#include "blk.h"
EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
static int __make_request(struct request_queue *q, struct bio *bio);
part_stat_inc(cpu, part, merges[rw]);
else {
part_round_stats(cpu, part);
- part_inc_in_flight(part);
+ part_inc_in_flight(part, rw);
}
part_stat_unlock();
rq->tag = -1;
rq->ref_count = 1;
rq->start_time = jiffies;
+ set_start_time_ns(rq);
}
EXPORT_SYMBOL(blk_rq_init);
printk(KERN_INFO " bio %p, biotail %p, buffer %p, len %u\n",
rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));
- if (blk_pc_request(rq)) {
+ if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
printk(KERN_INFO " cdb: ");
for (bit = 0; bit < BLK_MAX_CDB; bit++)
printk("%02x ", rq->cmd[bit]);
*/
blk_sync_queue(q);
+ del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
mutex_lock(&q->sysfs_lock);
queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
mutex_unlock(&q->sysfs_lock);
{
struct request_list *rl = &q->rq;
+ if (unlikely(rl->rq_pool))
+ return 0;
+
rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
rl->elvpriv = 0;
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->backing_dev_info.state = 0;
q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+ q->backing_dev_info.name = "block";
err = bdi_init(&q->backing_dev_info);
if (err) {
return NULL;
}
+ setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
+ laptop_mode_timer_fn, (unsigned long) q);
init_timer(&q->unplug_timer);
setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
INIT_LIST_HEAD(&q->timeout_list);
struct request_queue *
blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
{
- struct request_queue *q = blk_alloc_queue_node(GFP_KERNEL, node_id);
+ struct request_queue *uninit_q, *q;
+
+ uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id);
+ if (!uninit_q)
+ return NULL;
+
+ q = blk_init_allocated_queue_node(uninit_q, rfn, lock, node_id);
+ if (!q)
+ blk_cleanup_queue(uninit_q);
+
+ return q;
+}
+EXPORT_SYMBOL(blk_init_queue_node);
+
+struct request_queue *
+blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
+ spinlock_t *lock)
+{
+ return blk_init_allocated_queue_node(q, rfn, lock, -1);
+}
+EXPORT_SYMBOL(blk_init_allocated_queue);
+struct request_queue *
+blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn,
+ spinlock_t *lock, int node_id)
+{
if (!q)
return NULL;
q->node = node_id;
- if (blk_init_free_list(q)) {
- kmem_cache_free(blk_requestq_cachep, q);
+ if (blk_init_free_list(q))
return NULL;
- }
-
- /*
- * if caller didn't supply a lock, they get per-queue locking with
- * our embedded lock
- */
- if (!lock)
- lock = &q->__queue_lock;
q->request_fn = rfn;
q->prep_rq_fn = NULL;
+ q->unprep_rq_fn = NULL;
q->unplug_fn = generic_unplug_device;
q->queue_flags = QUEUE_FLAG_DEFAULT;
q->queue_lock = lock;
return q;
}
- blk_put_queue(q);
return NULL;
}
-EXPORT_SYMBOL(blk_init_queue_node);
+EXPORT_SYMBOL(blk_init_allocated_queue_node);
int blk_get_queue(struct request_queue *q)
{
if (now == part->stamp)
return;
- if (part->in_flight) {
+ if (part_in_flight(part)) {
__part_stat_add(cpu, part, time_in_queue,
- part->in_flight * (now - part->stamp));
+ part_in_flight(part) * (now - part->stamp));
__part_stat_add(cpu, part, io_ticks, (now - part->stamp));
}
part->stamp = now;
}
EXPORT_SYMBOL(blk_put_request);
+/**
+ * blk_add_request_payload - add a payload to a request
+ * @rq: request to update
+ * @page: page backing the payload
+ * @len: length of the payload.
+ *
+ * This allows to later add a payload to an already submitted request by
+ * a block driver. The driver needs to take care of freeing the payload
+ * itself.
+ *
+ * Note that this is a quite horrible hack and nothing but handling of
+ * discard requests should ever use it.
+ */
+void blk_add_request_payload(struct request *rq, struct page *page,
+ unsigned int len)
+{
+ struct bio *bio = rq->bio;
+
+ bio->bi_io_vec->bv_page = page;
+ bio->bi_io_vec->bv_offset = 0;
+ bio->bi_io_vec->bv_len = len;
+
+ bio->bi_size = len;
+ bio->bi_vcnt = 1;
+ bio->bi_phys_segments = 1;
+
+ rq->__data_len = rq->resid_len = len;
+ rq->nr_phys_segments = 1;
+ rq->buffer = bio_data(bio);
+}
+EXPORT_SYMBOL_GPL(blk_add_request_payload);
+
void init_request_from_bio(struct request *req, struct bio *bio)
{
req->cpu = bio->bi_comp_cpu;
req->cmd_type = REQ_TYPE_FS;
- /*
- * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
- */
- if (bio_rw_ahead(bio))
- req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
- REQ_FAILFAST_DRIVER);
- if (bio_failfast_dev(bio))
- req->cmd_flags |= REQ_FAILFAST_DEV;
- if (bio_failfast_transport(bio))
- req->cmd_flags |= REQ_FAILFAST_TRANSPORT;
- if (bio_failfast_driver(bio))
- req->cmd_flags |= REQ_FAILFAST_DRIVER;
-
- if (unlikely(bio_discard(bio))) {
- req->cmd_flags |= REQ_DISCARD;
- if (bio_barrier(bio))
- req->cmd_flags |= REQ_SOFTBARRIER;
- req->q->prepare_discard_fn(req->q, req);
- } else if (unlikely(bio_barrier(bio)))
- req->cmd_flags |= REQ_HARDBARRIER;
-
- if (bio_sync(bio))
- req->cmd_flags |= REQ_RW_SYNC;
- if (bio_rw_meta(bio))
- req->cmd_flags |= REQ_RW_META;
- if (bio_noidle(bio))
- req->cmd_flags |= REQ_NOIDLE;
+ req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK;
+ if (bio->bi_rw & REQ_RAHEAD)
+ req->cmd_flags |= REQ_FAILFAST_MASK;
req->errors = 0;
req->__sector = bio->bi_sector;
int el_ret;
unsigned int bytes = bio->bi_size;
const unsigned short prio = bio_prio(bio);
- const int sync = bio_sync(bio);
- const int unplug = bio_unplug(bio);
+ const bool sync = (bio->bi_rw & REQ_SYNC);
+ const bool unplug = (bio->bi_rw & REQ_UNPLUG);
+ const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
int rw_flags;
- if (bio_barrier(bio) && bio_has_data(bio) &&
+ if ((bio->bi_rw & REQ_HARDBARRIER) &&
(q->next_ordered == QUEUE_ORDERED_NONE)) {
bio_endio(bio, -EOPNOTSUPP);
return 0;
spin_lock_irq(q->queue_lock);
- if (unlikely(bio_barrier(bio)) || elv_queue_empty(q))
+ if (unlikely((bio->bi_rw & REQ_HARDBARRIER)) || elv_queue_empty(q))
goto get_rq;
el_ret = elv_merge(q, &req, bio);
trace_block_bio_backmerge(q, bio);
+ if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
+ blk_rq_set_mixed_merge(req);
+
req->biotail->bi_next = bio;
req->biotail = bio;
req->__data_len += bytes;
if (!blk_rq_cpu_valid(req))
req->cpu = bio->bi_comp_cpu;
drive_stat_acct(req, 0);
+ elv_bio_merged(q, req, bio);
if (!attempt_back_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out;
trace_block_bio_frontmerge(q, bio);
+ if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) {
+ blk_rq_set_mixed_merge(req);
+ req->cmd_flags &= ~REQ_FAILFAST_MASK;
+ req->cmd_flags |= ff;
+ }
+
bio->bi_next = req->bio;
req->bio = bio;
if (!blk_rq_cpu_valid(req))
req->cpu = bio->bi_comp_cpu;
drive_stat_acct(req, 0);
+ elv_bio_merged(q, req, bio);
if (!attempt_front_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out;
*/
rw_flags = bio_data_dir(bio);
if (sync)
- rw_flags |= REQ_RW_SYNC;
+ rw_flags |= REQ_SYNC;
/*
* Grab a free request. This is might sleep but can not fail.
goto end_io;
}
- if (unlikely(nr_sectors > queue_max_hw_sectors(q))) {
+ if (unlikely(!(bio->bi_rw & REQ_DISCARD) &&
+ nr_sectors > queue_max_hw_sectors(q))) {
printk(KERN_ERR "bio too big device %s (%u > %u)\n",
bdevname(bio->bi_bdev, b),
bio_sectors(bio),
if (old_sector != -1)
trace_block_remap(q, bio, old_dev, old_sector);
- trace_block_bio_queue(q, bio);
-
old_sector = bio->bi_sector;
old_dev = bio->bi_bdev->bd_dev;
if (bio_check_eod(bio, nr_sectors))
goto end_io;
- if (bio_discard(bio) && !q->prepare_discard_fn) {
+ if ((bio->bi_rw & REQ_DISCARD) && !blk_queue_discard(q)) {
err = -EOPNOTSUPP;
goto end_io;
}
+ trace_block_bio_queue(q, bio);
+
ret = q->make_request_fn(q, bio);
} while (ret);
/*
* We only want one ->make_request_fn to be active at a time,
* else stack usage with stacked devices could be a problem.
- * So use current->bio_{list,tail} to keep a list of requests
+ * So use current->bio_list to keep a list of requests
* submited by a make_request_fn function.
- * current->bio_tail is also used as a flag to say if
+ * current->bio_list is also used as a flag to say if
* generic_make_request is currently active in this task or not.
* If it is NULL, then no make_request is active. If it is non-NULL,
* then a make_request is active, and new requests should be added
*/
void generic_make_request(struct bio *bio)
{
- if (current->bio_tail) {
+ struct bio_list bio_list_on_stack;
+
+ if (current->bio_list) {
/* make_request is active */
- *(current->bio_tail) = bio;
- bio->bi_next = NULL;
- current->bio_tail = &bio->bi_next;
+ bio_list_add(current->bio_list, bio);
return;
}
/* following loop may be a bit non-obvious, and so deserves some
* Before entering the loop, bio->bi_next is NULL (as all callers
* ensure that) so we have a list with a single bio.
* We pretend that we have just taken it off a longer list, so
- * we assign bio_list to the next (which is NULL) and bio_tail
- * to &bio_list, thus initialising the bio_list of new bios to be
+ * we assign bio_list to a pointer to the bio_list_on_stack,
+ * thus initialising the bio_list of new bios to be
* added. __generic_make_request may indeed add some more bios
* through a recursive call to generic_make_request. If it
* did, we find a non-NULL value in bio_list and re-enter the loop
* from the top. In this case we really did just take the bio
- * of the top of the list (no pretending) and so fixup bio_list and
- * bio_tail or bi_next, and call into __generic_make_request again.
+ * of the top of the list (no pretending) and so remove it from
+ * bio_list, and call into __generic_make_request again.
*
* The loop was structured like this to make only one call to
* __generic_make_request (which is important as it is large and
* inlined) and to keep the structure simple.
*/
BUG_ON(bio->bi_next);
+ bio_list_init(&bio_list_on_stack);
+ current->bio_list = &bio_list_on_stack;
do {
- current->bio_list = bio->bi_next;
- if (bio->bi_next == NULL)
- current->bio_tail = ¤t->bio_list;
- else
- bio->bi_next = NULL;
__generic_make_request(bio);
- bio = current->bio_list;
+ bio = bio_list_pop(current->bio_list);
} while (bio);
- current->bio_tail = NULL; /* deactivate */
+ current->bio_list = NULL; /* deactivate */
}
EXPORT_SYMBOL(generic_make_request);
* If it's a regular read/write or a barrier with data attached,
* go through the normal accounting stuff before submission.
*/
- if (bio_has_data(bio)) {
+ if (bio_has_data(bio) && !(rw & REQ_DISCARD)) {
if (rw & WRITE) {
count_vm_events(PGPGOUT, count);
} else {
* the insertion using this generic function.
*
* This function should also be useful for request stacking drivers
- * in some cases below, so export this fuction.
+ * in some cases below, so export this function.
* Request stacking drivers like request-based dm may change the queue
* limits while requests are in the queue (e.g. dm's table swapping).
* Such request stacking drivers should check those requests agaist
*/
int blk_rq_check_limits(struct request_queue *q, struct request *rq)
{
+ if (rq->cmd_flags & REQ_DISCARD)
+ return 0;
+
if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
printk(KERN_ERR "%s: over max size limit.\n", __func__);
* limitation.
*/
blk_recalc_rq_segments(rq);
- if (rq->nr_phys_segments > queue_max_phys_segments(q) ||
- rq->nr_phys_segments > queue_max_hw_segments(q)) {
+ if (rq->nr_phys_segments > queue_max_segments(q)) {
printk(KERN_ERR "%s: over max segments limit.\n", __func__);
return -EIO;
}
}
EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
+/**
+ * blk_rq_err_bytes - determine number of bytes till the next failure boundary
+ * @rq: request to examine
+ *
+ * Description:
+ * A request could be merge of IOs which require different failure
+ * handling. This function determines the number of bytes which
+ * can be failed from the beginning of the request without
+ * crossing into area which need to be retried further.
+ *
+ * Return:
+ * The number of bytes to fail.
+ *
+ * Context:
+ * queue_lock must be held.
+ */
+unsigned int blk_rq_err_bytes(const struct request *rq)
+{
+ unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
+ unsigned int bytes = 0;
+ struct bio *bio;
+
+ if (!(rq->cmd_flags & REQ_MIXED_MERGE))
+ return blk_rq_bytes(rq);
+
+ /*
+ * Currently the only 'mixing' which can happen is between
+ * different fastfail types. We can safely fail portions
+ * which have all the failfast bits that the first one has -
+ * the ones which are at least as eager to fail as the first
+ * one.
+ */
+ for (bio = rq->bio; bio; bio = bio->bi_next) {
+ if ((bio->bi_rw & ff) != ff)
+ break;
+ bytes += bio->bi_size;
+ }
+
+ /* this could lead to infinite loop */
+ BUG_ON(blk_rq_bytes(rq) && !bytes);
+ return bytes;
+}
+EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
+
static void blk_account_io_completion(struct request *req, unsigned int bytes)
{
if (blk_do_io_stat(req)) {
part_stat_inc(cpu, part, ios[rw]);
part_stat_add(cpu, part, ticks[rw], duration);
part_round_stats(cpu, part);
- part_dec_in_flight(part);
+ part_dec_in_flight(part, rw);
part_stat_unlock();
}
* sees this request (possibly after
* requeueing). Notify IO scheduler.
*/
- if (blk_sorted_rq(rq))
+ if (rq->cmd_flags & REQ_SORTED)
elv_activate_rq(q, rq);
/*
* and to it is freed is accounted as io that is in progress at
* the driver side.
*/
- if (blk_account_rq(rq))
+ if (blk_account_rq(rq)) {
q->in_flight[rq_is_sync(rq)]++;
+ set_io_start_time_ns(rq);
+ }
}
/**
* TODO: tj: This is too subtle. It would be better to let
* low level drivers do what they see fit.
*/
- if (blk_fs_request(req))
+ if (req->cmd_type == REQ_TYPE_FS)
req->errors = 0;
- if (error && (blk_fs_request(req) && !(req->cmd_flags & REQ_QUIET))) {
+ if (error && req->cmd_type == REQ_TYPE_FS &&
+ !(req->cmd_flags & REQ_QUIET)) {
printk(KERN_ERR "end_request: I/O error, dev %s, sector %llu\n",
req->rq_disk ? req->rq_disk->disk_name : "?",
(unsigned long long)blk_rq_pos(req));
req->buffer = bio_data(req->bio);
/* update sector only for requests with clear definition of sector */
- if (blk_fs_request(req) || blk_discard_rq(req))
+ if (req->cmd_type == REQ_TYPE_FS || (req->cmd_flags & REQ_DISCARD))
req->__sector += total_bytes >> 9;
+ /* mixed attributes always follow the first bio */
+ if (req->cmd_flags & REQ_MIXED_MERGE) {
+ req->cmd_flags &= ~REQ_FAILFAST_MASK;
+ req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
+ }
+
/*
* If total number of sectors is less than the first segment
* size, something has gone terribly wrong.
blk_update_request(rq->next_rq, error, bidi_bytes))
return true;
- add_disk_randomness(rq->rq_disk);
+ if (blk_queue_add_random(rq->q))
+ add_disk_randomness(rq->rq_disk);
return false;
}
+/**
+ * blk_unprep_request - unprepare a request
+ * @req: the request
+ *
+ * This function makes a request ready for complete resubmission (or
+ * completion). It happens only after all error handling is complete,
+ * so represents the appropriate moment to deallocate any resources
+ * that were allocated to the request in the prep_rq_fn. The queue
+ * lock is held when calling this.
+ */
+void blk_unprep_request(struct request *req)
+{
+ struct request_queue *q = req->q;
+
+ req->cmd_flags &= ~REQ_DONTPREP;
+ if (q->unprep_rq_fn)
+ q->unprep_rq_fn(q, req);
+}
+EXPORT_SYMBOL_GPL(blk_unprep_request);
+
/*
* queue lock must be held
*/
BUG_ON(blk_queued_rq(req));
- if (unlikely(laptop_mode) && blk_fs_request(req))
- laptop_io_completion();
+ if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS)
+ laptop_io_completion(&req->q->backing_dev_info);
blk_delete_timer(req);
+ if (req->cmd_flags & REQ_DONTPREP)
+ blk_unprep_request(req);
+
+
blk_account_io_done(req);
if (req->end_io)
{
return blk_end_bidi_request(rq, error, nr_bytes, 0);
}
-EXPORT_SYMBOL_GPL(blk_end_request);
+EXPORT_SYMBOL(blk_end_request);
/**
* blk_end_request_all - Helper function for drives to finish the request.
pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
BUG_ON(pending);
}
-EXPORT_SYMBOL_GPL(blk_end_request_all);
+EXPORT_SYMBOL(blk_end_request_all);
/**
* blk_end_request_cur - Helper function to finish the current request chunk.
{
return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
-EXPORT_SYMBOL_GPL(blk_end_request_cur);
+EXPORT_SYMBOL(blk_end_request_cur);
+
+/**
+ * blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ * Complete @rq till the next failure boundary.
+ *
+ * Return:
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
+ */
+bool blk_end_request_err(struct request *rq, int error)
+{
+ WARN_ON(error >= 0);
+ return blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(blk_end_request_err);
/**
* __blk_end_request - Helper function for drivers to complete the request.
{
return __blk_end_bidi_request(rq, error, nr_bytes, 0);
}
-EXPORT_SYMBOL_GPL(__blk_end_request);
+EXPORT_SYMBOL(__blk_end_request);
/**
* __blk_end_request_all - Helper function for drives to finish the request.
pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
BUG_ON(pending);
}
-EXPORT_SYMBOL_GPL(__blk_end_request_all);
+EXPORT_SYMBOL(__blk_end_request_all);
/**
* __blk_end_request_cur - Helper function to finish the current request chunk.
{
return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
-EXPORT_SYMBOL_GPL(__blk_end_request_cur);
+EXPORT_SYMBOL(__blk_end_request_cur);
+
+/**
+ * __blk_end_request_err - Finish a request till the next failure boundary.
+ * @rq: the request to finish till the next failure boundary for
+ * @error: must be negative errno
+ *
+ * Description:
+ * Complete @rq till the next failure boundary. Must be called
+ * with queue lock held.
+ *
+ * Return:
+ * %false - we are done with this request
+ * %true - still buffers pending for this request
+ */
+bool __blk_end_request_err(struct request *rq, int error)
+{
+ WARN_ON(error >= 0);
+ return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
+}
+EXPORT_SYMBOL_GPL(__blk_end_request_err);
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio)
{
- /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw, and
- we want BIO_RW_AHEAD (bit 1) to imply REQ_FAILFAST (bit 1). */
- rq->cmd_flags |= (bio->bi_rw & 3);
+ /* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
+ rq->cmd_flags |= bio->bi_rw & REQ_WRITE;
if (bio_has_data(bio)) {
rq->nr_phys_segments = bio_phys_segments(q, bio);
rq->rq_disk = bio->bi_bdev->bd_disk;
}
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
+/**
+ * rq_flush_dcache_pages - Helper function to flush all pages in a request
+ * @rq: the request to be flushed
+ *
+ * Description:
+ * Flush all pages in @rq.
+ */
+void rq_flush_dcache_pages(struct request *rq)
+{
+ struct req_iterator iter;
+ struct bio_vec *bvec;
+
+ rq_for_each_segment(bvec, rq, iter)
+ flush_dcache_page(bvec->bv_page);
+}
+EXPORT_SYMBOL_GPL(rq_flush_dcache_pages);
+#endif
+
/**
* blk_lld_busy - Check if underlying low-level drivers of a device are busy
* @q : the queue of the device being checked
{
dst->cpu = src->cpu;
dst->cmd_flags = (rq_data_dir(src) | REQ_NOMERGE);
+ if (src->cmd_flags & REQ_DISCARD)
+ dst->cmd_flags |= REQ_DISCARD;
dst->cmd_type = src->cmd_type;
dst->__sector = blk_rq_pos(src);
dst->__data_len = blk_rq_bytes(src);
return 0;
}
-