process * like scsi-mls remove + put host @@ -2899,57 +3246,42 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn) { struct iscsi_conn *conn = cls_conn->dd_data; struct iscsi_session *session = conn->session; - unsigned long flags; - del_timer_sync(&conn->transport_timer); + iscsi_remove_conn(cls_conn); + + timer_delete_sync(&conn->transport_timer); - spin_lock_bh(&session->lock); + mutex_lock(&session->eh_mutex); + spin_lock_bh(&session->frwd_lock); conn->c_stage = ISCSI_CONN_CLEANUP_WAIT; if (session->leadconn == conn) { /* * leading connection? then give up on recovery. */ session->state = ISCSI_STATE_TERMINATE; - wake_up(&conn->ehwait); - } - spin_unlock_bh(&session->lock); - - /* - * Block until all in-progress commands for this connection - * time out or fail. - */ - for (;;) { - spin_lock_irqsave(session->host->host_lock, flags); - if (!session->host->host_busy) { /* OK for ERL == 0 */ - spin_unlock_irqrestore(session->host->host_lock, flags); - break; - } - spin_unlock_irqrestore(session->host->host_lock, flags); - msleep_interruptible(500); - iscsi_conn_printk(KERN_INFO, conn, "iscsi conn_destroy(): " - "host_busy %d host_failed %d\n", - session->host->host_busy, - session->host->host_failed); - /* - * force eh_abort() to unblock - */ - wake_up(&conn->ehwait); + wake_up(&session->ehwait); } + spin_unlock_bh(&session->frwd_lock); /* flush queued up work because we free the connection below */ iscsi_suspend_tx(conn); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); free_pages((unsigned long) conn->data, get_order(ISCSI_DEF_MAX_RECV_SEG_LEN)); kfree(conn->persistent_address); + kfree(conn->local_ipaddr); + /* regular RX path uses back_lock */ + spin_lock_bh(&session->back_lock); kfifo_in(&session->cmdpool.queue, (void*)&conn->login_task, sizeof(void*)); + spin_unlock_bh(&session->back_lock); if (session->leadconn == conn) session->leadconn = NULL; - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); + mutex_unlock(&session->eh_mutex); - iscsi_destroy_conn(cls_conn); + iscsi_put_conn(cls_conn); } EXPORT_SYMBOL_GPL(iscsi_conn_teardown); @@ -2984,7 +3316,7 @@ int iscsi_conn_start(struct iscsi_cls_conn *cls_conn) conn->ping_timeout = 5; } - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); conn->c_stage = ISCSI_CONN_STARTED; session->state = ISCSI_STATE_LOGGED_IN; session->queued_cmdsn = session->cmdsn; @@ -3002,7 +3334,7 @@ int iscsi_conn_start(struct iscsi_cls_conn *cls_conn) * commands after successful recovery */ conn->stop_stage = 0; - conn->tmf_state = TMF_INITIAL; + session->tmf_state = TMF_INITIAL; session->age++; if (session->age == 16) session->age = 0; @@ -3013,10 +3345,10 @@ int iscsi_conn_start(struct iscsi_cls_conn *cls_conn) default: break; } - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); iscsi_unblock_session(session->cls_session); - wake_up(&conn->ehwait); + wake_up(&session->ehwait); return 0; } EXPORT_SYMBOL_GPL(iscsi_conn_start); @@ -3038,23 +3370,31 @@ fail_mgmt_tasks(struct iscsi_session *session, struct iscsi_conn *conn) ISCSI_DBG_SESSION(conn->session, "failing mgmt itt 0x%x state %d\n", task->itt, task->state); + + spin_lock_bh(&session->back_lock); + if (cleanup_queued_task(task)) { + spin_unlock_bh(&session->back_lock); + continue; + } + state = ISCSI_TASK_ABRT_SESS_RECOV; if (task->state == ISCSI_TASK_PENDING) state = ISCSI_TASK_COMPLETED; iscsi_complete_task(task, state); - + spin_unlock_bh(&session->back_lock); } } -static void iscsi_start_session_recovery(struct iscsi_session *session, - struct iscsi_conn *conn, int flag) +void iscsi_conn_stop(struct iscsi_cls_conn *cls_conn, int flag) { + struct iscsi_conn *conn = cls_conn->dd_data; + struct iscsi_session *session = conn->session; int old_stop_stage; mutex_lock(&session->eh_mutex); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); if (conn->stop_stage == STOP_CONN_TERM) { - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); mutex_unlock(&session->eh_mutex); return; } @@ -3071,14 +3411,14 @@ static void iscsi_start_session_recovery(struct iscsi_session *session, old_stop_stage = conn->stop_stage; conn->stop_stage = flag; - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); - del_timer_sync(&conn->transport_timer); + timer_delete_sync(&conn->transport_timer); iscsi_suspend_tx(conn); - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); conn->c_stage = ISCSI_CONN_STOPPED; - spin_unlock_bh(&session->lock); + spin_unlock_bh(&session->frwd_lock); /* * for connection level recovery we should not calculate @@ -3099,29 +3439,13 @@ static void iscsi_start_session_recovery(struct iscsi_session *session, /* * flush queues. */ - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); fail_scsi_tasks(conn, -1, DID_TRANSPORT_DISRUPTED); fail_mgmt_tasks(session, conn); - memset(&conn->tmhdr, 0, sizeof(conn->tmhdr)); - spin_unlock_bh(&session->lock); + memset(&session->tmhdr, 0, sizeof(session->tmhdr)); + spin_unlock_bh(&session->frwd_lock); mutex_unlock(&session->eh_mutex); } - -void iscsi_conn_stop(struct iscsi_cls_conn *cls_conn, int flag) -{ - struct iscsi_conn *conn = cls_conn->dd_data; - struct iscsi_session *session = conn->session; - - switch (flag) { - case STOP_CONN_RECOVER: - case STOP_CONN_TERM: - iscsi_start_session_recovery(session, conn, flag); - break; - default: - iscsi_conn_printk(KERN_ERR, conn, - "invalid stop flag %d\n", flag); - } -} EXPORT_SYMBOL_GPL(iscsi_conn_stop); int iscsi_conn_bind(struct iscsi_cls_session *cls_session, @@ -3130,16 +3454,25 @@ int iscsi_conn_bind(struct iscsi_cls_session *cls_session, struct iscsi_session *session = cls_session->dd_data; struct iscsi_conn *conn = cls_conn->dd_data; - spin_lock_bh(&session->lock); + spin_lock_bh(&session->frwd_lock); if (is_leading) session->leadconn = conn; - spin_unlock_bh(&session->lock); + set_bit(ISCSI_CONN_FLAG_BOUND, &conn->flags); + spin_unlock_bh(&session->frwd_lock); + + /* + * The target could have reduced it's window size between logins, so + * we have to reset max/exp cmdsn so we can see the new values. + */ + spin_lock_bh(&session->back_lock); + session->max_cmdsn = session->exp_cmdsn = session->cmdsn + 1; + spin_unlock_bh(&session->back_lock); /* * Unblock xmitworker(), Login Phase will pass through. */ - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); - clear_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_RX, &conn->flags); + clear_bit(ISCSI_CONN_FLAG_SUSPEND_TX, &conn->flags); return 0; } EXPORT_SYMBOL_GPL(iscsi_conn_bind); @@ -3168,6 +3501,7 @@ int iscsi_set_param(struct iscsi_cls_conn *cls_conn, { struct iscsi_conn *conn = cls_conn->dd_data; struct iscsi_session *session = conn->session; + int val; switch(param) { case ISCSI_PARAM_FAST_ABORT: @@ -3257,6 +3591,17 @@ int iscsi_set_param(struct iscsi_cls_conn *cls_conn, return iscsi_switch_str_param(&session->boot_nic, buf); case ISCSI_PARAM_BOOT_TARGET: return iscsi_switch_str_param(&session->boot_target, buf); + case ISCSI_PARAM_PORTAL_TYPE: + return iscsi_switch_str_param(&session->portal_type, buf); + case ISCSI_PARAM_DISCOVERY_PARENT_TYPE: + return iscsi_switch_str_param(&session->discovery_parent_type, + buf); + case ISCSI_PARAM_DISCOVERY_SESS: + sscanf(buf, "%d", &val); + session->discovery_sess = !!val; + break; + case ISCSI_PARAM_LOCAL_IPADDR: + return iscsi_switch_str_param(&conn->local_ipaddr, buf); default: return -ENOSYS; } @@ -3273,76 +3618,125 @@ int iscsi_session_get_param(struct iscsi_cls_session *cls_session, switch(param) { case ISCSI_PARAM_FAST_ABORT: - len = sprintf(buf, "%d\n", session->fast_abort); + len = sysfs_emit(buf, "%d\n", session->fast_abort); break; case ISCSI_PARAM_ABORT_TMO: - len = sprintf(buf, "%d\n", session->abort_timeout); + len = sysfs_emit(buf, "%d\n", session->abort_timeout); break; case ISCSI_PARAM_LU_RESET_TMO: - len = sprintf(buf, "%d\n", session->lu_reset_timeout); + len = sysfs_emit(buf, "%d\n", session->lu_reset_timeout); break; case ISCSI_PARAM_TGT_RESET_TMO: - len = sprintf(buf, "%d\n", session->tgt_reset_timeout); + len = sysfs_emit(buf, "%d\n", session->tgt_reset_timeout); break; case ISCSI_PARAM_INITIAL_R2T_EN: - len = sprintf(buf, "%d\n", session->initial_r2t_en); + len = sysfs_emit(buf, "%d\n", session->initial_r2t_en); break; case ISCSI_PARAM_MAX_R2T: - len = sprintf(buf, "%hu\n", session->max_r2t); + len = sysfs_emit(buf, "%hu\n", session->max_r2t); break; case ISCSI_PARAM_IMM_DATA_EN: - len = sprintf(buf, "%d\n", session->imm_data_en); + len = sysfs_emit(buf, "%d\n", session->imm_data_en); break; case ISCSI_PARAM_FIRST_BURST: - len = sprintf(buf, "%u\n", session->first_burst); + len = sysfs_emit(buf, "%u\n", session->first_burst); break; case ISCSI_PARAM_MAX_BURST: - len = sprintf(buf, "%u\n", session->max_burst); + len = sysfs_emit(buf, "%u\n", session->max_burst); break; case ISCSI_PARAM_PDU_INORDER_EN: - len = sprintf(buf, "%d\n", session->pdu_inorder_en); + len = sysfs_emit(buf, "%d\n", session->pdu_inorder_en); break; case ISCSI_PARAM_DATASEQ_INORDER_EN: - len = sprintf(buf, "%d\n", session->dataseq_inorder_en); + len = sysfs_emit(buf, "%d\n", session->dataseq_inorder_en); + break; + case ISCSI_PARAM_DEF_TASKMGMT_TMO: + len = sysfs_emit(buf, "%d\n", session->def_taskmgmt_tmo); break; case ISCSI_PARAM_ERL: - len = sprintf(buf, "%d\n", session->erl); + len = sysfs_emit(buf, "%d\n", session->erl); break; case ISCSI_PARAM_TARGET_NAME: - len = sprintf(buf, "%s\n", session->targetname); + len = sysfs_emit(buf, "%s\n", session->targetname); break; case ISCSI_PARAM_TARGET_ALIAS: - len = sprintf(buf, "%s\n", session->targetalias); + len = sysfs_emit(buf, "%s\n", session->targetalias); break; case ISCSI_PARAM_TPGT: - len = sprintf(buf, "%d\n", session->tpgt); + len = sysfs_emit(buf, "%d\n", session->tpgt); break; case ISCSI_PARAM_USERNAME: - len = sprintf(buf, "%s\n", session->username); + len = sysfs_emit(buf, "%s\n", session->username); break; case ISCSI_PARAM_USERNAME_IN: - len = sprintf(buf, "%s\n", session->username_in); + len = sysfs_emit(buf, "%s\n", session->username_in); break; case ISCSI_PARAM_PASSWORD: - len = sprintf(buf, "%s\n", session->password); + len = sysfs_emit(buf, "%s\n", session->password); break; case ISCSI_PARAM_PASSWORD_IN: - len = sprintf(buf, "%s\n", session->password_in); + len = sysfs_emit(buf, "%s\n", session->password_in); break; case ISCSI_PARAM_IFACE_NAME: - len = sprintf(buf, "%s\n", session->ifacename); + len = sysfs_emit(buf, "%s\n", session->ifacename); break; case ISCSI_PARAM_INITIATOR_NAME: - len = sprintf(buf, "%s\n", session->initiatorname); + len = sysfs_emit(buf, "%s\n", session->initiatorname); break; case ISCSI_PARAM_BOOT_ROOT: - len = sprintf(buf, "%s\n", session->boot_root); + len = sysfs_emit(buf, "%s\n", session->boot_root); break; case ISCSI_PARAM_BOOT_NIC: - len = sprintf(buf, "%s\n", session->boot_nic); + len = sysfs_emit(buf, "%s\n", session->boot_nic); break; case ISCSI_PARAM_BOOT_TARGET: - len = sprintf(buf, "%s\n", session->boot_target); + len = sysfs_emit(buf, "%s\n", session->boot_target); + break; + case ISCSI_PARAM_AUTO_SND_TGT_DISABLE: + len = sysfs_emit(buf, "%u\n", session->auto_snd_tgt_disable); + break; + case ISCSI_PARAM_DISCOVERY_SESS: + len = sysfs_emit(buf, "%u\n", session->discovery_sess); + break; + case ISCSI_PARAM_PORTAL_TYPE: + len = sysfs_emit(buf, "%s\n", session->portal_type); + break; + case ISCSI_PARAM_CHAP_AUTH_EN: + len = sysfs_emit(buf, "%u\n", session->chap_auth_en); + break; + case ISCSI_PARAM_DISCOVERY_LOGOUT_EN: + len = sysfs_emit(buf, "%u\n", session->discovery_logout_en); + break; + case ISCSI_PARAM_BIDI_CHAP_EN: + len = sysfs_emit(buf, "%u\n", session->bidi_chap_en); + break; + case ISCSI_PARAM_DISCOVERY_AUTH_OPTIONAL: + len = sysfs_emit(buf, "%u\n", session->discovery_auth_optional); + break; + case ISCSI_PARAM_DEF_TIME2WAIT: + len = sysfs_emit(buf, "%d\n", session->time2wait); + break; + case ISCSI_PARAM_DEF_TIME2RETAIN: + len = sysfs_emit(buf, "%d\n", session->time2retain); + break; + case ISCSI_PARAM_TSID: + len = sysfs_emit(buf, "%u\n", session->tsid); + break; + case ISCSI_PARAM_ISID: + len = sysfs_emit(buf, "%02x%02x%02x%02x%02x%02x\n", + session->isid[0], session->isid[1], + session->isid[2], session->isid[3], + session->isid[4], session->isid[5]); + break; + case ISCSI_PARAM_DISCOVERY_PARENT_IDX: + len = sysfs_emit(buf, "%u\n", session->discovery_parent_idx); + break; + case ISCSI_PARAM_DISCOVERY_PARENT_TYPE: + if (session->discovery_parent_type) + len = sysfs_emit(buf, "%s\n", + session->discovery_parent_type); + else + len = sysfs_emit(buf, "\n"); break; default: return -ENOSYS; @@ -3374,15 +3768,16 @@ int iscsi_conn_get_addr_param(struct sockaddr_storage *addr, case ISCSI_PARAM_CONN_ADDRESS: case ISCSI_HOST_PARAM_IPADDRESS: if (sin) - len = sprintf(buf, "%pI4\n", &sin->sin_addr.s_addr); + len = sysfs_emit(buf, "%pI4\n", &sin->sin_addr.s_addr); else - len = sprintf(buf, "%pI6\n", &sin6->sin6_addr); + len = sysfs_emit(buf, "%pI6\n", &sin6->sin6_addr); break; case ISCSI_PARAM_CONN_PORT: + case ISCSI_PARAM_LOCAL_PORT: if (sin) - len = sprintf(buf, "%hu\n", be16_to_cpu(sin->sin_port)); + len = sysfs_emit(buf, "%hu\n", be16_to_cpu(sin->sin_port)); else - len = sprintf(buf, "%hu\n", + len = sysfs_emit(buf, "%hu\n", be16_to_cpu(sin6->sin6_port)); break; default: @@ -3401,37 +3796,88 @@ int iscsi_conn_get_param(struct iscsi_cls_conn *cls_conn, switch(param) { case ISCSI_PARAM_PING_TMO: - len = sprintf(buf, "%u\n", conn->ping_timeout); + len = sysfs_emit(buf, "%u\n", conn->ping_timeout); break; case ISCSI_PARAM_RECV_TMO: - len = sprintf(buf, "%u\n", conn->recv_timeout); + len = sysfs_emit(buf, "%u\n", conn->recv_timeout); break; case ISCSI_PARAM_MAX_RECV_DLENGTH: - len = sprintf(buf, "%u\n", conn->max_recv_dlength); + len = sysfs_emit(buf, "%u\n", conn->max_recv_dlength); break; case ISCSI_PARAM_MAX_XMIT_DLENGTH: - len = sprintf(buf, "%u\n", conn->max_xmit_dlength); + len = sysfs_emit(buf, "%u\n", conn->max_xmit_dlength); break; case ISCSI_PARAM_HDRDGST_EN: - len = sprintf(buf, "%d\n", conn->hdrdgst_en); + len = sysfs_emit(buf, "%d\n", conn->hdrdgst_en); break; case ISCSI_PARAM_DATADGST_EN: - len = sprintf(buf, "%d\n", conn->datadgst_en); + len = sysfs_emit(buf, "%d\n", conn->datadgst_en); break; case ISCSI_PARAM_IFMARKER_EN: - len = sprintf(buf, "%d\n", conn->ifmarker_en); + len = sysfs_emit(buf, "%d\n", conn->ifmarker_en); break; case ISCSI_PARAM_OFMARKER_EN: - len = sprintf(buf, "%d\n", conn->ofmarker_en); + len = sysfs_emit(buf, "%d\n", conn->ofmarker_en); break; case ISCSI_PARAM_EXP_STATSN: - len = sprintf(buf, "%u\n", conn->exp_statsn); + len = sysfs_emit(buf, "%u\n", conn->exp_statsn); break; case ISCSI_PARAM_PERSISTENT_PORT: - len = sprintf(buf, "%d\n", conn->persistent_port); + len = sysfs_emit(buf, "%d\n", conn->persistent_port); break; case ISCSI_PARAM_PERSISTENT_ADDRESS: - len = sprintf(buf, "%s\n", conn->persistent_address); + len = sysfs_emit(buf, "%s\n", conn->persistent_address); + break; + case ISCSI_PARAM_STATSN: + len = sysfs_emit(buf, "%u\n", conn->statsn); + break; + case ISCSI_PARAM_MAX_SEGMENT_SIZE: + len = sysfs_emit(buf, "%u\n", conn->max_segment_size); + break; + case ISCSI_PARAM_KEEPALIVE_TMO: + len = sysfs_emit(buf, "%u\n", conn->keepalive_tmo); + break; + case ISCSI_PARAM_LOCAL_PORT: + len = sysfs_emit(buf, "%u\n", conn->local_port); + break; + case ISCSI_PARAM_TCP_TIMESTAMP_STAT: + len = sysfs_emit(buf, "%u\n", conn->tcp_timestamp_stat); + break; + case ISCSI_PARAM_TCP_NAGLE_DISABLE: + len = sysfs_emit(buf, "%u\n", conn->tcp_nagle_disable); + break; + case ISCSI_PARAM_TCP_WSF_DISABLE: + len = sysfs_emit(buf, "%u\n", conn->tcp_wsf_disable); + break; + case ISCSI_PARAM_TCP_TIMER_SCALE: + len = sysfs_emit(buf, "%u\n", conn->tcp_timer_scale); + break; + case ISCSI_PARAM_TCP_TIMESTAMP_EN: + len = sysfs_emit(buf, "%u\n", conn->tcp_timestamp_en); + break; + case ISCSI_PARAM_IP_FRAGMENT_DISABLE: + len = sysfs_emit(buf, "%u\n", conn->fragment_disable); + break; + case ISCSI_PARAM_IPV4_TOS: + len = sysfs_emit(buf, "%u\n", conn->ipv4_tos); + break; + case ISCSI_PARAM_IPV6_TC: + len = sysfs_emit(buf, "%u\n", conn->ipv6_traffic_class); + break; + case ISCSI_PARAM_IPV6_FLOW_LABEL: + len = sysfs_emit(buf, "%u\n", conn->ipv6_flow_label); + break; + case ISCSI_PARAM_IS_FW_ASSIGNED_IPV6: + len = sysfs_emit(buf, "%u\n", conn->is_fw_assigned_ipv6); + break; + case ISCSI_PARAM_TCP_XMIT_WSF: + len = sysfs_emit(buf, "%u\n", conn->tcp_xmit_wsf); + break; + case ISCSI_PARAM_TCP_RECV_WSF: + len = sysfs_emit(buf, "%u\n", conn->tcp_recv_wsf); + break; + case ISCSI_PARAM_LOCAL_IPADDR: + len = sysfs_emit(buf, "%s\n", conn->local_ipaddr); break; default: return -ENOSYS; @@ -3449,13 +3895,13 @@ int iscsi_host_get_param(struct Scsi_Host *shost, enum iscsi_host_param param, switch (param) { case ISCSI_HOST_PARAM_NETDEV_NAME: - len = sprintf(buf, "%s\n", ihost->netdev); + len = sysfs_emit(buf, "%s\n", ihost->netdev); break; case ISCSI_HOST_PARAM_HWADDRESS: - len = sprintf(buf, "%s\n", ihost->hwaddress); + len = sysfs_emit(buf, "%s\n", ihost->hwaddress); break; case ISCSI_HOST_PARAM_INITIATOR_NAME: - len = sprintf(buf, "%s\n", ihost->initiatorname); + len = sysfs_emit(buf, "%s\n", ihost->initiatorname); break; default: return -ENOSYS; |