--- zzzz-none-000/linux-3.10.107/drivers/scsi/scsi_lib.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/scsi/scsi_lib.c 2021-02-04 17:41:59.000000000 +0000 @@ -1,5 +1,6 @@ /* - * scsi_lib.c Copyright (C) 1999 Eric Youngdale + * Copyright (C) 1999 Eric Youngdale + * Copyright (C) 2014 Christoph Hellwig * * SCSI queueing library. * Initial versions: Eric Youngdale (eric@andante.org). @@ -20,6 +21,8 @@ #include #include #include +#include +#include #include #include @@ -28,6 +31,9 @@ #include #include #include +#include + +#include #include "scsi_priv.h" #include "scsi_logging.h" @@ -43,7 +49,7 @@ mempool_t *pool; }; -#define SP(x) { x, "sgpool-" __stringify(x) } +#define SP(x) { .size = x, "sgpool-" __stringify(x) } #if (SCSI_MAX_SG_SEGMENTS < 32) #error SCSI_MAX_SG_SEGMENTS is too small (must be 32 or greater) #endif @@ -68,28 +74,6 @@ struct kmem_cache *scsi_sdb_cache; -#ifdef CONFIG_ACPI -#include - -static bool acpi_scsi_bus_match(struct device *dev) -{ - return dev->bus == &scsi_bus_type; -} - -int scsi_register_acpi_bus_type(struct acpi_bus_type *bus) -{ - bus->match = acpi_scsi_bus_match; - return register_acpi_bus_type(bus); -} -EXPORT_SYMBOL_GPL(scsi_register_acpi_bus_type); - -void scsi_unregister_acpi_bus_type(struct acpi_bus_type *bus) -{ - unregister_acpi_bus_type(bus); -} -EXPORT_SYMBOL_GPL(scsi_unregister_acpi_bus_type); -#endif - /* * When to reinvoke queueing after a resource shortage. It's 3 msecs to * not change behaviour from the previous unplug mechanism, experimentation @@ -97,50 +81,12 @@ */ #define SCSI_QUEUE_DELAY 3 -/* - * Function: scsi_unprep_request() - * - * Purpose: Remove all preparation done for a request, including its - * associated scsi_cmnd, so that it can be requeued. - * - * Arguments: req - request to unprepare - * - * Lock status: Assumed that no locks are held upon entry. - * - * Returns: Nothing. - */ -static void scsi_unprep_request(struct request *req) -{ - struct scsi_cmnd *cmd = req->special; - - blk_unprep_request(req); - req->special = NULL; - - scsi_put_command(cmd); -} - -/** - * __scsi_queue_insert - private queue insertion - * @cmd: The SCSI command being requeued - * @reason: The reason for the requeue - * @unbusy: Whether the queue should be unbusied - * - * This is a private queue insertion. The public interface - * scsi_queue_insert() always assumes the queue should be unbusied - * because it's always called before the completion. This function is - * for a requeue after completion, which should only occur in this - * file. - */ -static void __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, int unbusy) +static void +scsi_set_blocked(struct scsi_cmnd *cmd, int reason) { struct Scsi_Host *host = cmd->device->host; struct scsi_device *device = cmd->device; struct scsi_target *starget = scsi_target(device); - struct request_queue *q = device->request_queue; - unsigned long flags; - - SCSI_LOG_MLQUEUE(1, - printk("Inserting command %p into mlqueue\n", cmd)); /* * Set the appropriate busy bit for the device/host. @@ -157,16 +103,52 @@ */ switch (reason) { case SCSI_MLQUEUE_HOST_BUSY: - host->host_blocked = host->max_host_blocked; + atomic_set(&host->host_blocked, host->max_host_blocked); break; case SCSI_MLQUEUE_DEVICE_BUSY: case SCSI_MLQUEUE_EH_RETRY: - device->device_blocked = device->max_device_blocked; + atomic_set(&device->device_blocked, + device->max_device_blocked); break; case SCSI_MLQUEUE_TARGET_BUSY: - starget->target_blocked = starget->max_target_blocked; + atomic_set(&starget->target_blocked, + starget->max_target_blocked); break; } +} + +static void scsi_mq_requeue_cmd(struct scsi_cmnd *cmd) +{ + struct scsi_device *sdev = cmd->device; + struct request_queue *q = cmd->request->q; + + blk_mq_requeue_request(cmd->request); + blk_mq_kick_requeue_list(q); + put_device(&sdev->sdev_gendev); +} + +/** + * __scsi_queue_insert - private queue insertion + * @cmd: The SCSI command being requeued + * @reason: The reason for the requeue + * @unbusy: Whether the queue should be unbusied + * + * This is a private queue insertion. The public interface + * scsi_queue_insert() always assumes the queue should be unbusied + * because it's always called before the completion. This function is + * for a requeue after completion, which should only occur in this + * file. + */ +static void __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, int unbusy) +{ + struct scsi_device *device = cmd->device; + struct request_queue *q = device->request_queue; + unsigned long flags; + + SCSI_LOG_MLQUEUE(1, scmd_printk(KERN_INFO, cmd, + "Inserting command %p into mlqueue\n", cmd)); + + scsi_set_blocked(cmd, reason); /* * Decrement the counters, since these commands are no longer @@ -181,9 +163,14 @@ * lock such that the kblockd_schedule_work() call happens * before blk_cleanup_queue() finishes. */ + cmd->result = 0; + if (q->mq_ops) { + scsi_mq_requeue_cmd(cmd); + return; + } spin_lock_irqsave(q->queue_lock, flags); blk_requeue_request(q, cmd->request); - kblockd_schedule_work(q, &device->requeue_work); + kblockd_schedule_work(&device->requeue_work); spin_unlock_irqrestore(q->queue_lock, flags); } @@ -228,19 +215,20 @@ */ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, - unsigned char *sense, int timeout, int retries, int flags, + unsigned char *sense, int timeout, int retries, u64 flags, int *resid) { struct request *req; int write = (data_direction == DMA_TO_DEVICE); int ret = DRIVER_ERROR << 24; - req = blk_get_request(sdev->request_queue, write, __GFP_WAIT); - if (!req) + req = blk_get_request(sdev->request_queue, write, __GFP_RECLAIM); + if (IS_ERR(req)) return ret; + blk_rq_set_block_pc(req); if (bufflen && blk_rq_map_kern(sdev->request_queue, req, - buffer, bufflen, __GFP_WAIT)) + buffer, bufflen, __GFP_RECLAIM)) goto out; req->cmd_len = COMMAND_SIZE(cmd[0]); @@ -249,7 +237,6 @@ req->sense_len = 0; req->retries = retries; req->timeout = timeout; - req->cmd_type = REQ_TYPE_BLOCK_PC; req->cmd_flags |= flags | REQ_QUIET | REQ_PREEMPT; /* @@ -279,7 +266,7 @@ int scsi_execute_req_flags(struct scsi_device *sdev, const unsigned char *cmd, int data_direction, void *buffer, unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout, int retries, - int *resid, int flags) + int *resid, u64 flags) { char *sense = NULL; int result; @@ -325,16 +312,26 @@ struct scsi_target *starget = scsi_target(sdev); unsigned long flags; - spin_lock_irqsave(shost->host_lock, flags); - shost->host_busy--; - starget->target_busy--; + atomic_dec(&shost->host_busy); + if (starget->can_queue > 0) + atomic_dec(&starget->target_busy); + if (unlikely(scsi_host_in_recovery(shost) && - (shost->host_failed || shost->host_eh_scheduled))) + (shost->host_failed || shost->host_eh_scheduled))) { + spin_lock_irqsave(shost->host_lock, flags); scsi_eh_wakeup(shost); - spin_unlock(shost->host_lock); - spin_lock(sdev->request_queue->queue_lock); - sdev->device_busy--; - spin_unlock_irqrestore(sdev->request_queue->queue_lock, flags); + spin_unlock_irqrestore(shost->host_lock, flags); + } + + atomic_dec(&sdev->device_busy); +} + +static void scsi_kick_queue(struct request_queue *q) +{ + if (q->mq_ops) + blk_mq_start_hw_queues(q); + else + blk_run_queue(q); } /* @@ -361,7 +358,7 @@ * but in most cases, we will be first. Ideally, each LU on the * target would get some limited time or requests on the target. */ - blk_run_queue(current_sdev->request_queue); + scsi_kick_queue(current_sdev->request_queue); spin_lock_irqsave(shost->host_lock, flags); if (starget->starget_sdev_user) @@ -374,7 +371,7 @@ continue; spin_unlock_irqrestore(shost->host_lock, flags); - blk_run_queue(sdev->request_queue); + scsi_kick_queue(sdev->request_queue); spin_lock_irqsave(shost->host_lock, flags); scsi_device_put(sdev); @@ -383,57 +380,50 @@ spin_unlock_irqrestore(shost->host_lock, flags); } -static inline int scsi_device_is_busy(struct scsi_device *sdev) +static inline bool scsi_device_is_busy(struct scsi_device *sdev) { - if (sdev->device_busy >= sdev->queue_depth || sdev->device_blocked) - return 1; - - return 0; + if (atomic_read(&sdev->device_busy) >= sdev->queue_depth) + return true; + if (atomic_read(&sdev->device_blocked) > 0) + return true; + return false; } -static inline int scsi_target_is_busy(struct scsi_target *starget) +static inline bool scsi_target_is_busy(struct scsi_target *starget) { - return ((starget->can_queue > 0 && - starget->target_busy >= starget->can_queue) || - starget->target_blocked); + if (starget->can_queue > 0) { + if (atomic_read(&starget->target_busy) >= starget->can_queue) + return true; + if (atomic_read(&starget->target_blocked) > 0) + return true; + } + return false; } -static inline int scsi_host_is_busy(struct Scsi_Host *shost) +static inline bool scsi_host_is_busy(struct Scsi_Host *shost) { - if ((shost->can_queue > 0 && shost->host_busy >= shost->can_queue) || - shost->host_blocked || shost->host_self_blocked) - return 1; - - return 0; + if (shost->can_queue > 0 && + atomic_read(&shost->host_busy) >= shost->can_queue) + return true; + if (atomic_read(&shost->host_blocked) > 0) + return true; + if (shost->host_self_blocked) + return true; + return false; } -/* - * Function: scsi_run_queue() - * - * Purpose: Select a proper request queue to serve next - * - * Arguments: q - last request's queue - * - * Returns: Nothing - * - * Notes: The previous command was completely finished, start - * a new one if possible. - */ -static void scsi_run_queue(struct request_queue *q) +static void scsi_starved_list_run(struct Scsi_Host *shost) { - struct scsi_device *sdev = q->queuedata; - struct Scsi_Host *shost; LIST_HEAD(starved_list); + struct scsi_device *sdev; unsigned long flags; - shost = sdev->host; - if (scsi_target(sdev)->single_lun) - scsi_single_lun_run(sdev); - spin_lock_irqsave(shost->host_lock, flags); list_splice_init(&shost->starved_list, &starved_list); while (!list_empty(&starved_list)) { + struct request_queue *slq; + /* * As long as shost is accepting commands and we have * starved queues, call blk_run_queue. scsi_request_fn @@ -456,17 +446,56 @@ continue; } - spin_unlock(shost->host_lock); - spin_lock(sdev->request_queue->queue_lock); - __blk_run_queue(sdev->request_queue); - spin_unlock(sdev->request_queue->queue_lock); - spin_lock(shost->host_lock); + /* + * Once we drop the host lock, a racing scsi_remove_device() + * call may remove the sdev from the starved list and destroy + * it and the queue. Mitigate by taking a reference to the + * queue and never touching the sdev again after we drop the + * host lock. Note: if __scsi_remove_device() invokes + * blk_cleanup_queue() before the queue is run from this + * function then blk_run_queue() will return immediately since + * blk_cleanup_queue() marks the queue with QUEUE_FLAG_DYING. + */ + slq = sdev->request_queue; + if (!blk_get_queue(slq)) + continue; + spin_unlock_irqrestore(shost->host_lock, flags); + + scsi_kick_queue(slq); + blk_put_queue(slq); + + spin_lock_irqsave(shost->host_lock, flags); } /* put any unprocessed entries back */ list_splice(&starved_list, &shost->starved_list); spin_unlock_irqrestore(shost->host_lock, flags); +} + +/* + * Function: scsi_run_queue() + * + * Purpose: Select a proper request queue to serve next + * + * Arguments: q - last request's queue + * + * Returns: Nothing + * + * Notes: The previous command was completely finished, start + * a new one if possible. + */ +static void scsi_run_queue(struct request_queue *q) +{ + struct scsi_device *sdev = q->queuedata; - blk_run_queue(q); + if (scsi_target(sdev)->single_lun) + scsi_single_lun_run(sdev); + if (!list_empty(&sdev->host->starved_list)) + scsi_starved_list_run(sdev->host); + + if (q->mq_ops) + blk_mq_start_stopped_hw_queues(q, false); + else + blk_run_queue(q); } void scsi_requeue_run_queue(struct work_struct *work) @@ -503,16 +532,10 @@ struct request *req = cmd->request; unsigned long flags; - /* - * We need to hold a reference on the device to avoid the queue being - * killed after the unlock and before scsi_run_queue is invoked which - * may happen because scsi_unprep_request() puts the command which - * releases its reference on the device. - */ - get_device(&sdev->sdev_gendev); - spin_lock_irqsave(q->queue_lock, flags); - scsi_unprep_request(req); + blk_unprep_request(req); + req->special = NULL; + scsi_put_command(cmd); blk_requeue_request(q, req); spin_unlock_irqrestore(q->queue_lock, flags); @@ -521,21 +544,6 @@ put_device(&sdev->sdev_gendev); } -void scsi_next_command(struct scsi_cmnd *cmd) -{ - struct scsi_device *sdev = cmd->device; - struct request_queue *q = sdev->request_queue; - - /* need to hold a reference on the device before we let go of the cmd */ - get_device(&sdev->sdev_gendev); - - scsi_put_command(cmd); - scsi_run_queue(q); - - /* ok to remove device now */ - put_device(&sdev->sdev_gendev); -} - void scsi_run_host_queues(struct Scsi_Host *shost) { struct scsi_device *sdev; @@ -544,8 +552,6 @@ scsi_run_queue(sdev->request_queue); } -static void __scsi_release_buffers(struct scsi_cmnd *, int); - static inline unsigned int scsi_sgtable_index(unsigned short nents) { unsigned int index; @@ -576,51 +582,77 @@ return mempool_alloc(sgp->pool, gfp_mask); } -static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents, - gfp_t gfp_mask) +static void scsi_free_sgtable(struct scsi_data_buffer *sdb, bool mq) +{ + if (mq && sdb->table.orig_nents <= SCSI_MAX_SG_SEGMENTS) + return; + __sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, mq, scsi_sg_free); +} + +static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents, bool mq) { + struct scatterlist *first_chunk = NULL; int ret; BUG_ON(!nents); + if (mq) { + if (nents <= SCSI_MAX_SG_SEGMENTS) { + sdb->table.nents = sdb->table.orig_nents = nents; + sg_init_table(sdb->table.sgl, nents); + return 0; + } + first_chunk = sdb->table.sgl; + } + ret = __sg_alloc_table(&sdb->table, nents, SCSI_MAX_SG_SEGMENTS, - gfp_mask, scsi_sg_alloc); + first_chunk, GFP_ATOMIC, scsi_sg_alloc); if (unlikely(ret)) - __sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, - scsi_sg_free); - + scsi_free_sgtable(sdb, mq); return ret; } -static void scsi_free_sgtable(struct scsi_data_buffer *sdb) +static void scsi_uninit_cmd(struct scsi_cmnd *cmd) { - __sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, scsi_sg_free); + if (cmd->request->cmd_type == REQ_TYPE_FS) { + struct scsi_driver *drv = scsi_cmd_to_driver(cmd); + + if (drv->uninit_command) + drv->uninit_command(cmd); + } } -static void __scsi_release_buffers(struct scsi_cmnd *cmd, int do_bidi_check) +static void scsi_mq_free_sgtables(struct scsi_cmnd *cmd) { - if (cmd->sdb.table.nents) - scsi_free_sgtable(&cmd->sdb); + scsi_free_sgtable(&cmd->sdb, true); + if (cmd->request->next_rq && cmd->request->next_rq->special) + scsi_free_sgtable(cmd->request->next_rq->special, true); + if (scsi_prot_sg_count(cmd)) + scsi_free_sgtable(cmd->prot_sdb, true); +} - memset(&cmd->sdb, 0, sizeof(cmd->sdb)); +static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd) +{ + struct scsi_device *sdev = cmd->device; + struct Scsi_Host *shost = sdev->host; + unsigned long flags; - if (do_bidi_check && scsi_bidi_cmnd(cmd)) { - struct scsi_data_buffer *bidi_sdb = - cmd->request->next_rq->special; - scsi_free_sgtable(bidi_sdb); - kmem_cache_free(scsi_sdb_cache, bidi_sdb); - cmd->request->next_rq->special = NULL; - } + scsi_mq_free_sgtables(cmd); + scsi_uninit_cmd(cmd); - if (scsi_prot_sg_count(cmd)) - scsi_free_sgtable(cmd->prot_sdb); + if (shost->use_cmd_list) { + BUG_ON(list_empty(&cmd->list)); + spin_lock_irqsave(&sdev->list_lock, flags); + list_del_init(&cmd->list); + spin_unlock_irqrestore(&sdev->list_lock, flags); + } } /* * Function: scsi_release_buffers() * - * Purpose: Completion processing for block device I/O requests. + * Purpose: Free resources allocate for a scsi_command. * * Arguments: cmd - command that we are bailing. * @@ -631,15 +663,97 @@ * Notes: In the event that an upper level driver rejects a * command, we must release resources allocated during * the __init_io() function. Primarily this would involve - * the scatter-gather table, and potentially any bounce - * buffers. + * the scatter-gather table. */ -void scsi_release_buffers(struct scsi_cmnd *cmd) +static void scsi_release_buffers(struct scsi_cmnd *cmd) { - __scsi_release_buffers(cmd, 1); + if (cmd->sdb.table.nents) + scsi_free_sgtable(&cmd->sdb, false); + + memset(&cmd->sdb, 0, sizeof(cmd->sdb)); + + if (scsi_prot_sg_count(cmd)) + scsi_free_sgtable(cmd->prot_sdb, false); +} + +static void scsi_release_bidi_buffers(struct scsi_cmnd *cmd) +{ + struct scsi_data_buffer *bidi_sdb = cmd->request->next_rq->special; + + scsi_free_sgtable(bidi_sdb, false); + kmem_cache_free(scsi_sdb_cache, bidi_sdb); + cmd->request->next_rq->special = NULL; +} + +static bool scsi_end_request(struct request *req, int error, + unsigned int bytes, unsigned int bidi_bytes) +{ + struct scsi_cmnd *cmd = req->special; + struct scsi_device *sdev = cmd->device; + struct request_queue *q = sdev->request_queue; + + if (blk_update_request(req, error, bytes)) + return true; + + /* Bidi request must be completed as a whole */ + if (unlikely(bidi_bytes) && + blk_update_request(req->next_rq, error, bidi_bytes)) + return true; + + if (blk_queue_add_random(q)) + add_disk_randomness(req->rq_disk); + + if (req->mq_ctx) { + /* + * In the MQ case the command gets freed by __blk_mq_end_request, + * so we have to do all cleanup that depends on it earlier. + * + * We also can't kick the queues from irq context, so we + * will have to defer it to a workqueue. + */ + scsi_mq_uninit_cmd(cmd); + + __blk_mq_end_request(req, error); + + if (scsi_target(sdev)->single_lun || + !list_empty(&sdev->host->starved_list)) + kblockd_schedule_work(&sdev->requeue_work); + else + blk_mq_start_stopped_hw_queues(q, true); + } else { + unsigned long flags; + + if (bidi_bytes) + scsi_release_bidi_buffers(cmd); + + spin_lock_irqsave(q->queue_lock, flags); + blk_finish_request(req, error); + spin_unlock_irqrestore(q->queue_lock, flags); + + scsi_release_buffers(cmd); + + scsi_put_command(cmd); + scsi_run_queue(q); + } + + put_device(&sdev->sdev_gendev); + return false; } -EXPORT_SYMBOL(scsi_release_buffers); +/** + * __scsi_error_from_host_byte - translate SCSI error code into errno + * @cmd: SCSI command (unused) + * @result: scsi error code + * + * Translate SCSI error code into standard UNIX errno. + * Return values: + * -ENOLINK temporary transport failure + * -EREMOTEIO permanent target failure, do not retry + * -EBADE permanent nexus failure, retry on other path + * -ENOSPC No write space available + * -ENODATA Medium error + * -EIO unspecified I/O error + */ static int __scsi_error_from_host_byte(struct scsi_cmnd *cmd, int result) { int error = 0; @@ -656,6 +770,14 @@ set_host_byte(cmd, DID_OK); error = -EBADE; break; + case DID_ALLOC_FAILURE: + set_host_byte(cmd, DID_OK); + error = -ENOSPC; + break; + case DID_MEDIUM_ERROR: + set_host_byte(cmd, DID_OK); + error = -ENODATA; + break; default: error = -EIO; break; @@ -690,7 +812,7 @@ * be put back on the queue and retried using the same * command as before, possibly after a delay. * - * c) We can call blk_end_request() with -EIO to fail + * c) We can call scsi_end_request() with -EIO to fail * the remainder of the request. */ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) @@ -700,11 +822,11 @@ struct request *req = cmd->request; int error = 0; struct scsi_sense_hdr sshdr; - int sense_valid = 0; - int sense_deferred = 0; + bool sense_valid = false; + int sense_deferred = 0, level = 0; enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY, ACTION_DELAYED_RETRY} action; - char *description = NULL; + unsigned long wait_for = (cmd->allowed + 1) * req->timeout; if (result) { sense_valid = scsi_command_normalize_sense(cmd, &sshdr); @@ -741,11 +863,9 @@ * both sides at once. */ req->next_rq->resid_len = scsi_in(cmd)->resid; - - scsi_release_buffers(cmd); - blk_end_request_all(req, 0); - - scsi_next_command(cmd); + if (scsi_end_request(req, 0, blk_rq_bytes(req), + blk_rq_bytes(req->next_rq))) + BUG(); return; } } else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) { @@ -765,9 +885,9 @@ * Next deal with any sectors which we were able to correctly * handle. */ - SCSI_LOG_HLCOMPLETE(1, printk("%u sectors total, " - "%d bytes done.\n", - blk_rq_sectors(req), good_bytes)); + SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, cmd, + "%u sectors total, %d bytes done.\n", + blk_rq_sectors(req), good_bytes)); /* * Recovered errors need reporting, but they're always treated @@ -783,7 +903,7 @@ if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d)) ; else if (!(req->cmd_flags & REQ_QUIET)) - scsi_print_sense("", cmd); + scsi_print_sense(cmd); result = 0; /* BLOCK_PC may have set error */ error = 0; @@ -795,15 +915,16 @@ * all bytes in the request we are done now. */ if (!(blk_rq_bytes(req) == 0 && error) && - !blk_end_request(req, error, good_bytes)) - goto next_command; + !scsi_end_request(req, error, good_bytes, 0)) + return; /* * Kill remainder if no retrys. */ if (error && scsi_noretry_cmd(cmd)) { - blk_end_request_all(req, error); - goto next_command; + if (scsi_end_request(req, error, blk_rq_bytes(req), 0)) + BUG(); + return; } /* @@ -828,9 +949,14 @@ /* Detected disc change. Set a bit * and quietly refuse further access. */ +/* == 20171005 AVM/VGJ - Some devices need a retry after resume == */ +#if defined(CONFIG_AVM_USB_PM) + action = ACTION_DELAYED_RETRY; + printk(KERN_INFO "%s(): possible media change detected - retry\n", __func__); +#else cmd->device->changed = 1; - description = "Media Changed"; action = ACTION_FAIL; +#endif } else { /* Must have been a power glitch, or a * bus reset. Could not have been a @@ -857,27 +983,10 @@ cmd->device->use_10_for_rw = 0; action = ACTION_REPREP; } else if (sshdr.asc == 0x10) /* DIX */ { - description = "Host Data Integrity Failure"; action = ACTION_FAIL; error = -EILSEQ; /* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */ } else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) { - switch (cmd->cmnd[0]) { - case UNMAP: - description = "Discard failure"; - break; - case WRITE_SAME: - case WRITE_SAME_16: - if (cmd->cmnd[1] & 0x8) - description = "Discard failure"; - else - description = - "Write same failure"; - break; - default: - description = "Invalid command failure"; - break; - } action = ACTION_FAIL; error = -EREMOTEIO; } else @@ -885,10 +994,8 @@ break; case ABORTED_COMMAND: action = ACTION_FAIL; - if (sshdr.asc == 0x10) { /* DIF */ - description = "Target Data Integrity Failure"; + if (sshdr.asc == 0x10) /* DIF */ error = -EILSEQ; - } break; case NOT_READY: /* If the device is in the process of becoming @@ -907,51 +1014,66 @@ action = ACTION_DELAYED_RETRY; break; default: - description = "Device not ready"; action = ACTION_FAIL; break; } - } else { - description = "Device not ready"; + } else action = ACTION_FAIL; - } break; case VOLUME_OVERFLOW: /* See SSC3rXX or current. */ action = ACTION_FAIL; break; default: - description = "Unhandled sense code"; action = ACTION_FAIL; break; } - } else { - description = "Unhandled error code"; + } else + action = ACTION_FAIL; + + if (action != ACTION_FAIL && + time_before(cmd->jiffies_at_alloc + wait_for, jiffies)) action = ACTION_FAIL; - } switch (action) { case ACTION_FAIL: /* Give up and fail the remainder of the request */ if (!(req->cmd_flags & REQ_QUIET)) { - if (description) - scmd_printk(KERN_INFO, cmd, "%s\n", - description); - scsi_print_result(cmd); - if (driver_byte(result) & DRIVER_SENSE) - scsi_print_sense("", cmd); - scsi_print_command(cmd); + static DEFINE_RATELIMIT_STATE(_rs, + DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + if (unlikely(scsi_logging_level)) + level = SCSI_LOG_LEVEL(SCSI_LOG_MLCOMPLETE_SHIFT, + SCSI_LOG_MLCOMPLETE_BITS); + + /* + * if logging is enabled the failure will be printed + * in scsi_log_completion(), so avoid duplicate messages + */ + if (!level && __ratelimit(&_rs)) { + scsi_print_result(cmd, NULL, FAILED); + if (driver_byte(result) & DRIVER_SENSE) + scsi_print_sense(cmd); + scsi_print_command(cmd); + } } - if (!blk_end_request_err(req, error)) - goto next_command; + if (!scsi_end_request(req, error, blk_rq_err_bytes(req), 0)) + return; /*FALLTHRU*/ case ACTION_REPREP: requeue: /* Unprep the request and put it back at the head of the queue. * A new command will be prepared and issued. */ - scsi_release_buffers(cmd); - scsi_requeue_command(q, cmd); + if (q->mq_ops) { + cmd->request->cmd_flags &= ~REQ_DONTPREP; + scsi_mq_uninit_cmd(cmd); + scsi_mq_requeue_cmd(cmd); + } else { + scsi_release_buffers(cmd); + scsi_requeue_command(q, cmd); + } break; case ACTION_RETRY: /* Retry the same command immediately */ @@ -962,15 +1084,9 @@ __scsi_queue_insert(cmd, SCSI_MLQUEUE_DEVICE_BUSY, 0); break; } - return; - -next_command: - __scsi_release_buffers(cmd, 0); - scsi_next_command(cmd); } -static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb, - gfp_t gfp_mask) +static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb) { int count; @@ -978,11 +1094,8 @@ * If sg table allocation fails, requeue request later. */ if (unlikely(scsi_alloc_sgtable(sdb, req->nr_phys_segments, - gfp_mask))) { + req->mq_ctx != NULL))) return BLKPREP_DEFER; - } - - req->buffer = NULL; /* * Next, walk the list, and fill in the addresses and sizes of @@ -1006,28 +1119,33 @@ * BLKPREP_DEFER if the failure is retryable * BLKPREP_KILL if the failure is fatal */ -int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask) +int scsi_init_io(struct scsi_cmnd *cmd) { + struct scsi_device *sdev = cmd->device; struct request *rq = cmd->request; + bool is_mq = (rq->mq_ctx != NULL); int error; if (WARN_ON_ONCE(!rq->nr_phys_segments)) return -EINVAL; - error = scsi_init_sgtable(rq, &cmd->sdb, gfp_mask); + error = scsi_init_sgtable(rq, &cmd->sdb); if (error) goto err_exit; if (blk_bidi_rq(rq)) { - struct scsi_data_buffer *bidi_sdb = kmem_cache_zalloc( - scsi_sdb_cache, GFP_ATOMIC); - if (!bidi_sdb) { - error = BLKPREP_DEFER; - goto err_exit; + if (!rq->q->mq_ops) { + struct scsi_data_buffer *bidi_sdb = + kmem_cache_zalloc(scsi_sdb_cache, GFP_ATOMIC); + if (!bidi_sdb) { + error = BLKPREP_DEFER; + goto err_exit; + } + + rq->next_rq->special = bidi_sdb; } - rq->next_rq->special = bidi_sdb; - error = scsi_init_sgtable(rq->next_rq, bidi_sdb, GFP_ATOMIC); + error = scsi_init_sgtable(rq->next_rq, rq->next_rq->special); if (error) goto err_exit; } @@ -1036,10 +1154,20 @@ struct scsi_data_buffer *prot_sdb = cmd->prot_sdb; int ivecs, count; - BUG_ON(prot_sdb == NULL); + if (prot_sdb == NULL) { + /* + * This can happen if someone (e.g. multipath) + * queues a command to a device on an adapter + * that does not support DIX. + */ + WARN_ON_ONCE(1); + error = BLKPREP_KILL; + goto err_exit; + } + ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio); - if (scsi_alloc_sgtable(prot_sdb, ivecs, gfp_mask)) { + if (scsi_alloc_sgtable(prot_sdb, ivecs, is_mq)) { error = BLKPREP_DEFER; goto err_exit; } @@ -1053,12 +1181,16 @@ cmd->prot_sdb->table.nents = count; } - return BLKPREP_OK ; - + return BLKPREP_OK; err_exit: - scsi_release_buffers(cmd); - cmd->request->special = NULL; - scsi_put_command(cmd); + if (is_mq) { + scsi_mq_free_sgtables(cmd); + } else { + scsi_release_buffers(cmd); + cmd->request->special = NULL; + scsi_put_command(cmd); + put_device(&sdev->sdev_gendev); + } return error; } EXPORT_SYMBOL(scsi_init_io); @@ -1069,9 +1201,15 @@ struct scsi_cmnd *cmd; if (!req->special) { + /* Bail if we can't get a reference to the device */ + if (!get_device(&sdev->sdev_gendev)) + return NULL; + cmd = scsi_get_command(sdev, GFP_ATOMIC); - if (unlikely(!cmd)) + if (unlikely(!cmd)) { + put_device(&sdev->sdev_gendev); return NULL; + } req->special = cmd; } else { cmd = req->special; @@ -1087,17 +1225,9 @@ return cmd; } -int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req) +static int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req) { - struct scsi_cmnd *cmd; - int ret = scsi_prep_state_check(sdev, req); - - if (ret != BLKPREP_OK) - return ret; - - cmd = scsi_get_cmd_from_req(sdev, req); - if (unlikely(!cmd)) - return BLKPREP_DEFER; + struct scsi_cmnd *cmd = req->special; /* * BLOCK_PC requests may transfer data, in which case they must @@ -1106,60 +1236,62 @@ * submit a request without an attached bio. */ if (req->bio) { - int ret = scsi_init_io(cmd, GFP_ATOMIC); + int ret = scsi_init_io(cmd); if (unlikely(ret)) return ret; } else { BUG_ON(blk_rq_bytes(req)); memset(&cmd->sdb, 0, sizeof(cmd->sdb)); - req->buffer = NULL; } cmd->cmd_len = req->cmd_len; - if (!blk_rq_bytes(req)) - cmd->sc_data_direction = DMA_NONE; - else if (rq_data_dir(req) == WRITE) - cmd->sc_data_direction = DMA_TO_DEVICE; - else - cmd->sc_data_direction = DMA_FROM_DEVICE; - cmd->transfersize = blk_rq_bytes(req); cmd->allowed = req->retries; return BLKPREP_OK; } -EXPORT_SYMBOL(scsi_setup_blk_pc_cmnd); /* - * Setup a REQ_TYPE_FS command. These are simple read/write request - * from filesystems that still need to be translated to SCSI CDBs from - * the ULD. + * Setup a REQ_TYPE_FS command. These are simple request from filesystems + * that still need to be translated to SCSI CDBs from the ULD. */ -int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req) +static int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req) { - struct scsi_cmnd *cmd; - int ret = scsi_prep_state_check(sdev, req); - - if (ret != BLKPREP_OK) - return ret; + struct scsi_cmnd *cmd = req->special; - if (unlikely(sdev->scsi_dh_data && sdev->scsi_dh_data->scsi_dh - && sdev->scsi_dh_data->scsi_dh->prep_fn)) { - ret = sdev->scsi_dh_data->scsi_dh->prep_fn(sdev, req); + if (unlikely(sdev->handler && sdev->handler->prep_fn)) { + int ret = sdev->handler->prep_fn(sdev, req); if (ret != BLKPREP_OK) return ret; } - cmd = scsi_get_cmd_from_req(sdev, req); - if (unlikely(!cmd)) - return BLKPREP_DEFER; - memset(cmd->cmnd, 0, BLK_MAX_CDB); - return scsi_init_io(cmd, GFP_ATOMIC); + return scsi_cmd_to_driver(cmd)->init_command(cmd); } -EXPORT_SYMBOL(scsi_setup_fs_cmnd); -int scsi_prep_state_check(struct scsi_device *sdev, struct request *req) +static int scsi_setup_cmnd(struct scsi_device *sdev, struct request *req) +{ + struct scsi_cmnd *cmd = req->special; + + if (!blk_rq_bytes(req)) + cmd->sc_data_direction = DMA_NONE; + else if (rq_data_dir(req) == WRITE) + cmd->sc_data_direction = DMA_TO_DEVICE; + else + cmd->sc_data_direction = DMA_FROM_DEVICE; + + switch (req->cmd_type) { + case REQ_TYPE_FS: + return scsi_setup_fs_cmnd(sdev, req); + case REQ_TYPE_BLOCK_PC: + return scsi_setup_blk_pc_cmnd(sdev, req); + default: + return BLKPREP_KILL; + } +} + +static int +scsi_prep_state_check(struct scsi_device *sdev, struct request *req) { int ret = BLKPREP_OK; @@ -1213,9 +1345,9 @@ } return ret; } -EXPORT_SYMBOL(scsi_prep_state_check); -int scsi_prep_return(struct request_queue *q, struct request *req, int ret) +static int +scsi_prep_return(struct request_queue *q, struct request *req, int ret) { struct scsi_device *sdev = q->queuedata; @@ -1227,6 +1359,7 @@ struct scsi_cmnd *cmd = req->special; scsi_release_buffers(cmd); scsi_put_command(cmd); + put_device(&sdev->sdev_gendev); req->special = NULL; } break; @@ -1236,7 +1369,7 @@ * queue must be restarted, so we schedule a callback to happen * shortly. */ - if (sdev->device_busy == 0) + if (atomic_read(&sdev->device_busy) == 0) blk_delay_queue(q, SCSI_QUEUE_DELAY); break; default: @@ -1245,18 +1378,32 @@ return ret; } -EXPORT_SYMBOL(scsi_prep_return); -int scsi_prep_fn(struct request_queue *q, struct request *req) +static int scsi_prep_fn(struct request_queue *q, struct request *req) { struct scsi_device *sdev = q->queuedata; - int ret = BLKPREP_KILL; + struct scsi_cmnd *cmd; + int ret; - if (req->cmd_type == REQ_TYPE_BLOCK_PC) - ret = scsi_setup_blk_pc_cmnd(sdev, req); + ret = scsi_prep_state_check(sdev, req); + if (ret != BLKPREP_OK) + goto out; + + cmd = scsi_get_cmd_from_req(sdev, req); + if (unlikely(!cmd)) { + ret = BLKPREP_DEFER; + goto out; + } + + ret = scsi_setup_cmnd(sdev, req); +out: return scsi_prep_return(q, req, ret); } -EXPORT_SYMBOL(scsi_prep_fn); + +static void scsi_unprep_fn(struct request_queue *q, struct request *req) +{ + scsi_uninit_cmd(req->special); +} /* * scsi_dev_queue_ready: if we can send requests to sdev, return 1 else @@ -1267,99 +1414,144 @@ static inline int scsi_dev_queue_ready(struct request_queue *q, struct scsi_device *sdev) { - if (sdev->device_busy == 0 && sdev->device_blocked) { + unsigned int busy; + + busy = atomic_inc_return(&sdev->device_busy) - 1; + if (atomic_read(&sdev->device_blocked)) { + if (busy) + goto out_dec; + /* * unblock after device_blocked iterates to zero */ - if (--sdev->device_blocked == 0) { - SCSI_LOG_MLQUEUE(3, - sdev_printk(KERN_INFO, sdev, - "unblocking device at zero depth\n")); - } else { - blk_delay_queue(q, SCSI_QUEUE_DELAY); - return 0; + if (atomic_dec_return(&sdev->device_blocked) > 0) { + /* + * For the MQ case we take care of this in the caller. + */ + if (!q->mq_ops) + blk_delay_queue(q, SCSI_QUEUE_DELAY); + goto out_dec; } + SCSI_LOG_MLQUEUE(3, sdev_printk(KERN_INFO, sdev, + "unblocking device at zero depth\n")); } - if (scsi_device_is_busy(sdev)) - return 0; + + if (busy >= sdev->queue_depth) + goto out_dec; return 1; +out_dec: + atomic_dec(&sdev->device_busy); + return 0; } - /* * scsi_target_queue_ready: checks if there we can send commands to target * @sdev: scsi device on starget to check. - * - * Called with the host lock held. */ static inline int scsi_target_queue_ready(struct Scsi_Host *shost, struct scsi_device *sdev) { struct scsi_target *starget = scsi_target(sdev); + unsigned int busy; if (starget->single_lun) { + spin_lock_irq(shost->host_lock); if (starget->starget_sdev_user && - starget->starget_sdev_user != sdev) + starget->starget_sdev_user != sdev) { + spin_unlock_irq(shost->host_lock); return 0; + } starget->starget_sdev_user = sdev; + spin_unlock_irq(shost->host_lock); } - if (starget->target_busy == 0 && starget->target_blocked) { + if (starget->can_queue <= 0) + return 1; + + busy = atomic_inc_return(&starget->target_busy) - 1; + if (atomic_read(&starget->target_blocked) > 0) { + if (busy) + goto starved; + /* * unblock after target_blocked iterates to zero */ - if (--starget->target_blocked == 0) { - SCSI_LOG_MLQUEUE(3, starget_printk(KERN_INFO, starget, - "unblocking target at zero depth\n")); - } else - return 0; - } + if (atomic_dec_return(&starget->target_blocked) > 0) + goto out_dec; - if (scsi_target_is_busy(starget)) { - list_move_tail(&sdev->starved_entry, &shost->starved_list); - return 0; + SCSI_LOG_MLQUEUE(3, starget_printk(KERN_INFO, starget, + "unblocking target at zero depth\n")); } + if (busy >= starget->can_queue) + goto starved; + return 1; + +starved: + spin_lock_irq(shost->host_lock); + list_move_tail(&sdev->starved_entry, &shost->starved_list); + spin_unlock_irq(shost->host_lock); +out_dec: + if (starget->can_queue > 0) + atomic_dec(&starget->target_busy); + return 0; } /* * scsi_host_queue_ready: if we can send requests to shost, return 1 else * return 0. We must end up running the queue again whenever 0 is * returned, else IO can hang. - * - * Called with host_lock held. */ static inline int scsi_host_queue_ready(struct request_queue *q, struct Scsi_Host *shost, struct scsi_device *sdev) { + unsigned int busy; + if (scsi_host_in_recovery(shost)) return 0; - if (shost->host_busy == 0 && shost->host_blocked) { + + busy = atomic_inc_return(&shost->host_busy) - 1; + if (atomic_read(&shost->host_blocked) > 0) { + if (busy) + goto starved; + /* * unblock after host_blocked iterates to zero */ - if (--shost->host_blocked == 0) { - SCSI_LOG_MLQUEUE(3, - printk("scsi%d unblocking host at zero depth\n", - shost->host_no)); - } else { - return 0; - } - } - if (scsi_host_is_busy(shost)) { - if (list_empty(&sdev->starved_entry)) - list_add_tail(&sdev->starved_entry, &shost->starved_list); - return 0; + if (atomic_dec_return(&shost->host_blocked) > 0) + goto out_dec; + + SCSI_LOG_MLQUEUE(3, + shost_printk(KERN_INFO, shost, + "unblocking host at zero depth\n")); } + if (shost->can_queue > 0 && busy >= shost->can_queue) + goto starved; + if (shost->host_self_blocked) + goto starved; + /* We're OK to process the command, so we can't be starved */ - if (!list_empty(&sdev->starved_entry)) - list_del_init(&sdev->starved_entry); + if (!list_empty(&sdev->starved_entry)) { + spin_lock_irq(shost->host_lock); + if (!list_empty(&sdev->starved_entry)) + list_del_init(&sdev->starved_entry); + spin_unlock_irq(shost->host_lock); + } return 1; + +starved: + spin_lock_irq(shost->host_lock); + if (list_empty(&sdev->starved_entry)) + list_add_tail(&sdev->starved_entry, &shost->starved_list); + spin_unlock_irq(shost->host_lock); +out_dec: + atomic_dec(&shost->host_busy); + return 0; } /* @@ -1422,13 +1614,10 @@ * bump busy counts. To bump the counters, we need to dance * with the locks as normal issue path does. */ - sdev->device_busy++; - spin_unlock(sdev->request_queue->queue_lock); - spin_lock(shost->host_lock); - shost->host_busy++; - starget->target_busy++; - spin_unlock(shost->host_lock); - spin_lock(sdev->request_queue->queue_lock); + atomic_inc(&sdev->device_busy); + atomic_inc(&shost->host_busy); + if (starget->can_queue > 0) + atomic_inc(&starget->target_busy); blk_complete_request(req); } @@ -1453,7 +1642,7 @@ wait_for/HZ); disposition = SUCCESS; } - + scsi_log_completion(cmd, disposition); switch (disposition) { @@ -1472,6 +1661,104 @@ } } +/** + * scsi_dispatch_command - Dispatch a command to the low-level driver. + * @cmd: command block we are dispatching. + * + * Return: nonzero return request was rejected and device's queue needs to be + * plugged. + */ +static int scsi_dispatch_cmd(struct scsi_cmnd *cmd) +{ + struct Scsi_Host *host = cmd->device->host; + int rtn = 0; + + atomic_inc(&cmd->device->iorequest_cnt); + + /* check if the device is still usable */ + if (unlikely(cmd->device->sdev_state == SDEV_DEL)) { + /* in SDEV_DEL we error all commands. DID_NO_CONNECT + * returns an immediate error upwards, and signals + * that the device is no longer present */ + cmd->result = DID_NO_CONNECT << 16; + goto done; + } + + /* Check to see if the scsi lld made this device blocked. */ + if (unlikely(scsi_device_blocked(cmd->device))) { + /* + * in blocked state, the command is just put back on + * the device queue. The suspend state has already + * blocked the queue so future requests should not + * occur until the device transitions out of the + * suspend state. + */ + SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd, + "queuecommand : device blocked\n")); + return SCSI_MLQUEUE_DEVICE_BUSY; + } + + /* Store the LUN value in cmnd, if needed. */ + if (cmd->device->lun_in_cdb) + cmd->cmnd[1] = (cmd->cmnd[1] & 0x1f) | + (cmd->device->lun << 5 & 0xe0); + + scsi_log_send(cmd); + + /* + * Before we queue this command, check if the command + * length exceeds what the host adapter can handle. + */ + if (cmd->cmd_len > cmd->device->host->max_cmd_len) { + SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd, + "queuecommand : command too long. " + "cdb_size=%d host->max_cmd_len=%d\n", + cmd->cmd_len, cmd->device->host->max_cmd_len)); + cmd->result = (DID_ABORT << 16); + goto done; + } + + if (unlikely(host->shost_state == SHOST_DEL)) { + cmd->result = (DID_NO_CONNECT << 16); + goto done; + + } + + trace_scsi_dispatch_cmd_start(cmd); + rtn = host->hostt->queuecommand(host, cmd); + if (rtn) { + trace_scsi_dispatch_cmd_error(cmd, rtn); + if (rtn != SCSI_MLQUEUE_DEVICE_BUSY && + rtn != SCSI_MLQUEUE_TARGET_BUSY) + rtn = SCSI_MLQUEUE_HOST_BUSY; + + SCSI_LOG_MLQUEUE(3, scmd_printk(KERN_INFO, cmd, + "queuecommand : request rejected\n")); + } + + return rtn; + done: + cmd->scsi_done(cmd); + return 0; +} + +/** + * scsi_done - Invoke completion on finished SCSI command. + * @cmd: The SCSI Command for which a low-level device driver (LLDD) gives + * ownership back to SCSI Core -- i.e. the LLDD has finished with it. + * + * Description: This function is the mid-level's (SCSI Core) interrupt routine, + * which regains ownership of the SCSI command (de facto) from a LLDD, and + * calls blk_complete_request() for further processing. + * + * This function is interrupt context safe. + */ +static void scsi_done(struct scsi_cmnd *cmd) +{ + trace_scsi_dispatch_cmd_done(cmd); + blk_complete_request(cmd->request); +} + /* * Function: scsi_request_fn() * @@ -1484,16 +1771,14 @@ * Lock status: IO request lock assumed to be held when called. */ static void scsi_request_fn(struct request_queue *q) + __releases(q->queue_lock) + __acquires(q->queue_lock) { struct scsi_device *sdev = q->queuedata; struct Scsi_Host *shost; struct scsi_cmnd *cmd; struct request *req; - if(!get_device(&sdev->sdev_gendev)) - /* We must be tearing the block queue down already */ - return; - /* * To start with, we keep looping until the queue is empty, or until * the host is no longer able to accept any more requests. @@ -1503,11 +1788,11 @@ int rtn; /* * get next queueable request. We do this early to make sure - * that the request is fully prepared even if we cannot + * that the request is fully prepared even if we cannot * accept it. */ req = blk_peek_request(q); - if (!req || !scsi_dev_queue_ready(q, sdev)) + if (!req) break; if (unlikely(!scsi_device_online(sdev))) { @@ -1517,15 +1802,16 @@ continue; } + if (!scsi_dev_queue_ready(q, sdev)) + break; /* * Remove the request from the request list. */ if (!(blk_queue_tagged(q) && !blk_queue_start_tag(q, req))) blk_start_request(req); - sdev->device_busy++; - spin_unlock(q->queue_lock); + spin_unlock_irq(q->queue_lock); cmd = req->special; if (unlikely(cmd == NULL)) { printk(KERN_CRIT "impossible request in %s.\n" @@ -1535,7 +1821,6 @@ blk_dump_rq_flags(req, "foo"); BUG(); } - spin_lock(shost->host_lock); /* * We hit this when the driver is using a host wide @@ -1545,10 +1830,12 @@ * we add the dev to the starved list so it eventually gets * a run when a tag is freed. */ - if (blk_queue_tagged(q) && !blk_rq_tagged(req)) { + if (blk_queue_tagged(q) && !(req->cmd_flags & REQ_QUEUED)) { + spin_lock_irq(shost->host_lock); if (list_empty(&sdev->starved_entry)) list_add_tail(&sdev->starved_entry, &shost->starved_list); + spin_unlock_irq(shost->host_lock); goto not_ready; } @@ -1556,16 +1843,12 @@ goto not_ready; if (!scsi_host_queue_ready(q, shost, sdev)) - goto not_ready; - - scsi_target(sdev)->target_busy++; - shost->host_busy++; - - /* - * XXX(hch): This is rather suboptimal, scsi_dispatch_cmd will - * take the lock again. - */ - spin_unlock_irq(shost->host_lock); + goto host_not_ready; + + if (sdev->simple_tags) + cmd->flags |= SCMD_TAGGED; + else + cmd->flags &= ~SCMD_TAGGED; /* * Finally, initialize any error handling parameters, and set up @@ -1576,17 +1859,22 @@ /* * Dispatch the command to the low-level driver. */ + cmd->scsi_done = scsi_done; rtn = scsi_dispatch_cmd(cmd); - spin_lock_irq(q->queue_lock); - if (rtn) + if (rtn) { + scsi_queue_insert(cmd, rtn); + spin_lock_irq(q->queue_lock); goto out_delay; + } + spin_lock_irq(q->queue_lock); } - goto out; + return; + host_not_ready: + if (scsi_target(sdev)->can_queue > 0) + atomic_dec(&scsi_target(sdev)->target_busy); not_ready: - spin_unlock_irq(shost->host_lock); - /* * lock q, handle tag, requeue req, and decrement device_busy. We * must return with queue_lock held. @@ -1597,19 +1885,206 @@ */ spin_lock_irq(q->queue_lock); blk_requeue_request(q, req); - sdev->device_busy--; + atomic_dec(&sdev->device_busy); out_delay: - if (sdev->device_busy == 0) + if (!atomic_read(&sdev->device_busy) && !scsi_device_blocked(sdev)) blk_delay_queue(q, SCSI_QUEUE_DELAY); -out: - /* must be careful here...if we trigger the ->remove() function - * we cannot be holding the q lock */ - spin_unlock_irq(q->queue_lock); +} + +static inline int prep_to_mq(int ret) +{ + switch (ret) { + case BLKPREP_OK: + return 0; + case BLKPREP_DEFER: + return BLK_MQ_RQ_QUEUE_BUSY; + default: + return BLK_MQ_RQ_QUEUE_ERROR; + } +} + +static int scsi_mq_prep_fn(struct request *req) +{ + struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req); + struct scsi_device *sdev = req->q->queuedata; + struct Scsi_Host *shost = sdev->host; + unsigned char *sense_buf = cmd->sense_buffer; + struct scatterlist *sg; + + memset(cmd, 0, sizeof(struct scsi_cmnd)); + + req->special = cmd; + + cmd->request = req; + cmd->device = sdev; + cmd->sense_buffer = sense_buf; + + cmd->tag = req->tag; + + cmd->cmnd = req->cmd; + cmd->prot_op = SCSI_PROT_NORMAL; + + INIT_LIST_HEAD(&cmd->list); + INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler); + cmd->jiffies_at_alloc = jiffies; + + if (shost->use_cmd_list) { + spin_lock_irq(&sdev->list_lock); + list_add_tail(&cmd->list, &sdev->cmd_list); + spin_unlock_irq(&sdev->list_lock); + } + + sg = (void *)cmd + sizeof(struct scsi_cmnd) + shost->hostt->cmd_size; + cmd->sdb.table.sgl = sg; + + if (scsi_host_get_prot(shost)) { + cmd->prot_sdb = (void *)sg + + min_t(unsigned int, + shost->sg_tablesize, SCSI_MAX_SG_SEGMENTS) * + sizeof(struct scatterlist); + memset(cmd->prot_sdb, 0, sizeof(struct scsi_data_buffer)); + + cmd->prot_sdb->table.sgl = + (struct scatterlist *)(cmd->prot_sdb + 1); + } + + if (blk_bidi_rq(req)) { + struct request *next_rq = req->next_rq; + struct scsi_data_buffer *bidi_sdb = blk_mq_rq_to_pdu(next_rq); + + memset(bidi_sdb, 0, sizeof(struct scsi_data_buffer)); + bidi_sdb->table.sgl = + (struct scatterlist *)(bidi_sdb + 1); + + next_rq->special = bidi_sdb; + } + + blk_mq_start_request(req); + + return scsi_setup_cmnd(sdev, req); +} + +static void scsi_mq_done(struct scsi_cmnd *cmd) +{ + trace_scsi_dispatch_cmd_done(cmd); + blk_mq_complete_request(cmd->request, cmd->request->errors); +} + +static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + struct request *req = bd->rq; + struct request_queue *q = req->q; + struct scsi_device *sdev = q->queuedata; + struct Scsi_Host *shost = sdev->host; + struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req); + int ret; + int reason; + + ret = prep_to_mq(scsi_prep_state_check(sdev, req)); + if (ret) + goto out; + + ret = BLK_MQ_RQ_QUEUE_BUSY; + if (!get_device(&sdev->sdev_gendev)) + goto out; + + if (!scsi_dev_queue_ready(q, sdev)) + goto out_put_device; + if (!scsi_target_queue_ready(shost, sdev)) + goto out_dec_device_busy; + if (!scsi_host_queue_ready(q, shost, sdev)) + goto out_dec_target_busy; + + + if (!(req->cmd_flags & REQ_DONTPREP)) { + ret = prep_to_mq(scsi_mq_prep_fn(req)); + if (ret) + goto out_dec_host_busy; + req->cmd_flags |= REQ_DONTPREP; + } else { + blk_mq_start_request(req); + } + + if (sdev->simple_tags) + cmd->flags |= SCMD_TAGGED; + else + cmd->flags &= ~SCMD_TAGGED; + + scsi_init_cmd_errh(cmd); + cmd->scsi_done = scsi_mq_done; + + reason = scsi_dispatch_cmd(cmd); + if (reason) { + scsi_set_blocked(cmd, reason); + ret = BLK_MQ_RQ_QUEUE_BUSY; + goto out_dec_host_busy; + } + + return BLK_MQ_RQ_QUEUE_OK; + +out_dec_host_busy: + atomic_dec(&shost->host_busy); +out_dec_target_busy: + if (scsi_target(sdev)->can_queue > 0) + atomic_dec(&scsi_target(sdev)->target_busy); +out_dec_device_busy: + atomic_dec(&sdev->device_busy); +out_put_device: put_device(&sdev->sdev_gendev); - spin_lock_irq(q->queue_lock); +out: + switch (ret) { + case BLK_MQ_RQ_QUEUE_BUSY: + blk_mq_stop_hw_queue(hctx); + if (atomic_read(&sdev->device_busy) == 0 && + !scsi_device_blocked(sdev)) + blk_mq_delay_queue(hctx, SCSI_QUEUE_DELAY); + break; + case BLK_MQ_RQ_QUEUE_ERROR: + /* + * Make sure to release all allocated ressources when + * we hit an error, as we will never see this command + * again. + */ + if (req->cmd_flags & REQ_DONTPREP) + scsi_mq_uninit_cmd(cmd); + break; + default: + break; + } + return ret; +} + +static enum blk_eh_timer_return scsi_timeout(struct request *req, + bool reserved) +{ + if (reserved) + return BLK_EH_RESET_TIMER; + return scsi_times_out(req); +} + +static int scsi_init_request(void *data, struct request *rq, + unsigned int hctx_idx, unsigned int request_idx, + unsigned int numa_node) +{ + struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq); + + cmd->sense_buffer = kzalloc_node(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL, + numa_node); + if (!cmd->sense_buffer) + return -ENOMEM; + return 0; +} + +static void scsi_exit_request(void *data, struct request *rq, + unsigned int hctx_idx, unsigned int request_idx) +{ + struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq); + + kfree(cmd->sense_buffer); } -u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost) +static u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost) { struct device *host_dev; u64 bounce_limit = 0xffffffff; @@ -1625,22 +2100,15 @@ host_dev = scsi_get_device(shost); if (host_dev && host_dev->dma_mask) - bounce_limit = *host_dev->dma_mask; + bounce_limit = (u64)dma_max_pfn(host_dev) << PAGE_SHIFT; return bounce_limit; } -EXPORT_SYMBOL(scsi_calculate_bounce_limit); -struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, - request_fn_proc *request_fn) +static void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q) { - struct request_queue *q; struct device *dev = shost->dma_dev; - q = blk_init_queue(request_fn, NULL); - if (!q) - return NULL; - /* * this limit is imposed by hardware restrictions */ @@ -1671,7 +2139,17 @@ * blk_queue_update_dma_alignment() later. */ blk_queue_dma_alignment(q, 0x03); +} +struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, + request_fn_proc *request_fn) +{ + struct request_queue *q; + + q = blk_init_queue(request_fn, NULL); + if (!q) + return NULL; + __scsi_init_queue(shost, q); return q; } EXPORT_SYMBOL(__scsi_alloc_queue); @@ -1685,12 +2163,87 @@ return NULL; blk_queue_prep_rq(q, scsi_prep_fn); + blk_queue_unprep_rq(q, scsi_unprep_fn); blk_queue_softirq_done(q, scsi_softirq_done); blk_queue_rq_timed_out(q, scsi_times_out); blk_queue_lld_busy(q, scsi_lld_busy); return q; } +static struct blk_mq_ops scsi_mq_ops = { + .map_queue = blk_mq_map_queue, + .queue_rq = scsi_queue_rq, + .complete = scsi_softirq_done, + .timeout = scsi_timeout, + .init_request = scsi_init_request, + .exit_request = scsi_exit_request, +}; + +struct request_queue *scsi_mq_alloc_queue(struct scsi_device *sdev) +{ + sdev->request_queue = blk_mq_init_queue(&sdev->host->tag_set); + if (IS_ERR(sdev->request_queue)) + return NULL; + + sdev->request_queue->queuedata = sdev; + __scsi_init_queue(sdev->host, sdev->request_queue); + return sdev->request_queue; +} + +int scsi_mq_setup_tags(struct Scsi_Host *shost) +{ + unsigned int cmd_size, sgl_size, tbl_size; + + tbl_size = shost->sg_tablesize; + if (tbl_size > SCSI_MAX_SG_SEGMENTS) + tbl_size = SCSI_MAX_SG_SEGMENTS; + sgl_size = tbl_size * sizeof(struct scatterlist); + cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size + sgl_size; + if (scsi_host_get_prot(shost)) + cmd_size += sizeof(struct scsi_data_buffer) + sgl_size; + + memset(&shost->tag_set, 0, sizeof(shost->tag_set)); + shost->tag_set.ops = &scsi_mq_ops; + shost->tag_set.nr_hw_queues = shost->nr_hw_queues ? : 1; + shost->tag_set.queue_depth = shost->can_queue; + shost->tag_set.cmd_size = cmd_size; + shost->tag_set.numa_node = NUMA_NO_NODE; + shost->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE; + shost->tag_set.flags |= + BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy); + shost->tag_set.driver_data = shost; + + return blk_mq_alloc_tag_set(&shost->tag_set); +} + +void scsi_mq_destroy_tags(struct Scsi_Host *shost) +{ + blk_mq_free_tag_set(&shost->tag_set); +} + +/** + * scsi_device_from_queue - return sdev associated with a request_queue + * @q: The request queue to return the sdev from + * + * Return the sdev associated with a request queue or NULL if the + * request_queue does not reference a SCSI device. + */ +struct scsi_device *scsi_device_from_queue(struct request_queue *q) +{ + struct scsi_device *sdev = NULL; + + if (q->mq_ops) { + if (q->mq_ops == &scsi_mq_ops) + sdev = q->queuedata; + } else if (q->request_fn == scsi_request_fn) + sdev = q->queuedata; + if (!sdev || !get_device(&sdev->sdev_gendev)) + sdev = NULL; + + return sdev; +} +EXPORT_SYMBOL_GPL(scsi_device_from_queue); + /* * Function: scsi_block_requests() * @@ -1903,7 +2456,7 @@ unsigned char cmd[12]; int use_10_for_ms; int header_length; - int result; + int result, retry_count = retries; struct scsi_sense_hdr my_sshdr; memset(data, 0, sizeof(*data)); @@ -1982,6 +2535,11 @@ data->block_descriptor_length = buffer[3]; } data->header_length = header_length; + } else if ((status_byte(result) == CHECK_CONDITION) && + scsi_sense_valid(sshdr) && + sshdr->sense_key == UNIT_ATTENTION && retry_count) { + retry_count--; + goto retry; } return result; @@ -2134,6 +2692,7 @@ case SDEV_OFFLINE: case SDEV_TRANSPORT_OFFLINE: case SDEV_CANCEL: + case SDEV_CREATED_BLOCK: break; default: goto illegal; @@ -2145,9 +2704,9 @@ return 0; illegal: - SCSI_LOG_ERROR_RECOVERY(1, + SCSI_LOG_ERROR_RECOVERY(1, sdev_printk(KERN_ERR, sdev, - "Illegal state transition %s->%s\n", + "Illegal state transition %s->%s", scsi_device_state_name(oldstate), scsi_device_state_name(state)) ); @@ -2171,7 +2730,24 @@ case SDEV_EVT_MEDIA_CHANGE: envp[idx++] = "SDEV_MEDIA_CHANGE=1"; break; - + case SDEV_EVT_INQUIRY_CHANGE_REPORTED: + envp[idx++] = "SDEV_UA=INQUIRY_DATA_HAS_CHANGED"; + break; + case SDEV_EVT_CAPACITY_CHANGE_REPORTED: + envp[idx++] = "SDEV_UA=CAPACITY_DATA_HAS_CHANGED"; + break; + case SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED: + envp[idx++] = "SDEV_UA=THIN_PROVISIONING_SOFT_THRESHOLD_REACHED"; + break; + case SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED: + envp[idx++] = "SDEV_UA=MODE_PARAMETERS_CHANGED"; + break; + case SDEV_EVT_LUN_CHANGE_REPORTED: + envp[idx++] = "SDEV_UA=REPORTED_LUNS_DATA_HAS_CHANGED"; + break; + case SDEV_EVT_ALUA_STATE_CHANGE_REPORTED: + envp[idx++] = "SDEV_UA=ASYMMETRIC_ACCESS_STATE_CHANGED"; + break; default: /* do nothing */ break; @@ -2192,10 +2768,15 @@ void scsi_evt_thread(struct work_struct *work) { struct scsi_device *sdev; + enum scsi_device_event evt_type; LIST_HEAD(event_list); sdev = container_of(work, struct scsi_device, event_work); + for (evt_type = SDEV_EVT_FIRST; evt_type <= SDEV_EVT_LAST; evt_type++) + if (test_and_clear_bit(evt_type, sdev->pending_events)) + sdev_evt_send_simple(sdev, evt_type, GFP_KERNEL); + while (1) { struct scsi_event *evt; struct list_head *this, *tmp; @@ -2265,6 +2846,12 @@ /* evt_type-specific initialization, if any */ switch (evt_type) { case SDEV_EVT_MEDIA_CHANGE: + case SDEV_EVT_INQUIRY_CHANGE_REPORTED: + case SDEV_EVT_CAPACITY_CHANGE_REPORTED: + case SDEV_EVT_SOFT_THRESHOLD_REACHED_REPORTED: + case SDEV_EVT_MODE_PARAMETER_CHANGE_REPORTED: + case SDEV_EVT_LUN_CHANGE_REPORTED: + case SDEV_EVT_ALUA_STATE_CHANGE_REPORTED: default: /* do nothing */ break; @@ -2319,7 +2906,7 @@ return err; scsi_run_queue(sdev->request_queue); - while (sdev->device_busy) { + while (atomic_read(&sdev->device_busy)) { msleep_interruptible(200); scsi_run_queue(sdev->request_queue); } @@ -2411,9 +2998,13 @@ * block layer from calling the midlayer with this device's * request queue. */ - spin_lock_irqsave(q->queue_lock, flags); - blk_stop_queue(q); - spin_unlock_irqrestore(q->queue_lock, flags); + if (q->mq_ops) { + blk_mq_stop_hw_queues(q); + } else { + spin_lock_irqsave(q->queue_lock, flags); + blk_stop_queue(q); + spin_unlock_irqrestore(q->queue_lock, flags); + } return 0; } @@ -2459,9 +3050,13 @@ sdev->sdev_state != SDEV_OFFLINE) return -EINVAL; - spin_lock_irqsave(q->queue_lock, flags); - blk_start_queue(q); - spin_unlock_irqrestore(q->queue_lock, flags); + if (q->mq_ops) { + blk_mq_start_stopped_hw_queues(q, false); + } else { + spin_lock_irqsave(q->queue_lock, flags); + blk_start_queue(q); + spin_unlock_irqrestore(q->queue_lock, flags); + } return 0; }