UBUNTU: Ubuntu-2.6.38-12.51

[linux-flexiantxendom0-natty.git] / block / blk-core.c

diff --git a/block/blk-core.c b/block/blk-core.c
index 881fe44..518dd42 100644 (file)
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -33,7 +33,7 @@
 
 #include "blk.h"
 
-EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
 
@@ -70,6 +70,18 @@ static void drive_stat_acct(struct request *rq, int new_io)
                part_stat_inc(cpu, part, merges[rw]);
        } else {
                part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
+               if (!hd_struct_try_get(part)) {
+                       /*
+                        * The partition is already being removed,
+                        * the request will be accounted on the disk only
+                        *
+                        * We take a reference on disk->part0 although that
+                        * partition will never be deleted, so we can treat
+                        * it as any other partition.
+                        */
+                       part = &rq->rq_disk->part0;
+                       hd_struct_get(part);
+               }
                part_round_stats(cpu, part);
                part_inc_in_flight(part, rw);
                rq->part = part;
@@ -340,7 +352,7 @@ void blk_start_queue(struct request_queue *q)
        WARN_ON(!irqs_disabled());
 
        queue_flag_clear(QUEUE_FLAG_STOPPED, q);
-       __blk_run_queue(q);
+       __blk_run_queue(q, false);
 }
 EXPORT_SYMBOL(blk_start_queue);
 
@@ -391,13 +403,14 @@ EXPORT_SYMBOL(blk_sync_queue);
 /**
  * __blk_run_queue - run a single device queue
  * @q: The queue to run
+ * @force_kblockd: Don't run @q->request_fn directly.  Use kblockd.
  *
  * Description:
  *    See @blk_run_queue. This variant must be called with the queue lock
  *    held and interrupts disabled.
  *
  */
-void __blk_run_queue(struct request_queue *q)
+void __blk_run_queue(struct request_queue *q, bool force_kblockd)
 {
        blk_remove_plug(q);
 
@@ -411,7 +424,7 @@ void __blk_run_queue(struct request_queue *q)
         * Only recurse once to avoid overrunning the stack, let the unplug
         * handling reinvoke the handler shortly if we already got there.
         */
-       if (!queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
+       if (!force_kblockd && !queue_flag_test_and_set(QUEUE_FLAG_REENTER, q)) {
                q->request_fn(q);
                queue_flag_clear(QUEUE_FLAG_REENTER, q);
        } else {
@@ -434,7 +447,7 @@ void blk_run_queue(struct request_queue *q)
        unsigned long flags;
 
        spin_lock_irqsave(q->queue_lock, flags);
-       __blk_run_queue(q);
+       __blk_run_queue(q, false);
        spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_run_queue);
@@ -805,16 +818,11 @@ static struct request *get_request(struct request_queue *q, int rw_flags,
        rl->starved[is_sync] = 0;
 
        priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
-       if (priv) {
+       if (priv)
                rl->elvpriv++;
 
-               /*
-                * Don't do stats for non-priv requests
-                */
-               if (blk_queue_io_stat(q))
-                       rw_flags |= REQ_IO_STAT;
-       }
-
+       if (blk_queue_io_stat(q))
+               rw_flags |= REQ_IO_STAT;
        spin_unlock_irq(q->queue_lock);
 
        rq = blk_alloc_request(q, rw_flags, priv, gfp_mask);
@@ -1046,7 +1054,7 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 
        drive_stat_acct(rq, 1);
        __elv_add_request(q, rq, where, 0);
-       __blk_run_queue(q);
+       __blk_run_queue(q, false);
        spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_insert_request);
@@ -1202,13 +1210,6 @@ static int __make_request(struct request_queue *q, struct bio *bio)
        int where = ELEVATOR_INSERT_SORT;
        int rw_flags;
 
-       /* REQ_HARDBARRIER is no more */
-       if (WARN_ONCE(bio->bi_rw & REQ_HARDBARRIER,
-               "block: HARDBARRIER is deprecated, use FLUSH/FUA instead\n")) {
-               bio_endio(bio, -EOPNOTSUPP);
-               return 0;
-       }
-
        /*
         * low level driver can indicate that it wants pages above a
         * certain limit bounced to low memory (ie for highmem, or even
@@ -1344,9 +1345,9 @@ static inline void blk_partition_remap(struct bio *bio)
                bio->bi_sector += p->start_sect;
                bio->bi_bdev = bdev->bd_contains;
 
-               trace_block_remap(bdev_get_queue(bio->bi_bdev), bio,
-                                   bdev->bd_dev,
-                                   bio->bi_sector - p->start_sect);
+               trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio,
+                                     bdev->bd_dev,
+                                     bio->bi_sector - p->start_sect);
        }
 }
 
@@ -1359,7 +1360,7 @@ static void handle_bad_sector(struct bio *bio)
                        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));
+                       (long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
 
        set_bit(BIO_EOF, &bio->bi_flags);
 }
@@ -1412,7 +1413,7 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
                return 0;
 
        /* Test device or partition size, when known. */
-       maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
+       maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
        if (maxsector) {
                sector_t sector = bio->bi_sector;
 
@@ -1515,7 +1516,7 @@ static inline void __generic_make_request(struct bio *bio)
                        goto end_io;
 
                if (old_sector != -1)
-                       trace_block_remap(q, bio, old_dev, old_sector);
+                       trace_block_bio_remap(q, bio, old_dev, old_sector);
 
                old_sector = bio->bi_sector;
                old_dev = bio->bi_bdev->bd_dev;
@@ -1818,6 +1819,7 @@ static void blk_account_io_done(struct request *req)
                part_round_stats(cpu, part);
                part_dec_in_flight(part, rw);
 
+               hd_struct_put(part);
                part_stat_unlock();
        }
 }
@@ -2609,19 +2611,14 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
 }
 EXPORT_SYMBOL(kblockd_schedule_work);
 
-int kblockd_schedule_delayed_work(struct request_queue *q,
-                       struct delayed_work *dwork, unsigned long delay)
-{
-       return queue_delayed_work(kblockd_workqueue, dwork, delay);
-}
-EXPORT_SYMBOL(kblockd_schedule_delayed_work);
-
 int __init blk_dev_init(void)
 {
        BUILD_BUG_ON(__REQ_NR_BITS > 8 *
                        sizeof(((struct request *)0)->cmd_flags));
 
-       kblockd_workqueue = create_workqueue("kblockd");
+       /* used for unplugging and affects IO latency/throughput - HIGHPRI */
+       kblockd_workqueue = alloc_workqueue("kblockd",
+                                           WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
        if (!kblockd_workqueue)
                panic("Failed to create kblockd\n");