diff options
Diffstat (limited to 'drivers/scsi/scsi_lib.c')
| -rw-r--r-- | drivers/scsi/scsi_lib.c | 935 |
1 files changed, 669 insertions, 266 deletions
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 3f50dfcb3227..9c44392b748f 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -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 +21,7 @@ #include <linux/delay.h> #include <linux/hardirq.h> #include <linux/scatterlist.h> +#include <linux/blk-mq.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> @@ -29,6 +31,8 @@ #include <scsi/scsi_eh.h> #include <scsi/scsi_host.h> +#include <trace/events/scsi.h> + #include "scsi_priv.h" #include "scsi_logging.h" @@ -75,28 +79,12 @@ struct kmem_cache *scsi_sdb_cache; */ #define SCSI_QUEUE_DELAY 3 -/** - * __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. @@ -113,16 +101,52 @@ static void __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, int unbusy) */ 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 @@ -138,6 +162,10 @@ static void __scsi_queue_insert(struct scsi_cmnd *cmd, int reason, int unbusy) * 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(&device->requeue_work); @@ -282,16 +310,26 @@ void scsi_device_unbusy(struct scsi_device *sdev) 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); } /* @@ -318,7 +356,7 @@ static void scsi_single_lun_run(struct scsi_device *current_sdev) * 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) @@ -331,7 +369,7 @@ static void scsi_single_lun_run(struct scsi_device *current_sdev) 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); @@ -340,28 +378,36 @@ static void scsi_single_lun_run(struct scsi_device *current_sdev) 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; } static void scsi_starved_list_run(struct Scsi_Host *shost) @@ -413,7 +459,7 @@ static void scsi_starved_list_run(struct Scsi_Host *shost) continue; spin_unlock_irqrestore(shost->host_lock, flags); - blk_run_queue(slq); + scsi_kick_queue(slq); blk_put_queue(slq); spin_lock_irqsave(shost->host_lock, flags); @@ -444,7 +490,10 @@ static void scsi_run_queue(struct request_queue *q) if (!list_empty(&sdev->host->starved_list)) scsi_starved_list_run(sdev->host); - blk_run_queue(q); + 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) @@ -542,25 +591,70 @@ static struct scatterlist *scsi_sg_alloc(unsigned int nents, gfp_t gfp_mask) return mempool_alloc(sgp->pool, gfp_mask); } +static void scsi_free_sgtable(struct scsi_data_buffer *sdb, bool mq) +{ + if (mq && sdb->table.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, - gfp_t gfp_mask) + gfp_t gfp_mask, bool mq) { + struct scatterlist *first_chunk = NULL; int ret; BUG_ON(!nents); + if (mq) { + if (nents <= SCSI_MAX_SG_SEGMENTS) { + sdb->table.nents = nents; + sg_init_table(sdb->table.sgl, sdb->table.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_mask, 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) +{ + 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_mq_free_sgtables(struct scsi_cmnd *cmd) { - __sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, scsi_sg_free); + if (cmd->sdb.table.nents) + 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); +} + +static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd) +{ + struct scsi_device *sdev = cmd->device; + unsigned long flags; + + BUG_ON(list_empty(&cmd->list)); + + scsi_mq_free_sgtables(cmd); + scsi_uninit_cmd(cmd); + + spin_lock_irqsave(&sdev->list_lock, flags); + list_del_init(&cmd->list); + spin_unlock_irqrestore(&sdev->list_lock, flags); } /* @@ -579,27 +673,79 @@ static void scsi_free_sgtable(struct scsi_data_buffer *sdb) * the __init_io() function. Primarily this would involve * the scatter-gather table. */ -void scsi_release_buffers(struct scsi_cmnd *cmd) +static void scsi_release_buffers(struct scsi_cmnd *cmd) { if (cmd->sdb.table.nents) - scsi_free_sgtable(&cmd->sdb); + 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); + scsi_free_sgtable(cmd->prot_sdb, false); } -EXPORT_SYMBOL(scsi_release_buffers); 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); + 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_io, + * 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_io(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); + + put_device(&sdev->sdev_gendev); + } else { + unsigned long flags; + + spin_lock_irqsave(q->queue_lock, flags); + blk_finish_request(req, error); + spin_unlock_irqrestore(q->queue_lock, flags); + + if (bidi_bytes) + scsi_release_bidi_buffers(cmd); + scsi_release_buffers(cmd); + scsi_next_command(cmd); + } + + return false; +} + /** * __scsi_error_from_host_byte - translate SCSI error code into errno * @cmd: SCSI command (unused) @@ -672,7 +818,7 @@ static int __scsi_error_from_host_byte(struct scsi_cmnd *cmd, int result) * 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) @@ -686,7 +832,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) int sense_deferred = 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) { @@ -724,13 +869,9 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) * both sides at once. */ req->next_rq->resid_len = scsi_in(cmd)->resid; - - scsi_release_buffers(cmd); - scsi_release_bidi_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) { @@ -750,9 +891,9 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) * 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 @@ -777,15 +918,16 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) /* * If we finished all bytes in the request we are done now. */ - if (!blk_end_request(req, error, good_bytes)) - goto next_command; + if (!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; } /* @@ -811,7 +953,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) * and quietly refuse further access. */ cmd->device->changed = 1; - description = "Media Changed"; action = ACTION_FAIL; } else { /* Must have been a power glitch, or a @@ -839,27 +980,10 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) 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 @@ -867,10 +991,8 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) 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 @@ -889,57 +1011,52 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) 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)) { + time_before(cmd->jiffies_at_alloc + wait_for, jiffies)) action = ACTION_FAIL; - description = "Command timed out"; - } 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); } - 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 */ @@ -950,11 +1067,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) __scsi_queue_insert(cmd, SCSI_MLQUEUE_DEVICE_BUSY, 0); break; } - return; - -next_command: - scsi_release_buffers(cmd); - scsi_next_command(cmd); } static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb, @@ -966,9 +1078,8 @@ static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb, * If sg table allocation fails, requeue request later. */ if (unlikely(scsi_alloc_sgtable(sdb, req->nr_phys_segments, - gfp_mask))) { + gfp_mask, req->mq_ctx != NULL))) return BLKPREP_DEFER; - } /* * Next, walk the list, and fill in the addresses and sizes of @@ -996,21 +1107,29 @@ int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask) { struct scsi_device *sdev = cmd->device; struct request *rq = cmd->request; + bool is_mq = (rq->mq_ctx != NULL); + int error; + + BUG_ON(!rq->nr_phys_segments); - int error = scsi_init_sgtable(rq, &cmd->sdb, gfp_mask); + error = scsi_init_sgtable(rq, &cmd->sdb, gfp_mask); 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, + GFP_ATOMIC); if (error) goto err_exit; } @@ -1022,7 +1141,7 @@ int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask) BUG_ON(prot_sdb == NULL); 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, gfp_mask, is_mq)) { error = BLKPREP_DEFER; goto err_exit; } @@ -1036,13 +1155,16 @@ int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask) 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); - put_device(&sdev->sdev_gendev); + 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); @@ -1077,7 +1199,7 @@ static struct scsi_cmnd *scsi_get_cmd_from_req(struct scsi_device *sdev, 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 = req->special; @@ -1088,11 +1210,7 @@ int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req) * submit a request without an attached bio. */ if (req->bio) { - int ret; - - BUG_ON(!req->nr_phys_segments); - - ret = scsi_init_io(cmd, GFP_ATOMIC); + int ret = scsi_init_io(cmd, GFP_ATOMIC); if (unlikely(ret)) return ret; } else { @@ -1102,25 +1220,16 @@ int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req) } 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 = req->special; @@ -1131,15 +1240,30 @@ int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req) return ret; } - /* - * Filesystem requests must transfer data. - */ - BUG_ON(!req->nr_phys_segments); - memset(cmd->cmnd, 0, BLK_MAX_CDB); - return scsi_init_io(cmd, GFP_ATOMIC); + return scsi_cmd_to_driver(cmd)->init_command(cmd); +} + +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; + } } -EXPORT_SYMBOL(scsi_setup_fs_cmnd); static int scsi_prep_state_check(struct scsi_device *sdev, struct request *req) @@ -1218,7 +1342,7 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret) * 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: @@ -1244,26 +1368,14 @@ static int scsi_prep_fn(struct request_queue *q, struct request *req) goto out; } - if (req->cmd_type == REQ_TYPE_FS) - ret = scsi_cmd_to_driver(cmd)->init_command(cmd); - else if (req->cmd_type == REQ_TYPE_BLOCK_PC) - ret = scsi_setup_blk_pc_cmnd(sdev, req); - else - ret = BLKPREP_KILL; - + ret = scsi_setup_cmnd(sdev, req); out: return scsi_prep_return(q, req, ret); } static void scsi_unprep_fn(struct request_queue *q, struct request *req) { - if (req->cmd_type == REQ_TYPE_FS) { - struct scsi_cmnd *cmd = req->special; - struct scsi_driver *drv = scsi_cmd_to_driver(cmd); - - if (drv->uninit_command) - drv->uninit_command(cmd); - } + scsi_uninit_cmd(req->special); } /* @@ -1275,99 +1387,144 @@ static void scsi_unprep_fn(struct request_queue *q, struct request *req) 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; } /* @@ -1430,13 +1587,10 @@ static void scsi_kill_request(struct request *req, struct request_queue *q) * 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); } @@ -1461,7 +1615,7 @@ static void scsi_softirq_done(struct request *rq) wait_for/HZ); disposition = SUCCESS; } - + scsi_log_completion(cmd, disposition); switch (disposition) { @@ -1480,6 +1634,23 @@ static void scsi_softirq_done(struct request *rq) } } +/** + * 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() * @@ -1509,11 +1680,11 @@ static void scsi_request_fn(struct request_queue *q) 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))) { @@ -1523,15 +1694,16 @@ static void scsi_request_fn(struct request_queue *q) 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" @@ -1541,7 +1713,6 @@ static void scsi_request_fn(struct request_queue *q) blk_dump_rq_flags(req, "foo"); BUG(); } - spin_lock(shost->host_lock); /* * We hit this when the driver is using a host wide @@ -1552,9 +1723,11 @@ static void scsi_request_fn(struct request_queue *q) * a run when a tag is freed. */ if (blk_queue_tagged(q) && !blk_rq_tagged(req)) { + 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; } @@ -1562,16 +1735,7 @@ static void scsi_request_fn(struct request_queue *q) 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; /* * Finally, initialize any error handling parameters, and set up @@ -1582,17 +1746,22 @@ static void scsi_request_fn(struct request_queue *q) /* * 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); } 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. @@ -1603,13 +1772,187 @@ static void scsi_request_fn(struct request_queue *q) */ 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); } -u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost) +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; + + req->cmd = req->__cmd; + 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; + + /* + * XXX: cmd_list lookups are only used by two drivers, try to get + * rid of this list in common code. + */ + 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 + + shost->sg_tablesize * 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; + } + + 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); +} + +static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req) +{ + 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; + } + + 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); +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 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); +} + +static u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost) { struct device *host_dev; u64 bounce_limit = 0xffffffff; @@ -1629,18 +1972,11 @@ u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost) 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 +2007,17 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, * 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); @@ -1692,6 +2038,55 @@ struct request_queue *scsi_alloc_queue(struct scsi_device *sdev) 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_times_out, + .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 = 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.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); +} + /* * Function: scsi_block_requests() * @@ -2147,9 +2542,9 @@ scsi_device_set_state(struct scsi_device *sdev, enum scsi_device_state state) 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)) ); @@ -2345,7 +2740,7 @@ scsi_device_quiesce(struct scsi_device *sdev) 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); } @@ -2437,9 +2832,13 @@ scsi_internal_device_block(struct scsi_device *sdev) * 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; } @@ -2485,9 +2884,13 @@ scsi_internal_device_unblock(struct scsi_device *sdev, 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; } |