* blk_queue_ordered - does this queue support ordered writes
* @q: the request queue
* @ordered: one of QUEUE_ORDERED_*
+ * @prepare_flush_fn: rq setup helper for cache flush ordered writes
*
* Description:
* For journalled file systems, doing ordered writes on a commit
return -EINVAL;
}
+ q->ordered = ordered;
q->next_ordered = ordered;
q->prepare_flush_fn = prepare_flush_fn;
rq->end_io = end_io;
q->prepare_flush_fn(q, rq);
- __elv_add_request(q, rq, ELEVATOR_INSERT_FRONT, 0);
+ elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
}
static inline struct request *start_ordered(request_queue_t *q,
else
q->ordseq |= QUEUE_ORDSEQ_POSTFLUSH;
- __elv_add_request(q, rq, ELEVATOR_INSERT_FRONT, 0);
+ elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
if (q->ordered & QUEUE_ORDERED_PREFLUSH) {
queue_flush(q, QUEUE_ORDERED_PREFLUSH);
int blk_do_ordered(request_queue_t *q, struct request **rqp)
{
- struct request *rq = *rqp, *allowed_rq;
+ struct request *rq = *rqp;
int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
if (!q->ordseq) {
}
}
+ /*
+ * Ordered sequence in progress
+ */
+
+ /* Special requests are not subject to ordering rules. */
+ if (!blk_fs_request(rq) &&
+ rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
+ return 1;
+
if (q->ordered & QUEUE_ORDERED_TAG) {
+ /* Ordered by tag. Blocking the next barrier is enough. */
if (is_barrier && rq != &q->bar_rq)
*rqp = NULL;
- return 1;
- }
-
- switch (blk_ordered_cur_seq(q)) {
- case QUEUE_ORDSEQ_PREFLUSH:
- allowed_rq = &q->pre_flush_rq;
- break;
- case QUEUE_ORDSEQ_BAR:
- allowed_rq = &q->bar_rq;
- break;
- case QUEUE_ORDSEQ_POSTFLUSH:
- allowed_rq = &q->post_flush_rq;
- break;
- default:
- allowed_rq = NULL;
- break;
+ } else {
+ /* Ordered by draining. Wait for turn. */
+ WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
+ if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
+ *rqp = NULL;
}
- if (rq != allowed_rq &&
- (blk_fs_request(rq) || rq == &q->pre_flush_rq ||
- rq == &q->post_flush_rq))
- *rqp = NULL;
-
return 1;
}
* 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.
+ * buffers for doing I/O to pages residing above @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);
+ int dma = 0;
+
+ q->bounce_gfp = GFP_NOIO;
+#if BITS_PER_LONG == 64
+ /* Assume anything <= 4GB can be handled by IOMMU.
+ Actually some IOMMUs can handle everything, but I don't
+ know of a way to test this here. */
+ if (bounce_pfn < (0xffffffff>>PAGE_SHIFT))
+ dma = 1;
+ q->bounce_pfn = max_low_pfn;
+#else
+ if (bounce_pfn < blk_max_low_pfn)
+ dma = 1;
+ q->bounce_pfn = bounce_pfn;
+#endif
+ if (dma) {
init_emergency_isa_pool();
q->bounce_gfp = GFP_NOIO | GFP_DMA;
- } else
- q->bounce_gfp = GFP_NOIO;
-
- q->bounce_pfn = bounce_pfn;
+ q->bounce_pfn = bounce_pfn;
+ }
}
EXPORT_SYMBOL(blk_queue_bounce_limit);
* 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)
+void blk_queue_max_sectors(request_queue_t *q, unsigned int max_sectors)
{
if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
return NULL;
q->node = node_id;
- if (blk_init_free_list(q))
- goto out_init;
+ if (blk_init_free_list(q)) {
+ kmem_cache_free(requestq_cachep, q);
+ return NULL;
+ }
/*
* if caller didn't supply a lock, they get per-queue locking with
return q;
}
- blk_cleanup_queue(q);
-out_init:
- kmem_cache_free(requestq_cachep, q);
+ blk_put_queue(q);
return NULL;
}
EXPORT_SYMBOL(blk_init_queue_node);
disk->stamp = now;
}
+EXPORT_SYMBOL_GPL(disk_round_stats);
+
/*
* queue lock must be held
*/
/**
* blk_end_sync_rq - executes a completion event on a request
* @rq: request to complete
+ * @error: end io status of the request
*/
void blk_end_sync_rq(struct request *rq, int error)
{
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);
+ disk_stat_add(req->rq_disk, sectors[rw], nr_bytes >> 9);
}
total_bytes = bio_nbytes = 0;
iocontext_cachep = kmem_cache_create("blkdev_ioc",
sizeof(struct io_context), 0, SLAB_PANIC, NULL, NULL);
- for (i = 0; i < NR_CPUS; i++)
+ for_each_cpu(i)
INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
open_softirq(BLOCK_SOFTIRQ, blk_done_softirq, NULL);
queue_requests_store(struct request_queue *q, const char *page, size_t count)
{
struct request_list *rl = &q->rq;
+ unsigned long nr;
+ int ret = queue_var_store(&nr, page, count);
+ if (nr < BLKDEV_MIN_RQ)
+ nr = BLKDEV_MIN_RQ;
- int ret = queue_var_store(&q->nr_requests, page, count);
- if (q->nr_requests < BLKDEV_MIN_RQ)
- q->nr_requests = BLKDEV_MIN_RQ;
+ spin_lock_irq(q->queue_lock);
+ q->nr_requests = nr;
blk_queue_congestion_threshold(q);
if (rl->count[READ] >= queue_congestion_on_threshold(q))
blk_clear_queue_full(q, WRITE);
wake_up(&rl->wait[WRITE]);
}
+ spin_unlock_irq(q->queue_lock);
return ret;
}