--- /dev/null
- * Nick Piggin <piggin@cyberone.com.au>
+ /*
+ * linux/drivers/block/as-iosched.c
+ *
+ * Anticipatory & deadline i/o scheduler.
+ *
+ * Copyright (C) 2002 Jens Axboe <axboe@suse.de>
- AS_TASK_RUNNING=0, /* Process has not exitted */
++ * Nick Piggin <nickpiggin@yahoo.com.au>
+ *
+ */
+ #include <linux/kernel.h>
+ #include <linux/fs.h>
+ #include <linux/blkdev.h>
+ #include <linux/elevator.h>
+ #include <linux/bio.h>
+ #include <linux/config.h>
+ #include <linux/module.h>
+ #include <linux/slab.h>
+ #include <linux/init.h>
+ #include <linux/compiler.h>
+ #include <linux/hash.h>
+ #include <linux/rbtree.h>
+ #include <linux/interrupt.h>
+
+ #define REQ_SYNC 1
+ #define REQ_ASYNC 0
+
+ /*
+ * See Documentation/block/as-iosched.txt
+ */
+
+ /*
+ * max time before a read is submitted.
+ */
+ #define default_read_expire (HZ / 8)
+
+ /*
+ * ditto for writes, these limits are not hard, even
+ * if the disk is capable of satisfying them.
+ */
+ #define default_write_expire (HZ / 4)
+
+ /*
+ * read_batch_expire describes how long we will allow a stream of reads to
+ * persist before looking to see whether it is time to switch over to writes.
+ */
+ #define default_read_batch_expire (HZ / 2)
+
+ /*
+ * write_batch_expire describes how long we want a stream of writes to run for.
+ * This is not a hard limit, but a target we set for the auto-tuning thingy.
+ * See, the problem is: we can send a lot of writes to disk cache / TCQ in
+ * a short amount of time...
+ */
+ #define default_write_batch_expire (HZ / 8)
+
+ /*
+ * max time we may wait to anticipate a read (default around 6ms)
+ */
+ #define default_antic_expire ((HZ / 150) ? HZ / 150 : 1)
+
+ /*
+ * Keep track of up to 20ms thinktimes. We can go as big as we like here,
+ * however huge values tend to interfere and not decay fast enough. A program
+ * might be in a non-io phase of operation. Waiting on user input for example,
+ * or doing a lengthy computation. A small penalty can be justified there, and
+ * will still catch out those processes that constantly have large thinktimes.
+ */
+ #define MAX_THINKTIME (HZ/50UL)
+
+ /* Bits in as_io_context.state */
+ enum as_io_states {
- /* process anticipated on has exitted or timed out*/
++ AS_TASK_RUNNING=0, /* Process has not exited */
+ AS_TASK_IOSTARTED, /* Process has started some IO */
+ AS_TASK_IORUNNING, /* Process has completed some IO */
+ };
+
+ enum anticipation_status {
+ ANTIC_OFF=0, /* Not anticipating (normal operation) */
+ ANTIC_WAIT_REQ, /* The last read has not yet completed */
+ ANTIC_WAIT_NEXT, /* Currently anticipating a request vs
+ last read (which has completed) */
+ ANTIC_FINISHED, /* Anticipating but have found a candidate
+ * or timed out */
+ };
+
+ struct as_data {
+ /*
+ * run time data
+ */
+
+ struct request_queue *q; /* the "owner" queue */
+
+ /*
+ * requests (as_rq s) are present on both sort_list and fifo_list
+ */
+ struct rb_root sort_list[2];
+ struct list_head fifo_list[2];
+
+ struct as_rq *next_arq[2]; /* next in sort order */
+ sector_t last_sector[2]; /* last REQ_SYNC & REQ_ASYNC sectors */
+ struct list_head *hash; /* request hash */
+
+ unsigned long exit_prob; /* probability a task will exit while
+ being waited on */
++ unsigned long exit_no_coop; /* probablility an exited task will
++ not be part of a later cooperating
++ request */
+ unsigned long new_ttime_total; /* mean thinktime on new proc */
+ unsigned long new_ttime_mean;
+ u64 new_seek_total; /* mean seek on new proc */
+ sector_t new_seek_mean;
+
+ unsigned long current_batch_expires;
+ unsigned long last_check_fifo[2];
+ int changed_batch; /* 1: waiting for old batch to end */
+ int new_batch; /* 1: waiting on first read complete */
+ int batch_data_dir; /* current batch REQ_SYNC / REQ_ASYNC */
+ int write_batch_count; /* max # of reqs in a write batch */
+ int current_write_count; /* how many requests left this batch */
+ int write_batch_idled; /* has the write batch gone idle? */
+ mempool_t *arq_pool;
+
+ enum anticipation_status antic_status;
+ unsigned long antic_start; /* jiffies: when it started */
+ struct timer_list antic_timer; /* anticipatory scheduling timer */
+ struct work_struct antic_work; /* Deferred unplugging */
+ struct io_context *io_context; /* Identify the expected process */
+ int ioc_finished; /* IO associated with io_context is finished */
+ int nr_dispatched;
+
+ /*
+ * settings that change how the i/o scheduler behaves
+ */
+ unsigned long fifo_expire[2];
+ unsigned long batch_expire[2];
+ unsigned long antic_expire;
+ };
+
+ #define list_entry_fifo(ptr) list_entry((ptr), struct as_rq, fifo)
+
+ /*
+ * per-request data.
+ */
+ enum arq_state {
+ AS_RQ_NEW=0, /* New - not referenced and not on any lists */
+ AS_RQ_QUEUED, /* In the request queue. It belongs to the
+ scheduler */
+ AS_RQ_DISPATCHED, /* On the dispatch list. It belongs to the
+ driver now */
+ AS_RQ_PRESCHED, /* Debug poisoning for requests being used */
+ AS_RQ_REMOVED,
+ AS_RQ_MERGED,
+ AS_RQ_POSTSCHED, /* when they shouldn't be */
+ };
+
+ struct as_rq {
+ /*
+ * rbtree index, key is the starting offset
+ */
+ struct rb_node rb_node;
+ sector_t rb_key;
+
+ struct request *request;
+
+ struct io_context *io_context; /* The submitting task */
+
+ /*
+ * request hash, key is the ending offset (for back merge lookup)
+ */
+ struct list_head hash;
+ unsigned int on_hash;
+
+ /*
+ * expire fifo
+ */
+ struct list_head fifo;
+ unsigned long expires;
+
+ unsigned int is_sync;
+ enum arq_state state;
+ };
+
+ #define RQ_DATA(rq) ((struct as_rq *) (rq)->elevator_private)
+
+ static kmem_cache_t *arq_pool;
+
+ /*
+ * IO Context helper functions
+ */
+
+ /* Called to deallocate the as_io_context */
+ static void free_as_io_context(struct as_io_context *aic)
+ {
+ kfree(aic);
+ }
+
+ /* Called when the task exits */
+ static void exit_as_io_context(struct as_io_context *aic)
+ {
+ WARN_ON(!test_bit(AS_TASK_RUNNING, &aic->state));
+ clear_bit(AS_TASK_RUNNING, &aic->state);
+ }
+
+ static struct as_io_context *alloc_as_io_context(void)
+ {
+ struct as_io_context *ret;
+
+ ret = kmalloc(sizeof(*ret), GFP_ATOMIC);
+ if (ret) {
+ ret->dtor = free_as_io_context;
+ ret->exit = exit_as_io_context;
+ ret->state = 1 << AS_TASK_RUNNING;
+ atomic_set(&ret->nr_queued, 0);
+ atomic_set(&ret->nr_dispatched, 0);
+ spin_lock_init(&ret->lock);
+ ret->ttime_total = 0;
+ ret->ttime_samples = 0;
+ ret->ttime_mean = 0;
+ ret->seek_total = 0;
+ ret->seek_samples = 0;
+ ret->seek_mean = 0;
+ }
+
+ return ret;
+ }
+
+ /*
+ * If the current task has no AS IO context then create one and initialise it.
+ * Then take a ref on the task's io context and return it.
+ */
+ static struct io_context *as_get_io_context(void)
+ {
+ struct io_context *ioc = get_io_context(GFP_ATOMIC);
+ if (ioc && !ioc->aic) {
+ ioc->aic = alloc_as_io_context();
+ if (!ioc->aic) {
+ put_io_context(ioc);
+ ioc = NULL;
+ }
+ }
+ return ioc;
+ }
+
+ static void as_put_io_context(struct as_rq *arq)
+ {
+ struct as_io_context *aic;
+
+ if (unlikely(!arq->io_context))
+ return;
+
+ aic = arq->io_context->aic;
+
+ if (arq->is_sync == REQ_SYNC && aic) {
+ spin_lock(&aic->lock);
+ set_bit(AS_TASK_IORUNNING, &aic->state);
+ aic->last_end_request = jiffies;
+ spin_unlock(&aic->lock);
+ }
+
+ put_io_context(arq->io_context);
+ }
+
+ /*
+ * the back merge hash support functions
+ */
+ static const int as_hash_shift = 6;
+ #define AS_HASH_BLOCK(sec) ((sec) >> 3)
+ #define AS_HASH_FN(sec) (hash_long(AS_HASH_BLOCK((sec)), as_hash_shift))
+ #define AS_HASH_ENTRIES (1 << as_hash_shift)
+ #define rq_hash_key(rq) ((rq)->sector + (rq)->nr_sectors)
+ #define list_entry_hash(ptr) list_entry((ptr), struct as_rq, hash)
+
+ static inline void __as_del_arq_hash(struct as_rq *arq)
+ {
+ arq->on_hash = 0;
+ list_del_init(&arq->hash);
+ }
+
+ static inline void as_del_arq_hash(struct as_rq *arq)
+ {
+ if (arq->on_hash)
+ __as_del_arq_hash(arq);
+ }
+
+ static void as_add_arq_hash(struct as_data *ad, struct as_rq *arq)
+ {
+ struct request *rq = arq->request;
+
+ BUG_ON(arq->on_hash);
+
+ arq->on_hash = 1;
+ list_add(&arq->hash, &ad->hash[AS_HASH_FN(rq_hash_key(rq))]);
+ }
+
+ /*
+ * move hot entry to front of chain
+ */
+ static inline void as_hot_arq_hash(struct as_data *ad, struct as_rq *arq)
+ {
+ struct request *rq = arq->request;
+ struct list_head *head = &ad->hash[AS_HASH_FN(rq_hash_key(rq))];
+
+ if (!arq->on_hash) {
+ WARN_ON(1);
+ return;
+ }
+
+ if (arq->hash.prev != head) {
+ list_del(&arq->hash);
+ list_add(&arq->hash, head);
+ }
+ }
+
+ static struct request *as_find_arq_hash(struct as_data *ad, sector_t offset)
+ {
+ struct list_head *hash_list = &ad->hash[AS_HASH_FN(offset)];
+ struct list_head *entry, *next = hash_list->next;
+
+ while ((entry = next) != hash_list) {
+ struct as_rq *arq = list_entry_hash(entry);
+ struct request *__rq = arq->request;
+
+ next = entry->next;
+
+ BUG_ON(!arq->on_hash);
+
+ if (!rq_mergeable(__rq)) {
+ as_del_arq_hash(arq);
+ continue;
+ }
+
+ if (rq_hash_key(__rq) == offset)
+ return __rq;
+ }
+
+ return NULL;
+ }
+
+ /*
+ * rb tree support functions
+ */
+ #define RB_NONE (2)
+ #define RB_EMPTY(root) ((root)->rb_node == NULL)
+ #define ON_RB(node) ((node)->rb_color != RB_NONE)
+ #define RB_CLEAR(node) ((node)->rb_color = RB_NONE)
+ #define rb_entry_arq(node) rb_entry((node), struct as_rq, rb_node)
+ #define ARQ_RB_ROOT(ad, arq) (&(ad)->sort_list[(arq)->is_sync])
+ #define rq_rb_key(rq) (rq)->sector
+
+ /*
+ * as_find_first_arq finds the first (lowest sector numbered) request
+ * for the specified data_dir. Used to sweep back to the start of the disk
+ * (1-way elevator) after we process the last (highest sector) request.
+ */
+ static struct as_rq *as_find_first_arq(struct as_data *ad, int data_dir)
+ {
+ struct rb_node *n = ad->sort_list[data_dir].rb_node;
+
+ if (n == NULL)
+ return NULL;
+
+ for (;;) {
+ if (n->rb_left == NULL)
+ return rb_entry_arq(n);
+
+ n = n->rb_left;
+ }
+ }
+
+ /*
+ * Add the request to the rb tree if it is unique. If there is an alias (an
+ * existing request against the same sector), which can happen when using
+ * direct IO, then return the alias.
+ */
+ static struct as_rq *as_add_arq_rb(struct as_data *ad, struct as_rq *arq)
+ {
+ struct rb_node **p = &ARQ_RB_ROOT(ad, arq)->rb_node;
+ struct rb_node *parent = NULL;
+ struct as_rq *__arq;
+ struct request *rq = arq->request;
+
+ arq->rb_key = rq_rb_key(rq);
+
+ while (*p) {
+ parent = *p;
+ __arq = rb_entry_arq(parent);
+
+ if (arq->rb_key < __arq->rb_key)
+ p = &(*p)->rb_left;
+ else if (arq->rb_key > __arq->rb_key)
+ p = &(*p)->rb_right;
+ else
+ return __arq;
+ }
+
+ rb_link_node(&arq->rb_node, parent, p);
+ rb_insert_color(&arq->rb_node, ARQ_RB_ROOT(ad, arq));
+
+ return NULL;
+ }
+
+ static inline void as_del_arq_rb(struct as_data *ad, struct as_rq *arq)
+ {
+ if (!ON_RB(&arq->rb_node)) {
+ WARN_ON(1);
+ return;
+ }
+
+ rb_erase(&arq->rb_node, ARQ_RB_ROOT(ad, arq));
+ RB_CLEAR(&arq->rb_node);
+ }
+
+ static struct request *
+ as_find_arq_rb(struct as_data *ad, sector_t sector, int data_dir)
+ {
+ struct rb_node *n = ad->sort_list[data_dir].rb_node;
+ struct as_rq *arq;
+
+ while (n) {
+ arq = rb_entry_arq(n);
+
+ if (sector < arq->rb_key)
+ n = n->rb_left;
+ else if (sector > arq->rb_key)
+ n = n->rb_right;
+ else
+ return arq->request;
+ }
+
+ return NULL;
+ }
+
+ /*
+ * IO Scheduler proper
+ */
+
+ #define MAXBACK (1024 * 1024) /*
+ * Maximum distance the disk will go backward
+ * for a request.
+ */
+
+ #define BACK_PENALTY 2
+
+ /*
+ * as_choose_req selects the preferred one of two requests of the same data_dir
+ * ignoring time - eg. timeouts, which is the job of as_dispatch_request
+ */
+ static struct as_rq *
+ as_choose_req(struct as_data *ad, struct as_rq *arq1, struct as_rq *arq2)
+ {
+ int data_dir;
+ sector_t last, s1, s2, d1, d2;
+ int r1_wrap=0, r2_wrap=0; /* requests are behind the disk head */
+ const sector_t maxback = MAXBACK;
+
+ if (arq1 == NULL || arq1 == arq2)
+ return arq2;
+ if (arq2 == NULL)
+ return arq1;
+
+ data_dir = arq1->is_sync;
+
+ last = ad->last_sector[data_dir];
+ s1 = arq1->request->sector;
+ s2 = arq2->request->sector;
+
+ BUG_ON(data_dir != arq2->is_sync);
+
+ /*
+ * Strict one way elevator _except_ in the case where we allow
+ * short backward seeks which are biased as twice the cost of a
+ * similar forward seek.
+ */
+ if (s1 >= last)
+ d1 = s1 - last;
+ else if (s1+maxback >= last)
+ d1 = (last - s1)*BACK_PENALTY;
+ else {
+ r1_wrap = 1;
+ d1 = 0; /* shut up, gcc */
+ }
+
+ if (s2 >= last)
+ d2 = s2 - last;
+ else if (s2+maxback >= last)
+ d2 = (last - s2)*BACK_PENALTY;
+ else {
+ r2_wrap = 1;
+ d2 = 0;
+ }
+
+ /* Found required data */
+ if (!r1_wrap && r2_wrap)
+ return arq1;
+ else if (!r2_wrap && r1_wrap)
+ return arq2;
+ else if (r1_wrap && r2_wrap) {
+ /* both behind the head */
+ if (s1 <= s2)
+ return arq1;
+ else
+ return arq2;
+ }
+
+ /* Both requests in front of the head */
+ if (d1 < d2)
+ return arq1;
+ else if (d2 < d1)
+ return arq2;
+ else {
+ if (s1 >= s2)
+ return arq1;
+ else
+ return arq2;
+ }
+ }
+
+ /*
+ * as_find_next_arq finds the next request after @prev in elevator order.
+ * this with as_choose_req form the basis for how the scheduler chooses
+ * what request to process next. Anticipation works on top of this.
+ */
+ static struct as_rq *as_find_next_arq(struct as_data *ad, struct as_rq *last)
+ {
+ const int data_dir = last->is_sync;
+ struct as_rq *ret;
+ struct rb_node *rbnext = rb_next(&last->rb_node);
+ struct rb_node *rbprev = rb_prev(&last->rb_node);
+ struct as_rq *arq_next, *arq_prev;
+
+ BUG_ON(!ON_RB(&last->rb_node));
+
+ if (rbprev)
+ arq_prev = rb_entry_arq(rbprev);
+ else
+ arq_prev = NULL;
+
+ if (rbnext)
+ arq_next = rb_entry_arq(rbnext);
+ else {
+ arq_next = as_find_first_arq(ad, data_dir);
+ if (arq_next == last)
+ arq_next = NULL;
+ }
+
+ ret = as_choose_req(ad, arq_next, arq_prev);
+
+ return ret;
+ }
+
+ /*
+ * anticipatory scheduling functions follow
+ */
+
+ /*
+ * as_antic_expired tells us when we have anticipated too long.
+ * The funny "absolute difference" math on the elapsed time is to handle
+ * jiffy wraps, and disks which have been idle for 0x80000000 jiffies.
+ */
+ static int as_antic_expired(struct as_data *ad)
+ {
+ long delta_jif;
+
+ delta_jif = jiffies - ad->antic_start;
+ if (unlikely(delta_jif < 0))
+ delta_jif = -delta_jif;
+ if (delta_jif < ad->antic_expire)
+ return 0;
+
+ return 1;
+ }
+
+ /*
+ * as_antic_waitnext starts anticipating that a nice request will soon be
+ * submitted. See also as_antic_waitreq
+ */
+ static void as_antic_waitnext(struct as_data *ad)
+ {
+ unsigned long timeout;
+
+ BUG_ON(ad->antic_status != ANTIC_OFF
+ && ad->antic_status != ANTIC_WAIT_REQ);
+
+ timeout = ad->antic_start + ad->antic_expire;
+
+ mod_timer(&ad->antic_timer, timeout);
+
+ ad->antic_status = ANTIC_WAIT_NEXT;
+ }
+
+ /*
+ * as_antic_waitreq starts anticipating. We don't start timing the anticipation
+ * until the request that we're anticipating on has finished. This means we
+ * are timing from when the candidate process wakes up hopefully.
+ */
+ static void as_antic_waitreq(struct as_data *ad)
+ {
+ BUG_ON(ad->antic_status == ANTIC_FINISHED);
+ if (ad->antic_status == ANTIC_OFF) {
+ if (!ad->io_context || ad->ioc_finished)
+ as_antic_waitnext(ad);
+ else
+ ad->antic_status = ANTIC_WAIT_REQ;
+ }
+ }
+
+ /*
+ * This is called directly by the functions in this file to stop anticipation.
+ * We kill the timer and schedule a call to the request_fn asap.
+ */
+ static void as_antic_stop(struct as_data *ad)
+ {
+ int status = ad->antic_status;
+
+ if (status == ANTIC_WAIT_REQ || status == ANTIC_WAIT_NEXT) {
+ if (status == ANTIC_WAIT_NEXT)
+ del_timer(&ad->antic_timer);
+ ad->antic_status = ANTIC_FINISHED;
+ /* see as_work_handler */
+ kblockd_schedule_work(&ad->antic_work);
+ }
+ }
+
+ /*
+ * as_antic_timeout is the timer function set by as_antic_waitnext.
+ */
+ static void as_antic_timeout(unsigned long data)
+ {
+ struct request_queue *q = (struct request_queue *)data;
+ struct as_data *ad = q->elevator->elevator_data;
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ if (ad->antic_status == ANTIC_WAIT_REQ
+ || ad->antic_status == ANTIC_WAIT_NEXT) {
+ struct as_io_context *aic = ad->io_context->aic;
+
+ ad->antic_status = ANTIC_FINISHED;
+ kblockd_schedule_work(&ad->antic_work);
+
+ if (aic->ttime_samples == 0) {
-static int as_close_req(struct as_data *ad, struct as_rq *arq)
++ /* process anticipated on has exited or timed out*/
+ ad->exit_prob = (7*ad->exit_prob + 256)/8;
+ }
++ if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
++ /* process not "saved" by a cooperating request */
++ ad->exit_no_coop = (7*ad->exit_no_coop + 256)/8;
++ }
+ }
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ }
+
++static void as_update_thinktime(struct as_data *ad, struct as_io_context *aic,
++ unsigned long ttime)
++{
++ /* fixed point: 1.0 == 1<<8 */
++ if (aic->ttime_samples == 0) {
++ ad->new_ttime_total = (7*ad->new_ttime_total + 256*ttime) / 8;
++ ad->new_ttime_mean = ad->new_ttime_total / 256;
++
++ ad->exit_prob = (7*ad->exit_prob)/8;
++ }
++ aic->ttime_samples = (7*aic->ttime_samples + 256) / 8;
++ aic->ttime_total = (7*aic->ttime_total + 256*ttime) / 8;
++ aic->ttime_mean = (aic->ttime_total + 128) / aic->ttime_samples;
++}
++
++static void as_update_seekdist(struct as_data *ad, struct as_io_context *aic,
++ sector_t sdist)
++{
++ u64 total;
++
++ if (aic->seek_samples == 0) {
++ ad->new_seek_total = (7*ad->new_seek_total + 256*(u64)sdist)/8;
++ ad->new_seek_mean = ad->new_seek_total / 256;
++ }
++
++ /*
++ * Don't allow the seek distance to get too large from the
++ * odd fragment, pagein, etc
++ */
++ if (aic->seek_samples <= 60) /* second&third seek */
++ sdist = min(sdist, (aic->seek_mean * 4) + 2*1024*1024);
++ else
++ sdist = min(sdist, (aic->seek_mean * 4) + 2*1024*64);
++
++ aic->seek_samples = (7*aic->seek_samples + 256) / 8;
++ aic->seek_total = (7*aic->seek_total + (u64)256*sdist) / 8;
++ total = aic->seek_total + (aic->seek_samples/2);
++ do_div(total, aic->seek_samples);
++ aic->seek_mean = (sector_t)total;
++}
++
++/*
++ * as_update_iohist keeps a decaying histogram of IO thinktimes, and
++ * updates @aic->ttime_mean based on that. It is called when a new
++ * request is queued.
++ */
++static void as_update_iohist(struct as_data *ad, struct as_io_context *aic,
++ struct request *rq)
++{
++ struct as_rq *arq = RQ_DATA(rq);
++ int data_dir = arq->is_sync;
++ unsigned long thinktime = 0;
++ sector_t seek_dist;
++
++ if (aic == NULL)
++ return;
++
++ if (data_dir == REQ_SYNC) {
++ unsigned long in_flight = atomic_read(&aic->nr_queued)
++ + atomic_read(&aic->nr_dispatched);
++ spin_lock(&aic->lock);
++ if (test_bit(AS_TASK_IORUNNING, &aic->state) ||
++ test_bit(AS_TASK_IOSTARTED, &aic->state)) {
++ /* Calculate read -> read thinktime */
++ if (test_bit(AS_TASK_IORUNNING, &aic->state)
++ && in_flight == 0) {
++ thinktime = jiffies - aic->last_end_request;
++ thinktime = min(thinktime, MAX_THINKTIME-1);
++ }
++ as_update_thinktime(ad, aic, thinktime);
++
++ /* Calculate read -> read seek distance */
++ if (aic->last_request_pos < rq->sector)
++ seek_dist = rq->sector - aic->last_request_pos;
++ else
++ seek_dist = aic->last_request_pos - rq->sector;
++ as_update_seekdist(ad, aic, seek_dist);
++ }
++ aic->last_request_pos = rq->sector + rq->nr_sectors;
++ set_bit(AS_TASK_IOSTARTED, &aic->state);
++ spin_unlock(&aic->lock);
++ }
++}
++
+ /*
+ * as_close_req decides if one request is considered "close" to the
+ * previous one issued.
+ */
- if (delay <= 1)
- delta = 64;
++static int as_close_req(struct as_data *ad, struct as_io_context *aic,
++ struct as_rq *arq)
+ {
+ unsigned long delay; /* milliseconds */
+ sector_t last = ad->last_sector[ad->batch_data_dir];
+ sector_t next = arq->request->sector;
+ sector_t delta; /* acceptable close offset (in sectors) */
++ sector_t s;
+
+ if (ad->antic_status == ANTIC_OFF || !ad->ioc_finished)
+ delay = 0;
+ else
+ delay = ((jiffies - ad->antic_start) * 1000) / HZ;
+
- delta = 64 << (delay-1);
++ if (delay == 0)
++ delta = 8192;
+ else if (delay <= 20 && delay <= ad->antic_expire)
- return (last - (delta>>1) <= next) && (next <= last + delta);
++ delta = 8192 << delay;
+ else
+ return 1;
+
- * If the task which has submitted the request has exitted, break anticipation.
++ if ((last <= next + (delta>>1)) && (next <= last + delta))
++ return 1;
++
++ if (last < next)
++ s = next - last;
++ else
++ s = last - next;
++
++ if (aic->seek_samples == 0) {
++ /*
++ * Process has just started IO. Use past statistics to
++ * gauge success possibility
++ */
++ if (ad->new_seek_mean > s) {
++ /* this request is better than what we're expecting */
++ return 1;
++ }
++
++ } else {
++ if (aic->seek_mean > s) {
++ /* this request is better than what we're expecting */
++ return 1;
++ }
++ }
++
++ return 0;
+ }
+
+ /*
+ * as_can_break_anticipation returns true if we have been anticipating this
+ * request.
+ *
+ * It also returns true if the process against which we are anticipating
+ * submits a write - that's presumably an fsync, O_SYNC write, etc. We want to
+ * dispatch it ASAP, because we know that application will not be submitting
+ * any new reads.
+ *
- sector_t s;
++ * If the task which has submitted the request has exited, break anticipation.
+ *
+ * If this task has queued some other IO, do not enter enticipation.
+ */
+ static int as_can_break_anticipation(struct as_data *ad, struct as_rq *arq)
+ {
+ struct io_context *ioc;
+ struct as_io_context *aic;
- if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
- /* process anticipated on has exitted */
- if (aic->ttime_samples == 0)
- ad->exit_prob = (7*ad->exit_prob + 256)/8;
- return 1;
- }
-
+
+ ioc = ad->io_context;
+ BUG_ON(!ioc);
+
+ if (arq && ioc == arq->io_context) {
+ /* request from same process */
+ return 1;
+ }
+
+ if (ad->ioc_finished && as_antic_expired(ad)) {
+ /*
+ * In this situation status should really be FINISHED,
+ * however the timer hasn't had the chance to run yet.
+ */
+ return 1;
+ }
+
+ aic = ioc->aic;
+ if (!aic)
+ return 0;
+
- if (arq && arq->is_sync == REQ_SYNC && as_close_req(ad, arq)) {
+ if (atomic_read(&aic->nr_queued) > 0) {
+ /* process has more requests queued */
+ return 1;
+ }
+
+ if (atomic_read(&aic->nr_dispatched) > 0) {
+ /* process has more requests dispatched */
+ return 1;
+ }
+
- * This makes close requests from another process reset
- * our thinktime delay. Is generally useful when there are
++ if (arq && arq->is_sync == REQ_SYNC && as_close_req(ad, aic, arq)) {
+ /*
+ * Found a close request that is not one of ours.
+ *
- spin_lock(&aic->lock);
- aic->last_end_request = jiffies;
- spin_unlock(&aic->lock);
++ * This makes close requests from another process update
++ * our IO history. Is generally useful when there are
+ * two or more cooperating processes working in the same
+ * area.
+ */
- if (ad->exit_prob > 128)
++ if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
++ if (aic->ttime_samples == 0)
++ ad->exit_prob = (7*ad->exit_prob + 256)/8;
++
++ ad->exit_no_coop = (7*ad->exit_no_coop)/8;
++ }
++
++ as_update_iohist(ad, aic, arq->request);
+ return 1;
+ }
+
++ if (!test_bit(AS_TASK_RUNNING, &aic->state)) {
++ /* process anticipated on has exited */
++ if (aic->ttime_samples == 0)
++ ad->exit_prob = (7*ad->exit_prob + 256)/8;
++
++ if (ad->exit_no_coop > 128)
++ return 1;
++ }
+
+ if (aic->ttime_samples == 0) {
+ if (ad->new_ttime_mean > ad->antic_expire)
+ return 1;
- if (!arq)
- return 0;
-
- if (ad->last_sector[REQ_SYNC] < arq->request->sector)
- s = arq->request->sector - ad->last_sector[REQ_SYNC];
- else
- s = ad->last_sector[REQ_SYNC] - arq->request->sector;
-
- if (aic->seek_samples == 0) {
- /*
- * Process has just started IO. Use past statistics to
- * guage success possibility
- */
- if (ad->new_seek_mean > s) {
- /* this request is better than what we're expecting */
- return 1;
- }
-
- } else {
- if (aic->seek_mean > s) {
- /* this request is better than what we're expecting */
- return 1;
- }
- }
-
++ if (ad->exit_prob * ad->exit_no_coop > 128*256)
+ return 1;
+ } else if (aic->ttime_mean > ad->antic_expire) {
+ /* the process thinks too much between requests */
+ return 1;
+ }
+
- *
+ return 0;
+ }
+
+ /*
+ * as_can_anticipate indicates weather we should either run arq
+ * or keep anticipating a better request.
+ */
+ static int as_can_anticipate(struct as_data *ad, struct as_rq *arq)
+ {
+ if (!ad->io_context)
+ /*
+ * Last request submitted was a write
+ */
+ return 0;
+
+ if (ad->antic_status == ANTIC_FINISHED)
+ /*
+ * Don't restart if we have just finished. Run the next request
+ */
+ return 0;
+
+ if (as_can_break_anticipation(ad, arq))
+ /*
+ * This request is a good candidate. Don't keep anticipating,
+ * run it.
+ */
+ return 0;
+
+ /*
+ * OK from here, we haven't finished, and don't have a decent request!
+ * Status is either ANTIC_OFF so start waiting,
+ * ANTIC_WAIT_REQ so continue waiting for request to finish
+ * or ANTIC_WAIT_NEXT so continue waiting for an acceptable request.
-static void as_update_thinktime(struct as_data *ad, struct as_io_context *aic, unsigned long ttime)
-{
- /* fixed point: 1.0 == 1<<8 */
- if (aic->ttime_samples == 0) {
- ad->new_ttime_total = (7*ad->new_ttime_total + 256*ttime) / 8;
- ad->new_ttime_mean = ad->new_ttime_total / 256;
-
- ad->exit_prob = (7*ad->exit_prob)/8;
- }
- aic->ttime_samples = (7*aic->ttime_samples + 256) / 8;
- aic->ttime_total = (7*aic->ttime_total + 256*ttime) / 8;
- aic->ttime_mean = (aic->ttime_total + 128) / aic->ttime_samples;
-}
-
-static void as_update_seekdist(struct as_data *ad, struct as_io_context *aic, sector_t sdist)
-{
- u64 total;
-
- if (aic->seek_samples == 0) {
- ad->new_seek_total = (7*ad->new_seek_total + 256*(u64)sdist)/8;
- ad->new_seek_mean = ad->new_seek_total / 256;
- }
-
- /*
- * Don't allow the seek distance to get too large from the
- * odd fragment, pagein, etc
- */
- if (aic->seek_samples <= 60) /* second&third seek */
- sdist = min(sdist, (aic->seek_mean * 4) + 2*1024*1024);
- else
- sdist = min(sdist, (aic->seek_mean * 4) + 2*1024*64);
-
- aic->seek_samples = (7*aic->seek_samples + 256) / 8;
- aic->seek_total = (7*aic->seek_total + (u64)256*sdist) / 8;
- total = aic->seek_total + (aic->seek_samples/2);
- do_div(total, aic->seek_samples);
- aic->seek_mean = (sector_t)total;
-}
-
-/*
- * as_update_iohist keeps a decaying histogram of IO thinktimes, and
- * updates @aic->ttime_mean based on that. It is called when a new
- * request is queued.
- */
-static void as_update_iohist(struct as_data *ad, struct as_io_context *aic, struct request *rq)
-{
- struct as_rq *arq = RQ_DATA(rq);
- int data_dir = arq->is_sync;
- unsigned long thinktime;
- sector_t seek_dist;
-
- if (aic == NULL)
- return;
-
- if (data_dir == REQ_SYNC) {
- unsigned long in_flight = atomic_read(&aic->nr_queued)
- + atomic_read(&aic->nr_dispatched);
- spin_lock(&aic->lock);
- if (test_bit(AS_TASK_IORUNNING, &aic->state) ||
- test_bit(AS_TASK_IOSTARTED, &aic->state)) {
- /* Calculate read -> read thinktime */
- if (test_bit(AS_TASK_IORUNNING, &aic->state)
- && in_flight == 0) {
- thinktime = jiffies - aic->last_end_request;
- thinktime = min(thinktime, MAX_THINKTIME-1);
- } else
- thinktime = 0;
- as_update_thinktime(ad, aic, thinktime);
-
- /* Calculate read -> read seek distance */
- if (aic->last_request_pos < rq->sector)
- seek_dist = rq->sector - aic->last_request_pos;
- else
- seek_dist = aic->last_request_pos - rq->sector;
- as_update_seekdist(ad, aic, seek_dist);
- }
- aic->last_request_pos = rq->sector + rq->nr_sectors;
- set_bit(AS_TASK_IOSTARTED, &aic->state);
- spin_unlock(&aic->lock);
- }
-}
-
+ */
+
+ return 1;
+ }
+
- if (!(reads && writes && as_batch_expired(ad)) ) {
+ /*
+ * as_update_arq must be called whenever a request (arq) is added to
+ * the sort_list. This function keeps caches up to date, and checks if the
+ * request might be one we are "anticipating"
+ */
+ static void as_update_arq(struct as_data *ad, struct as_rq *arq)
+ {
+ const int data_dir = arq->is_sync;
+
+ /* keep the next_arq cache up to date */
+ ad->next_arq[data_dir] = as_choose_req(ad, arq, ad->next_arq[data_dir]);
+
+ /*
+ * have we been anticipating this request?
+ * or does it come from the same process as the one we are anticipating
+ * for?
+ */
+ if (ad->antic_status == ANTIC_WAIT_REQ
+ || ad->antic_status == ANTIC_WAIT_NEXT) {
+ if (as_can_break_anticipation(ad, arq))
+ as_antic_stop(ad);
+ }
+ }
+
+ /*
+ * Gathers timings and resizes the write batch automatically
+ */
+ static void update_write_batch(struct as_data *ad)
+ {
+ unsigned long batch = ad->batch_expire[REQ_ASYNC];
+ long write_time;
+
+ write_time = (jiffies - ad->current_batch_expires) + batch;
+ if (write_time < 0)
+ write_time = 0;
+
+ if (write_time > batch && !ad->write_batch_idled) {
+ if (write_time > batch * 3)
+ ad->write_batch_count /= 2;
+ else
+ ad->write_batch_count--;
+ } else if (write_time < batch && ad->current_write_count == 0) {
+ if (batch > write_time * 3)
+ ad->write_batch_count *= 2;
+ else
+ ad->write_batch_count++;
+ }
+
+ if (ad->write_batch_count < 1)
+ ad->write_batch_count = 1;
+ }
+
+ /*
+ * as_completed_request is to be called when a request has completed and
+ * returned something to the requesting process, be it an error or data.
+ */
+ static void as_completed_request(request_queue_t *q, struct request *rq)
+ {
+ struct as_data *ad = q->elevator->elevator_data;
+ struct as_rq *arq = RQ_DATA(rq);
+
+ WARN_ON(!list_empty(&rq->queuelist));
+
+ if (arq->state != AS_RQ_REMOVED) {
+ printk("arq->state %d\n", arq->state);
+ WARN_ON(1);
+ goto out;
+ }
+
+ if (ad->changed_batch && ad->nr_dispatched == 1) {
+ kblockd_schedule_work(&ad->antic_work);
+ ad->changed_batch = 0;
+
+ if (ad->batch_data_dir == REQ_SYNC)
+ ad->new_batch = 1;
+ }
+ WARN_ON(ad->nr_dispatched == 0);
+ ad->nr_dispatched--;
+
+ /*
+ * Start counting the batch from when a request of that direction is
+ * actually serviced. This should help devices with big TCQ windows
+ * and writeback caches
+ */
+ if (ad->new_batch && ad->batch_data_dir == arq->is_sync) {
+ update_write_batch(ad);
+ ad->current_batch_expires = jiffies +
+ ad->batch_expire[REQ_SYNC];
+ ad->new_batch = 0;
+ }
+
+ if (ad->io_context == arq->io_context && ad->io_context) {
+ ad->antic_start = jiffies;
+ ad->ioc_finished = 1;
+ if (ad->antic_status == ANTIC_WAIT_REQ) {
+ /*
+ * We were waiting on this request, now anticipate
+ * the next one
+ */
+ as_antic_waitnext(ad);
+ }
+ }
+
+ as_put_io_context(arq);
+ out:
+ arq->state = AS_RQ_POSTSCHED;
+ }
+
+ /*
+ * as_remove_queued_request removes a request from the pre dispatch queue
+ * without updating refcounts. It is expected the caller will drop the
+ * reference unless it replaces the request at somepart of the elevator
+ * (ie. the dispatch queue)
+ */
+ static void as_remove_queued_request(request_queue_t *q, struct request *rq)
+ {
+ struct as_rq *arq = RQ_DATA(rq);
+ const int data_dir = arq->is_sync;
+ struct as_data *ad = q->elevator->elevator_data;
+
+ WARN_ON(arq->state != AS_RQ_QUEUED);
+
+ if (arq->io_context && arq->io_context->aic) {
+ BUG_ON(!atomic_read(&arq->io_context->aic->nr_queued));
+ atomic_dec(&arq->io_context->aic->nr_queued);
+ }
+
+ /*
+ * Update the "next_arq" cache if we are about to remove its
+ * entry
+ */
+ if (ad->next_arq[data_dir] == arq)
+ ad->next_arq[data_dir] = as_find_next_arq(ad, arq);
+
+ list_del_init(&arq->fifo);
+ as_del_arq_hash(arq);
+ as_del_arq_rb(ad, arq);
+ }
+
+ /*
+ * as_fifo_expired returns 0 if there are no expired reads on the fifo,
+ * 1 otherwise. It is ratelimited so that we only perform the check once per
+ * `fifo_expire' interval. Otherwise a large number of expired requests
+ * would create a hopeless seekstorm.
+ *
+ * See as_antic_expired comment.
+ */
+ static int as_fifo_expired(struct as_data *ad, int adir)
+ {
+ struct as_rq *arq;
+ long delta_jif;
+
+ delta_jif = jiffies - ad->last_check_fifo[adir];
+ if (unlikely(delta_jif < 0))
+ delta_jif = -delta_jif;
+ if (delta_jif < ad->fifo_expire[adir])
+ return 0;
+
+ ad->last_check_fifo[adir] = jiffies;
+
+ if (list_empty(&ad->fifo_list[adir]))
+ return 0;
+
+ arq = list_entry_fifo(ad->fifo_list[adir].next);
+
+ return time_after(jiffies, arq->expires);
+ }
+
+ /*
+ * as_batch_expired returns true if the current batch has expired. A batch
+ * is a set of reads or a set of writes.
+ */
+ static inline int as_batch_expired(struct as_data *ad)
+ {
+ if (ad->changed_batch || ad->new_batch)
+ return 0;
+
+ if (ad->batch_data_dir == REQ_SYNC)
+ /* TODO! add a check so a complete fifo gets written? */
+ return time_after(jiffies, ad->current_batch_expires);
+
+ return time_after(jiffies, ad->current_batch_expires)
+ || ad->current_write_count == 0;
+ }
+
+ /*
+ * move an entry to dispatch queue
+ */
+ static void as_move_to_dispatch(struct as_data *ad, struct as_rq *arq)
+ {
+ struct request *rq = arq->request;
+ const int data_dir = arq->is_sync;
+
+ BUG_ON(!ON_RB(&arq->rb_node));
+
+ as_antic_stop(ad);
+ ad->antic_status = ANTIC_OFF;
+
+ /*
+ * This has to be set in order to be correctly updated by
+ * as_find_next_arq
+ */
+ ad->last_sector[data_dir] = rq->sector + rq->nr_sectors;
+
+ if (data_dir == REQ_SYNC) {
+ /* In case we have to anticipate after this */
+ copy_io_context(&ad->io_context, &arq->io_context);
+ } else {
+ if (ad->io_context) {
+ put_io_context(ad->io_context);
+ ad->io_context = NULL;
+ }
+
+ if (ad->current_write_count != 0)
+ ad->current_write_count--;
+ }
+ ad->ioc_finished = 0;
+
+ ad->next_arq[data_dir] = as_find_next_arq(ad, arq);
+
+ /*
+ * take it off the sort and fifo list, add to dispatch queue
+ */
+ while (!list_empty(&rq->queuelist)) {
+ struct request *__rq = list_entry_rq(rq->queuelist.next);
+ struct as_rq *__arq = RQ_DATA(__rq);
+
+ list_del(&__rq->queuelist);
+
+ elv_dispatch_add_tail(ad->q, __rq);
+
+ if (__arq->io_context && __arq->io_context->aic)
+ atomic_inc(&__arq->io_context->aic->nr_dispatched);
+
+ WARN_ON(__arq->state != AS_RQ_QUEUED);
+ __arq->state = AS_RQ_DISPATCHED;
+
+ ad->nr_dispatched++;
+ }
+
+ as_remove_queued_request(ad->q, rq);
+ WARN_ON(arq->state != AS_RQ_QUEUED);
+
+ elv_dispatch_sort(ad->q, rq);
+
+ arq->state = AS_RQ_DISPATCHED;
+ if (arq->io_context && arq->io_context->aic)
+ atomic_inc(&arq->io_context->aic->nr_dispatched);
+ ad->nr_dispatched++;
+ }
+
+ /*
+ * as_dispatch_request selects the best request according to
+ * read/write expire, batch expire, etc, and moves it to the dispatch
+ * queue. Returns 1 if a request was found, 0 otherwise.
+ */
+ static int as_dispatch_request(request_queue_t *q, int force)
+ {
+ struct as_data *ad = q->elevator->elevator_data;
+ struct as_rq *arq;
+ const int reads = !list_empty(&ad->fifo_list[REQ_SYNC]);
+ const int writes = !list_empty(&ad->fifo_list[REQ_ASYNC]);
+
+ if (unlikely(force)) {
+ /*
+ * Forced dispatch, accounting is useless. Reset
+ * accounting states and dump fifo_lists. Note that
+ * batch_data_dir is reset to REQ_SYNC to avoid
+ * screwing write batch accounting as write batch
+ * accounting occurs on W->R transition.
+ */
+ int dispatched = 0;
+
+ ad->batch_data_dir = REQ_SYNC;
+ ad->changed_batch = 0;
+ ad->new_batch = 0;
+
+ while (ad->next_arq[REQ_SYNC]) {
+ as_move_to_dispatch(ad, ad->next_arq[REQ_SYNC]);
+ dispatched++;
+ }
+ ad->last_check_fifo[REQ_SYNC] = jiffies;
+
+ while (ad->next_arq[REQ_ASYNC]) {
+ as_move_to_dispatch(ad, ad->next_arq[REQ_ASYNC]);
+ dispatched++;
+ }
+ ad->last_check_fifo[REQ_ASYNC] = jiffies;
+
+ return dispatched;
+ }
+
+ /* Signal that the write batch was uncontended, so we can't time it */
+ if (ad->batch_data_dir == REQ_ASYNC && !reads) {
+ if (ad->current_write_count == 0 || !writes)
+ ad->write_batch_idled = 1;
+ }
+
+ if (!(reads || writes)
+ || ad->antic_status == ANTIC_WAIT_REQ
+ || ad->antic_status == ANTIC_WAIT_NEXT
+ || ad->changed_batch)
+ return 0;
+
-as_add_aliased_request(struct as_data *ad, struct as_rq *arq, struct as_rq *alias)
++ if (!(reads && writes && as_batch_expired(ad))) {
+ /*
+ * batch is still running or no reads or no writes
+ */
+ arq = ad->next_arq[ad->batch_data_dir];
+
+ if (ad->batch_data_dir == REQ_SYNC && ad->antic_expire) {
+ if (as_fifo_expired(ad, REQ_SYNC))
+ goto fifo_expired;
+
+ if (as_can_anticipate(ad, arq)) {
+ as_antic_waitreq(ad);
+ return 0;
+ }
+ }
+
+ if (arq) {
+ /* we have a "next request" */
+ if (reads && !writes)
+ ad->current_batch_expires =
+ jiffies + ad->batch_expire[REQ_SYNC];
+ goto dispatch_request;
+ }
+ }
+
+ /*
+ * at this point we are not running a batch. select the appropriate
+ * data direction (read / write)
+ */
+
+ if (reads) {
+ BUG_ON(RB_EMPTY(&ad->sort_list[REQ_SYNC]));
+
+ if (writes && ad->batch_data_dir == REQ_SYNC)
+ /*
+ * Last batch was a read, switch to writes
+ */
+ goto dispatch_writes;
+
+ if (ad->batch_data_dir == REQ_ASYNC) {
+ WARN_ON(ad->new_batch);
+ ad->changed_batch = 1;
+ }
+ ad->batch_data_dir = REQ_SYNC;
+ arq = list_entry_fifo(ad->fifo_list[ad->batch_data_dir].next);
+ ad->last_check_fifo[ad->batch_data_dir] = jiffies;
+ goto dispatch_request;
+ }
+
+ /*
+ * the last batch was a read
+ */
+
+ if (writes) {
+ dispatch_writes:
+ BUG_ON(RB_EMPTY(&ad->sort_list[REQ_ASYNC]));
+
+ if (ad->batch_data_dir == REQ_SYNC) {
+ ad->changed_batch = 1;
+
+ /*
+ * new_batch might be 1 when the queue runs out of
+ * reads. A subsequent submission of a write might
+ * cause a change of batch before the read is finished.
+ */
+ ad->new_batch = 0;
+ }
+ ad->batch_data_dir = REQ_ASYNC;
+ ad->current_write_count = ad->write_batch_count;
+ ad->write_batch_idled = 0;
+ arq = ad->next_arq[ad->batch_data_dir];
+ goto dispatch_request;
+ }
+
+ BUG();
+ return 0;
+
+ dispatch_request:
+ /*
+ * If a request has expired, service it.
+ */
+
+ if (as_fifo_expired(ad, ad->batch_data_dir)) {
+ fifo_expired:
+ arq = list_entry_fifo(ad->fifo_list[ad->batch_data_dir].next);
+ BUG_ON(arq == NULL);
+ }
+
+ if (ad->changed_batch) {
+ WARN_ON(ad->new_batch);
+
+ if (ad->nr_dispatched)
+ return 0;
+
+ if (ad->batch_data_dir == REQ_ASYNC)
+ ad->current_batch_expires = jiffies +
+ ad->batch_expire[REQ_ASYNC];
+ else
+ ad->new_batch = 1;
+
+ ad->changed_batch = 0;
+ }
+
+ /*
+ * arq is the selected appropriate request.
+ */
+ as_move_to_dispatch(ad, arq);
+
+ return 1;
+ }
+
+ /*
+ * Add arq to a list behind alias
+ */
+ static inline void
-static struct request *
-as_former_request(request_queue_t *q, struct request *rq)
++as_add_aliased_request(struct as_data *ad, struct as_rq *arq,
++ struct as_rq *alias)
+ {
+ struct request *req = arq->request;
+ struct list_head *insert = alias->request->queuelist.prev;
+
+ /*
+ * Transfer list of aliases
+ */
+ while (!list_empty(&req->queuelist)) {
+ struct request *__rq = list_entry_rq(req->queuelist.next);
+ struct as_rq *__arq = RQ_DATA(__rq);
+
+ list_move_tail(&__rq->queuelist, &alias->request->queuelist);
+
+ WARN_ON(__arq->state != AS_RQ_QUEUED);
+ }
+
+ /*
+ * Another request with the same start sector on the rbtree.
+ * Link this request to that sector. They are untangled in
+ * as_move_to_dispatch
+ */
+ list_add(&arq->request->queuelist, insert);
+
+ /*
+ * Don't want to have to handle merges.
+ */
+ as_del_arq_hash(arq);
+ arq->request->flags |= REQ_NOMERGE;
+ }
+
+ /*
+ * add arq to rbtree and fifo
+ */
+ static void as_add_request(request_queue_t *q, struct request *rq)
+ {
+ struct as_data *ad = q->elevator->elevator_data;
+ struct as_rq *arq = RQ_DATA(rq);
+ struct as_rq *alias;
+ int data_dir;
+
+ if (arq->state != AS_RQ_PRESCHED) {
+ printk("arq->state: %d\n", arq->state);
+ WARN_ON(1);
+ }
+ arq->state = AS_RQ_NEW;
+
+ if (rq_data_dir(arq->request) == READ
+ || current->flags&PF_SYNCWRITE)
+ arq->is_sync = 1;
+ else
+ arq->is_sync = 0;
+ data_dir = arq->is_sync;
+
+ arq->io_context = as_get_io_context();
+
+ if (arq->io_context) {
+ as_update_iohist(ad, arq->io_context->aic, arq->request);
+ atomic_inc(&arq->io_context->aic->nr_queued);
+ }
+
+ alias = as_add_arq_rb(ad, arq);
+ if (!alias) {
+ /*
+ * set expire time (only used for reads) and add to fifo list
+ */
+ arq->expires = jiffies + ad->fifo_expire[data_dir];
+ list_add_tail(&arq->fifo, &ad->fifo_list[data_dir]);
+
+ if (rq_mergeable(arq->request))
+ as_add_arq_hash(ad, arq);
+ as_update_arq(ad, arq); /* keep state machine up to date */
+
+ } else {
+ as_add_aliased_request(ad, arq, alias);
+
+ /*
+ * have we been anticipating this request?
+ * or does it come from the same process as the one we are
+ * anticipating for?
+ */
+ if (ad->antic_status == ANTIC_WAIT_REQ
+ || ad->antic_status == ANTIC_WAIT_NEXT) {
+ if (as_can_break_anticipation(ad, arq))
+ as_antic_stop(ad);
+ }
+ }
+
+ arq->state = AS_RQ_QUEUED;
+ }
+
+ static void as_activate_request(request_queue_t *q, struct request *rq)
+ {
+ struct as_rq *arq = RQ_DATA(rq);
+
+ WARN_ON(arq->state != AS_RQ_DISPATCHED);
+ arq->state = AS_RQ_REMOVED;
+ if (arq->io_context && arq->io_context->aic)
+ atomic_dec(&arq->io_context->aic->nr_dispatched);
+ }
+
+ static void as_deactivate_request(request_queue_t *q, struct request *rq)
+ {
+ struct as_rq *arq = RQ_DATA(rq);
+
+ WARN_ON(arq->state != AS_RQ_REMOVED);
+ arq->state = AS_RQ_DISPATCHED;
+ if (arq->io_context && arq->io_context->aic)
+ atomic_inc(&arq->io_context->aic->nr_dispatched);
+ }
+
+ /*
+ * as_queue_empty tells us if there are requests left in the device. It may
+ * not be the case that a driver can get the next request even if the queue
+ * is not empty - it is used in the block layer to check for plugging and
+ * merging opportunities
+ */
+ static int as_queue_empty(request_queue_t *q)
+ {
+ struct as_data *ad = q->elevator->elevator_data;
+
+ return list_empty(&ad->fifo_list[REQ_ASYNC])
+ && list_empty(&ad->fifo_list[REQ_SYNC]);
+ }
+
-static struct request *
-as_latter_request(request_queue_t *q, struct request *rq)
++static struct request *as_former_request(request_queue_t *q,
++ struct request *rq)
+ {
+ struct as_rq *arq = RQ_DATA(rq);
+ struct rb_node *rbprev = rb_prev(&arq->rb_node);
+ struct request *ret = NULL;
+
+ if (rbprev)
+ ret = rb_entry_arq(rbprev)->request;
+
+ return ret;
+ }
+
- if ((alias = as_add_arq_rb(ad, arq)) ) {
++static struct request *as_latter_request(request_queue_t *q,
++ struct request *rq)
+ {
+ struct as_rq *arq = RQ_DATA(rq);
+ struct rb_node *rbnext = rb_next(&arq->rb_node);
+ struct request *ret = NULL;
+
+ if (rbnext)
+ ret = rb_entry_arq(rbnext)->request;
+
+ return ret;
+ }
+
+ static int
+ as_merge(request_queue_t *q, struct request **req, struct bio *bio)
+ {
+ struct as_data *ad = q->elevator->elevator_data;
+ sector_t rb_key = bio->bi_sector + bio_sectors(bio);
+ struct request *__rq;
+ int ret;
+
+ /*
+ * see if the merge hash can satisfy a back merge
+ */
+ __rq = as_find_arq_hash(ad, bio->bi_sector);
+ if (__rq) {
+ BUG_ON(__rq->sector + __rq->nr_sectors != bio->bi_sector);
+
+ if (elv_rq_merge_ok(__rq, bio)) {
+ ret = ELEVATOR_BACK_MERGE;
+ goto out;
+ }
+ }
+
+ /*
+ * check for front merge
+ */
+ __rq = as_find_arq_rb(ad, rb_key, bio_data_dir(bio));
+ if (__rq) {
+ BUG_ON(rb_key != rq_rb_key(__rq));
+
+ if (elv_rq_merge_ok(__rq, bio)) {
+ ret = ELEVATOR_FRONT_MERGE;
+ goto out;
+ }
+ }
+
+ return ELEVATOR_NO_MERGE;
+ out:
+ if (ret) {
+ if (rq_mergeable(__rq))
+ as_hot_arq_hash(ad, RQ_DATA(__rq));
+ }
+ *req = __rq;
+ return ret;
+ }
+
+ static void as_merged_request(request_queue_t *q, struct request *req)
+ {
+ struct as_data *ad = q->elevator->elevator_data;
+ struct as_rq *arq = RQ_DATA(req);
+
+ /*
+ * hash always needs to be repositioned, key is end sector
+ */
+ as_del_arq_hash(arq);
+ as_add_arq_hash(ad, arq);
+
+ /*
+ * if the merge was a front merge, we need to reposition request
+ */
+ if (rq_rb_key(req) != arq->rb_key) {
+ struct as_rq *alias, *next_arq = NULL;
+
+ if (ad->next_arq[arq->is_sync] == arq)
+ next_arq = as_find_next_arq(ad, arq);
+
+ /*
+ * Note! We should really be moving any old aliased requests
+ * off this request and try to insert them into the rbtree. We
+ * currently don't bother. Ditto the next function.
+ */
+ as_del_arq_rb(ad, arq);
-static void
-as_merged_requests(request_queue_t *q, struct request *req,
- struct request *next)
++ if ((alias = as_add_arq_rb(ad, arq))) {
+ list_del_init(&arq->fifo);
+ as_add_aliased_request(ad, arq, alias);
+ if (next_arq)
+ ad->next_arq[arq->is_sync] = next_arq;
+ }
+ /*
+ * Note! At this stage of this and the next function, our next
+ * request may not be optimal - eg the request may have "grown"
+ * behind the disk head. We currently don't bother adjusting.
+ */
+ }
+ }
+
- if ((alias = as_add_arq_rb(ad, arq)) ) {
++static void as_merged_requests(request_queue_t *q, struct request *req,
++ struct request *next)
+ {
+ struct as_data *ad = q->elevator->elevator_data;
+ struct as_rq *arq = RQ_DATA(req);
+ struct as_rq *anext = RQ_DATA(next);
+
+ BUG_ON(!arq);
+ BUG_ON(!anext);
+
+ /*
+ * reposition arq (this is the merged request) in hash, and in rbtree
+ * in case of a front merge
+ */
+ as_del_arq_hash(arq);
+ as_add_arq_hash(ad, arq);
+
+ if (rq_rb_key(req) != arq->rb_key) {
+ struct as_rq *alias, *next_arq = NULL;
+
+ if (ad->next_arq[arq->is_sync] == arq)
+ next_arq = as_find_next_arq(ad, arq);
+
+ as_del_arq_rb(ad, arq);
- pos += sprintf(page+pos, "%lu %% exit probability\n", 100*ad->exit_prob/256);
++ if ((alias = as_add_arq_rb(ad, arq))) {
+ list_del_init(&arq->fifo);
+ as_add_aliased_request(ad, arq, alias);
+ if (next_arq)
+ ad->next_arq[arq->is_sync] = next_arq;
+ }
+ }
+
+ /*
+ * if anext expires before arq, assign its expire time to arq
+ * and move into anext position (anext will be deleted) in fifo
+ */
+ if (!list_empty(&arq->fifo) && !list_empty(&anext->fifo)) {
+ if (time_before(anext->expires, arq->expires)) {
+ list_move(&arq->fifo, &anext->fifo);
+ arq->expires = anext->expires;
+ /*
+ * Don't copy here but swap, because when anext is
+ * removed below, it must contain the unused context
+ */
+ swap_io_context(&arq->io_context, &anext->io_context);
+ }
+ }
+
+ /*
+ * Transfer list of aliases
+ */
+ while (!list_empty(&next->queuelist)) {
+ struct request *__rq = list_entry_rq(next->queuelist.next);
+ struct as_rq *__arq = RQ_DATA(__rq);
+
+ list_move_tail(&__rq->queuelist, &req->queuelist);
+
+ WARN_ON(__arq->state != AS_RQ_QUEUED);
+ }
+
+ /*
+ * kill knowledge of next, this one is a goner
+ */
+ as_remove_queued_request(q, next);
+ as_put_io_context(anext);
+
+ anext->state = AS_RQ_MERGED;
+ }
+
+ /*
+ * This is executed in a "deferred" process context, by kblockd. It calls the
+ * driver's request_fn so the driver can submit that request.
+ *
+ * IMPORTANT! This guy will reenter the elevator, so set up all queue global
+ * state before calling, and don't rely on any state over calls.
+ *
+ * FIXME! dispatch queue is not a queue at all!
+ */
+ static void as_work_handler(void *data)
+ {
+ struct request_queue *q = data;
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ if (!as_queue_empty(q))
+ q->request_fn(q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ }
+
+ static void as_put_request(request_queue_t *q, struct request *rq)
+ {
+ struct as_data *ad = q->elevator->elevator_data;
+ struct as_rq *arq = RQ_DATA(rq);
+
+ if (!arq) {
+ WARN_ON(1);
+ return;
+ }
+
+ if (unlikely(arq->state != AS_RQ_POSTSCHED &&
+ arq->state != AS_RQ_PRESCHED &&
+ arq->state != AS_RQ_MERGED)) {
+ printk("arq->state %d\n", arq->state);
+ WARN_ON(1);
+ }
+
+ mempool_free(arq, ad->arq_pool);
+ rq->elevator_private = NULL;
+ }
+
+ static int as_set_request(request_queue_t *q, struct request *rq,
+ struct bio *bio, gfp_t gfp_mask)
+ {
+ struct as_data *ad = q->elevator->elevator_data;
+ struct as_rq *arq = mempool_alloc(ad->arq_pool, gfp_mask);
+
+ if (arq) {
+ memset(arq, 0, sizeof(*arq));
+ RB_CLEAR(&arq->rb_node);
+ arq->request = rq;
+ arq->state = AS_RQ_PRESCHED;
+ arq->io_context = NULL;
+ INIT_LIST_HEAD(&arq->hash);
+ arq->on_hash = 0;
+ INIT_LIST_HEAD(&arq->fifo);
+ rq->elevator_private = arq;
+ return 0;
+ }
+
+ return 1;
+ }
+
+ static int as_may_queue(request_queue_t *q, int rw, struct bio *bio)
+ {
+ int ret = ELV_MQUEUE_MAY;
+ struct as_data *ad = q->elevator->elevator_data;
+ struct io_context *ioc;
+ if (ad->antic_status == ANTIC_WAIT_REQ ||
+ ad->antic_status == ANTIC_WAIT_NEXT) {
+ ioc = as_get_io_context();
+ if (ad->io_context == ioc)
+ ret = ELV_MQUEUE_MUST;
+ put_io_context(ioc);
+ }
+
+ return ret;
+ }
+
+ static void as_exit_queue(elevator_t *e)
+ {
+ struct as_data *ad = e->elevator_data;
+
+ del_timer_sync(&ad->antic_timer);
+ kblockd_flush();
+
+ BUG_ON(!list_empty(&ad->fifo_list[REQ_SYNC]));
+ BUG_ON(!list_empty(&ad->fifo_list[REQ_ASYNC]));
+
+ mempool_destroy(ad->arq_pool);
+ put_io_context(ad->io_context);
+ kfree(ad->hash);
+ kfree(ad);
+ }
+
+ /*
+ * initialize elevator private data (as_data), and alloc a arq for
+ * each request on the free lists
+ */
+ static int as_init_queue(request_queue_t *q, elevator_t *e)
+ {
+ struct as_data *ad;
+ int i;
+
+ if (!arq_pool)
+ return -ENOMEM;
+
+ ad = kmalloc_node(sizeof(*ad), GFP_KERNEL, q->node);
+ if (!ad)
+ return -ENOMEM;
+ memset(ad, 0, sizeof(*ad));
+
+ ad->q = q; /* Identify what queue the data belongs to */
+
+ ad->hash = kmalloc_node(sizeof(struct list_head)*AS_HASH_ENTRIES,
+ GFP_KERNEL, q->node);
+ if (!ad->hash) {
+ kfree(ad);
+ return -ENOMEM;
+ }
+
+ ad->arq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
+ mempool_free_slab, arq_pool, q->node);
+ if (!ad->arq_pool) {
+ kfree(ad->hash);
+ kfree(ad);
+ return -ENOMEM;
+ }
+
+ /* anticipatory scheduling helpers */
+ ad->antic_timer.function = as_antic_timeout;
+ ad->antic_timer.data = (unsigned long)q;
+ init_timer(&ad->antic_timer);
+ INIT_WORK(&ad->antic_work, as_work_handler, q);
+
+ for (i = 0; i < AS_HASH_ENTRIES; i++)
+ INIT_LIST_HEAD(&ad->hash[i]);
+
+ INIT_LIST_HEAD(&ad->fifo_list[REQ_SYNC]);
+ INIT_LIST_HEAD(&ad->fifo_list[REQ_ASYNC]);
+ ad->sort_list[REQ_SYNC] = RB_ROOT;
+ ad->sort_list[REQ_ASYNC] = RB_ROOT;
+ ad->fifo_expire[REQ_SYNC] = default_read_expire;
+ ad->fifo_expire[REQ_ASYNC] = default_write_expire;
+ ad->antic_expire = default_antic_expire;
+ ad->batch_expire[REQ_SYNC] = default_read_batch_expire;
+ ad->batch_expire[REQ_ASYNC] = default_write_batch_expire;
+ e->elevator_data = ad;
+
+ ad->current_batch_expires = jiffies + ad->batch_expire[REQ_SYNC];
+ ad->write_batch_count = ad->batch_expire[REQ_ASYNC] / 10;
+ if (ad->write_batch_count < 2)
+ ad->write_batch_count = 2;
+
+ return 0;
+ }
+
+ /*
+ * sysfs parts below
+ */
+ struct as_fs_entry {
+ struct attribute attr;
+ ssize_t (*show)(struct as_data *, char *);
+ ssize_t (*store)(struct as_data *, const char *, size_t);
+ };
+
+ static ssize_t
+ as_var_show(unsigned int var, char *page)
+ {
+ return sprintf(page, "%d\n", var);
+ }
+
+ static ssize_t
+ as_var_store(unsigned long *var, const char *page, size_t count)
+ {
+ char *p = (char *) page;
+
+ *var = simple_strtoul(p, &p, 10);
+ return count;
+ }
+
+ static ssize_t as_est_show(struct as_data *ad, char *page)
+ {
+ int pos = 0;
+
- pos += sprintf(page+pos, "%llu sectors new seek distance\n", (unsigned long long)ad->new_seek_mean);
++ pos += sprintf(page+pos, "%lu %% exit probability\n",
++ 100*ad->exit_prob/256);
++ pos += sprintf(page+pos, "%lu %% probability of exiting without a "
++ "cooperating process submitting IO\n",
++ 100*ad->exit_no_coop/256);
+ pos += sprintf(page+pos, "%lu ms new thinktime\n", ad->new_ttime_mean);
++ pos += sprintf(page+pos, "%llu sectors new seek distance\n",
++ (unsigned long long)ad->new_seek_mean);
+
+ return pos;
+ }
+
+ #define SHOW_FUNCTION(__FUNC, __VAR) \
+ static ssize_t __FUNC(struct as_data *ad, char *page) \
+ { \
+ return as_var_show(jiffies_to_msecs((__VAR)), (page)); \
+ }
+ SHOW_FUNCTION(as_readexpire_show, ad->fifo_expire[REQ_SYNC]);
+ SHOW_FUNCTION(as_writeexpire_show, ad->fifo_expire[REQ_ASYNC]);
+ SHOW_FUNCTION(as_anticexpire_show, ad->antic_expire);
+ SHOW_FUNCTION(as_read_batchexpire_show, ad->batch_expire[REQ_SYNC]);
+ SHOW_FUNCTION(as_write_batchexpire_show, ad->batch_expire[REQ_ASYNC]);
+ #undef SHOW_FUNCTION
+
+ #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \
+ static ssize_t __FUNC(struct as_data *ad, const char *page, size_t count) \
+ { \
+ int ret = as_var_store(__PTR, (page), count); \
+ if (*(__PTR) < (MIN)) \
+ *(__PTR) = (MIN); \
+ else if (*(__PTR) > (MAX)) \
+ *(__PTR) = (MAX); \
+ *(__PTR) = msecs_to_jiffies(*(__PTR)); \
+ return ret; \
+ }
+ STORE_FUNCTION(as_readexpire_store, &ad->fifo_expire[REQ_SYNC], 0, INT_MAX);
+ STORE_FUNCTION(as_writeexpire_store, &ad->fifo_expire[REQ_ASYNC], 0, INT_MAX);
+ STORE_FUNCTION(as_anticexpire_store, &ad->antic_expire, 0, INT_MAX);
+ STORE_FUNCTION(as_read_batchexpire_store,
+ &ad->batch_expire[REQ_SYNC], 0, INT_MAX);
+ STORE_FUNCTION(as_write_batchexpire_store,
+ &ad->batch_expire[REQ_ASYNC], 0, INT_MAX);
+ #undef STORE_FUNCTION
+
+ static struct as_fs_entry as_est_entry = {
+ .attr = {.name = "est_time", .mode = S_IRUGO },
+ .show = as_est_show,
+ };
+ static struct as_fs_entry as_readexpire_entry = {
+ .attr = {.name = "read_expire", .mode = S_IRUGO | S_IWUSR },
+ .show = as_readexpire_show,
+ .store = as_readexpire_store,
+ };
+ static struct as_fs_entry as_writeexpire_entry = {
+ .attr = {.name = "write_expire", .mode = S_IRUGO | S_IWUSR },
+ .show = as_writeexpire_show,
+ .store = as_writeexpire_store,
+ };
+ static struct as_fs_entry as_anticexpire_entry = {
+ .attr = {.name = "antic_expire", .mode = S_IRUGO | S_IWUSR },
+ .show = as_anticexpire_show,
+ .store = as_anticexpire_store,
+ };
+ static struct as_fs_entry as_read_batchexpire_entry = {
+ .attr = {.name = "read_batch_expire", .mode = S_IRUGO | S_IWUSR },
+ .show = as_read_batchexpire_show,
+ .store = as_read_batchexpire_store,
+ };
+ static struct as_fs_entry as_write_batchexpire_entry = {
+ .attr = {.name = "write_batch_expire", .mode = S_IRUGO | S_IWUSR },
+ .show = as_write_batchexpire_show,
+ .store = as_write_batchexpire_store,
+ };
+
+ static struct attribute *default_attrs[] = {
+ &as_est_entry.attr,
+ &as_readexpire_entry.attr,
+ &as_writeexpire_entry.attr,
+ &as_anticexpire_entry.attr,
+ &as_read_batchexpire_entry.attr,
+ &as_write_batchexpire_entry.attr,
+ NULL,
+ };
+
+ #define to_as(atr) container_of((atr), struct as_fs_entry, attr)
+
+ static ssize_t
+ as_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+ {
+ elevator_t *e = container_of(kobj, elevator_t, kobj);
+ struct as_fs_entry *entry = to_as(attr);
+
+ if (!entry->show)
+ return -EIO;
+
+ return entry->show(e->elevator_data, page);
+ }
+
+ static ssize_t
+ as_attr_store(struct kobject *kobj, struct attribute *attr,
+ const char *page, size_t length)
+ {
+ elevator_t *e = container_of(kobj, elevator_t, kobj);
+ struct as_fs_entry *entry = to_as(attr);
+
+ if (!entry->store)
+ return -EIO;
+
+ return entry->store(e->elevator_data, page, length);
+ }
+
+ static struct sysfs_ops as_sysfs_ops = {
+ .show = as_attr_show,
+ .store = as_attr_store,
+ };
+
+ static struct kobj_type as_ktype = {
+ .sysfs_ops = &as_sysfs_ops,
+ .default_attrs = default_attrs,
+ };
+
+ static struct elevator_type iosched_as = {
+ .ops = {
+ .elevator_merge_fn = as_merge,
+ .elevator_merged_fn = as_merged_request,
+ .elevator_merge_req_fn = as_merged_requests,
+ .elevator_dispatch_fn = as_dispatch_request,
+ .elevator_add_req_fn = as_add_request,
+ .elevator_activate_req_fn = as_activate_request,
+ .elevator_deactivate_req_fn = as_deactivate_request,
+ .elevator_queue_empty_fn = as_queue_empty,
+ .elevator_completed_req_fn = as_completed_request,
+ .elevator_former_req_fn = as_former_request,
+ .elevator_latter_req_fn = as_latter_request,
+ .elevator_set_req_fn = as_set_request,
+ .elevator_put_req_fn = as_put_request,
+ .elevator_may_queue_fn = as_may_queue,
+ .elevator_init_fn = as_init_queue,
+ .elevator_exit_fn = as_exit_queue,
+ },
+
+ .elevator_ktype = &as_ktype,
+ .elevator_name = "anticipatory",
+ .elevator_owner = THIS_MODULE,
+ };
+
+ static int __init as_init(void)
+ {
+ int ret;
+
+ arq_pool = kmem_cache_create("as_arq", sizeof(struct as_rq),
+ 0, 0, NULL, NULL);
+ if (!arq_pool)
+ return -ENOMEM;
+
+ ret = elv_register(&iosched_as);
+ if (!ret) {
+ /*
+ * don't allow AS to get unregistered, since we would have
+ * to browse all tasks in the system and release their
+ * as_io_context first
+ */
+ __module_get(THIS_MODULE);
+ return 0;
+ }
+
+ kmem_cache_destroy(arq_pool);
+ return ret;
+ }
+
+ static void __exit as_exit(void)
+ {
+ elv_unregister(&iosched_as);
+ kmem_cache_destroy(arq_pool);
+ }
+
+ module_init(as_init);
+ module_exit(as_exit);
+
+ MODULE_AUTHOR("Nick Piggin");
+ MODULE_LICENSE("GPL");
+ MODULE_DESCRIPTION("anticipatory IO scheduler");
--- /dev/null
- *
+ /*
+ * linux/drivers/block/ll_rw_blk.c
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 1994, Karl Keyte: Added support for disk statistics
+ * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
+ * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de>
+ * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> - July2000
+ * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001
+ */
+
+ /*
+ * This handles all read/write requests to block devices
+ */
+ #include <linux/config.h>
+ #include <linux/kernel.h>
+ #include <linux/module.h>
+ #include <linux/backing-dev.h>
+ #include <linux/bio.h>
+ #include <linux/blkdev.h>
+ #include <linux/highmem.h>
+ #include <linux/mm.h>
+ #include <linux/kernel_stat.h>
+ #include <linux/string.h>
+ #include <linux/init.h>
+ #include <linux/bootmem.h> /* for max_pfn/max_low_pfn */
+ #include <linux/completion.h>
+ #include <linux/slab.h>
+ #include <linux/swap.h>
+ #include <linux/writeback.h>
+ #include <linux/blkdev.h>
+
+ /*
+ * for max sense size
+ */
+ #include <scsi/scsi_cmnd.h>
+
+ static void blk_unplug_work(void *data);
+ static void blk_unplug_timeout(unsigned long data);
+ static void drive_stat_acct(struct request *rq, int nr_sectors, int new_io);
+
+ /*
+ * For the allocated request tables
+ */
+ static kmem_cache_t *request_cachep;
+
+ /*
+ * For queue allocation
+ */
+ static kmem_cache_t *requestq_cachep;
+
+ /*
+ * For io context allocations
+ */
+ static kmem_cache_t *iocontext_cachep;
+
+ static wait_queue_head_t congestion_wqh[2] = {
+ __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
+ __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
+ };
+
+ /*
+ * Controlling structure to kblockd
+ */
+ static struct workqueue_struct *kblockd_workqueue;
+
+ unsigned long blk_max_low_pfn, blk_max_pfn;
+
+ EXPORT_SYMBOL(blk_max_low_pfn);
+ EXPORT_SYMBOL(blk_max_pfn);
+
+ /* Amount of time in which a process may batch requests */
+ #define BLK_BATCH_TIME (HZ/50UL)
+
+ /* Number of requests a "batching" process may submit */
+ #define BLK_BATCH_REQ 32
+
+ /*
+ * Return the threshold (number of used requests) at which the queue is
+ * considered to be congested. It include a little hysteresis to keep the
+ * context switch rate down.
+ */
+ static inline int queue_congestion_on_threshold(struct request_queue *q)
+ {
+ return q->nr_congestion_on;
+ }
+
+ /*
+ * The threshold at which a queue is considered to be uncongested
+ */
+ static inline int queue_congestion_off_threshold(struct request_queue *q)
+ {
+ return q->nr_congestion_off;
+ }
+
+ static void blk_queue_congestion_threshold(struct request_queue *q)
+ {
+ int nr;
+
+ nr = q->nr_requests - (q->nr_requests / 8) + 1;
+ if (nr > q->nr_requests)
+ nr = q->nr_requests;
+ q->nr_congestion_on = nr;
+
+ nr = q->nr_requests - (q->nr_requests / 8) - (q->nr_requests / 16) - 1;
+ if (nr < 1)
+ nr = 1;
+ q->nr_congestion_off = nr;
+ }
+
+ /*
+ * A queue has just exitted congestion. Note this in the global counter of
+ * congested queues, and wake up anyone who was waiting for requests to be
+ * put back.
+ */
+ static void clear_queue_congested(request_queue_t *q, int rw)
+ {
+ enum bdi_state bit;
+ wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+ bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
+ clear_bit(bit, &q->backing_dev_info.state);
+ smp_mb__after_clear_bit();
+ if (waitqueue_active(wqh))
+ wake_up(wqh);
+ }
+
+ /*
+ * A queue has just entered congestion. Flag that in the queue's VM-visible
+ * state flags and increment the global gounter of congested queues.
+ */
+ static void set_queue_congested(request_queue_t *q, int rw)
+ {
+ enum bdi_state bit;
+
+ bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
+ set_bit(bit, &q->backing_dev_info.state);
+ }
+
+ /**
+ * blk_get_backing_dev_info - get the address of a queue's backing_dev_info
+ * @bdev: device
+ *
+ * Locates the passed device's request queue and returns the address of its
+ * backing_dev_info
+ *
+ * Will return NULL if the request queue cannot be located.
+ */
+ struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
+ {
+ struct backing_dev_info *ret = NULL;
+ request_queue_t *q = bdev_get_queue(bdev);
+
+ if (q)
+ ret = &q->backing_dev_info;
+ return ret;
+ }
+
+ EXPORT_SYMBOL(blk_get_backing_dev_info);
+
+ void blk_queue_activity_fn(request_queue_t *q, activity_fn *fn, void *data)
+ {
+ q->activity_fn = fn;
+ q->activity_data = data;
+ }
+
+ EXPORT_SYMBOL(blk_queue_activity_fn);
+
+ /**
+ * blk_queue_prep_rq - set a prepare_request function for queue
+ * @q: queue
+ * @pfn: prepare_request function
+ *
+ * It's possible for a queue to register a prepare_request callback which
+ * is invoked before the request is handed to the request_fn. The goal of
+ * the function is to prepare a request for I/O, it can be used to build a
+ * cdb from the request data for instance.
+ *
+ */
+ void blk_queue_prep_rq(request_queue_t *q, prep_rq_fn *pfn)
+ {
+ q->prep_rq_fn = pfn;
+ }
+
+ EXPORT_SYMBOL(blk_queue_prep_rq);
+
+ /**
+ * blk_queue_merge_bvec - set a merge_bvec function for queue
+ * @q: queue
+ * @mbfn: merge_bvec_fn
+ *
+ * Usually queues have static limitations on the max sectors or segments that
+ * we can put in a request. Stacking drivers may have some settings that
+ * are dynamic, and thus we have to query the queue whether it is ok to
+ * add a new bio_vec to a bio at a given offset or not. If the block device
+ * has such limitations, it needs to register a merge_bvec_fn to control
+ * the size of bio's sent to it. Note that a block device *must* allow a
+ * single page to be added to an empty bio. The block device driver may want
+ * to use the bio_split() function to deal with these bio's. By default
+ * no merge_bvec_fn is defined for a queue, and only the fixed limits are
+ * honored.
+ */
+ void blk_queue_merge_bvec(request_queue_t *q, merge_bvec_fn *mbfn)
+ {
+ q->merge_bvec_fn = mbfn;
+ }
+
+ EXPORT_SYMBOL(blk_queue_merge_bvec);
+
+ /**
+ * blk_queue_make_request - define an alternate make_request function for a device
+ * @q: the request queue for the device to be affected
+ * @mfn: the alternate make_request function
+ *
+ * Description:
+ * The normal way for &struct bios to be passed to a device
+ * driver is for them to be collected into requests on a request
+ * queue, and then to allow the device driver to select requests
+ * off that queue when it is ready. This works well for many block
+ * devices. However some block devices (typically virtual devices
+ * such as md or lvm) do not benefit from the processing on the
+ * request queue, and are served best by having the requests passed
+ * directly to them. This can be achieved by providing a function
+ * to blk_queue_make_request().
+ *
+ * Caveat:
+ * The driver that does this *must* be able to deal appropriately
+ * with buffers in "highmemory". This can be accomplished by either calling
+ * __bio_kmap_atomic() to get a temporary kernel mapping, or by calling
+ * blk_queue_bounce() to create a buffer in normal memory.
+ **/
+ void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn)
+ {
+ /*
+ * set defaults
+ */
+ q->nr_requests = BLKDEV_MAX_RQ;
+ blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
+ blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
+ q->make_request_fn = mfn;
+ q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
+ q->backing_dev_info.state = 0;
+ q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+ blk_queue_max_sectors(q, MAX_SECTORS);
+ blk_queue_hardsect_size(q, 512);
+ blk_queue_dma_alignment(q, 511);
+ blk_queue_congestion_threshold(q);
+ q->nr_batching = BLK_BATCH_REQ;
+
+ q->unplug_thresh = 4; /* hmm */
+ q->unplug_delay = (3 * HZ) / 1000; /* 3 milliseconds */
+ if (q->unplug_delay == 0)
+ q->unplug_delay = 1;
+
+ INIT_WORK(&q->unplug_work, blk_unplug_work, q);
+
+ q->unplug_timer.function = blk_unplug_timeout;
+ q->unplug_timer.data = (unsigned long)q;
+
+ /*
+ * by default assume old behaviour and bounce for any highmem page
+ */
+ blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
+
+ blk_queue_activity_fn(q, NULL, NULL);
+ }
+
+ EXPORT_SYMBOL(blk_queue_make_request);
+
+ static inline void rq_init(request_queue_t *q, struct request *rq)
+ {
+ INIT_LIST_HEAD(&rq->queuelist);
+
+ rq->errors = 0;
+ rq->rq_status = RQ_ACTIVE;
+ rq->bio = rq->biotail = NULL;
+ rq->ioprio = 0;
+ rq->buffer = NULL;
+ rq->ref_count = 1;
+ rq->q = q;
+ rq->waiting = NULL;
+ rq->special = NULL;
+ rq->data_len = 0;
+ rq->data = NULL;
+ rq->nr_phys_segments = 0;
+ rq->sense = NULL;
+ rq->end_io = NULL;
+ rq->end_io_data = NULL;
+ }
+
+ /**
+ * blk_queue_ordered - does this queue support ordered writes
+ * @q: the request queue
+ * @flag: see below
+ *
+ * Description:
+ * For journalled file systems, doing ordered writes on a commit
+ * block instead of explicitly doing wait_on_buffer (which is bad
+ * for performance) can be a big win. Block drivers supporting this
+ * feature should call this function and indicate so.
+ *
+ **/
+ void blk_queue_ordered(request_queue_t *q, int flag)
+ {
+ switch (flag) {
+ case QUEUE_ORDERED_NONE:
+ if (q->flush_rq)
+ kmem_cache_free(request_cachep, q->flush_rq);
+ q->flush_rq = NULL;
+ q->ordered = flag;
+ break;
+ case QUEUE_ORDERED_TAG:
+ q->ordered = flag;
+ break;
+ case QUEUE_ORDERED_FLUSH:
+ q->ordered = flag;
+ if (!q->flush_rq)
+ q->flush_rq = kmem_cache_alloc(request_cachep,
+ GFP_KERNEL);
+ break;
+ default:
+ printk("blk_queue_ordered: bad value %d\n", flag);
+ break;
+ }
+ }
+
+ EXPORT_SYMBOL(blk_queue_ordered);
+
+ /**
+ * blk_queue_issue_flush_fn - set function for issuing a flush
+ * @q: the request queue
+ * @iff: the function to be called issuing the flush
+ *
+ * Description:
+ * If a driver supports issuing a flush command, the support is notified
+ * to the block layer by defining it through this call.
+ *
+ **/
+ void blk_queue_issue_flush_fn(request_queue_t *q, issue_flush_fn *iff)
+ {
+ q->issue_flush_fn = iff;
+ }
+
+ EXPORT_SYMBOL(blk_queue_issue_flush_fn);
+
+ /*
+ * Cache flushing for ordered writes handling
+ */
+ static void blk_pre_flush_end_io(struct request *flush_rq)
+ {
+ struct request *rq = flush_rq->end_io_data;
+ request_queue_t *q = rq->q;
+
+ elv_completed_request(q, flush_rq);
+
+ rq->flags |= REQ_BAR_PREFLUSH;
+
+ if (!flush_rq->errors)
+ elv_requeue_request(q, rq);
+ else {
+ q->end_flush_fn(q, flush_rq);
+ clear_bit(QUEUE_FLAG_FLUSH, &q->queue_flags);
+ q->request_fn(q);
+ }
+ }
+
+ static void blk_post_flush_end_io(struct request *flush_rq)
+ {
+ struct request *rq = flush_rq->end_io_data;
+ request_queue_t *q = rq->q;
+
+ elv_completed_request(q, flush_rq);
+
+ rq->flags |= REQ_BAR_POSTFLUSH;
+
+ q->end_flush_fn(q, flush_rq);
+ clear_bit(QUEUE_FLAG_FLUSH, &q->queue_flags);
+ q->request_fn(q);
+ }
+
+ struct request *blk_start_pre_flush(request_queue_t *q, struct request *rq)
+ {
+ struct request *flush_rq = q->flush_rq;
+
+ BUG_ON(!blk_barrier_rq(rq));
+
+ if (test_and_set_bit(QUEUE_FLAG_FLUSH, &q->queue_flags))
+ return NULL;
+
+ rq_init(q, flush_rq);
+ flush_rq->elevator_private = NULL;
+ flush_rq->flags = REQ_BAR_FLUSH;
+ flush_rq->rq_disk = rq->rq_disk;
+ flush_rq->rl = NULL;
+
+ /*
+ * prepare_flush returns 0 if no flush is needed, just mark both
+ * pre and post flush as done in that case
+ */
+ if (!q->prepare_flush_fn(q, flush_rq)) {
+ rq->flags |= REQ_BAR_PREFLUSH | REQ_BAR_POSTFLUSH;
+ clear_bit(QUEUE_FLAG_FLUSH, &q->queue_flags);
+ return rq;
+ }
+
+ /*
+ * some drivers dequeue requests right away, some only after io
+ * completion. make sure the request is dequeued.
+ */
+ if (!list_empty(&rq->queuelist))
+ blkdev_dequeue_request(rq);
+
+ flush_rq->end_io_data = rq;
+ flush_rq->end_io = blk_pre_flush_end_io;
+
+ __elv_add_request(q, flush_rq, ELEVATOR_INSERT_FRONT, 0);
+ return flush_rq;
+ }
+
+ static void blk_start_post_flush(request_queue_t *q, struct request *rq)
+ {
+ struct request *flush_rq = q->flush_rq;
+
+ BUG_ON(!blk_barrier_rq(rq));
+
+ rq_init(q, flush_rq);
+ flush_rq->elevator_private = NULL;
+ flush_rq->flags = REQ_BAR_FLUSH;
+ flush_rq->rq_disk = rq->rq_disk;
+ flush_rq->rl = NULL;
+
+ if (q->prepare_flush_fn(q, flush_rq)) {
+ flush_rq->end_io_data = rq;
+ flush_rq->end_io = blk_post_flush_end_io;
+
+ __elv_add_request(q, flush_rq, ELEVATOR_INSERT_FRONT, 0);
+ q->request_fn(q);
+ }
+ }
+
+ static inline int blk_check_end_barrier(request_queue_t *q, struct request *rq,
+ int sectors)
+ {
+ if (sectors > rq->nr_sectors)
+ sectors = rq->nr_sectors;
+
+ rq->nr_sectors -= sectors;
+ return rq->nr_sectors;
+ }
+
+ static int __blk_complete_barrier_rq(request_queue_t *q, struct request *rq,
+ int sectors, int queue_locked)
+ {
+ if (q->ordered != QUEUE_ORDERED_FLUSH)
+ return 0;
+ if (!blk_fs_request(rq) || !blk_barrier_rq(rq))
+ return 0;
+ if (blk_barrier_postflush(rq))
+ return 0;
+
+ if (!blk_check_end_barrier(q, rq, sectors)) {
+ unsigned long flags = 0;
+
+ if (!queue_locked)
+ spin_lock_irqsave(q->queue_lock, flags);
+
+ blk_start_post_flush(q, rq);
+
+ if (!queue_locked)
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ }
+
+ return 1;
+ }
+
+ /**
+ * blk_complete_barrier_rq - complete possible barrier request
+ * @q: the request queue for the device
+ * @rq: the request
+ * @sectors: number of sectors to complete
+ *
+ * Description:
+ * Used in driver end_io handling to determine whether to postpone
+ * completion of a barrier request until a post flush has been done. This
+ * is the unlocked variant, used if the caller doesn't already hold the
+ * queue lock.
+ **/
+ int blk_complete_barrier_rq(request_queue_t *q, struct request *rq, int sectors)
+ {
+ return __blk_complete_barrier_rq(q, rq, sectors, 0);
+ }
+ EXPORT_SYMBOL(blk_complete_barrier_rq);
+
+ /**
+ * blk_complete_barrier_rq_locked - complete possible barrier request
+ * @q: the request queue for the device
+ * @rq: the request
+ * @sectors: number of sectors to complete
+ *
+ * Description:
+ * See blk_complete_barrier_rq(). This variant must be used if the caller
+ * holds the queue lock.
+ **/
+ int blk_complete_barrier_rq_locked(request_queue_t *q, struct request *rq,
+ int sectors)
+ {
+ return __blk_complete_barrier_rq(q, rq, sectors, 1);
+ }
+ EXPORT_SYMBOL(blk_complete_barrier_rq_locked);
+
+ /**
+ * blk_queue_bounce_limit - set bounce buffer limit for queue
+ * @q: the request queue for the device
+ * @dma_addr: bus address limit
+ *
+ * Description:
+ * Different hardware can have different requirements as to what pages
+ * it can do I/O directly to. A low level driver can call
+ * blk_queue_bounce_limit to have lower memory pages allocated as bounce
+ * buffers for doing I/O to pages residing above @page. By default
+ * the block layer sets this to the highest numbered "low" memory page.
+ **/
+ void blk_queue_bounce_limit(request_queue_t *q, u64 dma_addr)
+ {
+ unsigned long bounce_pfn = dma_addr >> PAGE_SHIFT;
+
+ /*
+ * set appropriate bounce gfp mask -- unfortunately we don't have a
+ * full 4GB zone, so we have to resort to low memory for any bounces.
+ * ISA has its own < 16MB zone.
+ */
+ if (bounce_pfn < blk_max_low_pfn) {
+ BUG_ON(dma_addr < BLK_BOUNCE_ISA);
+ init_emergency_isa_pool();
+ q->bounce_gfp = GFP_NOIO | GFP_DMA;
+ } else
+ q->bounce_gfp = GFP_NOIO;
+
+ q->bounce_pfn = bounce_pfn;
+ }
+
+ EXPORT_SYMBOL(blk_queue_bounce_limit);
+
+ /**
+ * blk_queue_max_sectors - set max sectors for a request for this queue
+ * @q: the request queue for the device
+ * @max_sectors: max sectors in the usual 512b unit
+ *
+ * Description:
+ * Enables a low level driver to set an upper limit on the size of
+ * received requests.
+ **/
+ void blk_queue_max_sectors(request_queue_t *q, unsigned short max_sectors)
+ {
+ if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
+ max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
+ printk("%s: set to minimum %d\n", __FUNCTION__, max_sectors);
+ }
+
+ q->max_sectors = q->max_hw_sectors = max_sectors;
+ }
+
+ EXPORT_SYMBOL(blk_queue_max_sectors);
+
+ /**
+ * blk_queue_max_phys_segments - set max phys segments for a request for this queue
+ * @q: the request queue for the device
+ * @max_segments: max number of segments
+ *
+ * Description:
+ * Enables a low level driver to set an upper limit on the number of
+ * physical data segments in a request. This would be the largest sized
+ * scatter list the driver could handle.
+ **/
+ void blk_queue_max_phys_segments(request_queue_t *q, unsigned short max_segments)
+ {
+ if (!max_segments) {
+ max_segments = 1;
+ printk("%s: set to minimum %d\n", __FUNCTION__, max_segments);
+ }
+
+ q->max_phys_segments = max_segments;
+ }
+
+ EXPORT_SYMBOL(blk_queue_max_phys_segments);
+
+ /**
+ * blk_queue_max_hw_segments - set max hw segments for a request for this queue
+ * @q: the request queue for the device
+ * @max_segments: max number of segments
+ *
+ * Description:
+ * Enables a low level driver to set an upper limit on the number of
+ * hw data segments in a request. This would be the largest number of
+ * address/length pairs the host adapter can actually give as once
+ * to the device.
+ **/
+ void blk_queue_max_hw_segments(request_queue_t *q, unsigned short max_segments)
+ {
+ if (!max_segments) {
+ max_segments = 1;
+ printk("%s: set to minimum %d\n", __FUNCTION__, max_segments);
+ }
+
+ q->max_hw_segments = max_segments;
+ }
+
+ EXPORT_SYMBOL(blk_queue_max_hw_segments);
+
+ /**
+ * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
+ * @q: the request queue for the device
+ * @max_size: max size of segment in bytes
+ *
+ * Description:
+ * Enables a low level driver to set an upper limit on the size of a
+ * coalesced segment
+ **/
+ void blk_queue_max_segment_size(request_queue_t *q, unsigned int max_size)
+ {
+ if (max_size < PAGE_CACHE_SIZE) {
+ max_size = PAGE_CACHE_SIZE;
+ printk("%s: set to minimum %d\n", __FUNCTION__, max_size);
+ }
+
+ q->max_segment_size = max_size;
+ }
+
+ EXPORT_SYMBOL(blk_queue_max_segment_size);
+
+ /**
+ * blk_queue_hardsect_size - set hardware sector size for the queue
+ * @q: the request queue for the device
+ * @size: the hardware sector size, in bytes
+ *
+ * Description:
+ * This should typically be set to the lowest possible sector size
+ * that the hardware can operate on (possible without reverting to
+ * even internal read-modify-write operations). Usually the default
+ * of 512 covers most hardware.
+ **/
+ void blk_queue_hardsect_size(request_queue_t *q, unsigned short size)
+ {
+ q->hardsect_size = size;
+ }
+
+ EXPORT_SYMBOL(blk_queue_hardsect_size);
+
+ /*
+ * Returns the minimum that is _not_ zero, unless both are zero.
+ */
+ #define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))
+
+ /**
+ * blk_queue_stack_limits - inherit underlying queue limits for stacked drivers
+ * @t: the stacking driver (top)
+ * @b: the underlying device (bottom)
+ **/
+ void blk_queue_stack_limits(request_queue_t *t, request_queue_t *b)
+ {
+ /* zero is "infinity" */
+ t->max_sectors = t->max_hw_sectors =
+ min_not_zero(t->max_sectors,b->max_sectors);
+
+ t->max_phys_segments = min(t->max_phys_segments,b->max_phys_segments);
+ t->max_hw_segments = min(t->max_hw_segments,b->max_hw_segments);
+ t->max_segment_size = min(t->max_segment_size,b->max_segment_size);
+ t->hardsect_size = max(t->hardsect_size,b->hardsect_size);
+ }
+
+ EXPORT_SYMBOL(blk_queue_stack_limits);
+
+ /**
+ * blk_queue_segment_boundary - set boundary rules for segment merging
+ * @q: the request queue for the device
+ * @mask: the memory boundary mask
+ **/
+ void blk_queue_segment_boundary(request_queue_t *q, unsigned long mask)
+ {
+ if (mask < PAGE_CACHE_SIZE - 1) {
+ mask = PAGE_CACHE_SIZE - 1;
+ printk("%s: set to minimum %lx\n", __FUNCTION__, mask);
+ }
+
+ q->seg_boundary_mask = mask;
+ }
+
+ EXPORT_SYMBOL(blk_queue_segment_boundary);
+
+ /**
+ * blk_queue_dma_alignment - set dma length and memory alignment
+ * @q: the request queue for the device
+ * @mask: alignment mask
+ *
+ * description:
+ * set required memory and length aligment for direct dma transactions.
+ * this is used when buiding direct io requests for the queue.
+ *
+ **/
+ void blk_queue_dma_alignment(request_queue_t *q, int mask)
+ {
+ q->dma_alignment = mask;
+ }
+
+ EXPORT_SYMBOL(blk_queue_dma_alignment);
+
+ /**
+ * blk_queue_find_tag - find a request by its tag and queue
+ * @q: The request queue for the device
+ * @tag: The tag of the request
+ *
+ * Notes:
+ * Should be used when a device returns a tag and you want to match
+ * it with a request.
+ *
+ * no locks need be held.
+ **/
+ struct request *blk_queue_find_tag(request_queue_t *q, int tag)
+ {
+ struct blk_queue_tag *bqt = q->queue_tags;
+
+ if (unlikely(bqt == NULL || tag >= bqt->real_max_depth))
+ return NULL;
+
+ return bqt->tag_index[tag];
+ }
+
+ EXPORT_SYMBOL(blk_queue_find_tag);
+
+ /**
+ * __blk_queue_free_tags - release tag maintenance info
+ * @q: the request queue for the device
+ *
+ * Notes:
+ * blk_cleanup_queue() will take care of calling this function, if tagging
+ * has been used. So there's no need to call this directly.
+ **/
+ static void __blk_queue_free_tags(request_queue_t *q)
+ {
+ struct blk_queue_tag *bqt = q->queue_tags;
+
+ if (!bqt)
+ return;
+
+ if (atomic_dec_and_test(&bqt->refcnt)) {
+ BUG_ON(bqt->busy);
+ BUG_ON(!list_empty(&bqt->busy_list));
+
+ kfree(bqt->tag_index);
+ bqt->tag_index = NULL;
+
+ kfree(bqt->tag_map);
+ bqt->tag_map = NULL;
+
+ kfree(bqt);
+ }
+
+ q->queue_tags = NULL;
+ q->queue_flags &= ~(1 << QUEUE_FLAG_QUEUED);
+ }
+
+ /**
+ * blk_queue_free_tags - release tag maintenance info
+ * @q: the request queue for the device
+ *
+ * Notes:
+ * This is used to disabled tagged queuing to a device, yet leave
+ * queue in function.
+ **/
+ void blk_queue_free_tags(request_queue_t *q)
+ {
+ clear_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
+ }
+
+ EXPORT_SYMBOL(blk_queue_free_tags);
+
+ static int
+ init_tag_map(request_queue_t *q, struct blk_queue_tag *tags, int depth)
+ {
+ struct request **tag_index;
+ unsigned long *tag_map;
+ int nr_ulongs;
+
+ if (depth > q->nr_requests * 2) {
+ depth = q->nr_requests * 2;
+ printk(KERN_ERR "%s: adjusted depth to %d\n",
+ __FUNCTION__, depth);
+ }
+
+ tag_index = kmalloc(depth * sizeof(struct request *), GFP_ATOMIC);
+ if (!tag_index)
+ goto fail;
+
+ nr_ulongs = ALIGN(depth, BITS_PER_LONG) / BITS_PER_LONG;
+ tag_map = kmalloc(nr_ulongs * sizeof(unsigned long), GFP_ATOMIC);
+ if (!tag_map)
+ goto fail;
+
+ memset(tag_index, 0, depth * sizeof(struct request *));
+ memset(tag_map, 0, nr_ulongs * sizeof(unsigned long));
+ tags->real_max_depth = depth;
+ tags->max_depth = depth;
+ tags->tag_index = tag_index;
+ tags->tag_map = tag_map;
+
+ return 0;
+ fail:
+ kfree(tag_index);
+ return -ENOMEM;
+ }
+
+ /**
+ * blk_queue_init_tags - initialize the queue tag info
+ * @q: the request queue for the device
+ * @depth: the maximum queue depth supported
+ * @tags: the tag to use
+ **/
+ int blk_queue_init_tags(request_queue_t *q, int depth,
+ struct blk_queue_tag *tags)
+ {
+ int rc;
+
+ BUG_ON(tags && q->queue_tags && tags != q->queue_tags);
+
+ if (!tags && !q->queue_tags) {
+ tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC);
+ if (!tags)
+ goto fail;
+
+ if (init_tag_map(q, tags, depth))
+ goto fail;
+
+ INIT_LIST_HEAD(&tags->busy_list);
+ tags->busy = 0;
+ atomic_set(&tags->refcnt, 1);
+ } else if (q->queue_tags) {
+ if ((rc = blk_queue_resize_tags(q, depth)))
+ return rc;
+ set_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
+ return 0;
+ } else
+ atomic_inc(&tags->refcnt);
+
+ /*
+ * assign it, all done
+ */
+ q->queue_tags = tags;
+ q->queue_flags |= (1 << QUEUE_FLAG_QUEUED);
+ return 0;
+ fail:
+ kfree(tags);
+ return -ENOMEM;
+ }
+
+ EXPORT_SYMBOL(blk_queue_init_tags);
+
+ /**
+ * blk_queue_resize_tags - change the queueing depth
+ * @q: the request queue for the device
+ * @new_depth: the new max command queueing depth
+ *
+ * Notes:
+ * Must be called with the queue lock held.
+ **/
+ int blk_queue_resize_tags(request_queue_t *q, int new_depth)
+ {
+ struct blk_queue_tag *bqt = q->queue_tags;
+ struct request **tag_index;
+ unsigned long *tag_map;
+ int max_depth, nr_ulongs;
+
+ if (!bqt)
+ return -ENXIO;
+
+ /*
+ * if we already have large enough real_max_depth. just
+ * adjust max_depth. *NOTE* as requests with tag value
+ * between new_depth and real_max_depth can be in-flight, tag
+ * map can not be shrunk blindly here.
+ */
+ if (new_depth <= bqt->real_max_depth) {
+ bqt->max_depth = new_depth;
+ return 0;
+ }
+
+ /*
+ * save the old state info, so we can copy it back
+ */
+ tag_index = bqt->tag_index;
+ tag_map = bqt->tag_map;
+ max_depth = bqt->real_max_depth;
+
+ if (init_tag_map(q, bqt, new_depth))
+ return -ENOMEM;
+
+ memcpy(bqt->tag_index, tag_index, max_depth * sizeof(struct request *));
+ nr_ulongs = ALIGN(max_depth, BITS_PER_LONG) / BITS_PER_LONG;
+ memcpy(bqt->tag_map, tag_map, nr_ulongs * sizeof(unsigned long));
+
+ kfree(tag_index);
+ kfree(tag_map);
+ return 0;
+ }
+
+ EXPORT_SYMBOL(blk_queue_resize_tags);
+
+ /**
+ * blk_queue_end_tag - end tag operations for a request
+ * @q: the request queue for the device
+ * @rq: the request that has completed
+ *
+ * Description:
+ * Typically called when end_that_request_first() returns 0, meaning
+ * all transfers have been done for a request. It's important to call
+ * this function before end_that_request_last(), as that will put the
+ * request back on the free list thus corrupting the internal tag list.
+ *
+ * Notes:
+ * queue lock must be held.
+ **/
+ void blk_queue_end_tag(request_queue_t *q, struct request *rq)
+ {
+ struct blk_queue_tag *bqt = q->queue_tags;
+ int tag = rq->tag;
+
+ BUG_ON(tag == -1);
+
+ if (unlikely(tag >= bqt->real_max_depth))
+ /*
+ * This can happen after tag depth has been reduced.
+ * FIXME: how about a warning or info message here?
+ */
+ return;
+
+ if (unlikely(!__test_and_clear_bit(tag, bqt->tag_map))) {
+ printk(KERN_ERR "%s: attempt to clear non-busy tag (%d)\n",
+ __FUNCTION__, tag);
+ return;
+ }
+
+ list_del_init(&rq->queuelist);
+ rq->flags &= ~REQ_QUEUED;
+ rq->tag = -1;
+
+ if (unlikely(bqt->tag_index[tag] == NULL))
+ printk(KERN_ERR "%s: tag %d is missing\n",
+ __FUNCTION__, tag);
+
+ bqt->tag_index[tag] = NULL;
+ bqt->busy--;
+ }
+
+ EXPORT_SYMBOL(blk_queue_end_tag);
+
+ /**
+ * blk_queue_start_tag - find a free tag and assign it
+ * @q: the request queue for the device
+ * @rq: the block request that needs tagging
+ *
+ * Description:
+ * This can either be used as a stand-alone helper, or possibly be
+ * assigned as the queue &prep_rq_fn (in which case &struct request
+ * automagically gets a tag assigned). Note that this function
+ * assumes that any type of request can be queued! if this is not
+ * true for your device, you must check the request type before
+ * calling this function. The request will also be removed from
+ * the request queue, so it's the drivers responsibility to readd
+ * it if it should need to be restarted for some reason.
+ *
+ * Notes:
+ * queue lock must be held.
+ **/
+ int blk_queue_start_tag(request_queue_t *q, struct request *rq)
+ {
+ struct blk_queue_tag *bqt = q->queue_tags;
+ int tag;
+
+ if (unlikely((rq->flags & REQ_QUEUED))) {
+ printk(KERN_ERR
+ "%s: request %p for device [%s] already tagged %d",
+ __FUNCTION__, rq,
+ rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->tag);
+ BUG();
+ }
+
+ tag = find_first_zero_bit(bqt->tag_map, bqt->max_depth);
+ if (tag >= bqt->max_depth)
+ return 1;
+
+ __set_bit(tag, bqt->tag_map);
+
+ rq->flags |= REQ_QUEUED;
+ rq->tag = tag;
+ bqt->tag_index[tag] = rq;
+ blkdev_dequeue_request(rq);
+ list_add(&rq->queuelist, &bqt->busy_list);
+ bqt->busy++;
+ return 0;
+ }
+
+ EXPORT_SYMBOL(blk_queue_start_tag);
+
+ /**
+ * blk_queue_invalidate_tags - invalidate all pending tags
+ * @q: the request queue for the device
+ *
+ * Description:
+ * Hardware conditions may dictate a need to stop all pending requests.
+ * In this case, we will safely clear the block side of the tag queue and
+ * readd all requests to the request queue in the right order.
+ *
+ * Notes:
+ * queue lock must be held.
+ **/
+ void blk_queue_invalidate_tags(request_queue_t *q)
+ {
+ struct blk_queue_tag *bqt = q->queue_tags;
+ struct list_head *tmp, *n;
+ struct request *rq;
+
+ list_for_each_safe(tmp, n, &bqt->busy_list) {
+ rq = list_entry_rq(tmp);
+
+ if (rq->tag == -1) {
+ printk(KERN_ERR
+ "%s: bad tag found on list\n", __FUNCTION__);
+ list_del_init(&rq->queuelist);
+ rq->flags &= ~REQ_QUEUED;
+ } else
+ blk_queue_end_tag(q, rq);
+
+ rq->flags &= ~REQ_STARTED;
+ __elv_add_request(q, rq, ELEVATOR_INSERT_BACK, 0);
+ }
+ }
+
+ EXPORT_SYMBOL(blk_queue_invalidate_tags);
+
+ static char *rq_flags[] = {
+ "REQ_RW",
+ "REQ_FAILFAST",
+ "REQ_SORTED",
+ "REQ_SOFTBARRIER",
+ "REQ_HARDBARRIER",
+ "REQ_CMD",
+ "REQ_NOMERGE",
+ "REQ_STARTED",
+ "REQ_DONTPREP",
+ "REQ_QUEUED",
+ "REQ_ELVPRIV",
+ "REQ_PC",
+ "REQ_BLOCK_PC",
+ "REQ_SENSE",
+ "REQ_FAILED",
+ "REQ_QUIET",
+ "REQ_SPECIAL",
+ "REQ_DRIVE_CMD",
+ "REQ_DRIVE_TASK",
+ "REQ_DRIVE_TASKFILE",
+ "REQ_PREEMPT",
+ "REQ_PM_SUSPEND",
+ "REQ_PM_RESUME",
+ "REQ_PM_SHUTDOWN",
+ };
+
+ void blk_dump_rq_flags(struct request *rq, char *msg)
+ {
+ int bit;
+
+ printk("%s: dev %s: flags = ", msg,
+ rq->rq_disk ? rq->rq_disk->disk_name : "?");
+ bit = 0;
+ do {
+ if (rq->flags & (1 << bit))
+ printk("%s ", rq_flags[bit]);
+ bit++;
+ } while (bit < __REQ_NR_BITS);
+
+ printk("\nsector %llu, nr/cnr %lu/%u\n", (unsigned long long)rq->sector,
+ rq->nr_sectors,
+ rq->current_nr_sectors);
+ printk("bio %p, biotail %p, buffer %p, data %p, len %u\n", rq->bio, rq->biotail, rq->buffer, rq->data, rq->data_len);
+
+ if (rq->flags & (REQ_BLOCK_PC | REQ_PC)) {
+ printk("cdb: ");
+ for (bit = 0; bit < sizeof(rq->cmd); bit++)
+ printk("%02x ", rq->cmd[bit]);
+ printk("\n");
+ }
+ }
+
+ EXPORT_SYMBOL(blk_dump_rq_flags);
+
+ void blk_recount_segments(request_queue_t *q, struct bio *bio)
+ {
+ struct bio_vec *bv, *bvprv = NULL;
+ int i, nr_phys_segs, nr_hw_segs, seg_size, hw_seg_size, cluster;
+ int high, highprv = 1;
+
+ if (unlikely(!bio->bi_io_vec))
+ return;
+
+ cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
+ hw_seg_size = seg_size = nr_phys_segs = nr_hw_segs = 0;
+ bio_for_each_segment(bv, bio, i) {
+ /*
+ * the trick here is making sure that a high page is never
+ * considered part of another segment, since that might
+ * change with the bounce page.
+ */
+ high = page_to_pfn(bv->bv_page) >= q->bounce_pfn;
+ if (high || highprv)
+ goto new_hw_segment;
+ if (cluster) {
+ if (seg_size + bv->bv_len > q->max_segment_size)
+ goto new_segment;
+ if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
+ goto new_segment;
+ if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv))
+ goto new_segment;
+ if (BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len))
+ goto new_hw_segment;
+
+ seg_size += bv->bv_len;
+ hw_seg_size += bv->bv_len;
+ bvprv = bv;
+ continue;
+ }
+ new_segment:
+ if (BIOVEC_VIRT_MERGEABLE(bvprv, bv) &&
+ !BIOVEC_VIRT_OVERSIZE(hw_seg_size + bv->bv_len)) {
+ hw_seg_size += bv->bv_len;
+ } else {
+ new_hw_segment:
+ if (hw_seg_size > bio->bi_hw_front_size)
+ bio->bi_hw_front_size = hw_seg_size;
+ hw_seg_size = BIOVEC_VIRT_START_SIZE(bv) + bv->bv_len;
+ nr_hw_segs++;
+ }
+
+ nr_phys_segs++;
+ bvprv = bv;
+ seg_size = bv->bv_len;
+ highprv = high;
+ }
+ if (hw_seg_size > bio->bi_hw_back_size)
+ bio->bi_hw_back_size = hw_seg_size;
+ if (nr_hw_segs == 1 && hw_seg_size > bio->bi_hw_front_size)
+ bio->bi_hw_front_size = hw_seg_size;
+ bio->bi_phys_segments = nr_phys_segs;
+ bio->bi_hw_segments = nr_hw_segs;
+ bio->bi_flags |= (1 << BIO_SEG_VALID);
+ }
+
+
+ static int blk_phys_contig_segment(request_queue_t *q, struct bio *bio,
+ struct bio *nxt)
+ {
+ if (!(q->queue_flags & (1 << QUEUE_FLAG_CLUSTER)))
+ return 0;
+
+ if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
+ return 0;
+ if (bio->bi_size + nxt->bi_size > q->max_segment_size)
+ return 0;
+
+ /*
+ * bio and nxt are contigous in memory, check if the queue allows
+ * these two to be merged into one
+ */
+ if (BIO_SEG_BOUNDARY(q, bio, nxt))
+ return 1;
+
+ return 0;
+ }
+
+ static int blk_hw_contig_segment(request_queue_t *q, struct bio *bio,
+ struct bio *nxt)
+ {
+ if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
+ blk_recount_segments(q, bio);
+ if (unlikely(!bio_flagged(nxt, BIO_SEG_VALID)))
+ blk_recount_segments(q, nxt);
+ if (!BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)) ||
+ BIOVEC_VIRT_OVERSIZE(bio->bi_hw_front_size + bio->bi_hw_back_size))
+ return 0;
+ if (bio->bi_size + nxt->bi_size > q->max_segment_size)
+ return 0;
+
+ return 1;
+ }
+
+ /*
+ * map a request to scatterlist, return number of sg entries setup. Caller
+ * must make sure sg can hold rq->nr_phys_segments entries
+ */
+ int blk_rq_map_sg(request_queue_t *q, struct request *rq, struct scatterlist *sg)
+ {
+ struct bio_vec *bvec, *bvprv;
+ struct bio *bio;
+ int nsegs, i, cluster;
+
+ nsegs = 0;
+ cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
+
+ /*
+ * for each bio in rq
+ */
+ bvprv = NULL;
+ rq_for_each_bio(bio, rq) {
+ /*
+ * for each segment in bio
+ */
+ bio_for_each_segment(bvec, bio, i) {
+ int nbytes = bvec->bv_len;
+
+ if (bvprv && cluster) {
+ if (sg[nsegs - 1].length + nbytes > q->max_segment_size)
+ goto new_segment;
+
+ if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
+ goto new_segment;
+ if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
+ goto new_segment;
+
+ sg[nsegs - 1].length += nbytes;
+ } else {
+ new_segment:
+ memset(&sg[nsegs],0,sizeof(struct scatterlist));
+ sg[nsegs].page = bvec->bv_page;
+ sg[nsegs].length = nbytes;
+ sg[nsegs].offset = bvec->bv_offset;
+
+ nsegs++;
+ }
+ bvprv = bvec;
+ } /* segments in bio */
+ } /* bios in rq */
+
+ return nsegs;
+ }
+
+ EXPORT_SYMBOL(blk_rq_map_sg);
+
+ /*
+ * the standard queue merge functions, can be overridden with device
+ * specific ones if so desired
+ */
+
+ static inline int ll_new_mergeable(request_queue_t *q,
+ struct request *req,
+ struct bio *bio)
+ {
+ int nr_phys_segs = bio_phys_segments(q, bio);
+
+ if (req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
+ req->flags |= REQ_NOMERGE;
+ if (req == q->last_merge)
+ q->last_merge = NULL;
+ return 0;
+ }
+
+ /*
+ * A hw segment is just getting larger, bump just the phys
+ * counter.
+ */
+ req->nr_phys_segments += nr_phys_segs;
+ return 1;
+ }
+
+ static inline int ll_new_hw_segment(request_queue_t *q,
+ struct request *req,
+ struct bio *bio)
+ {
+ int nr_hw_segs = bio_hw_segments(q, bio);
+ int nr_phys_segs = bio_phys_segments(q, bio);
+
+ if (req->nr_hw_segments + nr_hw_segs > q->max_hw_segments
+ || req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
+ req->flags |= REQ_NOMERGE;
+ if (req == q->last_merge)
+ q->last_merge = NULL;
+ return 0;
+ }
+
+ /*
+ * This will form the start of a new hw segment. Bump both
+ * counters.
+ */
+ req->nr_hw_segments += nr_hw_segs;
+ req->nr_phys_segments += nr_phys_segs;
+ return 1;
+ }
+
+ static int ll_back_merge_fn(request_queue_t *q, struct request *req,
+ struct bio *bio)
+ {
+ int len;
+
+ if (req->nr_sectors + bio_sectors(bio) > q->max_sectors) {
+ req->flags |= REQ_NOMERGE;
+ if (req == q->last_merge)
+ q->last_merge = NULL;
+ return 0;
+ }
+ if (unlikely(!bio_flagged(req->biotail, BIO_SEG_VALID)))
+ blk_recount_segments(q, req->biotail);
+ if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
+ blk_recount_segments(q, bio);
+ len = req->biotail->bi_hw_back_size + bio->bi_hw_front_size;
+ if (BIOVEC_VIRT_MERGEABLE(__BVEC_END(req->biotail), __BVEC_START(bio)) &&
+ !BIOVEC_VIRT_OVERSIZE(len)) {
+ int mergeable = ll_new_mergeable(q, req, bio);
+
+ if (mergeable) {
+ if (req->nr_hw_segments == 1)
+ req->bio->bi_hw_front_size = len;
+ if (bio->bi_hw_segments == 1)
+ bio->bi_hw_back_size = len;
+ }
+ return mergeable;
+ }
+
+ return ll_new_hw_segment(q, req, bio);
+ }
+
+ static int ll_front_merge_fn(request_queue_t *q, struct request *req,
+ struct bio *bio)
+ {
+ int len;
+
+ if (req->nr_sectors + bio_sectors(bio) > q->max_sectors) {
+ req->flags |= REQ_NOMERGE;
+ if (req == q->last_merge)
+ q->last_merge = NULL;
+ return 0;
+ }
+ len = bio->bi_hw_back_size + req->bio->bi_hw_front_size;
+ if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
+ blk_recount_segments(q, bio);
+ if (unlikely(!bio_flagged(req->bio, BIO_SEG_VALID)))
+ blk_recount_segments(q, req->bio);
+ if (BIOVEC_VIRT_MERGEABLE(__BVEC_END(bio), __BVEC_START(req->bio)) &&
+ !BIOVEC_VIRT_OVERSIZE(len)) {
+ int mergeable = ll_new_mergeable(q, req, bio);
+
+ if (mergeable) {
+ if (bio->bi_hw_segments == 1)
+ bio->bi_hw_front_size = len;
+ if (req->nr_hw_segments == 1)
+ req->biotail->bi_hw_back_size = len;
+ }
+ return mergeable;
+ }
+
+ return ll_new_hw_segment(q, req, bio);
+ }
+
+ static int ll_merge_requests_fn(request_queue_t *q, struct request *req,
+ struct request *next)
+ {
+ int total_phys_segments;
+ int total_hw_segments;
+
+ /*
+ * First check if the either of the requests are re-queued
+ * requests. Can't merge them if they are.
+ */
+ if (req->special || next->special)
+ return 0;
+
+ /*
+ * Will it become too large?
+ */
+ if ((req->nr_sectors + next->nr_sectors) > q->max_sectors)
+ return 0;
+
+ total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
+ if (blk_phys_contig_segment(q, req->biotail, next->bio))
+ total_phys_segments--;
+
+ if (total_phys_segments > q->max_phys_segments)
+ return 0;
+
+ total_hw_segments = req->nr_hw_segments + next->nr_hw_segments;
+ if (blk_hw_contig_segment(q, req->biotail, next->bio)) {
+ int len = req->biotail->bi_hw_back_size + next->bio->bi_hw_front_size;
+ /*
+ * propagate the combined length to the end of the requests
+ */
+ if (req->nr_hw_segments == 1)
+ req->bio->bi_hw_front_size = len;
+ if (next->nr_hw_segments == 1)
+ next->biotail->bi_hw_back_size = len;
+ total_hw_segments--;
+ }
+
+ if (total_hw_segments > q->max_hw_segments)
+ return 0;
+
+ /* Merge is OK... */
+ req->nr_phys_segments = total_phys_segments;
+ req->nr_hw_segments = total_hw_segments;
+ return 1;
+ }
+
+ /*
+ * "plug" the device if there are no outstanding requests: this will
+ * force the transfer to start only after we have put all the requests
+ * on the list.
+ *
+ * This is called with interrupts off and no requests on the queue and
+ * with the queue lock held.
+ */
+ void blk_plug_device(request_queue_t *q)
+ {
+ WARN_ON(!irqs_disabled());
+
+ /*
+ * don't plug a stopped queue, it must be paired with blk_start_queue()
+ * which will restart the queueing
+ */
+ if (test_bit(QUEUE_FLAG_STOPPED, &q->queue_flags))
+ return;
+
+ if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
+ mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
+ }
+
+ EXPORT_SYMBOL(blk_plug_device);
+
+ /*
+ * remove the queue from the plugged list, if present. called with
+ * queue lock held and interrupts disabled.
+ */
+ int blk_remove_plug(request_queue_t *q)
+ {
+ WARN_ON(!irqs_disabled());
+
+ if (!test_and_clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
+ return 0;
+
+ del_timer(&q->unplug_timer);
+ return 1;
+ }
+
+ EXPORT_SYMBOL(blk_remove_plug);
+
+ /*
+ * remove the plug and let it rip..
+ */
+ void __generic_unplug_device(request_queue_t *q)
+ {
+ if (unlikely(test_bit(QUEUE_FLAG_STOPPED, &q->queue_flags)))
+ return;
+
+ if (!blk_remove_plug(q))
+ return;
+
+ q->request_fn(q);
+ }
+ EXPORT_SYMBOL(__generic_unplug_device);
+
+ /**
+ * generic_unplug_device - fire a request queue
+ * @q: The &request_queue_t in question
+ *
+ * Description:
+ * Linux uses plugging to build bigger requests queues before letting
+ * the device have at them. If a queue is plugged, the I/O scheduler
+ * is still adding and merging requests on the queue. Once the queue
+ * gets unplugged, the request_fn defined for the queue is invoked and
+ * transfers started.
+ **/
+ void generic_unplug_device(request_queue_t *q)
+ {
+ spin_lock_irq(q->queue_lock);
+ __generic_unplug_device(q);
+ spin_unlock_irq(q->queue_lock);
+ }
+ EXPORT_SYMBOL(generic_unplug_device);
+
+ static void blk_backing_dev_unplug(struct backing_dev_info *bdi,
+ struct page *page)
+ {
+ request_queue_t *q = bdi->unplug_io_data;
+
+ /*
+ * devices don't necessarily have an ->unplug_fn defined
+ */
+ if (q->unplug_fn)
+ q->unplug_fn(q);
+ }
+
+ static void blk_unplug_work(void *data)
+ {
+ request_queue_t *q = data;
+
+ q->unplug_fn(q);
+ }
+
+ static void blk_unplug_timeout(unsigned long data)
+ {
+ request_queue_t *q = (request_queue_t *)data;
+
+ kblockd_schedule_work(&q->unplug_work);
+ }
+
+ /**
+ * blk_start_queue - restart a previously stopped queue
+ * @q: The &request_queue_t in question
+ *
+ * Description:
+ * blk_start_queue() will clear the stop flag on the queue, and call
+ * the request_fn for the queue if it was in a stopped state when
+ * entered. Also see blk_stop_queue(). Queue lock must be held.
+ **/
+ void blk_start_queue(request_queue_t *q)
+ {
+ clear_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
+
+ /*
+ * one level of recursion is ok and is much faster than kicking
+ * the unplug handling
+ */
+ if (!test_and_set_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
+ q->request_fn(q);
+ clear_bit(QUEUE_FLAG_REENTER, &q->queue_flags);
+ } else {
+ blk_plug_device(q);
+ kblockd_schedule_work(&q->unplug_work);
+ }
+ }
+
+ EXPORT_SYMBOL(blk_start_queue);
+
+ /**
+ * blk_stop_queue - stop a queue
+ * @q: The &request_queue_t in question
+ *
+ * Description:
+ * The Linux block layer assumes that a block driver will consume all
+ * entries on the request queue when the request_fn strategy is called.
+ * Often this will not happen, because of hardware limitations (queue
+ * depth settings). If a device driver gets a 'queue full' response,
+ * or if it simply chooses not to queue more I/O at one point, it can
+ * call this function to prevent the request_fn from being called until
+ * the driver has signalled it's ready to go again. This happens by calling
+ * blk_start_queue() to restart queue operations. Queue lock must be held.
+ **/
+ void blk_stop_queue(request_queue_t *q)
+ {
+ blk_remove_plug(q);
+ set_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
+ }
+ EXPORT_SYMBOL(blk_stop_queue);
+
+ /**
+ * blk_sync_queue - cancel any pending callbacks on a queue
+ * @q: the queue
+ *
+ * Description:
+ * The block layer may perform asynchronous callback activity
+ * on a queue, such as calling the unplug function after a timeout.
+ * A block device may call blk_sync_queue to ensure that any
+ * such activity is cancelled, thus allowing it to release resources
+ * the the callbacks might use. The caller must already have made sure
+ * that its ->make_request_fn will not re-add plugging prior to calling
+ * this function.
+ *
+ */
+ void blk_sync_queue(struct request_queue *q)
+ {
+ del_timer_sync(&q->unplug_timer);
+ kblockd_flush();
+ }
+ EXPORT_SYMBOL(blk_sync_queue);
+
+ /**
+ * blk_run_queue - run a single device queue
+ * @q: The queue to run
+ */
+ void blk_run_queue(struct request_queue *q)
+ {
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ blk_remove_plug(q);
+ if (!elv_queue_empty(q))
+ q->request_fn(q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ }
+ EXPORT_SYMBOL(blk_run_queue);
+
+ /**
+ * blk_cleanup_queue: - release a &request_queue_t when it is no longer needed
+ * @q: the request queue to be released
+ *
+ * Description:
+ * blk_cleanup_queue is the pair to blk_init_queue() or
+ * blk_queue_make_request(). It should be called when a request queue is
+ * being released; typically when a block device is being de-registered.
+ * Currently, its primary task it to free all the &struct request
+ * structures that were allocated to the queue and the queue itself.
+ *
+ * Caveat:
+ * Hopefully the low level driver will have finished any
+ * outstanding requests first...
+ **/
+ void blk_cleanup_queue(request_queue_t * q)
+ {
+ struct request_list *rl = &q->rq;
+
+ if (!atomic_dec_and_test(&q->refcnt))
+ return;
+
+ if (q->elevator)
+ elevator_exit(q->elevator);
+
+ blk_sync_queue(q);
+
+ if (rl->rq_pool)
+ mempool_destroy(rl->rq_pool);
+
+ if (q->queue_tags)
+ __blk_queue_free_tags(q);
+
+ blk_queue_ordered(q, QUEUE_ORDERED_NONE);
+
+ kmem_cache_free(requestq_cachep, q);
+ }
+
+ EXPORT_SYMBOL(blk_cleanup_queue);
+
+ static int blk_init_free_list(request_queue_t *q)
+ {
+ struct request_list *rl = &q->rq;
+
+ rl->count[READ] = rl->count[WRITE] = 0;
+ rl->starved[READ] = rl->starved[WRITE] = 0;
+ rl->elvpriv = 0;
+ init_waitqueue_head(&rl->wait[READ]);
+ init_waitqueue_head(&rl->wait[WRITE]);
+
+ rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
+ mempool_free_slab, request_cachep, q->node);
+
+ if (!rl->rq_pool)
+ return -ENOMEM;
+
+ return 0;
+ }
+
+ static int __make_request(request_queue_t *, struct bio *);
+
+ request_queue_t *blk_alloc_queue(gfp_t gfp_mask)
+ {
+ return blk_alloc_queue_node(gfp_mask, -1);
+ }
+ EXPORT_SYMBOL(blk_alloc_queue);
+
+ request_queue_t *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
+ {
+ request_queue_t *q;
+
+ q = kmem_cache_alloc_node(requestq_cachep, gfp_mask, node_id);
+ if (!q)
+ return NULL;
+
+ memset(q, 0, sizeof(*q));
+ init_timer(&q->unplug_timer);
+ atomic_set(&q->refcnt, 1);
+
+ q->backing_dev_info.unplug_io_fn = blk_backing_dev_unplug;
+ q->backing_dev_info.unplug_io_data = q;
+
+ return q;
+ }
+ EXPORT_SYMBOL(blk_alloc_queue_node);
+
+ /**
+ * blk_init_queue - prepare a request queue for use with a block device
+ * @rfn: The function to be called to process requests that have been
+ * placed on the queue.
+ * @lock: Request queue spin lock
+ *
+ * Description:
+ * If a block device wishes to use the standard request handling procedures,
+ * which sorts requests and coalesces adjacent requests, then it must
+ * call blk_init_queue(). The function @rfn will be called when there
+ * are requests on the queue that need to be processed. If the device
+ * supports plugging, then @rfn may not be called immediately when requests
+ * are available on the queue, but may be called at some time later instead.
+ * Plugged queues are generally unplugged when a buffer belonging to one
+ * of the requests on the queue is needed, or due to memory pressure.
+ *
+ * @rfn is not required, or even expected, to remove all requests off the
+ * queue, but only as many as it can handle at a time. If it does leave
+ * requests on the queue, it is responsible for arranging that the requests
+ * get dealt with eventually.
+ *
+ * The queue spin lock must be held while manipulating the requests on the
+ * request queue.
+ *
+ * Function returns a pointer to the initialized request queue, or NULL if
+ * it didn't succeed.
+ *
+ * Note:
+ * blk_init_queue() must be paired with a blk_cleanup_queue() call
+ * when the block device is deactivated (such as at module unload).
+ **/
+
+ request_queue_t *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
+ {
+ return blk_init_queue_node(rfn, lock, -1);
+ }
+ EXPORT_SYMBOL(blk_init_queue);
+
+ request_queue_t *
+ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
+ {
+ request_queue_t *q = blk_alloc_queue_node(GFP_KERNEL, node_id);
+
+ if (!q)
+ return NULL;
+
+ q->node = node_id;
+ if (blk_init_free_list(q))
+ goto out_init;
+
+ /*
+ * if caller didn't supply a lock, they get per-queue locking with
+ * our embedded lock
+ */
+ if (!lock) {
+ spin_lock_init(&q->__queue_lock);
+ lock = &q->__queue_lock;
+ }
+
+ q->request_fn = rfn;
+ q->back_merge_fn = ll_back_merge_fn;
+ q->front_merge_fn = ll_front_merge_fn;
+ q->merge_requests_fn = ll_merge_requests_fn;
+ q->prep_rq_fn = NULL;
+ q->unplug_fn = generic_unplug_device;
+ q->queue_flags = (1 << QUEUE_FLAG_CLUSTER);
+ q->queue_lock = lock;
+
+ blk_queue_segment_boundary(q, 0xffffffff);
+
+ blk_queue_make_request(q, __make_request);
+ blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
+
+ blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
+ blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
+
+ /*
+ * all done
+ */
+ if (!elevator_init(q, NULL)) {
+ blk_queue_congestion_threshold(q);
+ return q;
+ }
+
+ blk_cleanup_queue(q);
+ out_init:
+ kmem_cache_free(requestq_cachep, q);
+ return NULL;
+ }
+ EXPORT_SYMBOL(blk_init_queue_node);
+
+ int blk_get_queue(request_queue_t *q)
+ {
+ if (likely(!test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) {
+ atomic_inc(&q->refcnt);
+ return 0;
+ }
+
+ return 1;
+ }
+
+ EXPORT_SYMBOL(blk_get_queue);
+
+ static inline void blk_free_request(request_queue_t *q, struct request *rq)
+ {
+ if (rq->flags & REQ_ELVPRIV)
+ elv_put_request(q, rq);
+ mempool_free(rq, q->rq.rq_pool);
+ }
+
+ static inline struct request *
+ blk_alloc_request(request_queue_t *q, int rw, struct bio *bio,
+ int priv, gfp_t gfp_mask)
+ {
+ struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);
+
+ if (!rq)
+ return NULL;
+
+ /*
+ * first three bits are identical in rq->flags and bio->bi_rw,
+ * see bio.h and blkdev.h
+ */
+ rq->flags = rw;
+
+ if (priv) {
+ if (unlikely(elv_set_request(q, rq, bio, gfp_mask))) {
+ mempool_free(rq, q->rq.rq_pool);
+ return NULL;
+ }
+ rq->flags |= REQ_ELVPRIV;
+ }
+
+ return rq;
+ }
+
+ /*
+ * ioc_batching returns true if the ioc is a valid batching request and
+ * should be given priority access to a request.
+ */
+ static inline int ioc_batching(request_queue_t *q, struct io_context *ioc)
+ {
+ if (!ioc)
+ return 0;
+
+ /*
+ * Make sure the process is able to allocate at least 1 request
+ * even if the batch times out, otherwise we could theoretically
+ * lose wakeups.
+ */
+ return ioc->nr_batch_requests == q->nr_batching ||
+ (ioc->nr_batch_requests > 0
+ && time_before(jiffies, ioc->last_waited + BLK_BATCH_TIME));
+ }
+
+ /*
+ * ioc_set_batching sets ioc to be a new "batcher" if it is not one. This
+ * will cause the process to be a "batcher" on all queues in the system. This
+ * is the behaviour we want though - once it gets a wakeup it should be given
+ * a nice run.
+ */
+ static void ioc_set_batching(request_queue_t *q, struct io_context *ioc)
+ {
+ if (!ioc || ioc_batching(q, ioc))
+ return;
+
+ ioc->nr_batch_requests = q->nr_batching;
+ ioc->last_waited = jiffies;
+ }
+
+ static void __freed_request(request_queue_t *q, int rw)
+ {
+ struct request_list *rl = &q->rq;
+
+ if (rl->count[rw] < queue_congestion_off_threshold(q))
+ clear_queue_congested(q, rw);
+
+ if (rl->count[rw] + 1 <= q->nr_requests) {
+ if (waitqueue_active(&rl->wait[rw]))
+ wake_up(&rl->wait[rw]);
+
+ blk_clear_queue_full(q, rw);
+ }
+ }
+
+ /*
+ * A request has just been released. Account for it, update the full and
+ * congestion status, wake up any waiters. Called under q->queue_lock.
+ */
+ static void freed_request(request_queue_t *q, int rw, int priv)
+ {
+ struct request_list *rl = &q->rq;
+
+ rl->count[rw]--;
+ if (priv)
+ rl->elvpriv--;
+
+ __freed_request(q, rw);
+
+ if (unlikely(rl->starved[rw ^ 1]))
+ __freed_request(q, rw ^ 1);
+ }
+
+ #define blkdev_free_rq(list) list_entry((list)->next, struct request, queuelist)
+ /*
+ * Get a free request, queue_lock must be held.
+ * Returns NULL on failure, with queue_lock held.
+ * Returns !NULL on success, with queue_lock *not held*.
+ */
+ static struct request *get_request(request_queue_t *q, int rw, struct bio *bio,
+ gfp_t gfp_mask)
+ {
+ struct request *rq = NULL;
+ struct request_list *rl = &q->rq;
+ struct io_context *ioc = current_io_context(GFP_ATOMIC);
+ int priv;
+
+ if (rl->count[rw]+1 >= q->nr_requests) {
+ /*
+ * The queue will fill after this allocation, so set it as
+ * full, and mark this process as "batching". This process
+ * will be allowed to complete a batch of requests, others
+ * will be blocked.
+ */
+ if (!blk_queue_full(q, rw)) {
+ ioc_set_batching(q, ioc);
+ blk_set_queue_full(q, rw);
+ }
+ }
+
+ switch (elv_may_queue(q, rw, bio)) {
+ case ELV_MQUEUE_NO:
+ goto rq_starved;
+ case ELV_MQUEUE_MAY:
+ break;
+ case ELV_MQUEUE_MUST:
+ goto get_rq;
+ }
+
+ if (blk_queue_full(q, rw) && !ioc_batching(q, ioc)) {
+ /*
+ * The queue is full and the allocating process is not a
+ * "batcher", and not exempted by the IO scheduler
+ */
+ goto out;
+ }
+
+ get_rq:
+ /*
+ * Only allow batching queuers to allocate up to 50% over the defined
+ * limit of requests, otherwise we could have thousands of requests
+ * allocated with any setting of ->nr_requests
+ */
+ if (rl->count[rw] >= (3 * q->nr_requests / 2))
+ goto out;
+
+ rl->count[rw]++;
+ rl->starved[rw] = 0;
+ if (rl->count[rw] >= queue_congestion_on_threshold(q))
+ set_queue_congested(q, rw);
+
+ priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+ if (priv)
+ rl->elvpriv++;
+
+ spin_unlock_irq(q->queue_lock);
+
+ rq = blk_alloc_request(q, rw, bio, priv, gfp_mask);
+ if (!rq) {
+ /*
+ * Allocation failed presumably due to memory. Undo anything
+ * we might have messed up.
+ *
+ * Allocating task should really be put onto the front of the
+ * wait queue, but this is pretty rare.
+ */
+ spin_lock_irq(q->queue_lock);
+ freed_request(q, rw, priv);
+
+ /*
+ * in the very unlikely event that allocation failed and no
+ * requests for this direction was pending, mark us starved
+ * so that freeing of a request in the other direction will
+ * notice us. another possible fix would be to split the
+ * rq mempool into READ and WRITE
+ */
+ rq_starved:
+ if (unlikely(rl->count[rw] == 0))
+ rl->starved[rw] = 1;
+
+ goto out;
+ }
+
+ if (ioc_batching(q, ioc))
+ ioc->nr_batch_requests--;
+
+ rq_init(q, rq);
+ rq->rl = rl;
+ out:
+ return rq;
+ }
+
+ /*
+ * No available requests for this queue, unplug the device and wait for some
+ * requests to become available.
+ *
+ * Called with q->queue_lock held, and returns with it unlocked.
+ */
+ static struct request *get_request_wait(request_queue_t *q, int rw,
+ struct bio *bio)
+ {
+ struct request *rq;
+
+ rq = get_request(q, rw, bio, GFP_NOIO);
+ while (!rq) {
+ DEFINE_WAIT(wait);
+ struct request_list *rl = &q->rq;
+
+ prepare_to_wait_exclusive(&rl->wait[rw], &wait,
+ TASK_UNINTERRUPTIBLE);
+
+ rq = get_request(q, rw, bio, GFP_NOIO);
+
+ if (!rq) {
+ struct io_context *ioc;
+
+ __generic_unplug_device(q);
+ spin_unlock_irq(q->queue_lock);
+ io_schedule();
+
+ /*
+ * After sleeping, we become a "batching" process and
+ * will be able to allocate at least one request, and
+ * up to a big batch of them for a small period time.
+ * See ioc_batching, ioc_set_batching
+ */
+ ioc = current_io_context(GFP_NOIO);
+ ioc_set_batching(q, ioc);
+
+ spin_lock_irq(q->queue_lock);
+ }
+ finish_wait(&rl->wait[rw], &wait);
+ }
+
+ return rq;
+ }
+
+ struct request *blk_get_request(request_queue_t *q, int rw, gfp_t gfp_mask)
+ {
+ struct request *rq;
+
+ BUG_ON(rw != READ && rw != WRITE);
+
+ spin_lock_irq(q->queue_lock);
+ if (gfp_mask & __GFP_WAIT) {
+ rq = get_request_wait(q, rw, NULL);
+ } else {
+ rq = get_request(q, rw, NULL, gfp_mask);
+ if (!rq)
+ spin_unlock_irq(q->queue_lock);
+ }
+ /* q->queue_lock is unlocked at this point */
+
+ return rq;
+ }
+ EXPORT_SYMBOL(blk_get_request);
+
+ /**
+ * blk_requeue_request - put a request back on queue
+ * @q: request queue where request should be inserted
+ * @rq: request to be inserted
+ *
+ * Description:
+ * Drivers often keep queueing requests until the hardware cannot accept
+ * more, when that condition happens we need to put the request back
+ * on the queue. Must be called with queue lock held.
+ */
+ void blk_requeue_request(request_queue_t *q, struct request *rq)
+ {
+ if (blk_rq_tagged(rq))
+ blk_queue_end_tag(q, rq);
+
+ elv_requeue_request(q, rq);
+ }
+
+ EXPORT_SYMBOL(blk_requeue_request);
+
+ /**
+ * blk_insert_request - insert a special request in to a request queue
+ * @q: request queue where request should be inserted
+ * @rq: request to be inserted
+ * @at_head: insert request at head or tail of queue
+ * @data: private data
+ *
+ * Description:
+ * Many block devices need to execute commands asynchronously, so they don't
+ * block the whole kernel from preemption during request execution. This is
+ * accomplished normally by inserting aritficial requests tagged as
+ * REQ_SPECIAL in to the corresponding request queue, and letting them be
+ * scheduled for actual execution by the request queue.
+ *
+ * We have the option of inserting the head or the tail of the queue.
+ * Typically we use the tail for new ioctls and so forth. We use the head
+ * of the queue for things like a QUEUE_FULL message from a device, or a
+ * host that is unable to accept a particular command.
+ */
+ void blk_insert_request(request_queue_t *q, struct request *rq,
+ int at_head, void *data)
+ {
+ int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
+ unsigned long flags;
+
+ /*
+ * tell I/O scheduler that this isn't a regular read/write (ie it
+ * must not attempt merges on this) and that it acts as a soft
+ * barrier
+ */
+ rq->flags |= REQ_SPECIAL | REQ_SOFTBARRIER;
+
+ rq->special = data;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+
+ /*
+ * If command is tagged, release the tag
+ */
+ if (blk_rq_tagged(rq))
+ blk_queue_end_tag(q, rq);
+
+ drive_stat_acct(rq, rq->nr_sectors, 1);
+ __elv_add_request(q, rq, where, 0);
+
+ if (blk_queue_plugged(q))
+ __generic_unplug_device(q);
+ else
+ q->request_fn(q);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ }
+
+ EXPORT_SYMBOL(blk_insert_request);
+
+ /**
+ * blk_rq_map_user - map user data to a request, for REQ_BLOCK_PC usage
+ * @q: request queue where request should be inserted
+ * @rq: request structure to fill
+ * @ubuf: the user buffer
+ * @len: length of user data
+ *
+ * Description:
+ * Data will be mapped directly for zero copy io, if possible. Otherwise
+ * a kernel bounce buffer is used.
+ *
+ * A matching blk_rq_unmap_user() must be issued at the end of io, while
+ * still in process context.
+ *
+ * Note: The mapped bio may need to be bounced through blk_queue_bounce()
+ * before being submitted to the device, as pages mapped may be out of
+ * reach. It's the callers responsibility to make sure this happens. The
+ * original bio must be passed back in to blk_rq_unmap_user() for proper
+ * unmapping.
+ */
+ int blk_rq_map_user(request_queue_t *q, struct request *rq, void __user *ubuf,
+ unsigned int len)
+ {
+ unsigned long uaddr;
+ struct bio *bio;
+ int reading;
+
+ if (len > (q->max_sectors << 9))
+ return -EINVAL;
+ if (!len || !ubuf)
+ return -EINVAL;
+
+ reading = rq_data_dir(rq) == READ;
+
+ /*
+ * if alignment requirement is satisfied, map in user pages for
+ * direct dma. else, set up kernel bounce buffers
+ */
+ uaddr = (unsigned long) ubuf;
+ if (!(uaddr & queue_dma_alignment(q)) && !(len & queue_dma_alignment(q)))
+ bio = bio_map_user(q, NULL, uaddr, len, reading);
+ else
+ bio = bio_copy_user(q, uaddr, len, reading);
+
+ if (!IS_ERR(bio)) {
+ rq->bio = rq->biotail = bio;
+ blk_rq_bio_prep(q, rq, bio);
+
+ rq->buffer = rq->data = NULL;
+ rq->data_len = len;
+ return 0;
+ }
+
+ /*
+ * bio is the err-ptr
+ */
+ return PTR_ERR(bio);
+ }
+
+ EXPORT_SYMBOL(blk_rq_map_user);
+
+ /**
+ * blk_rq_map_user_iov - map user data to a request, for REQ_BLOCK_PC usage
+ * @q: request queue where request should be inserted
+ * @rq: request to map data to
+ * @iov: pointer to the iovec
+ * @iov_count: number of elements in the iovec
+ *
+ * Description:
+ * Data will be mapped directly for zero copy io, if possible. Otherwise
+ * a kernel bounce buffer is used.
+ *
+ * A matching blk_rq_unmap_user() must be issued at the end of io, while
+ * still in process context.
+ *
+ * Note: The mapped bio may need to be bounced through blk_queue_bounce()
+ * before being submitted to the device, as pages mapped may be out of
+ * reach. It's the callers responsibility to make sure this happens. The
+ * original bio must be passed back in to blk_rq_unmap_user() for proper
+ * unmapping.
+ */
+ int blk_rq_map_user_iov(request_queue_t *q, struct request *rq,
+ struct sg_iovec *iov, int iov_count)
+ {
+ struct bio *bio;
+
+ if (!iov || iov_count <= 0)
+ return -EINVAL;
+
+ /* we don't allow misaligned data like bio_map_user() does. If the
+ * user is using sg, they're expected to know the alignment constraints
+ * and respect them accordingly */
+ bio = bio_map_user_iov(q, NULL, iov, iov_count, rq_data_dir(rq)== READ);
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ rq->bio = rq->biotail = bio;
+ blk_rq_bio_prep(q, rq, bio);
+ rq->buffer = rq->data = NULL;
+ rq->data_len = bio->bi_size;
+ return 0;
+ }
+
+ EXPORT_SYMBOL(blk_rq_map_user_iov);
+
+ /**
+ * blk_rq_unmap_user - unmap a request with user data
+ * @bio: bio to be unmapped
+ * @ulen: length of user buffer
+ *
+ * Description:
+ * Unmap a bio previously mapped by blk_rq_map_user().
+ */
+ int blk_rq_unmap_user(struct bio *bio, unsigned int ulen)
+ {
+ int ret = 0;
+
+ if (bio) {
+ if (bio_flagged(bio, BIO_USER_MAPPED))
+ bio_unmap_user(bio);
+ else
+ ret = bio_uncopy_user(bio);
+ }
+
+ return 0;
+ }
+
+ EXPORT_SYMBOL(blk_rq_unmap_user);
+
+ /**
+ * blk_rq_map_kern - map kernel data to a request, for REQ_BLOCK_PC usage
+ * @q: request queue where request should be inserted
+ * @rq: request to fill
+ * @kbuf: the kernel buffer
+ * @len: length of user data
+ * @gfp_mask: memory allocation flags
+ */
+ int blk_rq_map_kern(request_queue_t *q, struct request *rq, void *kbuf,
+ unsigned int len, gfp_t gfp_mask)
+ {
+ struct bio *bio;
+
+ if (len > (q->max_sectors << 9))
+ return -EINVAL;
+ if (!len || !kbuf)
+ return -EINVAL;
+
+ bio = bio_map_kern(q, kbuf, len, gfp_mask);
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ if (rq_data_dir(rq) == WRITE)
+ bio->bi_rw |= (1 << BIO_RW);
+
+ rq->bio = rq->biotail = bio;
+ blk_rq_bio_prep(q, rq, bio);
+
+ rq->buffer = rq->data = NULL;
+ rq->data_len = len;
+ return 0;
+ }
+
+ EXPORT_SYMBOL(blk_rq_map_kern);
+
+ /**
+ * blk_execute_rq_nowait - insert a request into queue for execution
+ * @q: queue to insert the request in
+ * @bd_disk: matching gendisk
+ * @rq: request to insert
+ * @at_head: insert request at head or tail of queue
+ * @done: I/O completion handler
+ *
+ * Description:
+ * Insert a fully prepared request at the back of the io scheduler queue
+ * for execution. Don't wait for completion.
+ */
+ void blk_execute_rq_nowait(request_queue_t *q, struct gendisk *bd_disk,
+ struct request *rq, int at_head,
+ void (*done)(struct request *))
+ {
+ int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
+
+ rq->rq_disk = bd_disk;
+ rq->flags |= REQ_NOMERGE;
+ rq->end_io = done;
+ elv_add_request(q, rq, where, 1);
+ generic_unplug_device(q);
+ }
+
+ /**
+ * blk_execute_rq - insert a request into queue for execution
+ * @q: queue to insert the request in
+ * @bd_disk: matching gendisk
+ * @rq: request to insert
+ * @at_head: insert request at head or tail of queue
+ *
+ * Description:
+ * Insert a fully prepared request at the back of the io scheduler queue
+ * for execution and wait for completion.
+ */
+ int blk_execute_rq(request_queue_t *q, struct gendisk *bd_disk,
+ struct request *rq, int at_head)
+ {
+ DECLARE_COMPLETION(wait);
+ char sense[SCSI_SENSE_BUFFERSIZE];
+ int err = 0;
+
+ /*
+ * we need an extra reference to the request, so we can look at
+ * it after io completion
+ */
+ rq->ref_count++;
+
+ if (!rq->sense) {
+ memset(sense, 0, sizeof(sense));
+ rq->sense = sense;
+ rq->sense_len = 0;
+ }
+
+ rq->waiting = &wait;
+ blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
+ wait_for_completion(&wait);
+ rq->waiting = NULL;
+
+ if (rq->errors)
+ err = -EIO;
+
+ return err;
+ }
+
+ EXPORT_SYMBOL(blk_execute_rq);
+
+ /**
+ * blkdev_issue_flush - queue a flush
+ * @bdev: blockdev to issue flush for
+ * @error_sector: error sector
+ *
+ * Description:
+ * Issue a flush for the block device in question. Caller can supply
+ * room for storing the error offset in case of a flush error, if they
+ * wish to. Caller must run wait_for_completion() on its own.
+ */
+ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
+ {
+ request_queue_t *q;
+
+ if (bdev->bd_disk == NULL)
+ return -ENXIO;
+
+ q = bdev_get_queue(bdev);
+ if (!q)
+ return -ENXIO;
+ if (!q->issue_flush_fn)
+ return -EOPNOTSUPP;
+
+ return q->issue_flush_fn(q, bdev->bd_disk, error_sector);
+ }
+
+ EXPORT_SYMBOL(blkdev_issue_flush);
+
+ static void drive_stat_acct(struct request *rq, int nr_sectors, int new_io)
+ {
+ int rw = rq_data_dir(rq);
+
+ if (!blk_fs_request(rq) || !rq->rq_disk)
+ return;
+
+ if (!new_io) {
+ __disk_stat_inc(rq->rq_disk, merges[rw]);
+ } else {
+ disk_round_stats(rq->rq_disk);
+ rq->rq_disk->in_flight++;
+ }
+ }
+
+ /*
+ * add-request adds a request to the linked list.
+ * queue lock is held and interrupts disabled, as we muck with the
+ * request queue list.
+ */
+ static inline void add_request(request_queue_t * q, struct request * req)
+ {
+ drive_stat_acct(req, req->nr_sectors, 1);
+
+ if (q->activity_fn)
+ q->activity_fn(q->activity_data, rq_data_dir(req));
+
+ /*
+ * elevator indicated where it wants this request to be
+ * inserted at elevator_merge time
+ */
+ __elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
+ }
+
+ /*
+ * disk_round_stats() - Round off the performance stats on a struct
+ * disk_stats.
+ *
+ * The average IO queue length and utilisation statistics are maintained
+ * by observing the current state of the queue length and the amount of
+ * time it has been in this state for.
+ *
+ * Normally, that accounting is done on IO completion, but that can result
+ * in more than a second's worth of IO being accounted for within any one
+ * second, leading to >100% utilisation. To deal with that, we call this
+ * function to do a round-off before returning the results when reading
+ * /proc/diskstats. This accounts immediately for all queue usage up to
+ * the current jiffies and restarts the counters again.
+ */
+ void disk_round_stats(struct gendisk *disk)
+ {
+ unsigned long now = jiffies;
+
+ if (now == disk->stamp)
+ return;
+
+ if (disk->in_flight) {
+ __disk_stat_add(disk, time_in_queue,
+ disk->in_flight * (now - disk->stamp));
+ __disk_stat_add(disk, io_ticks, (now - disk->stamp));
+ }
+ disk->stamp = now;
+ }
+
+ /*
+ * queue lock must be held
+ */
+ static void __blk_put_request(request_queue_t *q, struct request *req)
+ {
+ struct request_list *rl = req->rl;
+
+ if (unlikely(!q))
+ return;
+ if (unlikely(--req->ref_count))
+ return;
+
+ elv_completed_request(q, req);
+
+ req->rq_status = RQ_INACTIVE;
+ req->rl = NULL;
+
+ /*
+ * Request may not have originated from ll_rw_blk. if not,
+ * it didn't come out of our reserved rq pools
+ */
+ if (rl) {
+ int rw = rq_data_dir(req);
+ int priv = req->flags & REQ_ELVPRIV;
+
+ BUG_ON(!list_empty(&req->queuelist));
+
+ blk_free_request(q, req);
+ freed_request(q, rw, priv);
+ }
+ }
+
+ void blk_put_request(struct request *req)
+ {
+ unsigned long flags;
+ request_queue_t *q = req->q;
+
+ /*
+ * Gee, IDE calls in w/ NULL q. Fix IDE and remove the
+ * following if (q) test.
+ */
+ if (q) {
+ spin_lock_irqsave(q->queue_lock, flags);
+ __blk_put_request(q, req);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ }
+ }
+
+ EXPORT_SYMBOL(blk_put_request);
+
+ /**
+ * blk_end_sync_rq - executes a completion event on a request
+ * @rq: request to complete
+ */
+ void blk_end_sync_rq(struct request *rq)
+ {
+ struct completion *waiting = rq->waiting;
+
+ rq->waiting = NULL;
+ __blk_put_request(rq->q, rq);
+
+ /*
+ * complete last, if this is a stack request the process (and thus
+ * the rq pointer) could be invalid right after this complete()
+ */
+ complete(waiting);
+ }
+ EXPORT_SYMBOL(blk_end_sync_rq);
+
+ /**
+ * blk_congestion_wait - wait for a queue to become uncongested
+ * @rw: READ or WRITE
+ * @timeout: timeout in jiffies
+ *
+ * Waits for up to @timeout jiffies for a queue (any queue) to exit congestion.
+ * If no queues are congested then just wait for the next request to be
+ * returned.
+ */
+ long blk_congestion_wait(int rw, long timeout)
+ {
+ long ret;
+ DEFINE_WAIT(wait);
+ wait_queue_head_t *wqh = &congestion_wqh[rw];
+
+ prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+ ret = io_schedule_timeout(timeout);
+ finish_wait(wqh, &wait);
+ return ret;
+ }
+
+ EXPORT_SYMBOL(blk_congestion_wait);
+
+ /*
+ * Has to be called with the request spinlock acquired
+ */
+ static int attempt_merge(request_queue_t *q, struct request *req,
+ struct request *next)
+ {
+ if (!rq_mergeable(req) || !rq_mergeable(next))
+ return 0;
+
+ /*
+ * not contigious
+ */
+ if (req->sector + req->nr_sectors != next->sector)
+ return 0;
+
+ if (rq_data_dir(req) != rq_data_dir(next)
+ || req->rq_disk != next->rq_disk
+ || next->waiting || next->special)
+ return 0;
+
+ /*
+ * If we are allowed to merge, then append bio list
+ * from next to rq and release next. merge_requests_fn
+ * will have updated segment counts, update sector
+ * counts here.
+ */
+ if (!q->merge_requests_fn(q, req, next))
+ return 0;
+
+ /*
+ * 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.
+ */
+ if (time_after(req->start_time, next->start_time))
+ req->start_time = next->start_time;
+
+ req->biotail->bi_next = next->bio;
+ req->biotail = next->biotail;
+
+ req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;
+
+ elv_merge_requests(q, req, next);
+
+ if (req->rq_disk) {
+ disk_round_stats(req->rq_disk);
+ req->rq_disk->in_flight--;
+ }
+
+ req->ioprio = ioprio_best(req->ioprio, next->ioprio);
+
+ __blk_put_request(q, next);
+ return 1;
+ }
+
+ static inline int attempt_back_merge(request_queue_t *q, struct request *rq)
+ {
+ struct request *next = elv_latter_request(q, rq);
+
+ if (next)
+ return attempt_merge(q, rq, next);
+
+ return 0;
+ }
+
+ static inline int attempt_front_merge(request_queue_t *q, struct request *rq)
+ {
+ struct request *prev = elv_former_request(q, rq);
+
+ if (prev)
+ return attempt_merge(q, prev, rq);
+
+ return 0;
+ }
+
+ /**
+ * blk_attempt_remerge - attempt to remerge active head with next request
+ * @q: The &request_queue_t belonging to the device
+ * @rq: The head request (usually)
+ *
+ * Description:
+ * For head-active devices, the queue can easily be unplugged so quickly
+ * that proper merging is not done on the front request. This may hurt
+ * performance greatly for some devices. The block layer cannot safely
+ * do merging on that first request for these queues, but the driver can
+ * call this function and make it happen any way. Only the driver knows
+ * when it is safe to do so.
+ **/
+ void blk_attempt_remerge(request_queue_t *q, struct request *rq)
+ {
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ attempt_back_merge(q, rq);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ }
+
+ EXPORT_SYMBOL(blk_attempt_remerge);
+
+ static int __make_request(request_queue_t *q, struct bio *bio)
+ {
+ struct request *req;
+ int el_ret, rw, nr_sectors, cur_nr_sectors, barrier, err, sync;
+ unsigned short prio;
+ sector_t sector;
+
+ sector = bio->bi_sector;
+ nr_sectors = bio_sectors(bio);
+ cur_nr_sectors = bio_cur_sectors(bio);
+ prio = bio_prio(bio);
+
+ rw = bio_data_dir(bio);
+ sync = bio_sync(bio);
+
+ /*
+ * low level driver can indicate that it wants pages above a
+ * certain limit bounced to low memory (ie for highmem, or even
+ * ISA dma in theory)
+ */
+ blk_queue_bounce(q, &bio);
+
+ spin_lock_prefetch(q->queue_lock);
+
+ barrier = bio_barrier(bio);
+ if (unlikely(barrier) && (q->ordered == QUEUE_ORDERED_NONE)) {
+ err = -EOPNOTSUPP;
+ goto end_io;
+ }
+
+ spin_lock_irq(q->queue_lock);
+
+ if (unlikely(barrier) || elv_queue_empty(q))
+ goto get_rq;
+
+ el_ret = elv_merge(q, &req, bio);
+ switch (el_ret) {
+ case ELEVATOR_BACK_MERGE:
+ BUG_ON(!rq_mergeable(req));
+
+ if (!q->back_merge_fn(q, req, bio))
+ break;
+
+ req->biotail->bi_next = bio;
+ req->biotail = bio;
+ req->nr_sectors = req->hard_nr_sectors += nr_sectors;
+ req->ioprio = ioprio_best(req->ioprio, prio);
+ drive_stat_acct(req, nr_sectors, 0);
+ if (!attempt_back_merge(q, req))
+ elv_merged_request(q, req);
+ goto out;
+
+ case ELEVATOR_FRONT_MERGE:
+ BUG_ON(!rq_mergeable(req));
+
+ if (!q->front_merge_fn(q, req, bio))
+ break;
+
+ bio->bi_next = req->bio;
+ req->bio = bio;
+
+ /*
+ * may not be valid. if the low level driver said
+ * it didn't need a bounce buffer then it better
+ * not touch req->buffer either...
+ */
+ req->buffer = bio_data(bio);
+ req->current_nr_sectors = cur_nr_sectors;
+ req->hard_cur_sectors = cur_nr_sectors;
+ req->sector = req->hard_sector = sector;
+ req->nr_sectors = req->hard_nr_sectors += nr_sectors;
+ req->ioprio = ioprio_best(req->ioprio, prio);
+ drive_stat_acct(req, nr_sectors, 0);
+ if (!attempt_front_merge(q, req))
+ elv_merged_request(q, req);
+ goto out;
+
+ /* ELV_NO_MERGE: elevator says don't/can't merge. */
+ default:
+ ;
+ }
+
+ get_rq:
+ /*
+ * Grab a free request. This is might sleep but can not fail.
+ * Returns with the queue unlocked.
+ */
+ req = get_request_wait(q, rw, bio);
+
+ /*
+ * After dropping the lock and possibly sleeping here, our request
+ * may now be mergeable after it had proven unmergeable (above).
+ * We don't worry about that case for efficiency. It won't happen
+ * often, and the elevators are able to handle it.
+ */
+
+ req->flags |= REQ_CMD;
+
+ /*
+ * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
+ */
+ if (bio_rw_ahead(bio) || bio_failfast(bio))
+ req->flags |= REQ_FAILFAST;
+
+ /*
+ * REQ_BARRIER implies no merging, but lets make it explicit
+ */
+ if (unlikely(barrier))
+ req->flags |= (REQ_HARDBARRIER | REQ_NOMERGE);
+
+ req->errors = 0;
+ req->hard_sector = req->sector = sector;
+ req->hard_nr_sectors = req->nr_sectors = nr_sectors;
+ req->current_nr_sectors = req->hard_cur_sectors = cur_nr_sectors;
+ req->nr_phys_segments = bio_phys_segments(q, bio);
+ req->nr_hw_segments = bio_hw_segments(q, bio);
+ req->buffer = bio_data(bio); /* see ->buffer comment above */
+ req->waiting = NULL;
+ req->bio = req->biotail = bio;
+ req->ioprio = prio;
+ req->rq_disk = bio->bi_bdev->bd_disk;
+ req->start_time = jiffies;
+
+ spin_lock_irq(q->queue_lock);
+ if (elv_queue_empty(q))
+ blk_plug_device(q);
+ add_request(q, req);
+ out:
+ if (sync)
+ __generic_unplug_device(q);
+
+ spin_unlock_irq(q->queue_lock);
+ return 0;
+
+ end_io:
+ bio_endio(bio, nr_sectors << 9, err);
+ return 0;
+ }
+
+ /*
+ * If bio->bi_dev is a partition, remap the location
+ */
+ static inline void blk_partition_remap(struct bio *bio)
+ {
+ struct block_device *bdev = bio->bi_bdev;
+
+ if (bdev != bdev->bd_contains) {
+ struct hd_struct *p = bdev->bd_part;
+ const int rw = bio_data_dir(bio);
+
+ p->sectors[rw] += bio_sectors(bio);
+ p->ios[rw]++;
+
+ bio->bi_sector += p->start_sect;
+ bio->bi_bdev = bdev->bd_contains;
+ }
+ }
+
+ static void handle_bad_sector(struct bio *bio)
+ {
+ char b[BDEVNAME_SIZE];
+
+ printk(KERN_INFO "attempt to access beyond end of device\n");
+ printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
+ bdevname(bio->bi_bdev, b),
+ bio->bi_rw,
+ (unsigned long long)bio->bi_sector + bio_sectors(bio),
+ (long long)(bio->bi_bdev->bd_inode->i_size >> 9));
+
+ set_bit(BIO_EOF, &bio->bi_flags);
+ }
+
+ /**
+ * generic_make_request: hand a buffer to its device driver for I/O
+ * @bio: The bio describing the location in memory and on the device.
+ *
+ * generic_make_request() is used to make I/O requests of block
+ * devices. It is passed a &struct bio, which describes the I/O that needs
+ * to be done.
+ *
+ * generic_make_request() does not return any status. The
+ * success/failure status of the request, along with notification of
+ * completion, is delivered asynchronously through the bio->bi_end_io
+ * function described (one day) else where.
+ *
+ * The caller of generic_make_request must make sure that bi_io_vec
+ * are set to describe the memory buffer, and that bi_dev and bi_sector are
+ * set to describe the device address, and the
+ * bi_end_io and optionally bi_private are set to describe how
+ * completion notification should be signaled.
+ *
+ * generic_make_request and the drivers it calls may use bi_next if this
+ * bio happens to be merged with someone else, and may change bi_dev and
+ * bi_sector for remaps as it sees fit. So the values of these fields
+ * should NOT be depended on after the call to generic_make_request.
+ */
+ void generic_make_request(struct bio *bio)
+ {
+ request_queue_t *q;
+ sector_t maxsector;
+ int ret, nr_sectors = bio_sectors(bio);
+
+ might_sleep();
+ /* Test device or partition size, when known. */
+ maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
+ if (maxsector) {
+ sector_t sector = bio->bi_sector;
+
+ if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
+ /*
+ * This may well happen - the kernel calls bread()
+ * without checking the size of the device, e.g., when
+ * mounting a device.
+ */
+ handle_bad_sector(bio);
+ goto end_io;
+ }
+ }
+
+ /*
+ * Resolve the mapping until finished. (drivers are
+ * still free to implement/resolve their own stacking
+ * by explicitly returning 0)
+ *
+ * NOTE: we don't repeat the blk_size check for each new device.
+ * Stacking drivers are expected to know what they are doing.
+ */
+ do {
+ char b[BDEVNAME_SIZE];
+
+ q = bdev_get_queue(bio->bi_bdev);
+ if (!q) {
+ printk(KERN_ERR
+ "generic_make_request: Trying to access "
+ "nonexistent block-device %s (%Lu)\n",
+ bdevname(bio->bi_bdev, b),
+ (long long) bio->bi_sector);
+ end_io:
+ bio_endio(bio, bio->bi_size, -EIO);
+ break;
+ }
+
+ if (unlikely(bio_sectors(bio) > q->max_hw_sectors)) {
+ printk("bio too big device %s (%u > %u)\n",
+ bdevname(bio->bi_bdev, b),
+ bio_sectors(bio),
+ q->max_hw_sectors);
+ goto end_io;
+ }
+
+ if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
+ goto end_io;
+
+ /*
+ * If this device has partitions, remap block n
+ * of partition p to block n+start(p) of the disk.
+ */
+ blk_partition_remap(bio);
+
+ ret = q->make_request_fn(q, bio);
+ } while (ret);
+ }
+
+ EXPORT_SYMBOL(generic_make_request);
+
+ /**
+ * submit_bio: submit a bio to the block device layer for I/O
+ * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
+ * @bio: The &struct bio which describes the I/O
+ *
+ * submit_bio() is very similar in purpose to generic_make_request(), and
+ * uses that function to do most of the work. Both are fairly rough
+ * interfaces, @bio must be presetup and ready for I/O.
+ *
+ */
+ void submit_bio(int rw, struct bio *bio)
+ {
+ int count = bio_sectors(bio);
+
+ BIO_BUG_ON(!bio->bi_size);
+ BIO_BUG_ON(!bio->bi_io_vec);
+ bio->bi_rw |= rw;
+ if (rw & WRITE)
+ mod_page_state(pgpgout, count);
+ else
+ mod_page_state(pgpgin, count);
+
+ if (unlikely(block_dump)) {
+ char b[BDEVNAME_SIZE];
+ printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
+ current->comm, current->pid,
+ (rw & WRITE) ? "WRITE" : "READ",
+ (unsigned long long)bio->bi_sector,
+ bdevname(bio->bi_bdev,b));
+ }
+
+ generic_make_request(bio);
+ }
+
+ EXPORT_SYMBOL(submit_bio);
+
+ static void blk_recalc_rq_segments(struct request *rq)
+ {
+ struct bio *bio, *prevbio = NULL;
+ int nr_phys_segs, nr_hw_segs;
+ unsigned int phys_size, hw_size;
+ request_queue_t *q = rq->q;
+
+ if (!rq->bio)
+ return;
+
+ phys_size = hw_size = nr_phys_segs = nr_hw_segs = 0;
+ rq_for_each_bio(bio, rq) {
+ /* Force bio hw/phys segs to be recalculated. */
+ bio->bi_flags &= ~(1 << BIO_SEG_VALID);
+
+ nr_phys_segs += bio_phys_segments(q, bio);
+ nr_hw_segs += bio_hw_segments(q, bio);
+ if (prevbio) {
+ int pseg = phys_size + prevbio->bi_size + bio->bi_size;
+ int hseg = hw_size + prevbio->bi_size + bio->bi_size;
+
+ if (blk_phys_contig_segment(q, prevbio, bio) &&
+ pseg <= q->max_segment_size) {
+ nr_phys_segs--;
+ phys_size += prevbio->bi_size + bio->bi_size;
+ } else
+ phys_size = 0;
+
+ if (blk_hw_contig_segment(q, prevbio, bio) &&
+ hseg <= q->max_segment_size) {
+ nr_hw_segs--;
+ hw_size += prevbio->bi_size + bio->bi_size;
+ } else
+ hw_size = 0;
+ }
+ prevbio = bio;
+ }
+
+ rq->nr_phys_segments = nr_phys_segs;
+ rq->nr_hw_segments = nr_hw_segs;
+ }
+
+ static void blk_recalc_rq_sectors(struct request *rq, int nsect)
+ {
+ if (blk_fs_request(rq)) {
+ rq->hard_sector += nsect;
+ rq->hard_nr_sectors -= nsect;
+
+ /*
+ * Move the I/O submission pointers ahead if required.
+ */
+ if ((rq->nr_sectors >= rq->hard_nr_sectors) &&
+ (rq->sector <= rq->hard_sector)) {
+ rq->sector = rq->hard_sector;
+ rq->nr_sectors = rq->hard_nr_sectors;
+ rq->hard_cur_sectors = bio_cur_sectors(rq->bio);
+ rq->current_nr_sectors = rq->hard_cur_sectors;
+ rq->buffer = bio_data(rq->bio);
+ }
+
+ /*
+ * if total number of sectors is less than the first segment
+ * size, something has gone terribly wrong
+ */
+ if (rq->nr_sectors < rq->current_nr_sectors) {
+ printk("blk: request botched\n");
+ rq->nr_sectors = rq->current_nr_sectors;
+ }
+ }
+ }
+
+ static int __end_that_request_first(struct request *req, int uptodate,
+ int nr_bytes)
+ {
+ int total_bytes, bio_nbytes, error, next_idx = 0;
+ struct bio *bio;
+
+ /*
+ * extend uptodate bool to allow < 0 value to be direct io error
+ */
+ error = 0;
+ if (end_io_error(uptodate))
+ error = !uptodate ? -EIO : uptodate;
+
+ /*
+ * for a REQ_BLOCK_PC request, we want to carry any eventual
+ * sense key with us all the way through
+ */
+ if (!blk_pc_request(req))
+ req->errors = 0;
+
+ if (!uptodate) {
+ if (blk_fs_request(req) && !(req->flags & REQ_QUIET))
+ printk("end_request: I/O error, dev %s, sector %llu\n",
+ req->rq_disk ? req->rq_disk->disk_name : "?",
+ (unsigned long long)req->sector);
+ }
+
+ if (blk_fs_request(req) && req->rq_disk) {
+ const int rw = rq_data_dir(req);
+
+ __disk_stat_add(req->rq_disk, sectors[rw], nr_bytes >> 9);
+ }
+
+ total_bytes = bio_nbytes = 0;
+ while ((bio = req->bio) != NULL) {
+ int nbytes;
+
+ if (nr_bytes >= bio->bi_size) {
+ req->bio = bio->bi_next;
+ nbytes = bio->bi_size;
+ bio_endio(bio, nbytes, error);
+ next_idx = 0;
+ bio_nbytes = 0;
+ } else {
+ int idx = bio->bi_idx + next_idx;
+
+ if (unlikely(bio->bi_idx >= bio->bi_vcnt)) {
+ blk_dump_rq_flags(req, "__end_that");
+ printk("%s: bio idx %d >= vcnt %d\n",
+ __FUNCTION__,
+ bio->bi_idx, bio->bi_vcnt);
+ break;
+ }
+
+ nbytes = bio_iovec_idx(bio, idx)->bv_len;
+ BIO_BUG_ON(nbytes > bio->bi_size);
+
+ /*
+ * not a complete bvec done
+ */
+ if (unlikely(nbytes > nr_bytes)) {
+ bio_nbytes += nr_bytes;
+ total_bytes += nr_bytes;
+ break;
+ }
+
+ /*
+ * advance to the next vector
+ */
+ next_idx++;
+ bio_nbytes += nbytes;
+ }
+
+ total_bytes += nbytes;
+ nr_bytes -= nbytes;
+
+ if ((bio = req->bio)) {
+ /*
+ * end more in this run, or just return 'not-done'
+ */
+ if (unlikely(nr_bytes <= 0))
+ break;
+ }
+ }
+
+ /*
+ * completely done
+ */
+ if (!req->bio)
+ return 0;
+
+ /*
+ * if the request wasn't completed, update state
+ */
+ if (bio_nbytes) {
+ bio_endio(bio, bio_nbytes, error);
+ bio->bi_idx += next_idx;
+ bio_iovec(bio)->bv_offset += nr_bytes;
+ bio_iovec(bio)->bv_len -= nr_bytes;
+ }
+
+ blk_recalc_rq_sectors(req, total_bytes >> 9);
+ blk_recalc_rq_segments(req);
+ return 1;
+ }
+
+ /**
+ * end_that_request_first - end I/O on a request
+ * @req: the request being processed
+ * @uptodate: 1 for success, 0 for I/O error, < 0 for specific error
+ * @nr_sectors: number of sectors to end I/O on
+ *
+ * Description:
+ * Ends I/O on a number of sectors attached to @req, and sets it up
+ * for the next range of segments (if any) in the cluster.
+ *
+ * Return:
+ * 0 - we are done with this request, call end_that_request_last()
+ * 1 - still buffers pending for this request
+ **/
+ int end_that_request_first(struct request *req, int uptodate, int nr_sectors)
+ {
+ return __end_that_request_first(req, uptodate, nr_sectors << 9);
+ }
+
+ EXPORT_SYMBOL(end_that_request_first);
+
+ /**
+ * end_that_request_chunk - end I/O on a request
+ * @req: the request being processed
+ * @uptodate: 1 for success, 0 for I/O error, < 0 for specific error
+ * @nr_bytes: number of bytes to complete
+ *
+ * Description:
+ * Ends I/O on a number of bytes attached to @req, and sets it up
+ * for the next range of segments (if any). Like end_that_request_first(),
+ * but deals with bytes instead of sectors.
+ *
+ * Return:
+ * 0 - we are done with this request, call end_that_request_last()
+ * 1 - still buffers pending for this request
+ **/
+ int end_that_request_chunk(struct request *req, int uptodate, int nr_bytes)
+ {
+ return __end_that_request_first(req, uptodate, nr_bytes);
+ }
+
+ EXPORT_SYMBOL(end_that_request_chunk);
+
+ /*
+ * queue lock must be held
+ */
+ void end_that_request_last(struct request *req)
+ {
+ struct gendisk *disk = req->rq_disk;
+
+ if (unlikely(laptop_mode) && blk_fs_request(req))
+ laptop_io_completion();
+
+ if (disk && blk_fs_request(req)) {
+ unsigned long duration = jiffies - req->start_time;
+ const int rw = rq_data_dir(req);
+
+ __disk_stat_inc(disk, ios[rw]);
+ __disk_stat_add(disk, ticks[rw], duration);
+ disk_round_stats(disk);
+ disk->in_flight--;
+ }
+ if (req->end_io)
+ req->end_io(req);
+ else
+ __blk_put_request(req->q, req);
+ }
+
+ EXPORT_SYMBOL(end_that_request_last);
+
+ void end_request(struct request *req, int uptodate)
+ {
+ if (!end_that_request_first(req, uptodate, req->hard_cur_sectors)) {
+ add_disk_randomness(req->rq_disk);
+ blkdev_dequeue_request(req);
+ end_that_request_last(req);
+ }
+ }
+
+ EXPORT_SYMBOL(end_request);
+
+ void blk_rq_bio_prep(request_queue_t *q, struct request *rq, struct bio *bio)
+ {
+ /* first three bits are identical in rq->flags and bio->bi_rw */
+ rq->flags |= (bio->bi_rw & 7);
+
+ rq->nr_phys_segments = bio_phys_segments(q, bio);
+ rq->nr_hw_segments = bio_hw_segments(q, bio);
+ rq->current_nr_sectors = bio_cur_sectors(bio);
+ rq->hard_cur_sectors = rq->current_nr_sectors;
+ rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio);
+ rq->buffer = bio_data(bio);
+
+ rq->bio = rq->biotail = bio;
+ }
+
+ EXPORT_SYMBOL(blk_rq_bio_prep);
+
+ int kblockd_schedule_work(struct work_struct *work)
+ {
+ return queue_work(kblockd_workqueue, work);
+ }
+
+ EXPORT_SYMBOL(kblockd_schedule_work);
+
+ void kblockd_flush(void)
+ {
+ flush_workqueue(kblockd_workqueue);
+ }
+ EXPORT_SYMBOL(kblockd_flush);
+
+ int __init blk_dev_init(void)
+ {
+ kblockd_workqueue = create_workqueue("kblockd");
+ if (!kblockd_workqueue)
+ panic("Failed to create kblockd\n");
+
+ request_cachep = kmem_cache_create("blkdev_requests",
+ sizeof(struct request), 0, SLAB_PANIC, NULL, NULL);
+
+ requestq_cachep = kmem_cache_create("blkdev_queue",
+ sizeof(request_queue_t), 0, SLAB_PANIC, NULL, NULL);
+
+ iocontext_cachep = kmem_cache_create("blkdev_ioc",
+ sizeof(struct io_context), 0, SLAB_PANIC, NULL, NULL);
+
+ blk_max_low_pfn = max_low_pfn;
+ blk_max_pfn = max_pfn;
+
+ return 0;
+ }
+
+ /*
+ * IO Context helper functions
+ */
+ void put_io_context(struct io_context *ioc)
+ {
+ if (ioc == NULL)
+ return;
+
+ BUG_ON(atomic_read(&ioc->refcount) == 0);
+
+ if (atomic_dec_and_test(&ioc->refcount)) {
+ if (ioc->aic && ioc->aic->dtor)
+ ioc->aic->dtor(ioc->aic);
+ if (ioc->cic && ioc->cic->dtor)
+ ioc->cic->dtor(ioc->cic);
+
+ kmem_cache_free(iocontext_cachep, ioc);
+ }
+ }
+ EXPORT_SYMBOL(put_io_context);
+
+ /* Called by the exitting task */
+ void exit_io_context(void)
+ {
+ unsigned long flags;
+ struct io_context *ioc;
+
+ local_irq_save(flags);
+ task_lock(current);
+ ioc = current->io_context;
+ current->io_context = NULL;
+ ioc->task = NULL;
+ task_unlock(current);
+ local_irq_restore(flags);
+
+ if (ioc->aic && ioc->aic->exit)
+ ioc->aic->exit(ioc->aic);
+ if (ioc->cic && ioc->cic->exit)
+ ioc->cic->exit(ioc->cic);
+
+ put_io_context(ioc);
+ }
+
+ /*
+ * If the current task has no IO context then create one and initialise it.
+ * Otherwise, return its existing IO context.
+ *
+ * This returned IO context doesn't have a specifically elevated refcount,
+ * but since the current task itself holds a reference, the context can be
+ * used in general code, so long as it stays within `current` context.
+ */
+ struct io_context *current_io_context(gfp_t gfp_flags)
+ {
+ struct task_struct *tsk = current;
+ struct io_context *ret;
+
+ ret = tsk->io_context;
+ if (likely(ret))
+ return ret;
+
+ ret = kmem_cache_alloc(iocontext_cachep, gfp_flags);
+ if (ret) {
+ atomic_set(&ret->refcount, 1);
+ ret->task = current;
+ ret->set_ioprio = NULL;
+ ret->last_waited = jiffies; /* doesn't matter... */
+ ret->nr_batch_requests = 0; /* because this is 0 */
+ ret->aic = NULL;
+ ret->cic = NULL;
+ tsk->io_context = ret;
+ }
+
+ return ret;
+ }
+ EXPORT_SYMBOL(current_io_context);
+
+ /*
+ * If the current task has no IO context then create one and initialise it.
+ * If it does have a context, take a ref on it.
+ *
+ * This is always called in the context of the task which submitted the I/O.
+ */
+ struct io_context *get_io_context(gfp_t gfp_flags)
+ {
+ struct io_context *ret;
+ ret = current_io_context(gfp_flags);
+ if (likely(ret))
+ atomic_inc(&ret->refcount);
+ return ret;
+ }
+ EXPORT_SYMBOL(get_io_context);
+
+ void copy_io_context(struct io_context **pdst, struct io_context **psrc)
+ {
+ struct io_context *src = *psrc;
+ struct io_context *dst = *pdst;
+
+ if (src) {
+ BUG_ON(atomic_read(&src->refcount) == 0);
+ atomic_inc(&src->refcount);
+ put_io_context(dst);
+ *pdst = src;
+ }
+ }
+ EXPORT_SYMBOL(copy_io_context);
+
+ void swap_io_context(struct io_context **ioc1, struct io_context **ioc2)
+ {
+ struct io_context *temp;
+ temp = *ioc1;
+ *ioc1 = *ioc2;
+ *ioc2 = temp;
+ }
+ EXPORT_SYMBOL(swap_io_context);
+
+ /*
+ * sysfs parts below
+ */
+ struct queue_sysfs_entry {
+ struct attribute attr;
+ ssize_t (*show)(struct request_queue *, char *);
+ ssize_t (*store)(struct request_queue *, const char *, size_t);
+ };
+
+ static ssize_t
+ queue_var_show(unsigned int var, char *page)
+ {
+ return sprintf(page, "%d\n", var);
+ }
+
+ static ssize_t
+ queue_var_store(unsigned long *var, const char *page, size_t count)
+ {
+ char *p = (char *) page;
+
+ *var = simple_strtoul(p, &p, 10);
+ return count;
+ }
+
+ static ssize_t queue_requests_show(struct request_queue *q, char *page)
+ {
+ return queue_var_show(q->nr_requests, (page));
+ }
+
+ static ssize_t
+ queue_requests_store(struct request_queue *q, const char *page, size_t count)
+ {
+ struct request_list *rl = &q->rq;
+
+ int ret = queue_var_store(&q->nr_requests, page, count);
+ if (q->nr_requests < BLKDEV_MIN_RQ)
+ q->nr_requests = BLKDEV_MIN_RQ;
+ blk_queue_congestion_threshold(q);
+
+ if (rl->count[READ] >= queue_congestion_on_threshold(q))
+ set_queue_congested(q, READ);
+ else if (rl->count[READ] < queue_congestion_off_threshold(q))
+ clear_queue_congested(q, READ);
+
+ if (rl->count[WRITE] >= queue_congestion_on_threshold(q))
+ set_queue_congested(q, WRITE);
+ else if (rl->count[WRITE] < queue_congestion_off_threshold(q))
+ clear_queue_congested(q, WRITE);
+
+ if (rl->count[READ] >= q->nr_requests) {
+ blk_set_queue_full(q, READ);
+ } else if (rl->count[READ]+1 <= q->nr_requests) {
+ blk_clear_queue_full(q, READ);
+ wake_up(&rl->wait[READ]);
+ }
+
+ if (rl->count[WRITE] >= q->nr_requests) {
+ blk_set_queue_full(q, WRITE);
+ } else if (rl->count[WRITE]+1 <= q->nr_requests) {
+ blk_clear_queue_full(q, WRITE);
+ wake_up(&rl->wait[WRITE]);
+ }
+ return ret;
+ }
+
+ static ssize_t queue_ra_show(struct request_queue *q, char *page)
+ {
+ int ra_kb = q->backing_dev_info.ra_pages << (PAGE_CACHE_SHIFT - 10);
+
+ return queue_var_show(ra_kb, (page));
+ }
+
+ static ssize_t
+ queue_ra_store(struct request_queue *q, const char *page, size_t count)
+ {
+ unsigned long ra_kb;
+ ssize_t ret = queue_var_store(&ra_kb, page, count);
+
+ spin_lock_irq(q->queue_lock);
+ if (ra_kb > (q->max_sectors >> 1))
+ ra_kb = (q->max_sectors >> 1);
+
+ q->backing_dev_info.ra_pages = ra_kb >> (PAGE_CACHE_SHIFT - 10);
+ spin_unlock_irq(q->queue_lock);
+
+ return ret;
+ }
+
+ static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
+ {
+ int max_sectors_kb = q->max_sectors >> 1;
+
+ return queue_var_show(max_sectors_kb, (page));
+ }
+
+ static ssize_t
+ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
+ {
+ unsigned long max_sectors_kb,
+ max_hw_sectors_kb = q->max_hw_sectors >> 1,
+ page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
+ ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
+ int ra_kb;
+
+ if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
+ return -EINVAL;
+ /*
+ * Take the queue lock to update the readahead and max_sectors
+ * values synchronously:
+ */
+ spin_lock_irq(q->queue_lock);
+ /*
+ * Trim readahead window as well, if necessary:
+ */
+ ra_kb = q->backing_dev_info.ra_pages << (PAGE_CACHE_SHIFT - 10);
+ if (ra_kb > max_sectors_kb)
+ q->backing_dev_info.ra_pages =
+ max_sectors_kb >> (PAGE_CACHE_SHIFT - 10);
+
+ q->max_sectors = max_sectors_kb << 1;
+ spin_unlock_irq(q->queue_lock);
+
+ return ret;
+ }
+
+ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
+ {
+ int max_hw_sectors_kb = q->max_hw_sectors >> 1;
+
+ return queue_var_show(max_hw_sectors_kb, (page));
+ }
+
+
+ static struct queue_sysfs_entry queue_requests_entry = {
+ .attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
+ .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 },
+ .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 },
+ .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 },
+ .show = queue_max_hw_sectors_show,
+ };
+
+ static struct queue_sysfs_entry queue_iosched_entry = {
+ .attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
+ .show = elv_iosched_show,
+ .store = elv_iosched_store,
+ };
+
+ static struct attribute *default_attrs[] = {
+ &queue_requests_entry.attr,
+ &queue_ra_entry.attr,
+ &queue_max_hw_sectors_entry.attr,
+ &queue_max_sectors_entry.attr,
+ &queue_iosched_entry.attr,
+ NULL,
+ };
+
+ #define to_queue(atr) container_of((atr), struct queue_sysfs_entry, attr)
+
+ static ssize_t
+ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
+ {
+ struct queue_sysfs_entry *entry = to_queue(attr);
+ struct request_queue *q;
+
+ q = container_of(kobj, struct request_queue, kobj);
+ if (!entry->show)
+ return -EIO;
+
+ return entry->show(q, page);
+ }
+
+ static ssize_t
+ queue_attr_store(struct kobject *kobj, struct attribute *attr,
+ const char *page, size_t length)
+ {
+ struct queue_sysfs_entry *entry = to_queue(attr);
+ struct request_queue *q;
+
+ q = container_of(kobj, struct request_queue, kobj);
+ if (!entry->store)
+ return -EIO;
+
+ return entry->store(q, page, length);
+ }
+
+ static struct sysfs_ops queue_sysfs_ops = {
+ .show = queue_attr_show,
+ .store = queue_attr_store,
+ };
+
+ static struct kobj_type queue_ktype = {
+ .sysfs_ops = &queue_sysfs_ops,
+ .default_attrs = default_attrs,
+ };
+
+ int blk_register_queue(struct gendisk *disk)
+ {
+ int ret;
+
+ request_queue_t *q = disk->queue;
+
+ if (!q || !q->request_fn)
+ return -ENXIO;
+
+ q->kobj.parent = kobject_get(&disk->kobj);
+ if (!q->kobj.parent)
+ return -EBUSY;
+
+ snprintf(q->kobj.name, KOBJ_NAME_LEN, "%s", "queue");
+ q->kobj.ktype = &queue_ktype;
+
+ ret = kobject_register(&q->kobj);
+ if (ret < 0)
+ return ret;
+
+ ret = elv_register_queue(q);
+ if (ret) {
+ kobject_unregister(&q->kobj);
+ return ret;
+ }
+
+ return 0;
+ }
+
+ void blk_unregister_queue(struct gendisk *disk)
+ {
+ request_queue_t *q = disk->queue;
+
+ if (q && q->request_fn) {
+ elv_unregister_queue(q);
+
+ kobject_unregister(&q->kobj);
+ kobject_put(&disk->kobj);
+ }
+ }
projects / powerpc.git / commitdiff