From 1526d9f10c6184031e42afad0adbdde1213e8ad1 Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Sun, 1 Nov 2020 12:59:33 -0600 Subject: [PATCH] scsi: target: Make state_list per CPU Do a state_list/execute_task_lock per CPU, so we can do submissions from different CPUs without contention with each other. Note: tcm_fc was passing TARGET_SCF_USE_CPUID, but never set cpuid. The assumption is that it wanted to set the cpuid to the CPU it was submitting from so it will get this behavior with this patch. [mkp: s/printk/pr_err/ + resolve COMPARE AND WRITE patch conflict] Link: https://lore.kernel.org/r/1604257174-4524-8-git-send-email-michael.christie@oracle.com Reviewed-by: Himanshu Madhani Signed-off-by: Mike Christie Signed-off-by: Martin K. Petersen --- drivers/target/target_core_device.c | 16 +++- drivers/target/target_core_tmr.c | 166 +++++++++++++++++---------------- drivers/target/target_core_transport.c | 27 +++--- drivers/target/tcm_fc/tfc_cmd.c | 2 +- include/target/target_core_base.h | 13 ++- 5 files changed, 126 insertions(+), 98 deletions(-) diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 1f673fb..7787c52 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -721,11 +721,24 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) { struct se_device *dev; struct se_lun *xcopy_lun; + int i; dev = hba->backend->ops->alloc_device(hba, name); if (!dev) return NULL; + dev->queues = kcalloc(nr_cpu_ids, sizeof(*dev->queues), GFP_KERNEL); + if (!dev->queues) { + dev->transport->free_device(dev); + return NULL; + } + + dev->queue_cnt = nr_cpu_ids; + for (i = 0; i < dev->queue_cnt; i++) { + INIT_LIST_HEAD(&dev->queues[i].state_list); + spin_lock_init(&dev->queues[i].lock); + } + dev->se_hba = hba; dev->transport = hba->backend->ops; dev->transport_flags = dev->transport->transport_flags_default; @@ -735,9 +748,7 @@ struct se_device *target_alloc_device(struct se_hba *hba, const char *name) INIT_LIST_HEAD(&dev->dev_sep_list); INIT_LIST_HEAD(&dev->dev_tmr_list); INIT_LIST_HEAD(&dev->delayed_cmd_list); - INIT_LIST_HEAD(&dev->state_list); INIT_LIST_HEAD(&dev->qf_cmd_list); - spin_lock_init(&dev->execute_task_lock); spin_lock_init(&dev->delayed_cmd_lock); spin_lock_init(&dev->dev_reservation_lock); spin_lock_init(&dev->se_port_lock); @@ -1010,6 +1021,7 @@ void target_free_device(struct se_device *dev) if (dev->transport->free_prot) dev->transport->free_prot(dev); + kfree(dev->queues); dev->transport->free_device(dev); } diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index e4513ef..7347285 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -121,57 +121,61 @@ void core_tmr_abort_task( unsigned long flags; bool rc; u64 ref_tag; - - spin_lock_irqsave(&dev->execute_task_lock, flags); - list_for_each_entry_safe(se_cmd, next, &dev->state_list, state_list) { - - if (se_sess != se_cmd->se_sess) - continue; - - /* skip task management functions, including tmr->task_cmd */ - if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) - continue; - - ref_tag = se_cmd->tag; - if (tmr->ref_task_tag != ref_tag) - continue; - - printk("ABORT_TASK: Found referenced %s task_tag: %llu\n", - se_cmd->se_tfo->fabric_name, ref_tag); - - spin_lock(&se_sess->sess_cmd_lock); - rc = __target_check_io_state(se_cmd, se_sess, 0); - spin_unlock(&se_sess->sess_cmd_lock); - if (!rc) - continue; - - list_move_tail(&se_cmd->state_list, &aborted_list); - se_cmd->state_active = false; - - spin_unlock_irqrestore(&dev->execute_task_lock, flags); - - /* - * Ensure that this ABORT request is visible to the LU RESET - * code. - */ - if (!tmr->tmr_dev) - WARN_ON_ONCE(transport_lookup_tmr_lun(tmr->task_cmd) < - 0); - - if (dev->transport->tmr_notify) - dev->transport->tmr_notify(dev, TMR_ABORT_TASK, - &aborted_list); - - list_del_init(&se_cmd->state_list); - target_put_cmd_and_wait(se_cmd); - - printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for" - " ref_tag: %llu\n", ref_tag); - tmr->response = TMR_FUNCTION_COMPLETE; - atomic_long_inc(&dev->aborts_complete); - return; + int i; + + for (i = 0; i < dev->queue_cnt; i++) { + spin_lock_irqsave(&dev->queues[i].lock, flags); + list_for_each_entry_safe(se_cmd, next, &dev->queues[i].state_list, + state_list) { + if (se_sess != se_cmd->se_sess) + continue; + + /* + * skip task management functions, including + * tmr->task_cmd + */ + if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) + continue; + + ref_tag = se_cmd->tag; + if (tmr->ref_task_tag != ref_tag) + continue; + + pr_err("ABORT_TASK: Found referenced %s task_tag: %llu\n", + se_cmd->se_tfo->fabric_name, ref_tag); + + spin_lock(&se_sess->sess_cmd_lock); + rc = __target_check_io_state(se_cmd, se_sess, 0); + spin_unlock(&se_sess->sess_cmd_lock); + if (!rc) + continue; + + list_move_tail(&se_cmd->state_list, &aborted_list); + se_cmd->state_active = false; + spin_unlock_irqrestore(&dev->queues[i].lock, flags); + + /* + * Ensure that this ABORT request is visible to the LU + * RESET code. + */ + if (!tmr->tmr_dev) + WARN_ON_ONCE(transport_lookup_tmr_lun(tmr->task_cmd) < 0); + + if (dev->transport->tmr_notify) + dev->transport->tmr_notify(dev, TMR_ABORT_TASK, + &aborted_list); + + list_del_init(&se_cmd->state_list); + target_put_cmd_and_wait(se_cmd); + + pr_err("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for ref_tag: %llu\n", + ref_tag); + tmr->response = TMR_FUNCTION_COMPLETE; + atomic_long_inc(&dev->aborts_complete); + return; + } + spin_unlock_irqrestore(&dev->queues[i].lock, flags); } - spin_unlock_irqrestore(&dev->execute_task_lock, flags); if (dev->transport->tmr_notify) dev->transport->tmr_notify(dev, TMR_ABORT_TASK, &aborted_list); @@ -273,7 +277,7 @@ static void core_tmr_drain_state_list( struct se_session *sess; struct se_cmd *cmd, *next; unsigned long flags; - int rc; + int rc, i; /* * Complete outstanding commands with TASK_ABORTED SAM status. @@ -297,35 +301,39 @@ static void core_tmr_drain_state_list( * Note that this seems to be independent of TAS (Task Aborted Status) * in the Control Mode Page. */ - spin_lock_irqsave(&dev->execute_task_lock, flags); - list_for_each_entry_safe(cmd, next, &dev->state_list, state_list) { - /* - * For PREEMPT_AND_ABORT usage, only process commands - * with a matching reservation key. - */ - if (target_check_cdb_and_preempt(preempt_and_abort_list, cmd)) - continue; - - /* - * Not aborting PROUT PREEMPT_AND_ABORT CDB.. - */ - if (prout_cmd == cmd) - continue; - - sess = cmd->se_sess; - if (WARN_ON_ONCE(!sess)) - continue; - - spin_lock(&sess->sess_cmd_lock); - rc = __target_check_io_state(cmd, tmr_sess, tas); - spin_unlock(&sess->sess_cmd_lock); - if (!rc) - continue; - - list_move_tail(&cmd->state_list, &drain_task_list); - cmd->state_active = false; + for (i = 0; i < dev->queue_cnt; i++) { + spin_lock_irqsave(&dev->queues[i].lock, flags); + list_for_each_entry_safe(cmd, next, &dev->queues[i].state_list, + state_list) { + /* + * For PREEMPT_AND_ABORT usage, only process commands + * with a matching reservation key. + */ + if (target_check_cdb_and_preempt(preempt_and_abort_list, + cmd)) + continue; + + /* + * Not aborting PROUT PREEMPT_AND_ABORT CDB.. + */ + if (prout_cmd == cmd) + continue; + + sess = cmd->se_sess; + if (WARN_ON_ONCE(!sess)) + continue; + + spin_lock(&sess->sess_cmd_lock); + rc = __target_check_io_state(cmd, tmr_sess, tas); + spin_unlock(&sess->sess_cmd_lock); + if (!rc) + continue; + + list_move_tail(&cmd->state_list, &drain_task_list); + cmd->state_active = false; + } + spin_unlock_irqrestore(&dev->queues[i].lock, flags); } - spin_unlock_irqrestore(&dev->execute_task_lock, flags); if (dev->transport->tmr_notify) dev->transport->tmr_notify(dev, preempt_and_abort_list ? diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 485317c..fca4bd0 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -659,12 +659,12 @@ static void target_remove_from_state_list(struct se_cmd *cmd) if (!dev) return; - spin_lock_irqsave(&dev->execute_task_lock, flags); + spin_lock_irqsave(&dev->queues[cmd->cpuid].lock, flags); if (cmd->state_active) { list_del(&cmd->state_list); cmd->state_active = false; } - spin_unlock_irqrestore(&dev->execute_task_lock, flags); + spin_unlock_irqrestore(&dev->queues[cmd->cpuid].lock, flags); } /* @@ -875,10 +875,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) INIT_WORK(&cmd->work, success ? target_complete_ok_work : target_complete_failure_work); - if (cmd->se_cmd_flags & SCF_USE_CPUID) - queue_work_on(cmd->cpuid, target_completion_wq, &cmd->work); - else - queue_work(target_completion_wq, &cmd->work); + queue_work_on(cmd->cpuid, target_completion_wq, &cmd->work); } EXPORT_SYMBOL(target_complete_cmd); @@ -906,12 +903,13 @@ static void target_add_to_state_list(struct se_cmd *cmd) struct se_device *dev = cmd->se_dev; unsigned long flags; - spin_lock_irqsave(&dev->execute_task_lock, flags); + spin_lock_irqsave(&dev->queues[cmd->cpuid].lock, flags); if (!cmd->state_active) { - list_add_tail(&cmd->state_list, &dev->state_list); + list_add_tail(&cmd->state_list, + &dev->queues[cmd->cpuid].state_list); cmd->state_active = true; } - spin_unlock_irqrestore(&dev->execute_task_lock, flags); + spin_unlock_irqrestore(&dev->queues[cmd->cpuid].lock, flags); } /* @@ -1399,6 +1397,9 @@ void transport_init_se_cmd( cmd->sense_buffer = sense_buffer; cmd->orig_fe_lun = unpacked_lun; + if (!(cmd->se_cmd_flags & SCF_USE_CPUID)) + cmd->cpuid = smp_processor_id(); + cmd->state_active = false; } EXPORT_SYMBOL(transport_init_se_cmd); @@ -1616,6 +1617,9 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess BUG_ON(!se_tpg); BUG_ON(se_cmd->se_tfo || se_cmd->se_sess); BUG_ON(in_interrupt()); + + if (flags & TARGET_SCF_USE_CPUID) + se_cmd->se_cmd_flags |= SCF_USE_CPUID; /* * Initialize se_cmd for target operation. From this point * exceptions are handled by sending exception status via @@ -1625,11 +1629,6 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess data_length, data_dir, task_attr, sense, unpacked_lun); - if (flags & TARGET_SCF_USE_CPUID) - se_cmd->se_cmd_flags |= SCF_USE_CPUID; - else - se_cmd->cpuid = WORK_CPU_UNBOUND; - if (flags & TARGET_SCF_UNKNOWN_SIZE) se_cmd->unknown_data_length = 1; /* diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index 9c8c38a..768f250 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -550,7 +550,7 @@ static void ft_send_work(struct work_struct *work) if (target_submit_cmd(&cmd->se_cmd, cmd->sess->se_sess, fcp->fc_cdb, &cmd->ft_sense_buffer[0], scsilun_to_int(&fcp->fc_lun), ntohl(fcp->fc_dl), task_attr, data_dir, - TARGET_SCF_ACK_KREF | TARGET_SCF_USE_CPUID)) + TARGET_SCF_ACK_KREF)) goto err; pr_debug("r_ctl %x target_submit_cmd %p\n", fh->fh_r_ctl, cmd); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index c858dc0..63dd121 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -540,6 +540,10 @@ struct se_cmd { unsigned int t_prot_nents; sense_reason_t pi_err; u64 sense_info; + /* + * CPU LIO will execute the cmd on. Defaults to the CPU the cmd is + * initialized on. Drivers can override. + */ int cpuid; }; @@ -760,6 +764,11 @@ struct se_dev_stat_grps { struct config_group scsi_lu_group; }; +struct se_device_queue { + struct list_head state_list; + spinlock_t lock; +}; + struct se_device { /* RELATIVE TARGET PORT IDENTIFER Counter */ u16 dev_rpti_counter; @@ -792,7 +801,6 @@ struct se_device { atomic_t dev_qf_count; u32 export_count; spinlock_t delayed_cmd_lock; - spinlock_t execute_task_lock; spinlock_t dev_reservation_lock; unsigned int dev_reservation_flags; #define DRF_SPC2_RESERVATIONS 0x00000001 @@ -811,7 +819,6 @@ struct se_device { struct list_head dev_tmr_list; struct work_struct qf_work_queue; struct list_head delayed_cmd_list; - struct list_head state_list; struct list_head qf_cmd_list; /* Pointer to associated SE HBA */ struct se_hba *se_hba; @@ -838,6 +845,8 @@ struct se_device { /* For se_lun->lun_se_dev RCU read-side critical access */ u32 hba_index; struct rcu_head rcu_head; + int queue_cnt; + struct se_device_queue *queues; }; struct se_hba { -- 2.7.4