diff options
Diffstat (limited to 'block')
36 files changed, 1234 insertions, 1268 deletions
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index d819dc77fe659..a9e8633388f40 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -55,13 +55,13 @@ BFQG_FLAG_FNS(empty) /* This should be called with the scheduler lock held. */ static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats) { - unsigned long long now; + u64 now; if (!bfqg_stats_waiting(stats)) return; - now = sched_clock(); - if (time_after64(now, stats->start_group_wait_time)) + now = ktime_get_ns(); + if (now > stats->start_group_wait_time) blkg_stat_add(&stats->group_wait_time, now - stats->start_group_wait_time); bfqg_stats_clear_waiting(stats); @@ -77,20 +77,20 @@ static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg, return; if (bfqg == curr_bfqg) return; - stats->start_group_wait_time = sched_clock(); + stats->start_group_wait_time = ktime_get_ns(); bfqg_stats_mark_waiting(stats); } /* This should be called with the scheduler lock held. */ static void bfqg_stats_end_empty_time(struct bfqg_stats *stats) { - unsigned long long now; + u64 now; if (!bfqg_stats_empty(stats)) return; - now = sched_clock(); - if (time_after64(now, stats->start_empty_time)) + now = ktime_get_ns(); + if (now > stats->start_empty_time) blkg_stat_add(&stats->empty_time, now - stats->start_empty_time); bfqg_stats_clear_empty(stats); @@ -116,7 +116,7 @@ void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) if (bfqg_stats_empty(stats)) return; - stats->start_empty_time = sched_clock(); + stats->start_empty_time = ktime_get_ns(); bfqg_stats_mark_empty(stats); } @@ -125,9 +125,9 @@ void bfqg_stats_update_idle_time(struct bfq_group *bfqg) struct bfqg_stats *stats = &bfqg->stats; if (bfqg_stats_idling(stats)) { - unsigned long long now = sched_clock(); + u64 now = ktime_get_ns(); - if (time_after64(now, stats->start_idle_time)) + if (now > stats->start_idle_time) blkg_stat_add(&stats->idle_time, now - stats->start_idle_time); bfqg_stats_clear_idling(stats); @@ -138,7 +138,7 @@ void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { struct bfqg_stats *stats = &bfqg->stats; - stats->start_idle_time = sched_clock(); + stats->start_idle_time = ktime_get_ns(); bfqg_stats_mark_idling(stats); } @@ -171,18 +171,18 @@ void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) blkg_rwstat_add(&bfqg->stats.merged, op, 1); } -void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time, - uint64_t io_start_time, unsigned int op) +void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, + u64 io_start_time_ns, unsigned int op) { struct bfqg_stats *stats = &bfqg->stats; - unsigned long long now = sched_clock(); + u64 now = ktime_get_ns(); - if (time_after64(now, io_start_time)) + if (now > io_start_time_ns) blkg_rwstat_add(&stats->service_time, op, - now - io_start_time); - if (time_after64(io_start_time, start_time)) + now - io_start_time_ns); + if (io_start_time_ns > start_time_ns) blkg_rwstat_add(&stats->wait_time, op, - io_start_time - start_time); + io_start_time_ns - start_time_ns); } #else /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */ @@ -191,8 +191,8 @@ void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, unsigned int op) { } void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { } void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { } -void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time, - uint64_t io_start_time, unsigned int op) { } +void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, + u64 io_start_time_ns, unsigned int op) { } void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { } void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { } void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 771ae9730ac68..495b9ddb3355c 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -49,9 +49,39 @@ * * In particular, to provide these low-latency guarantees, BFQ * explicitly privileges the I/O of two classes of time-sensitive - * applications: interactive and soft real-time. This feature enables - * BFQ to provide applications in these classes with a very low - * latency. Finally, BFQ also features additional heuristics for + * applications: interactive and soft real-time. In more detail, BFQ + * behaves this way if the low_latency parameter is set (default + * configuration). This feature enables BFQ to provide applications in + * these classes with a very low latency. + * + * To implement this feature, BFQ constantly tries to detect whether + * the I/O requests in a bfq_queue come from an interactive or a soft + * real-time application. For brevity, in these cases, the queue is + * said to be interactive or soft real-time. In both cases, BFQ + * privileges the service of the queue, over that of non-interactive + * and non-soft-real-time queues. This privileging is performed, + * mainly, by raising the weight of the queue. So, for brevity, we + * call just weight-raising periods the time periods during which a + * queue is privileged, because deemed interactive or soft real-time. + * + * The detection of soft real-time queues/applications is described in + * detail in the comments on the function + * bfq_bfqq_softrt_next_start. On the other hand, the detection of an + * interactive queue works as follows: a queue is deemed interactive + * if it is constantly non empty only for a limited time interval, + * after which it does become empty. The queue may be deemed + * interactive again (for a limited time), if it restarts being + * constantly non empty, provided that this happens only after the + * queue has remained empty for a given minimum idle time. + * + * By default, BFQ computes automatically the above maximum time + * interval, i.e., the time interval after which a constantly + * non-empty queue stops being deemed interactive. Since a queue is + * weight-raised while it is deemed interactive, this maximum time + * interval happens to coincide with the (maximum) duration of the + * weight-raising for interactive queues. + * + * Finally, BFQ also features additional heuristics for * preserving both a low latency and a high throughput on NCQ-capable, * rotational or flash-based devices, and to get the job done quickly * for applications consisting in many I/O-bound processes. @@ -61,14 +91,14 @@ * all low-latency heuristics for that device, by setting low_latency * to 0. * - * BFQ is described in [1], where also a reference to the initial, more - * theoretical paper on BFQ can be found. The interested reader can find - * in the latter paper full details on the main algorithm, as well as - * formulas of the guarantees and formal proofs of all the properties. - * With respect to the version of BFQ presented in these papers, this - * implementation adds a few more heuristics, such as the one that - * guarantees a low latency to soft real-time applications, and a - * hierarchical extension based on H-WF2Q+. + * BFQ is described in [1], where also a reference to the initial, + * more theoretical paper on BFQ can be found. The interested reader + * can find in the latter paper full details on the main algorithm, as + * well as formulas of the guarantees and formal proofs of all the + * properties. With respect to the version of BFQ presented in these + * papers, this implementation adds a few more heuristics, such as the + * ones that guarantee a low latency to interactive and soft real-time + * applications, and a hierarchical extension based on H-WF2Q+. * * B-WF2Q+ is based on WF2Q+, which is described in [2], together with * H-WF2Q+, while the augmented tree used here to implement B-WF2Q+ @@ -218,56 +248,46 @@ static struct kmem_cache *bfq_pool; #define BFQ_RATE_SHIFT 16 /* - * By default, BFQ computes the duration of the weight raising for - * interactive applications automatically, using the following formula: - * duration = (R / r) * T, where r is the peak rate of the device, and - * R and T are two reference parameters. - * In particular, R is the peak rate of the reference device (see - * below), and T is a reference time: given the systems that are - * likely to be installed on the reference device according to its - * speed class, T is about the maximum time needed, under BFQ and - * while reading two files in parallel, to load typical large - * applications on these systems (see the comments on - * max_service_from_wr below, for more details on how T is obtained). - * In practice, the slower/faster the device at hand is, the more/less - * it takes to load applications with respect to the reference device. - * Accordingly, the longer/shorter BFQ grants weight raising to - * interactive applications. - * - * BFQ uses four different reference pairs (R, T), depending on: - * . whether the device is rotational or non-rotational; - * . whether the device is slow, such as old or portable HDDs, as well as - * SD cards, or fast, such as newer HDDs and SSDs. + * When configured for computing the duration of the weight-raising + * for interactive queues automatically (see the comments at the + * beginning of this file), BFQ does it using the following formula: + * duration = (ref_rate / r) * ref_wr_duration, + * where r is the peak rate of the device, and ref_rate and + * ref_wr_duration are two reference parameters. In particular, + * ref_rate is the peak rate of the reference storage device (see + * below), and ref_wr_duration is about the maximum time needed, with + * BFQ and while reading two files in parallel, to load typical large + * applications on the reference device (see the comments on + * max_service_from_wr below, for more details on how ref_wr_duration + * is obtained). In practice, the slower/faster the device at hand + * is, the more/less it takes to load applications with respect to the + * reference device. Accordingly, the longer/shorter BFQ grants + * weight raising to interactive applications. * - * The device's speed class is dynamically (re)detected in - * bfq_update_peak_rate() every time the estimated peak rate is updated. + * BFQ uses two different reference pairs (ref_rate, ref_wr_duration), + * depending on whether the device is rotational or non-rotational. * - * In the following definitions, R_slow[0]/R_fast[0] and - * T_slow[0]/T_fast[0] are the reference values for a slow/fast - * rotational device, whereas R_slow[1]/R_fast[1] and - * T_slow[1]/T_fast[1] are the reference values for a slow/fast - * non-rotational device. Finally, device_speed_thresh are the - * thresholds used to switch between speed classes. The reference - * rates are not the actual peak rates of the devices used as a - * reference, but slightly lower values. The reason for using these - * slightly lower values is that the peak-rate estimator tends to - * yield slightly lower values than the actual peak rate (it can yield - * the actual peak rate only if there is only one process doing I/O, - * and the process does sequential I/O). + * In the following definitions, ref_rate[0] and ref_wr_duration[0] + * are the reference values for a rotational device, whereas + * ref_rate[1] and ref_wr_duration[1] are the reference values for a + * non-rotational device. The reference rates are not the actual peak + * rates of the devices used as a reference, but slightly lower + * values. The reason for using slightly lower values is that the + * peak-rate estimator tends to yield slightly lower values than the + * actual peak rate (it can yield the actual peak rate only if there + * is only one process doing I/O, and the process does sequential + * I/O). * - * Both the reference peak rates and the thresholds are measured in - * sectors/usec, left-shifted by BFQ_RATE_SHIFT. + * The reference peak rates are measured in sectors/usec, left-shifted + * by BFQ_RATE_SHIFT. */ -static int R_slow[2] = {1000, 10700}; -static int R_fast[2] = {14000, 33000}; +static int ref_rate[2] = {14000, 33000}; /* - * To improve readability, a conversion function is used to initialize the - * following arrays, which entails that they can be initialized only in a - * function. + * To improve readability, a conversion function is used to initialize + * the following array, which entails that the array can be + * initialized only in a function. */ -static int T_slow[2]; -static int T_fast[2]; -static int device_speed_thresh[2]; +static int ref_wr_duration[2]; /* * BFQ uses the above-detailed, time-based weight-raising mechanism to @@ -487,46 +507,6 @@ static struct request *bfq_choose_req(struct bfq_data *bfqd, } /* - * See the comments on bfq_limit_depth for the purpose of - * the depths set in the function. - */ -static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt) -{ - bfqd->sb_shift = bt->sb.shift; - - /* - * In-word depths if no bfq_queue is being weight-raised: - * leaving 25% of tags only for sync reads. - * - * In next formulas, right-shift the value - * (1U<<bfqd->sb_shift), instead of computing directly - * (1U<<(bfqd->sb_shift - something)), to be robust against - * any possible value of bfqd->sb_shift, without having to - * limit 'something'. - */ - /* no more than 50% of tags for async I/O */ - bfqd->word_depths[0][0] = max((1U<<bfqd->sb_shift)>>1, 1U); - /* - * no more than 75% of tags for sync writes (25% extra tags - * w.r.t. async I/O, to prevent async I/O from starving sync - * writes) - */ - bfqd->word_depths[0][1] = max(((1U<<bfqd->sb_shift) * 3)>>2, 1U); - - /* - * In-word depths in case some bfq_queue is being weight- - * raised: leaving ~63% of tags for sync reads. This is the - * highest percentage for which, in our tests, application - * start-up times didn't suffer from any regression due to tag - * shortage. - */ - /* no more than ~18% of tags for async I/O */ - bfqd->word_depths[1][0] = max(((1U<<bfqd->sb_shift) * 3)>>4, 1U); - /* no more than ~37% of tags for sync writes (~20% extra tags) */ - bfqd->word_depths[1][1] = max(((1U<<bfqd->sb_shift) * 6)>>4, 1U); -} - -/* * Async I/O can easily starve sync I/O (both sync reads and sync * writes), by consuming all tags. Similarly, storms of sync writes, * such as those that sync(2) may trigger, can starve sync reads. @@ -535,25 +515,11 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt) */ static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) { - struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct bfq_data *bfqd = data->q->elevator->elevator_data; - struct sbitmap_queue *bt; if (op_is_sync(op) && !op_is_write(op)) return; - if (data->flags & BLK_MQ_REQ_RESERVED) { - if (unlikely(!tags->nr_reserved_tags)) { - WARN_ON_ONCE(1); - return; - } - bt = &tags->breserved_tags; - } else - bt = &tags->bitmap_tags; - - if (unlikely(bfqd->sb_shift != bt->sb.shift)) - bfq_update_depths(bfqd, bt); - data->shallow_depth = bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)]; @@ -906,26 +872,30 @@ static unsigned int bfq_wr_duration(struct bfq_data *bfqd) if (bfqd->bfq_wr_max_time > 0) return bfqd->bfq_wr_max_time; - dur = bfqd->RT_prod; + dur = bfqd->rate_dur_prod; do_div(dur, bfqd->peak_rate); /* - * Limit duration between 3 and 13 seconds. Tests show that - * higher values than 13 seconds often yield the opposite of - * the desired result, i.e., worsen responsiveness by letting - * non-interactive and non-soft-real-time applications - * preserve weight raising for a too long time interval. + * Limit duration between 3 and 25 seconds. The upper limit + * has been conservatively set after the following worst case: + * on a QEMU/KVM virtual machine + * - running in a slow PC + * - with a virtual disk stacked on a slow low-end 5400rpm HDD + * - serving a heavy I/O workload, such as the sequential reading + * of several files + * mplayer took 23 seconds to start, if constantly weight-raised. + * + * As for higher values than that accomodating the above bad + * scenario, tests show that higher values would often yield + * the opposite of the desired result, i.e., would worsen + * responsiveness by allowing non-interactive applications to + * preserve weight raising for too long. * * On the other end, lower values than 3 seconds make it * difficult for most interactive tasks to complete their jobs * before weight-raising finishes. */ - if (dur > msecs_to_jiffies(13000)) - dur = msecs_to_jiffies(13000); - else if (dur < msecs_to_jiffies(3000)) - dur = msecs_to_jiffies(3000); - - return dur; + return clamp_val(dur, msecs_to_jiffies(3000), msecs_to_jiffies(25000)); } /* switch back from soft real-time to interactive weight raising */ @@ -1393,15 +1363,6 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd, } /* - * Return the farthest future time instant according to jiffies - * macros. - */ -static unsigned long bfq_greatest_from_now(void) -{ - return jiffies + MAX_JIFFY_OFFSET; -} - -/* * Return the farthest past time instant according to jiffies * macros. */ @@ -1545,7 +1506,8 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, in_burst = bfq_bfqq_in_large_burst(bfqq); soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 && !in_burst && - time_is_before_jiffies(bfqq->soft_rt_next_start); + time_is_before_jiffies(bfqq->soft_rt_next_start) && + bfqq->dispatched == 0; *interactive = !in_burst && idle_for_long_time; wr_or_deserves_wr = bfqd->low_latency && (bfqq->wr_coeff > 1 || @@ -1858,6 +1820,8 @@ static int bfq_request_merge(struct request_queue *q, struct request **req, return ELEVATOR_NO_MERGE; } +static struct bfq_queue *bfq_init_rq(struct request *rq); + static void bfq_request_merged(struct request_queue *q, struct request *req, enum elv_merge type) { @@ -1866,7 +1830,7 @@ static void bfq_request_merged(struct request_queue *q, struct request *req, blk_rq_pos(req) < blk_rq_pos(container_of(rb_prev(&req->rb_node), struct request, rb_node))) { - struct bfq_queue *bfqq = RQ_BFQQ(req); + struct bfq_queue *bfqq = bfq_init_rq(req); struct bfq_data *bfqd = bfqq->bfqd; struct request *prev, *next_rq; @@ -1891,14 +1855,25 @@ static void bfq_request_merged(struct request_queue *q, struct request *req, } } +/* + * This function is called to notify the scheduler that the requests + * rq and 'next' have been merged, with 'next' going away. BFQ + * exploits this hook to address the following issue: if 'next' has a + * fifo_time lower that rq, then the fifo_time of rq must be set to + * the value of 'next', to not forget the greater age of 'next'. + * + * NOTE: in this function we assume that rq is in a bfq_queue, basing + * on that rq is picked from the hash table q->elevator->hash, which, + * in its turn, is filled only with I/O requests present in + * bfq_queues, while BFQ is in use for the request queue q. In fact, + * the function that fills this hash table (elv_rqhash_add) is called + * only by bfq_insert_request. + */ static void bfq_requests_merged(struct request_queue *q, struct request *rq, struct request *next) { - struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next); - - if (!RB_EMPTY_NODE(&rq->rb_node)) - goto end; - spin_lock_irq(&bfqq->bfqd->lock); + struct bfq_queue *bfqq = bfq_init_rq(rq), + *next_bfqq = bfq_init_rq(next); /* * If next and rq belong to the same bfq_queue and next is older @@ -1920,11 +1895,6 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq, if (bfqq->next_rq == next) bfqq->next_rq = rq; - bfq_remove_request(q, next); - bfqg_stats_update_io_remove(bfqq_group(bfqq), next->cmd_flags); - - spin_unlock_irq(&bfqq->bfqd->lock); -end: bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags); } @@ -2506,37 +2476,15 @@ static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd) /* * Update parameters related to throughput and responsiveness, as a * function of the estimated peak rate. See comments on - * bfq_calc_max_budget(), and on T_slow and T_fast arrays. + * bfq_calc_max_budget(), and on the ref_wr_duration array. */ static void update_thr_responsiveness_params(struct bfq_data *bfqd) { - int dev_type = blk_queue_nonrot(bfqd->queue); - - if (bfqd->bfq_user_max_budget == 0) + if (bfqd->bfq_user_max_budget == 0) { bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd); - - if (bfqd->device_speed == BFQ_BFQD_FAST && - bfqd->peak_rate < device_speed_thresh[dev_type]) { - bfqd->device_speed = BFQ_BFQD_SLOW; - bfqd->RT_prod = R_slow[dev_type] * - T_slow[dev_type]; - } else if (bfqd->device_speed == BFQ_BFQD_SLOW && - bfqd->peak_rate > device_speed_thresh[dev_type]) { - bfqd->device_speed = BFQ_BFQD_FAST; - bfqd->RT_prod = R_fast[dev_type] * - T_fast[dev_type]; + bfq_log(bfqd, "new max_budget = %d", bfqd->bfq_max_budget); } - - bfq_log(bfqd, -"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec", - dev_type == 0 ? "ROT" : "NONROT", - bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW", - bfqd->device_speed == BFQ_BFQD_FAST ? - (USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT : - (USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT, - (USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>> - BFQ_RATE_SHIFT); } static void bfq_reset_rate_computation(struct bfq_data *bfqd, @@ -3266,23 +3214,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd, bfq_bfqq_softrt_next_start(bfqd, bfqq); else { /* - * The application is still waiting for the - * completion of one or more requests: - * prevent it from possibly being incorrectly - * deemed as soft real-time by setting its - * soft_rt_next_start to infinity. In fact, - * without this assignment, the application - * would be incorrectly deemed as soft - * real-time if: - * 1) it issued a new request before the - * completion of all its in-flight - * requests, and - * 2) at that time, its soft_rt_next_start - * happened to be in the past. - */ - bfqq->soft_rt_next_start = - bfq_greatest_from_now(); - /* * Schedule an update of soft_rt_next_start to when * the task may be discovered to be isochronous. */ @@ -4540,14 +4471,12 @@ static inline void bfq_update_insert_stats(struct request_queue *q, unsigned int cmd_flags) {} #endif -static void bfq_prepare_request(struct request *rq, struct bio *bio); - static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head) { struct request_queue *q = hctx->queue; struct bfq_data *bfqd = q->elevator->elevator_data; - struct bfq_queue *bfqq = RQ_BFQQ(rq); + struct bfq_queue *bfqq; bool idle_timer_disabled = false; unsigned int cmd_flags; @@ -4562,24 +4491,13 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_mq_sched_request_inserted(rq); spin_lock_irq(&bfqd->lock); + bfqq = bfq_init_rq(rq); if (at_head || blk_rq_is_passthrough(rq)) { if (at_head) list_add(&rq->queuelist, &bfqd->dispatch); else list_add_tail(&rq->queuelist, &bfqd->dispatch); - } else { - if (WARN_ON_ONCE(!bfqq)) { - /* - * This should never happen. Most likely rq is - * a requeued regular request, being - * re-inserted without being first - * re-prepared. Do a prepare, to avoid - * failure. - */ - bfq_prepare_request(rq, rq->bio); - bfqq = RQ_BFQQ(rq); - } - + } else { /* bfqq is assumed to be non null here */ idle_timer_disabled = __bfq_insert_request(bfqd, rq); /* * Update bfqq, because, if a queue merge has occurred @@ -4778,8 +4696,8 @@ static void bfq_finish_requeue_request(struct request *rq) if (rq->rq_flags & RQF_STARTED) bfqg_stats_update_completion(bfqq_group(bfqq), - rq_start_time_ns(rq), - rq_io_start_time_ns(rq), + rq->start_time_ns, + rq->io_start_time_ns, rq->cmd_flags); if (likely(rq->rq_flags & RQF_STARTED)) { @@ -4922,11 +4840,48 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, } /* - * Allocate bfq data structures associated with this request. + * Only reset private fields. The actual request preparation will be + * performed by bfq_init_rq, when rq is either inserted or merged. See + * comments on bfq_init_rq for the reason behind this delayed + * preparation. */ static void bfq_prepare_request(struct request *rq, struct bio *bio) { + /* + * Regardless of whether we have an icq attached, we have to + * clear the scheduler pointers, as they might point to + * previously allocated bic/bfqq structs. + */ + rq->elv.priv[0] = rq->elv.priv[1] = NULL; +} + +/* + * If needed, init rq, allocate bfq data structures associated with + * rq, and increment reference counters in the destination bfq_queue + * for rq. Return the destination bfq_queue for rq, or NULL is rq is + * not associated with any bfq_queue. + * + * This function is invoked by the functions that perform rq insertion + * or merging. One may have expected the above preparation operations + * to be performed in bfq_prepare_request, and not delayed to when rq + * is inserted or merged. The rationale behind this delayed + * preparation is that, after the prepare_request hook is invoked for + * rq, rq may still be transformed into a request with no icq, i.e., a + * request not associated with any queue. No bfq hook is invoked to + * signal this tranformation. As a consequence, should these + * preparation operations be performed when the prepare_request hook + * is invoked, and should rq be transformed one moment later, bfq + * would end up in an inconsistent state, because it would have + * incremented some queue counters for an rq destined to + * transformation, without any chance to correctly lower these + * counters back. In contrast, no transformation can still happen for + * rq after rq has been inserted or merged. So, it is safe to execute + * these preparation operations when rq is finally inserted or merged. + */ +static struct bfq_queue *bfq_init_rq(struct request *rq) +{ struct request_queue *q = rq->q; + struct bio *bio = rq->bio; struct bfq_data *bfqd = q->elevator->elevator_data; struct bfq_io_cq *bic; const int is_sync = rq_is_sync(rq); @@ -4934,20 +4889,21 @@ static void bfq_prepare_request(struct request *rq, struct bio *bio) bool new_queue = false; bool bfqq_already_existing = false, split = false; + if (unlikely(!rq->elv.icq)) + return NULL; + /* - * Even if we don't have an icq attached, we should still clear - * the scheduler pointers, as they might point to previously - * allocated bic/bfqq structs. + * Assuming that elv.priv[1] is set only if everything is set + * for this rq. This holds true, because this function is + * invoked only for insertion or merging, and, after such + * events, a request cannot be manipulated any longer before + * being removed from bfq. */ - if (!rq->elv.icq) { - rq->elv.priv[0] = rq->elv.priv[1] = NULL; - return; - } + if (rq->elv.priv[1]) + return rq->elv.priv[1]; bic = icq_to_bic(rq->elv.icq); - spin_lock_irq(&bfqd->lock); - bfq_check_ioprio_change(bic, bio); bfq_bic_update_cgroup(bic, bio); @@ -5006,7 +4962,7 @@ static void bfq_prepare_request(struct request *rq, struct bio *bio) if (unlikely(bfq_bfqq_just_created(bfqq))) bfq_handle_burst(bfqd, bfqq); - spin_unlock_irq(&bfqd->lock); + return bfqq; } static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq) @@ -5105,6 +5061,64 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg) __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq); } +/* + * See the comments on bfq_limit_depth for the purpose of + * the depths set in the function. Return minimum shallow depth we'll use. + */ +static unsigned int bfq_update_depths(struct bfq_data *bfqd, + struct sbitmap_queue *bt) +{ + unsigned int i, j, min_shallow = UINT_MAX; + + /* + * In-word depths if no bfq_queue is being weight-raised: + * leaving 25% of tags only for sync reads. + * + * In next formulas, right-shift the value + * (1U<<bt->sb.shift), instead of computing directly + * (1U<<(bt->sb.shift - something)), to be robust against + * any possible value of bt->sb.shift, without having to + * limit 'something'. + */ + /* no more than 50% of tags for async I/O */ + bfqd->word_depths[0][0] = max((1U << bt->sb.shift) >> 1, 1U); + /* + * no more than 75% of tags for sync writes (25% extra tags + * w.r.t. async I/O, to prevent async I/O from starving sync + * writes) + */ + bfqd->word_depths[0][1] = max(((1U << bt->sb.shift) * 3) >> 2, 1U); + + /* + * In-word depths in case some bfq_queue is being weight- + * raised: leaving ~63% of tags for sync reads. This is the + * highest percentage for which, in our tests, application + * start-up times didn't suffer from any regression due to tag + * shortage. + */ + /* no more than ~18% of tags for async I/O */ + bfqd->word_depths[1][0] = max(((1U << bt->sb.shift) * 3) >> 4, 1U); + /* no more than ~37% of tags for sync writes (~20% extra tags) */ + bfqd->word_depths[1][1] = max(((1U << bt->sb.shift) * 6) >> 4, 1U); + + for (i = 0; i < 2; i++) + for (j = 0; j < 2; j++) + min_shallow = min(min_shallow, bfqd->word_depths[i][j]); + + return min_shallow; +} + +static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) +{ + struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; + struct blk_mq_tags *tags = hctx->sched_tags; + unsigned int min_shallow; + + min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags); + sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow); + return 0; +} + static void bfq_exit_queue(struct elevator_queue *e) { struct bfq_data *bfqd = e->elevator_data; @@ -5242,14 +5256,12 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfqd->wr_busy_queues = 0; /* - * Begin by assuming, optimistically, that the device is a - * high-speed one, and that its peak rate is equal to 2/3 of - * the highest reference rate. + * Begin by assuming, optimistically, that the device peak + * rate is equal to 2/3 of the highest reference rate. */ - bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] * - T_fast[blk_queue_nonrot(bfqd->queue)]; - bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3; - bfqd->device_speed = BFQ_BFQD_FAST; + bfqd->rate_dur_prod = ref_rate[blk_queue_nonrot(bfqd->queue)] * + ref_wr_duration[blk_queue_nonrot(bfqd->queue)]; + bfqd->peak_rate = ref_rate[blk_queue_nonrot(bfqd->queue)] * 2 / 3; spin_lock_init(&bfqd->lock); @@ -5526,6 +5538,7 @@ static struct elevator_type iosched_bfq_mq = { .requests_merged = bfq_requests_merged, .request_merged = bfq_request_merged, .has_work = bfq_has_work, + .init_hctx = bfq_init_hctx, .init_sched = bfq_init_queue, .exit_sched = bfq_exit_queue, }, @@ -5556,8 +5569,8 @@ static int __init bfq_init(void) /* * Times to load large popular applications for the typical * systems installed on the reference devices (see the - * comments before the definitions of the next two - * arrays). Actually, we use slightly slower values, as the + * comments before the definition of the next + * array). Actually, we use slightly lower values, as the * estimated peak rate tends to be smaller than the actual * peak rate. The reason for this last fact is that estimates * are computed over much shorter time intervals than the long @@ -5566,25 +5579,8 @@ static int __init bfq_init(void) * scheduler cannot rely on a peak-rate-evaluation workload to * be run for a long time. */ - T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */ - T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */ - T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */ - T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */ - - /* - * Thresholds that determine the switch between speed classes - * (see the comments before the definition of the array - * device_speed_thresh). These thresholds are biased towards - * transitions to the fast class. This is safer than the - * opposite bias. In fact, a wrong transition to the slow - * class results in short weight-raising periods, because the - * speed of the device then tends to be higher that the - * reference peak rate. On the opposite end, a wrong - * transition to the fast class tends to increase - * weight-raising periods, because of the opposite reason. - */ - device_speed_thresh[0] = (4 * R_slow[0]) / 3; - device_speed_thresh[1] = (4 * R_slow[1]) / 3; + ref_wr_duration[0] = msecs_to_jiffies(7000); /* actually 8 sec */ + ref_wr_duration[1] = msecs_to_jiffies(2500); /* actually 3 sec */ ret = elv_register(&iosched_bfq_mq); if (ret) diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index ae2f3dadec441..0f712e03b035a 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -399,11 +399,6 @@ struct bfq_io_cq { struct bfq_ttime saved_ttime; }; -enum bfq_device_speed { - BFQ_BFQD_FAST, - BFQ_BFQD_SLOW, -}; - /** * struct bfq_data - per-device data structure. * @@ -611,12 +606,11 @@ struct bfq_data { /* Max service-rate for a soft real-time queue, in sectors/sec */ unsigned int bfq_wr_max_softrt_rate; /* - * Cached value of the product R*T, used for computing the - * maximum duration of weight raising automatically. + * Cached value of the product ref_rate*ref_wr_duration, used + * for computing the maximum duration of weight raising + * automatically. */ - u64 RT_prod; - /* device-speed class for the low-latency heuristic */ - enum bfq_device_speed device_speed; + u64 rate_dur_prod; /* fallback dummy bfqq for extreme OOM conditions */ struct bfq_queue oom_bfqq; @@ -636,12 +630,6 @@ struct bfq_data { struct bfq_queue *bio_bfqq; /* - * Cached sbitmap shift, used to compute depth limits in - * bfq_update_depths. - */ - unsigned int sb_shift; - - /* * Depth limits used in bfq_limit_depth (see comments on the * function) */ @@ -732,9 +720,9 @@ struct bfqg_stats { /* total time with empty current active q with other requests queued */ struct blkg_stat empty_time; /* fields after this shouldn't be cleared on stat reset */ - uint64_t start_group_wait_time; - uint64_t start_idle_time; - uint64_t start_empty_time; + u64 start_group_wait_time; + u64 start_idle_time; + u64 start_empty_time; uint16_t flags; #endif /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */ }; @@ -856,8 +844,8 @@ void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, unsigned int op); void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op); void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op); -void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time, - uint64_t io_start_time, unsigned int op); +void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, + u64 io_start_time_ns, unsigned int op); void bfqg_stats_update_dequeue(struct bfq_group *bfqg); void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg); void bfqg_stats_update_idle_time(struct bfq_group *bfqg); diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 9cfdd6c83b5bb..add7c7c853352 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -56,12 +56,12 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, struct bio_set *bs = bio->bi_pool; unsigned inline_vecs; - if (!bs || !bs->bio_integrity_pool) { + if (!bs || !mempool_initialized(&bs->bio_integrity_pool)) { bip = kmalloc(sizeof(struct bio_integrity_payload) + sizeof(struct bio_vec) * nr_vecs, gfp_mask); inline_vecs = nr_vecs; } else { - bip = mempool_alloc(bs->bio_integrity_pool, gfp_mask); + bip = mempool_alloc(&bs->bio_integrity_pool, gfp_mask); inline_vecs = BIP_INLINE_VECS; } @@ -74,7 +74,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, unsigned long idx = 0; bip->bip_vec = bvec_alloc(gfp_mask, nr_vecs, &idx, - bs->bvec_integrity_pool); + &bs->bvec_integrity_pool); if (!bip->bip_vec) goto err; bip->bip_max_vcnt = bvec_nr_vecs(idx); @@ -90,7 +90,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, return bip; err: - mempool_free(bip, bs->bio_integrity_pool); + mempool_free(bip, &bs->bio_integrity_pool); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(bio_integrity_alloc); @@ -111,10 +111,10 @@ static void bio_integrity_free(struct bio *bio) kfree(page_address(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset); - if (bs && bs->bio_integrity_pool) { - bvec_free(bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab); + if (bs && mempool_initialized(&bs->bio_integrity_pool)) { + bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab); - mempool_free(bip, bs->bio_integrity_pool); + mempool_free(bip, &bs->bio_integrity_pool); } else { kfree(bip); } @@ -465,16 +465,15 @@ EXPORT_SYMBOL(bio_integrity_clone); int bioset_integrity_create(struct bio_set *bs, int pool_size) { - if (bs->bio_integrity_pool) + if (mempool_initialized(&bs->bio_integrity_pool)) return 0; - bs->bio_integrity_pool = mempool_create_slab_pool(pool_size, bip_slab); - if (!bs->bio_integrity_pool) + if (mempool_init_slab_pool(&bs->bio_integrity_pool, + pool_size, bip_slab)) return -1; - bs->bvec_integrity_pool = biovec_create_pool(pool_size); - if (!bs->bvec_integrity_pool) { - mempool_destroy(bs->bio_integrity_pool); + if (biovec_init_pool(&bs->bvec_integrity_pool, pool_size)) { + mempool_exit(&bs->bio_integrity_pool); return -1; } @@ -484,8 +483,8 @@ EXPORT_SYMBOL(bioset_integrity_create); void bioset_integrity_free(struct bio_set *bs) { - mempool_destroy(bs->bio_integrity_pool); - mempool_destroy(bs->bvec_integrity_pool); + mempool_exit(&bs->bio_integrity_pool); + mempool_exit(&bs->bvec_integrity_pool); } EXPORT_SYMBOL(bioset_integrity_free); diff --git a/block/bio.c b/block/bio.c index 53e0f0a1ed940..5f7563598b1cc 100644 --- a/block/bio.c +++ b/block/bio.c @@ -53,7 +53,7 @@ static struct biovec_slab bvec_slabs[BVEC_POOL_NR] __read_mostly = { * fs_bio_set is the bio_set containing bio and iovec memory pools used by * IO code that does not need private memory pools. */ -struct bio_set *fs_bio_set; +struct bio_set fs_bio_set; EXPORT_SYMBOL(fs_bio_set); /* @@ -254,7 +254,7 @@ static void bio_free(struct bio *bio) bio_uninit(bio); if (bs) { - bvec_free(bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio)); + bvec_free(&bs->bvec_pool, bio->bi_io_vec, BVEC_POOL_IDX(bio)); /* * If we have front padding, adjust the bio pointer before freeing @@ -262,7 +262,7 @@ static void bio_free(struct bio *bio) p = bio; p -= bs->front_pad; - mempool_free(p, bs->bio_pool); + mempool_free(p, &bs->bio_pool); } else { /* Bio was allocated by bio_kmalloc() */ kfree(bio); @@ -454,7 +454,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs, inline_vecs = nr_iovecs; } else { /* should not use nobvec bioset for nr_iovecs > 0 */ - if (WARN_ON_ONCE(!bs->bvec_pool && nr_iovecs > 0)) + if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && + nr_iovecs > 0)) return NULL; /* * generic_make_request() converts recursion to iteration; this @@ -483,11 +484,11 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs, bs->rescue_workqueue) gfp_mask &= ~__GFP_DIRECT_RECLAIM; - p = mempool_alloc(bs->bio_pool, gfp_mask); + p = mempool_alloc(&bs->bio_pool, gfp_mask); if (!p && gfp_mask != saved_gfp) { punt_bios_to_rescuer(bs); gfp_mask = saved_gfp; - p = mempool_alloc(bs->bio_pool, gfp_mask); + p = mempool_alloc(&bs->bio_pool, gfp_mask); } front_pad = bs->front_pad; @@ -503,11 +504,11 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs, if (nr_iovecs > inline_vecs) { unsigned long idx = 0; - bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool); + bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool); if (!bvl && gfp_mask != saved_gfp) { punt_bios_to_rescuer(bs); gfp_mask = saved_gfp; - bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool); + bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, &bs->bvec_pool); } if (unlikely(!bvl)) @@ -524,25 +525,25 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs, return bio; err_free: - mempool_free(p, bs->bio_pool); + mempool_free(p, &bs->bio_pool); return NULL; } EXPORT_SYMBOL(bio_alloc_bioset); -void zero_fill_bio(struct bio *bio) +void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start) { unsigned long flags; struct bio_vec bv; struct bvec_iter iter; - bio_for_each_segment(bv, bio, iter) { + __bio_for_each_segment(bv, bio, iter, start) { char *data = bvec_kmap_irq(&bv, &flags); memset(data, 0, bv.bv_len); flush_dcache_page(bv.bv_page); bvec_kunmap_irq(data, &flags); } } -EXPORT_SYMBOL(zero_fill_bio); +EXPORT_SYMBOL(zero_fill_bio_iter); /** * bio_put - release a reference to a bio @@ -773,7 +774,7 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page return 0; } - if (bio->bi_vcnt >= bio->bi_max_vecs) + if (bio_full(bio)) return 0; /* @@ -821,52 +822,82 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page EXPORT_SYMBOL(bio_add_pc_page); /** - * bio_add_page - attempt to add page to bio - * @bio: destination bio - * @page: page to add - * @len: vec entry length - * @offset: vec entry offset + * __bio_try_merge_page - try appending data to an existing bvec. + * @bio: destination bio + * @page: page to add + * @len: length of the data to add + * @off: offset of the data in @page * - * Attempt to add a page to the bio_vec maplist. This will only fail - * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio. + * Try to add the data at @page + @off to the last bvec of @bio. This is a + * a useful optimisation for file systems with a block size smaller than the + * page size. + * + * Return %true on success or %false on failure. */ -int bio_add_page(struct bio *bio, struct page *page, - unsigned int len, unsigned int offset) +bool __bio_try_merge_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off) { - struct bio_vec *bv; - - /* - * cloned bio must not modify vec list - */ if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) - return 0; + return false; - /* - * For filesystems with a blocksize smaller than the pagesize - * we will often be called with the same page as last time and - * a consecutive offset. Optimize this special case. - */ if (bio->bi_vcnt > 0) { - bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; + struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; - if (page == bv->bv_page && - offset == bv->bv_offset + bv->bv_len) { + if (page == bv->bv_page && off == bv->bv_offset + bv->bv_len) { bv->bv_len += len; - goto done; + bio->bi_iter.bi_size += len; + return true; } } + return false; +} +EXPORT_SYMBOL_GPL(__bio_try_merge_page); - if (bio->bi_vcnt >= bio->bi_max_vecs) - return 0; +/** + * __bio_add_page - add page to a bio in a new segment + * @bio: destination bio + * @page: page to add + * @len: length of the data to add + * @off: offset of the data in @page + * + * Add the data at @page + @off to @bio as a new bvec. The caller must ensure + * that @bio has space for another bvec. + */ +void __bio_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off) +{ + struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt]; - bv = &bio->bi_io_vec[bio->bi_vcnt]; - bv->bv_page = page; - bv->bv_len = len; - bv->bv_offset = offset; + WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); + WARN_ON_ONCE(bio_full(bio)); + + bv->bv_page = page; + bv->bv_offset = off; + bv->bv_len = len; - bio->bi_vcnt++; -done: bio->bi_iter.bi_size += len; + bio->bi_vcnt++; +} +EXPORT_SYMBOL_GPL(__bio_add_page); + +/** + * bio_add_page - attempt to add page to bio + * @bio: destination bio + * @page: page to add + * @len: vec entry length + * @offset: vec entry offset + * + * Attempt to add a page to the bio_vec maplist. This will only fail + * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio. + */ +int bio_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) +{ + if (!__bio_try_merge_page(bio, page, len, offset)) { + if (bio_full(bio)) + return 0; + __bio_add_page(bio, page, len, offset); + } return len; } EXPORT_SYMBOL(bio_add_page); @@ -970,27 +1001,68 @@ void bio_advance(struct bio *bio, unsigned bytes) } EXPORT_SYMBOL(bio_advance); +void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, + struct bio *src, struct bvec_iter *src_iter) +{ + struct bio_vec src_bv, dst_bv; + void *src_p, *dst_p; + unsigned bytes; + + while (src_iter->bi_size && dst_iter->bi_size) { + src_bv = bio_iter_iovec(src, *src_iter); + dst_bv = bio_iter_iovec(dst, *dst_iter); + + bytes = min(src_bv.bv_len, dst_bv.bv_len); + + src_p = kmap_atomic(src_bv.bv_page); + dst_p = kmap_atomic(dst_bv.bv_page); + + memcpy(dst_p + dst_bv.bv_offset, + src_p + src_bv.bv_offset, + bytes); + + kunmap_atomic(dst_p); + kunmap_atomic(src_p); + + flush_dcache_page(dst_bv.bv_page); + + bio_advance_iter(src, src_iter, bytes); + bio_advance_iter(dst, dst_iter, bytes); + } +} +EXPORT_SYMBOL(bio_copy_data_iter); + /** - * bio_copy_data - copy contents of data buffers from one chain of bios to - * another - * @src: source bio list - * @dst: destination bio list - * - * If @src and @dst are single bios, bi_next must be NULL - otherwise, treats - * @src and @dst as linked lists of bios. + * bio_copy_data - copy contents of data buffers from one bio to another + * @src: source bio + * @dst: destination bio * * Stops when it reaches the end of either @src or @dst - that is, copies * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios). */ void bio_copy_data(struct bio *dst, struct bio *src) { - struct bvec_iter src_iter, dst_iter; - struct bio_vec src_bv, dst_bv; - void *src_p, *dst_p; - unsigned bytes; + struct bvec_iter src_iter = src->bi_iter; + struct bvec_iter dst_iter = dst->bi_iter; - src_iter = src->bi_iter; - dst_iter = dst->bi_iter; + bio_copy_data_iter(dst, &dst_iter, src, &src_iter); +} +EXPORT_SYMBOL(bio_copy_data); + +/** + * bio_list_copy_data - copy contents of data buffers from one chain of bios to + * another + * @src: source bio list + * @dst: destination bio list + * + * Stops when it reaches the end of either the @src list or @dst list - that is, + * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of + * bios). + */ +void bio_list_copy_data(struct bio *dst, struct bio *src) +{ + struct bvec_iter src_iter = src->bi_iter; + struct bvec_iter dst_iter = dst->bi_iter; while (1) { if (!src_iter.bi_size) { @@ -1009,26 +1081,10 @@ void bio_copy_data(struct bio *dst, struct bio *src) dst_iter = dst->bi_iter; } - src_bv = bio_iter_iovec(src, src_iter); - dst_bv = bio_iter_iovec(dst, dst_iter); - - bytes = min(src_bv.bv_len, dst_bv.bv_len); - - src_p = kmap_atomic(src_bv.bv_page); - dst_p = kmap_atomic(dst_bv.bv_page); - - memcpy(dst_p + dst_bv.bv_offset, - src_p + src_bv.bv_offset, - bytes); - - kunmap_atomic(dst_p); - kunmap_atomic(src_p); - - bio_advance_iter(src, &src_iter, bytes); - bio_advance_iter(dst, &dst_iter, bytes); + bio_copy_data_iter(dst, &dst_iter, src, &src_iter); } } -EXPORT_SYMBOL(bio_copy_data); +EXPORT_SYMBOL(bio_list_copy_data); struct bio_map_data { int is_our_pages; @@ -1584,6 +1640,7 @@ void bio_set_pages_dirty(struct bio *bio) set_page_dirty_lock(page); } } +EXPORT_SYMBOL_GPL(bio_set_pages_dirty); static void bio_release_pages(struct bio *bio) { @@ -1667,6 +1724,7 @@ void bio_check_pages_dirty(struct bio *bio) bio_put(bio); } } +EXPORT_SYMBOL_GPL(bio_check_pages_dirty); void generic_start_io_acct(struct request_queue *q, int rw, unsigned long sectors, struct hd_struct *part) @@ -1749,6 +1807,9 @@ again: if (!bio_integrity_endio(bio)) return; + if (WARN_ONCE(bio->bi_next, "driver left bi_next not NULL")) + bio->bi_next = NULL; + /* * Need to have a real endio function for chained bios, otherwise * various corner cases will break (like stacking block devices that @@ -1848,30 +1909,38 @@ EXPORT_SYMBOL_GPL(bio_trim); * create memory pools for biovec's in a bio_set. * use the global biovec slabs created for general use. */ -mempool_t *biovec_create_pool(int pool_entries) +int biovec_init_pool(mempool_t *pool, int pool_entries) { struct biovec_slab *bp = bvec_slabs + BVEC_POOL_MAX; - return mempool_create_slab_pool(pool_entries, bp->slab); + return mempool_init_slab_pool(pool, pool_entries, bp->slab); } -void bioset_free(struct bio_set *bs) +/* + * bioset_exit - exit a bioset initialized with bioset_init() + * + * May be called on a zeroed but uninitialized bioset (i.e. allocated with + * kzalloc()). + */ +void bioset_exit(struct bio_set *bs) { if (bs->rescue_workqueue) destroy_workqueue(bs->rescue_workqueue); + bs->rescue_workqueue = NULL; - mempool_destroy(bs->bio_pool); - mempool_destroy(bs->bvec_pool); + mempool_exit(&bs->bio_pool); + mempool_exit(&bs->bvec_pool); bioset_integrity_free(bs); - bio_put_slab(bs); - - kfree(bs); + if (bs->bio_slab) + bio_put_slab(bs); + bs->bio_slab = NULL; } -EXPORT_SYMBOL(bioset_free); +EXPORT_SYMBOL(bioset_exit); /** - * bioset_create - Create a bio_set + * bioset_init - Initialize a bio_set + * @bs: pool to initialize * @pool_size: Number of bio and bio_vecs to cache in the mempool * @front_pad: Number of bytes to allocate in front of the returned bio * @flags: Flags to modify behavior, currently %BIOSET_NEED_BVECS @@ -1890,16 +1959,12 @@ EXPORT_SYMBOL(bioset_free); * dispatch queued requests when the mempool runs out of space. * */ -struct bio_set *bioset_create(unsigned int pool_size, - unsigned int front_pad, - int flags) +int bioset_init(struct bio_set *bs, + unsigned int pool_size, + unsigned int front_pad, + int flags) { unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec); - struct bio_set *bs; - - bs = kzalloc(sizeof(*bs), GFP_KERNEL); - if (!bs) - return NULL; bs->front_pad = front_pad; @@ -1908,34 +1973,29 @@ struct bio_set *bioset_create(unsigned int pool_size, INIT_WORK(&bs->rescue_work, bio_alloc_rescue); bs->bio_slab = bio_find_or_create_slab(front_pad + back_pad); - if (!bs->bio_slab) { - kfree(bs); - return NULL; - } + if (!bs->bio_slab) + return -ENOMEM; - bs->bio_pool = mempool_create_slab_pool(pool_size, bs->bio_slab); - if (!bs->bio_pool) + if (mempool_init_slab_pool(&bs->bio_pool, pool_size, bs->bio_slab)) goto bad; - if (flags & BIOSET_NEED_BVECS) { - bs->bvec_pool = biovec_create_pool(pool_size); - if (!bs->bvec_pool) - goto bad; - } + if ((flags & BIOSET_NEED_BVECS) && + biovec_init_pool(&bs->bvec_pool, pool_size)) + goto bad; if (!(flags & BIOSET_NEED_RESCUER)) - return bs; + return 0; bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0); if (!bs->rescue_workqueue) goto bad; - return bs; + return 0; bad: - bioset_free(bs); - return NULL; + bioset_exit(bs); + return -ENOMEM; } -EXPORT_SYMBOL(bioset_create); +EXPORT_SYMBOL(bioset_init); #ifdef CONFIG_BLK_CGROUP @@ -2020,11 +2080,10 @@ static int __init init_bio(void) bio_integrity_init(); biovec_init_slabs(); - fs_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - if (!fs_bio_set) + if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS)) panic("bio: can't allocate bios\n"); - if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE)) + if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE)) panic("bio: can't create integrity pool\n"); return 0; diff --git a/block/blk-core.c b/block/blk-core.c index 85909b431eb0d..3f56be15f17e9 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -196,15 +196,8 @@ void blk_rq_init(struct request_queue *q, struct request *rq) RB_CLEAR_NODE(&rq->rb_node); rq->tag = -1; rq->internal_tag = -1; - rq->start_time = jiffies; - set_start_time_ns(rq); + rq->start_time_ns = ktime_get_ns(); rq->part = NULL; - seqcount_init(&rq->gstate_seq); - u64_stats_init(&rq->aborted_gstate_sync); - /* - * See comment of blk_mq_init_request - */ - WRITE_ONCE(rq->gstate, MQ_RQ_GEN_INC); } EXPORT_SYMBOL(blk_rq_init); @@ -280,6 +273,10 @@ static void req_bio_endio(struct request *rq, struct bio *bio, bio_advance(bio, nbytes); /* don't actually finish bio if it's part of flush sequence */ + /* + * XXX this code looks suspicious - it's not consistent with advancing + * req->bio in caller + */ if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ)) bio_endio(bio); } @@ -360,7 +357,6 @@ EXPORT_SYMBOL(blk_start_queue_async); void blk_start_queue(struct request_queue *q) { lockdep_assert_held(q->queue_lock); - WARN_ON(!in_interrupt() && !irqs_disabled()); WARN_ON_ONCE(q->mq_ops); queue_flag_clear(QUEUE_FLAG_STOPPED, q); @@ -996,18 +992,24 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, spinlock_t *lock) { struct request_queue *q; + int ret; q = kmem_cache_alloc_node(blk_requestq_cachep, gfp_mask | __GFP_ZERO, node_id); if (!q) return NULL; + INIT_LIST_HEAD(&q->queue_head); + q->last_merge = NULL; + q->end_sector = 0; + q->boundary_rq = NULL; + q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask); if (q->id < 0) goto fail_q; - q->bio_split = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - if (!q->bio_split) + ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); + if (ret) goto fail_id; q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id); @@ -1079,7 +1081,7 @@ fail_bdi: fail_stats: bdi_put(q->backing_dev_info); fail_split: - bioset_free(q->bio_split); + bioset_exit(&q->bio_split); fail_id: ida_simple_remove(&blk_queue_ida, q->id); fail_q: @@ -1173,16 +1175,8 @@ int blk_init_allocated_queue(struct request_queue *q) q->sg_reserved_size = INT_MAX; - /* Protect q->elevator from elevator_change */ - mutex_lock(&q->sysfs_lock); - - /* init elevator */ - if (elevator_init(q, NULL)) { - mutex_unlock(&q->sysfs_lock); + if (elevator_init(q)) goto out_exit_flush_rq; - } - - mutex_unlock(&q->sysfs_lock); return 0; out_exit_flush_rq: @@ -1334,6 +1328,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr) * @op: operation and flags * @bio: bio to allocate request for (can be %NULL) * @flags: BLQ_MQ_REQ_* flags + * @gfp_mask: allocator flags * * Get a free request from @q. This function may fail under memory * pressure or if @q is dead. @@ -1343,7 +1338,7 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr) * Returns request pointer on success, with @q->queue_lock *not held*. */ static struct request *__get_request(struct request_list *rl, unsigned int op, - struct bio *bio, blk_mq_req_flags_t flags) + struct bio *bio, blk_mq_req_flags_t flags, gfp_t gfp_mask) { struct request_queue *q = rl->q; struct request *rq; @@ -1352,8 +1347,6 @@ static struct request *__get_request(struct request_list *rl, unsigned int op, struct io_cq *icq = NULL; const bool is_sync = op_is_sync(op); int may_queue; - gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC : - __GFP_DIRECT_RECLAIM; req_flags_t rq_flags = RQF_ALLOCED; lockdep_assert_held(q->queue_lock); @@ -1517,8 +1510,9 @@ rq_starved: * @op: operation and flags * @bio: bio to allocate request for (can be %NULL) * @flags: BLK_MQ_REQ_* flags. + * @gfp: allocator flags * - * Get a free request from @q. If %__GFP_DIRECT_RECLAIM is set in @gfp_mask, + * Get a free request from @q. If %BLK_MQ_REQ_NOWAIT is set in @flags, * this function keeps retrying under memory pressure and fails iff @q is dead. * * Must be called with @q->queue_lock held and, @@ -1526,7 +1520,7 @@ rq_starved: * Returns request pointer on success, with @q->queue_lock *not held*. */ static struct request *get_request(struct request_queue *q, unsigned int op, - struct bio *bio, blk_mq_req_flags_t flags) + struct bio *bio, blk_mq_req_flags_t flags, gfp_t gfp) { const bool is_sync = op_is_sync(op); DEFINE_WAIT(wait); @@ -1538,7 +1532,7 @@ static struct request *get_request(struct request_queue *q, unsigned int op, rl = blk_get_rl(q, bio); /* transferred to @rq on success */ retry: - rq = __get_request(rl, op, bio, flags); + rq = __get_request(rl, op, bio, flags, gfp); if (!IS_ERR(rq)) return rq; @@ -1579,8 +1573,7 @@ static struct request *blk_old_get_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags) { struct request *rq; - gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC : - __GFP_DIRECT_RECLAIM; + gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC : GFP_NOIO; int ret = 0; WARN_ON_ONCE(q->mq_ops); @@ -1592,7 +1585,7 @@ static struct request *blk_old_get_request(struct request_queue *q, if (ret) return ERR_PTR(ret); spin_lock_irq(q->queue_lock); - rq = get_request(q, op, NULL, flags); + rq = get_request(q, op, NULL, flags, gfp_mask); if (IS_ERR(rq)) { spin_unlock_irq(q->queue_lock); blk_queue_exit(q); @@ -1607,13 +1600,13 @@ static struct request *blk_old_get_request(struct request_queue *q, } /** - * blk_get_request_flags - allocate a request + * blk_get_request - allocate a request * @q: request queue to allocate a request for * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC. * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT. */ -struct request *blk_get_request_flags(struct request_queue *q, unsigned int op, - blk_mq_req_flags_t flags) +struct request *blk_get_request(struct request_queue *q, unsigned int op, + blk_mq_req_flags_t flags) { struct request *req; @@ -1632,14 +1625,6 @@ struct request *blk_get_request_flags(struct request_queue *q, unsigned int op, return req; } -EXPORT_SYMBOL(blk_get_request_flags); - -struct request *blk_get_request(struct request_queue *q, unsigned int op, - gfp_t gfp_mask) -{ - return blk_get_request_flags(q, op, gfp_mask & __GFP_DIRECT_RECLAIM ? - 0 : BLK_MQ_REQ_NOWAIT); -} EXPORT_SYMBOL(blk_get_request); /** @@ -1660,7 +1645,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq) blk_delete_timer(rq); blk_clear_rq_complete(rq); trace_block_rq_requeue(q, rq); - wbt_requeue(q->rq_wb, &rq->issue_stat); + wbt_requeue(q->rq_wb, rq); if (rq->rq_flags & RQF_QUEUED) blk_queue_end_tag(q, rq); @@ -1767,7 +1752,7 @@ void __blk_put_request(struct request_queue *q, struct request *req) /* this is a bio leak */ WARN_ON(req->bio != NULL); - wbt_done(q->rq_wb, &req->issue_stat); + wbt_done(q->rq_wb, req); /* * Request may not have originated from ll_rw_blk. if not, @@ -2066,7 +2051,7 @@ get_rq: * Returns with the queue unlocked. */ blk_queue_enter_live(q); - req = get_request(q, bio->bi_opf, bio, 0); + req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO); if (IS_ERR(req)) { blk_queue_exit(q); __wbt_done(q->rq_wb, wb_acct); @@ -2078,7 +2063,7 @@ get_rq: goto out_unlock; } - wbt_track(&req->issue_stat, wb_acct); + wbt_track(req, wb_acct); /* * After dropping the lock and possibly sleeping here, our request @@ -2392,7 +2377,9 @@ blk_qc_t generic_make_request(struct bio *bio) if (bio->bi_opf & REQ_NOWAIT) flags = BLK_MQ_REQ_NOWAIT; - if (blk_queue_enter(q, flags) < 0) { + if (bio_flagged(bio, BIO_QUEUE_ENTERED)) + blk_queue_enter_live(q); + else if (blk_queue_enter(q, flags) < 0) { if (!blk_queue_dying(q) && (bio->bi_opf & REQ_NOWAIT)) bio_wouldblock_error(bio); else @@ -2727,7 +2714,7 @@ void blk_account_io_completion(struct request *req, unsigned int bytes) } } -void blk_account_io_done(struct request *req) +void blk_account_io_done(struct request *req, u64 now) { /* * Account IO completion. flush_rq isn't accounted as a @@ -2735,11 +2722,12 @@ void blk_account_io_done(struct request *req) * containing request is enough. */ if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { - unsigned long duration = jiffies - req->start_time; + unsigned long duration; const int rw = rq_data_dir(req); struct hd_struct *part; int cpu; + duration = nsecs_to_jiffies(now - req->start_time_ns); cpu = part_stat_lock(); part = req->part; @@ -2970,10 +2958,8 @@ static void blk_dequeue_request(struct request *rq) * and to it is freed is accounted as io that is in progress at * the driver side. */ - if (blk_account_rq(rq)) { + if (blk_account_rq(rq)) q->in_flight[rq_is_sync(rq)]++; - set_io_start_time_ns(rq); - } } /** @@ -2992,9 +2978,12 @@ void blk_start_request(struct request *req) blk_dequeue_request(req); if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) { - blk_stat_set_issue(&req->issue_stat, blk_rq_sectors(req)); + req->io_start_time_ns = ktime_get_ns(); +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW + req->throtl_size = blk_rq_sectors(req); +#endif req->rq_flags |= RQF_STATS; - wbt_issue(req->q->rq_wb, &req->issue_stat); + wbt_issue(req->q->rq_wb, req); } BUG_ON(blk_rq_is_complete(req)); @@ -3092,8 +3081,10 @@ bool blk_update_request(struct request *req, blk_status_t error, struct bio *bio = req->bio; unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes); - if (bio_bytes == bio->bi_iter.bi_size) + if (bio_bytes == bio->bi_iter.bi_size) { req->bio = bio->bi_next; + bio->bi_next = NULL; + } /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); @@ -3190,12 +3181,13 @@ EXPORT_SYMBOL_GPL(blk_unprep_request); void blk_finish_request(struct request *req, blk_status_t error) { struct request_queue *q = req->q; + u64 now = ktime_get_ns(); lockdep_assert_held(req->q->queue_lock); WARN_ON_ONCE(q->mq_ops); if (req->rq_flags & RQF_STATS) - blk_stat_add(req); + blk_stat_add(req, now); if (req->rq_flags & RQF_QUEUED) blk_queue_end_tag(q, req); @@ -3210,10 +3202,10 @@ void blk_finish_request(struct request *req, blk_status_t error) if (req->rq_flags & RQF_DONTPREP) blk_unprep_request(req); - blk_account_io_done(req); + blk_account_io_done(req, now); if (req->end_io) { - wbt_done(req->q->rq_wb, &req->issue_stat); + wbt_done(req->q->rq_wb, req); req->end_io(req, error); } else { if (blk_bidi_rq(req)) @@ -3519,7 +3511,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio *bio, *bio_src; if (!bs) - bs = fs_bio_set; + bs = &fs_bio_set; __rq_for_each_bio(bio_src, rq_src) { bio = bio_clone_fast(bio_src, gfp_mask, bs); @@ -3630,7 +3622,7 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth, blk_run_queue_async(q); else __blk_run_queue(q); - spin_unlock(q->queue_lock); + spin_unlock_irq(q->queue_lock); } static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) @@ -3678,7 +3670,6 @@ EXPORT_SYMBOL(blk_check_plugged); void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) { struct request_queue *q; - unsigned long flags; struct request *rq; LIST_HEAD(list); unsigned int depth; @@ -3698,11 +3689,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) q = NULL; depth = 0; - /* - * Save and disable interrupts here, to avoid doing it for every - * queue lock we have to take. - */ - local_irq_save(flags); while (!list_empty(&list)) { rq = list_entry_rq(list.next); list_del_init(&rq->queuelist); @@ -3715,7 +3701,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) queue_unplugged(q, depth, from_schedule); q = rq->q; depth = 0; - spin_lock(q->queue_lock); + spin_lock_irq(q->queue_lock); } /* @@ -3742,8 +3728,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) */ if (q) queue_unplugged(q, depth, from_schedule); - - local_irq_restore(flags); } void blk_finish_plug(struct blk_plug *plug) diff --git a/block/blk-integrity.c b/block/blk-integrity.c index feb30570eaf56..6121611e13164 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -333,34 +333,34 @@ static ssize_t integrity_device_show(struct blk_integrity *bi, char *page) } static struct integrity_sysfs_entry integrity_format_entry = { - .attr = { .name = "format", .mode = S_IRUGO }, + .attr = { .name = "format", .mode = 0444 }, .show = integrity_format_show, }; static struct integrity_sysfs_entry integrity_tag_size_entry = { - .attr = { .name = "tag_size", .mode = S_IRUGO }, + .attr = { .name = "tag_size", .mode = 0444 }, .show = integrity_tag_size_show, }; static struct integrity_sysfs_entry integrity_interval_entry = { - .attr = { .name = "protection_interval_bytes", .mode = S_IRUGO }, + .attr = { .name = "protection_interval_bytes", .mode = 0444 }, .show = integrity_interval_show, }; static struct integrity_sysfs_entry integrity_verify_entry = { - .attr = { .name = "read_verify", .mode = S_IRUGO | S_IWUSR }, + .attr = { .name = "read_verify", .mode = 0644 }, .show = integrity_verify_show, .store = integrity_verify_store, }; static struct integrity_sysfs_entry integrity_generate_entry = { - .attr = { .name = "write_generate", .mode = S_IRUGO | S_IWUSR }, + .attr = { .name = "write_generate", .mode = 0644 }, .show = integrity_generate_show, .store = integrity_generate_store, }; static struct integrity_sysfs_entry integrity_device_entry = { - .attr = { .name = "device_is_integrity_capable", .mode = S_IRUGO }, + .attr = { .name = "device_is_integrity_capable", .mode = 0444 }, .show = integrity_device_show, }; diff --git a/block/blk-lib.c b/block/blk-lib.c index a676084d47404..8faa70f26fcd1 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -62,10 +62,16 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, unsigned int req_sects; sector_t end_sect, tmp; - /* Make sure bi_size doesn't overflow */ - req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9); + /* + * Issue in chunks of the user defined max discard setting, + * ensuring that bi_size doesn't overflow + */ + req_sects = min_t(sector_t, nr_sects, + q->limits.max_discard_sectors); + if (req_sects > UINT_MAX >> 9) + req_sects = UINT_MAX >> 9; - /** + /* * If splitting a request, and the next starting sector would be * misaligned, stop the discard at the previous aligned sector. */ diff --git a/block/blk-merge.c b/block/blk-merge.c index 782940c65d8a7..aaec38cc37b86 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -188,16 +188,16 @@ void blk_queue_split(struct request_queue *q, struct bio **bio) switch (bio_op(*bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: - split = blk_bio_discard_split(q, *bio, q->bio_split, &nsegs); + split = blk_bio_discard_split(q, *bio, &q->bio_split, &nsegs); break; case REQ_OP_WRITE_ZEROES: - split = blk_bio_write_zeroes_split(q, *bio, q->bio_split, &nsegs); + split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split, &nsegs); break; case REQ_OP_WRITE_SAME: - split = blk_bio_write_same_split(q, *bio, q->bio_split, &nsegs); + split = blk_bio_write_same_split(q, *bio, &q->bio_split, &nsegs); break; default: - split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs); + split = blk_bio_segment_split(q, *bio, &q->bio_split, &nsegs); break; } @@ -210,6 +210,16 @@ void blk_queue_split(struct request_queue *q, struct bio **bio) /* there isn't chance to merge the splitted bio */ split->bi_opf |= REQ_NOMERGE; + /* + * Since we're recursing into make_request here, ensure + * that we mark this bio as already having entered the queue. + * If not, and the queue is going away, we can get stuck + * forever on waiting for the queue reference to drop. But + * that will never happen, as we're already holding a + * reference to it. + */ + bio_set_flag(*bio, BIO_QUEUE_ENTERED); + bio_chain(split, *bio); trace_block_split(q, split, (*bio)->bi_iter.bi_sector); generic_make_request(*bio); @@ -724,13 +734,12 @@ static struct request *attempt_merge(struct request_queue *q, } /* - * At this point we have either done a back merge - * or front merge. We need the smaller start_time of - * the merged requests to be the current request - * for accounting purposes. + * At this point we have either done a back merge or front merge. We + * need the smaller start_time_ns of the merged requests to be the + * current request for accounting purposes. */ - if (time_after(req->start_time, next->start_time)) - req->start_time = next->start_time; + if (next->start_time_ns < req->start_time_ns) + req->start_time_ns = next->start_time_ns; req->biotail->bi_next = next->bio; req->biotail = next->biotail; diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 3080e18cb8590..ffa622366922f 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -344,7 +344,6 @@ static const char *const rqf_name[] = { RQF_NAME(STATS), RQF_NAME(SPECIAL_PAYLOAD), RQF_NAME(ZONE_WRITE_LOCKED), - RQF_NAME(MQ_TIMEOUT_EXPIRED), RQF_NAME(MQ_POLL_SLEPT), }; #undef RQF_NAME diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 25c14c58385c8..56c493c6cd903 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -268,19 +268,16 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge); /* - * Reverse check our software queue for entries that we could potentially - * merge with. Currently includes a hand-wavy stop count of 8, to not spend - * too much time checking for merges. + * Iterate list of requests and see if we can merge this bio with any + * of them. */ -static bool blk_mq_attempt_merge(struct request_queue *q, - struct blk_mq_ctx *ctx, struct bio *bio) +bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, + struct bio *bio) { struct request *rq; int checked = 8; - lockdep_assert_held(&ctx->lock); - - list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) { + list_for_each_entry_reverse(rq, list, queuelist) { bool merged = false; if (!checked--) @@ -305,13 +302,30 @@ static bool blk_mq_attempt_merge(struct request_queue *q, continue; } - if (merged) - ctx->rq_merged++; return merged; } return false; } +EXPORT_SYMBOL_GPL(blk_mq_bio_list_merge); + +/* + * Reverse check our software queue for entries that we could potentially + * merge with. Currently includes a hand-wavy stop count of 8, to not spend + * too much time checking for merges. + */ +static bool blk_mq_attempt_merge(struct request_queue *q, + struct blk_mq_ctx *ctx, struct bio *bio) +{ + lockdep_assert_held(&ctx->lock); + + if (blk_mq_bio_list_merge(q, &ctx->rq_list, bio)) { + ctx->rq_merged++; + return true; + } + + return false; +} bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio) { @@ -571,6 +585,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) if (!e) { q->elevator = NULL; + q->nr_requests = q->tag_set->queue_depth; return 0; } @@ -633,14 +648,3 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) blk_mq_sched_tags_teardown(q); q->elevator = NULL; } - -int blk_mq_sched_init(struct request_queue *q) -{ - int ret; - - mutex_lock(&q->sysfs_lock); - ret = elevator_init(q, NULL); - mutex_unlock(&q->sysfs_lock); - - return ret; -} diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 1e9c9018ace12..0cb8f938dff9d 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -33,8 +33,6 @@ int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx, void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx); -int blk_mq_sched_init(struct request_queue *q); - static inline bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio) { diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index a54b4b070f1c7..aafb44224c896 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -166,15 +166,15 @@ static struct attribute *default_ctx_attrs[] = { }; static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = { - .attr = {.name = "nr_tags", .mode = S_IRUGO }, + .attr = {.name = "nr_tags", .mode = 0444 }, .show = blk_mq_hw_sysfs_nr_tags_show, }; static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_reserved_tags = { - .attr = {.name = "nr_reserved_tags", .mode = S_IRUGO }, + .attr = {.name = "nr_reserved_tags", .mode = 0444 }, .show = blk_mq_hw_sysfs_nr_reserved_tags_show, }; static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_cpus = { - .attr = {.name = "cpu_list", .mode = S_IRUGO }, + .attr = {.name = "cpu_list", .mode = 0444 }, .show = blk_mq_hw_sysfs_cpus_show, }; diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 336dde07b2306..70356a2a11ab1 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -134,6 +134,8 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) ws = bt_wait_ptr(bt, data->hctx); drop_ctx = data->ctx == NULL; do { + struct sbitmap_queue *bt_prev; + /* * We're out of tags on this hardware queue, kick any * pending IO submits before going to sleep waiting for @@ -159,6 +161,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) if (data->ctx) blk_mq_put_ctx(data->ctx); + bt_prev = bt; io_schedule(); data->ctx = blk_mq_get_ctx(data->q); @@ -170,6 +173,15 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) bt = &tags->bitmap_tags; finish_wait(&ws->wait, &wait); + + /* + * If destination hw queue is changed, fake wake up on + * previous queue for compensating the wake up miss, so + * other allocations on previous queue won't be starved. + */ + if (bt != bt_prev) + sbitmap_queue_wake_up(bt_prev); + ws = bt_wait_ptr(bt, data->hctx); } while (1); @@ -259,7 +271,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * test and set the bit before assining ->rqs[]. */ rq = tags->rqs[bitnr]; - if (rq) + if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) iter_data->fn(rq, iter_data->data, reserved); return true; diff --git a/block/blk-mq.c b/block/blk-mq.c index c3621453ad879..d2de0a719ab80 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -95,18 +95,15 @@ static void blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, { struct mq_inflight *mi = priv; - if (blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) { - /* - * index[0] counts the specific partition that was asked - * for. index[1] counts the ones that are active on the - * whole device, so increment that if mi->part is indeed - * a partition, and not a whole device. - */ - if (rq->part == mi->part) - mi->inflight[0]++; - if (mi->part->partno) - mi->inflight[1]++; - } + /* + * index[0] counts the specific partition that was asked for. index[1] + * counts the ones that are active on the whole device, so increment + * that if mi->part is indeed a partition, and not a whole device. + */ + if (rq->part == mi->part) + mi->inflight[0]++; + if (mi->part->partno) + mi->inflight[1]++; } void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part, @@ -118,6 +115,25 @@ void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part, blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); } +static void blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx, + struct request *rq, void *priv, + bool reserved) +{ + struct mq_inflight *mi = priv; + + if (rq->part == mi->part) + mi->inflight[rq_data_dir(rq)]++; +} + +void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, + unsigned int inflight[2]) +{ + struct mq_inflight mi = { .part = part, .inflight = inflight, }; + + inflight[0] = inflight[1] = 0; + blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi); +} + void blk_freeze_queue_start(struct request_queue *q) { int freeze_depth; @@ -293,7 +309,8 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, RB_CLEAR_NODE(&rq->rb_node); rq->rq_disk = NULL; rq->part = NULL; - rq->start_time = jiffies; + rq->start_time_ns = ktime_get_ns(); + rq->io_start_time_ns = 0; rq->nr_phys_segments = 0; #if defined(CONFIG_BLK_DEV_INTEGRITY) rq->nr_integrity_segments = 0; @@ -312,11 +329,10 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, #ifdef CONFIG_BLK_CGROUP rq->rl = NULL; - set_start_time_ns(rq); - rq->io_start_time_ns = 0; #endif data->ctx->rq_dispatched[op_is_sync(op)]++; + refcount_set(&rq->ref, 1); return rq; } @@ -345,9 +361,11 @@ static struct request *blk_mq_get_request(struct request_queue *q, /* * Flush requests are special and go directly to the - * dispatch list. + * dispatch list. Don't include reserved tags in the + * limiting, as it isn't useful. */ - if (!op_is_flush(op) && e->type->ops.mq.limit_depth) + if (!op_is_flush(op) && e->type->ops.mq.limit_depth && + !(data->flags & BLK_MQ_REQ_RESERVED)) e->type->ops.mq.limit_depth(op, data); } @@ -448,13 +466,27 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); +static void __blk_mq_free_request(struct request *rq) +{ + struct request_queue *q = rq->q; + struct blk_mq_ctx *ctx = rq->mq_ctx; + struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu); + const int sched_tag = rq->internal_tag; + + if (rq->tag != -1) + blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag); + if (sched_tag != -1) + blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag); + blk_mq_sched_restart(hctx); + blk_queue_exit(q); +} + void blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu); - const int sched_tag = rq->internal_tag; if (rq->rq_flags & RQF_ELVPRIV) { if (e && e->type->ops.mq.finish_request) @@ -472,27 +504,30 @@ void blk_mq_free_request(struct request *rq) if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) laptop_io_completion(q->backing_dev_info); - wbt_done(q->rq_wb, &rq->issue_stat); + wbt_done(q->rq_wb, rq); if (blk_rq_rl(rq)) blk_put_rl(blk_rq_rl(rq)); - blk_mq_rq_update_state(rq, MQ_RQ_IDLE); - if (rq->tag != -1) - blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag); - if (sched_tag != -1) - blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag); - blk_mq_sched_restart(hctx); - blk_queue_exit(q); + WRITE_ONCE(rq->state, MQ_RQ_IDLE); + if (refcount_dec_and_test(&rq->ref)) + __blk_mq_free_request(rq); } EXPORT_SYMBOL_GPL(blk_mq_free_request); inline void __blk_mq_end_request(struct request *rq, blk_status_t error) { - blk_account_io_done(rq); + u64 now = ktime_get_ns(); + + if (rq->rq_flags & RQF_STATS) { + blk_mq_poll_stats_start(rq->q); + blk_stat_add(rq, now); + } + + blk_account_io_done(rq, now); if (rq->end_io) { - wbt_done(rq->q->rq_wb, &rq->issue_stat); + wbt_done(rq->q->rq_wb, rq); rq->end_io(rq, error); } else { if (unlikely(blk_bidi_rq(rq))) @@ -523,15 +558,12 @@ static void __blk_mq_complete_request(struct request *rq) bool shared = false; int cpu; - WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT); - blk_mq_rq_update_state(rq, MQ_RQ_COMPLETE); + if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) != + MQ_RQ_IN_FLIGHT) + return; if (rq->internal_tag != -1) blk_mq_sched_completed_request(rq); - if (rq->rq_flags & RQF_STATS) { - blk_mq_poll_stats_start(rq->q); - blk_stat_add(rq); - } if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) { rq->q->softirq_done_fn(rq); @@ -573,36 +605,6 @@ static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx) *srcu_idx = srcu_read_lock(hctx->srcu); } -static void blk_mq_rq_update_aborted_gstate(struct request *rq, u64 gstate) -{ - unsigned long flags; - - /* - * blk_mq_rq_aborted_gstate() is used from the completion path and - * can thus be called from irq context. u64_stats_fetch in the - * middle of update on the same CPU leads to lockup. Disable irq - * while updating. - */ - local_irq_save(flags); - u64_stats_update_begin(&rq->aborted_gstate_sync); - rq->aborted_gstate = gstate; - u64_stats_update_end(&rq->aborted_gstate_sync); - local_irq_restore(flags); -} - -static u64 blk_mq_rq_aborted_gstate(struct request *rq) -{ - unsigned int start; - u64 aborted_gstate; - - do { - start = u64_stats_fetch_begin(&rq->aborted_gstate_sync); - aborted_gstate = rq->aborted_gstate; - } while (u64_stats_fetch_retry(&rq->aborted_gstate_sync, start)); - - return aborted_gstate; -} - /** * blk_mq_complete_request - end I/O on a request * @rq: the request being processed @@ -613,28 +615,9 @@ static u64 blk_mq_rq_aborted_gstate(struct request *rq) **/ void blk_mq_complete_request(struct request *rq) { - struct request_queue *q = rq->q; - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu); - int srcu_idx; - - if (unlikely(blk_should_fake_timeout(q))) + if (unlikely(blk_should_fake_timeout(rq->q))) return; - - /* - * If @rq->aborted_gstate equals the current instance, timeout is - * claiming @rq and we lost. This is synchronized through - * hctx_lock(). See blk_mq_timeout_work() for details. - * - * Completion path never blocks and we can directly use RCU here - * instead of hctx_lock() which can be either RCU or SRCU. - * However, that would complicate paths which want to synchronize - * against us. Let stay in sync with the issue path so that - * hctx_lock() covers both issue and completion paths. - */ - hctx_lock(hctx, &srcu_idx); - if (blk_mq_rq_aborted_gstate(rq) != rq->gstate) - __blk_mq_complete_request(rq); - hctx_unlock(hctx, srcu_idx); + __blk_mq_complete_request(rq); } EXPORT_SYMBOL(blk_mq_complete_request); @@ -653,32 +636,18 @@ void blk_mq_start_request(struct request *rq) trace_block_rq_issue(q, rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) { - blk_stat_set_issue(&rq->issue_stat, blk_rq_sectors(rq)); + rq->io_start_time_ns = ktime_get_ns(); +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW + rq->throtl_size = blk_rq_sectors(rq); +#endif rq->rq_flags |= RQF_STATS; - wbt_issue(q->rq_wb, &rq->issue_stat); + wbt_issue(q->rq_wb, rq); } WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE); - /* - * Mark @rq in-flight which also advances the generation number, - * and register for timeout. Protect with a seqcount to allow the - * timeout path to read both @rq->gstate and @rq->deadline - * coherently. - * - * This is the only place where a request is marked in-flight. If - * the timeout path reads an in-flight @rq->gstate, the - * @rq->deadline it reads together under @rq->gstate_seq is - * guaranteed to be the matching one. - */ - preempt_disable(); - write_seqcount_begin(&rq->gstate_seq); - - blk_mq_rq_update_state(rq, MQ_RQ_IN_FLIGHT); blk_add_timer(rq); - - write_seqcount_end(&rq->gstate_seq); - preempt_enable(); + WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT); if (q->dma_drain_size && blk_rq_bytes(rq)) { /* @@ -691,11 +660,6 @@ void blk_mq_start_request(struct request *rq) } EXPORT_SYMBOL(blk_mq_start_request); -/* - * When we reach here because queue is busy, it's safe to change the state - * to IDLE without checking @rq->aborted_gstate because we should still be - * holding the RCU read lock and thus protected against timeout. - */ static void __blk_mq_requeue_request(struct request *rq) { struct request_queue *q = rq->q; @@ -703,10 +667,10 @@ static void __blk_mq_requeue_request(struct request *rq) blk_mq_put_driver_tag(rq); trace_block_rq_requeue(q, rq); - wbt_requeue(q->rq_wb, &rq->issue_stat); + wbt_requeue(q->rq_wb, rq); - if (blk_mq_rq_state(rq) != MQ_RQ_IDLE) { - blk_mq_rq_update_state(rq, MQ_RQ_IDLE); + if (blk_mq_request_started(rq)) { + WRITE_ONCE(rq->state, MQ_RQ_IDLE); if (q->dma_drain_size && blk_rq_bytes(rq)) rq->nr_phys_segments--; } @@ -804,101 +768,79 @@ struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag) } EXPORT_SYMBOL(blk_mq_tag_to_rq); -struct blk_mq_timeout_data { - unsigned long next; - unsigned int next_set; - unsigned int nr_expired; -}; - static void blk_mq_rq_timed_out(struct request *req, bool reserved) { - const struct blk_mq_ops *ops = req->q->mq_ops; - enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER; - - req->rq_flags |= RQF_MQ_TIMEOUT_EXPIRED; - - if (ops->timeout) - ret = ops->timeout(req, reserved); + if (req->q->mq_ops->timeout) { + enum blk_eh_timer_return ret; - switch (ret) { - case BLK_EH_HANDLED: - __blk_mq_complete_request(req); - break; - case BLK_EH_RESET_TIMER: - /* - * As nothing prevents from completion happening while - * ->aborted_gstate is set, this may lead to ignored - * completions and further spurious timeouts. - */ - blk_mq_rq_update_aborted_gstate(req, 0); - blk_add_timer(req); - break; - case BLK_EH_NOT_HANDLED: - break; - default: - printk(KERN_ERR "block: bad eh return: %d\n", ret); - break; + ret = req->q->mq_ops->timeout(req, reserved); + if (ret == BLK_EH_DONE) + return; + WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER); } + + blk_add_timer(req); } -static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, - struct request *rq, void *priv, bool reserved) +static bool blk_mq_req_expired(struct request *rq, unsigned long *next) { - struct blk_mq_timeout_data *data = priv; - unsigned long gstate, deadline; - int start; - - might_sleep(); + unsigned long deadline; - if (rq->rq_flags & RQF_MQ_TIMEOUT_EXPIRED) - return; + if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT) + return false; - /* read coherent snapshots of @rq->state_gen and @rq->deadline */ - while (true) { - start = read_seqcount_begin(&rq->gstate_seq); - gstate = READ_ONCE(rq->gstate); - deadline = blk_rq_deadline(rq); - if (!read_seqcount_retry(&rq->gstate_seq, start)) - break; - cond_resched(); - } + deadline = blk_rq_deadline(rq); + if (time_after_eq(jiffies, deadline)) + return true; - /* if in-flight && overdue, mark for abortion */ - if ((gstate & MQ_RQ_STATE_MASK) == MQ_RQ_IN_FLIGHT && - time_after_eq(jiffies, deadline)) { - blk_mq_rq_update_aborted_gstate(rq, gstate); - data->nr_expired++; - hctx->nr_expired++; - } else if (!data->next_set || time_after(data->next, deadline)) { - data->next = deadline; - data->next_set = 1; - } + if (*next == 0) + *next = deadline; + else if (time_after(*next, deadline)) + *next = deadline; + return false; } -static void blk_mq_terminate_expired(struct blk_mq_hw_ctx *hctx, +static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { + unsigned long *next = priv; + + /* + * Just do a quick check if it is expired before locking the request in + * so we're not unnecessarilly synchronizing across CPUs. + */ + if (!blk_mq_req_expired(rq, next)) + return; + /* - * We marked @rq->aborted_gstate and waited for RCU. If there were - * completions that we lost to, they would have finished and - * updated @rq->gstate by now; otherwise, the completion path is - * now guaranteed to see @rq->aborted_gstate and yield. If - * @rq->aborted_gstate still matches @rq->gstate, @rq is ours. + * We have reason to believe the request may be expired. Take a + * reference on the request to lock this request lifetime into its + * currently allocated context to prevent it from being reallocated in + * the event the completion by-passes this timeout handler. + * + * If the reference was already released, then the driver beat the + * timeout handler to posting a natural completion. */ - if (!(rq->rq_flags & RQF_MQ_TIMEOUT_EXPIRED) && - READ_ONCE(rq->gstate) == rq->aborted_gstate) + if (!refcount_inc_not_zero(&rq->ref)) + return; + + /* + * The request is now locked and cannot be reallocated underneath the + * timeout handler's processing. Re-verify this exact request is truly + * expired; if it is not expired, then the request was completed and + * reallocated as a new request. + */ + if (blk_mq_req_expired(rq, next)) blk_mq_rq_timed_out(rq, reserved); + if (refcount_dec_and_test(&rq->ref)) + __blk_mq_free_request(rq); } static void blk_mq_timeout_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, timeout_work); - struct blk_mq_timeout_data data = { - .next = 0, - .next_set = 0, - .nr_expired = 0, - }; + unsigned long next = 0; struct blk_mq_hw_ctx *hctx; int i; @@ -918,39 +860,10 @@ static void blk_mq_timeout_work(struct work_struct *work) if (!percpu_ref_tryget(&q->q_usage_counter)) return; - /* scan for the expired ones and set their ->aborted_gstate */ - blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &data); - - if (data.nr_expired) { - bool has_rcu = false; - - /* - * Wait till everyone sees ->aborted_gstate. The - * sequential waits for SRCUs aren't ideal. If this ever - * becomes a problem, we can add per-hw_ctx rcu_head and - * wait in parallel. - */ - queue_for_each_hw_ctx(q, hctx, i) { - if (!hctx->nr_expired) - continue; - - if (!(hctx->flags & BLK_MQ_F_BLOCKING)) - has_rcu = true; - else - synchronize_srcu(hctx->srcu); - - hctx->nr_expired = 0; - } - if (has_rcu) - synchronize_rcu(); + blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &next); - /* terminate the ones we won */ - blk_mq_queue_tag_busy_iter(q, blk_mq_terminate_expired, NULL); - } - - if (data.next_set) { - data.next = blk_rq_timeout(round_jiffies_up(data.next)); - mod_timer(&q->timeout, data.next); + if (next != 0) { + mod_timer(&q->timeout, next); } else { /* * Request timeouts are handled as a forward rolling timer. If @@ -1013,7 +926,7 @@ static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr, struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; spin_lock(&ctx->lock); - if (unlikely(!list_empty(&ctx->rq_list))) { + if (!list_empty(&ctx->rq_list)) { dispatch_data->rq = list_entry_rq(ctx->rq_list.next); list_del_init(&dispatch_data->rq->queuelist); if (list_empty(&ctx->rq_list)) @@ -1562,7 +1475,7 @@ static void blk_mq_run_work_fn(struct work_struct *work) * If we are stopped, don't run the queue. */ if (test_bit(BLK_MQ_S_STOPPED, &hctx->state)) - clear_bit(BLK_MQ_S_STOPPED, &hctx->state); + return; __blk_mq_run_hw_queue(hctx); } @@ -1700,15 +1613,6 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio) blk_account_io_start(rq, true); } -static inline void blk_mq_queue_io(struct blk_mq_hw_ctx *hctx, - struct blk_mq_ctx *ctx, - struct request *rq) -{ - spin_lock(&ctx->lock); - __blk_mq_insert_request(hctx, rq, false); - spin_unlock(&ctx->lock); -} - static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq) { if (rq->tag != -1) @@ -1866,7 +1770,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) return BLK_QC_T_NONE; } - wbt_track(&rq->issue_stat, wb_acct); + wbt_track(rq, wb_acct); cookie = request_to_qc_t(data.hctx, rq); @@ -1933,15 +1837,10 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_mq_put_ctx(data.ctx); blk_mq_bio_to_request(rq, bio); blk_mq_try_issue_directly(data.hctx, rq, &cookie); - } else if (q->elevator) { - blk_mq_put_ctx(data.ctx); - blk_mq_bio_to_request(rq, bio); - blk_mq_sched_insert_request(rq, false, true, true); } else { blk_mq_put_ctx(data.ctx); blk_mq_bio_to_request(rq, bio); - blk_mq_queue_io(data.hctx, data.ctx, rq); - blk_mq_run_hw_queue(data.hctx, true); + blk_mq_sched_insert_request(rq, false, true, true); } return cookie; @@ -2040,15 +1939,7 @@ static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, return ret; } - seqcount_init(&rq->gstate_seq); - u64_stats_init(&rq->aborted_gstate_sync); - /* - * start gstate with gen 1 instead of 0, otherwise it will be equal - * to aborted_gstate, and be identified timed out by - * blk_mq_terminate_expired. - */ - WRITE_ONCE(rq->gstate, MQ_RQ_GEN_INC); - + WRITE_ONCE(rq->state, MQ_RQ_IDLE); return 0; } @@ -2349,6 +2240,7 @@ static void blk_mq_map_swqueue(struct request_queue *q) queue_for_each_hw_ctx(q, hctx, i) { cpumask_clear(hctx->cpumask); hctx->nr_ctx = 0; + hctx->dispatch_from = NULL; } /* @@ -2681,7 +2573,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, if (!(set->flags & BLK_MQ_F_NO_SCHED)) { int ret; - ret = blk_mq_sched_init(q); + ret = elevator_init_mq(q); if (ret) return ERR_PTR(ret); } diff --git a/block/blk-mq.h b/block/blk-mq.h index 89b5cd3a6c708..89231e439b2f6 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -30,20 +30,6 @@ struct blk_mq_ctx { struct kobject kobj; } ____cacheline_aligned_in_smp; -/* - * Bits for request->gstate. The lower two bits carry MQ_RQ_* state value - * and the upper bits the generation number. - */ -enum mq_rq_state { - MQ_RQ_IDLE = 0, - MQ_RQ_IN_FLIGHT = 1, - MQ_RQ_COMPLETE = 2, - - MQ_RQ_STATE_BITS = 2, - MQ_RQ_STATE_MASK = (1 << MQ_RQ_STATE_BITS) - 1, - MQ_RQ_GEN_INC = 1 << MQ_RQ_STATE_BITS, -}; - void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_free_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); @@ -107,33 +93,9 @@ void blk_mq_release(struct request_queue *q); * blk_mq_rq_state() - read the current MQ_RQ_* state of a request * @rq: target request. */ -static inline int blk_mq_rq_state(struct request *rq) +static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) { - return READ_ONCE(rq->gstate) & MQ_RQ_STATE_MASK; -} - -/** - * blk_mq_rq_update_state() - set the current MQ_RQ_* state of a request - * @rq: target request. - * @state: new state to set. - * - * Set @rq's state to @state. The caller is responsible for ensuring that - * there are no other updaters. A request can transition into IN_FLIGHT - * only from IDLE and doing so increments the generation number. - */ -static inline void blk_mq_rq_update_state(struct request *rq, - enum mq_rq_state state) -{ - u64 old_val = READ_ONCE(rq->gstate); - u64 new_val = (old_val & ~MQ_RQ_STATE_MASK) | state; - - if (state == MQ_RQ_IN_FLIGHT) { - WARN_ON_ONCE((old_val & MQ_RQ_STATE_MASK) != MQ_RQ_IDLE); - new_val += MQ_RQ_GEN_INC; - } - - /* avoid exposing interim values */ - WRITE_ONCE(rq->gstate, new_val); + return READ_ONCE(rq->state); } static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, @@ -188,7 +150,9 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) } void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part, - unsigned int inflight[2]); + unsigned int inflight[2]); +void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, + unsigned int inflight[2]); static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx) { diff --git a/block/blk-stat.c b/block/blk-stat.c index bd365a95fcf86..175c143ac5b91 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -47,19 +47,15 @@ static void __blk_stat_add(struct blk_rq_stat *stat, u64 value) stat->nr_samples++; } -void blk_stat_add(struct request *rq) +void blk_stat_add(struct request *rq, u64 now) { struct request_queue *q = rq->q; struct blk_stat_callback *cb; struct blk_rq_stat *stat; int bucket; - u64 now, value; + u64 value; - now = __blk_stat_time(ktime_to_ns(ktime_get())); - if (now < blk_stat_time(&rq->issue_stat)) - return; - - value = now - blk_stat_time(&rq->issue_stat); + value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0; blk_throtl_stat_add(rq, value); diff --git a/block/blk-stat.h b/block/blk-stat.h index 2dd36347252ab..78399cdde9c91 100644 --- a/block/blk-stat.h +++ b/block/blk-stat.h @@ -8,21 +8,6 @@ #include <linux/rcupdate.h> #include <linux/timer.h> -/* - * from upper: - * 3 bits: reserved for other usage - * 12 bits: size - * 49 bits: time - */ -#define BLK_STAT_RES_BITS 3 -#define BLK_STAT_SIZE_BITS 12 -#define BLK_STAT_RES_SHIFT (64 - BLK_STAT_RES_BITS) -#define BLK_STAT_SIZE_SHIFT (BLK_STAT_RES_SHIFT - BLK_STAT_SIZE_BITS) -#define BLK_STAT_TIME_MASK ((1ULL << BLK_STAT_SIZE_SHIFT) - 1) -#define BLK_STAT_SIZE_MASK \ - (((1ULL << BLK_STAT_SIZE_BITS) - 1) << BLK_STAT_SIZE_SHIFT) -#define BLK_STAT_RES_MASK (~((1ULL << BLK_STAT_RES_SHIFT) - 1)) - /** * struct blk_stat_callback - Block statistics callback. * @@ -80,35 +65,7 @@ struct blk_stat_callback { struct blk_queue_stats *blk_alloc_queue_stats(void); void blk_free_queue_stats(struct blk_queue_stats *); -void blk_stat_add(struct request *); - -static inline u64 __blk_stat_time(u64 time) -{ - return time & BLK_STAT_TIME_MASK; -} - -static inline u64 blk_stat_time(struct blk_issue_stat *stat) -{ - return __blk_stat_time(stat->stat); -} - -static inline sector_t blk_capped_size(sector_t size) -{ - return size & ((1ULL << BLK_STAT_SIZE_BITS) - 1); -} - -static inline sector_t blk_stat_size(struct blk_issue_stat *stat) -{ - return (stat->stat & BLK_STAT_SIZE_MASK) >> BLK_STAT_SIZE_SHIFT; -} - -static inline void blk_stat_set_issue(struct blk_issue_stat *stat, - sector_t size) -{ - stat->stat = (stat->stat & BLK_STAT_RES_MASK) | - (ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK) | - (((u64)blk_capped_size(size)) << BLK_STAT_SIZE_SHIFT); -} +void blk_stat_add(struct request *rq, u64 now); /* record time/size info in request but not add a callback */ void blk_stat_enable_accounting(struct request_queue *q); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index d00d1b0ec1099..94987b1f69e15 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -491,188 +491,198 @@ static ssize_t queue_wc_store(struct request_queue *q, const char *page, return count; } +static ssize_t queue_fua_show(struct request_queue *q, char *page) +{ + return sprintf(page, "%u\n", test_bit(QUEUE_FLAG_FUA, &q->queue_flags)); +} + static ssize_t queue_dax_show(struct request_queue *q, char *page) { return queue_var_show(blk_queue_dax(q), page); } static struct queue_sysfs_entry queue_requests_entry = { - .attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "nr_requests", .mode = 0644 }, .show = queue_requests_show, .store = queue_requests_store, }; static struct queue_sysfs_entry queue_ra_entry = { - .attr = {.name = "read_ahead_kb", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "read_ahead_kb", .mode = 0644 }, .show = queue_ra_show, .store = queue_ra_store, }; static struct queue_sysfs_entry queue_max_sectors_entry = { - .attr = {.name = "max_sectors_kb", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "max_sectors_kb", .mode = 0644 }, .show = queue_max_sectors_show, .store = queue_max_sectors_store, }; static struct queue_sysfs_entry queue_max_hw_sectors_entry = { - .attr = {.name = "max_hw_sectors_kb", .mode = S_IRUGO }, + .attr = {.name = "max_hw_sectors_kb", .mode = 0444 }, .show = queue_max_hw_sectors_show, }; static struct queue_sysfs_entry queue_max_segments_entry = { - .attr = {.name = "max_segments", .mode = S_IRUGO }, + .attr = {.name = "max_segments", .mode = 0444 }, .show = queue_max_segments_show, }; static struct queue_sysfs_entry queue_max_discard_segments_entry = { - .attr = {.name = "max_discard_segments", .mode = S_IRUGO }, + .attr = {.name = "max_discard_segments", .mode = 0444 }, .show = queue_max_discard_segments_show, }; static struct queue_sysfs_entry queue_max_integrity_segments_entry = { - .attr = {.name = "max_integrity_segments", .mode = S_IRUGO }, + .attr = {.name = "max_integrity_segments", .mode = 0444 }, .show = queue_max_integrity_segments_show, }; static struct queue_sysfs_entry queue_max_segment_size_entry = { - .attr = {.name = "max_segment_size", .mode = S_IRUGO }, + .attr = {.name = "max_segment_size", .mode = 0444 }, .show = queue_max_segment_size_show, }; static struct queue_sysfs_entry queue_iosched_entry = { - .attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "scheduler", .mode = 0644 }, .show = elv_iosched_show, .store = elv_iosched_store, }; static struct queue_sysfs_entry queue_hw_sector_size_entry = { - .attr = {.name = "hw_sector_size", .mode = S_IRUGO }, + .attr = {.name = "hw_sector_size", .mode = 0444 }, .show = queue_logical_block_size_show, }; static struct queue_sysfs_entry queue_logical_block_size_entry = { - .attr = {.name = "logical_block_size", .mode = S_IRUGO }, + .attr = {.name = "logical_block_size", .mode = 0444 }, .show = queue_logical_block_size_show, }; static struct queue_sysfs_entry queue_physical_block_size_entry = { - .attr = {.name = "physical_block_size", .mode = S_IRUGO }, + .attr = {.name = "physical_block_size", .mode = 0444 }, .show = queue_physical_block_size_show, }; static struct queue_sysfs_entry queue_chunk_sectors_entry = { - .attr = {.name = "chunk_sectors", .mode = S_IRUGO }, + .attr = {.name = "chunk_sectors", .mode = 0444 }, .show = queue_chunk_sectors_show, }; static struct queue_sysfs_entry queue_io_min_entry = { - .attr = {.name = "minimum_io_size", .mode = S_IRUGO }, + .attr = {.name = "minimum_io_size", .mode = 0444 }, .show = queue_io_min_show, }; static struct queue_sysfs_entry queue_io_opt_entry = { - .attr = {.name = "optimal_io_size", .mode = S_IRUGO }, + .attr = {.name = "optimal_io_size", .mode = 0444 }, .show = queue_io_opt_show, }; static struct queue_sysfs_entry queue_discard_granularity_entry = { - .attr = {.name = "discard_granularity", .mode = S_IRUGO }, + .attr = {.name = "discard_granularity", .mode = 0444 }, .show = queue_discard_granularity_show, }; static struct queue_sysfs_entry queue_discard_max_hw_entry = { - .attr = {.name = "discard_max_hw_bytes", .mode = S_IRUGO }, + .attr = {.name = "discard_max_hw_bytes", .mode = 0444 }, .show = queue_discard_max_hw_show, }; static struct queue_sysfs_entry queue_discard_max_entry = { - .attr = {.name = "discard_max_bytes", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "discard_max_bytes", .mode = 0644 }, .show = queue_discard_max_show, .store = queue_discard_max_store, }; static struct queue_sysfs_entry queue_discard_zeroes_data_entry = { - .attr = {.name = "discard_zeroes_data", .mode = S_IRUGO }, + .attr = {.name = "discard_zeroes_data", .mode = 0444 }, .show = queue_discard_zeroes_data_show, }; static struct queue_sysfs_entry queue_write_same_max_entry = { - .attr = {.name = "write_same_max_bytes", .mode = S_IRUGO }, + .attr = {.name = "write_same_max_bytes", .mode = 0444 }, .show = queue_write_same_max_show, }; static struct queue_sysfs_entry queue_write_zeroes_max_entry = { - .attr = {.name = "write_zeroes_max_bytes", .mode = S_IRUGO }, + .attr = {.name = "write_zeroes_max_bytes", .mode = 0444 }, .show = queue_write_zeroes_max_show, }; static struct queue_sysfs_entry queue_nonrot_entry = { - .attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "rotational", .mode = 0644 }, .show = queue_show_nonrot, .store = queue_store_nonrot, }; static struct queue_sysfs_entry queue_zoned_entry = { - .attr = {.name = "zoned", .mode = S_IRUGO }, + .attr = {.name = "zoned", .mode = 0444 }, .show = queue_zoned_show, }; static struct queue_sysfs_entry queue_nomerges_entry = { - .attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "nomerges", .mode = 0644 }, .show = queue_nomerges_show, .store = queue_nomerges_store, }; static struct queue_sysfs_entry queue_rq_affinity_entry = { - .attr = {.name = "rq_affinity", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "rq_affinity", .mode = 0644 }, .show = queue_rq_affinity_show, .store = queue_rq_affinity_store, }; static struct queue_sysfs_entry queue_iostats_entry = { - .attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "iostats", .mode = 0644 }, .show = queue_show_iostats, .store = queue_store_iostats, }; static struct queue_sysfs_entry queue_random_entry = { - .attr = {.name = "add_random", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "add_random", .mode = 0644 }, .show = queue_show_random, .store = queue_store_random, }; static struct queue_sysfs_entry queue_poll_entry = { - .attr = {.name = "io_poll", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "io_poll", .mode = 0644 }, .show = queue_poll_show, .store = queue_poll_store, }; static struct queue_sysfs_entry queue_poll_delay_entry = { - .attr = {.name = "io_poll_delay", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "io_poll_delay", .mode = 0644 }, .show = queue_poll_delay_show, .store = queue_poll_delay_store, }; static struct queue_sysfs_entry queue_wc_entry = { - .attr = {.name = "write_cache", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "write_cache", .mode = 0644 }, .show = queue_wc_show, .store = queue_wc_store, }; +static struct queue_sysfs_entry queue_fua_entry = { + .attr = {.name = "fua", .mode = 0444 }, + .show = queue_fua_show, +}; + static struct queue_sysfs_entry queue_dax_entry = { - .attr = {.name = "dax", .mode = S_IRUGO }, + .attr = {.name = "dax", .mode = 0444 }, .show = queue_dax_show, }; static struct queue_sysfs_entry queue_wb_lat_entry = { - .attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "wbt_lat_usec", .mode = 0644 }, .show = queue_wb_lat_show, .store = queue_wb_lat_store, }; #ifdef CONFIG_BLK_DEV_THROTTLING_LOW static struct queue_sysfs_entry throtl_sample_time_entry = { - .attr = {.name = "throttle_sample_time", .mode = S_IRUGO | S_IWUSR }, + .attr = {.name = "throttle_sample_time", .mode = 0644 }, .show = blk_throtl_sample_time_show, .store = blk_throtl_sample_time_store, }; @@ -708,6 +718,7 @@ static struct attribute *default_attrs[] = { &queue_random_entry.attr, &queue_poll_entry.attr, &queue_wc_entry.attr, + &queue_fua_entry.attr, &queue_dax_entry.attr, &queue_wb_lat_entry.attr, &queue_poll_delay_entry.attr, @@ -813,8 +824,7 @@ static void __blk_release_queue(struct work_struct *work) if (q->mq_ops) blk_mq_debugfs_unregister(q); - if (q->bio_split) - bioset_free(q->bio_split); + bioset_exit(&q->bio_split); ida_simple_remove(&blk_queue_ida, q->id); call_rcu(&q->rcu_head, blk_free_queue_rcu); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index c5a1316737331..82282e6fdcf82 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -36,8 +36,6 @@ static int throtl_quantum = 32; */ #define LATENCY_FILTERED_HD (1000L) /* 1ms */ -#define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT) - static struct blkcg_policy blkcg_policy_throtl; /* A workqueue to queue throttle related work */ @@ -821,7 +819,7 @@ static bool throtl_slice_used(struct throtl_grp *tg, bool rw) if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw])) return false; - return 1; + return true; } /* Trim the used slices and adjust slice start accordingly */ @@ -931,7 +929,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio, if (wait) *wait = jiffy_wait; - return 0; + return false; } static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, @@ -974,7 +972,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed); if (wait) *wait = jiffy_wait; - return 0; + return false; } /* @@ -1024,7 +1022,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, tg_with_in_iops_limit(tg, bio, &iops_wait)) { if (wait) *wait = 0; - return 1; + return true; } max_wait = max(bps_wait, iops_wait); @@ -1035,7 +1033,7 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, if (time_before(tg->slice_end[rw], jiffies + max_wait)) throtl_extend_slice(tg, rw, jiffies + max_wait); - return 0; + return false; } static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) @@ -1209,7 +1207,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq) while (1) { struct throtl_grp *tg = throtl_rb_first(parent_sq); - struct throtl_service_queue *sq = &tg->service_queue; + struct throtl_service_queue *sq; if (!tg) break; @@ -1221,6 +1219,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq) nr_disp += throtl_dispatch_tg(tg); + sq = &tg->service_queue; if (sq->nr_queued[0] || sq->nr_queued[1]) tg_update_disptime(tg); @@ -2139,7 +2138,7 @@ static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio) bio->bi_cg_private = tg; blkg_get(tg_to_blkg(tg)); } - blk_stat_set_issue(&bio->bi_issue_stat, bio_sectors(bio)); + bio_issue_init(&bio->bi_issue, bio_sectors(bio)); #endif } @@ -2251,7 +2250,7 @@ out: #ifdef CONFIG_BLK_DEV_THROTTLING_LOW if (throttled || !td->track_bio_latency) - bio->bi_issue_stat.stat |= SKIP_LATENCY; + bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY; #endif return throttled; } @@ -2281,8 +2280,7 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns) struct request_queue *q = rq->q; struct throtl_data *td = q->td; - throtl_track_latency(td, blk_stat_size(&rq->issue_stat), - req_op(rq), time_ns >> 10); + throtl_track_latency(td, rq->throtl_size, req_op(rq), time_ns >> 10); } void blk_throtl_bio_endio(struct bio *bio) @@ -2302,8 +2300,8 @@ void blk_throtl_bio_endio(struct bio *bio) finish_time_ns = ktime_get_ns(); tg->last_finish_time = finish_time_ns >> 10; - start_time = blk_stat_time(&bio->bi_issue_stat) >> 10; - finish_time = __blk_stat_time(finish_time_ns) >> 10; + start_time = bio_issue_time(&bio->bi_issue) >> 10; + finish_time = __bio_issue_time(finish_time_ns) >> 10; if (!start_time || finish_time <= start_time) { blkg_put(tg_to_blkg(tg)); return; @@ -2311,16 +2309,15 @@ void blk_throtl_bio_endio(struct bio *bio) lat = finish_time - start_time; /* this is only for bio based driver */ - if (!(bio->bi_issue_stat.stat & SKIP_LATENCY)) - throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat), - bio_op(bio), lat); + if (!(bio->bi_issue.value & BIO_ISSUE_THROTL_SKIP_LATENCY)) + throtl_track_latency(tg->td, bio_issue_size(&bio->bi_issue), + bio_op(bio), lat); if (tg->latency_target && lat >= tg->td->filtered_latency) { int bucket; unsigned int threshold; - bucket = request_bucket_index( - blk_stat_size(&bio->bi_issue_stat)); + bucket = request_bucket_index(bio_issue_size(&bio->bi_issue)); threshold = tg->td->avg_buckets[rw][bucket].latency + tg->latency_target; if (lat > threshold) diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 652d4d4d3e972..4b8a48d48ba13 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -86,14 +86,11 @@ static void blk_rq_timed_out(struct request *req) if (q->rq_timed_out_fn) ret = q->rq_timed_out_fn(req); switch (ret) { - case BLK_EH_HANDLED: - __blk_complete_request(req); - break; case BLK_EH_RESET_TIMER: blk_add_timer(req); blk_clear_rq_complete(req); break; - case BLK_EH_NOT_HANDLED: + case BLK_EH_DONE: /* * LLD handles this for now but in the future * we can send a request msg to abort the command @@ -214,7 +211,6 @@ void blk_add_timer(struct request *req) req->timeout = q->rq_timeout; blk_rq_set_deadline(req, jiffies + req->timeout); - req->rq_flags &= ~RQF_MQ_TIMEOUT_EXPIRED; /* * Only the non-mq case needs to add the request to a protected list. diff --git a/block/blk-wbt.c b/block/blk-wbt.c index f92fc84b5e2c4..4f89b28fa6524 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -29,6 +29,26 @@ #define CREATE_TRACE_POINTS #include <trace/events/wbt.h> +static inline void wbt_clear_state(struct request *rq) +{ + rq->wbt_flags = 0; +} + +static inline enum wbt_flags wbt_flags(struct request *rq) +{ + return rq->wbt_flags; +} + +static inline bool wbt_is_tracked(struct request *rq) +{ + return rq->wbt_flags & WBT_TRACKED; +} + +static inline bool wbt_is_read(struct request *rq) +{ + return rq->wbt_flags & WBT_READ; +} + enum { /* * Default setting, we'll scale up (to 75% of QD max) or down (min 1) @@ -101,9 +121,15 @@ static bool wb_recent_wait(struct rq_wb *rwb) return time_before(jiffies, wb->dirty_sleep + HZ); } -static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, bool is_kswapd) +static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb, + enum wbt_flags wb_acct) { - return &rwb->rq_wait[is_kswapd]; + if (wb_acct & WBT_KSWAPD) + return &rwb->rq_wait[WBT_RWQ_KSWAPD]; + else if (wb_acct & WBT_DISCARD) + return &rwb->rq_wait[WBT_RWQ_DISCARD]; + + return &rwb->rq_wait[WBT_RWQ_BG]; } static void rwb_wake_all(struct rq_wb *rwb) @@ -126,7 +152,7 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct) if (!(wb_acct & WBT_TRACKED)) return; - rqw = get_rq_wait(rwb, wb_acct & WBT_KSWAPD); + rqw = get_rq_wait(rwb, wb_acct); inflight = atomic_dec_return(&rqw->inflight); /* @@ -139,10 +165,13 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct) } /* - * If the device does write back caching, drop further down - * before we wake people up. + * For discards, our limit is always the background. For writes, if + * the device does write back caching, drop further down before we + * wake people up. */ - if (rwb->wc && !wb_recent_wait(rwb)) + if (wb_acct & WBT_DISCARD) + limit = rwb->wb_background; + else if (rwb->wc && !wb_recent_wait(rwb)) limit = 0; else limit = rwb->wb_normal; @@ -165,24 +194,24 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct) * Called on completion of a request. Note that it's also called when * a request is merged, when the request gets freed. */ -void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat) +void wbt_done(struct rq_wb *rwb, struct request *rq) { if (!rwb) return; - if (!wbt_is_tracked(stat)) { - if (rwb->sync_cookie == stat) { + if (!wbt_is_tracked(rq)) { + if (rwb->sync_cookie == rq) { rwb->sync_issue = 0; rwb->sync_cookie = NULL; } - if (wbt_is_read(stat)) + if (wbt_is_read(rq)) wb_timestamp(rwb, &rwb->last_comp); } else { - WARN_ON_ONCE(stat == rwb->sync_cookie); - __wbt_done(rwb, wbt_stat_to_mask(stat)); + WARN_ON_ONCE(rq == rwb->sync_cookie); + __wbt_done(rwb, wbt_flags(rq)); } - wbt_clear_state(stat); + wbt_clear_state(rq); } /* @@ -479,6 +508,9 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw) { unsigned int limit; + if ((rw & REQ_OP_MASK) == REQ_OP_DISCARD) + return rwb->wb_background; + /* * At this point we know it's a buffered write. If this is * kswapd trying to free memory, or REQ_SYNC is set, then @@ -529,11 +561,12 @@ static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw, * Block if we will exceed our limit, or if we are currently waiting for * the timer to kick off queuing again. */ -static void __wbt_wait(struct rq_wb *rwb, unsigned long rw, spinlock_t *lock) +static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct, + unsigned long rw, spinlock_t *lock) __releases(lock) __acquires(lock) { - struct rq_wait *rqw = get_rq_wait(rwb, current_is_kswapd()); + struct rq_wait *rqw = get_rq_wait(rwb, wb_acct); DEFINE_WAIT(wait); if (may_queue(rwb, rqw, &wait, rw)) @@ -559,21 +592,20 @@ static void __wbt_wait(struct rq_wb *rwb, unsigned long rw, spinlock_t *lock) static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio) { - const int op = bio_op(bio); - - /* - * If not a WRITE, do nothing - */ - if (op != REQ_OP_WRITE) - return false; - - /* - * Don't throttle WRITE_ODIRECT - */ - if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) == (REQ_SYNC | REQ_IDLE)) + switch (bio_op(bio)) { + case REQ_OP_WRITE: + /* + * Don't throttle WRITE_ODIRECT + */ + if ((bio->bi_opf & (REQ_SYNC | REQ_IDLE)) == + (REQ_SYNC | REQ_IDLE)) + return false; + /* fallthrough */ + case REQ_OP_DISCARD: + return true; + default: return false; - - return true; + } } /* @@ -584,7 +616,7 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio) */ enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock) { - unsigned int ret = 0; + enum wbt_flags ret = 0; if (!rwb_enabled(rwb)) return 0; @@ -598,41 +630,42 @@ enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock) return ret; } - __wbt_wait(rwb, bio->bi_opf, lock); + if (current_is_kswapd()) + ret |= WBT_KSWAPD; + if (bio_op(bio) == REQ_OP_DISCARD) + ret |= WBT_DISCARD; + + __wbt_wait(rwb, ret, bio->bi_opf, lock); if (!blk_stat_is_active(rwb->cb)) rwb_arm_timer(rwb); - if (current_is_kswapd()) - ret |= WBT_KSWAPD; - return ret | WBT_TRACKED; } -void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat) +void wbt_issue(struct rq_wb *rwb, struct request *rq) { if (!rwb_enabled(rwb)) return; /* - * Track sync issue, in case it takes a long time to complete. Allows - * us to react quicker, if a sync IO takes a long time to complete. - * Note that this is just a hint. 'stat' can go away when the - * request completes, so it's important we never dereference it. We - * only use the address to compare with, which is why we store the - * sync_issue time locally. + * Track sync issue, in case it takes a long time to complete. Allows us + * to react quicker, if a sync IO takes a long time to complete. Note + * that this is just a hint. The request can go away when it completes, + * so it's important we never dereference it. We only use the address to + * compare with, which is why we store the sync_issue time locally. */ - if (wbt_is_read(stat) && !rwb->sync_issue) { - rwb->sync_cookie = stat; - rwb->sync_issue = blk_stat_time(stat); + if (wbt_is_read(rq) && !rwb->sync_issue) { + rwb->sync_cookie = rq; + rwb->sync_issue = rq->io_start_time_ns; } } -void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat) +void wbt_requeue(struct rq_wb *rwb, struct request *rq) { if (!rwb_enabled(rwb)) return; - if (stat == rwb->sync_cookie) { + if (rq == rwb->sync_cookie) { rwb->sync_issue = 0; rwb->sync_cookie = NULL; } @@ -701,7 +734,7 @@ static int wbt_data_dir(const struct request *rq) if (op == REQ_OP_READ) return READ; - else if (op == REQ_OP_WRITE || op == REQ_OP_FLUSH) + else if (op_is_write(op)) return WRITE; /* don't account */ @@ -713,8 +746,6 @@ int wbt_init(struct request_queue *q) struct rq_wb *rwb; int i; - BUILD_BUG_ON(WBT_NR_BITS > BLK_STAT_RES_BITS); - rwb = kzalloc(sizeof(*rwb), GFP_KERNEL); if (!rwb) return -ENOMEM; diff --git a/block/blk-wbt.h b/block/blk-wbt.h index a232c98fbf4d8..300df531d0a66 100644 --- a/block/blk-wbt.h +++ b/block/blk-wbt.h @@ -14,12 +14,16 @@ enum wbt_flags { WBT_TRACKED = 1, /* write, tracked for throttling */ WBT_READ = 2, /* read */ WBT_KSWAPD = 4, /* write, from kswapd */ + WBT_DISCARD = 8, /* discard */ - WBT_NR_BITS = 3, /* number of bits */ + WBT_NR_BITS = 4, /* number of bits */ }; enum { - WBT_NUM_RWQ = 2, + WBT_RWQ_BG = 0, + WBT_RWQ_KSWAPD, + WBT_RWQ_DISCARD, + WBT_NUM_RWQ, }; /* @@ -31,31 +35,6 @@ enum { WBT_STATE_ON_MANUAL = 2, }; -static inline void wbt_clear_state(struct blk_issue_stat *stat) -{ - stat->stat &= ~BLK_STAT_RES_MASK; -} - -static inline enum wbt_flags wbt_stat_to_mask(struct blk_issue_stat *stat) -{ - return (stat->stat & BLK_STAT_RES_MASK) >> BLK_STAT_RES_SHIFT; -} - -static inline void wbt_track(struct blk_issue_stat *stat, enum wbt_flags wb_acct) -{ - stat->stat |= ((u64) wb_acct) << BLK_STAT_RES_SHIFT; -} - -static inline bool wbt_is_tracked(struct blk_issue_stat *stat) -{ - return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_TRACKED; -} - -static inline bool wbt_is_read(struct blk_issue_stat *stat) -{ - return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_READ; -} - struct rq_wait { wait_queue_head_t wait; atomic_t inflight; @@ -84,7 +63,7 @@ struct rq_wb { struct blk_stat_callback *cb; - s64 sync_issue; + u64 sync_issue; void *sync_cookie; unsigned int wc; @@ -109,14 +88,19 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb) #ifdef CONFIG_BLK_WBT +static inline void wbt_track(struct request *rq, enum wbt_flags flags) +{ + rq->wbt_flags |= flags; +} + void __wbt_done(struct rq_wb *, enum wbt_flags); -void wbt_done(struct rq_wb *, struct blk_issue_stat *); +void wbt_done(struct rq_wb *, struct request *); enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *); int wbt_init(struct request_queue *); void wbt_exit(struct request_queue *); void wbt_update_limits(struct rq_wb *); -void wbt_requeue(struct rq_wb *, struct blk_issue_stat *); -void wbt_issue(struct rq_wb *, struct blk_issue_stat *); +void wbt_requeue(struct rq_wb *, struct request *); +void wbt_issue(struct rq_wb *, struct request *); void wbt_disable_default(struct request_queue *); void wbt_enable_default(struct request_queue *); @@ -127,10 +111,13 @@ u64 wbt_default_latency_nsec(struct request_queue *); #else +static inline void wbt_track(struct request *rq, enum wbt_flags flags) +{ +} static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags) { } -static inline void wbt_done(struct rq_wb *rwb, struct blk_issue_stat *stat) +static inline void wbt_done(struct rq_wb *rwb, struct request *rq) { } static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, @@ -148,10 +135,10 @@ static inline void wbt_exit(struct request_queue *q) static inline void wbt_update_limits(struct rq_wb *rwb) { } -static inline void wbt_requeue(struct rq_wb *rwb, struct blk_issue_stat *stat) +static inline void wbt_requeue(struct rq_wb *rwb, struct request *rq) { } -static inline void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat) +static inline void wbt_issue(struct rq_wb *rwb, struct request *rq) { } static inline void wbt_disable_default(struct request_queue *q) diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 08e84ef2bc054..3d08dc84db167 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -328,7 +328,11 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, if (!rep.nr_zones) return -EINVAL; - zones = kcalloc(rep.nr_zones, sizeof(struct blk_zone), GFP_KERNEL); + if (rep.nr_zones > INT_MAX / sizeof(struct blk_zone)) + return -ERANGE; + + zones = kvmalloc(rep.nr_zones * sizeof(struct blk_zone), + GFP_KERNEL | __GFP_ZERO); if (!zones) return -ENOMEM; @@ -350,7 +354,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, } out: - kfree(zones); + kvfree(zones); return ret; } diff --git a/block/blk.h b/block/blk.h index b034fd2460c41..8d23aea96ce9e 100644 --- a/block/blk.h +++ b/block/blk.h @@ -186,7 +186,7 @@ unsigned int blk_plug_queued_count(struct request_queue *q); void blk_account_io_start(struct request *req, bool new_io); void blk_account_io_completion(struct request *req, unsigned int bytes); -void blk_account_io_done(struct request *req); +void blk_account_io_done(struct request *req, u64 now); /* * EH timer and IO completion will both attempt to 'grab' the request, make @@ -231,6 +231,9 @@ static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq e->type->ops.sq.elevator_deactivate_req_fn(q, rq); } +int elevator_init(struct request_queue *); +int elevator_init_mq(struct request_queue *q); +void elevator_exit(struct request_queue *, struct elevator_queue *); int elv_register_queue(struct request_queue *q); void elv_unregister_queue(struct request_queue *q); diff --git a/block/bounce.c b/block/bounce.c index dd0b93f2a8717..fd31347b78361 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -28,28 +28,29 @@ #define POOL_SIZE 64 #define ISA_POOL_SIZE 16 -static struct bio_set *bounce_bio_set, *bounce_bio_split; -static mempool_t *page_pool, *isa_page_pool; +static struct bio_set bounce_bio_set, bounce_bio_split; +static mempool_t page_pool, isa_page_pool; #if defined(CONFIG_HIGHMEM) static __init int init_emergency_pool(void) { + int ret; #if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG) if (max_pfn <= max_low_pfn) return 0; #endif - page_pool = mempool_create_page_pool(POOL_SIZE, 0); - BUG_ON(!page_pool); + ret = mempool_init_page_pool(&page_pool, POOL_SIZE, 0); + BUG_ON(ret); pr_info("pool size: %d pages\n", POOL_SIZE); - bounce_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); - BUG_ON(!bounce_bio_set); - if (bioset_integrity_create(bounce_bio_set, BIO_POOL_SIZE)) + ret = bioset_init(&bounce_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); + BUG_ON(ret); + if (bioset_integrity_create(&bounce_bio_set, BIO_POOL_SIZE)) BUG_ON(1); - bounce_bio_split = bioset_create(BIO_POOL_SIZE, 0, 0); - BUG_ON(!bounce_bio_split); + ret = bioset_init(&bounce_bio_split, BIO_POOL_SIZE, 0, 0); + BUG_ON(ret); return 0; } @@ -63,14 +64,11 @@ __initcall(init_emergency_pool); */ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom) { - unsigned long flags; unsigned char *vto; - local_irq_save(flags); vto = kmap_atomic(to->bv_page); memcpy(vto + to->bv_offset, vfrom, to->bv_len); kunmap_atomic(vto); - local_irq_restore(flags); } #else /* CONFIG_HIGHMEM */ @@ -94,12 +92,14 @@ static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data) */ int init_emergency_isa_pool(void) { - if (isa_page_pool) + int ret; + + if (mempool_initialized(&isa_page_pool)) return 0; - isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa, - mempool_free_pages, (void *) 0); - BUG_ON(!isa_page_pool); + ret = mempool_init(&isa_page_pool, ISA_POOL_SIZE, mempool_alloc_pages_isa, + mempool_free_pages, (void *) 0); + BUG_ON(ret); pr_info("isa pool size: %d pages\n", ISA_POOL_SIZE); return 0; @@ -166,13 +166,13 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool) static void bounce_end_io_write(struct bio *bio) { - bounce_end_io(bio, page_pool); + bounce_end_io(bio, &page_pool); } static void bounce_end_io_write_isa(struct bio *bio) { - bounce_end_io(bio, isa_page_pool); + bounce_end_io(bio, &isa_page_pool); } static void __bounce_end_io_read(struct bio *bio, mempool_t *pool) @@ -187,12 +187,12 @@ static void __bounce_end_io_read(struct bio *bio, mempool_t *pool) static void bounce_end_io_read(struct bio *bio) { - __bounce_end_io_read(bio, page_pool); + __bounce_end_io_read(bio, &page_pool); } static void bounce_end_io_read_isa(struct bio *bio) { - __bounce_end_io_read(bio, isa_page_pool); + __bounce_end_io_read(bio, &isa_page_pool); } static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, @@ -217,13 +217,13 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, return; if (!passthrough && sectors < bio_sectors(*bio_orig)) { - bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split); + bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split); bio_chain(bio, *bio_orig); generic_make_request(*bio_orig); *bio_orig = bio; } bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL : - bounce_bio_set); + &bounce_bio_set); bio_for_each_segment_all(to, bio, i) { struct page *page = to->bv_page; @@ -250,7 +250,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, bio->bi_flags |= (1 << BIO_BOUNCED); - if (pool == page_pool) { + if (pool == &page_pool) { bio->bi_end_io = bounce_end_io_write; if (rw == READ) bio->bi_end_io = bounce_end_io_read; @@ -282,10 +282,10 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) if (!(q->bounce_gfp & GFP_DMA)) { if (q->limits.bounce_pfn >= blk_max_pfn) return; - pool = page_pool; + pool = &page_pool; } else { - BUG_ON(!isa_page_pool); - pool = isa_page_pool; + BUG_ON(!mempool_initialized(&isa_page_pool)); + pool = &isa_page_pool; } /* diff --git a/block/bsg-lib.c b/block/bsg-lib.c index fc2e5ff2c4b9e..9419def8c0175 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -303,11 +303,9 @@ static void bsg_exit_rq(struct request_queue *q, struct request *req) * @name: device to give bsg device * @job_fn: bsg job handler * @dd_job_size: size of LLD data needed for each job - * @release: @dev release function */ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, - bsg_job_fn *job_fn, int dd_job_size, - void (*release)(struct device *)) + bsg_job_fn *job_fn, int dd_job_size) { struct request_queue *q; int ret; @@ -331,7 +329,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, blk_queue_softirq_done(q, bsg_softirq_done); blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); - ret = bsg_register_queue(q, dev, name, &bsg_transport_ops, release); + ret = bsg_register_queue(q, dev, name, &bsg_transport_ops); if (ret) { printk(KERN_ERR "%s: bsg interface failed to " "initialize - register queue\n", dev->kobj.name); diff --git a/block/bsg.c b/block/bsg.c index defa06c118587..132e657e2d913 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -226,8 +226,7 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode) return ERR_PTR(ret); rq = blk_get_request(q, hdr->dout_xfer_len ? - REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, - GFP_KERNEL); + REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0); if (IS_ERR(rq)) return rq; @@ -249,7 +248,7 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode) goto out; } - next_rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL); + next_rq = blk_get_request(q, REQ_OP_SCSI_IN, 0); if (IS_ERR(next_rq)) { ret = PTR_ERR(next_rq); goto out; @@ -650,18 +649,6 @@ static struct bsg_device *bsg_alloc_device(void) return bd; } -static void bsg_kref_release_function(struct kref *kref) -{ - struct bsg_class_device *bcd = - container_of(kref, struct bsg_class_device, ref); - struct device *parent = bcd->parent; - - if (bcd->release) - bcd->release(bcd->parent); - - put_device(parent); -} - static int bsg_put_device(struct bsg_device *bd) { int ret = 0, do_free; @@ -694,7 +681,6 @@ static int bsg_put_device(struct bsg_device *bd) kfree(bd); out: - kref_put(&q->bsg_dev.ref, bsg_kref_release_function); if (do_free) blk_put_queue(q); return ret; @@ -760,8 +746,6 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file) */ mutex_lock(&bsg_mutex); bcd = idr_find(&bsg_minor_idr, iminor(inode)); - if (bcd) - kref_get(&bcd->ref); mutex_unlock(&bsg_mutex); if (!bcd) @@ -772,8 +756,6 @@ static struct bsg_device *bsg_get_device(struct inode *inode, struct file *file) return bd; bd = bsg_add_device(inode, bcd->queue, file); - if (IS_ERR(bd)) - kref_put(&bcd->ref, bsg_kref_release_function); return bd; } @@ -913,25 +895,17 @@ void bsg_unregister_queue(struct request_queue *q) sysfs_remove_link(&q->kobj, "bsg"); device_unregister(bcd->class_dev); bcd->class_dev = NULL; - kref_put(&bcd->ref, bsg_kref_release_function); mutex_unlock(&bsg_mutex); } EXPORT_SYMBOL_GPL(bsg_unregister_queue); int bsg_register_queue(struct request_queue *q, struct device *parent, - const char *name, const struct bsg_ops *ops, - void (*release)(struct device *)) + const char *name, const struct bsg_ops *ops) { struct bsg_class_device *bcd; dev_t dev; int ret; struct device *class_dev = NULL; - const char *devname; - - if (name) - devname = name; - else - devname = dev_name(parent); /* * we need a proper transport to send commands, not a stacked device @@ -955,15 +929,12 @@ int bsg_register_queue(struct request_queue *q, struct device *parent, bcd->minor = ret; bcd->queue = q; - bcd->parent = get_device(parent); - bcd->release = release; bcd->ops = ops; - kref_init(&bcd->ref); dev = MKDEV(bsg_major, bcd->minor); - class_dev = device_create(bsg_class, parent, dev, NULL, "%s", devname); + class_dev = device_create(bsg_class, parent, dev, NULL, "%s", name); if (IS_ERR(class_dev)) { ret = PTR_ERR(class_dev); - goto put_dev; + goto idr_remove; } bcd->class_dev = class_dev; @@ -978,8 +949,7 @@ int bsg_register_queue(struct request_queue *q, struct device *parent, unregister_class_dev: device_unregister(class_dev); -put_dev: - put_device(parent); +idr_remove: idr_remove(&bsg_minor_idr, bcd->minor); unlock: mutex_unlock(&bsg_mutex); @@ -993,7 +963,7 @@ int bsg_scsi_register_queue(struct request_queue *q, struct device *parent) return -EINVAL; } - return bsg_register_queue(q, parent, NULL, &bsg_scsi_ops, NULL); + return bsg_register_queue(q, parent, dev_name(parent), &bsg_scsi_ops); } EXPORT_SYMBOL_GPL(bsg_scsi_register_queue); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 9f342ef1ad426..82b6c27b32455 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -210,9 +210,9 @@ struct cfqg_stats { /* total time with empty current active q with other requests queued */ struct blkg_stat empty_time; /* fields after this shouldn't be cleared on stat reset */ - uint64_t start_group_wait_time; - uint64_t start_idle_time; - uint64_t start_empty_time; + u64 start_group_wait_time; + u64 start_idle_time; + u64 start_empty_time; uint16_t flags; #endif /* CONFIG_DEBUG_BLK_CGROUP */ #endif /* CONFIG_CFQ_GROUP_IOSCHED */ @@ -491,13 +491,13 @@ CFQG_FLAG_FNS(empty) /* This should be called with the queue_lock held. */ static void cfqg_stats_update_group_wait_time(struct cfqg_stats *stats) { - unsigned long long now; + u64 now; if (!cfqg_stats_waiting(stats)) return; - now = sched_clock(); - if (time_after64(now, stats->start_group_wait_time)) + now = ktime_get_ns(); + if (now > stats->start_group_wait_time) blkg_stat_add(&stats->group_wait_time, now - stats->start_group_wait_time); cfqg_stats_clear_waiting(stats); @@ -513,20 +513,20 @@ static void cfqg_stats_set_start_group_wait_time(struct cfq_group *cfqg, return; if (cfqg == curr_cfqg) return; - stats->start_group_wait_time = sched_clock(); + stats->start_group_wait_time = ktime_get_ns(); cfqg_stats_mark_waiting(stats); } /* This should be called with the queue_lock held. */ static void cfqg_stats_end_empty_time(struct cfqg_stats *stats) { - unsigned long long now; + u64 now; if (!cfqg_stats_empty(stats)) return; - now = sched_clock(); - if (time_after64(now, stats->start_empty_time)) + now = ktime_get_ns(); + if (now > stats->start_empty_time) blkg_stat_add(&stats->empty_time, now - stats->start_empty_time); cfqg_stats_clear_empty(stats); @@ -552,7 +552,7 @@ static void cfqg_stats_set_start_empty_time(struct cfq_group *cfqg) if (cfqg_stats_empty(stats)) return; - stats->start_empty_time = sched_clock(); + stats->start_empty_time = ktime_get_ns(); cfqg_stats_mark_empty(stats); } @@ -561,9 +561,9 @@ static void cfqg_stats_update_idle_time(struct cfq_group *cfqg) struct cfqg_stats *stats = &cfqg->stats; if (cfqg_stats_idling(stats)) { - unsigned long long now = sched_clock(); + u64 now = ktime_get_ns(); - if (time_after64(now, stats->start_idle_time)) + if (now > stats->start_idle_time) blkg_stat_add(&stats->idle_time, now - stats->start_idle_time); cfqg_stats_clear_idling(stats); @@ -576,7 +576,7 @@ static void cfqg_stats_set_start_idle_time(struct cfq_group *cfqg) BUG_ON(cfqg_stats_idling(stats)); - stats->start_idle_time = sched_clock(); + stats->start_idle_time = ktime_get_ns(); cfqg_stats_mark_idling(stats); } @@ -701,17 +701,19 @@ static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, } static inline void cfqg_stats_update_completion(struct cfq_group *cfqg, - uint64_t start_time, uint64_t io_start_time, - unsigned int op) + u64 start_time_ns, + u64 io_start_time_ns, + unsigned int op) { struct cfqg_stats *stats = &cfqg->stats; - unsigned long long now = sched_clock(); + u64 now = ktime_get_ns(); - if (time_after64(now, io_start_time)) - blkg_rwstat_add(&stats->service_time, op, now - io_start_time); - if (time_after64(io_start_time, start_time)) + if (now > io_start_time_ns) + blkg_rwstat_add(&stats->service_time, op, + now - io_start_time_ns); + if (io_start_time_ns > start_time_ns) blkg_rwstat_add(&stats->wait_time, op, - io_start_time - start_time); + io_start_time_ns - start_time_ns); } /* @stats = 0 */ @@ -797,8 +799,9 @@ static inline void cfqg_stats_update_io_remove(struct cfq_group *cfqg, static inline void cfqg_stats_update_io_merged(struct cfq_group *cfqg, unsigned int op) { } static inline void cfqg_stats_update_completion(struct cfq_group *cfqg, - uint64_t start_time, uint64_t io_start_time, - unsigned int op) { } + u64 start_time_ns, + u64 io_start_time_ns, + unsigned int op) { } #endif /* CONFIG_CFQ_GROUP_IOSCHED */ @@ -4225,8 +4228,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) cfqd->rq_in_driver--; cfqq->dispatched--; (RQ_CFQG(rq))->dispatched--; - cfqg_stats_update_completion(cfqq->cfqg, rq_start_time_ns(rq), - rq_io_start_time_ns(rq), rq->cmd_flags); + cfqg_stats_update_completion(cfqq->cfqg, rq->start_time_ns, + rq->io_start_time_ns, rq->cmd_flags); cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--; @@ -4242,16 +4245,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) cfqq_type(cfqq)); st->ttime.last_end_request = now; - /* - * We have to do this check in jiffies since start_time is in - * jiffies and it is not trivial to convert to ns. If - * cfq_fifo_expire[1] ever comes close to 1 jiffie, this test - * will become problematic but so far we are fine (the default - * is 128 ms). - */ - if (!time_after(rq->start_time + - nsecs_to_jiffies(cfqd->cfq_fifo_expire[1]), - jiffies)) + if (rq->start_time_ns + cfqd->cfq_fifo_expire[1] <= now) cfqd->last_delayed_sync = now; } @@ -4792,7 +4786,7 @@ USEC_STORE_FUNCTION(cfq_target_latency_us_store, &cfqd->cfq_target_latency, 1, U #undef USEC_STORE_FUNCTION #define CFQ_ATTR(name) \ - __ATTR(name, S_IRUGO|S_IWUSR, cfq_##name##_show, cfq_##name##_store) + __ATTR(name, 0644, cfq_##name##_show, cfq_##name##_store) static struct elv_fs_entry cfq_attrs[] = { CFQ_ATTR(quantum), diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c index 9de9f156e203a..ef2f1f09e9b3e 100644 --- a/block/deadline-iosched.c +++ b/block/deadline-iosched.c @@ -512,8 +512,7 @@ STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0); #undef STORE_FUNCTION #define DD_ATTR(name) \ - __ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \ - deadline_##name##_store) + __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store) static struct elv_fs_entry deadline_attrs[] = { DD_ATTR(read_expire), diff --git a/block/elevator.c b/block/elevator.c index e87e9b43aba09..fa828b5bfd4b1 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -199,76 +199,46 @@ static void elevator_release(struct kobject *kobj) kfree(e); } -int elevator_init(struct request_queue *q, char *name) +/* + * Use the default elevator specified by config boot param for non-mq devices, + * or by config option. Don't try to load modules as we could be running off + * async and request_module() isn't allowed from async. + */ +int elevator_init(struct request_queue *q) { struct elevator_type *e = NULL; - int err; + int err = 0; /* * q->sysfs_lock must be held to provide mutual exclusion between * elevator_switch() and here. */ - lockdep_assert_held(&q->sysfs_lock); - + mutex_lock(&q->sysfs_lock); if (unlikely(q->elevator)) - return 0; - - INIT_LIST_HEAD(&q->queue_head); - q->last_merge = NULL; - q->end_sector = 0; - q->boundary_rq = NULL; - - if (name) { - e = elevator_get(q, name, true); - if (!e) - return -EINVAL; - } + goto out_unlock; - /* - * Use the default elevator specified by config boot param for - * non-mq devices, or by config option. Don't try to load modules - * as we could be running off async and request_module() isn't - * allowed from async. - */ - if (!e && !q->mq_ops && *chosen_elevator) { + if (*chosen_elevator) { e = elevator_get(q, chosen_elevator, false); if (!e) printk(KERN_ERR "I/O scheduler %s not found\n", chosen_elevator); } + if (!e) + e = elevator_get(q, CONFIG_DEFAULT_IOSCHED, false); if (!e) { - /* - * For blk-mq devices, we default to using mq-deadline, - * if available, for single queue devices. If deadline - * isn't available OR we have multiple queues, default - * to "none". - */ - if (q->mq_ops) { - if (q->nr_hw_queues == 1) - e = elevator_get(q, "mq-deadline", false); - if (!e) - return 0; - } else - e = elevator_get(q, CONFIG_DEFAULT_IOSCHED, false); - - if (!e) { - printk(KERN_ERR - "Default I/O scheduler not found. " \ - "Using noop.\n"); - e = elevator_get(q, "noop", false); - } + printk(KERN_ERR + "Default I/O scheduler not found. Using noop.\n"); + e = elevator_get(q, "noop", false); } - if (e->uses_mq) - err = blk_mq_init_sched(q, e); - else - err = e->ops.sq.elevator_init_fn(q, e); + err = e->ops.sq.elevator_init_fn(q, e); if (err) elevator_put(e); +out_unlock: + mutex_unlock(&q->sysfs_lock); return err; } -EXPORT_SYMBOL(elevator_init); void elevator_exit(struct request_queue *q, struct elevator_queue *e) { @@ -281,7 +251,6 @@ void elevator_exit(struct request_queue *q, struct elevator_queue *e) kobject_put(&e->kobj); } -EXPORT_SYMBOL(elevator_exit); static inline void __elv_rqhash_del(struct request *rq) { @@ -1005,6 +974,40 @@ out: } /* + * For blk-mq devices, we default to using mq-deadline, if available, for single + * queue devices. If deadline isn't available OR we have multiple queues, + * default to "none". + */ +int elevator_init_mq(struct request_queue *q) +{ + struct elevator_type *e; + int err = 0; + + if (q->nr_hw_queues != 1) + return 0; + + /* + * q->sysfs_lock must be held to provide mutual exclusion between + * elevator_switch() and here. + */ + mutex_lock(&q->sysfs_lock); + if (unlikely(q->elevator)) + goto out_unlock; + + e = elevator_get(q, "mq-deadline", false); + if (!e) + goto out_unlock; + + err = blk_mq_init_sched(q, e); + if (err) + elevator_put(e); +out_unlock: + mutex_unlock(&q->sysfs_lock); + return err; +} + + +/* * switch to new_e io scheduler. be careful not to introduce deadlocks - * we don't free the old io scheduler, before we have allocated what we * need for the new one. this way we have a chance of going back to the old diff --git a/block/genhd.c b/block/genhd.c index dc7e089373b94..f1543a45e73bf 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -82,6 +82,18 @@ void part_in_flight(struct request_queue *q, struct hd_struct *part, } } +void part_in_flight_rw(struct request_queue *q, struct hd_struct *part, + unsigned int inflight[2]) +{ + if (q->mq_ops) { + blk_mq_in_flight_rw(q, part, inflight); + return; + } + + inflight[0] = atomic_read(&part->in_flight[0]); + inflight[1] = atomic_read(&part->in_flight[1]); +} + struct hd_struct *__disk_get_part(struct gendisk *disk, int partno) { struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl); @@ -1015,18 +1027,6 @@ static const struct seq_operations partitions_op = { .stop = disk_seqf_stop, .show = show_partition }; - -static int partitions_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &partitions_op); -} - -static const struct file_operations proc_partitions_operations = { - .open = partitions_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; #endif @@ -1127,28 +1127,25 @@ static ssize_t disk_discard_alignment_show(struct device *dev, return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue)); } -static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL); -static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL); -static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL); -static DEVICE_ATTR(hidden, S_IRUGO, disk_hidden_show, NULL); -static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL); -static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); -static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL); -static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show, - NULL); -static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); -static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); -static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); -static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show, - disk_badblocks_store); +static DEVICE_ATTR(range, 0444, disk_range_show, NULL); +static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL); +static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL); +static DEVICE_ATTR(hidden, 0444, disk_hidden_show, NULL); +static DEVICE_ATTR(ro, 0444, disk_ro_show, NULL); +static DEVICE_ATTR(size, 0444, part_size_show, NULL); +static DEVICE_ATTR(alignment_offset, 0444, disk_alignment_offset_show, NULL); +static DEVICE_ATTR(discard_alignment, 0444, disk_discard_alignment_show, NULL); +static DEVICE_ATTR(capability, 0444, disk_capability_show, NULL); +static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); +static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); +static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = - __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); + __ATTR(make-it-fail, 0644, part_fail_show, part_fail_store); #endif #ifdef CONFIG_FAIL_IO_TIMEOUT static struct device_attribute dev_attr_fail_timeout = - __ATTR(io-timeout-fail, S_IRUGO|S_IWUSR, part_timeout_show, - part_timeout_store); + __ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store); #endif static struct attribute *disk_attrs[] = { @@ -1365,22 +1362,10 @@ static const struct seq_operations diskstats_op = { .show = diskstats_show }; -static int diskstats_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &diskstats_op); -} - -static const struct file_operations proc_diskstats_operations = { - .open = diskstats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static int __init proc_genhd_init(void) { - proc_create("diskstats", 0, NULL, &proc_diskstats_operations); - proc_create("partitions", 0, NULL, &proc_partitions_operations); + proc_create_seq("diskstats", 0, NULL, &diskstats_op); + proc_create_seq("partitions", 0, NULL, &partitions_op); return 0; } module_init(proc_genhd_init); @@ -1912,9 +1897,9 @@ static ssize_t disk_events_poll_msecs_store(struct device *dev, return count; } -static const DEVICE_ATTR(events, S_IRUGO, disk_events_show, NULL); -static const DEVICE_ATTR(events_async, S_IRUGO, disk_events_async_show, NULL); -static const DEVICE_ATTR(events_poll_msecs, S_IRUGO|S_IWUSR, +static const DEVICE_ATTR(events, 0444, disk_events_show, NULL); +static const DEVICE_ATTR(events_async, 0444, disk_events_async_show, NULL); +static const DEVICE_ATTR(events_poll_msecs, 0644, disk_events_poll_msecs_show, disk_events_poll_msecs_store); diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 0d6d25e32e1f4..a1660bafc9124 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -72,6 +72,19 @@ static const unsigned int kyber_batch_size[] = { [KYBER_OTHER] = 8, }; +/* + * There is a same mapping between ctx & hctx and kcq & khd, + * we use request->mq_ctx->index_hw to index the kcq in khd. + */ +struct kyber_ctx_queue { + /* + * Used to ensure operations on rq_list and kcq_map to be an atmoic one. + * Also protect the rqs on rq_list when merge. + */ + spinlock_t lock; + struct list_head rq_list[KYBER_NUM_DOMAINS]; +} ____cacheline_aligned_in_smp; + struct kyber_queue_data { struct request_queue *q; @@ -99,6 +112,8 @@ struct kyber_hctx_data { struct list_head rqs[KYBER_NUM_DOMAINS]; unsigned int cur_domain; unsigned int batching; + struct kyber_ctx_queue *kcqs; + struct sbitmap kcq_map[KYBER_NUM_DOMAINS]; wait_queue_entry_t domain_wait[KYBER_NUM_DOMAINS]; struct sbq_wait_state *domain_ws[KYBER_NUM_DOMAINS]; atomic_t wait_index[KYBER_NUM_DOMAINS]; @@ -107,10 +122,8 @@ struct kyber_hctx_data { static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags, void *key); -static int rq_sched_domain(const struct request *rq) +static unsigned int kyber_sched_domain(unsigned int op) { - unsigned int op = rq->cmd_flags; - if ((op & REQ_OP_MASK) == REQ_OP_READ) return KYBER_READ; else if ((op & REQ_OP_MASK) == REQ_OP_WRITE && op_is_sync(op)) @@ -284,6 +297,11 @@ static unsigned int kyber_sched_tags_shift(struct kyber_queue_data *kqd) return kqd->q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift; } +static int kyber_bucket_fn(const struct request *rq) +{ + return kyber_sched_domain(rq->cmd_flags); +} + static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q) { struct kyber_queue_data *kqd; @@ -297,7 +315,7 @@ static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q) goto err; kqd->q = q; - kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, rq_sched_domain, + kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, kyber_bucket_fn, KYBER_NUM_DOMAINS, kqd); if (!kqd->cb) goto err_kqd; @@ -376,8 +394,18 @@ static void kyber_exit_sched(struct elevator_queue *e) kfree(kqd); } +static void kyber_ctx_queue_init(struct kyber_ctx_queue *kcq) +{ + unsigned int i; + + spin_lock_init(&kcq->lock); + for (i = 0; i < KYBER_NUM_DOMAINS; i++) + INIT_LIST_HEAD(&kcq->rq_list[i]); +} + static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { + struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data; struct kyber_hctx_data *khd; int i; @@ -385,6 +413,24 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) if (!khd) return -ENOMEM; + khd->kcqs = kmalloc_array_node(hctx->nr_ctx, + sizeof(struct kyber_ctx_queue), + GFP_KERNEL, hctx->numa_node); + if (!khd->kcqs) + goto err_khd; + + for (i = 0; i < hctx->nr_ctx; i++) + kyber_ctx_queue_init(&khd->kcqs[i]); + + for (i = 0; i < KYBER_NUM_DOMAINS; i++) { + if (sbitmap_init_node(&khd->kcq_map[i], hctx->nr_ctx, + ilog2(8), GFP_KERNEL, hctx->numa_node)) { + while (--i >= 0) + sbitmap_free(&khd->kcq_map[i]); + goto err_kcqs; + } + } + spin_lock_init(&khd->lock); for (i = 0; i < KYBER_NUM_DOMAINS; i++) { @@ -400,12 +446,26 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) khd->batching = 0; hctx->sched_data = khd; + sbitmap_queue_min_shallow_depth(&hctx->sched_tags->bitmap_tags, + kqd->async_depth); return 0; + +err_kcqs: + kfree(khd->kcqs); +err_khd: + kfree(khd); + return -ENOMEM; } static void kyber_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { + struct kyber_hctx_data *khd = hctx->sched_data; + int i; + + for (i = 0; i < KYBER_NUM_DOMAINS; i++) + sbitmap_free(&khd->kcq_map[i]); + kfree(khd->kcqs); kfree(hctx->sched_data); } @@ -427,7 +487,7 @@ static void rq_clear_domain_token(struct kyber_queue_data *kqd, nr = rq_get_domain_token(rq); if (nr != -1) { - sched_domain = rq_sched_domain(rq); + sched_domain = kyber_sched_domain(rq->cmd_flags); sbitmap_queue_clear(&kqd->domain_tokens[sched_domain], nr, rq->mq_ctx->cpu); } @@ -446,11 +506,51 @@ static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) } } +static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio) +{ + struct kyber_hctx_data *khd = hctx->sched_data; + struct blk_mq_ctx *ctx = blk_mq_get_ctx(hctx->queue); + struct kyber_ctx_queue *kcq = &khd->kcqs[ctx->index_hw]; + unsigned int sched_domain = kyber_sched_domain(bio->bi_opf); + struct list_head *rq_list = &kcq->rq_list[sched_domain]; + bool merged; + + spin_lock(&kcq->lock); + merged = blk_mq_bio_list_merge(hctx->queue, rq_list, bio); + spin_unlock(&kcq->lock); + blk_mq_put_ctx(ctx); + + return merged; +} + static void kyber_prepare_request(struct request *rq, struct bio *bio) { rq_set_domain_token(rq, -1); } +static void kyber_insert_requests(struct blk_mq_hw_ctx *hctx, + struct list_head *rq_list, bool at_head) +{ + struct kyber_hctx_data *khd = hctx->sched_data; + struct request *rq, *next; + + list_for_each_entry_safe(rq, next, rq_list, queuelist) { + unsigned int sched_domain = kyber_sched_domain(rq->cmd_flags); + struct kyber_ctx_queue *kcq = &khd->kcqs[rq->mq_ctx->index_hw]; + struct list_head *head = &kcq->rq_list[sched_domain]; + + spin_lock(&kcq->lock); + if (at_head) + list_move(&rq->queuelist, head); + else + list_move_tail(&rq->queuelist, head); + sbitmap_set_bit(&khd->kcq_map[sched_domain], + rq->mq_ctx->index_hw); + blk_mq_sched_request_inserted(rq); + spin_unlock(&kcq->lock); + } +} + static void kyber_finish_request(struct request *rq) { struct kyber_queue_data *kqd = rq->q->elevator->elevator_data; @@ -469,7 +569,7 @@ static void kyber_completed_request(struct request *rq) * Check if this request met our latency goal. If not, quickly gather * some statistics and start throttling. */ - sched_domain = rq_sched_domain(rq); + sched_domain = kyber_sched_domain(rq->cmd_flags); switch (sched_domain) { case KYBER_READ: target = kqd->read_lat_nsec; @@ -485,29 +585,48 @@ static void kyber_completed_request(struct request *rq) if (blk_stat_is_active(kqd->cb)) return; - now = __blk_stat_time(ktime_to_ns(ktime_get())); - if (now < blk_stat_time(&rq->issue_stat)) + now = ktime_get_ns(); + if (now < rq->io_start_time_ns) return; - latency = now - blk_stat_time(&rq->issue_stat); + latency = now - rq->io_start_time_ns; if (latency > target) blk_stat_activate_msecs(kqd->cb, 10); } -static void kyber_flush_busy_ctxs(struct kyber_hctx_data *khd, - struct blk_mq_hw_ctx *hctx) +struct flush_kcq_data { + struct kyber_hctx_data *khd; + unsigned int sched_domain; + struct list_head *list; +}; + +static bool flush_busy_kcq(struct sbitmap *sb, unsigned int bitnr, void *data) { - LIST_HEAD(rq_list); - struct request *rq, *next; + struct flush_kcq_data *flush_data = data; + struct kyber_ctx_queue *kcq = &flush_data->khd->kcqs[bitnr]; - blk_mq_flush_busy_ctxs(hctx, &rq_list); - list_for_each_entry_safe(rq, next, &rq_list, queuelist) { - unsigned int sched_domain; + spin_lock(&kcq->lock); + list_splice_tail_init(&kcq->rq_list[flush_data->sched_domain], + flush_data->list); + sbitmap_clear_bit(sb, bitnr); + spin_unlock(&kcq->lock); - sched_domain = rq_sched_domain(rq); - list_move_tail(&rq->queuelist, &khd->rqs[sched_domain]); - } + return true; +} + +static void kyber_flush_busy_kcqs(struct kyber_hctx_data *khd, + unsigned int sched_domain, + struct list_head *list) +{ + struct flush_kcq_data data = { + .khd = khd, + .sched_domain = sched_domain, + .list = list, + }; + + sbitmap_for_each_set(&khd->kcq_map[sched_domain], + flush_busy_kcq, &data); } static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags, @@ -570,26 +689,23 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd, static struct request * kyber_dispatch_cur_domain(struct kyber_queue_data *kqd, struct kyber_hctx_data *khd, - struct blk_mq_hw_ctx *hctx, - bool *flushed) + struct blk_mq_hw_ctx *hctx) { struct list_head *rqs; struct request *rq; int nr; rqs = &khd->rqs[khd->cur_domain]; - rq = list_first_entry_or_null(rqs, struct request, queuelist); /* - * If there wasn't already a pending request and we haven't flushed the - * software queues yet, flush the software queues and check again. + * If we already have a flushed request, then we just need to get a + * token for it. Otherwise, if there are pending requests in the kcqs, + * flush the kcqs, but only if we can get a token. If not, we should + * leave the requests in the kcqs so that they can be merged. Note that + * khd->lock serializes the flushes, so if we observed any bit set in + * the kcq_map, we will always get a request. */ - if (!rq && !*flushed) { - kyber_flush_busy_ctxs(khd, hctx); - *flushed = true; - rq = list_first_entry_or_null(rqs, struct request, queuelist); - } - + rq = list_first_entry_or_null(rqs, struct request, queuelist); if (rq) { nr = kyber_get_domain_token(kqd, khd, hctx); if (nr >= 0) { @@ -598,6 +714,16 @@ kyber_dispatch_cur_domain(struct kyber_queue_data *kqd, list_del_init(&rq->queuelist); return rq; } + } else if (sbitmap_any_bit_set(&khd->kcq_map[khd->cur_domain])) { + nr = kyber_get_domain_token(kqd, khd, hctx); + if (nr >= 0) { + kyber_flush_busy_kcqs(khd, khd->cur_domain, rqs); + rq = list_first_entry(rqs, struct request, queuelist); + khd->batching++; + rq_set_domain_token(rq, nr); + list_del_init(&rq->queuelist); + return rq; + } } /* There were either no pending requests or no tokens. */ @@ -608,7 +734,6 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx) { struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data; struct kyber_hctx_data *khd = hctx->sched_data; - bool flushed = false; struct request *rq; int i; @@ -619,7 +744,7 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx) * from the batch. */ if (khd->batching < kyber_batch_size[khd->cur_domain]) { - rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed); + rq = kyber_dispatch_cur_domain(kqd, khd, hctx); if (rq) goto out; } @@ -640,7 +765,7 @@ static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx) else khd->cur_domain++; - rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed); + rq = kyber_dispatch_cur_domain(kqd, khd, hctx); if (rq) goto out; } @@ -657,10 +782,12 @@ static bool kyber_has_work(struct blk_mq_hw_ctx *hctx) int i; for (i = 0; i < KYBER_NUM_DOMAINS; i++) { - if (!list_empty_careful(&khd->rqs[i])) + if (!list_empty_careful(&khd->rqs[i]) || + sbitmap_any_bit_set(&khd->kcq_map[i])) return true; } - return sbitmap_any_bit_set(&hctx->ctx_map); + + return false; } #define KYBER_LAT_SHOW_STORE(op) \ @@ -831,7 +958,9 @@ static struct elevator_type kyber_sched = { .init_hctx = kyber_init_hctx, .exit_hctx = kyber_exit_hctx, .limit_depth = kyber_limit_depth, + .bio_merge = kyber_bio_merge, .prepare_request = kyber_prepare_request, + .insert_requests = kyber_insert_requests, .finish_request = kyber_finish_request, .requeue_request = kyber_finish_request, .completed_request = kyber_completed_request, diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 8ec0ba9f53861..099a9e05854c3 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -630,8 +630,7 @@ STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0); #undef STORE_FUNCTION #define DD_ATTR(name) \ - __ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \ - deadline_##name##_store) + __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store) static struct elv_fs_entry deadline_attrs[] = { DD_ATTR(read_expire), diff --git a/block/partition-generic.c b/block/partition-generic.c index 08dabcd8b6aef..3dcfd4ec0e111 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -145,13 +145,15 @@ ssize_t part_stat_show(struct device *dev, jiffies_to_msecs(part_stat_read(p, time_in_queue))); } -ssize_t part_inflight_show(struct device *dev, - struct device_attribute *attr, char *buf) +ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct hd_struct *p = dev_to_part(dev); + struct request_queue *q = part_to_disk(p)->queue; + unsigned int inflight[2]; - return sprintf(buf, "%8u %8u\n", atomic_read(&p->in_flight[0]), - atomic_read(&p->in_flight[1])); + part_in_flight_rw(q, p, inflight); + return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]); } #ifdef CONFIG_FAIL_MAKE_REQUEST @@ -177,18 +179,17 @@ ssize_t part_fail_store(struct device *dev, } #endif -static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL); -static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL); -static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); -static DEVICE_ATTR(ro, S_IRUGO, part_ro_show, NULL); -static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL); -static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show, - NULL); -static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); -static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); +static DEVICE_ATTR(partition, 0444, part_partition_show, NULL); +static DEVICE_ATTR(start, 0444, part_start_show, NULL); +static DEVICE_ATTR(size, 0444, part_size_show, NULL); +static DEVICE_ATTR(ro, 0444, part_ro_show, NULL); +static DEVICE_ATTR(alignment_offset, 0444, part_alignment_offset_show, NULL); +static DEVICE_ATTR(discard_alignment, 0444, part_discard_alignment_show, NULL); +static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); +static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = - __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); + __ATTR(make-it-fail, 0644, part_fail_show, part_fail_store); #endif static struct attribute *part_attrs[] = { @@ -289,8 +290,7 @@ static ssize_t whole_disk_show(struct device *dev, { return 0; } -static DEVICE_ATTR(whole_disk, S_IRUSR | S_IRGRP | S_IROTH, - whole_disk_show, NULL); +static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); /* * Must be called either with bd_mutex held, before a disk can be opened or @@ -516,7 +516,7 @@ rescan: if (disk->fops->revalidate_disk) disk->fops->revalidate_disk(disk); - check_disk_size_change(disk, bdev); + check_disk_size_change(disk, bdev, true); bdev->bd_invalidated = 0; if (!get_capacity(disk) || !(state = check_partition(disk, bdev))) return 0; @@ -641,7 +641,7 @@ int invalidate_partitions(struct gendisk *disk, struct block_device *bdev) return res; set_capacity(disk, 0); - check_disk_size_change(disk, bdev); + check_disk_size_change(disk, bdev, false); bdev->bd_invalidated = 0; /* tell userspace that the media / partition table may have changed */ kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 60b471f8621bf..533f4aee8567a 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -321,8 +321,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk, at_head = 1; ret = -ENOMEM; - rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, - GFP_KERNEL); + rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0); if (IS_ERR(rq)) return PTR_ERR(rq); req = scsi_req(rq); @@ -449,8 +448,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, } - rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, - __GFP_RECLAIM); + rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0); if (IS_ERR(rq)) { err = PTR_ERR(rq); goto error_free_buffer; @@ -501,7 +499,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode, break; } - if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_RECLAIM)) { + if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, GFP_NOIO)) { err = DRIVER_ERROR << 24; goto error; } @@ -538,7 +536,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk, struct request *rq; int err; - rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM); + rq = blk_get_request(q, REQ_OP_SCSI_OUT, 0); if (IS_ERR(rq)) return PTR_ERR(rq); rq->timeout = BLK_DEFAULT_SG_TIMEOUT; |