diff options
Diffstat (limited to 'block')
| -rw-r--r-- | block/blk-core.c | 261 | ||||
| -rw-r--r-- | block/blk-sysfs.c | 6 | ||||
| -rw-r--r-- | block/elevator.c | 2 |
3 files changed, 128 insertions, 141 deletions
diff --git a/block/blk-core.c b/block/blk-core.c index d34433ae7917..79e41a76d96a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -38,8 +38,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_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); - /* * For the allocated request tables */ @@ -541,7 +539,7 @@ blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn, /* * This also sets hw/phys segments, boundary and size */ - blk_queue_make_request(q, __make_request); + blk_queue_make_request(q, blk_queue_bio); q->sg_reserved_size = INT_MAX; @@ -1215,7 +1213,7 @@ void init_request_from_bio(struct request *req, struct bio *bio) blk_rq_bio_prep(req->q, req, bio); } -static int __make_request(struct request_queue *q, struct bio *bio) +void blk_queue_bio(struct request_queue *q, struct bio *bio) { const bool sync = !!(bio->bi_rw & REQ_SYNC); struct blk_plug *plug; @@ -1241,7 +1239,7 @@ static int __make_request(struct request_queue *q, struct bio *bio) * any locks. */ if (attempt_plug_merge(current, q, bio, &request_count)) - goto out; + return; spin_lock_irq(q->queue_lock); @@ -1316,9 +1314,8 @@ get_rq: out_unlock: spin_unlock_irq(q->queue_lock); } -out: - return 0; } +EXPORT_SYMBOL_GPL(blk_queue_bio); /* for device mapper only */ /* * If bio->bi_dev is a partition, remap the location @@ -1417,165 +1414,142 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors) return 0; } -/** - * 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. - */ -static inline void __generic_make_request(struct bio *bio) +static noinline_for_stack bool +generic_make_request_checks(struct bio *bio) { struct request_queue *q; - sector_t old_sector; - int ret, nr_sectors = bio_sectors(bio); - dev_t old_dev; + int nr_sectors = bio_sectors(bio); int err = -EIO; + char b[BDEVNAME_SIZE]; + struct hd_struct *part; might_sleep(); if (bio_check_eod(bio, nr_sectors)) 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. - */ - old_sector = -1; - old_dev = 0; - do { - char b[BDEVNAME_SIZE]; - struct hd_struct *part; - - q = bdev_get_queue(bio->bi_bdev); - if (unlikely(!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); - goto end_io; - } - - 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), - queue_max_hw_sectors(q)); - goto end_io; - } - - if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) - goto end_io; - - part = bio->bi_bdev->bd_part; - if (should_fail_request(part, bio->bi_size) || - should_fail_request(&part_to_disk(part)->part0, - bio->bi_size)) - goto end_io; + q = bdev_get_queue(bio->bi_bdev); + if (unlikely(!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); + 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); + 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), + queue_max_hw_sectors(q)); + goto end_io; + } - if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) - goto end_io; + if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) + goto end_io; - if (old_sector != -1) - trace_block_bio_remap(q, bio, old_dev, old_sector); + part = bio->bi_bdev->bd_part; + if (should_fail_request(part, bio->bi_size) || + should_fail_request(&part_to_disk(part)->part0, + bio->bi_size)) + goto end_io; - old_sector = bio->bi_sector; - old_dev = bio->bi_bdev->bd_dev; + /* + * If this device has partitions, remap block n + * of partition p to block n+start(p) of the disk. + */ + blk_partition_remap(bio); - if (bio_check_eod(bio, nr_sectors)) - goto end_io; + if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) + goto end_io; - /* - * Filter flush bio's early so that make_request based - * drivers without flush support don't have to worry - * about them. - */ - if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) { - bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA); - if (!nr_sectors) { - err = 0; - goto end_io; - } - } + if (bio_check_eod(bio, nr_sectors)) + goto end_io; - if ((bio->bi_rw & REQ_DISCARD) && - (!blk_queue_discard(q) || - ((bio->bi_rw & REQ_SECURE) && - !blk_queue_secdiscard(q)))) { - err = -EOPNOTSUPP; + /* + * Filter flush bio's early so that make_request based + * drivers without flush support don't have to worry + * about them. + */ + if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) { + bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA); + if (!nr_sectors) { + err = 0; goto end_io; } + } - if (blk_throtl_bio(q, &bio)) - goto end_io; - - /* - * If bio = NULL, bio has been throttled and will be submitted - * later. - */ - if (!bio) - break; + if ((bio->bi_rw & REQ_DISCARD) && + (!blk_queue_discard(q) || + ((bio->bi_rw & REQ_SECURE) && + !blk_queue_secdiscard(q)))) { + err = -EOPNOTSUPP; + goto end_io; + } - trace_block_bio_queue(q, bio); + if (blk_throtl_bio(q, &bio)) + goto end_io; - ret = q->make_request_fn(q, bio); - } while (ret); + /* if bio = NULL, bio has been throttled and will be submitted later. */ + if (!bio) + return false; - return; + trace_block_bio_queue(q, bio); + return true; end_io: bio_endio(bio, err); + return false; } -/* - * 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 to keep a list of requests - * submited by a make_request_fn function. - * 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 - * at the tail +/** + * 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 resubmit the bio to + * a lower device by calling into generic_make_request recursively, which + * means the bio should NOT be touched after the call to ->make_request_fn. */ void generic_make_request(struct bio *bio) { struct bio_list bio_list_on_stack; + if (!generic_make_request_checks(bio)) + return; + + /* + * 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 to keep a list of requests submited by a + * make_request_fn function. 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 at the tail + */ if (current->bio_list) { - /* make_request is active */ bio_list_add(current->bio_list, bio); return; } + /* following loop may be a bit non-obvious, and so deserves some * explanation. * Before entering the loop, bio->bi_next is NULL (as all callers @@ -1583,22 +1557,21 @@ void generic_make_request(struct bio *bio) * We pretend that we have just taken it off a longer list, so * 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 + * added. ->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 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. + * bio_list, and call into ->make_request() again. */ BUG_ON(bio->bi_next); bio_list_init(&bio_list_on_stack); current->bio_list = &bio_list_on_stack; do { - __generic_make_request(bio); + struct request_queue *q = bdev_get_queue(bio->bi_bdev); + + q->make_request_fn(q, bio); + bio = bio_list_pop(current->bio_list); } while (bio); current->bio_list = NULL; /* deactivate */ @@ -2628,6 +2601,20 @@ EXPORT_SYMBOL(kblockd_schedule_delayed_work); #define PLUG_MAGIC 0x91827364 +/** + * blk_start_plug - initialize blk_plug and track it inside the task_struct + * @plug: The &struct blk_plug that needs to be initialized + * + * Description: + * Tracking blk_plug inside the task_struct will help with auto-flushing the + * pending I/O should the task end up blocking between blk_start_plug() and + * blk_finish_plug(). This is important from a performance perspective, but + * also ensures that we don't deadlock. For instance, if the task is blocking + * for a memory allocation, memory reclaim could end up wanting to free a + * page belonging to that request that is currently residing in our private + * plug. By flushing the pending I/O when the process goes to sleep, we avoid + * this kind of deadlock. + */ void blk_start_plug(struct blk_plug *plug) { struct task_struct *tsk = current; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 60fda88c57f0..a8eff5f8b9c5 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -457,11 +457,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, } /** - * blk_cleanup_queue: - release a &struct request_queue when it is no longer needed - * @kobj: the kobj belonging of the request queue to be released + * blk_release_queue: - release a &struct request_queue when it is no longer needed + * @kobj: the kobj belonging to the request queue to be released * * Description: - * blk_cleanup_queue is the pair to blk_init_queue() or + * blk_release_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 diff --git a/block/elevator.c b/block/elevator.c index a3b64bc71d88..cb332cb7ac6b 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -182,7 +182,7 @@ static void elevator_attach(struct request_queue *q, struct elevator_queue *eq, eq->elevator_data = data; } -static char chosen_elevator[16]; +static char chosen_elevator[ELV_NAME_MAX]; static int __init elevator_setup(char *str) { |