X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=block%2Fcfq-iosched.c;h=a55a9bd75bd1baf616a3a1b7118acaeee328759f;hb=ddf59a35e98aa12255ed64c892271339504cc65c;hp=ca198e61fa65c555bf936d2d628876313b62dbb1;hpb=fe094d98e79351344c9e0e2c1446794240d247a4;p=safe%2Fjmp%2Flinux-2.6 diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index ca198e6..a55a9bd 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -11,6 +11,7 @@ #include #include #include +#include /* * tunables @@ -38,24 +39,23 @@ static int cfq_slice_idle = HZ / 125; #define CFQ_MIN_TT (2) #define CFQ_SLICE_SCALE (5) +#define CFQ_HW_QUEUE_MIN (5) #define RQ_CIC(rq) \ ((struct cfq_io_context *) (rq)->elevator_private) -#define RQ_CFQQ(rq) ((rq)->elevator_private2) +#define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elevator_private2) static struct kmem_cache *cfq_pool; static struct kmem_cache *cfq_ioc_pool; static DEFINE_PER_CPU(unsigned long, ioc_count); static struct completion *ioc_gone; +static DEFINE_SPINLOCK(ioc_gone_lock); #define CFQ_PRIO_LISTS IOPRIO_BE_NR #define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE) #define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT) -#define ASYNC (0) -#define SYNC (1) - #define sample_valid(samples) ((samples) > 80) /* @@ -80,11 +80,31 @@ struct cfq_data { * rr list of queues with requests and the count of them */ struct cfq_rb_root service_tree; + + /* + * Each priority tree is sorted by next_request position. These + * trees are used when determining if two or more queues are + * interleaving requests (see cfq_close_cooperator). + */ + struct rb_root prio_trees[CFQ_PRIO_LISTS]; + unsigned int busy_queues; + /* + * Used to track any pending rt requests so we can pre-empt current + * non-RT cfqq in service when this value is non-zero. + */ + unsigned int busy_rt_queues; int rq_in_driver; int sync_flight; + + /* + * queue-depth detection + */ + int rq_queued; int hw_tag; + int hw_tag_samples; + int rq_in_driver_peak; /* * idle window management @@ -124,12 +144,18 @@ struct cfq_data { struct cfq_queue { /* reference count */ atomic_t ref; + /* various state flags, see below */ + unsigned int flags; /* parent cfq_data */ struct cfq_data *cfqd; /* service_tree member */ struct rb_node rb_node; /* service_tree key */ unsigned long rb_key; + /* prio tree member */ + struct rb_node p_node; + /* prio tree root we belong to, if any */ + struct rb_root *p_root; /* sorted list of pending requests */ struct rb_root sort_list; /* if fifo isn't expired, next request to serve */ @@ -138,14 +164,15 @@ struct cfq_queue { int queued[2]; /* currently allocated requests */ int allocated[2]; - /* pending metadata requests */ - int meta_pending; /* fifo list of requests in sort_list */ struct list_head fifo; unsigned long slice_end; long slice_resid; + unsigned int slice_dispatch; + /* pending metadata requests */ + int meta_pending; /* number of requests that are on the dispatch list or inside driver */ int dispatched; @@ -153,22 +180,21 @@ struct cfq_queue { unsigned short ioprio, org_ioprio; unsigned short ioprio_class, org_ioprio_class; - /* various state flags, see below */ - unsigned int flags; + pid_t pid; }; enum cfqq_state_flags { CFQ_CFQQ_FLAG_on_rr = 0, /* on round-robin busy list */ CFQ_CFQQ_FLAG_wait_request, /* waiting for a request */ + CFQ_CFQQ_FLAG_must_dispatch, /* must be allowed a dispatch */ CFQ_CFQQ_FLAG_must_alloc, /* must be allowed rq alloc */ CFQ_CFQQ_FLAG_must_alloc_slice, /* per-slice must_alloc flag */ - CFQ_CFQQ_FLAG_must_dispatch, /* must dispatch, even if expired */ CFQ_CFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */ CFQ_CFQQ_FLAG_idle_window, /* slice idling enabled */ CFQ_CFQQ_FLAG_prio_changed, /* task priority has changed */ - CFQ_CFQQ_FLAG_queue_new, /* queue never been serviced */ CFQ_CFQQ_FLAG_slice_new, /* no requests dispatched in slice */ CFQ_CFQQ_FLAG_sync, /* synchronous queue */ + CFQ_CFQQ_FLAG_coop, /* has done a coop jump of the queue */ }; #define CFQ_CFQQ_FNS(name) \ @@ -187,17 +213,22 @@ static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq) \ CFQ_CFQQ_FNS(on_rr); CFQ_CFQQ_FNS(wait_request); +CFQ_CFQQ_FNS(must_dispatch); CFQ_CFQQ_FNS(must_alloc); CFQ_CFQQ_FNS(must_alloc_slice); -CFQ_CFQQ_FNS(must_dispatch); CFQ_CFQQ_FNS(fifo_expire); CFQ_CFQQ_FNS(idle_window); CFQ_CFQQ_FNS(prio_changed); -CFQ_CFQQ_FNS(queue_new); CFQ_CFQQ_FNS(slice_new); CFQ_CFQQ_FNS(sync); +CFQ_CFQQ_FNS(coop); #undef CFQ_CFQQ_FNS +#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \ + blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args) +#define cfq_log(cfqd, fmt, args...) \ + blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args) + static void cfq_dispatch_insert(struct request_queue *, struct request *); static struct cfq_queue *cfq_get_queue(struct cfq_data *, int, struct io_context *, gfp_t); @@ -234,8 +265,10 @@ static inline int cfq_bio_sync(struct bio *bio) */ static inline void cfq_schedule_dispatch(struct cfq_data *cfqd) { - if (cfqd->busy_queues) - kblockd_schedule_work(&cfqd->unplug_work); + if (cfqd->busy_queues) { + cfq_log(cfqd, "schedule dispatch"); + kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work); + } } static int cfq_queue_empty(struct request_queue *q) @@ -270,6 +303,7 @@ static inline void cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq) { cfqq->slice_end = cfq_prio_to_slice(cfqd, cfqq) + jiffies; + cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies); } /* @@ -396,13 +430,17 @@ static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root) return NULL; } +static void rb_erase_init(struct rb_node *n, struct rb_root *root) +{ + rb_erase(n, root); + RB_CLEAR_NODE(n); +} + static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root) { if (root->left == n) root->left = NULL; - - rb_erase(n, &root->rb); - RB_CLEAR_NODE(n); + rb_erase_init(n, &root->rb); } /* @@ -447,8 +485,8 @@ static unsigned long cfq_slice_offset(struct cfq_data *cfqd, * requests waiting to be processed. It is sorted in the order that * we will service the queues. */ -static void cfq_service_tree_add(struct cfq_data *cfqd, - struct cfq_queue *cfqq, int add_front) +static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq, + int add_front) { struct rb_node **p, *parent; struct cfq_queue *__cfqq; @@ -521,6 +559,67 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, rb_insert_color(&cfqq->rb_node, &cfqd->service_tree.rb); } +static struct cfq_queue * +cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root, + sector_t sector, struct rb_node **ret_parent, + struct rb_node ***rb_link) +{ + struct rb_node **p, *parent; + struct cfq_queue *cfqq = NULL; + + parent = NULL; + p = &root->rb_node; + while (*p) { + struct rb_node **n; + + parent = *p; + cfqq = rb_entry(parent, struct cfq_queue, p_node); + + /* + * Sort strictly based on sector. Smallest to the left, + * largest to the right. + */ + if (sector > cfqq->next_rq->sector) + n = &(*p)->rb_right; + else if (sector < cfqq->next_rq->sector) + n = &(*p)->rb_left; + else + break; + p = n; + cfqq = NULL; + } + + *ret_parent = parent; + if (rb_link) + *rb_link = p; + return cfqq; +} + +static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + struct rb_node **p, *parent; + struct cfq_queue *__cfqq; + + if (cfqq->p_root) { + rb_erase(&cfqq->p_node, cfqq->p_root); + cfqq->p_root = NULL; + } + + if (cfq_class_idle(cfqq)) + return; + if (!cfqq->next_rq) + return; + + cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio]; + __cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root, cfqq->next_rq->sector, + &parent, &p); + if (!__cfqq) { + rb_link_node(&cfqq->p_node, parent, p); + rb_insert_color(&cfqq->p_node, cfqq->p_root); + } else + cfqq->p_root = NULL; +} + /* * Update cfqq's position in the service tree. */ @@ -529,8 +628,10 @@ static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq) /* * Resorting requires the cfqq to be on the RR list already. */ - if (cfq_cfqq_on_rr(cfqq)) + if (cfq_cfqq_on_rr(cfqq)) { cfq_service_tree_add(cfqd, cfqq, 0); + cfq_prio_tree_add(cfqd, cfqq); + } } /* @@ -539,9 +640,12 @@ static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq) */ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq) { + cfq_log_cfqq(cfqd, cfqq, "add_to_rr"); BUG_ON(cfq_cfqq_on_rr(cfqq)); cfq_mark_cfqq_on_rr(cfqq); cfqd->busy_queues++; + if (cfq_class_rt(cfqq)) + cfqd->busy_rt_queues++; cfq_resort_rr_list(cfqd, cfqq); } @@ -552,14 +656,21 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq) */ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq) { + cfq_log_cfqq(cfqd, cfqq, "del_from_rr"); BUG_ON(!cfq_cfqq_on_rr(cfqq)); cfq_clear_cfqq_on_rr(cfqq); if (!RB_EMPTY_NODE(&cfqq->rb_node)) cfq_rb_erase(&cfqq->rb_node, &cfqd->service_tree); + if (cfqq->p_root) { + rb_erase(&cfqq->p_node, cfqq->p_root); + cfqq->p_root = NULL; + } BUG_ON(!cfqd->busy_queues); cfqd->busy_queues--; + if (cfq_class_rt(cfqq)) + cfqd->busy_rt_queues--; } /* @@ -584,7 +695,7 @@ static void cfq_add_rq_rb(struct request *rq) { struct cfq_queue *cfqq = RQ_CFQQ(rq); struct cfq_data *cfqd = cfqq->cfqd; - struct request *__alias; + struct request *__alias, *prev; cfqq->queued[rq_is_sync(rq)]++; @@ -601,7 +712,15 @@ static void cfq_add_rq_rb(struct request *rq) /* * check if this request is a better next-serve candidate */ + prev = cfqq->next_rq; cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq); + + /* + * adjust priority tree position, if ->next_rq changes + */ + if (prev != cfqq->next_rq) + cfq_prio_tree_add(cfqd, cfqq); + BUG_ON(!cfqq->next_rq); } @@ -638,15 +757,8 @@ static void cfq_activate_request(struct request_queue *q, struct request *rq) struct cfq_data *cfqd = q->elevator->elevator_data; cfqd->rq_in_driver++; - - /* - * If the depth is larger 1, it really could be queueing. But lets - * make the mark a little higher - idling could still be good for - * low queueing, and a low queueing number could also just indicate - * a SCSI mid layer like behaviour where limit+1 is often seen. - */ - if (!cfqd->hw_tag && cfqd->rq_in_driver > 4) - cfqd->hw_tag = 1; + cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d", + cfqd->rq_in_driver); cfqd->last_position = rq->hard_sector + rq->hard_nr_sectors; } @@ -657,6 +769,8 @@ static void cfq_deactivate_request(struct request_queue *q, struct request *rq) WARN_ON(!cfqd->rq_in_driver); cfqd->rq_in_driver--; + cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d", + cfqd->rq_in_driver); } static void cfq_remove_request(struct request *rq) @@ -669,6 +783,7 @@ static void cfq_remove_request(struct request *rq) list_del_init(&rq->queuelist); cfq_del_rq_rb(rq); + cfqq->cfqd->rq_queued--; if (rq_is_meta(rq)) { WARN_ON(!cfqq->meta_pending); cfqq->meta_pending--; @@ -746,11 +861,17 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq) { if (cfqq) { + cfq_log_cfqq(cfqd, cfqq, "set_active"); cfqq->slice_end = 0; + cfqq->slice_dispatch = 0; + + cfq_clear_cfqq_wait_request(cfqq); + cfq_clear_cfqq_must_dispatch(cfqq); cfq_clear_cfqq_must_alloc_slice(cfqq); cfq_clear_cfqq_fifo_expire(cfqq); cfq_mark_cfqq_slice_new(cfqq); - cfq_clear_cfqq_queue_new(cfqq); + + del_timer(&cfqd->idle_slice_timer); } cfqd->active_queue = cfqq; @@ -763,17 +884,20 @@ static void __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq, int timed_out) { + cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out); + if (cfq_cfqq_wait_request(cfqq)) del_timer(&cfqd->idle_slice_timer); - cfq_clear_cfqq_must_dispatch(cfqq); cfq_clear_cfqq_wait_request(cfqq); /* * store what was left of this slice, if the queue idled/timed out */ - if (timed_out && !cfq_cfqq_slice_new(cfqq)) + if (timed_out && !cfq_cfqq_slice_new(cfqq)) { cfqq->slice_resid = cfqq->slice_end - jiffies; + cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid); + } cfq_resort_rr_list(cfqd, cfqq); @@ -809,11 +933,15 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd) /* * Get and set a new active queue for service. */ -static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd) +static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd, + struct cfq_queue *cfqq) { - struct cfq_queue *cfqq; + if (!cfqq) { + cfqq = cfq_get_next_queue(cfqd); + if (cfqq) + cfq_clear_cfqq_coop(cfqq); + } - cfqq = cfq_get_next_queue(cfqd); __cfq_set_active_queue(cfqd, cfqq); return cfqq; } @@ -827,28 +955,100 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd, return cfqd->last_position - rq->sector; } +#define CIC_SEEK_THR 8 * 1024 +#define CIC_SEEKY(cic) ((cic)->seek_mean > CIC_SEEK_THR) + static inline int cfq_rq_close(struct cfq_data *cfqd, struct request *rq) { struct cfq_io_context *cic = cfqd->active_cic; + sector_t sdist = cic->seek_mean; if (!sample_valid(cic->seek_samples)) - return 0; + sdist = CIC_SEEK_THR; - return cfq_dist_from_last(cfqd, rq) <= cic->seek_mean; + return cfq_dist_from_last(cfqd, rq) <= sdist; } -static int cfq_close_cooperator(struct cfq_data *cfq_data, - struct cfq_queue *cfqq) +static struct cfq_queue *cfqq_close(struct cfq_data *cfqd, + struct cfq_queue *cur_cfqq) { + struct rb_root *root = &cfqd->prio_trees[cur_cfqq->org_ioprio]; + struct rb_node *parent, *node; + struct cfq_queue *__cfqq; + sector_t sector = cfqd->last_position; + + if (RB_EMPTY_ROOT(root)) + return NULL; + + /* + * First, if we find a request starting at the end of the last + * request, choose it. + */ + __cfqq = cfq_prio_tree_lookup(cfqd, root, sector, &parent, NULL); + if (__cfqq) + return __cfqq; + + /* + * If the exact sector wasn't found, the parent of the NULL leaf + * will contain the closest sector. + */ + __cfqq = rb_entry(parent, struct cfq_queue, p_node); + if (cfq_rq_close(cfqd, __cfqq->next_rq)) + return __cfqq; + + if (__cfqq->next_rq->sector < sector) + node = rb_next(&__cfqq->p_node); + else + node = rb_prev(&__cfqq->p_node); + if (!node) + return NULL; + + __cfqq = rb_entry(node, struct cfq_queue, p_node); + if (cfq_rq_close(cfqd, __cfqq->next_rq)) + return __cfqq; + + return NULL; +} + +/* + * cfqd - obvious + * cur_cfqq - passed in so that we don't decide that the current queue is + * closely cooperating with itself. + * + * So, basically we're assuming that that cur_cfqq has dispatched at least + * one request, and that cfqd->last_position reflects a position on the disk + * associated with the I/O issued by cur_cfqq. I'm not sure this is a valid + * assumption. + */ +static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd, + struct cfq_queue *cur_cfqq, + int probe) +{ + struct cfq_queue *cfqq; + + /* + * A valid cfq_io_context is necessary to compare requests against + * the seek_mean of the current cfqq. + */ + if (!cfqd->active_cic) + return NULL; + /* * We should notice if some of the queues are cooperating, eg * working closely on the same area of the disk. In that case, * we can group them together and don't waste time idling. */ - return 0; -} + cfqq = cfqq_close(cfqd, cur_cfqq); + if (!cfqq) + return NULL; + + if (cfq_cfqq_coop(cfqq)) + return NULL; -#define CIC_SEEKY(cic) ((cic)->seek_mean > (8 * 1024)) + if (!probe) + cfq_mark_cfqq_coop(cfqq); + return cfqq; +} static void cfq_arm_slice_timer(struct cfq_data *cfqd) { @@ -856,6 +1056,14 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) struct cfq_io_context *cic; unsigned long sl; + /* + * SSD device without seek penalty, disable idling. But only do so + * for devices that support queuing, otherwise we still have a problem + * with sync vs async workloads. + */ + if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag) + return; + WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list)); WARN_ON(cfq_cfqq_slice_new(cfqq)); @@ -866,20 +1074,18 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) return; /* - * task has exited, don't wait + * still requests with the driver, don't idle */ - cic = cfqd->active_cic; - if (!cic || !atomic_read(&cic->ioc->nr_tasks)) + if (cfqd->rq_in_driver) return; /* - * See if this prio level has a good candidate + * task has exited, don't wait */ - if (cfq_close_cooperator(cfqd, cfqq) && - (sample_valid(cic->ttime_samples) && cic->ttime_mean > 2)) + cic = cfqd->active_cic; + if (!cic || !atomic_read(&cic->ioc->nr_tasks)) return; - cfq_mark_cfqq_must_dispatch(cfqq); cfq_mark_cfqq_wait_request(cfqq); /* @@ -892,6 +1098,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) sl = min(sl, msecs_to_jiffies(CFQ_MIN_TT)); mod_timer(&cfqd->idle_slice_timer, jiffies + sl); + cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl); } /* @@ -902,6 +1109,8 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq) struct cfq_data *cfqd = q->elevator->elevator_data; struct cfq_queue *cfqq = RQ_CFQQ(rq); + cfq_log_cfqq(cfqd, cfqq, "dispatch_insert"); + cfq_remove_request(rq); cfqq->dispatched++; elv_dispatch_sort(q, rq); @@ -931,8 +1140,9 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq) rq = rq_entry_fifo(cfqq->fifo.next); if (time_before(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo])) - return NULL; + rq = NULL; + cfq_log_cfqq(cfqd, cfqq, "fifo=%p", rq); return rq; } @@ -952,7 +1162,7 @@ cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq) */ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) { - struct cfq_queue *cfqq; + struct cfq_queue *cfqq, *new_cfqq = NULL; cfqq = cfqd->active_queue; if (!cfqq) @@ -961,10 +1171,24 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) /* * The active queue has run out of time, expire it and select new. */ - if (cfq_slice_used(cfqq)) + if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) goto expire; /* + * If we have a RT cfqq waiting, then we pre-empt the current non-rt + * cfqq. + */ + if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues) { + /* + * We simulate this as cfqq timed out so that it gets to bank + * the remaining of its time slice. + */ + cfq_log_cfqq(cfqd, cfqq, "preempt"); + cfq_slice_expired(cfqd, 1); + goto new_queue; + } + + /* * The active queue has requests and isn't expired, allow it to * dispatch. */ @@ -972,6 +1196,16 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) goto keep_queue; /* + * If another queue has a request waiting within our mean seek + * distance, let it run. The expire code will check for close + * cooperators and put the close queue at the front of the service + * tree. + */ + new_cfqq = cfq_close_cooperator(cfqd, cfqq, 0); + if (new_cfqq) + goto expire; + + /* * No requests pending. If the active queue still has requests in * flight or is idling for a new request, allow either of these * conditions to happen (or time out) before selecting a new queue. @@ -985,64 +1219,11 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) expire: cfq_slice_expired(cfqd, 0); new_queue: - cfqq = cfq_set_active_queue(cfqd); + cfqq = cfq_set_active_queue(cfqd, new_cfqq); keep_queue: return cfqq; } -/* - * Dispatch some requests from cfqq, moving them to the request queue - * dispatch list. - */ -static int -__cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq, - int max_dispatch) -{ - int dispatched = 0; - - BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list)); - - do { - struct request *rq; - - /* - * follow expired path, else get first next available - */ - rq = cfq_check_fifo(cfqq); - if (rq == NULL) - rq = cfqq->next_rq; - - /* - * finally, insert request into driver dispatch list - */ - cfq_dispatch_insert(cfqd->queue, rq); - - dispatched++; - - if (!cfqd->active_cic) { - atomic_inc(&RQ_CIC(rq)->ioc->refcount); - cfqd->active_cic = RQ_CIC(rq); - } - - if (RB_EMPTY_ROOT(&cfqq->sort_list)) - break; - - } while (dispatched < max_dispatch); - - /* - * expire an async queue immediately if it has used up its slice. idle - * queue always expire after 1 dispatch round. - */ - if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) && - dispatched >= cfq_prio_to_maxrq(cfqd, cfqq)) || - cfq_class_idle(cfqq))) { - cfqq->slice_end = jiffies + 1; - cfq_slice_expired(cfqd, 0); - } - - return dispatched; -} - static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq) { int dispatched = 0; @@ -1072,14 +1253,49 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd) BUG_ON(cfqd->busy_queues); + cfq_log(cfqd, "forced_dispatch=%d\n", dispatched); return dispatched; } +/* + * Dispatch a request from cfqq, moving them to the request queue + * dispatch list. + */ +static void cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq) +{ + struct request *rq; + + BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list)); + + /* + * follow expired path, else get first next available + */ + rq = cfq_check_fifo(cfqq); + if (!rq) + rq = cfqq->next_rq; + + /* + * insert request into driver dispatch list + */ + cfq_dispatch_insert(cfqd->queue, rq); + + if (!cfqd->active_cic) { + struct cfq_io_context *cic = RQ_CIC(rq); + + atomic_inc(&cic->ioc->refcount); + cfqd->active_cic = cic; + } +} + +/* + * Find the cfqq that we need to service and move a request from that to the + * dispatch list + */ static int cfq_dispatch_requests(struct request_queue *q, int force) { struct cfq_data *cfqd = q->elevator->elevator_data; struct cfq_queue *cfqq; - int dispatched; + unsigned int max_dispatch; if (!cfqd->busy_queues) return 0; @@ -1087,32 +1303,63 @@ static int cfq_dispatch_requests(struct request_queue *q, int force) if (unlikely(force)) return cfq_forced_dispatch(cfqd); - dispatched = 0; - while ((cfqq = cfq_select_queue(cfqd)) != NULL) { - int max_dispatch; + cfqq = cfq_select_queue(cfqd); + if (!cfqq) + return 0; + + /* + * If this is an async queue and we have sync IO in flight, let it wait + */ + if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq)) + return 0; - max_dispatch = cfqd->cfq_quantum; + max_dispatch = cfqd->cfq_quantum; + if (cfq_class_idle(cfqq)) + max_dispatch = 1; + + /* + * Does this cfqq already have too much IO in flight? + */ + if (cfqq->dispatched >= max_dispatch) { + /* + * idle queue must always only have a single IO in flight + */ if (cfq_class_idle(cfqq)) - max_dispatch = 1; + return 0; - if (cfqq->dispatched >= max_dispatch) { - if (cfqd->busy_queues > 1) - break; - if (cfqq->dispatched >= 4 * max_dispatch) - break; - } + /* + * We have other queues, don't allow more IO from this one + */ + if (cfqd->busy_queues > 1) + return 0; - if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq)) - break; + /* + * we are the only queue, allow up to 4 times of 'quantum' + */ + if (cfqq->dispatched >= 4 * max_dispatch) + return 0; + } - cfq_clear_cfqq_must_dispatch(cfqq); - cfq_clear_cfqq_wait_request(cfqq); - del_timer(&cfqd->idle_slice_timer); + /* + * Dispatch a request from this cfqq + */ + cfq_dispatch_request(cfqd, cfqq); + cfqq->slice_dispatch++; + cfq_clear_cfqq_must_dispatch(cfqq); - dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch); + /* + * expire an async queue immediately if it has used up its slice. idle + * queue always expire after 1 dispatch round. + */ + if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) && + cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) || + cfq_class_idle(cfqq))) { + cfqq->slice_end = jiffies + 1; + cfq_slice_expired(cfqd, 0); } - return dispatched; + cfq_log(cfqd, "dispatched a request"); + return 1; } /* @@ -1130,6 +1377,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq) if (!atomic_dec_and_test(&cfqq->ref)) return; + cfq_log_cfqq(cfqd, cfqq, "put_queue"); BUG_ON(rb_first(&cfqq->sort_list)); BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]); BUG_ON(cfq_cfqq_on_rr(cfqq)); @@ -1143,43 +1391,58 @@ static void cfq_put_queue(struct cfq_queue *cfqq) } /* - * Call func for each cic attached to this ioc. Returns number of cic's seen. + * Must always be called with the rcu_read_lock() held */ -#define CIC_GANG_NR 16 -static unsigned int +static void +__call_for_each_cic(struct io_context *ioc, + void (*func)(struct io_context *, struct cfq_io_context *)) +{ + struct cfq_io_context *cic; + struct hlist_node *n; + + hlist_for_each_entry_rcu(cic, n, &ioc->cic_list, cic_list) + func(ioc, cic); +} + +/* + * Call func for each cic attached to this ioc. + */ +static void call_for_each_cic(struct io_context *ioc, void (*func)(struct io_context *, struct cfq_io_context *)) { - struct cfq_io_context *cics[CIC_GANG_NR]; - unsigned long index = 0; - unsigned int called = 0; - int nr; - rcu_read_lock(); + __call_for_each_cic(ioc, func); + rcu_read_unlock(); +} - do { - int i; - - /* - * Perhaps there's a better way - this just gang lookups from - * 0 to the end, restarting after each CIC_GANG_NR from the - * last key + 1. - */ - nr = radix_tree_gang_lookup(&ioc->radix_root, (void **) cics, - index, CIC_GANG_NR); - if (!nr) - break; +static void cfq_cic_free_rcu(struct rcu_head *head) +{ + struct cfq_io_context *cic; - called += nr; - index = 1 + (unsigned long) cics[nr - 1]->key; + cic = container_of(head, struct cfq_io_context, rcu_head); - for (i = 0; i < nr; i++) - func(ioc, cics[i]); - } while (nr == CIC_GANG_NR); + kmem_cache_free(cfq_ioc_pool, cic); + elv_ioc_count_dec(ioc_count); - rcu_read_unlock(); + if (ioc_gone) { + /* + * CFQ scheduler is exiting, grab exit lock and check + * the pending io context count. If it hits zero, + * complete ioc_gone and set it back to NULL + */ + spin_lock(&ioc_gone_lock); + if (ioc_gone && !elv_ioc_count_read(ioc_count)) { + complete(ioc_gone); + ioc_gone = NULL; + } + spin_unlock(&ioc_gone_lock); + } +} - return called; +static void cfq_cic_free(struct cfq_io_context *cic) +{ + call_rcu(&cic->rcu_head, cfq_cic_free_rcu); } static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic) @@ -1190,26 +1453,26 @@ static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic) spin_lock_irqsave(&ioc->lock, flags); radix_tree_delete(&ioc->radix_root, cic->dead_key); + hlist_del_rcu(&cic->cic_list); spin_unlock_irqrestore(&ioc->lock, flags); - kmem_cache_free(cfq_ioc_pool, cic); + cfq_cic_free(cic); } +/* + * Must be called with rcu_read_lock() held or preemption otherwise disabled. + * Only two callers of this - ->dtor() which is called with the rcu_read_lock(), + * and ->trim() which is called with the task lock held + */ static void cfq_free_io_context(struct io_context *ioc) { - int freed; - /* - * ioc->refcount is zero here, so no more cic's are allowed to be - * linked into this ioc. So it should be ok to iterate over the known - * list, we will see all cic's since no new ones are added. + * ioc->refcount is zero here, or we are called from elv_unregister(), + * so no more cic's are allowed to be linked into this ioc. So it + * should be ok to iterate over the known list, we will see all cic's + * since no new ones are added. */ - freed = call_for_each_cic(ioc, cic_free_func); - - elv_ioc_count_mod(ioc_count, -freed); - - if (ioc_gone && !elv_ioc_count_read(ioc_count)) - complete(ioc_gone); + __call_for_each_cic(ioc, cic_free_func); } static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) @@ -1225,6 +1488,8 @@ static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq) static void __cfq_exit_single_io_context(struct cfq_data *cfqd, struct cfq_io_context *cic) { + struct io_context *ioc = cic->ioc; + list_del_init(&cic->queue_list); /* @@ -1234,14 +1499,17 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd, cic->dead_key = (unsigned long) cic->key; cic->key = NULL; - if (cic->cfqq[ASYNC]) { - cfq_exit_cfqq(cfqd, cic->cfqq[ASYNC]); - cic->cfqq[ASYNC] = NULL; + if (ioc->ioc_data == cic) + rcu_assign_pointer(ioc->ioc_data, NULL); + + if (cic->cfqq[BLK_RW_ASYNC]) { + cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]); + cic->cfqq[BLK_RW_ASYNC] = NULL; } - if (cic->cfqq[SYNC]) { - cfq_exit_cfqq(cfqd, cic->cfqq[SYNC]); - cic->cfqq[SYNC] = NULL; + if (cic->cfqq[BLK_RW_SYNC]) { + cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_SYNC]); + cic->cfqq[BLK_RW_SYNC] = NULL; } } @@ -1255,7 +1523,15 @@ static void cfq_exit_single_io_context(struct io_context *ioc, unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); - __cfq_exit_single_io_context(cfqd, cic); + + /* + * Ensure we get a fresh copy of the ->key to prevent + * race between exiting task and queue + */ + smp_read_barrier_depends(); + if (cic->key) + __cfq_exit_single_io_context(cfqd, cic); + spin_unlock_irqrestore(q->queue_lock, flags); } } @@ -1266,7 +1542,6 @@ static void cfq_exit_single_io_context(struct io_context *ioc, */ static void cfq_exit_io_context(struct io_context *ioc) { - rcu_assign_pointer(ioc->ioc_data, NULL); call_for_each_cic(ioc, cfq_exit_single_io_context); } @@ -1280,6 +1555,7 @@ cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask) if (cic) { cic->last_end_request = jiffies; INIT_LIST_HEAD(&cic->queue_list); + INIT_HLIST_NODE(&cic->cic_list); cic->dtor = cfq_free_io_context; cic->exit = cfq_exit_io_context; elv_ioc_count_inc(ioc_count); @@ -1302,10 +1578,10 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc) printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class); case IOPRIO_CLASS_NONE: /* - * no prio set, place us in the middle of the BE classes + * no prio set, inherit CPU scheduling settings */ cfqq->ioprio = task_nice_ioprio(tsk); - cfqq->ioprio_class = IOPRIO_CLASS_BE; + cfqq->ioprio_class = task_nice_ioclass(tsk); break; case IOPRIO_CLASS_RT: cfqq->ioprio = task_ioprio(ioc); @@ -1342,17 +1618,18 @@ static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic) spin_lock_irqsave(cfqd->queue->queue_lock, flags); - cfqq = cic->cfqq[ASYNC]; + cfqq = cic->cfqq[BLK_RW_ASYNC]; if (cfqq) { struct cfq_queue *new_cfqq; - new_cfqq = cfq_get_queue(cfqd, ASYNC, cic->ioc, GFP_ATOMIC); + new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic->ioc, + GFP_ATOMIC); if (new_cfqq) { - cic->cfqq[ASYNC] = new_cfqq; + cic->cfqq[BLK_RW_ASYNC] = new_cfqq; cfq_put_queue(cfqq); } } - cfqq = cic->cfqq[SYNC]; + cfqq = cic->cfqq[BLK_RW_SYNC]; if (cfqq) cfq_mark_cfqq_prio_changed(cfqq); @@ -1403,13 +1680,13 @@ retry: } RB_CLEAR_NODE(&cfqq->rb_node); + RB_CLEAR_NODE(&cfqq->p_node); INIT_LIST_HEAD(&cfqq->fifo); atomic_set(&cfqq->ref, 0); cfqq->cfqd = cfqd; cfq_mark_cfqq_prio_changed(cfqq); - cfq_mark_cfqq_queue_new(cfqq); cfq_init_prio_data(cfqq, ioc); @@ -1418,6 +1695,8 @@ retry: cfq_mark_cfqq_idle_window(cfqq); cfq_mark_cfqq_sync(cfqq); } + cfqq->pid = current->pid; + cfq_log_cfqq(cfqd, cfqq, "alloced"); } if (new_cfqq) @@ -1475,15 +1754,6 @@ cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct io_context *ioc, return cfqq; } -static void cfq_cic_free(struct cfq_io_context *cic) -{ - kmem_cache_free(cfq_ioc_pool, cic); - elv_ioc_count_dec(ioc_count); - - if (ioc_gone && !elv_ioc_count_read(ioc_count)) - complete(ioc_gone); -} - /* * We drop cfq io contexts lazily, so we may find a dead one. */ @@ -1497,10 +1767,10 @@ cfq_drop_dead_cic(struct cfq_data *cfqd, struct io_context *ioc, spin_lock_irqsave(&ioc->lock, flags); - if (ioc->ioc_data == cic) - rcu_assign_pointer(ioc->ioc_data, NULL); + BUG_ON(ioc->ioc_data == cic); radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd); + hlist_del_rcu(&cic->cic_list); spin_unlock_irqrestore(&ioc->lock, flags); cfq_cic_free(cic); @@ -1510,20 +1780,24 @@ static struct cfq_io_context * cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc) { struct cfq_io_context *cic; + unsigned long flags; void *k; if (unlikely(!ioc)) return NULL; + rcu_read_lock(); + /* * we maintain a last-hit cache, to avoid browsing over the tree */ cic = rcu_dereference(ioc->ioc_data); - if (cic && cic->key == cfqd) + if (cic && cic->key == cfqd) { + rcu_read_unlock(); return cic; + } do { - rcu_read_lock(); cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd); rcu_read_unlock(); if (!cic) @@ -1532,10 +1806,13 @@ cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc) k = cic->key; if (unlikely(!k)) { cfq_drop_dead_cic(cfqd, ioc, cic); + rcu_read_lock(); continue; } + spin_lock_irqsave(&ioc->lock, flags); rcu_assign_pointer(ioc->ioc_data, cic); + spin_unlock_irqrestore(&ioc->lock, flags); break; } while (1); @@ -1561,6 +1838,8 @@ static int cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc, spin_lock_irqsave(&ioc->lock, flags); ret = radix_tree_insert(&ioc->radix_root, (unsigned long) cfqd, cic); + if (!ret) + hlist_add_head_rcu(&cic->cic_list, &ioc->cic_list); spin_unlock_irqrestore(&ioc->lock, flags); radix_tree_preload_end(); @@ -1637,7 +1916,9 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_io_context *cic, sector_t sdist; u64 total; - if (cic->last_request_pos < rq->sector) + if (!cic->last_request_pos) + sdist = 0; + else if (cic->last_request_pos < rq->sector) sdist = rq->sector - cic->last_request_pos; else sdist = cic->last_request_pos - rq->sector; @@ -1666,7 +1947,7 @@ static void cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct cfq_io_context *cic) { - int enable_idle; + int old_idle, enable_idle; /* * Don't idle for async or idle io prio class @@ -1674,7 +1955,7 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, if (!cfq_cfqq_sync(cfqq) || cfq_class_idle(cfqq)) return; - enable_idle = cfq_cfqq_idle_window(cfqq); + enable_idle = old_idle = cfq_cfqq_idle_window(cfqq); if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle || (cfqd->hw_tag && CIC_SEEKY(cic))) @@ -1686,10 +1967,13 @@ cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq, enable_idle = 1; } - if (enable_idle) - cfq_mark_cfqq_idle_window(cfqq); - else - cfq_clear_cfqq_idle_window(cfqq); + if (old_idle != enable_idle) { + cfq_log_cfqq(cfqd, cfqq, "idle=%d", enable_idle); + if (enable_idle) + cfq_mark_cfqq_idle_window(cfqq); + else + cfq_clear_cfqq_idle_window(cfqq); + } } /* @@ -1729,6 +2013,12 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, if (rq_is_meta(rq) && !cfqq->meta_pending) return 1; + /* + * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice. + */ + if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq)) + return 1; + if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq)) return 0; @@ -1748,6 +2038,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, */ static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq) { + cfq_log_cfqq(cfqd, cfqq, "preempt"); cfq_slice_expired(cfqd, 1); /* @@ -1772,6 +2063,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, { struct cfq_io_context *cic = RQ_CIC(rq); + cfqd->rq_queued++; if (rq_is_meta(rq)) cfqq->meta_pending++; @@ -1783,23 +2075,31 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, if (cfqq == cfqd->active_queue) { /* - * if we are waiting for a request for this queue, let it rip - * immediately and flag that we must not expire this queue - * just now + * Remember that we saw a request from this process, but + * don't start queuing just yet. Otherwise we risk seeing lots + * of tiny requests, because we disrupt the normal plugging + * and merging. If the request is already larger than a single + * page, let it rip immediately. For that case we assume that + * merging is already done. Ditto for a busy system that + * has other work pending, don't risk delaying until the + * idle timer unplug to continue working. */ if (cfq_cfqq_wait_request(cfqq)) { + if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE || + cfqd->busy_queues > 1) { + del_timer(&cfqd->idle_slice_timer); + blk_start_queueing(cfqd->queue); + } cfq_mark_cfqq_must_dispatch(cfqq); - del_timer(&cfqd->idle_slice_timer); - blk_start_queueing(cfqd->queue); } } else if (cfq_should_preempt(cfqd, cfqq, rq)) { /* * not the active queue - expire current slice if it is * idle and has expired it's mean thinktime or this new queue - * has some old slice time left and is of higher priority + * has some old slice time left and is of higher priority or + * this new queue is RT and the current one is BE */ cfq_preempt_queue(cfqd, cfqq); - cfq_mark_cfqq_must_dispatch(cfqq); blk_start_queueing(cfqd->queue); } } @@ -1809,6 +2109,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) struct cfq_data *cfqd = q->elevator->elevator_data; struct cfq_queue *cfqq = RQ_CFQQ(rq); + cfq_log_cfqq(cfqd, cfqq, "insert_request"); cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc); cfq_add_rq_rb(rq); @@ -1818,6 +2119,31 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq) cfq_rq_enqueued(cfqd, cfqq, rq); } +/* + * Update hw_tag based on peak queue depth over 50 samples under + * sufficient load. + */ +static void cfq_update_hw_tag(struct cfq_data *cfqd) +{ + if (cfqd->rq_in_driver > cfqd->rq_in_driver_peak) + cfqd->rq_in_driver_peak = cfqd->rq_in_driver; + + if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN && + cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN) + return; + + if (cfqd->hw_tag_samples++ < 50) + return; + + if (cfqd->rq_in_driver_peak >= CFQ_HW_QUEUE_MIN) + cfqd->hw_tag = 1; + else + cfqd->hw_tag = 0; + + cfqd->hw_tag_samples = 0; + cfqd->rq_in_driver_peak = 0; +} + static void cfq_completed_request(struct request_queue *q, struct request *rq) { struct cfq_queue *cfqq = RQ_CFQQ(rq); @@ -1826,6 +2152,9 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) unsigned long now; now = jiffies; + cfq_log_cfqq(cfqd, cfqq, "complete"); + + cfq_update_hw_tag(cfqd); WARN_ON(!cfqd->rq_in_driver); WARN_ON(!cfqq->dispatched); @@ -1846,13 +2175,23 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) * or if we want to idle in case it has no pending requests. */ if (cfqd->active_queue == cfqq) { + const bool cfqq_empty = RB_EMPTY_ROOT(&cfqq->sort_list); + if (cfq_cfqq_slice_new(cfqq)) { cfq_set_prio_slice(cfqd, cfqq); cfq_clear_cfqq_slice_new(cfqq); } + /* + * If there are no requests waiting in this queue, and + * there are other queues ready to issue requests, AND + * those other queues are issuing requests within our + * mean seek distance, give them a chance to run instead + * of idling. + */ if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq)) cfq_slice_expired(cfqd, 1); - else if (sync && RB_EMPTY_ROOT(&cfqq->sort_list)) + else if (cfqq_empty && !cfq_close_cooperator(cfqd, cfqq, 1) && + sync && !rq_noidle(rq)) cfq_arm_slice_timer(cfqd); } @@ -1914,7 +2253,7 @@ static int cfq_may_queue(struct request_queue *q, int rw) if (!cic) return ELV_MQUEUE_MAY; - cfqq = cic_to_cfqq(cic, rw & REQ_RW_SYNC); + cfqq = cic_to_cfqq(cic, rw_is_sync(rw)); if (cfqq) { cfq_init_prio_data(cfqq, cic->ioc); cfq_prio_boost(cfqq); @@ -1995,6 +2334,7 @@ queue_fail: cfq_schedule_dispatch(cfqd); spin_unlock_irqrestore(q->queue_lock, flags); + cfq_log(cfqd, "set_request fail"); return 1; } @@ -2003,11 +2343,10 @@ static void cfq_kick_queue(struct work_struct *work) struct cfq_data *cfqd = container_of(work, struct cfq_data, unplug_work); struct request_queue *q = cfqd->queue; - unsigned long flags; - spin_lock_irqsave(q->queue_lock, flags); + spin_lock_irq(q->queue_lock); blk_start_queueing(q); - spin_unlock_irqrestore(q->queue_lock, flags); + spin_unlock_irq(q->queue_lock); } /* @@ -2020,6 +2359,8 @@ static void cfq_idle_slice_timer(unsigned long data) unsigned long flags; int timed_out = 1; + cfq_log(cfqd, "idle timer fired"); + spin_lock_irqsave(cfqd->queue->queue_lock, flags); cfqq = cfqd->active_queue; @@ -2027,6 +2368,12 @@ static void cfq_idle_slice_timer(unsigned long data) timed_out = 0; /* + * We saw a request before the queue expired, let it through + */ + if (cfq_cfqq_must_dispatch(cfqq)) + goto out_kick; + + /* * expired */ if (cfq_slice_used(cfqq)) @@ -2042,10 +2389,8 @@ static void cfq_idle_slice_timer(unsigned long data) /* * not expired and it has a request pending, let it dispatch */ - if (!RB_EMPTY_ROOT(&cfqq->sort_list)) { - cfq_mark_cfqq_must_dispatch(cfqq); + if (!RB_EMPTY_ROOT(&cfqq->sort_list)) goto out_kick; - } } expire: cfq_slice_expired(cfqd, timed_out); @@ -2058,7 +2403,7 @@ out_cont: static void cfq_shutdown_timer_wq(struct cfq_data *cfqd) { del_timer_sync(&cfqd->idle_slice_timer); - kblockd_flush_work(&cfqd->unplug_work); + cancel_work_sync(&cfqd->unplug_work); } static void cfq_put_async_queues(struct cfq_data *cfqd) @@ -2076,7 +2421,7 @@ static void cfq_put_async_queues(struct cfq_data *cfqd) cfq_put_queue(cfqd->async_idle_cfqq); } -static void cfq_exit_queue(elevator_t *e) +static void cfq_exit_queue(struct elevator_queue *e) { struct cfq_data *cfqd = e->elevator_data; struct request_queue *q = cfqd->queue; @@ -2108,12 +2453,22 @@ static void cfq_exit_queue(elevator_t *e) static void *cfq_init_queue(struct request_queue *q) { struct cfq_data *cfqd; + int i; cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node); if (!cfqd) return NULL; cfqd->service_tree = CFQ_RB_ROOT; + + /* + * Not strictly needed (since RB_ROOT just clears the node and we + * zeroed cfqd on alloc), but better be safe in case someone decides + * to add magic to the rb code + */ + for (i = 0; i < CFQ_PRIO_LISTS; i++) + cfqd->prio_trees[i] = RB_ROOT; + INIT_LIST_HEAD(&cfqd->cic_list); cfqd->queue = q; @@ -2134,12 +2489,17 @@ static void *cfq_init_queue(struct request_queue *q) cfqd->cfq_slice[1] = cfq_slice_sync; cfqd->cfq_slice_async_rq = cfq_slice_async_rq; cfqd->cfq_slice_idle = cfq_slice_idle; + cfqd->hw_tag = 1; return cfqd; } static void cfq_slab_kill(void) { + /* + * Caller already ensured that pending RCU callbacks are completed, + * so we should have no busy allocations at this point. + */ if (cfq_pool) kmem_cache_destroy(cfq_pool); if (cfq_ioc_pool) @@ -2152,7 +2512,7 @@ static int __init cfq_slab_setup(void) if (!cfq_pool) goto fail; - cfq_ioc_pool = KMEM_CACHE(cfq_io_context, SLAB_DESTROY_BY_RCU); + cfq_ioc_pool = KMEM_CACHE(cfq_io_context, 0); if (!cfq_ioc_pool) goto fail; @@ -2181,7 +2541,7 @@ cfq_var_store(unsigned int *var, const char *page, size_t count) } #define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \ -static ssize_t __FUNC(elevator_t *e, char *page) \ +static ssize_t __FUNC(struct elevator_queue *e, char *page) \ { \ struct cfq_data *cfqd = e->elevator_data; \ unsigned int __data = __VAR; \ @@ -2201,7 +2561,7 @@ SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0); #undef SHOW_FUNCTION #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ -static ssize_t __FUNC(elevator_t *e, const char *page, size_t count) \ +static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \ { \ struct cfq_data *cfqd = e->elevator_data; \ unsigned int __data; \ @@ -2298,9 +2658,13 @@ static void __exit cfq_exit(void) ioc_gone = &all_gone; /* ioc_gone's update must be visible before reading ioc_count */ smp_wmb(); + + /* + * this also protects us from entering cfq_slab_kill() with + * pending RCU callbacks + */ if (elv_ioc_count_read(ioc_count)) - wait_for_completion(ioc_gone); - synchronize_rcu(); + wait_for_completion(&all_gone); cfq_slab_kill(); }